From 65be2c79acc3aa0f9c0e8d4871f5a451d854465a Mon Sep 17 00:00:00 2001 From: "Matthew R. Ochs" Date: Thu, 13 Aug 2015 21:47:43 -0500 Subject: cxlflash: Superpipe support Add superpipe supporting infrastructure to device driver for the IBM CXL Flash adapter. This patch allows userspace applications to take advantage of the accelerated I/O features that this adapter provides and bypass the traditional filesystem stack. Signed-off-by: Matthew R. Ochs Signed-off-by: Manoj N. Kumar Reviewed-by: Michael Neuling Reviewed-by: Wen Xiong Reviewed-by: Brian King Signed-off-by: James Bottomley --- drivers/scsi/cxlflash/superpipe.c | 2014 +++++++++++++++++++++++++++++++++++++ 1 file changed, 2014 insertions(+) create mode 100644 drivers/scsi/cxlflash/superpipe.c (limited to 'drivers/scsi/cxlflash/superpipe.c') diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c new file mode 100644 index 000000000000..3c8bce8bbb0b --- /dev/null +++ b/drivers/scsi/cxlflash/superpipe.c @@ -0,0 +1,2014 @@ +/* + * CXL Flash Device Driver + * + * Written by: Manoj N. Kumar , IBM Corporation + * Matthew R. Ochs , 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 +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include "sislite.h" +#include "common.h" +#include "superpipe.h" + +struct cxlflash_global global; + +/** + * marshal_det_to_rele() - translate detach to release structure + * @detach: Destination structure for the translate/copy. + * @rele: Source structure from which to translate/copy. + */ +static void marshal_det_to_rele(struct dk_cxlflash_detach *detach, + struct dk_cxlflash_release *release) +{ + release->hdr = detach->hdr; + release->context_id = detach->context_id; +} + +/** + * cxlflash_free_errpage() - frees resources associated with global error page + */ +void cxlflash_free_errpage(void) +{ + + mutex_lock(&global.mutex); + if (global.err_page) { + __free_page(global.err_page); + global.err_page = NULL; + } + mutex_unlock(&global.mutex); +} + +/** + * cxlflash_stop_term_user_contexts() - stops/terminates known user contexts + * @cfg: Internal structure associated with the host. + * + * When the host needs to go down, all users must be quiesced and their + * memory freed. This is accomplished by putting the contexts in error + * state which will notify the user and let them 'drive' the tear-down. + * Meanwhile, this routine camps until all user contexts have been removed. + */ +void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *cfg) +{ + struct device *dev = &cfg->dev->dev; + int i, found; + + cxlflash_mark_contexts_error(cfg); + + while (true) { + found = false; + + for (i = 0; i < MAX_CONTEXT; i++) + if (cfg->ctx_tbl[i]) { + found = true; + break; + } + + if (!found && list_empty(&cfg->ctx_err_recovery)) + return; + + dev_dbg(dev, "%s: Wait for user contexts to quiesce...\n", + __func__); + wake_up_all(&cfg->limbo_waitq); + ssleep(1); + } +} + +/** + * find_error_context() - locates a context by cookie on the error recovery list + * @cfg: Internal structure associated with the host. + * @rctxid: Desired context by id. + * @file: Desired context by file. + * + * Return: Found context on success, NULL on failure + */ +static struct ctx_info *find_error_context(struct cxlflash_cfg *cfg, u64 rctxid, + struct file *file) +{ + struct ctx_info *ctxi; + + list_for_each_entry(ctxi, &cfg->ctx_err_recovery, list) + if ((ctxi->ctxid == rctxid) || (ctxi->file == file)) + return ctxi; + + return NULL; +} + +/** + * get_context() - obtains a validated and locked context reference + * @cfg: Internal structure associated with the host. + * @rctxid: Desired context (raw, un-decoded format). + * @arg: LUN information or file associated with request. + * @ctx_ctrl: Control information to 'steer' desired lookup. + * + * NOTE: despite the name pid, in linux, current->pid actually refers + * to the lightweight process id (tid) and can change if the process is + * multi threaded. The tgid remains constant for the process and only changes + * when the process of fork. For all intents and purposes, think of tgid + * as a pid in the traditional sense. + * + * Return: Validated context on success, NULL on failure + */ +struct ctx_info *get_context(struct cxlflash_cfg *cfg, u64 rctxid, + void *arg, enum ctx_ctrl ctx_ctrl) +{ + struct device *dev = &cfg->dev->dev; + struct ctx_info *ctxi = NULL; + struct lun_access *lun_access = NULL; + struct file *file = NULL; + struct llun_info *lli = arg; + u64 ctxid = DECODE_CTXID(rctxid); + int rc; + pid_t pid = current->tgid, ctxpid = 0; + + if (ctx_ctrl & CTX_CTRL_FILE) { + lli = NULL; + file = (struct file *)arg; + } + + if (ctx_ctrl & CTX_CTRL_CLONE) + pid = current->parent->tgid; + + if (likely(ctxid < MAX_CONTEXT)) { + while (true) { + rc = mutex_lock_interruptible(&cfg->ctx_tbl_list_mutex); + if (rc) + goto out; + + ctxi = cfg->ctx_tbl[ctxid]; + if (ctxi) + if ((file && (ctxi->file != file)) || + (!file && (ctxi->ctxid != rctxid))) + ctxi = NULL; + + if ((ctx_ctrl & CTX_CTRL_ERR) || + (!ctxi && (ctx_ctrl & CTX_CTRL_ERR_FALLBACK))) + ctxi = find_error_context(cfg, rctxid, file); + if (!ctxi) { + mutex_unlock(&cfg->ctx_tbl_list_mutex); + goto out; + } + + /* + * Need to acquire ownership of the context while still + * under the table/list lock to serialize with a remove + * thread. Use the 'try' to avoid stalling the + * table/list lock for a single context. + * + * Note that the lock order is: + * + * cfg->ctx_tbl_list_mutex -> ctxi->mutex + * + * Therefore release ctx_tbl_list_mutex before retrying. + */ + rc = mutex_trylock(&ctxi->mutex); + mutex_unlock(&cfg->ctx_tbl_list_mutex); + if (rc) + break; /* got the context's lock! */ + } + + if (ctxi->unavail) + goto denied; + + ctxpid = ctxi->pid; + if (likely(!(ctx_ctrl & CTX_CTRL_NOPID))) + if (pid != ctxpid) + goto denied; + + if (lli) { + list_for_each_entry(lun_access, &ctxi->luns, list) + if (lun_access->lli == lli) + goto out; + goto denied; + } + } + +out: + dev_dbg(dev, "%s: rctxid=%016llX ctxinfo=%p ctxpid=%u pid=%u " + "ctx_ctrl=%u\n", __func__, rctxid, ctxi, ctxpid, pid, + ctx_ctrl); + + return ctxi; + +denied: + mutex_unlock(&ctxi->mutex); + ctxi = NULL; + goto out; +} + +/** + * put_context() - release a context that was retrieved from get_context() + * @ctxi: Context to release. + * + * For now, releasing the context equates to unlocking it's mutex. + */ +void put_context(struct ctx_info *ctxi) +{ + mutex_unlock(&ctxi->mutex); +} + +/** + * afu_attach() - attach a context to the AFU + * @cfg: Internal structure associated with the host. + * @ctxi: Context to attach. + * + * Upon setting the context capabilities, they must be confirmed with + * a read back operation as the context might have been closed since + * the mailbox was unlocked. When this occurs, registration is failed. + * + * Return: 0 on success, -errno on failure + */ +static int afu_attach(struct cxlflash_cfg *cfg, struct ctx_info *ctxi) +{ + struct device *dev = &cfg->dev->dev; + struct afu *afu = cfg->afu; + struct sisl_ctrl_map *ctrl_map = ctxi->ctrl_map; + int rc = 0; + u64 val; + + /* Unlock cap and restrict user to read/write cmds in translated mode */ + readq_be(&ctrl_map->mbox_r); + val = (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD); + writeq_be(val, &ctrl_map->ctx_cap); + val = readq_be(&ctrl_map->ctx_cap); + if (val != (SISL_CTX_CAP_READ_CMD | SISL_CTX_CAP_WRITE_CMD)) { + dev_err(dev, "%s: ctx may be closed val=%016llX\n", + __func__, val); + rc = -EAGAIN; + goto out; + } + + /* Set up MMIO registers pointing to the RHT */ + writeq_be((u64)ctxi->rht_start, &ctrl_map->rht_start); + val = SISL_RHT_CNT_ID((u64)MAX_RHT_PER_CONTEXT, (u64)(afu->ctx_hndl)); + writeq_be(val, &ctrl_map->rht_cnt_id); +out: + dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); + return rc; +} + +/** + * read_cap16() - issues a SCSI READ_CAP16 command + * @sdev: SCSI device associated with LUN. + * @lli: LUN destined for capacity request. + * + * Return: 0 on success, -errno