diff options
54 files changed, 331 insertions, 377 deletions
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt index 62328d76b55b..b0e911e0e8f5 100644 --- a/Documentation/power/pci.txt +++ b/Documentation/power/pci.txt @@ -979,20 +979,45 @@ every time right after the runtime_resume() callback has returned (alternatively, the runtime_suspend() callback will have to check if the device should really be suspended and return -EAGAIN if that is not the case). -The runtime PM of PCI devices is disabled by default. It is also blocked by -pci_pm_init() that runs the pm_runtime_forbid() helper function. If a PCI -driver implements the runtime PM callbacks and intends to use the runtime PM -framework provided by the PM core and the PCI subsystem, it should enable this -feature by executing the pm_runtime_enable() helper function. However, the -driver should not call the pm_runtime_allow() helper function unblocking -the runtime PM of the device. Instead, it should allow user space or some -platform-specific code to do that (user space can do it via sysfs), although -once it has called pm_runtime_enable(), it must be prepared to handle the +The runtime PM of PCI devices is enabled by default by the PCI core. PCI +device drivers do not need to enable it and should not attempt to do so. +However, it is blocked by pci_pm_init() that runs the pm_runtime_forbid() +helper function. In addition to that, the runtime PM usage counter of +each PCI device is incremented by local_pci_probe() before executing the +probe callback provided by the device's driver. + +If a PCI driver implements the runtime PM callbacks and intends to use the +runtime PM framework provided by the PM core and the PCI subsystem, it needs +to decrement the device's runtime PM usage counter in its probe callback +function. If it doesn't do that, the counter will always be different from +zero for the device and it will never be runtime-suspended. The simplest +way to do that is by calling pm_runtime_put_noidle(), but if the driver +wants to schedule an autosuspend right away, for example, it may call +pm_runtime_put_autosuspend() instead for this purpose. Generally, it +just needs to call a function that decrements the devices usage counter +from its probe routine to make runtime PM work for the device. + +It is important to remember that the driver's runtime_suspend() callback +may be executed right after the usage counter has been decremented, because +user space may already have cuased the pm_runtime_allow() helper function +unblocking the runtime PM of the device to run via sysfs, so the driver must +be prepared to cope with that. + +The driver itself should not call pm_runtime_allow(), though. Instead, it +should let user space or some platform-specific code do that (user space can +do it via sysfs as stated above), but it must be prepared to handle the runtime PM of the device correctly as soon as pm_runtime_allow() is called -(which may happen at any time). [It also is possible that user space causes -pm_runtime_allow() to be called via sysfs before the driver is loaded, so in -fact the driver has to be prepared to handle the runtime PM of the device as -soon as it calls pm_runtime_enable().] +(which may happen at any time, even before the driver is loaded). + +When the driver's remove callback runs, it has to balance the decrementation +of the device's runtime PM usage counter at the probe time. For this reason, +if it has decremented the counter in its probe callback, it must run +pm_runtime_get_noresume() in its remove callback. [Since the core carries +out a runtime resume of the device and bumps up the device's usage counter +before running the driver's remove callback, the runtime PM of the device +is effectively disabled for the duration of the remove execution and all +runtime PM helper functions incrementing the device's usage counter are +then effectively equivalent to pm_runtime_get_noresume().] The runtime PM framework works by processing requests to suspend or resume devices, or to check if they are idle (in which cases it is reasonable to diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c index 2bc8abc57fa0..6c6247aaa7b9 100644 --- a/Documentation/ptp/testptp.c +++ b/Documentation/ptp/testptp.c @@ -18,6 +18,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ #define _GNU_SOURCE +#define __SANE_USERSPACE_TYPES__ /* For PPC64, to get LL64 types */ #include <errno.h> #include <fcntl.h> #include <inttypes.h> diff --git a/MAINTAINERS b/MAINTAINERS index 9f6685f6c5a9..797236befd27 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -5957,7 +5957,7 @@ F: virt/kvm/ KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V M: Joerg Roedel <joro@8bytes.org> L: kvm@vger.kernel.org -W: http://kvm.qumranet.com +W: http://www.linux-kvm.org/ S: Maintained F: arch/x86/include/asm/svm.h F: arch/x86/kvm/svm.c @@ -5965,7 +5965,7 @@ F: arch/x86/kvm/svm.c KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC M: Alexander Graf <agraf@suse.com> L: kvm-ppc@vger.kernel.org -W: http://kvm.qumranet.com +W: http://www.linux-kvm.org/ T: git git://github.com/agraf/linux-2.6.git S: Supported F: arch/powerpc/include/asm/kvm* diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h index 655e07a48f6c..67f08230103a 100644 --- a/arch/x86/include/asm/pvclock-abi.h +++ b/arch/x86/include/asm/pvclock-abi.h @@ -41,6 +41,7 @@ struct pvclock_wall_clock { #define PVCLOCK_TSC_STABLE_BIT (1 << 0) #define PVCLOCK_GUEST_STOPPED (1 << 1) +/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */ #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2) #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PVCLOCK_ABI_H */ diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 94b7d15db3fc..2f9ed1ff0632 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -514,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu) struct vcpu_svm *svm = to_svm(vcpu); if (svm->vmcb->control.next_rip != 0) { - WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS)); + WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS)); svm->next_rip = svm->vmcb->control.next_rip; } @@ -866,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm) set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0); } -#define MTRR_TYPE_UC_MINUS 7 -#define MTRR2PROTVAL_INVALID 0xff - -static u8 mtrr2protval[8]; - -static u8 fallback_mtrr_type(int mtrr) -{ - /* - * WT and WP aren't always available in the host PAT. Treat - * them as UC and UC- respectively. Everything else should be - * there. - */ - switch (mtrr) - { - case MTRR_TYPE_WRTHROUGH: - return MTRR_TYPE_UNCACHABLE; - case MTRR_TYPE_WRPROT: - return MTRR_TYPE_UC_MINUS; - default: - BUG(); - } -} - -static