inet6_dev->ac_list is protected by inet6_dev->lock, so rtnl_dereference()
is a bit rough annotation.
As done in mcast.c, we can use ac_dereference() that checks if
inet6_dev->lock is held.
Let's replace rtnl_dereference() with a new helper ac_dereference().
Note that now addrconf_join_solict() / addrconf_leave_solict() in
__ipv6_dev_ac_inc() / __ipv6_dev_ac_dec() does not need RTNL, so we
can remove ASSERT_RTNL() there.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-12-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Now, RTNL is not needed for mcast code, and what's commented in
ip6_mc_msfget() is apparent by for_each_pmc_socklock(), which has
lockdep annotation for lock_sock().
Let's remove the comment and ASSERT_RTNL() in ipv6_mc_rejoin_groups().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-11-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In ip6_mc_source() and ip6_mc_msfilter(), per-socket mld data is
protected by lock_sock() and inet6_dev->mc_lock is also held for
some per-interface functions.
ip6_mc_find_dev_rtnl() only depends on RTNL. If we want to remove
it, we need to check inet6_dev->dead under mc_lock to close the race
with addrconf_ifdown(), as mentioned earlier.
Let's do that and drop RTNL for the rest of MCAST_ socket options.
Note that ip6_mc_msfilter() has unnecessary lock dances and they
are integrated into one to avoid the last-minute error and simplify
the error handling.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-10-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In __ipv6_sock_mc_close(), per-socket mld data is protected by lock_sock(),
and only __dev_get_by_index() and __in6_dev_get() require RTNL.
Let's call __ipv6_sock_mc_drop() and drop RTNL in ipv6_sock_mc_close().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-9-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In __ipv6_sock_mc_drop(), per-socket mld data is protected by lock_sock(),
and only __dev_get_by_index() and __in6_dev_get() require RTNL.
Let's use dev_get_by_index() and in6_dev_get() and drop RTNL for
IPV6_ADD_MEMBERSHIP and MCAST_JOIN_GROUP.
Note that __ipv6_sock_mc_drop() is factorised to reuse in the next patch.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-8-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In __ipv6_sock_mc_join(), per-socket mld data is protected by lock_sock(),
and only __dev_get_by_index() requires RTNL.
Let's use dev_get_by_index() and drop RTNL for IPV6_ADD_MEMBERSHIP and
MCAST_JOIN_GROUP.
Note that we must call rt6_lookup() and dev_hold() under RCU.
If rt6_lookup() returns an entry from the exception table, dst_dev_put()
could change rt->dev.dst to loopback concurrently, and the original device
could lose the refcount before dev_hold() and unblock device registration.
dst_dev_put() is called from NETDEV_UNREGISTER and synchronize_net() follows
it, so as long as rt6_lookup() and dev_hold() are called within the same
RCU critical section, the dev is alive.
Even if the race happens, they are synchronised by idev->dead and mcast
addresses are cleaned up.
For the racy access to rt->dst.dev, we use dst_dev().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-7-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
As well as __ipv6_dev_mc_inc(), all code in __ipv6_dev_mc_dec() are
protected by inet6_dev->mc_lock, and RTNL is not needed.
Let's use in6_dev_get() in ipv6_dev_mc_dec() and remove ASSERT_RTNL()
in __ipv6_dev_mc_dec().
Now, we can remove the RTNL comment above addrconf_leave_solict() too.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-6-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 63ed8de4be ("mld: add mc_lock for protecting per-interface
mld data"), the newly allocated struct ifmcaddr6 cannot be removed until
inet6_dev->mc_lock is released, so mca_get() and mc_put() are unnecessary.
Let's remove the extra refcounting.
Note that mca_get() was only used in __ipv6_dev_mc_inc().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-5-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Since commit 63ed8de4be ("mld: add mc_lock for protecting
per-interface mld data"), every multicast resource is protected
by inet6_dev->mc_lock.
RTNL is unnecessary in terms of protection but still needed for
synchronisation between addrconf_ifdown() and __ipv6_dev_mc_inc().
Once we removed RTNL, there would be a race below, where we could
add a multicast address to a dead inet6_dev.
