From 425784aa5b029eeb80498c73a68f62c3ad1d3b3f Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Thu, 24 Jan 2019 14:33:12 +0200 Subject: IB/uverbs: Fix OOPs upon device disassociation The async_file might be freed before the disassociation has been ended, causing qp shutdown to use after free on it. Since uverbs_destroy_ufile_hw is not a fence, it returns if a disassociation is ongoing in another thread. It has to be written this way to avoid deadlock. However this means that the ufile FD close cannot destroy anything that may still be used by an active kref, such as the the async_file. To fix that move the kref_put() to be in ib_uverbs_release_file(). BUG: unable to handle kernel paging request at ffffffffba682787 PGD bc80e067 P4D bc80e067 PUD bc80f063 PMD 1313df163 PTE 80000000bc682061 Oops: 0003 [#1] SMP PTI CPU: 1 PID: 32410 Comm: bash Tainted: G OE 4.20.0-rc6+ #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__pv_queued_spin_lock_slowpath+0x1b3/0x2a0 Code: 98 83 e2 60 49 89 df 48 8b 04 c5 80 18 72 ba 48 8d ba 80 32 02 00 ba 00 80 00 00 4c 8d 65 14 41 bd 01 00 00 00 48 01 c7 85 d2 <48> 89 2f 48 89 fb 74 14 8b 45 08 85 c0 75 42 84 d2 74 6b f3 90 83 RSP: 0018:ffffc1bbc064fb58 EFLAGS: 00010006 RAX: ffffffffba65f4e7 RBX: ffff9f209c656c00 RCX: 0000000000000001 RDX: 0000000000008000 RSI: 0000000000000000 RDI: ffffffffba682787 RBP: ffff9f217bb23280 R08: 0000000000000001 R09: 0000000000000000 R10: ffff9f209d2c7800 R11: ffffffffffffffe8 R12: ffff9f217bb23294 R13: 0000000000000001 R14: 0000000000000000 R15: ffff9f209c656c00 FS: 00007fac55aad740(0000) GS:ffff9f217bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffba682787 CR3: 000000012f8e0000 CR4: 00000000000006e0 Call Trace: _raw_spin_lock_irq+0x27/0x30 ib_uverbs_release_uevent+0x1e/0xa0 [ib_uverbs] uverbs_free_qp+0x7e/0x90 [ib_uverbs] destroy_hw_idr_uobject+0x1c/0x50 [ib_uverbs] uverbs_destroy_uobject+0x2e/0x180 [ib_uverbs] __uverbs_cleanup_ufile+0x73/0x90 [ib_uverbs] uverbs_destroy_ufile_hw+0x5d/0x120 [ib_uverbs] ib_uverbs_remove_one+0xea/0x240 [ib_uverbs] ib_unregister_device+0xfb/0x200 [ib_core] mlx5_ib_remove+0x51/0xe0 [mlx5_ib] mlx5_remove_device+0xc1/0xd0 [mlx5_core] mlx5_unregister_device+0x3d/0xb0 [mlx5_core] remove_one+0x2a/0x90 [mlx5_core] pci_device_remove+0x3b/0xc0 device_release_driver_internal+0x16d/0x240 unbind_store+0xb2/0x100 kernfs_fop_write+0x102/0x180 __vfs_write+0x36/0x1a0 ? __alloc_fd+0xa9/0x170 ? set_close_on_exec+0x49/0x70 vfs_write+0xad/0x1a0 ksys_write+0x52/0xc0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7fac551aac60 Cc: # 4.2 Fixes: 036b10635739 ("IB/uverbs: Enable device removal when there are active user space applications") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_main.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'drivers/infiniband/core/uverbs_main.c') diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 2890a77339e1..15add0688fbb 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -204,6 +204,9 @@ void ib_uverbs_release_file(struct kref *ref) if (atomic_dec_and_test(&file->device->refcount)) ib_uverbs_comp_dev(file->device); + if (file->async_file) + kref_put(&file->async_file->ref, + ib_uverbs_release_async_event_file); put_device(&file->device->dev); kfree(file); } @@ -1096,10 +1099,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp) list_del_init(&file->list); mutex_unlock(&file->device->lists_mutex); - if (file->async_file) - kref_put(&file->async_file->ref, - ib_uverbs_release_async_event_file); - kref_put(&file->ref, ib_uverbs_release_file); return 