void build_mtrr2protval(void) -{ - int i; - u64 pat; - - for (i = 0; i < 8; i++) - mtrr2protval[i] = MTRR2PROTVAL_INVALID; - - /* Ignore the invalid MTRR types. */ - mtrr2protval[2] = 0; - mtrr2protval[3] = 0; - - /* - * Use host PAT value to figure out the mapping from guest MTRR - * values to nested page table PAT/PCD/PWT values. We do not - * want to change the host PAT value every time we enter the - * guest. - */ - rdmsrl(MSR_IA32_CR_PAT, pat); - for (i = 0; i < 8; i++) { - u8 mtrr = pat >> (8 * i); - - if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID) - mtrr2protval[mtrr] = __cm_idx2pte(i); - } - - for (i = 0; i < 8; i++) { - if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) { - u8 fallback = fallback_mtrr_type(i); - mtrr2protval[i] = mtrr2protval[fallback]; - BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID); - } - } -} - static __init int svm_hardware_setup(void) { int cpu; @@ -990,7 +932,6 @@ static __init int svm_hardware_setup(void) } else kvm_disable_tdp(); - build_mtrr2protval(); return 0; err: @@ -1145,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc) return target_tsc - tsc; } -static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat) -{ - struct kvm_vcpu *vcpu = &svm->vcpu; - - /* Unlike Intel, AMD takes the guest's CR0.CD into account. - * - * AMD does not have IPAT. To emulate it for the case of guests - * with no assigned devices, just set everything to WB. If guests - * have assigned devices, however, we cannot force WB for RAM - * pages only, so use the guest PAT directly. - */ - if (!kvm_arch_has_assigned_device(vcpu->kvm)) - *g_pat = 0x0606060606060606; - else - *g_pat = vcpu->arch.pat; -} - -static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) -{ - u8 mtrr; - - /* - * 1. MMIO: trust guest MTRR, so same as item 3. - * 2. No passthrough: always map as WB, and force guest PAT to WB as well - * 3. Passthrough: can't guarantee the result, try to trust guest. - */ - if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm)) - return 0; - - if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) && - kvm_read_cr0(vcpu) & X86_CR0_CD) - return _PAGE_NOCACHE; - - mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn); - return mtrr2protval[mtrr]; -} - static void init_vmcb(struct vcpu_svm *svm, bool init_event) { struct vmcb_control_area *control = &svm->vmcb->control; @@ -1278,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event) clr_cr_intercept(svm, INTERCEPT_CR3_READ); clr_cr_intercept(svm, INTERCEPT_CR3_WRITE); save->g_pat = svm->vcpu.arch.pat; - svm_set_guest_pat(svm, &save->g_pat); save->cr3 = 0; save->cr4 = 0; } @@ -1673,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0) if (!vcpu->fpu_active) cr0 |= X86_CR0_TS; - - /* These are emulated via page tables. */ - cr0 &= ~(X86_CR0_CD | X86_CR0_NW); - + /* + * re-enable caching here because the QEMU bios + * does not do it - this results in some delay at + * reboot + */ + if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED)) + cr0 &= ~(X86_CR0_CD | X86_CR0_NW); svm->vmcb->save.cr0 = cr0; mark_dirty(svm->vmcb, VMCB_CR); update_cr0_intercept(svm); @@ -3351,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_VM_IGNNE: vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data); break; - case MSR_IA32_CR_PAT: - if (npt_enabled) { - if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data)) - return 1; - vcpu->arch.pat = data; - svm_set_guest_pat(svm, &svm->vmcb->save.g_pat); - mark_dirty(svm->vmcb, VMCB_NPT); - break; - } - /* fall through */ default: return kvm_set_msr_common(vcpu, msr); } @@ -4195,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void) return true; } +static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) +{ + return 0; +} + static void svm_cpuid_update(struct kvm_vcpu *vcpu) { } diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 64076740251e..06ef4908ba61 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -8617,17 +8617,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio) u64 ipat = 0; /* For VT-d and EPT combination - * 1. MMIO: guest may want to apply WC, trust it. + * 1. MMIO: always map as UC * 2. EPT with VT-d: * a. VT-d without snooping control feature: can't guarantee the - * result, try to trust guest. So the same as item 1. + * result, try to trust guest. * b. VT-d with snooping control feature: snooping control feature of * VT-d engine can guarantee the cache correctness. Just set it * to WB to keep consistent with host. So the same as item 3. * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep * consistent with host MTRR */ - if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) { + if (is_mmio) { + cache = MTRR_TYPE_UNCACHABLE; + goto exit; + } + + if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) { ipat = VMX_EPT_IPAT_BIT; cache = MTRR_TYPE_WRBACK; goto exit; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 991466bf8dee..92511d4b7236 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1708,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) vcpu->pvclock_set_guest_stopped_request = false; } - pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO; - /* If the host uses TSC clocksource, then it is stable */ if (use_master_clock) pvclock_flags |= PVCLOCK_TSC_STABLE_BIT; @@ -2007,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info) &vcpu->requests); ka->boot_vcpu_runs_old_kvmclock = tmp; - - ka->kvmclock_offset = -get_kernel_ns(); } vcpu->arch.time = data; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 2614a839c60d..42c66b64c12c 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1044,8 +1044,10 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data) goto err_exit; mutex_lock(&ec->mutex); + result = -ENODATA; list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { + result = 0; q->handler = acpi_ec_get_query_handler(handler); ec_dbg_evt("Query(0x%02x) scheduled", q->handler->query_bit); diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c index 6da0f9beab19..c9336751e5e3 100644 --- a/drivers/acpi/pci_irq.c +++ b/drivers/acpi/pci_irq.c @@ -372,6 +372,7 @@ static int acpi_isa_register_gsi(struct pci_dev *dev) /* Interrupt Line values above 0xF are forbidden */ if (dev->irq > 0 && (dev->irq <= 0xF) && + acpi_isa_irq_available(dev->irq) && (acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) { dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n", pin_name(dev->pin), dev->irq); diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c index 3b4ea98e3ea0..7c8408b946ca 100644 --- a/drivers/acpi/pci_link.c +++ b/drivers/acpi/pci_link.c @@ -498,8 +498,7 @@ int __init acpi_irq_penalty_init(void) PIRQ_PENALTY_PCI_POSSIBLE; } } - /* Add