May 2025 - Linux-stable-mirror

[PATCH v3 2/6] PCI: cadence-ep: Fix broken set_msix() callback

by Niklas Cassel

While the set_msix() callback function in pcie-cadence-ep writes the Table Size field correctly (N-1), the calculation of the PBA offset is wrong because it calculates space for (N-1) entries instead of N. This results in e.g. the following error when using QEMU with PCI passthrough on a device which relies on the PCI endpoint subsystem: failed to add PCI capability 0x11[0x50]@0xb0: table & pba overlap, or they don't fit in BARs, or don't align Fix the calculation of PBA offset in the MSI-X capability. Cc: stable(a)vger.kernel.org Fixes: 3ef5d16f50f8 ("PCI: cadence: Add MSI-X support to Endpoint driver") Reviewed-by: Wilfred Mallawa <wilfred.mallawa(a)wdc.com> Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/cadence/pcie-cadence-ep.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c index 599ec4b1223e..112ae200b393 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -292,13 +292,14 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, struct cdns_pcie *pcie = &ep->pcie; u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; u32 val, reg; + u16 actual_interrupts = interrupts + 1; fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); reg = cap + PCI_MSIX_FLAGS; val = cdns_pcie_ep_fn_readw(pcie, fn, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; + val |= interrupts; /* 0's based value */ cdns_pcie_ep_fn_writew(pcie, fn, reg, val); /* Set MSI-X BAR and offset */ @@ -308,7 +309,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, /* Set PBA BAR and offset. BAR must match MSI-X BAR */ reg = cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; cdns_pcie_ep_fn_writel(pcie, fn, reg, val); return 0; -- 2.49.0

3 months, 4 weeks

1
0
0 0

[PATCH v3 1/6] PCI: dwc: ep: Fix broken set_msix() callback

by Niklas Cassel

While the set_msix() callback function in pcie-designware-ep writes the Table Size field correctly (N-1), the calculation of the PBA offset is wrong because it calculates space for (N-1) entries instead of N. This results in e.g. the following error when using QEMU with PCI passthrough on a device which relies on the PCI endpoint subsystem: failed to add PCI capability 0x11[0x50]@0xb0: table & pba overlap, or they don't fit in BARs, or don't align Fix the calculation of PBA offset in the MSI-X capability. Cc: stable(a)vger.kernel.org Fixes: 83153d9f36e2 ("PCI: endpoint: Fix ->set_msix() to take BIR and offset as arguments") Reviewed-by: Wilfred Mallawa <wilfred.mallawa(a)wdc.com> Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org> Signed-off-by: Niklas Cassel <cassel(a)kernel.org> --- drivers/pci/controller/dwc/pcie-designware-ep.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 1a0bf9341542..24026f3f3413 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -585,6 +585,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dw_pcie_ep_func *ep_func; u32 val, reg; + u16 actual_interrupts = interrupts + 1; ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); if (!ep_func || !ep_func->msix_cap) @@ -595,7 +596,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, reg = ep_func->msix_cap + PCI_MSIX_FLAGS; val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; + val |= interrupts; /* 0's based value */ dw_pcie_writew_dbi(pci, reg, val); reg = ep_func->msix_cap + PCI_MSIX_TABLE; @@ -603,7 +604,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, dw_pcie_ep_writel_dbi(ep, func_no, reg, val); reg = ep_func->msix_cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (actual_interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; dw_pcie_ep_writel_dbi(ep, func_no, reg, val); dw_pcie_dbi_ro_wr_dis(pci); -- 2.49.0

3 months, 4 weeks

1
0
0 0

[PATCH 0/4] crypto: octeontx2: Fix hang and address alignment issues

by Bharat Bhushan

First patch of the series fixes possible infinite loop. Remaining three patches fixes address alignment issue observed after "9382bc44b5f5 arm64: allow kmalloc() caches aligned to the smaller cache_line_size()" Patch-2 and patch-3 applies to stable version 6.6 onwards. Patch-4 applies to stable version 6.12 onwards Bharat Bhushan (4): crypto: octeontx2: add timeout for load_fvc completion poll crypto: octeontx2: Fix address alignment issue on ucode loading crypto: octeontx2: Fix address alignment on CN10K A0/A1 and OcteonTX2 crypto: octeontx2: Fix address alignment on CN10KB and CN10KA-B0 .../marvell/octeontx2/otx2_cpt_reqmgr.h | 119 +++++++++++++----- .../marvell/octeontx2/otx2_cptpf_ucode.c | 46 ++++--- 2 files changed, 121 insertions(+), 44 deletions(-) -- 2.34.1

3 months, 4 weeks

2
5
0 0

[REGRESSION] applespi from 6.12 onwards

by Berkel Jörg

Keyboard and touchpad stopped working on several Apple Macbooks from the year 2017 using kernel 6.12.xx . Until now I could only find this discussion affirming the bug on Debian and Fedora: https://github.com/Dunedan/mbp-2016-linux/issues/202 On siduction I also tried the more recent kernels 6.14.5 and mainline 6.15-rc4 (from Ubuntu) and the issue persisted with my testdevice MacBookPro14,1 -- see the relevant output: kernel: platform pxa2xx-spi.3: Adding to iommu group 20 kernel: input: Apple SPI Keyboard as /devices/pci0000:00/0000:00:1e.3/pxa2xx-spi.3/spi_master/spi2/spi-APP000D:00/input/input0 kernel: DMAR: DRHD: handling fault status reg 3 kernel: DMAR: [DMA Read NO_PASID] Request device [00:1e.3] fault addr 0xffffa000 [fault reason 0x06] PTE Read access is not set kernel: DMAR: DRHD: handling fault status reg 3 kernel: DMAR: [DMA Read NO_PASID] Request device [00:1e.3] fault addr 0xffffa000 [fault reason 0x06] PTE Read access is not set kernel: applespi spi-APP000D:00: Error writing to device: 01 0e 00 00 kernel: DMAR: DRHD: handling fault status reg 3 kernel: DMAR: [DMA Read NO_PASID] Request device [00:1e.3] fault addr 0xffffa000 [fault reason 0x06] PTE Read access is not set kernel: DMAR: DRHD: handling fault status reg 3 kernel: applespi spi-APP000D:00: Error writing to device: 01 0e 00 00 Many thanks, Jörg Berkel