on failure + */ +static int read_cap16(struct scsi_device *sdev, struct llun_info *lli) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct glun_info *gli = lli->parent; + u8 *cmd_buf = NULL; + u8 *scsi_cmd = NULL; + u8 *sense_buf = NULL; + int rc = 0; + int result = 0; + int retry_cnt = 0; + u32 tout = (MC_DISCOVERY_TIMEOUT * HZ); + +retry: + cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL); + scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL); + sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL); + if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) { + rc = -ENOMEM; + goto out; + } + + scsi_cmd[0] = SERVICE_ACTION_IN_16; /* read cap(16) */ + scsi_cmd[1] = SAI_READ_CAPACITY_16; /* service action */ + put_unaligned_be32(CMD_BUFSIZE, &scsi_cmd[10]); + + dev_dbg(dev, "%s: %ssending cmd(0x%x)\n", __func__, + retry_cnt ? "re" : "", scsi_cmd[0]); + + result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf, + CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL); + + if (driver_byte(result) == DRIVER_SENSE) { + result &= ~(0xFF<<24); /* DRIVER_SENSE is not an error */ + if (result & SAM_STAT_CHECK_CONDITION) { + struct scsi_sense_hdr sshdr; + + scsi_normalize_sense(sense_buf, SCSI_SENSE_BUFFERSIZE, + &sshdr); + switch (sshdr.sense_key) { + case NO_SENSE: + case RECOVERED_ERROR: + /* fall through */ + case NOT_READY: + result &= ~SAM_STAT_CHECK_CONDITION; + break; + case UNIT_ATTENTION: + switch (sshdr.asc) { + case 0x29: /* Power on Reset or Device Reset */ + /* fall through */ + case 0x2A: /* Device capacity changed */ + case 0x3F: /* Report LUNs changed */ + /* Retry the command once more */ + if (retry_cnt++ < 1) { + kfree(cmd_buf); + kfree(scsi_cmd); + kfree(sense_buf); + goto retry; + } + } + break; + default: + break; + } + } + } + + if (result) { + dev_err(dev, "%s: command failed, result=0x%x\n", + __func__, result); + rc = -EIO; + goto out; + } + + /* + * Read cap was successful, grab values from the buffer; + * note that we don't need to worry about unaligned access + * as the buffer is allocated on an aligned boundary. + */ + mutex_lock(&gli->mutex); + gli->max_lba = be64_to_cpu(*((u64 *)&cmd_buf[0])); + gli->blk_len = be32_to_cpu(*((u32 *)&cmd_buf[8])); + mutex_unlock(&gli->mutex); + +out: + kfree(cmd_buf); + kfree(scsi_cmd); + kfree(sense_buf); + + dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n", + __func__, gli->max_lba, gli->blk_len, rc); + return rc; +} + +/** + * get_rhte() - obtains validated resource handle table entry reference + * @ctxi: Context owning the resource handle. + * @rhndl: Resource handle associated with entry. + * @lli: LUN associated with request. + * + * Return: Validated RHTE on success, NULL on failure + */ +struct sisl_rht_entry *get_rhte(struct ctx_info *ctxi, res_hndl_t rhndl, + struct llun_info *lli) +{ + struct sisl_rht_entry *rhte = NULL; + + if (unlikely(!ctxi->rht_start)) { + pr_debug("%s: Context does not have allocated RHT!\n", + __func__); + goto out; + } + + if (unlikely(rhndl >= MAX_RHT_PER_CONTEXT)) { + pr_debug("%s: Bad resource handle! (%d)\n", __func__, rhndl); + goto out; + } + + if (unlikely(ctxi->rht_lun[rhndl] != lli)) { + pr_debug("%s: Bad resource handle LUN! (%d)\n", + __func__, rhndl); + goto out; + } + + rhte = &ctxi->rht_start[rhndl]; + if (unlikely(rhte->nmask == 0)) { + pr_debug("%s: Unopened resource handle! (%d)\n", + __func__, rhndl); + rhte = NULL; + goto out; + } + +out: + return rhte; +} + +/** + * rhte_checkout() - obtains free/empty resource handle table entry + * @ctxi: Context owning the resource handle. + * @lli: LUN associated with request. + * + * Return: Free RHTE on success, NULL on failure + */ +struct sisl_rht_entry *rhte_checkout(struct ctx_info *ctxi, + struct llun_info *lli) +{ + struct sisl_rht_entry *rhte = NULL; + int i; + + /* Find a free RHT entry */ + for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) + if (ctxi->rht_start[i].nmask == 0) { + rhte = &ctxi->rht_start[i]; + ctxi->rht_out++; + break; + } + + if (likely(rhte)) + ctxi->rht_lun[i] = lli; + + pr_debug("%s: returning rhte=%p (%d)\n", __func__, rhte, i); + return rhte; +} + +/** + * rhte_checkin() - releases a resource handle table entry + * @ctxi: Context owning the resource handle. + * @rhte: RHTE to release. + */ +void rhte_checkin(struct ctx_info *ctxi, + struct sisl_rht_entry *rhte) +{ + u32 rsrc_handle = rhte - ctxi->rht_start; + + rhte->nmask = 0; + rhte->fp = 0; + ctxi->rht_out--; + ctxi->rht_lun[rsrc_handle] = NULL; +} + +/** + * rhte_format1() - populates a RHTE for format 1 + * @rhte: RHTE to populate. + * @lun_id: LUN ID of LUN associated with RHTE. + * @perm: Desired permissions for RHTE. + * @port_sel: Port selection mask + */ +static void rht_format1(struct sisl_rht_entry *rhte, u64 lun_id, u32 perm, + u32 port_sel) +{ + /* + * Populate the Format 1 RHT entry for direct access (physical + * LUN) using the synchronization sequence defined in the + * SISLite specification. + */ + struct sisl_rht_entry_f1 dummy = { 0 }; + struct sisl_rht_entry_f1 *rhte_f1 = (struct sisl_rht_entry_f1 *)rhte; + + memset(rhte_f1, 0, sizeof(*rhte_f1)); + rhte_f1->fp = SISL_RHT_FP(1U, 0); + dma_wmb(); /* Make setting of format bit visible */ + + rhte_f1->lun_id = lun_id; + dma_wmb(); /* Make setting of LUN id visible */ + + /* + * Use a dummy RHT Format 1 entry to build the second dword + * of the entry that must be populated in a single write when + * enabled (valid bit set to TRUE). + */ + dummy.valid = 0x80; + dummy.fp = SISL_RHT_FP(1U, perm); + dummy.port_sel = port_sel; + rhte_f1->dw = dummy.dw; + + dma_wmb(); /* Make remaining RHT entry fields visible */ +} + +/** + * cxlflash_lun_attach() - attaches a user to a LUN and manages the LUN's mode + * @gli: LUN to attach. + * @mode: Desired mode of the LUN. + * @locked: Mutex status on current thread. + * + * Return: 0 on success, -errno on failure + */ +int cxlflash_lun_attach(struct glun_info *gli, enum lun_mode mode, bool locked) +{ + int rc = 0; + + if (!locked) + mutex_lock(&gli->mutex); + + if (gli->mode == MODE_NONE) + gli->mode = mode; + else if (gli->mode != mode) { + pr_debug("%s: LUN operating in mode %d, requested mode %d\n", + __func__, gli->mode, mode); + rc = -EINVAL; + goto out; + } + + gli->users++; + WARN_ON(gli->users <= 0); +out: + pr_debug("%s: Returning rc=%d gli->mode=%u gli->users=%u\n", + __func__, rc, gli->mode, gli->users); + if (!locked) + mutex_unlock(&gli->mutex); + return rc; +} + +/** + * cxlflash_lun_detach() - detaches a user from a LUN and resets the LUN's mode + * @gli: LUN to detach. + */ +void cxlflash_lun_detach(struct glun_info *gli) +{ + mutex_lock(&gli->mutex); + WARN_ON(gli->mode == MODE_NONE); + if (--gli->users == 0) + gli->mode = MODE_NONE; + pr_debug("%s: gli->users=%u\n", __func__, gli->users); + WARN_ON(gli->users < 0); + mutex_unlock(&gli->mutex); +} + +/** + * _cxlflash_disk_release() - releases the specified resource entry + * @sdev: SCSI device associated with LUN. + * @ctxi: Context owning resources. + * @release: Release ioctl data structure. + * + * Note that the AFU sync should _not_ be performed when the context is sitting + * on the error recovery list. A context on the error recovery list is not known + * to the AFU due to reset. When the context is recovered, it will be reattached + * and made known again to the AFU. + * + * Return: 0 on success, -errno on failure + */ +int _cxlflash_disk_release(struct scsi_device *sdev, + struct ctx_info *ctxi, + struct dk_cxlflash_release *release) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct afu *afu = cfg->afu; + bool put_ctx = false; + + res_hndl_t rhndl = release->rsrc_handle; + + int rc = 0; + u64 ctxid = DECODE_CTXID(release->context_id), + rctxid = release->context_id; + + struct sisl_rht_entry *rhte; + struct sisl_rht_entry_f1 *rhte_f1; + + dev_dbg(dev, "%s: ctxid=%llu rhndl=0x%llx gli->mode=%u gli->users=%u\n", + __func__, ctxid, release->rsrc_handle, gli->mode, gli->users); + + if (!ctxi) { + ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%llu)\n", + __func__, ctxid); + rc = -EINVAL; + goto out; + } + + put_ctx = true; + } + + rhte = get_rhte(ctxi, rhndl, lli); + if (unlikely(!rhte)) { + dev_dbg(dev, "%s: Bad resource handle! (%d)\n", + __func__, rhndl); + rc = -EINVAL; + goto out; + } + + switch (gli->mode) { + case MODE_PHYSICAL: + /* + * Clear the Format 1 RHT entry for direct access + * (physical LUN) using the synchronization sequence + * defined in the SISLite specification. + */ + rhte_f1 = (struct sisl_rht_entry_f1 *)rhte; + + rhte_f1->valid = 0; + dma_wmb(); /* Make revocation of RHT entry visible */ + + rhte_f1->lun_id = 0; + dma_wmb(); /* Make clearing of LUN id visible */ + + rhte_f1->dw = 0; + dma_wmb(); /* Make RHT entry bottom-half clearing visible */ + + if (!ctxi->err_recovery_active) + cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC); + break; + default: + WARN(1, "Unsupported LUN mode!"); + goto out; + } + + rhte_checkin(ctxi, rhte); + cxlflash_lun_detach(gli); + +out: + if (put_ctx) + put_context(ctxi); + dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); + return rc; +} + +int cxlflash_disk_release(struct scsi_device *sdev, + struct dk_cxlflash_release *release) +{ + return _cxlflash_disk_release(sdev, NULL, release); +} + +/** + * destroy_context() - releases a context + * @cfg: Internal structure associated with the host. + * @ctxi: Context to release. + * + * Note that the rht_lun member of the context was cut from a single + * allocation when the context was created and therefore does not need + * to be explicitly freed. Also note that we conditionally check for the + * existence of the context control map before clearing the RHT registers + * and context capabilities because it is possible to destroy a context + * while the context is in the error state (previous mapping was removed + * [so we don't have to worry about clearing] and context is waiting for + * a new mapping). + */ +static void destroy_context(struct cxlflash_cfg *cfg, + struct ctx_info *ctxi) +{ + struct afu *afu = cfg->afu; + + WARN_ON(!list_empty(&ctxi->luns)); + + /* Clear RHT registers and drop all capabilities for this context */ + if (afu->afu_map && ctxi->ctrl_map) { + writeq_be(0, &ctxi->ctrl_map->rht_start); + writeq_be(0, &ctxi->ctrl_map->rht_cnt_id); + writeq_be(0, &ctxi->ctrl_map->ctx_cap); + } + + /* Free memory associated with context */ + free_page((ulong)ctxi->rht_start); + kfree(ctxi->rht_lun); + kfree(ctxi); + atomic_dec_if_positive(&cfg->num_user_contexts); +} + +/** + * create_context() - allocates and initializes a context + * @cfg: Internal structure associated with the host. + * @ctx: Previously obtained CXL context reference. + * @ctxid: Previously obtained process element associated with CXL context. + * @adap_fd: Previously obtained adapter fd associated with CXL context. + * @file: Previously obtained file associated with CXL context. + * @perms: User-specified permissions. + * + * The context's mutex is locked when an allocated context is returned. + * + * Return: Allocated context on success, NULL on failure + */ +static struct ctx_info *create_context(struct cxlflash_cfg *cfg, + struct cxl_context *ctx, int ctxid, + int adap_fd, struct file *file, + u32 perms) +{ + struct device *dev = &cfg->dev->dev; + struct afu *afu = cfg->afu; + struct ctx_info *ctxi = NULL; + struct llun_info **lli = NULL; + struct sisl_rht_entry *rhte; + + ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL); + lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL); + if (unlikely(!ctxi || !lli)) { + dev_err(dev, "%s: Unable to allocate context!\n", __func__); + goto err; + } + + rhte = (struct sisl_rht_entry *)get_zeroed_page(GFP_KERNEL); + if (unlikely(!rhte)) { + dev_err(dev, "%s: Unable to allocate RHT!\n", __func__); + goto err; + } + + ctxi->rht_lun = lli; + ctxi->rht_start = rhte; + ctxi->rht_perms = perms; + + ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl; + ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid); + ctxi->lfd = adap_fd; + ctxi->pid = current->tgid; /* tgid = pid */ + ctxi->ctx = ctx; + ctxi->file = file; + mutex_init(&ctxi->mutex); + INIT_LIST_HEAD(&ctxi->luns); + INIT_LIST_HEAD(&ctxi->list); /* initialize for list_empty() */ + + atomic_inc(&cfg->num_user_contexts); + mutex_lock(&ctxi->mutex); +out: + return ctxi; + +err: + kfree(lli); + kfree(ctxi); + ctxi = NULL; + goto out; +} + +/** + * _cxlflash_disk_detach() - detaches a LUN from a context + * @sdev: SCSI device associated with LUN. + * @ctxi: Context owning resources. + * @detach: Detach ioctl data structure. + * + * As part of the detach, all per-context resources associated with the LUN + * are cleaned up. When detaching the last LUN for a context, the context + * itself is cleaned up and released. + * + * Return: 0 on success, -errno on failure + */ +static int _cxlflash_disk_detach(struct scsi_device *sdev, + struct ctx_info *ctxi, + struct dk_cxlflash_detach *detach) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct lun_access *lun_access, *t; + struct dk_cxlflash_release rel; + bool put_ctx = false; + + int i; + int rc = 0; + int lfd; + u64 ctxid = DECODE_CTXID(detach->context_id), + rctxid = detach->context_id; + + dev_dbg(dev, "%s: ctxid=%llu\n", __func__, ctxid); + + if (!ctxi) { + ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%llu)\n", + __func__, ctxid); + rc = -EINVAL; + goto out; + } + + put_ctx = true; + } + + /* Cleanup outstanding resources tied to this LUN */ + if (ctxi->rht_out) { + marshal_det_to_rele(detach, &rel); + for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) { + if (ctxi->rht_lun[i] == lli) { + rel.rsrc_handle = i; + _cxlflash_disk_release(sdev, ctxi, &rel); + } + + /* No need to loop further if we're done */ + if (ctxi->rht_out == 0) + break; + } + } + + /* Take our LUN out of context, free the node */ + list_for_each_entry_safe(lun_access, t, &ctxi->luns, list) + if (lun_access->lli == lli) { + list_del(&lun_access->list); + kfree(lun_access); + lun_access = NULL; + break; + } + + /* Tear down context following last LUN cleanup */ + if (list_empty(&ctxi->luns)) { + ctxi->unavail = true; + mutex_unlock(&ctxi->mutex); + mutex_lock(&cfg->ctx_tbl_list_mutex); + mutex_lock(&ctxi->mutex); + + /* Might not have been in error list so conditionally remove */ + if (!list_empty(&ctxi->list)) + list_del(&ctxi->list); + cfg->ctx_tbl[ctxid] = NULL; + mutex_unlock(&cfg->ctx_tbl_list_mutex); + mutex_unlock(&ctxi->mutex); + + lfd = ctxi->lfd; + destroy_context(cfg, ctxi); + ctxi = NULL; + put_ctx = false; + + /* + * As a last step, clean up external resources when not + * already on an external cleanup thread, i.e.: close(adap_fd). + * + * NOTE: this will free up the context from the CXL services, + * allowing it to dole out the same context_id on a future + * (or even currently in-flight) disk_attach operation. + */ + if (lfd != -1) + sys_close(lfd); + } + +out: + if (put_ctx) + put_context(ctxi); + dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); + return rc; +} + +static int cxlflash_disk_detach(struct scsi_device *sdev, + struct dk_cxlflash_detach *detach) +{ + return _cxlflash_disk_detach(sdev, NULL, detach); +} + +/** + * cxlflash_cxl_release() - release handler for adapter file descriptor + * @inode: File-system inode associated with fd. + * @file: File installed with adapter file descriptor. + * + * This routine is the release handler for the fops registered with + * the CXL services on an initial attach for a context. It is called + * when a close is performed on the adapter file descriptor returned + * to the user. Programmatically, the user is not required to perform + * the close, as it is handled internally via the detach ioctl when + * a context is being removed. Note that nothing prevents the user + * from performing a close, but the user should be aware that doing + * so is considered catastrophic and subsequent usage