From 7582207b1059129e59eb92026fca2cfc088a74fc Mon Sep 17 00:00:00 2001 From: Md Haris Iqbal Date: Thu, 25 Mar 2021 16:32:57 +0100 Subject: [PATCH 1/9] RDMA/rtrs-clt: Close rtrs client conn before destroying rtrs clt session files KASAN detected the following BUG: BUG: KASAN: use-after-free in rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client] Read of size 8 at addr ffff88bf2fb4adc0 by task swapper/0/0 CPU: 0 PID: 0 Comm: swapper/0 Tainted: G O 5.4.84-pserver #5.4.84-1+feature+linux+5.4.y+dbg+20201216.1319+b6b887b~deb10 Hardware name: Supermicro H8QG6/H8QG6, BIOS 3.00 09/04/2012 Call Trace: dump_stack+0x96/0xe0 print_address_description.constprop.4+0x1f/0x300 ? irq_work_claim+0x2e/0x50 __kasan_report.cold.8+0x78/0x92 ? rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client] kasan_report+0x10/0x20 rtrs_clt_update_wc_stats+0x41/0x100 [rtrs_client] rtrs_clt_rdma_done+0xb1/0x760 [rtrs_client] ? lockdep_hardirqs_on+0x1a8/0x290 ? process_io_rsp+0xb0/0xb0 [rtrs_client] ? mlx4_ib_destroy_cq+0x100/0x100 [mlx4_ib] ? add_interrupt_randomness+0x1a2/0x340 __ib_process_cq+0x97/0x100 [ib_core] ib_poll_handler+0x41/0xb0 [ib_core] irq_poll_softirq+0xe0/0x260 __do_softirq+0x127/0x672 irq_exit+0xd1/0xe0 do_IRQ+0xa3/0x1d0 common_interrupt+0xf/0xf RIP: 0010:cpuidle_enter_state+0xea/0x780 Code: 31 ff e8 99 48 47 ff 80 7c 24 08 00 74 12 9c 58 f6 c4 02 0f 85 53 05 00 00 31 ff e8 b0 6f 53 ff e8 ab 4f 5e ff fb 8b 44 24 04 <85> c0 0f 89 f3 01 00 00 48 8d 7b 14 e8 65 1e 77 ff c7 43 14 00 00 RSP: 0018:ffffffffab007d58 EFLAGS: 00000246 ORIG_RAX: ffffffffffffffca RAX: 0000000000000002 RBX: ffff88b803d69800 RCX: ffffffffa91a8298 RDX: 0000000000000007 RSI: dffffc0000000000 RDI: ffffffffab021414 RBP: ffffffffab6329e0 R08: 0000000000000002 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000002 R13: 000000bf39d82466 R14: ffffffffab632aa0 R15: ffffffffab632ae0 ? lockdep_hardirqs_on+0x1a8/0x290 ? cpuidle_enter_state+0xe5/0x780 cpuidle_enter+0x3c/0x60 do_idle+0x2fb/0x390 ? arch_cpu_idle_exit+0x40/0x40 ? schedule+0x94/0x120 cpu_startup_entry+0x19/0x1b start_kernel+0x5da/0x61b ? thread_stack_cache_init+0x6/0x6 ? load_ucode_amd_bsp+0x6f/0xc4 ? init_amd_microcode+0xa6/0xa6 ? x86_family+0x5/0x20 ? load_ucode_bsp+0x182/0x1fd secondary_startup_64+0xa4/0xb0 Allocated by task 5730: save_stack+0x19/0x80 __kasan_kmalloc.constprop.9+0xc1/0xd0 kmem_cache_alloc_trace+0x15b/0x350 alloc_sess+0xf4/0x570 [rtrs_client] rtrs_clt_open+0x3b4/0x780 [rtrs_client] find_and_get_or_create_sess+0x649/0x9d0 [rnbd_client] rnbd_clt_map_device+0xd7/0xf50 [rnbd_client] rnbd_clt_map_device_store+0x4ee/0x970 [rnbd_client] kernfs_fop_write+0x141/0x240 vfs_write+0xf3/0x280 ksys_write+0xba/0x150 do_syscall_64+0x68/0x270 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 5822: save_stack+0x19/0x80 __kasan_slab_free+0x125/0x170 kfree+0xe7/0x3f0 kobject_put+0xd3/0x240 rtrs_clt_destroy_sess_files+0x3f/0x60 [rtrs_client] rtrs_clt_close+0x3c/0x80 [rtrs_client] close_rtrs+0x45/0x80 [rnbd_client] rnbd_client_exit+0x10f/0x2bd [rnbd_client] __x64_sys_delete_module+0x27b/0x340 do_syscall_64+0x68/0x270 entry_SYSCALL_64_after_hwframe+0x49/0xbe When rtrs_clt_close is triggered, it iterates over all the present rtrs_clt_sess and triggers close on them. However, the call to rtrs_clt_destroy_sess_files is done before the rtrs_clt_close_conns. This is