CPU1 CPU2
==== ====
addrconf_ifdown() __ipv6_dev_mc_inc()
if (idev->dead) <-- false
dead = true return -ENODEV;
ipv6_mc_destroy_dev() / ipv6_mc_down()
mutex_lock(&idev->mc_lock)
...
mutex_unlock(&idev->mc_lock)
mutex_lock(&idev->mc_lock)
...
mutex_unlock(&idev->mc_lock)
The race window can be easily closed by checking inet6_dev->dead
under inet6_dev->mc_lock in __ipv6_dev_mc_inc() as addrconf_ifdown()
will acquire it after marking inet6_dev dead.
Let's check inet6_dev->dead under mc_lock in __ipv6_dev_mc_inc().
Note that now __ipv6_dev_mc_inc() no longer depends on RTNL and
we can remove ASSERT_RTNL() there and the RTNL comment above
addrconf_join_solict().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-4-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Commit 63ed8de4be ("mld: add mc_lock for protecting per-interface
mld data") added the same comments regarding locking to many functions.
Let's replace the comments with lockdep annotation, which is more helpful.
Note that we just remove the comment for mld_clear_zeros() and
mld_send_cr(), where mc_dereference() is used in the entry of the
function.
While at it, a comment for __ipv6_sock_mc_join() is moved back to the
correct place.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-3-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
ipv6_dev_mc_{inc,dec}() has the same check.
Let's remove __in6_dev_get() from pndisc_constructor() and
pndisc_destructor().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-2-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jason Xing says:
====================
net: xsk: update tx queue consumer
Patch 1 makes sure the consumer is updated at the end of generic xmit.
Patch 2 adds corresponding test.
====================
Link: https://patch.msgid.link/20250703141712.33190-1-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The subtest sends 33 packets at one time on purpose to see if xsk
exitting __xsk_generic_xmit() updates the global consumer of tx queue
when reaching the max loop (max_tx_budget, 32 by default). The number 33
can avoid xskq_cons_peek_desc() updates the consumer when it's about to
quit sending, to accurately check if the issue that the first patch
resolves remains. The new case will not check this issue in zero copy
mode.
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250703141712.33190-3-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
For afxdp, the return value of sendto() syscall doesn't reflect how many
descs handled in the kernel. One of use cases is that when user-space
application tries to know the number of transmitted skbs and then decides
if it continues to send, say, is it stopped due to max tx budget?
The following formular can be used after sending to learn how many
skbs/descs the kernel takes care of:
tx_queue.consumers_before - tx_queue.consumers_after
Prior to the current patch, in non-zc mode, the consumer of tx queue is
not immediately updated at the end of each sendto syscall when error
occurs, which leads to the consumer value out-of-dated from the perspective
of user space. So this patch requires store operation to pass the cached
value to the shared value to handle the problem.
More than those explicit errors appearing in the while() loop in
__xsk_generic_xmit(), there are a few possible error cases that might
be neglected in the following call trace:
__xsk_generic_xmit()
xskq_cons_peek_desc()
xskq_cons_read_desc()
xskq_cons_is_valid_desc()
It will also cause the premature exit in the while() loop even if not
all the descs are consumed.
Based on the above analysis, using @sent_frame could cover all the possible
cases where it might lead to out-of-dated global state of consumer after
finishing __xsk_generic_xmit().
The patch also adds a common helper __xsk_tx_release() to keep align
with the zc mode usage in xsk_tx_release().
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250703141712.33190-2-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Oleksij Rempel says:
====================
net: phy: smsc: robustness fixes for LAN87xx/LAN9500
The SMSC 10/100 PHYs (LAN87xx family) found in smsc95xx (lan95xx)
USB-Ethernet adapters show several quirks around the Auto-MDIX feature:
- A hardware strap (AUTOMDIX_EN) may boot the PHY in fixed-MDI mode, and
the current driver cannot always override it.
- When Auto-MDIX is left enabled while autonegotiation is forced off,
the PHY endlessly swaps the TX/RX pairs and never links up.
- The driver sets the enable bit for Auto-MDIX but forgets the override
bit, so userspace requests are silently ignored.
- Rapid configuration changes can wedge the link if PHY IRQs are
enabled.
The four patches below make the MDIX state fully predictable and prevent
link failures in every tested strap / autoneg / MDI-X permutation.
Tested on LAN9512 Eval board.
====================
Link: https://patch.msgid.link/20250703114941.3243890-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Force a fixed MDI-X mode when auto-negotiation is disabled to prevent
link instability.
When forcing the link speed and duplex on a LAN9500 PHY (e.g., with
`ethtool -s eth0 autoneg off ...`) while leaving MDI-X control in auto
mode, the PHY fails to establish a stable link. This occurs because the
PHY's Auto-MDIX algorithm is not designed to operate when
auto-negotiation is disabled. In this state, the PHY continuously
toggles the TX/RX signal pairs, which prevents the link partner from
synchronizing.
This patch resolves the issue by detecting when auto-negotiation is
disabled. If the MDI-X control mode is set to 'auto', the driver now
forces a specific, stable mode (ETH_TP_MDI) to prevent the pair
toggling. This choice of a fixed MDI mode mirrors the behavior the
hardware would exhibit if the AUTOMDIX_EN strap were configured for a
fixed MDI connection.
Fixes: 05b35e7eb9 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250703114941.3243890-4-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Override the hardware strap configuration for MDI-X mode to ensure a
predictable initial state for the driver. The initial mode of the LAN87xx
PHY is determined by the AUTOMDIX_EN strap pin, but the driver has no
documented way to read its latched status.
This unpredictability means the driver cannot know if the PHY has
initialized with Auto-MDIX enabled or disabled, preventing it from
providing a reliable interface to the user.
This patch introduces a `config_init` hook that forces the PHY into a
known state by explicitly enabling Auto-MDIX.
Fixes: 05b35e7eb9 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250703114941.3243890-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Correct the Auto-MDIX configuration to ensure userspace settings are
respected when the feature is disabled by the AUTOMDIX_EN hardware strap.
The LAN9500 PHY allows its default MDI-X mode to be configured via a
hardware strap. If this strap sets the default to "MDI-X off", the
driver was previously unable to enable Auto-MDIX from userspace.
When handling the ETH_TP_MDI_AUTO case, the driver would set the
SPECIAL_CTRL_STS_AMDIX_ENABLE_ bit but neglected to set the required
SPECIAL_CTRL_STS_OVRRD_AMDIX_ bit. Without the override flag, the PHY
falls back to its hardware strap default, ignoring the software request.
This patch corrects the behavior by also setting the override bit when
enabling Auto-MDIX. This ensures that the userspace configuration takes
precedence over the hardware strap, allowing Auto-MDIX to be enabled
correctly in all scenarios.
Fixes: 05b35e7eb9 ("smsc95xx: add phylib support")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Cc: Andre Edich <andre.edich@microchip.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250703114941.3243890-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
According to the Synopsys Controller IP XGMAC-10G Ethernet MAC Databook
v3.30a (section 2.7.2), when the INTM bit in the DMA_Mode register is set
to 2, the sbd_perch_tx_intr_o[] and sbd_perch_rx_intr_o[] signals operate
in level-triggered mode. However, in this configuration, the DMA does not
assert the XGMAC_NIS status bit for Rx or Tx interrupt events.
This creates a functional regression where the condition
if (likely(intr_status & XGMAC_NIS)) in dwxgmac2_dma_interrupt() will
never evaluate to true, preventing proper interrupt handling for
level-triggered mode. The hardware specification explicitly states that
"The DMA does not assert the NIS status bit for the Rx or Tx interrupt
events" (Synopsys DWC_XGMAC2 Databook v3.30a, sec. 2.7.2).
The fix ensures correct handling of both edge and level-triggered
interrupts while maintaining backward compatibility with existing
configurations. It has been tested on the hardware device (not publicly
available), and it can properly trigger the RX and TX interrupt handling
in both the INTM=0 and INTM=2 configurations.
Fixes: d6ddfacd95 ("net: stmmac: Add DMA related callbacks for XGMAC2")
Tested-by: EricChan <chenchuangyu@xiaomi.com>
Signed-off-by: EricChan <chenchuangyu@xiaomi.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250703020449.105730-1-chenchuangyu@xiaomi.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Kuniyuki Iwashima says:
====================
af_unix: Introduce SO_INQ & SCM_INQ.