3 months, 4 weeks

6
17
0 0

Unfamiliar Charge on Account – Question

by suzanne＠tierrabonita.ch

Hey, I just saw that I was debited twice for my latest transaction on your website. Transaction appears twice on my payment history, and I need to get a reversal for the duplicate transaction. Please investigate this and fix the issue at your earliest convenience? I’d appreciate a reply as fast as possible. Thank you for your help in advance. Eagerly awaiting your update. Best regards, Charles Edwards

3 months, 4 weeks

1
0
0 0

[PATCH 5.15.y] tty: add the option to have a tty reject a new ldisc

by jianqi.ren.cn＠windriver.com

From: Linus Torvalds <torvalds(a)linux-foundation.org> [ Upstream commit 6bd23e0c2bb6c65d4f5754d1456bc9a4427fc59b ] ... and use it to limit the virtual terminals to just N_TTY. They are kind of special, and in particular, the "con_write()" routine violates the "writes cannot sleep" rule that some ldiscs rely on. This avoids the BUG: sleeping function called from invalid context at kernel/printk/printk.c:2659 when N_GSM has been attached to a virtual console, and gsmld_write() calls con_write() while holding a spinlock, and con_write() then tries to get the console lock. Tested-by: Tetsuo Handa <penguin-kernel(a)i-love.sakura.ne.jp> Cc: Jiri Slaby <jirislaby(a)kernel.org> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Daniel Starke <daniel.starke(a)siemens.com> Reported-by: syzbot <syzbot+dbac96d8e73b61aa559c(a)syzkaller.appspotmail.com> Closes: https://syzkaller.appspot.com/bug?extid=dbac96d8e73b61aa559c Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Link: https://lore.kernel.org/r/20240423163339.59780-1-torvalds@linux-foundation.… Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> [Minor conflict resolved due to code context change. And also backport description comments for struct tty_operations.] Signed-off-by: Jianqi Ren <jianqi.ren.cn(a)windriver.com> Signed-off-by: He Zhe <zhe.he(a)windriver.com> --- Verified the build test --- drivers/tty/tty_ldisc.c | 6 + drivers/tty/vt/vt.c | 10 ++ include/linux/tty_driver.h | 339 +++++++++++++++++++++++++++++++++++++ 3 files changed, 355 insertions(+) diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c index c34c01579b75..1ab3c4eb3359 100644 --- a/drivers/tty/tty_ldisc.c +++ b/drivers/tty/tty_ldisc.c @@ -567,6 +567,12 @@ int tty_set_ldisc(struct tty_struct *tty, int disc) goto out; } + if (tty->ops->ldisc_ok) { + retval = tty->ops->ldisc_ok(tty, disc); + if (retval) + goto out; + } + old_ldisc = tty->ldisc; /* Shutdown the old discipline. */ diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c index bd125ea5c51f..5b35ea7744a4 100644 --- a/drivers/tty/vt/vt.c +++ b/drivers/tty/vt/vt.c @@ -3440,6 +3440,15 @@ static void con_cleanup(struct tty_struct *tty) tty_port_put(&vc->port); } +/* + * We can't deal with anything but the N_TTY ldisc, + * because we can sleep in our write() routine. + */ +static int con_ldisc_ok(struct tty_struct *tty, int ldisc) +{ + return ldisc == N_TTY ? 0 : -EINVAL; +} + static int default_color = 7; /* white */ static int default_italic_color = 2; // green (ASCII) static int default_underline_color = 3; // cyan (ASCII) @@ -3567,6 +3576,7 @@ static const struct tty_operations con_ops = { .resize = vt_resize, .shutdown = con_shutdown, .cleanup = con_cleanup, + .ldisc_ok = con_ldisc_ok, }; static struct cdev vc0_cdev; diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h index c20431d8def8..9707328595df 100644 --- a/include/linux/tty_driver.h +++ b/include/linux/tty_driver.h @@ -244,6 +244,344 @@ struct tty_driver; struct serial_icounter_struct; struct serial_struct; +/** + * struct tty_operations -- interface between driver and tty + * + * @lookup: ``struct tty_struct *()(struct tty_driver *self, struct file *, + * int idx)`` + * + * Return the tty device corresponding to @idx, %NULL if there is not + * one currently in use and an %ERR_PTR value on error. Called under + * %tty_mutex (for now!) + * + * Optional method. Default behaviour is to use the @self->ttys array. + * + * @install: ``int ()(struct tty_driver *self, struct tty_struct *tty)`` + * + * Install a new @tty into the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. + * + * Optional method. Default behaviour is to use the @self->ttys array. + * + * @remove: ``void ()(struct tty_driver *self, struct tty_struct *tty)`` + * + * Remove a closed @tty from the @self's internal tables. Used in + * conjunction with @lookup and @remove methods. + * + * Optional method. Default behaviour is to use the @self->ttys array. + * + * @open: ``int ()(struct tty_struct *tty, struct file *)`` + * + * This routine is called when a particular @tty device is opened. This + * routine is mandatory; if this routine is not filled in, the attempted + * open will fail with %ENODEV. + * + * Required method. Called with tty lock held. May sleep. + * + * @close: ``void ()(struct tty_struct *tty, struct file *)`` + * + * This routine is called when a particular @tty device is closed. At the + * point of return from this call the driver must make no further ldisc + * calls of any kind. + * + * Remark: called even if the corresponding @open() failed. + * + * Required method. Called with tty lock held. May sleep. + * + * @shutdown: ``void ()(struct tty_struct *tty)`` + * + * This routine is called under the tty lock when a particular @tty device + * is closed for the last time. It executes before the @tty resources + * are freed so may execute while another function holds a @tty kref. + * + * @cleanup: ``void ()(struct tty_struct *tty)`` + * + * This routine is called asynchronously when a particular @tty device + * is closed for the last time freeing up the resources. This is + * actually the second part of shutdown for routines that might sleep. + * + * @write: ``int ()(struct tty_struct *tty, const unsigned char *buf, + * int count)`` + * + * This routine is called by the kernel to write a series (@count) of + * characters (@buf) to the @tty device. The characters may come from + * user space or kernel space. This routine will return the + * number of characters actually accepted for writing. + * + * May occur in parallel in special cases. Because this includes panic + * paths drivers generally shouldn't try and do clever locking here. + * + * Optional: Required for writable devices. May not sleep. + * + * @put_char: ``int ()(struct tty_struct *tty, unsigned char ch)`` + * + * This routine is called by the kernel to write a single character @ch to + * the @tty device. If the kernel uses this routine, it must call the + * @flush_chars() routine (if defined) when it is done stuffing characters + * into the driver. If there is no room in the queue, the character is + * ignored. + * + * Optional: Kernel will use the @write method if not provided. Do not + * call this function directly, call tty_put_char(). + * + * @flush_chars: ``void ()(struct tty_struct *tty)`` + * + * This routine is called by the kernel after it has written a + * series of characters to the tty device using @put_char(). + * + * Optional. Do not call this function directly, call + * tty_driver_flush_chars(). + * + * @write_room: ``unsigned int ()(struct tty_struct *tty)`` + * + * This routine returns the numbers of characters the @tty driver + * will accept for queuing to be written. This number is subject + * to change as output buffers get emptied, or if the output flow + * control is acted. + * + * The ldisc is responsible for being intelligent about multi-threading of + * write_room/write calls + * + * Required if @write method is provided else not needed. Do not call this + * function directly, call tty_write_room() + * + * @chars_in_buffer: ``unsigned int ()(struct tty_struct *tty)`` + * + * This routine returns the number of characters in the device private + * output queue. Used in tty_wait_until_sent() and for poll() + * implementation. + * + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call tty_chars_in_buffer(). + * + * @ioctl: ``int ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * This routine allows the @tty driver to implement device-specific + * ioctls. If the ioctl number passed in @cmd is not recognized by the + * driver, it should return %ENOIOCTLCMD. + * + * Optional. + * + * @compat_ioctl: ``long ()(struct tty_struct *tty, unsigned int cmd, + * unsigned long arg)`` + * + * Implement ioctl processing for 32 bit process on 64 bit system. + * + * Optional. + * + * @set_termios: ``void ()(struct tty_struct *tty, struct ktermios *old)`` + * + * This routine allows the @tty driver to be notified when device's + * termios settings have changed. New settings are in @tty->termios. + * Previous settings are passed in the @old argument. + * + * The API is defined such that the driver should return the actual modes + * selected. This means that the driver is responsible for modifying any + * bits in @tty->termios it cannot fulfill to indicate the actual modes + * being used. + * + * Optional. Called under the @tty->termios_rwsem. May sleep. + * + * @ldisc_ok: ``int ()(struct tty_struct *tty, int ldisc)`` + * + * This routine allows the @tty driver to decide if it can deal + * with a particular @ldisc. + * + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. + * + * @set_ldisc: ``void ()(struct tty_struct *tty)`` + * + * This routine allows the @tty driver to be notified when the device's + * line discipline is being changed. At the point this is done the + * discipline is not yet usable. + * + * Optional. Called under the @tty->ldisc_sem and @tty->termios_rwsem. + * + * @throttle: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that input buffers for the line + * discipline are close to full, and it should somehow signal that no more + * characters should be sent to the @tty. + * + * Serialization including with @unthrottle() is the job of the ldisc + * layer. + * + * Optional: Always invoke via tty_throttle_safe(). Called under the + * @tty->termios_rwsem. + * + * @unthrottle: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should signal that + * characters can now be sent to the @tty without fear of overrunning the + * input buffers of the line disciplines. + * + * Optional. Always invoke via tty_unthrottle(). Called under the + * @tty->termios_rwsem. + * + * @stop: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should stop outputting + * characters to the tty device. + * + * Called with @tty->flow.lock held. Serialized with @start() method. + * + * Optional. Always invoke via stop_tty(). + * + * @start: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it resumed sending + * characters to the @tty device. + * + * Called with @tty->flow.lock held. Serialized with stop() method. + * + * Optional. Always invoke via start_tty(). + * + * @hangup: ``void ()(struct tty_struct *tty)`` + * + * This routine notifies the @tty driver that it should hang up the @tty + * device. + * + * Optional. Called with tty lock held. + * + * @break_ctl: ``int ()(struct tty_struct *tty, int state)`` + * + * This optional routine requests the @tty driver to turn on or off BREAK + * status on the RS-232 port. If @state is -1, then the BREAK status + * should be turned on; if @state is 0, then BREAK should be turned off. + * + * If this routine is implemented, the high-level tty driver will handle + * the following ioctls: %TCSBRK, %TCSBRKP, %TIOCSBRK, %TIOCCBRK. + * + * If the driver sets %TTY_DRIVER_HARDWARE_BREAK in tty_alloc_driver(), + * then the interface will also be called with actual times and the + * hardware is expected to do the delay work itself. 0 and -1 are still + * used for on/off. + * + * Optional: Required for %TCSBRK/%BRKP/etc. handling. May sleep. + * + * @flush_buffer: ``void ()(struct tty_struct *tty)`` + * + * This routine discards device private output buffer. Invoked on close, + * hangup, to implement %TCOFLUSH ioctl and similar. + * + * Optional: if not provided, it is assumed there is no queue on the + * device. Do not call this function directly, call + * tty_driver_flush_buffer(). + * + * @wait_until_sent: ``void ()(struct tty_struct *tty, int timeout)`` + * + * This routine waits until the device has written out all of the + * characters in its transmitter FIFO. Or until @timeout (in jiffies) is + * reached. + * + * Optional: If not provided, the device is assumed to have no FIFO. + * Usually correct to invoke via tty_wait_until_sent(). May sleep. + * + * @send_xchar: ``void ()(struct tty_struct *tty, char ch)`` + * + * This routine is used to send a high-priority XON/XOFF character (@ch) + * to the @tty device. + * + * Optional: If not provided, then the @write method is called under + * the @tty->atomic_write_lock to keep it serialized with the ldisc. + * + * @tiocmget: ``int ()(struct tty_struct *tty)`` + * + * This routine is used to obtain the modem status bits from the @tty + * driver. + * + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMGET + * ioctl. Do not call this function directly, call tty_tiocmget(). + * + * @tiocmset: ``int ()(struct tty_struct *tty, + * unsigned int set, unsigned int clear)`` + * + * This routine is used to set the modem status bits to the @tty driver. + * First, @clear bits should be cleared, then @set bits set. + * + * Optional: If not provided, then %ENOTTY is returned from the %TIOCMSET + * ioctl. Do not call this function directly, call tty_tiocmset(). + * + * @resize: ``int ()(struct tty_struct *tty, struct winsize *ws)`` + * + * Called when a termios request is issued which changes the requested + * terminal geometry to @ws. + * + * Optional: the default action is to update the termios structure + * without error. This is usually the correct behaviour. Drivers should + * not force errors here if they are not resizable objects (e.g. a serial + * line). See tty_do_resize() if you need to wrap the standard method + * in your own logic -- the usual case. + * + * @get_icount: ``int ()(struct tty_struct *tty, + * struct serial_icounter *icount)`` + * + * Called when the @tty device receives a %TIOCGICOUNT ioctl. Passed a + * kernel structure @icount to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * + * @get_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCGSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to complete. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocgserial(). + * + * @set_serial: ``int ()(struct tty_struct *tty, struct serial_struct *p)`` + * + * Called when the @tty device receives a %TIOCSSERIAL ioctl. Passed a + * kernel structure @p (&struct serial_struct) to set the values from. + * + * Optional: called only if provided, otherwise %ENOTTY will be returned. + * Do not call this function directly, call tty_tiocsserial(). + * + * @show_fdinfo: ``void ()(struct tty_struct *tty, struct seq_file *m)`` + * + * Called when the @tty device file descriptor receives a fdinfo request + * from VFS (to show in /proc/<pid>/fdinfo/). @m should be filled with + * information. + * + * Optional: called only if provided, otherwise nothing is written to @m. + * Do not call this function directly, call tty_show_fdinfo(). + * + * @poll_init: ``int ()(struct tty_driver *driver, int line, char *options)`` + * + * kgdboc support (Documentation/dev-tools/kgdb.rst). This routine is + * called to initialize the HW for later use by calling @poll_get_char or + * @poll_put_char. + * + * Optional: called only if provided, otherwise skipped as a non-polling + * driver. + * + * @poll_get_char: ``int ()(struct tty_driver *driver, int line)`` + * + * kgdboc support (see @poll_init). @driver should read a character from a + * tty identified by @line and return it. + * + * Optional: called only if @poll_init provided. + * + * @poll_put_char: ``void ()(struct tty_driver *driver, int line, char ch)`` + * + * kgdboc support (see @poll_init). @driver should write character @ch to + * a tty identified by @line. + * + * Optional: called only if @poll_init provided. + * + * @proc_show: ``int ()(struct seq_file *m, void *driver)`` + * + * Driver @driver (cast to &struct tty_driver) can show additional info in + * /proc/tty/driver/<driver_name>. It is enough to fill in the information + * into @m. + * + * Optional: called only if provided, otherwise no /proc entry created. + * + * This structure defines the interface between the low-level tty driver and + * the tty routines. These routines can be defined. Unless noted otherwise, + * they are optional, and can be filled in with a %NULL pointer. + */ struct tty_operations { struct tty_struct * (*lookup)(struct tty_driver *driver, struct file *filp, int idx); @@ -271,6 +609,7 @@ struct tty_operations { void (*hangup)(struct tty_struct *tty); int (*break_ctl)(struct tty_struct *tty, int state); void (*flush_buffer)(struct tty_struct *tty); + int (*ldisc_ok)(struct tty_struct *tty, int ldisc); void (*set_ldisc)(struct tty_struct *tty); void (*wait_until_sent)(struct tty_struct *tty, int timeout); void (*send_xchar)(struct tty_struct *tty, char ch); -- 2.34.1