incorrect since during the initialization phase we allocate rtrs_clt_sess first, and then we go ahead and create rtrs_clt_con for it. If we free the rtrs_clt_sess structure before closing the rtrs_clt_con, it may so happen that an inflight IO completion would trigger the function rtrs_clt_rdma_done, which would lead to the above UAF case. Hence close the rtrs_clt_con connections first, and then trigger the destruction of session files. Fixes: 6a98d71daea1 ("RDMA/rtrs: client: main functionality") Link: https://lore.kernel.org/r/20210325153308.1214057-12-gi-oh.kim@ionos.com Signed-off-by: Md Haris Iqbal Signed-off-by: Jack Wang Signed-off-by: Gioh Kim Signed-off-by: Jason Gunthorpe --- drivers/infiniband/ulp/rtrs/rtrs-clt.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c index 0a08b4b742a3..6734329cca33 100644 --- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c +++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c @@ -2720,8 +2720,8 @@ void rtrs_clt_close(struct rtrs_clt *clt) /* Now it is safe to iterate over all paths without locks */ list_for_each_entry_safe(sess, tmp, &clt->paths_list, s.entry) { - rtrs_clt_destroy_sess_files(sess, NULL); rtrs_clt_close_conns(sess, true); + rtrs_clt_destroy_sess_files(sess, NULL); kobject_put(&sess->kobj); } free_clt(clt); From 7a2f91441b2c1d81b77c1cd816a4659f4abc9cbe Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 29 Mar 2021 18:35:07 +0200 Subject: [PATCH 2/9] s390/cpcmd: fix inline assembly register clobbering Register variables initialized using arithmetic. That leads to kasan instrumentaton code corrupting the registers contents. Follow GCC guidlines and use temporary variables for assigning init values to register variables. Fixes: 94c12cc7d196 ("[S390] Inline assembly cleanup.") Signed-off-by: Alexander Gordeev Acked-by: Ilya Leoshkevich Link: https://gcc.gnu.org/onlinedocs/gcc-10.2.0/gcc/Local-Register-Variables.html Signed-off-by: Heiko Carstens --- arch/s390/kernel/cpcmd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/s390/kernel/cpcmd.c b/arch/s390/kernel/cpcmd.c index af013b4244d3..2da027359798 100644 --- a/arch/s390/kernel/cpcmd.c +++ b/arch/s390/kernel/cpcmd.c @@ -37,10 +37,12 @@ static int diag8_noresponse(int cmdlen) static int diag8_response(int cmdlen, char *response, int *rlen) { + unsigned long _cmdlen = cmdlen | 0x40000000L; + unsigned long _rlen = *rlen; register unsigned long reg2 asm ("2") = (addr_t) cpcmd_buf; register unsigned long reg3 asm ("3") = (addr_t) response; - register unsigned long reg4 asm ("4") = cmdlen | 0x40000000L; - register unsigned long reg5 asm ("5") = *rlen; + register unsigned long reg4 asm ("4") = _cmdlen; + register unsigned long reg5 asm ("5") = _rlen; asm volatile( " diag %2,%0,0x8\n" From 08edb9683e47f5183aed9aa3f926292b54c278c1 Mon Sep 17 00:00:00 2001 From: Vasily Gorbik Date: Wed, 31 Mar 2021 11:44:50 +0200 Subject: [PATCH 3/9] s390/unwind: add machine check handler stack Fixes: b61b1595124a ("s390: add stack for machine check handler") Signed-off-by: Vasily Gorbik Signed-off-by: Heiko Carstens --- arch/s390/include/asm/stacktrace.h | 1 + arch/s390/kernel/dumpstack.