OpenCloudOS-Kernel/drivers/scsi/ibmvscsi/rpa_vscsi.c

369 lines
10 KiB
C
Raw Normal View History

/* ------------------------------------------------------------
* rpa_vscsi.c
* (C) Copyright IBM Corporation 1994, 2003
* Authors: Colin DeVilbiss (devilbis@us.ibm.com)
* Santiago Leon (santil@us.ibm.com)
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
* USA
*
* ------------------------------------------------------------
* RPA-specific functions of the SCSI host adapter for Virtual I/O devices
*
* This driver allows the Linux SCSI peripheral drivers to directly
* access devices in the hosting partition, either on an iSeries
* hypervisor system or a converged hypervisor system.
*/
#include <asm/vio.h>
#include <asm/prom.h>
#include <asm/iommu.h>
#include <asm/hvcall.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/interrupt.h>
#include "ibmvscsi.h"
static char partition_name[97] = "UNKNOWN";
static unsigned int partition_number = -1;
/* ------------------------------------------------------------
* Routines for managing the command/response queue
*/
/**
* rpavscsi_handle_event: - Interrupt handler for crq events
* @irq: number of irq to handle, not used
* @dev_instance: ibmvscsi_host_data of host that received interrupt
*
* Disables interrupts and schedules srp_task
* Always returns IRQ_HANDLED
*/
static irqreturn_t rpavscsi_handle_event(int irq, void *dev_instance)
{
struct ibmvscsi_host_data *hostdata =
(struct ibmvscsi_host_data *)dev_instance;
vio_disable_interrupts(to_vio_dev(hostdata->dev));
tasklet_schedule(&hostdata->srp_task);
return IRQ_HANDLED;
}
/**
* release_crq_queue: - Deallocates data and unregisters CRQ
* @queue: crq_queue to initialize and register
* @host_data: ibmvscsi_host_data of host
*
* Frees irq, deallocates a page for messages, unmaps dma, and unregisters
* the crq with the hypervisor.
*/
static void rpavscsi_release_crq_queue(struct crq_queue *queue,
struct ibmvscsi_host_data *hostdata,
int max_requests)
{
long rc = 0;
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
free_irq(vdev->irq, (void *)hostdata);
tasklet_kill(&hostdata->srp_task);
do {
if (rc)
msleep(100);
rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
} while ((rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
dma_unmap_single(hostdata->dev,
queue->msg_token,
queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL);
free_page((unsigned long)queue->msgs);
}
/**
* crq_queue_next_crq: - Returns the next entry in message queue
* @queue: crq_queue to use
*
* Returns pointer to next entry in queue, or NULL if there are no new
* entried in the CRQ.
*/
static struct viosrp_crq *crq_queue_next_crq(struct crq_queue *queue)
{
struct viosrp_crq *crq;
unsigned long flags;
spin_lock_irqsave(&queue->lock, flags);
crq = &queue->msgs[queue->cur];
if (crq->valid & 0x80) {
if (++queue->cur == queue->size)
queue->cur = 0;
} else
crq = NULL;
spin_unlock_irqrestore(&queue->lock, flags);
return crq;
}
/**
* rpavscsi_send_crq: - Send a CRQ
* @hostdata: the adapter
* @word1: the first 64 bits of the data
* @word2: the second 64 bits of the data
*/
static int rpavscsi_send_crq(struct ibmvscsi_host_data *hostdata,
u64 word1, u64 word2)
{
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
return plpar_hcall_norets(H_SEND_CRQ, vdev->unit_address, word1, word2);
}
/**
* rpavscsi_task: - Process srps asynchronously
* @data: ibmvscsi_host_data of host
*/
static void rpavscsi_task(void *data)
{
struct ibmvscsi_host_data *hostdata = (struct ibmvscsi_host_data *)data;
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
struct viosrp_crq *crq;
int done = 0;
while (!done) {
/* Pull all the valid messages off the CRQ */
while ((crq = crq_queue_next_crq(&hostdata->queue)) != NULL) {
ibmvscsi_handle_crq(crq, hostdata);
crq->valid = 0x00;
}
vio_enable_interrupts(vdev);
