Merge 4.9.85 into android-4.9
Changes in 4.9.85
netfilter: drop outermost socket lock in getsockopt()
xtensa: fix high memory/reserved memory collision
scsi: ibmvfc: fix misdefined reserved field in ibmvfc_fcp_rsp_info
cfg80211: fix cfg80211_beacon_dup
X.509: fix BUG_ON() when hash algorithm is unsupported
PKCS#7: fix certificate chain verification
RDMA/uverbs: Protect from command mask overflow
iio: buffer: check if a buffer has been set up when poll is called
iio: adis_lib: Initialize trigger before requesting interrupt
x86/oprofile: Fix bogus GCC-8 warning in nmi_setup()
irqchip/gic-v3: Use wmb() instead of smb_wmb() in gic_raise_softirq()
PCI/cxgb4: Extend T3 PCI quirk to T4+ devices
ohci-hcd: Fix race condition caused by ohci_urb_enqueue() and io_watchdog_func()
usb: ohci: Proper handling of ed_rm_list to handle race condition between usb_kill_urb() and finish_unlinks()
arm64: Disable unhandled signal log messages by default
Add delay-init quirk for Corsair K70 RGB keyboards
drm/edid: Add 6 bpc quirk for CPT panel in Asus UX303LA
usb: dwc3: gadget: Set maxpacket size for ep0 IN
usb: ldusb: add PIDs for new CASSY devices supported by this driver
Revert "usb: musb: host: don't start next rx urb if current one failed"
usb: gadget: f_fs: Process all descriptors during bind
usb: renesas_usbhs: missed the "running" flag in usb_dmac with rx path
drm/amdgpu: Add dpm quirk for Jet PRO (v2)
drm/amdgpu: add atpx quirk handling (v2)
drm/amdgpu: Avoid leaking PM domain on driver unbind (v2)
drm/amdgpu: add new device to use atpx quirk
binder: add missing binder_unlock()
X.509: fix NULL dereference when restricting key with unsupported_sig
mm: avoid spurious 'bad pmd' warning messages
fs/dax.c: fix inefficiency in dax_writeback_mapping_range()
libnvdimm: fix integer overflow static analysis warning
device-dax: implement ->split() to catch invalid munmap attempts
mm: introduce get_user_pages_longterm
v4l2: disable filesystem-dax mapping support
IB/core: disable memory registration of filesystem-dax vmas
libnvdimm, dax: fix 1GB-aligned namespaces vs physical misalignment
mm: Fix devm_memremap_pages() collision handling
mm: fail get_vaddr_frames() for filesystem-dax mappings
x86/entry/64: Clear extra registers beyond syscall arguments, to reduce speculation attack surface
Linux 4.9.85
Signed-off-by: Greg Kroah-Hartman <gregkh@google.com>
diff --git a/Makefile b/Makefile
index b5c94ec..b8ec38e 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 5fd787a..d210bbf 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -51,7 +51,7 @@
"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 8be2aaa..30350b7 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -176,13 +176,26 @@
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 28c0412..842ca3c 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -472,7 +472,7 @@
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 80e4cfb..d5abdf8 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -77,19 +77,75 @@
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 5a37962..df1bde2 100644
--- a/crypto/asymmetric_keys/pkcs7_verify.c
+++ b/crypto/asymmetric_keys/pkcs7_verify.c
@@ -261,7 +261,7 @@
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 4955eb6..8525fe4 100644
--- a/crypto/asymmetric_keys/public_key.c
+++ b/crypto/asymmetric_keys/public_key.c
@@ -93,9 +93,11 @@
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 19d1afb9..09b1374 100644
--- a/crypto/asymmetric_keys/restrict.c
+++ b/crypto/asymmetric_keys/restrict.c
@@ -66,8 +66,9 @@
*
* 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 @@
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 ff367b8fa..4d4fd91 100644
--- a/drivers/android/binder.c
+++ b/drivers/android/binder.c
@@ -4573,8 +4573,10 @@
bool wait_for_proc_work;
thread = binder_get_thread(proc);
- if (!thread)
+ if (!thread) {
+ binder_unlock(__func__);
return POLLERR;
+ }
binder_inner_proc_lock(thread->proc);
thread->looper |= BINDER_LOOPER_STATE_POLL;
diff --git a/drivers/dax/dax.c b/drivers/dax/dax.c
index 40be374..473b44c 100644
--- a/drivers/dax/dax.c
+++ b/drivers/dax/dax.c
@@ -453,9 +453,21 @@
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 6c343a9..0e8f897 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 @@
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 @@
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 @@
.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 @@
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 @@
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 ce9797b..50f18f6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1678,8 +1678,6 @@
* 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 4cb347e..002862b 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3507,6 +3507,11 @@
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 0151ed2..c6b281a 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -107,6 +107,9 @@
/* 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 03cac57..49406e1 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -2443,6 +2443,9 @@
{ 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 244b97c..9347b37 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 f53e9a8..93b99bd 100644
--- a/drivers/iio/imu/adis_trigger.c
+++ b/drivers/iio/imu/adis_trigger.c
@@ -47,6 +47,10 @@
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 @@
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 158aaf4..5d05c38 100644
--- a/drivers/iio/industrialio-buffer.c
+++ b/drivers/iio/industrialio-buffer.c
@@ -174,7 +174,7 @@
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 c22fde6..8e973a2 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -193,7 +193,7 @@
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 44b1104..c5e921b 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -735,12 +735,21 @@
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 @@
