diff --git a/Makefile b/Makefile index db13b13cdcc2..77deaa395d69 100644 --- a/Makefile +++ b/Makefile @@ -1,6 +1,6 @@ VERSION = 4 PATCHLEVEL = 9 -SUBLEVEL = 84 +SUBLEVEL = 85 EXTRAVERSION = NAME = Roaring Lionus diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index c743d1fd8286..5963be2e05f0 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -50,7 +50,7 @@ static const char *handler[]= { "Error" }; -int show_unhandled_signals = 1; +int show_unhandled_signals = 0; /* * Dump out the contents of some kernel memory nicely... diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index db5009ce065a..8d7e4d48db0d 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -176,13 +176,26 @@ GLOBAL(entry_SYSCALL_64_after_swapgs) pushq %r8 /* pt_regs->r8 */ pushq %r9 /* pt_regs->r9 */ pushq %r10 /* pt_regs->r10 */ + /* + * Clear extra registers that a speculation attack might + * otherwise want to exploit. Interleave XOR with PUSH + * for better uop scheduling: + */ + xorq %r10, %r10 /* nospec r10 */ pushq %r11 /* pt_regs->r11 */ + xorq %r11, %r11 /* nospec r11 */ pushq %rbx /* pt_regs->rbx */ + xorl %ebx, %ebx /* nospec rbx */ pushq %rbp /* pt_regs->rbp */ + xorl %ebp, %ebp /* nospec rbp */ pushq %r12 /* pt_regs->r12 */ + xorq %r12, %r12 /* nospec r12 */ pushq %r13 /* pt_regs->r13 */ + xorq %r13, %r13 /* nospec r13 */ pushq %r14 /* pt_regs->r14 */ + xorq %r14, %r14 /* nospec r14 */ pushq %r15 /* pt_regs->r15 */ + xorq %r15, %r15 /* nospec r15 */ /* IRQs are off. */ movq %rsp, %rdi diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c index 28c04123b6dd..842ca3cab6b3 100644 --- a/arch/x86/oprofile/nmi_int.c +++ b/arch/x86/oprofile/nmi_int.c @@ -472,7 +472,7 @@ static int nmi_setup(void) goto fail; for_each_possible_cpu(cpu) { - if (!cpu) + if (!IS_ENABLED(CONFIG_SMP) || !cpu) continue; memcpy(per_cpu(cpu_msrs, cpu).counters, diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 80e4cfb2471a..d5abdf8878fe 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -77,19 +77,75 @@ void __init zones_init(void) free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL); } +#ifdef CONFIG_HIGHMEM +static void __init free_area_high(unsigned long pfn, unsigned long end) +{ + for (; pfn < end; pfn++) + free_highmem_page(pfn_to_page(pfn)); +} + +static void __init free_highpages(void) +{ + unsigned long max_low = max_low_pfn; + struct memblock_region *mem, *res; + + reset_all_zones_managed_pages(); + /* set highmem page free */ + for_each_memblock(memory, mem) { + unsigned long start = memblock_region_memory_base_pfn(mem); + unsigned long end = memblock_region_memory_end_pfn(mem); + + /* Ignore complete lowmem entries */ + if (end <= max_low) + continue; + + if (memblock_is_nomap(mem)) + continue; + + /* Truncate partial highmem entries */ + if (start < max_low) + start = max_low; + + /* Find and exclude any reserved regions */ + for_each_memblock(reserved, res) { + unsigned long res_start, res_end; + + res_start = memblock_region_reserved_base_pfn(res); + res_end = memblock_region_reserved_end_pfn(res); + + if (res_end < start) + continue; + if (res_start < start) + res_start = start; + if (res_start > end) + res_start = end; + if (res_end > end) + res_end = end; + if (res_start != start) + free_area_high(start, res_start); + start = res_end; + if (start == end) + break; + } + + /* And now free anything which remains */ + if (start < end) + free_area_high(start, end); + } +} +#else +static void __init free_highpages(void) +{ +} +#endif + /* * Initialize memory pages. */ void __init mem_init(void) { -#ifdef CONFIG_HIGHMEM - unsigned long tmp; - - reset_all_zones_managed_pages(); - for (tmp = max_low_pfn; tmp < max_pfn; tmp++) - free_highmem_page(pfn_to_page(tmp)); -#endif + free_highpages(); max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); diff --git a/crypto/asymmetric_keys/pkcs7_verify.c b/crypto/asymmetric_keys/pkcs7_verify.c index 5a37962d2199..df1bde273bba 100644 --- a/crypto/asymmetric_keys/pkcs7_verify.c +++ b/crypto/asymmetric_keys/pkcs7_verify.c @@ -261,7 +261,7 @@ static int pkcs7_verify_sig_chain(struct pkcs7_message *pkcs7, sinfo->index); return 0; } - ret = public_key_verify_signature(p->pub, p->sig); + ret = public_key_verify_signature(p->pub, x509->sig); if (ret < 0) return ret; x509->signer = p; diff --git a/crypto/asymmetric_keys/public_key.c b/crypto/asymmetric_keys/public_key.c index 4955eb66e361..8525fe474abd 100644 --- a/crypto/asymmetric_keys/public_key.c +++ b/crypto/asymmetric_keys/public_key.c @@ -93,9 +93,11 @@ int public_key_verify_signature(const struct public_key *pkey, BUG_ON(!pkey); BUG_ON(!sig); - BUG_ON(!sig->digest); BUG_ON(!sig->s); + if (!sig->digest) + return -ENOPKG; + alg_name = sig->pkey_algo; if (strcmp(sig->pkey_algo, "rsa") == 0) { /* The data wangled by the RSA algorithm is typically padded diff --git a/crypto/asymmetric_keys/restrict.c b/crypto/asymmetric_keys/restrict.c index 19d1afb9890f..09b1374dc619 100644 --- a/crypto/asymmetric_keys/restrict.c +++ b/crypto/asymmetric_keys/restrict.c @@ -66,8 +66,9 @@ __setup("ca_keys=", ca_keys_setup); * * Returns 0 if the new certificate was accepted, -ENOKEY if we couldn't find a * matching parent certificate in the trusted list, -EKEYREJECTED if the - * signature check fails or the key is blacklisted and some other error if - * there is a matching certificate but the signature check cannot be performed. + * signature check fails or the key is blacklisted, -ENOPKG if the signature + * uses unsupported crypto, or some other error if there is a matching + * certificate