if ((crq = crq_queue_next_crq(&hostdata->queue)) != NULL) {
vio_disable_interrupts(vdev);
ibmvscsi_handle_crq(crq, hostdata);
crq->valid = 0x00;
} else {
done = 1;
}
}
}
static void gather_partition_info(void)
{
struct device_node *rootdn;
const char *ppartition_name;
const unsigned int *p_number_ptr;
/* Retrieve information about this partition */
rootdn = of_find_node_by_path("/");
if (!rootdn) {
return;
}
ppartition_name = of_get_property(rootdn, "ibm,partition-name", NULL);
if (ppartition_name)
strncpy(partition_name, ppartition_name,
sizeof(partition_name));
p_number_ptr = of_get_property(rootdn, "ibm,partition-no", NULL);
if (p_number_ptr)
partition_number = *p_number_ptr;
of_node_put(rootdn);
}
static void set_adapter_info(struct ibmvscsi_host_data *hostdata)
{
memset(&hostdata->madapter_info, 0x00,
sizeof(hostdata->madapter_info));
dev_info(hostdata->dev, "SRP_VERSION: %s\n", SRP_VERSION);
strcpy(hostdata->madapter_info.srp_version, SRP_VERSION);
strncpy(hostdata->madapter_info.partition_name, partition_name,
sizeof(hostdata->madapter_info.partition_name));
hostdata->madapter_info.partition_number = partition_number;
hostdata->madapter_info.mad_version = 1;
hostdata->madapter_info.os_type = 2;
}
/**
* reset_crq_queue: - resets a crq after a failure
* @queue: crq_queue to initialize and register
* @hostdata: ibmvscsi_host_data of host
*
*/
static int rpavscsi_reset_crq_queue(struct crq_queue *queue,
struct ibmvscsi_host_data *hostdata)
{
int rc = 0;
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
/* Close the CRQ */
do {
if (rc)
msleep(100);
rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
} while ((rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
/* Clean out the queue */
memset(queue->msgs, 0x00, PAGE_SIZE);
queue->cur = 0;
set_adapter_info(hostdata);
/* And re-open it again */
rc = plpar_hcall_norets(H_REG_CRQ,
vdev->unit_address,
queue->msg_token, PAGE_SIZE);
if (rc == 2) {
/* Adapter is good, but other end is not ready */
dev_warn(hostdata->dev, "Partner adapter not ready\n");
} else if (rc != 0) {
dev_warn(hostdata->dev, "couldn't register crq--rc 0x%x\n", rc);
}
return rc;
}
/**
* initialize_crq_queue: - Initializes and registers CRQ with hypervisor
* @queue: crq_queue to initialize and register
* @hostdata: ibmvscsi_host_data of host
*
* Allocates a page for messages, maps it for dma, and registers
* the crq with the hypervisor.
* Returns zero on success.
*/
static int rpavscsi_init_crq_queue(struct crq_queue *queue,
struct ibmvscsi_host_data *hostdata,
int max_requests)
{
int rc;
int retrc;
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
queue->msgs = (struct viosrp_crq *)get_zeroed_page(GFP_KERNEL);
if (!queue->msgs)
goto malloc_failed;
queue->size = PAGE_SIZE / sizeof(*queue->msgs);
queue->msg_token = dma_map_single(hostdata->dev, queue->msgs,
queue->size * sizeof(*queue->msgs),
DMA_BIDIRECTIONAL);
dma-mapping: add the device argument to dma_mapping_error() Add per-device dma_mapping_ops support for CONFIG_X86_64 as POWER architecture does: This enables us to cleanly fix the Calgary IOMMU issue that some devices are not behind the IOMMU (http://lkml.org/lkml/2008/5/8/423). I think that per-device dma_mapping_ops support would be also helpful for KVM people to support PCI passthrough but Andi thinks that this makes it difficult to support the PCI passthrough (see the above thread). So I CC'ed this to KVM camp. Comments are appreciated. A pointer to dma_mapping_ops to struct dev_archdata is added. If the pointer is non NULL, DMA operations in asm/dma-mapping.h use it. If it's NULL, the system-wide dma_ops pointer is used as before. If it's useful for KVM people, I plan to implement a mechanism to register a hook called when a new pci (or dma capable) device is created (it works with hot plugging). It enables IOMMUs to set up an appropriate dma_mapping_ops per