We have an application that uses almost the same code for TCP and
AF_UNIX (SOCK_STREAM).
The application uses TCP_INQ for TCP, but AF_UNIX doesn't have it
and requires an extra syscall, ioctl(SIOCINQ) or getsockopt(SO_MEMINFO)
as an alternative.
Also, ioctl(SIOCINQ) for AF_UNIX SOCK_STREAM is more expensive because
it needs to iterate all skb in the receive queue.
This series adds a cached field for SIOCINQ to speed it up and introduce
SO_INQ, the generic version of TCP_INQ to get the queue length as cmsg in
each recvmsg().
====================
Link: https://patch.msgid.link/20250702223606.1054680-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Let's add a simple test to check the basic functionality of SO_INQ.
The test does the following:
1. Create socketpair in self->fd[]
2. Enable SO_INQ
3. Send data via self->fd[0]
4. Receive data from self->fd[1]
5. Compare the SCM_INQ cmsg with ioctl(SIOCINQ)
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-8-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
We have an application that uses almost the same code for TCP and
AF_UNIX (SOCK_STREAM).
TCP can use TCP_INQ, but AF_UNIX doesn't have it and requires an
extra syscall, ioctl(SIOCINQ) or getsockopt(SO_MEMINFO) as an
alternative.
Let's introduce the generic version of TCP_INQ.
If SO_INQ is enabled, recvmsg() will put a cmsg of SCM_INQ that
contains the exact value of ioctl(SIOCINQ). The cmsg is also
included when msg->msg_get_inq is non-zero to make sockets
io_uring-friendly.
Note that SOCK_CUSTOM_SOCKOPT is flagged only for SOCK_STREAM to
override setsockopt() for SOL_SOCKET.
By having the flag in struct unix_sock, instead of struct sock, we
can later add SO_INQ support for TCP and reuse tcp_sk(sk)->recvmsg_inq.
Note also that supporting custom getsockopt() for SOL_SOCKET will need
preparation for other SOCK_CUSTOM_SOCKOPT users (UDP, vsock, MPTCP).
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-7-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
In unix_stream_read_generic(), state->msg is fetched multiple times.
Let's cache it in a local variable.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-6-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Compared to TCP, ioctl(SIOCINQ) for AF_UNIX SOCK_STREAM socket is more
expensive, as unix_inq_len() requires iterating through the receive queue
and accumulating skb->len.
Let's cache the value for SOCK_STREAM to a new field during sendmsg()
and recvmsg().
The field is protected by the receive queue lock.
Note that ioctl(SIOCINQ) for SOCK_DGRAM returns the length of the first
skb in the queue.
SOCK_SEQPACKET still requires iterating through the queue because we do
not touch functions shared with unix_dgram_ops. But, if really needed,
we can support it by switching __skb_try_recv_datagram() to a custom
version.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-5-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
unix_stream_read_skb() calls skb_recv_datagram() with MSG_DONTWAIT,
which is mostly equivalent to sock_error(sk) + skb_dequeue().
In the following patch, we will add a new field to cache the number
of bytes in the receive queue. Then, we want to avoid introducing
atomic ops in the fast path, so we will reuse the receive queue lock.
As a preparation for the change, let's not use skb_recv_datagram()
in unix_stream_read_skb().
Note that sock_error() is now moved out of the u->iolock mutex as
the mutex does not synchronise the peer's close() at all.
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-4-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
unix_stream_read_skb() checks SOCK_DEAD only when the dequeued skb is
OOB skb.
unix_stream_read_skb() is called for a SOCK_STREAM socket in SOCKMAP
when data is sent to it.
The function is invoked via sk_psock_verdict_data_ready(), which is
set to sk->sk_data_ready().
During sendmsg(), we check if the receiver has SOCK_DEAD, so there
is no point in checking it again later in ->read_skb().
Also, unix_read_skb() for SOCK_DGRAM does not have the test either.
Let's remove the SOCK_DEAD test in unix_stream_read_skb().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-3-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When __skb_try_recv_datagram() returns NULL in __unix_dgram_recvmsg(),
we hold unix_state_lock() unconditionally.