but the signature check cannot be performed. */ int restrict_link_by_signature(struct key *trust_keyring, const struct key_type *type, @@ -86,6 +87,8 @@ int restrict_link_by_signature(struct key *trust_keyring, return -EOPNOTSUPP; sig = payload->data[asym_auth]; + if (!sig) + return -ENOPKG; if (!sig->auth_ids[0] && !sig->auth_ids[1]) return -ENOKEY; diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 3b6ac80b2127..49199bd2ab93 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -2628,8 +2628,10 @@ static unsigned int binder_poll(struct file *filp, binder_lock(__func__); thread = binder_get_thread(proc); - if (!thread) + if (!thread) { + binder_unlock(__func__); return POLLERR; + } wait_for_proc_work = thread->transaction_stack == NULL && list_empty(&thread->todo) && thread->return_error == BR_OK; diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c index 40be3747724d..473b44c008dd 100644 --- a/drivers/dax/dax.c +++ b/drivers/dax/dax.c @@ -453,9 +453,21 @@ static int dax_dev_pmd_fault(struct vm_area_struct *vma, unsigned long addr, return rc; } +static int dax_dev_split(struct vm_area_struct *vma, unsigned long addr) +{ + struct file *filp = vma->vm_file; + struct dax_dev *dax_dev = filp->private_data; + struct dax_region *dax_region = dax_dev->region; + + if (!IS_ALIGNED(addr, dax_region->align)) + return -EINVAL; + return 0; +} + static const struct vm_operations_struct dax_dev_vm_ops = { .fault = dax_dev_fault, .pmd_fault = dax_dev_pmd_fault, + .split = dax_dev_split, }; static int dax_mmap(struct file *filp, struct vm_area_struct *vma) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c index 6c343a933182..0e8f8972a160 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c @@ -14,6 +14,16 @@ #include "amd_acpi.h" +#define AMDGPU_PX_QUIRK_FORCE_ATPX (1 << 0) + +struct amdgpu_px_quirk { + u32 chip_vendor; + u32 chip_device; + u32 subsys_vendor; + u32 subsys_device; + u32 px_quirk_flags; +}; + struct amdgpu_atpx_functions { bool px_params; bool power_cntl; @@ -35,6 +45,7 @@ struct amdgpu_atpx { static struct amdgpu_atpx_priv { bool atpx_detected; bool bridge_pm_usable; + unsigned int quirks; /* handle for device - and atpx */ acpi_handle dhandle; acpi_handle other_handle; @@ -205,13 +216,19 @@ static int amdgpu_atpx_validate(struct amdgpu_atpx *atpx) atpx->is_hybrid = false; if (valid_bits & ATPX_MS_HYBRID_GFX_SUPPORTED) { - printk("ATPX Hybrid Graphics\n"); - /* - * Disable legacy PM methods only when pcie port PM is usable, - * otherwise the device might fail to power off or power on. - */ - atpx->functions.power_cntl = !amdgpu_atpx_priv.bridge_pm_usable; - atpx->is_hybrid = true; + if (amdgpu_atpx_priv.quirks & AMDGPU_PX_QUIRK_FORCE_ATPX) { + printk("ATPX Hybrid Graphics, forcing to ATPX\n"); + atpx->functions.power_cntl = true; + atpx->is_hybrid = false; + } else { + printk("ATPX Hybrid Graphics\n"); + /* + * Disable legacy PM methods only when pcie port PM is usable, + * otherwise the device might fail to power off or power on. + */ + atpx->functions.power_cntl = !amdgpu_atpx_priv.bridge_pm_usable; + atpx->is_hybrid = true; + } } atpx->dgpu_req_power_for_displays = false; @@ -547,6 +564,31 @@ static const struct vga_switcheroo_handler amdgpu_atpx_handler = { .get_client_id = amdgpu_atpx_get_client_id, }; +static const struct amdgpu_px_quirk amdgpu_px_quirk_list[] = { + /* HG _PR3 doesn't seem to work on this A+A weston board */ + { 0x1002, 0x6900, 0x1002, 0x0124, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1028, 0x0812, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0x1002, 0x6900, 0x1028, 0x0813, AMDGPU_PX_QUIRK_FORCE_ATPX }, + { 0, 0, 0, 0, 0 }, +}; + +static void amdgpu_atpx_get_quirks(struct pci_dev *pdev) +{ + const struct amdgpu_px_quirk *p = amdgpu_px_quirk_list; + + /* Apply PX quirks */ + while (p && p->chip_device != 0) { + if (pdev->vendor == p->chip_vendor && + pdev->device == p->chip_device && + pdev->subsystem_vendor == p->subsys_vendor && + pdev->subsystem_device == p->subsys_device) { + amdgpu_atpx_priv.quirks |= p->px_quirk_flags; + break; + } + ++p; + } +} + /** * amdgpu_atpx_detect - detect whether we have PX * @@ -570,6 +612,7 @@ static bool amdgpu_atpx_detect(void) parent_pdev = pci_upstream_bridge(pdev); d3_supported |= parent_pdev && parent_pdev->bridge_d3; + amdgpu_atpx_get_quirks(pdev); } while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_OTHER << 8, pdev)) != NULL) { @@ -579,6 +622,7 @@ static bool amdgpu_atpx_detect(void) parent_pdev = pci_upstream_bridge(pdev); d3_supported |= parent_pdev && parent_pdev->bridge_d3; + amdgpu_atpx_get_quirks(pdev); } if (has_atpx && vga_count == 2) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index ce9797b6f9c7..50f18f666d67 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1678,8 +1678,6 @@ int amdgpu_device_init(struct amdgpu_device *adev, * ignore it */ vga_client_register(adev->pdev, adev, NULL, amdgpu_vga_set_decode); - if (amdgpu_runtime_pm == 1) - runtime = true; if (amdgpu_device_is_px(ddev)) runtime = true; vga_switcheroo_register_client(adev->pdev, &amdgpu_switcheroo_ops, runtime); diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c index 4cb347e88cf0..002862be2df6 100644 --- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c +++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c @@ -3507,6 +3507,11 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev, max_sclk = 75000; max_mclk = 80000; } + if ((adev->pdev->revision == 0xC3) || + (adev->pdev->device == 0x6665)) { + max_sclk = 60000; + max_mclk = 