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/arch/s390/include/asm/stacktrace.h b/arch/s390/include/asm/stacktrace.h index ee056f4a4fa3..2b543163d90a 100644 --- a/arch/s390/include/asm/stacktrace.h +++ b/arch/s390/include/asm/stacktrace.h @@ -12,6 +12,7 @@ enum stack_type { STACK_TYPE_IRQ, STACK_TYPE_NODAT, STACK_TYPE_RESTART, + STACK_TYPE_MCCK, }; struct stack_info { diff --git a/arch/s390/kernel/dumpstack.c b/arch/s390/kernel/dumpstack.c index 0dc4b258b98d..db1bc00229ca 100644 --- a/arch/s390/kernel/dumpstack.c +++ b/arch/s390/kernel/dumpstack.c @@ -79,6 +79,15 @@ static bool in_nodat_stack(unsigned long sp, struct stack_info *info) return in_stack(sp, info, STACK_TYPE_NODAT, top - THREAD_SIZE, top); } +static bool in_mcck_stack(unsigned long sp, struct stack_info *info) +{ + unsigned long frame_size, top; + + frame_size = STACK_FRAME_OVERHEAD + sizeof(struct pt_regs); + top = S390_lowcore.mcck_stack + frame_size; + return in_stack(sp, info, STACK_TYPE_MCCK, top - THREAD_SIZE, top); +} + static bool in_restart_stack(unsigned long sp, struct stack_info *info) { unsigned long frame_size, top; @@ -108,7 +117,8 @@ int get_stack_info(unsigned long sp, struct task_struct *task, /* Check per-cpu stacks */ if (!in_irq_stack(sp, info) && !in_nodat_stack(sp, info) && - !in_restart_stack(sp, info)) + !in_restart_stack(sp, info) && + !in_mcck_stack(sp, info)) goto unknown; recursion_check: From 85012e764d3a1be02297b23c1aa3467f0df212aa Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Sat, 3 Apr 2021 12:15:13 +0200 Subject: [PATCH 4/9] s390/irq: fix reading of ext_params2 field from lowcore The contents of the ext_params2 field of the lowcore should just be copied to the pt_regs structure, not dereferenced. Fixes crashes / program check loops like this: Krnl PSW : 0404c00180000000 00000000d6d02b3c (do_ext_irq+0x74/0x170) R:0 T:1 IO:0 EX:0 Key:0 M:1 W:0 P:0 AS:3 CC:0 PM:0 RI:0 EA:3 Krnl GPRS: 0000000000000000 80000000000b974e 00000000d71abee0 00000000d71abee0 0000000080030000 000000000000000f 0000000000000000 0000000000000000 0000000000000001 00000380000bf918 00000000d73ef780 00000380000bf518 0000000080348000 00000000d6d13350 00000000d6d02b1e 00000380000bf428 Krnl Code: 00000000d6d02b2e: 58100080 l %r1,128 00000000d6d02b32: 5010b0a4 st %r1,164(%r11) #00000000d6d02b36: e31001b80104 lg %r1,4536 >00000000d6d02b3c: e31010000004 lg %r1,0(%r1) 00000000d6d02b42: e310b0a80024 stg %r1,168(%r11) 00000000d6d02b48: c01000242270 larl %r1,00000000d7187028 00000000d6d02b4e: d5071000b010 clc 0(8,%r1),16(%r11) 00000000d6d02b54: a784001b brc 8,00000000d6d02b8a Call Trace: [<00000000d6d02b3c>] do_ext_irq+0x74/0x170 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4 [<00000000d621d266>] die+0x106/0x188 [<00000000d62305b8>] do_no_context+0xc8/0x100 [<00000000d6d02790>] __do_pgm_check+0xe0/0x1f0 [<00000000d6d0e950>] pgm_check_handler+0x118/0x160 [<00000000d6d02b3c>] do_ext_irq+0x74/0x170 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4 [<00000000d621d266>] die+0x106/0x188 [<00000000d62305b8>] do_no_context+0xc8/0x100 [<00000000d6d02790>] __do_pgm_check+0xe0/0x1f0 [<00000000d6d0e950>] pgm_check_handler+0x118/0x160 [<00000000d6d02b3c>] do_ext_irq+0x74/0x170 [<00000000d6d0ea5c>] ext_int_handler+0xc4/0xf4 [<0000000000000000>] 0x0 [<00000000d6d0e57a>] default_idle_call+0x42/0x110 [<00000000d629856e>] do_idle+0xce/0x160 [<00000000d62987be>] cpu_startup_entry+0x36/0x40 [<00000000d621f2f2>] smp_start_secondary+0x82/0x88 Cc: Sven Schnelle Cc: Vasily Gorbik Fixes: 56e62a737028 ("s390: convert to generic