linux-stable.git/drivers/net/ethernet/broadcom, branch linux-6.13.y

eth: bnxt: fix memory leak in queue reset

2025-03-22T19:56:42+00:00

[ Upstream commit 87dd2850835dd7886726b428a8ef7d73a60520c7 ]

When the queue is reset, the bnxt_alloc_one_tpa_info() is called to
allocate tpa_info for the new queue.
And then the old queue's tpa_info should be removed by the
bnxt_free_one_tpa_info(), but it is not called.
So memory leak occurs.
It adds the bnxt_free_one_tpa_info() in the bnxt_queue_mem_free().

unreferenced object 0xffff888293cc0000 (size 16384):
  comm "ncdevmem", pid 2076, jiffies 4296604081
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 40 75 78 93 82 88 ff ff  ........@ux.....
    40 75 78 93 02 00 00 00 00 00 00 00 00 00 00 00  @ux.............
  backtrace (crc 5d7d4798):
    ___kmalloc_large_node+0x10d/0x1b0
    __kmalloc_large_node_noprof+0x17/0x60
    __kmalloc_noprof+0x3f6/0x520
    bnxt_alloc_one_tpa_info+0x5f/0x300 [bnxt_en]
    bnxt_queue_mem_alloc+0x8e8/0x14f0 [bnxt_en]
    netdev_rx_queue_restart+0x233/0x620
    net_devmem_bind_dmabuf_to_queue+0x2a3/0x600
    netdev_nl_bind_rx_doit+0xc00/0x10a0
    genl_family_rcv_msg_doit+0x1d4/0x2b0
    genl_rcv_msg+0x3fb/0x6c0
    netlink_rcv_skb+0x12c/0x360
    genl_rcv+0x24/0x40
    netlink_unicast+0x447/0x710
    netlink_sendmsg+0x712/0xbc0
    __sys_sendto+0x3fd/0x4d0
    __x64_sys_sendto+0xdc/0x1b0

Fixes: 2d694c27d32e ("bnxt_en: implement netdev_queue_mgmt_ops")
Signed-off-by: Taehee Yoo 
Link: https://patch.msgid.link/20250309134219.91670-7-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: fix kernel panic in the bnxt_get_queue_stats{rx | tx}

2025-03-22T19:56:42+00:00

[ Upstream commit f09af5fdfbd9b0fcee73aab1116904c53b199e97 ]

When qstats-get operation is executed, callbacks of netdev_stats_ops
are called. The bnxt_get_queue_stats{rx | tx} collect per-queue stats
from sw_stats in the rings.
But {rx | tx | cp}_ring are allocated when the interface is up.
So, these rings are not allocated when the interface is down.

The qstats-get is allowed even if the interface is down. However,
the bnxt_get_queue_stats{rx | tx}() accesses cp_ring and tx_ring
without null check.
So, it needs to avoid accessing rings if the interface is down.

Reproducer:
 ip link set $interface down
 ./cli.py --spec netdev.yaml --dump qstats-get
OR
 ip link set $interface down
 python ./stats.py

Splat looks like:
 BUG: kernel NULL pointer dereference, address: 0000000000000000
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 1680fa067 P4D 1680fa067 PUD 16be3b067 PMD 0
 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 0 UID: 0 PID: 1495 Comm: python3 Not tainted 6.14.0-rc4+ #32 5cd0f999d5a15c574ac72b3e4b907341
 Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
 RIP: 0010:bnxt_get_queue_stats_rx+0xf/0x70 [bnxt_en]
 Code: c6 87 b5 18 00 00 02 eb a2 66 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 01
 RSP: 0018:ffffabef43cdb7e0 EFLAGS: 00010282
 RAX: 0000000000000000 RBX: ffffffffc04c8710 RCX: 0000000000000000
 RDX: ffffabef43cdb858 RSI: 0000000000000000 RDI: ffff8d504e850000
 RBP: ffff8d506c9f9c00 R08: 0000000000000004 R09: ffff8d506bcd901c
 R10: 0000000000000015 R11: ffff8d506bcd9000 R12: 0000000000000000
 R13: ffffabef43cdb8c0 R14: ffff8d504e850000 R15: 0000000000000000
 FS:  00007f2c5462b080(0000) GS:ffff8d575f600000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 0000000167fd0000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  
  ? __die+0x20/0x70
  ? page_fault_oops+0x15a/0x460
  ? sched_balance_find_src_group+0x58d/0xd10
  ? exc_page_fault+0x6e/0x180
  ? asm_exc_page_fault+0x22/0x30
  ? bnxt_get_queue_stats_rx+0xf/0x70 [bnxt_en cdd546fd48563c280cfd30e9647efa420db07bf1]
  netdev_nl_stats_by_netdev+0x2b1/0x4e0
  ? xas_load+0x9/0xb0
  ? xas_find+0x183/0x1d0
  ? xa_find+0x8b/0xe0
  netdev_nl_qstats_get_dumpit+0xbf/0x1e0
  genl_dumpit+0x31/0x90
  netlink_dump+0x1a8/0x360

