6.4.2-rc1 review

This is the start of the stable review cycle for the 6.4.2 release. There are 13 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.

Responses should be made by Wed, 05 Jul 2023 18:45:08 +0000. Anything received after that time might be too late.

The whole patch series can be found in one patch at:

	https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.4.2-rc1.gz

or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.4.y
and the diffstat can be found below.

thanks,

greg k-h

-------------
Pseudo-Shortlog of commits:

Greg Kroah-Hartman <[email protected]>

    Linux 6.4.2-rc1

Bas Nieuwenhuizen <[email protected]>
drm/amdgpu: Validate VM ioctl flags.

Demi Marie Obenour <[email protected]>
dm ioctl: Avoid double-fetch of version

Ahmed S. Darwish <[email protected]>
docs: Set minimal gtags / GNU GLOBAL version to 6.6.5

Ahmed S. Darwish <[email protected]>
scripts/tags.sh: Resolve gtags empty index generation

Mike Kravetz <[email protected]>
hugetlb: revert use of page_cache_next_miss()

Finn Thain <[email protected]>
nubus: Partially revert proc_create_single_data() conversion

Dan Williams <[email protected]>
Revert "cxl/port: Enable the HDM decoder capability for switch ports"

Jeff Layton <[email protected]>

    nfs: don't report STATX_BTIME in ->getattr

Linus Torvalds <[email protected]>
execve: always mark stack as growing down during early stack setup

Mario Limonciello <[email protected]>
PCI/ACPI: Call _REG when transitioning D-states

Bjorn Helgaas <[email protected]>
PCI/ACPI: Validate acpi_pci_set_power_state() parameter

Thomas Weißschuh <[email protected]>
tools/nolibc: x86_64: disable stack protector for _start

Max Filippov <[email protected]>
xtensa: fix lock_mm_and_find_vma in case VMA not found

-------------

Diffstat:

 Documentation/process/changes.rst      |  7 +++++
 Makefile                               |  4 +--
 drivers/cxl/core/pci.c                 | 27 +++--------------
 drivers/cxl/cxl.h                      |  1 -
 drivers/cxl/port.c                     | 14 ++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c |  4 +++
 drivers/md/dm-ioctl.c                  | 33 +++++++++++++--------
 drivers/nubus/proc.c                   | 22 ++++++++++----
 drivers/pci/pci-acpi.c                 | 53 +++++++++++++++++++++++++---------
 fs/hugetlbfs/inode.c                   |  8 ++---
 fs/nfs/inode.c                         |  2 +-
 include/linux/mm.h                     |  4 ++-
 mm/hugetlb.c                           | 12 ++++----
 mm/nommu.c                             |  7 ++++-
 scripts/tags.sh                        |  9 +++++-
 tools/include/nolibc/arch-x86_64.h     |  2 +-
 tools/testing/cxl/Kbuild               |  1 -
 tools/testing/cxl/test/mock.c          | 15 ----------
 18 files changed, 128 insertions(+), 97 deletions(-)

From: Max Filippov <[email protected]>

commit 03f889378f33aa9a9d8e5f49ba94134cf6158090 upstream.

MMU version of lock_mm_and_find_vma releases the mm lock before returning when VMA is not found. Do the same in noMMU version. This fixes hang on an attempt to handle protection fault.

---
 mm/nommu.c |    7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

@@ -637,8 +637,13 @@ EXPORT_SYMBOL(find_vma);
 struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
 			unsigned long addr, struct pt_regs *regs)
 {
+	struct vm_area_struct *vma;
+
 	mmap_read_lock(mm);
-	return vma_lookup(mm, addr);
+	vma = vma_lookup(mm, addr);
+	if (!vma)
+		mmap_read_unlock(mm);
+	return vma;
 }
 
 /*

From: Thomas Weißschuh <[email protected]>

commit 7a9b2345202a14dfec9081994486156f7a691513 upstream.

This was forgotten in the original submission.

It is unknown why it worked for x86_64 on some compiler without this attribute.

---
 tools/include/nolibc/arch-x86_64.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

index d98f6c89d143..e201af15e142 100644
@@ -190,7 +190,7 @@ const unsigned long *_auxv __attribute__((weak));
  * 2) The deepest stack frame should be zero (the %rbp).
  *
  */
-void __attribute__((weak,noreturn,optimize("omit-frame-pointer"))) _start(void)
+void __attribute__((weak,noreturn,optimize("omit-frame-pointer"),no_stack_protector)) _start(void)
 {
 	__asm__ volatile (
 #ifdef NOLIBC_STACKPROTECTOR

2.41.0

From: Bjorn Helgaas <[email protected]>

commit 5557b62634abbd55bab7b154ce4bca348ad7f96f upstream.