80000; + } } else if (adev->asic_type == CHIP_OLAND) { if ((adev->pdev->revision == 0xC7) || (adev->pdev->revision == 0x80) || diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c index 0151ed2de770..c6b281aa762f 100644 --- a/drivers/gpu/drm/drm_edid.c +++ b/drivers/gpu/drm/drm_edid.c @@ -107,6 +107,9 @@ static const struct edid_quirk { /* AEO model 0 reports 8 bpc, but is a 6 bpc panel */ { "AEO", 0, EDID_QUIRK_FORCE_6BPC }, + /* CPT panel of Asus UX303LA reports 8 bpc, but is a 6 bpc panel */ + { "CPT", 0x17df, EDID_QUIRK_FORCE_6BPC }, + /* Belinea 10 15 55 */ { "MAX", 1516, EDID_QUIRK_PREFER_LARGE_60 }, { "MAX", 0x77e, EDID_QUIRK_PREFER_LARGE_60 }, diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index 03cac5731afc..49406e106cee 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -2443,6 +2443,9 @@ static const struct hid_device_id hid_ignore_list[] = { { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTIME) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYPH) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_POWERANALYSERCASSY) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY) }, + { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MACHINETESTCASSY) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_JWM) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_DMMP) }, { HID_USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_UMIP) }, diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index 244b97c1b74e..9347b37a1303 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -608,6 +608,9 @@ #define USB_DEVICE_ID_LD_MICROCASSYTIME 0x1033 #define USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE 0x1035 #define USB_DEVICE_ID_LD_MICROCASSYPH 0x1038 +#define USB_DEVICE_ID_LD_POWERANALYSERCASSY 0x1040 +#define USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY 0x1042 +#define USB_DEVICE_ID_LD_MACHINETESTCASSY 0x1043 #define USB_DEVICE_ID_LD_JWM 0x1080 #define USB_DEVICE_ID_LD_DMMP 0x1081 #define USB_DEVICE_ID_LD_UMIP 0x1090 diff --git a/drivers/iio/imu/adis_trigger.c b/drivers/iio/imu/adis_trigger.c index f53e9a803a0e..93b99bd93738 100644 --- a/drivers/iio/imu/adis_trigger.c +++ b/drivers/iio/imu/adis_trigger.c @@ -47,6 +47,10 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) if (adis->trig == NULL) return -ENOMEM; + adis->trig->dev.parent = &adis->spi->dev; + adis->trig->ops = &adis_trigger_ops; + iio_trigger_set_drvdata(adis->trig, adis); + ret = request_irq(adis->spi->irq, &iio_trigger_generic_data_rdy_poll, IRQF_TRIGGER_RISING, @@ -55,9 +59,6 @@ int adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev) if (ret) goto error_free_trig; - adis->trig->dev.parent = &adis->spi->dev; - adis->trig->ops = &adis_trigger_ops; - iio_trigger_set_drvdata(adis->trig, adis); ret = iio_trigger_register(adis->trig); indio_dev->trig = iio_trigger_get(adis->trig); diff --git a/drivers/iio/industrialio-buffer.c b/drivers/iio/industrialio-buffer.c index 158aaf44dd95..5d05c38c4ba9 100644 --- a/drivers/iio/industrialio-buffer.c +++ b/drivers/iio/industrialio-buffer.c @@ -174,7 +174,7 @@ unsigned int iio_buffer_poll(struct file *filp, struct iio_dev *indio_dev = filp->private_data; struct iio_buffer *rb = indio_dev->buffer; - if (!indio_dev->info) + if (!indio_dev->info || rb == NULL) return 0; poll_wait(filp, &rb->pollq, wait); diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index c22fde6207d1..8e973a2993a6 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -193,7 +193,7 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, sg_list_start = umem->sg_head.sgl; while (npages) { - ret = get_user_pages(cur_base, + ret = get_user_pages_longterm(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof (struct page *)), gup_flags, page_list, vma_list); diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 44b1104eb168..c5e921bf9130 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -735,12 +735,21 @@ static int verify_command_mask(struct ib_device *ib_dev, __u32 command) return -1; } +static bool verify_command_idx(u32 command, bool extended) +{ + if (extended) + return command < ARRAY_SIZE(uverbs_ex_cmd_table); + + return command < ARRAY_SIZE(uverbs_cmd_table); +} + static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, size_t count, loff_t *pos) { struct ib_uverbs_file *file = filp->private_data; struct ib_device *ib_dev; struct ib_uverbs_cmd_hdr hdr; + bool extended_command; __u32 command; __u32 flags; int srcu_key; @@ -770,6 +779,15 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, } command = hdr.command & IB_USER_VERBS_CMD_COMMAND_MASK; + flags = (hdr.command & + IB_USER_VERBS_CMD_FLAGS_MASK) >> IB_USER_VERBS_CMD_FLAGS_SHIFT; + + extended_command = flags & IB_USER_VERBS_CMD_FLAG_EXTENDED; + if (!verify_command_idx(command, extended_command)) { + ret = -EINVAL; + goto out; + } + if (verify_command_mask(ib_dev, command)) { ret = -EOPNOTSUPP; goto out; @@ -781,12 +799,8 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, goto out; } - flags = (hdr.command & - IB_USER_VERBS_CMD_FLAGS_MASK) >> IB_USER_VERBS_CMD_FLAGS_SHIFT; - if (!flags) { - if (command >= ARRAY_SIZE(uverbs_cmd_table) || - !uverbs_cmd_table[command]) { + if (!uverbs_cmd_table[command]) { ret = -EINVAL; goto out; } @@ -807,8 +821,7 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, struct ib_udata uhw; size_t written_count = count; - if (command >= ARRAY_SIZE(uverbs_ex_cmd_table) || - !uverbs_ex_cmd_table[command]) { + if (!uverbs_ex_cmd_table[command]) { ret = -ENOSYS; goto out; } diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c