This is because SOCK_SEQPACKET sk needs to return EOF in case its peer
has been close()d concurrently.
This behaviour totally depends on the timing of the peer's close() and
reading sk->sk_shutdown, and taking the lock does not play a role.
Let's drop the lock from __unix_dgram_recvmsg() and use READ_ONCE().
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250702223606.1054680-2-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Lee Trager says:
====================
eth: fbnic: Add firmware logging support
Firmware running on fbnic generates device logs. These logs contain useful
information about the device which may or may not be related to the host.
Logs are stored in a ring buffer and accessible through DebugFS.
====================
Link: https://patch.msgid.link/20250702192207.697368-1-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Allow reading the firmware log in DebugFS by accessing the fw_log file.
Buffer is read while a spinlock is acquired.
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-7-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The firmware log buffer is enabled during probe and freed during remove.
Early versions of firmware do not support sending logs. Once the mailbox is
up driver will enable logging when supported firmware versions are detected.
Logging is disabled before the mailbox is freed.
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-6-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
By default firmware will not send logs to the host. This must be explicitly
enabled by the driver. The mailbox has the concept of a flag which is a u32
used as a boolean. Lack of flag defaults to a value of false. When enabling
logging historical logs may be optionally requested. These are log messages
generated by the NIC before the driver was loaded. The driver also sends a
log version to support changing the logging format in the future.
[SEND_LOGS_REQ] = {
[SEND_LOGS] /* flag to request log reporting */
[SEND_LOGS_HISTORY] /* flag to request historical logs */
[SEND_LOGS_VERSION] /* u32 indicating the log format version */
}
Logs may be sent to the user either one at a time, or when historical logs
are requested in bulk. Firmware may not send more than 14 messages in bulk
to prevent flooding the mailbox.
[LOG_MSG] = {
[LOG_INDEX] /* entry 0 - u64 index of log */
[LOG_MSEC] /* entry 0 - u32 timestamp of log */
[LOG_MSG] /* entry 0 - char log message up to 256 */
[LOG_LENGTH] /* u32 of remaining log items in arrays */
[LOG_INDEX_ARRAY] = {
[LOG_INDEX] /* entry 1 - u64 index of log */
[LOG_INDEX] /* entry 2 - u64 index of log */
...
}
[LOG_MSEC_ARRAY] = {
[LOG_MSEC] /* entry 1 - u32 timestamp of log */
[LOG_MSEC] /* entry 2 - u32 timestamp of log */
...
}
[LOG_MSG_ARRAY] = {
[LOG_MSG] /* entry 1 - char log message up to 256 */
[LOG_MSG] /* entry 2 - char log message up to 256 */
...
}
}
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-5-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When enabled, firmware may send logs messages which are specific to the
device and not the host. Create a ring buffer to store these messages
which are read by a user through DebugFS. Buffer access is protected by
a spinlock.
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-4-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Create a new macro based on FIELD_PREP to generate easily readable minimum
firmware version ints. This macro will prevent the mistake from the
previous patch from happening again.
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-3-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The full minimum version is 0.10.6-0. The six is now correctly defined as
patch and shifted appropriately. 0.10.6-0 is a preproduction version of
firmware which was released over a year and a half ago. All production
devices meet this requirement.
Signed-off-by: Lee Trager <lee@trager.us>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250702192207.697368-2-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Tariq Toukan says:
====================
mlx5-next updates 2025-07-08
The following pull-request contains common mlx5 updates
for your *net-next* tree.
v2: https://lore.kernel.org/1751574385-24672-1-git-send-email-tariqt@nvidia.com
* 'mlx5-next' of git://git.kernel.org/pub/scm/linux/kernel/git/mellanox/linux:
net/mlx5: Check device memory pointer before usage
net/mlx5: fs, fix RDMA TRANSPORT init cleanup flow
net/mlx5: Add IFC bits for PCIe Congestion Event object
net/mlx5: Small refactor for general object capabilities
net/mlx5: fs, add multiple prios to RDMA TRANSPORT steering domain
====================
Link: https://patch.msgid.link/1752002102-11316-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Generalize node_random() and make it available to general bitmaps and
cpumasks users.
Notice, find_first_bit() is generally faster than find_nth_bit(), and we
employ it when there's a single set bit in the bitmap.
