mirror of
https://github.com/torvalds/linux.git
synced 2026-05-12 16:18:45 +02:00
95084f1883
During Function Level Reset recovery, the MANA driver reads
hardware BAR0 registers that may temporarily contain garbage values.
The SHM (Shared Memory) offset read from GDMA_REG_SHM_OFFSET is used
to compute gc->shm_base, which is later dereferenced via readl() in
mana_smc_poll_register(). If the hardware returns an unaligned or
out-of-range value, the driver must not blindly use it, as this would
propagate the hardware error into a kernel crash.
The following crash was observed on an arm64 Hyper-V guest running
kernel 6.17.0-3013-azure during VF reset recovery triggered by HWC
timeout.
[13291.785274] Unable to handle kernel paging request at virtual address ffff8000a200001b
[13291.785311] Mem abort info:
[13291.785332] ESR = 0x0000000096000021
[13291.785343] EC = 0x25: DABT (current EL), IL = 32 bits
[13291.785355] SET = 0, FnV = 0
[13291.785363] EA = 0, S1PTW = 0
[13291.785372] FSC = 0x21: alignment fault
[13291.785382] Data abort info:
[13291.785391] ISV = 0, ISS = 0x00000021, ISS2 = 0x00000000
[13291.785404] CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[13291.785412] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[13291.785421] swapper pgtable: 4k pages, 48-bit VAs, pgdp=00000014df3a1000
[13291.785432] [ffff8000a200001b] pgd=1000000100438403, p4d=1000000100438403, pud=1000000100439403, pmd=0068000fc2000711
[13291.785703] Internal error: Oops: 0000000096000021 [#1] SMP
[13291.830975] Modules linked in: tls qrtr mana_ib ib_uverbs ib_core xt_owner xt_tcpudp xt_conntrack nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nft_compat nf_tables cfg80211 8021q garp mrp stp llc binfmt_misc joydev serio_raw nls_iso8859_1 hid_generic aes_ce_blk aes_ce_cipher polyval_ce ghash_ce sm4_ce_gcm sm4_ce_ccm sm4_ce sm4_ce_cipher hid_hyperv sm4 sm3_ce sha3_ce hv_netvsc hid vmgenid hyperv_keyboard hyperv_drm sch_fq_codel nvme_fabrics efi_pstore dm_multipath nfnetlink vsock_loopback vmw_vsock_virtio_transport_common hv_sock vmw_vsock_vmci_transport vmw_vmci vsock dmi_sysfs ip_tables x_tables autofs4
[13291.862630] CPU: 122 UID: 0 PID: 61796 Comm: kworker/122:2 Tainted: G W 6.17.0-3013-azure #13-Ubuntu VOLUNTARY
[13291.869902] Tainted: [W]=WARN
[13291.871901] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 01/08/2026
[13291.878086] Workqueue: events mana_serv_func
[13291.880718] pstate: 62400005 (nZCv daif +PAN -UAO +TCO -DIT -SSBS BTYPE=--)
[13291.884835] pc : mana_smc_poll_register+0x48/0xb0
[13291.887902] lr : mana_smc_setup_hwc+0x70/0x1c0
[13291.890493] sp : ffff8000ab79bbb0
[13291.892364] x29: ffff8000ab79bbb0 x28: ffff00410c8b5900 x27: ffff00410d630680
[13291.896252] x26: ffff004171f9fd80 x25: 000000016ed55000 x24: 000000017f37e000
[13291.899990] x23: 0000000000000000 x22: 000000016ed55000 x21: 0000000000000000
[13291.904497] x20: ffff8000a200001b x19: 0000000000004e20 x18: ffff8000a6183050
[13291.908308] x17: 0000000000000000 x16: 0000000000000000 x15: 000000000000000a
[13291.912542] x14: 0000000000000004 x13: 0000000000000000 x12: 0000000000000000
[13291.916298] x11: 0000000000000000 x10: 0000000000000001 x9 : ffffc45006af1bd8
[13291.920945] x8 : ffff000151129000 x7 : 0000000000000000 x6 : 0000000000000000
[13291.925293] x5 : 000000015f214000 x4 : 000000017217a000 x3 : 000000016ed50000
[13291.930436] x2 : 000000016ed55000 x1 : 0000000000000000 x0 : ffff8000a1ffffff
[13291.934342] Call trace:
[13291.935736] mana_smc_poll_register+0x48/0xb0 (P)
[13291.938611] mana_smc_setup_hwc+0x70/0x1c0
[13291.941113] mana_hwc_create_channel+0x1a0/0x3a0
[13291.944283] mana_gd_setup+0x16c/0x398
[13291.946584] mana_gd_resume+0x24/0x70
[13291.948917] mana_do_service+0x13c/0x1d0
[13291.951583] mana_serv_func+0x34/0x68
[13291.953732] process_one_work+0x168/0x3d0
[13291.956745] worker_thread+0x2ac/0x480
[13291.959104] kthread+0xf8/0x110
[13291.961026] ret_from_fork+0x10/0x20
[13291.963560] Code: d2807d00 9417c551 71000673 54000220 (b9400281)
[13291.967299] ---[ end trace 0000000000000000 ]---
Disassembly of mana_smc_poll_register() around the crash site:
Disassembly of section .text:
00000000000047c8 <mana_smc_poll_register>:
47c8: d503201f nop
47cc: d503201f nop
47d0: d503233f paciasp
47d4: f800865e str x30, [x18], #8
47d8: a9bd7bfd stp x29, x30, [sp, #-48]!
