diff options
24 files changed, 327 insertions, 184 deletions
diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index eee9f857a986..896914e3a847 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -7213,14 +7213,13 @@ veto the transition. :Parameters: args[0] is the maximum poll time in nanoseconds :Returns: 0 on success; -1 on error -This capability overrides the kvm module parameter halt_poll_ns for the -target VM. - -VCPU polling allows a VCPU to poll for wakeup events instead of immediately -scheduling during guest halts. The maximum time a VCPU can spend polling is -controlled by the kvm module parameter halt_poll_ns. This capability allows -the maximum halt time to specified on a per-VM basis, effectively overriding -the module parameter for the target VM. +KVM_CAP_HALT_POLL overrides the kvm.halt_poll_ns module parameter to set the +maximum halt-polling time for all vCPUs in the target VM. This capability can +be invoked at any time and any number of times to dynamically change the +maximum halt-polling time. + +See Documentation/virt/kvm/halt-polling.rst for more information on halt +polling. 7.21 KVM_CAP_X86_USER_SPACE_MSR ------------------------------- diff --git a/Documentation/virt/kvm/x86/halt-polling.rst b/Documentation/virt/kvm/halt-polling.rst index 4922e4a15f18..3fae39b1a5ba 100644 --- a/Documentation/virt/kvm/x86/halt-polling.rst +++ b/Documentation/virt/kvm/halt-polling.rst @@ -119,6 +119,19 @@ These module parameters can be set from the debugfs files in: Note: that these module parameters are system wide values and are not able to be tuned on a per vm basis. +Any changes to these parameters will be picked up by new and existing vCPUs the +next time they halt, with the notable exception of VMs using KVM_CAP_HALT_POLL +(see next section). + +KVM_CAP_HALT_POLL +================= + +KVM_CAP_HALT_POLL is a VM capability that allows userspace to override halt_poll_ns +on a per-VM basis. VMs using KVM_CAP_HALT_POLL ignore halt_poll_ns completely (but +still obey halt_poll_ns_grow, halt_poll_ns_grow_start, and halt_poll_ns_shrink). + +See Documentation/virt/kvm/api.rst for more information on this capability. + Further Notes ============= diff --git a/Documentation/virt/kvm/index.rst b/Documentation/virt/kvm/index.rst index e0a2c74e1043..ad13ec55ddfe 100644 --- a/Documentation/virt/kvm/index.rst +++ b/Documentation/virt/kvm/index.rst @@ -17,4 +17,5 @@ KVM locking vcpu-requests + halt-polling review-checklist diff --git a/Documentation/virt/kvm/x86/index.rst b/Documentation/virt/kvm/x86/index.rst index 7ff588826b9f..9ece6b8dc817 100644 --- a/Documentation/virt/kvm/x86/index.rst +++ b/Documentation/virt/kvm/x86/index.rst @@ -10,7 +10,6 @@ KVM for x86 systems amd-memory-encryption cpuid errata - halt-polling hypercalls mmu msr diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 3cb101e8cb29..5240f6acad64 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -36,7 +36,22 @@ void arch_dma_prep_coherent(struct page *page, size_t size) { unsigned long start = (unsigned long)page_address(page); - dcache_clean_poc(start, start + size); + /* + * The architecture only requires a clean to the PoC here in order to + * meet the requirements of the DMA API. However, some vendors (i.e. + * Qualcomm) abuse the DMA API for transferring buffers from the + * non-secure to the secure world, resetting the system if a non-secure + * access shows up after the buffer has been transferred: + * + * https://lore.kernel.org/r/20221114110329.68413-1-manivannan.sadhasivam@linaro.org + * + * Using clean+invalidate appears to make this issue less likely, but + * the drivers themselves still need fixing as the CPU could issue a + * speculative read from the buffer via the linear mapping irrespective + * of the cache maintenance we use. Once the drivers are fixed, we can + * relax this to a clean operation. + */ + dcache_clean_inval_poc(start, start + size); } #ifdef CONFIG_IOMMU_DMA diff --git a/arch/s390/kvm/vsie.c b/arch/s390/kvm/vsie.c index 94138f8f0c1c..ace2541ababd 100644 --- a/arch/s390/kvm/vsie.c +++ b/arch/s390/kvm/vsie.c @@ -546,8 +546,10 @@ static int shadow_scb(struct kvm_vcpu *vcpu, struct vsie_page *vsie_page) if (test_kvm_cpu_feat(vcpu->kvm, KVM_S390_VM_CPU_FEAT_CEI)) scb_s->eca |= scb_o->eca & ECA_CEI; /* Epoch Extension */ - if (test_kvm_facility(vcpu->kvm, 139)) + if (test_kvm_facility(vcpu->kvm, 139)) { scb_s->ecd |= scb_o->ecd & ECD_MEF; + scb_s->epdx = scb_o->epdx; + } /* etoken */ if (test_kvm_facility(vcpu->kvm, 156)) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 2835bd796639..69227f77b201 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -10574,8 +10574,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN; vcpu->mmio_needed = 0; r = 0; + goto out; } - goto out; } if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) { /* Page is swapped out. Do synthetic halt */ diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c index ddf17e2d266c..b9e336bacf17 100644 --- a/drivers/ata/libahci_platform.c +++ b/drivers/ata/libahci_platform.c @@ -109,7 +109,7 @@ struct clk *ahci_platform_find_clk(struct ahci_host_priv *hpriv, const char *con int i; for (i = 0; i < hpriv->n_clks; i++) { - if (!strcmp(hpriv->clks[i].id, con_id)) + if (hpriv->clks[i].id && !strcmp(hpriv->clks[i].id, con_id)) return hpriv->clks[i].clk; } diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c index 14e6b3e64add..6f3ded619c8b 100644 --- a/drivers/gpio/gpio-amd8111.c +++ b/drivers/gpio/gpio-amd8111.c @@ -226,7 +226,10 @@ found: ioport_unmap(gp.pm); goto out; } + return 0; + out: + pci_dev_put(pdev); return err; } @@ -234,6 +237,7 @@ static void __exit amd_gpio_exit(void) { gpiochip_remove(&gp.chip); ioport_unmap(gp.pm); + pci_dev_put(gp.pdev); } module_init(amd_gpio_init); diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c index 870910bb9dd3..200e43a6f4b4 100644 --- a/drivers/gpio/gpio-rockchip.c +++ b/drivers/gpio/gpio-rockchip.c @@ -610,6 +610,7 @@ static int rockchip_gpiolib_register(struct rockchip_pin_bank *bank) return -ENODATA; pctldev = of_pinctrl_get(pctlnp); + of_node_put(pctlnp); if (!pctldev) return -ENODEV; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 4756ea08894f..a70522aef355 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -526,12 +526,13 @@ static int gpiochip_setup_dev(struct gpio_device *gdev) if (ret) return ret; + /* From this point, the .release() function cleans up gpio_device */ + gdev->dev.release = gpiodevice_release; + ret = gpiochip_sysfs_register(gdev); if (ret) goto err_remove_device; - /* From this point, the .release() function cleans up gpio_device */ - gdev->dev.release = gpiodevice_release; dev_dbg(&gdev->dev, "registered GPIOs %d to %d on %s\n", gdev->base, gdev->base + gdev->ngpio - 1, gdev->chip->label ? : "generic"); @@ -597,10 +598,10 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, struct fwnode_handle *fwnode = NULL; struct gpio_device *gdev; unsigned long flags; - int base = gc->base; unsigned int i; + u32 ngpios = 0; + int base = 0; int ret = 0; - u32 ngpios; if (gc->fwnode) fwnode = gc->fwnode; @@ -647,17 +648,12 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, else gdev->owner = THIS_MODULE; - gdev->descs = kcalloc(gc->ngpio, sizeof(gdev->descs[0]), GFP_KERNEL); - if (!gdev->descs) { - ret = -ENOMEM; - goto err_free_dev_name; - } - /* * Try the device properties if the driver didn't supply the number * of GPIO lines. */ - if (gc->ngpio == 0) { + ngpios = gc->ngpio; + if (ngpios == 0) { ret = device_property_read_u32(&gdev->dev, "ngpios", &ngpios); if (ret == -ENODATA) /* @@ -668,7 +664,7 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, */ ngpios = 0; else if (ret) - goto err_free_descs; + goto err_free_dev_name; gc->ngpio = ngpios; } @@ -676,13 +672,19 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, if (gc->ngpio == 0) { chip_err(gc, "tried to insert a GPIO chip with zero lines\n"); ret = -EINVAL; - goto err_free_descs; + goto err_free_dev_name; } if (gc->ngpio > FASTPATH_NGPIO) chip_warn(gc, "line cnt %u is greater than fast path cnt %u\n", gc->ngpio, FASTPATH_NGPIO); + gdev->descs = kcalloc(gc->ngpio, sizeof(*gdev->descs), GFP_KERNEL); + if (!gdev->descs) { + ret = -ENOMEM; + goto err_free_dev_name; + } + gdev->label = kstrdup_const(gc->label ?: "unknown", GFP_KERNEL); if (!gdev->label) { ret = -ENOMEM; @@ -701,11 +703,13 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data, * it may be a pipe dream. It will not happen before we get rid * of the sysfs interface anyways. */ + base = gc->base; if (base < 0) { base = gpiochip_find_base(gc->ngpio); if (base < 0) { - ret = base; spin_unlock_irqrestore(&gpio_lock, flags); + ret = base; + base = 0; goto err_free_label; } /* @@ -816,6 +820,11 @@ err_remove_of_chip: err_free_gpiochip_mask: gpiochip_remove_pin_ranges(gc); gpiochip_free_valid_mask(gc); + if (gdev->dev.release) { + /* release() has been registered by gpiochip_setup_dev() */ + put_device(&gdev->dev); + goto err_print_message; + } err_remove_from_list: spin_lock_irqsave(&gpio_lock, flags); list_del(&gdev->list); @@ -829,13 +838,14 @@ err_free_dev_name: err_free_ida: ida_free(&gpio_ida, gdev->id); err_free_gdev: + kfree(gdev); +err_print_message: /* failures here can mean systems won't boot... */ if (ret != -EPROBE_DEFER) { pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__, - gdev->base, gdev->base + gdev->ngpio - 1, + base, base + (int)ngpios - 1, gc->label ? : "generic", ret); } - kfree(gdev); return ret; } EXPORT_SYMBOL_GPL(gpiochip_add_data_with_key); diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index ab9697f3b5f1..92efc4676df6 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -813,7 +813,13 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, num_buffers = max_t(unsigned int, *count, q->min_buffers_needed); num_buffers = min_t(unsigned int, num_buffers, VB2_MAX_FRAME); memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory value + * in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); set_queue_coherency(q, non_coherent_mem); /* @@ -823,22 +829,27 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Check that driver has set sane values */ - if (WARN_ON(!num_planes)) - return -EINVAL; + if (WARN_ON(!num_planes)) { + ret = -EINVAL; + goto error; + } for (i = 0; i < num_planes; i++) - if (WARN_ON(!plane_sizes[i])) - return -EINVAL; + if (WARN_ON(!plane_sizes[i])) { + ret = -EINVAL; + goto error; + } /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -879,7 +890,8 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -895,6 +907,12 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, q->waiting_for_buffers = !q->is_output; return 0; + +error: + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_core_reqbufs); @@ -906,6 +924,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; + bool no_previous_buffers = !q->num_buffers; int ret; if (q->num_buffers == VB2_MAX_FRAME) { @@ -913,13 +932,19 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, return -ENOBUFS; } - if (!q->num_buffers) { + if (no_previous_buffers) { if (q->waiting_in_dqbuf && *count) { dprintk(q, 1, "another dup()ped fd is waiting for a buffer\n"); return -EBUSY; } memset(q->alloc_devs, 0, sizeof(q->alloc_devs)); + /* + * Set this now to ensure that drivers see the correct q->memory + * value in the queue_setup op. + */ + mutex_lock(&q->mmap_lock); q->memory = memory; + mutex_unlock(&q->mmap_lock); q->waiting_for_buffers = !q->is_output; set_queue_coherency(q, non_coherent_mem); } else { @@ -945,14 +970,15 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, ret = call_qop(q, queue_setup, q, &num_buffers, &num_planes, plane_sizes, q->alloc_devs); if (ret) - return ret; + goto error; /* Finally, allocate buffers and video memory */ allocated_buffers = __vb2_queue_alloc(q, memory, num_buffers, num_planes, plane_sizes); if (allocated_buffers == 0) { dprintk(q, 1, "memory allocation failed\n"); - return -ENOMEM; + ret = -ENOMEM; + goto error; } /* @@ -983,7 +1009,8 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, if (ret < 0) { /* * Note: __vb2_queue_free() will subtract 'allocated_buffers' - * from q->num_buffers. + * from q->num_buffers and it will reset q->memory to + * VB2_MEMORY_UNKNOWN. */ __vb2_queue_free(q, allocated_buffers); mutex_unlock(&q->mmap_lock); @@ -998,6 +1025,14 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, *count = allocated_buffers; return 0; + +error: + if (no_previous_buffers) { + mutex_lock(&q->mmap_lock); + q->memory = VB2_MEMORY_UNKNOWN; + mutex_unlock(&q->mmap_lock); + } + return ret; } EXPORT_SYMBOL_GPL(vb2_core_create_bufs); @@ -2165,6 +2200,22 @@ static int __find_plane_by_offset(struct vb2_queue *q, unsigned long off, unsigned int buffer, plane; /* + * Sanity checks to ensure the lock is held, MEMORY_MMAP is + * used and fileio isn't active. + */ + lockdep_assert_held(&q->mmap_lock); + + if (q->memory != VB2_MEMORY_MMAP) { + dprintk(q, 1, "queue is not currently set up for mmap\n"); + return -EINVAL; + } + + if (vb2_fileio_is_active(q)) { + dprintk(q, 1, "file io in progress\n"); + return -EBUSY; + } + + /* * Go over all buffers and their planes, comparing the given offset * with an offset assigned to each plane. If a match is found, * return its buffer and plane numbers. @@ -2265,11 +2316,6 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) int ret; unsigned long length; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } - /* * Check memory area access mode. */ @@ -2291,14 +2337,9 @@ int vb2_mmap(struct vb2_queue *q, struct vm_area_struct *vma) mutex_lock(&q->mmap_lock); - if (vb2_fileio_is_active(q)) { - dprintk(q, 1, "mmap: file io in progress\n"); - ret = -EBUSY; - goto unlock; - } - /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) @@ -2351,22 +2392,25 @@ unsigned long vb2_get_unmapped_area(struct vb2_queue *q, void *vaddr; int ret; - if (q->memory != VB2_MEMORY_MMAP) { - dprintk(q, 1, "queue is not currently set up for mmap\n"); - return -EINVAL; - } + mutex_lock(&q->mmap_lock); /* - * Find the plane corresponding to the offset passed by userspace. + * Find the plane corresponding to the offset passed by userspace. This + * will return an error if not MEMORY_MMAP or file I/O is in progress. */ ret = __find_plane_by_offset(q, off, &buffer, &plane); if (ret) - return ret; + goto unlock; vb = q->bufs[buffer]; vaddr = vb2_plane_vaddr(vb, plane); + mutex_unlock(&q->mmap_lock); return vaddr ? (unsigned long)vaddr : -EINVAL; + +unlock: + mutex_unlock(&q->mmap_lock); + return ret; } EXPORT_SYMBOL_GPL(vb2_get_unmapped_area); #endif diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index 1545cbee77a4..3dbfc8a6924e 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -386,7 +386,7 @@ int xenvif_dealloc_kthread(void *data); irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data); bool xenvif_have_rx_work(struct xenvif_queue *queue, bool test_kthread); -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); void xenvif_carrier_on(struct xenvif *vif); diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index 650fa180220f..f3f2c07423a6 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -254,14 +254,16 @@ xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE) skb_clear_hash(skb); - xenvif_rx_queue_tail(queue, skb); + if (!xenvif_rx_queue_tail(queue, skb)) + goto drop; + xenvif_kick_thread(queue); return NETDEV_TX_OK; drop: vif->dev->stats.tx_dropped++; - dev_kfree_skb(skb); + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 3d2081bbbc86..bf627af723bf 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -332,10 +332,13 @@ static int xenvif_count_requests(struct xenvif_queue *queue, struct xenvif_tx_cb { - u16 pending_idx; + u16 copy_pending_idx[XEN_NETBK_LEGACY_SLOTS_MAX + 1]; + u8 copy_count; }; #define XENVIF_TX_CB(skb) ((struct xenvif_tx_cb *)(skb)->cb) +#define copy_pending_idx(skb, i) (XENVIF_TX_CB(skb)->copy_pending_idx[i]) +#define copy_count(skb) (XENVIF_TX_CB(skb)->copy_count) static inline void xenvif_tx_create_map_op(struct xenvif_queue *queue, u16 pending_idx, @@ -370,31 +373,93 @@ static inline struct sk_buff *xenvif_alloc_skb(unsigned int size) return skb; } -static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue, - struct sk_buff *skb, - struct xen_netif_tx_request *txp, - struct