This is a note to let you know that I've just added the patch titled
IB/hfi1: Fix early init panic
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
ib-hfi1-fix-early-init-panic.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From f6a3cfec3c01f9983e961c3327cef0db129a3c43 Mon Sep 17 00:00:00 2001
From: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxxxxxxxxxxxxx>
Date: Mon, 29 Nov 2021 14:20:03 -0500
Subject: IB/hfi1: Fix early init panic
From: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxxxxxxxxxxxxx>
commit f6a3cfec3c01f9983e961c3327cef0db129a3c43 upstream.
The following trace can be observed with an init failure such as firmware
load failures:
BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
PGD 0 P4D 0
Oops: 0010 [#1] SMP PTI
CPU: 0 PID: 537 Comm: kworker/0:3 Tainted: G OE --------- - - 4.18.0-240.el8.x86_64 #1
Workqueue: events work_for_cpu_fn
RIP: 0010:0x0
Code: Bad RIP value.
RSP: 0000:ffffae5f878a3c98 EFLAGS: 00010046
RAX: 0000000000000000 RBX: ffff95e48e025c00 RCX: 0000000000000000
RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffff95e48e025c00
RBP: ffff95e4bf3660a4 R08: 0000000000000000 R09: ffffffff86d5e100
R10: ffff95e49e1de600 R11: 0000000000000001 R12: ffff95e4bf366180
R13: ffff95e48e025c00 R14: ffff95e4bf366028 R15: ffff95e4bf366000
FS: 0000000000000000(0000) GS:ffff95e4df200000(0000) knlGS:0000000000000000
CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: ffffffffffffffd6 CR3: 0000000f86a0a003 CR4: 00000000001606f0
Call Trace:
receive_context_interrupt+0x1f/0x40 [hfi1]
__free_irq+0x201/0x300
free_irq+0x2e/0x60
pci_free_irq+0x18/0x30
msix_free_irq.part.2+0x46/0x80 [hfi1]
msix_clean_up_interrupts+0x2b/0x70 [hfi1]
hfi1_init_dd+0x640/0x1a90 [hfi1]
do_init_one.isra.19+0x34d/0x680 [hfi1]
local_pci_probe+0x41/0x90
work_for_cpu_fn+0x16/0x20
process_one_work+0x1a7/0x360
worker_thread+0x1cf/0x390
? create_worker+0x1a0/0x1a0
kthread+0x112/0x130
? kthread_flush_work_fn+0x10/0x10
ret_from_fork+0x35/0x40
The free_irq() results in a callback to the registered interrupt handler,
and rcd->do_interrupt is NULL because the receive context data structures
are not fully initialized.
Fix by ensuring that the do_interrupt is always assigned and adding a
guards in the slow path handler to detect and handle a partially
initialized receive context and noop the receive.
Link: https://lore.kernel.org/r/20211129192003.101968.33612.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxx
Cc: stable@xxxxxxxxxxxxxxx
Fixes: b0ba3c18d6bf ("IB/hfi1: Move normal functions from hfi1_devdata to const array")
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Jason Gunthorpe <jgg@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/infiniband/hw/hfi1/chip.c | 2 ++
drivers/infiniband/hw/hfi1/driver.c | 2 ++
drivers/infiniband/hw/hfi1/init.c | 5 ++---
3 files changed, 6 insertions(+), 3 deletions(-)
--- a/drivers/infiniband/hw/hfi1/chip.c
+++ b/drivers/infiniband/hw/hfi1/chip.c
@@ -8414,6 +8414,8 @@ static void receive_interrupt_common(str
*/
static void __hfi1_rcd_eoi_intr(struct hfi1_ctxtdata *rcd)
{
+ if (!rcd->rcvhdrq)
+ return;
clear_recv_intr(rcd);
if (check_packet_present(rcd))
force_recv_intr(rcd);
--- a/drivers/infiniband/hw/hfi1/driver.c
+++ b/drivers/infiniband/hw/hfi1/driver.c
@@ -1011,6 +1011,8 @@ int handle_receive_interrupt(struct hfi1
struct hfi1_packet packet;
int skip_pkt = 0;
+ if (!rcd->rcvhdrq)
+ return RCV_PKT_OK;
/* Control context will always use the slow path interrupt handler */
needset = (rcd->ctxt == HFI1_CTRL_CTXT) ? 0 : 1;
--- a/drivers/infiniband/hw/hfi1/init.c
+++ b/drivers/infiniband/hw/hfi1/init.c
@@ -112,7 +112,6 @@ static int hfi1_create_kctxt(struct hfi1
rcd->fast_handler = get_dma_rtail_setting(rcd) ?
handle_receive_interrupt_dma_rtail :
handle_receive_interrupt_nodma_rtail;
- rcd->slow_handler = handle_receive_interrupt;
hfi1_set_seq_cnt(rcd, 1);
@@ -333,6 +332,8 @@ int hfi1_create_ctxtdata(struct hfi1_ppo
rcd->numa_id = numa;
rcd->rcv_array_groups = dd->rcv_entries.ngroups;
rcd->rhf_rcv_function_map = normal_rhf_rcv_functions;
+ rcd->slow_handler = handle_receive_interrupt;
+ rcd->do_interrupt = rcd->slow_handler;
rcd->msix_intr = CCE_NUM_MSIX_VECTORS;
mutex_init(&rcd->exp_mutex);
@@ -897,8 +898,6 @@ int hfi1_init(struct hfi1_devdata *dd, i
if (!rcd)
continue;
- rcd->do_interrupt = &handle_receive_interrupt;
-
lastfail = hfi1_create_rcvhdrq(dd, rcd);
if (!lastfail)
lastfail = hfi1_setup_eagerbufs(rcd);
Patches currently in stable-queue which might be from mike.marciniszyn@xxxxxxxxxxxxxxxxxxxx are
queue-5.15/ib-hfi1-insure-use-of-smp_processor_id-is-preempt-disabled.patch
queue-5.15/ib-hfi1-fix-early-init-panic.patch
queue-5.15/ib-hfi1-fix-leak-of-rcvhdrtail_dummy_kvaddr.patch