a penalty for the SCI */ - acpi_irq_penalty[acpi_gbl_FADT.sci_interrupt] += PIRQ_PENALTY_PCI_USING; + return 0; } @@ -553,6 +552,13 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link) irq = link->irq.possible[i]; } } + if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) { + printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. " + "Try pci=noacpi or acpi=off\n", + acpi_device_name(link->device), + acpi_device_bid(link->device)); + return -ENODEV; + } /* Attempt to enable the link device at this IRQ. */ if (acpi_pci_link_set(link, irq)) { @@ -821,6 +827,12 @@ void acpi_penalize_isa_irq(int irq, int active) } } +bool acpi_isa_irq_available(int irq) +{ + return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) || + acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS); +} + /* * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with * PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c index 28cd75c535b0..7ae7cd990fbf 100644 --- a/drivers/base/power/opp.c +++ b/drivers/base/power/opp.c @@ -892,10 +892,17 @@ static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev) u32 microvolt[3] = {0}; int count, ret; - count = of_property_count_u32_elems(opp->np, "opp-microvolt"); - if (!count) + /* Missing property isn't a problem, but an invalid entry is */ + if (!of_find_property(opp->np, "opp-microvolt", NULL)) return 0; + count = of_property_count_u32_elems(opp->np, "opp-microvolt"); + if (count < 0) { + dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n", + __func__, count); + return count; + } + /* There can be one or three elements here */ if (count != 1 && count != 3) { dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n", @@ -1063,7 +1070,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add); * share a common logic which is isolated here. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. * * Locking: The internal device_opp and opp structures are RCU protected. @@ -1151,7 +1158,7 @@ unlock: * mutex locking or synchronize_rcu() blocking calls cannot be used. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. */ int dev_pm_opp_enable(struct device *dev, unsigned long freq) @@ -1177,7 +1184,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable); * mutex locking or synchronize_rcu() blocking calls cannot be used. * * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the - * copy operation, returns 0 if no modifcation was done OR modification was + * copy operation, returns 0 if no modification was done OR modification was * successful. */ int dev_pm_opp_disable(struct device *dev, unsigned long freq) diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 3a3738fe016b..cd4510a63375 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -620,7 +620,7 @@ static struct cpuidle_state skl_cstates[] = { .name = "C6-SKL", .desc = "MWAIT 0x20", .flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 75, + .exit_latency = 85, .target_residency = 200, .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, @@ -636,11 +636,19 @@ static struct cpuidle_state skl_cstates[] = { .name = "C8-SKL", .desc = "MWAIT 0x40", .flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED, - .exit_latency = 174, + .exit_latency = 200, .target_residency = 800, .enter = &intel_idle, .enter_freeze = intel_idle_freeze, }, { + .name = "C9-SKL", + .desc = "MWAIT 0x50", + .flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED, + .exit_latency = 480, + .target_residency = 5000, + .enter = &intel_idle, + .enter_freeze = intel_idle_freeze, }, + { .name = "C10-SKL", .desc = "MWAIT 0x60", .flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED, diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 41d6911e244e..f1ccd40beae9 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -245,7 +245,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev, props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR; if (MLX5_CAP_GEN(mdev, apm)) props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG; - props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY; if (MLX5_CAP_GEN(mdev, xrc)) props->device_cap_flags |= IB_DEVICE_XRC; props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; @@ -795,53 +794,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm return 0; } -static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn) -{ - struct mlx5_create_mkey_mbox_in *in; - struct mlx5_mkey_seg *seg; - struct mlx5_core_mr mr; - int err; - - in = kzalloc(sizeof(*in), GFP_KERNEL); - if (!in) - return -ENOMEM; - - seg = &in->seg; - seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA; - seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64); - seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8); - seg->start_addr = 0; - - err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in), - NULL, NULL, NULL); - if (err) { - mlx5_ib_warn(dev, "failed to create mkey, %d\n", err); - goto err_in; - } - - kfree(in); - *key = mr.key; - - return 0; - -err_in: - kfree(in); - - return err; -} - -static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key) -{ - struct mlx5_core_mr mr; - int err; - - memset(&mr, 0, sizeof(mr)); - mr.key = key; - err = mlx5_core_destroy_mkey(dev->mdev, &mr); - if (err) - mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key); -} - static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev, struct ib_ucontext *context, struct ib_udata *udata) @@ -867,13 +819,6 @@ static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev, kfree(pd); return ERR_PTR(-EFAULT); } - } else { - err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn); - if (err) { - mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn); - kfree(pd); - return ERR_PTR(err); - } } return &pd->ibpd; @@ -884,9 +829,6 @@ static int mlx5_ib_dealloc_pd(struct ib_pd *pd) struct mlx5_ib_dev *mdev = to_mdev(pd->device); struct mlx5_ib_pd *mpd = to_mpd(pd); - if (!pd->uobject) - free_pa_mkey(mdev, mpd->pa_lkey); - mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn); kfree(mpd); @@ -1245,18 +1187,10 @@ static int create_dev_resources(struct mlx5_ib_resources *devr) struct ib_srq_init_attr attr; struct mlx5_ib_dev *dev; struct ib_cq_init_attr cq_attr = {.cqe = 1}; - u32 rsvd_lkey; int ret = 0; dev = container_of(devr, struct mlx5_ib_dev, devr); - ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey); - if (ret) { - pr_err("Failed to query special context %d\n", ret); - return ret; - } - dev->ib_dev.local_dma_lkey = rsvd_lkey; - devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL); if (IS_ERR(devr->p0)) { ret = PTR_ERR(devr->p0); @@ -1418,6 +1352,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev) strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX); dev->ib_dev.owner = THIS_MODULE; dev->ib_dev.node_type = RDMA_NODE_IB_CA; + dev->ib_dev.local_dma_lkey = 0 /* not supported for now */; dev->num_ports = MLX5_CAP_GEN(mdev, num_ports); dev->ib_dev.phys_port_cnt = dev->num_ports; dev->ib_dev.num_comp_vectors = diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index bb8cda79e881..22123b79d550 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -103,7 +103,6 @@ static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibuconte struct mlx5_ib_pd { struct ib_pd ibpd; u32 pdn; - u32 pa_lkey; }; /* Use macros here so that don't have to duplicate @@ -213,7 +212,6 @@ struct mlx5_ib_qp { int uuarn; int create_type; - u32 pa_lkey; /* Store signature errors */ bool signature_en; diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index c745c6c5e10d..6f521a3418e8 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -925,8 +925,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd, err = create_kernel_qp(dev, init_attr, qp, &in, &inlen); if (err) mlx5_ib_dbg(dev, "err %d\n", err); - else - qp->pa_lkey = to_mpd(pd)->pa_lkey; } if (err) @@ -2045,7 +2043,7 @@ static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg, mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm); dseg->addr = cpu_to_be64(mfrpl->map); dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64)); - dseg->lkey = cpu_to_be32(pd->pa_lkey); + dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey); } static __be32 send_ieth(struct ib_send_wr *wr) diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h index ca2873698d75..4cd5428a2399 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib.h +++ b/drivers/infiniband/ulp/ipoib/ipoib.h @@ -80,7 +80,7 @@ enum { IPOIB_NUM_WC = 4, IPOIB_MAX_PATH_REC_QUEUE = 3, - IPOIB_MAX_MCAST_QUEUE = 3, + IPOIB_MAX_MCAST_QUEUE = 64, IPOIB_FLAG_OPER_UP = 0, IPOIB_FLAG_INITIALIZED = 1, @@ -548,6 +548,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter, int ipoib_mcast_attach(struct net_device *dev, u16 mlid, union ib_gid *mgid, int set_qkey); +int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast); +struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid); int ipoib_init_qp(struct net_device *dev); int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca); diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 36536ce5a3e2..f74316e679d2 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) unsigned long dt; unsigned long flags; int i; + LIST_HEAD(remove_list); + struct ipoib_mcast *mcast, *tmcast; + struct net_device *dev = priv->dev; if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags)) return; @@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) lockdep_is_held(&priv->lock))) != NULL) { /* was the neigh idle for two GC periods */ if (time_after(neigh_obsolete, neigh->alive)) { + u8 *mgid = neigh->daddr + 4; + + /* Is this multicast ? */ + if (*mgid == 0xff) { + mcast = __ipoib_mcast_find(dev, mgid); + + if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) { + list_del(&mcast->list); + rb_erase(&mcast->rb_node, &priv->multicast_tree); + list_add_tail(&mcast->list, &remove_list); + } + } + rcu_assign_pointer(*np, rcu_dereference_protected(neigh->hnext, lockdep_is_held(&priv->lock))); @@ -1191,6 +1207,8 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv) out_unlock: spin_unlock_irqrestore(&priv->lock, flags); + list_for_each_entry_safe(mcast, tmcast, &remove_list, list) + ipoib_mcast_leave(dev, mcast); } static void ipoib_reap_neigh(struct work_struct *work) diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c index 09a1748f9d13..136cbefe00f8 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c @@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev, return mcast; } -static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid) +struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct rb_node *n = priv->multicast_tree.rb_node; @@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast) rec.hop_limit = priv->broadcast->mcmember.hop_limit; /* - * Historically Linux IPoIB has never properly supported SEND - * ONLY join. It emulated it by not providing all the required - * attributes, which is enough to prevent group creation and - * detect if there are full members or not. A major problem - * with supporting SEND ONLY is detecting when the group is - * auto-destroyed as IPoIB will cache the MLID.. + * Send-only IB Multicast joins do not work at the core + * IB layer yet, so we can't use them here. However, + * we are emulating an Ethernet multicast send, which + * does not require a multicast subscription and will + * still send properly. The most appropriate thing to + * do is to create the group if it doesn't exist as that + * most closely emulates the behavior, from a user space + * application perspecitive, of Ethernet multicast + * operation. For now, we do a full join, maybe later + * when the core IB layers support send only joins we + * will use them. */ -#if 1 - if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) - comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS; -#else +#if 0 if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) rec.join_state = 4; #endif @@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev) return 0; } -static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) +int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast) { struct ipoib_dev_priv *priv = netdev_priv(dev); int ret = 0; diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 1ace5d83a4d7..f58ff96b6cbb 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -97,6 +97,11 @@ unsigned int iser_max_sectors = ISER_DEF_MAX_SECTORS; module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR); MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024"); +bool iser_always_reg = true; +module_param_named(always_register, iser_always_reg, bool, S_IRUGO); +MODULE_PARM_DESC(always_register, + "Always register memory, even for continuous memory regions (default:true)"); + bool iser_pi_enable = false; module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO); MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)"); diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index 86f6583485ef..a5edd6ede692 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -611,6 +611,7 @@ extern int iser_debug_level; extern bool iser_pi_enable; extern int iser_pi_guard; extern unsigned int iser_max_sectors; +extern bool iser_always_reg; int iser_assign_reg_ops(struct iser_device *device); diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c index 2493cc748db8..4c46d67d37a1 100644 --- a/drivers/infiniband/ulp/iser/iser_memory.c +++ b/drivers/infiniband/ulp/iser/iser_memory.c @@ -803,11 +803,12 @@ static int iser_reg_prot_sg(struct iscsi_iser_task *task, struct iser_data_buf *mem, struct iser_fr_desc *desc, + bool use_dma_key, struct iser_mem_reg *reg) { struct iser_device *device = task->iser_conn->ib_conn.device; - if (mem->dma_nents == 1) + if (use_dma_key) return iser_reg_dma(device, mem, reg); return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg); @@ -817,11 +818,12 @@ static int iser_reg_data_sg(struct iscsi_iser_task *task, struct iser_data_buf *mem, struct iser_fr_desc *desc, + bool use_dma_key, struct iser_mem_reg *reg) { struct iser_device *device = task->iser_conn->ib_conn.device; - if (mem->dma_nents == 1) + if (use_dma_key) return iser_reg_dma(device, mem, reg); return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg); @@ -836,14 +838,17 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task, struct iser_mem_reg *reg = &task->rdma_reg[dir]; struct iser_mem_reg *data_reg; struct iser_fr_desc *desc = NULL; + bool use_dma_key; int err; err = iser_handle_unaligned_buf(task, mem, dir); if (unlikely(err)) return err; - if (mem->dma_nents != 1 || - scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) { + use_dma_key = (mem->dma_nents == 1 && !iser_always_reg && + scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL); + + if (!use_dma_key) { desc = device->reg_ops->reg_desc_get(ib_conn); reg->mem_h = desc; } @@ -853,7 +858,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task, else data_reg = &task->desc.data_reg; - err = iser_reg_data_sg(task, mem, desc, data_reg); + err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg); if (unlikely(err)) goto err_reg; @@ -866,7 +871,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task, if (unlikely(err)) goto err_reg; - err = iser_reg_prot_sg(task, mem, desc, prot_reg); + err = iser_reg_prot_sg(task, mem, desc, + use_dma_key, prot_reg); if (unlikely(err)) goto err_reg; } diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c index ae70cc1463ac..85132d867bc8 100644 --- a/drivers/infiniband/ulp/iser/iser_verbs.c +++ b/drivers/infiniband/ulp/iser/iser_verbs.c @@ -133,11 +133,15 @@ static int iser_create_device_ib_res(struct iser_device *device) (unsigned long)comp); } - device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE | - IB_ACCESS_REMOTE_WRITE | - IB_ACCESS_REMOTE_READ); - if (IS_ERR(device->mr)) - goto dma_mr_err; + if (!iser_always_reg) { + int access = IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ; + + device->mr = ib_get_dma_mr(device->pd, access); + if (IS_ERR(device->mr)) + goto dma_mr_err; + } INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device, iser_event_handler); @@ -147,7 +151,8 @@ static int iser_create_device_ib_res(struct iser_device *device) return 0; handler_err: - ib_dereg_mr(device->mr); + if (device->mr) + ib_dereg_mr(device->mr); dma_mr_err: for (i = 0; i < device->comps_used; i++) tasklet_kill(&device->comps[i].tasklet); @@ -173,7 +178,6 @@ comps_err: static void iser_free_device_ib_res(struct iser_device *device) { int i; - BUG_ON(device->mr == NULL); for (i = 0; i < device->comps_used; i++) { struct iser_comp *comp = &device->comps[i]; @@ -184,7 +188,8 @@ static void iser_free_device_ib_res(struct iser_device *device) } (void)ib_unregister_event_handler(&device->event_handler); - (void)ib_dereg_mr(device->mr); + if (device->mr) + (void)ib_dereg_mr(device->mr); ib_dealloc_pd(device->pd); kfree(device->comps); diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c index f8baa897d1a0..1f7dd927cc5e 100644 --- a/drivers/net/dsa/mv88e6xxx.c +++ b/drivers/net/dsa/mv88e6xxx.c @@ -2051,6 +2051,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port) reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA; else reg |= PORT_CONTROL_FRAME_MODE_DSA; + reg |= PORT_CONTROL_FORWARD_UNKNOWN | + PORT_CONTROL_FORWARD_UNKNOWN_MC; } if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) || diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c index b7a0f7879de2..9e59663a6ead 100644 --- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c +++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c @@ -1543,7 +1543,7 @@ bfa_flash_cmd_act_check(void __iomem *pci_bar) } /* Flush FLI data fifo. */ -static u32 +static int bfa_flash_fifo_flush(void __iomem *pci_bar) { u32 i; @@ -1573,11 +1573,11 @@ bfa_flash_fifo_flush(void __iomem *pci_bar) } /* Read flash status. */ -static u32 +static int bfa_flash_status_read(void __iomem *pci_bar) { union bfa_flash_dev_status_reg dev_status; - u32 status; + int status; u32 ret_status; int i; @@ -1611,11 +1611,11 @@ bfa_flash_status_read(void __iomem *pci_bar) } /* Start flash read operation. */ -static u32 +static int bfa_flash_read_start(void __iomem *pci_bar, u32 offset, u32 len, char *buf) { - u32 status; + int status; /* len must be mutiple of 4 and not exceeding fifo size */ if (len == 0 || len > BFA_FLASH_FIFO_SIZE || (len & 0x03) != 0) @@ -1703,7 +1703,8 @@ static enum bfa_status bfa_flash_raw_read(void __iomem *pci_bar, u32 offset, char *buf, u32 len) { - u32 n, status; + u32 n; + int status; u32 off, l, s, residue, fifo_sz; residue = len; diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c index cc2d8b4b18e3..253f8ed0537a 100644 --- a/drivers/net/ethernet/hisilicon/hip04_eth.c +++ b/drivers/net/ethernet/hisilicon/hip04_eth.c @@ -816,7 +816,7 @@ static int hip04_mac_probe(struct platform_device *pdev) struct net_device *ndev; struct hip04_priv *priv; struct resource *res; - unsigned int irq; + int irq; int ret; ndev = alloc_etherdev(sizeof(struct hip04_priv)); diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h index 28df37420da9..ac02c675c59c 100644 --- a/drivers/net/ethernet/ibm/emac/core.h +++ b/drivers/net/ethernet/ibm/emac/core.h @@ -460,8 +460,8 @@ struct emac_ethtool_regs_subhdr { u32 index; }; -#define EMAC_ETHTOOL_REGS_VER 0 -#define EMAC4_ETHTOOL_REGS_VER 1 -#define EMAC4SYNC_ETHTOOL_REGS_VER 2 +#define EMAC_ETHTOOL_REGS_VER 3 +#define EMAC4_ETHTOOL_REGS_VER 4 +#define EMAC4SYNC_ETHTOOL_REGS_VER 5 #endif /* __IBM_NEWEMAC_CORE_H */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 3e0d20037675..62488a67149d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -946,6 +946,13 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw, /* take the lock before we start messing with the ring */ mutex_lock(&hw->aq.arq_mutex); + if (hw->aq.arq.count == 0) { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQRX: Admin queue not initialized.