}
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 @@
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 @@
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 a37576a..fd4a782 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -616,7 +616,7 @@
* 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 1db0af6..b6189a4 100644
--- a/drivers/media/v4l2-core/videobuf-dma-sg.c
+++ b/drivers/media/v4l2-core/videobuf-dma-sg.c
@@ -185,12 +185,13 @@
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 9e073fb..6fd3be6 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2596,7 +2596,6 @@
}
#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 @@
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 0392eb8..8311a93 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -812,16 +812,17 @@
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 @@
}
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 @@
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 42abdd2..d6aa59c 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -563,6 +563,12 @@
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 @@
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 98eba91..0c9edc9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3369,22 +3369,29 @@
static void quirk_chelsio_extend_vpd(struct pci_dev *dev)
{
- pci_set_vpd_size(dev, 8192);
+ 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, 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);
+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 9a0696f..b81a53c 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.h
+++ b/drivers/scsi/ibmvscsi/ibmvfc.h
@@ -367,7 +367,7 @@
};
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 c05c4f8..774c97b 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -225,6 +225,9 @@
{ 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 f483c3b..26efe8c 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2528,6 +2528,8 @@
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 d90bf57..48f5213 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -2956,10 +2956,8 @@
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 f6c7a27..a646ca3 100644
--- a/drivers/usb/host/ohci-hcd.c
+++ b/drivers/usb/host/ohci-hcd.c
@@ -73,6 +73,7 @@
#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 @@
}
/* 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 @@
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 @@
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 @@
}
}
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 @@
}
done:
+ ohci->prev_frame_no = prev_frame_no;
spin_unlock_irqrestore(&ohci->lock, flags);
}
@@ -973,6 +976,7 @@
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 ed678c17..798b2d2 100644
--- a/drivers/usb/host/ohci-hub.c
+++ b/drivers/usb/host/ohci-hub.c
@@ -310,8 +310,10 @@
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 641fed6..24edb76 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -1018,6 +1018,8 @@
* 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 @@
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 9ca5956..c5e3032 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 @@
{ 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 55c624f..4303389 100644
--- a/drivers/usb/musb/musb_host.c
+++ b/drivers/usb/musb/musb_host.c
@@ -418,13 +418,7 @@
}
}
- /*
- * 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 6c6a3a8..968ade5 100644
--- a/drivers/usb/renesas_usbhs/fifo.c
+++ b/drivers/usb/renesas_usbhs/fifo.c
@@ -1001,6 +1001,10 @@
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 @@
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 800748f..71f87d7 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -785,6 +785,7 @@
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 add6c4b..ed9cf2f 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -61,11 +61,6 @@
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 cbcdcb2..3e16d65 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -18,6 +18,7 @@
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
+#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fiemap.h>
@@ -3057,6 +3058,25 @@
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 bc6ed52..61054f1 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 67dffb8..cf56fe6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1293,6 +1293,19 @@
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 426547a..f61a8c3 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -194,7 +194,7 @@
}
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 @@
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 @@
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 @@
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 @@
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 db77dcb..375a103 100644
--- a/mm/frame_vector.c
+++ b/mm/frame_vector.c
@@ -52,6 +52,18 @@
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 c63a034..6c3b4e8 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -982,6 +982,70 @@
}
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 e2e6876..d2db2c4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2848,6 +2848,17 @@
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 @@
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 @@
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 bf62fa4..fd1e6b8 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1552,10 +1552,7 @@
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 @@
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 493a32f..c66b9a8 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -1343,10 +1343,7 @@
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 @@
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 07001b6..dee6042 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2792,7 +2792,7 @@
}
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;
}