Fixes: af7b3b4adda5 ("eth: bnxt: support per-queue statistics")
Signed-off-by: Taehee Yoo 
Reviewed-by: Somnath Kotur 
Link: https://patch.msgid.link/20250309134219.91670-6-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: do not update checksum in bnxt_xdp_build_skb()

2025-03-22T19:56:42+00:00

[ Upstream commit c03e7d05aa0e2f7e9a9ce5ad8a12471a53f941dc ]

The bnxt_rx_pkt() updates ip_summed value at the end if checksum offload
is enabled.
When the XDP-MB program is attached and it returns XDP_PASS, the
bnxt_xdp_build_skb() is called to update skb_shared_info.
The main purpose of bnxt_xdp_build_skb() is to update skb_shared_info,
but it updates ip_summed value too if checksum offload is enabled.
This is actually duplicate work.

When the bnxt_rx_pkt() updates ip_summed value, it checks if ip_summed
is CHECKSUM_NONE or not.
It means that ip_summed should be CHECKSUM_NONE at this moment.
But ip_summed may already be updated to CHECKSUM_UNNECESSARY in the
XDP-MB-PASS path.
So the by skb_checksum_none_assert() WARNS about it.

This is duplicate work and updating ip_summed in the
bnxt_xdp_build_skb() is not needed.

Splat looks like:
WARNING: CPU: 3 PID: 5782 at ./include/linux/skbuff.h:5155 bnxt_rx_pkt+0x479b/0x7610 [bnxt_en]
Modules linked in: bnxt_re bnxt_en rdma_ucm rdma_cm iw_cm ib_cm ib_uverbs veth xt_nat xt_tcpudp xt_conntrack nft_chain_nat xt_MASQUERADE nf_]
CPU: 3 UID: 0 PID: 5782 Comm: socat Tainted: G        W          6.14.0-rc4+ #27
Tainted: [W]=WARN
Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
RIP: 0010:bnxt_rx_pkt+0x479b/0x7610 [bnxt_en]
Code: 54 24 0c 4c 89 f1 4c 89 ff c1 ea 1f ff d3 0f 1f 00 49 89 c6 48 85 c0 0f 84 4c e5 ff ff 48 89 c7 e8 ca 3d a0 c8 e9 8f f4 ff ff <0f> 0b f
RSP: 0018:ffff88881ba09928 EFLAGS: 00010202
RAX: 0000000000000000 RBX: 00000000c7590303 RCX: 0000000000000000
RDX: 1ffff1104e7d1610 RSI: 0000000000000001 RDI: ffff8881c91300b8
RBP: ffff88881ba09b28 R08: ffff888273e8b0d0 R09: ffff888273e8b070
R10: ffff888273e8b010 R11: ffff888278b0f000 R12: ffff888273e8b080
R13: ffff8881c9130e00 R14: ffff8881505d3800 R15: ffff888273e8b000
FS:  00007f5a2e7be080(0000) GS:ffff88881ba00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fff2e708ff8 CR3: 000000013e3b0000 CR4: 00000000007506f0
PKRU: 55555554
Call Trace:
 