of the superpipe + * API with previously saved off tokens will fail. + * + * When initiated from an external close (either by the user or via + * a process tear down), the routine derives the context reference + * and calls detach for each LUN associated with the context. The + * final detach operation will cause the context itself to be freed. + * Note that the saved off lfd is reset prior to calling detach to + * signify that the final detach should not perform a close. + * + * When initiated from a detach operation as part of the tear down + * of a context, the context is first completely freed and then the + * close is performed. This routine will fail to derive the context + * reference (due to the context having already been freed) and then + * call into the CXL release entry point. + * + * Thus, with exception to when the CXL process element (context id) + * lookup fails (a case that should theoretically never occur), every + * call into this routine results in a complete freeing of a context. + * + * As part of the detach, all per-context resources associated with the LUN + * are cleaned up. When detaching the last LUN for a context, the context + * itself is cleaned up and released. + * + * Return: 0 on success + */ +static int cxlflash_cxl_release(struct inode *inode, struct file *file) +{ + struct cxl_context *ctx = cxl_fops_get_context(file); + struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg, + cxl_fops); + struct device *dev = &cfg->dev->dev; + struct ctx_info *ctxi = NULL; + struct dk_cxlflash_detach detach = { { 0 }, 0 }; + struct lun_access *lun_access, *t; + enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE; + int ctxid; + + ctxid = cxl_process_element(ctx); + if (unlikely(ctxid < 0)) { + dev_err(dev, "%s: Context %p was closed! (%d)\n", + __func__, ctx, ctxid); + goto out; + } + + ctxi = get_context(cfg, ctxid, file, ctrl); + if (unlikely(!ctxi)) { + ctxi = get_context(cfg, ctxid, file, ctrl | CTX_CTRL_CLONE); + if (!ctxi) { + dev_dbg(dev, "%s: Context %d already free!\n", + __func__, ctxid); + goto out_release; + } + + dev_dbg(dev, "%s: Another process owns context %d!\n", + __func__, ctxid); + put_context(ctxi); + goto out; + } + + dev_dbg(dev, "%s: close(%d) for context %d\n", + __func__, ctxi->lfd, ctxid); + + /* Reset the file descriptor to indicate we're on a close() thread */ + ctxi->lfd = -1; + detach.context_id = ctxi->ctxid; + list_for_each_entry_safe(lun_access, t, &ctxi->luns, list) + _cxlflash_disk_detach(lun_access->sdev, ctxi, &detach); +out_release: + cxl_fd_release(inode, file); +out: + dev_dbg(dev, "%s: returning\n", __func__); + return 0; +} + +/** + * unmap_context() - clears a previously established mapping + * @ctxi: Context owning the mapping. + * + * This routine is used to switch between the error notification page + * (dummy page of all 1's) and the real mapping (established by the CXL + * fault handler). + */ +static void unmap_context(struct ctx_info *ctxi) +{ + unmap_mapping_range(ctxi->file->f_mapping, 0, 0, 1); +} + +/** + * get_err_page() - obtains and allocates the error notification page + * + * Return: error notification page on success, NULL on failure + */ +static struct page *get_err_page(void) +{ + struct page *err_page = global.err_page; + + if (unlikely(!err_page)) { + err_page = alloc_page(GFP_KERNEL); + if (unlikely(!err_page)) { + pr_err("%s: Unable to allocate err_page!\n", __func__); + goto out; + } + + memset(page_address(err_page), -1, PAGE_SIZE); + + /* Serialize update w/ other threads to avoid a leak */ + mutex_lock(&global.mutex); + if (likely(!global.err_page)) + global.err_page = err_page; + else { + __free_page(err_page); + err_page = global.err_page; + } + mutex_unlock(&global.mutex); + } + +out: + pr_debug("%s: returning err_page=%p\n", __func__, err_page); + return err_page; +} + +/** + * cxlflash_mmap_fault() - mmap fault handler for adapter file descriptor + * @vma: VM area associated with mapping. + * @vmf: VM fault associated with current fault. + * + * To support error notification via MMIO, faults are 'caught' by this routine + * that was inserted before passing back the adapter file descriptor on attach. + * When a fault occurs, this routine evaluates if error recovery is active and + * if so, installs the error page to 'notify' the user about the error state. + * During normal operation, the fault is simply handled by the original fault + * handler that was installed by CXL services as part of initializing the + * adapter file descriptor. The VMA's page protection bits are toggled to + * indicate cached/not-cached depending on the memory backing the fault. + * + * Return: 0 on success, VM_FAULT_SIGBUS on failure + */ +static int cxlflash_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf) +{ + struct file *file = vma->vm_file; + struct cxl_context *ctx = cxl_fops_get_context(file); + struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg, + cxl_fops); + struct device *dev = &cfg->dev->dev; + struct ctx_info *ctxi = NULL; + struct page *err_page = NULL; + enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE; + int rc = 0; + int ctxid; + + ctxid = cxl_process_element(ctx); + if (unlikely(ctxid < 0)) { + dev_err(dev, "%s: Context %p was closed! (%d)\n", + __func__, ctx, ctxid); + goto err; + } + + ctxi = get_context(cfg, ctxid, file, ctrl); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid); + goto err; + } + + dev_dbg(dev, "%s: fault(%d) for context %d\n", + __func__, ctxi->lfd, ctxid); + + if (likely(!ctxi->err_recovery_active)) { + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + rc = ctxi->cxl_mmap_vmops->fault(vma, vmf); + } else { + dev_dbg(dev, "%s: err recovery active, use err_page!\n", + __func__); + + err_page = get_err_page(); + if (unlikely(!err_page)) { + dev_err(dev, "%s: Could not obtain error page!\n", + __func__); + rc = VM_FAULT_RETRY; + goto out; + } + + get_page(err_page); + vmf->page = err_page; + vma->vm_page_prot = pgprot_cached(vma->vm_page_prot); + } + +out: + if (likely(ctxi)) + put_context(ctxi); + dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc); + return rc; + +err: + rc = VM_FAULT_SIGBUS; + goto out; +} + +/* + * Local MMAP vmops to 'catch' faults + */ +static const struct vm_operations_struct cxlflash_mmap_vmops = { + .fault = cxlflash_mmap_fault, +}; + +/** + * cxlflash_cxl_mmap() - mmap handler for adapter file descriptor + * @file: File installed with adapter file descriptor. + * @vma: VM area associated with mapping. + * + * Installs local mmap vmops to 'catch' faults for error notification support. + * + * Return: 0 on success, -errno on failure + */ +static int cxlflash_cxl_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct cxl_context *ctx = cxl_fops_get_context(file); + struct cxlflash_cfg *cfg = container_of(file->f_op, struct cxlflash_cfg, + cxl_fops); + struct device *dev = &cfg->dev->dev; + struct ctx_info *ctxi = NULL; + enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE; + int ctxid; + int rc = 0; + + ctxid = cxl_process_element(ctx); + if (unlikely(ctxid < 0)) { + dev_err(dev, "%s: Context %p was closed! (%d)\n", + __func__, ctx, ctxid); + rc = -EIO; + goto out; + } + + ctxi = get_context(cfg, ctxid, file, ctrl); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%d)\n", __func__, ctxid); + rc = -EIO; + goto out; + } + + dev_dbg(dev, "%s: mmap(%d) for context %d\n", + __func__, ctxi->lfd, ctxid); + + rc = cxl_fd_mmap(file, vma); + if (likely(!rc)) { + /* Insert ourself in the mmap fault handler path */ + ctxi->cxl_mmap_vmops = vma->vm_ops; + vma->vm_ops = &cxlflash_mmap_vmops; + } + +out: + if (likely(ctxi)) + put_context(ctxi); + return rc; +} + +/* + * Local fops for adapter file descriptor + */ +static const struct file_operations cxlflash_cxl_fops = { + .owner = THIS_MODULE, + .mmap = cxlflash_cxl_mmap, + .release = cxlflash_cxl_release, +}; + +/** + * cxlflash_mark_contexts_error() - move contexts to error state and list + * @cfg: Internal structure associated with the host. + * + * A context is only moved over to the error list when there are no outstanding + * references to it. This ensures that a running operation has completed. + * + * Return: 0 on success, -errno on failure + */ +int cxlflash_mark_contexts_error(struct cxlflash_cfg *cfg) +{ + int i, rc = 0; + struct ctx_info *ctxi = NULL; + + mutex_lock(&cfg->ctx_tbl_list_mutex); + + for (i = 0; i < MAX_CONTEXT; i++) { + ctxi = cfg->ctx_tbl[i]; + if (ctxi) { + mutex_lock(&ctxi->mutex); + cfg->ctx_tbl[i] = NULL; + list_add(&ctxi->list, &cfg->ctx_err_recovery); + ctxi->err_recovery_active = true; + ctxi->ctrl_map = NULL; + unmap_context(ctxi); + mutex_unlock(&ctxi->mutex); + } + } + + mutex_unlock(&cfg->ctx_tbl_list_mutex); + return rc; +} + +/* + * Dummy NULL fops + */ +static const struct file_operations null_fops = { + .owner = THIS_MODULE, +}; + +/** + * cxlflash_disk_attach() - attach a LUN to a context + * @sdev: SCSI device associated with LUN. + * @attach: Attach ioctl data structure. + * + * Creates a context and attaches LUN to it. A LUN can only be attached + * one time to a context (subsequent attaches for the same context/LUN pair + * are not supported). Additional LUNs can be attached to a context by + * specifying the 'reuse' flag defined in the cxlflash_ioctl.h header. + * + * Return: 0 on success, -errno on failure + */ +static int cxlflash_disk_attach(struct scsi_device *sdev, + struct dk_cxlflash_attach *attach) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct afu *afu = cfg->afu; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct cxl_ioctl_start_work *work; + struct ctx_info *ctxi = NULL; + struct lun_access *lun_access = NULL; + int rc = 0; + u32 perms; + int ctxid = -1; + u64 rctxid = 0UL; + struct file *file; + + struct cxl_context *ctx; + + int fd = -1; + + /* On first attach set fileops */ + if (atomic_read(&cfg->num_user_contexts) == 0) + cfg->cxl_fops = cxlflash_cxl_fops; + + if (attach->num_interrupts > 4) { + dev_dbg(dev, "%s: Cannot support this many interrupts %llu\n", + __func__, attach->num_interrupts); + rc = -EINVAL; + goto out; + } + + if (gli->max_lba == 0) { + dev_dbg(dev, "%s: No capacity info for this LUN (%016llX)\n", + __func__, lli->lun_id[sdev->channel]); + rc = read_cap16(sdev, lli); + if (rc) { + dev_err(dev, "%s: Invalid device! (%d)\n", + __func__, rc); + rc = -ENODEV; + goto out; + } + dev_dbg(dev, "%s: LBA = %016llX\n", __func__, gli->max_lba); + dev_dbg(dev, "%s: BLK_LEN = %08X\n", __func__, gli->blk_len); + } + + if (attach->hdr.flags & DK_CXLFLASH_ATTACH_REUSE_CONTEXT) { + rctxid = attach->context_id; + ctxi = get_context(cfg, rctxid, NULL, 0); + if (!ctxi) { + dev_dbg(dev, "%s: Bad context! (%016llX)\n", + __func__, rctxid); + rc = -EINVAL; + goto out; + } + + list_for_each_entry(lun_access, &ctxi->luns, list) + if (lun_access->lli == lli) { + dev_dbg(dev, "%s: Already attached!\n", + __func__); + rc = -EINVAL; + goto out; + } + } + + lun_access = kzalloc(sizeof(*lun_access), GFP_KERNEL); + if (unlikely(!lun_access)) { + dev_err(dev, "%s: Unable to allocate lun_access!\n", __func__); + rc = -ENOMEM; + goto out; + } + + lun_access->lli = lli; + lun_access->sdev = sdev; + + /* Non-NULL context indicates reuse */ + if (ctxi) { + dev_dbg(dev, "%s: Reusing context for LUN! (%016llX)\n", + __func__, rctxid); + list_add(&lun_access->list, &ctxi->luns); + fd = ctxi->lfd; + goto out_attach; + } + + ctx = cxl_dev_context_init(cfg->dev); + if (unlikely(IS_ERR_OR_NULL(ctx))) { + dev_err(dev, "%s: Could not initialize context %p\n", + __func__, ctx); + rc = -ENODEV; + goto err0; + } + + ctxid = cxl_process_element(ctx); + if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) { + dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid); + rc = -EPERM; + goto err1; + } + + file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd); + if (unlikely(fd < 0)) { + rc = -ENODEV; + dev_err(dev, "%s: Could not get file descriptor\n", __func__); + goto err1; + } + + /* Translate read/write O_* flags from fcntl.h to AFU permission bits */ + perms = SISL_RHT_PERM(attach->hdr.flags + 1); + + ctxi = create_context(cfg, ctx, ctxid, fd, file, perms); + if (unlikely(!ctxi)) { + dev_err(dev, "%s: Failed to create context! (%d)\n", + __func__, ctxid); + goto err2; + } + + work = &ctxi->work; + work->num_interrupts = attach->num_interrupts; + work->flags = CXL_START_WORK_NUM_IRQS; + + rc = cxl_start_work(ctx, work); + if (unlikely(rc)) { + dev_dbg(dev, "%s: Could not start context rc=%d\n", + __func__, rc); + goto err3; + } + + rc = afu_attach(cfg, ctxi); + if (unlikely(rc)) { + dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc); + goto err4; + } + + /* + * No error paths after this point. Once the fd is installed it's + * visible to user space and can't be undone safely on this thread. + * There is no need to worry about a deadlock here because no one + * knows about us yet; we can be the only one holding our mutex. + */ + list_add(&lun_access->list, &ctxi->luns); + mutex_unlock(&ctxi->mutex); + mutex_lock(&cfg->ctx_tbl_list_mutex); + mutex_lock(&ctxi->mutex); + cfg->ctx_tbl[ctxid] = ctxi; + mutex_unlock(&cfg->ctx_tbl_list_mutex); + fd_install(fd, file); + +out_attach: + attach->hdr.return_flags = 0; + attach->context_id = ctxi->ctxid; + attach->block_size = gli->blk_len; + attach->mmio_size = sizeof(afu->afu_map->hosts[0].harea); + attach->last_lba = gli->max_lba; + attach->max_xfer = (sdev->host->max_sectors * 512) / gli->blk_len; + +out: + attach->adap_fd = fd; + + if (ctxi) + put_context(ctxi); + + dev_dbg(dev, "%s: returning ctxid=%d fd=%d bs=%lld rc=%d llba=%lld\n", + __func__, ctxid, fd, attach->block_size, rc, attach->last_lba); + return rc; + +err4: + cxl_stop_context(ctx); +err3: + put_context(ctxi); + destroy_context(cfg, ctxi); + ctxi = NULL; +err2: + /* + * Here, we're overriding the fops with a dummy all-NULL fops because + * fput() calls the release fop, which will cause us to mistakenly + * call into the CXL code. Rather than try to add yet more complexity + * to that routine (cxlflash_cxl_release) we should try to fix the + * issue here. + */ + file->f_op = &null_fops; + fput(file); + put_unused_fd(fd); + fd = -1; +err1: + cxl_release_context(ctx); +err0: + kfree(lun_access); + goto out; +} + +/** + * recover_context() - recovers a context in error + * @cfg: Internal structure associated with the host. + * @ctxi: Context to release. + * + * Restablishes the state for a context-in-error. + * + * Return: 0 on success, -errno on failure + */ +static int recover_context(struct cxlflash_cfg *cfg, struct ctx_info *ctxi) +{ + struct device *dev = &cfg->dev->dev; + int rc = 0; + int old_fd, fd = -1; + int ctxid = -1; + struct file *file; + struct cxl_context *ctx; + struct afu *afu = cfg->afu; + + ctx = cxl_dev_context_init(cfg->dev); + if (unlikely(IS_ERR_OR_NULL(ctx))) { + dev_err(dev, "%s: Could not initialize context %p\n", + __func__, ctx); + rc = -ENODEV; + goto out; + } + + ctxid = cxl_process_element(ctx); + if (unlikely((ctxid > MAX_CONTEXT) || (ctxid < 0))) { + dev_err(dev, "%s: ctxid (%d) invalid!