linux_dsm_epyc7002/drivers/infiniband/core/restrack.c

269 lines
5.9 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
/*
* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
*/
#include <rdma/rdma_cm.h>
#include <rdma/ib_verbs.h>
#include <rdma/restrack.h>
#include <linux/mutex.h>
#include <linux/sched/task.h>
#include <linux/pid_namespace.h>
#include "cma_priv.h"
static int fill_res_noop(struct sk_buff *msg,
struct rdma_restrack_entry *entry)
{
return 0;
}
/**
* rdma_restrack_init() - initialize resource tracking
* @dev: IB device
*/
void rdma_restrack_init(struct ib_device *dev)
{
struct rdma_restrack_root *res = &dev->res;
init_rwsem(&res->rwsem);
res->fill_res_entry = fill_res_noop;
}
static const char *type2str(enum rdma_restrack_type type)
{
static const char * const names[RDMA_RESTRACK_MAX] = {
[RDMA_RESTRACK_PD] = "PD",
[RDMA_RESTRACK_CQ] = "CQ",
[RDMA_RESTRACK_QP] = "QP",
[RDMA_RESTRACK_CM_ID] = "CM_ID",
[RDMA_RESTRACK_MR] = "MR",
[RDMA_RESTRACK_CTX] = "CTX",
};
return names[type];
};
/**
* rdma_restrack_clean() - clean resource tracking
* @dev: IB device
*/
void rdma_restrack_clean(struct ib_device *dev)
{
struct rdma_restrack_root *res = &dev->res;
struct rdma_restrack_entry *e;
char buf[TASK_COMM_LEN];
const char *owner;
int bkt;
if (hash_empty(res->hash))
return;
dev = container_of(res, struct ib_device, res);
pr_err("restrack: %s", CUT_HERE);
dev_err(&dev->dev, "BUG: RESTRACK detected leak of resources\n");
hash_for_each(res->hash, bkt, e, node) {
if (rdma_is_kernel_res(e)) {
owner = e->kern_name;
} else {
/*
* There is no need to call get_task_struct here,
* because we can be here only if there are more
* get_task_struct() call than put_task_struct().
*/
get_task_comm(buf, e->task);
owner = buf;
}
pr_err("restrack: %s %s object allocated by %s is not freed\n",
rdma_is_kernel_res(e) ? "Kernel" : "User",
type2str(e->type), owner);
}
pr_err("restrack: %s", CUT_HERE);
}
/**
* rdma_restrack_count() - the current usage of specific object
* @dev: IB device
* @type: actual type of object to operate
* @ns: PID namespace
*/
int rdma_restrack_count(struct ib_device *dev, enum rdma_restrack_type type,
struct pid_namespace *ns)
{
struct rdma_restrack_root *res = &dev->res;
struct rdma_restrack_entry *e;
u32 cnt = 0;
down_read(&res->rwsem);
hash_for_each_possible(res->hash, e, node, type) {
if (ns == &init_pid_ns ||
(!rdma_is_kernel_res(e) &&
ns == task_active_pid_ns(e->task)))
cnt++;
}
up_read(&res->rwsem);
return cnt;
}
EXPORT_SYMBOL(rdma_restrack_count);
static void set_kern_name(struct rdma_restrack_entry *res)
{
struct ib_pd *pd;
switch (res->type) {
case RDMA_RESTRACK_QP:
pd = container_of(res, struct ib_qp, res)->pd;
if (!pd) {
WARN_ONCE(true, "XRC QPs are not supported\n");
/* Survive, despite the programmer's error */
res->kern_name = " ";
}
break;
case RDMA_RESTRACK_MR:
pd = container_of(res, struct ib_mr, res)->pd;
break;
default:
/* Other types set kern_name directly */
pd = NULL;
break;
}
if (pd)
res->kern_name = pd->res.kern_name;
}
static struct ib_device *res_to_dev(struct rdma_restrack_entry *res)
{
switch (res->type) {
case RDMA_RESTRACK_PD:
return container_of(res, struct ib_pd, res)->device;
case RDMA_RESTRACK_CQ:
return container_of(res, struct ib_cq, res)->device;
case RDMA_RESTRACK_QP:
