Hi Doug and Jason,
Here are two patches that would be good to land in the RC. One fixes a bug found by KASAN that was marked stable. The other fixes something that was introduced in the last release cycle.
Both patches are pretty small.
---
Michael J. Ruhl (1): IB/hfi1: Fix a latency issue for small messages
Piotr Stankiewicz (1): IB/hfi1: Fix an out-of-bounds access in get_hw_stats
drivers/infiniband/hw/hfi1/chip.c | 3 ++- drivers/infiniband/hw/hfi1/hfi.h | 2 ++ drivers/infiniband/hw/hfi1/qp.c | 7 +++++++ drivers/infiniband/hw/hfi1/verbs.c | 2 +- 4 files changed, 12 insertions(+), 2 deletions(-)
-- -Denny
From: Piotr Stankiewicz piotr.stankiewicz@intel.com
When running with KASAN, the following trace is produced:
[ 62.535888] ================================================================== [ 62.544930] BUG: KASAN: slab-out-of-bounds in gut_hw_stats+0x122/0x230 [hfi1] [ 62.553856] Write of size 8 at addr ffff88080e8d6330 by task kworker/0:1/14
[ 62.565333] CPU: 0 PID: 14 Comm: kworker/0:1 Not tainted 4.19.0-test-build-kasan+ #8 [ 62.575087] Hardware name: Intel Corporation S2600KPR/S2600KPR, BIOS SE5C610.86B.01.01.0019.101220160604 10/12/2016 [ 62.587951] Workqueue: events work_for_cpu_fn [ 62.594050] Call Trace: [ 62.598023] dump_stack+0xc6/0x14c [ 62.603089] ? dump_stack_print_info.cold.1+0x2f/0x2f [ 62.610041] ? kmsg_dump_rewind_nolock+0x59/0x59 [ 62.616615] ? get_hw_stats+0x122/0x230 [hfi1] [ 62.622985] print_address_description+0x6c/0x23c [ 62.629744] ? get_hw_stats+0x122/0x230 [hfi1] [ 62.636108] kasan_report.cold.6+0x241/0x308 [ 62.642365] get_hw_stats+0x122/0x230 [hfi1] [ 62.648703] ? hfi1_alloc_rn+0x40/0x40 [hfi1] [ 62.655088] ? __kmalloc+0x110/0x240 [ 62.660695] ? hfi1_alloc_rn+0x40/0x40 [hfi1] [ 62.667142] setup_hw_stats+0xd8/0x430 [ib_core] [ 62.673972] ? show_hfi+0x50/0x50 [hfi1] [ 62.680026] ib_device_register_sysfs+0x165/0x180 [ib_core] [ 62.687995] ib_register_device+0x5a2/0xa10 [ib_core] [ 62.695340] ? show_hfi+0x50/0x50 [hfi1] [ 62.701421] ? ib_unregister_device+0x2e0/0x2e0 [ib_core] [ 62.709222] ? __vmalloc_node_range+0x2d0/0x380 [ 62.716131] ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt] [ 62.723735] ? vmalloc_node+0x5c/0x70 [ 62.729697] ? rvt_driver_mr_init+0x11f/0x2d0 [rdmavt] [ 62.737347] ? rvt_driver_mr_init+0x1f5/0x2d0 [rdmavt] [ 62.744998] ? __rvt_alloc_mr+0x110/0x110 [rdmavt] [ 62.752315] ? rvt_rc_error+0x140/0x140 [rdmavt] [ 62.759434] ? rvt_vma_open+0x30/0x30 [rdmavt] [ 62.766364] ? mutex_unlock+0x1d/0x40 [ 62.772445] ? kmem_cache_create_usercopy+0x15d/0x230 [ 62.780115] rvt_register_device+0x1f6/0x360 [rdmavt] [ 62.787823] ? rvt_get_port_immutable+0x180/0x180 [rdmavt] [ 62.796058] ? __get_txreq+0x400/0x400 [hfi1] [ 62.802969] ? memcpy+0x34/0x50 [ 62.808611] hfi1_register_ib_device+0xde6/0xeb0 [hfi1] [ 62.816601] ? hfi1_get_npkeys+0x10/0x10 [hfi1] [ 62.823760] ? hfi1_init+0x89f/0x9a0 [hfi1] [ 62.830469] ? hfi1_setup_eagerbufs+0xad0/0xad0 [hfi1] [ 62.838204] ? pcie_capability_clear_and_set_word+0xcd/0xe0 [ 62.846429] ? pcie_capability_read_word+0xd0/0xd0 [ 62.853791] ? hfi1_pcie_init+0x187/0x4b0 [hfi1] [ 62.860958] init_one+0x67f/0xae0 [hfi1] [ 62.867301] ? hfi1_init+0x9a0/0x9a0 [hfi1] [ 62.873876] ? wait_woken+0x130/0x130 [ 62.879860] ? read_word_at_a_time+0xe/0x20 [ 62.886329] ? strscpy+0x14b/0x280 [ 62.891998] ? hfi1_init+0x9a0/0x9a0 [hfi1] [ 62.898405] local_pci_probe+0x70/0xd0 [ 62.904295] ? pci_device_shutdown+0x90/0x90 [ 62.910833] work_for_cpu_fn+0x29/0x40 [ 62.916750] process_one_work+0x584/0x960 [ 62.922974] ? rcu_work_rcufn+0x40/0x40 [ 62.928991] ? __schedule+0x396/0xdc0 [ 62.934806] ? __sched_text_start+0x8/0x8 [ 62.941020] ? pick_next_task_fair+0x68b/0xc60 [ 62.947674] ? run_rebalance_domains+0x260/0x260 [ 62.954471] ? __list_add_valid+0x29/0xa0 [ 62.960607] ? move_linked_works+0x1c7/0x230 [ 62.967077] ? trace_event_raw_event_workqueue_execute_start+0x140/0x140 [ 62.976248] ? mutex_lock+0xa6/0x100 [ 62.982029] ? __mutex_lock_slowpath+0x10/0x10 [ 62.988795] ? __switch_to+0x37a/0x710 [ 62.994731] worker_thread+0x62e/0x9d0 [ 63.000602] ? max_active_store+0xf0/0xf0 [ 63.006828] ? __switch_to_asm+0x40/0x70 [ 63.012932] ? __switch_to_asm+0x34/0x70 [ 63.019013] ? __switch_to_asm+0x40/0x70 [ 63.025042] ? __switch_to_asm+0x34/0x70 [ 63.031030] ? __switch_to_asm+0x40/0x70 [ 63.037006] ? __schedule+0x396/0xdc0 [ 63.042660] ? kmem_cache_alloc_trace+0xf3/0x1f0 [ 63.049323] ? kthread+0x59/0x1d0 [ 63.054594] ? ret_from_fork+0x35/0x40 [ 63.060257] ? __sched_text_start+0x8/0x8 [ 63.066212] ? schedule+0xcf/0x250 [ 63.071529] ? __wake_up_common+0x110/0x350 [ 63.077794] ? __schedule+0xdc0/0xdc0 [ 63.083348] ? wait_woken+0x130/0x130 [ 63.088963] ? finish_task_switch+0x1f1/0x520 [ 63.095258] ? kasan_unpoison_shadow+0x30/0x40 [ 63.101792] ? __init_waitqueue_head+0xa0/0xd0 [ 63.108183] ? replenish_dl_entity.cold.60+0x18/0x18 [ 63.115151] ? _raw_spin_lock_irqsave+0x25/0x50 [ 63.121754] ? max_active_store+0xf0/0xf0 [ 63.127753] kthread+0x1ae/0x1d0 [ 63.132894] ? kthread_bind+0x30/0x30 [ 63.138422] ret_from_fork+0x35/0x40
[ 63.146973] Allocated by task 14: [ 63.152077] kasan_kmalloc+0xbf/0xe0 [ 63.157471] __kmalloc+0x110/0x240 [ 63.162804] init_cntrs+0x34d/0xdf0 [hfi1] [ 63.168883] hfi1_init_dd+0x29a3/0x2f90 [hfi1] [ 63.175244] init_one+0x551/0xae0 [hfi1] [ 63.181065] local_pci_probe+0x70/0xd0 [ 63.186759] work_for_cpu_fn+0x29/0x40 [ 63.192310] process_one_work+0x584/0x960 [ 63.198163] worker_thread+0x62e/0x9d0 [ 63.203843] kthread+0x1ae/0x1d0 [ 63.208874] ret_from_fork+0x35/0x40
[ 63.217203] Freed by task 1: [ 63.221844] __kasan_slab_free+0x12e/0x180 [ 63.227844] kfree+0x92/0x1a0 [ 63.232570] single_release+0x3a/0x60 [ 63.238024] __fput+0x1d9/0x480 [ 63.242911] task_work_run+0x139/0x190 [ 63.248440] exit_to_usermode_loop+0x191/0x1a0 [ 63.254814] do_syscall_64+0x301/0x330 [ 63.260283] entry_SYSCALL_64_after_hwframe+0x44/0xa9
[ 63.270199] The buggy address belongs to the object at ffff88080e8d5500 which belongs to the cache kmalloc-4096 of size 4096 [ 63.287247] The buggy address is located 3632 bytes inside of 4096-byte region [ffff88080e8d5500, ffff88080e8d6500) [ 63.303564] The buggy address belongs to the page: [ 63.310447] page:ffffea00203a3400 count:1 mapcount:0 mapping:ffff88081380e840 index:0x0 compound_mapcount: 0 [ 63.323102] flags: 0x2fffff80008100(slab|head) [ 63.329775] raw: 002fffff80008100 0000000000000000 0000000100000001 ffff88081380e840 [ 63.340175] raw: 0000000000000000 0000000000070007 00000001ffffffff 0000000000000000 [ 63.350564] page dumped because: kasan: bad access detected
