linux/drivers/scsi/cxlflash/lunmgt.c

283 lines
7.4 KiB
C
Raw Normal View History

/*
* CXL Flash Device Driver
*
* Written by: Manoj N. Kumar <manoj@linux.vnet.ibm.com>, IBM Corporation
* Matthew R. Ochs <mrochs@linux.vnet.ibm.com>, IBM Corporation
*
* Copyright (C) 2015 IBM Corporation
*
* 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.
*/
#include <asm/unaligned.h>
#include <linux/interrupt.h>
#include <linux/pci.h>
#include <scsi/scsi_host.h>
#include <uapi/scsi/cxlflash_ioctl.h>
#include "sislite.h"
#include "common.h"
#include "vlun.h"
#include "superpipe.h"
/**
* create_local() - allocate and initialize a local LUN information structure
* @sdev: SCSI device associated with LUN.
* @wwid: World Wide Node Name for LUN.
*
* Return: Allocated local llun_info structure on success, NULL on failure
*/
static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid)
{
struct cxlflash_cfg *cfg = shost_priv(sdev->host);
struct device *dev = &cfg->dev->dev;
struct llun_info *lli = NULL;
lli = kzalloc(sizeof(*lli), GFP_KERNEL);
if (unlikely(!lli)) {
dev_err(dev, "%s: could not allocate lli\n", __func__);
goto out;
}
lli->sdev = sdev;
lli->host_no = sdev->host->host_no;
lli->in_table = false;
memcpy(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN);
out:
return lli;
}
/**
* create_global() - allocate and initialize a global LUN information structure
* @sdev: SCSI device associated with LUN.
* @wwid: World Wide Node Name for LUN.
*
* Return: Allocated global glun_info structure on success, NULL on failure
*/
static struct glun_info *create_global(struct scsi_device *sdev, u8 *wwid)
{
struct cxlflash_cfg *cfg = shost_priv(sdev->host);
struct device *dev = &cfg->dev->dev;
struct glun_info *gli = NULL;
gli = kzalloc(sizeof(*gli), GFP_KERNEL);
if (unlikely(!gli)) {
dev_err(dev, "%s: could not allocate gli\n", __func__);
goto out;
}
mutex_init(&gli->mutex);
memcpy(gli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN);
out:
return gli;
}
/**
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
* lookup_local() - find a local LUN information structure by WWID
* @cfg: Internal structure associated with the host.
* @wwid: WWID associated with LUN.
*
* Return: Found local lun_info structure on success, NULL on failure
*/
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
static struct llun_info *lookup_local(struct cxlflash_cfg *cfg, u8 *wwid)
{
struct llun_info *lli, *temp;
list_for_each_entry_safe(lli, temp, &cfg->lluns, list)
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
if (!memcmp(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN))
return lli;
return NULL;
}
/**
* lookup_global() - find a global LUN information structure by WWID
* @wwid: WWID associated with LUN.
*
* Return: Found global lun_info structure on success, NULL on failure
*/
static struct glun_info *lookup_global(u8 *wwid)
{
struct glun_info *gli, *temp;
list_for_each_entry_safe(gli, temp, &global.gluns, list)
if (!memcmp(gli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN))
return gli;
return NULL;
}
/**
* find_and_create_lun() - find or create a local LUN information structure
* @sdev: SCSI device associated with LUN.
* @wwid: WWID associated with LUN.
*
* The LUN is kept both in a local list (per adapter) and in a global list
* (across all adapters). Certain attributes of the LUN are local to the
* adapter (such as index, port selection mask, etc.).
*
* The block allocation map is shared across all adapters (i.e. associated
* wih the global list). Since different attributes are associated with
* the per adapter and global entries, allocate two separate structures for each
* LUN (one local, one global).
*
* Keep a pointer back from the local to the global entry.
*
* This routine assumes the caller holds the global mutex.
*
* Return: Found/Allocated local lun_info structure on success, NULL on failure
*/
static struct llun_info *find_and_create_lun(struct scsi_device *sdev, u8 *wwid)
{
struct cxlflash_cfg *cfg = shost_priv(sdev->host);
struct device *dev = &cfg->dev->dev;
struct llun_info *lli = NULL;
struct glun_info *gli = NULL;
if (unlikely(!wwid))
goto out;
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
lli = lookup_local(cfg, wwid);
if (lli)
goto out;
lli = create_local(sdev, wwid);
if (unlikely(!lli))
goto out;
gli = lookup_global(wwid);
if (gli) {
lli->parent = gli;
list_add(&lli->list, &cfg->lluns);
goto out;
}
gli = create_global(sdev, wwid);
if (unlikely(!gli)) {
kfree(lli);
lli = NULL;
goto out;
}
lli->parent = gli;
list_add(&lli->list, &cfg->lluns);
list_add(&gli->list, &global.gluns);
out:
dev_dbg(dev, "%s: returning lli=%p, gli=%p\n", __func__, lli, gli);
return lli;
}
/**
* cxlflash_term_local_luns() - Delete all entries from local LUN list, free.