0; -- cgit v1.2.3-70-g09d2 From 7b21b69ab203136fdc153c7707fa6c409e523c2e Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 27 Jan 2019 10:11:27 +0200 Subject: IB/uverbs: Fix OOPs in uverbs_user_mmap_disassociate The vma->vm_mm can become impossible to get before rdma_umap_close() is called, in this case we must not try to get an mm that is already undergoing process exit. In this case there is no need to wait for anything as the VMA will be destroyed by another thread soon and is already effectively 'unreachable' by userspace. BUG: unable to handle kernel NULL pointer dereference at 0000000000000000 PGD 800000012bc50067 P4D 800000012bc50067 PUD 129db5067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 1 PID: 2050 Comm: bash Tainted: G W OE 4.20.0-rc6+ #3 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:__rb_erase_color+0xb9/0x280 Code: 84 17 01 00 00 48 3b 68 10 0f 84 15 01 00 00 48 89 58 08 48 89 de 48 89 ef 4c 89 e3 e8 90 84 22 00 e9 60 ff ff ff 48 8b 5d 10 03 01 0f 84 9c 00 00 00 48 8b 43 10 48 85 c0 74 09 f6 00 01 0f RSP: 0018:ffffbecfc090bab8 EFLAGS: 00010246 RAX: ffff97616346cf30 RBX: 0000000000000000 RCX: 0000000000000101 RDX: 0000000000000000 RSI: ffff97623b6ca828 RDI: ffff97621ef10828 RBP: ffff97621ef10828 R08: ffff97621ef10828 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000000 R12: ffff97623b6ca838 R13: ffffffffbb3fef50 R14: ffff97623b6ca828 R15: 0000000000000000 FS: 00007f7a5c31d740(0000) GS:ffff97623bb00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000000 CR3: 000000011255a000 CR4: 00000000000006e0 Call Trace: unlink_file_vma+0x3b/0x50 free_pgtables+0xa1/0x110 exit_mmap+0xca/0x1a0 ? mlx5_ib_dealloc_pd+0x28/0x30 [mlx5_ib] mmput+0x54/0x140 uverbs_user_mmap_disassociate+0xcc/0x160 [ib_uverbs] uverbs_destroy_ufile_hw+0xf7/0x120 [ib_uverbs] ib_uverbs_remove_one+0xea/0x240 [ib_uverbs] ib_unregister_device+0xfb/0x200 [ib_core] mlx5_ib_remove+0x51/0xe0 [mlx5_ib] mlx5_remove_device+0xc1/0xd0 [mlx5_core] mlx5_unregister_device+0x3d/0xb0 [mlx5_core] remove_one+0x2a/0x90 [mlx5_core] pci_device_remove+0x3b/0xc0 device_release_driver_internal+0x16d/0x240 unbind_store+0xb2/0x100 kernfs_fop_write+0x102/0x180 __vfs_write+0x36/0x1a0 ? __alloc_fd+0xa9/0x170 ? set_close_on_exec+0x49/0x70 vfs_write+0xad/0x1a0 ksys_write+0x52/0xc0 do_syscall_64+0x5b/0x180 entry_SYSCALL_64_after_hwframe+0x44/0xa9 Cc: # 4.19 Fixes: 5f9794dc94f5 ("RDMA/ucontext: Add a core API for mmaping driver IO memory") Signed-off-by: Yishai Hadas Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/uverbs_main.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'drivers/infiniband/core/uverbs_main.c') diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 15add0688fbb..5f366838b7ff 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -967,11 +967,19 @@ void uverbs_user_mmap_disassociate(struct ib_uverbs_file *ufile) /* Get an arbitrary mm pointer that hasn't been cleaned yet */ mutex_lock(&ufile->umap_lock); - if (!list_empty(&ufile->umaps)) { - mm = list_first_entry(&ufile->umaps, - struct rdma_umap_priv, list) - ->vma->vm_mm; - mmget(mm); + while (!list_empty(&ufile->umaps)) { + int ret; + + priv = list_first_entry(&ufile->umaps, + struct rdma_umap_priv, list); + mm = priv->vma->vm_mm; + ret = mmget_not_zero(mm); + if (!ret) { + list_del_init(&priv->list); + mm = NULL; + continue; + } + break; } mutex_unlock(&ufile->umap_lock); if (!mm) -- cgit v1.2.3-70-g09d2