6.6.48-rc1 review
Subsystems (9)
Greg Kroah-Hartman
maintainerPATCH 1/341 tty: serial: fsl_lpuart: mark last busy before uart_add_one_port
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Peng Fan <[email protected]>
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.
--- drivers/tty/serial/fsl_lpuart.c | 1 + 1 file changed, 1 insertion(+)
drivers/tty/serial/fsl_lpuart.c +1 -0
@@ -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)
Greg Kroah-Hartman
maintainerPATCH 10/341 char: xillybus: Check USB endpoints when probing device
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eli Billauer <[email protected]>
commit 2374bf7558de915edc6ec8cb10ec3291dfab9594 upstream.
Ensure, as the driver probes the device, that all endpoints that the driver may attempt to access exist and are of the correct type.
All XillyUSB devices must have a Bulk IN and Bulk OUT endpoint at address 1. This is verified in xillyusb_setup_base_eps().
On top of that, a XillyUSB device may have additional Bulk OUT endpoints. The information about these endpoints' addresses is deduced from a data structure (the IDT) that the driver fetches from the device while probing it. These endpoints are checked in setup_channels().
A XillyUSB device never has more than one IN endpoint, as all data towards the host is multiplexed in this single Bulk IN endpoint. This is why setup_channels() only checks OUT endpoints.
--- drivers/char/xillybus/xillyusb.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)
drivers/char/xillybus/xillyusb.c +20 -2
@@ -1903,6 +1903,13 @@ static const struct file_operations xillstatic int xillyusb_setup_base_eps (struct xillyusb_dev *xdev) { +struct usb_device *udev = xdev->udev; + +/* Verify that device has the two fundamental bulk in/out endpoints */ +if (usb_pipe_type_check (udev,usb_sndbulkpipe (udev,MSG_EP_NUM )) || +usb_pipe_type_check (udev,usb_rcvbulkpipe (udev,IN_EP_NUM ))) +return -ENODEV ; + xdev->msg_ep =endpoint_alloc (xdev,MSG_EP_NUM |USB_DIR_OUT , bulk_out_work,1 ,2 );if (!xdev->msg_ep)
@@ -1932,14 +1939,15 @@ static int setup_channels(struct xillyus __le16 *chandesc, int num_channels) { -struct xillyusb_channel *chan; +struct usb_device *udev = xdev->udev; +struct xillyusb_channel *chan, *new_channels;int i; chan =kcalloc (num_channels,sizeof (*chan),GFP_KERNEL );if (!chan)return -ENOMEM ; - xdev->channels = chan; + new_channels = chan;for (i =0 ; i < num_channels; i++, chan++) {unsigned int in_desc =le16_to_cpu (*chandesc++);
@@ -1968,6 +1976,15 @@ static int setup_channels(struct xillyus*/ if ((out_desc &0x80 ) && i <14 ) {/* Entry is valid */ +if (usb_pipe_type_check (udev, +usb_sndbulkpipe (udev, i +2 ))) { +dev_err (xdev->dev, +"Missing BULK OUT endpoint %d\n" , + i +2 ); +kfree (new_channels); +return -ENODEV ; + } + chan->writable =1 ; chan->out_synchronous = !!(out_desc &0x40 ); chan->out_seekable = !!(out_desc &0x20 );
@@ -1977,6 +1994,7 @@ static int setup_channels(struct xillyus } } + xdev->channels = new_channels;return 0 ; }
Greg Kroah-Hartman
maintainerPATCH 11/341 ALSA: usb-audio: Add delay quirk for VIVO USB-C-XE710 HEADSET
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lianqin Hu <[email protected]>
commit 004eb8ba776ccd3e296ea6f78f7ae7985b12824e upstream.
Audio control requests that sets sampling frequency sometimes fail on this card. Adding delay between control messages eliminates that problem.
--- sound/usb/quirks.c | 2 ++ 1 file changed, 2 insertions(+)
sound/usb/quirks.c +2 -0
@@ -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 */
Greg Kroah-Hartman
maintainerPATCH 12/341 ALSA: usb-audio: Support Yamaha P-125 quirk entry
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Juan José Arboleda <[email protected]>
commit c286f204ce6ba7b48e3dcba53eda7df8eaa64dd9 upstream.
This patch adds a USB quirk for the Yamaha P-125 digital piano.
--- sound/usb/quirks-table.h | 1 + 1 file changed, 1 insertion(+)
sound/usb/quirks-table.h +1 -0
@@ -273,6 +273,7 @@ YAMAHA_DEVICE(0x105a, NULL), YAMAHA_DEVICE(0x105b, NULL), YAMAHA_DEVICE(0x105c, NULL), YAMAHA_DEVICE(0x105d, NULL), +YAMAHA_DEVICE(0x1718, "P-125"), { USB_DEVICE(0x0499, 0x1503), .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
Greg Kroah-Hartman
maintainerPATCH 13/341 xhci: Fix Panther point NULL pointer deref at full-speed re-enumeration
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mathias Nyman <[email protected]>
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.
--- drivers/usb/host/xhci.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/usb/host/xhci.c +5 -3
@@ -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 ;
Greg Kroah-Hartman
maintainerPATCH 2/341 tty: atmel_serial: use the correct RTS flag.
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mathieu Othacehe <[email protected]>
commit c9f6613b16123989f2c3bd04b1d9b2365d6914e7 upstream.
In RS485 mode, the RTS pin is driven high by hardware when the transmitter is operating. This behaviour cannot be changed. This means that the driver should claim that it supports SER_RS485_RTS_ON_SEND and not SER_RS485_RTS_AFTER_SEND.
Otherwise, when configuring the port with the SER_RS485_RTS_ON_SEND, one get the following warning:
kern.warning kernel: atmel_usart_serial atmel_usart_serial.2.auto:
ttyS1 (1): invalid RTS setting, using RTS_AFTER_SEND instead
which is contradictory with what's really happening.
--- drivers/tty/serial/atmel_serial.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/tty/serial/atmel_serial.c +1 -1
@@ -2522,7 +2522,7 @@ static const struct uart_ops atmel_pops };static const struct serial_rs485 atmel_rs485_supported = { - .flags =SER_RS485_ENABLED |SER_RS485_RTS_AFTER_SEND |SER_RS485_RX_DURING_TX , + .flags =SER_RS485_ENABLED |SER_RS485_RTS_ON_SEND |SER_RS485_RX_DURING_TX , .delay_rts_before_send =1 , .delay_rts_after_send =1 , };
Greg Kroah-Hartman
maintainerPATCH 3/341 Revert "ACPI: EC: Evaluate orphan _REG under EC device"
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
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.
--- 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(-)
drivers/acpi/acpica/acevents.h +0 -4
@@ -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);
drivers/acpi/acpica/evregion.c +5 -1
@@ -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) {
drivers/acpi/acpica/evxfregn.c +0 -54
57 lines not on this page · raw message
drivers/acpi/ec.c +0 -3
@@ -1507,9 +1507,6 @@ static int ec_install_handlers(struct acif (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); }
include/acpi/acpixf.h +0 -4
@@ -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
Greg Kroah-Hartman
maintainerPATCH 4/341 Revert "misc: fastrpc: Restrict untrusted app to attach to privileged PD"
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Griffin Kroah-Hartman <[email protected]>
commit 9bb5e74b2bf88fbb024bb15ded3b011e02c673be upstream.
This reverts commit bab2f5e8fd5d2f759db26b78d9db57412888f187.
Joel reported that this commit breaks userspace and stops sensors in SDM845 from working. Also breaks other qcom SoC devices running postmarketOS.
--- drivers/misc/fastrpc.c | 22 +++------------------- include/uapi/misc/fastrpc.h | 3 --- 2 files changed, 3 insertions(+), 22 deletions(-)
drivers/misc/fastrpc.c +3 -19
@@ -2087,16 +2087,6 @@ err_invoke:return err; } -static int is_attach_rejected (struct fastrpc_user *fl) -{ -/* Check if the device node is non-secure */ -if (!fl->is_secure_dev) { -dev_dbg (&fl->cctx->rpdev->dev,"untrusted app trying to attach to privileged DSP PD\n" ); -return -EACCES ; - } -return 0 ; -} -static long fastrpc_device_ioctl (struct file *file,unsigned int cmd,unsigned long arg) {
@@ -2109,19 +2099,13 @@ static long fastrpc_device_ioctl(struct err =fastrpc_invoke (fl, argp);break ;case FASTRPC_IOCTL_INIT_ATTACH : - err =is_attach_rejected (fl); -if (!err) - err =fastrpc_init_attach (fl,ROOT_PD ); + err =fastrpc_init_attach (fl,ROOT_PD );break ;case FASTRPC_IOCTL_INIT_ATTACH_SNS : - err =is_attach_rejected (fl); -if (!err) - err =fastrpc_init_attach (fl,SENSORS_PD ); + err =fastrpc_init_attach (fl,SENSORS_PD );break ;case FASTRPC_IOCTL_INIT_CREATE_STATIC : - err =is_attach_rejected (fl); -if (!err) - err =fastrpc_init_create_static_process (fl, argp); + err =fastrpc_init_create_static_process (fl, argp);break ;case FASTRPC_IOCTL_INIT_CREATE : err =fastrpc_init_create_process (fl, argp);
include/uapi/misc/fastrpc.h +0 -3
@@ -8,14 +8,11 @@#define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf)#define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32)#define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4)#define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create)#define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap)#define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8) -/* This ioctl is only supported with secure device nodes */ #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)#define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map)#define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap)
Greg Kroah-Hartman
maintainerPATCH 5/341 Revert "usb: typec: tcpm: clear pd_event queue in PORT_RESET"
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Xu Yang <[email protected]>
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]
--- drivers/usb/typec/tcpm/tcpm.c | 1 - 1 file changed, 1 deletion(-)
drivers/usb/typec/tcpm/tcpm.c +0 -1
@@ -4880,7 +4880,6 @@ static void run_state_machine(struct tcpbreak ;case PORT_RESET :tcpm_reset_port (port); - port->pd_events =0 ;if (port->self_powered)tcpm_set_cc (port,TYPEC_CC_OPEN );else
Greg Kroah-Hartman
maintainerPATCH 6/341 selinux: revert our use of vma_is_initial_heap()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Paul Moore <[email protected]>
commit 05a3d6e9307250a5911d75308e4363466794ab21 upstream.
Unfortunately it appears that vma_is_initial_heap() is currently broken for applications that do not currently have any heap allocated, e.g. brk == start_brk. The breakage is such that it will cause SELinux to check for the process/execheap permission on memory regions that cross brk/start_brk even when there is no heap.
The proper fix would be to correct vma_is_initial_heap(), but as there are multiple callers I am hesitant to unilaterally modify the helper out of concern that I would end up breaking some other subsystem. The mm developers have been made aware of the situation and hopefully they will have a fix at some point in the future, but we need a fix soon so we are simply going to revert our use of vma_is_initial_heap() in favor of our old logic/code which works as expected, even in the face of a zero size heap. We can return to using vma_is_initial_heap() at some point in the future when it is fixed.
--- security/selinux/hooks.c | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-)
security/selinux/hooks.c +11 -1
@@ -3835,7 +3835,17 @@ static int selinux_file_mprotect(structif (default_noexec && (prot &PROT_EXEC ) && !(vma->vm_flags &VM_EXEC )) {int rc =0 ; -if (vma_is_initial_heap (vma)) { +/* +* We don't use the vma_is_initial_heap() helper as it has +* a history of problems and is currently broken on systems +* where there is no heap, e.g. brk == start_brk. Before +* replacing the conditional below with vma_is_initial_heap(), +* or something similar, please ensure that the logic is the +* same as what we have below or you have tested every possible +* corner case you can think to test. +*/ +if (vma->vm_start >= vma->vm_mm->start_brk && + vma->vm_end <= vma->vm_mm->brk) { rc =avc_has_perm (sid, sid,SECCLASS_PROCESS ,PROCESS__EXECHEAP ,NULL ); } else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
Greg Kroah-Hartman
maintainerPATCH 7/341 fuse: Initialize beyond-EOF page contents before setting uptodate
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jann Horn <[email protected]>
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).
--- fs/fuse/dev.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
fs/fuse/dev.c +4 -2
@@ -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);
Greg Kroah-Hartman
maintainerPATCH 8/341 char: xillybus: Dont destroy workqueue from work item running on it
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eli Billauer <[email protected]>
commit ccbde4b128ef9c73d14d0d7817d68ef795f6d131 upstream.
Triggered by a kref decrement, destroy_workqueue() may be called from within a work item for destroying its own workqueue. This illegal situation is averted by adding a module-global workqueue for exclusive use of the offending work item. Other work items continue to be queued on per-device workqueues to ensure performance.
--- drivers/char/xillybus/xillyusb.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-)
drivers/char/xillybus/xillyusb.c +11 -5
@@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2");static const char xillyname[] ="xillyusb" ;static unsigned int fifo_buf_order; +static struct workqueue_struct *wakeup_wq;#define USB_VENDOR_ID_XILINX 0x03fd#define USB_VENDOR_ID_ALTERA 0x09fb
@@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kre* errors if executed. The mechanism relies on that xdev->error is assigned * a non-zero value by report_io_error() prior to queueing wakeup_all(), * which prevents bulk_in_work() from calling process_bulk_in(). -* -* The fact that wakeup_all() and bulk_in_work() are queued on the same -* workqueue makes their concurrent execution very unlikely, however the -* kernel's API doesn't seem to ensure this strictly. */ static void wakeup_all (struct work_struct *work)
@@ -627,7 +624,7 @@ static void report_io_error(struct xillyif (do_once) {kref_get (&xdev->kref);/* xdev is used by work item */ -queue_work (xdev->workq, &xdev->wakeup_workitem); +queue_work (wakeup_wq, &xdev->wakeup_workitem); } }
@@ -2258,6 +2255,10 @@ static int __init xillyusb_init(void) {int rc =0 ; + wakeup_wq =alloc_workqueue (xillyname,0 ,0 ); +if (!wakeup_wq) +return -ENOMEM ; +if (LOG2_INITIAL_FIFO_BUF_SIZE >PAGE_SHIFT ) fifo_buf_order =LOG2_INITIAL_FIFO_BUF_SIZE -PAGE_SHIFT ;else
@@ -2265,11 +2266,16 @@ static int __init xillyusb_init(void) rc =usb_register (&xillyusb_driver); +if (rc) +destroy_workqueue (wakeup_wq); +return rc; } static void __exit xillyusb_exit(void) { +destroy_workqueue (wakeup_wq); +usb_deregister (&xillyusb_driver); }
Greg Kroah-Hartman
maintainerPATCH 9/341 char: xillybus: Refine workqueue handling
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eli Billauer <[email protected]>
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.
--- drivers/char/xillybus/xillyusb.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
drivers/char/xillybus/xillyusb.c +5 -3
@@ -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);
Greg Kroah-Hartman
maintainercover 6.6.48-rc1 review
This is the start of the stable review cycle for the 6.6.48 release. There are 341 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Thu, 29 Aug 2024 14:37:36 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at:
https://www.kernel.org/pub/linux/kernel/v6.x/stable-review/patch-6.6.48-rc1.gz
or in the git tree and branch at:
git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-6.6.y
and the diffstat can be found below.
thanks,
greg k-h
-------------
Pseudo-Shortlog of commits:
Greg Kroah-Hartman <[email protected]>
Linux 6.6.48-rc1
Tetsuo Handa <[email protected]>
Input: MT - limit max slots
Jan Höppner <[email protected]>
Revert "s390/dasd: Establish DMA alignment"
Mengyuan Lou <[email protected]>
net: ngbe: Fix phy mode set to external phy
Namjae Jeon <[email protected]>
ksmbd: fix race condition between destroy_previous_session() and smb2 operations()
Boyuan Zhang <[email protected]>
drm/amdgpu/vcn: not pause dpg for unified queue
Boyuan Zhang <[email protected]>
drm/amdgpu/vcn: identify unified queue in sw init
NeilBrown <[email protected]>
NFSD: simplify error paths in nfsd_svc()
Yonghong Song <[email protected]>
selftests/bpf: Add a test to verify previous stacksafe() fix
Yonghong Song <[email protected]>
bpf: Fix a kernel verifier crash in stacksafe()
Zi Yan <[email protected]>
mm/numa: no task_numa_fault() call if PTE is changed
Zi Yan <[email protected]>
mm/numa: no task_numa_fault() call if PMD is changed
Takashi Iwai <[email protected]>
ALSA: timer: Relax start tick time check for slave timer elements
Faizal Rahim <[email protected]>
igc: Fix qbv tx latency by setting gtxoffset
Jianhua Lu <[email protected]>
drm/panel: nt36523: Set 120Hz fps for xiaomi,elish panels
Dmitry Baryshkov <[email protected]>
drm/msm/mdss: specify cfg bandwidth for SDM670
Javier Carrasco <[email protected]>
hwmon: (ltc2992) Fix memory leak in ltc2992_parse_dt()
Eric Dumazet <[email protected]>
tcp: do not export tcp_twsk_purge()
Jithu Joseph <[email protected]>
platform/x86/intel/ifs: Call release_firmware() when handling errors.
Alex Hung <[email protected]>
Revert "drm/amd/display: Validate hw_points_num before using it"
Greg Kroah-Hartman <[email protected]>
Revert "usb: gadget: uvc: cleanup request when not in correct state"
Matthieu Baerts (NGI0) <[email protected]>
selftests: mptcp: join: check re-using ID of closed subflow
Matthieu Baerts (NGI0) <[email protected]>
selftests: mptcp: join: validate fullmesh endp on 1st sf
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: avoid possible UaF when selecting endp
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: fullmesh: select the right ID later
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: only in-kernel cannot have entries with ID 0
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: check add_addr_accept_max before accepting new ADD_ADDR
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: only decrement add_addr_accepted for MPJ req
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: only mark 'subflow' endp as available
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: remove mptcp_pm_remove_subflow()
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: re-using ID of unused flushed subflows
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: re-using ID of unused removed subflows
Matthieu Baerts (NGI0) <[email protected]>
mptcp: pm: re-using ID of unused removed ADD_ADDR
Dave Airlie <[email protected]>
nouveau/firmware: use dma non-coherent allocator
Peng Fan <[email protected]>
pmdomain: imx: wait SSAR when i.MX93 power domain on
Alexander Stein <[email protected]>
pmdomain: imx: scu-pd: Remove duplicated clocks
Ben Whitten <[email protected]>
mmc: dw_mmc: allow biu and ciu clocks to defer
Mengqi Zhang <[email protected]>
mmc: mtk-sd: receive cmd8 data when hs400 tuning fail
Marc Zyngier <[email protected]>
KVM: arm64: Make ICC_*SGI*_EL1 undef in the absence of a vGICv3
Nikolay Kuratov <[email protected]>
cxgb4: add forgotten u64 ivlan cast before shift
Werner Sembach <[email protected]>
Input: i8042 - use new forcenorestore quirk to replace old buggy quirk combination
Werner Sembach <[email protected]>
Input: i8042 - add forcenorestore quirk to leave controller untouched even on s3
Jason Gerecke <[email protected]>
HID: wacom: Defer calculation of resolution until resolution_code is known
Jiaxun Yang <[email protected]>
MIPS: Loongson64: Set timer mode in cpu-probe
Martin Whitaker <[email protected]>
net: dsa: microchip: fix PTP config failure when using multiple ports
Candice Li <[email protected]>
drm/amdgpu: Validate TA binary size
Namjae Jeon <[email protected]>
ksmbd: the buffer of smb2 query dir response has at least 1 byte
Chaotian Jing <[email protected]>
scsi: core: Fix the return value of scsi_logical_block_count()
Griffin Kroah-Hartman <[email protected]>
Bluetooth: MGMT: Add error handling to pair_device()
Paulo Alcantara <[email protected]>
smb: client: ignore unhandled reparse tags
Dan Carpenter <[email protected]>
mmc: mmc_test: Fix NULL dereference on allocation failure
Abhinav Kumar <[email protected]>
drm/msm: fix the highest_bank_bit for sc7180
Dmitry Baryshkov <[email protected]>
drm/msm/mdss: Handle the reg bus ICC path
Konrad Dybcio <[email protected]>
drm/msm/mdss: Rename path references to mdp_path
Dmitry Baryshkov <[email protected]>
drm/msm/mdss: switch mdss to use devm_of_icc_get()
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: take plane rotation into account for wide planes
Abhinav Kumar <[email protected]>
drm/msm/dpu: try multirect based on mdp clock limits
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: cleanup FB if dpu_format_populate_layout fails
Abhinav Kumar <[email protected]>
drm/msm/dp: reset the link phy params before link training
Abhinav Kumar <[email protected]>
drm/msm/dpu: move dpu_encoder's connector assignment to atomic_enable()
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: capture snapshot on the first commit_done timeout
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: split dpu_encoder_wait_for_event into two functions
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: drop MSM_ENC_VBLANK support
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: use drmm-managed allocation for dpu_encoder_phys
Abhinav Kumar <[email protected]>
drm/msm/dp: fix the max supported bpp logic
Dmitry Baryshkov <[email protected]>
drm/msm/dpu: don't play tricks with debug macros
Menglong Dong <[email protected]>
net: ovs: fix ovs_drop_reasons error
Sean Anderson <[email protected]>
net: xilinx: axienet: Fix dangling multicast addresses
Sean Anderson <[email protected]>
net: xilinx: axienet: Always disable promiscuous mode
Bharat Bhushan <[email protected]>
octeontx2-af: Fix CPT AF register offset calculation
Pablo Neira Ayuso <[email protected]>
netfilter: flowtable: validate vlan header
Somnath Kotur <[email protected]>
bnxt_en: Fix double DMA unmapping for XDP_REDIRECT
Eric Dumazet <[email protected]>
ipv6: prevent possible UAF in ip6_xmit()
Eric Dumazet <[email protected]>
ipv6: fix possible UAF in ip6_finish_output2()
Eric Dumazet <[email protected]>
ipv6: prevent UAF in ip6_send_skb()
Felix Fietkau <[email protected]>
udp: fix receiving fraglist GSO packets
Stephen Hemminger <[email protected]>
netem: fix return value if duplicate enqueue fails
Joseph Huang <[email protected]>
net: dsa: mv88e6xxx: Fix out-of-bound access
Paolo Abeni <[email protected]>
igb: cope with large MAX_SKB_FRAGS
Dan Carpenter <[email protected]>
dpaa2-switch: Fix error checking in dpaa2_switch_seed_bp()
Maciej Fijalkowski <[email protected]>
ice: fix truesize operations for PAGE_SIZE >= 8192
Maciej Fijalkowski <[email protected]>
ice: fix ICE_LAST_OFFSET formula
Maciej Fijalkowski <[email protected]>
ice: fix page reuse when PAGE_SIZE is over 8k
Nikolay Aleksandrov <[email protected]>
bonding: fix xfrm state handling when clearing active slave
Nikolay Aleksandrov <[email protected]>
bonding: fix xfrm real_dev null pointer dereference
Nikolay Aleksandrov <[email protected]>
bonding: fix null pointer deref in bond_ipsec_offload_ok
Nikolay Aleksandrov <[email protected]>
bonding: fix bond_ipsec_offload_ok return type
Thomas Bogendoerfer <[email protected]>
ip6_tunnel: Fix broken GRO
Sebastian Andrzej Siewior <[email protected]>
netfilter: nft_counter: Synchronize nft_counter_reset() against reader.
Sebastian Andrzej Siewior <[email protected]>
netfilter: nft_counter: Disable BH in nft_counter_offload_stats().
Kuniyuki Iwashima <[email protected]>
kcm: Serialise kcm_sendmsg() for the same socket.
Jeremy Kerr <[email protected]>
net: mctp: test: Use correct skb for route input check
Florian Westphal <[email protected]>
tcp: prevent concurrent execution of tcp_sk_exit_batch
Eric Dumazet <[email protected]>
tcp/dccp: do not care about families in inet_twsk_purge()
Eric Dumazet <[email protected]>
tcp/dccp: bypass empty buckets in inet_twsk_purge()
Hangbin Liu <[email protected]>
selftests: udpgro: report error when receive failed
Simon Horman <[email protected]>
tc-testing: don't access non-existent variable on exception
Vladimir Oltean <[email protected]>
net: mscc: ocelot: serialize access to the injection/extraction groups
Vladimir Oltean <[email protected]>
net: mscc: ocelot: fix QoS class for injected packets with "ocelot-8021q"
Vladimir Oltean <[email protected]>
net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and register injection
Luiz Augusto von Dentz <[email protected]>
Bluetooth: SMP: Fix assumption of Central always being Initiator
Luiz Augusto von Dentz <[email protected]>
Bluetooth: hci_core: Fix LE quote calculation
Lang Yu <[email protected]>
drm/amdkfd: reserve the BO before validating it
Takashi Iwai <[email protected]>
ALSA: hda/tas2781: Use correct endian conversion
Maximilian Luz <[email protected]>
platform/surface: aggregator: Fix warning when controller is destroyed in probe
David (Ming Qiang) Wu <[email protected]>
drm/amd/amdgpu: command submission parser for JPEG
Melissa Wen <[email protected]>
drm/amd/display: fix cursor offset on rotation 180
Loan Chen <[email protected]>
drm/amd/display: Enable otg synchronization logic for DCN321
Rodrigo Siqueira <[email protected]>
drm/amd/display: Adjust cursor position
Filipe Manana <[email protected]>
btrfs: send: allow cloning non-aligned extent if it ends at i_size
David Sterba <[email protected]>
btrfs: replace sb::s_blocksize by fs_info::sectorsize
Hailong Liu <[email protected]>
mm/vmalloc: fix page mapping if vm_area_alloc_pages() with high order fallback to order 0
Suren Baghdasaryan <[email protected]>
change alloc_pages name in dma_map_ops to avoid name conflicts
Muhammad Usama Anjum <[email protected]>
selftests: memfd_secret: don't build memfd_secret test on unsupported arches
Ryan Roberts <[email protected]>
selftests/mm: log run_vmtests.sh results in TAP format
Itaru Kitayama <[email protected]>
tools/testing/selftests/mm/run_vmtests.sh: lower the ptrace permissions
Kirill A. Shutemov <[email protected]>
mm: fix endless reclaim on machines with unaccepted memory
Mikulas Patocka <[email protected]>
dm suspend: return -ERESTARTSYS instead of -EINTR
Celeste Liu <[email protected]>
riscv: entry: always initialize regs->a0 to -ENOSYS
Sean Nyekjaer <[email protected]>
i2c: stm32f7: Add atomic_xfer method to driver
Dave Kleikamp <[email protected]>
jfs: define xtree root and page independently
Eric Dumazet <[email protected]>
gtp: pull network headers in gtp_dev_xmit()
Keith Busch <[email protected]>
nvme: fix namespace removal list
Qiuxu Zhuo <[email protected]>
EDAC/skx_common: Allow decoding of SGX addresses
Shannon Nelson <[email protected]>
ionic: check cmd_regs before copying in or out
Shannon Nelson <[email protected]>
ionic: use pci_is_enabled not open code
Phil Chang <[email protected]>
hrtimer: Prevent queuing of hrtimer without a function callback
Jesse Zhang <[email protected]>
drm/amdgpu: fix dereference null return value for the function amdgpu_vm_pt_parent
Keith Busch <[email protected]>
nvme: use srcu for iterating namespace list
Jakub Sitnicki <[email protected]>
Revert "bpf, sockmap: Prevent lock inversion deadlock in map delete elem"
Cupertino Miranda <[email protected]>
selftests/bpf: Fix a few tests for GCC related warnings.