Previously acpi_pci_set_power_state() assumed the requested power state was valid (PCI_D0 ... PCI_D3cold). If a caller supplied something else, we could index outside the state_conv[] array and pass junk to acpi_device_set_power().

Validate the pci_power_t parameter and return -EINVAL if it's invalid.

---
 drivers/pci/pci-acpi.c |   31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

@@ -1053,32 +1053,37 @@ int acpi_pci_set_power_state(struct pci_
 		[PCI_D3hot] = ACPI_STATE_D3_HOT,
 		[PCI_D3cold] = ACPI_STATE_D3_COLD,
 	};
-	int error = -EINVAL;
+	int error;
 
 	/* If the ACPI device has _EJ0, ignore the device */
 	if (!adev || acpi_has_method(adev->handle, "_EJ0"))
 		return -ENODEV;
 
 	switch (state) {
-	case PCI_D3cold:
-		if (dev_pm_qos_flags(&dev->dev, PM_QOS_FLAG_NO_POWER_OFF) ==
-				PM_QOS_FLAGS_ALL) {
-			error = -EBUSY;
-			break;
-		}
-		fallthrough;
 	case PCI_D0:
 	case PCI_D1:
 	case PCI_D2:
 	case PCI_D3hot:
-		error = acpi_device_set_power(adev, state_conv[state]);
+	case PCI_D3cold:
+		break;
+	default:
+		return -EINVAL;
 	}
 
-	if (!error)
-		pci_dbg(dev, "power state changed by ACPI to %s\n",
-		        acpi_power_state_string(adev->power.state));
+	if (state == PCI_D3cold) {
+		if (dev_pm_qos_flags(&dev->dev, PM_QOS_FLAG_NO_POWER_OFF) ==
+				PM_QOS_FLAGS_ALL)
+			return -EBUSY;
+	}
+
+	error = acpi_device_set_power(adev, state_conv[state]);
+	if (error)
+		return error;
+
+	pci_dbg(dev, "power state changed by ACPI to %s\n",
+	        acpi_power_state_string(adev->power.state));
 
-	return error;
+	return 0;
 }
 
 pci_power_t acpi_pci_get_power_state(struct pci_dev *dev)

From: Mario Limonciello <[email protected]>

commit 112a7f9c8edbf76f7cb83856a6cb6b60a210b659 upstream.

ACPI r6.5, sec 6.5.4, describes how AML is unable to access an OperationRegion unless _REG has been called to connect a handler:

The OS runs _REG control methods to inform AML code of a change in the availability of an operation region. When an operation region handler is unavailable, AML cannot access data fields in that region. (Operation region writes will be ignored and reads will return indeterminate data.)

The PCI core does not call _REG at any time, leading to the undefined behavior mentioned in the spec.

The spec explains that _REG should be executed to indicate whether a given region can be accessed:

Once _REG has been executed for a particular operation region, indicating that the operation region handler is ready, a control method can access fields in the operation region. Conversely, control methods must not access fields in operation regions when _REG method execution has not indicated that the operation region handler is ready.

An example included in the spec demonstrates calling _REG when devices are turned off: "when the host controller or bridge controller is turned off or disabled, PCI Config Space Operation Regions for child devices are no longer available. As such, ETH0’s _REG method will be run when it is turned off and will again be run when PCI1 is turned off."

It is reported that ASMedia PCIe GPIO controllers fail functional tests after the system has returning from suspend (S3 or s2idle). This is because the BIOS checks whether the OSPM has called the _REG method to determine whether it can interact with the OperationRegion assigned to the device as part of the other AML called for the device.

To fix this issue, call acpi_evaluate_reg() when devices are transitioning to D3cold or D0.