\n"); + ret_code = I40E_ERR_QUEUE_EMPTY; + goto clean_arq_element_err; + } + /* set next_to_use to head */ ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK); if (ntu == ntc) { @@ -1007,6 +1014,8 @@ clean_arq_element_out: /* Set pending if needed, unlock and return */ if (pending != NULL) *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc); + +clean_arq_element_err: mutex_unlock(&hw->aq.arq_mutex); if (i40e_is_nvm_update_op(&e->desc)) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 851c1a159be8..2fdf978ae6a5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2672,7 +2672,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) rx_ctx.lrxqthresh = 2; rx_ctx.crcstrip = 1; rx_ctx.l2tsel = 1; - rx_ctx.showiv = 1; + /* this controls whether VLAN is stripped from inner headers */ + rx_ctx.showiv = 0; #ifdef I40E_FCOE rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE); #endif diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index f08450b90774..929d47152bf2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -887,6 +887,13 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw, /* take the lock before we start messing with the ring */ mutex_lock(&hw->aq.arq_mutex); + if (hw->aq.arq.count == 0) { + i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE, + "AQRX: Admin queue not initialized.\n"); + ret_code = I40E_ERR_QUEUE_EMPTY; + goto clean_arq_element_err; + } + /* set next_to_use to head */ ntu = (rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK); if (ntu == ntc) { @@ -948,6 +955,8 @@ clean_arq_element_out: /* Set pending if needed, unlock and return */ if (pending != NULL) *pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc); + +clean_arq_element_err: mutex_unlock(&hw->aq.arq_mutex); return ret_code; diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index bd9ea0d01aae..1d4e2e054647 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -1184,10 +1184,11 @@ out: if (prot == MLX4_PROT_ETH) { /* manage the steering entry for promisc mode */ if (new_entry) - new_steering_entry(dev, port, steer, index, qp->qpn); + err = new_steering_entry(dev, port, steer, + index, qp->qpn); else - existing_steering_entry(dev, port, steer, - index, qp->qpn); + err = existing_steering_entry(dev, port, steer, + index, qp->qpn); } if (err && link && index != -1) { if (index < dev->caps.num_mgms) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c index aa0d5ffe92d8..9335e5ae18cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c @@ -200,25 +200,3 @@ int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev) return err; } - -int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey) -{ - struct mlx5_cmd_query_special_contexts_mbox_in in; - struct mlx5_cmd_query_special_contexts_mbox_out out; - int err; - - memset(&in, 0, sizeof(in)); - memset(&out, 0, sizeof(out)); - in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS); - err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out)); - if (err) - return err; - - if (out.hdr.status) - err = mlx5_cmd_status_to_err(&out.hdr); - - *rsvd_lkey = be32_to_cpu(out.resd_lkey); - - return err; -} -EXPORT_SYMBOL(mlx5_core_query_special_context); diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index 2b32e0c5a0b4..b4f21232019a 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -6081,7 +6081,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { void __iomem *ioaddr = tp->mmio_addr; struct pci_dev *pdev = tp->pci_dev; - u16 rg_saw_cnt; + int rg_saw_cnt; u32 data; static const struct ephy_info e_info_8168h_1[] = { { 0x1e, 0x0800, 0x0001 }, diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index dd652f2ae03d..108a3118ace7 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -299,9 +299,10 @@ static long local_pci_probe(void *_ddi) * Unbound PCI devices are always put in D0, regardless of * runtime PM status. During probe, the device is set to * active and the usage count is incremented. If the driver - * supports runtime PM, it should call pm_runtime_put_noidle() - * in its probe routine and pm_runtime_get_noresume() in its - * remove routine. + * supports runtime PM, it should call pm_runtime_put_noidle(), + * or any other runtime PM helper function decrementing the usage + * count, in its probe routine and pm_runtime_get_noresume() in + * its remove routine. */ pm_runtime_get_sync(dev); pci_dev->driver = pci_drv; diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 7235c4851460..43856d19cf4d 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -217,6 +217,7 @@ struct pci_dev; int acpi_pci_irq_enable (struct pci_dev *dev); void acpi_penalize_isa_irq(int irq, int active); +bool acpi_isa_irq_available(int irq); void acpi_penalize_sci_irq(int irq, int trigger, int polarity); void acpi_pci_irq_disable (struct pci_dev *dev); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 8eb3b19af2a4..250b1ff8b48d 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -402,17 +402,6 @@ struct mlx5_cmd_teardown_hca_mbox_out { u8 rsvd[8]; }; -struct mlx5_cmd_query_special_contexts_mbox_in { - struct mlx5_inbox_hdr hdr; - u8 rsvd[8]; -}; - -struct mlx5_cmd_query_special_contexts_mbox_out { - struct mlx5_outbox_hdr hdr; - __be32 dump_fill_mkey; - __be32 resd_lkey; -}; - struct mlx5_cmd_layout { u8 type; u8 rsvd0[3]; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 27b53f9a24ad..8b6d6f2154a4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -845,7 +845,6 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol); int mlx5_register_interface(struct mlx5_interface *intf); void mlx5_unregister_interface(struct mlx5_interface *intf); int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id); -int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey); struct mlx5_profile { u64 mask; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2b0a30a6e31c..4398411236f1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2708,7 +2708,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, if (skb->ip_summed == CHECKSUM_COMPLETE) skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) <= len) + skb_checksum_start_offset(skb) < 0) skb->ip_summed = CHECKSUM_NONE; } diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 4a167b30a12f..cb1b9bbda332 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -63,7 +63,11 @@ struct unix_sock { #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; }; -#define unix_sk(__sk) ((struct unix_sock *)__sk) + +static inline struct unix_sock *unix_sk(struct sock *sk) +{ + return (struct unix_sock *)sk; +} #define peer_wait peer_wq.wait diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 805a95a48107..830f8a7c1cb1 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -31,7 +31,6 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; -static const char fmt_udec[] = "%u\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; @@ -202,7 +201,7 @@ static ssize_t speed_show(struct device *dev, if (netif_running(netdev)) { struct ethtool_cmd cmd; if (!