From: Finn Thain fthain@linux-m68k.org
stable inclusion from stable-v4.19.313 commit 69a02273e288011b521ee7c1f3ab2c23fda633ce category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9L5KR CVE: CVE-2024-26999
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...
--------------------------------
commit 1be3226445362bfbf461c92a5bcdb1723f2e4907 upstream.
The mitigation was intended to stop the irq completely. That may be better than a hard lock-up but it turns out that you get a crash anyway if you're using pmac_zilog as a serial console:
ttyPZ0: pmz: rx irq flood ! BUG: spinlock recursion on CPU#0, swapper/0
That's because the pr_err() call in pmz_receive_chars() results in pmz_console_write() attempting to lock a spinlock already locked in pmz_interrupt(). With CONFIG_DEBUG_SPINLOCK=y, this produces a fatal BUG splat. The spinlock in question is the one in struct uart_port.
Even when it's not fatal, the serial port rx function ceases to work. Also, the iteration limit doesn't play nicely with QEMU, as can be seen in the bug report linked below.
A web search for other reports of the error message "pmz: rx irq flood" didn't produce anything. So I don't think this code is needed any more. Remove it.
Cc: Benjamin Herrenschmidt benh@kernel.crashing.org Cc: Michael Ellerman mpe@ellerman.id.au Cc: Nicholas Piggin npiggin@gmail.com Cc: Christophe Leroy christophe.leroy@csgroup.eu Cc: Aneesh Kumar K.V aneesh.kumar@kernel.org Cc: Naveen N. Rao naveen.n.rao@linux.ibm.com Cc: Andy Shevchenko andy.shevchenko@gmail.com Cc: stable@kernel.org Cc: linux-m68k@lists.linux-m68k.org Link: https://github.com/vivier/qemu-m68k/issues/44 Link: https://lore.kernel.org/all/1078874617.9746.36.camel@gaston/ Acked-by: Michael Ellerman mpe@ellerman.id.au Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Cc: stable stable@kernel.org Signed-off-by: Finn Thain fthain@linux-m68k.org Link: https://lore.kernel.org/r/e853cf2c762f23101cd2ddec0cc0c2be0e72685f.171256822... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yi Yang yiyang13@huawei.com --- drivers/tty/serial/pmac_zilog.c | 14 -------------- 1 file changed, 14 deletions(-)
diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c index 3d21790d961e..2cddcf74f702 100644 --- a/drivers/tty/serial/pmac_zilog.c +++ b/drivers/tty/serial/pmac_zilog.c @@ -220,7 +220,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) { struct tty_port *port; unsigned char ch, r1, drop, error, flag; - int loops = 0;
/* Sanity check, make sure the old bug is no longer happening */ if (uap->port.state == NULL) { @@ -303,24 +302,11 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap) if (r1 & Rx_OVR) tty_insert_flip_char(port, 0, TTY_OVERRUN); next_char: - /* We can get stuck in an infinite loop getting char 0 when the - * line is in a wrong HW state, we break that here. - * When that happens, I disable the receive side of the driver. - * Note that what I've been experiencing is a real irq loop where - * I'm getting flooded regardless of the actual port speed. - * Something strange is going on with the HW - */ - if ((++loops) > 1000) - goto flood; ch = read_zsreg(uap, R0); if (!(ch & Rx_CH_AV)) break; }
- return true; - flood: - pmz_interrupt_control(uap, 0); - pmz_error("pmz: rx irq flood !\n"); return true; }
-
Yi Yang