[PATCH v6 0/4] scsi: libsas: Fix the failure of adding phy with zero-address to port

[PATCH v6 0/4] scsi: libsas: Fix the failure of adding phy with zero-address to port

[Xingui Yang]

This series is to solve the problem of a BUG() when adding phy with zero
address to a new port.

v5 -> v6
1. rename sas_add_parent_port() to sas_ex_add_parent_port() based on
   John's suggestion.
2. Distill port settings into a single patch.
3. Update comments information.

v4 -> v5
1. Add new helper sas_port_add_ex_phy() based on John's suggestion.
2. Move sas_add_parent_port() to sas_expander.c based on John's suggestion.
3. Update the comments.

v3 -> v4:
1. Update patch title and comments based on John's suggestion.

v2 -> v3:
1. Set ex_dev->parent_port to NULL when the number of PHYs of the parent
   port becomes 0.
2. Update the comments.

v1 -> v2:
1. Set ex_phy->port with parent_port when ex_phy is added to the parent
   port.
2. Set ex_phy to NULL when free expander.
3. Update the comments.

Xingui Yang (4):
  scsi: libsas: Add helper for port add ex_phy
  scsi: libsas: Move sas_add_parent_port() to sas_expander.c
  scsi: libsas: Set port when ex_phy is added or deleted
  scsi: libsas: Fix the failure of adding phy with zero-address to port

 drivers/scsi/libsas/sas_expander.c | 38 +++++++++++++++++++++++-------
 drivers/scsi/libsas/sas_internal.h | 15 ------------
 2 files changed, 30 insertions(+), 23 deletions(-)

-- 
2.17.1

[PATCH v6 1/4] scsi: libsas: Add helper for port add ex_phy

[Xingui Yang]

This moves the process of adding ex_phy to a port into a new helper.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
---
 drivers/scsi/libsas/sas_expander.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index ee3808bfd534..c8d4aef2f567 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -26,6 +26,13 @@ static int sas_configure_phy(struct domain_device *dev, int phy_id,
 			     u8 *sas_addr, int include);
 static int sas_disable_routing(struct domain_device *dev,  u8 *sas_addr);
 
+static void sas_port_add_ex_phy(struct sas_port *port, struct ex_phy *ex_phy)
+{
+	sas_port_add_phy(port, ex_phy->phy);
+	ex_phy->port = port;
+	ex_phy->phy_state = PHY_DEVICE_DISCOVERED;
+}
+
 /* ---------- SMP task management ---------- */
 
 /* Give it some long enough timeout. In seconds. */
@@ -867,9 +874,7 @@ static bool sas_ex_join_wide_port(struct domain_device *parent, int phy_id)
 
 		if (!memcmp(phy->attached_sas_addr, ephy->attached_sas_addr,
 			    SAS_ADDR_SIZE) && ephy->port) {
-			sas_port_add_phy(ephy->port, phy->phy);
-			phy->port = ephy->port;
-			phy->phy_state = PHY_DEVICE_DISCOVERED;
+			sas_port_add_ex_phy(ephy->port, phy);
 			return true;
 		}
 	}
-- 
2.17.1

[PATCH v6 2/4] scsi: libsas: Move sas_add_parent_port() to sas_expander.c

[Xingui Yang]

Move sas_add_parent_port() to sas_expander.c and rename it to
sas_ex_add_parent_port() as it is only used in this file.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
---
 drivers/scsi/libsas/sas_expander.c | 19 +++++++++++++++++--
 drivers/scsi/libsas/sas_internal.h | 15 ---------------
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index c8d4aef2f567..f28a83803947 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -33,6 +33,21 @@ static void sas_port_add_ex_phy(struct sas_port *port, struct ex_phy *ex_phy)
 	ex_phy->phy_state = PHY_DEVICE_DISCOVERED;
 }
 
+static void sas_ex_add_parent_port(struct domain_device *dev, int phy_id)
+{
+	struct expander_device *ex = &dev->ex_dev;
+	struct ex_phy *ex_phy = &ex->ex_phy[phy_id];
+
+	if (!ex->parent_port) {
+		ex->parent_port = sas_port_alloc(&dev->rphy->dev, phy_id);
+		/* FIXME: error handling */
+		BUG_ON(!ex->parent_port);
+		BUG_ON(sas_port_add(ex->parent_port));
+		sas_port_mark_backlink(ex->parent_port);
+	}
+	sas_port_add_phy(ex->parent_port, ex_phy->phy);
+}
+
 /* ---------- SMP task management ---------- */
 
