OpenCloudOS-Kernel/drivers/scsi/cxlflash/common.h

341 lines
9.0 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* 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
*/
#ifndef _CXLFLASH_COMMON_H
#define _CXLFLASH_COMMON_H
#include <linux/async.h>
#include <linux/cdev.h>
#include <linux/irq_poll.h>
#include <linux/list.h>
#include <linux/rwsem.h>
#include <linux/types.h>
#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>
#include <scsi/scsi_device.h>
#include "backend.h"
cxlflash: Fix to avoid corrupting adapter fops The fops owned by the adapter can be corrupted in certain scenarios, opening a window where certain fops are temporarily NULLed before being reset to their proper value. This can potentially lead software to make incorrect decisions, leaving the user with the inability to function as intended. An example of this behavior can be observed when there are a number of users with a high rate of turn around (attach to LUN, perform an I/O, detach from LUN, repeat). Every so often a user is given a valid context and adapter file descriptor, but the file associated with the descriptor lacks the correct read permission bit (FMODE_CAN_READ) and thus the read system call bails before calling the valid read fop. Background: The fops is stored in the adapter structure to provide the ability to lookup the adapter structure from within the fop handler. CXL services use the file's private_data and at present, the CXL context does not have a private section. In an effort to limit areas of the cxlflash driver with code specific the superpipe function, a design choice was made to keep the details of the fops situated away from the legacy portions of the driver. This drove the behavior that the adapter fops is set at the beginning of the disk attach ioctl handler when there are no users present. The corruption that this fix remedies is due to the fact that the fops is initially defaulted to values found within a static structure. When the fops is handed down to the CXL services later in the attach path, certain services are patched. The fops structure remains correct until the user count drops to 0 and the fops is reset, triggering the process to repeat again. The user counts are tightly coupled with the creation and deletion of the user context. If multiple users perform a disk attach at the same time, when the user count is currently 0, some users can be in the middle of obtaining a file descriptor and have not yet reached the context creation code that [in addition to creating the context] increments the user count. Subsequent users coming in to perform the attach see that the user count is still 0, and reinitialize the fops, temporarily removing the patched fops. The users that are in the middle obtaining their file descriptor may then receive an invalid descriptor. The fix simply removes the user count altogether and moves the fops initialization to probe time such that it is only performed one time for the life of the adapter. In the future, if the CXL services adopt a private member for their context, that could be used to store the adapter structure reference and cxlflash could revert to a model that does not require an embedded fops. Signed-off-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Manoj N. Kumar <manoj@linux.vnet.ibm.com> Reviewed-by: Brian King <brking@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Reviewed-by: Daniel Axtens <dja@axtens.net> Reviewed-by: Tomas Henzl <thenzl@redhat.com> Signed-off-by: James Bottomley <JBottomley@Odin.com>
2015-10-22 04:15:37 +08:00
extern const struct file_operations cxlflash_cxl_fops;
#define MAX_CONTEXT CXLFLASH_MAX_CONTEXT /* num contexts per afu */
#define MAX_FC_PORTS CXLFLASH_MAX_FC_PORTS /* max ports per AFU */