3 months, 4 weeks

4
3
0 0

[PATCH] usb: cdnsp: Fix issue with detecting USB 3.2 speed

by Pawel Laszczak

Patch adds support for detecting SuperSpeedPlus Gen1 x2 and SuperSpeedPlus Gen2 x2 speed. Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver") cc: stable(a)vger.kernel.org Signed-off-by: Pawel Laszczak <pawell(a)cadence.com> --- drivers/usb/cdns3/cdnsp-gadget.c | 3 ++- drivers/usb/cdns3/cdnsp-gadget.h | 4 ++++ 2 files changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/usb/cdns3/cdnsp-gadget.c b/drivers/usb/cdns3/cdnsp-gadget.c index 52431ea41669..893b55823261 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.c +++ b/drivers/usb/cdns3/cdnsp-gadget.c @@ -29,7 +29,8 @@ unsigned int cdnsp_port_speed(unsigned int port_status) { /*Detect gadget speed based on PORTSC register*/ - if (DEV_SUPERSPEEDPLUS(port_status)) + if (DEV_SUPERSPEEDPLUS(port_status) || + DEV_SSP_GEN1x2(port_status) || DEV_SSP_GEN2x2(port_status)) return USB_SPEED_SUPER_PLUS; else if (DEV_SUPERSPEED(port_status)) return USB_SPEED_SUPER; diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h index 12534be52f39..2afa3e558f85 100644 --- a/drivers/usb/cdns3/cdnsp-gadget.h +++ b/drivers/usb/cdns3/cdnsp-gadget.h @@ -285,11 +285,15 @@ struct cdnsp_port_regs { #define XDEV_HS (0x3 << 10) #define XDEV_SS (0x4 << 10) #define XDEV_SSP (0x5 << 10) +#define XDEV_SSP1x2 (0x6 << 10) +#define XDEV_SSP2x2 (0x7 << 10) #define DEV_UNDEFSPEED(p) (((p) & DEV_SPEED_MASK) == (0x0 << 10)) #define DEV_FULLSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_FS) #define DEV_HIGHSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_HS) #define DEV_SUPERSPEED(p) (((p) & DEV_SPEED_MASK) == XDEV_SS) #define DEV_SUPERSPEEDPLUS(p) (((p) & DEV_SPEED_MASK) == XDEV_SSP) +#define DEV_SSP_GEN1x2(p) (((p) & DEV_SPEED_MASK) == XDEV_SSP1x2) +#define DEV_SSP_GEN2x2(p) (((p) & DEV_SPEED_MASK) == XDEV_SSP2x2) #define DEV_SUPERSPEED_ANY(p) (((p) & DEV_SPEED_MASK) >= XDEV_SS) #define DEV_PORT_SPEED(p) (((p) >> 10) & 0x0f) /* Port Link State Write Strobe - set this when changing link state */ -- 2.43.0