return container_of(res, struct ib_qp, res)->device;
case RDMA_RESTRACK_CM_ID:
return container_of(res, struct rdma_id_private,
res)->id.device;
case RDMA_RESTRACK_MR:
return container_of(res, struct ib_mr, res)->device;
case RDMA_RESTRACK_CTX:
return container_of(res, struct ib_ucontext, res)->device;
default:
WARN_ONCE(true, "Wrong resource tracking type %u\n", res->type);
return NULL;
}
}
void rdma_restrack_set_task(struct rdma_restrack_entry *res,
const char *caller)
{
if (caller) {
res->kern_name = caller;
return;
}
if (res->task)
put_task_struct(res->task);
get_task_struct(current);
res->task = current;
}
EXPORT_SYMBOL(rdma_restrack_set_task);
static void rdma_restrack_add(struct rdma_restrack_entry *res)
{
struct ib_device *dev = res_to_dev(res);
if (!dev)
return;
if (res->type != RDMA_RESTRACK_CM_ID || rdma_is_kernel_res(res))
RDMA/restrack: Don't rely on uninitialized variable in restrack_add flow The restrack code relies on the fact that object structures are zeroed at the allocation stage, the mlx4 CQ wasn't allocated with kzalloc and it caused to the following crash. [ 137.392209] general protection fault: 0000 [#1] SMP KASAN PTI [ 137.392972] CPU: 0 PID: 622 Comm: ibv_rc_pingpong Tainted: G W 4.16.0-rc1-00099-g00313983cda6 #11 [ 137.395079] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-2.fc27 04/01/2014 [ 137.396866] RIP: 0010:rdma_restrack_del+0xc8/0xf0 [ 137.397762] RSP: 0018:ffff8801b54e7968 EFLAGS: 00010206 [ 137.399008] RAX: 0000000000000000 RBX: ffff8801d8bcbae8 RCX: ffffffffb82314df [ 137.400055] RDX: dffffc0000000000 RSI: dffffc0000000000 RDI: 70696b533d454741 [ 137.401103] RBP: ffff8801d90c07a0 R08: ffff8801d8bcbb00 R09: 0000000000000000 [ 137.402470] R10: 0000000000000001 R11: ffffed0036a9cf52 R12: ffff8801d90c0ad0 [ 137.403318] R13: ffff8801d853fb20 R14: ffff8801d8bcbb28 R15: 0000000000000014 [ 137.404736] FS: 00007fb415d43740(0000) GS:ffff8801e5c00000(0000) knlGS:0000000000000000 [ 137.406074] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 137.407101] CR2: 00007fb41557df20 CR3: 00000001b580c001 CR4: 00000000003606b0 [ 137.408308] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 137.409352] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 137.410385] Call Trace: [ 137.411058] ib_destroy_cq+0x23/0x60 [ 137.411460] uverbs_free_cq+0x37/0xa0 [ 137.412040] remove_commit_idr_uobject+0x38/0xf0 [ 137.413042] _rdma_remove_commit_uobject+0x5c/0x160 [ 137.413782] ? lookup_get_idr_uobject+0x39/0x50 [ 137.414737] rdma_remove_commit_uobject+0x3b/0x70 [ 137.415742] ib_uverbs_destroy_cq+0x114/0x1d0 [ 137.416260] ? ib_uverbs_req_notify_cq+0x160/0x160 [ 137.417073] ? kernel_text_address+0x5c/0x90 [ 137.417805] ? __kernel_text_address+0xe/0x30 [ 137.418766] ? unwind_get_return_address+0x2f/0x50 [ 137.419558] ib_uverbs_write+0x453/0x6a0 [ 137.420220] ? show_ibdev+0x90/0x90 [ 137.420653] ? __kasan_slab_free+0x136/0x180 [ 137.421155] ? kmem_cache_free+0x78/0x1e0 [ 137.422192] ? remove_vma+0x83/0x90 [ 137.422614] ? do_munmap+0x447/0x6c0 [ 137.423045] ? vm_munmap+0xb0/0x100 [ 137.423481] ? SyS_munmap+0x1d/0x30 [ 137.424120] ? do_syscall_64+0xeb/0x250 [ 137.424984] ? entry_SYSCALL_64_after_hwframe+0x21/0x86 [ 137.425611] ? lru_add_drain_all+0x270/0x270 [ 137.426116] ? lru_add_drain_cpu+0xa3/0x170 [ 