6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Peng Fan peng.fan@nxp.com

commit dc98d76a15bc29a9a4e76f2f65f39f3e590fb15c upstream.

With "earlycon initcall_debug=1 loglevel=8" in bootargs, kernel sometimes boot hang. It is because normal console still is not ready, but runtime suspend is called, so early console putchar will hang in waiting TRDE set in UARTSTAT.

The lpuart driver has auto suspend delay set to 3000ms, but during uart_add_one_port, a child device serial ctrl will added and probed with its pm runtime enabled(see serial_ctrl.c). The runtime suspend call path is: device_add |-> bus_probe_device |->device_initial_probe |->__device_attach |-> pm_runtime_get_sync(dev->parent); |-> pm_request_idle(dev); |-> pm_runtime_put(dev->parent);

So in the end, before normal console ready, the lpuart get runtime suspended. And earlycon putchar will hang.

To address the issue, mark last busy just after pm_runtime_enable, three seconds is long enough to switch from bootconsole to normal console.

Fixes: 43543e6f539b ("tty: serial: fsl_lpuart: Add runtime pm support") Cc: stable stable@kernel.org Signed-off-by: Peng Fan peng.fan@nxp.com Link: https://lore.kernel.org/r/20240808140325.580105-1-peng.fan@oss.nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/tty/serial/fsl_lpuart.c | 1 + 1 file changed, 1 insertion(+)

--- a/drivers/tty/serial/fsl_lpuart.c +++ b/drivers/tty/serial/fsl_lpuart.c @@ -2930,6 +2930,7 @@ static int lpuart_probe(struct platform_ pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT); pm_runtime_set_active(&pdev->dev); pm_runtime_enable(&pdev->dev); + pm_runtime_mark_last_busy(&pdev->dev);

ret = lpuart_global_reset(sport); if (ret)

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 779bac9994452f6a894524f70c00cfb0cd4b6364 upstream.

This reverts commit 0e6b6dedf168 ("Revert "ACPI: EC: Evaluate orphan _REG under EC device") because the problem addressed by it will be addressed differently in what follows.

Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Hans de Goede hdegoede@redhat.com Cc: All applicable stable@vger.kernel.org Link: https://patch.msgid.link/3236716.5fSG56mABF@rjwysocki.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/acpica/acevents.h | 4 --- drivers/acpi/acpica/evregion.c | 6 +++- drivers/acpi/acpica/evxfregn.c | 54 ----------------------------------------- drivers/acpi/ec.c | 3 -- include/acpi/acpixf.h | 4 --- 5 files changed, 5 insertions(+), 66 deletions(-)

--- a/drivers/acpi/acpica/acevents.h +++ b/drivers/acpi/acpica/acevents.h @@ -191,10 +191,6 @@ void acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, acpi_adr_space_type space_id, u32 function);

-void -acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node, - acpi_adr_space_type space_id); - acpi_status acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);

--- a/drivers/acpi/acpica/evregion.c +++ b/drivers/acpi/acpica/evregion.c @@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_space

/* Local prototypes */

+static void +acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, + acpi_adr_space_type space_id); + static acpi_status acpi_ev_reg_run(acpi_handle obj_handle, u32 level, void *context, void **return_value); @@ -814,7 +818,7 @@ acpi_ev_reg_run(acpi_handle obj_handle, * ******************************************************************************/

-void +static void acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node, acpi_adr_space_type space_id) { --- a/drivers/acpi/acpica/evxfregn.c +++ b/drivers/acpi/acpica/evxfregn.c @@ -306,57 +306,3 @@ acpi_execute_reg_methods(acpi_handle dev }

ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods) - -/******************************************************************************* - * - * FUNCTION: acpi_execute_orphan_reg_method - * - * PARAMETERS: device - Handle for the device - * space_id - The address space ID - * - * RETURN: Status - * - * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI - * device. This is a _REG method that has no corresponding region - * within the device's scope. - * - ******************************************************************************/ -acpi_status -acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id) -{ - struct acpi_namespace_node *node; - acpi_status status; - - ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method); - - /* Parameter validation */ - - if (!device) { - return_ACPI_STATUS(AE_BAD_PARAMETER); - } - - status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE); - if (ACPI_FAILURE(status)) { - return_ACPI_STATUS(status); - } - - /* Convert and validate the device handle */ - - node = acpi_ns_validate_handle(device); - if (node) { - - /* - * If an "orphan" _REG method is present in the device's scope - * for the given address space ID, run it. - */ - - acpi_ev_execute_orphan_reg_method(node, space_id); - } else { - status = AE_BAD_PARAMETER; - } - - (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE); - return_ACPI_STATUS(status); -} - -ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method) --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1507,9 +1507,6 @@ static int ec_install_handlers(struct ac

if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC); - if (scope_handle != ec->handle) - acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC); - set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); }

--- a/include/acpi/acpixf.h +++ b/include/acpi/acpixf.h @@ -663,10 +663,6 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status - acpi_execute_orphan_reg_method(acpi_handle device, - acpi_adr_space_type - space_id)) -ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_remove_address_space_handler(acpi_handle device, acpi_adr_space_type

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Xu Yang xu.yang_2@nxp.com

commit 21ea1ce37fc267dc45fe27517bbde926211683df upstream.

This reverts commit bf20c69cf3cf9c6445c4925dd9a8a6ca1b78bfdf.

During tcpm_init() stage, if the VBUS is still present after tcpm_reset_port(), then we assume that VBUS will off and goto safe0v after a specific discharge time. Following a TCPM_VBUS_EVENT event if VBUS reach to off state. TCPM_VBUS_EVENT event may be set during PORT_RESET handling stage. If pd_events reset to 0 after TCPM_VBUS_EVENT set, we will lost this VBUS event. Then the port state machine may stuck at one state.

Before:

[ 2.570172] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev1 NONE_AMS] [ 2.570179] state change PORT_RESET -> PORT_RESET_WAIT_OFF [delayed 100 ms] [ 2.570182] pending state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED @ 920 ms [rev1 NONE_AMS] [ 3.490213] state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED [delayed 920 ms] [ 3.490220] Start toggling [ 3.546050] CC1: 0 -> 0, CC2: 0 -> 2 [state TOGGLING, polarity 0, connected] [ 3.546057] state change TOGGLING -> SRC_ATTACH_WAIT [rev1 NONE_AMS]

After revert this patch, we can see VBUS off event and the port will goto expected state.

[ 2.441992] pending state change PORT_RESET -> PORT_RESET_WAIT_OFF @ 100 ms [rev1 NONE_AMS] [ 2.441999] state change PORT_RESET -> PORT_RESET_WAIT_OFF [delayed 100 ms] [ 2.442002] pending state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED @ 920 ms [rev1 NONE_AMS] [ 2.442122] VBUS off [ 2.442125] state change PORT_RESET_WAIT_OFF -> SNK_UNATTACHED [rev1 NONE_AMS] [ 2.442127] VBUS VSAFE0V [ 2.442351] CC1: 0 -> 0, CC2: 0 -> 0 [state SNK_UNATTACHED, polarity 0, disconnected] [ 2.442357] Start toggling [ 2.491850] CC1: 0 -> 0, CC2: 0 -> 2 [state TOGGLING, polarity 0, connected] [ 2.491858] state change TOGGLING -> SRC_ATTACH_WAIT [rev1 NONE_AMS] [ 2.491863] pending state change SRC_ATTACH_WAIT -> SNK_TRY @ 200 ms [rev1 NONE_AMS] [ 2.691905] state change SRC_ATTACH_WAIT -> SNK_TRY [delayed 200 ms]

Fixes: bf20c69cf3cf ("usb: typec: tcpm: clear pd_event queue in PORT_RESET") Cc: stable@vger.kernel.org Signed-off-by: Xu Yang xu.yang_2@nxp.com Acked-by: Heikki Krogerus heikki.krogerus@linux.intel.com Link: https://lore.kernel.org/r/20240809112901.535072-1-xu.yang_2@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/typec/tcpm/tcpm.c | 1 - 1 file changed, 1 deletion(-)

--- a/drivers/usb/typec/tcpm/tcpm.c +++ b/drivers/usb/typec/tcpm/tcpm.c @@ -4880,7 +4880,6 @@ static void run_state_machine(struct tcp break; case PORT_RESET: tcpm_reset_port(port); - port->pd_events = 0; if (port->self_powered) tcpm_set_cc(port, TYPEC_CC_OPEN); else

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Jann Horn jannh@google.com

commit 3c0da3d163eb32f1f91891efaade027fa9b245b9 upstream.

fuse_notify_store(), unlike fuse_do_readpage(), does not enable page zeroing (because it can be used to change partial page contents).

So fuse_notify_store() must be more careful to fully initialize page contents (including parts of the page that are beyond end-of-file) before marking the page uptodate.

The current code can leave beyond-EOF page contents uninitialized, which makes these uninitialized page contents visible to userspace via mmap().

This is an information leak, but only affects systems which do not enable init-on-alloc (via CONFIG_INIT_ON_ALLOC_DEFAULT_ON=y or the corresponding kernel command line parameter).

Link: https://bugs.chromium.org/p/project-zero/issues/detail?id=2574 Cc: stable@kernel.org Fixes: a1d75f258230 ("fuse: add store request") Signed-off-by: Jann Horn jannh@google.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/fuse/dev.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

--- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1618,9 +1618,11 @@ static int fuse_notify_store(struct fuse

this_num = min_t(unsigned, num, PAGE_SIZE - offset); err = fuse_copy_page(cs, &page, offset, this_num, 0); - if (!err && offset == 0 && - (this_num == PAGE_SIZE || file_size == end)) + if (!PageUptodate(page) && !err && offset == 0 && + (this_num == PAGE_SIZE || file_size == end)) { + zero_user_segment(page, this_num, PAGE_SIZE); SetPageUptodate(page); + } unlock_page(page); put_page(page);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Eli Billauer eli.billauer@gmail.com

commit ad899c301c880766cc709aad277991b3ab671b66 upstream.

As the wakeup work item now runs on a separate workqueue, it needs to be flushed separately along with flushing the device's workqueue.

Also, move the destroy_workqueue() call to the end of the exit method, so that deinitialization is done in the opposite order of initialization.

Fixes: ccbde4b128ef ("char: xillybus: Don't destroy workqueue from work item running on it") Cc: stable stable@kernel.org Signed-off-by: Eli Billauer eli.billauer@gmail.com Link: https://lore.kernel.org/r/20240816070200.50695-1-eli.billauer@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/char/xillybus/xillyusb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

--- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -2093,9 +2093,11 @@ static int xillyusb_discovery(struct usb * just after responding with the IDT, there is no reason for any * work item to be running now. To be sure that xdev->channels * is updated on anything that might run in parallel, flush the - * workqueue, which rarely does anything. + * device's workqueue and the wakeup work item. This rarely + * does anything. */ flush_workqueue(xdev->workq); + flush_work(&xdev->wakeup_workitem);

xdev->num_channels = num_channels;

@@ -2274,9 +2276,9 @@ static int __init xillyusb_init(void)

static void __exit xillyusb_exit(void) { - destroy_workqueue(wakeup_wq); - usb_deregister(&xillyusb_driver); + + destroy_workqueue(wakeup_wq); }

module_init(xillyusb_init);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Lianqin Hu hulianqin@vivo.com

commit 004eb8ba776ccd3e296ea6f78f7ae7985b12824e upstream.

Audio control requests that sets sampling frequency sometimes fail on this card. Adding delay between control messages eliminates that problem.

Signed-off-by: Lianqin Hu hulianqin@vivo.com Cc: stable@vger.kernel.org Link: https://patch.msgid.link/TYUPR06MB6217FF67076AF3E49E12C877D2842@TYUPR06MB621... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+)

--- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -2181,6 +2181,8 @@ static const struct usb_audio_quirk_flag QUIRK_FLAG_GENERIC_IMPLICIT_FB), DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */ QUIRK_FLAG_GENERIC_IMPLICIT_FB), + DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */ + QUIRK_FLAG_CTL_MSG_DELAY_1M), DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */ QUIRK_FLAG_IGNORE_CTL_ERROR), DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Mathias Nyman mathias.nyman@linux.intel.com

commit af8e119f52e9c13e556be9e03f27957554a84656 upstream.

re-enumerating full-speed devices after a failed address device command can trigger a NULL pointer dereference.

Full-speed devices may need to reconfigure the endpoint 0 Max Packet Size value during enumeration. Usb core calls usb_ep0_reinit() in this case, which ends up calling xhci_configure_endpoint().

On Panther point xHC the xhci_configure_endpoint() function will additionally check and reserve bandwidth in software. Other hosts do this in hardware

If xHC address device command fails then a new xhci_virt_device structure is allocated as part of re-enabling the slot, but the bandwidth table pointers are not set up properly here. This triggers the NULL pointer dereference the next time usb_ep0_reinit() is called and xhci_configure_endpoint() tries to check and reserve bandwidth

[46710.713538] usb 3-1: new full-speed USB device number 5 using xhci_hcd [46710.713699] usb 3-1: Device not responding to setup address. [46710.917684] usb 3-1: Device not responding to setup address. [46711.125536] usb 3-1: device not accepting address 5, error -71 [46711.125594] BUG: kernel NULL pointer dereference, address: 0000000000000008 [46711.125600] #PF: supervisor read access in kernel mode [46711.125603] #PF: error_code(0x0000) - not-present page [46711.125606] PGD 0 P4D 0 [46711.125610] Oops: Oops: 0000 [#1] PREEMPT SMP PTI [46711.125615] CPU: 1 PID: 25760 Comm: kworker/1:2 Not tainted 6.10.3_2 #1 [46711.125620] Hardware name: Gigabyte Technology Co., Ltd. [46711.125623] Workqueue: usb_hub_wq hub_event [usbcore] [46711.125668] RIP: 0010:xhci_reserve_bandwidth (drivers/usb/host/xhci.c

Fix this by making sure bandwidth table pointers are set up correctly after a failed address device command, and additionally by avoiding checking for bandwidth in cases like this where no actual endpoints are added or removed, i.e. only context for default control endpoint 0 is evaluated.

Reported-by: Karel Balej balejk@matfyz.cz Closes: https://lore.kernel.org/linux-usb/D3CKQQAETH47.1MUO22RTCH2O3@matfyz.cz/ Cc: stable@vger.kernel.org Fixes: 651aaf36a7d7 ("usb: xhci: Handle USB transaction error on address command") Signed-off-by: Mathias Nyman mathias.nyman@linux.intel.com Link: https://lore.kernel.org/r/20240815141117.2702314-2-mathias.nyman@linux.intel... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/usb/host/xhci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)

--- a/drivers/usb/host/xhci.c +++ b/drivers/usb/host/xhci.c @@ -2808,7 +2808,7 @@ static int xhci_configure_endpoint(struc xhci->num_active_eps); return -ENOMEM; } - if ((xhci->quirks & XHCI_SW_BW_CHECKING) && + if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change && xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) { if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK)) xhci_free_host_resources(xhci, ctrl_ctx); @@ -4150,8 +4150,10 @@ static int xhci_setup_device(struct usb_ mutex_unlock(&xhci->mutex); ret = xhci_disable_slot(xhci, udev->slot_id); xhci_free_virt_device(xhci, udev->slot_id); - if (!ret) - xhci_alloc_dev(hcd, udev); + if (!ret) { + if (xhci_alloc_dev(hcd, udev) == 1) + xhci_setup_addressable_virt_dev(xhci, udev); + } kfree(command->completion); kfree(command); return -EPROTO;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Baojun Xu baojun.xu@ti.com

commit 3beddef84d90590270465a907de1cfe2539ac70d upstream.

Wrong calibration data order cause sound too low in some device. Fix wrong calibrated data order, add calibration data converssion by get_unaligned_be32() after reading from UEFI.

Fixes: 5be27f1e3ec9 ("ALSA: hda/tas2781: Add tas2781 HDA driver") Cc: stable@vger.kernel.org Signed-off-by: Baojun Xu baojun.xu@ti.com Link: https://patch.msgid.link/20240813043749.108-1-shenghao-ding@ti.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- sound/pci/hda/tas2781_hda_i2c.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)

--- a/sound/pci/hda/tas2781_hda_i2c.c +++ b/sound/pci/hda/tas2781_hda_i2c.c @@ -2,10 +2,12 @@ // // TAS2781 HDA I2C driver // -// Copyright 2023 Texas Instruments, Inc. +// Copyright 2023 - 2024 Texas Instruments, Inc. // // Author: Shenghao Ding shenghao-ding@ti.com +// Current maintainer: Baojun Xu baojun.xu@ti.com

+#include <asm/unaligned.h> #include <linux/acpi.h> #include <linux/crc8.h> #include <linux/crc32.h> @@ -425,20 +427,22 @@ static void tas2781_apply_calib(struct t static const unsigned char rgno_array[CALIB_MAX] = { 0x74, 0x0c, 0x14, 0x70, 0x7c, }; - unsigned char *data; + int offset = 0; int i, j, rc; + __be32 data;

for (i = 0; i < tas_priv->ndev; i++) { - data = tas_priv->cali_data.data + - i * TASDEVICE_SPEAKER_CALIBRATION_SIZE; for (j = 0; j < CALIB_MAX; j++) { + data = get_unaligned_be32( + &tas_priv->cali_data.data[offset]); rc = tasdevice_dev_bulk_write(tas_priv, i, TASDEVICE_REG(0, page_array[j], rgno_array[j]), - &(data[4 * j]), 4); + (unsigned char *)&data, 4); if (rc < 0) dev_err(tas_priv->dev, "chn %d calib %d bulk_wr err = %d\n", i, j, rc); + offset += 4; } } }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Michael Mueller mimu@linux.ibm.com

commit 5a44bb061d04b0306f2aa8add761d86d152b9377 upstream.

We might run into a SIE validity if gisa has been disabled either via using kernel parameter "kvm.use_gisa=0" or by setting the related sysfs attribute to N (echo N >/sys/module/kvm/parameters/use_gisa).

The validity is caused by an invalid value in the SIE control block's gisa designation. That happens because we pass the uninitialized gisa origin to virt_to_phys() before writing it to the gisa designation.

To fix this we return 0 in kvm_s390_get_gisa_desc() if the origin is 0. kvm_s390_get_gisa_desc() is used to determine which gisa designation to set in the SIE control block. A value of 0 in the gisa designation disables gisa usage.

The issue surfaces in the host kernel with the following kernel message as soon a new kvm guest start is attemted.

kvm: unhandled validity intercept 0x1011 WARNING: CPU: 0 PID: 781237 at arch/s390/kvm/intercept.c:101 kvm_handle_sie_intercept+0x42e/0x4d0 [kvm] Modules linked in: vhost_net tap tun xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT xt_tcpudp nft_compat x_tables nf_nat_tftp nf_conntrack_tftp vfio_pci_core irqbypass vhost_vsock vmw_vsock_virtio_transport_common vsock vhost vhost_iotlb kvm nft_fib_inet nft_fib_ipv4 nft_fib_ipv6 nft_fib nft_reject_inet nf_reject_ipv4 nf_reject_ipv6 nft_reject nft_ct nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ip_set nf_tables sunrpc mlx5_ib ib_uverbs ib_core mlx5_core uvdevice s390_trng eadm_sch vfio_ccw zcrypt_cex4 mdev vfio_iommu_type1 vfio sch_fq_codel drm i2c_core loop drm_panel_orientation_quirks configfs nfnetlink lcs ctcm fsm dm_service_time ghash_s390 prng chacha_s390 libchacha aes_s390 des_s390 libdes sha3_512_s390 sha3_256_s390 sha512_s390 sha256_s390 sha1_s390 sha_common dm_mirror dm_region_hash dm_log zfcp scsi_transport_fc scsi_dh_rdac scsi_dh_emc scsi_dh_alua pkey zcrypt dm_multipath rng_core autofs4 [last unloaded: vfio_pci] CPU: 0 PID: 781237 Comm: CPU 0/KVM Not tainted 6.10.0-08682-gcad9f11498ea #6 Hardware name: IBM 3931 A01 701 (LPAR) Krnl PSW : 0704c00180000000 000003d93deb0122 (kvm_handle_sie_intercept+0x432/0x4d0 [kvm]) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 Krnl GPRS: 000003d900000027 000003d900000023 0000000000000028 000002cd00000000 000002d063a00900 00000359c6daf708 00000000000bebb5 0000000000001eff 000002cfd82e9000 000002cfd80bc000 0000000000001011 000003d93deda412 000003ff8962df98 000003d93de77ce0 000003d93deb011e 00000359c6daf960 Krnl Code: 000003d93deb0112: c020fffe7259 larl %r2,000003d93de7e5c4 000003d93deb0118: c0e53fa8beac brasl %r14,000003d9bd3c7e70 #000003d93deb011e: af000000 mc 0,0 >000003d93deb0122: a728ffea lhi %r2,-22 000003d93deb0126: a7f4fe24 brc 15,000003d93deafd6e 000003d93deb012a: 9101f0b0 tm 176(%r15),1 000003d93deb012e: a774fe48 brc 7,000003d93deafdbe 000003d93deb0132: 40a0f0ae sth %r10,174(%r15) Call Trace: [<000003d93deb0122>] kvm_handle_sie_intercept+0x432/0x4d0 [kvm] ([<000003d93deb011e>] kvm_handle_sie_intercept+0x42e/0x4d0 [kvm]) [<000003d93deacc10>] vcpu_post_run+0x1d0/0x3b0 [kvm] [<000003d93deaceda>] __vcpu_run+0xea/0x2d0 [kvm] [<000003d93dead9da>] kvm_arch_vcpu_ioctl_run+0x16a/0x430 [kvm] [<000003d93de93ee0>] kvm_vcpu_ioctl+0x190/0x7c0 [kvm] [<000003d9bd728b4e>] vfs_ioctl+0x2e/0x70 [<000003d9bd72a092>] __s390x_sys_ioctl+0xc2/0xd0 [<000003d9be0e9222>] __do_syscall+0x1f2/0x2e0 [<000003d9be0f9a90>] system_call+0x70/0x98 Last Breaking-Event-Address: [<000003d9bd3c7f58>] __warn_printk+0xe8/0xf0

Cc: stable@vger.kernel.org Reported-by: Christian Borntraeger borntraeger@linux.ibm.com Fixes: fe0ef0030463 ("KVM: s390: sort out physical vs virtual pointers usage") Signed-off-by: Michael Mueller mimu@linux.ibm.com Tested-by: Christian Borntraeger borntraeger@linux.ibm.com Reviewed-by: Janosch Frank frankja@linux.ibm.com Link: https://lore.kernel.org/r/20240801123109.2782155-1-mimu@linux.ibm.com Message-ID: 20240801123109.2782155-1-mimu@linux.ibm.com Signed-off-by: Janosch Frank frankja@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/kvm/kvm-s390.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -249,7 +249,12 @@ static inline unsigned long kvm_s390_get

static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) { - u32 gd = virt_to_phys(kvm->arch.gisa_int.origin); + u32 gd; + + if (!kvm->arch.gisa_int.origin) + return 0; + + gd = virt_to_phys(kvm->arch.gisa_int.origin);

if (gd && sclp.has_gisaf) gd |= GISA_FORMAT1;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Breno Leitao leitao@debian.org

commit 14d069d92951a3e150c0a81f2ca3b93e54da913b upstream.

On ACPI machines, the tegra i2c module encounters an issue due to a mutex being called inside a spinlock. This leads to the following bug:

BUG: sleeping function called from invalid context at kernel/locking/mutex.c:585 ...

Call trace: __might_sleep __mutex_lock_common mutex_lock_nested acpi_subsys_runtime_resume rpm_resume tegra_i2c_xfer

The problem arises because during __pm_runtime_resume(), the spinlock &dev->power.lock is acquired before rpm_resume() is called. Later, rpm_resume() invokes acpi_subsys_runtime_resume(), which relies on mutexes, triggering the error.

To address this issue, devices on ACPI are now marked as not IRQ-safe, considering the dependency of acpi_subsys_runtime_resume() on mutexes.