 ? __warn+0xcd/0x2f0
 ? bnxt_rx_pkt+0x479b/0x7610
 ? report_bug+0x326/0x3c0
 ? handle_bug+0x53/0xa0
 ? exc_invalid_op+0x14/0x50
 ? asm_exc_invalid_op+0x16/0x20
 ? bnxt_rx_pkt+0x479b/0x7610
 ? bnxt_rx_pkt+0x3e41/0x7610
 ? __pfx_bnxt_rx_pkt+0x10/0x10
 ? napi_complete_done+0x2cf/0x7d0
 __bnxt_poll_work+0x4e8/0x1220
 ? __pfx___bnxt_poll_work+0x10/0x10
 ? __pfx_mark_lock.part.0+0x10/0x10
 bnxt_poll_p5+0x36a/0xfa0
 ? __pfx_bnxt_poll_p5+0x10/0x10
 __napi_poll.constprop.0+0xa0/0x440
 net_rx_action+0x899/0xd00
...

Following ping.py patch adds xdp-mb-pass case. so ping.py is going
to be able to reproduce this issue.

Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff")
Signed-off-by: Taehee Yoo 
Reviewed-by: Somnath Kotur 
Link: https://patch.msgid.link/20250309134219.91670-5-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: do not use BNXT_VNIC_NTUPLE unconditionally in queue restart logic

2025-03-22T19:56:42+00:00

[ Upstream commit 661958552eda5bf64bfafb4821cbdded935f1f68 ]

When a queue is restarted, it sets MRU to 0 for stopping packet flow.
MRU variable is a member of vnic_info[], the first vnic_info is default
and the second is ntuple.
Only when ntuple is enabled(ethtool -K eth0 ntuple on), vnic_info for
ntuple is allocated in init logic.
The bp->nr_vnics indicates how many vnic_info are allocated.
However bnxt_queue_{start | stop}() accesses vnic_info[BNXT_VNIC_NTUPLE]
regardless of ntuple state.

Reviewed-by: Somnath Kotur 
Fixes: b9d2956e869c ("bnxt_en: stop packet flow during bnxt_queue_stop/start")
Signed-off-by: Taehee Yoo 
Link: https://patch.msgid.link/20250309134219.91670-4-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: return fail if interface is down in bnxt_queue_mem_alloc()

2025-03-22T19:56:42+00:00

[ Upstream commit ca2456e073957781e1184de68551c65161b2bd30 ]

The bnxt_queue_mem_alloc() is called to allocate new queue memory when
a queue is restarted.
It internally accesses rx buffer descriptor corresponding to the index.
The rx buffer descriptor is allocated and set when the interface is up
and it's freed when the interface is down.
So, if queue is restarted if interface is down, kernel panic occurs.

Splat looks like:
 BUG: unable to handle page fault for address: 000000000000b240
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 3 UID: 0 PID: 1563 Comm: ncdevmem2 Not tainted 6.14.0-rc2+ #9 844ddba6e7c459cafd0bf4db9a3198e
 Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
 RIP: 0010:bnxt_queue_mem_alloc+0x3f/0x4e0 [bnxt_en]
 Code: 41 54 4d 89 c4 4d 69 c0 c0 05 00 00 55 48 89 f5 53 48 89 fb 4c 8d b5 40 05 00 00 48 83 ec 15
 RSP: 0018:ffff9dcc83fef9e8 EFLAGS: 00010202
 RAX: ffffffffc0457720 RBX: ffff934ed8d40000 RCX: 0000000000000000
 RDX: 000000000000001f RSI: ffff934ea508f800 RDI: ffff934ea508f808
 RBP: ffff934ea508f800 R08: 000000000000b240 R09: ffff934e84f4b000
 R10: ffff9dcc83fefa30 R11: ffff934e84f4b000 R12: 000000000000001f
 R13: ffff934ed8d40ac0 R14: ffff934ea508fd40 R15: ffff934e84f4b000
 FS:  00007fa73888c740(0000) GS:ffff93559f780000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000000b240 CR3: 0000000145a2e000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  
  ? __die+0x20/0x70
  ? page_fault_oops+0x15a/0x460
  ? exc_page_fault+0x6e/0x180
  ? asm_exc_page_fault+0x22/0x30
  ? __pfx_bnxt_queue_mem_alloc+0x10/0x10 [bnxt_en 7f85e76f4d724ba07471d7e39d9e773aea6597b7]
  ? bnxt_queue_mem_alloc+0x3f/0x4e0 [bnxt_en 7f85e76f4d724ba07471d7e39d9e773aea6597b7]
  netdev_rx_queue_restart+0xc5/0x240
  net_devmem_bind_dmabuf_to_queue+0xf8/0x200
  netdev_nl_bind_rx_doit+0x3a7/0x450
  genl_family_rcv_msg_doit+0xd9/0x130
  genl_rcv_msg+0x184/0x2b0
  ? __pfx_netdev_nl_bind_rx_doit+0x10/0x10
  ? __pfx_genl_rcv_msg+0x10/0x10
  netlink_rcv_skb+0x54/0x100
  genl_rcv+0x24/0x40
...