3 months, 4 weeks

2
1
0 0

+ mm-hugetlb-fix-a-deadlock-with-pagecache_folio-and-hugetlb_fault_mutex_table.patch added to mm-new branch

by Andrew Morton

The patch titled Subject: mm/hugetlb: fix a deadlock with pagecache_folio and hugetlb_fault_mutex_table has been added to the -mm mm-new branch. Its filename is mm-hugetlb-fix-a-deadlock-with-pagecache_folio-and-hugetlb_fault_mutex_table.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patche… This patch will later appear in the mm-new branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Note, mm-new is a provisional staging ground for work-in-progress patches, and acceptance into mm-new is a notification for others take notice and to finish up reviews. Please do not hesitate to respond to review feedback and post updated versions to replace or incrementally fixup patches in mm-new. Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Gavin Guo <gavinguo(a)igalia.com> Subject: mm/hugetlb: fix a deadlock with pagecache_folio and hugetlb_fault_mutex_table Date: Tue, 13 May 2025 17:34:48 +0800 Fix a deadlock which can be triggered by an internal syzkaller [1] reproducer and captured by bpftrace script [2] and its log [3] in this scenario: Process 1 Process 2 --- --- hugetlb_fault mutex_lock(B) // take B filemap_lock_hugetlb_folio filemap_lock_folio __filemap_get_folio folio_lock(A) // take A hugetlb_wp mutex_unlock(B) // release B ... hugetlb_fault ... mutex_lock(B) // take B filemap_lock_hugetlb_folio filemap_lock_folio __filemap_get_folio folio_lock(A) // blocked unmap_ref_private ... mutex_lock(B) // retake and blocked This is a ABBA deadlock involving two locks: - Lock A: pagecache_folio lock - Lock B: hugetlb_fault_mutex_table lock The deadlock occurs between two processes as follows: 1. The first process (let's call it Process 1) is handling a copy-on-write (COW) operation on a hugepage via hugetlb_wp. Due to insufficient reserved hugetlb pages, Process 1, owner of the reserved hugetlb page, attempts to unmap a hugepage owned by another process (non-owner) to satisfy the reservation. Before unmapping, Process 1 acquires lock B (hugetlb_fault_mutex_table lock) and then lock A (pagecache_folio lock). To proceed with the unmap, it releases Lock B but retains Lock A. After the unmap, Process 1 tries to reacquire Lock B. However, at this point, Lock B has already been acquired by another process. 2. The second process (Process 2) enters the hugetlb_fault handler during the unmap operation. It successfully acquires Lock B (hugetlb_fault_mutex_table lock) that was just released by Process 1, but then attempts to acquire Lock A (pagecache_folio lock), which is still held by Process 1. As a result, Process 1 (holding Lock A) is blocked waiting for Lock B (held by Process 2), while Process 2 (holding Lock B) is blocked waiting for Lock A (held by Process 1), constructing a ABBA deadlock scenario. The solution here is to unlock the pagecache_folio and provide the pagecache_folio_unlocked variable to the caller to have the visibility over the pagecache_folio status for subsequent handling. The error message: INFO: task repro_20250402_:13229 blocked for more than 64 seconds. Not tainted 6.15.0-rc3+ #24 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:repro_20250402_ state:D stack:25856 pid:13229 tgid:13228 ppid:3513 task_flags:0x400040 flags:0x00004006 Call Trace: <TASK> __schedule+0x1755/0x4f50 schedule+0x158/0x330 schedule_preempt_disabled+0x15/0x30 __mutex_lock+0x75f/0xeb0 hugetlb_wp+0xf88/0x3440 hugetlb_fault+0x14c8/0x2c30 trace_clock_x86_tsc+0x20/0x20 do_user_addr_fault+0x61d/0x1490 exc_page_fault+0x64/0x100 asm_exc_page_fault+0x26/0x30 RIP: 0010:__put_user_4+0xd/0x20 copy_process+0x1f4a/0x3d60 kernel_clone+0x210/0x8f0 __x64_sys_clone+0x18d/0x1f0 do_syscall_64+0x6a/0x120 entry_SYSCALL_64_after_hwframe+0x76/0x7e RIP: 0033:0x41b26d </TASK> INFO: task repro_20250402_:13229 is blocked on a mutex likely owned by task repro_20250402_:13250. task:repro_20250402_ state:D stack:28288 pid:13250 tgid:13228 ppid:3513 task_flags:0x400040 flags:0x00000006 Call Trace: <TASK> __schedule+0x1755/0x4f50 schedule+0x158/0x330 io_schedule+0x92/0x110 folio_wait_bit_common+0x69a/0xba0 __filemap_get_folio+0x154/0xb70 hugetlb_fault+0xa50/0x2c30 trace_clock_x86_tsc+0x20/0x20 do_user_addr_fault+0xace/0x1490 exc_page_fault+0x64/0x100 asm_exc_page_fault+0x26/0x30 RIP: 0033:0x402619 </TASK> INFO: task repro_20250402_:13250 blocked for more than 65 seconds. Not tainted 6.15.0-rc3+ #24 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:repro_20250402_ state:D stack:28288 pid:13250 tgid:13228 ppid:3513 task_flags:0x400040 flags:0x00000006 Call Trace: <TASK> __schedule+0x1755/0x4f50 schedule+0x158/0x330 io_schedule+0x92/0x110 folio_wait_bit_common+0x69a/0xba0 __filemap_get_folio+0x154/0xb70 hugetlb_fault+0xa50/0x2c30 trace_clock_x86_tsc+0x20/0x20 do_user_addr_fault+0xace/0x1490 exc_page_fault+0x64/0x100 asm_exc_page_fault+0x26/0x30 RIP: 0033:0x402619 </TASK> Showing all locks held in the system: 1 lock held by khungtaskd/35: #0: ffffffff879a7440 (rcu_read_lock){....