Fixes: bd2fdedbf2ba ("i2c: tegra: Add the ACPI support") Cc: stable@vger.kernel.org # v5.17+ Co-developed-by: Michael van der Westhuizen rmikey@meta.com Signed-off-by: Michael van der Westhuizen rmikey@meta.com Signed-off-by: Breno Leitao leitao@debian.org Reviewed-by: Dmitry Osipenko digetx@gmail.com Reviewed-by: Andy Shevchenko andy@kernel.org Signed-off-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/i2c/busses/i2c-tegra.c +++ b/drivers/i2c/busses/i2c-tegra.c @@ -1804,9 +1804,9 @@ static int tegra_i2c_probe(struct platfo * domain. * * VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't - * be used for atomic transfers. + * be used for atomic transfers. ACPI device is not IRQ safe also. */ - if (!IS_VI(i2c_dev)) + if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev)) pm_runtime_irq_safe(i2c_dev->dev);

pm_runtime_enable(i2c_dev->dev);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Rafael J. Wysocki rafael.j.wysocki@intel.com

commit 71bf41b8e913ec9fc91f0d39ab8fb320229ec604 upstream.

Commit 60fa6ae6e6d0 ("ACPI: EC: Install address space handler at the namespace root") caused _REG methods for EC operation regions outside the EC device scope to be evaluated which on some systems leads to the evaluation of _REG methods in the scopes of device objects representing devices that are not present and not functional according to the _STA return values. Some of those device objects represent EC "alternatives" and if _REG is evaluated for their operation regions, the platform firmware may be confused and the platform may start to behave incorrectly.

To avoid this problem, only evaluate _REG for EC operation regions located in the scopes of device objects representing known-to-be-present devices.

For this purpose, partially revert commit 60fa6ae6e6d0 and trigger the evaluation of _REG for EC operation regions from acpi_bus_attach() for the known-valid devices.

Fixes: 60fa6ae6e6d0 ("ACPI: EC: Install address space handler at the namespace root") Link: https://lore.kernel.org/linux-acpi/1f76b7e2-1928-4598-8037-28a1785c2d13@redh... Link: https://bugzilla.redhat.com/show_bug.cgi?id=2298938 Link: https://bugzilla.redhat.com/show_bug.cgi?id=2302253 Reported-by: Hans de Goede hdegoede@redhat.com Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Reviewed-by: Hans de Goede hdegoede@redhat.com Cc: All applicable stable@vger.kernel.org Link: https://patch.msgid.link/23612351.6Emhk5qWAg@rjwysocki.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/acpi/ec.c | 11 +++++++++-- drivers/acpi/internal.h | 1 + drivers/acpi/scan.c | 2 ++ 3 files changed, 12 insertions(+), 2 deletions(-)

--- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handl static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device, bool call_reg) { - acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; acpi_status status;

acpi_ec_start(ec, false);

if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) { + acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle; + acpi_ec_enter_noirq(ec); status = acpi_install_address_space_handler_no_reg(scope_handle, ACPI_ADR_SPACE_EC, @@ -1506,7 +1507,7 @@ static int ec_install_handlers(struct ac }

if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) { - acpi_execute_reg_methods(scope_handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); + acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC); set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags); }

@@ -1721,6 +1722,12 @@ static void acpi_ec_remove(struct acpi_d } }

+void acpi_ec_register_opregions(struct acpi_device *adev) +{ + if (first_ec && first_ec->handle != adev->handle) + acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC); +} + static acpi_status ec_parse_io_ports(struct acpi_resource *resource, void *context) { --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -204,6 +204,7 @@ int acpi_ec_add_query_handler(struct acp acpi_handle handle, acpi_ec_query_func func, void *data); void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit); +void acpi_ec_register_opregions(struct acpi_device *adev);

#ifdef CONFIG_PM_SLEEP void acpi_ec_flush_work(void); --- a/drivers/acpi/scan.c +++ b/drivers/acpi/scan.c @@ -2198,6 +2198,8 @@ static int acpi_bus_attach(struct acpi_d if (device->handler) goto ok;

+ acpi_ec_register_opregions(device); + if (!device->flags.initialized) { device->flags.power_manageable = device->power.states[ACPI_STATE_D0].flags.valid;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Khazhismel Kumykov khazhy@google.com

commit 7a636b4f03af9d541205f69e373672e7b2b60a8a upstream.

If the dm_resume method is called on a device that is not suspended, the method will suspend the device briefly, before resuming it (so that the table will be swapped).

However, there was a bug that the return value of dm_suspended_md was not checked. dm_suspended_md may return an error when it is interrupted by a signal. In this case, do_resume would call dm_swap_table, which would return -EINVAL.

This commit fixes the logic, so that error returned by dm_suspend is checked and the resume operation is undone.

Signed-off-by: Mikulas Patocka mpatocka@redhat.com Signed-off-by: Khazhismel Kumykov khazhy@google.com Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/dm-ioctl.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)

--- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1181,8 +1181,26 @@ static int do_resume(struct dm_ioctl *pa suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG; if (param->flags & DM_NOFLUSH_FLAG) suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG; - if (!dm_suspended_md(md)) - dm_suspend(md, suspend_flags); + if (!dm_suspended_md(md)) { + r = dm_suspend(md, suspend_flags); + if (r) { + down_write(&_hash_lock); + hc = dm_get_mdptr(md); + if (hc && !hc->new_map) { + hc->new_map = new_map; + new_map = NULL; + } else { + r = -ENXIO; + } + up_write(&_hash_lock); + if (new_map) { + dm_sync_table(md); + dm_table_destroy(new_map); + } + dm_put(md); + return r; + } + }

old_size = dm_get_size(md); old_map = dm_swap_table(md, new_map);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Zhihao Cheng chengzhihao1@huawei.com

commit 2a0629834cd82f05d424bbc193374f9a43d1f87d upstream.

The inode reclaiming process(See function prune_icache_sb) collects all reclaimable inodes and mark them with I_FREEING flag at first, at that time, other processes will be stuck if they try getting these inodes (See function find_inode_fast), then the reclaiming process destroy the inodes by function dispose_list(). Some filesystems(eg. ext4 with ea_inode feature, ubifs with xattr) may do inode lookup in the inode evicting callback function, if the inode lookup is operated under the inode lru traversing context, deadlock problems may happen.

Case 1: In function ext4_evict_inode(), the ea inode lookup could happen if ea_inode feature is enabled, the lookup process will be stuck under the evicting context like this:

1. File A has inode i_reg and an ea inode i_ea 2. getfattr(A, xattr_buf) // i_ea is added into lru // lru->i_ea 3. Then, following three processes running like this:

PA PB echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // i_reg is added into lru, lru->i_ea->i_reg prune_icache_sb list_lru_walk_one inode_lru_isolate i_ea->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(i_reg) spin_unlock(&i_reg->i_lock) spin_unlock(lru_lock) rm file A i_reg->nlink = 0 iput(i_reg) // i_reg->nlink is 0, do evict ext4_evict_inode ext4_xattr_delete_inode ext4_xattr_inode_dec_ref_all ext4_xattr_inode_iget ext4_iget(i_ea->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(i_ea) ----→ AA deadlock dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&i_ea->i_state)

Case 2: In deleted inode writing function ubifs_jnl_write_inode(), file deleting process holds BASEHD's wbuf->io_mutex while getting the xattr inode, which could race with inode reclaiming process(The reclaiming process could try locking BASEHD's wbuf->io_mutex in inode evicting function), then an ABBA deadlock problem would happen as following:

1. File A has inode ia and a xattr(with inode ixa), regular file B has inode ib and a xattr. 2. getfattr(A, xattr_buf) // ixa is added into lru // lru->ixa 3. Then, following three processes running like this:

PA PB PC echo 2 > /proc/sys/vm/drop_caches shrink_slab prune_dcache_sb // ib and ia are added into lru, lru->ixa->ib->ia prune_icache_sb list_lru_walk_one inode_lru_isolate ixa->i_state |= I_FREEING // set inode state inode_lru_isolate __iget(ib) spin_unlock(&ib->i_lock) spin_unlock(lru_lock) rm file B ib->nlink = 0 rm file A iput(ia) ubifs_evict_inode(ia) ubifs_jnl_delete_inode(ia) ubifs_jnl_write_inode(ia) make_reservation(BASEHD) // Lock wbuf->io_mutex ubifs_iget(ixa->i_ino) iget_locked find_inode_fast __wait_on_freeing_inode(ixa) | iput(ib) // ib->nlink is 0, do evict | ubifs_evict_inode | ubifs_jnl_delete_inode(ib) ↓ ubifs_jnl_write_inode ABBA deadlock ←-----make_reservation(BASEHD) dispose_list // cannot be executed by prune_icache_sb wake_up_bit(&ixa->i_state)

Fix the possible deadlock by using new inode state flag I_LRU_ISOLATING to pin the inode in memory while inode_lru_isolate() reclaims its pages instead of using ordinary inode reference. This way inode deletion cannot be triggered from inode_lru_isolate() thus avoiding the deadlock. evict() is made to wait for I_LRU_ISOLATING to be cleared before proceeding with inode cleanup.

Link: https://lore.kernel.org/all/37c29c42-7685-d1f0-067d-63582ffac405@huaweicloud... Link: https://bugzilla.kernel.org/show_bug.cgi?id=219022 Fixes: e50e5129f384 ("ext4: xattr-in-inode support") Fixes: 7959cf3a7506 ("ubifs: journal: Handle xattrs like files") Cc: stable@vger.kernel.org Signed-off-by: Zhihao Cheng chengzhihao1@huawei.com Link: https://lore.kernel.org/r/20240809031628.1069873-1-chengzhihao@huaweicloud.c... Reviewed-by: Jan Kara jack@suse.cz Suggested-by: Jan Kara jack@suse.cz Suggested-by: Mateusz Guzik mjguzik@gmail.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/inode.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 5 +++++ 2 files changed, 42 insertions(+), 2 deletions(-)

--- a/fs/inode.c +++ b/fs/inode.c @@ -486,6 +486,39 @@ static void inode_lru_list_del(struct in this_cpu_dec(nr_unused); }

+static void inode_pin_lru_isolating(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); + inode->i_state |= I_LRU_ISOLATING; +} + +static void inode_unpin_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); + inode->i_state &= ~I_LRU_ISOLATING; + smp_mb(); + wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); +} + +static void inode_wait_for_lru_isolating(struct inode *inode) +{ + spin_lock(&inode->i_lock); + if (inode->i_state & I_LRU_ISOLATING) { + DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); + wait_queue_head_t *wqh; + + wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); + spin_unlock(&inode->i_lock); + __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); + spin_lock(&inode->i_lock); + WARN_ON(inode->i_state & I_LRU_ISOLATING); + } + spin_unlock(&inode->i_lock); +} + /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add @@ -654,6 +687,8 @@ static void evict(struct inode *inode)

inode_sb_list_del(inode);

+ inode_wait_for_lru_isolating(inode); + /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since @@ -842,7 +877,7 @@ static enum lru_status inode_lru_isolate * be under pressure before the cache inside the highmem zone. */ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) { - __iget(inode); + inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { @@ -854,7 +889,7 @@ static enum lru_status inode_lru_isolate __count_vm_events(PGINODESTEAL, reap); mm_account_reclaimed_pages(reap); } - iput(inode); + inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2265,6 +2265,9 @@ static inline void kiocb_clone(struct ki * * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback. * + * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding + * i_count. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -2288,6 +2291,8 @@ static inline void kiocb_clone(struct ki #define I_DONTCACHE (1 << 16) #define I_SYNC_QUEUED (1 << 17) #define I_PINNING_FSCACHE_WB (1 << 18) +#define __I_LRU_ISOLATING 19 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)

#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Alexander Lobakin aleksander.lobakin@intel.com

commit c1023f5634b9bfcbfff0dc200245309e3cde9b54 upstream.

bitmap_size() is a pretty generic name and one may want to use it for a generic bitmap API function. At the same time, its logic is not "generic", i.e. it's not just `nbits -> size of bitmap in bytes` converter as it would be expected from its name. Add the prefix 'idset_' used throughout the file where the function resides.

Reviewed-by: Przemek Kitszel przemyslaw.kitszel@intel.com Acked-by: Peter Oberparleiter oberpar@linux.ibm.com Signed-off-by: Alexander Lobakin aleksander.lobakin@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/s390/cio/idset.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

--- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -16,7 +16,7 @@ struct idset { unsigned long bitmap[]; };

-static inline unsigned long bitmap_size(int num_ssid, int num_id) +static inline unsigned long idset_bitmap_size(int num_ssid, int num_id) { return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long); } @@ -25,11 +25,12 @@ static struct idset *idset_new(int num_s { struct idset *set;

- set = vmalloc(sizeof(struct idset) + bitmap_size(num_ssid, num_id)); + set = vmalloc(sizeof(struct idset) + + idset_bitmap_size(num_ssid, num_id)); if (set) { set->num_ssid = num_ssid; set->num_id = num_id; - memset(set->bitmap, 0, bitmap_size(num_ssid, num_id)); + memset(set->bitmap, 0, idset_bitmap_size(num_ssid, num_id)); } return set; } @@ -41,7 +42,8 @@ void idset_free(struct idset *set)

void idset_fill(struct idset *set) { - memset(set->bitmap, 0xff, bitmap_size(set->num_ssid, set->num_id)); + memset(set->bitmap, 0xff, + idset_bitmap_size(set->num_ssid, set->num_id)); }

static inline void idset_add(struct idset *set, int ssid, int id)

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Alexander Lobakin aleksander.lobakin@intel.com

commit a37fbe666c016fd89e4460d0ebfcea05baba46dc upstream.

The number of times yet another open coded `BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge. Some generic helper is long overdue.

Add one, bitmap_size(), but with one detail. BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both divident and divisor are compile-time constants or when the divisor is not a pow-of-2. When it is however, the compilers sometimes tend to generate suboptimal code (GCC 13):

48 83 c0 3f add $0x3f,%rax 48 c1 e8 06 shr $0x6,%rax 48 8d 14 c5 00 00 00 00 lea 0x0(,%rax,8),%rdx

%BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does full division of `nbits + 63` by it and then multiplication by 8. Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC:

8d 50 3f lea 0x3f(%rax),%edx c1 ea 03 shr $0x3,%edx 81 e2 f8 ff ff 1f and $0x1ffffff8,%edx

Now it shifts `nbits + 63` by 3 positions (IOW performs fast division by 8) and then masks bits[2:0]. bloat-o-meter:

add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617)

Clang does it better and generates the same code before/after starting from -O1, except that with the ALIGN() approach it uses %edx and thus still saves some bytes:

add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520)

Note that we can't expand DIV_ROUND_UP() by adding a check and using this approach there, as it's used in array declarations where expressions are not allowed. Add this helper to tools/ as well.

Reviewed-by: Przemek Kitszel przemyslaw.kitszel@intel.com Acked-by: Yury Norov yury.norov@gmail.com Signed-off-by: Alexander Lobakin aleksander.lobakin@intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/md/dm-clone-metadata.c | 5 ----- drivers/s390/cio/idset.c | 2 +- include/linux/bitmap.h | 8 +++++--- include/linux/cpumask.h | 2 +- lib/math/prime_numbers.c | 2 -- tools/include/linux/bitmap.h | 7 ++++--- 6 files changed, 11 insertions(+), 15 deletions(-)

--- a/drivers/md/dm-clone-metadata.c +++ b/drivers/md/dm-clone-metadata.c @@ -465,11 +465,6 @@ static void __destroy_persistent_data_st

/*---------------------------------------------------------------------------*/

-static size_t bitmap_size(unsigned long nr_bits) -{ - return BITS_TO_LONGS(nr_bits) * sizeof(long); -} - static int __dirty_map_init(struct dirty_map *dmap, unsigned long nr_words, unsigned long nr_regions) { --- a/drivers/s390/cio/idset.c +++ b/drivers/s390/cio/idset.c @@ -18,7 +18,7 @@ struct idset {

static inline unsigned long idset_bitmap_size(int num_ssid, int num_id) { - return BITS_TO_LONGS(num_ssid * num_id) * sizeof(unsigned long); + return bitmap_size(size_mul(num_ssid, num_id)); }

static struct idset *idset_new(int num_ssid, int num_id) --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -237,9 +237,11 @@ extern int bitmap_print_list_to_buf(char #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))

+#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits);

if (small_const_nbits(nbits)) *dst = 0; @@ -249,7 +251,7 @@ static inline void bitmap_zero(unsigned

static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits);

if (small_const_nbits(nbits)) *dst = ~0UL; @@ -260,7 +262,7 @@ static inline void bitmap_fill(unsigned static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { - unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); + unsigned int len = bitmap_size(nbits);

if (small_const_nbits(nbits)) *dst = *src; --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -821,7 +821,7 @@ static inline int cpulist_parse(const ch */ static inline unsigned int cpumask_size(void) { - return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long); + return bitmap_size(large_cpumask_bits); }

/* --- a/lib/math/prime_numbers.c +++ b/lib/math/prime_numbers.c @@ -6,8 +6,6 @@ #include <linux/prime_numbers.h> #include <linux/slab.h>

-#define bitmap_size(nbits) (BITS_TO_LONGS(nbits) * sizeof(unsigned long)) - struct primes { struct rcu_head rcu; unsigned long last, sz; --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -25,13 +25,14 @@ bool __bitmap_intersects(const unsigned #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1))) #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))

+#define bitmap_size(nbits) (ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE) + static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { if (small_const_nbits(nbits)) *dst = 0UL; else { - int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + memset(dst, 0, bitmap_size(nbits)); } }

@@ -83,7 +84,7 @@ static inline void bitmap_or(unsigned lo */ static inline unsigned long *bitmap_zalloc(int nbits) { - return calloc(1, BITS_TO_LONGS(nbits) * sizeof(unsigned long)); + return calloc(1, bitmap_size(nbits)); }

/*

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Andi Shyti andi.shyti@kernel.org

commit 4e91fa1ef3ce6290b4c598e54b5eb6cf134fbec8 upstream.

Add the missing geni_icc_disable() call before returning in the geni_i2c_runtime_resume() function.

Commit 9ba48db9f77c ("i2c: qcom-geni: Add missing geni_icc_disable in geni_i2c_runtime_resume") by Gaosheng missed disabling the interconnect in one case.

Fixes: bf225ed357c6 ("i2c: i2c-qcom-geni: Add interconnect support") Cc: Gaosheng Cui cuigaosheng1@huawei.com Cc: stable@vger.kernel.org # v5.9+ Signed-off-by: Andi Shyti andi.shyti@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/i2c/busses/i2c-qcom-geni.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

--- a/drivers/i2c/busses/i2c-qcom-geni.c +++ b/drivers/i2c/busses/i2c-qcom-geni.c @@ -987,8 +987,10 @@ static int __maybe_unused geni_i2c_runti return ret;

ret = clk_prepare_enable(gi2c->core_clk); - if (ret) + if (ret) { + geni_icc_disable(&gi2c->se); return ret; + }

ret = geni_se_resources_on(&gi2c->se); if (ret) {

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Haiyang Zhang haiyangz@microsoft.com

commit 32316f676b4ee87c0404d333d248ccf777f739bc upstream.

The MANA driver's RX buffer alloc_size is passed into napi_build_skb() to create SKB. skb_shinfo(skb) is located at the end of skb, and its alignment is affected by the alloc_size passed into napi_build_skb(). The size needs to be aligned properly for better performance and atomic operations. Otherwise, on ARM64 CPU, for certain MTU settings like 4000, atomic operations may panic on the skb_shinfo(skb)->dataref due to alignment fault.

To fix this bug, add proper alignment to the alloc_size calculation.

Sample panic info: [ 253.298819] Unable to handle kernel paging request at virtual address ffff000129ba5cce [ 253.300900] Mem abort info: [ 253.301760] ESR = 0x0000000096000021 [ 253.302825] EC = 0x25: DABT (current EL), IL = 32 bits [ 253.304268] SET = 0, FnV = 0 [ 253.305172] EA = 0, S1PTW = 0 [ 253.306103] FSC = 0x21: alignment fault Call trace: __skb_clone+0xfc/0x198 skb_clone+0x78/0xe0 raw6_local_deliver+0xfc/0x228 ip6_protocol_deliver_rcu+0x80/0x500 ip6_input_finish+0x48/0x80 ip6_input+0x48/0xc0 ip6_sublist_rcv_finish+0x50/0x78 ip6_sublist_rcv+0x1cc/0x2b8 ipv6_list_rcv+0x100/0x150 __netif_receive_skb_list_core+0x180/0x220 netif_receive_skb_list_internal+0x198/0x2a8 __napi_poll+0x138/0x250 net_rx_action+0x148/0x330 handle_softirqs+0x12c/0x3a0

Cc: stable@vger.kernel.org Fixes: 80f6215b450e ("net: mana: Add support for jumbo frame") Signed-off-by: Haiyang Zhang haiyangz@microsoft.com Reviewed-by: Long Li longli@microsoft.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/microsoft/mana/mana_en.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c index d2f07e179e86..ae717d06e66f 100644 --- a/drivers/net/ethernet/microsoft/mana/mana_en.c +++ b/drivers/net/ethernet/microsoft/mana/mana_en.c @@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size, else *headroom = XDP_PACKET_HEADROOM;

- *alloc_size = mtu + MANA_RXBUF_PAD + *headroom; + *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom); + + /* Using page pool in this case, so alloc_size is PAGE_SIZE */ + if (*alloc_size < PAGE_SIZE) + *alloc_size = PAGE_SIZE;

*datasize = mtu + ETH_HLEN; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Janne Grunau j@jannau.net

commit 2ad4e1ada8eebafa2d75a4b75eeeca882de6ada1 upstream.

wpa_supplicant 2.11 sends since 1efdba5fdc2c ("Handle PMKSA flush in the driver for SAE/OWE offload cases") SSID based PMKSA del commands. brcmfmac is not prepared and tries to dereference the NULL bssid and pmkid pointers in cfg80211_pmksa. PMKID_V3 operations support SSID based updates so copy the SSID.

Fixes: a96202acaea4 ("wifi: brcmfmac: cfg80211: Add support for PMKID_V3 operations") Cc: stable@vger.kernel.org # 6.4.x Signed-off-by: Janne Grunau j@jannau.net Reviewed-by: Neal Gompa neal@gompa.dev Acked-by: Arend van Spriel arend.vanspriel@broadcom.com Signed-off-by: Kalle Valo kvalo@kernel.org Link: https://patch.msgid.link/20240803-brcmfmac_pmksa_del_ssid-v1-1-4e85f19135e1@... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 13 +++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)

--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -4321,9 +4321,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, /* Single PMK operation */ pmk_op->count = cpu_to_le16(1); length += sizeof(struct brcmf_pmksa_v3); - memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); - memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); - pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + if (pmksa->bssid) + memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN); + if (pmksa->pmkid) { + memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN); + pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN; + } + if (pmksa->ssid && pmksa->ssid_len) { + memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len); + pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len; + } pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0); }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Zhen Lei thunder.leizhen@huawei.com

commit 379d9af3f3da2da1bbfa67baf1820c72a080d1f1 upstream.

The count increases only when a node is successfully added to the linked list.

Cc: stable@vger.kernel.org Fixes: fa1aa143ac4a ("selinux: extended permissions for ioctls") Signed-off-by: Zhen Lei thunder.leizhen@huawei.com Acked-by: Stephen Smalley stephen.smalley.work@gmail.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- security/selinux/avc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/security/selinux/avc.c +++ b/security/selinux/avc.c @@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struc { struct avc_xperms_decision_node *dest_xpd;

- node->ae.xp_node->xp.len++; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); + node->ae.xp_node->xp.len++; return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Waiman Long longman@redhat.com

commit d75abd0d0bc29e6ebfebbf76d11b4067b35844af upstream.

The memory_failure_cpu structure is a per-cpu structure. Access to its content requires the use of get_cpu_var() to lock in the current CPU and disable preemption. The use of a regular spinlock_t for locking purpose is fine for a non-RT kernel.

Since the integration of RT spinlock support into the v5.15 kernel, a spinlock_t in a RT kernel becomes a sleeping lock and taking a sleeping lock in a preemption disabled context is illegal resulting in the following kind of warning.

[12135.732244] BUG: sleeping function called from invalid context at kernel/locking/spinlock_rt.c:48 [12135.732248] in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 270076, name: kworker/0:0 [12135.732252] preempt_count: 1, expected: 0 [12135.732255] RCU nest depth: 2, expected: 2 : [12135.732420] Hardware name: Dell Inc. PowerEdge R640/0HG0J8, BIOS 2.10.2 02/24/2021 [12135.732423] Workqueue: kacpi_notify acpi_os_execute_deferred [12135.732433] Call Trace: [12135.732436] <TASK> [12135.732450] dump_stack_lvl+0x57/0x81 [12135.732461] __might_resched.cold+0xf4/0x12f [12135.732479] rt_spin_lock+0x4c/0x100 [12135.732491] memory_failure_queue+0x40/0xe0 [12135.732503] ghes_do_memory_failure+0x53/0x390 [12135.732516] ghes_do_proc.constprop.0+0x229/0x3e0 [12135.732575] ghes_proc+0xf9/0x1a0 [12135.732591] ghes_notify_hed+0x6a/0x150 [12135.732602] notifier_call_chain+0x43/0xb0 [12135.732626] blocking_notifier_call_chain+0x43/0x60 [12135.732637] acpi_ev_notify_dispatch+0x47/0x70 [12135.732648] acpi_os_execute_deferred+0x13/0x20 [12135.732654] process_one_work+0x41f/0x500 [12135.732695] worker_thread+0x192/0x360 [12135.732715] kthread+0x111/0x140 [12135.732733] ret_from_fork+0x29/0x50 [12135.732779] </TASK>

Fix it by using a raw_spinlock_t for locking instead.