Reviewed-by: Somnath Kotur 
Reviewed-by: Jakub Kicinski 
Fixes: 2d694c27d32e ("bnxt_en: implement netdev_queue_mgmt_ops")
Signed-off-by: Taehee Yoo 
Reviewed-by: Mina Almasry 
Link: https://patch.msgid.link/20250309134219.91670-3-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: fix truesize for mb-xdp-pass case

2025-03-22T19:56:42+00:00

[ Upstream commit 9f7b2aa5034e24d3c49db73d5f760c0435fe31c2 ]

When mb-xdp is set and return is XDP_PASS, packet is converted from
xdp_buff to sk_buff with xdp_update_skb_shared_info() in
bnxt_xdp_build_skb().
bnxt_xdp_build_skb() passes incorrect truesize argument to
xdp_update_skb_shared_info().
The truesize is calculated as BNXT_RX_PAGE_SIZE * sinfo->nr_frags but
the skb_shared_info was wiped by napi_build_skb() before.
So it stores sinfo->nr_frags before bnxt_xdp_build_skb() and use it
instead of getting skb_shared_info from xdp_get_shared_info_from_buff().

Splat looks like:
 ------------[ cut here ]------------
 WARNING: CPU: 2 PID: 0 at net/core/skbuff.c:6072 skb_try_coalesce+0x504/0x590
 Modules linked in: xt_nat xt_tcpudp veth af_packet xt_conntrack nft_chain_nat xt_MASQUERADE nf_conntrack_netlink xfrm_user xt_addrtype nft_coms
 CPU: 2 UID: 0 PID: 0 Comm: swapper/2 Not tainted 6.14.0-rc2+ #3
 RIP: 0010:skb_try_coalesce+0x504/0x590
 Code: 4b fd ff ff 49 8b 34 24 40 80 e6 40 0f 84 3d fd ff ff 49 8b 74 24 48 40 f6 c6 01 0f 84 2e fd ff ff 48 8d 4e ff e9 25 fd ff ff <0f> 0b e99
 RSP: 0018:ffffb62c4120caa8 EFLAGS: 00010287
 RAX: 0000000000000003 RBX: ffffb62c4120cb14 RCX: 0000000000000ec0
 RDX: 0000000000001000 RSI: ffffa06e5d7dc000 RDI: 0000000000000003
 RBP: ffffa06e5d7ddec0 R08: ffffa06e6120a800 R09: ffffa06e7a119900
 R10: 0000000000002310 R11: ffffa06e5d7dcec0 R12: ffffe4360575f740
 R13: ffffe43600000000 R14: 0000000000000002 R15: 0000000000000002
 FS:  0000000000000000(0000) GS:ffffa0755f700000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f147b76b0f8 CR3: 00000001615d4000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  
  ? __warn+0x84/0x130
  ? skb_try_coalesce+0x504/0x590
  ? report_bug+0x18a/0x1a0
  ? handle_bug+0x53/0x90
  ? exc_invalid_op+0x14/0x70
  ? asm_exc_invalid_op+0x16/0x20
  ? skb_try_coalesce+0x504/0x590
  inet_frag_reasm_finish+0x11f/0x2e0
  ip_defrag+0x37a/0x900
  ip_local_deliver+0x51/0x120
  ip_sublist_rcv_finish+0x64/0x70
  ip_sublist_rcv+0x179/0x210
  ip_list_rcv+0xf9/0x130