}-{1:3}, at: debug_show_all_locks+0x30/0x180 2 locks held by repro_20250402_/13229: #0: ffff888017d801e0 (&mm->mmap_lock){++++}-{4:4}, at: lock_mm_and_find_vma+0x37/0x300 #1: ffff888000fec848 (&hugetlb_fault_mutex_table[i]){+.+.}-{4:4}, at: hugetlb_wp+0xf88/0x3440 3 locks held by repro_20250402_/13250: #0: ffff8880177f3d08 (vm_lock){++++}-{0:0}, at: do_user_addr_fault+0x41b/0x1490 #1: ffff888000fec848 (&hugetlb_fault_mutex_table[i]){+.+.}-{4:4}, at: hugetlb_fault+0x3b8/0x2c30 #2: ffff8880129500e8 (&resv_map->rw_sema){++++}-{4:4}, at: hugetlb_fault+0x494/0x2c30 Link: https://drive.google.com/file/d/1DVRnIW-vSayU5J1re9Ct_br3jJQU6Vpb/view?usp=… [1] Link: https://github.com/bboymimi/bpftracer/blob/master/scripts/hugetlb_lock_debu… [2] Link: https://drive.google.com/file/d/1bWq2-8o-BJAuhoHWX7zAhI6ggfhVzQUI/view?usp=… [3] Link: https://lkml.kernel.org/r/20250513093448.592150-1-gavinguo@igalia.com Fixes: 40549ba8f8e0 ("hugetlb: use new vma_lock for pmd sharing synchronization") Signed-off-by: Gavin Guo <gavinguo(a)igalia.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Florent Revest <revest(a)google.com> Cc: Gavin Shan <gshan(a)redhat.com> Cc: Muchun Song <muchun.song(a)linux.dev> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Byungchul Park <byungchul(a)sk.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/hugetlb.c | 33 ++++++++++++++++++++++++++++----- 1 file changed, 28 insertions(+), 5 deletions(-) --- a/mm/hugetlb.c~mm-hugetlb-fix-a-deadlock-with-pagecache_folio-and-hugetlb_fault_mutex_table +++ a/mm/hugetlb.c @@ -6131,7 +6131,8 @@ static void unmap_ref_private(struct mm_ * Keep the pte_same checks anyway to make transition from the mutex easier. */ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio, - struct vm_fault *vmf) + struct vm_fault *vmf, + bool *pagecache_folio_unlocked) { struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; @@ -6229,6 +6230,22 @@ retry_avoidcopy: folio_put(old_folio); /* + * The pagecache_folio needs to be unlocked to avoid + * deadlock and we won't re-lock it in hugetlb_wp(). The + * pagecache_folio could be truncated after being + * unlocked. So its state should not be relied + * subsequently. + * + * Setting *pagecache_folio_unlocked to true allows the + * caller to handle any necessary logic related to the + * folio's unlocked state. + */ + if (pagecache_folio) { + folio_unlock(pagecache_folio); + if (pagecache_folio_unlocked) + *pagecache_folio_unlocked = true; + } + /* * Drop hugetlb_fault_mutex and vma_lock before * unmapping. unmapping needs to hold vma_lock * in write mode. Dropping vma_lock in read mode @@ -6581,7 +6598,7 @@ static vm_fault_t hugetlb_no_page(struct hugetlb_count_add(pages_per_huge_page(h), mm); if ((vmf->flags & FAULT_FLAG_WRITE) && !(vma->vm_flags & VM_SHARED)) { /* Optimization, do the COW without a second fault */ - ret = hugetlb_wp(folio, vmf); + ret = hugetlb_wp(folio, vmf, NULL); } spin_unlock(vmf->ptl); @@ -6653,6 +6670,7 @@ vm_fault_t hugetlb_fault(struct mm_struc struct hstate *h = hstate_vma(vma); struct address_space *mapping; int need_wait_lock = 0; + bool pagecache_folio_unlocked = false; struct vm_fault vmf = { .vma = vma, .address = address & huge_page_mask(h), @@ -6807,7 +6825,8 @@ vm_fault_t hugetlb_fault(struct mm_struc if (flags & (FAULT_FLAG_WRITE|FAULT_FLAG_UNSHARE)) { if (!huge_pte_write(vmf.orig_pte)) { - ret = hugetlb_wp(pagecache_folio, &vmf); + ret = hugetlb_wp(pagecache_folio, &vmf, + &pagecache_folio_unlocked); goto out_put_page; } else if (likely(flags & FAULT_FLAG_WRITE)) { vmf.orig_pte = huge_pte_mkdirty(vmf.orig_pte); @@ -6824,10 +6843,14 @@ out_put_page: out_ptl: spin_unlock(vmf.ptl); - if (pagecache_folio) { + /* + * If the pagecache_folio is unlocked in hugetlb_wp(), we skip + * folio_unlock() here. + */ + if (pagecache_folio && !pagecache_folio_unlocked) folio_unlock(pagecache_folio); + if (pagecache_folio) folio_put(pagecache_folio); - } out_mutex: hugetlb_vma_unlock_read(vma); _ Patches currently in -mm which might be from gavinguo(a)igalia.com are mm-hugetlb-fix-a-deadlock-with-pagecache_folio-and-hugetlb_fault_mutex_table.patch