gnttab_map_grant_ref *gop, - unsigned int frag_overflow, - struct sk_buff *nskb) +static void xenvif_get_requests(struct xenvif_queue *queue, + struct sk_buff *skb, + struct xen_netif_tx_request *first, + struct xen_netif_tx_request *txfrags, + unsigned *copy_ops, + unsigned *map_ops, + unsigned int frag_overflow, + struct sk_buff *nskb, + unsigned int extra_count, + unsigned int data_len) { struct skb_shared_info *shinfo = skb_shinfo(skb); skb_frag_t *frags = shinfo->frags; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; - int start; + u16 pending_idx; pending_ring_idx_t index; unsigned int nr_slots; + struct gnttab_copy *cop = queue->tx_copy_ops + *copy_ops; + struct gnttab_map_grant_ref *gop = queue->tx_map_ops + *map_ops; + struct xen_netif_tx_request *txp = first; + + nr_slots = shinfo->nr_frags + 1; + + copy_count(skb) = 0; + + /* Create copy ops for exactly data_len bytes into the skb head. */ + __skb_put(skb, data_len); + while (data_len > 0) { + int amount = data_len > txp->size ? txp->size : data_len; + + cop->source.u.ref = txp->gref; + cop->source.domid = queue->vif->domid; + cop->source.offset = txp->offset; + + cop->dest.domid = DOMID_SELF; + cop->dest.offset = (offset_in_page(skb->data + + skb_headlen(skb) - + data_len)) & ~XEN_PAGE_MASK; + cop->dest.u.gmfn = virt_to_gfn(skb->data + skb_headlen(skb) + - data_len); + + cop->len = amount; + cop->flags = GNTCOPY_source_gref; - nr_slots = shinfo->nr_frags; + index = pending_index(queue->pending_cons); + pending_idx = queue->pending_ring[index]; + callback_param(queue, pending_idx).ctx = NULL; + copy_pending_idx(skb, copy_count(skb)) = pending_idx; + copy_count(skb)++; + + cop++; + data_len -= amount; - /* Skip first skb fragment if it is on same page as header fragment. */ - start = (frag_get_pending_idx(&shinfo->frags[0]) == pending_idx); + if (amount == txp->size) { + /* The copy op covered the full tx_request */ + + memcpy(&queue->pending_tx_info[pending_idx].req, + txp, sizeof(*txp)); + queue->pending_tx_info[pending_idx].extra_count = + (txp == first) ? extra_count : 0; + + if (txp == first) + txp = txfrags; + else + txp++; + queue->pending_cons++; + nr_slots--; + } else { + /* The copy op partially covered the tx_request. + * The remainder will be mapped. + */ + txp->offset += amount; + txp->size -= amount; + } + } - for (shinfo->nr_frags = start; shinfo->nr_frags < nr_slots; - shinfo->nr_frags++, txp++, gop++) { + for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; + shinfo->nr_frags++, gop++) { index = pending_index(queue->pending_cons++); pending_idx = queue->pending_ring[index]; - xenvif_tx_create_map_op(queue, pending_idx, txp, 0, gop); + xenvif_tx_create_map_op(queue, pending_idx, txp, + txp == first ? extra_count : 0, gop); frag_set_pending_idx(&frags[shinfo->nr_frags], pending_idx); + + if (txp == first) + txp = txfrags; + else + txp++; } if (frag_overflow) { @@ -415,7 +480,8 @@ static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *que skb_shinfo(skb)->frag_list = nskb; } - return gop; + (*copy_ops) = cop - queue->tx_copy_ops; + (*map_ops) = gop - queue->tx_map_ops; } static inline void xenvif_grant_handle_set(struct xenvif_queue *queue, @@ -451,7 +517,7 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct gnttab_copy **gopp_copy) { struct gnttab_map_grant_ref *gop_map = *gopp_map; - u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx; + u16 pending_idx; /* This always points to the shinfo of the skb being checked, which * could be either the first or the one on the frag_list */ @@ -462,24 +528,37 @@ static int xenvif_tx_check_gop(struct xenvif_queue *queue, struct skb_shared_info *first_shinfo = NULL; int nr_frags = shinfo->nr_frags; const bool sharedslot = nr_frags && - frag_get_pending_idx(&shinfo->frags[0]) == pending_idx; - int i, err; + frag_get_pending_idx(&shinfo->frags[0]) == + copy_pending_idx(skb, copy_count(skb) - 1); + int i, err = 0; - /* Check status of header. */ - err = (*gopp_copy)->status; - if (unlikely(err)) { - if (net_ratelimit()) - netdev_dbg(queue->vif->dev, - "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", - (*gopp_copy)->status, - pending_idx, - (*gopp_copy)->source.u.ref); - /* The first frag might still have this slot mapped */ - if (!sharedslot) - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_ERROR); + for (i = 0; i < copy_count(skb); i++) { + int newerr; + + /* Check status of header. */ + pending_idx = copy_pending_idx(skb, i); + + newerr = (*gopp_copy)->status; + if (likely(!newerr)) { + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_OKAY); + } else { + err = newerr; + if (net_ratelimit()) + netdev_dbg(queue->vif->dev, + "Grant copy of header failed! status: %d pending_idx: %u ref: %u\n", + (*gopp_copy)->status, + pending_idx, + (*gopp_copy)->source.u.ref); + /* The first frag might still have this slot mapped */ + if (i < copy_count(skb) - 1 || !sharedslot) + xenvif_idx_release(queue, pending_idx, + XEN_NETIF_RSP_ERROR); + } + (*gopp_copy)++; } - (*gopp_copy)++; check_frags: for (i = 0; i < nr_frags; i++, gop_map++) { @@ -526,14 +605,6 @@ check_frags: if (err) continue; - /* First error: if the header haven't shared a slot with the - * first frag, release it as well. - */ - if (!sharedslot) - xenvif_idx_release(queue, - XENVIF_TX_CB(skb)->pending_idx, - XEN_NETIF_RSP_OKAY); - /* Invalidate preceding fragments of this skb. */ for (j = 0; j < i; j++) { pending_idx = frag_get_pending_idx(&shinfo->frags[j]); @@ -803,7 +874,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, unsigned *copy_ops, unsigned *map_ops) { - struct gnttab_map_grant_ref *gop = queue->tx_map_ops; struct sk_buff *skb, *nskb; int ret; unsigned int frag_overflow; @@ -885,8 +955,12 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, continue; } + data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN) ? + XEN_NETBACK_TX_COPY_LEN : txreq.size; + ret = xenvif_count_requests(queue, &txreq, extra_count, txfrags, work_to_do); + if (unlikely(ret < 0)) break; @@ -912,9 +986,8 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, index = pending_index(queue->pending_cons); pending_idx = queue->pending_ring[index]; - data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN && - ret < XEN_NETBK_LEGACY_SLOTS_MAX) ? - XEN_NETBACK_TX_COPY_LEN : txreq.size; + if (ret >= XEN_NETBK_LEGACY_SLOTS_MAX - 1 && data_len < txreq.size) + data_len = txreq.size; skb = xenvif_alloc_skb(data_len); if (unlikely(skb == NULL)) { @@ -925,8 +998,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, } skb_shinfo(skb)->nr_frags = ret; - if (data_len < txreq.size) - skb_shinfo(skb)->nr_frags++; /* At this point shinfo->nr_frags is in fact the number of * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX. */ @@ -988,54 +1059,19 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue, type); } - XENVIF_TX_CB(skb)->pending_idx = pending_idx; - - __skb_put(skb, data_len); - queue->tx_copy_ops[*copy_ops].source.u.ref = txreq.gref; - queue->tx_copy_ops[*copy_ops].source.domid = queue->vif->domid; - queue->tx_copy_ops[*copy_ops].source.offset = txreq.offset; - - queue->tx_copy_ops[*copy_ops].dest.u.gmfn = - virt_to_gfn(skb->data); - queue->tx_copy_ops[*copy_ops].dest.domid = DOMID_SELF; - queue->tx_copy_ops[*copy_ops].dest.offset = - offset_in_page(skb->data) & ~XEN_PAGE_MASK; - - queue->tx_copy_ops[*copy_ops].len = data_len; - queue->tx_copy_ops[*copy_ops].flags = GNTCOPY_source_gref; - - (*copy_ops)++; - - if (data_len < txreq.size) { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - pending_idx); - xenvif_tx_create_map_op(queue, pending_idx, &txreq, - extra_count, gop); - gop++; - } else { - frag_set_pending_idx(&skb_shinfo(skb)->frags[0], - INVALID_PENDING_IDX); - memcpy(&queue->pending_tx_info[pending_idx].req, - &txreq, sizeof(txreq)); - queue->pending_tx_info[pending_idx].extra_count = - extra_count; - } - - queue->pending_cons++; - - gop = xenvif_get_requests(queue, skb, txfrags, gop, - frag_overflow, nskb); + xenvif_get_requests(queue, skb, &txreq, txfrags, copy_ops, + map_ops, frag_overflow, nskb, extra_count, + data_len); __skb_queue_tail(&queue->tx_queue, skb); queue->tx.req_cons = idx; - if (((gop-queue->tx_map_ops) >= ARRAY_SIZE(queue->tx_map_ops)) || + if ((*map_ops >= ARRAY_SIZE(queue->tx_map_ops)) || (*copy_ops >= ARRAY_SIZE(queue->tx_copy_ops))) break; } - (*map_ops) = gop - queue->tx_map_ops; return; } @@ -1114,9 +1150,8 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) while ((skb = __skb_dequeue(&queue->tx_queue)) != NULL) { struct xen_netif_tx_request *txp; u16 pending_idx; - unsigned data_len; - pending_idx = XENVIF_TX_CB(skb)->pending_idx; + pending_idx = copy_pending_idx(skb, 0); txp = &queue->pending_tx_info[pending_idx].req; /* Check the remap error code. */ @@ -1135,18 +1170,6 @@ static int xenvif_tx_submit(struct xenvif_queue *queue) continue; } - data_len = skb->len; - callback_param(queue, pending_idx).ctx = NULL; - if (data_len < txp->size) { - /* Append the packet payload as a fragment. */ - txp->offset += data_len; - txp->size -= data_len; - } else { - /* Schedule a response immediately. */ - xenvif_idx_release(queue, pending_idx, - XEN_NETIF_RSP_OKAY); - } - if (txp->flags & XEN_NETTXF_csum_blank) skb->ip_summed = CHECKSUM_PARTIAL; else if (txp->flags & XEN_NETTXF_data_validated) @@ -1332,7 +1355,7 @@ static inline void xenvif_tx_dealloc_action(struct xenvif_queue *queue) /* Called after netfront has transmitted */ int xenvif_tx_action(struct xenvif_queue *queue, int budget) { - unsigned nr_mops, nr_cops = 0; + unsigned nr_mops = 0, nr_cops = 0; int work_done, ret; if (unlikely(!tx_work_todo(queue))) diff --git a/drivers/net/xen-netback/rx.c b/drivers/net/xen-netback/rx.c index 932762177110..0ba754ebc5ba 100644 --- a/drivers/net/xen-netback/rx.c +++ b/drivers/net/xen-netback/rx.c @@ -82,9 +82,10 @@ static bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue) return false; } -void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +bool xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) { unsigned long flags; + bool ret = true; spin_lock_irqsave(&queue->rx_queue.lock, flags); @@ -92,8 +93,7 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) struct net_device *dev = queue->vif->dev; netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); - kfree_skb(skb); - queue->vif->dev->stats.rx_dropped++; + ret = false; } else { if (skb_queue_empty(&queue->rx_queue)) xenvif_update_needed_slots(queue, skb); @@ -104,6 +104,8 @@ void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) } spin_unlock_irqrestore(&queue->rx_queue.lock, flags); + + return ret; } static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) diff --git a/drivers/platform/x86/amd/pmc.c b/drivers/platform/x86/amd/pmc.c index ef4ae977b8e0..439d282aafd1 100644 --- a/drivers/platform/x86/amd/pmc.c +++ b/drivers/platform/x86/amd/pmc.c @@ -739,8 +739,14 @@ static void amd_pmc_s2idle_prepare(void) static void amd_pmc_s2idle_check(void) { struct amd_pmc_dev *pdev = &pmc; + struct smu_metrics table; int rc; + /* CZN: Ensure that future s0i3 entry attempts at least 10ms passed */ + if (pdev->cpu_id == AMD_CPU_ID_CZN && !get_metrics_table(pdev, &table) && + table.s0i3_last_entry_status) + usleep_range(10000, 20000); + /* Dump the IdleMask before we add to the STB */ amd_pmc_idlemask_read(pdev, pdev->dev, NULL); diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c index 451d8a077e12..bce2492186d0 100644 --- a/fs/fscache/cookie.c +++ b/fs/fscache/cookie.c @@ -605,6 +605,14 @@ again: set_bit(FSCACHE_COOKIE_DO_PREP_TO_WRITE, &cookie->flags); queue = true; } + /* + * We could race with cookie_lru which may set LRU_DISCARD bit + * but has yet to run the cookie state machine. If this happens + * and another thread tries to use the cookie, clear LRU_DISCARD + * so we don't end up withdrawing the cookie while in use. + */ + if (test_and_clear_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) + fscache_see_cookie(cookie, fscache_cookie_see_lru_discard_clear); break; case FSCACHE_COOKIE_STATE_FAILED: diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index 528bd44b59e2..2b7d077de7ef 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -68,6 +68,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/include/trace/events/fscache.h