#define LEGACY_FC_PORTS 2 /* legacy ports per AFU */
#define CHAN2PORTBANK(_x) ((_x) >> ilog2(CXLFLASH_NUM_FC_PORTS_PER_BANK))
#define CHAN2BANKPORT(_x) ((_x) & (CXLFLASH_NUM_FC_PORTS_PER_BANK - 1))
#define CHAN2PORTMASK(_x) (1 << (_x)) /* channel to port mask */
#define PORTMASK2CHAN(_x) (ilog2((_x))) /* port mask to channel */
#define PORTNUM2CHAN(_x) ((_x) - 1) /* port number to channel */
#define CXLFLASH_BLOCK_SIZE 4096 /* 4K blocks */
#define CXLFLASH_MAX_XFER_SIZE 16777216 /* 16MB transfer */
#define CXLFLASH_MAX_SECTORS (CXLFLASH_MAX_XFER_SIZE/512) /* SCSI wants
* max_sectors
* in units of
* 512 byte
* sectors
*/
#define MAX_RHT_PER_CONTEXT (PAGE_SIZE / sizeof(struct sisl_rht_entry))
/* AFU command retry limit */
#define MC_RETRY_CNT 5 /* Sufficient for SCSI and certain AFU errors */
/* Command management definitions */
#define CXLFLASH_MAX_CMDS 256
#define CXLFLASH_MAX_CMDS_PER_LUN CXLFLASH_MAX_CMDS
/* RRQ for master issued cmds */
#define NUM_RRQ_ENTRY CXLFLASH_MAX_CMDS
/* SQ for master issued cmds */
#define NUM_SQ_ENTRY CXLFLASH_MAX_CMDS
/* Hardware queue definitions */
#define CXLFLASH_DEF_HWQS 1
#define CXLFLASH_MAX_HWQS 8
#define PRIMARY_HWQ 0
static inline void check_sizes(void)
{
BUILD_BUG_ON_NOT_POWER_OF_2(CXLFLASH_NUM_FC_PORTS_PER_BANK);
BUILD_BUG_ON_NOT_POWER_OF_2(CXLFLASH_MAX_CMDS);
}
/* AFU defines a fixed size of 4K for command buffers (borrow 4K page define) */
#define CMD_BUFSIZE SIZE_4K
enum cxlflash_lr_state {
LINK_RESET_INVALID,
LINK_RESET_REQUIRED,
LINK_RESET_COMPLETE
};
enum cxlflash_init_state {
INIT_STATE_NONE,
INIT_STATE_PCI,
INIT_STATE_AFU,
INIT_STATE_SCSI,
INIT_STATE_CDEV
};
enum cxlflash_state {
STATE_PROBING, /* Initial state during probe */
STATE_PROBED, /* Temporary state, probe completed but EEH occurred */
STATE_NORMAL, /* Normal running state, everything good */
STATE_RESET, /* Reset state, trying to reset/recover */
STATE_FAILTERM /* Failed/terminating state, error out users/threads */
};
enum cxlflash_hwq_mode {
HWQ_MODE_RR, /* Roundrobin (default) */
HWQ_MODE_TAG, /* Distribute based on block MQ tag */
HWQ_MODE_CPU, /* CPU affinity */
MAX_HWQ_MODE
};
/*
* Each context has its own set of resource handles that is visible
* only from that context.
*/
struct cxlflash_cfg {
struct afu *afu;
const struct cxlflash_backend_ops *ops;
struct pci_dev *dev;
struct pci_device_id *dev_id;
struct Scsi_Host *host;
int num_fc_ports;
struct cdev cdev;
struct device *chardev;
ulong cxlflash_regs_pci;
struct work_struct work_q;
enum cxlflash_init_state init_state;
enum cxlflash_lr_state lr_state;
int lr_port;
atomic_t scan_host_needed;
void *afu_cookie;
atomic_t recovery_threads;
struct mutex ctx_recovery_mutex;
struct mutex ctx_tbl_list_mutex;
struct rw_semaphore ioctl_rwsem;
struct ctx_info *ctx_tbl[MAX_CONTEXT];
struct list_head ctx_err_recovery; /* contexts w/ recovery pending */
struct file_operations cxl_fops;
/* Parameters that are LUN table related */
int last_lun_index[MAX_FC_PORTS];
int promote_lun_index;
struct list_head lluns; /* list of llun_info structs */
wait_queue_head_t tmf_waitq;
spinlock_t tmf_slock;
bool tmf_active;
bool ws_unmap; /* Write-same unmap supported */
wait_queue_head_t reset_waitq;
enum cxlflash_state state;
async_cookie_t async_reset_cookie;
};
struct afu_cmd {
struct sisl_ioarcb rcb; /* IOARCB (cache line aligned) */
struct sisl_ioasa sa; /* IOASA must follow IOARCB */
struct afu *parent;
struct scsi_cmnd *scp;
struct completion cevent;
struct list_head queue;
u32 hwq_index;
u8 cmd_tmf:1,
cmd_aborted:1;
struct list_head list; /* Pending commands link */
/* As per the SISLITE spec the IOARCB EA has to be 16-byte aligned.
* However for performance reasons the IOARCB/IOASA should be
* cache line aligned.
