[PATCH AUTOSEL 4.19 054/167] IB/uverbs: Fix OOPs upon device disassociation

[PATCH AUTOSEL 4.19 054/167] IB/uverbs: Fix OOPs upon device disassociation

[Sasha Levin]

From: Yishai Hadas <yishaih@mellanox.com>

[ Upstream commit 425784aa5b029eeb80498c73a68f62c3ad1d3b3f ]

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: <stable@vger.kernel.org> # 4.2
Fixes: 036b10635739 ("IB/uverbs: Enable device removal when there are active user space applications")
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/core/uverbs_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 50152c1b10045..357de3b4fdddf 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -265,6 +265,9 @@ 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);
 	kobject_put(&file->device->kobj);
 	kfree(file);
 }
@@ -915,10 +918,6 @@ static int ib_uverbs_close(struct inode *inode, struct file *filp)
 	}
 	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;
-- 
2.20.1

[PATCH AUTOSEL 4.19 091/167] IB/mlx5: Reset access mask when looping inside page fault handler

[Sasha Levin]

From: Moni Shoua <monis@mellanox.com>

[ Upstream commit 1abe186ed8a6593069bc122da55fc684383fdc1c ]

If page-fault handler spans multiple MRs then the access mask needs to
be reset before each MR handling or otherwise write access will be
granted to mapped pages instead of read-only.

Cc: <stable@vger.kernel.org> # 3.19
Fixes: 7bdf65d411c1 ("IB/mlx5: Handle page faults")
Reported-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/hw/mlx5/odp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index 9e1cac8cb2609..453e5c4ac19f4 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -497,7 +497,7 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr)
 static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 			u64 io_virt, size_t bcnt, u32 *bytes_mapped)
 {
-	u64 access_mask = ODP_READ_ALLOWED_BIT;
+	u64 access_mask;
 	int npages = 0, page_shift, np;
 	u64 start_idx, page_mask;
 	struct ib_umem_odp *odp;
@@ -522,6 +522,7 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr,
 	page_shift = mr->umem->page_shift;
 	page_mask = ~(BIT(page_shift) - 1);
 	start_idx = (io_virt - (mr->mmkey.iova & page_mask)) >> page_shift;
+	access_mask = ODP_READ_ALLOWED_BIT;
 
 	if (mr->umem->writable)
 		access_mask |= ODP_WRITE_ALLOWED_BIT;
-- 
2.20.1

[PATCH AUTOSEL 4.19 122/167] IB/hfi1: Avoid hardlockup with flushlist_lock

[Sasha Levin]

From: Mike Marciniszyn <mike.marciniszyn@intel.com>

[ Upstream commit cf131a81967583ae737df6383a0893b9fee75b4e ]

Heavy contention of the sde flushlist_lock can cause hard lockups at
extreme scale when the flushing logic is under stress.

Mitigate by replacing the item at a time copy to the local list with
an O(1) list_splice_init() and using the high priority work queue to
do the flushes.

Fixes: 7724105686e7 ("IB/hfi1: add driver files")
Cc: <stable@vger.kernel.org>
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/hw/hfi1/sdma.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 88e326d6cc494..d648a4167832c 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -410,10 +410,7 @@ static void sdma_flush(struct sdma_engine *sde)
 	sdma_flush_descq(sde);
 	spin_lock_irqsave(&sde->flushlist_lock, flags);
 	/* copy flush list */
-	list_for_each_entry_safe(txp, txp_next, &sde->flushlist, list) {
-		list_del_init(&txp->list);
-		list_add_tail(&txp->list, &flushlist);
-	}
+	list_splice_init(&sde->flushlist, &flushlist);
 	spin_unlock_irqrestore(&sde->flushlist_lock, flags);
 	/* flush from flush list */
 	list_for_each_entry_safe(txp, txp_next, &flushlist, list)
@@ -2426,7 +2423,7 @@ int sdma_send_txreq(struct sdma_engine *sde,
 		wait->tx_count++;
 		wait->count += tx->num_desc;
 	}
-	schedule_work(&sde->flush_worker);
+	queue_work_on(sde->cpu, system_highpri_wq, &sde->flush_worker);
 	ret = -ECOMM;
 	goto unlock;
 nodesc:
@@ -2526,7 +2523,7 @@ int sdma_send_txlist(struct sdma_engine *sde, struct iowait *wait,
 		}
 	}
 	spin_unlock(&sde->flushlist_lock);
-	schedule_work(&sde->flush_worker);
+	queue_work_on(sde->cpu, system_highpri_wq, &sde->flush_worker);
 	ret = -ECOMM;
 	goto update_tail;
 nodesc:
-- 
2.20.1

[PATCH AUTOSEL 4.19 139/167] RDMA/srp: Document srp_parse_in() arguments

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit e37df2d5b569390e3b80ebed9a73fd5b9dcda010 ]

This patch avoids that a warning is reported when building with W=1.