\n", __func__, ctxid); + rc = -EPERM; + goto err1; + } + + file = cxl_get_fd(ctx, &cfg->cxl_fops, &fd); + if (unlikely(fd < 0)) { + rc = -ENODEV; + dev_err(dev, "%s: Could not get file descriptor\n", __func__); + goto err1; + } + + rc = cxl_start_work(ctx, &ctxi->work); + if (unlikely(rc)) { + dev_dbg(dev, "%s: Could not start context rc=%d\n", + __func__, rc); + goto err2; + } + + /* Update with new MMIO area based on updated context id */ + ctxi->ctrl_map = &afu->afu_map->ctrls[ctxid].ctrl; + + rc = afu_attach(cfg, ctxi); + if (rc) { + dev_err(dev, "%s: Could not attach AFU rc %d\n", __func__, rc); + goto err3; + } + + /* + * No error paths after this point. Once the fd is installed it's + * visible to user space and can't be undone safely on this thread. + */ + old_fd = ctxi->lfd; + ctxi->ctxid = ENCODE_CTXID(ctxi, ctxid); + ctxi->lfd = fd; + ctxi->ctx = ctx; + ctxi->file = file; + + /* + * Put context back in table (note the reinit of the context list); + * we must first drop the context's mutex and then acquire it in + * order with the table/list mutex to avoid a deadlock - safe to do + * here because no one can find us at this moment in time. + */ + mutex_unlock(&ctxi->mutex); + mutex_lock(&cfg->ctx_tbl_list_mutex); + mutex_lock(&ctxi->mutex); + list_del_init(&ctxi->list); + cfg->ctx_tbl[ctxid] = ctxi; + mutex_unlock(&cfg->ctx_tbl_list_mutex); + fd_install(fd, file); + + /* Release the original adapter fd and associated CXL resources */ + sys_close(old_fd); +out: + dev_dbg(dev, "%s: returning ctxid=%d fd=%d rc=%d\n", + __func__, ctxid, fd, rc); + return rc; + +err3: + cxl_stop_context(ctx); +err2: + fput(file); + put_unused_fd(fd); +err1: + cxl_release_context(ctx); + goto out; +} + +/** + * check_state() - checks and responds to the current adapter state + * @cfg: Internal structure associated with the host. + * + * This routine can block and should only be used on process context. + * Note that when waking up from waiting in limbo, the state is unknown + * and must be checked again before proceeding. + * + * Return: 0 on success, -errno on failure + */ +static int check_state(struct cxlflash_cfg *cfg) +{ + struct device *dev = &cfg->dev->dev; + int rc = 0; + +retry: + switch (cfg->state) { + case STATE_LIMBO: + dev_dbg(dev, "%s: Limbo, going to wait...\n", __func__); + rc = wait_event_interruptible(cfg->limbo_waitq, + cfg->state != STATE_LIMBO); + if (unlikely(rc)) + break; + goto retry; + case STATE_FAILTERM: + dev_dbg(dev, "%s: Failed/Terminating!\n", __func__); + rc = -ENODEV; + break; + default: + break; + } + + return rc; +} + +/** + * cxlflash_afu_recover() - initiates AFU recovery + * @sdev: SCSI device associated with LUN. + * @recover: Recover ioctl data structure. + * + * Only a single recovery is allowed at a time to avoid exhausting CXL + * resources (leading to recovery failure) in the event that we're up + * against the maximum number of contexts limit. For similar reasons, + * a context recovery is retried if there are multiple recoveries taking + * place at the same time and the failure was due to CXL services being + * unable to keep up. + * + * Because a user can detect an error condition before the kernel, it is + * quite possible for this routine to act as the kernel's EEH detection + * source (MMIO read of mbox_r). Because of this, there is a window of + * time where an EEH might have been detected but not yet 'serviced' + * (callback invoked, causing the device to enter limbo state). To avoid + * looping in this routine during that window, a 1 second sleep is in place + * between the time the MMIO failure is detected and the time a wait on the + * limbo wait queue is attempted via check_state(). + * + * Return: 0 on success, -errno on failure + */ +static int cxlflash_afu_recover(struct scsi_device *sdev, + struct dk_cxlflash_recover_afu *recover) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct afu *afu = cfg->afu; + struct ctx_info *ctxi = NULL; + struct mutex *mutex = &cfg->ctx_recovery_mutex; + u64 ctxid = DECODE_CTXID(recover->context_id), + rctxid = recover->context_id; + long reg; + int lretry = 20; /* up to 2 seconds */ + int rc = 0; + + atomic_inc(&cfg->recovery_threads); + rc = mutex_lock_interruptible(mutex); + if (rc) + goto out; + + dev_dbg(dev, "%s: reason 0x%016llX rctxid=%016llX\n", + __func__, recover->reason, rctxid); + +retry: + /* Ensure that this process is attached to the context */ + ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid); + rc = -EINVAL; + goto out; + } + + if (ctxi->err_recovery_active) { +retry_recover: + rc = recover_context(cfg, ctxi); + if (unlikely(rc)) { + dev_err(dev, "%s: Recovery failed for context %llu (rc=%d)\n", + __func__, ctxid, rc); + if ((rc == -ENODEV) && + ((atomic_read(&cfg->recovery_threads) > 1) || + (lretry--))) { + dev_dbg(dev, "%s: Going to try again!\n", + __func__); + mutex_unlock(mutex); + msleep(100); + rc = mutex_lock_interruptible(mutex); + if (rc) + goto out; + goto retry_recover; + } + + goto out; + } + + ctxi->err_recovery_active = false; + recover->context_id = ctxi->ctxid; + recover->adap_fd = ctxi->lfd; + recover->mmio_size = sizeof(afu->afu_map->hosts[0].harea); + recover->hdr.return_flags |= + DK_CXLFLASH_RECOVER_AFU_CONTEXT_RESET; + goto out; + } + + /* Test if in error state */ + reg = readq_be(&afu->ctrl_map->mbox_r); + if (reg == -1) { + dev_dbg(dev, "%s: MMIO read fail! Wait for recovery...\n", + __func__); + mutex_unlock(&ctxi->mutex); + ctxi = NULL; + ssleep(1); + rc = check_state(cfg); + if (unlikely(rc)) + goto out; + goto retry; + } + + dev_dbg(dev, "%s: MMIO working, no recovery required!\n", __func__); +out: + if (likely(ctxi)) + put_context(ctxi); + mutex_unlock(mutex); + atomic_dec_if_positive(&cfg->recovery_threads); + return rc; +} + +/** + * process_sense() - evaluates and processes sense data + * @sdev: SCSI device associated with LUN. + * @verify: Verify ioctl data structure. + * + * Return: 0 on success, -errno on failure + */ +static int process_sense(struct scsi_device *sdev, + struct dk_cxlflash_verify *verify) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + u64 prev_lba = gli->max_lba; + struct scsi_sense_hdr sshdr = { 0 }; + int rc = 0; + + rc = scsi_normalize_sense((const u8 *)&verify->sense_data, + DK_CXLFLASH_VERIFY_SENSE_LEN, &sshdr); + if (!rc) { + dev_err(dev, "%s: Failed to normalize sense data!\n", __func__); + rc = -EINVAL; + goto out; + } + + switch (sshdr.sense_key) { + case NO_SENSE: + case RECOVERED_ERROR: + /* fall through */ + case NOT_READY: + break; + case UNIT_ATTENTION: + switch (sshdr.asc) { + case 0x29: /* Power on Reset or Device Reset */ + /* fall through */ + case 0x2A: /* Device settings/capacity changed */ + rc = read_cap16(sdev, lli); + if (rc) { + rc = -ENODEV; + break; + } + if (prev_lba != gli->max_lba) + dev_dbg(dev, "%s: Capacity changed old=%lld " + "new=%lld\n", __func__, prev_lba, + gli->max_lba); + break; + case 0x3F: /* Report LUNs changed, Rescan. */ + scsi_scan_host(cfg->host); + break; + default: + rc = -EIO; + break; + } + break; + default: + rc = -EIO; + break; + } +out: + dev_dbg(dev, "%s: sense_key %x asc %x ascq %x rc %d\n", __func__, + sshdr.sense_key, sshdr.asc, sshdr.ascq, rc); + return rc; +} + +/** + * cxlflash_disk_verify() - verifies a LUN is the same and handle size changes + * @sdev: SCSI device associated with LUN. + * @verify: Verify ioctl data structure. + * + * Return: 0 on success, -errno on failure + */ +static int cxlflash_disk_verify(struct scsi_device *sdev, + struct dk_cxlflash_verify *verify) +{ + int rc = 0; + struct ctx_info *ctxi = NULL; + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct sisl_rht_entry *rhte = NULL; + res_hndl_t rhndl = verify->rsrc_handle; + u64 ctxid = DECODE_CTXID(verify->context_id), + rctxid = verify->context_id; + u64 last_lba = 0; + + dev_dbg(dev, "%s: ctxid=%llu rhndl=%016llX, hint=%016llX, " + "flags=%016llX\n", __func__, ctxid, verify->rsrc_handle, + verify->hint, verify->hdr.flags); + + ctxi = get_context(cfg, rctxid, lli, 0); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid); + rc = -EINVAL; + goto out; + } + + rhte = get_rhte(ctxi, rhndl, lli); + if (unlikely(!rhte)) { + dev_dbg(dev, "%s: Bad resource handle! (%d)\n", + __func__, rhndl); + rc = -EINVAL; + goto out; + } + + /* + * Look at the hint/sense to see if it requires us to redrive + * inquiry (i.e. the Unit attention is due to the WWN changing). + */ + if (verify->hint & DK_CXLFLASH_VERIFY_HINT_SENSE) { + rc = process_sense(sdev, verify); + if (unlikely(rc)) { + dev_err(dev, "%s: Failed to validate sense data (%d)\n", + __func__, rc); + goto out; + } + } + + switch (gli->mode) { + case MODE_PHYSICAL: + last_lba = gli->max_lba; + break; + default: + WARN(1, "Unsupported LUN mode!"); + } + + verify->last_lba = last_lba; + +out: + if (likely(ctxi)) + put_context(ctxi); + dev_dbg(dev, "%s: returning rc=%d llba=%llX\n", + __func__, rc, verify->last_lba); + return rc; +} + +/** + * decode_ioctl() - translates an encoded ioctl to an easily identifiable string + * @cmd: The ioctl command to decode. + * + * Return: A string identifying the decoded ioctl. + */ +static char *decode_ioctl(int cmd) +{ + switch (cmd) { + case DK_CXLFLASH_ATTACH: + return __stringify_1(DK_CXLFLASH_ATTACH); + case DK_CXLFLASH_USER_DIRECT: + return __stringify_1(DK_CXLFLASH_USER_DIRECT); + case DK_CXLFLASH_RELEASE: + return __stringify_1(DK_CXLFLASH_RELEASE); + case DK_CXLFLASH_DETACH: + return __stringify_1(DK_CXLFLASH_DETACH); + case DK_CXLFLASH_VERIFY: + return __stringify_1(DK_CXLFLASH_VERIFY); + case DK_CXLFLASH_RECOVER_AFU: + return __stringify_1(DK_CXLFLASH_RECOVER_AFU); + case DK_CXLFLASH_MANAGE_LUN: + return __stringify_1(DK_CXLFLASH_MANAGE_LUN); + } + + return "UNKNOWN"; +} + +/** + * cxlflash_disk_direct_open() - opens a direct (physical) disk + * @sdev: SCSI device associated with LUN. + * @arg: UDirect ioctl data structure. + * + * On successful return, the user is informed of the resource handle + * to be used to identify the direct lun and the size (in blocks) of + * the direct lun in last LBA format. + * + * Return: 0 on success, -errno on failure + */ +static int cxlflash_disk_direct_open(struct scsi_device *sdev, void *arg) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct afu *afu = cfg->afu; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + + struct dk_cxlflash_udirect *pphys = (struct dk_cxlflash_udirect *)arg; + + u64 ctxid = DECODE_CTXID(pphys->context_id), + rctxid = pphys->context_id; + u64 lun_size = 0; + u64 last_lba = 0; + u64 rsrc_handle = -1; + u32 port = CHAN2PORT(sdev->channel); + + int rc = 0; + + struct ctx_info *ctxi = NULL; + struct sisl_rht_entry *rhte = NULL; + + pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size); + + rc = cxlflash_lun_attach(gli, MODE_PHYSICAL, false); + if (unlikely(rc)) { + dev_dbg(dev, "%s: Failed to attach to LUN! (PHYSICAL)\n", + __func__); + goto out; + } + + ctxi = get_context(cfg, rctxid, lli, 0); + if (unlikely(!ctxi)) { + dev_dbg(dev, "%s: Bad context! (%llu)\n", __func__, ctxid); + rc = -EINVAL; + goto err1; + } + + rhte = rhte_checkout(ctxi, lli); + if (unlikely(!rhte)) { + dev_dbg(dev, "%s: too many opens for this context\n", __func__); + rc = -EMFILE; /* too many opens */ + goto err1; + } + + rsrc_handle = (rhte - ctxi->rht_start); + + rht_format1(rhte, lli->lun_id[sdev->channel], ctxi->rht_perms, port); + cxlflash_afu_sync(afu, ctxid, rsrc_handle, AFU_LW_SYNC); + + last_lba = gli->max_lba; + pphys->hdr.return_flags = 0; + pphys->last_lba = last_lba; + pphys->rsrc_handle = rsrc_handle; + +out: + if (likely(ctxi)) + put_context(ctxi); + dev_dbg(dev, "%s: returning handle 0x%llx rc=%d llba %lld\n", + __func__, rsrc_handle, rc, last_lba); + return rc; + +err1: + cxlflash_lun_detach(gli); + goto out; +} + +/** + * ioctl_common() - common IOCTL handler for driver + * @sdev: SCSI device associated with LUN. + * @cmd: IOCTL command. + * + * Handles common fencing operations that are valid for multiple ioctls. Always + * allow through ioctls that are cleanup oriented in nature, even when operating + * in a failed/terminating state. + * + * Return: 0 on success, -errno on failure + */ +static int ioctl_common(struct scsi_device *sdev, int cmd) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + int rc = 0; + + if (unlikely(!lli)) { + dev_dbg(dev, "%s: Unknown LUN\n", __func__); + rc = -EINVAL; + goto out; + } + + rc = check_state(cfg); + if (unlikely(rc) && (cfg->state == STATE_FAILTERM)) { + switch (cmd) { + case DK_CXLFLASH_RELEASE: + case DK_CXLFLASH_DETACH: + dev_dbg(dev, "%s: Command override! (%d)\n", + __func__, rc); + rc = 0; + break; + } + } +out: + return rc; +} + +/** + * cxlflash_ioctl() - IOCTL handler for driver + * @sdev: SCSI device associated with LUN. + * @cmd: IOCTL command. + * @arg: Userspace ioctl data structure. + * + * Return: 0 on success, -errno on failure + */ +int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg) +{ + typedef int (*sioctl) (struct scsi_device *, void *); + + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct afu *afu = cfg->afu; + struct dk_cxlflash_hdr *hdr; + char buf[sizeof(union cxlflash_ioctls)]; + size_t size = 0; + bool known_ioctl = false; + int idx; + int rc = 0; + struct Scsi_Host *shost = sdev->host; + sioctl do_ioctl = NULL; + + static const struct { + size_t size; + sioctl ioctl; + } ioctl_tbl[] = { /* NOTE: order matters here */ + {sizeof(struct dk_cxlflash_attach), (sioctl)cxlflash_disk_attach}, + {sizeof(struct dk_cxlflash_udirect), cxlflash_disk_direct_open}, + {sizeof(struct dk_cxlflash_release), (sioctl)cxlflash_disk_release}, + {sizeof(struct dk_cxlflash_detach), (sioctl)cxlflash_disk_detach}, + {sizeof(struct dk_cxlflash_verify), (sioctl)cxlflash_disk_verify}, + {sizeof(struct dk_cxlflash_recover_afu), (sioctl)cxlflash_afu_recover}, + {sizeof(struct dk_cxlflash_manage_lun), (sioctl)cxlflash_manage_lun}, + }; + + /* Restrict command set to physical support only for internal LUN */ + if (afu->internal_lun) + switch (cmd) { + case DK_CXLFLASH_RELEASE: + dev_dbg(dev, "%s: %s not supported for lun_mode=%d\n", + __func__, decode_ioctl(cmd), afu->internal_lun); + rc = -EINVAL; + goto cxlflash_ioctl_exit; + } + + switch (cmd) { + case DK_CXLFLASH_ATTACH: + case DK_CXLFLASH_USER_DIRECT: + case DK_CXLFLASH_RELEASE: + case DK_CXLFLASH_DETACH: + case DK_CXLFLASH_VERIFY: + case DK_CXLFLASH_RECOVER_AFU: + dev_dbg(dev, "%s: %s (%08X) on dev(%d/%d/%d/%llu)\n", + __func__, decode_ioctl(cmd), cmd, shost->host_no, + sdev->channel, sdev->id, sdev->lun); + rc = ioctl_common(sdev, cmd); + if (unlikely(rc)) + goto cxlflash_ioctl_exit; + + /* fall through */ + + case DK_CXLFLASH_MANAGE_LUN: + known_ioctl = true; + idx = _IOC_NR(cmd) - _IOC_NR(DK_CXLFLASH_ATTACH); + size = ioctl_tbl[idx].size; + do_ioctl = ioctl_tbl[idx].ioctl; + + if (likely(do_ioctl)) + break; + + /* fall through */ + default: + rc = -EINVAL; + goto cxlflash_ioctl_exit; + } + + if (unlikely(copy_from_user(&buf, arg, size))) { + dev_err(dev, "%s: copy_from_user() fail! " + "size=%lu cmd=%d (%s) arg=%p\n", + __func__, size, cmd, decode_ioctl(cmd), arg); + rc = -EFAULT; + goto cxlflash_ioctl_exit; + } + + hdr = (struct dk_cxlflash_hdr *)&buf; + if (hdr->version != DK_CXLFLASH_VERSION_0) { + dev_dbg(dev, "%s: Version %u not supported for %s\n", + __func__, hdr->version, decode_ioctl(cmd)); + rc = -EINVAL; + goto cxlflash_ioctl_exit; + } + + if (hdr->rsvd[0] || hdr->rsvd[1] || hdr->rsvd[2] || hdr->return_flags) { + dev_dbg(dev, "%s: Reserved/rflags populated!\n", __func__); + rc = -EINVAL; + goto cxlflash_ioctl_exit; + } + + rc = do_ioctl(sdev, (void *)&buf); + if (likely(!rc)) + if (unlikely(copy_to_user(arg, &buf, size))) { + dev_err(dev, "%s: copy_to_user() fail! " + "size=%lu cmd=%d (%s) arg=%p\n", + __func__, size, cmd, decode_ioctl(cmd), arg); + rc = -EFAULT; + } + + /* fall through to exit */ + +cxlflash_ioctl_exit: + if (unlikely(rc && known_ioctl)) + dev_err(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) " + "returned rc %d\n", __func__, + decode_ioctl(cmd), cmd, shost->host_no, + sdev->channel, sdev->id, sdev->lun, rc); + else + dev_dbg(dev, "%s: ioctl %s (%08X) on dev(%d/%d/%d/%llu) " + "returned rc %d\n", __func__, decode_ioctl(cmd), + cmd, shost->host_no, sdev->channel, sdev->id, + sdev->lun, rc); + return rc; +} -- cgit v1.2.3 From 2cb79266d6b229dbebd31fe114af1bdab25c8076 Mon Sep 17 00:00:00 2001 From: "Matthew R. Ochs" Date: Thu, 13 Aug 2015 21:47:53 -0500 Subject: cxlflash: Virtual LUN support Add support for physical LUN segmentation (virtual LUNs) to device driver supporting the IBM CXL Flash adapter. This patch allows user space applications to virtually segment a physical LUN into N virtual LUNs, taking advantage of the translation features provided by this