Sagi Grimberg <[email protected]>
nvmet-rdma: fix possible bad dereference when freeing rsps
Baokun Li <[email protected]>
ext4: set the type of max_zeroout to unsigned int to avoid overflow
Guanrui Huang <[email protected]>
irqchip/gic-v3-its: Remove BUG_ON in its_vpe_irq_domain_alloc
Krishna Kurapati <[email protected]>
usb: dwc3: core: Skip setting event buffers for host only controllers
Gergo Koteles <[email protected]>
platform/x86: lg-laptop: fix %s null argument warning
Adrian Hunter <[email protected]>
clocksource: Make watchdog and suspend-timing multiplication overflow safe
Biju Das <[email protected]>
irqchip/renesas-rzg2l: Do not set TIEN and TINT source at the same time
Alexander Gordeev <[email protected]>
s390/iucv: fix receive buffer virtual vs physical address confusion
Oreoluwa Babatunde <[email protected]>
openrisc: Call setup_memory() earlier in the init sequence
NeilBrown <[email protected]>
NFS: avoid infinite loop in pnfs_update_layout.
Hannes Reinecke <[email protected]>
nvmet-tcp: do not continue for invalid icreq
Jian Shen <[email protected]>
net: hns3: add checking for vf id of mailbox
Alexandre Belloni <[email protected]>
rtc: nct3018y: fix possible NULL dereference
Richard Fitzgerald <[email protected]>
firmware: cirrus: cs_dsp: Initialize debugfs_root to invalid
Luiz Augusto von Dentz <[email protected]>
Bluetooth: bnep: Fix out-of-bound access
Keith Busch <[email protected]>
nvme: clear caller pointer on identify failure
Uwe Kleine-König <[email protected]>
usb: gadget: fsl: Increase size of name buffer for endpoints
Zhiguo Niu <[email protected]>
f2fs: fix to do sanity check in update_sit_entry
David Sterba <[email protected]>
btrfs: delete pointless BUG_ON check on quota root in btrfs_qgroup_account_extent()
David Sterba <[email protected]>
btrfs: change BUG_ON to assertion in tree_move_down()
David Sterba <[email protected]>
btrfs: send: handle unexpected inode in header process_recorded_refs()
David Sterba <[email protected]>
btrfs: send: handle unexpected data in header buffer in begin_cmd()
David Sterba <[email protected]>
btrfs: handle invalid root reference found in may_destroy_subvol()
David Sterba <[email protected]>
btrfs: push errors up from add_async_extent()
David Sterba <[email protected]>
btrfs: tests: allocate dummy fs_info and root in test_find_delalloc()
David Sterba <[email protected]>
btrfs: change BUG_ON to assertion when checking for delayed_node root
David Sterba <[email protected]>
btrfs: defrag: change BUG_ON to assertion in btrfs_defrag_leaves()
David Sterba <[email protected]>
btrfs: delayed-inode: drop pointless BUG_ON in __btrfs_remove_delayed_item()
Michael Ellerman <[email protected]>
powerpc/boot: Only free if realloc() succeeds
Li zeming <[email protected]>
powerpc/boot: Handle allocation failure in simple_realloc()
Zhiguo Niu <[email protected]>
f2fs: stop checkpoint when get a out-of-bounds segment
David Howells <[email protected]>
rxrpc: Don't pick values out of the wire header when setting up security
Helge Deller <[email protected]>
parisc: Use irq_enter_rcu() to fix warning at kernel/context_tracking.c:367
Christophe Kerello <[email protected]>
memory: stm32-fmc2-ebi: check regmap_read return value
Kees Cook <[email protected]>
x86: Increase brk randomness entropy for 64-bit systems
Li Nan <[email protected]>
md: clean up invalid BUG_ON in md_ioctl
Eric Dumazet <[email protected]>
netlink: hold nlk->cb_mutex longer in __netlink_dump_start()
Frederic Weisbecker <[email protected]>
tick: Move got_idle_tick away from common flags
Martin Blumenstingl <[email protected]>
clocksource/drivers/arm_global_timer: Guard against division by zero
Avri Kehat <[email protected]>
accel/habanalabs: fix debugfs files permissions
Stefan Hajnoczi <[email protected]>
virtiofs: forbid newlines in tags
Costa Shulyupin <[email protected]>
hrtimer: Select housekeeping CPU during migration
Bartosz Golaszewski <[email protected]>
gpio: sysfs: extend the critical section for unregistering sysfs devices
Erico Nunes <[email protected]>
drm/lima: set gp bus_stop bit before hard reset
Kees Cook <[email protected]>
net/sun3_82586: Avoid reading past buffer in debug output
Shaul Triebitz <[email protected]>
wifi: iwlwifi: mvm: avoid garbage iPN
Philipp Stanner <[email protected]>
media: drivers/media/dvb-core: copy user arrays safely
Justin Tee <[email protected]>
scsi: lpfc: Initialize status local variable in lpfc_sli4_repost_sgl_list()
Max Filippov <[email protected]>
fs: binfmt_elf_efpic: don't use missing interpreter's properties
Hans Verkuil <[email protected]>
media: pci: cx23885: check cx23885_vdev_init() return
Neel Natu <[email protected]>
kernfs: fix false-positive WARN(nr_mmapped) in kernfs_drain_open_files
Clément Léger <[email protected]>
riscv: blacklist assembly symbols for kprobe
Jan Kara <[email protected]>
quota: Remove BUG_ON from dqget()
Jeff Johnson <[email protected]>
wifi: ath12k: Add missing qmi_txn_cancel() calls
Al Viro <[email protected]>
fuse: fix UAF in rcu pathwalks
Al Viro <[email protected]>
afs: fix __afs_break_callback() / afs_drop_open_mmap() race
Qu Wenruo <[email protected]>
btrfs: zlib: fix and simplify the inline extent decompression
Baokun Li <[email protected]>
ext4: do not trim the group with corrupted block bitmap
Daniel Wagner <[email protected]>
nvmet-trace: avoid dereferencing pointer too early
Qiuxu Zhuo <[email protected]>
EDAC/skx_common: Filter out the invalid address
Andreas Gruenbacher <[email protected]>
gfs2: Refcounting fix in gfs2_thaw_super
Zijun Hu <[email protected]>
Bluetooth: hci_conn: Check non NULL function before calling for HFP offload
Mimi Zohar <[email protected]>
evm: don't copy up 'security.evm' xattr
Andy Yan <[email protected]>
drm/rockchip: vop2: clear afbc en and transform bit for cluster window at linear mode
Shannon Nelson <[email protected]>
ionic: no fw read when PCI reset failed
Shannon Nelson <[email protected]>
ionic: prevent pci disable of already disabled device
Nathan Lynch <[email protected]>
powerpc/pseries/papr-sysparm: Validate buffer object lengths
Kees Cook <[email protected]>
hwmon: (pc87360) Bounds check data->innr usage
Bard Liao <[email protected]>
ASoC: SOF: ipc4: check return value of snd_sof_ipc_msg_data
Kunwu Chan <[email protected]>
powerpc/xics: Check return value of kasprintf in icp_native_map_one_cpu
Ashish Mhetre <[email protected]>
memory: tegra: Skip SID programming if SID registers aren't set
Rob Clark <[email protected]>
drm/msm: Reduce fallout of fence signaling vs reclaim hangs
Li Lingfeng <[email protected]>
block: Fix lockdep warning in blk_mq_mark_tag_wait
Samuel Holland <[email protected]>
arm64: Fix KASAN random tag seed initialization
Nysal Jan K.A <[email protected]>
powerpc/topology: Check if a core is online
Nysal Jan K.A <[email protected]>
cpu/SMT: Enable SMT only if a core is online
Masahiro Yamada <[email protected]>
rust: fix the default format for CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT
Masahiro Yamada <[email protected]>
rust: suppress error messages from CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT
Miguel Ojeda <[email protected]>
rust: work around bindgen 0.69.0 issue
Antoniu Miclaus <[email protected]>
hwmon: (ltc2992) Avoid division by zero
Chengfeng Ye <[email protected]>
IB/hfi1: Fix potential deadlock on &irq_src_lock and &dd->uctxt_lock
Gustavo A. R. Silva <[email protected]>
clk: visconti: Add bounds-checking coverage for struct visconti_pll_provider
Dmitry Antipov <[email protected]>
wifi: iwlwifi: check for kmemdup() return value in iwl_parse_tlv_firmware()
Mukesh Sisodiya <[email protected]>
wifi: iwlwifi: fw: Fix debugfs command sending
Miri Korenblit <[email protected]>
wifi: iwlwifi: abort scan when rfkill on but device enabled
Andreas Gruenbacher <[email protected]>
gfs2: setattr_chown: Add missing initialization
Johannes Berg <[email protected]>
wifi: mac80211: flush STA queues on unauthorization
Mike Christie <[email protected]>
scsi: spi: Fix sshdr use
Peter Ujfalusi <[email protected]>
ASoC: SOF: Intel: hda-dsp: Make sure that no irq handler is pending before suspend
Richard Acayan <[email protected]>
iommu/arm-smmu-qcom: Add SDM670 MDSS compatible
Hans Verkuil <[email protected]>
media: qcom: venus: fix incorrect return value
Mikko Perttunen <[email protected]>
drm/tegra: Zero-initialize iosys_map
Christian Brauner <[email protected]>
binfmt_misc: cleanup on filesystem umount
Yu Kuai <[email protected]>
md/raid5-cache: use READ_ONCE/WRITE_ONCE for 'conf->log'
farah kassabri <[email protected]>
accel/habanalabs: fix bug in timestamp interrupt handling
Tomer Tayar <[email protected]>
accel/habanalabs: export dma-buf only if size/offset multiples of PAGE_SIZE
Ofir Bitton <[email protected]>
accel/habanalabs/gaudi2: unsecure tpc count registers
Chengfeng Ye <[email protected]>
media: s5p-mfc: Fix potential deadlock on condlock
Jithu Joseph <[email protected]>
platform/x86/intel/ifs: Validate image size
Chengfeng Ye <[email protected]>
staging: ks7010: disable bh on tx_dev_lock
Alex Hung <[email protected]>
drm/amd/display: Validate hw_points_num before using it
Michael Grzeschik <[email protected]>
usb: gadget: uvc: cleanup request when not in correct state
Felix Fietkau <[email protected]>
wifi: mt76: fix race condition related to checking tx queue fill status
David Lechner <[email protected]>
staging: iio: resolver: ad2s1210: fix use before initialization
Dmitry Antipov <[email protected]>
wifi: ath11k: fix ath11k_mac_op_remain_on_channel() stack usage
Hans Verkuil <[email protected]>
media: radio-isa: use dev_name to fill in bus_info
Philip Yang <[email protected]>
drm/amdkfd: Move dma unmapping after TLB flush
Jarkko Nikula <[email protected]>
i3c: mipi-i3c-hci: Do not unmap region not mapped for transfer
Jarkko Nikula <[email protected]>
i3c: mipi-i3c-hci: Remove BUG() when Ring Abort request times out
Manish Dharanenthiran <[email protected]>
wifi: ath12k: fix WARN_ON during ath12k_mac_update_vif_chan
Tomi Valkeinen <[email protected]>
drm/bridge: tc358768: Attempt to fix DSI horizontal timings
Heiko Carstens <[email protected]>
s390/smp,mcck: fix early IPI handling
Zhu Yanjun <[email protected]>
RDMA/rtrs: Fix the problem of variable not initialized fully
Wolfram Sang <[email protected]>
i2c: riic: avoid potential division by zero
Kamalesh Babulal <[email protected]>
cgroup: Avoid extra dereference in css_populate_dir()
Jeff Johnson <[email protected]>
wifi: cw1200: Avoid processing an invalid TIM IE
Yury Norov <[email protected]>
sched/topology: Handle NUMA_NO_NODE in sched_numa_find_nth_cpu()
Lorenzo Bianconi <[email protected]>
net: ethernet: mtk_wed: check update_wo_rx_stats in mtk_wed_update_rx_stats()
Paul E. McKenney <[email protected]>
rcu: Eliminate rcu_gp_slow_unregister() false positive
Zhen Lei <[email protected]>
rcu: Dump memory object info if callback function is invalid
Emmanuel Grumbach <[email protected]>
wifi: iwlwifi: mvm: fix recovery flow in CSA
Johannes Berg <[email protected]>
wifi: mac80211: fix BA session teardown race
Johannes Berg <[email protected]>
wifi: cfg80211: check wiphy mutex is held for wdev mutex
Johannes Berg <[email protected]>
wifi: mac80211: lock wiphy in IP address notifier
Ricardo Rivera-Matos <[email protected]>
ASoC: cs35l45: Checks index of cs35l45_irqs[]
Rand Deeb <[email protected]>
ssb: Fix division by zero issue in ssb_calc_clock_rate
ZhenGuo Yin <[email protected]>
drm/amdgpu: access RLC_SPM_MC_CNTL through MMIO in SRIOV runtime
Lee Jones <[email protected]>
drm/amd/amdgpu/imu_v11_0: Increase buffer size to ensure all possible values can be stored
Alex Deucher <[email protected]>
drm/amd/pm: fix error flow in sensor fetching
Parsa Poorshikhian <[email protected]>
ALSA: hda/realtek: Fix noise from speakers on Lenovo IdeaPad 3 15IAU7
Asmaa Mnebhi <[email protected]>
gpio: mlxbf3: Support shutdown() function
Jie Wang <[email protected]>
net: hns3: fix a deadlock problem when config TC during resetting
Peiyang Wang <[email protected]>
net: hns3: use the user's cfg after reset
Jie Wang <[email protected]>
net: hns3: fix wrong use of semaphore up
Matthieu Baerts (NGI0) <[email protected]>
selftests: net: lib: kill PIDs before del netns
Matthieu Baerts (NGI0) <[email protected]>
selftests: net: lib: ignore possible errors
Cong Wang <[email protected]>
vsock: fix recursive ->recvmsg calls
Phil Sutter <[email protected]>
netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests
Phil Sutter <[email protected]>
netfilter: nf_tables: Introduce nf_tables_getobj_single
Phil Sutter <[email protected]>
netfilter: nf_tables: Carry reset boolean in nft_obj_dump_ctx
Phil Sutter <[email protected]>
netfilter: nf_tables: nft_obj_filter fits into cb->ctx
Phil Sutter <[email protected]>
netfilter: nf_tables: Carry s_idx in nft_obj_dump_ctx
Phil Sutter <[email protected]>
netfilter: nf_tables: A better name for nft_obj_filter
Phil Sutter <[email protected]>
netfilter: nf_tables: Unconditionally allocate nft_obj_filter
Phil Sutter <[email protected]>
netfilter: nf_tables: Drop pointless memset in nf_tables_dump_obj
Phil Sutter <[email protected]>
netfilter: nf_tables: Audit log dump reset after the fact
Florian Westphal <[email protected]>
netfilter: nf_queue: drop packets with cloned unconfirmed conntracks
Donald Hunter <[email protected]>
netfilter: flowtable: initialise extack before use
Tom Hughes <[email protected]>
netfilter: allow ipv6 fragments to arrive on different devices
Subash Abhinov Kasiviswanathan <[email protected]>
tcp: Update window clamping condition
Eugene Syromiatnikov <[email protected]>
mptcp: correct MPTCP_SUBFLOW_ATTR_SSN_OFFSET reserved size
David Thompson <[email protected]>
mlxbf_gige: disable RX filters until RX path initialized
Zheng Zhang <[email protected]>
net: ethernet: mtk_wed: fix use-after-free panic in mtk_wed_setup_tc_block_cb()
Pawel Dembicki <[email protected]>
net: dsa: vsc73xx: check busy flag in MDIO operations
Pawel Dembicki <[email protected]>
net: dsa: vsc73xx: use read_poll_timeout instead delay loop
Pawel Dembicki <[email protected]>
net: dsa: vsc73xx: pass value in phy_write operation
Radhey Shyam Pandey <[email protected]>
net: axienet: Fix register defines comment description
Dan Carpenter <[email protected]>
atm: idt77252: prevent use after free in dequeue_rx()
Cosmin Ratiu <[email protected]>
net/mlx5e: Correctly report errors for ethtool rx flows
Dragos Tatulea <[email protected]>
net/mlx5e: Take state lock during tx timeout reporter
Faizal Rahim <[email protected]>
igc: Fix reset adapter logics when tx mode change
Faizal Rahim <[email protected]>
igc: Fix qbv_config_change_errors logics
Faizal Rahim <[email protected]>
igc: Fix packet still tx after gate close by reducing i226 MAC retry buffer
Leon Hwang <[email protected]>
bpf: Fix updating attached freplace prog in prog_array map
Claudio Imbrenda <[email protected]>
s390/uv: Panic for set and remove shared access UVC errors
Alex Deucher <[email protected]>
drm/amdgpu/jpeg4: properly set atomics vmid field
Alex Deucher <[email protected]>
drm/amdgpu/jpeg2: properly set atomics vmid field
Al Viro <[email protected]>
memcg_write_event_control(): fix a user-triggerable oops
Bas Nieuwenhuizen <[email protected]>
drm/amdgpu: Actually check flags for all context ops.
Qu Wenruo <[email protected]>
btrfs: tree-checker: add dev extent item checks
Naohiro Aota <[email protected]>
btrfs: zoned: properly take lock to read/update block group's zoned variables
Qu Wenruo <[email protected]>
btrfs: tree-checker: reject BTRFS_FT_UNKNOWN dir type
Waiman Long <[email protected]>
mm/memory-failure: use raw_spinlock_t in struct memory_failure_cpu
Zhen Lei <[email protected]>
selinux: add the processing of the failure of avc_add_xperms_decision()
Zhen Lei <[email protected]>
selinux: fix potential counting error in avc_add_xperms_decision()
Max Kellermann <[email protected]>
fs/netfs/fscache_cookie: add missing "n_accesses" check
Janne Grunau <[email protected]>
wifi: brcmfmac: cfg80211: Handle SSID based pmksa deletion
Long Li <[email protected]>
net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings
Haiyang Zhang <[email protected]>
net: mana: Fix RX buf alloc_size alignment and atomic op panic
Dan Carpenter <[email protected]>
rtla/osnoise: Prevent NULL dereference in error handling
Andi Shyti <[email protected]>
i2c: qcom-geni: Add missing geni_icc_disable in geni_i2c_runtime_resume
Al Viro <[email protected]>
fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE
Alexander Lobakin <[email protected]>
bitmap: introduce generic optimized bitmap_size()
Alexander Lobakin <[email protected]>
btrfs: rename bitmap_set_bits() -> btrfs_bitmap_set_bits()
Alexander Lobakin <[email protected]>
s390/cio: rename bitmap_size() -> idset_bitmap_size()
Alexander Lobakin <[email protected]>
fs/ntfs3: add prefix to bitmap_size() and use BITS_TO_U64()
Zhihao Cheng <[email protected]>
vfs: Don't evict inode under the inode lru traversing context
Mikulas Patocka <[email protected]>
dm persistent data: fix memory allocation failure
Khazhismel Kumykov <[email protected]>
dm resume: don't return EINVAL when signalled
Haibo Xu <[email protected]>
arm64: ACPI: NUMA: initialize all values of acpi_early_node_map to NUMA_NO_NODE
Rafael J. Wysocki <[email protected]>
ACPI: EC: Evaluate _REG outside the EC scope more carefully
Rafael J. Wysocki <[email protected]>
ACPICA: Add a depth argument to acpi_execute_reg_methods()
Breno Leitao <[email protected]>
i2c: tegra: Do not mark ACPI devices as irq safe
Nam Cao <[email protected]>
riscv: change XIP's kernel_map.size to be size of the entire kernel
Michael Mueller <[email protected]>
KVM: s390: fix validity interception issue when gisa is switched off
Stefan Haberland <[email protected]>
s390/dasd: fix error recovery leading to data corruption on ESE devices
Baojun Xu <[email protected]>
ALSA: hda/tas2781: fix wrong calibrated data order
Mika Westerberg <[email protected]>
thunderbolt: Mark XDomain as unplugged when router is removed
Mathias Nyman <[email protected]>
xhci: Fix Panther point NULL pointer deref at full-speed re-enumeration
Juan José Arboleda <[email protected]>
ALSA: usb-audio: Support Yamaha P-125 quirk entry
Lianqin Hu <[email protected]>
ALSA: usb-audio: Add delay quirk for VIVO USB-C-XE710 HEADSET
Eli Billauer <[email protected]>
char: xillybus: Check USB endpoints when probing device
Eli Billauer <[email protected]>
char: xillybus: Refine workqueue handling
Eli Billauer <[email protected]>
char: xillybus: Don't destroy workqueue from work item running on it
Jann Horn <[email protected]>
fuse: Initialize beyond-EOF page contents before setting uptodate
Paul Moore <[email protected]>
selinux: revert our use of vma_is_initial_heap()
Xu Yang <[email protected]>
Revert "usb: typec: tcpm: clear pd_event queue in PORT_RESET"
Griffin Kroah-Hartman <[email protected]>
Revert "misc: fastrpc: Restrict untrusted app to attach to privileged PD"
Rafael J. Wysocki <[email protected]>
Revert "ACPI: EC: Evaluate orphan _REG under EC device"
Mathieu Othacehe <[email protected]>
tty: atmel_serial: use the correct RTS flag.