Cc: Sergey Gorenko <sergeygo@mellanox.com>
Cc: Max Gurtovoy <maxg@mellanox.com>
Cc: Laurence Oberman <loberman@redhat.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 2c1114ee0c6da..9da30d88a615e 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3401,6 +3401,9 @@ static const match_table_t srp_opt_tokens = {
 
 /**
  * srp_parse_in - parse an IP address and port number combination
+ * @net:	   [in]  Network namespace.
+ * @sa:		   [out] Address family, IP address and port number.
+ * @addr_port_str: [in]  IP address and port number.
  *
  * Parse the following address formats:
  * - IPv4: <ip_address>:<port>, e.g. 1.2.3.4:5.
-- 
2.20.1

[PATCH AUTOSEL 4.19 140/167] RDMA/srp: Accept again source addresses that do not have a port number

[Sasha Levin]

From: Bart Van Assche <bvanassche@acm.org>

[ Upstream commit bcef5b7215681250c4bf8961dfe15e9e4fef97d0 ]

The function srp_parse_in() is used both for parsing source address
specifications and for target address specifications. Target addresses
must have a port number. Having to specify a port number for source
addresses is inconvenient. Make sure that srp_parse_in() supports again
parsing addresses with no port number.

Cc: <stable@vger.kernel.org>
Fixes: c62adb7def71 ("IB/srp: Fix IPv6 address parsing")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/infiniband/ulp/srp/ib_srp.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 9da30d88a615e..bc6a44a16445c 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -3404,13 +3404,14 @@ static const match_table_t srp_opt_tokens = {
  * @net:	   [in]  Network namespace.
  * @sa:		   [out] Address family, IP address and port number.
  * @addr_port_str: [in]  IP address and port number.
+ * @has_port:	   [out] Whether or not @addr_port_str includes a port number.
  *
  * Parse the following address formats:
  * - IPv4: <ip_address>:<port>, e.g. 1.2.3.4:5.
  * - IPv6: \[<ipv6_address>\]:<port>, e.g. [1::2:3%4]:5.
  */
 static int srp_parse_in(struct net *net, struct sockaddr_storage *sa,
-			const char *addr_port_str)
+			const char *addr_port_str, bool *has_port)
 {
 	char *addr_end, *addr = kstrdup(addr_port_str, GFP_KERNEL);
 	char *port_str;
@@ -3419,9 +3420,12 @@ static int srp_parse_in(struct net *net, struct sockaddr_storage *sa,
 	if (!addr)
 		return -ENOMEM;
 	port_str = strrchr(addr, ':');
-	if (!port_str)
-		return -EINVAL;
-	*port_str++ = '\0';
+	if (port_str && strchr(port_str, ']'))
+		port_str = NULL;
+	if (port_str)
+		*port_str++ = '\0';
+	if (has_port)
+		*has_port = port_str != NULL;
 	ret = inet_pton_with_scope(net, AF_INET, addr, port_str, sa);
 	if (ret && addr[0]) {
 		addr_end = addr + strlen(addr) - 1;
@@ -3443,6 +3447,7 @@ static int srp_parse_options(struct net *net, const char *buf,
 	char *p;
 	substring_t args[MAX_OPT_ARGS];
 	unsigned long long ull;
+	bool has_port;
 	int opt_mask = 0;
 	int token;
 	int ret = -EINVAL;
@@ -3541,7 +3546,8 @@ static int srp_parse_options(struct net *net, const char *buf,
 				ret = -ENOMEM;
 				goto out;
 			}
-			ret = srp_parse_in(net, &target->rdma_cm.src.ss, p);
+			ret = srp_parse_in(net, &target->rdma_cm.src.ss, p,
+					   NULL);
 			if (ret < 0) {
 				pr_warn("bad source parameter '%s'\n", p);
 				kfree(p);
@@ -3557,7 +3563,10 @@ static int srp_parse_options(struct net *net, const char *buf,
 				ret = -ENOMEM;
 				goto out;
 			}
-			ret = srp_parse_in(net, &target->rdma_cm.dst.ss, p);
+			ret = srp_parse_in(net, &target->rdma_cm.dst.ss, p,
+					   &has_port);
+			if (!has_port)
+				ret = -EINVAL;
 			if (ret < 0) {
 				pr_warn("bad dest parameter '%s'\n", p);
 				kfree(p);
-- 
2.20.1