entry") Signed-off-by: Heiko Carstens --- arch/s390/kernel/irq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c index 601c21791338..714269e10eec 100644 --- a/arch/s390/kernel/irq.c +++ b/arch/s390/kernel/irq.c @@ -174,7 +174,7 @@ void noinstr do_ext_irq(struct pt_regs *regs) memcpy(®s->int_code, &S390_lowcore.ext_cpu_addr, 4); regs->int_parm = S390_lowcore.ext_params; - regs->int_parm_long = *(unsigned long *)S390_lowcore.ext_params2; + regs->int_parm_long = S390_lowcore.ext_params2; from_idle = !user_mode(regs) && regs->psw.addr == (unsigned long)psw_idle_exit; if (from_idle) From ad31a8c05196a3dc5283b193e9c74a72022d3c65 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 5 Apr 2021 22:32:27 +0200 Subject: [PATCH 5/9] s390/setup: use memblock_free_late() to free old stack Use memblock_free_late() to free the old machine check stack to the buddy allocator instead of leaking it. Fixes: b61b1595124a ("s390: add stack for machine check handler") Cc: Vasily Gorbik Acked-by: Sven Schnelle Signed-off-by: Heiko Carstens --- arch/s390/kernel/setup.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 60da976eee6f..72134f9f6ff5 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -354,7 +354,7 @@ static int __init stack_realloc(void) if (!new) panic("Couldn't allocate machine check stack"); WRITE_ONCE(S390_lowcore.mcck_stack, new + STACK_INIT_OFFSET); - memblock_free(old, THREAD_SIZE); + memblock_free_late(old, THREAD_SIZE); return 0; } early_initcall(stack_realloc); From 603c4690b01aaffe3a6c3605a429f6dac39852ae Mon Sep 17 00:00:00 2001 From: Potnuri Bharat Teja Date: Wed, 31 Mar 2021 19:27:15 +0530 Subject: [PATCH 6/9] RDMA/cxgb4: check for ipv6 address properly while destroying listener ipv6 bit is wrongly set by the below which causes fatal adapter lookup engine errors for ipv4 connections while destroying a listener. Fix it to properly check the local address for ipv6. Fixes: 3408be145a5d ("RDMA/cxgb4: Fix adapter LE hash errors while destroying ipv6 listening server") Link: https://lore.kernel.org/r/20210331135715.30072-1-bharat@chelsio.com Signed-off-by: Potnuri Bharat Teja Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/cxgb4/cm.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 81903749d241..e42c812e74c3 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3616,7 +3616,8 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id) c4iw_init_wr_wait(ep->com.wr_waitp); err = cxgb4_remove_server( ep->com.dev->rdev.lldi.ports[0], ep->stid, - ep->com.dev->rdev.lldi.rxq_ids[0], true); + ep->com.dev->rdev.lldi.rxq_ids[0], + ep->com.local_addr.ss_family == AF_INET6); if (err) goto done; err = c4iw_wait_for_reply(&ep->com.dev->rdev, ep->com.wr_waitp, From 5de61a47eb9064cbbc5f3360d639e8e34a690a54 Mon Sep 17 00:00:00 2001 From: Mike Marciniszyn Date: Mon, 29 Mar 2021 09:48:19 -0400 Subject: [PATCH 7/9] IB/hfi1: Fix probe time panic when AIP is enabled with a buggy BIOS A panic can result when AIP is enabled: BUG: unable to handle kernel NULL pointer dereference at 000000000000000 PGD 0 P4D 0 Oops: 0000 1 SMP PTI CPU: 70 PID: 981 Comm: systemd-udevd Tainted: G OE --------- - - 4.18.0-240.el8.x86_64 #1 Hardware name: Intel Corporation S2600KP/S2600KP, BIOS SE5C610.86B.01.01.0005.101720141054 10/17/2014 RIP: 0010:__bitmap_and+0x1b/0x70 RSP: 0018:ffff99aa0845f9f0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8d5a6fc18000 