Peng Fan <[email protected]>
tty: serial: fsl_lpuart: mark last busy before uart_add_one_port
-------------
Diffstat:
Documentation/ABI/testing/sysfs-devices-system-cpu | 3 +- Makefile | 4 +- arch/alpha/kernel/pci_iommu.c | 2 +- arch/arm64/kernel/acpi_numa.c | 2 +- arch/arm64/kernel/setup.c | 3 - arch/arm64/kernel/smp.c | 2 + arch/arm64/kvm/sys_regs.c | 6 + arch/arm64/kvm/vgic/vgic.h | 7 + arch/mips/jazz/jazzdma.c | 2 +- arch/mips/kernel/cpu-probe.c | 4 + arch/openrisc/kernel/setup.c | 6 +- arch/parisc/kernel/irq.c | 4 +- arch/powerpc/boot/simple_alloc.c | 7 +- arch/powerpc/include/asm/topology.h | 13 ++ arch/powerpc/kernel/dma-iommu.c | 2 +- arch/powerpc/platforms/ps3/system-bus.c | 4 +- arch/powerpc/platforms/pseries/papr-sysparm.c | 47 +++++ arch/powerpc/platforms/pseries/vio.c | 2 +- arch/powerpc/sysdev/xics/icp-native.c | 2 + arch/riscv/include/asm/asm.h | 10 + arch/riscv/kernel/entry.S | 3 + arch/riscv/kernel/traps.c | 3 +- arch/riscv/mm/init.c | 4 +- arch/s390/include/asm/uv.h | 5 +- arch/s390/kernel/early.c | 12 +- arch/s390/kernel/smp.c | 4 +- arch/s390/kvm/kvm-s390.h | 7 +- arch/x86/kernel/amd_gart_64.c | 2 +- arch/x86/kernel/process.c | 5 +- block/blk-mq-tag.c | 5 +- drivers/accel/habanalabs/common/debugfs.c | 14 +- drivers/accel/habanalabs/common/irq.c | 3 + drivers/accel/habanalabs/common/memory.c | 15 +- drivers/accel/habanalabs/gaudi2/gaudi2_security.c | 1 + drivers/acpi/acpica/acevents.h | 6 +- drivers/acpi/acpica/evregion.c | 12 +- drivers/acpi/acpica/evxfregn.c | 64 +----- drivers/acpi/ec.c | 14 +- drivers/acpi/internal.h | 1 + drivers/acpi/scan.c | 2 + drivers/atm/idt77252.c | 9 +- drivers/char/xillybus/xillyusb.c | 42 +++- drivers/clk/visconti/pll.c | 6 +- drivers/clocksource/arm_global_timer.c | 11 +- drivers/edac/skx_common.c | 4 + drivers/firmware/cirrus/cs_dsp.c | 7 +- drivers/gpio/gpio-mlxbf3.c | 14 ++ drivers/gpio/gpiolib-sysfs.c | 15 +- drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 40 +++- drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 3 + drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 8 + drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c | 3 + drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 53 +++-- drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c | 6 +- drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c | 13 +- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 13 +- drivers/gpu/drm/amd/amdgpu/imu_v11_0.c | 2 +- drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 4 +- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 63 +++++- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h | 6 + drivers/gpu/drm/amd/amdgpu/soc15d.h | 6 + drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 24 ++- .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 4 +- .../drm/amd/display/dc/dcn321/dcn321_resource.c | 3 + drivers/gpu/drm/amd/pm/amdgpu_pm.c | 14 +- drivers/gpu/drm/bridge/tc358768.c | 215 +++++++++++++++++--- drivers/gpu/drm/lima/lima_gp.c | 12 ++ drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 96 ++++++--- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h | 22 +- drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h | 9 +- .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c | 43 +--- .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c | 22 +- .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c | 21 +- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 2 +- drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h | 14 +- drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 23 ++- drivers/gpu/drm/msm/dp/dp_ctrl.c | 2 + drivers/gpu/drm/msm/dp/dp_panel.c | 19 +- drivers/gpu/drm/msm/msm_drv.h | 12 -- drivers/gpu/drm/msm/msm_gem_shrinker.c | 2 +- drivers/gpu/drm/msm/msm_mdss.c | 84 +++++--- drivers/gpu/drm/msm/msm_mdss.h | 1 + drivers/gpu/drm/nouveau/nvkm/core/firmware.c | 9 +- drivers/gpu/drm/nouveau/nvkm/falcon/fw.c | 6 + drivers/gpu/drm/panel/panel-novatek-nt36523.c | 6 +- drivers/gpu/drm/rockchip/rockchip_drm_vop2.c | 5 + drivers/gpu/drm/tegra/gem.c | 2 +- drivers/hid/wacom_wac.c | 4 +- drivers/hwmon/ltc2992.c | 8 +- drivers/hwmon/pc87360.c | 6 +- drivers/i2c/busses/i2c-qcom-geni.c | 4 +- drivers/i2c/busses/i2c-riic.c | 2 +- drivers/i2c/busses/i2c-stm32f7.c | 51 ++++- drivers/i2c/busses/i2c-tegra.c | 4 +- drivers/i3c/master/mipi-i3c-hci/dma.c | 5 +- drivers/infiniband/hw/hfi1/chip.c | 5 +- drivers/infiniband/ulp/rtrs/rtrs.c | 2 +- drivers/input/input-mt.c | 3 + drivers/input/serio/i8042-acpipnpio.h | 20 +- drivers/input/serio/i8042.c | 10 +- drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c | 1 + drivers/iommu/dma-iommu.c | 2 +- drivers/irqchip/irq-gic-v3-its.c | 2 - drivers/irqchip/irq-renesas-rzg2l.c | 5 +- drivers/md/dm-clone-metadata.c | 5 - drivers/md/dm-ioctl.c | 22 +- drivers/md/dm.c | 4 +- drivers/md/md.c | 5 - drivers/md/persistent-data/dm-space-map-metadata.c | 4 +- drivers/md/raid5-cache.c | 47 +++-- drivers/media/dvb-core/dvb_frontend.c | 12 +- drivers/media/pci/cx23885/cx23885-video.c | 8 + drivers/media/platform/qcom/venus/pm_helpers.c | 2 +- .../media/platform/samsung/s5p-mfc/s5p_mfc_enc.c | 2 +- drivers/media/radio/radio-isa.c | 2 +- drivers/memory/stm32-fmc2-ebi.c | 122 +++++++---- drivers/memory/tegra/tegra186.c | 3 + drivers/misc/fastrpc.c | 22 +- drivers/mmc/core/mmc_test.c | 9 +- drivers/mmc/host/dw_mmc.c | 8 + drivers/mmc/host/mtk-sd.c | 8 +- drivers/net/bonding/bond_main.c | 21 +- drivers/net/bonding/bond_options.c | 2 +- drivers/net/dsa/microchip/ksz_ptp.c | 5 +- drivers/net/dsa/mv88e6xxx/global1_atu.c | 3 +- drivers/net/dsa/ocelot/felix.c | 11 + drivers/net/dsa/vitesse-vsc73xx-core.c | 69 +++++-- drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 5 - drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 +- .../net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 +- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 + .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 28 ++- .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 7 +- .../ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 3 + .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 +- drivers/net/ethernet/i825xx/sun3_82586.c | 2 +- drivers/net/ethernet/intel/ice/ice_base.c | 21 +- drivers/net/ethernet/intel/ice/ice_txrx.c | 47 +---- drivers/net/ethernet/intel/igb/igb_main.c | 1 + drivers/net/ethernet/intel/igc/igc_defines.h | 6 + drivers/net/ethernet/intel/igc/igc_main.c | 8 +- drivers/net/ethernet/intel/igc/igc_tsn.c | 76 +++++-- drivers/net/ethernet/intel/igc/igc_tsn.h | 1 + .../net/ethernet/marvell/octeontx2/af/rvu_cpt.c | 23 +-- drivers/net/ethernet/mediatek/mtk_wed.c | 6 +- drivers/net/ethernet/mediatek/mtk_wed_mcu.c | 3 + .../ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 + .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +- .../net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h | 8 + .../ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c | 10 + .../ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h | 2 + .../ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c | 50 ++++- drivers/net/ethernet/microsoft/mana/mana_en.c | 28 ++- drivers/net/ethernet/mscc/ocelot.c | 91 ++++++++- drivers/net/ethernet/mscc/ocelot_fdma.c | 3 +- drivers/net/ethernet/mscc/ocelot_vsc7514.c | 4 + .../net/ethernet/pensando/ionic/ionic_bus_pci.c | 9 +- drivers/net/ethernet/pensando/ionic/ionic_dev.c | 33 ++- .../net/ethernet/pensando/ionic/ionic_ethtool.c | 7 +- drivers/net/ethernet/pensando/ionic/ionic_fw.c | 5 + drivers/net/ethernet/pensando/ionic/ionic_main.c | 3 + drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 6 +- drivers/net/ethernet/xilinx/xilinx_axienet.h | 17 +- drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 25 +-- drivers/net/gtp.c | 3 + drivers/net/wireless/ath/ath11k/mac.c | 42 ++-- drivers/net/wireless/ath/ath12k/mac.c | 27 ++- drivers/net/wireless/ath/ath12k/qmi.c | 7 + .../broadcom/brcm80211/brcmfmac/cfg80211.c | 13 +- drivers/net/wireless/intel/iwlwifi/fw/debugfs.c | 6 +- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 6 +- drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 3 + drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 7 +- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +- drivers/net/wireless/mediatek/mt76/mac80211.c | 50 ++++- drivers/net/wireless/mediatek/mt76/mt76.h | 24 +-- drivers/net/wireless/mediatek/mt76/mt7603/main.c | 4 +- drivers/net/wireless/mediatek/mt76/mt7615/main.c | 4 +- drivers/net/wireless/mediatek/mt76/mt76x02_util.c | 4 +- drivers/net/wireless/mediatek/mt76/mt7915/main.c | 4 +- drivers/net/wireless/mediatek/mt76/mt7921/main.c | 2 +- drivers/net/wireless/mediatek/mt76/mt792x_core.c | 2 +- drivers/net/wireless/mediatek/mt76/mt7996/main.c | 4 +- drivers/net/wireless/mediatek/mt76/tx.c | 108 ++++++++-- drivers/net/wireless/st/cw1200/txrx.c | 2 +- drivers/nvme/host/core.c | 107 ++++++---- drivers/nvme/host/ioctl.c | 15 +- drivers/nvme/host/multipath.c | 21 +- drivers/nvme/host/nvme.h | 4 +- drivers/nvme/target/rdma.c | 16 +- drivers/nvme/target/tcp.c | 1 + drivers/nvme/target/trace.c | 6 +- drivers/nvme/target/trace.h | 28 ++- drivers/parisc/ccio-dma.c | 2 +- drivers/parisc/sba_iommu.c | 2 +- drivers/platform/surface/aggregator/controller.c | 3 +- drivers/platform/x86/intel/ifs/load.c | 9 + drivers/platform/x86/lg-laptop.c | 2 +- drivers/pmdomain/imx/imx93-pd.c | 5 +- drivers/pmdomain/imx/scu-pd.c | 5 - drivers/rtc/rtc-nct3018y.c | 6 +- drivers/s390/block/dasd.c | 36 ++-- drivers/s390/block/dasd_3990_erp.c | 10 +- drivers/s390/block/dasd_diag.c | 1 - drivers/s390/block/dasd_eckd.c | 58 +++--- drivers/s390/block/dasd_int.h | 2 +- drivers/s390/cio/idset.c | 12 +- drivers/scsi/lpfc/lpfc_sli.c | 2 +- drivers/scsi/scsi_transport_spi.c | 4 +- drivers/ssb/main.c | 2 +- drivers/staging/iio/resolver/ad2s1210.c | 7 +- drivers/staging/ks7010/ks7010_sdio.c | 4 +- drivers/thunderbolt/switch.c | 1 + drivers/tty/serial/atmel_serial.c | 2 +- drivers/tty/serial/fsl_lpuart.c | 1 + drivers/usb/dwc3/core.c | 13 ++ drivers/usb/gadget/udc/fsl_udc_core.c | 2 +- drivers/usb/host/xhci.c | 8 +- drivers/usb/typec/tcpm/tcpm.c | 1 - drivers/xen/grant-dma-ops.c | 2 +- drivers/xen/swiotlb-xen.c | 2 +- fs/afs/file.c | 8 +- fs/binfmt_elf_fdpic.c | 2 +- fs/binfmt_misc.c | 216 +++++++++++++++----- fs/btrfs/compression.c | 23 ++- fs/btrfs/compression.h | 2 +- fs/btrfs/defrag.c | 2 +- fs/btrfs/delayed-inode.c | 4 +- fs/btrfs/disk-io.c | 2 + fs/btrfs/extent_io.c | 4 +- fs/btrfs/free-space-cache.c | 22 +- fs/btrfs/inode.c | 24 ++- fs/btrfs/ioctl.c | 2 +- fs/btrfs/qgroup.c | 2 - fs/btrfs/reflink.c | 6 +- fs/btrfs/send.c | 71 +++++-- fs/btrfs/super.c | 2 +- fs/btrfs/tests/extent-io-tests.c | 28 ++- fs/btrfs/tree-checker.c | 74 ++++++- fs/btrfs/zlib.c | 73 ++----- fs/ext4/extents.c | 3 +- fs/ext4/mballoc.c | 3 + fs/f2fs/segment.c | 17 +- fs/file.c | 28 ++- fs/fscache/cookie.c | 4 + fs/fuse/cuse.c | 3 +- fs/fuse/dev.c | 6 +- fs/fuse/fuse_i.h | 1 + fs/fuse/inode.c | 15 +- fs/fuse/virtio_fs.c | 10 + fs/gfs2/inode.c | 2 +- fs/gfs2/super.c | 2 + fs/inode.c | 39 +++- fs/jfs/jfs_dinode.h | 2 +- fs/jfs/jfs_imap.c | 6 +- fs/jfs/jfs_incore.h | 2 +- fs/jfs/jfs_txnmgr.c | 4 +- fs/jfs/jfs_xtree.c | 4 +- fs/jfs/jfs_xtree.h | 37 ++-- fs/kernfs/file.c | 8 +- fs/nfs/pnfs.c | 8 + fs/nfsd/nfssvc.c | 14 +- fs/ntfs3/bitmap.c | 4 +- fs/ntfs3/fsntfs.c | 2 +- fs/ntfs3/index.c | 11 +- fs/ntfs3/ntfs_fs.h | 4 +- fs/ntfs3/super.c | 2 +- fs/quota/dquot.c | 5 +- fs/smb/client/reparse.c | 11 +- fs/smb/server/connection.c | 34 +++- fs/smb/server/connection.h | 3 +- fs/smb/server/mgmt/user_session.c | 8 + fs/smb/server/smb2pdu.c | 5 +- include/acpi/acpixf.h | 5 +- include/linux/bitmap.h | 20 +- include/linux/bpf_verifier.h | 4 +- include/linux/cpumask.h | 2 +- include/linux/dma-map-ops.h | 2 +- include/linux/dsa/ocelot.h | 47 +++++ include/linux/evm.h | 6 + include/linux/f2fs_fs.h | 1 + include/linux/fs.h | 5 + include/net/af_vsock.h | 4 + include/net/inet_timewait_sock.h | 2 +- include/net/kcm.h | 1 + include/net/mana/mana.h | 1 + include/net/tcp.h | 2 +- include/scsi/scsi_cmnd.h | 2 +- include/soc/mscc/ocelot.h | 12 +- include/uapi/misc/fastrpc.h | 3 - init/Kconfig | 7 +- kernel/bpf/verifier.c | 5 +- kernel/cgroup/cgroup.c | 4 +- kernel/cpu.c | 12 +- kernel/dma/mapping.c | 4 +- kernel/rcu/rcu.h | 7 + kernel/rcu/srcutiny.c | 1 + kernel/rcu/srcutree.c | 1 + kernel/rcu/tasks.h | 1 + kernel/rcu/tiny.c | 1 + kernel/rcu/tree.c | 3 +- kernel/sched/topology.c | 3 + kernel/time/clocksource.c | 42 ++-- kernel/time/hrtimer.c | 5 +- kernel/time/tick-sched.h | 2 +- lib/cpumask.c | 4 +- lib/math/prime_numbers.c | 2 - mm/huge_memory.c | 30 ++- mm/memcontrol.c | 7 +- mm/memory-failure.c | 20 +- mm/memory.c | 33 ++- mm/page_alloc.c | 42 ++-- mm/vmalloc.c | 11 +- net/bluetooth/bnep/core.c | 3 +- net/bluetooth/hci_conn.c | 11 +- net/bluetooth/hci_core.c | 19 +- net/bluetooth/mgmt.c | 4 + net/bluetooth/smp.c | 146 ++++++------- net/bridge/br_netfilter_hooks.c | 6 +- net/core/sock_map.c | 6 - net/dccp/ipv4.c | 2 +- net/dccp/ipv6.c | 6 - net/dsa/tag_ocelot.c | 37 +--- net/ipv4/inet_timewait_sock.c | 16 +- net/ipv4/tcp_input.c | 28 ++- net/ipv4/tcp_ipv4.c | 16 +- net/ipv4/tcp_minisocks.c | 7 +- net/ipv4/udp_offload.c | 3 +- net/ipv6/ip6_output.c | 10 + net/ipv6/ip6_tunnel.c | 12 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 + net/ipv6/tcp_ipv6.c | 6 - net/iucv/iucv.c | 3 +- net/kcm/kcmsock.c | 4 + net/mac80211/agg-tx.c | 6 +- net/mac80211/driver-ops.c | 3 - net/mac80211/iface.c | 14 ++ net/mac80211/main.c | 22 +- net/mac80211/sta_info.c | 46 +++-- net/mctp/test/route-test.c | 2 +- net/mptcp/diag.c | 2 +- net/mptcp/pm.c | 13 -- net/mptcp/pm_netlink.c | 142 ++++++++----- net/mptcp/protocol.h | 3 - net/netfilter/nf_flow_table_inet.c | 3 + net/netfilter/nf_flow_table_ip.c | 3 + net/netfilter/nf_flow_table_offload.c | 2 +- net/netfilter/nf_tables_api.c | 225 ++++++++++++--------- net/netfilter/nfnetlink_queue.c | 35 +++- net/netfilter/nft_counter.c | 9 +- net/netlink/af_netlink.c | 13 +- net/openvswitch/datapath.c | 2 +- net/rxrpc/rxkad.c | 8 +- net/sched/sch_netem.c | 47 +++-- net/vmw_vsock/af_vsock.c | 50 +++-- net/vmw_vsock/vsock_bpf.c | 4 +- net/wireless/core.h | 8 +- scripts/rust_is_available.sh | 6 +- security/integrity/evm/evm_main.c | 7 + security/security.c | 2 +- security/selinux/avc.c | 8 +- security/selinux/hooks.c | 12 +- sound/core/timer.c | 2 +- sound/pci/hda/patch_realtek.c | 1 - sound/pci/hda/tas2781_hda_i2c.c | 14 +- sound/soc/codecs/cs35l45.c | 5 +- sound/soc/sof/intel/hda-dsp.c | 3 + sound/soc/sof/ipc4.c | 9 +- sound/usb/quirks-table.h | 1 + sound/usb/quirks.c | 2 + tools/include/linux/bitmap.h | 7 +- .../testing/selftests/bpf/progs/cpumask_failure.c | 3 - tools/testing/selftests/bpf/progs/dynptr_fail.c | 12 +- tools/testing/selftests/bpf/progs/iters.c | 54 +++++ .../selftests/bpf/progs/jeq_infer_not_null_fail.c | 4 + .../testing/selftests/bpf/progs/test_tunnel_kern.c | 47 +++-- tools/testing/selftests/core/close_range_test.c | 35 ++++ tools/testing/selftests/mm/Makefile | 2 + tools/testing/selftests/mm/run_vmtests.sh | 53 ++++- tools/testing/selftests/net/lib.sh | 11 +- tools/testing/selftests/net/mptcp/mptcp_join.sh | 28 ++- tools/testing/selftests/net/udpgro.sh | 44 ++-- tools/testing/selftests/tc-testing/tdc.py | 1 - tools/tracing/rtla/src/osnoise_top.c | 11 +- 386 files changed, 3829 insertions(+), 1937 deletions(-)
Greg Kroah-Hartman
maintainerPATCH 15/341 ALSA: hda/tas2781: fix wrong calibrated data order
6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Baojun Xu <[email protected]>
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.
--- sound/pci/hda/tas2781_hda_i2c.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-)
sound/pci/hda/tas2781_hda_i2c.c +9 -5
@@ -2,10 +2,12 @@// // TAS2781 HDA I2C driver // -// Copyright 2023 Texas Instruments, Inc. +// Copyright 2023 - 2024 Texas Instruments, Inc. // // Author: Shenghao Ding <[email protected]> +// Current maintainer: Baojun Xu <[email protected]> +#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 tstatic 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 ; } } }
Greg Kroah-Hartman
maintainerPATCH 24/341 dm persistent data: fix memory allocation failure
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mikulas Patocka <[email protected]>
commit faada2174c08662ae98b439c69efe3e79382c538 upstream.
kmalloc is unreliable when allocating more than 8 pages of memory. It may fail when there is plenty of free memory but the memory is fragmented. Zdenek Kabelac observed such failure in his tests.
This commit changes kmalloc to kvmalloc - kvmalloc will fall back to vmalloc if the large allocation fails.
--- drivers/md/persistent-data/dm-space-map-metadata.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/md/persistent-data/dm-space-map-metadata.c +2 -2
@@ -277,7 +277,7 @@ static void sm_metadata_destroy(struct d { struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm); -kfree (smm); +kvfree (smm); }static int sm_metadata_get_nr_blocks (struct dm_space_map *sm,dm_block_t *count)
@@ -772,7 +772,7 @@ struct dm_space_map *dm_sm_metadata_init {struct sm_metadata *smm; - smm =kmalloc (sizeof (*smm),GFP_KERNEL ); + smm =kvmalloc (sizeof (*smm),GFP_KERNEL );if (!smm)return ERR_PTR (-ENOMEM );
Greg Kroah-Hartman
maintainerPATCH 25/341 vfs: Dont evict inode under the inode lru traversing context
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhihao Cheng <[email protected]>
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.
--- fs/inode.c | 39 +++++++++++++++++++++++++++++++++++++-- include/linux/fs.h | 5 +++++ 2 files changed, 42 insertions(+), 2 deletions(-)
fs/inode.c +37 -2
@@ -486,6 +486,39 @@ static void inode_lru_list_del(struct inthis_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 ; }
include/linux/fs.h +5 -0
@@ -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)
Greg Kroah-Hartman
maintainerPATCH 26/341 fs/ntfs3: add prefix to bitmap_size() and use BITS_TO_U64()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexander Lobakin <[email protected]>
commit 3f5ef5109f6a054ce58b3bec7214ed76c9cc269f 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 NTFS-specific, as it aligns to the sizeof(u64), not the sizeof(long) (although it uses ideologically right ALIGN() instead of division). Add the prefix 'ntfs3_' used for that FS (not just 'ntfs_' to not mix it with the legacy module) and use generic BITS_TO_U64() while at it.
--- fs/ntfs3/bitmap.c | 4 ++-- fs/ntfs3/fsntfs.c | 2 +- fs/ntfs3/index.c | 11 ++++++----- fs/ntfs3/ntfs_fs.h | 4 ++-- fs/ntfs3/super.c | 2 +- 5 files changed, 12 insertions(+), 11 deletions(-)
fs/ntfs3/bitmap.c +2 -2
@@ -654,7 +654,7 @@ int wnd_init(struct wnd_bitmap *wnd, str wnd->total_zeroes = nbits; wnd->extent_max =MINUS_ONE_T ; wnd->zone_bit = wnd->zone_end =0 ; - wnd->nwnd =bytes_to_block (sb,bitmap_size (nbits)); + wnd->nwnd =bytes_to_block (sb,ntfs3_bitmap_size (nbits)); wnd->bits_last = nbits & (wbits -1 );if (!wnd->bits_last) wnd->bits_last = wbits;
@@ -1347,7 +1347,7 @@ int wnd_extend(struct wnd_bitmap *wnd, sreturn -EINVAL ;/* Align to 8 byte boundary. */ - new_wnd =bytes_to_block (sb,bitmap_size (new_bits)); + new_wnd =bytes_to_block (sb,ntfs3_bitmap_size (new_bits)); new_last = new_bits & (wbits -1 );if (!new_last) new_last = wbits;
fs/ntfs3/fsntfs.c +1 -1
@@ -522,7 +522,7 @@ static int ntfs_extend_mft(struct ntfs_s ni->mi.dirty = true;/* Step 2: Resize $MFT::BITMAP. */ - new_bitmap_bytes =bitmap_size (new_mft_total); + new_bitmap_bytes =ntfs3_bitmap_size (new_mft_total); err =attr_set_size (ni,ATTR_BITMAP ,NULL ,0 , &sbi->mft.bitmap.run, new_bitmap_bytes, &new_bitmap_bytes, true,NULL );
fs/ntfs3/index.c +6 -5
@@ -1456,8 +1456,8 @@ static int indx_create_allocate(struct n alloc->nres.valid_size = alloc->nres.data_size =cpu_to_le64 (data_size); - err =ni_insert_resident (ni,bitmap_size (1 ),ATTR_BITMAP , in->name, - in->name_len, &bitmap,NULL ,NULL ); + err =ni_insert_resident (ni,ntfs3_bitmap_size (1 ),ATTR_BITMAP , + in->name, in->name_len, &bitmap,NULL ,NULL );if (err) goto out2;
@@ -1518,8 +1518,9 @@ static int indx_add_allocate(struct ntfsif (bmp) {/* Increase bitmap. */ err =attr_set_size (ni,ATTR_BITMAP , in->name, in->name_len, - &indx->bitmap_run,bitmap_size (bit +1 ), -NULL , true,NULL ); + &indx->bitmap_run, +ntfs3_bitmap_size (bit +1 ),NULL , true, +NULL );if (err) goto out1; }
@@ -2098,7 +2099,7 @@ static int indx_shrink(struct ntfs_indexif (in->name ==I30_NAME )i_size_write (&ni->vfs_inode, new_data); - bpb =bitmap_size (bit); + bpb =ntfs3_bitmap_size (bit);if (bpb *8 == nbits)return 0 ;
fs/ntfs3/ntfs_fs.h +2 -2
@@ -964,9 +964,9 @@ static inline bool run_is_empty(struct r }/* NTFS uses quad aligned bitmaps. */ -static inline size_t bitmap_size (size_t bits) +static inline size_t ntfs3_bitmap_size (size_t bits) { -return ALIGN ((bits +7 ) >>3 ,8 ); +return BITS_TO_U64 (bits) *sizeof (u64); }#define _100ns2seconds 10000000
fs/ntfs3/super.c +1 -1
@@ -1341,7 +1341,7 @@ static int ntfs_fill_super(struct super_/* Check bitmap boundary. */ tt = sbi->used.bitmap.nbits; -if (inode->i_size <bitmap_size (tt)) { +if (inode->i_size <ntfs3_bitmap_size (tt)) {ntfs_err (sb,"$Bitmap is corrupted." ); err = -EINVAL ; goto put_inode_out;
Greg Kroah-Hartman
maintainerPATCH 27/341 s390/cio: rename bitmap_size() -> idset_bitmap_size()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexander Lobakin <[email protected]>
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.
--- drivers/s390/cio/idset.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)
drivers/s390/cio/idset.c +6 -4
@@ -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)
Greg Kroah-Hartman
maintainerPATCH 28/341 btrfs: rename bitmap_set_bits() -> btrfs_bitmap_set_bits()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexander Lobakin <[email protected]>
commit 4ca532d64648d4776d15512caed3efea05ca7195 upstream.
bitmap_set_bits() does not start with the FS' prefix and may collide with a new generic helper one day. It operates with the FS-specific types, so there's no change those two could do the same thing. Just add the prefix to exclude such possible conflict.
--- fs/btrfs/free-space-cache.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-)
fs/btrfs/free-space-cache.c +4 -4
@@ -1910,9 +1910,9 @@ static inline void bitmap_clear_bits(str ctl->free_space -= bytes; } -static void bitmap_set_bits (struct btrfs_free_space_ctl *ctl, -struct btrfs_free_space *info,u64 offset, -u64 bytes) +static void btrfs_bitmap_set_bits (struct btrfs_free_space_ctl *ctl, +struct btrfs_free_space *info,u64 offset, +u64 bytes) {unsigned long start, count, end;int extent_delta =1 ;
@@ -2248,7 +2248,7 @@ static u64 add_bytes_to_bitmap(struct bt bytes_to_set =min (end - offset, bytes); -bitmap_set_bits (ctl, info, offset, bytes_to_set); +btrfs_bitmap_set_bits (ctl, info, offset, bytes_to_set);return bytes_to_set;
Greg Kroah-Hartman
maintainerPATCH 29/341 bitmap: introduce generic optimized bitmap_size()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alexander Lobakin <[email protected]>
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.
--- 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(-)
drivers/md/dm-clone-metadata.c +0 -5
@@ -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) {
drivers/s390/cio/idset.c +1 -1
@@ -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)
include/linux/bitmap.h +5 -3
@@ -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(unsignedstatic 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(unsignedstatic 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;
include/linux/cpumask.h +1 -1
@@ -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); }/*
lib/math/prime_numbers.c +0 -2
@@ -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;
tools/include/linux/bitmap.h +4 -3
@@ -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)); }/*
Greg Kroah-Hartman
maintainerPATCH 30/341 fix bitmap corruption on close_range() with CLOSE_RANGE_UNSHARE
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Al Viro <[email protected]>
commit 9a2fa1472083580b6c66bdaf291f591e1170123a upstream.
copy_fd_bitmaps(new, old, count) is expected to copy the first count/BITS_PER_LONG bits from old->full_fds_bits[] and fill the rest with zeroes. What it does is copying enough words (BITS_TO_LONGS(count/BITS_PER_LONG)), then memsets the rest. That works fine, *if* all bits past the cutoff point are clear. Otherwise we are risking garbage from the last word we'd copied.
For most of the callers that is true - expand_fdtable() has count equal to old->max_fds, so there's no open descriptors past count, let alone fully occupied words in ->open_fds[], which is what bits in ->full_fds_bits[] correspond to.
The other caller (dup_fd()) passes sane_fdtable_size(old_fdt, max_fds), which is the smallest multiple of BITS_PER_LONG that covers all opened descriptors below max_fds. In the common case (copying on fork()) max_fds is ~0U, so all opened descriptors will be below it and we are fine, by the same reasons why the call in expand_fdtable() is safe.
Unfortunately, there is a case where max_fds is less than that and where we might, indeed, end up with junk in ->full_fds_bits[] - close_range(from, to, CLOSE_RANGE_UNSHARE) with
* descriptor table being currently shared
* 'to' being above the current capacity of descriptor table
* 'from' being just under some chunk of opened descriptors.
In that case we end up with observably wrong behaviour - e.g. spawn a child with CLONE_FILES, get all descriptors in range 0..127 open, then close_range(64, ~0U, CLOSE_RANGE_UNSHARE) and watch dup(0) ending up with descriptor #128, despite #64 being observably not open.
The minimally invasive fix would be to deal with that in dup_fd(). If this proves to add measurable overhead, we can go that way, but let's try to fix copy_fd_bitmaps() first.
* new helper: bitmap_copy_and_expand(to, from, bits_to_copy, size).
* make copy_fd_bitmaps() take the bitmap size in words, rather than bits; it's 'count' argument is always a multiple of BITS_PER_LONG, so we are not losing any information, and that way we can use the same helper for all three bitmaps - compiler will see that count is a multiple of BITS_PER_LONG for the large ones, so it'll generate plain memcpy()+memset().