3 months, 4 weeks

1
0
0 0

[PATCH net v2] net: dsa: microchip: linearize skb for tail-tagging switches

by Jakob Unterwurzacher

The pointer arithmentic for accessing the tail tag only works for linear skbs. For nonlinear skbs, it reads uninitialized memory inside the skb headroom, essentially randomizing the tag. I have observed it gets set to 6 most of the time. Example where ksz9477_rcv thinks that the packet from port 1 comes from port 6 (which does not exist for the ksz9896 that's in use), dropping the packet. Debug prints added by me (not included in this patch): [ 256.645337] ksz9477_rcv:323 tag0=6 [ 256.645349] skb len=47 headroom=78 headlen=0 tailroom=0 mac=(64,14) mac_len=14 net=(78,0) trans=78 shinfo(txflags=0 nr_frags=1 gso(size=0 type=0 segs=0)) csum(0x0 start=0 offset=0 ip_summed=0 complete_sw=0 valid=0 level=0) hash(0x0 sw=0 l4=0) proto=0x00f8 pkttype=1 iif=3 priority=0x0 mark=0x0 alloc_cpu=0 vlan_all=0x0 encapsulation=0 inner(proto=0x0000, mac=0, net=0, trans=0) [ 256.645377] dev name=end1 feat=0x0002e10200114bb3 [ 256.645386] skb headroom: 00000000: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645395] skb headroom: 00000010: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645403] skb headroom: 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645411] skb headroom: 00000030: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 256.645420] skb headroom: 00000040: ff ff ff ff ff ff 00 1c 19 f2 e2 db 08 06 [ 256.645428] skb frag: 00000000: 00 01 08 00 06 04 00 01 00 1c 19 f2 e2 db 0a 02 [ 256.645436] skb frag: 00000010: 00 83 00 00 00 00 00 00 0a 02 a0 2f 00 00 00 00 [ 256.645444] skb frag: 00000020: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 01 [ 256.645452] ksz_common_rcv:92 dsa_conduit_find_user returned NULL Call skb_linearize before trying to access the tag. This patch fixes ksz9477_rcv which is used by the ksz9896 I have at hand, and also applies the same fix to ksz8795_rcv which seems to have the same problem. Signed-off-by: Jakob Unterwurzacher <jakob.unterwurzacher(a)cherry.de> Cc: stable(a)vger.kernel.org Fixes: 016e43a26bab ("net: dsa: ksz: Add KSZ8795 tag code") Fixes: 8b8010fb7876 ("dsa: add support for Microchip KSZ tail tagging) --- v1: https://lore.kernel.org/netdev/20250509071820.4100022-1-jakob.unterwurzache… v2: add Fixes tags, Cc stable, "[PATCH net]" prefix net/dsa/tag_ksz.c | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 281bbac5539d..55ef093fe66b 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -140,7 +140,12 @@ static struct sk_buff *ksz8795_xmit(struct sk_buff *skb, struct net_device *dev) static struct sk_buff *ksz8795_rcv(struct sk_buff *skb, struct net_device *dev) { - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; return ksz_common_rcv(skb, dev, tag[0] & KSZ8795_TAIL_TAG_EG_PORT_M, KSZ_EGRESS_TAG_LEN); @@ -311,8 +316,13 @@ static struct sk_buff *ksz9477_xmit(struct sk_buff *skb, static struct sk_buff *ksz9477_rcv(struct sk_buff *skb, struct net_device *dev) { + u8 *tag; + + if (skb_linearize(skb)) + return NULL; + /* Tag decoding */ - u8 *tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; + tag = skb_tail_pointer(skb) - KSZ_EGRESS_TAG_LEN; unsigned int port = tag[0] & KSZ9477_TAIL_TAG_EG_PORT_M; unsigned int len = KSZ_EGRESS_TAG_LEN; -- 2.39.5