Also move the pr_err() out of the lock critical section and after put_cpu_ptr() to avoid indeterminate latency and the possibility of sleep with this call.

[longman@redhat.com: don't hold percpu ref across pr_err(), per Miaohe] Link: https://lkml.kernel.org/r/20240807181130.1122660-1-longman@redhat.com Link: https://lkml.kernel.org/r/20240806164107.1044956-1-longman@redhat.com Fixes: 0f383b6dc96e ("locking/spinlock: Provide RT variant") Signed-off-by: Waiman Long longman@redhat.com Acked-by: Miaohe Lin linmiaohe@huawei.com Cc: "Huang, Ying" ying.huang@intel.com Cc: Juri Lelli juri.lelli@redhat.com Cc: Len Brown len.brown@intel.com Cc: Naoya Horiguchi nao.horiguchi@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory-failure.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

--- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2395,7 +2395,7 @@ struct memory_failure_entry { struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); - spinlock_t lock; + raw_spinlock_t lock; struct work_struct work; };

@@ -2421,20 +2421,22 @@ void memory_failure_queue(unsigned long { struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; + bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, };

mf_cpu = &get_cpu_var(memory_failure_cpu); - spin_lock_irqsave(&mf_cpu->lock, proc_flags); - if (kfifo_put(&mf_cpu->fifo, entry)) + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); + buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); + if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); - else + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + put_cpu_var(memory_failure_cpu); + if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); - put_cpu_var(memory_failure_cpu); } EXPORT_SYMBOL_GPL(memory_failure_queue);

@@ -2447,9 +2449,9 @@ static void memory_failure_work_func(str

mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { - spin_lock_irqsave(&mf_cpu->lock, proc_flags); + raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); - spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); + raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) @@ -2479,7 +2481,7 @@ static int __init memory_failure_init(vo

for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); - spin_lock_init(&mf_cpu->lock); + raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Naohiro Aota naohiro.aota@wdc.com

commit e30729d4bd4001881be4d1ad4332a5d4985398f8 upstream.

__btrfs_add_free_space_zoned() references and modifies bg's alloc_offset, ro, and zone_unusable, but without taking the lock. It is mostly safe because they monotonically increase (at least for now) and this function is mostly called by a transaction commit, which is serialized by itself.

Still, taking the lock is a safer and correct option and I'm going to add a change to reset zone_unusable while a block group is still alive. So, add locking around the operations.

Fixes: 169e0da91a21 ("btrfs: zoned: track unusable bytes for zones") CC: stable@vger.kernel.org # 5.15+ Reviewed-by: Johannes Thumshirn johannes.thumshirn@wdc.com Signed-off-by: Naohiro Aota naohiro.aota@wdc.com Reviewed-by: David Sterba dsterba@suse.com Signed-off-by: David Sterba dsterba@suse.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/btrfs/free-space-cache.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)

--- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2696,15 +2696,16 @@ static int __btrfs_add_free_space_zoned( u64 offset = bytenr - block_group->start; u64 to_free, to_unusable; int bg_reclaim_threshold = 0; - bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + bool initial; u64 reclaimable_unusable;

- WARN_ON(!initial && offset + size > block_group->zone_capacity); + spin_lock(&block_group->lock);

+ initial = ((size == block_group->length) && (block_group->alloc_offset == 0)); + WARN_ON(!initial && offset + size > block_group->zone_capacity); if (!initial) bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);

- spin_lock(&ctl->tree_lock); if (!used) to_free = size; else if (initial) @@ -2717,7 +2718,9 @@ static int __btrfs_add_free_space_zoned( to_free = offset + size - block_group->alloc_offset; to_unusable = size - to_free;

+ spin_lock(&ctl->tree_lock); ctl->free_space += to_free; + spin_unlock(&ctl->tree_lock); /* * If the block group is read-only, we should account freed space into * bytes_readonly. @@ -2726,11 +2729,8 @@ static int __btrfs_add_free_space_zoned( block_group->zone_unusable += to_unusable; WARN_ON(block_group->zone_unusable > block_group->length); } - spin_unlock(&ctl->tree_lock); if (!used) { - spin_lock(&block_group->lock); block_group->alloc_offset -= size; - spin_unlock(&block_group->lock); }

reclaimable_unusable = block_group->zone_unusable - @@ -2744,6 +2744,8 @@ static int __btrfs_add_free_space_zoned( btrfs_mark_bg_to_reclaim(block_group); }

+ spin_unlock(&block_group->lock); + return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Bas Nieuwenhuizen bas@basnieuwenhuizen.nl

commit 0573a1e2ea7e35bff08944a40f1adf2bb35cea61 upstream.

Missing validation ...

Checked libdrm and it clears all the structs, so we should be safe to just check everything.

Signed-off-by: Bas Nieuwenhuizen bas@basnieuwenhuizen.nl Signed-off-by: Alex Deucher alexander.deucher@amd.com (cherry picked from commit c6b86421f1f9ddf9d706f2453159813ee39d0cf9) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 8 ++++++++ 1 file changed, 8 insertions(+)

--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -684,16 +684,24 @@ int amdgpu_ctx_ioctl(struct drm_device *

switch (args->in.op) { case AMDGPU_CTX_OP_ALLOC_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id); args->out.alloc.ctx_id = id; break; case AMDGPU_CTX_OP_FREE_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_free(fpriv, id); break; case AMDGPU_CTX_OP_QUERY_STATE: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_QUERY_STATE2: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query2(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_GET_STABLE_PSTATE:

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Alex Deucher alexander.deucher@amd.com

commit e414a304f2c5368a84f03ad34d29b89f965a33c9 upstream.

This needs to be set as well if the IB uses atomics.

Reviewed-by: Leo Liu leo.liu@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com (cherry picked from commit 35c628774e50b3784c59e8ca7973f03bcb067132) Cc: stable@vger.kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -543,11 +543,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct a

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));

amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0));

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Claudio Imbrenda imbrenda@linux.ibm.com

[ Upstream commit cff59d8631e1409ffdd22d9d717e15810181b32c ]

The return value uv_set_shared() and uv_remove_shared() (which are wrappers around the share() function) is not always checked. The system integrity of a protected guest depends on the Share and Unshare UVCs being successful. This means that any caller that fails to check the return value will compromise the security of the protected guest.

No code path that would lead to such violation of the security guarantees is currently exercised, since all the areas that are shared never get unshared during the lifetime of the system. This might change and become an issue in the future.

The Share and Unshare UVCs can only fail in case of hypervisor misbehaviour (either a bug or malicious behaviour). In such cases there is no reasonable way forward, and the system needs to panic.

This patch replaces the return at the end of the share() function with a panic, to guarantee system integrity.

Fixes: 5abb9351dfd9 ("s390/uv: introduce guest side ultravisor code") Signed-off-by: Claudio Imbrenda imbrenda@linux.ibm.com Reviewed-by: Christian Borntraeger borntraeger@linux.ibm.com Reviewed-by: Steffen Eiden seiden@linux.ibm.com Reviewed-by: Janosch Frank frankja@linux.ibm.com Link: https://lore.kernel.org/r/20240801112548.85303-1-imbrenda@linux.ibm.com Message-ID: 20240801112548.85303-1-imbrenda@linux.ibm.com [frankja@linux.ibm.com: Fixed up patch subject] Signed-off-by: Janosch Frank frankja@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/s390/include/asm/uv.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index 0e7bd3873907f..b2e2f9a4163c5 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -442,7 +442,10 @@ static inline int share(unsigned long addr, u16 cmd)

if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); }

/*

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Faizal Rahim faizal.abdul.rahim@linux.intel.com

[ Upstream commit e037a26ead187901f83cad9c503ccece5ff6817a ]

Testing uncovered that even when the taprio gate is closed, some packets still transmit.

According to i225/6 hardware errata [1], traffic might overflow the planned QBV window. This happens because MAC maintains an internal buffer, primarily for supporting half duplex retries. Therefore, even when the gate closes, residual MAC data in the buffer may still transmit.

To mitigate this for i226, reduce the MAC's internal buffer from 192 bytes to the recommended 88 bytes by modifying the RETX_CTL register value.

This follows guidelines from: [1] Ethernet Controller I225/I22 Spec Update Rev 2.1 Errata Item 9: TSN: Packet Transmission Might Cross Qbv Window [2] I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control

Note that the RETX_CTL register can't be used in TSN mode because half duplex feature cannot coexist with TSN.

Test Steps: 1. Send taprio cmd to board A: tc qdisc replace dev enp1s0 parent root handle 100 taprio \ num_tc 4 \ map 3 2 1 0 3 3 3 3 3 3 3 3 3 3 3 3 \ queues 1@0 1@1 1@2 1@3 \ base-time 0 \ sched-entry S 0x07 500000 \ sched-entry S 0x0f 500000 \ flags 0x2 \ txtime-delay 0

Note that for TC3, gate should open for 500us and close for another 500us.

3. Take tcpdump log on Board B.

4. Send udp packets via UDP tai app from Board A to Board B.

5. Analyze tcpdump log via wireshark log on Board B. Ensure that the total time from the first to the last packet received during one cycle for TC3 does not exceed 500us.

Fixes: 43546211738e ("igc: Add new device ID's") Signed-off-by: Faizal Rahim faizal.abdul.rahim@linux.intel.com Acked-by: Vinicius Costa Gomes vinicius.gomes@intel.com Tested-by: Mor Bar-Gabay morx.bar.gabay@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_defines.h | 6 ++++ drivers/net/ethernet/intel/igc/igc_tsn.c | 34 ++++++++++++++++++++ 2 files changed, 40 insertions(+)

diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index b3037016f31d2..a18af5c87cde4 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -402,6 +402,12 @@ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */

+/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedfa..46d4c3275bbb5 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -78,6 +78,15 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); }

+static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ @@ -91,6 +100,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);

+ if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); @@ -111,6 +123,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) return 0; }

+/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -123,6 +154,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter) wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);

+ if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Faizal Rahim faizal.abdul.rahim@linux.intel.com

[ Upstream commit 0afeaeb5dae86aceded0d5f0c3a54d27858c0c6f ]

Following the "igc: Fix TX Hang issue when QBV Gate is close" changes, remaining issues with the reset adapter logic in igc_tsn_offload_apply() have been observed:

1. The reset adapter logics for i225 and i226 differ, although they should be the same according to the guidelines in I225/6 HW Design Section 7.5.2.1 on software initialization during tx mode changes. 2. The i225 resets adapter every time, even though tx mode doesn't change. This occurs solely based on the condition igc_is_device_id_i225() when calling schedule_work(). 3. i226 doesn't reset adapter for tsn->legacy tx mode changes. It only resets adapter for legacy->tsn tx mode transitions. 4. qbv_count introduced in the patch is actually not needed; in this context, a non-zero value of qbv_count is used to indicate if tx mode was unconditionally set to tsn in igc_tsn_enable_offload(). This could be replaced by checking the existing register IGC_TQAVCTRL_TRANSMIT_MODE_TSN bit.

This patch resolves all issues and enters schedule_work() to reset the adapter only when changing tx mode. It also removes reliance on qbv_count.

qbv_count field will be removed in a future patch.

Test ran:

1. Verify reset adapter behaviour in i225/6: a) Enrol a new GCL Reset adapter observed (tx mode change legacy->tsn) b) Enrol a new GCL without deleting qdisc No reset adapter observed (tx mode remain tsn->tsn) c) Delete qdisc Reset adapter observed (tx mode change tsn->legacy)

2. Tested scenario from "igc: Fix TX Hang issue when QBV Gate is closed" to confirm it remains resolved.

Fixes: 175c241288c0 ("igc: Fix TX Hang issue when QBV Gate is closed") Signed-off-by: Faizal Rahim faizal.abdul.rahim@linux.intel.com Reviewed-by: Simon Horman horms@kernel.org Acked-by: Vinicius Costa Gomes vinicius.gomes@intel.com Tested-by: Mor Bar-Gabay morx.bar.gabay@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/intel/igc/igc_tsn.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 8ed7b965484da..ada7514305171 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -49,6 +49,13 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) return new_flags; }

+static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; @@ -365,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; }

-int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); + + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +}

- /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Cosmin Ratiu cratiu@nvidia.com

[ Upstream commit cbc796be1779c4dbc9a482c7233995e2a8b6bfb3 ]

Previously, an ethtool rx flow with no attrs would not be added to the NIC as it has no rules to configure the hw with, but it would be reported as successful to the caller (return code 0). This is confusing for the user as ethtool then reports "Added rule $num", but no rule was actually added.

This change corrects that by instead reporting these wrong rules as -EINVAL.

Fixes: b29c61dac3a2 ("net/mlx5e: Ethtool steering flow validation refactoring") Signed-off-by: Cosmin Ratiu cratiu@nvidia.com Reviewed-by: Saeed Mahameed saeedm@nvidia.com Reviewed-by: Dragos Tatulea dtatulea@nvidia.com Signed-off-by: Tariq Toukan tariqt@nvidia.com Link: https://patch.msgid.link/20240808144107.2095424-5-tariqt@nvidia.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 3eccdadc03578..773624bb2c5d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv, if (num_tuples <= 0) { netdev_warn(priv->netdev, "%s: flow is not valid %d\n", __func__, num_tuples); - return num_tuples; + return num_tuples < 0 ? num_tuples : -EINVAL; }

eth_ft = get_flow_table(priv, fs, num_tuples);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Radhey Shyam Pandey radhey.shyam.pandey@amd.com

[ Upstream commit 9ff2f816e2aa65ca9a1cdf0954842f8173c0f48d ]

In axiethernet header fix register defines comment description to be inline with IP documentation. It updates MAC configuration register, MDIO configuration register and frame filter control description.

Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver") Signed-off-by: Radhey Shyam Pandey radhey.shyam.pandey@amd.com Reviewed-by: Andrew Lunn andrew@lunn.ch Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/xilinx/xilinx_axienet.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h index 575ff9de8985b..a62c2b4c6b2f2 100644 --- a/drivers/net/ethernet/xilinx/xilinx_axienet.h +++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h @@ -159,16 +159,16 @@ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */ -#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */ -#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */ +#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */ +#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */ -#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */ -#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */ -#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */ -#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */ +#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */ +#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */ +#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */ +#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */ -#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */ +#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */

@@ -307,7 +307,7 @@ */ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF

-/* Bit masks for Axi Ethernet FMI register */ +/* Bit masks for Axi Ethernet FMC register */ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Pawel Dembicki paweldembicki@gmail.com

[ Upstream commit eb7e33d01db3aec128590391b2397384bab406b6 ]

Switch the delay loop during the Arbiter empty check from vsc73xx_adjust_link() to use read_poll_timeout(). Functionally, one msleep() call is eliminated at the end of the loop in the timeout case.

As Russell King suggested:

"This [change] avoids the issue that on the last iteration, the code reads the register, tests it, finds the condition that's being waiting for is false, _then_ waits and end up printing the error message - that last wait is rather useless, and as the arbiter state isn't checked after waiting, it could be that we had success during the last wait."

Suggested-by: Russell King linux@armlinux.org.uk Reviewed-by: Andrew Lunn andrew@lunn.ch Reviewed-by: Linus Walleij linus.walleij@linaro.org Reviewed-by: Florian Fainelli florian.fainelli@broadcom.com Signed-off-by: Pawel Dembicki paweldembicki@gmail.com Link: https://lore.kernel.org/r/20240417205048.3542839-2-paweldembicki@gmail.com Signed-off-by: Jakub Kicinski kuba@kernel.org Stable-dep-of: fa63c6434b6f ("net: dsa: vsc73xx: check busy flag in MDIO operations") Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/dsa/vitesse-vsc73xx-core.c | 30 ++++++++++++++------------ 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index dedebb95ece6c..d8f368df8b06f 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/device.h> +#include <linux/iopoll.h> #include <linux/of.h> #include <linux/of_mdio.h> #include <linux/bitops.h> @@ -268,6 +269,9 @@ #define IS_7398(a) ((a)->chipid == VSC73XX_CHIPID_ID_7398) #define IS_739X(a) (IS_7395(a) || IS_7398(a))

+#define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_POLL_TIMEOUT_US 10000 + struct vsc73xx_counter { u8 counter; const char *name; @@ -779,7 +783,7 @@ static void vsc73xx_adjust_link(struct dsa_switch *ds, int port, * after a PHY or the CPU port comes up or down. */ if (!phydev->link) { - int maxloop = 10; + int ret, err;

dev_dbg(vsc->dev, "port %d: went down\n", port); @@ -794,19 +798,17 @@ static void vsc73xx_adjust_link(struct dsa_switch *ds, int port, VSC73XX_ARBDISC, BIT(port), BIT(port));

/* Wait until queue is empty */ - vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0, - VSC73XX_ARBEMPTY, &val); - while (!(val & BIT(port))) { - msleep(1); - vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0, - VSC73XX_ARBEMPTY, &val); - if (--maxloop == 0) { - dev_err(vsc->dev, - "timeout waiting for block arbiter\n"); - /* Continue anyway */ - break; - } - } + ret = read_poll_timeout(vsc73xx_read, err, + err < 0 || (val & BIT(port)), + VSC73XX_POLL_SLEEP_US, + VSC73XX_POLL_TIMEOUT_US, false, + vsc, VSC73XX_BLOCK_ARBITER, 0, + VSC73XX_ARBEMPTY, &val); + if (ret) + dev_err(vsc->dev, + "timeout waiting for block arbiter\n"); + else if (err < 0) + dev_err(vsc->dev, "error reading arbiter\n");

/* Put this port into reset */ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG,

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Zheng Zhang everything411@qq.com

[ Upstream commit db1b4bedb9b97c6d34b03d03815147c04fffe8b4 ]

When there are multiple ap interfaces on one band and with WED on, turning the interface down will cause a kernel panic on MT798X.

Previously, cb_priv was freed in mtk_wed_setup_tc_block() without marking NULL,and mtk_wed_setup_tc_block_cb() didn't check the value, too.

Assign NULL after free cb_priv in mtk_wed_setup_tc_block() and check NULL in mtk_wed_setup_tc_block_cb().

---------- Unable to handle kernel paging request at virtual address 0072460bca32b4f5 Call trace: mtk_wed_setup_tc_block_cb+0x4/0x38 0xffffffc0794084bc tcf_block_playback_offloads+0x70/0x1e8 tcf_block_unbind+0x6c/0xc8 ... ---------

Fixes: 799684448e3e ("net: ethernet: mtk_wed: introduce wed wo support") Signed-off-by: Zheng Zhang everything411@qq.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/mediatek/mtk_wed.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c index c7196055c8c98..85a9ad2b86bff 100644 --- a/drivers/net/ethernet/mediatek/mtk_wed.c +++ b/drivers/net/ethernet/mediatek/mtk_wed.c @@ -1762,14 +1762,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri { struct mtk_wed_flow_block_priv *priv = cb_priv; struct flow_cls_offload *cls = type_data; - struct mtk_wed_hw *hw = priv->hw; + struct mtk_wed_hw *hw = NULL;

- if (!tc_can_offload(priv->dev)) + if (!priv || !tc_can_offload(priv->dev)) return -EOPNOTSUPP;

if (type != TC_SETUP_CLSFLOWER) return -EOPNOTSUPP;

+ hw = priv->hw; return mtk_flow_offload_cmd(hw->eth, cls, hw->index); }

@@ -1825,6 +1826,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev, flow_block_cb_remove(block_cb, f); list_del(&block_cb->driver_list); kfree(block_cb->cb_priv); + block_cb->cb_priv = NULL; } return 0; default:

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Eugene Syromiatnikov esyr@redhat.com

[ Upstream commit 655111b838cdabdb604f3625a9ff08c5eedb11da ]

ssn_offset field is u32 and is placed into the netlink response with nla_put_u32(), but only 2 bytes are reserved for the attribute payload in subflow_get_info_size() (even though it makes no difference in the end, as it is aligned up to 4 bytes). Supply the correct argument to the relevant nla_total_size() call to make it less confusing.

Fixes: 5147dfb50832 ("mptcp: allow dumping subflow context to userspace") Signed-off-by: Eugene Syromiatnikov esyr@redhat.com Reviewed-by: Matthieu Baerts (NGI0) matttbe@kernel.org Link: https://patch.msgid.link/20240812065024.GA19719@asgard.redhat.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index 7017dd60659dc..b2199cc282384 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -95,7 +95,7 @@ static size_t subflow_get_info_size(const struct sock *sk) nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */ - nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ + nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Tom Hughes tom@compton.nu

[ Upstream commit 3cd740b985963f874a1a094f1969e998b9d05554 ]

Commit 264640fc2c5f4 ("ipv6: distinguish frag queues by device for multicast and link-local packets") modified the ipv6 fragment reassembly logic to distinguish frag queues by device for multicast and link-local packets but in fact only the main reassembly code limits the use of the device to those address types and the netfilter reassembly code uses the device for all packets.

This means that if fragments of a packet arrive on different interfaces then netfilter will fail to reassemble them and the fragments will be expired without going any further through the filters.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Tom Hughes tom@compton.nu Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index efbec7ee27d0a..c78b13ea5b196 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -155,6 +155,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, }; struct inet_frag_queue *q;

+ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0; + q = inet_frag_find(nf_frag->fqdir, &key); if (!q) return NULL;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Florian Westphal fw@strlen.de

[ Upstream commit 7d8dc1c7be8d3509e8f5164dd5df64c8e34d7eeb ]

Conntrack assumes an unconfirmed entry (not yet committed to global hash table) has a refcount of 1 and is not visible to other cores.

With multicast forwarding this assumption breaks down because such skbs get cloned after being picked up, i.e. ct->use refcount is > 1.

Likewise, bridge netfilter will clone broad/mutlicast frames and all frames in case they need to be flood-forwarded during learning phase.

For ip multicast forwarding or plain bridge flood-forward this will "work" because packets don't leave softirq and are implicitly serialized.

With nfqueue this no longer holds true, the packets get queued and can be reinjected in arbitrary ways.

Disable this feature, I see no other solution.

After this patch, nfqueue cannot queue packets except the last multicast/broadcast packet.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bridge/br_netfilter_hooks.c | 6 +++++- net/netfilter/nfnetlink_queue.c | 35 +++++++++++++++++++++++++++++++-- 2 files changed, 38 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index d848c84ed030d..68d5538613032 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -618,8 +618,12 @@ static unsigned int br_nf_local_in(void *priv, if (likely(nf_ct_is_confirmed(ct))) return NF_ACCEPT;

+ if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) { + nf_reset_ct(skb); + return NF_ACCEPT; + } + WARN_ON_ONCE(skb_shared(skb)); - WARN_ON_ONCE(refcount_read(&nfct->use) != 1);

/* We can't call nf_confirm here, it would create a dependency * on nf_conntrack module. diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index dfc856b3e1fa4..09209b4952ad1 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -668,10 +668,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry) { #if IS_ENABLED(CONFIG_NF_CONNTRACK) static const unsigned long flags = IPS_CONFIRMED | IPS_DYING; - const struct nf_conn *ct = (void *)skb_nfct(entry->skb); + struct nf_conn *ct = (void *)skb_nfct(entry->skb); + unsigned long status; + unsigned int use;

- if (ct && ((ct->status & flags) == IPS_DYING)) + if (!ct) + return false; + + status = READ_ONCE(ct->status); + if ((status & flags) == IPS_DYING) return true; + + if (status & IPS_CONFIRMED) + return false; + + /* in some cases skb_clone() can occur after initial conntrack + * pickup, but conntrack assumes exclusive skb->_nfct ownership for + * unconfirmed entries. + * + * This happens for br_netfilter and with ip multicast routing. + * We can't be solved with serialization here because one clone could + * have been queued for local delivery. + */ + use = refcount_read(&ct->ct_general.use); + if (likely(use == 1)) + return false; + + /* Can't decrement further? Exclusive ownership. */ + if (!refcount_dec_not_one(&ct->ct_general.use)) + return false; + + skb_set_nfct(entry->skb, 0); + /* No nf_ct_put(): we already decremented .use and it cannot + * drop down to 0. + */ + return true; #endif return false; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Phil Sutter phil@nwl.cc

[ Upstream commit ff16111cc10c82ee065ffbd9fa8d6210394ff8c6 ]

The code does not make use of cb->args fields past the first one, no need to zero them.