Reproducer added to tools/testing/selftests/core/close_range_test.c
--- fs/file.c | 28 ++++++++----------- include/linux/bitmap.h | 12 ++++++++ tools/testing/selftests/core/close_range_test.c | 35 ++++++++++++++++++++++++ 3 files changed, 59 insertions(+), 16 deletions(-)
fs/file.c +12 -16
@@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_#define BITBIT_NR (nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))#define BITBIT_SIZE (nr) (BITBIT_NR(nr) * sizeof(long)) +#define fdt_words (fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds/* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ -static void copy_fd_bitmaps (struct fdtable *nfdt,struct fdtable *ofdt, -unsigned int count) +static inline void copy_fd_bitmaps (struct fdtable *nfdt,struct fdtable *ofdt, +unsigned int copy_words) { -unsigned int cpy, set; +unsigned int nwords =fdt_words (nfdt); - cpy = count /BITS_PER_BYTE ; - set = (nfdt->max_fds - count) /BITS_PER_BYTE ; -memcpy (nfdt->open_fds, ofdt->open_fds, cpy); -memset ((char *)nfdt->open_fds + cpy,0 , set); -memcpy (nfdt->close_on_exec, ofdt->close_on_exec, cpy); -memset ((char *)nfdt->close_on_exec + cpy,0 , set); - - cpy =BITBIT_SIZE (count); - set =BITBIT_SIZE (nfdt->max_fds) - cpy; -memcpy (nfdt->full_fds_bits, ofdt->full_fds_bits, cpy); -memset ((char *)nfdt->full_fds_bits + cpy,0 , set); +bitmap_copy_and_extend (nfdt->open_fds, ofdt->open_fds, + copy_words *BITS_PER_LONG , nwords *BITS_PER_LONG ); +bitmap_copy_and_extend (nfdt->close_on_exec, ofdt->close_on_exec, + copy_words *BITS_PER_LONG , nwords *BITS_PER_LONG ); +bitmap_copy_and_extend (nfdt->full_fds_bits, ofdt->full_fds_bits, + copy_words, nwords); }/*
@@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtablememcpy (nfdt->fd, ofdt->fd, cpy);memset ((char *)nfdt->fd + cpy,0 , set); -copy_fd_bitmaps (nfdt, ofdt, ofdt->max_fds); +copy_fd_bitmaps (nfdt, ofdt,fdt_words (ofdt)); }/*
@@ -374,7 +370,7 @@ struct files_struct *dup_fd(struct files open_files =sane_fdtable_size (old_fdt, max_fds); } -copy_fd_bitmaps (new_fdt, old_fdt, open_files); +copy_fd_bitmaps (new_fdt, old_fdt, open_files /BITS_PER_LONG ); old_fds = old_fdt->fd; new_fds = new_fdt->fd;
include/linux/bitmap.h +12 -0
@@ -281,6 +281,18 @@ static inline void bitmap_copy_clear_tai dst[nbits /BITS_PER_LONG ] &=BITMAP_LAST_WORD_MASK (nbits); } +static inline void bitmap_copy_and_extend (unsigned long *to, +const unsigned long *from, +unsigned int count,unsigned int size) +{ +unsigned int copy =BITS_TO_LONGS (count); + +memcpy (to, from, copy *sizeof (long )); +if (count %BITS_PER_LONG ) + to[copy -1 ] &=BITMAP_LAST_WORD_MASK (count); +memset (to + copy,0 ,bitmap_size (size) - copy *sizeof (long )); +} +/* * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64 * machines the order of hi and lo parts of numbers match the bitmap structure.
tools/testing/selftests/core/close_range_test.c +35 -0
@@ -563,4 +563,39 @@ TEST(close_range_cloexec_unshare_syzbot)EXPECT_EQ (close (fd3),0 ); } +TEST (close_range_bitmap_corruption) +{ +pid_t pid; +int status; +struct __clone_args args = { + .flags =CLONE_FILES , + .exit_signal =SIGCHLD , + }; + +/* get the first 128 descriptors open */ +for (int i =2 ; i <128 ; i++) +EXPECT_GE (dup2 (0 , i),0 ); + +/* get descriptor table shared */ + pid =sys_clone3 (&args,sizeof (args)); +ASSERT_GE (pid,0 ); + +if (pid ==0 ) { +/* unshare and truncate descriptor table down to 64 */ +if (sys_close_range (64 , ~0U ,CLOSE_RANGE_UNSHARE )) +exit (EXIT_FAILURE ); + +ASSERT_EQ (fcntl (64 ,F_GETFD ),-1 ); +/* ... and verify that the range 64..127 is not +stuck "fully used" according to secondary bitmap */ + EXPECT_EQ(dup(0), 64) +exit (EXIT_FAILURE ); +exit (EXIT_SUCCESS ); + } + +EXPECT_EQ (waitpid (pid, &status,0 ), pid); +EXPECT_EQ (true,WIFEXITED (status)); +EXPECT_EQ (0 ,WEXITSTATUS (status)); +} +TEST_HARNESS_MAIN
Greg Kroah-Hartman
maintainerPATCH 31/341 i2c: qcom-geni: Add missing geni_icc_disable in geni_i2c_runtime_resume
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Andi Shyti <[email protected]>
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.
--- drivers/i2c/busses/i2c-qcom-geni.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
drivers/i2c/busses/i2c-qcom-geni.c +3 -1
@@ -987,8 +987,10 @@ static int __maybe_unused geni_i2c_runtireturn 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) {
Greg Kroah-Hartman
maintainerPATCH 32/341 rtla/osnoise: Prevent NULL dereference in error handling
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dan Carpenter <[email protected]>
commit 90574d2a675947858b47008df8d07f75ea50d0d0 upstream.
If the "tool->data" allocation fails then there is no need to call osnoise_free_top() and, in fact, doing so will lead to a NULL dereference.
--- tools/tracing/rtla/src/osnoise_top.c | 11 ++++------- 1 file changed, 4 insertions(+), 7 deletions(-)
tools/tracing/rtla/src/osnoise_top.c +4 -7
@@ -624,8 +624,10 @@ struct osnoise_tool *osnoise_init_top(streturn NULL ; tool->data =osnoise_alloc_top (nr_cpus); -if (!tool->data) - goto out_err; +if (!tool->data) { +osnoise_destroy_tool (tool); +return NULL ; + } tool->params = params;
@@ -633,11 +635,6 @@ struct osnoise_tool *osnoise_init_top(st osnoise_top_handler, NULL);return tool; - -out_err: -osnoise_free_top (tool->data); -osnoise_destroy_tool (tool); -return NULL ; }static int stop_tracing;
Greg Kroah-Hartman
maintainerPATCH 33/341 net: mana: Fix RX buf alloc_size alignment and atomic op panic
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Haiyang Zhang <[email protected]>
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
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +5 -1
@@ -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 ; }
Signature · 1 line
2.46.0
Greg Kroah-Hartman
maintainerPATCH 16/341 s390/dasd: fix error recovery leading to data corruption on ESE devices
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Stefan Haberland <[email protected]>
commit 7db4042336580dfd75cb5faa82c12cd51098c90b upstream.
Extent Space Efficient (ESE) or thin provisioned volumes need to be formatted on demand during usual IO processing.
The dasd_ese_needs_format function checks for error codes that signal the non existence of a proper track format.
The check for incorrect length is to imprecise since other error cases leading to transport of insufficient data also have this flag set. This might lead to data corruption in certain error cases for example during a storage server warmstart.
Fix by removing the check for incorrect length and replacing by explicitly checking for invalid track format in transport mode.
Also remove the check for file protected since this is not a valid ESE handling case.
--- drivers/s390/block/dasd.c | 36 +++++++++++++++--------- drivers/s390/block/dasd_3990_erp.c | 10 +----- drivers/s390/block/dasd_eckd.c | 55 ++++++++++++++++--------------------- drivers/s390/block/dasd_int.h | 2 - 4 files changed, 50 insertions(+), 53 deletions(-)
drivers/s390/block/dasd.c +23 -13
@@ -1599,9 +1599,15 @@ static int dasd_ese_needs_format(structif (!sense)return 0 ; -return !!(sense[1 ] &SNS1_NO_REC_FOUND ) || - !!(sense[1 ] &SNS1_FILE_PROTECTED ) || -scsw_cstat (&irb->scsw) ==SCHN_STAT_INCORR_LEN ; +if (sense[1 ] &SNS1_NO_REC_FOUND ) +return 1 ; + +if ((sense[1 ] &SNS1_INV_TRACK_FORMAT ) && +scsw_is_tm (&irb->scsw) && + !(sense[2 ] &SNS2_ENV_DATA_PRESENT )) +return 1 ; + +return 0 ; }static int dasd_ese_oos_cond (u8 *sense)
@@ -1622,7 +1628,7 @@ void dasd_int_handler(struct ccw_devicestruct dasd_device *device;unsigned long now;int nrf_suppressed =0 ; -int fp_suppressed =0 ; +int it_suppressed =0 ;struct request *req;u8 *sense =NULL ;int expires;
@@ -1677,8 +1683,9 @@ void dasd_int_handler(struct ccw_device*/ sense =dasd_get_sense (irb);if (sense) { - fp_suppressed = (sense[1 ] &SNS1_FILE_PROTECTED ) && -test_bit (DASD_CQR_SUPPRESS_FP , &cqr->flags); + it_suppressed = (sense[1 ] &SNS1_INV_TRACK_FORMAT ) && + !(sense[2 ] &SNS2_ENV_DATA_PRESENT ) && +test_bit (DASD_CQR_SUPPRESS_IT , &cqr->flags); nrf_suppressed = (sense[1 ] &SNS1_NO_REC_FOUND ) &&test_bit (DASD_CQR_SUPPRESS_NRF , &cqr->flags);
@@ -1693,7 +1700,7 @@ void dasd_int_handler(struct ccw_devicereturn ; } } -if (!(fp_suppressed || nrf_suppressed)) +if (!(it_suppressed || nrf_suppressed)) device->discipline->dump_sense_dbf (device, irb,"int" );if (device->features &DASD_FEATURE_ERPLOG )
@@ -2465,14 +2472,17 @@ retry: rc =0 ;list_for_each_entry_safe (cqr, n, ccw_queue, blocklist) {/* -* In some cases the 'File Protected' or 'Incorrect Length' -* error might be expected and error recovery would be -* unnecessary in these cases. Check if the according suppress -* bit is set. +* In some cases certain errors might be expected and +* error recovery would be unnecessary in these cases. +* Check if the according suppress bit is set. */ sense =dasd_get_sense (&cqr->irb); -if (sense && sense[1 ] &SNS1_FILE_PROTECTED && -test_bit (DASD_CQR_SUPPRESS_FP , &cqr->flags)) +if (sense && (sense[1 ] &SNS1_INV_TRACK_FORMAT ) && + !(sense[2 ] &SNS2_ENV_DATA_PRESENT ) && +test_bit (DASD_CQR_SUPPRESS_IT , &cqr->flags)) +continue ; +if (sense && (sense[1 ] &SNS1_NO_REC_FOUND ) && +test_bit (DASD_CQR_SUPPRESS_NRF , &cqr->flags))continue ;if (scsw_cstat (&cqr->irb.scsw) ==0x40 &&test_bit (DASD_CQR_SUPPRESS_IL , &cqr->flags))
drivers/s390/block/dasd_3990_erp.c +2 -8
@@ -1406,14 +1406,8 @@ dasd_3990_erp_file_prot(struct dasd_ccw_struct dasd_device *device = erp->startdev; -/* -* In some cases the 'File Protected' error might be expected and -* log messages shouldn't be written then. -* Check if the according suppress bit is set. -*/ -if (!test_bit (DASD_CQR_SUPPRESS_FP , &erp->flags)) -dev_err (&device->cdev->dev, -"Accessing the DASD failed because of a hardware error\n" ); +dev_err (&device->cdev->dev, +"Accessing the DASD failed because of a hardware error\n" );return dasd_3990_erp_cleanup (erp,DASD_CQR_FAILED );
drivers/s390/block/dasd_eckd.c +24 -31
90 lines not on this page · raw message
drivers/s390/block/dasd_int.h +1 -1
@@ -225,7 +225,7 @@ struct dasd_ccw_req {* The following flags are used to suppress output of certain errors. */ #define DASD_CQR_SUPPRESS_NRF 4/* Suppress 'No Record Found' error */ -#define DASD_CQR_SUPPRESS_FP 5/* Suppress 'File Protected' error*/ +#define DASD_CQR_SUPPRESS_IT 5/* Suppress 'Invalid Track' error*/ #define DASD_CQR_SUPPRESS_IL 6/* Suppress 'Incorrect Length' error */ #define DASD_CQR_SUPPRESS_CR 7/* Suppress 'Command Reject' error */
Greg Kroah-Hartman
maintainerPATCH 34/341 net: mana: Fix doorbell out of order violation and avoid unnecessary doorbell rings
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Long Li <[email protected]>
commit 58a63729c957621f1990c3494c702711188ca347 upstream.
After napi_complete_done() is called when NAPI is polling in the current process context, another NAPI may be scheduled and start running in softirq on another CPU and may ring the doorbell before the current CPU does. When combined with unnecessary rings when there is no need to arm the CQ, it triggers error paths in the hardware.
This patch fixes this by calling napi_complete_done() after doorbell rings. It limits the number of unnecessary rings when there is no need to arm. MANA hardware specifies that there must be one doorbell ring every 8 CQ wraparounds. This driver guarantees one doorbell ring as soon as the number of consumed CQEs exceeds 4 CQ wraparounds. In practical workloads, the 4 CQ wraparounds proves to be big enough that it rarely exceeds this limit before all the napi weight is consumed.
To implement this, add a per-CQ counter cq->work_done_since_doorbell, and make sure the CQ is armed as soon as passing 4 wraparounds of the CQ.
--- drivers/net/ethernet/microsoft/mana/mana_en.c | 22 ++++++++++++++-------- include/net/mana/mana.h | 1 + 2 files changed, 15 insertions(+), 8 deletions(-)
drivers/net/ethernet/microsoft/mana/mana_en.c +14 -8
@@ -1778,7 +1778,6 @@ static void mana_poll_rx_cq(struct mana_static int mana_cq_handler (void *context,struct gdma_queue *gdma_queue) {struct mana_cq *cq = context; -u8 arm_bit;int w;WARN_ON_ONCE (cq->gdma_cq != gdma_queue);
@@ -1789,16 +1788,23 @@ static int mana_cq_handler(void *contextmana_poll_tx_cq (cq); w = cq->work_done; + cq->work_done_since_doorbell += w; -if (w < cq->budget && -napi_complete_done (&cq->napi, w)) { - arm_bit =SET_ARM_BIT ; - }else { - arm_bit =0 ; +if (w < cq->budget) { +mana_gd_ring_cq (gdma_queue,SET_ARM_BIT ); + cq->work_done_since_doorbell =0 ; +napi_complete_done (&cq->napi, w); + }else if (cq->work_done_since_doorbell > + cq->gdma_cq->queue_size /COMP_ENTRY_SIZE *4 ) { +/* MANA hardware requires at least one doorbell ring every 8 +* wraparounds of CQ even if there is no need to arm the CQ. +* This driver rings the doorbell as soon as we have exceeded +* 4 wraparounds. +*/ +mana_gd_ring_cq (gdma_queue,0 ); + cq->work_done_since_doorbell =0 ; } -mana_gd_ring_cq (gdma_queue, arm_bit); -return w; }
include/net/mana/mana.h +1 -0
@@ -274,6 +274,7 @@ struct mana_cq {/* NAPI data */ struct napi_struct napi;int work_done; +int work_done_since_doorbell;int budget; };
Greg Kroah-Hartman
maintainerPATCH 35/341 wifi: brcmfmac: cfg80211: Handle SSID based pmksa deletion
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Janne Grunau <[email protected]>
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.
--- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 13 +++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +10 -3
@@ -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 ); }
Greg Kroah-Hartman
maintainerPATCH 36/341 fs/netfs/fscache_cookie: add missing "n_accesses" check
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Max Kellermann <[email protected]>
commit f71aa06398aabc2e3eaac25acdf3d62e0094ba70 upstream.
This fixes a NULL pointer dereference bug due to a data race which looks like this:
BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 33 PID: 16573 Comm: kworker/u97:799 Not tainted 6.8.7-cm4all1-hp+ #43 Hardware name: HP ProLiant DL380 Gen9/ProLiant DL380 Gen9, BIOS P89 10/17/2018 Workqueue: events_unbound netfs_rreq_write_to_cache_work RIP: 0010:cachefiles_prepare_write+0x30/0xa0 Code: 57 41 56 45 89 ce 41 55 49 89 cd 41 54 49 89 d4 55 53 48 89 fb 48 83 ec 08 48 8b 47 08 48 83 7f 10 00 48 89 34 24 48 8b 68 20 <48> 8b 45 08 4c 8b 38 74 45 49 8b 7f 50 e8 4e a9 b0 ff 48 8b 73 10 RSP: 0018:ffffb4e78113bde0 EFLAGS: 00010286 RAX: ffff976126be6d10 RBX: ffff97615cdb8438 RCX: 0000000000020000 RDX: ffff97605e6c4c68 RSI: ffff97605e6c4c60 RDI: ffff97615cdb8438 RBP: 0000000000000000 R08: 0000000000278333 R09: 0000000000000001 R10: ffff97605e6c4600 R11: 0000000000000001 R12: ffff97605e6c4c68 R13: 0000000000020000 R14: 0000000000000001 R15: ffff976064fe2c00 FS: 0000000000000000(0000) GS:ffff9776dfd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 000000005942c002 CR4: 00000000001706f0 Call Trace: <TASK> ? __die+0x1f/0x70 ? page_fault_oops+0x15d/0x440 ? search_module_extables+0xe/0x40 ? fixup_exception+0x22/0x2f0 ? exc_page_fault+0x5f/0x100 ? asm_exc_page_fault+0x22/0x30 ? cachefiles_prepare_write+0x30/0xa0 netfs_rreq_write_to_cache_work+0x135/0x2e0 process_one_work+0x137/0x2c0 worker_thread+0x2e9/0x400 ? __pfx_worker_thread+0x10/0x10 kthread+0xcc/0x100 ? __pfx_kthread+0x10/0x10 ret_from_fork+0x30/0x50 ? __pfx_kthread+0x10/0x10 ret_from_fork_asm+0x1b/0x30 </TASK> Modules linked in: CR2: 0000000000000008 ---[ end trace 0000000000000000 ]---
This happened because fscache_cookie_state_machine() was slow and was still running while another process invoked fscache_unuse_cookie(); this led to a fscache_cookie_lru_do_one() call, setting the FSCACHE_COOKIE_DO_LRU_DISCARD flag, which was picked up by fscache_cookie_state_machine(), withdrawing the cookie via cachefiles_withdraw_cookie(), clearing cookie->cache_priv.
At the same time, yet another process invoked cachefiles_prepare_write(), which found a NULL pointer in this code line:
struct cachefiles_object *object = cachefiles_cres_object(cres);
The next line crashes, obviously:
struct cachefiles_cache *cache = object->volume->cache;
During cachefiles_prepare_write(), the "n_accesses" counter is non-zero (via fscache_begin_operation()). The cookie must not be withdrawn until it drops to zero.
The counter is checked by fscache_cookie_state_machine() before switching to FSCACHE_COOKIE_STATE_RELINQUISHING and FSCACHE_COOKIE_STATE_WITHDRAWING (in "case FSCACHE_COOKIE_STATE_FAILED"), but not for FSCACHE_COOKIE_STATE_LRU_DISCARDING ("case FSCACHE_COOKIE_STATE_ACTIVE").
This patch adds the missing check. With a non-zero access counter, the function returns and the next fscache_end_cookie_access() call will queue another fscache_cookie_state_machine() call to handle the still-pending FSCACHE_COOKIE_DO_LRU_DISCARD.
--- fs/fscache/cookie.c | 4 ++++ 1 file changed, 4 insertions(+)
fs/fscache/cookie.c +4 -0
@@ -741,6 +741,10 @@ again_locked:spin_lock (&cookie->lock); }if (test_bit (FSCACHE_COOKIE_DO_LRU_DISCARD , &cookie->flags)) { +if (atomic_read (&cookie->n_accesses) !=0 ) +/* still being accessed: postpone it */ +break ; +__fscache_set_cookie_state (cookie,FSCACHE_COOKIE_STATE_LRU_DISCARDING ); wake = true;
Greg Kroah-Hartman
maintainerPATCH 37/341 selinux: fix potential counting error in avc_add_xperms_decision()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhen Lei <[email protected]>
commit 379d9af3f3da2da1bbfa67baf1820c72a080d1f1 upstream.
The count increases only when a node is successfully added to the linked list.
--- security/selinux/avc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
security/selinux/avc.c +1 -1
@@ -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 ; }
Greg Kroah-Hartman
maintainerPATCH 38/341 selinux: add the processing of the failure of avc_add_xperms_decision()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhen Lei <[email protected]>
commit 6dd1e4c045afa6a4ba5d46f044c83bd357c593c2 upstream.
When avc_add_xperms_decision() fails, the information recorded by the new avc node is incomplete. In this case, the new avc node should be released instead of replacing the old avc node.
--- security/selinux/avc.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
security/selinux/avc.c +5 -1
@@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u3 node->ae.avd.auditdeny &= ~perms;break ;case AVC_CALLBACK_ADD_XPERMS : -avc_add_xperms_decision (node, xpd); + rc =avc_add_xperms_decision (node, xpd); +if (rc) { +avc_node_kill (node); + goto out_unlock; + }break ; }avc_node_replace (node, orig);
Greg Kroah-Hartman
maintainerPATCH 39/341 mm/memory-failure: use raw_spinlock_t in struct memory_failure_cpu
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Waiman Long <[email protected]>
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.
--- mm/memory-failure.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)
mm/memory-failure.c +11 -9
@@ -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(vofor_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); }
Greg Kroah-Hartman
maintainerPATCH 40/341 btrfs: tree-checker: reject BTRFS_FT_UNKNOWN dir type
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qu Wenruo <[email protected]>
commit 31723c9542dba1681cc3720571fdf12ffe0eddd9 upstream.
[REPORT]
There is a bug report that kernel is rejecting a mismatching inode mode and its dir item:
[ 1881.553937] BTRFS critical (device dm-0): inode mode mismatch with dir: inode mode=040700 btrfs type=2 dir type=0
[CAUSE]
It looks like the inode mode is correct, while the dir item type 0 is BTRFS_FT_UNKNOWN, which should not be generated by btrfs at all.
This may be caused by a memory bit flip.
[ENHANCEMENT]
Although tree-checker is not able to do any cross-leaf verification, for this particular case we can at least reject any dir type with BTRFS_FT_UNKNOWN.
So here we enhance the dir type check from [0, BTRFS_FT_MAX), to (0, BTRFS_FT_MAX).
Although the existing corruption can not be fixed just by such enhanced checking, it should prevent the same 0x2->0x0 bitflip for dir type to reach disk in the future.
--- fs/btrfs/tree-checker.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
fs/btrfs/tree-checker.c +3 -2
@@ -548,9 +548,10 @@ static int check_dir_item(struct extent_/* dir type check */ dir_type =btrfs_dir_ftype (leaf, di); -if (unlikely (dir_type >=BTRFS_FT_MAX )) { +if (unlikely (dir_type <=BTRFS_FT_UNKNOWN || + dir_type >=BTRFS_FT_MAX )) {dir_item_err (leaf, slot, -"invalid dir item type, have %u expect [0, %u)" , +"invalid dir item type, have %u expect (0, %u)" , dir_type,BTRFS_FT_MAX );return -EUCLEAN ; }
Greg Kroah-Hartman
maintainerPATCH 41/341 btrfs: zoned: properly take lock to read/update block groups zoned variables
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Naohiro Aota <[email protected]>
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.
--- fs/btrfs/free-space-cache.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-)
fs/btrfs/free-space-cache.c +8 -6
@@ -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 ; }
Greg Kroah-Hartman
maintainerPATCH 42/341 btrfs: tree-checker: add dev extent item checks
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Qu Wenruo <[email protected]>
commit 008e2512dc5696ab2dc5bf264e98a9fe9ceb830e upstream.
[REPORT]
There is a corruption report that btrfs refused to mount a fs that has overlapping dev extents:
BTRFS error (device sdc): dev extent devid 4 physical offset 14263979671552 overlap with previous dev extent end 14263980982272 BTRFS error (device sdc): failed to verify dev extents against chunks: -117
BTRFS error (device sdc): open_ctree failed
[CAUSE]
The direct cause is very obvious, there is a bad dev extent item with incorrect length.
With btrfs check reporting two overlapping extents, the second one shows some clue on the cause:
ERROR: dev extent devid 4 offset 14263979671552 len 6488064 overlap with previous dev extent end 14263980982272
ERROR: dev extent devid 13 offset 2257707008000 len 6488064 overlap with previous dev extent end 2257707270144
ERROR: errors found in extent allocation tree or chunk allocation
The second one looks like a bitflip happened during new chunk allocation:
hex(2257707008000) = 0x20da9d30000 hex(2257707270144) = 0x20da9d70000
diff = 0x00000040000
So it looks like a bitflip happened during new dev extent allocation, resulting the second overlap.
Currently we only do the dev-extent verification at mount time, but if the corruption is caused by memory bitflip, we really want to catch it before writing the corruption to the storage.
Furthermore the dev extent items has the following key definition:
(<device id> DEV_EXTENT <physical offset>)
Thus we can not just rely on the generic key order check to make sure there is no overlapping.
[ENHANCEMENT]
Introduce dedicated dev extent checks, including:
- Fixed member checks
* chunk_tree should always be BTRFS_CHUNK_TREE_OBJECTID (3)
* chunk_objectid should always be BTRFS_FIRST_CHUNK_CHUNK_TREE_OBJECTID (256)
- Alignment checks
* chunk_offset should be aligned to sectorsize
* length should be aligned to sectorsize
* key.offset should be aligned to sectorsize
- Overlap checks
If the previous key is also a dev-extent item, with the same device id, make sure we do not overlap with the previous dev extent.
Reported: Stefan N <[email protected]>
--- fs/btrfs/tree-checker.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 69 insertions(+)
fs/btrfs/tree-checker.c +69 -0
@@ -1671,6 +1671,72 @@ static int check_inode_ref(struct extentreturn 0 ; } +static int check_dev_extent_item (const struct extent_buffer *leaf, +const struct btrfs_key *key, +int slot, +struct btrfs_key *prev_key) +{ +struct btrfs_dev_extent *de; +const u32 sectorsize = leaf->fs_info->sectorsize; + + de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent); +/* Basic fixed member checks. */ +if (unlikely (btrfs_dev_extent_chunk_tree (leaf, de) != +BTRFS_CHUNK_TREE_OBJECTID )) { +generic_err (leaf, slot, +"invalid dev extent chunk tree id, has %llu expect %llu" , +btrfs_dev_extent_chunk_tree (leaf, de), +BTRFS_CHUNK_TREE_OBJECTID ); +return -EUCLEAN ; + } +if (unlikely (btrfs_dev_extent_chunk_objectid (leaf, de) != +BTRFS_FIRST_CHUNK_TREE_OBJECTID )) { +generic_err (leaf, slot, +"invalid dev extent chunk objectid, has %llu expect %llu" , +btrfs_dev_extent_chunk_objectid (leaf, de), +BTRFS_FIRST_CHUNK_TREE_OBJECTID ); +return -EUCLEAN ; + } +/* Alignment check. */ +if (unlikely (!IS_ALIGNED (key->offset, sectorsize))) { +generic_err (leaf, slot, +"invalid dev extent key.offset, has %llu not aligned to %u" , + key->offset, sectorsize); +return -EUCLEAN ; + } +if (unlikely (!IS_ALIGNED (btrfs_dev_extent_chunk_offset (leaf, de), + sectorsize))) { +generic_err (leaf, slot, +"invalid dev extent chunk offset, has %llu not aligned to %u" , +btrfs_dev_extent_chunk_objectid (leaf, de), + sectorsize); +return -EUCLEAN ; + } +if (unlikely (!IS_ALIGNED (btrfs_dev_extent_length (leaf, de), + sectorsize))) { +generic_err (leaf, slot, +"invalid dev extent length, has %llu not aligned to %u" , +btrfs_dev_extent_length (leaf, de), sectorsize); +return -EUCLEAN ; + } +/* Overlap check with previous dev extent. */ +if (slot && prev_key->objectid == key->objectid && + prev_key->type == key->type) { +struct btrfs_dev_extent *prev_de; +u64 prev_len; + + prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent); + prev_len =btrfs_dev_extent_length (leaf, prev_de); +if (unlikely (prev_key->offset + prev_len > key->offset)) { +generic_err (leaf, slot, +"dev extent overlap, prev offset %llu len %llu current offset %llu" , + prev_key->objectid, prev_len, key->offset); +return -EUCLEAN ; + } + } +return 0 ; +} +/* * Common point to switch the item-specific validation. */
@@ -1707,6 +1773,9 @@ static enum btrfs_tree_block_status checcase BTRFS_DEV_ITEM_KEY : ret =check_dev_item (leaf, key, slot);break ; +case BTRFS_DEV_EXTENT_KEY : + ret =check_dev_extent_item (leaf, key, slot, prev_key); +break ;case BTRFS_INODE_ITEM_KEY : ret =check_inode_item (leaf, key, slot);break ;
Greg Kroah-Hartman
maintainerPATCH 43/341 drm/amdgpu: Actually check flags for all context ops.
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Bas Nieuwenhuizen <[email protected]>
commit 0573a1e2ea7e35bff08944a40f1adf2bb35cea61 upstream.
Missing validation ...
Checked libdrm and it clears all the structs, so we should be safe to just check everything.
--- drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +8 -0
@@ -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 :
Greg Kroah-Hartman
maintainerPATCH 17/341 KVM: s390: fix validity interception issue when gisa is switched off
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Mueller <[email protected]>
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+0x70/0x98Last Breaking-Event-Address:
[<000003d9bd3c7f58>] __warn_printk+0xe8/0xf0
Message-ID: <[email protected]>
--- arch/s390/kvm/kvm-s390.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
arch/s390/kvm/kvm-s390.h +6 -1
@@ -249,7 +249,12 @@ static inline unsigned long kvm_s390_getstatic 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 ;
Greg Kroah-Hartman
maintainerPATCH 44/341 memcg_write_event_control(): fix a user-triggerable oops
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Al Viro <[email protected]>
commit 046667c4d3196938e992fba0dfcde570aa85cd0e upstream.
we are *not* guaranteed that anything past the terminating NUL is mapped (let alone initialized with anything sane).
--- mm/memcontrol.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
mm/memcontrol.c +5 -2
@@ -4880,9 +4880,12 @@ static ssize_t memcg_write_event_control buf = endp +1 ; cfd =simple_strtoul (buf, &endp,10 ); -if ((*endp !=' ' ) && (*endp !='\0' )) +if (*endp =='\0' ) + buf = endp; +else if (*endp ==' ' ) + buf = endp +1 ; +else return -EINVAL ; - buf = endp +1 ; event =kzalloc (sizeof (*event),GFP_KERNEL );if (!event)
Greg Kroah-Hartman
maintainerPATCH 45/341 drm/amdgpu/jpeg2: properly set atomics vmid field
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alex Deucher <[email protected]>
commit e414a304f2c5368a84f03ad34d29b89f965a33c9 upstream.
This needs to be set as well if the IB uses atomics.
--- drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +2 -2
@@ -543,11 +543,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct aamdgpu_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 ));
Greg Kroah-Hartman
maintainerPATCH 46/341 drm/amdgpu/jpeg4: properly set atomics vmid field
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alex Deucher <[email protected]>
commit e6c6bd6253e792cee6c5c065e106e87b9f0d9ae9 upstream.
This needs to be set as well if the IB uses atomics.
--- drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c +2 -2
@@ -769,11 +769,11 @@ static void jpeg_v4_0_3_dec_ring_emit_ibamdgpu_ring_write (ring,PACKETJ (regUVD_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 (regUVD_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 (regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,0 ,0 ,PACKETJ_TYPE0 ));
Greg Kroah-Hartman
maintainerPATCH 47/341 s390/uv: Panic for set and remove shared access UVC errors
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Claudio Imbrenda <[email protected]>
[ 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.
Message-ID: <[email protected]>
--- arch/s390/include/asm/uv.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
arch/s390/include/asm/uv.h +4 -1
@@ -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" ); }/*
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 18/341 riscv: change XIPs kernel_map.size to be size of the entire kernel
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nam Cao <[email protected]>
commit 57d76bc51fd80824bcc0c84a5b5ec944f1b51edd upstream.
With XIP kernel, kernel_map.size is set to be only the size of data part of the kernel. This is inconsistent with "normal" kernel, who sets it to be the size of the entire kernel.
More importantly, XIP kernel fails to boot if CONFIG_DEBUG_VIRTUAL is enabled, because there are checks on virtual addresses with the assumption that kernel_map.size is the size of the entire kernel (these checks are in arch/riscv/mm/physaddr.c).
Change XIP's kernel_map.size to be the size of the entire kernel.
--- arch/riscv/mm/init.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
arch/riscv/mm/init.c +2 -2
@@ -912,7 +912,7 @@ static void __init create_kernel_page_ta PMD_SIZE, PAGE_KERNEL_EXEC);/* Map the data in RAM */ - end_va = kernel_map.virt_addr +XIP_OFFSET + kernel_map.size; + end_va = kernel_map.virt_addr + kernel_map.size;for (va = kernel_map.virt_addr +XIP_OFFSET ; va < end_va; va +=PMD_SIZE ) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
@@ -1081,7 +1081,7 @@ asmlinkage void __init setup_vm(uintptr_ phys_ram_base =CONFIG_PHYS_RAM_BASE ; kernel_map.phys_addr = (uintptr_t )CONFIG_PHYS_RAM_BASE ; - kernel_map.size = (uintptr_t )(&_end) - (uintptr_t )(&_sdata); + kernel_map.size = (uintptr_t )(&_end) - (uintptr_t )(&_start); kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;#else
Greg Kroah-Hartman
maintainerPATCH 19/341 i2c: tegra: Do not mark ACPI devices as irq safe
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Breno Leitao <[email protected]>
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.
--- drivers/i2c/busses/i2c-tegra.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/i2c/busses/i2c-tegra.c +2 -2
@@ -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);
Greg Kroah-Hartman
maintainerPATCH 20/341 ACPICA: Add a depth argument to acpi_execute_reg_methods()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
commit cdf65d73e001fde600b18d7e45afadf559425ce5 upstream.
A subsequent change will need to pass a depth argument to acpi_execute_reg_methods(), so prepare that function for it.
No intentional functional changes.
--- drivers/acpi/acpica/acevents.h | 2 +- drivers/acpi/acpica/evregion.c | 6 ++++-- drivers/acpi/acpica/evxfregn.c | 10 +++++++--- drivers/acpi/ec.c | 2 +- include/acpi/acpixf.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-)
drivers/acpi/acpica/acevents.h +1 -1
@@ -188,7 +188,7 @@ acpi_ev_detach_region(union acpi_operand u8 acpi_ns_is_locked);void -acpi_ev_execute_reg_methods (struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods (struct acpi_namespace_node *node,u32 max_depth,acpi_adr_space_type space_id,u32 function); acpi_status
drivers/acpi/acpica/evregion.c +4 -2
@@ -65,6 +65,7 @@ acpi_status acpi_ev_initialize_op_region acpi_gbl_default_address_spaces [i])) {acpi_ev_execute_reg_methods (acpi_gbl_root_node, +ACPI_UINT32_MAX , acpi_gbl_default_address_spaces [i],ACPI_REG_CONNECT ); }
@@ -672,6 +673,7 @@ cleanup1:* FUNCTION: acpi_ev_execute_reg_methods * * PARAMETERS: node - Namespace node for the device +* max_depth - Depth to which search for _REG * space_id - The address space ID * function - Passed to _REG: On (1) or Off (0) *
@@ -683,7 +685,7 @@ cleanup1:******************************************************************************/ void -acpi_ev_execute_reg_methods (struct acpi_namespace_node *node, +acpi_ev_execute_reg_methods (struct acpi_namespace_node *node,u32 max_depth,acpi_adr_space_type space_id,u32 function) {struct acpi_reg_walk_info info;
@@ -717,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_* regions and _REG methods. (i.e. handlers must be installed for all * regions of this Space ID before we can run any _REG methods) */ - (void )acpi_ns_walk_namespace (ACPI_TYPE_ANY , node,ACPI_UINT32_MAX , + (void )acpi_ns_walk_namespace (ACPI_TYPE_ANY , node, max_depth,ACPI_NS_WALK_UNLOCK , acpi_ev_reg_run,NULL , &info,NULL );
drivers/acpi/acpica/evxfregn.c +7 -3
@@ -85,7 +85,8 @@ acpi_install_address_space_handler_inter/* Run all _REG methods for this address space */ if (run_reg) { -acpi_ev_execute_reg_methods (node, space_id,ACPI_REG_CONNECT ); +acpi_ev_execute_reg_methods (node,ACPI_UINT32_MAX , space_id, +ACPI_REG_CONNECT ); } unlock_and_exit:
@@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_s* FUNCTION: acpi_execute_reg_methods * * PARAMETERS: device - Handle for the device +* max_depth - Depth to which search for _REG * space_id - The address space ID * * RETURN: Status
@@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_s* ******************************************************************************/ acpi_status -acpi_execute_reg_methods (acpi_handle device,acpi_adr_space_type space_id) +acpi_execute_reg_methods (acpi_handle device,u32 max_depth, +acpi_adr_space_type space_id) {struct acpi_namespace_node *node;acpi_status status;
@@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle dev/* Run all _REG methods for this address space */ -acpi_ev_execute_reg_methods (node, space_id,ACPI_REG_CONNECT ); +acpi_ev_execute_reg_methods (node, max_depth, space_id, +ACPI_REG_CONNECT ); }else { status =AE_BAD_PARAMETER ; }
drivers/acpi/ec.c +1 -1
@@ -1506,7 +1506,7 @@ 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_ADR_SPACE_EC ); +acpi_execute_reg_methods (scope_handle,ACPI_UINT32_MAX ,ACPI_ADR_SPACE_EC );set_bit (EC_FLAGS_EC_REG_CALLED , &ec->flags); }
include/acpi/acpixf.h +1 -0
@@ -660,6 +660,7 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status void *context)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status acpi_execute_reg_methods(acpi_handle device, + u32 nax_depth, acpi_adr_space_type space_id)) ACPI_EXTERNAL_RETURN_STATUS(acpi_status
Greg Kroah-Hartman
maintainerPATCH 21/341 ACPI: EC: Evaluate _REG outside the EC scope more carefully
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rafael J. Wysocki <[email protected]>
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.
--- drivers/acpi/ec.c | 11 +++++++++-- drivers/acpi/internal.h | 1 + drivers/acpi/scan.c | 2 ++ 3 files changed, 12 insertions(+), 2 deletions(-)
drivers/acpi/ec.c +9 -2
@@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handlstatic 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) {
drivers/acpi/internal.h +1 -0
@@ -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 );
drivers/acpi/scan.c +2 -0
@@ -2198,6 +2198,8 @@ static int acpi_bus_attach(struct acpi_dif (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;
Greg Kroah-Hartman
maintainerPATCH 22/341 arm64: ACPI: NUMA: initialize all values of acpi_early_node_map to NUMA_NO_NODE
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Haibo Xu <[email protected]>
commit a21dcf0ea8566ebbe011c79d6ed08cdfea771de3 upstream.
Currently, only acpi_early_node_map[0] was initialized to NUMA_NO_NODE. To ensure all the values were properly initialized, switch to initialize all of them to NUMA_NO_NODE.
--- arch/arm64/kernel/acpi_numa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
arch/arm64/kernel/acpi_numa.c +1 -1
@@ -27,7 +27,7 @@#include <asm/numa.h> -static int acpi_early_node_map[NR_CPUS ]__initdata = {NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS ]__initdata = { [0 ...NR_CPUS -1 ] =NUMA_NO_NODE };int __init acpi_numa_get_nid (unsigned int cpu) {
Greg Kroah-Hartman
maintainerPATCH 23/341 dm resume: dont return EINVAL when signalled
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Khazhismel Kumykov <[email protected]>
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.
--- drivers/md/dm-ioctl.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-)
drivers/md/dm-ioctl.c +20 -2
@@ -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);
Greg Kroah-Hartman
maintainerPATCH 14/341 thunderbolt: Mark XDomain as unplugged when router is removed
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mika Westerberg <[email protected]>
commit e2006140ad2e01a02ed0aff49cc2ae3ceeb11f8d upstream.
I noticed that when we do discrete host router NVM upgrade and it gets hot-removed from the PCIe side as a result of NVM firmware authentication, if there is another host connected with enabled paths we hang in tearing them down. This is due to fact that the Thunderbolt networking driver also tries to cleanup the paths and ends up blocking in tb_disconnect_xdomain_paths() waiting for the domain lock.
However, at this point we already cleaned the paths in tb_stop() so there is really no need for tb_disconnect_xdomain_paths() to do that anymore. Furthermore it already checks if the XDomain is unplugged and bails out early so take advantage of that and mark the XDomain as unplugged when we remove the parent router.
--- drivers/thunderbolt/switch.c | 1 + 1 file changed, 1 insertion(+)
drivers/thunderbolt/switch.c +1 -0
@@ -3159,6 +3159,7 @@ void tb_switch_remove(struct tb_switch *tb_switch_remove (port->remote->sw); port->remote =NULL ; }else if (port->xdomain) { + port->xdomain->is_unplugged = true;tb_xdomain_remove (port->xdomain); port->xdomain =NULL ; }
Greg Kroah-Hartman
maintainerPATCH 49/341 igc: Fix packet still tx after gate close by reducing i226 MAC retry buffer
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Faizal Rahim <[email protected]>
[ 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.
--- drivers/net/ethernet/intel/igc/igc_defines.h | 6 ++++ drivers/net/ethernet/intel/igc/igc_tsn.c | 34 ++++++++++++++++++++ 2 files changed, 40 insertions(+)
drivers/net/ethernet/intel/igc/igc_defines.h +6 -0
@@ -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.
drivers/net/ethernet/intel/igc/igc_tsn.c +34 -0
@@ -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 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 58/341 net: dsa: vsc73xx: check busy flag in MDIO operations
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pawel Dembicki <[email protected]>
[ Upstream commit fa63c6434b6f6aaf9d8d599dc899bc0a074cc0ad ]
The VSC73xx has a busy flag used during MDIO operations. It is raised when MDIO read/write operations are in progress. Without it, PHYs are misconfigured and bus operations do not work as expected.
--- drivers/net/dsa/vitesse-vsc73xx-core.c | 37 +++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-)
drivers/net/dsa/vitesse-vsc73xx-core.c +36 -1
@@ -38,6 +38,10 @@#define VSC73XX_BLOCK_ARBITER 0x5/* Only subblock 0 */ #define VSC73XX_BLOCK_SYSTEM 0x7/* Only subblock 0 */ +/* MII Block subblock */ +#define VSC73XX_BLOCK_MII_INTERNAL 0x0/* Internal MDIO subblock */ +#define VSC73XX_BLOCK_MII_EXTERNAL 0x1/* External MDIO subblock */ +#define CPU_PORT 6/* CPU port */ /* MAC Block registers */
@@ -196,6 +200,8 @@#define VSC73XX_MII_CMD 0x1#define VSC73XX_MII_DATA 0x2 +#define VSC73XX_MII_STAT_BUSY BIT(3) +/* Arbiter block 5 registers */ #define VSC73XX_ARBEMPTY 0x0c#define VSC73XX_ARBDISC 0x0e
@@ -270,6 +276,7 @@#define IS_739X (a) (IS_7395(a) || IS_7398(a))#define VSC73XX_POLL_SLEEP_US 1000 +#define VSC73XX_MDIO_POLL_SLEEP_US 5#define VSC73XX_POLL_TIMEOUT_US 10000struct vsc73xx_counter {
@@ -487,6 +494,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc)return 0 ; } +static int vsc73xx_mdio_busy_check (struct vsc73xx *vsc) +{ +int ret, err; +u32 val; + + ret =read_poll_timeout (vsc73xx_read, err, + err <0 || !(val &VSC73XX_MII_STAT_BUSY ), +VSC73XX_MDIO_POLL_SLEEP_US , +VSC73XX_POLL_TIMEOUT_US , false, vsc, +VSC73XX_BLOCK_MII ,VSC73XX_BLOCK_MII_INTERNAL , +VSC73XX_MII_STAT , &val); +if (ret) +return ret; +return err; +} +static int vsc73xx_phy_read (struct dsa_switch *ds,int phy,int regnum) {struct vsc73xx *vsc = ds->priv;
@@ -494,12 +517,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)u32 val;int ret; + ret =vsc73xx_mdio_busy_check (vsc); +if (ret) +return ret; +/* Setting bit 26 means "read" */ cmd =BIT (26 ) | (phy <<21 ) | (regnum <<16 ); ret =vsc73xx_write (vsc,VSC73XX_BLOCK_MII ,0 ,1 , cmd);if (ret)return ret; -msleep (2 ); + + ret =vsc73xx_mdio_busy_check (vsc); +if (ret) +return ret; + ret =vsc73xx_read (vsc,VSC73XX_BLOCK_MII ,0 ,2 , &val);if (ret)return ret;
@@ -523,6 +554,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,u32 cmd;int ret; + ret =vsc73xx_mdio_busy_check (vsc); +if (ret) +return ret; +/* It was found through tedious experiments that this router * chip really hates to have it's PHYs reset. They * never recover if that happens: autonegotiation stops
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 59/341 net: ethernet: mtk_wed: fix use-after-free panic in mtk_wed_setup_tc_block_cb()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zheng Zhang <[email protected]>
[ 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
...
---------
--- drivers/net/ethernet/mediatek/mtk_wed.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/net/ethernet/mediatek/mtk_wed.c +4 -2
@@ -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 :
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 60/341 mlxbf_gige: disable RX filters until RX path initialized
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Thompson <[email protected]>
[ Upstream commit df934abb185c71c9f2fa07a5013672d0cbd36560 ]
A recent change to the driver exposed a bug where the MAC RX filters (unicast MAC, broadcast MAC, and multicast MAC) are configured and enabled before the RX path is fully initialized. The result of this bug is that after the PHY is started packets that match these MAC RX filters start to flow into the RX FIFO. And then, after rx_init() is completed, these packets will go into the driver RX ring as well. If enough packets are received to fill the RX ring (default size is 128 packets) before the call to request_irq() completes, the driver RX function becomes stuck.
This bug is intermittent but is most likely to be seen where the oob_net0 interface is connected to a busy network with lots of broadcast and multicast traffic.
All the MAC RX filters must be disabled until the RX path is ready, i.e. all initialization is done and all the IRQs are installed.
--- .../ethernet/mellanox/mlxbf_gige/mlxbf_gige.h | 8 +++ .../mellanox/mlxbf_gige/mlxbf_gige_main.c | 10 ++++ .../mellanox/mlxbf_gige/mlxbf_gige_regs.h | 2 + .../mellanox/mlxbf_gige/mlxbf_gige_rx.c | 50 ++++++++++++++++--- 4 files changed, 64 insertions(+), 6 deletions(-)
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h +8 -0
@@ -40,6 +40,7 @@*/ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0#define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1 +#define MLXBF_GIGE_MAX_FILTER_IDX 3/* Define for broadcast MAC literal */ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF
@@ -175,6 +176,13 @@ enum mlxbf_gige_res {int mlxbf_gige_mdio_probe (struct platform_device *pdev,struct mlxbf_gige *priv);void mlxbf_gige_mdio_remove (struct mlxbf_gige *priv); + +void mlxbf_gige_enable_multicast_rx (struct mlxbf_gige *priv); +void mlxbf_gige_disable_multicast_rx (struct mlxbf_gige *priv); +void mlxbf_gige_enable_mac_rx_filter (struct mlxbf_gige *priv, +unsigned int index); +void mlxbf_gige_disable_mac_rx_filter (struct mlxbf_gige *priv, +unsigned int index);void mlxbf_gige_set_mac_rx_filter (struct mlxbf_gige *priv,unsigned int index,u64 dmac); void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c +10 -0
@@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev)if (err) goto napi_deinit; +mlxbf_gige_enable_mac_rx_filter (priv,MLXBF_GIGE_BCAST_MAC_FILTER_IDX ); +mlxbf_gige_enable_mac_rx_filter (priv,MLXBF_GIGE_LOCAL_MAC_FILTER_IDX ); +mlxbf_gige_enable_multicast_rx (priv); +/* Set bits in INT_EN that we care about */ int_en =MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR | MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS |
@@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)void __iomem *plu_base;void __iomem *base;int addr, phy_irq; +unsigned int i;int err; base =devm_platform_ioremap_resource (pdev,MLXBF_GIGE_RES_MAC );
@@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev) priv->rx_q_entries =MLXBF_GIGE_DEFAULT_RXQ_SZ ; priv->tx_q_entries =MLXBF_GIGE_DEFAULT_TXQ_SZ ; +for (i =0 ; i <=MLXBF_GIGE_MAX_FILTER_IDX ; i++) +mlxbf_gige_disable_mac_rx_filter (priv, i); +mlxbf_gige_disable_multicast_rx (priv); +mlxbf_gige_disable_promisc (priv); +/* Write initial MAC address to hardware */ mlxbf_gige_initial_mac (priv);
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h +2 -0
@@ -62,6 +62,8 @@#define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1)#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520#define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528 +#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530 +#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1)#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0)#define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548
drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c +44 -6
65 lines not on this page · raw message
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 61/341 mptcp: correct MPTCP_SUBFLOW_ATTR_SSN_OFFSET reserved size
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eugene Syromiatnikov <[email protected]>
[ 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.
--- net/mptcp/diag.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/mptcp/diag.c +1 -1
@@ -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 */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 62/341 tcp: Update window clamping condition
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Subash Abhinov Kasiviswanathan <[email protected]>
[ Upstream commit a2cbb1603943281a604f5adc48079a148db5cb0d ]
This patch is based on the discussions between Neal Cardwell and Eric Dumazet in the link
https://lore.kernel.org/netdev/[email protected]/
It was correctly pointed out that tp->window_clamp would not be updated in cases where net.ipv4.tcp_moderate_rcvbuf=0 or if (copied <= tp->rcvq_space.space). While it is expected for most setups to leave the sysctl enabled, the latter condition may not end up hitting depending on the TCP receive queue size and the pattern of arriving data.
The updated check should be hit only on initial MSS update from TCP_MIN_MSS to measured MSS value and subsequently if there was an update to a larger value.
--- net/ipv4/tcp_input.c | 28 ++++++++++++---------------- 1 file changed, 12 insertions(+), 16 deletions(-)
net/ipv4/tcp_input.c +12 -16
@@ -243,9 +243,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)*/ if (unlikely (len != icsk->icsk_ack.rcv_mss)) {u64 val = (u64 )skb->len <<TCP_RMEM_TO_WIN_SCALE ; +u8 old_ratio =tcp_sk (sk)->scaling_ratio;do_div (val, skb->truesize);tcp_sk (sk)->scaling_ratio = val ? val :1 ; + +if (old_ratio !=tcp_sk (sk)->scaling_ratio) +WRITE_ONCE (tcp_sk (sk)->window_clamp, +tcp_win_from_space (sk, sk->sk_rcvbuf)); } icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,tcp_sk (sk)->advmss);
@@ -748,7 +753,8 @@ void tcp_rcv_space_adjust(struct sock *sk)* <prev RTT . ><current RTT .. ><next RTT .... > */ -if (READ_ONCE (sock_net (sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) { +if (READ_ONCE (sock_net (sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && + !(sk->sk_userlocks &SOCK_RCVBUF_LOCK )) {u64 rcvwin, grow;int rcvbuf;
@@ -764,22 +770,12 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf =min_t (u64,tcp_space_from_win (sk, rcvwin),READ_ONCE (sock_net (sk)->ipv4.sysctl_tcp_rmem[2 ])); -if (!(sk->sk_userlocks &SOCK_RCVBUF_LOCK )) { -if (rcvbuf > sk->sk_rcvbuf) { -WRITE_ONCE (sk->sk_rcvbuf, rcvbuf); - -/* Make the window clamp follow along. */ -WRITE_ONCE (tp->window_clamp, -tcp_win_from_space (sk, rcvbuf)); - } - }else { -/* Make the window clamp follow along while being bounded -* by SO_RCVBUF. -*/ -int clamp =tcp_win_from_space (sk,min (rcvbuf, sk->sk_rcvbuf)); +if (rcvbuf > sk->sk_rcvbuf) { +WRITE_ONCE (sk->sk_rcvbuf, rcvbuf); -if (clamp > tp->window_clamp) -WRITE_ONCE (tp->window_clamp, clamp); +/* Make the window clamp follow along. */ +WRITE_ONCE (tp->window_clamp, +tcp_win_from_space (sk, rcvbuf)); } } tp->rcvq_space.space = copied;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 63/341 netfilter: allow ipv6 fragments to arrive on different devices
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tom Hughes <[email protected]>
[ 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.
--- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++++ 1 file changed, 4 insertions(+)
net/ipv6/netfilter/nf_conntrack_reasm.c +4 -0
@@ -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 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 64/341 netfilter: flowtable: initialise extack before use
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Donald Hunter <[email protected]>
[ Upstream commit e9767137308daf906496613fd879808a07f006a2 ]
Fix missing initialisation of extack in flow offload.
--- net/netfilter/nf_flow_table_offload.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/nf_flow_table_offload.c +1 -1
@@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, struct list_head *block_cb_list) {struct flow_cls_offload cls_flow = {}; +struct netlink_ext_ack extack = {};struct flow_block_cb *block_cb; -struct netlink_ext_ack extack;__be16 proto =ETH_P_ALL ;int err, i =0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 65/341 netfilter: nf_queue: drop packets with cloned unconfirmed conntracks
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Florian Westphal <[email protected]>
[ 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.
--- net/bridge/br_netfilter_hooks.c | 6 +++++- net/netfilter/nfnetlink_queue.c | 35 +++++++++++++++++++++++++++++++-- 2 files changed, 38 insertions(+), 3 deletions(-)
net/bridge/br_netfilter_hooks.c +5 -1
@@ -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.
net/netfilter/nfnetlink_queue.c +33 -2
@@ -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; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 66/341 netfilter: nf_tables: Audit log dump reset after the fact
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit e0b6648b0446e59522819c75ba1dcb09e68d3e94 ]
In theory, dumpreset may fail and invalidate the preceeding log message. Fix this and use the occasion to prepare for object reset locking, which benefits from a few unrelated changes:
* Add an early call to nfnetlink_unicast if not resetting which effectively skips the audit logging but also unindents it.
* Extract the table's name from the netlink attribute (which is verified via earlier table lookup) to not rely upon validity of the looked up table pointer.
* Do not use local variable family, it will vanish.
--- net/netfilter/nf_tables_api.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-)
net/netfilter/nf_tables_api.c +13 -15
@@ -7832,6 +7832,7 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)static int nf_tables_getobj (struct sk_buff *skb,const struct nfnl_info *info,const struct nlattr *const nla[]) { +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;
@@ -7841,6 +7842,7 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,struct sk_buff *skb2;bool reset = false;u32 objtype; +char *buf;int err;if (info->nlh->nlmsg_flags &NLM_F_DUMP ) {
@@ -7879,27 +7881,23 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,if (NFNL_MSG_TYPE (info->nlh->nlmsg_type) ==NFT_MSG_GETOBJ_RESET ) reset = true; -if (reset) { -const struct nftables_pernet *nft_net; -char *buf; - - nft_net =nft_pernet (net); - buf =kasprintf (GFP_ATOMIC ,"%s:%u" , table->name, nft_net->base_seq); - -audit_log_nfcfg (buf, - family, -1 , -AUDIT_NFT_OP_OBJ_RESET , -GFP_ATOMIC ); -kfree (buf); - } - 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; +if (!reset) +return nfnetlink_unicast (skb2, net,NETLINK_CB (skb).portid); + + buf =kasprintf (GFP_ATOMIC ,"%.*s:%u" , +nla_len (nla[NFTA_OBJ_TABLE ]), + (char *)nla_data (nla[NFTA_OBJ_TABLE ]), + nft_net->base_seq); +audit_log_nfcfg (buf, info->nfmsg->nfgen_family,1 , +AUDIT_NFT_OP_OBJ_RESET ,GFP_ATOMIC ); +kfree (buf); +return nfnetlink_unicast (skb2, net,NETLINK_CB (skb).portid); err_fill_obj_info:
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 67/341 netfilter: nf_tables: Drop pointless memset in nf_tables_dump_obj
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit ff16111cc10c82ee065ffbd9fa8d6210394ff8c6 ]
The code does not make use of cb->args fields past the first one, no need to zero them.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 3 --- 1 file changed, 3 deletions(-)
net/netfilter/nf_tables_api.c +0 -3
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 50/341 igc: Fix qbv_config_change_errors logics
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Faizal Rahim <[email protected]>
[ Upstream commit f8d6acaee9d35cbff3c3cfad94641666c596f8da ]
When user issues these cmds:
1. Either a) or b)
a) mqprio with hardware offload disabled
b) taprio with txtime-assist feature enabled
2. etf
3. tc qdisc delete
4. taprio with base time in the past
At step 4, qbv_config_change_errors wrongly increased by 1.