47dc: 910003fd mov x29, sp
47e0: a90153f3 stp x19, x20, [sp, #16]
47e4: 91007014 add x20, x0, #0x1c
47e8: 5289c413 mov w19, #0x4e20
47ec: f90013f5 str x21, [sp, #32]
47f0: 12001c35 and w21, w1, #0xff
47f4: 14000008 b 4814 <mana_smc_poll_register+0x4c>
47f8: 36f801e1 tbz w1, #31, 4834 <mana_smc_poll_register+0x6c>
47fc: 52800042 mov w2, #0x2
4800: d280fa01 mov x1, #0x7d0
4804: d2807d00 mov x0, #0x3e8
4808: 94000000 bl 0 <usleep_range_state>
480c: 71000673 subs w19, w19, #0x1
4810: 54000200 b.eq 4850 <mana_smc_poll_register+0x88>
4814: b9400281 ldr w1, [x20] <-- **** CRASHED HERE *****
4818: d50331bf dmb oshld
481c: 2a0103e2 mov w2, w1
...
From the crash signature x20 = ffff8000a200001b, this address
ends in 0x1b which is not 4-byte aligned, so the 'ldr w1, [x20]'
instruction (readl) triggers the arm64 alignment fault (FSC = 0x21).
The root cause is in mana_gd_init_vf_regs(), which computes:
gc->shm_base = gc->bar0_va + mana_gd_r64(gc, GDMA_REG_SHM_OFFSET);
The offset is used without any validation. The same problem exists
in mana_gd_init_pf_regs() for sriov_base_off and sriov_shm_off.
Fix this by validating all offsets before use:
- VF: check shm_off is within BAR0, properly aligned to 4 bytes
(readl requirement), and leaves room for the full 256-bit
(32-byte) SMC aperture.
- PF: check sriov_base_off is within BAR0, aligned to 8 bytes
(readq requirement), and leaves room to safely read the
sriov_shm_off register at sriov_base_off + GDMA_PF_REG_SHM_OFF.
Then check sriov_shm_off leaves room for the full SMC aperture.
All arithmetic uses subtraction rather than addition to avoid
integer overflow on garbage values.
Define SMC_APERTURE_SIZE (32 bytes, derived from the 256-bit aperture
width)
Return -EPROTO on invalid values. The existing recovery path in
mana_serv_reset() already handles -EPROTO by falling through to PCI
device rescan, giving the hardware another chance to present valid
register values after reset.
Fixes:
|
||
|---|---|---|
| .. | ||
| 9p | ||
| bluetooth | ||
| iucv | ||
| libeth | ||
| mana | ||
| netfilter | ||
| netns | ||
| nfc | ||
| page_pool | ||
| phonet | ||
| phy | ||
| psp | ||
| sctp | ||
| tc_act | ||
| 6lowpan.h | ||
| act_api.h | ||
| addrconf.h | ||
| af_ieee802154.h | ||
| af_rxrpc.h | ||
| af_unix.h | ||
| af_vsock.h | ||
| ah.h | ||
| aligned_data.h | ||
| amt.h | ||
| arp.h | ||
| ax25.h | ||
| ax88796.h | ||
| bareudp.h | ||
| bond_3ad.h | ||
| bond_alb.h | ||
| bond_options.h | ||
| bonding.h | ||
| bpf_sk_storage.h | ||
| busy_poll.h | ||
| calipso.h | ||
| can.h | ||
| cfg80211-wext.h | ||
| cfg80211.h | ||
| cfg802154.h | ||
| checksum.h | ||
| cipso_ipv4.h | ||
| cls_cgroup.h | ||
| codel_impl.h | ||
| codel_qdisc.h | ||
| codel.h | ||
| compat.h | ||
| datalink.h | ||
| dcbevent.h | ||
| dcbnl.h | ||
| devlink.h | ||
| dropreason-core.h | ||
| dropreason-qdisc.h | ||
| dropreason.h | ||
| dsa_stubs.h | ||
| dsa.h | ||
| dscp.h | ||
| dsfield.h | ||
| dst_cache.h | ||
| dst_metadata.h | ||
| dst_ops.h | ||
| dst.h | ||
| eee.h | ||
| erspan.h | ||
| esp.h | ||
| espintcp.h | ||