---
 drivers/pci/pci-acpi.c |   22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

@@ -1043,6 +1043,16 @@ bool acpi_pci_bridge_d3(struct pci_dev *
 	return false;
 }
 
+static void acpi_pci_config_space_access(struct pci_dev *dev, bool enable)
+{
+	int val = enable ? ACPI_REG_CONNECT : ACPI_REG_DISCONNECT;
+	int ret = acpi_evaluate_reg(ACPI_HANDLE(&dev->dev),
+				    ACPI_ADR_SPACE_PCI_CONFIG, val);
+	if (ret)
+		pci_dbg(dev, "ACPI _REG %s evaluation failed (%d)\n",
+			enable ? "connect" : "disconnect", ret);
+}
+
 int acpi_pci_set_power_state(struct pci_dev *dev, pci_power_t state)
 {
 	struct acpi_device *adev = ACPI_COMPANION(&dev->dev);

@@ -1074,6 +1084,9 @@ int acpi_pci_set_power_state(struct pci_
 		if (dev_pm_qos_flags(&dev->dev, PM_QOS_FLAG_NO_POWER_OFF) ==
 				PM_QOS_FLAGS_ALL)
 			return -EBUSY;
+
+		/* Notify AML lack of PCI config space availability */
+		acpi_pci_config_space_access(dev, false);
 	}
 
 	error = acpi_device_set_power(adev, state_conv[state]);

@@ -1083,6 +1096,15 @@ int acpi_pci_set_power_state(struct pci_
 	pci_dbg(dev, "power state changed by ACPI to %s\n",
 	        acpi_power_state_string(adev->power.state));
 
+	/*
+	 * Notify AML of PCI config space availability.  Config space is
+	 * accessible in all states except D3cold; the only transitions
+	 * that change availability are transitions to D3cold and from
+	 * D3cold to D0.
+	 */
+	if (state == PCI_D0)
+		acpi_pci_config_space_access(dev, true);
+
 	return 0;
 }
 

From: Linus Torvalds <[email protected]>

commit f66066bc5136f25e36a2daff4896c768f18c211e upstream.

While our user stacks can grow either down (all common architectures) or up (parisc and the ia64 register stack), the initial stack setup when we copy the argument and environment strings to the new stack at execve() time is always done by extending the stack downwards.

But it turns out that in commit 8d7071af8907 ("mm: always expand the stack with the mmap write lock held"), as part of making the stack growing code more robust, 'expand_downwards()' was now made to actually check the vma flags:

	if (!(vma->vm_flags & VM_GROWSDOWN))
		return -EFAULT;

and that meant that this execve-time stack expansion started failing on parisc, because on that architecture, the stack flags do not contain the VM_GROWSDOWN bit.

At the same time the new check in expand_downwards() is clearly correct, and simplified the callers, so let's not remove it.

The solution is instead to just codify the fact that yes, during execve(), the stack grows down. This not only matches reality, it ends up being particularly simple: we already have special execve-time flags for the stack (VM_STACK_INCOMPLETE_SETUP) and use those flags to avoid page migration during this setup time (see vma_is_temporary_stack() and invalid_migration_vma()).

So just add VM_GROWSDOWN to that set of temporary flags, and now our stack flags automatically match reality, and the parisc stack expansion works again.

Note that the VM_STACK_INCOMPLETE_SETUP bits will be cleared when the stack is finalized, so we only add the extra VM_GROWSDOWN bit on CONFIG_STACK_GROWSUP architectures (ie parisc) rather than adding it in general.

---
 include/linux/mm.h |    4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

@@ -377,7 +377,7 @@ extern unsigned int kobjsize(const void
 #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
 
 /* Bits set in the VMA until the stack is in its final location */
-#define VM_STACK_INCOMPLETE_SETUP	(VM_RAND_READ | VM_SEQ_READ)
+#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
 
 #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
 

@@ -399,8 +399,10 @@ extern unsigned int kobjsize(const void
 
 #ifdef CONFIG_STACK_GROWSUP
 #define VM_STACK	VM_GROWSUP
+#define VM_STACK_EARLY	VM_GROWSDOWN
 #else
 #define VM_STACK	VM_GROWSDOWN
+#define VM_STACK_EARLY	0
 #endif
 
 #define VM_STACK_FLAGS	(VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)

From: Jeff Layton <[email protected]>

commit cded49ba366220ae7009d71c5804baa01acfb860 upstream.

NFS doesn't properly support reporting the btime in getattr (yet), but 61a968b4f05e mistakenly added it to the request_mask. This causes statx for STATX_BTIME to report a zeroed out btime instead of properly clearing the flag.