Excerpt from IEEE 802.1Q-2018 8.6.9.3.1:
"If AdminBaseTime specifies a time in the past, and the current schedule is running, then: Increment ConfigChangeError counter"
qbv_config_change_errors should only increase if base time is in the past and no taprio is active. In user perspective, taprio was not active when first triggered at step 4. However, i225/6 reuses qbv for etf, so qbv is enabled with a dummy schedule at step 2 where it enters igc_tsn_enable_offload() and qbv_count got incremented to 1. At step 4, it enters igc_tsn_enable_offload() again, qbv_count is incremented to 2. Because taprio is running, tc_setup_type is TC_SETUP_QDISC_ETF and qbv_count > 1, qbv_config_change_errors value got incremented.
This issue happens due to reliance on qbv_count field where a non-zero value indicates that taprio is running. But qbv_count increases regardless if taprio is triggered by user or by other tsn feature. It does not align with qbv_config_change_errors expectation where it is only concerned with taprio triggered by user.
Fixing this by relocating the qbv_config_change_errors logic to igc_save_qbv_schedule(), eliminating reliance on qbv_count and its inaccuracies from i225/6's multiple uses of qbv feature for other TSN features.
The new function created: igc_tsn_is_taprio_activated_by_user() uses taprio_offload_enable field to indicate that the current running taprio was triggered by user, instead of triggered by non-qbv feature like etf.
--- drivers/net/ethernet/intel/igc/igc_main.c | 8 ++++++-- drivers/net/ethernet/intel/igc/igc_tsn.c | 16 ++++++++-------- drivers/net/ethernet/intel/igc/igc_tsn.h | 1 + 3 files changed, 15 insertions(+), 10 deletions(-)
drivers/net/ethernet/intel/igc/igc_main.c +6 -2
@@ -6217,12 +6217,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,if (!validate_schedule (adapter, qopt))return -EINVAL ; +igc_ptp_read (adapter, &now); + +if (igc_tsn_is_taprio_activated_by_user (adapter) && +is_base_time_past (qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; -igc_ptp_read (adapter, &now); -for (n =0 ; n < qopt->num_entries; n++) {struct tc_taprio_sched_entry *e = &qopt->entries[n];
drivers/net/ethernet/intel/igc/igc_tsn.c +8 -8
@@ -87,6 +87,14 @@ static void igc_tsn_restore_retx_default(struct igc_adapter *adapter)wr32 (IGC_RETX_CTL , retxctl); } +bool igc_tsn_is_taprio_activated_by_user (struct igc_adapter *adapter) +{ +struct igc_hw *hw = &adapter->hw; + +return (rd32 (IGC_BASET_H ) ||rd32 (IGC_BASET_L )) && + adapter->taprio_offload_enable; +} +/* Returns the TSN specific registers to their default values after * the adapter is reset. */
@@ -296,14 +304,6 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)s64 n =div64_s64 (ktime_sub_ns (systim, base_time), cycle); base_time =ktime_add_ns (base_time, (n +1 ) * cycle); - -/* Increase the counter if scheduling into the past while -* Gate Control List (GCL) is running. -*/ -if ((rd32 (IGC_BASET_H ) ||rd32 (IGC_BASET_L )) && - (adapter->tc_setup_type ==TC_SETUP_QDISC_TAPRIO ) && - (adapter->qbv_count >1 )) - adapter->qbv_config_change_errors++; }else {if (igc_is_device_id_i226 (hw)) {ktime_t adjust_time, expires_time;
drivers/net/ethernet/intel/igc/igc_tsn.h +1 -0
@@ -7,5 +7,6 @@int igc_tsn_offload_apply (struct igc_adapter *adapter);int igc_tsn_reset (struct igc_adapter *adapter);void igc_tsn_adjust_txtime_offset (struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user (struct igc_adapter *adapter);#endif /* _IGC_BASE_H */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 68/341 netfilter: nf_tables: Unconditionally allocate nft_obj_filter
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit 4279cc60b354d2d2b970655a70a151cbfa1d958b ]
Prep work for moving the filter into struct netlink_callback's scratch area.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 36 +++++++++++++++-------------------- 1 file changed, 15 insertions(+), 21 deletions(-)
net/netfilter/nf_tables_api.c +15 -21
@@ -7753,11 +7753,9 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) goto cont;if (idx < s_idx) goto cont; -if (filter && filter->table && -strcmp (filter->table, table->name)) +if (filter->table &&strcmp (filter->table, table->name)) goto cont; -if (filter && - filter->type !=NFT_OBJECT_UNSPEC && +if (filter->type !=NFT_OBJECT_UNSPEC && obj->ops->type->type != filter->type) goto cont;
@@ -7792,23 +7790,21 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)const struct nlattr *const *nla = cb->data;struct nft_obj_filter *filter =NULL ; -if (nla[NFTA_OBJ_TABLE ] || nla[NFTA_OBJ_TYPE ]) { - filter =kzalloc (sizeof (*filter),GFP_ATOMIC ); -if (!filter) -return -ENOMEM ; + filter =kzalloc (sizeof (*filter),GFP_ATOMIC ); +if (!filter) +return -ENOMEM ; -if (nla[NFTA_OBJ_TABLE ]) { - filter->table =nla_strdup (nla[NFTA_OBJ_TABLE ],GFP_ATOMIC ); -if (!filter->table) { -kfree (filter); -return -ENOMEM ; - } +if (nla[NFTA_OBJ_TABLE ]) { + filter->table =nla_strdup (nla[NFTA_OBJ_TABLE ],GFP_ATOMIC ); +if (!filter->table) { +kfree (filter); +return -ENOMEM ; } - -if (nla[NFTA_OBJ_TYPE ]) - filter->type =ntohl (nla_get_be32 (nla[NFTA_OBJ_TYPE ])); } +if (nla[NFTA_OBJ_TYPE ]) + filter->type =ntohl (nla_get_be32 (nla[NFTA_OBJ_TYPE ])); + cb->data = filter;return 0 ; }
@@ -7817,10 +7813,8 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb) {struct nft_obj_filter *filter = cb->data; -if (filter) { -kfree (filter->table); -kfree (filter); - } +kfree (filter->table); +kfree (filter);return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 69/341 netfilter: nf_tables: A better name for nft_obj_filter
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit ecf49cad807061d880bea27a5da8e0114ddc7690 ]
Name it for what it is supposed to become, a real nft_obj_dump_ctx. No functional change intended.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-)
net/netfilter/nf_tables_api.c +16 -16
@@ -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 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 70/341 netfilter: nf_tables: Carry s_idx in nft_obj_dump_ctx
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit 2eda95cfa2fc43bcb21a801dc1d16a0b7cc73860 ]
Prep work for moving the context into struct netlink_callback scratch area.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
net/netfilter/nf_tables_api.c +5 -4
@@ -7718,6 +7718,7 @@ static void audit_log_obj_reset(const struct nft_table *table, }struct nft_obj_dump_ctx { +unsigned int s_idx;char *table;u32 type; };
@@ -7725,14 +7726,14 @@ 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); -const struct nft_table *table; -unsigned int idx =0 , s_idx = cb->args[0 ];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; +const struct nft_table *table;unsigned int entries =0 ;struct nft_object *obj; +unsigned int idx =0 ;bool reset = false;int rc =0 ;
@@ -7751,7 +7752,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)list_for_each_entry_rcu (obj, &table->objects, list) {if (!nft_is_active (net, obj)) goto cont; -if (idx < s_idx) +if (idx < ctx->s_idx) goto cont;if (ctx->table &&strcmp (ctx->table, table->name)) goto cont;
@@ -7781,7 +7782,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) }rcu_read_unlock (); - cb->args[0 ] = idx; + ctx->s_idx = idx;return skb->len; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 71/341 netfilter: nf_tables: nft_obj_filter fits into cb->ctx
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit 5a893b9cdf6fa5758f43d323a1d7fa6d1bf489ff ]
No need to allocate it if one may just use struct netlink_callback's scratch area for it.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)
net/netfilter/nf_tables_api.c +5 -11
@@ -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 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 72/341 netfilter: nf_tables: Carry reset boolean in nft_obj_dump_ctx
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit a552339063d37b3b1133d9dfc31f851edafb27bb ]
Relieve the dump callback from having to inspect nlmsg_type upon each call, just do it once at start of the dump.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
net/netfilter/nf_tables_api.c +6 -6
@@ -7721,6 +7721,7 @@ struct nft_obj_dump_ctx {unsigned int s_idx;char *table;u32 type; +bool reset; };static int nf_tables_dump_obj (struct sk_buff *skb,struct netlink_callback *cb)
@@ -7734,12 +7735,8 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)unsigned int entries =0 ;struct nft_object *obj;unsigned int idx =0 ; -bool reset = false;int rc =0 ; -if (NFNL_MSG_TYPE (cb->nlh->nlmsg_type) ==NFT_MSG_GETOBJ_RESET ) - reset = true; -rcu_read_lock (); nft_net =nft_pernet (net); cb->seq =READ_ONCE (nft_net->base_seq);
@@ -7766,7 +7763,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)NFT_MSG_NEWOBJ ,NLM_F_MULTI |NLM_F_APPEND , table->family, table, - obj, reset); + obj, ctx->reset);if (rc <0 )break ;
@@ -7775,7 +7772,7 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb) cont: idx++; } -if (reset && entries) +if (ctx->reset && entries)audit_log_obj_reset (table, nft_net->base_seq, entries);if (rc <0 )break ;
@@ -7802,6 +7799,9 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)if (nla[NFTA_OBJ_TYPE ]) ctx->type =ntohl (nla_get_be32 (nla[NFTA_OBJ_TYPE ])); +if (NFNL_MSG_TYPE (cb->nlh->nlmsg_type) ==NFT_MSG_GETOBJ_RESET ) + ctx->reset = true; +return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 73/341 netfilter: nf_tables: Introduce nf_tables_getobj_single
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit 69fc3e9e90f1afc11f4015e6b75d18ab9acee348 ]
Outsource the reply skb preparation for non-dump getrule requests into a distinct function. Prep work for object reset locking.
Stable-dep-of: bd662c4218f9 ("netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests")
--- net/netfilter/nf_tables_api.c | 75 ++++++++++++++++++++--------------- 1 file changed, 44 insertions(+), 31 deletions(-)
net/netfilter/nf_tables_api.c +44 -31
@@ -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)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 74/341 netfilter: nf_tables: Add locking for NFT_MSG_GETOBJ_RESET requests
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Phil Sutter <[email protected]>
[ Upstream commit bd662c4218f9648e888bebde9468146965f3f8a0 ]
Objects' dump callbacks are not concurrency-safe per-se with reset bit set. If two CPUs perform a reset at the same time, at least counter and quota objects suffer from value underrun.
Prevent this by introducing dedicated locking callbacks for nfnetlink and the asynchronous dump handling to serialize access.
--- net/netfilter/nf_tables_api.c | 72 ++++++++++++++++++++++++++++------- 1 file changed, 59 insertions(+), 13 deletions(-)
net/netfilter/nf_tables_api.c +59 -13
@@ -7783,6 +7783,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)return skb->len; } +static int nf_tables_dumpreset_obj (struct sk_buff *skb, +struct netlink_callback *cb) +{ +struct nftables_pernet *nft_net =nft_pernet (sock_net (skb->sk)); +int ret; + +mutex_lock (&nft_net->commit_mutex); + ret =nf_tables_dump_obj (skb, cb); +mutex_unlock (&nft_net->commit_mutex); + +return ret; +} +static int nf_tables_dump_obj_start (struct netlink_callback *cb) {struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -7799,12 +7812,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)if (nla[NFTA_OBJ_TYPE ]) ctx->type =ntohl (nla_get_be32 (nla[NFTA_OBJ_TYPE ])); -if (NFNL_MSG_TYPE (cb->nlh->nlmsg_type) ==NFT_MSG_GETOBJ_RESET ) - ctx->reset = true; -return 0 ; } +static int nf_tables_dumpreset_obj_start (struct netlink_callback *cb) +{ +struct nft_obj_dump_ctx *ctx = (void *)cb->ctx; + + ctx->reset = true; + +return nf_tables_dump_obj_start (cb); +} +static int nf_tables_dump_obj_done (struct netlink_callback *cb) {struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
@@ -7863,18 +7882,43 @@ nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,static int nf_tables_getobj (struct sk_buff *skb,const struct nfnl_info *info,const struct nlattr *const nla[]) +{ +u32 portid =NETLINK_CB (skb).portid; +struct sk_buff *skb2; + +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); + } + + skb2 =nf_tables_getobj_single (portid, info, nla, false); +if (IS_ERR (skb2)) +return PTR_ERR (skb2); + +return nfnetlink_unicast (skb2, info->net, portid); +} + +static int nf_tables_getobj_reset (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, + .start = nf_tables_dumpreset_obj_start, + .dump = nf_tables_dumpreset_obj, .done = nf_tables_dump_obj_done, .module =THIS_MODULE , .data = (void *)nla,
@@ -7883,16 +7927,18 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,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; +if (!try_module_get (THIS_MODULE )) +return -EINVAL ; +rcu_read_unlock (); +mutex_lock (&nft_net->commit_mutex); + skb2 =nf_tables_getobj_single (portid, info, nla, true); +mutex_unlock (&nft_net->commit_mutex); +rcu_read_lock (); +module_put (THIS_MODULE ); - 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); - buf = kasprintf(GFP_ATOMIC, "%.*s:%u", nla_len(nla[NFTA_OBJ_TABLE]), (char *)nla_data(nla[NFTA_OBJ_TABLE]),
@@ -9179,7 +9225,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .policy = nft_obj_policy, }, [NFT_MSG_GETOBJ_RESET] = { - .call = nf_tables_getobj, + .call = nf_tables_getobj_reset, .type = NFNL_CB_RCU, .attr_count = NFTA_OBJ_MAX, .policy = nft_obj_policy,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 75/341 vsock: fix recursive ->recvmsg calls
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cong Wang <[email protected]>
[ 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().
--- 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(-)
include/net/af_vsock.h +4 -0
@@ -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);
net/vmw_vsock/af_vsock.c +29 -21
89 lines not on this page · raw message
net/vmw_vsock/vsock_bpf.c +2 -2
@@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, intint 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 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 76/341 selftests: net: lib: ignore possible errors
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
[ Upstream commit 7e0620bc6a5ec6b340a0be40054f294ca26c010f ]
No need to disable errexit temporary, simply ignore the only possible and not handled error.
Stable-dep-of: 7965a7f32a53 ("selftests: net: lib: kill PIDs before del netns")
--- tools/testing/selftests/net/lib.sh | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-)
tools/testing/selftests/net/lib.sh +1 -9
@@ -38,25 +38,17 @@ busywait() cleanup_ns() { local ns="" - local errexit=0 local ret=0 - # disable errexit temporary - if [[ $- =~ "e" ]]; then - errexit=1 - set +e - fi - for ns in "$@"; do [ -z "${ns}" ] && continue - ip netns delete "${ns}" &> /dev/null + 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" ret=1 fi done - [ $errexit -eq 1 ] && set -e return $ret }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 77/341 selftests: net: lib: kill PIDs before del netns
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Matthieu Baerts (NGI0) <[email protected]>
[ Upstream commit 7965a7f32a53d9ad807ce2c53bdda69ba104974f ]
When deleting netns, it is possible to still have some tasks running, e.g. background tasks like tcpdump running in the background, not stopped because the test has been interrupted.
Before deleting the netns, it is then safer to kill all attached PIDs, if any. That should reduce some noises after the end of some tests, and help with the debugging of some issues. That's why this modification is seen as a "fix".
--- tools/testing/selftests/net/lib.sh | 1 + 1 file changed, 1 insertion(+)
tools/testing/selftests/net/lib.sh +1 -0
@@ -42,6 +42,7 @@ cleanup_ns() for ns in "$@"; 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"
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 51/341 igc: Fix reset adapter logics when tx mode change
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Faizal Rahim <[email protected]>
[ 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.
--- drivers/net/ethernet/intel/igc/igc_tsn.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/igc/igc_tsn.c +19 -5
@@ -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 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 78/341 net: hns3: fix wrong use of semaphore up
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jie Wang <[email protected]>
[ Upstream commit 8445d9d3c03101859663d34fda747f6a50947556 ]
Currently, if hns3 PF or VF FLR reset failed after five times retry, the reset done process will directly release the semaphore which has already released in hclge_reset_prepare_general. This will cause down operation fail.
So this patch fixes it by adding reset state judgement. The up operation is only called after successful PF FLR reset.
--- drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 4 ++-- drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +2 -2
@@ -11430,8 +11430,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev)dev_err (&hdev->pdev->dev,"fail to rebuild, ret=%d\n" , ret); hdev->reset_type =HNAE3_NONE_RESET ; -clear_bit (HCLGE_STATE_RST_HANDLING , &hdev->state); -up (&hdev->reset_sem); +if (test_and_clear_bit (HCLGE_STATE_RST_HANDLING , &hdev->state)) +up (&hdev->reset_sem); }static void hclge_clear_resetting_state (struct hclge_dev *hdev)
drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +2 -2
@@ -1710,8 +1710,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev) ret); hdev->reset_type =HNAE3_NONE_RESET ; -clear_bit (HCLGEVF_STATE_RST_HANDLING , &hdev->state); -up (&hdev->reset_sem); +if (test_and_clear_bit (HCLGEVF_STATE_RST_HANDLING , &hdev->state)) +up (&hdev->reset_sem); }static u32 hclgevf_get_fw_version (struct hnae3_handle *handle)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 79/341 net: hns3: use the users cfg after reset
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Peiyang Wang <[email protected]>
[ 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 vThis patch save new speed if hw change speed successfully, which will be used after reset successfully.
--- .../hisilicon/hns3/hns3pf/hclge_main.c | 24 ++++++++++++++----- .../hisilicon/hns3/hns3pf/hclge_mdio.c | 3 +++ 2 files changed, 21 insertions(+), 6 deletions(-)
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +18 -6
@@ -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 )) {
drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +3 -0
@@ -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" );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 80/341 net: hns3: fix a deadlock problem when config TC during resetting
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jie Wang <[email protected]>
[ Upstream commit be5e816d00a506719e9dbb1a9c861c5ced30a109 ]
When config TC during the reset process, may cause a deadlock, the flow is as below:
pf reset start
│
▼
......
setup tc │
│ ▼
▼ DOWN: napi_disable()
napi_disable()(skip) │
│ │
▼ ▼
...... ......
│ │
▼ │
napi_enable() │
▼
UINIT: netif_napi_del()
│
▼
......
│
▼
INIT: netif_napi_add()
│
▼
...... global reset start
│ │
▼ ▼
UP: napi_enable()(skip) ......
│ │
▼ ▼
...... napi_disable()In reset process, the driver will DOWN the port and then UINIT, in this case, the setup tc process will UP the port before UINIT, so cause the problem. Adds a DOWN process in UINIT to fix it.
--- drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +3 -0
@@ -5729,6 +5729,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)struct net_device *netdev = handle->kinfo.netdev;struct hns3_nic_priv *priv =netdev_priv (netdev); +if (!test_bit (HNS3_NIC_STATE_DOWN , &priv->state)) +hns3_nic_net_stop (netdev); +if (!test_and_clear_bit (HNS3_NIC_STATE_INITED , &priv->state)) {netdev_warn (netdev,"already uninitialized\n" );return 0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 81/341 gpio: mlxbf3: Support shutdown() function
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Asmaa Mnebhi <[email protected]>
[ 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().
--- drivers/gpio/gpio-mlxbf3.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+)
drivers/gpio/gpio-mlxbf3.c +14 -0
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 52/341 net/mlx5e: Take state lock during tx timeout reporter
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dragos Tatulea <[email protected]>
[ Upstream commit e6b5afd30b99b43682a7764e1a74a42fe4d5f4b3 ]
mlx5e_safe_reopen_channels() requires the state lock taken. The referenced changed in the Fixes tag removed the lock to fix another issue. This patch adds it back but at a later point (when calling mlx5e_safe_reopen_channels()) to avoid the deadlock referenced in the Fixes tag.
--- drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +2 -0
@@ -149,7 +149,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)return err; } +mutex_lock (&priv->state_lock); err =mlx5e_safe_reopen_channels (priv); +mutex_unlock (&priv->state_lock);if (!err) { to_ctx->status =1 ;/* all channels recovered */ return err;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 53/341 net/mlx5e: Correctly report errors for ethtool rx flows
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Cosmin Ratiu <[email protected]>
[ 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.
--- drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +1 -1
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 54/341 atm: idt77252: prevent use after free in dequeue_rx()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dan Carpenter <[email protected]>
[ Upstream commit a9a18e8f770c9b0703dab93580d0b02e199a4c79 ]
We can't dereference "skb" after calling vcc->push() because the skb is released.
--- drivers/atm/idt77252.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
drivers/atm/idt77252.c +5 -4
@@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len;if (stat &SAR_RSQE_EPDU ) { +unsigned int len, truesize;unsigned char *l1l2; -unsigned int len; l1l2 = (unsigned char *) ((unsigned long ) skb->data + skb->len -6 );
@@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe)ATM_SKB (skb)->vcc = vcc;__net_timestamp (skb); + truesize = skb->truesize; vcc->push (vcc, skb);atomic_inc (&vcc->stats->rx); -if (skb->truesize >SAR_FB_SIZE_3 ) +if (truesize >SAR_FB_SIZE_3 )add_rx_skb (card,3 ,SAR_FB_SIZE_3 ,1 ); -else if (skb->truesize >SAR_FB_SIZE_2 ) +else if (truesize >SAR_FB_SIZE_2 )add_rx_skb (card,2 ,SAR_FB_SIZE_2 ,1 ); -else if (skb->truesize >SAR_FB_SIZE_1 ) +else if (truesize >SAR_FB_SIZE_1 )add_rx_skb (card,1 ,SAR_FB_SIZE_1 ,1 );else add_rx_skb (card,0 ,SAR_FB_SIZE_0 ,1 );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 55/341 net: axienet: Fix register defines comment description
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Radhey Shyam Pandey <[email protected]>
[ 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.
--- drivers/net/ethernet/xilinx/xilinx_axienet.h | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-)
drivers/net/ethernet/xilinx/xilinx_axienet.h +8 -8
@@ -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 */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 56/341 net: dsa: vsc73xx: pass value in phy_write operation
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pawel Dembicki <[email protected]>
[ Upstream commit 5b9eebc2c7a5f0cc7950d918c1e8a4ad4bed5010 ]
In the 'vsc73xx_phy_write' function, the register value is missing, and the phy write operation always sends zeros.
This commit passes the value variable into the proper register.
--- drivers/net/dsa/vitesse-vsc73xx-core.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/dsa/vitesse-vsc73xx-core.c +1 -1
@@ -530,7 +530,7 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,return 0 ; } - cmd = (phy <<21 ) | (regnum <<16 ); + cmd = (phy <<21 ) | (regnum <<16 ) | val; ret =vsc73xx_write (vsc,VSC73XX_BLOCK_MII ,0 ,1 , cmd);if (ret)return ret;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 57/341 net: dsa: vsc73xx: use read_poll_timeout instead delay loop
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pawel Dembicki <[email protected]>
[ 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."
Stable-dep-of: fa63c6434b6f ("net: dsa: vsc73xx: check busy flag in MDIO operations")
--- drivers/net/dsa/vitesse-vsc73xx-core.c | 30 ++++++++++++++------------ 1 file changed, 16 insertions(+), 14 deletions(-)
drivers/net/dsa/vitesse-vsc73xx-core.c +16 -14
@@ -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,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 48/341 bpf: Fix updating attached freplace prog in prog_array map
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Leon Hwang <[email protected]>
[ Upstream commit fdad456cbcca739bae1849549c7a999857c56f88 ]
The commit f7866c358733 ("bpf: Fix null pointer dereference in resolve_prog_type() for BPF_PROG_TYPE_EXT") fixed a NULL pointer dereference panic, but didn't fix the issue that
fails to update attached freplace prog to prog_array map.
Since commit 1c123c567fb1 ("bpf: Resolve fext program type when checking map compatibility"), freplace prog and its target prog are able to tail call each other.
And the commit 3aac1ead5eb6 ("bpf: Move prog->aux->linked_prog and trampoline into bpf_link on attach") sets prog->aux->dst_prog as NULL after attaching freplace prog to its
target prog.
After loading freplace the prog_array's owner type is BPF_PROG_TYPE_SCHED_CLS. Then, after attaching freplace its prog->aux->dst_prog is NULL. Then, while updating freplace in prog_array the bpf_prog_map_compatible() incorrectly returns false because resolve_prog_type() returns BPF_PROG_TYPE_EXT instead of BPF_PROG_TYPE_SCHED_CLS.
After this patch the resolve_prog_type() returns BPF_PROG_TYPE_SCHED_CLS and update to prog_array can succeed.
--- include/linux/bpf_verifier.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
include/linux/bpf_verifier.h +2 -2
@@ -760,8 +760,8 @@ static inline u32 type_flag(u32 type)/* only use after check_attach_btf_id() */ static inline enum bpf_prog_type resolve_prog_type (const struct bpf_prog *prog) { -return (prog->type ==BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ? - prog->aux->dst_prog->type : prog->type; +return (prog->type ==BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ? + prog->aux->saved_dst_prog_type : prog->type; }static inline bool bpf_prog_check_recur (const struct bpf_prog *prog)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 83/341 drm/amd/pm: fix error flow in sensor fetching
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alex Deucher <[email protected]>
[ Upstream commit a5600853167aeba5cade81f184a382a0d1b14641 ]
Sensor fetching functions should return an signed int to handle errors properly.
--- drivers/gpu/drm/amd/pm/amdgpu_pm.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-)
drivers/gpu/drm/amd/pm/amdgpu_pm.c +7 -7
@@ -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 )
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 92/341 rcu: Dump memory object info if callback function is invalid
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhen Lei <[email protected]>
[ Upstream commit 2cbc482d325ee58001472c4359b311958c4efdd1 ]
When a structure containing an RCU callback rhp is (incorrectly) freed and reallocated after rhp is passed to call_rcu(), it is not unusual for rhp->func to be set to NULL. This defeats the debugging prints used by __call_rcu_common() in kernels built with CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, which expect to identify the offending code using the identity of this function.
And in kernels build without CONFIG_DEBUG_OBJECTS_RCU_HEAD=y, things are even worse, as can be seen from this splat:
Unable to handle kernel NULL pointer dereference at virtual address 0
... ...
PC is at 0x0
LR is at rcu_do_batch+0x1c0/0x3b8
... ...
(rcu_do_batch) from (rcu_core+0x1d4/0x284) (rcu_core) from (__do_softirq+0x24c/0x344) (__do_softirq) from (__irq_exit_rcu+0x64/0x108) (__irq_exit_rcu) from (irq_exit+0x8/0x10) (irq_exit) from (__handle_domain_irq+0x74/0x9c) (__handle_domain_irq) from (gic_handle_irq+0x8c/0x98) (gic_handle_irq) from (__irq_svc+0x5c/0x94) (__irq_svc) from (arch_cpu_idle+0x20/0x3c) (arch_cpu_idle) from (default_idle_call+0x4c/0x78) (default_idle_call) from (do_idle+0xf8/0x150) (do_idle) from (cpu_startup_entry+0x18/0x20) (cpu_startup_entry) from (0xc01530)
This commit therefore adds calls to mem_dump_obj(rhp) to output some information, for example:
slab kmalloc-256 start ffff410c45019900 pointer offset 0 size 256
This provides the rough size of the memory block and the offset of the rcu_head structure, which as least provides at least a few clues to help locate the problem. If the problem is reproducible, additional slab debugging can be enabled, for example, CONFIG_DEBUG_SLAB=y, which can provide significantly more information.