RCX: 0000000000000048 RDX: 0000000000000000 RSI: ffffffffc06336f0 RDI: ffff8d5a8fa67750 RBP: 0000000000000079 R08: 0000000fffffffff R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000001 R12: ffffffffc06336f0 R13: 00000000000000a0 R14: ffff8d5a6fc18000 R15: 0000000000000003 FS: 00007fec137a5980(0000) GS:ffff8d5a9fa80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 0000000a04b48002 CR4: 00000000001606e0 Call Trace: hfi1_num_netdev_contexts+0x7c/0x110 [hfi1] hfi1_init_dd+0xd7f/0x1a90 [hfi1] ? pci_bus_read_config_dword+0x49/0x70 ? pci_mmcfg_read+0x3e/0xe0 do_init_one.isra.18+0x336/0x640 [hfi1] local_pci_probe+0x41/0x90 pci_device_probe+0x105/0x1c0 really_probe+0x212/0x440 driver_probe_device+0x49/0xc0 device_driver_attach+0x50/0x60 __driver_attach+0x61/0x130 ? device_driver_attach+0x60/0x60 bus_for_each_dev+0x77/0xc0 ? klist_add_tail+0x3b/0x70 bus_add_driver+0x14d/0x1e0 ? dev_init+0x10b/0x10b [hfi1] driver_register+0x6b/0xb0 ? dev_init+0x10b/0x10b [hfi1] hfi1_mod_init+0x1e6/0x20a [hfi1] do_one_initcall+0x46/0x1c3 ? free_unref_page_commit+0x91/0x100 ? _cond_resched+0x15/0x30 ? kmem_cache_alloc_trace+0x140/0x1c0 do_init_module+0x5a/0x220 load_module+0x14b4/0x17e0 ? __do_sys_finit_module+0xa8/0x110 __do_sys_finit_module+0xa8/0x110 do_syscall_64+0x5b/0x1a0 The issue happens when pcibus_to_node() returns NO_NUMA_NODE. Fix this issue by moving the initialization of dd->node to hfi1_devdata allocation and remove the other pcibus_to_node() calls in the probe path and use dd->node instead. Affinity logic is adjusted to use a new field dd->affinity_entry as a guard instead of dd->node. Fixes: 4730f4a6c6b2 ("IB/hfi1: Activate the dummy netdev") Link: https://lore.kernel.org/r/1617025700-31865-4-git-send-email-dennis.dalessandro@cornelisnetworks.com Cc: stable@vger.kernel.org Signed-off-by: Mike Marciniszyn Signed-off-by: Dennis Dalessandro Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/hfi1/affinity.c | 21 +++++---------------- drivers/infiniband/hw/hfi1/hfi.h | 1 + drivers/infiniband/hw/hfi1/init.c | 10 +++++++++- drivers/infiniband/hw/hfi1/netdev_rx.c | 3 +-- 4 files changed, 16 insertions(+), 19 deletions(-) diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c index 2a91b8d95e12..04b1e8f021f6 100644 --- a/drivers/infiniband/hw/hfi1/affinity.c +++ b/drivers/infiniband/hw/hfi1/affinity.c @@ -632,22 +632,11 @@ static void _dev_comp_vect_cpu_mask_clean_up(struct hfi1_devdata *dd, */ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) { - int node = pcibus_to_node(dd->pcidev->bus); struct hfi1_affinity_node *entry; const struct cpumask *local_mask; int curr_cpu, possible, i, ret; bool new_entry = false; - /* - * If the BIOS does not have the NUMA node information set, select - * NUMA 0 so we get consistent performance. - */ - if (node < 0) { - dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); - node = 0; - } - dd->node = node; - local_mask = cpumask_of_node(dd->node); if (cpumask_first(local_mask) >= nr_cpu_ids) local_mask = topology_core_cpumask(0); @@ -660,7 +649,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) * create an entry in the global affinity structure and initialize it. */ if (!entry) { - entry = node_affinity_allocate(node); + entry = node_affinity_allocate(dd->node); if (!entry) { dd_dev_err(dd, "Unable to allocate