---
 fs/nfs/inode.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

@@ -845,7 +845,7 @@ int nfs_getattr(struct mnt_idmap *idmap,
 
 	request_mask &= STATX_TYPE | STATX_MODE | STATX_NLINK | STATX_UID |
 			STATX_GID | STATX_ATIME | STATX_MTIME | STATX_CTIME |
-			STATX_INO | STATX_SIZE | STATX_BLOCKS | STATX_BTIME |
+			STATX_INO | STATX_SIZE | STATX_BLOCKS |
 			STATX_CHANGE_COOKIE;
 
 	if ((query_flags & AT_STATX_DONT_SYNC) && !force_sync) {

From: Dan Williams <[email protected]>

commit 8f0220af58c3b73e9041377a23708d37600b33c1 upstream.

commit eb0764b822b9 ("cxl/port: Enable the HDM decoder capability for switch ports")

...was added on the observation of CXL memory not being accessible after setting up a region on a "cold-plugged" device. A "cold-plugged" CXL device is one that was not present at boot, so platform-firmware/BIOS has no chance to set it up.

While it is true that the debug found the enable bit clear in the host-bridge's instance of the global control register (CXL 3.0 8.2.4.19.2 CXL HDM Decoder Global Control Register), that bit is described as:

"This bit is only applicable to CXL.mem devices and shall return 0 on CXL Host Bridges and Upstream Switch Ports."

So it is meant to be zero, and further testing confirmed that this "fix" had no effect on the failure. Revert it, and be more vigilant about proposed fixes in the future. Since the original copied stable@, flag this revert for stable@ as well.

---
 drivers/cxl/core/pci.c        |   27 ++++-----------------------
 drivers/cxl/cxl.h             |    1 -
 drivers/cxl/port.c            |   14 +++++---------
 tools/testing/cxl/Kbuild      |    1 -
 tools/testing/cxl/test/mock.c |   15 ---------------
 5 files changed, 9 insertions(+), 49 deletions(-)

@@ -308,36 +308,17 @@ static void disable_hdm(void *_cxlhdm)
 	       hdm + CXL_HDM_DECODER_CTRL_OFFSET);
 }
 
-int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm)
+static int devm_cxl_enable_hdm(struct device *host, struct cxl_hdm *cxlhdm)
 {
-	void __iomem *hdm;
+	void __iomem *hdm = cxlhdm->regs.hdm_decoder;
 	u32 global_ctrl;
 
-	/*
-	 * If the hdm capability was not mapped there is nothing to enable and
-	 * the caller is responsible for what happens next.  For example,
-	 * emulate a passthrough decoder.
-	 */
-	if (IS_ERR(cxlhdm))
-		return 0;
-
-	hdm = cxlhdm->regs.hdm_decoder;
 	global_ctrl = readl(hdm + CXL_HDM_DECODER_CTRL_OFFSET);
-
-	/*
-	 * If the HDM decoder capability was enabled on entry, skip
-	 * registering disable_hdm() since this decode capability may be
-	 * owned by platform firmware.
-	 */
-	if (global_ctrl & CXL_HDM_DECODER_ENABLE)
-		return 0;
-
 	writel(global_ctrl | CXL_HDM_DECODER_ENABLE,
 	       hdm + CXL_HDM_DECODER_CTRL_OFFSET);
 
-	return devm_add_action_or_reset(&port->dev, disable_hdm, cxlhdm);
+	return devm_add_action_or_reset(host, disable_hdm, cxlhdm);
 }
-EXPORT_SYMBOL_NS_GPL(devm_cxl_enable_hdm, CXL);
 
 int cxl_dvsec_rr_decode(struct device *dev, int d,
 			struct cxl_endpoint_dvsec_info *info)

@@ -511,7 +492,7 @@ int cxl_hdm_decode_init(struct cxl_dev_s
 	if (info->mem_enabled)
 		return 0;
 
-	rc = devm_cxl_enable_hdm(port, cxlhdm);
+	rc = devm_cxl_enable_hdm(&port->dev, cxlhdm);
 	if (rc)
 		return rc;
 

@@ -710,7 +710,6 @@ struct cxl_endpoint_dvsec_info {
 struct cxl_hdm;
 struct cxl_hdm *devm_cxl_setup_hdm(struct cxl_port *port,
 				   struct cxl_endpoint_dvsec_info *info);
-int devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm);
 int devm_cxl_enumerate_decoders(struct cxl_hdm *cxlhdm,
 				struct cxl_endpoint_dvsec_info *info);
 int devm_cxl_add_passthrough_decoder(struct cxl_port *port);

@@ -60,17 +60,13 @@ static int discover_region(struct device
 static int cxl_switch_port_probe(struct cxl_port *port)
 {
 	struct cxl_hdm *cxlhdm;
-	int rc, nr_dports;
+	int rc;
 