*/
} __aligned(cache_line_size());
static inline struct afu_cmd *sc_to_afuc(struct scsi_cmnd *sc)
{
return PTR_ALIGN(scsi_cmd_priv(sc), __alignof__(struct afu_cmd));
}
static inline struct afu_cmd *sc_to_afuci(struct scsi_cmnd *sc)
{
struct afu_cmd *afuc = sc_to_afuc(sc);
INIT_LIST_HEAD(&afuc->queue);
return afuc;
}
static inline struct afu_cmd *sc_to_afucz(struct scsi_cmnd *sc)
{
struct afu_cmd *afuc = sc_to_afuc(sc);
memset(afuc, 0, sizeof(*afuc));
return sc_to_afuci(sc);
}
struct hwq {
/* Stuff requiring alignment go first. */
struct sisl_ioarcb sq[NUM_SQ_ENTRY]; /* 16K SQ */
u64 rrq_entry[NUM_RRQ_ENTRY]; /* 2K RRQ */
/* Beware of alignment till here. Preferably introduce new
* fields after this point
*/
struct afu *afu;
void *ctx_cookie;
struct sisl_host_map __iomem *host_map; /* MC host map */
struct sisl_ctrl_map __iomem *ctrl_map; /* MC control map */
ctx_hndl_t ctx_hndl; /* master's context handle */
u32 index; /* Index of this hwq */
int num_irqs; /* Number of interrupts requested for context */
struct list_head pending_cmds; /* Commands pending completion */
atomic_t hsq_credits;
spinlock_t hsq_slock; /* Hardware send queue lock */
struct sisl_ioarcb *hsq_start;
struct sisl_ioarcb *hsq_end;
struct sisl_ioarcb *hsq_curr;
spinlock_t hrrq_slock;
u64 *hrrq_start;
u64 *hrrq_end;
u64 *hrrq_curr;
bool toggle;
scsi: cxlflash: Handle spurious interrupts The following Oops can occur when there is heavy I/O traffic and the host is reset by a tool such as sg_reset. [c000200fff3fbc90] c00800001690117c process_cmd_doneq+0x104/0x500 [cxlflash] (unreliable) [c000200fff3fbd80] c008000016901648 cxlflash_rrq_irq+0xd0/0x150 [cxlflash] [c000200fff3fbde0] c000000000193130 __handle_irq_event_percpu+0xa0/0x310 [c000200fff3fbea0] c0000000001933d8 handle_irq_event_percpu+0x38/0x90 [c000200fff3fbee0] c000000000193494 handle_irq_event+0x64/0xb0 [c000200fff3fbf10] c000000000198ea0 handle_fasteoi_irq+0xc0/0x230 [c000200fff3fbf40] c00000000019182c generic_handle_irq+0x4c/0x70 [c000200fff3fbf60] c00000000001794c __do_irq+0x7c/0x1c0 [c000200fff3fbf90] c00000000002a390 call_do_irq+0x14/0x24 [c000200e5828fab0] c000000000017b2c do_IRQ+0x9c/0x130 [c000200e5828fb00] c000000000009b04 h_virt_irq_common+0x114/0x120 When a context is reset, the pending commands are flushed and the AFU is notified. Before the AFU handles this request there could be command completion interrupts queued to PHB which are yet to be delivered to the context. In this scenario, a context could receive an interrupt for a command that has been flushed, leading to a possible crash when the memory for the flushed command is accessed. To resolve this problem, a boolean will indicate if the hardware queue is ready to process interrupts or not. This can be evaluated in the interrupt handler before proessing an interrupt. 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>
2018-03-27 00:35:42 +08:00
bool hrrq_online;
2016-11-29 08:41:45 +08:00
s64 room;
struct irq_poll irqpoll;
} __aligned(cache_line_size());
struct afu {
struct hwq hwqs[CXLFLASH_MAX_HWQS];
int (*send_cmd)(struct afu *afu, struct afu_cmd *cmd);
int (*context_reset)(struct hwq *hwq);
/* AFU HW */
struct cxlflash_afu_map __iomem *afu_map; /* entire MMIO map */
atomic_t cmds_active; /* Number of currently active AFU commands */
struct mutex sync_active; /* Mutex to serialize AFU commands */
u64 hb;
u32 internal_lun; /* User-desired LUN mode for this AFU */
u32 num_hwqs; /* Number of hardware queues */
u32 desired_hwqs; /* Desired h/w queues, effective on AFU reset */
enum cxlflash_hwq_mode hwq_mode; /* Steering mode for h/w queues */
u32 hwq_rr_count; /* Count to distribute traffic for roundrobin */
char version[16];
u64 interface_version;
u32 irqpoll_weight;
struct cxlflash_cfg *parent; /* Pointer back to parent cxlflash_cfg */
};