global affinity node\n"); @@ -751,6 +740,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd) if (new_entry) node_affinity_add_tail(entry); + dd->affinity_entry = entry; mutex_unlock(&node_affinity.lock); return 0; @@ -766,10 +756,9 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) { struct hfi1_affinity_node *entry; - if (dd->node < 0) - return; - mutex_lock(&node_affinity.lock); + if (!dd->affinity_entry) + goto unlock; entry = node_affinity_lookup(dd->node); if (!entry) goto unlock; @@ -780,8 +769,8 @@ void hfi1_dev_affinity_clean_up(struct hfi1_devdata *dd) */ _dev_comp_vect_cpu_mask_clean_up(dd, entry); unlock: + dd->affinity_entry = NULL; mutex_unlock(&node_affinity.lock); - dd->node = NUMA_NO_NODE; } /* diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index e09e8244a94c..2a9a040569eb 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -1409,6 +1409,7 @@ struct hfi1_devdata { spinlock_t irq_src_lock; int vnic_num_vports; struct net_device *dummy_netdev; + struct hfi1_affinity_node *affinity_entry; /* Keeps track of IPoIB RSM rule users */ atomic_t ipoib_rsm_usr_num; diff --git a/drivers/infiniband/hw/hfi1/init.c b/drivers/infiniband/hw/hfi1/init.c index cb7ad1288821..786c6316273f 100644 --- a/drivers/infiniband/hw/hfi1/init.c +++ b/drivers/infiniband/hw/hfi1/init.c @@ -1277,7 +1277,6 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, dd->pport = (struct hfi1_pportdata *)(dd + 1); dd->pcidev = pdev; pci_set_drvdata(pdev, dd); - dd->node = NUMA_NO_NODE; ret = xa_alloc_irq(&hfi1_dev_table, &dd->unit, dd, xa_limit_32b, GFP_KERNEL); @@ -1287,6 +1286,15 @@ static struct hfi1_devdata *hfi1_alloc_devdata(struct pci_dev *pdev, goto bail; } rvt_set_ibdev_name(&dd->verbs_dev.rdi, "%s_%d", class_name(), dd->unit); + /* + * If the BIOS does not have the NUMA node information set, select + * NUMA 0 so we get consistent performance. + */ + dd->node = pcibus_to_node(pdev->bus); + if (dd->node == NUMA_NO_NODE) { + dd_dev_err(dd, "Invalid PCI NUMA node. Performance may be affected\n"); + dd->node = 0; + } /* * Initialize all locks for the device. This needs to be as early as diff --git a/drivers/infiniband/hw/hfi1/netdev_rx.c b/drivers/infiniband/hw/hfi1/netdev_rx.c index 1fb6e1a0e4e1..1bcab992ac26 100644 --- a/drivers/infiniband/hw/hfi1/netdev_rx.c +++ b/drivers/infiniband/hw/hfi1/netdev_rx.c @@ -173,8 +173,7 @@ u32 hfi1_num_netdev_contexts(struct hfi1_devdata *dd, u32 available_contexts, return 0; } - cpumask_and(node_cpu_mask, cpu_mask, - cpumask_of_node(pcibus_to_node(dd->pcidev->bus))); + cpumask_and(node_cpu_mask, cpu_mask, cpumask_of_node(dd->node)); available_cpus = cpumask_weight(node_cpu_mask); From e1ad897b9c738d5550be6762bf3a6ef1672259a4 Mon Sep 17 00:00:00 2001 From: Kamal Heib Date: Sun, 4 Apr 2021 15:55:01 +0300 Subject: [PATCH 8/9] RDMA/qedr: Fix kernel panic when trying to access recv_cq As INI QP does not require a recv_cq, avoid the following null pointer dereference by checking if the qp_type is not INI before trying to extract the recv_cq. BUG: kernel NULL pointer dereference, address: 00000000000000e0 #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page PGD 0 P4D 0 Oops: 0000 [#1] SMP PTI CPU: 0 PID: 54250 Comm: mpitests-IMB-MP Not tainted 5.12.0-rc5 #1 Hardware name: Dell Inc. PowerEdge R320/0KM5PX, BIOS 2.7.0 08/19/2019 RIP: 0010:qedr_create_qp+0x378/0x820 [qedr] Code: 02 00 00 50 e8 29 d4 a9 d1 48 83 c4 18 e9 65 fe ff ff 48 8b 53 10 48 8b 43 18 44 8b 82 e0 00 00 00 45 85 c0 0f 84 10 74 00 00 <8b> b8 e0 00 00 00 85 ff 0f 85 50 fd ff ff e9 fd 73 00 00 48 8d bd RSP: 0018:ffff9c8f056f7a70 EFLAGS: 00010202 RAX: 0000000000000000 RBX: ffff9c8f056f7b58 RCX: 0000000000000009 RDX: ffff8c41a9744c00 RSI: ffff9c8f056f7b58 RDI: ffff8c41c0dfa280 RBP: ffff8c41c0dfa280 R08: 0000000000000002 R09: 0000000000000001 R10: 0000000000000000 R11: ffff8c41e06fc608 R12: ffff8c4194052000 R13: 0000000000000000 R14: ffff8c4191546070 R15: ffff8c41c0dfa280 FS: 00007f78b2787b80(0000) GS:ffff8c43a3200000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00000000000000e0 CR3: 00000001011d6002 CR4: 00000000001706f0 Call Trace: ib_uverbs_handler_UVERBS_METHOD_QP_CREATE+0x4e4/0xb90 [ib_uverbs] ? ib_uverbs_cq_event_handler+0x30/0x30 [ib_uverbs] ib_uverbs_run_method+0x6f6/0x7a0 [ib_uverbs] ? ib_uverbs_handler_UVERBS_METHOD_QP_DESTROY+0x70/0x70 [ib_uverbs] ? __cond_resched+0x15/0x30 ? __kmalloc+0x5a/0x440 ib_uverbs_cmd_verbs+0x195/0x360 [ib_uverbs] ? xa_load+0x6e/0x90 ? cred_has_capability+0x7c/0x130 ? avc_has_extended_perms+0x17f/0x440 ? vma_link+0xae/0xb0 ? vma_set_page_prot+0x2a/0x60 ? mmap_region+0x298/0x6c0 ? do_mmap+0x373/0x520 ? selinux_file_ioctl+0x17f/0x220 ib_uverbs_ioctl+0xa7/0x110 [ib_uverbs] __x64_sys_ioctl+0x84/0xc0 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f78b120262b Fixes: 06e8d1df46ed ("RDMA/qedr: Add support for user mode XRC-SRQ's") Link: https://lore.kernel.org/r/20210404125501.154789-1-kamalheib1@gmail.com Signed-off-by: Kamal Heib Signed-off-by: Jason Gunthorpe --- drivers/infiniband/hw/qedr/verbs.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 0eb6a7a618e0..9ea542270ed4 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1244,7 +1244,8 @@ static int qedr_check_qp_attrs(struct ib_pd *ibpd, struct qedr_dev *dev, * TGT QP isn't associated with RQ/SQ */ if ((attrs->qp_type != IB_QPT_GSI) && (dev->gsi_qp_created) && - (attrs->qp_type != IB_QPT_XRC_TGT)) { + (attrs->qp_type != IB_QPT_XRC_TGT) && + (attrs->qp_type != IB_QPT_XRC_INI)) { struct qedr_cq *send_cq = get_qedr_cq(attrs->send_cq); struct qedr_cq *recv_cq = get_qedr_cq(attrs->recv_cq); From d1c803a9ccd7bd3aff5e989ccfb39ed3b799b975 Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Mon, 5 Apr 2021 10:44:34 +0300 Subject: [PATCH 9/9] RDMA/addr: Be strict with gid size The nla_len() is less than or equal to 16. If it's less than 16 then end of the "gid" buffer is uninitialized. Fixes: ae43f8286730 ("IB/core: Add IP to GID netlink offload") Link: https://lore.kernel.org/r/20210405074434.264221-1-leon@kernel.org Reported-by: Dan Carpenter Signed-off-by: Mark Bloch Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/addr.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c index 0abce004a959..65e3e7df8a4b 100644 --- a/drivers/infiniband/core/addr.c +++ b/drivers/infiniband/core/addr.c @@ -76,7 +76,9 @@ static struct workqueue_struct *addr_wq; static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = { [LS_NLA_TYPE_DGID] = {.type = NLA_BINARY, - .len = sizeof(struct rdma_nla_ls_gid)}, + .len = sizeof(struct rdma_nla_ls_gid), + .validation_type = NLA_VALIDATE_MIN, + .min = sizeof(struct rdma_nla_ls_gid)}, }; static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)