3 months, 4 weeks

3
3
0 0

[STABLE 5.10 5.15] ice: arfs: fix use-after-free when freeing @rx_cpu_rmap

by Suraj Jitindar Singh

From: Alexander Lobakin <alexandr.lobakin(a)intel.com> [ Upstream commit d7442f512b71fc63a99c8a801422dde4fbbf9f93 ] The CI testing bots triggered the following splat: [ 718.203054] BUG: KASAN: use-after-free in free_irq_cpu_rmap+0x53/0x80 [ 718.206349] Read of size 4 at addr ffff8881bd127e00 by task sh/20834 [ 718.212852] CPU: 28 PID: 20834 Comm: sh Kdump: loaded Tainted: G S W IOE 5.17.0-rc8_nextqueue-devqueue-02643-g23f3121aca93 #1 [ 718.219695] Hardware name: Intel Corporation S2600WFT/S2600WFT, BIOS SE5C620.86B.02.01.0012.070720200218 07/07/2020 [ 718.223418] Call Trace: [ 718.227139] [ 718.230783] dump_stack_lvl+0x33/0x42 [ 718.234431] print_address_description.constprop.9+0x21/0x170 [ 718.238177] ? free_irq_cpu_rmap+0x53/0x80 [ 718.241885] ? free_irq_cpu_rmap+0x53/0x80 [ 718.245539] kasan_report.cold.18+0x7f/0x11b [ 718.249197] ? free_irq_cpu_rmap+0x53/0x80 [ 718.252852] free_irq_cpu_rmap+0x53/0x80 [ 718.256471] ice_free_cpu_rx_rmap.part.11+0x37/0x50 [ice] [ 718.260174] ice_remove_arfs+0x5f/0x70 [ice] [ 718.263810] ice_rebuild_arfs+0x3b/0x70 [ice] [ 718.267419] ice_rebuild+0x39c/0xb60 [ice] [ 718.270974] ? asm_sysvec_apic_timer_interrupt+0x12/0x20 [ 718.274472] ? ice_init_phy_user_cfg+0x360/0x360 [ice] [ 718.278033] ? delay_tsc+0x4a/0xb0 [ 718.281513] ? preempt_count_sub+0x14/0xc0 [ 718.284984] ? delay_tsc+0x8f/0xb0 [ 718.288463] ice_do_reset+0x92/0xf0 [ice] [ 718.292014] ice_pci_err_resume+0x91/0xf0 [ice] [ 718.295561] pci_reset_function+0x53/0x80 <...> [ 718.393035] Allocated by task 690: [ 718.433497] Freed by task 20834: [ 718.495688] Last potentially related work creation: [ 718.568966] The buggy address belongs to the object at ffff8881bd127e00 which belongs to the cache kmalloc-96 of size 96 [ 718.574085] The buggy address is located 0 bytes inside of 96-byte region [ffff8881bd127e00, ffff8881bd127e60) [ 718.579265] The buggy address belongs to the page: [ 718.598905] Memory state around the buggy address: [ 718.601809] ffff8881bd127d00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 718.604796] ffff8881bd127d80: 00 00 00 00 00 00 00 00 00 00 fc fc fc fc fc fc [ 718.607794] >ffff8881bd127e00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc [ 718.610811] ^ [ 718.613819] ffff8881bd127e80: 00 00 00 00 00 00 00 00 00 00 00 00 fc fc fc fc [ 718.617107] ffff8881bd127f00: fa fb fb fb fb fb fb fb fb fb fb fb fc fc fc fc This is due to that free_irq_cpu_rmap() is always being called *after* (devm_)free_irq() and thus it tries to work with IRQ descs already freed. For example, on device reset the driver frees the rmap right before allocating a new one (the splat above). Make rmap creation and freeing function symmetrical with {request,free}_irq() calls i.e. do that on ifup/ifdown instead of device probe/remove/resume. These operations can be performed independently from the actual device aRFS configuration. Also, make sure ice_vsi_free_irq() clears IRQ affinity notifiers only when aRFS is disabled -- otherwise, CPU rmap sets and clears its own and they must not be touched manually. Fixes: 28bf26724fdb0 ("ice: Implement aRFS") Co-developed-by: Ivan Vecera <ivecera(a)redhat.com> Signed-off-by: Ivan Vecera <ivecera(a)redhat.com> Signed-off-by: Alexander Lobakin <alexandr.lobakin(a)intel.com> Tested-by: Ivan Vecera <ivecera(a)redhat.com> Signed-off-by: Tony Nguyen <anthony.l.nguyen(a)intel.com> Cc: <stable(a)vger.kernel.org> # 5.10.x Cc: <stable(a)vger.kernel.org> # 5.15.x Signed-off-by: Suraj Jitindar Singh <surajjs(a)amazon.com> --- drivers/net/ethernet/intel/ice/ice_arfs.c | 9 ++------- drivers/net/ethernet/intel/ice/ice_lib.c | 5 ++++- drivers/net/ethernet/intel/ice/ice_main.c | 20 ++++++++------------ 3 files changed, 14 insertions(+), 20 deletions(-) diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 632f16ffee40..085b1a0d67c5 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -577,7 +577,7 @@ void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; - if (!vsi || vsi->type != ICE_VSI_PF || !vsi->arfs_fltr_list) + if (!vsi || vsi->type != ICE_VSI_PF) return; netdev = vsi->netdev; @@ -600,7 +600,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) int base_idx, i; if (!vsi || vsi->type != ICE_VSI_PF) - return -EINVAL; + return 0; pf = vsi->back; netdev = vsi->netdev; @@ -638,7 +638,6 @@ void ice_remove_arfs(struct ice_pf *pf) if (!pf_vsi) return; - ice_free_cpu_rx_rmap(pf_vsi); ice_clear_arfs(pf_vsi); } @@ -655,9 +654,5 @@ void ice_rebuild_arfs(struct ice_pf *pf) return; ice_remove_arfs(pf); - if (ice_set_cpu_rx_rmap(pf_vsi)) { - dev_err(ice_pf_to_dev(pf), "Failed to rebuild aRFS\n"); - return; - } ice_init_arfs(pf_vsi); } diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index e99c8c10bc61..d3e5bf180c37 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2411,6 +2411,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; + ice_free_cpu_rx_rmap(vsi); + ice_for_each_q_vector(vsi, i) { u16 vector = i + base; int irq_num; @@ -2424,7 +2426,8 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) continue; /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + if (!IS_ENABLED(CONFIG_RFS_ACCEL)) + irq_set_affinity_notifier(irq_num, NULL); /* clear the affinity_mask in the IRQ descriptor */ irq_set_affinity_hint(irq_num, NULL); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 035bc90c8124..a337a6826a84 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2247,6 +2247,13 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) irq_set_affinity_hint(irq_num, &q_vector->affinity_mask); } + err = ice_set_cpu_rx_rmap(vsi); + if (err) { + netdev_err(vsi->netdev, "Failed to setup CPU RMAP on VSI %u: %pe\n", + vsi->vsi_num, ERR_PTR(err)); + goto free_q_irqs; + } + vsi->irqs_ready = true; return 0; @@ -3242,22 +3249,12 @@ static int ice_setup_pf_sw(struct ice_pf *pf) */ ice_napi_add(vsi); - status = ice_set_cpu_rx_rmap(vsi); - if (status) { - dev_err(ice_pf_to_dev(pf), "Failed to set CPU Rx map VSI %d error %d\n", - vsi->vsi_num, status); - status = -EINVAL; - goto unroll_napi_add; - } status = ice_init_mac_fltr(pf); if (status) - goto free_cpu_rx_map; + goto unroll_napi_add; return status; -free_cpu_rx_map: - ice_free_cpu_rx_rmap(vsi); - unroll_napi_add: if (vsi) { ice_napi_del(vsi); @@ -4598,7 +4595,6 @@ static int __maybe_unused ice_suspend(struct device *dev) continue; ice_vsi_free_q_vectors(pf->vsi[v]); } - ice_free_cpu_rx_rmap(ice_get_main_vsi(pf)); ice_clear_interrupt_scheme(pf); pci_save_state(pdev); -- 2.47.1

3 months, 4 weeks

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror May 2025