137.426616] ? lru_add_drain+0x11/0x20 [ 137.427058] ? free_pages_and_swap_cache+0xa6/0x120 [ 137.427672] ? tlb_flush_mmu_free+0x78/0x90 [ 137.428168] ? arch_tlb_finish_mmu+0x6d/0xb0 [ 137.428680] __vfs_write+0xc4/0x350 [ 137.430917] ? kernel_read+0xa0/0xa0 [ 137.432758] ? remove_vma+0x90/0x90 [ 137.434781] ? __kasan_slab_free+0x14b/0x180 [ 137.437486] ? remove_vma+0x83/0x90 [ 137.439836] ? kmem_cache_free+0x78/0x1e0 [ 137.442195] ? percpu_counter_add_batch+0x1d/0x90 [ 137.444389] vfs_write+0xf7/0x280 [ 137.446030] SyS_write+0xa1/0x120 [ 137.447867] ? SyS_read+0x120/0x120 [ 137.449670] ? mm_fault_error+0x180/0x180 [ 137.451539] ? _cond_resched+0x16/0x50 [ 137.453697] ? SyS_read+0x120/0x120 [ 137.455883] do_syscall_64+0xeb/0x250 [ 137.457686] entry_SYSCALL_64_after_hwframe+0x21/0x86 [ 137.459595] RIP: 0033:0x7fb415637b94 [ 137.461315] RSP: 002b:00007ffdebea7d88 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 [ 137.463879] RAX: ffffffffffffffda RBX: 00005565022d1bd0 RCX: 00007fb415637b94 [ 137.466519] RDX: 0000000000000018 RSI: 00007ffdebea7da0 RDI: 0000000000000003 [ 137.469543] RBP: 00007ffdebea7d98 R08: 0000000000000000 R09: 00005565022d40c0 [ 137.472479] R10: 00000000000009cf R11: 0000000000000246 R12: 00005565022d2520 [ 137.475125] R13: 00000000000003e8 R14: 0000000000000000 R15: 00007ffdebea7fd0 [ 137.477760] Code: f7 e8 dd 0d 0b ff 48 c7 43 40 00 00 00 00 48 89 df e8 0d 0b 0b ff 48 8d 7b 28 c6 03 00 e8 41 0d 0b ff 48 8b 7b 28 48 85 ff 74 06 <f0> ff 4f 48 74 10 5b 48 89 ef 5d 41 5c 41 5d 41 5e e9 32 b0 ee [ 137.483375] RIP: rdma_restrack_del+0xc8/0xf0 RSP: ffff8801b54e7968 [ 137.486436] ---[ end trace 81835a1ea6722eed ]--- [ 137.488566] Kernel panic - not syncing: Fatal exception [ 137.491162] Kernel Offset: 0x36000000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) Fixes: 00313983cda6 ("RDMA/nldev: provide detailed CM_ID information") Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Steve Wise <swise@opengridcomputing.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-03-15 16:10:42 +07:00
res->task = NULL;
if (!rdma_is_kernel_res(res)) {
if (!res->task)
rdma_restrack_set_task(res, NULL);
res->kern_name = NULL;
} else {
set_kern_name(res);
}
kref_init(&res->kref);
init_completion(&res->comp);
res->valid = true;
down_write(&dev->res.rwsem);
hash_add(dev->res.hash, &res->node, res->type);
up_write(&dev->res.rwsem);
}
/**
* rdma_restrack_kadd() - add kernel object to the reource tracking database
* @res: resource entry
*/
void rdma_restrack_kadd(struct rdma_restrack_entry *res)
{
res->user = false;
rdma_restrack_add(res);
}
EXPORT_SYMBOL(rdma_restrack_kadd);
/**
* rdma_restrack_uadd() - add user object to the reource tracking database
* @res: resource entry
*/
void rdma_restrack_uadd(struct rdma_restrack_entry *res)
{
res->user = true;
rdma_restrack_add(res);
}
EXPORT_SYMBOL(rdma_restrack_uadd);
int __must_check rdma_restrack_get(struct rdma_restrack_entry *res)
{
return kref_get_unless_zero(&res->kref);
}
EXPORT_SYMBOL(rdma_restrack_get);
static void restrack_release(struct kref *kref)
{
struct rdma_restrack_entry *res;
res = container_of(kref, struct rdma_restrack_entry, kref);
complete(&res->comp);
}
int rdma_restrack_put(struct rdma_restrack_entry *res)
{
return kref_put(&res->kref, restrack_release);
}
