[SCSI] mpt2sas: Redesign Raid devices event handling using pd_handles per HBA

Actual problem :
Driver  may receiving the top level expander
removal event prior to all the individual PD removal events, hence the
driver is breaking down all the PDs in advanced to the actaul PD UNHIDE
event. Driver sends multiple
Target Resets to the same volume handle for each individual PD removal.

FIX DESCRIPTION:
To fix this issue, the entire PD device handshake protocal has to be
moved to interrupt context so the breakdown occurs immediately after the
actual UNHIDE event arrives.  The driver will only issue one Target Reset to
the volume handle, occurring after the FAILED or MISSING volume status
event arrives from interrupt context. For the PD UNHIDE event, the driver
will issue target resets to the PD handles, followed by OP_REMOVE.  The
driver will set the "deteleted" flag during interrupt context.  A "pd_handle"
bitmask was introduced so the driver has a list of known pds during entire
life of the PD; this replaces the "hidden_raid_component" flag handle in
the sas_device object.  Each bit in the bitmask represents a device handle.
The bit in the bitmask would be toggled ON/OFF when the HIDE/UNHIDE
events arrive; also this pd_handle bitmask would bould be refreshed
across host resets.

Here we kept older behavior of sending target reset to volume when there is
a single drive pull, wait for the reply, then send target resets
to the PDs.  We kept this behavior so the driver will
behave the same for older versions of firmware.
Signed-off-by: Kashyap Desai <kashyap.desai@lsi.com>
Signed-off-by: James Bottomley <James.Bottomley@suse.de>

drivers/scsi/mpt2sas/mpt2sas_base.c

@@ -3468,6 +3468,12 @@ _base_make_ioc_operational(struct MPT2SAS_ADAPTER *ioc, int sleep_flag)
 		kfree(delayed_tr);
 	}
 
+	list_for_each_entry_safe(delayed_tr, delayed_tr_next,
+	    &ioc->delayed_tr_volume_list, list) {
+		list_del(&delayed_tr->list);
+		kfree(delayed_tr);
+	}
+
 	/* initialize the scsi lookup free list */
 	spin_lock_irqsave(&ioc->scsi_lookup_lock, flags);
 	INIT_LIST_HEAD(&ioc->free_list);
@@ -3622,6 +3628,15 @@ mpt2sas_base_attach(struct MPT2SAS_ADAPTER *ioc)
 
 	init_waitqueue_head(&ioc->reset_wq);
 
+	/* allocate memory pd handle bitmask list */
+	ioc->pd_handles_sz = (ioc->facts.MaxDevHandle / 8);
+	if (ioc->facts.MaxDevHandle % 8)
+		ioc->pd_handles_sz++;
+	ioc->pd_handles = kzalloc(ioc->pd_handles_sz,
+	    GFP_KERNEL);
+	if (!ioc->pd_handles)
+		goto out_free_resources;
+
 	ioc->fwfault_debug = mpt2sas_fwfault_debug;
 
 	/* base internal command bits */
@@ -3691,6 +3706,7 @@ mpt2sas_base_attach(struct MPT2SAS_ADAPTER *ioc)
 	mpt2sas_base_free_resources(ioc);
 	_base_release_memory_pools(ioc);
 	pci_set_drvdata(ioc->pdev, NULL);
+	kfree(ioc->pd_handles);
 	kfree(ioc->tm_cmds.reply);
 	kfree(ioc->transport_cmds.reply);
 	kfree(ioc->scsih_cmds.reply);
@@ -3726,6 +3742,7 @@ mpt2sas_base_detach(struct MPT2SAS_ADAPTER *ioc)
 	mpt2sas_base_free_resources(ioc);
 	_base_release_memory_pools(ioc);
 	pci_set_drvdata(ioc->pdev, NULL);
+	kfree(ioc->pd_handles);
 	kfree(ioc->pfacts);
 	kfree(ioc->ctl_cmds.reply);
 	kfree(ioc->base_cmds.reply);

drivers/scsi/mpt2sas/mpt2sas_base.h

@@ -276,7 +276,6 @@ struct _internal_cmd {
  * @channel: target channel
  * @slot: number number
  * @phy: phy identifier provided in sas device page 0
- * @hidden_raid_component: set to 1 when this is a raid member
  * @responding: used in _scsih_sas_device_mark_responding
  */
 struct _sas_device {
@@ -295,7 +294,6 @@ struct _sas_device {
 	int	channel;
 	u16	slot;
 	u8	phy;
-	u8	hidden_raid_component;
 	u8	responding;
 };
 
@@ -489,6 +487,8 @@ typedef void (*MPT_ADD_SGE)(void *paddr, u32 flags_length, dma_addr_t dma_addr);
  * @ctl_cb_idx: clt internal commands
  * @base_cb_idx: base internal commands
  * @config_cb_idx: base internal commands
+ * @tm_tr_cb_idx : device removal target reset handshake
+ * @tm_tr_volume_cb_idx : volume removal target reset
  * @base_cmds:
  * @transport_cmds:
  * @scsih_cmds:
@@ -517,6 +517,9 @@ typedef void (*MPT_ADD_SGE)(void *paddr, u32 flags_length, dma_addr_t dma_addr);
  * @sas_device_lock:
  * @io_missing_delay: time for IO completed by fw when PDR enabled
  * @device_missing_delay: time for device missing by fw when PDR enabled
+ * @sas_id : used for setting volume target IDs
+ * @pd_handles : bitmask for PD handles
+ * @pd_handles_sz : size of pd_handle bitmask
  * @config_page_sz: config page size
  * @config_page: reserve memory for config page payload
  * @config_page_dma:
@@ -569,6 +572,8 @@ typedef void (*MPT_ADD_SGE)(void *paddr, u32 flags_length, dma_addr_t dma_addr);
  * @reply_post_free_dma:
  * @reply_post_free_dma_pool:
  * @reply_post_host_index: head index in the pool where FW completes IO
+ * @delayed_tr_list: target reset link list
+ * @delayed_tr_volume_list: volume target reset link list
  */
 struct MPT2SAS_ADAPTER {
 	struct list_head list;
@@ -627,6 +632,7 @@ struct MPT2SAS_ADAPTER {
 	u8		base_cb_idx;
 	u8		config_cb_idx;
 	u8		tm_tr_cb_idx;
+	u8		tm_tr_volume_cb_idx;
 	u8		tm_sas_control_cb_idx;
 	struct _internal_cmd base_cmds;
 	struct _internal_cmd transport_cmds;
@@ -670,6 +676,9 @@ struct MPT2SAS_ADAPTER {
 	u16		device_missing_delay;
 	int		sas_id;
 
+	void		*pd_handles;
+	u16		pd_handles_sz;
+
 	/* config page */
 	u16		config_page_sz;
 	void 		*config_page;
@@ -741,6 +750,7 @@ struct MPT2SAS_ADAPTER {
 	u32		reply_post_host_index;
 
 	struct list_head delayed_tr_list;
+	struct list_head delayed_tr_volume_list;
 
 	/* diag buffer support */
 	u8		*diag_buffer[MPI2_DIAG_BUF_TYPE_COUNT];