index a37576a1798d..fd4a78296b48 100644 --- a/drivers/irqchip/irq-gic-v3.c +++ b/drivers/irqchip/irq-gic-v3.c @@ -616,7 +616,7 @@ static void gic_raise_softirq(const struct cpumask *mask, unsigned int irq) * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ - smp_wmb(); + wmb(); for_each_cpu(cpu, mask) { unsigned long cluster_id = cpu_logical_map(cpu) & ~0xffUL; diff --git a/drivers/media/v4l2-core/videobuf-dma-sg.c b/drivers/media/v4l2-core/videobuf-dma-sg.c index 1db0af6c7f94..b6189a4958c5 100644 --- a/drivers/media/v4l2-core/videobuf-dma-sg.c +++ b/drivers/media/v4l2-core/videobuf-dma-sg.c @@ -185,12 +185,13 @@ static int videobuf_dma_init_user_locked(struct videobuf_dmabuf *dma, dprintk(1, "init user [0x%lx+0x%lx => %d pages]\n", data, size, dma->nr_pages); - err = get_user_pages(data & PAGE_MASK, dma->nr_pages, + err = get_user_pages_longterm(data & PAGE_MASK, dma->nr_pages, flags, dma->pages, NULL); if (err != dma->nr_pages) { dma->nr_pages = (err >= 0) ? err : 0; - dprintk(1, "get_user_pages: err=%d [%d]\n", err, dma->nr_pages); + dprintk(1, "get_user_pages_longterm: err=%d [%d]\n", err, + dma->nr_pages); return err < 0 ? err : -EINVAL; } return 0; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 9e073fb6870a..6fd3be69ff21 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -2596,7 +2596,6 @@ void t4_get_regs(struct adapter *adap, void *buf, size_t buf_size) } #define EEPROM_STAT_ADDR 0x7bfc -#define VPD_SIZE 0x800 #define VPD_BASE 0x400 #define VPD_BASE_OLD 0 #define VPD_LEN 1024 @@ -2634,15 +2633,6 @@ int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p) if (!vpd) return -ENOMEM; - /* We have two VPD data structures stored in the adapter VPD area. - * By default, Linux calculates the size of the VPD area by traversing - * the first VPD area at offset 0x0, so we need to tell the OS what - * our real VPD size is. - */ - ret = pci_set_vpd_size(adapter->pdev, VPD_SIZE); - if (ret < 0) - goto out; - /* Card information normally starts at VPD_BASE but early cards had * it at 0. */ diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c index 0392eb8a0dea..8311a93cabd8 100644 --- a/drivers/nvdimm/bus.c +++ b/drivers/nvdimm/bus.c @@ -812,16 +812,17 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, int read_only, unsigned int ioctl_cmd, unsigned long arg) { struct nvdimm_bus_descriptor *nd_desc = nvdimm_bus->nd_desc; - size_t buf_len = 0, in_len = 0, out_len = 0; static char out_env[ND_CMD_MAX_ENVELOPE]; static char in_env[ND_CMD_MAX_ENVELOPE]; const struct nd_cmd_desc *desc = NULL; unsigned int cmd = _IOC_NR(ioctl_cmd); void __user *p = (void __user *) arg; struct device *dev = &nvdimm_bus->dev; - struct nd_cmd_pkg pkg; const char *cmd_name, *dimm_name; + u32 in_len = 0, out_len = 0; unsigned long cmd_mask; + struct nd_cmd_pkg pkg; + u64 buf_len = 0; void *buf; int rc, i; @@ -882,7 +883,7 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, } if (cmd == ND_CMD_CALL) { - dev_dbg(dev, "%s:%s, idx: %llu, in: %zu, out: %zu, len %zu\n", + dev_dbg(dev, "%s:%s, idx: %llu, in: %u, out: %u, len %llu\n", __func__, dimm_name, pkg.nd_command, in_len, out_len, buf_len); @@ -912,9 +913,9 @@ static int __nd_ioctl(struct nvdimm_bus *nvdimm_bus, struct nvdimm *nvdimm, out_len += out_size; } - buf_len = out_len + in_len; + buf_len = (u64) out_len + (u64) in_len; if (buf_len > ND_IOCTL_MAX_BUFLEN) { - dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__, + dev_dbg(dev, "%s:%s cmd: %s buf_len: %llu > %d\n", __func__, dimm_name, cmd_name, buf_len, ND_IOCTL_MAX_BUFLEN); return -EINVAL; diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c index 42abdd2391c9..d6aa59ca68b9 100644 --- a/drivers/nvdimm/pfn_devs.c +++ b/drivers/nvdimm/pfn_devs.c @@ -563,6 +563,12 @@ static struct vmem_altmap *__nvdimm_setup_pfn(struct nd_pfn *nd_pfn, return altmap; } +static u64 phys_pmem_align_down(struct nd_pfn *nd_pfn, u64 phys) +{ + return min_t(u64, PHYS_SECTION_ALIGN_DOWN(phys), + ALIGN_DOWN(phys, nd_pfn->align)); +} + static int nd_pfn_init(struct nd_pfn *nd_pfn) { u32 dax_label_reserve = is_nd_dax(&nd_pfn->dev) ? SZ_128K : 0; @@ -618,13 +624,16 @@ static int nd_pfn_init(struct nd_pfn *nd_pfn) start = nsio->res.start; size = PHYS_SECTION_ALIGN_UP(start + size) - start; if (region_intersects(start, size, IORESOURCE_SYSTEM_RAM, - IORES_DESC_NONE) == REGION_MIXED) { + IORES_DESC_NONE) == REGION_MIXED + || !IS_ALIGNED(start + resource_size(&nsio->res), + nd_pfn->align)) { size = resource_size(&nsio->res); - end_trunc = start + size - PHYS_SECTION_ALIGN_DOWN(start + size); + end_trunc = start + size - phys_pmem_align_down(nd_pfn, + start + size); } if (start_pad + end_trunc) - dev_info(&nd_pfn->dev, "%s section collision, truncate %d bytes\n", + dev_info(&nd_pfn->dev, "%s alignment collision, truncate %d bytes\n", dev_name(&ndns->dev), start_pad + end_trunc); /* diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 98eba9127a0b..0c9edc9d7c44 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3369,22 +3369,29 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_PORT_RIDGE, static void quirk_chelsio_extend_vpd(struct pci_dev *dev) { - pci_set_vpd_size(dev, 8192); -} - -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x20, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x21, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x22, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x23, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x24, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x25, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x26, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x30, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x31, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x32, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x35, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x36, quirk_chelsio_extend_vpd); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, 