How to reproduce:

ip link set $interface1 xdp obj xdp_pass.o
ip link set $interface1 mtu 9000 up
ip a a 10.0.0.1/24 dev $interface1

ip link set $interfac2 mtu 9000 up
ip a a 10.0.0.2/24 dev $interface2
ping 10.0.0.1 -s 65000

Following ping.py patch adds xdp-mb-pass case. so ping.py is going to be
able to reproduce this issue.

Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff")
Signed-off-by: Taehee Yoo 
Link: https://patch.msgid.link/20250309134219.91670-2-ap420073@gmail.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

tg3: Disable tg3 PCIe AER on system reboot

2025-02-17T10:36:10+00:00

[ Upstream commit e0efe83ed325277bb70f9435d4d9fc70bebdcca8 ]

Disable PCIe AER on the tg3 device on system reboot on a limited
list of Dell PowerEdge systems. This prevents a fatal PCIe AER event
on the tg3 device during the ACPI _PTS (prepare to sleep) method for
S5 on those systems. The _PTS is invoked by acpi_enter_sleep_state_prep()
as part of the kernel's reboot sequence as a result of commit
38f34dba806a ("PM: ACPI: reboot: Reinstate S5 for reboot").

There was an earlier fix for this problem by commit 2ca1c94ce0b6
("tg3: Disable tg3 device on system reboot to avoid triggering AER").
But it was discovered that this earlier fix caused a reboot hang
when some Dell PowerEdge servers were booted via ipxe. To address
this reboot hang, the earlier fix was essentially reverted by commit
9fc3bc764334 ("tg3: power down device only on SYSTEM_POWER_OFF").
This re-exposed the tg3 PCIe AER on reboot problem.

This fix is not an ideal solution because the root cause of the AER
is in system firmware. Instead, it's a targeted work-around in the
tg3 driver.

Note also that the PCIe AER must be disabled on the tg3 device even
if the system is configured to use "firmware first" error handling.

V3:
   - Fix sparse warning on improper comparison of pdev->current_state
   - Adhere to netdev comment style

Fixes: 9fc3bc764334 ("tg3: power down device only on SYSTEM_POWER_OFF")
Signed-off-by: Lenny Szubowicz 
Reviewed-by: Pavan Chebbi 
Reviewed-by: Simon Horman 
Signed-off-by: David S. Miller 
Signed-off-by: Sasha Levin

net: bcmgenet: Correct overlaying of PHY and MAC Wake-on-LAN

2025-02-17T10:36:10+00:00

[ Upstream commit 46ded709232344b5750a852747a8881763c721ab ]

Some Wake-on-LAN modes such as WAKE_FILTER may only be supported by the MAC,
while others might be only supported by the PHY. Make sure that the .get_wol()
returns the union of both rather than only that of the PHY if the PHY supports
Wake-on-LAN.

When disabling Wake-on-LAN, make sure that this is done at both the PHY
and MAC level, rather than doing an early return from the PHY driver.

Fixes: 7e400ff35cbe ("net: bcmgenet: Add support for PHY-based Wake-on-LAN")
Fixes: 9ee09edc05f2 ("net: bcmgenet: Properly overlay PHY and MAC Wake-on-LAN capabilities")
Signed-off-by: Florian Fainelli 
Link: https://patch.msgid.link/20250129231342.35013-1-florian.fainelli@broadcom.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

bgmac: reduce max frame size to support just MTU 1500

2025-02-08T09:02:15+00:00

[ Upstream commit 752e5fcc2e77358936d36ef8e522d6439372e201 ]

bgmac allocates new replacement buffer before handling each received
frame. Allocating & DMA-preparing 9724 B each time consumes a lot of CPU
time. Ideally bgmac should just respect currently set MTU but it isn't
the case right now. For now just revert back to the old limited frame
size.

This change bumps NAT masquerade speed by ~95%.