* @cfg: Internal structure associated with the host.
*/
void cxlflash_term_local_luns(struct cxlflash_cfg *cfg)
{
struct llun_info *lli, *temp;
mutex_lock(&global.mutex);
list_for_each_entry_safe(lli, temp, &cfg->lluns, list) {
list_del(&lli->list);
kfree(lli);
}
mutex_unlock(&global.mutex);
}
/**
* cxlflash_list_init() - initializes the global LUN list
*/
void cxlflash_list_init(void)
{
INIT_LIST_HEAD(&global.gluns);
mutex_init(&global.mutex);
global.err_page = NULL;
}
/**
* cxlflash_term_global_luns() - frees resources associated with global LUN list
*/
void cxlflash_term_global_luns(void)
{
struct glun_info *gli, *temp;
mutex_lock(&global.mutex);
list_for_each_entry_safe(gli, temp, &global.gluns, list) {
list_del(&gli->list);
cxlflash_ba_terminate(&gli->blka.ba_lun);
kfree(gli);
}
mutex_unlock(&global.mutex);
}
/**
* cxlflash_manage_lun() - handles LUN management activities
* @sdev: SCSI device associated with LUN.
* @manage: Manage ioctl data structure.
*
* This routine is used to notify the driver about a LUN's WWID and associate
* SCSI devices (sdev) with a global LUN instance. Additionally it serves to
* change a LUN's operating mode: legacy or superpipe.
*
* Return: 0 on success, -errno on failure
*/
int cxlflash_manage_lun(struct scsi_device *sdev,
struct dk_cxlflash_manage_lun *manage)
{
struct cxlflash_cfg *cfg = shost_priv(sdev->host);
struct device *dev = &cfg->dev->dev;
struct llun_info *lli = NULL;
int rc = 0;
u64 flags = manage->hdr.flags;
u32 chan = sdev->channel;
mutex_lock(&global.mutex);
lli = find_and_create_lun(sdev, manage->wwid);
dev_dbg(dev, "%s: WWID=%016llx%016llx, flags=%016llx lli=%p\n",
__func__, get_unaligned_be64(&manage->wwid[0]),
get_unaligned_be64(&manage->wwid[8]), manage->hdr.flags, lli);
if (unlikely(!lli)) {
rc = -ENOMEM;
goto out;
}
if (flags & DK_CXLFLASH_MANAGE_LUN_ENABLE_SUPERPIPE) {
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
/*
* Update port selection mask based upon channel, store off LUN
* in unpacked, AFU-friendly format, and hang LUN reference in
* the sdev.
*/
lli->port_sel |= CHAN2PORTMASK(chan);
lli->lun_id[chan] = lun_to_lunid(sdev->lun);
sdev->hostdata = lli;
} else if (flags & DK_CXLFLASH_MANAGE_LUN_DISABLE_SUPERPIPE) {
if (lli->parent->mode != MODE_NONE)
rc = -EBUSY;
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
else {
scsi: cxlflash: Fix crash in cxlflash_restore_luntable() During test, the following crash was observed: [34538.981505] Faulting instruction address: 0xd000000007c9c870 cpu 0x9: Vector: 300 (Data Access) at [c0000007f1e8f590] pc: d000000007c9c870: cxlflash_restore_luntable+0x70/0x1d0 [cxlflash] lr: d000000007c9c84c: cxlflash_restore_luntable+0x4c/0x1d0 [cxlflash] sp: c0000007f1e8f810 msr: 9000000100009033 dar: c00000171d637438 dsisr: 40000000 current = 0xc0000007f1e43f90 paca = 0xc000000007b25100 softe: 0 irq_happened: 0x01 pid = 493, comm = eehd enter ? for help [c0000007f1e8f8a0] d000000007c940b0 init_afu+0xd60/0x1200 [cxlflash] [c0000007f1e8f9a0] d000000007c945a8 cxlflash_pci_slot_reset+0x58/0xe0 [cxlflash] [c0000007f1e8fa20] d00000000715f790 cxl_pci_slot_reset+0x230/0x340 [cxl] [c0000007f1e8fae0] c000000000040dd4 eeh_report_reset+0x144/0x180 [c0000007f1e8fb20] c00000000003f708 eeh_pe_dev_traverse+0x98/0x170 [c0000007f1e8fbb0] c000000000041618 eeh_handle_normal_event+0x328/0x410 [c0000007f1e8fc30] c000000000041db8 eeh_handle_event+0x178/0x330 [c0000007f1e8fce0] c000000000042118 eeh_event_handler+0x1a8/0x1b0 [c0000007f1e8fd80] c00000000011420c kthread+0xec/0x100 [c0000007f1e8fe30] c00000000000a47c ret_from_kernel_thread+0x5c/0xe0 When superpipe mode is disabled for a LUN, the references for the local lun are deleted but the LUN is still identified as being present in the LUN table. This mismatched state can result in the above crash when the LUN table is restored during an error recovery operation. To fix this issue, the local LUN information structure is updated to reflect the LUN is no longer in the LUN table once all references to the LUN are gone. Signed-off-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com> Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-11-29 00:41:19 +00:00
/*
* Clean up local LUN for this port and reset table
* tracking when no more references exist.