0x37, quirk_chelsio_extend_vpd); + int chip = (dev->device & 0xf000) >> 12; + int func = (dev->device & 0x0f00) >> 8; + int prod = (dev->device & 0x00ff) >> 0; + + /* + * If this is a T3-based adapter, there's a 1KB VPD area at offset + * 0xc00 which contains the preferred VPD values. If this is a T4 or + * later based adapter, the special VPD is at offset 0x400 for the + * Physical Functions (the SR-IOV Virtual Functions have no VPD + * Capabilities). The PCI VPD Access core routines will normally + * compute the size of the VPD by parsing the VPD Data Structure at + * offset 0x000. This will result in silent failures when attempting + * to accesses these other VPD areas which are beyond those computed + * limits. + */ + if (chip == 0x0 && prod >= 0x20) + pci_set_vpd_size(dev, 8192); + else if (chip >= 0x4 && func < 0x8) + pci_set_vpd_size(dev, 2048); +} + +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID, + quirk_chelsio_extend_vpd); #ifdef CONFIG_ACPI /* diff --git a/drivers/scsi/ibmvscsi/ibmvfc.h b/drivers/scsi/ibmvscsi/ibmvfc.h index 9a0696f68f37..b81a53c4a9a8 100644 --- a/drivers/scsi/ibmvscsi/ibmvfc.h +++ b/drivers/scsi/ibmvscsi/ibmvfc.h @@ -367,7 +367,7 @@ enum ibmvfc_fcp_rsp_info_codes { }; struct ibmvfc_fcp_rsp_info { - __be16 reserved; + u8 reserved[3]; u8 rsp_code; u8 reserved2[4]; }__attribute__((packed, aligned (2))); diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c index c05c4f877750..774c97bb1c08 100644 --- a/drivers/usb/core/quirks.c +++ b/drivers/usb/core/quirks.c @@ -225,6 +225,9 @@ static const struct usb_device_id usb_quirk_list[] = { { USB_DEVICE(0x1a0a, 0x0200), .driver_info = USB_QUIRK_LINEAR_UFRAME_INTR_BINTERVAL }, + /* Corsair K70 RGB */ + { USB_DEVICE(0x1b1c, 0x1b13), .driver_info = USB_QUIRK_DELAY_INIT }, + /* Corsair Strafe RGB */ { USB_DEVICE(0x1b1c, 0x1b20), .driver_info = USB_QUIRK_DELAY_INIT }, diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c index f483c3b1e971..26efe8c7535f 100644 --- a/drivers/usb/dwc3/gadget.c +++ b/drivers/usb/dwc3/gadget.c @@ -2528,6 +2528,8 @@ static void dwc3_gadget_conndone_interrupt(struct dwc3 *dwc) break; } + dwc->eps[1]->endpoint.maxpacket = dwc->gadget.ep0->maxpacket; + /* Enable USB2 LPM Capability */ if ((dwc->revision > DWC3_REVISION_194A) && diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c index d90bf57ba30e..48f52138bb1a 100644 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@ -2956,10 +2956,8 @@ static int _ffs_func_bind(struct usb_configuration *c, struct ffs_data *ffs = func->ffs; const int full = !!func->ffs->fs_descs_count; - const int high = gadget_is_dualspeed(func->gadget) && - func->ffs->hs_descs_count; - const int super = gadget_is_superspeed(func->gadget) && - func->ffs->ss_descs_count; + const int high = !!func->ffs->hs_descs_count; + const int super = !!func->ffs->ss_descs_count; int fs_len, hs_len, ss_len, ret, i; struct ffs_ep *eps_ptr; diff --git a/drivers/usb/host/ohci-hcd.c b/drivers/usb/host/ohci-hcd.c index f6c7a2744e5c..a646ca3b0d00 100644 --- a/drivers/usb/host/ohci-hcd.c +++ b/drivers/usb/host/ohci-hcd.c @@ -73,6 +73,7 @@ static const char hcd_name [] = "ohci_hcd"; #define STATECHANGE_DELAY msecs_to_jiffies(300) #define IO_WATCHDOG_DELAY msecs_to_jiffies(275) +#define IO_WATCHDOG_OFF 0xffffff00 #include "ohci.h" #include "pci-quirks.h" @@ -230,7 +231,7 @@ static int ohci_urb_enqueue ( } /* Start up the I/O watchdog timer, if it's not running */ - if (!timer_pending(&ohci->io_watchdog) && + if (ohci->prev_frame_no == IO_WATCHDOG_OFF && list_empty(&ohci->eds_in_use) && !(ohci->flags & OHCI_QUIRK_QEMU)) { ohci->prev_frame_no = ohci_frame_no(ohci); @@ -501,6 +502,7 @@ static int ohci_init (struct ohci_hcd *ohci) setup_timer(&ohci->io_watchdog, io_watchdog_func, (unsigned long) ohci); + ohci->prev_frame_no = IO_WATCHDOG_OFF; ohci->hcca = dma_alloc_coherent (hcd->self.controller, sizeof(*ohci->hcca), &ohci->hcca_dma, GFP_KERNEL); @@ -730,7 +732,7 @@ static void io_watchdog_func(unsigned long _ohci) u32 head; struct ed *ed; struct td *td, *td_start, *td_next; - unsigned frame_no; + unsigned frame_no, prev_frame_no = IO_WATCHDOG_OFF; unsigned long flags; spin_lock_irqsave(&ohci->lock, flags); @@ -835,7 +837,7 @@ static void io_watchdog_func(unsigned long _ohci) } } if (!list_empty(&ohci->eds_in_use)) { - ohci->prev_frame_no = frame_no; + prev_frame_no = frame_no; ohci->prev_wdh_cnt = ohci->wdh_cnt; ohci->prev_donehead = ohci_readl(ohci, &ohci->regs->donehead); @@ -845,6 +847,7 @@ static void io_watchdog_func(unsigned long _ohci) } done: + ohci->prev_frame_no = prev_frame_no; spin_unlock_irqrestore(&ohci->lock, flags); } @@ -973,6 +976,7 @@ static void ohci_stop (struct usb_hcd *hcd) if (quirk_nec(ohci)) flush_work(&ohci->nec_work); del_timer_sync(&ohci->io_watchdog); + ohci->prev_frame_no = IO_WATCHDOG_OFF; ohci_writel (ohci, OHCI_INTR_MIE, &ohci->regs->intrdisable); ohci_usb_reset(ohci); diff --git a/drivers/usb/host/ohci-hub.c b/drivers/usb/host/ohci-hub.c index ed678c17c4ea..798b2d25dda9 100644 --- a/drivers/usb/host/ohci-hub.c +++ b/drivers/usb/host/ohci-hub.c @@ -310,8 +310,10 @@ static int ohci_bus_suspend (struct usb_hcd *hcd) rc = ohci_rh_suspend (ohci, 0); spin_unlock_irq (&ohci->lock); - if (rc == 0) + if (rc == 0) { del_timer_sync(&ohci->io_watchdog); + ohci->prev_frame_no = IO_WATCHDOG_OFF; + } return rc; } diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c index 641fed609911..24edb7674710 100644 --- a/drivers/usb/host/ohci-q.c +++ b/drivers/usb/host/ohci-q.c @@ -1018,6 +1018,8 @@ static void finish_unlinks(struct ohci_hcd *ohci) * have modified this list. normally it's just prepending * entries (which we'd ignore), but paranoia won't hurt. */ + *last = ed->ed_next; + ed->ed_next = NULL; modified = 0; /* unlink urbs as requested, but rescan the list after @@ -1076,21 +1078,22 @@ static void finish_unlinks(struct ohci_hcd *ohci) goto rescan_this; /* - * If no TDs are queued, take ED off the ed_rm_list. + * If no TDs are queued, ED is now idle. * Otherwise, if the HC is running, reschedule. - * If not, leave it on the list for further dequeues. + * If the HC isn't running, add ED back to the + * start of the list for later processing. */ if (list_empty(&ed->td_list)) { - *last = ed->ed_next; - ed->ed_next = NULL; ed->state = ED_IDLE; list_del(&ed->in_use_list); } else if (ohci->rh_state == OHCI_RH_RUNNING) { - *last = ed->ed_next; - ed->ed_next = NULL; ed_schedule(ohci, ed); } else { - last = &ed->ed_next; + ed->ed_next = ohci->ed_rm_list; + ohci->ed_rm_list = ed; + /* Don't loop on the same ED */ + if (last == &ohci->ed_rm_list) + last = &ed->ed_next; } if (modified) diff --git a/drivers/usb/misc/ldusb.c b/drivers/usb/misc/ldusb.c index 9ca595632f17..c5e3032a4d6b 100644 --- a/drivers/usb/misc/ldusb.c +++ b/drivers/usb/misc/ldusb.c @@ -46,6 +46,9 @@ #define USB_DEVICE_ID_LD_MICROCASSYTIME 0x1033 /* USB Product ID of Micro-CASSY Time (reserved) */ #define USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE 0x1035 /* USB Product ID of Micro-CASSY Temperature */ #define USB_DEVICE_ID_LD_MICROCASSYPH 0x1038 /* USB Product ID of Micro-CASSY pH */ +#define USB_DEVICE_ID_LD_POWERANALYSERCASSY 0x1040 /* USB Product ID of Power Analyser CASSY */ +#define USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY 0x1042 /* USB Product ID of Converter Controller CASSY */ +#define USB_DEVICE_ID_LD_MACHINETESTCASSY 0x1043 /* USB Product ID of Machine Test CASSY */ #define USB_DEVICE_ID_LD_JWM 0x1080 /* USB Product ID of Joule and Wattmeter */ #define USB_DEVICE_ID_LD_DMMP 0x1081 /* USB Product ID of Digital Multimeter P (reserved) */ #define USB_DEVICE_ID_LD_UMIP 0x1090 /* USB Product ID of UMI P */ @@ -88,6 +91,9 @@ static const struct usb_device_id ld_usb_table[] = { { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTIME) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYTEMPERATURE) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MICROCASSYPH) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_POWERANALYSERCASSY) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_CONVERTERCONTROLLERCASSY) }, + { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_MACHINETESTCASSY) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_JWM) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_DMMP) }, { USB_DEVICE(USB_VENDOR_ID_LD, USB_DEVICE_ID_LD_UMIP) }, diff --git a/drivers/usb/musb/musb_host.c b/drivers/usb/musb/musb_host.c index 55c624f2a8c0..43033895e8f6 100644 --- a/drivers/usb/musb/musb_host.c +++ b/drivers/usb/musb/musb_host.c @@ -418,13 +418,7 @@ static void musb_advance_schedule(struct musb *musb, struct urb *urb, } } - /* - * The pipe must be broken if current urb->status is set, so don't - * start next urb. - * TODO: to minimize the risk of regression, only check urb->status - * for RX, until we have a test case to understand the behavior of TX. - */ - if ((!status || !is_in) && qh && qh->is_ready) { + if (qh != NULL && qh->is_ready) { musb_dbg(musb, "... next ep%d %cX urb %p", hw_ep->epnum, is_in ? 'R' : 'T', next_urb(qh)); musb_start_urb(musb, is_in, qh); diff --git a/drivers/usb/renesas_usbhs/fifo.c b/drivers/usb/renesas_usbhs/fifo.c index 6c6a3a8df07a..968ade5a35f5 100644 --- a/drivers/usb/renesas_usbhs/fifo.c +++ b/drivers/usb/renesas_usbhs/fifo.c @@ -1001,6 +1001,10 @@ static int usbhsf_dma_prepare_pop_with_usb_dmac(struct usbhs_pkt *pkt, if ((uintptr_t)pkt->buf & (USBHS_USB_DMAC_XFER_SIZE - 1)) goto usbhsf_pio_prepare_pop; + /* return at this time if the pipe is running */ + if (usbhs_pipe_is_running(pipe)) + return 0; + usbhs_pipe_config_change_bfre(pipe, 1); ret = usbhsf_fifo_select(pipe, fifo, 0); @@ -1191,6 +1195,7 @@ static int usbhsf_dma_pop_done_with_usb_dmac(struct usbhs_pkt *pkt, usbhsf_fifo_clear(pipe, fifo); pkt->actual = usbhs_dma_calc_received_size(pkt, chan, rcv_len); + usbhs_pipe_running(pipe, 0); usbhsf_dma_stop(pipe, fifo); usbhsf_dma_unmap(pkt); usbhsf_fifo_unselect(pipe, pipe->fifo); diff --git a/fs/dax.c b/fs/dax.c index 800748f10b3d..71f87d74afe1 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -785,6 +785,7 @@ int dax_writeback_mapping_range(struct address_space *mapping, if (ret < 0) return ret; } + start_index = indices[pvec.nr - 1] + 1; } return 0; } diff --git a/include/linux/dax.h b/include/linux/dax.h index add6c4bc568f..ed9cf2f5cd06 100644 --- a/include/linux/dax.h +++ b/include/linux/dax.h @@ -61,11 +61,6 @@ static inline int dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr, int dax_pfn_mkwrite(struct vm_area_struct *, struct vm_fault *); #define dax_mkwrite(vma, vmf, gb) dax_fault(vma, vmf, gb) -static inline bool vma_is_dax(struct vm_area_struct *vma) -{ - return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); -} - static