__ethtool_get_settings(netdev, &cmd)) - ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd)); + ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); } rtnl_unlock(); return ret; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index dad4dd37e2aa..fab4599ba8b2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags); */ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { + unsigned char *data = skb->data; + BUG_ON(len > skb->len); - skb->len -= len; - BUG_ON(skb->len < skb->data_len); - skb_postpull_rcsum(skb, skb->data, len); - return skb->data += len; + __skb_pull(skb, len); + skb_postpull_rcsum(skb, data, len); + return skb->data; } EXPORT_SYMBOL_GPL(skb_pull_rcsum); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index cce97385f743..7d91f4612ac0 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -458,12 +458,17 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) static int dsa_slave_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { - int ret = 0; + struct dsa_slave_priv *p = netdev_priv(dev); + struct dsa_switch *ds = p->parent; + int ret; switch (attr->id) { case SWITCHDEV_ATTR_PORT_STP_STATE: - if (attr->trans == SWITCHDEV_TRANS_COMMIT) - ret = dsa_slave_stp_update(dev, attr->u.stp_state); + if (attr->trans == SWITCHDEV_TRANS_PREPARE) + ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP; + else + ret = ds->drv->port_stp_update(ds, p->port, + attr->u.stp_state); break; default: ret = -EOPNOTSUPP; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6fcbd215cdbc..690bcbc59f26 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -340,6 +340,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_tun_key.tun_id = 0; + fl4.flowi4_flags = 0; no_addr = idev->ifa_list == NULL; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index c6ad99ad0ffb..c81deb85acb4 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1737,6 +1737,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; err = fib_lookup(net, &fl4, &res, 0); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f204089e854c..cb32ce250db0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1193,7 +1193,8 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk, fl6->flowi6_iif = LOOPBACK_IFINDEX; - if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr)) + if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) || + fl6->flowi6_oif) flags |= RT6_LOOKUP_F_IFACE; if (!ipv6_addr_any(&fl6->saddr)) diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index f6b090df3930..afca2eb4dfa7 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -1319,7 +1319,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work) tunnel = container_of(work, struct l2tp_tunnel, del_work); sk = l2tp_tunnel_sock_lookup(tunnel); if (!sk) - return; + goto out; sock = sk->sk_socket; @@ -1341,6 +1341,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work) } l2tp_tunnel_sock_put(sk); +out: + l2tp_tunnel_dec_refcount(tunnel); } /* Create a socket for the tunnel, if one isn't set up by @@ -1636,8 +1638,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create); */ int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel) { + l2tp_tunnel_inc_refcount(tunnel); l2tp_tunnel_closeall(tunnel); - return (false == queue_work(l2tp_wq, &tunnel->del_work)); + if (false == queue_work(l2tp_wq, &tunnel->del_work)) { + l2tp_tunnel_dec_refcount(tunnel); + return 1; + } + return 0; } EXPORT_SYMBOL_GPL(l2tp_tunnel_delete); diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 197c3f59ecbf..b00f1f9611d6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1208,20 +1208,22 @@ void sctp_assoc_update(struct sctp_association *asoc, * within this document. * * Our basic strategy is to round-robin transports in priorities - * according to sctp_state_prio_map[] e.g., if no such + * according to sctp_trans_score() e.g., if no such * transport with state SCTP_ACTIVE exists, round-robin through * SCTP_UNKNOWN, etc. You get the picture. */ -static const u8 sctp_trans_state_to_prio_map[] = { - [SCTP_ACTIVE] = 3, /* best case */ - [SCTP_UNKNOWN] = 2, - [SCTP_PF] = 1, - [SCTP_INACTIVE] = 0, /* worst case */ -}; - static u8 sctp_trans_score(const struct sctp_transport *trans) { - return sctp_trans_state_to_prio_map[trans->state]; + switch (trans->state) { + case SCTP_ACTIVE: + return 3; /* best case */ + case SCTP_UNKNOWN: + return 2; + case SCTP_PF: + return 1; + default: /* case SCTP_INACTIVE */ + return 0; /* worst case */ + } } static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1, diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 35df1266bf07..6098d4c42fa9 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -244,12 +244,13 @@ void sctp_generate_t3_rtx_event(unsigned long peer) int error; struct sctp_transport *transport = (struct sctp_transport *) peer; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); /* Check whether a task is in the sock. */ - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -272,10 +273,10 @@ void sctp_generate_t3_rtx_event(unsigned long peer) transport, GFP_ATOMIC); if (error) - asoc->base.sk->sk_err = -error; + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_transport_put(transport); } @@ -285,11 +286,12 @@ out_unlock: static void sctp_generate_timeout_event(struct sctp_association *asoc, sctp_event_timeout_t timeout_type) { - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); int error = 0; - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy: timer %d\n", __func__, timeout_type); @@ -312,10 +314,10 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc, (void *)timeout_type, GFP_ATOMIC); if (error) - asoc->base.sk->sk_err = -error; + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_association_put(asoc); } @@ -365,10 +367,11 @@ void sctp_generate_heartbeat_event(unsigned long data) int error = 0; struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -388,11 +391,11 @@ void sctp_generate_heartbeat_event(unsigned long data) asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); - if (error) - asoc->base.sk->sk_err = -error; + if (error) + sk->sk_err = -error; out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_transport_put(transport); } @@ -403,10 +406,11 @@ void sctp_generate_proto_unreach_event(unsigned long data) { struct sctp_transport *transport = (struct sctp_transport *) data; struct sctp_association *asoc = transport->asoc; - struct net *net = sock_net(asoc->base.sk); + struct sock *sk = asoc->base.sk; + struct net *net = sock_net(sk); - bh_lock_sock(asoc->base.sk); - if (sock_owned_by_user(asoc->base.sk)) { + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { pr_debug("%s: sock is busy\n", __func__); /* Try again later. */ @@ -427,7 +431,7 @@ void sctp_generate_proto_unreach_event(unsigned long data) asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC); out_unlock: - bh_unlock_sock(asoc->base.sk); + bh_unlock_sock(sk); sctp_association_put(asoc); } diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c index cb25c89da623..f1e8dafbd507 100644 --- a/net/sunrpc/xprtrdma/fmr_ops.c +++ b/net/sunrpc/xprtrdma/fmr_ops.c @@ -39,25 +39,6 @@ static int fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { - struct ib_device_attr *devattr = &ia->ri_devattr; - struct ib_mr *mr; - - /* Obtain an lkey to use for the regbufs, which are - * protected from remote access. - */ - if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) { - ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; - } else { - mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(mr)) { - pr_err("%s: ib_get_dma_mr for failed with %lX\n", - __func__, PTR_ERR(mr)); - return -ENOMEM; - } - ia->ri_dma_lkey = ia->ri_dma_mr->lkey; - ia->ri_dma_mr = mr; - } - return 0; } diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index d6653f5d0830..5318951b3b53 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -189,11 +189,6 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct ib_device_attr *devattr = &ia->ri_devattr; int depth, delta; - /* Obtain an lkey to use for the regbufs, which are - * protected from remote access. - */ - ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; - ia->ri_max_frmr_depth = min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS, devattr->max_fast_reg_page_list_len); diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c index 72cf8b15bbb4..617b76f22154 100644 --- a/net/sunrpc/xprtrdma/physical_ops.c +++ b/net/sunrpc/xprtrdma/physical_ops.c @@ -23,7 +23,6 @@ static int physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, struct rpcrdma_create_data_internal *cdata) { - struct ib_device_attr *devattr = &ia->ri_devattr; struct ib_mr *mr; /* Obtain an rkey to use for RPC data payloads. @@ -37,15 +36,8 @@ physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep, __func__, PTR_ERR(mr)); return -ENOMEM; } - ia->ri_dma_mr = mr; - - /* Obtain an lkey to use for regbufs. - */ - if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) - ia->ri_dma_lkey = ia->ri_device->local_dma_lkey; - else - ia->ri_dma_lkey = ia->ri_dma_mr->lkey; + ia->ri_dma_mr = mr; return 0; } diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 682996779970..eb081ad05e33 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -1252,7 +1252,7 @@ rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags) goto out_free; iov->length = size; - iov->lkey = ia->ri_dma_lkey; + iov->lkey = ia->ri_pd->local_dma_lkey; rb->rg_size = size; rb->rg_owner = NULL; return rb; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 02512221b8bc..c09414e6f91b 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -65,7 +65,6 @@ struct rpcrdma_ia { struct rdma_cm_id *ri_id; struct ib_pd *ri_pd; struct ib_mr *ri_dma_mr; - u32 ri_dma_lkey; struct completion ri_done; int ri_async_rc; unsigned int ri_max_frmr_depth; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 03ee4d359f6a..ef31b40ad550 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2179,8 +2179,21 @@ unlock: if (UNIXCB(skb).fp) scm.fp = scm_fp_dup(UNIXCB(skb).fp); - sk_peek_offset_fwd(sk, chunk); + if (skip) { + sk_peek_offset_fwd(sk, chunk); + skip -= chunk; + } + if (UNIXCB(skb).fp) + break; + + last = skb; + last_len = skb->len; + unix_state_lock(sk); + skb = skb_peek_next(skb, &sk->sk_receive_queue); + if (skb) + goto again; + unix_state_unlock(sk); break; } } while (size); diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 9655cb49c7cb..bde0ef1a63df 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -71,8 +71,11 @@ unsigned int extra_msr_offset32; unsigned int extra_msr_offset64; unsigned int extra_delta_offset32; unsigned int extra_delta_offset64; +unsigned int aperf_mperf_multiplier = 1; int do_smi; double bclk; +double base_hz; +double tsc_tweak = 1.0; unsigned int show_pkg; unsigned int show_core; unsigned int show_cpu; @@ -502,7 +505,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* %Busy */ if (has_aperf) { if (!skip_c0) - outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc); + outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak); else outp += sprintf(outp, "********"); } @@ -510,7 +513,7 @@ int format_counters(struct thread_data *t, struct core_data *c, /* Bzy_MHz */ if (has_aperf) outp += sprintf(outp, "%8.0f", - 1.0 * t->tsc / units * t->aperf / t->mperf / interval_float); + 1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float); /* TSC_MHz */ outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float); @@ -984,6 +987,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) return -3; if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf)) return -4; + t->aperf = t->aperf * aperf_mperf_multiplier; + t->mperf = t->mperf * aperf_mperf_multiplier; } if (do_smi) { @@ -1149,6 +1154,19 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV, int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV}; + +static void +calculate_tsc_tweak() +{ + unsigned long long msr; + unsigned int base_ratio; + + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); + base_ratio = (msr >> 8) & 0xFF; + base_hz = base_ratio * bclk * 1000000; + tsc_tweak = base_hz / tsc_hz; +} + static void dump_nhm_platform_info(void) { @@ -1926,8 +1944,6 @@ int has_config_tdp(unsigned int family, unsigned int model) switch (model) { case 0x3A: /* IVB */ - case 0x3E: /* IVB Xeon */ - case 0x3C: /* HSW */ case 0x3F: /* HSX */ case 0x45: /* HSW */ @@ -2543,6 +2559,13 @@ int is_knl(unsigned int family, unsigned int model) return 0; } +unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model) +{ + if (is_knl(family, model)) + return 1024; + return 1; +} + #define SLM_BCLK_FREQS 5 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; @@ -2744,6 +2767,9 @@ void process_cpuid() } } + if (has_aperf) + aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model); + do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model); do_snb_cstates = has_snb_msrs(family, model); do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2); @@ -2762,6 +2788,9 @@ void process_cpuid() if (debug) dump_cstate_pstate_config_info(); + if (has_skl_msrs(family, model)) + calculate_tsc_tweak(); + return; } @@ -3090,7 +3119,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(stderr, "turbostat version 4.7 17-June, 2015" + fprintf(stderr, "turbostat version 4.8 26-Sep, 2015" " - Len Brown <lenb@kernel.org>\n"); } |