 /* Give it some long enough timeout. In seconds. */
@@ -978,11 +993,11 @@ static int sas_ex_discover_dev(struct domain_device *dev, int phy_id)
 
 	/* Parent and domain coherency */
 	if (!dev->parent && sas_phy_match_port_addr(dev->port, ex_phy)) {
-		sas_add_parent_port(dev, phy_id);
+		sas_ex_add_parent_port(dev, phy_id);
 		return 0;
 	}
 	if (dev->parent && sas_phy_match_dev_addr(dev->parent, ex_phy)) {
-		sas_add_parent_port(dev, phy_id);
+		sas_ex_add_parent_port(dev, phy_id);
 		if (ex_phy->routing_attr == TABLE_ROUTING)
 			sas_configure_phy(dev, phy_id, dev->port->sas_addr, 1);
 		return 0;
diff --git a/drivers/scsi/libsas/sas_internal.h b/drivers/scsi/libsas/sas_internal.h
index 3804aef165ad..85948963fb97 100644
--- a/drivers/scsi/libsas/sas_internal.h
+++ b/drivers/scsi/libsas/sas_internal.h
@@ -189,21 +189,6 @@ static inline void sas_phy_set_target(struct asd_sas_phy *p, struct domain_devic
 	}
 }
 
-static inline void sas_add_parent_port(struct domain_device *dev, int phy_id)
-{
-	struct expander_device *ex = &dev->ex_dev;
-	struct ex_phy *ex_phy = &ex->ex_phy[phy_id];
-
-	if (!ex->parent_port) {
-		ex->parent_port = sas_port_alloc(&dev->rphy->dev, phy_id);
-		/* FIXME: error handling */
-		BUG_ON(!ex->parent_port);
-		BUG_ON(sas_port_add(ex->parent_port));
-		sas_port_mark_backlink(ex->parent_port);
-	}
-	sas_port_add_phy(ex->parent_port, ex_phy->phy);
-}
-
 static inline struct domain_device *sas_alloc_device(void)
 {
 	struct domain_device *dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-- 
2.17.1

[PATCH v6 3/4] scsi: libsas: Set port when ex_phy is added or deleted

[Xingui Yang]

We found that when ex_phy was attached and added to the parent wide port,
ex_phy->port was not set, resulting in sas_unregister_devs_sas_addr() not
calling sas_port_delete_phy() when deleting the phy, and the deleted phy
was still on the parent wide port's phy_list.

When we use sas_port_add_ex_phy() to set ex_phy->port to solve the above
problem, we find that after all the phys of the parent_port are removed and
the number of phy becomes 0, the parent_port will not be set to NULL.
Causes the freed parent port to be used when attaching a new ex_phy in
sas_ex_add_parent_port().

So use sas_port_add_ex_phy() instead of sas_port_add_phy() to set
ex_phy->port when ex_phy is added to the parent port, and set
ex_dev->parent_port to NULL when the number of phy on the port becomes 0.

Signed-off-by: Xingui Yang <yangxingui@huawei.com>
---
 drivers/scsi/libsas/sas_expander.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index f28a83803947..77daae36232b 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -45,7 +45,7 @@ static void sas_ex_add_parent_port(struct domain_device *dev, int phy_id)
 		BUG_ON(sas_port_add(ex->parent_port));
 		sas_port_mark_backlink(ex->parent_port);
 	}
-	sas_port_add_phy(ex->parent_port, ex_phy->phy);
+	sas_port_add_ex_phy(ex->parent_port, ex_phy);
 }
 
 /* ---------- SMP task management ---------- */
@@ -1879,9 +1879,12 @@ static void sas_unregister_devs_sas_addr(struct domain_device *parent,
 	if (phy->port) {
 		sas_port_delete_phy(phy->port, phy->phy);
 		sas_device_set_phy(found, phy->port);
-		if (phy->port->num_phys == 0)
+		if (phy->port->num_phys == 0) {
 			list_add_tail(&phy->port->del_list,
 				&parent->port->sas_port_del_list);
+			if (ex_dev->parent_port == phy->port)
+				ex_dev->parent_port = NULL;
+		}
 		phy->port = NULL;
 	}
 }
-- 
2.17.1

[PATCH v6 4/4] scsi: libsas: Fix the failure of adding phy with zero-address to port

[Xingui Yang]

As of commit 7d1d86518118 ("[SCSI] libsas: fix false positive 'device
attached' conditions"), reset the phy->entacted_sas_addr address to a
zero-address when the link rate is less than 1.5G.