-	nr_dports = devm_cxl_port_enumerate_dports(port);
-	if (nr_dports < 0)
-		return nr_dports;
-
-	cxlhdm = devm_cxl_setup_hdm(port, NULL);
-	rc = devm_cxl_enable_hdm(port, cxlhdm);
-	if (rc)
+	rc = devm_cxl_port_enumerate_dports(port);
+	if (rc < 0)
 		return rc;
 
+	cxlhdm = devm_cxl_setup_hdm(port, NULL);
 	if (!IS_ERR(cxlhdm))
 		return devm_cxl_enumerate_decoders(cxlhdm, NULL);
 

@@ -79,7 +75,7 @@ static int cxl_switch_port_probe(struct
 		return PTR_ERR(cxlhdm);
 	}
 
-	if (nr_dports == 1) {
+	if (rc == 1) {
 		dev_dbg(&port->dev, "Fallback to passthrough decoder\n");
 		return devm_cxl_add_passthrough_decoder(port);
 	}

@@ -6,7 +6,6 @@ ldflags-y += --wrap=acpi_pci_find_root
 ldflags-y += --wrap=nvdimm_bus_register
 ldflags-y += --wrap=devm_cxl_port_enumerate_dports
 ldflags-y += --wrap=devm_cxl_setup_hdm
-ldflags-y += --wrap=devm_cxl_enable_hdm
 ldflags-y += --wrap=devm_cxl_add_passthrough_decoder
 ldflags-y += --wrap=devm_cxl_enumerate_decoders
 ldflags-y += --wrap=cxl_await_media_ready

@@ -149,21 +149,6 @@ struct cxl_hdm *__wrap_devm_cxl_setup_hd
 }
 EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_setup_hdm, CXL);
 
-int __wrap_devm_cxl_enable_hdm(struct cxl_port *port, struct cxl_hdm *cxlhdm)
-{
-	int index, rc;
-	struct cxl_mock_ops *ops = get_cxl_mock_ops(&index);
-
-	if (ops && ops->is_mock_port(port->uport))
-		rc = 0;
-	else
-		rc = devm_cxl_enable_hdm(port, cxlhdm);
-	put_cxl_mock_ops(index);
-
-	return rc;
-}
-EXPORT_SYMBOL_NS_GPL(__wrap_devm_cxl_enable_hdm, CXL);
-
 int __wrap_devm_cxl_add_passthrough_decoder(struct cxl_port *port)
 {
 	int rc, index;

From: Finn Thain <[email protected]>

commit 0e96647cff9224db564a1cee6efccb13dbe11ee2 upstream.

The conversion to proc_create_single_data() introduced a regression whereby reading a file in /proc/bus/nubus results in a seg fault:

    # grep -r . /proc/bus/nubus/e/
    Data read fault at 0x00000020 in Super Data (pc=0x1074c2)
    BAD KERNEL BUSERR
    Oops: 00000000
    Modules linked in:
    PC: [<001074c2>] PDE_DATA+0xc/0x16
    SR: 2010  SP: 38284958  a2: 01152370
    d0: 00000001    d1: 01013000    d2: 01002790    d3: 00000000
    d4: 00000001    d5: 0008ce2e    a0: 00000000    a1: 00222a40
    Process grep (pid: 45, task=142f8727)
    Frame format=B ssw=074d isc=2008 isb=4e5e daddr=00000020 dobuf=01199e70
    baddr=001074c8 dibuf=ffffffff ver=f
    Stack from 01199e48:
	    01199e70 00222a58 01002790 00000000 011a3000 01199eb0 015000c0 00000000
	    00000000 01199ec0 01199ec0 000d551a 011a3000 00000001 00000000 00018000
	    d003f000 00000003 00000001 0002800d 01052840 01199fa8 c01f8000 00000000
	    00000029 0b532b80 00000000 00000000 00000029 0b532b80 01199ee4 00103640
	    011198c0 d003f000 00018000 01199fa8 00000000 011198c0 00000000 01199f4c
	    000b3344 011198c0 d003f000 00018000 01199fa8 00000000 00018000 011198c0
    Call Trace: [<00222a58>] nubus_proc_rsrc_show+0x18/0xa0
     [<000d551a>] seq_read+0xc4/0x510
     [<00018000>] fp_fcos+0x2/0x82
     [<0002800d>] __sys_setreuid+0x115/0x1c6
     [<00103640>] proc_reg_read+0x5c/0xb0
     [<00018000>] fp_fcos+0x2/0x82
     [<000b3344>] __vfs_read+0x2c/0x13c
     [<00018000>] fp_fcos+0x2/0x82
     [<00018000>] fp_fcos+0x2/0x82
     [<000b8aa2>] sys_statx+0x60/0x7e
     [<000b34b6>] vfs_read+0x62/0x12a
     [<00018000>] fp_fcos+0x2/0x82
     [<00018000>] fp_fcos+0x2/0x82
     [<000b39c2>] ksys_read+0x48/0xbe
     [<00018000>] fp_fcos+0x2/0x82
     [<000b3a4e>] sys_read+0x16/0x1a
     [<00018000>] fp_fcos+0x2/0x82
     [<00002b84>] syscall+0x8/0xc
     [<00018000>] fp_fcos+0x2/0x82
     [<0000c016>] not_ext+0xa/0x18
    Code: 4e5e 4e75 4e56 0000 206e 0008 2068 ffe8 <2068> 0020 2008 4e5e 4e75 4e56 0000 2f0b 206e 0008 2068 0004 2668 0020 206b ffe8
    Disabling lock debugging due to kernel taint