device. The major obstacle is that dma_mapping_error doesn't take a pointer to the device unlike other DMA operations. So x86 can't have dma_mapping_ops per device. Note all the POWER IOMMUs use the same dma_mapping_error function so this is not a problem for POWER but x86 IOMMUs use different dma_mapping_error functions. The first patch adds the device argument to dma_mapping_error. The patch is trivial but large since it touches lots of drivers and dma-mapping.h in all the architecture. This patch: dma_mapping_error() doesn't take a pointer to the device unlike other DMA operations. So we can't have dma_mapping_ops per device. Note that POWER already has dma_mapping_ops per device but all the POWER IOMMUs use the same dma_mapping_error function. x86 IOMMUs use device argument. [akpm@linux-foundation.org: fix sge] [akpm@linux-foundation.org: fix svc_rdma] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix bnx2x] [akpm@linux-foundation.org: fix s2io] [akpm@linux-foundation.org: fix pasemi_mac] [akpm@linux-foundation.org: fix sdhci] [akpm@linux-foundation.org: build fix] [akpm@linux-foundation.org: fix sparc] [akpm@linux-foundation.org: fix ibmvscsi] Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Cc: Muli Ben-Yehuda <muli@il.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: Avi Kivity <avi@qumranet.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-07-26 10:44:49 +08:00
if (dma_mapping_error(hostdata->dev, queue->msg_token))
goto map_failed;
gather_partition_info();
set_adapter_info(hostdata);
retrc = rc = plpar_hcall_norets(H_REG_CRQ,
vdev->unit_address,
queue->msg_token, PAGE_SIZE);
if (rc == H_RESOURCE)
/* maybe kexecing and resource is busy. try a reset */
rc = rpavscsi_reset_crq_queue(queue,
hostdata);
if (rc == 2) {
/* Adapter is good, but other end is not ready */
dev_warn(hostdata->dev, "Partner adapter not ready\n");
retrc = 0;
} else if (rc != 0) {
dev_warn(hostdata->dev, "Error %d opening adapter\n", rc);
goto reg_crq_failed;
}
[SCSI] ibmvscsi: Fix oops when an interrupt is pending during probe A driver needs to be ready to take an interrupt as soon as it registers an interrupt handler. I noticed the following oops when testing kdump: ipr: IBM Power RAID SCSI Device Driver version: 2.5.0 (February 11, 2010) ibmvscsi 30000002: SRP_VERSION: 16.a ibmvscsi 30000002: SRP_VERSION: 16.a Unable to handle kernel paging request for data at address 0x00000000 ... pc: c000000004085e34: .tasklet_action+0xf4/0x1dc ... c000000004086fe4 .__do_softirq+0x16c/0x2c0 c00000000403138c .call_do_softirq+0x14/0x24 c00000000400ee14 .do_softirq+0xa0/0x104 c00000000408690c .irq_exit+0x70/0xd0 c00000000400f190 .do_IRQ+0x214/0x2a8 c000000004004804 hardware_interrupt_entry+0x1c/0x98 --- Exception: 501 (Hardware Interrupt) at c00000000400c544 .raw_local_irq_restore+0x48/0x54 c00000000465d2a8 ._raw_spin_unlock_irqrestore+0x74/0xa0 c0000000040e7f00 .__setup_irq+0x2ec/0x3f0 c0000000040e8198 .request_threaded_irq+0x194/0x22c c00000000446d854 .rpavscsi_init_crq_queue+0x284/0x3f0 c00000000446c764 .ibmvscsi_probe+0x688/0x710 c00000000402903c .vio_bus_probe+0x37c/0x3e4 c000000004403f10 .driver_probe_device+0xec/0x1b8 c000000004404088 .__driver_attach+0xac/0xf4 c000000004403184 .bus_for_each_dev+0x98/0x104 c000000004403c98 .driver_attach+0x40/0x60 c0000000044026f0 .bus_add_driver+0x154/0x324 c0000000044045d0 .driver_register+0xe8/0x1ac c00000000402b2a8 .vio_register_driver+0x54/0x74 c000000004933ea4 .ibmvscsi_module_init+0x80/0xc0 c000000004009834 .do_one_initcall+0x98/0x1d8 c0000000049005b4 .kernel_init+0x27c/0x33c c000000004031550 .kernel_thread+0x54/0x70 srp_task needs to be setup before request_irq. The patch below fixes the oops. Signed-off-by: Anton Blanchard <anton@samba.org> Acked-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-07-13 12:59:29 +08:00
queue->cur = 0;
