@@ -296,8 +296,10 @@ void sas_free_device(struct kref *kref)
dev->phy = NULL;
/* remove the phys and ports, everything else should be gone */
- if (dev_is_expander(dev->dev_type))
+ if (dev_is_expander(dev->dev_type)) {
kfree(dev->ex_dev.ex_phy);
+ dev->ex_dev.ex_phy = NULL;
+ }
if (dev_is_sata(dev) && dev->sata_dev.ap) {
ata_sas_tport_delete(dev->sata_dev.ap);
@@ -239,8 +239,7 @@ 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);
@@ -1844,9 +1843,12 @@ 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;
}
}
@@ -202,6 +202,7 @@ static inline void sas_add_parent_port(struct domain_device *dev, int phy_id)
sas_port_mark_backlink(ex->parent_port);
}
sas_port_add_phy(ex->parent_port, ex_phy->phy);
+ ex_phy->port = ex->parent_port;
}
static inline struct domain_device *sas_alloc_device(void)
Firstly, when ex_phy is added to the parent port, ex_phy->port is not set. As a result, sas_port_delete_phy() won't be called in sas_unregister_devs_sas_addr(), and although ex_phy's sas_address is zero, it is not deleted from the parent port's phy_list. Secondly, phy->attached_sas_addr will be set to a zero-address when phy->linkrate < SAS_LINK_RATE_1_5_GBPS and device-type != NO_DEVICE during device registration, such as stp. It will create a new port and all other ex_phys whose addresses are zero will be added to the new port in sas_ex_get_linkrate(), and it may trigger BUG() as follows: [562240.051046] sas: phy19 part of wide port with phy16 [562240.051197] sas: ex 500e004aaaaaaa1f phy19:U:0 attached: 0000000000000000 (no device) [562240.051203] sas: done REVALIDATING DOMAIN on port 0, pid:435909, res 0x0 [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 [562240.085064] ------------[ cut here ]------------ [562240.096612] kernel BUG at drivers/scsi/scsi_transport_sas.c:1083! [562240.109611] Internal error: Oops - BUG: 0 [#1] SMP [562240.343518] Process kworker/u256:3 (pid: 435909, stack limit = 0x0000000003bcbebf) [562240.421714] Workqueue: 0000:b4:02.0_disco_q sas_revalidate_domain [libsas] [562240.437173] pstate: 40c00009 (nZcv daif +PAN +UAO) [562240.450478] pc : sas_port_add_phy+0x13c/0x168 [scsi_transport_sas] [562240.465283] lr : sas_port_add_phy+0x13c/0x168 [scsi_transport_sas] [562240.479751] sp : ffff0000300cfa70 [562240.674822] Call trace: [562240.682709] sas_port_add_phy+0x13c/0x168 [scsi_transport_sas] [562240.694013] sas_ex_get_linkrate.isra.5+0xcc/0x128 [libsas] [562240.704957] sas_ex_discover_end_dev+0xfc/0x538 [libsas] [562240.715508] sas_ex_discover_dev+0x3cc/0x4b8 [libsas] [562240.725634] sas_ex_discover_devices+0x9c/0x1a8 [libsas] [562240.735855] sas_ex_revalidate_domain+0x2f0/0x450 [libsas] [562240.746123] sas_revalidate_domain+0x158/0x160 [libsas] [562240.756014] process_one_work+0x1b4/0x448 [562240.764548] worker_thread+0x54/0x468 [562240.772562] kthread+0x134/0x138 [562240.779989] ret_from_fork+0x10/0x18 We've done the following to solve this problem: Firstly, 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 PHYs of the parent port becomes 0. Secondly, don't set a zero-address for phy->attached_sas_addr when phy->attached_dev_type != NO_DEVICE. Fixes: 7d1d86518118 ("[SCSI] libsas: fix false positive 'device attached' conditions") Signed-off-by: Xingui Yang <yangxingui@huawei.com> --- 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 --- drivers/scsi/libsas/sas_discover.c | 4 +++- drivers/scsi/libsas/sas_expander.c | 8 +++++--- drivers/scsi/libsas/sas_internal.h | 1 + 3 files changed, 9 insertions(+), 4 deletions(-)