*/
sdev->hostdata = NULL;
lli->port_sel &= ~CHAN2PORTMASK(chan);
scsi: cxlflash: Fix crash in cxlflash_restore_luntable() During test, the following crash was observed: [34538.981505] Faulting instruction address: 0xd000000007c9c870 cpu 0x9: Vector: 300 (Data Access) at [c0000007f1e8f590] pc: d000000007c9c870: cxlflash_restore_luntable+0x70/0x1d0 [cxlflash] lr: d000000007c9c84c: cxlflash_restore_luntable+0x4c/0x1d0 [cxlflash] sp: c0000007f1e8f810 msr: 9000000100009033 dar: c00000171d637438 dsisr: 40000000 current = 0xc0000007f1e43f90 paca = 0xc000000007b25100 softe: 0 irq_happened: 0x01 pid = 493, comm = eehd enter ? for help [c0000007f1e8f8a0] d000000007c940b0 init_afu+0xd60/0x1200 [cxlflash] [c0000007f1e8f9a0] d000000007c945a8 cxlflash_pci_slot_reset+0x58/0xe0 [cxlflash] [c0000007f1e8fa20] d00000000715f790 cxl_pci_slot_reset+0x230/0x340 [cxl] [c0000007f1e8fae0] c000000000040dd4 eeh_report_reset+0x144/0x180 [c0000007f1e8fb20] c00000000003f708 eeh_pe_dev_traverse+0x98/0x170 [c0000007f1e8fbb0] c000000000041618 eeh_handle_normal_event+0x328/0x410 [c0000007f1e8fc30] c000000000041db8 eeh_handle_event+0x178/0x330 [c0000007f1e8fce0] c000000000042118 eeh_event_handler+0x1a8/0x1b0 [c0000007f1e8fd80] c00000000011420c kthread+0xec/0x100 [c0000007f1e8fe30] c00000000000a47c ret_from_kernel_thread+0x5c/0xe0 When superpipe mode is disabled for a LUN, the references for the local lun are deleted but the LUN is still identified as being present in the LUN table. This mismatched state can result in the above crash when the LUN table is restored during an error recovery operation. To fix this issue, the local LUN information structure is updated to reflect the LUN is no longer in the LUN table once all references to the LUN are gone. Signed-off-by: Uma Krishnan <ukrishn@linux.vnet.ibm.com> Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2016-11-29 00:41:19 +00:00
if (lli->port_sel == 0U)
lli->in_table = false;
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
}
}
dev_dbg(dev, "%s: port_sel=%08x chan=%u lun_id=%016llx\n",
__func__, lli->port_sel, chan, lli->lun_id[chan]);
cxlflash: Fix to avoid corrupting port selection mask The port selection mask of a LUN can be corrupted when the manage LUN ioctl (DK_CXLFLASH_MANAGE_LUN) is issued more than once for any device. This mask indicates to the AFU which port[s] can be used for a data transfer to/from a particular LUN. The mask is critical to ensuring the correct behavior when using the virtual LUN function of this adapter. When the mask is configured for both ports, an I/O may be sent to either port as the AFU assumes that each port has access to the same physical device (specified by LUN ID in the port LUN table). In a situation where the mask becomes incorrectly configured to reflect access to both ports when in fact there is only access through a single port, an I/O can be targeted to the wrong physical device. This can lead to data corruption among other ill effects (e.g. security leaks). The cause for this corruption is the assumption that the ioctl will only be called a second time for a LUN when it is being configured for access via a second port. A boolean 'newly_created' variable is used to differentiate between a LUN that was created (and subsequently configured for single port access) and one that is destined for access across both ports. While initially set to 'true', this sticky boolean is toggled to the 'false' state during a lookup on any next ioctl performed on a device with a matching WWN/WWID. The code fails to realize that the match could in fact be the same device calling in again. From here, an assumption is made that any LUN with 'newly_created' set to 'false' is configured for access over both ports and the port selection mask is set to reflect this. Any future attempts to use this LUN for hosting a virtual LUN will result in the port LUN table being incorrectly programmed. As a remedy, the 'newly_created' concept was removed entirely and replaced with code that always constructs the port selection mask based upon the SCSI channel of the LUN being accessed. The bits remain sticky, therefore allowing for a device to be accessed over both ports when that is in fact the correct physical configuration. Also included in this commit are a few minor related changes to enhance the fix and provide better debug information for port selection mask and port LUN table bugs in the future. These include renaming refresh_local() to lookup_local(), tracing the WWN/WWID as a big-endian entity, and tracing the port selection mask, SCSI channel, and LUN ID each time the port LUN table is programmed. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Acked-by: Manoj Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-21 20:16:15 +00:00
out:
mutex_unlock(&global.mutex);
dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
return rc;
}