Signed-off-by: Phil Sutter phil@nwl.cc Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests") Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 3 --- 1 file changed, 3 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index c6296ffd9b91b..d29c5803c3ff0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7753,9 +7753,6 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) goto cont; if (idx < s_idx) goto cont; - if (idx > s_idx) - memset(&cb->args[1], 0, - sizeof(cb->args) - sizeof(cb->args[0])); if (filter && filter->table && strcmp(filter->table, table->name)) goto cont;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Phil Sutter phil@nwl.cc

[ Upstream commit ecf49cad807061d880bea27a5da8e0114ddc7690 ]

Name it for what it is supposed to become, a real nft_obj_dump_ctx. No functional change intended.

Signed-off-by: Phil Sutter phil@nwl.cc Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests") Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 35d5848cb3d0d..ca5fb700d15cf 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7717,7 +7717,7 @@ static void audit_log_obj_reset(const struct nft_table *table, kfree(buf); }

-struct nft_obj_filter { +struct nft_obj_dump_ctx { char *table; u32 type; }; @@ -7727,7 +7727,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); const struct nft_table *table; unsigned int idx = 0, s_idx = cb->args[0]; - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = cb->data; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; @@ -7753,10 +7753,10 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) goto cont; if (idx < s_idx) goto cont; - if (filter->table && strcmp(filter->table, table->name)) + if (ctx->table && strcmp(ctx->table, table->name)) goto cont; - if (filter->type != NFT_OBJECT_UNSPEC && - obj->ops->type->type != filter->type) + if (ctx->type != NFT_OBJECT_UNSPEC && + obj->ops->type->type != ctx->type) goto cont;

rc = nf_tables_fill_obj_info(skb, net, @@ -7788,33 +7788,33 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) static int nf_tables_dump_obj_start(struct netlink_callback *cb) { const struct nlattr * const *nla = cb->data; - struct nft_obj_filter *filter = NULL; + struct nft_obj_dump_ctx *ctx = NULL;

- filter = kzalloc(sizeof(*filter), GFP_ATOMIC); - if (!filter) + ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); + if (!ctx) return -ENOMEM;

if (nla[NFTA_OBJ_TABLE]) { - filter->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!filter->table) { - kfree(filter); + ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); + if (!ctx->table) { + kfree(ctx); return -ENOMEM; } }

if (nla[NFTA_OBJ_TYPE]) - filter->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); + ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));

- cb->data = filter; + cb->data = ctx; return 0; }

static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_filter *filter = cb->data; + struct nft_obj_dump_ctx *ctx = cb->data;

- kfree(filter->table); - kfree(filter); + kfree(ctx->table); + kfree(ctx);

return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Phil Sutter phil@nwl.cc

[ Upstream commit 5a893b9cdf6fa5758f43d323a1d7fa6d1bf489ff ]

No need to allocate it if one may just use struct netlink_callback's scratch area for it.

Signed-off-by: Phil Sutter phil@nwl.cc Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests") Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 7d6146923819c..e3e3ad532ec9f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7726,7 +7726,7 @@ struct nft_obj_dump_ctx { static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) { const struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh); - struct nft_obj_dump_ctx *ctx = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; @@ -7788,34 +7788,28 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)

static int nf_tables_dump_obj_start(struct netlink_callback *cb) { + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; const struct nlattr * const *nla = cb->data; - struct nft_obj_dump_ctx *ctx = NULL;

- ctx = kzalloc(sizeof(*ctx), GFP_ATOMIC); - if (!ctx) - return -ENOMEM; + BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));

if (nla[NFTA_OBJ_TABLE]) { ctx->table = nla_strdup(nla[NFTA_OBJ_TABLE], GFP_ATOMIC); - if (!ctx->table) { - kfree(ctx); + if (!ctx->table) return -ENOMEM; - } }

if (nla[NFTA_OBJ_TYPE]) ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));

- cb->data = ctx; return 0; }

static int nf_tables_dump_obj_done(struct netlink_callback *cb) { - struct nft_obj_dump_ctx *ctx = cb->data; + struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;

kfree(ctx->table); - kfree(ctx);

return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Phil Sutter phil@nwl.cc

[ Upstream commit 69fc3e9e90f1afc11f4015e6b75d18ab9acee348 ]

Outsource the reply skb preparation for non-dump getrule requests into a distinct function. Prep work for object reset locking.

Signed-off-by: Phil Sutter phil@nwl.cc Reviewed-by: Florian Westphal fw@strlen.de Signed-off-by: Pablo Neira Ayuso pablo@netfilter.org Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests") Signed-off-by: Sasha Levin sashal@kernel.org --- net/netfilter/nf_tables_api.c | 75 ++++++++++++++++++++--------------- 1 file changed, 44 insertions(+), 31 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 170f6f624ac16..a3ed9437e21b4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -7815,10 +7815,10 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) }

/* called with rcu_read_lock held */ -static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, - const struct nlattr * const nla[]) +static struct sk_buff * +nf_tables_getobj_single(u32 portid, const struct nfnl_info *info, + const struct nlattr * const nla[], bool reset) { - const struct nftables_pernet *nft_net = nft_pernet(info->net); struct netlink_ext_ack *extack = info->extack; u8 genmask = nft_genmask_cur(info->net); u8 family = info->nfmsg->nfgen_family; @@ -7826,52 +7826,69 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_object *obj; struct sk_buff *skb2; - bool reset = false; u32 objtype; - char *buf; int err;

- if (info->nlh->nlmsg_flags & NLM_F_DUMP) { - struct netlink_dump_control c = { - .start = nf_tables_dump_obj_start, - .dump = nf_tables_dump_obj, - .done = nf_tables_dump_obj_done, - .module = THIS_MODULE, - .data = (void *)nla, - }; - - return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); - } - if (!nla[NFTA_OBJ_NAME] || !nla[NFTA_OBJ_TYPE]) - return -EINVAL; + return ERR_PTR(-EINVAL);

table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0); if (IS_ERR(table)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); - return PTR_ERR(table); + return ERR_CAST(table); }

objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); - return PTR_ERR(obj); + return ERR_CAST(obj); }

skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb2) - return -ENOMEM; + return ERR_PTR(-ENOMEM); + + err = nf_tables_fill_obj_info(skb2, net, portid, + info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, + family, table, obj, reset); + if (err < 0) { + kfree_skb(skb2); + return ERR_PTR(err); + } + + return skb2; +} + +static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, + const struct nlattr * const nla[]) +{ + struct nftables_pernet *nft_net = nft_pernet(info->net); + u32 portid = NETLINK_CB(skb).portid; + struct net *net = info->net; + struct sk_buff *skb2; + bool reset = false; + char *buf; + + if (info->nlh->nlmsg_flags & NLM_F_DUMP) { + struct netlink_dump_control c = { + .start = nf_tables_dump_obj_start, + .dump = nf_tables_dump_obj, + .done = nf_tables_dump_obj_done, + .module = THIS_MODULE, + .data = (void *)nla, + }; + + return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c); + }

if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET) reset = true;

- err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid, - info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0, - family, table, obj, reset); - if (err < 0) - goto err_fill_obj_info; + skb2 = nf_tables_getobj_single(portid, info, nla, reset); + if (IS_ERR(skb2)) + return PTR_ERR(skb2);

if (!reset) return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); @@ -7884,11 +7901,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info, AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC); kfree(buf);

- return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid); - -err_fill_obj_info: - kfree_skb(skb2); - return err; + return nfnetlink_unicast(skb2, net, portid); }

static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Cong Wang cong.wang@bytedance.com

[ Upstream commit 69139d2919dd4aa9a553c8245e7c63e82613e3fc ]

After a vsock socket has been added to a BPF sockmap, its prot->recvmsg has been replaced with vsock_bpf_recvmsg(). Thus the following recursiion could happen:

vsock_bpf_recvmsg() -> __vsock_recvmsg() -> vsock_connectible_recvmsg() -> prot->recvmsg() -> vsock_bpf_recvmsg() again

We need to fix it by calling the original ->recvmsg() without any BPF sockmap logic in __vsock_recvmsg().

Fixes: 634f1a7110b4 ("vsock: support sockmap") Reported-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Tested-by: syzbot+bdb4bd87b5e22058e2a4@syzkaller.appspotmail.com Cc: Bobby Eshleman bobby.eshleman@bytedance.com Cc: Michael S. Tsirkin mst@redhat.com Cc: Stefano Garzarella sgarzare@redhat.com Signed-off-by: Cong Wang cong.wang@bytedance.com Acked-by: Michael S. Tsirkin mst@redhat.com Link: https://patch.msgid.link/20240812022153.86512-1-xiyou.wangcong@gmail.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/net/af_vsock.h | 4 ++++ net/vmw_vsock/af_vsock.c | 50 +++++++++++++++++++++++---------------- net/vmw_vsock/vsock_bpf.c | 4 ++-- 3 files changed, 35 insertions(+), 23 deletions(-)

diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index dc3cb16835b63..f8b09a82f62e1 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -227,8 +227,12 @@ struct vsock_tap { int vsock_add_tap(struct vsock_tap *vt); int vsock_remove_tap(struct vsock_tap *vt); void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque); +int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags); int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags); +int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags); int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags);

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 4afb6a541cf38..f5eb737a677d9 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1270,25 +1270,28 @@ static int vsock_dgram_connect(struct socket *sock, return err; }

+int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, + size_t len, int flags) +{ + struct sock *sk = sock->sk; + struct vsock_sock *vsk = vsock_sk(sk); + + return vsk->transport->dgram_dequeue(vsk, msg, len, flags); +} + int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { #ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; const struct proto *prot; -#endif - struct vsock_sock *vsk; - struct sock *sk;

- sk = sock->sk; - vsk = vsock_sk(sk); - -#ifdef CONFIG_BPF_SYSCALL prot = READ_ONCE(sk->sk_prot); if (prot != &vsock_proto) return prot->recvmsg(sk, msg, len, flags, NULL); #endif

- return vsk->transport->dgram_dequeue(vsk, msg, len, flags); + return __vsock_dgram_recvmsg(sock, msg, len, flags); } EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);

@@ -2124,15 +2127,12 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, }

int -vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) { struct sock *sk; struct vsock_sock *vsk; const struct vsock_transport *transport; -#ifdef CONFIG_BPF_SYSCALL - const struct proto *prot; -#endif int err;

sk = sock->sk; @@ -2183,14 +2183,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; }

-#ifdef CONFIG_BPF_SYSCALL - prot = READ_ONCE(sk->sk_prot); - if (prot != &vsock_proto) { - release_sock(sk); - return prot->recvmsg(sk, msg, len, flags, NULL); - } -#endif - if (sk->sk_type == SOCK_STREAM) err = __vsock_stream_recvmsg(sk, msg, len, flags); else @@ -2200,6 +2192,22 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, release_sock(sk); return err; } + +int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ +#ifdef CONFIG_BPF_SYSCALL + struct sock *sk = sock->sk; + const struct proto *prot; + + prot = READ_ONCE(sk->sk_prot); + if (prot != &vsock_proto) + return prot->recvmsg(sk, msg, len, flags, NULL); +#endif + + return __vsock_connectible_recvmsg(sock, msg, len, flags); +} EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);

static int vsock_set_rcvlowat(struct sock *sk, int val) diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c index a3c97546ab84a..c42c5cc18f324 100644 --- a/net/vmw_vsock/vsock_bpf.c +++ b/net/vmw_vsock/vsock_bpf.c @@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int int err;

if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) - err = vsock_connectible_recvmsg(sock, msg, len, flags); + err = __vsock_connectible_recvmsg(sock, msg, len, flags); else if (sk->sk_type == SOCK_DGRAM) - err = vsock_dgram_recvmsg(sock, msg, len, flags); + err = __vsock_dgram_recvmsg(sock, msg, len, flags); else err = -EPROTOTYPE;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Matthieu Baerts (NGI0) matttbe@kernel.org

[ Upstream commit 7965a7f32a53d9ad807ce2c53bdda69ba104974f ]

When deleting netns, it is possible to still have some tasks running, e.g. background tasks like tcpdump running in the background, not stopped because the test has been interrupted.

Before deleting the netns, it is then safer to kill all attached PIDs, if any. That should reduce some noises after the end of some tests, and help with the debugging of some issues. That's why this modification is seen as a "fix".

Fixes: 25ae948b4478 ("selftests/net: add lib.sh") Acked-by: Mat Martineau martineau@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Acked-by: Florian Westphal fw@strlen.de Reviewed-by: Hangbin Liu liuhangbin@gmail.com Link: https://patch.msgid.link/20240813-upstream-net-20240813-selftests-net-lib-ki... Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/testing/selftests/net/lib.sh | 1 + 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh index 323a7c305ccd4..e2c35eda230af 100644 --- a/tools/testing/selftests/net/lib.sh +++ b/tools/testing/selftests/net/lib.sh @@ -42,6 +42,7 @@ cleanup_ns()

for ns in "$@"; do [ -z "${ns}" ] && continue + ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true ip netns delete "${ns}" &> /dev/null || true if ! busywait $BUSYWAIT_TIMEOUT ip netns list | grep -vq "^$ns$" &> /dev/null; then echo "Warn: Failed to remove namespace $ns"

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Peiyang Wang wangpeiyang1@huawei.com

[ Upstream commit 30545e17eac1f50c5ef49644daf6af205100a965 ]

Consider the followed case that the user change speed and reset the net interface. Before the hw change speed successfully, the driver get old old speed from hw by timer task. After reset, the previous speed is config to hw. As a result, the new speed is configed successfully but lost after PF reset. The followed pictured shows more dirrectly.

+------+ +----+ +----+ | USER | | PF | | HW | +---+--+ +-+--+ +-+--+ | ethtool -s 100G | | +------------------>| set speed 100G | | +--------------------->| | | set successfully | | |<---------------------+---+ | |query cfg (timer task)| | | +--------------------->| | handle speed | | return 200G | | changing event | ethtool --reset |<---------------------+ | (100G) +------------------>| cfg previous speed |<--+ | | after reset (200G) | | +--------------------->| | | +---+ | |query cfg (timer task)| | | +--------------------->| | handle speed | | return 100G | | changing event | |<---------------------+ | (200G) | | |<--+ | |query cfg (timer task)| | +--------------------->| | | return 200G | | |<---------------------+ | | | v v v

This patch save new speed if hw change speed successfully, which will be used after reset successfully.

Fixes: 2d03eacc0b7e ("net: hns3: Only update mac configuation when necessary") Signed-off-by: Peiyang Wang wangpeiyang1@huawei.com Signed-off-by: Jijie Shao shaojijie@huawei.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../hisilicon/hns3/hns3pf/hclge_main.c | 24 ++++++++++++++----- .../hisilicon/hns3/hns3pf/hclge_mdio.c | 3 +++ 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index ad8e56234b284..92c592c177e67 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2598,8 +2598,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed, { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num);

- return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num); + if (ret) + return ret; + + hdev->hw.mac.req_speed = speed; + hdev->hw.mac.req_duplex = duplex; + + return 0; }

static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable) @@ -2901,17 +2910,20 @@ static int hclge_mac_init(struct hclge_dev *hdev) if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state)) hdev->hw.mac.duplex = HCLGE_MAC_FULL;

- ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed, - hdev->hw.mac.duplex, hdev->hw.mac.lane_num); - if (ret) - return ret; - if (hdev->hw.mac.support_autoneg) { ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg); if (ret) return ret; }

+ if (!hdev->hw.mac.autoneg) { + ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed, + hdev->hw.mac.req_duplex, + hdev->hw.mac.lane_num); + if (ret) + return ret; + } + mac->link = 0;

if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 85fb11de43a12..80079657afebe 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev) if (ret) netdev_err(netdev, "failed to adjust link.\n");

+ hdev->hw.mac.req_speed = (u32)speed; + hdev->hw.mac.req_duplex = (u8)duplex; + ret = hclge_cfg_flowctrl(hdev); if (ret) netdev_err(netdev, "failed to configure flow control.\n");

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Asmaa Mnebhi asmaa@nvidia.com

[ Upstream commit aad41832326723627ad8ac9ee8a543b6dca4454d ]

During Linux graceful reboot, the GPIO interrupts are not disabled. Since the drivers are not removed during graceful reboot, the logic to call mlxbf3_gpio_irq_disable() is not triggered. Interrupts that remain enabled can cause issues on subsequent boots.

For example, the mlxbf-gige driver contains PHY logic to bring up the link. If the gpio-mlxbf3 driver loads first, the mlxbf-gige driver will use a GPIO interrupt to bring up the link. Otherwise, it will use polling. The next time Linux boots and loads the drivers in this order, we encounter the issue: - mlxbf-gige loads first and uses polling while the GPIO10 interrupt is still enabled from the previous boot. So if the interrupt triggers, there is nothing to clear it. - gpio-mlxbf3 loads. - i2c-mlxbf loads. The interrupt doesn't trigger for I2C because it is shared with the GPIO interrupt line which was not cleared.

The solution is to add a shutdown function to the GPIO driver to clear and disable all interrupts. Also clear the interrupt after disabling it in mlxbf3_gpio_irq_disable().

Fixes: 38a700efc510 ("gpio: mlxbf3: Add gpio driver support") Signed-off-by: Asmaa Mnebhi asmaa@nvidia.com Reviewed-by: David Thompson davthompson@nvidia.com Reviewed-by: Andy Shevchenko andy@kernel.org Reviewed-by: Linus Walleij linus.walleij@linaro.org Link: https://lore.kernel.org/r/20240611171509.22151-1-asmaa@nvidia.com Signed-off-by: Bartosz Golaszewski bartosz.golaszewski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpio/gpio-mlxbf3.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)

diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c index d5906d419b0ab..10ea71273c891 100644 --- a/drivers/gpio/gpio-mlxbf3.c +++ b/drivers/gpio/gpio-mlxbf3.c @@ -39,6 +39,8 @@ #define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14 #define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18

+#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0) + struct mlxbf3_gpio_context { struct gpio_chip gc;

@@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd) val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); val &= ~BIT(offset); writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + + writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);

gpiochip_disable_irq(gc, offset); @@ -253,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev) return 0; }

+static void mlxbf3_gpio_shutdown(struct platform_device *pdev) +{ + struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev); + + /* Disable and clear all interrupts */ + writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0); + writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE); +} + static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = { { "MLNXBF33", 0 }, {} @@ -265,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = { .acpi_match_table = mlxbf3_gpio_acpi_match, }, .probe = mlxbf3_gpio_probe, + .shutdown = mlxbf3_gpio_shutdown, }; module_platform_driver(mlxbf3_gpio_driver);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Alex Deucher alexander.deucher@amd.com

[ Upstream commit a5600853167aeba5cade81f184a382a0d1b14641 ]

Sensor fetching functions should return an signed int to handle errors properly.

Reviewed-by: Srinivasan Shanmugam srinivasan.shanmugam@amd.com Reported-by: Jiapeng Chong jiapeng.chong@linux.alibaba.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/pm/amdgpu_pm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/amdgpu_pm.c b/drivers/gpu/drm/amd/pm/amdgpu_pm.c index 7372eae0b0ef8..babb73147adfb 100644 --- a/drivers/gpu/drm/amd/pm/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/pm/amdgpu_pm.c @@ -1471,9 +1471,9 @@ static ssize_t amdgpu_set_pp_power_profile_mode(struct device *dev, return -EINVAL; }

-static unsigned int amdgpu_hwmon_get_sensor_generic(struct amdgpu_device *adev, - enum amd_pp_sensors sensor, - void *query) +static int amdgpu_hwmon_get_sensor_generic(struct amdgpu_device *adev, + enum amd_pp_sensors sensor, + void *query) { int r, size = sizeof(uint32_t);

@@ -2787,8 +2787,8 @@ static ssize_t amdgpu_hwmon_show_vddnb_label(struct device *dev, return sysfs_emit(buf, "vddnb\n"); }

-static unsigned int amdgpu_hwmon_get_power(struct device *dev, - enum amd_pp_sensors sensor) +static int amdgpu_hwmon_get_power(struct device *dev, + enum amd_pp_sensors sensor) { struct amdgpu_device *adev = dev_get_drvdata(dev); unsigned int uw; @@ -2809,7 +2809,7 @@ static ssize_t amdgpu_hwmon_show_power_avg(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned int val; + int val;

val = amdgpu_hwmon_get_power(dev, AMDGPU_PP_SENSOR_GPU_AVG_POWER); if (val < 0) @@ -2822,7 +2822,7 @@ static ssize_t amdgpu_hwmon_show_power_input(struct device *dev, struct device_attribute *attr, char *buf) { - unsigned int val; + int val;

val = amdgpu_hwmon_get_power(dev, AMDGPU_PP_SENSOR_GPU_INPUT_POWER); if (val < 0)

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: ZhenGuo Yin zhenguo.yin@amd.com

[ Upstream commit 9f05cfc78c6880e06940ea78fbc43f6392710f17 ]

Register RLC_SPM_MC_CNTL is not blocked by L1 policy, VF can directly access it through MMIO during SRIOV runtime.

v2: use SOC15 interface to access registers

Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: ZhenGuo Yin zhenguo.yin@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 13 +++---------- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 13 +++---------- 2 files changed, 6 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c index 3560a3f2c848e..cd594b92c6129 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c @@ -7892,22 +7892,15 @@ static int gfx_v10_0_update_gfx_clock_gating(struct amdgpu_device *adev, static void gfx_v10_0_update_spm_vmid_internal(struct amdgpu_device *adev, unsigned int vmid) { - u32 reg, data; + u32 data;

/* not for *_SOC15 */ - reg = SOC15_REG_OFFSET(GC, 0, mmRLC_SPM_MC_CNTL); - if (amdgpu_sriov_is_pp_one_vf(adev)) - data = RREG32_NO_KIQ(reg); - else - data = RREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL); + data = RREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL);

data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK; data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;

- if (amdgpu_sriov_is_pp_one_vf(adev)) - WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); - else - WREG32_SOC15(GC, 0, mmRLC_SPM_MC_CNTL, data); + WREG32_SOC15_NO_KIQ(GC, 0, mmRLC_SPM_MC_CNTL, data); }

static void gfx_v10_0_update_spm_vmid(struct amdgpu_device *adev, unsigned int vmid) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index daab4c7a073ac..c81e98f0d17ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4961,23 +4961,16 @@ static int gfx_v11_0_update_gfx_clock_gating(struct amdgpu_device *adev,

static void gfx_v11_0_update_spm_vmid(struct amdgpu_device *adev, unsigned vmid) { - u32 reg, data; + u32 data;

amdgpu_gfx_off_ctrl(adev, false);

- reg = SOC15_REG_OFFSET(GC, 0, regRLC_SPM_MC_CNTL); - if (amdgpu_sriov_is_pp_one_vf(adev)) - data = RREG32_NO_KIQ(reg); - else - data = RREG32(reg); + data = RREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL);

data &= ~RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK; data |= (vmid & RLC_SPM_MC_CNTL__RLC_SPM_VMID_MASK) << RLC_SPM_MC_CNTL__RLC_SPM_VMID__SHIFT;

- if (amdgpu_sriov_is_pp_one_vf(adev)) - WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data); - else - WREG32_SOC15(GC, 0, regRLC_SPM_MC_CNTL, data); + WREG32_SOC15_NO_KIQ(GC, 0, regRLC_SPM_MC_CNTL, data);

amdgpu_gfx_off_ctrl(adev, true); }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Ricardo Rivera-Matos rriveram@opensource.cirrus.com

[ Upstream commit 44f37b6ce041c838cb2f49f08998c41f1ab3b08c ]

Checks the index computed by the virq offset before printing the error condition in cs35l45_spk_safe_err() handler.