EXPORT_SYMBOL(rdma_restrack_put);
void rdma_restrack_del(struct rdma_restrack_entry *res)
{
struct ib_device *dev;
if (!res->valid)
goto out;
dev = res_to_dev(res);
if (!dev)
return;
rdma_restrack_put(res);
wait_for_completion(&res->comp);
down_write(&dev->res.rwsem);
hash_del(&res->node);
res->valid = false;
up_write(&dev->res.rwsem);
out:
RDMA/restrack: Protect from reentry to resource return path Nullify the resource task struct pointer to ensure that subsequent calls won't try to release task_struct again. ------------[ cut here ]------------ ODEBUG: free active (active state 1) object type: rcu_head hint: (null) WARNING: CPU: 0 PID: 6048 at lib/debugobjects.c:329 debug_print_object+0x16a/0x210 lib/debugobjects.c:326 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 6048 Comm: syz-executor022 Not tainted 4.19.0-rc7-next-20181008+ #89 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x3ab lib/dump_stack.c:113 panic+0x238/0x4e7 kernel/panic.c:184 __warn.cold.8+0x163/0x1ba kernel/panic.c:536 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:debug_print_object+0x16a/0x210 lib/debugobjects.c:326 Code: 41 88 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 92 00 00 00 48 8b 14 dd 60 02 41 88 4c 89 fe 48 c7 c7 00 f8 40 88 e8 36 2f b4 fd <0f> 0b 83 05 a9 f4 5e 06 01 48 83 c4 18 5b 41 5c 41 5d 41 5e 41 5f RSP: 0018:ffff8801d8c3eda8 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8164d235 RDI: 0000000000000005 RBP: ffff8801d8c3ede8 R08: ffff8801d70aa280 R09: ffffed003b5c3eda R10: ffffed003b5c3eda R11: ffff8801dae1f6d7 R12: 0000000000000001 R13: ffffffff8939a760 R14: 0000000000000000 R15: ffffffff8840fca0 __debug_check_no_obj_freed lib/debugobjects.c:786 [inline] debug_check_no_obj_freed+0x3ae/0x58d lib/debugobjects.c:818 kmem_cache_free+0x202/0x290 mm/slab.c:3759 free_task_struct kernel/fork.c:163 [inline] free_task+0x16e/0x1f0 kernel/fork.c:457 __put_task_struct+0x2e6/0x620 kernel/fork.c:730 put_task_struct include/linux/sched/task.h:96 [inline] finish_task_switch+0x66c/0x900 kernel/sched/core.c:2715 context_switch kernel/sched/core.c:2834 [inline] __schedule+0x8d7/0x21d0 kernel/sched/core.c:3480 schedule+0xfe/0x460 kernel/sched/core.c:3524 freezable_schedule include/linux/freezer.h:172 [inline] futex_wait_queue_me+0x3f9/0x840 kernel/futex.c:2530 futex_wait+0x45c/0xa50 kernel/futex.c:2645 do_futex+0x31a/0x26d0 kernel/futex.c:3528 __do_sys_futex kernel/futex.c:3589 [inline] __se_sys_futex kernel/futex.c:3557 [inline] __x64_sys_futex+0x472/0x6a0 kernel/futex.c:3557 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x446549 Code: e8 2c b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f3a998f5da8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: ffffffffffffffda RBX: 00000000006dbc38 RCX: 0000000000446549 RDX: 0000000000000000 RSI: 0000000000000080 RDI: 00000000006dbc38 RBP: 00000000006dbc30 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dbc3c R13: 2f646e6162696e69 R14: 666e692f7665642f R15: 00000000006dbd2c Kernel Offset: disabled Reported-by: syzbot+71aff6ea121ffefc280f@syzkaller.appspotmail.com Fixes: ed7a01fd3fd7 ("RDMA/restrack: Release task struct which was hold by CM_ID object") Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-12 02:10:10 +07:00
if (res->task) {
put_task_struct(res->task);