Since commit 8218f62c9c9b ("mm: page_frag: use initial zero offset for
page_frag_alloc_align()"), the bgmac driver fails to open its network
interface successfully and runs out of memory in the following call
stack:

bgmac_open
  -> bgmac_dma_init
    -> bgmac_dma_rx_skb_for_slot
      -> netdev_alloc_frag

BGMAC_RX_ALLOC_SIZE = 10048 and PAGE_FRAG_CACHE_MAX_SIZE = 32768.

Eventually we land into __page_frag_alloc_align() with the following
parameters across multiple successive calls:

__page_frag_alloc_align: fragsz=10048, align_mask=-1, size=32768, offset=0
__page_frag_alloc_align: fragsz=10048, align_mask=-1, size=32768, offset=10048
__page_frag_alloc_align: fragsz=10048, align_mask=-1, size=32768, offset=20096
__page_frag_alloc_align: fragsz=10048, align_mask=-1, size=32768, offset=30144

So in that case we do indeed have offset + fragsz (40192) > size (32768)
and so we would eventually return NULL. Reverting to the older 1500
bytes MTU allows the network driver to be usable again.

Fixes: 8c7da63978f1 ("bgmac: configure MTU and add support for frames beyond 8192 byte size")
Signed-off-by: Rafał Miłecki 
[florian: expand commit message about recent commits]
Reviewed-by: Simon Horman 
Signed-off-by: Florian Fainelli 
Link: https://patch.msgid.link/20250127175159.1788246-1-florian.fainelli@broadcom.com
Signed-off-by: Jakub Kicinski 
Signed-off-by: Sasha Levin

eth: bnxt: always recalculate features after XDP clearing, fix null-deref

2025-01-11T02:01:29+00:00

Recalculate features when XDP is detached.

Before:
  # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp
  # ip li set dev eth0 xdp off
  # ethtool -k eth0 | grep gro
  rx-gro-hw: off [requested on]

After:
  # ip li set dev eth0 xdp obj xdp_dummy.bpf.o sec xdp
  # ip li set dev eth0 xdp off
  # ethtool -k eth0 | grep gro
  rx-gro-hw: on

The fact that HW-GRO doesn't get re-enabled automatically is just
a minor annoyance. The real issue is that the features will randomly
come back during another reconfiguration which just happens to invoke
netdev_update_features(). The driver doesn't handle reconfiguring
two things at a time very robustly.

Starting with commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in
__bnxt_reserve_rings()") we only reconfigure the RSS hash table
if the "effective" number of Rx rings has changed. If HW-GRO is
enabled "effective" number of rings is 2x what user sees.
So if we are in the bad state, with HW-GRO re-enablement "pending"
after XDP off, and we lower the rings by / 2 - the HW-GRO rings
doing 2x and the ethtool -L doing / 2 may cancel each other out,
and the:

  if (old_rx_rings != bp->hw_resc.resv_rx_rings &&

condition in __bnxt_reserve_rings() will be false.
The RSS map won't get updated, and we'll crash with:

  BUG: kernel NULL pointer dereference, address: 0000000000000168
  RIP: 0010:__bnxt_hwrm_vnic_set_rss+0x13a/0x1a0
    bnxt_hwrm_vnic_rss_cfg_p5+0x47/0x180
    __bnxt_setup_vnic_p5+0x58/0x110
    bnxt_init_nic+0xb72/0xf50
    __bnxt_open_nic+0x40d/0xab0
    bnxt_open_nic+0x2b/0x60
    ethtool_set_channels+0x18c/0x1d0

As we try to access a freed ring.

The issue is present since XDP support was added, really, but
prior to commit 98ba1d931f61 ("bnxt_en: Fix RSS logic in
__bnxt_reserve_rings()") it wasn't causing major issues.

Fixes: 1054aee82321 ("bnxt_en: Use NETIF_F_GRO_HW.")
Fixes: 98ba1d931f61 ("bnxt_en: Fix RSS logic in __bnxt_reserve_rings()")
Reviewed-by: Michael Chan 
Reviewed-by: Somnath Kotur 
Link: https://patch.msgid.link/20250109043057.2888953-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski