79cb2bbefa
commit e6f57c6881916df39db7d95981a8ad2b9c3458d6 upstream. Unfortunately the commit `fd8958efe877` introduced another error causing the `descs` array to overflow. This reults in further crashes easily reproducible by `sendmsg` system call. [ 1080.836473] general protection fault, probably for non-canonical address 0x400300015528b00a: 0000 [#1] PREEMPT SMP PTI [ 1080.869326] RIP: 0010:hfi1_ipoib_build_ib_tx_headers.constprop.0+0xe1/0x2b0 [hfi1] -- [ 1080.974535] Call Trace: [ 1080.976990] <TASK> [ 1081.021929] hfi1_ipoib_send_dma_common+0x7a/0x2e0 [hfi1] [ 1081.027364] hfi1_ipoib_send_dma_list+0x62/0x270 [hfi1] [ 1081.032633] hfi1_ipoib_send+0x112/0x300 [hfi1] [ 1081.042001] ipoib_start_xmit+0x2a9/0x2d0 [ib_ipoib] [ 1081.046978] dev_hard_start_xmit+0xc4/0x210 -- [ 1081.148347] __sys_sendmsg+0x59/0xa0 crash> ipoib_txreq 0xffff9cfeba229f00 struct ipoib_txreq { txreq = { list = { next = 0xffff9cfeba229f00, prev = 0xffff9cfeba229f00 }, descp = 0xffff9cfeba229f40, coalesce_buf = 0x0, wait = 0xffff9cfea4e69a48, complete = 0xffffffffc0fe0760 <hfi1_ipoib_sdma_complete>, packet_len = 0x46d, tlen = 0x0, num_desc = 0x0, desc_limit = 0x6, next_descq_idx = 0x45c, coalesce_idx = 0x0, flags = 0x0, descs = {{ qw = {0x8024000120dffb00, 0x4} # SDMA_DESC0_FIRST_DESC_FLAG (bit 63) }, { qw = { 0x3800014231b108, 0x4} }, { qw = { 0x310000e4ee0fcf0, 0x8} }, { qw = { 0x3000012e9f8000, 0x8} }, { qw = { 0x59000dfb9d0000, 0x8} }, { qw = { 0x78000e02e40000, 0x8} }} }, sdma_hdr = 0x400300015528b000, <<< invalid pointer in the tx request structure sdma_status = 0x0, SDMA_DESC0_LAST_DESC_FLAG (bit 62) complete = 0x0, priv = 0x0, txq = 0xffff9cfea4e69880, skb = 0xffff9d099809f400 } If an SDMA send consists of exactly 6 descriptors and requires dword padding (in the 7th descriptor), the sdma_txreq descriptor array is not properly expanded and the packet will overflow into the container structure. This results in a panic when the send completion runs. The exact panic varies depending on what elements of the container structure get corrupted. The fix is to use the correct expression in _pad_sdma_tx_descs() to test the need to expand the descriptor array. With this patch the crashes are no longer reproducible and the machine is stable. Fixes: fd8958efe877 ("IB/hfi1: Fix sdma.h tx->num_descs off-by-one errors") Cc: stable@vger.kernel.org Reported-by: Mats Kronberg <kronberg@nsc.liu.se> Tested-by: Mats Kronberg <kronberg@nsc.liu.se> Signed-off-by: Daniel Vacek <neelx@redhat.com> Link: https://lore.kernel.org/r/20240201081009.1109442-1-neelx@redhat.com Signed-off-by: Leon Romanovsky <leon@kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> |
||
---|---|---|
.. | ||
affinity.c | ||
affinity.h | ||
aspm.c | ||
aspm.h | ||
chip.c | ||
chip.h | ||
chip_registers.h | ||
common.h | ||
debugfs.c | ||
debugfs.h | ||
device.c | ||
device.h | ||
driver.c | ||
efivar.c | ||
efivar.h | ||
eprom.c | ||
eprom.h | ||
exp_rcv.c | ||
exp_rcv.h | ||
fault.c | ||
fault.h | ||
file_ops.c | ||
firmware.c | ||
hfi.h | ||
init.c | ||
intr.c | ||
iowait.c | ||
iowait.h | ||
ipoib.h | ||
ipoib_main.c | ||
ipoib_rx.c | ||
ipoib_tx.c | ||
Kconfig | ||
mad.c | ||
mad.h | ||
Makefile | ||
mmu_rb.c | ||
mmu_rb.h | ||
msix.c | ||
msix.h | ||
netdev.h | ||
netdev_rx.c | ||
opa_compat.h | ||
opfn.c | ||
opfn.h | ||
pcie.c | ||
pio.c | ||
pio.h | ||
pio_copy.c | ||
platform.c | ||
platform.h | ||
qp.c | ||
qp.h | ||
qsfp.c | ||
qsfp.h | ||
rc.c | ||
rc.h | ||
ruc.c | ||
sdma.c | ||
sdma.h | ||
sdma_txreq.h | ||
sysfs.c | ||
tid_rdma.c | ||
tid_rdma.h | ||
trace.c | ||
trace.h | ||
trace_ctxts.h | ||
trace_dbg.h | ||
trace_ibhdrs.h | ||
trace_iowait.h | ||
trace_misc.h | ||
trace_mmu.h | ||
trace_rc.h | ||
trace_rx.h | ||
trace_tid.h | ||
trace_tx.h | ||
uc.c | ||
ud.c | ||
user_exp_rcv.c | ||
user_exp_rcv.h | ||
user_pages.c | ||
user_sdma.c | ||
user_sdma.h | ||
verbs.c | ||
verbs.h | ||
verbs_txreq.c | ||
verbs_txreq.h | ||
vnic.h | ||
vnic_main.c | ||
vnic_sdma.c |