spin_lock_init(&queue->lock);
tasklet_init(&hostdata->srp_task, (void *)rpavscsi_task,
(unsigned long)hostdata);
if (request_irq(vdev->irq,
rpavscsi_handle_event,
0, "ibmvscsi", (void *)hostdata) != 0) {
dev_err(hostdata->dev, "couldn't register irq 0x%x\n",
vdev->irq);
goto req_irq_failed;
}
rc = vio_enable_interrupts(vdev);
if (rc != 0) {
dev_err(hostdata->dev, "Error %d enabling interrupts!!!\n", rc);
goto req_irq_failed;
}
return retrc;
req_irq_failed:
[SCSI] ibmvscsi: Fix oops when an interrupt is pending during probe A driver needs to be ready to take an interrupt as soon as it registers an interrupt handler. I noticed the following oops when testing kdump: ipr: IBM Power RAID SCSI Device Driver version: 2.5.0 (February 11, 2010) ibmvscsi 30000002: SRP_VERSION: 16.a ibmvscsi 30000002: SRP_VERSION: 16.a Unable to handle kernel paging request for data at address 0x00000000 ... pc: c000000004085e34: .tasklet_action+0xf4/0x1dc ... c000000004086fe4 .__do_softirq+0x16c/0x2c0 c00000000403138c .call_do_softirq+0x14/0x24 c00000000400ee14 .do_softirq+0xa0/0x104 c00000000408690c .irq_exit+0x70/0xd0 c00000000400f190 .do_IRQ+0x214/0x2a8 c000000004004804 hardware_interrupt_entry+0x1c/0x98 --- Exception: 501 (Hardware Interrupt) at c00000000400c544 .raw_local_irq_restore+0x48/0x54 c00000000465d2a8 ._raw_spin_unlock_irqrestore+0x74/0xa0 c0000000040e7f00 .__setup_irq+0x2ec/0x3f0 c0000000040e8198 .request_threaded_irq+0x194/0x22c c00000000446d854 .rpavscsi_init_crq_queue+0x284/0x3f0 c00000000446c764 .ibmvscsi_probe+0x688/0x710 c00000000402903c .vio_bus_probe+0x37c/0x3e4 c000000004403f10 .driver_probe_device+0xec/0x1b8 c000000004404088 .__driver_attach+0xac/0xf4 c000000004403184 .bus_for_each_dev+0x98/0x104 c000000004403c98 .driver_attach+0x40/0x60 c0000000044026f0 .bus_add_driver+0x154/0x324 c0000000044045d0 .driver_register+0xe8/0x1ac c00000000402b2a8 .vio_register_driver+0x54/0x74 c000000004933ea4 .ibmvscsi_module_init+0x80/0xc0 c000000004009834 .do_one_initcall+0x98/0x1d8 c0000000049005b4 .kernel_init+0x27c/0x33c c000000004031550 .kernel_thread+0x54/0x70 srp_task needs to be setup before request_irq. The patch below fixes the oops. Signed-off-by: Anton Blanchard <anton@samba.org> Acked-by: Brian King <brking@linux.vnet.ibm.com> Signed-off-by: James Bottomley <James.Bottomley@suse.de>
2010-07-13 12:59:29 +08:00
tasklet_kill(&hostdata->srp_task);
rc = 0;
do {
if (rc)
msleep(100);
rc = plpar_hcall_norets(H_FREE_CRQ, vdev->unit_address);
} while ((rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
reg_crq_failed:
dma_unmap_single(hostdata->dev,
queue->msg_token,
queue->size * sizeof(*queue->msgs), DMA_BIDIRECTIONAL);
map_failed:
free_page((unsigned long)queue->msgs);
malloc_failed:
return -1;
}
/**
* reenable_crq_queue: - reenables a crq after
* @queue: crq_queue to initialize and register
* @hostdata: ibmvscsi_host_data of host
*
*/
static int rpavscsi_reenable_crq_queue(struct crq_queue *queue,
struct ibmvscsi_host_data *hostdata)
{
int rc = 0;
struct vio_dev *vdev = to_vio_dev(hostdata->dev);
/* Re-enable the CRQ */
do {
if (rc)
msleep(100);
rc = plpar_hcall_norets(H_ENABLE_CRQ, vdev->unit_address);
} while ((rc == H_IN_PROGRESS) || (rc == H_BUSY) || (H_IS_LONG_BUSY(rc)));
if (rc)
dev_err(hostdata->dev, "Error %d enabling adapter\n", rc);
return rc;
}
/**
* rpavscsi_resume: - resume after suspend
* @hostdata: ibmvscsi_host_data of host
*
*/
static int rpavscsi_resume(struct ibmvscsi_host_data *hostdata)
{
vio_disable_interrupts(to_vio_dev(hostdata->dev));
tasklet_schedule(&hostdata->srp_task);
return 0;
}
struct ibmvscsi_ops rpavscsi_ops = {
.init_crq_queue = rpavscsi_init_crq_queue,
.release_crq_queue = rpavscsi_release_crq_queue,
.reset_crq_queue = rpavscsi_reset_crq_queue,
.reenable_crq_queue = rpavscsi_reenable_crq_queue,
.send_crq = rpavscsi_send_crq,
.resume = rpavscsi_resume,
};