--- kernel/rcu/rcu.h | 7 +++++++ kernel/rcu/srcutiny.c | 1 + kernel/rcu/srcutree.c | 1 + kernel/rcu/tasks.h | 1 + kernel/rcu/tiny.c | 1 + kernel/rcu/tree.c | 1 + 6 files changed, 12 insertions(+)
kernel/rcu/rcu.h +7 -0
@@ -10,6 +10,7 @@#ifndef __LINUX_RCU_H#define __LINUX_RCU_H +#include <linux/slab.h> #include <trace/events/rcu.h> /*
@@ -248,6 +249,12 @@ static inline void debug_rcu_head_unqueue(struct rcu_head *head) }#endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ +static inline void debug_rcu_head_callback (struct rcu_head *rhp) +{ +if (unlikely (!rhp->func)) +kmem_dump_obj (rhp); +} +extern int rcu_cpu_stall_suppress_at_boot;static inline bool rcu_stall_is_suppressed_at_boot (void )
kernel/rcu/srcutiny.c +1 -0
@@ -138,6 +138,7 @@ void srcu_drive_gp(struct work_struct *wp)while (lh) { rhp = lh; lh = lh->next; +debug_rcu_head_callback (rhp);local_bh_disable (); rhp->func (rhp);local_bh_enable ();
kernel/rcu/srcutree.c +1 -0
@@ -1735,6 +1735,7 @@ static void srcu_invoke_callbacks(struct work_struct *work) rhp =rcu_cblist_dequeue (&ready_cbs);for (; rhp !=NULL ; rhp =rcu_cblist_dequeue (&ready_cbs)) {debug_rcu_head_unqueue (rhp); +debug_rcu_head_callback (rhp);local_bh_disable (); rhp->func (rhp);local_bh_enable ();
kernel/rcu/tasks.h +1 -0
@@ -538,6 +538,7 @@ static void rcu_tasks_invoke_cbs(struct rcu_tasks *rtp, struct rcu_tasks_percpuraw_spin_unlock_irqrestore_rcu_node (rtpcp, flags); len = rcl.len;for (rhp =rcu_cblist_dequeue (&rcl); rhp; rhp =rcu_cblist_dequeue (&rcl)) { +debug_rcu_head_callback (rhp);local_bh_disable (); rhp->func (rhp);local_bh_enable ();
kernel/rcu/tiny.c +1 -0
@@ -97,6 +97,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head)trace_rcu_invoke_callback ("" , head); f = head->func; +debug_rcu_head_callback (head);WRITE_ONCE (head->func, (rcu_callback_t )0L );f (head);rcu_lock_release (&rcu_callback_map);
kernel/rcu/tree.c +1 -0
@@ -2185,6 +2185,7 @@ static void rcu_do_batch(struct rcu_data *rdp)trace_rcu_invoke_callback (rcu_state.name, rhp); f = rhp->func; +debug_rcu_head_callback (rhp);WRITE_ONCE (rhp->func, (rcu_callback_t )0L );f (rhp);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 93/341 rcu: Eliminate rcu_gp_slow_unregister() false positive
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Paul E. McKenney <[email protected]>
[ 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.
--- kernel/rcu/tree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
kernel/rcu/tree.c +1 -1
@@ -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 ); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 94/341 net: ethernet: mtk_wed: check update_wo_rx_stats in mtk_wed_update_rx_stats()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lorenzo Bianconi <[email protected]>
[ Upstream commit 486e6ca6b48d68d7fefc99e15cc1865e2210d893 ]
Check if update_wo_rx_stats function pointer is properly set in mtk_wed_update_rx_stats routine before accessing it.
--- drivers/net/ethernet/mediatek/mtk_wed_mcu.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/net/ethernet/mediatek/mtk_wed_mcu.c +3 -0
@@ -68,6 +68,9 @@ mtk_wed_update_rx_stats(struct mtk_wed_device *wed, struct sk_buff *skb)struct mtk_wed_wo_rx_stats *stats;int i; +if (!wed->wlan.update_wo_rx_stats) +return ; +if (count *sizeof (*stats) > skb->len -sizeof (u32))return ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 95/341 sched/topology: Handle NUMA_NO_NODE in sched_numa_find_nth_cpu()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yury Norov <[email protected]>
[ 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().
--- kernel/sched/topology.c | 3 +++ lib/cpumask.c | 4 +--- 2 files changed, 4 insertions(+), 3 deletions(-)
kernel/sched/topology.c +3 -0
@@ -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 */
lib/cpumask.c +1 -3
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 96/341 wifi: cw1200: Avoid processing an invalid TIM IE
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jeff Johnson <[email protected]>
[ Upstream commit b7bcea9c27b3d87b54075735c870500123582145 ]
While converting struct ieee80211_tim_ie::virtual_map to be a flexible array it was observed that the TIM IE processing in cw1200_rx_cb() could potentially process a malformed IE in a manner that could result in a buffer over-read. Add logic to verify that the TIM IE length is large enough to hold a valid TIM payload before processing it.
--- drivers/net/wireless/st/cw1200/txrx.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/st/cw1200/txrx.c +1 -1
@@ -1166,7 +1166,7 @@ void cw1200_rx_cb(struct cw1200_common *priv,size_t ies_len = skb->len - (ies - (u8 *)(skb->data)); tim_ie =cfg80211_find_ie (WLAN_EID_TIM , ies, ies_len); -if (tim_ie) { +if (tim_ie && tim_ie[1 ] >=sizeof (struct ieee80211_tim_ie )) {struct ieee80211_tim_ie *tim = (struct ieee80211_tim_ie *)&tim_ie[2 ];
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 97/341 cgroup: Avoid extra dereference in css_populate_dir()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Kamalesh Babulal <[email protected]>
[ 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.
--- kernel/cgroup/cgroup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
kernel/cgroup/cgroup.c +2 -2
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 98/341 i2c: riic: avoid potential division by zero
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Wolfram Sang <[email protected]>
[ Upstream commit 7890fce6201aed46d3576e3d641f9ee5c1f0e16f ]
Value comes from DT, so it could be 0. Unlikely, but could be.
--- drivers/i2c/busses/i2c-riic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/i2c/busses/i2c-riic.c +1 -1
@@ -313,7 +313,7 @@ static int riic_init_hw(struct riic_dev *riic, struct i2c_timings *t)* frequency with only 62 clock ticks max (31 high, 31 low). * Aim for a duty of 60% LOW, 40% HIGH. */ - total_ticks =DIV_ROUND_UP (rate, t->bus_freq_hz); + total_ticks =DIV_ROUND_UP (rate, t->bus_freq_hz ?:1 );for (cks =0 ; cks <7 ; cks++) {/*
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 99/341 RDMA/rtrs: Fix the problem of variable not initialized fully
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Zhu Yanjun <[email protected]>
[ Upstream commit c5930a1aa08aafe6ffe15b5d28fe875f88f6ac86 ]
No functionality change. The variable which is not initialized fully will introduce potential risks.
--- drivers/infiniband/ulp/rtrs/rtrs.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/infiniband/ulp/rtrs/rtrs.c +1 -1
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 100/341 s390/smp,mcck: fix early IPI handling
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Heiko Carstens <[email protected]>
[ Upstream commit 4a1725281fc5b0009944b1c0e1d2c1dc311a09ec ]
Both the external call as well as the emergency signal submask bits in control register 0 are set before any interrupt handler is registered.
Change the order and first register the interrupt handler and only then enable the interrupts by setting the corresponding bits in control register 0.
This prevents that the second part of the machine check handler for early machine check handling is not executed: the machine check handler sends an IPI to the CPU it runs on. If the corresponding interrupts are enabled, but no interrupt handler is present, the interrupt is ignored.
--- arch/s390/kernel/early.c | 12 +++--------- arch/s390/kernel/smp.c | 4 ++-- 2 files changed, 5 insertions(+), 11 deletions(-)
arch/s390/kernel/early.c +3 -9
@@ -258,15 +258,9 @@ static inline void save_vector_registers(void)#endif } -static inline void setup_control_registers (void ) +static inline void setup_low_address_protection (void ) { -unsigned long reg; - -__ctl_store (reg,0 ,0 ); - reg |=CR0_LOW_ADDRESS_PROTECTION ; - reg |=CR0_EMERGENCY_SIGNAL_SUBMASK ; - reg |=CR0_EXTERNAL_CALL_SUBMASK ; -__ctl_load (reg,0 ,0 ); +__ctl_set_bit (0 ,28 ); }static inline void setup_access_registers (void )
@@ -314,7 +308,7 @@ void __init startup_init(void)save_vector_registers ();setup_topology ();sclp_early_detect (); -setup_control_registers (); +setup_low_address_protection ();setup_access_registers ();lockdep_on (); }
arch/s390/kernel/smp.c +2 -2
@@ -1013,12 +1013,12 @@ void __init smp_fill_possible_mask(void)void __init smp_prepare_cpus (unsigned int max_cpus) { -/* request the 0x1201 emergency signal external interrupt */ if (register_external_irq (EXT_IRQ_EMERGENCY_SIG , do_ext_call_interrupt))panic ("Couldn't request external interrupt 0x1201" ); -/* request the 0x1202 external call external interrupt */ +ctl_set_bit (0 ,14 );if (register_external_irq (EXT_IRQ_EXTERNAL_CALL , do_ext_call_interrupt))panic ("Couldn't request external interrupt 0x1202" ); +ctl_set_bit (0 ,13 ); }void __init smp_prepare_boot_cpu (void )
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 101/341 drm/bridge: tc358768: Attempt to fix DSI horizontal timings
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tomi Valkeinen <[email protected]>
[ 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.
--- drivers/gpu/drm/bridge/tc358768.c | 213 ++++++++++++++++++++++++++---- 1 file changed, 185 insertions(+), 28 deletions(-)
drivers/gpu/drm/bridge/tc358768.c +185 -28
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 84/341 drm/amd/amdgpu/imu_v11_0: Increase buffer size to ensure all possible values can be stored
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Lee Jones <[email protected]>
[ Upstream commit a728342ae4ec2a7fdab0038b11427579424f133e ]
Fixes the following W=1 kernel build warning(s):
drivers/gpu/drm/amd/amdgpu/imu_v11_0.c: In function ‘imu_v11_0_init_microcode’:
drivers/gpu/drm/amd/amdgpu/imu_v11_0.c:52:54: warning: ‘_imu.bin’ directive output may be truncated writing 8 bytes into a region of size between 4 and 33 [-Wformat-truncation=] drivers/gpu/drm/amd/amdgpu/imu_v11_0.c:52:9: note: ‘snprintf’ output between 16 and 45 bytes into a destination of size 40
--- drivers/gpu/drm/amd/amdgpu/imu_v11_0.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +1 -1
@@ -39,7 +39,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_4_imu.bin");static int imu_v11_0_init_microcode (struct amdgpu_device *adev) { -char fw_name[40 ]; +char fw_name[45 ];char ucode_prefix[30 ];int err;const struct imu_firmware_header_v1_0 *imu_hdr;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 102/341 wifi: ath12k: fix WARN_ON during ath12k_mac_update_vif_chan
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Manish Dharanenthiran <[email protected]>
[ Upstream commit 8b8b990fe495e9be057249e1651b59b5ebacf2ef ]
Fix WARN_ON() from ath12k_mac_update_vif_chan() if vdev is not up. Since change_chanctx can be called even before vdev_up.
Do vdev stop followed by a vdev start in case of vdev is down.
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0-02903-QCAHKSWPL_SILICONZ-1
--- drivers/net/wireless/ath/ath12k/mac.c | 27 +++++++++++++++++++++------ 1 file changed, 21 insertions(+), 6 deletions(-)
drivers/net/wireless/ath/ath12k/mac.c +21 -6
@@ -6039,13 +6039,28 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,if (WARN_ON (!arvif->is_started))continue ; -if (WARN_ON (!arvif->is_up)) -continue ; +/* Firmware expect vdev_restart only if vdev is up. +* If vdev is down then it expect vdev_stop->vdev_start. +*/ +if (arvif->is_up) { + ret =ath12k_mac_vdev_restart (arvif, &vifs[i].new_ctx->def); +if (ret) { +ath12k_warn (ab,"failed to restart vdev %d: %d\n" , + arvif->vdev_id, ret); +continue ; + } + }else { + ret =ath12k_mac_vdev_stop (arvif); +if (ret) { +ath12k_warn (ab,"failed to stop vdev %d: %d\n" , + arvif->vdev_id, ret); +continue ; + } - ret =ath12k_mac_vdev_restart (arvif, &vifs[i].new_ctx->def); -if (ret) { -ath12k_warn (ab,"failed to restart vdev %d: %d\n" , - arvif->vdev_id, ret); + ret =ath12k_mac_vdev_start (arvif, &vifs[i].new_ctx->def); +if (ret) +ath12k_warn (ab,"failed to start vdev %d: %d\n" , + arvif->vdev_id, ret);continue ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 103/341 i3c: mipi-i3c-hci: Remove BUG() when Ring Abort request times out
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jarkko Nikula <[email protected]>
[ 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().
--- drivers/i3c/master/mipi-i3c-hci/dma.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)
drivers/i3c/master/mipi-i3c-hci/dma.c +1 -2
@@ -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++) {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 104/341 i3c: mipi-i3c-hci: Do not unmap region not mapped for transfer
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jarkko Nikula <[email protected]>
[ Upstream commit b8806e0c939f168237593af0056c309bf31022b0 ]
Fix following warning (with CONFIG_DMA_API_DEBUG) which happens with a transfer without a data buffer.
DMA-API: i3c mipi-i3c-hci.0: device driver tries to free DMA memory it has not allocated [device address=0x0000000000000000] [size=0 bytes]
For those transfers the hci_dma_queue_xfer() doesn't create a mapping and the DMA address pointer xfer->data_dma is not set.
--- drivers/i3c/master/mipi-i3c-hci/dma.c | 2 ++ 1 file changed, 2 insertions(+)
drivers/i3c/master/mipi-i3c-hci/dma.c +2 -0
@@ -345,6 +345,8 @@ static void hci_dma_unmap_xfer(struct i3c_hci *hci,for (i =0 ; i < n; i++) { xfer = xfer_list + i; +if (!xfer->data) +continue ;dma_unmap_single (&hci->master.dev, xfer->data_dma, xfer->data_len, xfer->rnw ?DMA_FROM_DEVICE :DMA_TO_DEVICE );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 105/341 drm/amdkfd: Move dma unmapping after TLB flush
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Philip Yang <[email protected]>
[ 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.
--- 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(-)
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +1 -0
@@ -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,
drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +22 -4
@@ -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) {
drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +12 -8
@@ -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 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 106/341 media: radio-isa: use dev_name to fill in bus_info
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hans Verkuil <[email protected]>
[ Upstream commit 8b7f3cf4eb9a95940eaabad3226caeaa0d9aa59d ]
This fixes this warning:
drivers/media/radio/radio-isa.c: In function 'radio_isa_querycap':drivers/media/radio/radio-isa.c:39:57: warning: '%s' directive output may be truncated writing up to 35 bytes into a region of size 28 [-Wformat-truncation=]
39 | snprintf(v->bus_info, sizeof(v->bus_info), "ISA:%s", isa->v4l2_dev.name);
| ^~drivers/media/radio/radio-isa.c:39:9: note: 'snprintf' output between 5 and 40 bytes into a destination of size 32
39 | snprintf(v->bus_info, sizeof(v->bus_info), "ISA:%s", isa->v4l2_dev.name);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~--- drivers/media/radio/radio-isa.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/media/radio/radio-isa.c +1 -1
@@ -36,7 +36,7 @@ static int radio_isa_querycap(struct file *file, void *priv,strscpy (v->driver, isa->drv->driver.driver.name,sizeof (v->driver));strscpy (v->card, isa->drv->card,sizeof (v->card)); -snprintf (v->bus_info,sizeof (v->bus_info),"ISA:%s" , isa->v4l2_dev.name); +snprintf (v->bus_info,sizeof (v->bus_info),"ISA:%s" ,dev_name (isa->v4l2_dev.dev));return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 107/341 wifi: ath11k: fix ath11k_mac_op_remain_on_channel() stack usage
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dmitry Antipov <[email protected]>
[ 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.
--- drivers/net/wireless/ath/ath11k/mac.c | 44 +++++++++++++++------------ 1 file changed, 25 insertions(+), 19 deletions(-)
drivers/net/wireless/ath/ath11k/mac.c +25 -19
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 108/341 staging: iio: resolver: ad2s1210: fix use before initialization
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: David Lechner <[email protected]>
[ Upstream commit 7fe2d05cee46b1c4d9f1efaeab08cc31a0dfff60 ]
This fixes a use before initialization in ad2s1210_probe(). The ad2s1210_setup_gpios() function uses st->sdev but it was being called before this field was initialized.
--- drivers/staging/iio/resolver/ad2s1210.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
drivers/staging/iio/resolver/ad2s1210.c +4 -3
@@ -658,9 +658,6 @@ static int ad2s1210_probe(struct spi_device *spi)if (!indio_dev)return -ENOMEM ; st =iio_priv (indio_dev); - ret =ad2s1210_setup_gpios (st); -if (ret <0 ) -return ret;spi_set_drvdata (spi, indio_dev);
@@ -671,6 +668,10 @@ static int ad2s1210_probe(struct spi_device *spi) st->resolution =12 ; st->fexcit =AD2S1210_DEF_EXCIT ; + ret =ad2s1210_setup_gpios (st); +if (ret <0 ) +return ret; + indio_dev->info = &ad2s1210_info; indio_dev->modes =INDIO_DIRECT_MODE ; indio_dev->channels = ad2s1210_channels;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 109/341 wifi: mt76: fix race condition related to checking tx queue fill status
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Felix Fietkau <[email protected]>
[ 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.
--- 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(-)
drivers/net/wireless/mediatek/mt76/mac80211.c +48 -2
@@ -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) {
drivers/net/wireless/mediatek/mt76/mt76.h +7 -17
@@ -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
drivers/net/wireless/mediatek/mt76/mt7603/main.c +2 -2
@@ -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)
drivers/net/wireless/mediatek/mt76/mt7615/main.c +2 -2
@@ -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)
drivers/net/wireless/mediatek/mt76/mt76x02_util.c +2 -2
@@ -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);
drivers/net/wireless/mediatek/mt76/mt7915/main.c +2 -2
@@ -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)
drivers/net/wireless/mediatek/mt76/mt7921/main.c +1 -1
@@ -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 );
drivers/net/wireless/mediatek/mt76/mt792x_core.c +1 -1
@@ -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);
drivers/net/wireless/mediatek/mt76/mt7996/main.c +2 -2
@@ -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)
drivers/net/wireless/mediatek/mt76/tx.c +88 -20
138 lines not on this page · raw message
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 110/341 usb: gadget: uvc: cleanup request when not in correct state
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Michael Grzeschik <[email protected]>
[ Upstream commit 52a39f2cf62bb5430ad1f54cd522dbfdab1d71ba ]
The uvc_video_enable function of the uvc-gadget driver is dequeing and immediately deallocs all requests on its disable codepath. This is not save since the dequeue function is async and does not ensure that the requests are left unlinked in the controller driver.
By adding the ep_free_request into the completion path of the requests we ensure that the request will be properly deallocated.
--- drivers/usb/gadget/function/uvc_video.c | 6 ++++++ 1 file changed, 6 insertions(+)
drivers/usb/gadget/function/uvc_video.c +6 -0
@@ -259,6 +259,12 @@ uvc_video_complete(struct usb_ep *ep, struct usb_request *req)struct uvc_device *uvc = video->uvc;unsigned long flags; +if (uvc->state ==UVC_STATE_CONNECTED ) { +usb_ep_free_request (video->ep, ureq->req); + ureq->req =NULL ; +return ; + } +switch (req->status) {case 0 :break ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 111/341 drm/amd/display: Validate hw_points_num before using it
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Alex Hung <[email protected]>
[ 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.
--- drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/amd/display/dc/dcn30/dcn30_dwb_cm.c +3 -0
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 85/341 drm/amdgpu: access RLC_SPM_MC_CNTL through MMIO in SRIOV runtime
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: ZhenGuo Yin <[email protected]>
[ 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
--- 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(-)
drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c +3 -10
@@ -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)
drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +3 -10
@@ -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); }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 112/341 staging: ks7010: disable bh on tx_dev_lock
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chengfeng Ye <[email protected]>
[ Upstream commit 058cbee52ccd7be77e373d31a4f14670cfd32018 ]
As &priv->tx_dev.tx_dev_lock is also acquired by xmit callback which could be call from timer under softirq context, use spin_lock_bh() on it to prevent potential deadlock.
hostif_sme_work()
--> hostif_sme_set_pmksa()
--> hostif_mib_set_request()
--> ks_wlan_hw_tx()
--> spin_lock(&priv->tx_dev.tx_dev_lock)
ks_wlan_start_xmit()
--> hostif_data_request()
--> ks_wlan_hw_tx()
--> spin_lock(&priv->tx_dev.tx_dev_lock)
--- drivers/staging/ks7010/ks7010_sdio.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
drivers/staging/ks7010/ks7010_sdio.c +2 -2
@@ -395,9 +395,9 @@ int ks_wlan_hw_tx(struct ks_wlan_private *priv, void *p, unsigned long size, priv->hostt.buff[priv->hostt.qtail] =le16_to_cpu (hdr->event); priv->hostt.qtail = (priv->hostt.qtail +1 ) %SME_EVENT_BUFF_SIZE ; -spin_lock (&priv->tx_dev.tx_dev_lock); +spin_lock_bh (&priv->tx_dev.tx_dev_lock); result =enqueue_txdev (priv, p, size, complete_handler, skb); -spin_unlock (&priv->tx_dev.tx_dev_lock); +spin_unlock_bh (&priv->tx_dev.tx_dev_lock);if (txq_has_space (priv))queue_delayed_work (priv->wq, &priv->rw_dwork,0 );
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 113/341 platform/x86/intel/ifs: Validate image size
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Jithu Joseph <[email protected]>
[ 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.
--- drivers/platform/x86/intel/ifs/load.c | 8 ++++++++ 1 file changed, 8 insertions(+)
drivers/platform/x86/intel/ifs/load.c +8 -0
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 114/341 media: s5p-mfc: Fix potential deadlock on condlock
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chengfeng Ye <[email protected]>
[ Upstream commit 04d19e65137e3cd4a5004e624c85c762933d115c ]
As &dev->condlock is acquired under irq context along the following call chain from s5p_mfc_irq(), other acquisition of the same lock inside process context or softirq context should disable irq avoid double lock. enc_post_frame_start() seems to be one such function that execute under process context or softirq context.
<deadlock #1>
enc_post_frame_start()
--> clear_work_bit()
--> spin_loc(&dev->condlock)
<interrupt>
--> s5p_mfc_irq()
--> s5p_mfc_handle_frame()
--> clear_work_bit()
--> spin_lock(&dev->condlock)
This flaw was found by an experimental static analysis tool I am developing for irq-related deadlock.
To prevent the potential deadlock, the patch change clear_work_bit() inside enc_post_frame_start() to clear_work_bit_irqsave().
--- drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/media/platform/samsung/s5p-mfc/s5p_mfc_enc.c +1 -1
@@ -1297,7 +1297,7 @@ static int enc_post_frame_start(struct s5p_mfc_ctx *ctx)if (ctx->state ==MFCINST_FINISHING && ctx->ref_queue_cnt ==0 ) src_ready = false;if (!src_ready || ctx->dst_queue_cnt ==0 ) -clear_work_bit (ctx); +clear_work_bit_irqsave (ctx);return 0 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 115/341 accel/habanalabs/gaudi2: unsecure tpc count registers
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ofir Bitton <[email protected]>
[ Upstream commit 1e3a78270b4ec1c8c177eb310c08128d52137a69 ]
As TPC kernels now must use those registers we unsecure them.
--- drivers/accel/habanalabs/gaudi2/gaudi2_security.c | 1 + 1 file changed, 1 insertion(+)
drivers/accel/habanalabs/gaudi2/gaudi2_security.c +1 -0
@@ -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,
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 116/341 accel/habanalabs: export dma-buf only if size/offset multiples of PAGE_SIZE
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Tomer Tayar <[email protected]>
[ Upstream commit 0b75cb5b240fddf181c284d415ee77ef61b418d6 ]
It is currently allowed for a user to export dma-buf with size and offset that are not multiples of PAGE_SIZE.
The exported memory is mapped for the importer device, and there it will be rounded to PAGE_SIZE, leading to actually exporting more than the user intended to.
To make the user be aware of it, accept only size and offset which are multiple of PAGE_SIZE.
--- drivers/accel/habanalabs/common/memory.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-)
drivers/accel/habanalabs/common/memory.c +11 -4
@@ -1878,16 +1878,16 @@ static int export_dmabuf(struct hl_ctx *ctx,static int validate_export_params_common (struct hl_device *hdev,u64 device_addr,u64 size) { -if (!IS_ALIGNED (device_addr,PAGE_SIZE )) { +if (!PAGE_ALIGNED (device_addr)) {dev_dbg (hdev->dev, -"exported device memory address 0x%llx should be aligned to 0x%lx\n" , +"exported device memory address 0x%llx should be aligned to PAGE_SIZE 0x%lx\n" , device_addr,PAGE_SIZE );return -EINVAL ; } -if (size <PAGE_SIZE ) { +if (!size || !PAGE_ALIGNED (size)) {dev_dbg (hdev->dev, -"exported device memory size %llu should be equal to or greater than %lu\n" , +"exported device memory size %llu should be a multiple of PAGE_SIZE %lu\n" , size,PAGE_SIZE );return -EINVAL ; }
@@ -1938,6 +1938,13 @@ static int validate_export_params(struct hl_device *hdev, u64 device_addr, u64 sif (rc)return rc; +if (!PAGE_ALIGNED (offset)) { +dev_dbg (hdev->dev, +"exported device memory offset %llu should be a multiple of PAGE_SIZE %lu\n" , + offset,PAGE_SIZE ); +return -EINVAL ; + } +if ((offset + size) > phys_pg_pack->total_size) {dev_dbg (hdev->dev,"offset %#llx and size %#llx exceed total map size %#llx\n" , offset, size, phys_pg_pack->total_size);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 86/341 ssb: Fix division by zero issue in ssb_calc_clock_rate
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Rand Deeb <[email protected]>
[ Upstream commit e0b5127fa134fe0284d58877b6b3133939c8b3ce ]
In ssb_calc_clock_rate(), there is a potential issue where the value of m1 could be zero due to initialization using clkfactor_f6_resolv(). This situation raised concerns about the possibility of a division by zero error.
We fixed it by following the suggestions provided by Larry Finger <[email protected]> and Michael Büsch <[email protected]>. The fix involves returning a value of 1 instead of 0 in clkfactor_f6_resolv(). This modification ensures the proper functioning of the code and eliminates the risk of division by zero errors.
--- drivers/ssb/main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/ssb/main.c +1 -1
@@ -839,7 +839,7 @@ static u32 clkfactor_f6_resolve(u32 v)case SSB_CHIPCO_CLK_F6_7 :return 7 ; } -return 0 ; +return 1 ; }/* Calculate the speed the backplane would run at a given set of clockcontrol values */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 87/341 ASoC: cs35l45: Checks index of cs35l45_irqs[]
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Ricardo Rivera-Matos <[email protected]>
[ Upstream commit 44f37b6ce041c838cb2f49f08998c41f1ab3b08c ]
Checks the index computed by the virq offset before printing the error condition in cs35l45_spk_safe_err() handler.