Signed-off-by: Ricardo Rivera-Matos rriveram@opensource.cirrus.com Signed-off-by: Vlad Karpovich vkarpovi@opensource.cirrus.com Acked-by: Ricardo Rivera-Matos rriveram@opensource.cirrus.com Acked-by: Charles Keepax ckeepax@opensource.cirrus.com Link: https://lore.kernel.org/r/20230831162042.471801-1-vkarpovi@opensource.cirrus... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/codecs/cs35l45.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs35l45.c b/sound/soc/codecs/cs35l45.c index 9b9fc2d491089..7e439c778c6b4 100644 --- a/sound/soc/codecs/cs35l45.c +++ b/sound/soc/codecs/cs35l45.c @@ -1067,7 +1067,10 @@ static irqreturn_t cs35l45_spk_safe_err(int irq, void *data)

i = irq - regmap_irq_get_virq(cs35l45->irq_data, 0);

- dev_err(cs35l45->dev, "%s condition detected!\n", cs35l45_irqs[i].name); + if (i < 0 || i >= ARRAY_SIZE(cs35l45_irqs)) + dev_err(cs35l45->dev, "Unspecified global error condition (%d) detected!\n", irq); + else + dev_err(cs35l45->dev, "%s condition detected!\n", cs35l45_irqs[i].name);

return IRQ_HANDLED; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 1474bc87fe57deac726cc10203f73daa6c3212f7 ]

This might seem pretty pointless rather than changing the locking immediately, but it seems safer to run for a while with checks and the old locking scheme, and then remove the wdev lock later.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/wireless/core.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/wireless/core.h b/net/wireless/core.h index f0a3a23176385..c955be6c6daa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -228,6 +228,7 @@ void cfg80211_register_wdev(struct cfg80211_registered_device *rdev, static inline void wdev_lock(struct wireless_dev *wdev) __acquires(wdev) { + lockdep_assert_held(&wdev->wiphy->mtx); mutex_lock(&wdev->mtx); __acquire(wdev->mtx); } @@ -235,11 +236,16 @@ static inline void wdev_lock(struct wireless_dev *wdev) static inline void wdev_unlock(struct wireless_dev *wdev) __releases(wdev) { + lockdep_assert_held(&wdev->wiphy->mtx); __release(wdev->mtx); mutex_unlock(&wdev->mtx); }

-#define ASSERT_WDEV_LOCK(wdev) lockdep_assert_held(&(wdev)->mtx) +static inline void ASSERT_WDEV_LOCK(struct wireless_dev *wdev) +{ + lockdep_assert_held(&wdev->wiphy->mtx); + lockdep_assert_held(&wdev->mtx); +}

static inline bool cfg80211_has_monitors_only(struct cfg80211_registered_device *rdev) {

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Emmanuel Grumbach emmanuel.grumbach@intel.com

[ Upstream commit 828c79d9feb000acbd9c15bd1ed7e0914473b363 ]

If the firmware crashes in the de-activation / re-activation of the link during CSA, we will not have a valid phy_ctxt pointer in mvmvif. This is a legit case, but when mac80211 removes the station to cleanup our state during the re-configuration, we need to make sure we clear ap_sta otherwise we won't re-add the station after the firmware has been restarted. Later on, we'd activate the link, try to send a TLC command crash again on ASSERT 3508.

Fix this by properly cleaning up our state.

Signed-off-by: Emmanuel Grumbach emmanuel.grumbach@intel.com Signed-off-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20230913145231.2651e6f6a55a.I4cd50e88ee5c23c1c8dd5... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c index 8f49de1206e03..f973efbbc3795 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c @@ -1035,6 +1035,7 @@ static void iwl_mvm_cleanup_iterator(void *data, u8 *mac, spin_unlock_bh(&mvm->time_event_lock);

memset(&mvmvif->bf_data, 0, sizeof(mvmvif->bf_data)); + mvmvif->ap_sta = NULL;

for_each_mvm_vif_valid_link(mvmvif, link_id) { mvmvif->link[link_id]->ap_sta_id = IWL_MVM_INVALID_STA; @@ -3934,7 +3935,11 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw,

mutex_lock(&mvm->mutex);

- /* this would be a mac80211 bug ... but don't crash */ + /* this would be a mac80211 bug ... but don't crash, unless we had a + * firmware crash while we were activating a link, in which case it is + * legit to have phy_ctxt = NULL. Don't bother not to WARN if we are in + * recovery flow since we spit tons of error messages anyway. + */ for_each_sta_active_link(vif, sta, link_sta, link_id) { if (WARN_ON_ONCE(!mvmvif->link[link_id]->phy_ctxt)) { mutex_unlock(&mvm->mutex);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Paul E. McKenney paulmck@kernel.org

[ Upstream commit 0ae9942f03d0d034fdb0a4f44fc99f62a3107987 ]

When using rcutorture as a module, there are a number of conditions that can abort the modprobe operation, for example, when attempting to run both RCU CPU stall warning tests and forward-progress tests. This can cause rcu_torture_cleanup() to be invoked on the unwind path out of rcu_rcu_torture_init(), which will mean that rcu_gp_slow_unregister() is invoked without a matching rcu_gp_slow_register(). This will cause a splat because rcu_gp_slow_unregister() is passed rcu_fwd_cb_nodelay, which does not match a NULL pointer.

This commit therefore forgives a mismatch involving a NULL pointer, thus avoiding this false-positive splat.

Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Frederic Weisbecker frederic@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c index c7cb465e2e0c7..8541084eeba50 100644 --- a/kernel/rcu/tree.c +++ b/kernel/rcu/tree.c @@ -1298,7 +1298,7 @@ EXPORT_SYMBOL_GPL(rcu_gp_slow_register); /* Unregister a counter, with NULL for not caring which. */ void rcu_gp_slow_unregister(atomic_t *rgssp) { - WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress); + WARN_ON_ONCE(rgssp && rgssp != rcu_gp_slow_suppress && rcu_gp_slow_suppress != NULL);

WRITE_ONCE(rcu_gp_slow_suppress, NULL); }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Yury Norov yury.norov@gmail.com

[ Upstream commit 9ecea9ae4d3127a09fb5dfcea87f248937a39ff5 ]

sched_numa_find_nth_cpu() doesn't handle NUMA_NO_NODE properly, and may crash kernel if passed with it. On the other hand, the only user of sched_numa_find_nth_cpu() has to check NUMA_NO_NODE case explicitly.

It would be easier for users if this logic will get moved into sched_numa_find_nth_cpu().

Signed-off-by: Yury Norov yury.norov@gmail.com Signed-off-by: Ingo Molnar mingo@kernel.org Cc: Mel Gorman mgorman@suse.de Link: https://lore.kernel.org/r/20230819141239.287290-6-yury.norov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/sched/topology.c | 3 +++ lib/cpumask.c | 4 +--- 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c index 8c1e183329d97..3a13cecf17740 100644 --- a/kernel/sched/topology.c +++ b/kernel/sched/topology.c @@ -2126,6 +2126,9 @@ int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) struct cpumask ***hop_masks; int hop, ret = nr_cpu_ids;

+ if (node == NUMA_NO_NODE) + return cpumask_nth_and(cpu, cpus, cpu_online_mask); + rcu_read_lock();

/* CPU-less node entries are uninitialized in sched_domains_numa_masks */ diff --git a/lib/cpumask.c b/lib/cpumask.c index a7fd02b5ae264..34335c1e72653 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -146,9 +146,7 @@ unsigned int cpumask_local_spread(unsigned int i, int node) /* Wrap: we always want a cpu. */ i %= num_online_cpus();

- cpu = (node == NUMA_NO_NODE) ? - cpumask_nth(i, cpu_online_mask) : - sched_numa_find_nth_cpu(cpu_online_mask, i, node); + cpu = sched_numa_find_nth_cpu(cpu_online_mask, i, node);

WARN_ON(cpu >= nr_cpu_ids); return cpu;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Kamalesh Babulal kamalesh.babulal@oracle.com

[ Upstream commit d24f05987ce8bf61e62d86fedbe47523dc5c3393 ]

Use css directly instead of dereferencing it from &cgroup->self, while adding the cgroup v2 cft base and psi files in css_populate_dir(). Both points to the same css, when css->ss is NULL, this avoids extra deferences and makes code consistent in usage across the function.

Signed-off-by: Kamalesh Babulal kamalesh.babulal@oracle.com Signed-off-by: Tejun Heo tj@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/cgroup/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index d872fff901073..5eca6281d1aa6 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -1728,13 +1728,13 @@ static int css_populate_dir(struct cgroup_subsys_state *css)

if (!css->ss) { if (cgroup_on_dfl(cgrp)) { - ret = cgroup_addrm_files(&cgrp->self, cgrp, + ret = cgroup_addrm_files(css, cgrp, cgroup_base_files, true); if (ret < 0) return ret;

if (cgroup_psi_enabled()) { - ret = cgroup_addrm_files(&cgrp->self, cgrp, + ret = cgroup_addrm_files(css, cgrp, cgroup_psi_files, true); if (ret < 0) return ret;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Zhu Yanjun yanjun.zhu@linux.dev

[ Upstream commit c5930a1aa08aafe6ffe15b5d28fe875f88f6ac86 ]

No functionality change. The variable which is not initialized fully will introduce potential risks.

Signed-off-by: Zhu Yanjun yanjun.zhu@linux.dev Link: https://lore.kernel.org/r/20230919020806.534183-1-yanjun.zhu@intel.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/ulp/rtrs/rtrs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c index 3696f367ff515..d80edfffd2e49 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs.c +++ b/drivers/infiniband/ulp/rtrs/rtrs.c @@ -255,7 +255,7 @@ static int create_cq(struct rtrs_con *con, int cq_vector, int nr_cqe, static int create_qp(struct rtrs_con *con, struct ib_pd *pd, u32 max_send_wr, u32 max_recv_wr, u32 max_sge) { - struct ib_qp_init_attr init_attr = {NULL}; + struct ib_qp_init_attr init_attr = {}; struct rdma_cm_id *cm_id = con->cm_id; int ret;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Tomi Valkeinen tomi.valkeinen@ideasonboard.com

[ Upstream commit 9fc75c40faa29df14ba16066be6bdfaea9f39ce4 ]

The DSI horizontal timing calculations done by the driver seem to often lead to underflows or overflows, depending on the videomode.

There are two main things the current driver doesn't seem to get right: DSI HSW and HFP, and VSDly. However, even following Toshiba's documentation it seems we don't always get a working display.

This patch attempts to fix the horizontal timings for DSI event mode, and on a system with a DSI->HDMI encoder, a lot of standard HDMI modes now seem to work. The work relies on Toshiba's documentation, but also quite a bit on empirical testing.

This also adds timing related debug prints to make it easier to improve on this later.

The DSI pulse mode has only been tested with a fixed-resolution panel, which limits the testing of different modes on DSI pulse mode. However, as the VSDly calculation also affects pulse mode, so this might cause a regression.

Reviewed-by: Peter Ujfalusi peter.ujfalusi@gmail.com Tested-by: Marcel Ziswiler marcel.ziswiler@toradex.com Tested-by: Maxim Schwalm maxim.schwalm@gmail.com # Asus TF700T Signed-off-by: Tomi Valkeinen tomi.valkeinen@ideasonboard.com Signed-off-by: Robert Foss rfoss@kernel.org Link: https://patchwork.freedesktop.org/patch/msgid/20230906-tc358768-v4-12-31725f... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/bridge/tc358768.c | 213 ++++++++++++++++++++++++++---- 1 file changed, 185 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 6eed5c4232956..c72d5fbbb0ec4 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -9,6 +9,7 @@ #include <linux/gpio/consumer.h> #include <linux/i2c.h> #include <linux/kernel.h> +#include <linux/math64.h> #include <linux/media-bus-format.h> #include <linux/minmax.h> #include <linux/module.h> @@ -157,6 +158,7 @@ struct tc358768_priv { u32 frs; /* PLL Freqency range for HSCK (post divider) */

u32 dsiclk; /* pll_clk / 2 */ + u32 pclk; /* incoming pclk rate */ };

static inline struct tc358768_priv *dsi_host_to_tc358768(struct mipi_dsi_host @@ -380,6 +382,7 @@ static int tc358768_calc_pll(struct tc358768_priv *priv, priv->prd = best_prd; priv->frs = frs; priv->dsiclk = best_pll / 2; + priv->pclk = mode->clock * 1000;

return 0; } @@ -638,6 +641,28 @@ static u32 tc358768_ps_to_ns(u32 ps) return ps / 1000; }

+static u32 tc358768_dpi_to_ns(u32 val, u32 pclk) +{ + return (u32)div_u64((u64)val * NANO, pclk); +} + +/* Convert value in DPI pixel clock units to DSI byte count */ +static u32 tc358768_dpi_to_dsi_bytes(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * priv->dsiclk / 4 * priv->dsi_lanes; + u64 n = priv->pclk; + + return (u32)div_u64(m + n - 1, n); +} + +static u32 tc358768_dsi_bytes_to_ns(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * NANO; + u64 n = priv->dsiclk / 4 * priv->dsi_lanes; + + return (u32)div_u64(m, n); +} + static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) { struct tc358768_priv *priv = bridge_to_tc358768(bridge); @@ -647,11 +672,19 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) s32 raw_val; const struct drm_display_mode *mode; u32 hsbyteclk_ps, dsiclk_ps, ui_ps; - u32 dsiclk, hsbyteclk, video_start; - const u32 internal_delay = 40; + u32 dsiclk, hsbyteclk; int ret, i; struct videomode vm; struct device *dev = priv->dev; + /* In pixelclock units */ + u32 dpi_htot, dpi_data_start; + /* In byte units */ + u32 dsi_dpi_htot, dsi_dpi_data_start; + u32 dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp; + const u32 dsi_hss = 4; /* HSS is a short packet (4 bytes) */ + /* In hsbyteclk units */ + u32 dsi_vsdly; + const u32 internal_dly = 40;

if (mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) { dev_warn_once(dev, "Non-continuous mode unimplemented, falling back to continuous\n"); @@ -686,27 +719,23 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) case MIPI_DSI_FMT_RGB888: val |= (0x3 << 4); hact = vm.hactive * 3; - video_start = (vm.hsync_len + vm.hback_porch) * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_24; break; case MIPI_DSI_FMT_RGB666: val |= (0x4 << 4); hact = vm.hactive * 3; - video_start = (vm.hsync_len + vm.hback_porch) * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_18; break;

case MIPI_DSI_FMT_RGB666_PACKED: val |= (0x4 << 4) | BIT(3); hact = vm.hactive * 18 / 8; - video_start = (vm.hsync_len + vm.hback_porch) * 18 / 8; data_type = MIPI_DSI_PIXEL_STREAM_3BYTE_18; break;

case MIPI_DSI_FMT_RGB565: val |= (0x5 << 4); hact = vm.hactive * 2; - video_start = (vm.hsync_len + vm.hback_porch) * 2; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_16; break; default: @@ -716,9 +745,152 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) return; }

+ /* + * There are three important things to make TC358768 work correctly, + * which are not trivial to manage: + * + * 1. Keep the DPI line-time and the DSI line-time as close to each + * other as possible. + * 2. TC358768 goes to LP mode after each line's active area. The DSI + * HFP period has to be long enough for entering and exiting LP mode. + * But it is not clear how to calculate this. + * 3. VSDly (video start delay) has to be long enough to ensure that the + * DSI TX does not start transmitting until we have started receiving + * pixel data from the DPI input. It is not clear how to calculate + * this either. + */ + + dpi_htot = vm.hactive + vm.hfront_porch + vm.hsync_len + vm.hback_porch; + dpi_data_start = vm.hsync_len + vm.hback_porch; + + dev_dbg(dev, "dpi horiz timing (pclk): %u + %u + %u + %u = %u\n", + vm.hsync_len, vm.hback_porch, vm.hactive, vm.hfront_porch, + dpi_htot); + + dev_dbg(dev, "dpi horiz timing (ns): %u + %u + %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(vm.hactive, vm.pixelclock), + tc358768_dpi_to_ns(vm.hfront_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_htot, vm.pixelclock)); + + dev_dbg(dev, "dpi data start (ns): %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_data_start, vm.pixelclock)); + + dsi_dpi_htot = tc358768_dpi_to_dsi_bytes(priv, dpi_htot); + dsi_dpi_data_start = tc358768_dpi_to_dsi_bytes(priv, dpi_data_start); + + if (dsi_dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) { + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, vm.hsync_len); + dsi_hbp = tc358768_dpi_to_dsi_bytes(priv, vm.hback_porch); + } else { + /* HBP is included in HSW in event mode */ + dsi_hbp = 0; + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, + vm.hsync_len + + vm.hback_porch); + + /* + * The pixel packet includes the actual pixel data, and: + * DSI packet header = 4 bytes + * DCS code = 1 byte + * DSI packet footer = 2 bytes + */ + dsi_hact = hact + 4 + 1 + 2; + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + /* + * Here we should check if HFP is long enough for entering LP + * and exiting LP, but it's not clear how to calculate that. + * Instead, this is a naive algorithm that just adjusts the HFP + * and HSW so that HFP is (at least) roughly 2/3 of the total + * blanking time. + */ + if (dsi_hfp < (dsi_hfp + dsi_hsw + dsi_hss) * 2 / 3) { + u32 old_hfp = dsi_hfp; + u32 old_hsw = dsi_hsw; + u32 tot = dsi_hfp + dsi_hsw + dsi_hss; + + dsi_hsw = tot / 3; + + /* + * Seems like sometimes HSW has to be divisible by num-lanes, but + * not always... + */ + dsi_hsw = roundup(dsi_hsw, priv->dsi_lanes); + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + dev_dbg(dev, + "hfp too short, adjusting dsi hfp and dsi hsw from %u, %u to %u, %u\n", + old_hfp, old_hsw, dsi_hfp, dsi_hsw); + } + + dev_dbg(dev, + "dsi horiz timing (bytes): %u, %u + %u + %u + %u = %u\n", + dsi_hss, dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp, + dsi_hss + dsi_hsw + dsi_hbp + dsi_hact + dsi_hfp); + + dev_dbg(dev, "dsi horiz timing (ns): %u + %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_hact), + tc358768_dsi_bytes_to_ns(priv, dsi_hfp), + tc358768_dsi_bytes_to_ns(priv, dsi_hss + dsi_hsw + + dsi_hbp + dsi_hact + dsi_hfp)); + } + + /* VSDly calculation */ + + /* Start with the HW internal delay */ + dsi_vsdly = internal_dly; + + /* Convert to byte units as the other variables are in byte units */ + dsi_vsdly *= priv->dsi_lanes; + + /* Do we need more delay, in addition to the internal? */ + if (dsi_dpi_data_start > dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp) { + dsi_vsdly = dsi_dpi_data_start - dsi_hss - dsi_hsw - dsi_hbp; + dsi_vsdly = roundup(dsi_vsdly, priv->dsi_lanes); + } + + dev_dbg(dev, "dsi data start (bytes) %u + %u + %u + %u = %u\n", + dsi_vsdly, dsi_hss, dsi_hsw, dsi_hbp, + dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp); + + dev_dbg(dev, "dsi data start (ns) %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly), + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp)); + + /* Convert back to hsbyteclk */ + dsi_vsdly /= priv->dsi_lanes; + + /* + * The docs say that there is an internal delay of 40 cycles. + * However, we get underflows if we follow that rule. If we + * instead ignore the internal delay, things work. So either + * the docs are wrong or the calculations are wrong. + * + * As a temporary fix, add the internal delay here, to counter + * the subtraction when writing the register. + */ + dsi_vsdly += internal_dly; + + /* Clamp to the register max */ + if (dsi_vsdly - internal_dly > 0x3ff) { + dev_warn(dev, "VSDly too high, underflows likely\n"); + dsi_vsdly = 0x3ff + internal_dly; + } + /* VSDly[9:0] */ - video_start = max(video_start, internal_delay + 1) - internal_delay; - tc358768_write(priv, TC358768_VSDLY, video_start); + tc358768_write(priv, TC358768_VSDLY, dsi_vsdly - internal_dly);

tc358768_write(priv, TC358768_DATAFMT, val); tc358768_write(priv, TC358768_DSITX_DT, data_type); @@ -826,18 +998,6 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge)

/* vbp */ tc358768_write(priv, TC358768_DSI_VBPR, vm.vback_porch); - - /* hsw * byteclk * ndl / pclk */ - val = (u32)div_u64(vm.hsync_len * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HSW, val); - - /* hbp * byteclk * ndl / pclk */ - val = (u32)div_u64(vm.hback_porch * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HBPR, val); } else { /* Set event mode */ tc358768_write(priv, TC358768_DSI_EVENT, 1); @@ -851,16 +1011,13 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge)

/* vbp (not used in event mode) */ tc358768_write(priv, TC358768_DSI_VBPR, 0); + }

- /* (hsw + hbp) * byteclk * ndl / pclk */ - val = (u32)div_u64((vm.hsync_len + vm.hback_porch) * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HSW, val); + /* hsw (bytes) */ + tc358768_write(priv, TC358768_DSI_HSW, dsi_hsw);

- /* hbp (not used in event mode) */ - tc358768_write(priv, TC358768_DSI_HBPR, 0); - } + /* hbp (bytes) */ + tc358768_write(priv, TC358768_DSI_HBPR, dsi_hbp);

/* hact (bytes) */ tc358768_write(priv, TC358768_DSI_HACT, hact);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Jarkko Nikula jarkko.nikula@linux.intel.com

[ Upstream commit 361acacaf7c706223968c8186f0d3b6e214e7403 ]

Ring Abort request will timeout in case there is an error in the Host Controller interrupt delivery or Ring Header configuration. Using BUG() makes hard to debug those cases.

Make it less severe and turn BUG() to WARN_ON().

Signed-off-by: Jarkko Nikula jarkko.nikula@linux.intel.com Link: https://lore.kernel.org/r/20230921055704.1087277-6-jarkko.nikula@linux.intel... Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/i3c/master/mipi-i3c-hci/dma.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c index 71b5dbe45c45c..a28ff177022ce 100644 --- a/drivers/i3c/master/mipi-i3c-hci/dma.c +++ b/drivers/i3c/master/mipi-i3c-hci/dma.c @@ -450,10 +450,9 @@ static bool hci_dma_dequeue_xfer(struct i3c_hci *hci, /* * We're deep in it if ever this condition is ever met. * Hardware might still be writing to memory, etc. - * Better suspend the world than risking silent corruption. */ dev_crit(&hci->master.dev, "unable to abort the ring\n"); - BUG(); + WARN_ON(1); }

for (i = 0; i < n; i++) {

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Philip Yang Philip.Yang@amd.com

[ Upstream commit 101b8104307eac734f2dfa4d3511430b0b631c73 ]

Otherwise GPU may access the stale mapping and generate IOMMU IO_PAGE_FAULT.

Move this to inside p->mutex to prevent multiple threads mapping and unmapping concurrently race condition.

After kfd_mem_dmaunmap_attachment is removed from unmap_bo_from_gpuvm, kfd_mem_dmaunmap_attachment is called if failed to map to GPUs, and before free the mem attachment in case failed to unmap from GPUs.

Signed-off-by: Philip Yang Philip.Yang@amd.com Reviewed-by: Felix Kuehling Felix.Kuehling@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + .../gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 26 ++++++++++++++++--- drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 20 ++++++++------ 3 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index 2fe9860725bd9..5e4fb33b97351 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -303,6 +303,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); +void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( struct amdgpu_device *adev, struct kgd_mem *mem, bool intr); int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 62c1dc9510a41..c2d1d57a6c668 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -733,7 +733,7 @@ kfd_mem_dmaunmap_sg_bo(struct kgd_mem *mem, enum dma_data_direction dir;

if (unlikely(!ttm->sg)) { - pr_err("SG Table of BO is UNEXPECTEDLY NULL"); + pr_debug("SG Table of BO is NULL"); return; }

@@ -1202,8 +1202,6 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update);

amdgpu_sync_fence(sync, bo_va->last_pt_update); - - kfd_mem_dmaunmap_attachment(mem, entry); }

static int update_gpuvm_pte(struct kgd_mem *mem, @@ -1258,6 +1256,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem,

update_gpuvm_pte_failed: unmap_bo_from_gpuvm(mem, entry, sync); + kfd_mem_dmaunmap_attachment(mem, entry); return ret; }

@@ -1862,8 +1861,10 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( mem->va + bo_size * (1 + mem->aql_queue));

/* Remove from VM internal data structures */ - list_for_each_entry_safe(entry, tmp, &mem->attachments, list) + list_for_each_entry_safe(entry, tmp, &mem->attachments, list) { + kfd_mem_dmaunmap_attachment(mem, entry); kfd_mem_detach(entry); + }

ret = unreserve_bo_and_vms(&ctx, false, false);

@@ -2037,6 +2038,23 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu( return ret; }

+void amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv) +{ + struct kfd_mem_attachment *entry; + struct amdgpu_vm *vm; + + vm = drm_priv_to_vm(drm_priv); + + mutex_lock(&mem->lock); + + list_for_each_entry(entry, &mem->attachments, list) { + if (entry->bo_va->base.vm == vm) + kfd_mem_dmaunmap_attachment(mem, entry); + } + + mutex_unlock(&mem->lock); +} + int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv) { diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index d33ba4fe9ad5b..045280c2b607c 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1432,17 +1432,21 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, goto sync_memory_failed; } } - mutex_unlock(&p->mutex);

- if (flush_tlb) { - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); - if (WARN_ON_ONCE(!peer_pdd)) - continue; + /* Flush TLBs after waiting for the page table updates to complete */ + for (i = 0; i < args->n_devices; i++) { + peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + if (flush_tlb) kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } + + /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ + amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); } + + mutex_unlock(&p->mutex); + kfree(devices_arr);

return 0;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit 4fd15bb705d3faa7e6adab2daba2e3af80d9b6bd ]

When compiling with clang 16.0.6, I've noticed the following:

drivers/net/wireless/ath/ath11k/mac.c:8903:12: warning: stack frame size (1032) exceeds limit (1024) in 'ath11k_mac_op_remain_on_channel' [-Wframe-larger-than] static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw, ^ 68/1032 (6.59%) spills, 964/1032 (93.41%) variables

So switch to kzalloc()'ed instance of 'struct scan_req_params' like it's done in 'ath11k_mac_op_hw_scan()'. Compile tested only.

Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Acked-by: Jeff Johnson quic_jjohnson@quicinc.com Signed-off-by: Kalle Valo quic_kvalo@quicinc.com Link: https://lore.kernel.org/r/20230926042906.13725-1-dmantipov@yandex.ru Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath11k/mac.c | 44 +++++++++++++++------------ 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c index 33f2c189b4d86..4247c0f840a48 100644 --- a/drivers/net/wireless/ath/ath11k/mac.c +++ b/drivers/net/wireless/ath/ath11k/mac.c @@ -8910,7 +8910,7 @@ static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw, { struct ath11k *ar = hw->priv; struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif); - struct scan_req_params arg; + struct scan_req_params *arg; int ret; u32 scan_time_msec;

@@ -8942,27 +8942,31 @@ static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw,

scan_time_msec = ar->hw->wiphy->max_remain_on_channel_duration * 2;

- memset(&arg, 0, sizeof(arg)); - ath11k_wmi_start_scan_init(ar, &arg); - arg.num_chan = 1; - arg.chan_list = kcalloc(arg.num_chan, sizeof(*arg.chan_list), - GFP_KERNEL); - if (!arg.chan_list) { + arg = kzalloc(sizeof(*arg), GFP_KERNEL); + if (!arg) { ret = -ENOMEM; goto exit; } + ath11k_wmi_start_scan_init(ar, arg); + arg->num_chan = 1; + arg->chan_list = kcalloc(arg->num_chan, sizeof(*arg->chan_list), + GFP_KERNEL); + if (!arg->chan_list) { + ret = -ENOMEM; + goto free_arg; + }

- arg.vdev_id = arvif->vdev_id; - arg.scan_id = ATH11K_SCAN_ID; - arg.chan_list[0] = chan->center_freq; - arg.dwell_time_active = scan_time_msec; - arg.dwell_time_passive = scan_time_msec; - arg.max_scan_time = scan_time_msec; - arg.scan_flags |= WMI_SCAN_FLAG_PASSIVE; - arg.scan_flags |= WMI_SCAN_FILTER_PROBE_REQ; - arg.burst_duration = duration; - - ret = ath11k_start_scan(ar, &arg); + arg->vdev_id = arvif->vdev_id; + arg->scan_id = ATH11K_SCAN_ID; + arg->chan_list[0] = chan->center_freq; + arg->dwell_time_active = scan_time_msec; + arg->dwell_time_passive = scan_time_msec; + arg->max_scan_time = scan_time_msec; + arg->scan_flags |= WMI_SCAN_FLAG_PASSIVE; + arg->scan_flags |= WMI_SCAN_FILTER_PROBE_REQ; + arg->burst_duration = duration; + + ret = ath11k_start_scan(ar, arg); if (ret) { ath11k_warn(ar->ab, "failed to start roc scan: %d\n", ret);

@@ -8988,7 +8992,9 @@ static int ath11k_mac_op_remain_on_channel(struct ieee80211_hw *hw, ret = 0;

free_chan_list: - kfree(arg.chan_list); + kfree(arg->chan_list); +free_arg: + kfree(arg); exit: mutex_unlock(&ar->conf_mutex); return ret;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Felix Fietkau nbd@nbd.name

[ Upstream commit 0335c034e7265d36d956e806f33202c94a8a9860 ]

When drv_tx calls race against local tx scheduling, the queue fill status checks can potentially race, leading to dma queue entries being overwritten. Fix this by deferring packets from drv_tx calls to the tx worker, in order to ensure that all regular queue tx comes from the same context.

Reported-by: Ryder Lee Ryder.Lee@mediatek.com Signed-off-by: Felix Fietkau nbd@nbd.name Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/mediatek/mt76/mac80211.c | 50 +++++++- drivers/net/wireless/mediatek/mt76/mt76.h | 24 ++-- .../net/wireless/mediatek/mt76/mt7603/main.c | 4 +- .../net/wireless/mediatek/mt76/mt7615/main.c | 4 +- .../net/wireless/mediatek/mt76/mt76x02_util.c | 4 +- .../net/wireless/mediatek/mt76/mt7915/main.c | 4 +- .../net/wireless/mediatek/mt76/mt7921/main.c | 2 +- .../net/wireless/mediatek/mt76/mt792x_core.c | 2 +- .../net/wireless/mediatek/mt76/mt7996/main.c | 4 +- drivers/net/wireless/mediatek/mt76/tx.c | 108 ++++++++++++++---- 10 files changed, 155 insertions(+), 51 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c index dbab400969202..85bffcf4f6fbf 100644 --- a/drivers/net/wireless/mediatek/mt76/mac80211.c +++ b/drivers/net/wireless/mediatek/mt76/mac80211.c @@ -415,6 +415,9 @@ mt76_phy_init(struct mt76_phy *phy, struct ieee80211_hw *hw) struct mt76_dev *dev = phy->dev; struct wiphy *wiphy = hw->wiphy;

+ INIT_LIST_HEAD(&phy->tx_list); + spin_lock_init(&phy->tx_lock); + SET_IEEE80211_DEV(hw, dev->dev); SET_IEEE80211_PERM_ADDR(hw, phy->macaddr);

@@ -688,6 +691,7 @@ int mt76_register_device(struct mt76_dev *dev, bool vht, int ret;

dev_set_drvdata(dev->dev, dev); + mt76_wcid_init(&dev->global_wcid); ret = mt76_phy_init(phy, hw); if (ret) return ret; @@ -743,6 +747,7 @@ void mt76_unregister_device(struct mt76_dev *dev) if (IS_ENABLED(CONFIG_MT76_LEDS)) mt76_led_cleanup(&dev->phy); mt76_tx_status_check(dev, true); + mt76_wcid_cleanup(dev, &dev->global_wcid); ieee80211_unregister_hw(hw); } EXPORT_SYMBOL_GPL(mt76_unregister_device); @@ -1411,7 +1416,7 @@ mt76_sta_add(struct mt76_phy *phy, struct ieee80211_vif *vif, wcid->phy_idx = phy->band_idx; rcu_assign_pointer(dev->wcid[wcid->idx], wcid);

- mt76_packet_id_init(wcid); + mt76_wcid_init(wcid); out: mutex_unlock(&dev->mutex);

@@ -1430,7 +1435,7 @@ void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif, if (dev->drv->sta_remove) dev->drv->sta_remove(dev, vif, sta);

- mt76_packet_id_flush(dev, wcid); + mt76_wcid_cleanup(dev, wcid);

mt76_wcid_mask_clear(dev->wcid_mask, idx); mt76_wcid_mask_clear(dev->wcid_phy_mask, idx); @@ -1486,6 +1491,47 @@ void mt76_sta_pre_rcu_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif, } EXPORT_SYMBOL_GPL(mt76_sta_pre_rcu_remove);

+void mt76_wcid_init(struct mt76_wcid *wcid) +{ + INIT_LIST_HEAD(&wcid->tx_list); + skb_queue_head_init(&wcid->tx_pending); + + INIT_LIST_HEAD(&wcid->list); + idr_init(&wcid->pktid); +} +EXPORT_SYMBOL_GPL(mt76_wcid_init); + +void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid) +{ + struct mt76_phy *phy = dev->phys[wcid->phy_idx]; + struct ieee80211_hw *hw; + struct sk_buff_head list; + struct sk_buff *skb; + + mt76_tx_status_lock(dev, &list); + mt76_tx_status_skb_get(dev, wcid, -1, &list); + mt76_tx_status_unlock(dev, &list); + + idr_destroy(&wcid->pktid); + + spin_lock_bh(&phy->tx_lock); + + if (!list_empty(&wcid->tx_list)) + list_del_init(&wcid->tx_list); + + spin_lock(&wcid->tx_pending.lock); + skb_queue_splice_tail_init(&wcid->tx_pending, &list); + spin_unlock(&wcid->tx_pending.lock); + + spin_unlock_bh(&phy->tx_lock); + + while ((skb = __skb_dequeue(&list)) != NULL) { + hw = mt76_tx_status_get_hw(dev, skb); + ieee80211_free_txskb(hw, skb); + } +} +EXPORT_SYMBOL_GPL(mt76_wcid_cleanup); + int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm) { diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h index 7f44736ca26f0..8b620d4fed439 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@ -334,6 +334,9 @@ struct mt76_wcid { u32 tx_info; bool sw_iv;

+ struct list_head tx_list; + struct sk_buff_head tx_pending; + struct list_head list; struct idr pktid;

@@ -719,6 +722,8 @@ struct mt76_phy { unsigned long state; u8 band_idx;

+ spinlock_t tx_lock; + struct list_head tx_list; struct mt76_queue *q_tx[__MT_TXQ_MAX];

struct cfg80211_chan_def chandef; @@ -1599,22 +1604,7 @@ mt76_token_put(struct mt76_dev *dev, int token) return txwi; }

-static inline void mt76_packet_id_init(struct mt76_wcid *wcid) -{ - INIT_LIST_HEAD(&wcid->list); - idr_init(&wcid->pktid); -} - -static inline void -mt76_packet_id_flush(struct mt76_dev *dev, struct mt76_wcid *wcid) -{ - struct sk_buff_head list; - - mt76_tx_status_lock(dev, &list); - mt76_tx_status_skb_get(dev, wcid, -1, &list); - mt76_tx_status_unlock(dev, &list); - - idr_destroy(&wcid->pktid); -} +void mt76_wcid_init(struct mt76_wcid *wcid); +void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid);

#endif diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/main.c b/drivers/net/wireless/mediatek/mt76/mt7603/main.c index c213fd2a5216b..89d738deea62e 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7603/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7603/main.c @@ -70,7 +70,7 @@ mt7603_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->sta.wcid.idx = idx; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.vif = mvif; - mt76_packet_id_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid);

eth_broadcast_addr(bc_addr); mt7603_wtbl_init(dev, idx, mvif->idx, bc_addr); @@ -110,7 +110,7 @@ mt7603_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) dev->mt76.vif_mask &= ~BIT_ULL(mvif->idx); mutex_unlock(&dev->mt76.mutex);

- mt76_packet_id_flush(&dev->mt76, &mvif->sta.wcid); + mt76_wcid_cleanup(&dev->mt76, &mvif->sta.wcid); }

void mt7603_init_edcca(struct mt7603_dev *dev) diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/main.c b/drivers/net/wireless/mediatek/mt76/mt7615/main.c index 200b1752ca77f..dab16b5fc3861 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7615/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7615/main.c @@ -226,7 +226,7 @@ static int mt7615_add_interface(struct ieee80211_hw *hw, mvif->sta.wcid.idx = idx; mvif->sta.wcid.phy_idx = mvif->mt76.band_idx; mvif->sta.wcid.hw_key_idx = -1; - mt76_packet_id_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid);

mt7615_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -279,7 +279,7 @@ static void mt7615_remove_interface(struct ieee80211_hw *hw, list_del_init(&msta->wcid.poll_list); spin_unlock_bh(&dev->mt76.sta_poll_lock);

- mt76_packet_id_flush(&dev->mt76, &mvif->sta.wcid); + mt76_wcid_cleanup(&dev->mt76, &mvif->sta.wcid); }

int mt7615_set_channel(struct mt7615_phy *phy) diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c index dcbb5c605dfe6..8a0e8124b8940 100644 --- a/drivers/net/wireless/mediatek/mt76/mt76x02_util.c +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_util.c @@ -288,7 +288,7 @@ mt76x02_vif_init(struct mt76x02_dev *dev, struct ieee80211_vif *vif, mvif->idx = idx; mvif->group_wcid.idx = MT_VIF_WCID(idx); mvif->group_wcid.hw_key_idx = -1; - mt76_packet_id_init(&mvif->group_wcid); + mt76_wcid_init(&mvif->group_wcid);

mtxq = (struct mt76_txq *)vif->txq->drv_priv; rcu_assign_pointer(dev->mt76.wcid[MT_VIF_WCID(idx)], &mvif->group_wcid); @@ -346,7 +346,7 @@ void mt76x02_remove_interface(struct ieee80211_hw *hw,

dev->mt76.vif_mask &= ~BIT_ULL(mvif->idx); rcu_assign_pointer(dev->mt76.wcid[mvif->group_wcid.idx], NULL); - mt76_packet_id_flush(&dev->mt76, &mvif->group_wcid); + mt76_wcid_cleanup(&dev->mt76, &mvif->group_wcid); } EXPORT_SYMBOL_GPL(mt76x02_remove_interface);

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c index 3196f56cdf4ab..260fe00d7dc6d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c @@ -253,7 +253,7 @@ static int mt7915_add_interface(struct ieee80211_hw *hw, mvif->sta.wcid.phy_idx = ext_phy; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_packet_id_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid);

mt7915_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -314,7 +314,7 @@ static void mt7915_remove_interface(struct ieee80211_hw *hw, list_del_init(&msta->wcid.poll_list); spin_unlock_bh(&dev->mt76.sta_poll_lock);

- mt76_packet_id_flush(&dev->mt76, &msta->wcid); + mt76_wcid_cleanup(&dev->mt76, &msta->wcid); }

int mt7915_set_channel(struct mt7915_phy *phy) diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c index d8851cb5f400b..6a5c2cae087d0 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c @@ -318,7 +318,7 @@ mt7921_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) mvif->sta.wcid.phy_idx = mvif->mt76.band_idx; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_packet_id_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid);

mt7921_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c index 2fb1141e5fa96..66806ed4f942d 100644 --- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c +++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c @@ -115,7 +115,7 @@ void mt792x_remove_interface(struct ieee80211_hw *hw, list_del_init(&msta->wcid.poll_list); spin_unlock_bh(&dev->mt76.sta_poll_lock);

- mt76_packet_id_flush(&dev->mt76, &msta->wcid); + mt76_wcid_cleanup(&dev->mt76, &msta->wcid); } EXPORT_SYMBOL_GPL(mt792x_remove_interface);

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c index 620880e560e00..7fea9f0d409bf 100644 --- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c +++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c @@ -207,7 +207,7 @@ static int mt7996_add_interface(struct ieee80211_hw *hw, mvif->sta.wcid.phy_idx = band_idx; mvif->sta.wcid.hw_key_idx = -1; mvif->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET; - mt76_packet_id_init(&mvif->sta.wcid); + mt76_wcid_init(&mvif->sta.wcid);

mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR); @@ -268,7 +268,7 @@ static void mt7996_remove_interface(struct ieee80211_hw *hw, list_del_init(&msta->wcid.poll_list); spin_unlock_bh(&dev->mt76.sta_poll_lock);

- mt76_packet_id_flush(&dev->mt76, &msta->wcid); + mt76_wcid_cleanup(&dev->mt76, &msta->wcid); }

int mt7996_set_channel(struct mt7996_phy *phy) diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c index 6cc26cc6c5178..1809b03292c3d 100644 --- a/drivers/net/wireless/mediatek/mt76/tx.c +++ b/drivers/net/wireless/mediatek/mt76/tx.c @@ -329,40 +329,32 @@ void mt76_tx(struct mt76_phy *phy, struct ieee80211_sta *sta, struct mt76_wcid *wcid, struct sk_buff *skb) { - struct mt76_dev *dev = phy->dev; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - struct mt76_queue *q; - int qid = skb_get_queue_mapping(skb);

if (mt76_testmode_enabled(phy)) { ieee80211_free_txskb(phy->hw, skb); return; }

- if (WARN_ON(qid >= MT_TXQ_PSD)) { - qid = MT_TXQ_BE; - skb_set_queue_mapping(skb, qid); - } - - if ((dev->drv->drv_flags & MT_DRV_HW_MGMT_TXQ) && - !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) && - !ieee80211_is_data(hdr->frame_control) && - !ieee80211_is_bufferable_mmpdu(skb)) { - qid = MT_TXQ_PSD; - } + if (WARN_ON(skb_get_queue_mapping(skb) >= MT_TXQ_PSD)) + skb_set_queue_mapping(skb, MT_TXQ_BE);

if (wcid && !(wcid->tx_info & MT_WCID_TX_INFO_SET)) ieee80211_get_tx_rates(info->control.vif, sta, skb, info->control.rates, 1);

info->hw_queue |= FIELD_PREP(MT_TX_HW_QUEUE_PHY, phy->band_idx); - q = phy->q_tx[qid];

- spin_lock_bh(&q->lock); - __mt76_tx_queue_skb(phy, qid, skb, wcid, sta, NULL); - dev->queue_ops->kick(dev, q); - spin_unlock_bh(&q->lock); + spin_lock_bh(&wcid->tx_pending.lock); + __skb_queue_tail(&wcid->tx_pending, skb); + spin_unlock_bh(&wcid->tx_pending.lock); + + spin_lock_bh(&phy->tx_lock); + if (list_empty(&wcid->tx_list)) + list_add_tail(&wcid->tx_list, &phy->tx_list); + spin_unlock_bh(&phy->tx_lock); + + mt76_worker_schedule(&phy->dev->tx_worker); } EXPORT_SYMBOL_GPL(mt76_tx);

@@ -593,10 +585,86 @@ void mt76_txq_schedule(struct mt76_phy *phy, enum mt76_txq_id qid) } EXPORT_SYMBOL_GPL(mt76_txq_schedule);

+static int +mt76_txq_schedule_pending_wcid(struct mt76_phy *phy, struct mt76_wcid *wcid) +{ + struct mt76_dev *dev = phy->dev; + struct ieee80211_sta *sta; + struct mt76_queue *q; + struct sk_buff *skb; + int ret = 0; + + spin_lock(&wcid->tx_pending.lock); + while ((skb = skb_peek(&wcid->tx_pending)) != NULL) { + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + int qid = skb_get_queue_mapping(skb); + + if ((dev->drv->drv_flags & MT_DRV_HW_MGMT_TXQ) && + !(info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP) && + !ieee80211_is_data(hdr->frame_control) && + !ieee80211_is_bufferable_mmpdu(skb)) + qid = MT_TXQ_PSD; + + q = phy->q_tx[qid]; + if (mt76_txq_stopped(q)) { + ret = -1; + break; + } + + __skb_unlink(skb, &wcid->tx_pending); + spin_unlock(&wcid->tx_pending.lock); + + sta = wcid_to_sta(wcid); + spin_lock(&q->lock); + __mt76_tx_queue_skb(phy, qid, skb, wcid, sta, NULL); + dev->queue_ops->kick(dev, q); + spin_unlock(&q->lock); + + spin_lock(&wcid->tx_pending.lock); + } + spin_unlock(&wcid->tx_pending.lock); + + return ret; +} + +static void mt76_txq_schedule_pending(struct mt76_phy *phy) +{ + if (list_empty(&phy->tx_list)) + return; + + local_bh_disable(); + rcu_read_lock(); + + spin_lock(&phy->tx_lock); + while (!list_empty(&phy->tx_list)) { + struct mt76_wcid *wcid = NULL; + int ret; + + wcid = list_first_entry(&phy->tx_list, struct mt76_wcid, tx_list); + list_del_init(&wcid->tx_list); + + spin_unlock(&phy->tx_lock); + ret = mt76_txq_schedule_pending_wcid(phy, wcid); + spin_lock(&phy->tx_lock); + + if (ret) { + if (list_empty(&wcid->tx_list)) + list_add_tail(&wcid->tx_list, &phy->tx_list); + break; + } + } + spin_unlock(&phy->tx_lock); + + rcu_read_unlock(); + local_bh_enable(); +} + void mt76_txq_schedule_all(struct mt76_phy *phy) { int i;

+ mt76_txq_schedule_pending(phy); for (i = 0; i <= MT_TXQ_BK; i++) mt76_txq_schedule(phy, i); }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Alex Hung alex.hung@amd.com

[ Upstream commit 58c3b3341cea4f75dc8c003b89f8a6dd8ec55e50 ]

[WHAT] hw_points_num is 0 before ogam LUT is programmed; however, function "dwb3_program_ogam_pwl" assumes hw_points_num is always greater than 0, i.e. substracting it by 1 as an array index.

[HOW] Check hw_points_num is not equal to 0 before using it.

Reviewed-by: Harry Wentland harry.wentland@amd.com Signed-off-by: Alex Hung alex.hung@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c index 701c7d8bc038a..03a50c32fcfe1 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c @@ -243,6 +243,9 @@ static bool dwb3_program_ogam_lut( return false; }

+ if (params->hw_points_num == 0) + return false; + REG_SET(DWB_OGAM_CONTROL, 0, DWB_OGAM_MODE, 2);

current_mode = dwb3_get_ogam_current(dwbc30);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Jithu Joseph jithu.joseph@intel.com

[ Upstream commit 25a76dbb36dd58ad4df7f6a4dc43061a10b0d817 ]

Perform additional validation prior to loading IFS image.

Error out if the size of the file being loaded doesn't match the size specified in the header.

Signed-off-by: Jithu Joseph jithu.joseph@intel.com Reviewed-by: Tony Luck tony.luck@intel.com Reviewed-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Tested-by: Pengfei Xu pengfei.xu@intel.com Link: https://lore.kernel.org/r/20231005195137.3117166-6-jithu.joseph@intel.com Signed-off-by: Ilpo Järvinen ilpo.jarvinen@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/platform/x86/intel/ifs/load.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/drivers/platform/x86/intel/ifs/load.c b/drivers/platform/x86/intel/ifs/load.c index cefd0d886cfd4..ae52de138a6ea 100644 --- a/drivers/platform/x86/intel/ifs/load.c +++ b/drivers/platform/x86/intel/ifs/load.c @@ -260,6 +260,7 @@ int ifs_load_firmware(struct device *dev) { const struct ifs_test_caps *test = ifs_get_test_caps(dev); struct ifs_data *ifsd = ifs_get_data(dev); + unsigned int expected_size; const struct firmware *fw; char scan_path[64]; int ret = -EINVAL; @@ -274,6 +275,13 @@ int ifs_load_firmware(struct device *dev) goto done; }

+ expected_size = ((struct microcode_header_intel *)fw->data)->totalsize; + if (fw->size != expected_size) { + dev_err(dev, "File size mismatch (expected %u, actual %zu). Corrupted IFS image.\n", + expected_size, fw->size); + return -EINVAL; + } + ret = image_sanity_check(dev, (struct microcode_header_intel *)fw->data); if (ret) goto release;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Ofir Bitton obitton@habana.ai

[ Upstream commit 1e3a78270b4ec1c8c177eb310c08128d52137a69 ]

As TPC kernels now must use those registers we unsecure them.