static inline struct hwq *get_hwq(struct afu *afu, u32 index)
{
WARN_ON(index >= CXLFLASH_MAX_HWQS);
return &afu->hwqs[index];
}
static inline bool afu_is_irqpoll_enabled(struct afu *afu)
{
return !!afu->irqpoll_weight;
}
static inline bool afu_has_cap(struct afu *afu, u64 cap)
{
u64 afu_cap = afu->interface_version >> SISL_INTVER_CAP_SHIFT;
return afu_cap & cap;
}
static inline bool afu_is_ocxl_lisn(struct afu *afu)
{
return afu_has_cap(afu, SISL_INTVER_CAP_OCXL_LISN);
}
static inline bool afu_is_afu_debug(struct afu *afu)
{
return afu_has_cap(afu, SISL_INTVER_CAP_AFU_DEBUG);
}
static inline bool afu_is_lun_provision(struct afu *afu)
{
return afu_has_cap(afu, SISL_INTVER_CAP_LUN_PROVISION);
}
static inline bool afu_is_sq_cmd_mode(struct afu *afu)
{
return afu_has_cap(afu, SISL_INTVER_CAP_SQ_CMD_MODE);
}
static inline bool afu_is_ioarrin_cmd_mode(struct afu *afu)
{
return afu_has_cap(afu, SISL_INTVER_CAP_IOARRIN_CMD_MODE);
}
static inline u64 lun_to_lunid(u64 lun)
{
__be64 lun_id;
int_to_scsilun(lun, (struct scsi_lun *)&lun_id);
return be64_to_cpu(lun_id);
}
static inline struct fc_port_bank __iomem *get_fc_port_bank(
struct cxlflash_cfg *cfg, int i)
{
struct afu *afu = cfg->afu;
return &afu->afu_map->global.bank[CHAN2PORTBANK(i)];
}
static inline __be64 __iomem *get_fc_port_regs(struct cxlflash_cfg *cfg, int i)
{
struct fc_port_bank __iomem *fcpb = get_fc_port_bank(cfg, i);
return &fcpb->fc_port_regs[CHAN2BANKPORT(i)][0];
}
static inline __be64 __iomem *get_fc_port_luns(struct cxlflash_cfg *cfg, int i)
{
struct fc_port_bank __iomem *fcpb = get_fc_port_bank(cfg, i);
return &fcpb->fc_port_luns[CHAN2BANKPORT(i)][0];
}
int cxlflash_afu_sync(struct afu *afu, ctx_hndl_t c, res_hndl_t r, u8 mode);
void cxlflash_list_init(void);
void cxlflash_term_global_luns(void);
void cxlflash_free_errpage(void);
scsi: ata: Use unsigned int for cmd's type in ioctls in scsi_host_template Clang warns several times in the scsi subsystem (trimmed for brevity): drivers/scsi/hpsa.c:6209:7: warning: overflow converting case value to switch condition type (2147762695 to 18446744071562347015) [-Wswitch] case CCISS_GETBUSTYPES: ^ drivers/scsi/hpsa.c:6208:7: warning: overflow converting case value to switch condition type (2147762694 to 18446744071562347014) [-Wswitch] case CCISS_GETHEARTBEAT: ^ The root cause is that the _IOC macro can generate really large numbers, which don't fit into type 'int', which is used for the cmd parameter in the ioctls in scsi_host_template. My research into how GCC and Clang are handling this at a low level didn't prove fruitful. However, looking at the rest of the kernel tree, all ioctls use an 'unsigned int' for the cmd parameter, which will fit all of the _IOC values in the scsi/ata subsystems. Make that change because none of the ioctls expect a negative value for any command, it brings the ioctls inline with the reset of the kernel, and it removes ambiguity, which is never good when dealing with compilers. Link: https://github.com/ClangBuiltLinux/linux/issues/85 Link: https://github.com/ClangBuiltLinux/linux/issues/154 Link: https://github.com/ClangBuiltLinux/linux/issues/157 Signed-off-by: Nathan Chancellor <natechancellor@gmail.com> Acked-by: Bradley Grove <bgrove@attotech.com> Acked-by: Don Brace <don.brace@microsemi.com> Reviewed-by: Bart Van Assche <bvanassche@acm.org> Tested-by: Nick Desaulniers <ndesaulniers@google.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
2019-02-08 00:07:20 +08:00
int cxlflash_ioctl(struct scsi_device *sdev, unsigned int cmd,
void __user *arg);
void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg);
int cxlflash_mark_contexts_error(struct cxlflash_cfg *cfg);
void cxlflash_term_local_luns(struct cxlflash_cfg *cfg);
void cxlflash_restore_luntable(struct cxlflash_cfg *cfg);
#endif /* ifndef _CXLFLASH_COMMON_H */