| ethoc.h | ||
| failover.h | ||
| fib_notifier.h | ||
| fib_rules.h | ||
| firewire.h | ||
| flow_dissector.h | ||
| flow_offload.h | ||
| flow.h | ||
| fou.h | ||
| fq_impl.h | ||
| fq.h | ||
| garp.h | ||
| gen_stats.h | ||
| genetlink.h | ||
| geneve.h | ||
| gre.h | ||
| gro_cells.h | ||
| gro.h | ||
| gso.h | ||
| gtp.h | ||
| gue.h | ||
| handshake.h | ||
| hotdata.h | ||
| hwbm.h | ||
| icmp.h | ||
| ieee8021q.h | ||
| ieee80211_radiotap.h | ||
| ieee802154_netdev.h | ||
| if_inet6.h | ||
| ife.h | ||
| inet_common.h | ||
| inet_connection_sock.h | ||
| inet_dscp.h | ||
| inet_ecn.h | ||
| inet_frag.h | ||
| inet_hashtables.h | ||
| inet_sock.h | ||
| inet_timewait_sock.h | ||
| inet6_connection_sock.h | ||
| inet6_hashtables.h | ||
| inetpeer.h | ||
| ioam6.h | ||
| ip_fib.h | ||
| ip_tunnels.h | ||
| ip_vs.h | ||
| ip.h | ||
| ip6_checksum.h | ||
| ip6_fib.h | ||
| ip6_route.h | ||
| ip6_tunnel.h | ||
| ipcomp.h | ||
| ipconfig.h | ||
| ipv6_frag.h | ||
| ipv6.h | ||
| iw_handler.h | ||
| kcm.h | ||
| l3mdev.h | ||
| lag.h | ||
| lapb.h | ||
| llc_c_ac.h | ||
| llc_c_ev.h | ||
| llc_c_st.h | ||
| llc_conn.h | ||
| llc_if.h | ||
| llc_pdu.h | ||
| llc_s_ac.h | ||
| llc_s_ev.h | ||
| llc_s_st.h | ||
| llc_sap.h | ||
| llc.h | ||
| lwtunnel.h | ||
| mac80211.h | ||
| mac802154.h | ||
| macsec.h | ||
| mctp.h | ||
| mctpdevice.h | ||
| mip6.h | ||
| mld.h | ||
| mpls_iptunnel.h | ||
| mpls.h | ||
| mptcp.h | ||
| mrp.h | ||
| ncsi.h | ||
| ndisc.h | ||
| neighbour_tables.h | ||
| neighbour.h | ||
| net_debug.h | ||
| net_failover.h | ||
| net_namespace.h | ||
| net_ratelimit.h | ||
| net_shaper.h | ||
| net_trackers.h | ||
| netdev_lock.h | ||
| netdev_netlink.h | ||
| netdev_queues.h | ||
| netdev_rx_queue.h | ||
| netevent.h | ||
| netkit.h | ||
| netlabel.h | ||
| netlink.h | ||
| netmem.h | ||
| netprio_cgroup.h | ||
| nexthop.h | ||
| nl802154.h | ||
| nsh.h | ||
| pfcp.h | ||
| pie.h | ||
| ping.h | ||
| pkt_cls.h | ||
| pkt_sched.h | ||
| pptp.h | ||
| proto_memory.h | ||
| protocol.h | ||
| psample.h | ||
| psnap.h | ||
| psp.h | ||
| raw.h | ||
| rawv6.h | ||
| red.h | ||
| regulatory.h | ||
| request_sock.h | ||
| rose.h | ||
| route.h | ||
| rpl.h | ||
| rps-types.h | ||
| rps.h | ||
| rsi_91x.h | ||
| rstreason.h | ||
| rtnetlink.h | ||
| rtnh.h | ||
| sch_generic.h | ||
| sch_priv.h | ||
| scm.h | ||
| secure_seq.h | ||
| seg6_hmac.h | ||
| seg6_local.h | ||
| seg6.h | ||
| selftests.h | ||
| slhc_vj.h | ||
| smc.h | ||
| snmp.h | ||
| sock_reuseport.h | ||
| sock.h | ||
| Space.h | ||
| stp.h | ||
| strparser.h | ||
| switchdev.h | ||
| tc_wrapper.h | ||
| tcp_ao.h | ||
| tcp_ecn.h | ||
| tcp_states.h | ||
| tcp.h | ||
| tcx.h | ||
| timewait_sock.h | ||
| tipc.h | ||
| tls_prot.h | ||
| tls_toe.h | ||
| tls.h | ||
| transp_v6.h | ||
| tso.h | ||
| tun_proto.h | ||
| udp_tunnel.h | ||
| udp.h | ||
| vsock_addr.h | ||
| vxlan.h | ||
| wext.h | ||
| x25.h | ||
| x25device.h | ||
| xdp_priv.h | ||
| xdp_sock_drv.h | ||
| xdp_sock.h | ||
| xdp.h | ||
| xfrm.h | ||
| xsk_buff_pool.h | ||