Signed-off-by: Ofir Bitton obitton@habana.ai Reviewed-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/accel/habanalabs/gaudi2/gaudi2_security.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c index 2742b1f801eb2..908710524dc9e 100644 --- a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c +++ b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c @@ -1601,6 +1601,7 @@ static const u32 gaudi2_pb_dcr0_tpc0_unsecured_regs[] = { mmDCORE0_TPC0_CFG_KERNEL_SRF_30, mmDCORE0_TPC0_CFG_KERNEL_SRF_31, mmDCORE0_TPC0_CFG_TPC_SB_L0CD, + mmDCORE0_TPC0_CFG_TPC_COUNT, mmDCORE0_TPC0_CFG_TPC_ID, mmDCORE0_TPC0_CFG_QM_KERNEL_ID_INC, mmDCORE0_TPC0_CFG_QM_TID_BASE_SIZE_HIGH_DIM_0,

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: farah kassabri fkassabri@habana.ai

[ Upstream commit 0165994c215f321e2d055368f89b424756e340eb ]

There is a potential race between user thread seeking to re-use a timestamp record with new interrupt id, while this record is still in the middle of interrupt handling and it is about to be freed. Imagine the driver set the record in_use to 0 and only then fill the free_node information. This might lead to unpleasant scenario where the new registration thread detects the record as free to use, and change the cq buff address. That will cause the free_node to get the wrong buffer address to put refcount to.

Signed-off-by: farah kassabri fkassabri@habana.ai Reviewed-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Oded Gabbay ogabbay@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/accel/habanalabs/common/irq.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/accel/habanalabs/common/irq.c b/drivers/accel/habanalabs/common/irq.c index b1010d206c2ef..813315cea4a7b 100644 --- a/drivers/accel/habanalabs/common/irq.c +++ b/drivers/accel/habanalabs/common/irq.c @@ -271,6 +271,9 @@ static int handle_registration_node(struct hl_device *hdev, struct hl_user_pendi free_node->cq_cb = pend->ts_reg_info.cq_cb; list_add(&free_node->free_objects_node, *free_list);

+ /* Mark TS record as free */ + pend->ts_reg_info.in_use = false; + return 0; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Christian Brauner christian.brauner@ubuntu.com

[ Upstream commit 1c5976ef0f7ad76319df748ccb99a4c7ba2ba464 ]

Currently, registering a new binary type pins the binfmt_misc filesystem. Specifically, this means that as long as there is at least one binary type registered the binfmt_misc filesystem survives all umounts, i.e. the superblock is not destroyed. Meaning that a umount followed by another mount will end up with the same superblock and the same binary type handlers. This is a behavior we tend to discourage for any new filesystems (apart from a few special filesystems such as e.g. configfs or debugfs). A umount operation without the filesystem being pinned - by e.g. someone holding a file descriptor to an open file - should usually result in the destruction of the superblock and all associated resources. This makes introspection easier and leads to clearly defined, simple and clean semantics. An administrator can rely on the fact that a umount will guarantee a clean slate making it possible to reinitialize a filesystem. Right now all binary types would need to be explicitly deleted before that can happen.

This allows us to remove the heavy-handed calls to simple_pin_fs() and simple_release_fs() when creating and deleting binary types. This in turn allows us to replace the current brittle pinning mechanism abusing dget() which has caused a range of bugs judging from prior fixes in [2] and [3]. The additional dget() in load_misc_binary() pins the dentry but only does so for the sake to prevent ->evict_inode() from freeing the node when a user removes the binary type and kill_node() is run. Which would mean ->interpreter and ->interp_file would be freed causing a UAF.

This isn't really nicely documented nor is it very clean because it relies on simple_pin_fs() pinning the filesystem as long as at least one binary type exists. Otherwise it would cause load_misc_binary() to hold on to a dentry belonging to a superblock that has been shutdown. Replace that implicit pinning with a clean and simple per-node refcount and get rid of the ugly dget() pinning. A similar mechanism exists for e.g. binderfs (cf. [4]). All the cleanup work can now be done in ->evict_inode().

In a follow-up patch we will make it possible to use binfmt_misc in sandboxes. We will use the cleaner semantics where a umount for the filesystem will cause the superblock and all resources to be deallocated. In preparation for this apply the same semantics to the initial binfmt_misc mount. Note, that this is a user-visible change and as such a uapi change but one that we can reasonably risk. We've discussed this in earlier versions of this patchset (cf. [1]).

The main user and provider of binfmt_misc is systemd. Systemd provides binfmt_misc via autofs since it is configurable as a kernel module and is used by a few exotic packages and users. As such a binfmt_misc mount is triggered when /proc/sys/fs/binfmt_misc is accessed and is only provided on demand. Other autofs on demand filesystems include EFI ESP which systemd umounts if the mountpoint stays idle for a certain amount of time. This doesn't apply to the binfmt_misc autofs mount which isn't touched once it is mounted meaning this change can't accidently wipe binary type handlers without someone having explicitly unmounted binfmt_misc. After speaking to systemd folks they don't expect this change to affect them.

In line with our general policy, if we see a regression for systemd or other users with this change we will switch back to the old behavior for the initial binfmt_misc mount and have binary types pin the filesystem again. But while we touch this code let's take the chance and let's improve on the status quo.

[1]: https://lore.kernel.org/r/20191216091220.465626-2-laurent@vivier.eu [2]: commit 43a4f2619038 ("exec: binfmt_misc: fix race between load_misc_binary() and kill_node()" [3]: commit 83f918274e4b ("exec: binfmt_misc: shift filp_close(interp_file) from kill_node() to bm_evict_inode()") [4]: commit f0fe2c0f050d ("binder: prevent UAF for binderfs devices II")

Link: https://lore.kernel.org/r/20211028103114.2849140-1-brauner@kernel.org (v1) Cc: Sargun Dhillon sargun@sargun.me Cc: Serge Hallyn serge@hallyn.com Cc: Jann Horn jannh@google.com Cc: Henning Schild henning.schild@siemens.com Cc: Andrei Vagin avagin@gmail.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Laurent Vivier laurent@vivier.eu Cc: linux-fsdevel@vger.kernel.org Acked-by: Serge Hallyn serge@hallyn.com Signed-off-by: Christian Brauner christian.brauner@ubuntu.com Signed-off-by: Christian Brauner brauner@kernel.org Signed-off-by: Kees Cook keescook@chromium.org --- /* v2 */ - Christian Brauner christian.brauner@ubuntu.com: - Add more comments that explain what's going on. - Rename functions while changing them to better reflect what they are doing to make the code easier to understand. - In the first version when a specific binary type handler was removed either through a write to the entry's file or all binary type handlers were removed by a write to the binfmt_misc mount's status file all cleanup work happened during inode eviction. That includes removal of the relevant entries from entry list. While that works fine I disliked that model after thinking about it for a bit. Because it means that there was a window were someone has already removed a or all binary handlers but they could still be safely reached from load_misc_binary() when it has managed to take the read_lock() on the entries list while inode eviction was already happening. Again, that perfectly benign but it's cleaner to remove the binary handler from the list immediately meaning that ones the write to then entry's file or the binfmt_misc status file returns the binary type cannot be executed anymore. That gives stronger guarantees to the user. Signed-off-by: Sasha Levin sashal@kernel.org --- fs/binfmt_misc.c | 216 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 168 insertions(+), 48 deletions(-)

diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index e0108d17b085c..cf5ed5cd4102d 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -60,12 +60,11 @@ typedef struct { char *name; struct dentry *dentry; struct file *interp_file; + refcount_t users; /* sync removal with load_misc_binary() */ } Node;

static DEFINE_RWLOCK(entries_lock); static struct file_system_type bm_fs_type; -static struct vfsmount *bm_mnt; -static int entry_count;

/* * Max length of the register string. Determined by: @@ -82,19 +81,23 @@ static int entry_count; */ #define MAX_REGISTER_LENGTH 1920

-/* - * Check if we support the binfmt - * if we do, return the node, else NULL - * locking is done in load_misc_binary +/** + * search_binfmt_handler - search for a binary handler for @bprm + * @misc: handle to binfmt_misc instance + * @bprm: binary for which we are looking for a handler + * + * Search for a binary type handler for @bprm in the list of registered binary + * type handlers. + * + * Return: binary type list entry on success, NULL on failure */ -static Node *check_file(struct linux_binprm *bprm) +static Node *search_binfmt_handler(struct linux_binprm *bprm) { char *p = strrchr(bprm->interp, '.'); - struct list_head *l; + Node *e;

/* Walk all the registered handlers. */ - list_for_each(l, &entries) { - Node *e = list_entry(l, Node, list); + list_for_each_entry(e, &entries, list) { char *s; int j;

@@ -123,9 +126,49 @@ static Node *check_file(struct linux_binprm *bprm) if (j == e->size) return e; } + return NULL; }

+/** + * get_binfmt_handler - try to find a binary type handler + * @misc: handle to binfmt_misc instance + * @bprm: binary for which we are looking for a handler + * + * Try to find a binfmt handler for the binary type. If one is found take a + * reference to protect against removal via bm_{entry,status}_write(). + * + * Return: binary type list entry on success, NULL on failure + */ +static Node *get_binfmt_handler(struct linux_binprm *bprm) +{ + Node *e; + + read_lock(&entries_lock); + e = search_binfmt_handler(bprm); + if (e) + refcount_inc(&e->users); + read_unlock(&entries_lock); + return e; +} + +/** + * put_binfmt_handler - put binary handler node + * @e: node to put + * + * Free node syncing with load_misc_binary() and defer final free to + * load_misc_binary() in case it is using the binary type handler we were + * requested to remove. + */ +static void put_binfmt_handler(Node *e) +{ + if (refcount_dec_and_test(&e->users)) { + if (e->flags & MISC_FMT_OPEN_FILE) + filp_close(e->interp_file, NULL); + kfree(e); + } +} + /* * the loader itself */ @@ -139,12 +182,7 @@ static int load_misc_binary(struct linux_binprm *bprm) if (!enabled) return retval;

- /* to keep locking time low, we copy the interpreter string */ - read_lock(&entries_lock); - fmt = check_file(bprm); - if (fmt) - dget(fmt->dentry); - read_unlock(&entries_lock); + fmt = get_binfmt_handler(bprm); if (!fmt) return retval;

@@ -198,7 +236,16 @@ static int load_misc_binary(struct linux_binprm *bprm)

retval = 0; ret: - dput(fmt->dentry); + + /* + * If we actually put the node here all concurrent calls to + * load_misc_binary() will have finished. We also know + * that for the refcount to be zero ->evict_inode() must have removed + * the node to be deleted from the list. All that is left for us is to + * close and free. + */ + put_binfmt_handler(fmt); + return retval; }

@@ -552,30 +599,90 @@ static struct inode *bm_get_inode(struct super_block *sb, int mode) return inode; }

+/** + * bm_evict_inode - cleanup data associated with @inode + * @inode: inode to which the data is attached + * + * Cleanup the binary type handler data associated with @inode if a binary type + * entry is removed or the filesystem is unmounted and the super block is + * shutdown. + * + * If the ->evict call was not caused by a super block shutdown but by a write + * to remove the entry or all entries via bm_{entry,status}_write() the entry + * will have already been removed from the list. We keep the list_empty() check + * to make that explicit. +*/ static void bm_evict_inode(struct inode *inode) { Node *e = inode->i_private;

- if (e && e->flags & MISC_FMT_OPEN_FILE) - filp_close(e->interp_file, NULL); - clear_inode(inode); - kfree(e); + + if (e) { + write_lock(&entries_lock); + if (!list_empty(&e->list)) + list_del_init(&e->list); + write_unlock(&entries_lock); + put_binfmt_handler(e); + } }

-static void kill_node(Node *e) +/** + * unlink_binfmt_dentry - remove the dentry for the binary type handler + * @dentry: dentry associated with the binary type handler + * + * Do the actual filesystem work to remove a dentry for a registered binary + * type handler. Since binfmt_misc only allows simple files to be created + * directly under the root dentry of the filesystem we ensure that we are + * indeed passed a dentry directly beneath the root dentry, that the inode + * associated with the root dentry is locked, and that it is a regular file we + * are asked to remove. + */ +static void unlink_binfmt_dentry(struct dentry *dentry) { - struct dentry *dentry; + struct dentry *parent = dentry->d_parent; + struct inode *inode, *parent_inode; + + /* All entries are immediate descendants of the root dentry. */ + if (WARN_ON_ONCE(dentry->d_sb->s_root != parent)) + return;

+ /* We only expect to be called on regular files. */ + inode = d_inode(dentry); + if (WARN_ON_ONCE(!S_ISREG(inode->i_mode))) + return; + + /* The parent inode must be locked. */ + parent_inode = d_inode(parent); + if (WARN_ON_ONCE(!inode_is_locked(parent_inode))) + return; + + if (simple_positive(dentry)) { + dget(dentry); + simple_unlink(parent_inode, dentry); + d_delete(dentry); + dput(dentry); + } +} + +/** + * remove_binfmt_handler - remove a binary type handler + * @misc: handle to binfmt_misc instance + * @e: binary type handler to remove + * + * Remove a binary type handler from the list of binary type handlers and + * remove its associated dentry. This is called from + * binfmt_{entry,status}_write(). In the future, we might want to think about + * adding a proper ->unlink() method to binfmt_misc instead of forcing caller's + * to use writes to files in order to delete binary type handlers. But it has + * worked for so long that it's not a pressing issue. + */ +static void remove_binfmt_handler(Node *e) +{ write_lock(&entries_lock); list_del_init(&e->list); write_unlock(&entries_lock); - - dentry = e->dentry; - drop_nlink(d_inode(dentry)); - d_drop(dentry); - dput(dentry); - simple_release_fs(&bm_mnt, &entry_count); + unlink_binfmt_dentry(e->dentry); }

/* /<entry> */ @@ -602,8 +709,8 @@ bm_entry_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos) static ssize_t bm_entry_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { - struct dentry *root; - Node *e = file_inode(file)->i_private; + struct inode *inode = file_inode(file); + Node *e = inode->i_private; int res = parse_command(buffer, count);

switch (res) { @@ -617,13 +724,22 @@ static ssize_t bm_entry_write(struct file *file, const char __user *buffer, break; case 3: /* Delete this handler. */ - root = file_inode(file)->i_sb->s_root; - inode_lock(d_inode(root)); + inode = d_inode(inode->i_sb->s_root); + inode_lock(inode);

+ /* + * In order to add new element or remove elements from the list + * via bm_{entry,register,status}_write() inode_lock() on the + * root inode must be held. + * The lock is exclusive ensuring that the list can't be + * modified. Only load_misc_binary() can access but does so + * read-only. So we only need to take the write lock when we + * actually remove the entry from the list. + */ if (!list_empty(&e->list)) - kill_node(e); + remove_binfmt_handler(e);

- inode_unlock(d_inode(root)); + inode_unlock(inode); break; default: return res; @@ -682,13 +798,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, if (!inode) goto out2;

- err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count); - if (err) { - iput(inode); - inode = NULL; - goto out2; - } - + refcount_set(&e->users, 1); e->dentry = dget(dentry); inode->i_private = e; inode->i_fop = &bm_entry_operations; @@ -732,7 +842,8 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos) { int res = parse_command(buffer, count); - struct dentry *root; + Node *e, *next; + struct inode *inode;

switch (res) { case 1: @@ -745,13 +856,22 @@ static ssize_t bm_status_write(struct file *file, const char __user *buffer, break; case 3: /* Delete all handlers. */ - root = file_inode(file)->i_sb->s_root; - inode_lock(d_inode(root)); + inode = d_inode(file_inode(file)->i_sb->s_root); + inode_lock(inode);

- while (!list_empty(&entries)) - kill_node(list_first_entry(&entries, Node, list)); + /* + * In order to add new element or remove elements from the list + * via bm_{entry,register,status}_write() inode_lock() on the + * root inode must be held. + * The lock is exclusive ensuring that the list can't be + * modified. Only load_misc_binary() can access but does so + * read-only. So we only need to take the write lock when we + * actually remove the entry from the list. + */ + list_for_each_entry_safe(e, next, &entries, list) + remove_binfmt_handler(e);

- inode_unlock(d_inode(root)); + inode_unlock(inode); break; default: return res;

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Hans Verkuil hverkuil-cisco@xs4all.nl

[ Upstream commit 51b74c09ac8c5862007fc2bf0d465529d06dd446 ]

'pd' can be NULL, and in that case it shouldn't be passed to PTR_ERR. Fixes a smatch warning:

drivers/media/platform/qcom/venus/pm_helpers.c:873 vcodec_domains_get() warn: passing zero to 'PTR_ERR'

Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Reviewed-by: Bryan O'Donoghue bryan.odonoghue@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/media/platform/qcom/venus/pm_helpers.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/venus/pm_helpers.c b/drivers/media/platform/qcom/venus/pm_helpers.c index 48c9084bb4dba..a1b127caa90a7 100644 --- a/drivers/media/platform/qcom/venus/pm_helpers.c +++ b/drivers/media/platform/qcom/venus/pm_helpers.c @@ -870,7 +870,7 @@ static int vcodec_domains_get(struct venus_core *core) pd = dev_pm_domain_attach_by_name(dev, res->vcodec_pmdomains[i]); if (IS_ERR_OR_NULL(pd)) - return PTR_ERR(pd) ? : -ENODATA; + return pd ? PTR_ERR(pd) : -ENODATA; core->pmdomains[i] = pd; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Peter Ujfalusi peter.ujfalusi@linux.intel.com

[ Upstream commit 576a0b71b5b479008dacb3047a346625040f5ac6 ]

In the existing IPC support, the reply to each IPC message is handled in an IRQ thread. The assumption is that the IRQ thread is scheduled without significant delays.

On an experimental (iow, buggy) kernel, the IRQ thread dealing with the reply to the last IPC message before powering-down the DSP can be delayed by several seconds. The IRQ thread will proceed with register accesses after the DSP is powered-down which results in a kernel crash.

While the bug which causes the delay is not in the audio stack, we must handle such cases with defensive programming to avoid such crashes.

Call synchronize_irq() before proceeding to power down the DSP to make sure that no irq thread is pending execution.

Closes: https://github.com/thesofproject/linux/issues/4608 Reviewed-by: Guennadi Liakhovetski guennadi.liakhovetski@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Signed-off-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Link: https://lore.kernel.org/r/20231012191850.147140-3-pierre-louis.bossart@linux... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/intel/hda-dsp.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/sound/soc/sof/intel/hda-dsp.c b/sound/soc/sof/intel/hda-dsp.c index e80a2a5ec56a1..1506982a56c30 100644 --- a/sound/soc/sof/intel/hda-dsp.c +++ b/sound/soc/sof/intel/hda-dsp.c @@ -709,6 +709,9 @@ static int hda_suspend(struct snd_sof_dev *sdev, bool runtime_suspend) if (ret < 0) return ret;

+ /* make sure that no irq handler is pending before shutdown */ + synchronize_irq(sdev->ipc_irq); + hda_codec_jack_wake_enable(sdev, runtime_suspend);

/* power down all hda links */

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Johannes Berg johannes.berg@intel.com

[ Upstream commit 06d6af4e1223339bb597b02fa8ad3f979ddb5511 ]

When the station is marked as no longer authorized, we shouldn't transmit to it any longer, but in particular we shouldn't be able to transmit to it after removing keys, which might lead to frames being sent out unencrypted depending on the exact hardware offload mechanism. Thus, instead of flushing only on station destruction, which covers only some cases, always flush on unauthorization.

Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20230928172905.d47f528829e7.I96903652c7ee0c5c66891... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- net/mac80211/sta_info.c | 32 ++++++++++++++++++++------------ 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 42ba51a9700f2..5d71e8d084c45 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -1284,6 +1284,8 @@ static int _sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state, bool recalc) { + struct ieee80211_local *local = sta->local; + might_sleep();

if (sta->sta_state == new_state) @@ -1359,6 +1361,24 @@ static int _sta_info_move_state(struct sta_info *sta, } else if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { ieee80211_vif_dec_num_mcast(sta->sdata); clear_bit(WLAN_STA_AUTHORIZED, &sta->_flags); + + /* + * If we have encryption offload, flush (station) queues + * (after ensuring concurrent TX completed) so we won't + * transmit anything later unencrypted if/when keys are + * also removed, which might otherwise happen depending + * on how the hardware offload works. + */ + if (local->ops->set_key) { + synchronize_net(); + if (local->ops->flush_sta) + drv_flush_sta(local, sta->sdata, sta); + else + ieee80211_flush_queues(local, + sta->sdata, + false); + } + ieee80211_clear_fast_xmit(sta); ieee80211_clear_fast_rx(sta); } @@ -1424,18 +1444,6 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc) WARN_ON_ONCE(ret); }

- /* Flush queues before removing keys, as that might remove them - * from hardware, and then depending on the offload method, any - * frames sitting on hardware queues might be sent out without - * any encryption at all. - */ - if (local->ops->set_key) { - if (local->ops->flush_sta) - drv_flush_sta(local, sta->sdata, sta); - else - ieee80211_flush_queues(local, sta->sdata, false); - } - /* now keys can no longer be reached */ ieee80211_free_sta_keys(local, sta);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Miri Korenblit miriam.rachel.korenblit@intel.com

[ Upstream commit 3c6a0b1f0add72e7f522bc9145222b86d0a7712a ]

In RFKILL we first set the RFKILL bit, then we abort scan (if one exists) by waiting for the notification from FW and notifying mac80211. And then we stop the device. But in case we have a scan ongoing in the period of time between rfkill on and before the device is stopped - we will not wait for the FW notification because of the iwl_mvm_is_radio_killed() condition, and then the scan_status and uid_status are misconfigured, (scan_status is cleared but uid_status not) and when the notification suddenly arrives (before stopping the device) we will get into the assert about scan_status and uid_status mismatch. Fix this by waiting for FW notif when rfkill is on but the device isn't disabled yet.

Signed-off-by: Miri Korenblit miriam.rachel.korenblit@intel.com Signed-off-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20231004123422.c43b69aa2c77.Icc7b5efb47974d6f49915... Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c index 6ef932e6299da..9ca90c0806c0f 100644 --- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c @@ -3413,7 +3413,7 @@ int iwl_mvm_scan_stop(struct iwl_mvm *mvm, int type, bool notify) if (!(mvm->scan_status & type)) return 0;

- if (iwl_mvm_is_radio_killed(mvm)) { + if (!test_bit(STATUS_DEVICE_ENABLED, &mvm->trans->status)) { ret = 0; goto out; }

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Dmitry Antipov dmantipov@yandex.ru

[ Upstream commit 3c8aaaa7557b1e33e6ef95a27a5d8a139dcd0874 ]

In 'iwl_parse_tlv_firmware()', check for 'kmemdup()' return value when handling IWL_UCODE_TLV_CURRENT_PC and set the number of parsed entries only if an allocation was successful (just like it does with handling IWL_UCODE_TLV_CMD_VERSIONS above). Compile tested only.

Signed-off-by: Dmitry Antipov dmantipov@yandex.ru Acked-by: Gregory Greenman gregory.greenman@intel.com Link: https://lore.kernel.org/r/20231009170453.149905-1-dmantipov@yandex.ru Signed-off-by: Johannes Berg johannes.berg@intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c index a56593b6135f6..47bea1855e8c8 100644 --- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c +++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c @@ -1304,10 +1304,12 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv, case IWL_UCODE_TLV_CURRENT_PC: if (tlv_len < sizeof(struct iwl_pc_data)) goto invalid_tlv_len; - drv->trans->dbg.num_pc = - tlv_len / sizeof(struct iwl_pc_data); drv->trans->dbg.pc_data = kmemdup(tlv_data, tlv_len, GFP_KERNEL); + if (!drv->trans->dbg.pc_data) + return -ENOMEM; + drv->trans->dbg.num_pc = + tlv_len / sizeof(struct iwl_pc_data); break; default: IWL_DEBUG_INFO(drv, "unknown TLV: %d\n", tlv_type);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Chengfeng Ye dg573847474@gmail.com

[ Upstream commit 2f19c4b8395ccb6eb25ccafee883c8cfbe3fc193 ]

handle_receive_interrupt_napi_sp() running inside interrupt handler could introduce inverse lock ordering between &dd->irq_src_lock and &dd->uctxt_lock, if read_mod_write() is preempted by the isr.

[CPU0] | [CPU1] hfi1_ipoib_dev_open() | --> hfi1_netdev_enable_queues() | --> enable_queues(rx) | --> hfi1_rcvctrl() | --> set_intr_bits() | --> read_mod_write() | --> spin_lock(&dd->irq_src_lock) | | hfi1_poll() | --> poll_next() | --> spin_lock_irq(&dd->uctxt_lock) | | --> hfi1_rcvctrl() | --> set_intr_bits() | --> read_mod_write() | --> spin_lock(&dd->irq_src_lock) <interrupt> | --> handle_receive_interrupt_napi_sp() | --> set_all_fastpath() | --> hfi1_rcd_get_by_index() | --> spin_lock_irqsave(&dd->uctxt_lock) |

This flaw was found by an experimental static analysis tool I am developing for irq-related deadlock.