Segmentation fault

The proc_create_single_data() conversion does not work because single_open(file, nubus_proc_rsrc_show, PDE_DATA(inode)) is not equivalent to the original code.

---
 drivers/nubus/proc.c |   22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

@@ -137,6 +137,18 @@ static int nubus_proc_rsrc_show(struct s
 	return 0;
 }
 
+static int nubus_rsrc_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nubus_proc_rsrc_show, inode);
+}
+
+static const struct proc_ops nubus_rsrc_proc_ops = {
+	.proc_open	= nubus_rsrc_proc_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= single_release,
+};
+
 void nubus_proc_add_rsrc_mem(struct proc_dir_entry *procdir,
 			     const struct nubus_dirent *ent,
 			     unsigned int size)

@@ -152,8 +164,8 @@ void nubus_proc_add_rsrc_mem(struct proc
 		pded = nubus_proc_alloc_pde_data(nubus_dirptr(ent), size);
 	else
 		pded = NULL;
-	proc_create_single_data(name, S_IFREG | 0444, procdir,
-			nubus_proc_rsrc_show, pded);
+	proc_create_data(name, S_IFREG | 0444, procdir,
+			 &nubus_rsrc_proc_ops, pded);
 }
 
 void nubus_proc_add_rsrc(struct proc_dir_entry *procdir,

@@ -166,9 +178,9 @@ void nubus_proc_add_rsrc(struct proc_dir
 		return;
 
 	snprintf(name, sizeof(name), "%x", ent->type);
-	proc_create_single_data(name, S_IFREG | 0444, procdir,
-			nubus_proc_rsrc_show,
-			nubus_proc_alloc_pde_data(data, 0));
+	proc_create_data(name, S_IFREG | 0444, procdir,
+			 &nubus_rsrc_proc_ops,
+			 nubus_proc_alloc_pde_data(data, 0));
 }
 
 /*

From: Mike Kravetz <[email protected]>

commit fd4aed8d985a3236d0877ff6d0c80ad39d4ce81a upstream.

Ackerley Tng reported an issue with hugetlbfs fallocate as noted in the Closes tag. The issue showed up after the conversion of hugetlb page cache lookup code to use page_cache_next_miss. User visible effects are:

- hugetlbfs fallocate incorrectly returns -EEXIST if pages are presnet in the file.
- hugetlb pages will not be included in core dumps if they need to be brought in via GUP.
- userfaultfd UFFDIO_COPY will not notice pages already present in the cache. It may try to allocate a new page and potentially return ENOMEM as opposed to EEXIST.

Revert the use page_cache_next_miss() in hugetlb code.

IMPORTANT NOTE FOR STABLE BACKPORTS:
This patch will apply cleanly to v6.3. However, due to the change of filemap_get_folio() return values, it will not function correctly. This patch must be modified for stable backports.