RDMA/restrack: Protect from reentry to resource return path Nullify the resource task struct pointer to ensure that subsequent calls won't try to release task_struct again. ------------[ cut here ]------------ ODEBUG: free active (active state 1) object type: rcu_head hint: (null) WARNING: CPU: 0 PID: 6048 at lib/debugobjects.c:329 debug_print_object+0x16a/0x210 lib/debugobjects.c:326 Kernel panic - not syncing: panic_on_warn set ... CPU: 0 PID: 6048 Comm: syz-executor022 Not tainted 4.19.0-rc7-next-20181008+ #89 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x244/0x3ab lib/dump_stack.c:113 panic+0x238/0x4e7 kernel/panic.c:184 __warn.cold.8+0x163/0x1ba kernel/panic.c:536 report_bug+0x254/0x2d0 lib/bug.c:186 fixup_bug arch/x86/kernel/traps.c:178 [inline] do_error_trap+0x11b/0x200 arch/x86/kernel/traps.c:271 do_invalid_op+0x36/0x40 arch/x86/kernel/traps.c:290 invalid_op+0x14/0x20 arch/x86/entry/entry_64.S:969 RIP: 0010:debug_print_object+0x16a/0x210 lib/debugobjects.c:326 Code: 41 88 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 92 00 00 00 48 8b 14 dd 60 02 41 88 4c 89 fe 48 c7 c7 00 f8 40 88 e8 36 2f b4 fd <0f> 0b 83 05 a9 f4 5e 06 01 48 83 c4 18 5b 41 5c 41 5d 41 5e 41 5f RSP: 0018:ffff8801d8c3eda8 EFLAGS: 00010086 RAX: 0000000000000000 RBX: 0000000000000003 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff8164d235 RDI: 0000000000000005 RBP: ffff8801d8c3ede8 R08: ffff8801d70aa280 R09: ffffed003b5c3eda R10: ffffed003b5c3eda R11: ffff8801dae1f6d7 R12: 0000000000000001 R13: ffffffff8939a760 R14: 0000000000000000 R15: ffffffff8840fca0 __debug_check_no_obj_freed lib/debugobjects.c:786 [inline] debug_check_no_obj_freed+0x3ae/0x58d lib/debugobjects.c:818 kmem_cache_free+0x202/0x290 mm/slab.c:3759 free_task_struct kernel/fork.c:163 [inline] free_task+0x16e/0x1f0 kernel/fork.c:457 __put_task_struct+0x2e6/0x620 kernel/fork.c:730 put_task_struct include/linux/sched/task.h:96 [inline] finish_task_switch+0x66c/0x900 kernel/sched/core.c:2715 context_switch kernel/sched/core.c:2834 [inline] __schedule+0x8d7/0x21d0 kernel/sched/core.c:3480 schedule+0xfe/0x460 kernel/sched/core.c:3524 freezable_schedule include/linux/freezer.h:172 [inline] futex_wait_queue_me+0x3f9/0x840 kernel/futex.c:2530 futex_wait+0x45c/0xa50 kernel/futex.c:2645 do_futex+0x31a/0x26d0 kernel/futex.c:3528 __do_sys_futex kernel/futex.c:3589 [inline] __se_sys_futex kernel/futex.c:3557 [inline] __x64_sys_futex+0x472/0x6a0 kernel/futex.c:3557 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x446549 Code: e8 2c b3 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 2b 09 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007f3a998f5da8 EFLAGS: 00000246 ORIG_RAX: 00000000000000ca RAX: ffffffffffffffda RBX: 00000000006dbc38 RCX: 0000000000446549 RDX: 0000000000000000 RSI: 0000000000000080 RDI: 00000000006dbc38 RBP: 00000000006dbc30 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dbc3c R13: 2f646e6162696e69 R14: 666e692f7665642f R15: 00000000006dbd2c Kernel Offset: disabled Reported-by: syzbot+71aff6ea121ffefc280f@syzkaller.appspotmail.com Fixes: ed7a01fd3fd7 ("RDMA/restrack: Release task struct which was hold by CM_ID object") Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
2018-10-12 02:10:10 +07:00
res->task = NULL;
}
}
EXPORT_SYMBOL(rdma_restrack_del);