To prevent the potential deadlock, the patch use spin_lock_irqsave() on &dd->irq_src_lock inside read_mod_write() to prevent the possible deadlock scenario.

Signed-off-by: Chengfeng Ye dg573847474@gmail.com Link: https://lore.kernel.org/r/20230926101116.2797-1-dg573847474@gmail.com Acked-by: Dennis Dalessandro dennis.dalessandro@cornelisnetworks.com Signed-off-by: Leon Romanovsky leon@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/hfi1/chip.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 0814291a04120..9b542f7c6c115 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -13185,15 +13185,16 @@ static void read_mod_write(struct hfi1_devdata *dd, u16 src, u64 bits, { u64 reg; u16 idx = src / BITS_PER_REGISTER; + unsigned long flags;

- spin_lock(&dd->irq_src_lock); + spin_lock_irqsave(&dd->irq_src_lock, flags); reg = read_csr(dd, CCE_INT_MASK + (8 * idx)); if (set) reg |= bits; else reg &= ~bits; write_csr(dd, CCE_INT_MASK + (8 * idx), reg); - spin_unlock(&dd->irq_src_lock); + spin_unlock_irqrestore(&dd->irq_src_lock, flags); }

/**

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Miguel Ojeda ojeda@kernel.org

[ Upstream commit 9e98db17837093cb0f4dcfcc3524739d93249c45 ]

`bindgen` 0.69.0 contains a bug: `--version` does not work without providing a header [1]:

error: the following required arguments were not provided: <HEADER>

Usage: bindgen <FLAGS> <OPTIONS> <HEADER> -- <CLANG_ARGS>...

Thus, in preparation for supporting several `bindgen` versions, work around the issue by passing a dummy argument.

Include a comment so that we can remove the workaround in the future.

Link: https://github.com/rust-lang/rust-bindgen/pull/2678 [1] Reviewed-by: Finn Behrens me@kloenk.dev Tested-by: Benno Lossin benno.lossin@proton.me Tested-by: Andreas Hindborg a.hindborg@samsung.com Link: https://lore.kernel.org/r/20240709160615.998336-9-ojeda@kernel.org Signed-off-by: Miguel Ojeda ojeda@kernel.org Stable-dep-of: 5ce86c6c8613 ("rust: suppress error messages from CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT") Signed-off-by: Sasha Levin sashal@kernel.org --- init/Kconfig | 5 ++++- scripts/rust_is_available.sh | 6 +++++- 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig index e173364abd6c0..777113dceca55 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1921,7 +1921,10 @@ config RUSTC_VERSION_TEXT config BINDGEN_VERSION_TEXT string depends on RUST - default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n) + # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 + # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when + # the minimum version is upgraded past that (0.69.1 already fixed the issue). + default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version workaround-for-0.69.0 || echo n)

# # Place an empty function call at each tracepoint site. Can be diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh index 117018946b577..a6fdcf13e0e53 100755 --- a/scripts/rust_is_available.sh +++ b/scripts/rust_is_available.sh @@ -129,8 +129,12 @@ fi # Check that the Rust bindings generator is suitable. # # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. +# +# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 +# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when +# the minimum version is upgraded past that (0.69.1 already fixed the issue). rust_bindings_generator_output=$( \ - LC_ALL=C "$BINDGEN" --version 2>/dev/null + LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null ) || rust_bindings_generator_code=$? if [ -n "$rust_bindings_generator_code" ]; then echo >&2 "***"

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Masahiro Yamada masahiroy@kernel.org

[ Upstream commit aacf93e87f0d808ef46e621aa56caea336b4433c ]

Another oddity in these config entries is their default value can fall back to 'n', which is a value for bool or tristate symbols.

The '|| echo n' is an incorrect workaround to avoid the syntax error. This is not a big deal, as the entry is hidden by 'depends on RUST' in situations where '$(RUSTC) --version' or '$(BINDGEN) --version' fails. Anyway, it looks odd.

The default of a string type symbol should be a double-quoted string literal. Turn it into an empty string when the version command fails.

Fixes: 2f7ab1267dc9 ("Kbuild: add Rust support") Signed-off-by: Masahiro Yamada masahiroy@kernel.org Link: https://lore.kernel.org/r/20240727140302.1806011-2-masahiroy@kernel.org [ Rebased on top of v6.11-rc1. - Miguel ] Signed-off-by: Miguel Ojeda ojeda@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig index b5bcc863bf608..6054ba684c539 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -1916,7 +1916,7 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default $(shell,$(RUSTC) --version 2>/dev/null || echo n) + default "$(shell,$(RUSTC) --version 2>/dev/null)"

config BINDGEN_VERSION_TEXT string @@ -1924,7 +1924,7 @@ config BINDGEN_VERSION_TEXT # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when # the minimum version is upgraded past that (0.69.1 already fixed the issue). - default $(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null || echo n) + default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)"

# # Place an empty function call at each tracepoint site. Can be

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Nysal Jan K.A nysal@linux.ibm.com

[ Upstream commit 227bbaabe64b6f9cd98aa051454c1d4a194a8c6a ]

topology_is_core_online() checks if the core a CPU belongs to is online. The core is online if at least one of the sibling CPUs is online. The first CPU of an online core is also online in the common case, so this should be fairly quick.

Fixes: 73c58e7e1412 ("powerpc: Add HOTPLUG_SMT support") Signed-off-by: Nysal Jan K.A nysal@linux.ibm.com Reviewed-by: Shrikanth Hegde sshegde@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20240731030126.956210-3-nysal@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/include/asm/topology.h | 13 +++++++++++++ 1 file changed, 13 insertions(+)

diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h index f4e6f2dd04b73..16bacfe8c7a2c 100644 --- a/arch/powerpc/include/asm/topology.h +++ b/arch/powerpc/include/asm/topology.h @@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu)

#ifdef CONFIG_HOTPLUG_SMT #include <linux/cpu_smt.h> +#include <linux/cpumask.h> #include <asm/cputhreads.h>

static inline bool topology_is_primary_thread(unsigned int cpu) @@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu) { return cpu_thread_in_core(cpu) < cpu_smt_num_threads; } + +#define topology_is_core_online topology_is_core_online +static inline bool topology_is_core_online(unsigned int cpu) +{ + int i, first_cpu = cpu_first_thread_sibling(cpu); + + for (i = first_cpu; i < first_cpu + threads_per_core; ++i) { + if (cpu_online(i)) + return true; + } + return false; +} #endif

#endif /* __KERNEL__ */

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Li Lingfeng lilingfeng3@huawei.com

[ Upstream commit b313a8c835516bdda85025500be866ac8a74e022 ]

Lockdep reported a warning in Linux version 6.6:

[ 414.344659] ================================ [ 414.345155] WARNING: inconsistent lock state [ 414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted [ 414.346221] -------------------------------- [ 414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. [ 414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes: [ 414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.351204] {IN-SOFTIRQ-W} state was registered at: [ 414.351751] lock_acquire+0x18d/0x460 [ 414.352218] _raw_spin_lock_irqsave+0x39/0x60 [ 414.352769] __wake_up_common_lock+0x22/0x60 [ 414.353289] sbitmap_queue_wake_up+0x375/0x4f0 [ 414.353829] sbitmap_queue_clear+0xdd/0x270 [ 414.354338] blk_mq_put_tag+0xdf/0x170 [ 414.354807] __blk_mq_free_request+0x381/0x4d0 [ 414.355335] blk_mq_free_request+0x28b/0x3e0 [ 414.355847] __blk_mq_end_request+0x242/0xc30 [ 414.356367] scsi_end_request+0x2c1/0x830 [ 414.345155] WARNING: inconsistent lock state [ 414.345658] 6.6.0-07439-gba2303cacfda #6 Not tainted [ 414.346221] -------------------------------- [ 414.346712] inconsistent {IN-SOFTIRQ-W} -> {SOFTIRQ-ON-W} usage. [ 414.347545] kworker/u10:3/1152 [HC0[0]:SC0[0]:HE0:SE1] takes: [ 414.349245] ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.351204] {IN-SOFTIRQ-W} state was registered at: [ 414.351751] lock_acquire+0x18d/0x460 [ 414.352218] _raw_spin_lock_irqsave+0x39/0x60 [ 414.352769] __wake_up_common_lock+0x22/0x60 [ 414.353289] sbitmap_queue_wake_up+0x375/0x4f0 [ 414.353829] sbitmap_queue_clear+0xdd/0x270 [ 414.354338] blk_mq_put_tag+0xdf/0x170 [ 414.354807] __blk_mq_free_request+0x381/0x4d0 [ 414.355335] blk_mq_free_request+0x28b/0x3e0 [ 414.355847] __blk_mq_end_request+0x242/0xc30 [ 414.356367] scsi_end_request+0x2c1/0x830 [ 414.356863] scsi_io_completion+0x177/0x1610 [ 414.357379] scsi_complete+0x12f/0x260 [ 414.357856] blk_complete_reqs+0xba/0xf0 [ 414.358338] __do_softirq+0x1b0/0x7a2 [ 414.358796] irq_exit_rcu+0x14b/0x1a0 [ 414.359262] sysvec_call_function_single+0xaf/0xc0 [ 414.359828] asm_sysvec_call_function_single+0x1a/0x20 [ 414.360426] default_idle+0x1e/0x30 [ 414.360873] default_idle_call+0x9b/0x1f0 [ 414.361390] do_idle+0x2d2/0x3e0 [ 414.361819] cpu_startup_entry+0x55/0x60 [ 414.362314] start_secondary+0x235/0x2b0 [ 414.362809] secondary_startup_64_no_verify+0x18f/0x19b [ 414.363413] irq event stamp: 428794 [ 414.363825] hardirqs last enabled at (428793): [<ffffffff816bfd1c>] ktime_get+0x1dc/0x200 [ 414.364694] hardirqs last disabled at (428794): [<ffffffff85470177>] _raw_spin_lock_irq+0x47/0x50 [ 414.365629] softirqs last enabled at (428444): [<ffffffff85474780>] __do_softirq+0x540/0x7a2 [ 414.366522] softirqs last disabled at (428419): [<ffffffff813f65ab>] irq_exit_rcu+0x14b/0x1a0 [ 414.367425] other info that might help us debug this: [ 414.368194] Possible unsafe locking scenario: [ 414.368900] CPU0 [ 414.369225] ---- [ 414.369548] lock(&sbq->ws[i].wait); [ 414.370000] <Interrupt> [ 414.370342] lock(&sbq->ws[i].wait); [ 414.370802] *** DEADLOCK *** [ 414.371569] 5 locks held by kworker/u10:3/1152: [ 414.372088] #0: ffff88810130e938 ((wq_completion)writeback){+.+.}-{0:0}, at: process_scheduled_works+0x357/0x13f0 [ 414.373180] #1: ffff88810201fdb8 ((work_completion)(&(&wb->dwork)->work)){+.+.}-{0:0}, at: process_scheduled_works+0x3a3/0x13f0 [ 414.374384] #2: ffffffff86ffbdc0 (rcu_read_lock){....}-{1:2}, at: blk_mq_run_hw_queue+0x637/0xa00 [ 414.375342] #3: ffff88810edd1098 (&sbq->ws[i].wait){+.?.}-{2:2}, at: blk_mq_dispatch_rq_list+0x131c/0x1ee0 [ 414.376377] #4: ffff888106205a08 (&hctx->dispatch_wait_lock){+.-.}-{2:2}, at: blk_mq_dispatch_rq_list+0x1337/0x1ee0 [ 414.378607] stack backtrace: [ 414.379177] CPU: 0 PID: 1152 Comm: kworker/u10:3 Not tainted 6.6.0-07439-gba2303cacfda #6 [ 414.380032] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.14.0-0-g155821a1990b-prebuilt.qemu.org 04/01/2014 [ 414.381177] Workqueue: writeback wb_workfn (flush-253:0) [ 414.381805] Call Trace: [ 414.382136] <TASK> [ 414.382429] dump_stack_lvl+0x91/0xf0 [ 414.382884] mark_lock_irq+0xb3b/0x1260 [ 414.383367] ? __pfx_mark_lock_irq+0x10/0x10 [ 414.383889] ? stack_trace_save+0x8e/0xc0 [ 414.384373] ? __pfx_stack_trace_save+0x10/0x10 [ 414.384903] ? graph_lock+0xcf/0x410 [ 414.385350] ? save_trace+0x3d/0xc70 [ 414.385808] mark_lock.part.20+0x56d/0xa90 [ 414.386317] mark_held_locks+0xb0/0x110 [ 414.386791] ? __pfx_do_raw_spin_lock+0x10/0x10 [ 414.387320] lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.387901] ? _raw_spin_unlock_irq+0x28/0x50 [ 414.388422] trace_hardirqs_on+0x58/0x100 [ 414.388917] _raw_spin_unlock_irq+0x28/0x50 [ 414.389422] __blk_mq_tag_busy+0x1d6/0x2a0 [ 414.389920] __blk_mq_get_driver_tag+0x761/0x9f0 [ 414.390899] blk_mq_dispatch_rq_list+0x1780/0x1ee0 [ 414.391473] ? __pfx_blk_mq_dispatch_rq_list+0x10/0x10 [ 414.392070] ? sbitmap_get+0x2b8/0x450 [ 414.392533] ? __blk_mq_get_driver_tag+0x210/0x9f0 [ 414.393095] __blk_mq_sched_dispatch_requests+0xd99/0x1690 [ 414.393730] ? elv_attempt_insert_merge+0x1b1/0x420 [ 414.394302] ? __pfx___blk_mq_sched_dispatch_requests+0x10/0x10 [ 414.394970] ? lock_acquire+0x18d/0x460 [ 414.395456] ? blk_mq_run_hw_queue+0x637/0xa00 [ 414.395986] ? __pfx_lock_acquire+0x10/0x10 [ 414.396499] blk_mq_sched_dispatch_requests+0x109/0x190 [ 414.397100] blk_mq_run_hw_queue+0x66e/0xa00 [ 414.397616] blk_mq_flush_plug_list.part.17+0x614/0x2030 [ 414.398244] ? __pfx_blk_mq_flush_plug_list.part.17+0x10/0x10 [ 414.398897] ? writeback_sb_inodes+0x241/0xcc0 [ 414.399429] blk_mq_flush_plug_list+0x65/0x80 [ 414.399957] __blk_flush_plug+0x2f1/0x530 [ 414.400458] ? __pfx___blk_flush_plug+0x10/0x10 [ 414.400999] blk_finish_plug+0x59/0xa0 [ 414.401467] wb_writeback+0x7cc/0x920 [ 414.401935] ? __pfx_wb_writeback+0x10/0x10 [ 414.402442] ? mark_held_locks+0xb0/0x110 [ 414.402931] ? __pfx_do_raw_spin_lock+0x10/0x10 [ 414.403462] ? lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.404062] wb_workfn+0x2b3/0xcf0 [ 414.404500] ? __pfx_wb_workfn+0x10/0x10 [ 414.404989] process_scheduled_works+0x432/0x13f0 [ 414.405546] ? __pfx_process_scheduled_works+0x10/0x10 [ 414.406139] ? do_raw_spin_lock+0x101/0x2a0 [ 414.406641] ? assign_work+0x19b/0x240 [ 414.407106] ? lock_is_held_type+0x9d/0x110 [ 414.407604] worker_thread+0x6f2/0x1160 [ 414.408075] ? __kthread_parkme+0x62/0x210 [ 414.408572] ? lockdep_hardirqs_on_prepare+0x297/0x3f0 [ 414.409168] ? __kthread_parkme+0x13c/0x210 [ 414.409678] ? __pfx_worker_thread+0x10/0x10 [ 414.410191] kthread+0x33c/0x440 [ 414.410602] ? __pfx_kthread+0x10/0x10 [ 414.411068] ret_from_fork+0x4d/0x80 [ 414.411526] ? __pfx_kthread+0x10/0x10 [ 414.411993] ret_from_fork_asm+0x1b/0x30 [ 414.412489] </TASK>

When interrupt is turned on while a lock holding by spin_lock_irq it throws a warning because of potential deadlock.

blk_mq_prep_dispatch_rq blk_mq_get_driver_tag __blk_mq_get_driver_tag __blk_mq_alloc_driver_tag blk_mq_tag_busy -> tag is already busy // failed to get driver tag blk_mq_mark_tag_wait spin_lock_irq(&wq->lock) -> lock A (&sbq->ws[i].wait) __add_wait_queue(wq, wait) -> wait queue active blk_mq_get_driver_tag __blk_mq_tag_busy -> 1) tag must be idle, which means there can't be inflight IO spin_lock_irq(&tags->lock) -> lock B (hctx->tags) spin_unlock_irq(&tags->lock) -> unlock B, turn on interrupt accidentally -> 2) context must be preempt by IO interrupt to trigger deadlock.

As shown above, the deadlock is not possible in theory, but the warning still need to be fixed.

Fix it by using spin_lock_irqsave to get lockB instead of spin_lock_irq.

Fixes: 4f1731df60f9 ("blk-mq: fix potential io hang by wrong 'wake_batch'") Signed-off-by: Li Lingfeng lilingfeng3@huawei.com Reviewed-by: Ming Lei ming.lei@redhat.com Reviewed-by: Yu Kuai yukuai3@huawei.com Reviewed-by: Bart Van Assche bvanassche@acm.org Link: https://lore.kernel.org/r/20240815024736.2040971-1-lilingfeng@huaweicloud.co... Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- block/blk-mq-tag.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index cc57e2dd9a0bb..2cafcf11ee8be 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + unsigned long flags; struct blk_mq_tags *tags = hctx->tags;

/* @@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; }

- spin_lock_irq(&tags->lock); + spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); - spin_unlock_irq(&tags->lock); + spin_unlock_irqrestore(&tags->lock, flags); }

/*

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Ashish Mhetre amhetre@nvidia.com

[ Upstream commit 0d6c918011ce4764ed277de4726a468b7ffe5fed ]

There are few MC clients where SID security and override register offsets are not specified like "sw_cluster0" in tegra234. Don't program SID override for such clients because it leads to access to invalid addresses.

Signed-off-by: Ashish Mhetre amhetre@nvidia.com Link: https://lore.kernel.org/r/20231107112713.21399-2-amhetre@nvidia.com Signed-off-by: Krzysztof Kozlowski krzysztof.kozlowski@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/memory/tegra/tegra186.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/memory/tegra/tegra186.c b/drivers/memory/tegra/tegra186.c index 533f85a4b2bdb..7633481e547d2 100644 --- a/drivers/memory/tegra/tegra186.c +++ b/drivers/memory/tegra/tegra186.c @@ -75,6 +75,9 @@ static void tegra186_mc_client_sid_override(struct tegra_mc *mc, { u32 value, old;

+ if (client->regs.sid.security == 0 && client->regs.sid.override == 0) + return; + value = readl(mc->regs + client->regs.sid.security); if ((value & MC_SID_STREAMID_SECURITY_OVERRIDE) == 0) { /*

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Bard Liao yung-chuan.liao@linux.intel.com

[ Upstream commit 2bd512626f8ea3957c981cadd2ebf75feff737dd ]

snd_sof_ipc_msg_data could return error.

Signed-off-by: Bard Liao yung-chuan.liao@linux.intel.com Reviewed-by: Péter Ujfalusi peter.ujfalusi@linux.intel.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Peter Ujfalusi peter.ujfalusi@linux.intel.com Link: https://lore.kernel.org/r/20231129122021.679-1-peter.ujfalusi@linux.intel.co... Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- sound/soc/sof/ipc4.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sof/ipc4.c b/sound/soc/sof/ipc4.c index 1b09496733fb8..81d1ce4b5f0cd 100644 --- a/sound/soc/sof/ipc4.c +++ b/sound/soc/sof/ipc4.c @@ -629,7 +629,14 @@ static void sof_ipc4_rx_msg(struct snd_sof_dev *sdev) return;

ipc4_msg->data_size = data_size; - snd_sof_ipc_msg_data(sdev, NULL, ipc4_msg->data_ptr, ipc4_msg->data_size); + err = snd_sof_ipc_msg_data(sdev, NULL, ipc4_msg->data_ptr, ipc4_msg->data_size); + if (err < 0) { + dev_err(sdev->dev, "failed to read IPC notification data: %d\n", err); + kfree(ipc4_msg->data_ptr); + ipc4_msg->data_ptr = NULL; + ipc4_msg->data_size = 0; + return; + } }

sof_ipc4_log_header(sdev->dev, "ipc rx done ", ipc4_msg, true);

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Nathan Lynch nathanl@linux.ibm.com

[ Upstream commit 35aae182bd7b422be3cefc08c12207bf2b973364 ]

The ability to get and set system parameters will be exposed to user space, so let's get a little more strict about malformed papr_sysparm_buf objects.

* Create accessors for the length field of struct papr_sysparm_buf. The length is always stored in MSB order and this is better than spreading the necessary conversions all over.

* Reject attempts to submit invalid buffers to RTAS.

* Warn if RTAS returns a buffer with an invalid length, clamping the returned length to a safe value that won't overrun the buffer.

These are meant as precautionary measures to mitigate both firmware and kernel bugs in this area, should they arise, but I am not aware of any.

Signed-off-by: Nathan Lynch nathanl@linux.ibm.com Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://msgid.link/20231212-papr-sys_rtas-vs-lockdown-v6-10-e9eafd0c8c6c@lin... Signed-off-by: Sasha Levin sashal@kernel.org --- arch/powerpc/platforms/pseries/papr-sysparm.c | 47 +++++++++++++++++++ 1 file changed, 47 insertions(+)

diff --git a/arch/powerpc/platforms/pseries/papr-sysparm.c b/arch/powerpc/platforms/pseries/papr-sysparm.c index fedc61599e6cc..a1e7aeac74161 100644 --- a/arch/powerpc/platforms/pseries/papr-sysparm.c +++ b/arch/powerpc/platforms/pseries/papr-sysparm.c @@ -23,6 +23,46 @@ void papr_sysparm_buf_free(struct papr_sysparm_buf *buf) kfree(buf); }

+static size_t papr_sysparm_buf_get_length(const struct papr_sysparm_buf *buf) +{ + return be16_to_cpu(buf->len); +} + +static void papr_sysparm_buf_set_length(struct papr_sysparm_buf *buf, size_t length) +{ + WARN_ONCE(length > sizeof(buf->val), + "bogus length %zu, clamping to safe value", length); + length = min(sizeof(buf->val), length); + buf->len = cpu_to_be16(length); +} + +/* + * For use on buffers returned from ibm,get-system-parameter before + * returning them to callers. Ensures the encoded length of valid data + * cannot overrun buf->val[]. + */ +static void papr_sysparm_buf_clamp_length(struct papr_sysparm_buf *buf) +{ + papr_sysparm_buf_set_length(buf, papr_sysparm_buf_get_length(buf)); +} + +/* + * Perform some basic diligence on the system parameter buffer before + * submitting it to RTAS. + */ +static bool papr_sysparm_buf_can_submit(const struct papr_sysparm_buf *buf) +{ + /* + * Firmware ought to reject buffer lengths that exceed the + * maximum specified in PAPR, but there's no reason for the + * kernel to allow them either. + */ + if (papr_sysparm_buf_get_length(buf) > sizeof(buf->val)) + return false; + + return true; +} + /** * papr_sysparm_get() - Retrieve the value of a PAPR system parameter. * @param: PAPR system parameter token as described in @@ -63,6 +103,9 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf) if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT;

+ if (!papr_sysparm_buf_can_submit(buf)) + return -EINVAL; + work_area = rtas_work_area_alloc(sizeof(*buf));

memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf)); @@ -77,6 +120,7 @@ int papr_sysparm_get(papr_sysparm_t param, struct papr_sysparm_buf *buf) case 0: ret = 0; memcpy(buf, rtas_work_area_raw_buf(work_area), sizeof(*buf)); + papr_sysparm_buf_clamp_length(buf); break; case -3: /* parameter not implemented */ ret = -EOPNOTSUPP; @@ -115,6 +159,9 @@ int papr_sysparm_set(papr_sysparm_t param, const struct papr_sysparm_buf *buf) if (token == RTAS_UNKNOWN_SERVICE) return -ENOENT;

+ if (!papr_sysparm_buf_can_submit(buf)) + return -EINVAL; + work_area = rtas_work_area_alloc(sizeof(*buf));

memcpy(rtas_work_area_raw_buf(work_area), buf, sizeof(*buf));

6.6-stable review patch. If anyone has any objections, please let me know.

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

From: Shannon Nelson shannon.nelson@amd.com

[ Upstream commit 219e183272b4a566650a37264aff90a8c613d9b5 ]