---
 fs/hugetlbfs/inode.c |    8 +++-----
 mm/hugetlb.c         |   12 ++++++------
 2 files changed, 9 insertions(+), 11 deletions(-)

@@ -821,7 +821,6 @@ static long hugetlbfs_fallocate(struct f
 		 */
 		struct folio *folio;
 		unsigned long addr;
-		bool present;
 
 		cond_resched();
 

@@ -845,10 +844,9 @@ static long hugetlbfs_fallocate(struct f
 		mutex_lock(&hugetlb_fault_mutex_table[hash]);
 
 		/* See if already present in mapping to avoid alloc/free */
-		rcu_read_lock();
-		present = page_cache_next_miss(mapping, index, 1) != index;
-		rcu_read_unlock();
-		if (present) {
+		folio = filemap_get_folio(mapping, index);
+		if (!IS_ERR(folio)) {
+			folio_put(folio);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			hugetlb_drop_vma_policy(&pseudo_vma);
 			continue;

@@ -5731,13 +5731,13 @@ static bool hugetlbfs_pagecache_present(
 {
 	struct address_space *mapping = vma->vm_file->f_mapping;
 	pgoff_t idx = vma_hugecache_offset(h, vma, address);
-	bool present;
+	struct folio *folio;
 
-	rcu_read_lock();
-	present = page_cache_next_miss(mapping, idx, 1) != idx;
-	rcu_read_unlock();
-
-	return present;
+	folio = filemap_get_folio(mapping, idx);
+	if (IS_ERR(folio))
+		return false;
+	folio_put(folio);
+	return true;
 }
 
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,

From: Ahmed S. Darwish <[email protected]>

commit e1b37563caffc410bb4b55f153ccb14dede66815 upstream.

gtags considers any file outside of its current working directory "outside the source tree" and refuses to index it. For O= kernel builds, or when "make" is invoked from a directory other then the kernel source tree, gtags ignores the entire kernel source and generates an empty index.

Force-set gtags current working directory to the kernel source tree.

Due to commit 9da0763bdd82 ("kbuild: Use relative path when building in a subdir of the source tree"), if the kernel build is done in a sub-directory of the kernel source tree, the kernel Makefile will set the kernel's $srctree to ".." for shorter compile-time and run-time warnings. Consequently, the list of files to be indexed will be in the "../*" form, rendering all such paths invalid once gtags switches to the kernel source tree as its current working directory.

If gtags indexing is requested and the build directory is not the kernel source tree, index all files in absolute-path form.

Note, indexing in absolute-path form will not affect the generated index, as paths in gtags indices are always relative to the gtags "root directory" anyway (as evidenced by "gtags --dump").

---
 scripts/tags.sh |    9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

@@ -32,6 +32,13 @@ else
 	tree=${srctree}/
 fi
 
+# gtags(1) refuses to index any file outside of its current working dir.
+# If gtags indexing is requested and the build output directory is not
+# the kernel source tree, index all files in absolute-path form.
+if [[ "$1" == "gtags" && -n "${tree}" ]]; then
+	tree=$(realpath "$tree")/
+fi
+
 # Detect if ALLSOURCE_ARCHS is set. If not, we assume SRCARCH
 if [ "${ALLSOURCE_ARCHS}" = "" ]; then
 	ALLSOURCE_ARCHS=${SRCARCH}

@@ -131,7 +138,7 @@ docscope()
 
 dogtags()
 {
-	all_target_sources | gtags -i -f -
+	all_target_sources | gtags -i -C "${tree:-.}" -f - "$PWD"
 }
 
 # Basic regular expressions with an optional /kind-spec/ for ctags and

From: Ahmed S. Darwish <[email protected]>

commit b230235b386589d8f0d631b1c77a95ca79bb0732 upstream.

Kernel build now uses the gtags "-C (--directory)" option, available since GNU GLOBAL v6.6.5. Update the documentation accordingly.

---
 Documentation/process/changes.rst |    7 +++++++
 1 file changed, 7 insertions(+)

@@ -60,6 +60,7 @@ openssl & libcrypto    1.0.0
 bc                     1.06.95          bc --version
 Sphinx\ [#f1]_         1.7              sphinx-build --version
 cpio                   any              cpio --version
+gtags (optional)       6.6.5            gtags --version
 ====================== ===============  ========================================
 
 .. [#f1] Sphinx is needed only to build the Kernel documentation

@@ -174,6 +175,12 @@ You will need openssl to build kernels 3
 enabled.  You will also need openssl development packages to build kernels 4.3
 and higher.
 
+gtags / GNU GLOBAL (optional)
+-----------------------------
+
+The kernel build requires GNU GLOBAL version 6.6.5 or later to generate
+tag files through ``make gtags``.  This is due to its use of the gtags
+``-C (--directory)`` flag.
 
 System utilities
 ****************

From: Demi Marie Obenour <[email protected]>

commit 249bed821b4db6d95a99160f7d6d236ea5fe6362 upstream.