See commit 3e061d924f ("lib/nodemask: optimize node_random for
nodemask with single NUMA node").
CC: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Instances of the Falcon microcontroller appear in modern Nvidia GPUs and
are crucial to the GPU boot process. Document some concepts which will
make nova-core boot code easier to digest. All the information is
derived from public sources such as public documents, OpenRM and Nouveau
code.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-8-9d188772c4c7@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Add explanation of fwsec with diagrams. This helps clarify how the
nova-core falcon boot works.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-7-9d188772c4c7@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
devinit is mentioned in the code. This patch explains it so it is clear
what it does. devinit is not only essential at boot-time, but also at
runtime due to suspend-resume and things like re-clocking.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-6-9d188772c4c7@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Add detailed explanation and block diagrams of the layout of the vBIOS
on Nvidia GPUs. This is important to understand how nova-core boots an
Nvidia GPU.
[ Applied Timur Tabi's feedback on providing link to BIT documentation. ]
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-5-9d188772c4c7@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
A CPU mask on the stack is broken for large values of CONFIG_NR_CPUS:
kernel/trace/preemptirq_delay_test.c: In function ‘preemptirq_delay_run’:
kernel/trace/preemptirq_delay_test.c:143:1: error: the frame size of 8512 bytes is larger than 1536 bytes [-Werror=frame-larger-than=]
Fall back to dynamic allocation here.
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Song Chen <chensong_2000@189.cn>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250620111215.3365305-1-arnd@kernel.org
Fixes: 4b9091e1c1 ("kernel: trace: preemptirq_delay_test: add cpu affinity")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Freeing of filters requires to wait for both an RCU grace period as well as
a RCU task trace wait period after they have been detached from their
lists. The trace task period can be quite large so the freeing of the
filters was moved to use the call_rcu*() routines. The problem with that is
that the callback functions of call_rcu*() is done from a soft irq and can
cause latencies if the callback takes a bit of time.
The filters are freed per event in a system and the syscalls system
contains an event per system call, which can be over 700 events. Freeing 700
filters in a bottom half is undesirable.
Instead, move the freeing to use queue_rcu_work() which is done in task
context.
Link: https://lore.kernel.org/all/9a2f0cd0-1561-4206-8966-f93ccd25927f@paulmck-laptop/
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250609131732.04fd303b@gandalf.local.home
Fixes: a9d0aab5eb ("tracing: Fix regression of filter waiting a long time on RCU synchronization")
Suggested-by: "Paul E. McKenney" <paulmck@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
The dedicated cpumask_next_wrap() is more verbose and effective than
cpumask_next() followed by cpumask_first().
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250605000651.45281-1-yury.norov@gmail.com
Signed-off-by: Yury Norov <yury.norov@gmail.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
sysmembar is a critical operation that the GSP falcon needs to perform
in the reset sequence. Add some code comments to clarify.
[acourbot@nvdidia.com: move relevant documentation to SysmemFlush type]
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-2-9d188772c4c7@nvidia.com
[ Minor grammar fix in the PFB register documentation. - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
xe_pm_runtime_put() is missed to be called for the error path in
xe_devcoredump_read().
Add function description comments for xe_devcoredump_read() to help
understand it.
v2: more detail function comments and refine goto logic (Matt)
Fixes: c4a2e5f865 ("drm/xe: Add devcoredump chunking")
Cc: stable@vger.kernel.org
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250707004911.3502904-6-shuicheng.lin@intel.com
The deleted code is no longer needed because patch "drm/xe/guc: Plumb
GuC-capture into dev coredump" has removed the related usage code.
Remove the code to tidy up the function.
v2: s/bacause/because
Reviewed-by: Zhanjun Dong <zhanjun.dong@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Shuicheng Lin <shuicheng.lin@intel.com>
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Link: https://lore.kernel.org/r/20250707004911.3502904-5-shuicheng.lin@intel.com
Add several code comments to reduce acronym soup and explain how devinit
magic and bootflow works before driver loads. These are essential for
debug and development of the nova driver.
[acourbot@nvidia.com: reformat and reword a couple of sentences]
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250708-nova-docs-v4-1-9d188772c4c7@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