inline bool dax_mapping(struct address_space *mapping) { return mapping->host && IS_DAX(mapping->host); diff --git a/include/linux/fs.h b/include/linux/fs.h index d705ae084edd..745ea1b2e02c 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -18,6 +18,7 @@ #include #include #include +#include #include #include #include @@ -3033,6 +3034,25 @@ static inline bool io_is_direct(struct file *filp) return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + +static inline bool vma_is_fsdax(struct vm_area_struct *vma) +{ + struct inode *inode; + + if (!vma->vm_file) + return false; + if (!vma_is_dax(vma)) + return false; + inode = file_inode(vma->vm_file); + if (inode->i_mode == S_IFCHR) + return false; /* device-dax */ + return true; +} + static inline int iocb_flags(struct file *file) { int res = 0; diff --git a/include/linux/kernel.h b/include/linux/kernel.h index bc6ed52a39b9..61054f12be7c 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -46,6 +46,7 @@ #define REPEAT_BYTE(x) ((~0ul / 0xff) * (x)) #define ALIGN(x, a) __ALIGN_KERNEL((x), (a)) +#define ALIGN_DOWN(x, a) __ALIGN_KERNEL((x) - ((a) - 1), (a)) #define __ALIGN_MASK(x, mask) __ALIGN_KERNEL_MASK((x), (mask)) #define PTR_ALIGN(p, a) ((typeof(p))ALIGN((unsigned long)(p), (a))) #define IS_ALIGNED(x, a) (((x) & ((typeof(x))(a) - 1)) == 0) diff --git a/include/linux/mm.h b/include/linux/mm.h index 2217e2f18247..8e506783631b 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1288,6 +1288,19 @@ long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, struct page **pages, unsigned int gup_flags); long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags); +#ifdef CONFIG_FS_DAX +long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas); +#else +static inline long get_user_pages_longterm(unsigned long start, + unsigned long nr_pages, unsigned int gup_flags, + struct page **pages, struct vm_area_struct **vmas) +{ + return get_user_pages(start, nr_pages, gup_flags, pages, vmas); +} +#endif /* CONFIG_FS_DAX */ + int get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages); diff --git a/kernel/memremap.c b/kernel/memremap.c index 426547a21a0c..f61a8c387c3e 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -194,7 +194,7 @@ void put_zone_device_page(struct page *page) } EXPORT_SYMBOL(put_zone_device_page); -static void pgmap_radix_release(struct resource *res) +static void pgmap_radix_release(struct resource *res, resource_size_t end_key) { resource_size_t key, align_start, align_size, align_end; @@ -203,8 +203,11 @@ static void pgmap_radix_release(struct resource *res) align_end = align_start + align_size - 1; mutex_lock(&pgmap_lock); - for (key = res->start; key <= res->end; key += SECTION_SIZE) + for (key = res->start; key <= res->end; key += SECTION_SIZE) { + if (key >= end_key) + break; radix_tree_delete(&pgmap_radix, key >> PA_SECTION_SHIFT); + } mutex_unlock(&pgmap_lock); } @@ -255,7 +258,7 @@ static void devm_memremap_pages_release(struct device *dev, void *data) unlock_device_hotplug(); untrack_pfn(NULL, PHYS_PFN(align_start), align_size); - pgmap_radix_release(res); + pgmap_radix_release(res, -1); dev_WARN_ONCE(dev, pgmap->altmap && pgmap->altmap->alloc, "%s: failed to free all reserved pages\n", __func__); } @@ -289,7 +292,7 @@ struct dev_pagemap *find_dev_pagemap(resource_size_t phys) void *devm_memremap_pages(struct device *dev, struct resource *res, struct percpu_ref *ref, struct vmem_altmap *altmap) { - resource_size_t key, align_start, align_size, align_end; + resource_size_t key = 0, align_start, align_size, align_end; pgprot_t pgprot = PAGE_KERNEL; struct dev_pagemap *pgmap; struct page_map *page_map; @@ -392,7 +395,7 @@ void *devm_memremap_pages(struct device *dev, struct resource *res, untrack_pfn(NULL, PHYS_PFN(align_start), align_size); err_pfn_remap: err_radix: - pgmap_radix_release(res); + pgmap_radix_release(res, key); devres_free(page_map); return ERR_PTR(error); } diff --git a/mm/frame_vector.c b/mm/frame_vector.c index db77dcb38afd..375a103d7a56 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -52,6 +52,18 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, ret = -EFAULT; goto out; } + + /* + * While get_vaddr_frames() could be used for transient (kernel + * controlled lifetime) pinning of memory pages all current + * users establish long term (userspace controlled lifetime) + * page pinning. Treat get_vaddr_frames() like + * get_user_pages_longterm() and disallow it for filesystem-dax + * mappings. + */ + if (vma_is_fsdax(vma)) + return -EOPNOTSUPP; + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) { vec->got_ref = true; vec->is_pfns = false; diff --git a/mm/gup.c b/mm/gup.c index c63a0341ae38..6c3b4e822946 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -982,6 +982,70 @@ long get_user_pages(unsigned long start, unsigned long nr_pages, } EXPORT_SYMBOL(get_user_pages); +#ifdef CONFIG_FS_DAX +/* + * This is the same as get_user_pages() in that it assumes we are + * operating on the current task's mm, but it goes further to validate + * that the vmas associated with the address range are suitable for + * longterm elevated page reference counts. For example, filesystem-dax + * mappings are subject to the lifetime enforced by the filesystem and + * we need guarantees that longterm users like RDMA and V4L2 only + * establish mappings that have a kernel enforced revocation mechanism. + * + * "longterm" == userspace controlled elevated page count lifetime. + * Contrast this to iov_iter_get_pages() usages which are transient. + */ +long get_user_pages_longterm(unsigned long start, unsigned long nr_pages, + unsigned int gup_flags, struct page **pages, + struct vm_area_struct **vmas_arg) +{ + struct vm_area_struct **vmas = vmas_arg; + struct vm_area_struct *vma_prev = NULL; + long rc, i; + + if (!pages) + return -EINVAL; + + if (!vmas) { + vmas = kcalloc(nr_pages, sizeof(struct vm_area_struct *), + GFP_KERNEL); + if (!vmas) + return -ENOMEM; + } + + rc = get_user_pages(start, nr_pages, gup_flags, pages, vmas); + + for (i = 0; i < rc; i++) { + struct vm_area_struct *vma = vmas[i]; + + if (vma == vma_prev) + continue; + + vma_prev = vma; + + if (vma_is_fsdax(vma)) + break; + } + + /* + * Either get_user_pages() failed, or the vma validation + * succeeded, in either case we don't need to put_page() before + * returning. + */ + if (i >= rc) + goto out; + + for (i = 0; i < rc; i++) + put_page(pages[i]); + rc = -EOPNOTSUPP; +out: + if (vmas != vmas_arg) + kfree(vmas); + return rc; +} +EXPORT_SYMBOL(get_user_pages_longterm); +#endif /* CONFIG_FS_DAX */ + /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma diff --git a/mm/memory.c b/mm/memory.c index e2e68767a373..d2db2c4eb0a4 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2848,6 +2848,17 @@ static int __do_fault(struct fault_env *fe, pgoff_t pgoff, return ret; } +/* + * The ordering of these checks is important for pmds with _PAGE_DEVMAP set. + * If we check pmd_trans_unstable() first we will trip the bad_pmd() check + * inside of pmd_none_or_trans_huge_or_clear_bad(). This will end up correctly + * returning 1 but not before it spams dmesg with the pmd_clear_bad() output. + */ +static int pmd_devmap_trans_unstable(pmd_t *pmd) +{ + return pmd_devmap(*pmd) || pmd_trans_unstable(pmd); +} + static int pte_alloc_one_map(struct fault_env *fe) { struct vm_area_struct *vma = fe->vma; @@ -2871,18 +2882,27 @@ static int pte_alloc_one_map(struct fault_env *fe) map_pte: /* * If a huge pmd materialized under us just retry later. Use - * pmd_trans_unstable() instead of pmd_trans_huge() to ensure the pmd - * didn't become pmd_trans_huge under us and then back to pmd_none, as - * a result of MADV_DONTNEED running immediately after a huge pmd fault - * in a different thread of this mm, in turn leading to a misleading - * pmd_trans_huge() retval. All we have to ensure is that it is a - * regular pmd that we can walk with pte_offset_map() and we can do that - * through an atomic read in C, which is what pmd_trans_unstable() - * provides. + * pmd_trans_unstable() via pmd_devmap_trans_unstable() instead of + * pmd_trans_huge() to ensure the pmd didn't become pmd_trans_huge + * under us and then back to pmd_none, as a result of MADV_DONTNEED + * running immediately after a huge pmd fault in a different thread of + * this mm, in turn leading to a misleading pmd_trans_huge() retval. + * All we have to ensure is that it is a regular pmd that we can walk + * with pte_offset_map() and we can do that through an atomic read in + * C, which is what pmd_trans_unstable() provides. */ - if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) + if (pmd_devmap_trans_unstable(fe->pmd)) return VM_FAULT_NOPAGE; + /* + * At this point we know that our vmf->pmd points to a page of ptes + * and it cannot become pmd_none(), pmd_devmap() or pmd_trans_huge() + * for the duration of the fault. If a racing MADV_DONTNEED runs and + * we zap the ptes pointed to by our vmf->pmd, the vmf->ptl will still + * be valid and we will re-check to make sure the vmf->pte isn't + * pte_none() under vmf->ptl protection when we return to + * alloc_set_pte(). + */ fe->pte = pte_offset_map_lock(vma->vm_mm, fe->pmd, fe->address, &fe->ptl); return 0; @@ -3456,7 +3476,7 @@ static int handle_pte_fault(struct fault_env *fe) fe->pte = NULL; } else { /* See comment in pte_alloc_one_map() */ - if (pmd_trans_unstable(fe->pmd) || pmd_devmap(*fe->pmd)) + if (pmd_devmap_trans_unstable(fe->pmd)) return 0; /* * A regular pmd is established and it can't morph into a huge diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index bf62fa487262..fd1e6b8562e0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -1552,10 +1552,7 @@ int ip_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); return err; @@ -1587,9 +1584,7 @@ int compat_ip_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); err = compat_nf_getsockopt(sk, PF_INET, optname, optval, &len); - release_sock(sk); if (err >= 0) err = put_user(len, optlen); return err; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 493a32f6a5f2..c66b9a87e995 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -1343,10 +1343,7 @@ int ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = nf_getsockopt(sk, PF_INET6, optname, optval, - &len); - release_sock(sk); + err = nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } @@ -1385,10 +1382,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - lock_sock(sk); - err = compat_nf_getsockopt(sk, PF_INET6, - optname, optval, &len); - release_sock(sk); + err = compat_nf_getsockopt(sk, PF_INET6, optname, optval, &len); if (err >= 0) err = put_user(len, optlen); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 07001b6d36cc..dee60428c78c 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2792,7 +2792,7 @@ cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) } if (beacon->probe_resp_len) { new_beacon->probe_resp_len = beacon->probe_resp_len; - beacon->probe_resp = pos; + new_beacon->probe_resp = pos; memcpy(pos, beacon->probe_resp, beacon->probe_resp_len); pos += beacon->probe_resp_len; }