Currently we find that when a new device is attached, and the link rate is
less than 1.5G, but the device type is not NO_DEVICE, for example: the link
rate is SAS_PHY_RESET_IN_PROGRESS and the device type is stp. After setting
the phy->entacted_sas_addr address to the zero address, the port will
continue to be created for the phy with the zero-address, and other phys
with the zero-address will be tried to be added to the new port:

[562240.051197] sas: ex 500e004aaaaaaa1f phy19:U:0 attached: 0000000000000000 (no device)
// phy19 is deleted but still on the parent port's phy_list
[562240.062536] sas: ex 500e004aaaaaaa1f phy0 new device attached
[562240.062616] sas: ex 500e004aaaaaaa1f phy00:U:5 attached: 0000000000000000 (stp)
[562240.062680] port-7:7:0: trying to add phy phy-7:7:19 fails: it's already part of another port

Therefore, it should be the same as sas_get_phy_attached_dev(). Only when
device_type is SAS_PHY_UNUSED, sas_address is set to the 0 address.

Fixes: 7d1d86518118 ("[SCSI] libsas: fix false positive 'device attached' conditions")
Signed-off-by: Xingui Yang <yangxingui@huawei.com>
---
 drivers/scsi/libsas/sas_expander.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index 77daae36232b..430575b86e3e 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -271,8 +271,7 @@ static void sas_set_ex_phy(struct domain_device *dev, int phy_id,
 	/* help some expanders that fail to zero sas_address in the 'no
 	 * device' case
 	 */
-	if (phy->attached_dev_type == SAS_PHY_UNUSED ||
-	    phy->linkrate < SAS_LINK_RATE_1_5_GBPS)
+	if (phy->attached_dev_type == SAS_PHY_UNUSED)
 		memset(phy->attached_sas_addr, 0, SAS_ADDR_SIZE);
 	else
 		memcpy(phy->attached_sas_addr, dr->attached_sas_addr, SAS_ADDR_SIZE);
-- 
2.17.1

Re: [PATCH v6 0/4] scsi: libsas: Fix the failure of adding phy with zero-address to port

[Martin K. Petersen]

Xingui,

> This series is to solve the problem of a BUG() when adding phy with zero
> address to a new port.

Applied to 6.10/scsi-staging, thanks!

-- 
Martin K. Petersen	Oracle Linux Engineering

Re: [PATCH v6 0/4] scsi: libsas: Fix the failure of adding phy with zero-address to port

[Martin K. Petersen]

On Tue, 12 Mar 2024 14:10:59 +0000, Xingui Yang wrote:

> This series is to solve the problem of a BUG() when adding phy with zero
> address to a new port.
> 
> v5 -> v6
> 1. rename sas_add_parent_port() to sas_ex_add_parent_port() based on
>    John's suggestion.
> 2. Distill port settings into a single patch.
> 3. Update comments information.
> 
> [...]

Applied to 6.10/scsi-queue, thanks!

[1/4] scsi: libsas: Add helper for port add ex_phy
      https://git.kernel.org/mkp/scsi/c/888ea1b12b06
[2/4] scsi: libsas: Move sas_add_parent_port() to sas_expander.c
      https://git.kernel.org/mkp/scsi/c/48032c0be6c7
[3/4] scsi: libsas: Set port when ex_phy is added or deleted
      https://git.kernel.org/mkp/scsi/c/7a165a81d55f
[4/4] scsi: libsas: Fix the failure of adding phy with zero-address to port
      https://git.kernel.org/mkp/scsi/c/06036a0a5db3

-- 
Martin K. Petersen	Oracle Linux Engineering