[ 63.361974] Memory state around the buggy address: [ 63.369137] ffff88080e8d6200: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 63.379082] ffff88080e8d6280: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 63.389032] >ffff88080e8d6300: 00 00 00 00 00 00 fc fc fc fc fc fc fc fc fc fc [ 63.398944] ^ [ 63.406141] ffff88080e8d6380: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 63.416109] ffff88080e8d6400: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 63.426099] ==================================================================
The trace happens because get_hw_stats() assumes there is room in the memory allocated in init_cntrs() to accommodate the driver counters. Unfortunately, that routine only allocated space for the device counters.
Fix by insuring the allocation has room for the additional driver counters.
Cc: Stable@vger.kernel.org # v4.14+ Fixes: b7481944b06e9 ("IB/hfi1: Show statistics counters under IB stats interface") Reviewed-by: Mike Marciniczyn mike.marciniszyn@intel.com Reviewed-by: Mike Ruhl michael.j.ruhl@intel.com Signed-off-by: Piotr Stankiewicz piotr.stankiewicz@intel.com Signed-off-by: Dennis Dalessandro dennis.dalessandro@intel.com --- drivers/infiniband/hw/hfi1/chip.c | 3 ++- drivers/infiniband/hw/hfi1/hfi.h | 2 ++ drivers/infiniband/hw/hfi1/verbs.c | 2 +- 3 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 9b20479..7e6d709 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12500,7 +12500,8 @@ static int init_cntrs(struct hfi1_devdata *dd) }
/* allocate space for the counter values */ - dd->cntrs = kcalloc(dd->ndevcntrs, sizeof(u64), GFP_KERNEL); + dd->cntrs = kcalloc(dd->ndevcntrs + num_driver_cntrs, sizeof(u64), + GFP_KERNEL); if (!dd->cntrs) goto bail;
diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1401b6e..2b88234 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -155,6 +155,8 @@ struct hfi1_ib_stats { extern struct hfi1_ib_stats hfi1_stats; extern const struct pci_error_handlers hfi1_pci_err_handler;
+extern int num_driver_cntrs; + /* * First-cut criterion for "device is active" is * two thousand dwords combined Tx, Rx traffic per diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 48e11e5..a365089 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1479,7 +1479,7 @@ static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str) static DEFINE_MUTEX(cntr_names_lock); /* protects the *_cntr_names bufers */ static const char **dev_cntr_names; static const char **port_cntr_names; -static int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); +int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); static int num_dev_cntrs; static int num_port_cntrs; static int cntr_names_initialized;
On Wed, 2018-11-28 at 06:44 -0800, Dennis Dalessandro wrote:
Hi Doug and Jason,
Here are two patches that would be good to land in the RC. One fixes a bug found by KASAN that was marked stable. The other fixes something that was introduced in the last release cycle.
Both patches are pretty small.
The first patch was more of a performance issue than a true bugfix. I took it, but mainly because it was small and the commit message implied the regression was significant.
Michael J. Ruhl (1): IB/hfi1: Fix a latency issue for small messages
Piotr Stankiewicz (1): IB/hfi1: Fix an out-of-bounds access in get_hw_stats
drivers/infiniband/hw/hfi1/chip.c | 3 ++- drivers/infiniband/hw/hfi1/hfi.h | 2 ++ drivers/infiniband/hw/hfi1/qp.c | 7 +++++++ drivers/infiniband/hw/hfi1/verbs.c | 2 +- 4 files changed, 12 insertions(+), 2 deletions(-)
-- -Denny
linux-stable-mirror@lists.linaro.org