b/include/trace/events/fscache.h index c078c48a8e6d..a6190aa1b406 100644 --- a/include/trace/events/fscache.h +++ b/include/trace/events/fscache.h @@ -66,6 +66,7 @@ enum fscache_cookie_trace { fscache_cookie_put_work, fscache_cookie_see_active, fscache_cookie_see_lru_discard, + fscache_cookie_see_lru_discard_clear, fscache_cookie_see_lru_do_one, fscache_cookie_see_relinquish, fscache_cookie_see_withdraw, @@ -149,6 +150,7 @@ enum fscache_access_trace { EM(fscache_cookie_put_work, "PQ work ") \ EM(fscache_cookie_see_active, "- activ") \ EM(fscache_cookie_see_lru_discard, "- x-lru") \ + EM(fscache_cookie_see_lru_discard_clear,"- lrudc") \ EM(fscache_cookie_see_lru_do_one, "- lrudo") \ EM(fscache_cookie_see_relinquish, "- x-rlq") \ EM(fscache_cookie_see_withdraw, "- x-wth") \ diff --git a/ipc/sem.c b/ipc/sem.c index c8496f98b139..00f88aa01ac5 100644 --- a/ipc/sem.c +++ b/ipc/sem.c @@ -2179,14 +2179,15 @@ long __do_semtimedop(int semid, struct sembuf *sops, * scenarios where we were awakened externally, during the * window between wake_q_add() and wake_up_q(). */ + rcu_read_lock(); error = READ_ONCE(queue.status); if (error != -EINTR) { /* see SEM_BARRIER_2 for purpose/pairing */ smp_acquire__after_ctrl_dep(); + rcu_read_unlock(); goto out; } - rcu_read_lock(); locknum = sem_lock(sma, sops, nsops); if (!ipc_valid_object(&sma->sem_perm)) diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index fd4020835ec6..367b0a42ada9 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -167,7 +167,6 @@ struct cgroup_mgctx { extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 188c305aeb8b..c6d9dec11b74 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -267,13 +267,14 @@ int proc_dostring(struct ctl_table *table, int write, ppos); } -static size_t proc_skip_spaces(char **buf) +static void proc_skip_spaces(char **buf, size_t *size) { - size_t ret; - char *tmp = skip_spaces(*buf); - ret = tmp - *buf; - *buf = tmp; - return ret; + while (*size) { + if (!isspace(**buf)) + break; + (*size)--; + (*buf)++; + } } static void proc_skip_char(char **buf, size_t *size, const char v) @@ -342,13 +343,12 @@ static int proc_get_long(char **buf, size_t *size, unsigned long *val, bool *neg, const char *perm_tr, unsigned perm_tr_len, char *tr) { - int len; char *p, tmp[TMPBUFLEN]; + ssize_t len = *size; - if (!*size) + if (len <= 0) return -EINVAL; - len = *size; if (len > TMPBUFLEN - 1) len = TMPBUFLEN - 1; @@ -521,7 +521,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, bool neg; if (write) { - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -548,7 +548,7 @@ static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; @@ -590,7 +590,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, if (left > PAGE_SIZE - 1) left = PAGE_SIZE - 1; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) { err = -EINVAL; goto out_free; @@ -610,7 +610,7 @@ static int do_proc_douintvec_w(unsigned int *tbl_data, } if (!err && left) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); out_free: if (err) @@ -1075,7 +1075,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (write) { bool neg; - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (!left) break; @@ -1104,7 +1104,7 @@ static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, if (!write && !first && left && !err) proc_put_char(&buffer, &left, '\n'); if (write && !err) - left -= proc_skip_spaces(&p); + proc_skip_spaces(&p, &left); if (write && first) return err ? : -EINVAL; *lenp -= left; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a1a35c12635e..266a1ab05434 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4832,6 +4832,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4886,6 +4887,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, goto out_put_cfile; /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows * about these events. The following is crude but the whole thing @@ -4893,7 +4904,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4917,7 +4928,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) |