--- sound/soc/codecs/cs35l45.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
sound/soc/codecs/cs35l45.c +4 -1
@@ -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 ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 88/341 wifi: mac80211: lock wiphy in IP address notifier
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
[ Upstream commit 730538edc8e0eb14b02708f65100a0deaf43e6cd ]
Lock the wiphy in the IP address notifier as another place that should have it locked before calling into the driver. This needs a bit of attention since the notifier can be called while the wiphy is already locked, when we remove an interface. Handle this by not running the notifier in this case, and instead calling out to the driver directly.
--- net/mac80211/iface.c | 14 ++++++++++++++ net/mac80211/main.c | 22 +++++++++++++++++++++- 2 files changed, 35 insertions(+), 1 deletion(-)
net/mac80211/iface.c +14 -0
@@ -2315,6 +2315,20 @@ void ieee80211_remove_interfaces(struct ieee80211_local *local)list_for_each_entry_safe (sdata, tmp, &unreg_list, list) {bool netdev = sdata->dev; +/* +* Remove IP addresses explicitly, since the notifier will +* skip the callbacks if wdev->registered is false, since +* we can't acquire the wiphy_lock() again there if already +* inside this locked section. +*/ +sdata_lock (sdata); + sdata->vif.cfg.arp_addr_cnt =0 ; +if (sdata->vif.type ==NL80211_IFTYPE_STATION && + sdata->u.mgd.associated) +ieee80211_vif_cfg_change_notify (sdata, +BSS_CHANGED_ARP_FILTER ); +sdata_unlock (sdata); +list_del (&sdata->list);cfg80211_unregister_wdev (&sdata->wdev);
net/mac80211/main.c +21 -1
@@ -443,7 +443,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,if (!wdev)return NOTIFY_DONE ; -if (wdev->wiphy != local->hw.wiphy) +if (wdev->wiphy != local->hw.wiphy || !wdev->registered)return NOTIFY_DONE ; sdata =IEEE80211_DEV_TO_SUB_IF (ndev);
@@ -458,6 +458,25 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,return NOTIFY_DONE ; ifmgd = &sdata->u.mgd; + +/* +* The nested here is needed to convince lockdep that this is +* all OK. Yes, we lock the wiphy mutex here while we already +* hold the notifier rwsem, that's the normal case. And yes, +* we also acquire the notifier rwsem again when unregistering +* a netdev while we already hold the wiphy mutex, so it does +* look like a typical ABBA deadlock. +* +* However, both of these things happen with the RTNL held +* already. Therefore, they can't actually happen, since the +* lock orders really are ABC and ACB, which is fine due to +* the RTNL (A). +* +* We still need to prevent recursion, which is accomplished +* by the !wdev->registered check above. +*/ +mutex_lock_nested (&local->hw.wiphy->mtx,1 ); +__acquire (&local->hw.wiphy->mtx);sdata_lock (sdata);/* Copy the addresses to the vif config list */
@@ -476,6 +495,7 @@ static int ieee80211_ifa_changed(struct notifier_block *nb,ieee80211_vif_cfg_change_notify (sdata,BSS_CHANGED_ARP_FILTER );sdata_unlock (sdata); +wiphy_unlock (local->hw.wiphy);return NOTIFY_OK ; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 89/341 wifi: cfg80211: check wiphy mutex is held for wdev mutex
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
[ 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.
--- net/wireless/core.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
net/wireless/core.h +7 -1
@@ -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) {
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 90/341 wifi: mac80211: fix BA session teardown race
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Johannes Berg <[email protected]>
[ Upstream commit 05f136220d17839eb7c155f015ace9152f603225 ]
As previously reported by Alexander, whose commit 69403bad97aa ("wifi: mac80211: sdata can be NULL during AMPDU start") I'm reverting as part of this commit, there's a race between station destruction and aggregation setup, where the aggregation setup can happen while the station is being removed and queue the work after ieee80211_sta_tear_down_BA_sessions() has already run in __sta_info_destroy_part1(), and thus the worker will run with a now freed station. In his case, this manifested in a NULL sdata pointer, but really there's no guarantee whatsoever.
The real issue seems to be that it's possible at all to have a situation where this occurs - we want to stop the BA sessions when doing _part1, but we cannot be sure, and WLAN_STA_BLOCK_BA isn't necessarily effective since we don't know that the setup isn't concurrently running and already got past the check.
Simply call ieee80211_sta_tear_down_BA_sessions() again in the second part of station destruction, since at that point really nothing else can hold a reference to the station any more.
Also revert the sdata checks since those are just misleading at this point.
--- net/mac80211/agg-tx.c | 6 +----- net/mac80211/driver-ops.c | 3 --- net/mac80211/sta_info.c | 14 ++++++++++++++ 3 files changed, 15 insertions(+), 8 deletions(-)
net/mac80211/agg-tx.c +1 -5
@@ -497,7 +497,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) {struct tid_ampdu_tx *tid_tx;struct ieee80211_local *local = sta->local; -struct ieee80211_sub_if_data *sdata; +struct ieee80211_sub_if_data *sdata = sta->sdata;struct ieee80211_ampdu_params params = { .sta = &sta->sta, .action =IEEE80211_AMPDU_TX_START ,
@@ -525,7 +525,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)*/ synchronize_net (); - sdata = sta->sdata; params.ssn = sta->tid_seq[tid] >>4 ; ret =drv_ampdu_action (local, sdata, ¶ms); tid_tx->ssn = params.ssn;
@@ -539,9 +538,6 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)*/ set_bit (HT_AGG_STATE_DRV_READY , &tid_tx->state); }else if (ret) { -if (!sdata) -return ; -ht_dbg (sdata,"BA request denied - HW unavailable for %pM tid %d\n" , sta->sta.addr, tid);
net/mac80211/driver-ops.c +0 -3
@@ -393,9 +393,6 @@ int drv_ampdu_action(struct ieee80211_local *local,might_sleep (); -if (!sdata) -return -EIO ; - sdata =get_bss_sdata (sdata);if (!check_sdata_in_driver (sdata))return -EIO ;
net/mac80211/sta_info.c +14 -0
@@ -1402,6 +1402,20 @@ static void __sta_info_destroy_part2(struct sta_info *sta, bool recalc)* after _part1 and before _part2! */ +/* +* There's a potential race in _part1 where we set WLAN_STA_BLOCK_BA +* but someone might have just gotten past a check, and not yet into +* queuing the work/creating the data/etc. +* +* Do another round of destruction so that the worker is certainly +* canceled before we later free the station. +* +* Since this is after synchronize_rcu()/synchronize_net() we're now +* certain that nobody can actually hold a reference to the STA and +* be calling e.g. ieee80211_start_tx_ba_session(). +*/ +ieee80211_sta_tear_down_BA_sessions (sta,AGG_STOP_DESTROY_STA ); +might_sleep ();lockdep_assert_held (&local->sta_mtx);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 91/341 wifi: iwlwifi: mvm: fix recovery flow in CSA
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Emmanuel Grumbach <[email protected]>
[ 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.
--- drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c +6 -1
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 82/341 ALSA: hda/realtek: Fix noise from speakers on Lenovo IdeaPad 3 15IAU7
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Parsa Poorshikhian <[email protected]>
[ Upstream commit ef9718b3d54e822de294351251f3a574f8a082ce ]
Fix noise from speakers connected to AUX port when no sound is playing. The problem occurs because the alc_shutup_pins function includes a 0x10ec0257 vendor ID, which causes noise on Lenovo IdeaPad 3 15IAU7 with Realtek ALC257 codec when no sound is playing.
Removing this vendor ID from the function fixes the bug.
--- sound/pci/hda/patch_realtek.c | 1 - 1 file changed, 1 deletion(-)
sound/pci/hda/patch_realtek.c +0 -1
@@ -585,7 +585,6 @@ static void alc_shutup_pins(struct hda_codec *codec)switch (codec->core.vendor_id) {case 0x10ec0236 :case 0x10ec0256 : -case 0x10ec0257 :case 0x19e58326 :case 0x10ec0283 :case 0x10ec0285 :
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 118/341 md/raid5-cache: use READ_ONCE/WRITE_ONCE for conf->log
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yu Kuai <[email protected]>
[ Upstream commit 06a4d0d8c642b5ea654e832b74dca12965356da0 ]
'conf->log' is set with 'reconfig_mutex' grabbed, however, readers are not procted, hence protect it with READ_ONCE/WRITE_ONCE to prevent reading abnormal values.
--- drivers/md/raid5-cache.c | 47 +++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 22 deletions(-)
drivers/md/raid5-cache.c +25 -22
@@ -327,8 +327,9 @@ void r5l_wake_reclaim(struct r5l_log *log, sector_t space);void r5c_check_stripe_cache_usage (struct r5conf *conf) {int total_cached; +struct r5l_log *log =READ_ONCE (conf->log); -if (!r5c_is_writeback (conf->log)) +if (!r5c_is_writeback (log))return ; total_cached = atomic_read(&conf->r5c_cached_partial_stripes) +
@@ -344,7 +345,7 @@ void r5c_check_stripe_cache_usage(struct r5conf *conf)*/ if (total_cached > conf->min_nr_stripes *1 /2 ||atomic_read (&conf->empty_inactive_list_nr) >0 ) -r5l_wake_reclaim (conf->log,0 ); +r5l_wake_reclaim (log,0 ); }/*
@@ -353,7 +354,9 @@ void r5c_check_stripe_cache_usage(struct r5conf *conf)*/ void r5c_check_cached_full_stripe (struct r5conf *conf) { -if (!r5c_is_writeback (conf->log)) +struct r5l_log *log =READ_ONCE (conf->log); + +if (!r5c_is_writeback (log))return ;/*
@@ -363,7 +366,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)if (atomic_read (&conf->r5c_cached_full_stripes) >=min (R5C_FULL_STRIPE_FLUSH_BATCH (conf), conf->chunk_sectors >>RAID5_STRIPE_SHIFT (conf))) -r5l_wake_reclaim (conf->log,0 ); +r5l_wake_reclaim (log,0 ); }/*
@@ -396,7 +399,7 @@ void r5c_check_cached_full_stripe(struct r5conf *conf)*/ static sector_t r5c_log_required_to_flush_cache (struct r5conf *conf) { -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);if (!r5c_is_writeback (log))return 0 ;
@@ -449,7 +452,7 @@ static inline void r5c_update_log_state(struct r5l_log *log)void r5c_make_stripe_write_out (struct stripe_head *sh) {struct r5conf *conf = sh->raid_conf; -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);BUG_ON (!r5c_is_writeback (log));
@@ -491,7 +494,7 @@ static void r5c_handle_parity_cached(struct stripe_head *sh)*/ static void r5c_finish_cache_stripe (struct stripe_head *sh) { -struct r5l_log *log = sh->raid_conf->log; +struct r5l_log *log =READ_ONCE (sh->raid_conf->log);if (log->r5c_journal_mode ==R5C_JOURNAL_MODE_WRITE_THROUGH ) {BUG_ON (test_bit (STRIPE_R5C_CACHING , &sh->state));
@@ -692,7 +695,7 @@ static void r5c_disable_writeback_async(struct work_struct *work)/* wait superblock change before suspend */ wait_event (mddev->sb_wait, - conf->log ==NULL || + !READ_ONCE (conf->log) || (!test_bit (MD_SB_CHANGE_PENDING , &mddev->sb_flags) && (locked =mddev_trylock (mddev))));if (locked) {
@@ -1151,7 +1154,7 @@ static void r5l_run_no_space_stripes(struct r5l_log *log)static sector_t r5c_calculate_new_cp (struct r5conf *conf) {struct stripe_head *sh; -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);sector_t new_cp;unsigned long flags;
@@ -1159,12 +1162,12 @@ static sector_t r5c_calculate_new_cp(struct r5conf *conf)return log->next_checkpoint;spin_lock_irqsave (&log->stripe_in_journal_lock, flags); -if (list_empty (&conf->log->stripe_in_journal_list)) { +if (list_empty (&log->stripe_in_journal_list)) {/* all stripes flushed */ spin_unlock_irqrestore (&log->stripe_in_journal_lock, flags);return log->next_checkpoint; } - sh =list_first_entry (&conf->log->stripe_in_journal_list, + sh =list_first_entry (&log->stripe_in_journal_list, struct stripe_head, r5c); new_cp = sh->log_start;spin_unlock_irqrestore (&log->stripe_in_journal_lock, flags);
@@ -1399,7 +1402,7 @@ void r5c_flush_cache(struct r5conf *conf, int num)struct stripe_head *sh, *next;lockdep_assert_held (&conf->device_lock); -if (!conf->log) +if (!READ_ONCE (conf->log))return ; count =0 ;
@@ -1420,7 +1423,7 @@ void r5c_flush_cache(struct r5conf *conf, int num)static void r5c_do_reclaim (struct r5conf *conf) { -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);struct stripe_head *sh;int count =0 ;unsigned long flags;
@@ -1549,7 +1552,7 @@ static void r5l_reclaim_thread(struct md_thread *thread) {struct mddev *mddev = thread->mddev;struct r5conf *conf = mddev->private; -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);if (!log)return ;
@@ -1591,7 +1594,7 @@ void r5l_quiesce(struct r5l_log *log, int quiesce)bool r5l_log_disk_error (struct r5conf *conf) { -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);/* don't allow write if journal disk is missing */ if (!log)
@@ -2635,7 +2638,7 @@ int r5c_try_caching_write(struct r5conf *conf, struct stripe_head_state *s, int disks) { -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);int i;struct r5dev *dev;int to_cache =0 ;
@@ -2802,7 +2805,7 @@ void r5c_finish_stripe_write_out(struct r5conf *conf,struct stripe_head *sh, struct stripe_head_state *s) { - struct r5l_log *log = conf->log; + struct r5l_log *log = READ_ONCE(conf->log);int i;int do_wakeup =0 ;sector_t tree_index;
@@ -2941,7 +2944,7 @@ int r5c_cache_data(struct r5l_log *log, struct stripe_head *sh)/* check whether this big stripe is in write back cache. */ bool r5c_big_stripe_cached (struct r5conf *conf,sector_t sect) { -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);sector_t tree_index;void *slot;
@@ -3049,14 +3052,14 @@ int r5l_start(struct r5l_log *log)void r5c_update_on_rdev_error (struct mddev *mddev,struct md_rdev *rdev) {struct r5conf *conf = mddev->private; -struct r5l_log *log = conf->log; +struct r5l_log *log =READ_ONCE (conf->log);if (!log)return ;if ((raid5_calc_degraded (conf) >0 ||test_bit (Journal, &rdev->flags)) && - conf->log->r5c_journal_mode ==R5C_JOURNAL_MODE_WRITE_BACK ) + log->r5c_journal_mode ==R5C_JOURNAL_MODE_WRITE_BACK )schedule_work (&log->disable_writeback_work); }
@@ -3145,7 +3148,7 @@ int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev)spin_lock_init (&log->stripe_in_journal_lock);atomic_set (&log->stripe_in_journal_count,0 ); - conf->log = log; +WRITE_ONCE (conf->log, log);set_bit (MD_HAS_JOURNAL , &conf->mddev->flags);return 0 ;
@@ -3173,7 +3176,7 @@ void r5l_exit_log(struct r5conf *conf)* 'reconfig_mutex' is held by caller, set 'confg->log' to NULL to * ensure disable_writeback_work wakes up and exits. */ - conf->log =NULL ; +WRITE_ONCE (conf->log,NULL );wake_up (&conf->mddev->sb_wait);flush_work (&log->disable_writeback_work);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 127/341 wifi: iwlwifi: abort scan when rfkill on but device enabled
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Miri Korenblit <[email protected]>
[ 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.
--- drivers/net/wireless/intel/iwlwifi/mvm/scan.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/mvm/scan.c +1 -1
@@ -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; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 128/341 wifi: iwlwifi: fw: Fix debugfs command sending
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mukesh Sisodiya <[email protected]>
[ Upstream commit 048449fc666d736a1a17d950fde0b5c5c8fd10cc ]
During debugfs command handling transport function is used directly, this bypasses the locking used by runtime operation function and leads to a kernel warning when two commands are
sent in parallel.
Fix it by using runtime operations function when sending debugfs command.
--- drivers/net/wireless/intel/iwlwifi/fw/debugfs.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/net/wireless/intel/iwlwifi/fw/debugfs.c +5 -1
@@ -141,7 +141,11 @@ static int iwl_dbgfs_enabled_severities_write(struct iwl_fw_runtime *fwrt, event_cfg.enabled_severities =cpu_to_le32 (enabled_severities); - ret =iwl_trans_send_cmd (fwrt->trans, &hcmd); +if (fwrt->ops && fwrt->ops->send_hcmd) + ret = fwrt->ops->send_hcmd (fwrt->ops_ctx, &hcmd); +else + ret = -EPERM ; +IWL_INFO (fwrt,"sent host event cfg with enabled_severities: %u, ret: %d\n" , enabled_severities, ret);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 129/341 wifi: iwlwifi: check for kmemdup() return value in iwl_parse_tlv_firmware()
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Dmitry Antipov <[email protected]>
[ 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.
--- drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
drivers/net/wireless/intel/iwlwifi/iwl-drv.c +4 -2
@@ -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);
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 130/341 clk: visconti: Add bounds-checking coverage for struct visconti_pll_provider
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Gustavo A. R. Silva <[email protected]>
[ Upstream commit 397d887c1601a71e8a8abdb6beea67d58f0472d3 ]
In order to gain the bounds-checking coverage that __counted_by provides to flexible-array members at run-time via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions), we must make sure that the counter member, in this particular case num, is updated before the first access to the flex-array member, in this particular case array hws. See below:
commit f316cdff8d67 ("clk: Annotate struct clk_hw_onecell_data with __counted_by") introduced __counted_by for struct clk_hw_onecell_data together with changes to relocate some of assignments of counter num before hws is accessed:
include/linux/clk-provider.h:
1380 struct clk_hw_onecell_data {
1381 unsigned int num;
1382 struct clk_hw *hws[] __counted_by(num);
1383 };
However, this structure is used as a member in other structs, in this case in struct visconti_pll_provider:
drivers/clk/visconti/pll.h:
16 struct visconti_pll_provider {
17 void __iomem *reg_base;
18 struct device_node *node;
19
20 /* Must be last */
21 struct clk_hw_onecell_data clk_data;
22 };
Hence, we need to move the assignments to ctx->clk_data.num after allocation for struct visconti_pll_provider and before accessing the flexible array ctx->clk_data.hws. And, as assignments for all members in struct visconti_pll_provider are originally adjacent to each other, relocate all assignments together, so we don't split up ctx->clk_data.hws = nr_plls from the rest. :)
--- drivers/clk/visconti/pll.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
drivers/clk/visconti/pll.c +3 -3
@@ -329,12 +329,12 @@ struct visconti_pll_provider * __init visconti_init_pll(struct device_node *np,if (!ctx)return ERR_PTR (-ENOMEM ); -for (i =0 ; i < nr_plls; ++i) - ctx->clk_data.hws[i] =ERR_PTR (-ENOENT ); - ctx->node = np; ctx->reg_base = base; ctx->clk_data.num = nr_plls; +for (i =0 ; i < nr_plls; ++i) + ctx->clk_data.hws[i] =ERR_PTR (-ENOENT ); +return ctx; }
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 131/341 IB/hfi1: Fix potential deadlock on &irq_src_lock and &dd->uctxt_lock
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Chengfeng Ye <[email protected]>
[ 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.
--- drivers/infiniband/hw/hfi1/chip.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/infiniband/hw/hfi1/chip.c +3 -2
@@ -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); }/**
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 132/341 hwmon: (ltc2992) Avoid division by zero
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Antoniu Miclaus <[email protected]>
[ Upstream commit 10b02902048737f376104bc69e5212466e65a542 ]
Do not allow setting shunt resistor to 0. This results in a division by zero when performing current value computations based on input voltages and connected resistor values.
--- drivers/hwmon/ltc2992.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)
drivers/hwmon/ltc2992.c +5 -1
@@ -875,8 +875,12 @@ static int ltc2992_parse_dt(struct ltc2992_state *st) } ret =fwnode_property_read_u32 (child,"shunt-resistor-micro-ohms" , &val); -if (!ret) +if (!ret) { +if (!val) +return dev_err_probe (&st->client->dev, -EINVAL , +"shunt resistor value cannot be zero\n" ); st->r_sense_uohm[addr] = val; + } }return 0 ;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 133/341 rust: work around `bindgen` 0.69.0 issue
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Miguel Ojeda <[email protected]>
[ 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.
Stable-dep-of: 5ce86c6c8613 ("rust: suppress error messages from CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT")
--- init/Kconfig | 5 ++++- scripts/rust_is_available.sh | 6 +++++- 2 files changed, 9 insertions(+), 2 deletions(-)
init/Kconfig +4 -1
@@ -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 && $(BINDGEN) --version workaround-for-0.69.0 || echo n) # # Place an empty function call at each tracepoint site. Can be
scripts/rust_is_available.sh +5 -1
@@ -129,8 +129,12 @@ fi # Check that the Rust bindings generator is suitable. # # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`. +# +# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0 +# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when +# the minimum version is upgraded past that (0.69.1 already fixed the issue). rust_bindings_generator_output=$( \ - 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 "***"
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 134/341 rust: suppress error messages from CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Masahiro Yamada <[email protected]>
[ Upstream commit 5ce86c6c861352c9346ebb5c96ed70cb67414aa3 ]
While this is a somewhat unusual case, I encountered odd error messages when I ran Kconfig in a foreign architecture chroot.
$ make allmodconfig sh: 1: rustc: not found sh: 1: bindgen: not found # # configuration written to .config #
The successful execution of 'command -v rustc' does not necessarily mean that 'rustc --version' will succeed.
$ sh -c 'command -v rustc' /home/masahiro/.cargo/bin/rustc $ sh -c 'rustc --version' sh: 1: rustc: not found
Here, 'rustc' is built for x86, and I ran it in an arm64 system.
The current code:
command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n
can be turned into:
command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version 2>/dev/null || echo n
However, I did not understand the necessity of 'command -v $(RUSTC)'.
I simplified it to:
$(RUSTC) --version 2>/dev/null || echo n
--- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
init/Kconfig +2 -2
@@ -1916,7 +1916,7 @@ config RUST config RUSTC_VERSION_TEXT string depends on RUST - default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n) + default $(shell,$(RUSTC) --version 2>/dev/null || echo n) 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,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version workaround-for-0.69.0 || echo n) + default $(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null || echo n) # # Place an empty function call at each tracepoint site. Can be
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 135/341 rust: fix the default format for CONFIG_{RUSTC,BINDGEN}_VERSION_TEXT
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Masahiro Yamada <[email protected]>
[ 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.
--- init/Kconfig | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
init/Kconfig +2 -2
@@ -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
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 136/341 cpu/SMT: Enable SMT only if a core is online
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nysal Jan K.A <[email protected]>
[ Upstream commit 6c17ea1f3eaa330d445ac14a9428402ce4e3055e ]
If a core is offline then enabling SMT should not online CPUs of this core. By enabling SMT, what is intended is either changing the SMT value from "off" to "on" or setting the SMT level (threads per core) from a lower to higher value.
On PowerPC the ppc64_cpu utility can be used, among other things, to perform the following functions:
ppc64_cpu --cores-on # Get the number of online coresppc64_cpu --cores-on=X # Put exactly X cores onlineppc64_cpu --offline-cores=X[,Y,...] # Put specified cores offlineppc64_cpu --smt={on|off|value} # Enable, disable or change SMT level
If the user has decided to offline certain cores, enabling SMT should not online CPUs in those cores. This patch fixes the issue and changes the behaviour as described, by introducing an arch specific function topology_is_core_online(). It is currently implemented only for PowerPC.
--- Documentation/ABI/testing/sysfs-devices-system-cpu | 3 ++- kernel/cpu.c | 12 +++++++++++- 2 files changed, 13 insertions(+), 2 deletions(-)
Documentation/ABI/testing/sysfs-devices-system-cpu +2 -1
@@ -565,7 +565,8 @@ Description: Control Symmetric Multi Threading (SMT) ================ ========================================= If control status is "forceoff" or "notsupported" writes - are rejected. + are rejected. Note that enabling SMT on PowerPC skips + offline cores. What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias Date: March 2019
kernel/cpu.c +11 -1
@@ -2728,6 +2728,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)return ret; } +/** +* Check if the core a CPU belongs to is online +*/ +#if !defined(topology_is_core_online) +static inline bool topology_is_core_online (unsigned int cpu) +{ +return true; +} +#endif +int cpuhp_smt_enable (void ) {int cpu, ret =0 ;
@@ -2738,7 +2748,7 @@ int cpuhp_smt_enable(void)/* Skip online CPUs and CPUs on offline nodes */ if (cpu_online (cpu) || !node_online (cpu_to_node (cpu)))continue ; -if (!cpu_smt_thread_allowed (cpu)) +if (!cpu_smt_thread_allowed (cpu) || !topology_is_core_online (cpu))continue ; ret =_cpu_up (cpu,0 ,CPUHP_ONLINE );if (ret)
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 119/341 binfmt_misc: cleanup on filesystem umount
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christian Brauner <[email protected]>
[ 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/[email protected]
[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")
---
/* v2 */
- Christian Brauner <[email protected]>:
- 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.
--- fs/binfmt_misc.c | 216 ++++++++++++++++++++++++++++++++++++----------- 1 file changed, 168 insertions(+), 48 deletions(-)
fs/binfmt_misc.c +168 -48
@@ -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;
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 137/341 powerpc/topology: Check if a core is online
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Nysal Jan K.A <[email protected]>
[ 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.
--- arch/powerpc/include/asm/topology.h | 13 +++++++++++++ 1 file changed, 13 insertions(+)
arch/powerpc/include/asm/topology.h +13 -0
@@ -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__ */
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 138/341 arm64: Fix KASAN random tag seed initialization
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Samuel Holland <[email protected]>
[ Upstream commit f75c235565f90c4a17b125e47f1c68ef6b8c2bce ]
Currently, kasan_init_sw_tags() is called before setup_per_cpu_areas(), so per_cpu(prng_state, cpu) accesses the same address regardless of the value of "cpu", and the same seed value gets copied to the percpu area for every CPU. Fix this by moving the call to smp_prepare_boot_cpu(), which is the first architecture hook after setup_per_cpu_areas().
--- arch/arm64/kernel/setup.c | 3 --- arch/arm64/kernel/smp.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-)
arch/arm64/kernel/setup.c +0 -3
@@ -371,9 +371,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)smp_init_cpus ();smp_build_mpidr_hash (); -/* Init percpu seeds for random tags after cpus are set up. */ -kasan_init_sw_tags (); -#ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation
arch/arm64/kernel/smp.c +2 -0
@@ -459,6 +459,8 @@ void __init smp_prepare_boot_cpu(void)init_gic_priority_masking ();kasan_init_hw_tags (); +/* Init percpu seeds for random tags after cpus are set up. */ +kasan_init_sw_tags (); }/*
Signature · 1 line
2.43.0
Greg Kroah-Hartman
maintainerPATCH 139/341 block: Fix lockdep warning in blk_mq_mark_tag_wait
In reply to Greg Kroah-Hartman6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Li Lingfeng <[email protected]>
[ 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.
--- block/blk-mq-tag.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
block/blk-mq-tag.c +3 -2
@@ -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); }/*
Signature · 1 line
2.43.0