The version is fetched once in check_version(), which then does some validation and then overwrites the version in userspace with the API version supported by the kernel. copy_params() then fetches the version from userspace *again*, and this time no validation is done. The result is that the kernel's version number is completely controllable by userspace, provided that userspace can win a race condition.

Fix this flaw by not copying the version back to the kernel the second time. This is not exploitable as the version is not further used in the kernel. However, it could become a problem if future patches start relying on the version field.

---
 drivers/md/dm-ioctl.c |   33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

@@ -1830,30 +1830,36 @@ static ioctl_fn lookup_ioctl(unsigned in
  * As well as checking the version compatibility this always
  * copies the kernel interface version out.
  */
-static int check_version(unsigned int cmd, struct dm_ioctl __user *user)
+static int check_version(unsigned int cmd, struct dm_ioctl __user *user,
+			 struct dm_ioctl *kernel_params)
 {
-	uint32_t version[3];
 	int r = 0;
 
-	if (copy_from_user(version, user->version, sizeof(version)))
+	/* Make certain version is first member of dm_ioctl struct */
+	BUILD_BUG_ON(offsetof(struct dm_ioctl, version) != 0);
+
+	if (copy_from_user(kernel_params->version, user->version, sizeof(kernel_params->version)))
 		return -EFAULT;
 
-	if ((version[0] != DM_VERSION_MAJOR) ||
-	    (version[1] > DM_VERSION_MINOR)) {
+	if ((kernel_params->version[0] != DM_VERSION_MAJOR) ||
+	    (kernel_params->version[1] > DM_VERSION_MINOR)) {
 		DMERR("ioctl interface mismatch: kernel(%u.%u.%u), user(%u.%u.%u), cmd(%d)",
 		      DM_VERSION_MAJOR, DM_VERSION_MINOR,
 		      DM_VERSION_PATCHLEVEL,
-		      version[0], version[1], version[2], cmd);
+		      kernel_params->version[0],
+		      kernel_params->version[1],
+		      kernel_params->version[2],
+		      cmd);
 		r = -EINVAL;
 	}
 
 	/*
 	 * Fill in the kernel version.
 	 */
-	version[0] = DM_VERSION_MAJOR;
-	version[1] = DM_VERSION_MINOR;
-	version[2] = DM_VERSION_PATCHLEVEL;
-	if (copy_to_user(user->version, version, sizeof(version)))
+	kernel_params->version[0] = DM_VERSION_MAJOR;
+	kernel_params->version[1] = DM_VERSION_MINOR;
+	kernel_params->version[2] = DM_VERSION_PATCHLEVEL;
+	if (copy_to_user(user->version, kernel_params->version, sizeof(kernel_params->version)))
 		return -EFAULT;
 
 	return r;

@@ -1879,7 +1885,10 @@ static int copy_params(struct dm_ioctl _
 	const size_t minimum_data_size = offsetof(struct dm_ioctl, data);
 	unsigned int noio_flag;
 
-	if (copy_from_user(param_kernel, user, minimum_data_size))
+	/* check_version() already copied version from userspace, avoid TOCTOU */
+	if (copy_from_user((char *)param_kernel + sizeof(param_kernel->version),
+			   (char __user *)user + sizeof(param_kernel->version),
+			   minimum_data_size - sizeof(param_kernel->version)))
 		return -EFAULT;
 
 	if (param_kernel->data_size < minimum_data_size) {

@@ -1991,7 +2000,7 @@ static int ctl_ioctl(struct file *file,
 	 * Check the interface version passed in.  This also
 	 * writes out the kernel's interface version.
 	 */
-	r = check_version(cmd, user);
+	r = check_version(cmd, user, &param_kernel);
 	if (r)
 		return r;
 

From: Bas Nieuwenhuizen <[email protected]>

commit a2b308044dcaca8d3e580959a4f867a1d5c37fac upstream.

None have been defined yet, so reject anybody setting any. Mesa sets it to 0 anyway.

---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c |    4 ++++
 1 file changed, 4 insertions(+)

@@ -2368,6 +2368,10 @@ int amdgpu_vm_ioctl(struct drm_device *d
 	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	int r;
 
+	/* No valid flags defined yet */
+	if (args->in.flags)
+		return -EINVAL;
+
 	switch (args->in.op) {
 	case AMDGPU_VM_OP_RESERVE_VMID:
 		/* We only have requirement to reserve vmid from gfxhub */