adapter. Signed-off-by: Matthew R. Ochs Signed-off-by: Manoj N. Kumar Reviewed-by: Michael Neuling Reviewed-by: Wen Xiong Signed-off-by: James Bottomley --- Documentation/powerpc/cxlflash.txt | 63 +- drivers/scsi/cxlflash/Makefile | 2 +- drivers/scsi/cxlflash/common.h | 4 + drivers/scsi/cxlflash/lunmgt.c | 3 + drivers/scsi/cxlflash/main.c | 13 + drivers/scsi/cxlflash/sislite.h | 20 +- drivers/scsi/cxlflash/superpipe.c | 82 ++- drivers/scsi/cxlflash/superpipe.h | 17 +- drivers/scsi/cxlflash/vlun.c | 1243 ++++++++++++++++++++++++++++++++++++ drivers/scsi/cxlflash/vlun.h | 86 +++ include/uapi/scsi/cxlflash_ioctl.h | 34 + 11 files changed, 1550 insertions(+), 17 deletions(-) create mode 100644 drivers/scsi/cxlflash/vlun.c create mode 100644 drivers/scsi/cxlflash/vlun.h (limited to 'drivers/scsi/cxlflash/superpipe.c') diff --git a/Documentation/powerpc/cxlflash.txt b/Documentation/powerpc/cxlflash.txt index f943967f90ce..4202d1bc583c 100644 --- a/Documentation/powerpc/cxlflash.txt +++ b/Documentation/powerpc/cxlflash.txt @@ -163,7 +163,8 @@ DK_CXLFLASH_ATTACH - These tokens are only valid for the process under which they were created. The child of a forked process cannot continue - to use the context id or file descriptor created by its parent. + to use the context id or file descriptor created by its parent + (see DK_CXLFLASH_VLUN_CLONE for further details). - These tokens are only valid for the lifetime of the context and the process under which they were created. Once either is @@ -193,6 +194,45 @@ DK_CXLFLASH_USER_DIRECT treated as a resource handle that is returned to the user. The user is then able to use the handle to reference the LUN during I/O. +DK_CXLFLASH_USER_VIRTUAL +------------------------ + This ioctl is responsible for transitioning the LUN to virtual mode + of access and configuring the AFU for virtual access from user space + on a per-context basis. Additionally, the block size and last logical + block address (LBA) are returned to the user. + + As mentioned previously, when operating in user space access mode, + LUNs may be accessed in whole or in part. Only one mode is allowed + at a time and if one mode is active (outstanding references exist), + requests to use the LUN in a different mode are denied. + + The AFU is configured for virtual access from user space by adding + an entry to the AFU's resource handle table. The index of the entry + is treated as a resource handle that is returned to the user. The + user is then able to use the handle to reference the LUN during I/O. + + By default, the virtual LUN is created with a size of 0. The user + would need to use the DK_CXLFLASH_VLUN_RESIZE ioctl to adjust the grow + the virtual LUN to a desired size. To avoid having to perform this + resize for the initial creation of the virtual LUN, the user has the + option of specifying a size as part of the DK_CXLFLASH_USER_VIRTUAL + ioctl, such that when success is returned to the user, the + resource handle that is provided is already referencing provisioned + storage. This is reflected by the last LBA being a non-zero value. + +DK_CXLFLASH_VLUN_RESIZE +----------------------- + This ioctl is responsible for resizing a previously created virtual + LUN and will fail if invoked upon a LUN that is not in virtual + mode. Upon success, an updated last LBA is returned to the user + indicating the new size of the virtual LUN associated with the + resource handle. + + The partitioning of virtual LUNs is jointly mediated by the cxlflash + driver and the AFU. An allocation table is kept for each LUN that is + operating in the virtual mode and used to program a LUN translation + table that the AFU references when provided with a resource handle. + DK_CXLFLASH_RELEASE ------------------- This ioctl is responsible for releasing a previously obtained @@ -214,6 +254,27 @@ DK_CXLFLASH_DETACH success, all "tokens" which had been provided to the user from the DK_CXLFLASH_ATTACH onward are no longer valid. +DK_CXLFLASH_VLUN_CLONE +---------------------- + This ioctl is responsible for cloning a previously created + context to a more recently created context. It exists solely to + support maintaining user space access to storage after a process + forks. Upon success, the child process (which invoked the ioctl) + will have access to the same LUNs via the same resource handle(s) + and fd2 as the parent, but under a different context. + + Context sharing across processes is not supported with CXL and + therefore each fork must be met with establishing a new context + for the child process. This ioctl simplifies the state management + and playback required by a user in such a scenario. When a process + forks, child process can clone the parents context by first creating + a context (via DK_CXLFLASH_ATTACH) and then using this ioctl to + perform the clone from the parent to the child. + + The clone itself is fairly simple. The resource handle and lun + translation tables are copied from the parent context to the child's + and then synced with the AFU. + DK_CXLFLASH_VERIFY ------------------ This ioctl is used to detect various changes such as the capacity of diff --git a/drivers/scsi/cxlflash/Makefile b/drivers/scsi/cxlflash/Makefile index c14d24c720d6..9e39866d473b 100644 --- a/drivers/scsi/cxlflash/Makefile +++ b/drivers/scsi/cxlflash/Makefile @@ -1,2 +1,2 @@ obj-$(CONFIG_CXLFLASH) += cxlflash.o -cxlflash-y += main.o superpipe.o lunmgt.o +cxlflash-y += main.o superpipe.o lunmgt.o vlun.o diff --git a/drivers/scsi/cxlflash/common.h b/drivers/scsi/cxlflash/common.h index d3e54e61c7a5..1c56037146e1 100644 --- a/drivers/scsi/cxlflash/common.h +++ b/drivers/scsi/cxlflash/common.h @@ -116,6 +116,9 @@ struct cxlflash_cfg { atomic_t num_user_contexts; + /* Parameters that are LUN table related */ + int last_lun_index[CXLFLASH_NUM_FC_PORTS]; + int promote_lun_index; struct list_head lluns; /* list of llun_info structs */ wait_queue_head_t tmf_waitq; @@ -200,5 +203,6 @@ int cxlflash_ioctl(struct scsi_device *, int, void __user *); void cxlflash_stop_term_user_contexts(struct cxlflash_cfg *); int cxlflash_mark_contexts_error(struct cxlflash_cfg *); void cxlflash_term_local_luns(struct cxlflash_cfg *); +void cxlflash_restore_luntable(struct cxlflash_cfg *); #endif /* ifndef _CXLFLASH_COMMON_H */ diff --git a/drivers/scsi/cxlflash/lunmgt.c b/drivers/scsi/cxlflash/lunmgt.c index 66d5bef11ee6..d98ad0ff64c1 100644 --- a/drivers/scsi/cxlflash/lunmgt.c +++ b/drivers/scsi/cxlflash/lunmgt.c @@ -20,6 +20,7 @@ #include "sislite.h" #include "common.h" +#include "vlun.h" #include "superpipe.h" /** @@ -42,6 +43,7 @@ static struct llun_info *create_local(struct scsi_device *sdev, u8 *wwid) lli->sdev = sdev; lli->newly_created = true; lli->host_no = sdev->host->host_no; + lli->in_table = false; memcpy(lli->wwid, wwid, DK_CXLFLASH_MANAGE_LUN_WWID_LEN); out: @@ -208,6 +210,7 @@ void cxlflash_term_global_luns(void) 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); diff --git a/drivers/scsi/cxlflash/main.c b/drivers/scsi/cxlflash/main.c index 02d464f41b7f..458ed838f83a 100644 --- a/drivers/scsi/cxlflash/main.c +++ b/drivers/scsi/cxlflash/main.c @@ -1989,6 +1989,8 @@ static int init_afu(struct cxlflash_cfg *cfg) afu_err_intr_init(cfg->afu); atomic64_set(&afu->room, readq_be(&afu->host_map->cmd_room)); + /* Restore the LUN mappings */ + cxlflash_restore_luntable(cfg); err1: pr_debug("%s: returning rc=%d\n", __func__, rc); return rc; @@ -2286,6 +2288,17 @@ static int cxlflash_probe(struct pci_dev *pdev, cfg->init_state = INIT_STATE_NONE; cfg->dev = pdev; + + /* + * The promoted LUNs move to the top of the LUN table. The rest stay + * on the bottom half. The bottom half grows from the end + * (index = 255), whereas the top half grows from the beginning + * (index = 0). + */ + cfg->promote_lun_index = 0; + cfg->last_lun_index[0] = CXLFLASH_NUM_VLUNS/2 - 1; + cfg->last_lun_index[1] = CXLFLASH_NUM_VLUNS/2 - 1; + cfg->dev_id = (struct pci_device_id *)dev_id; cfg->mcctx = NULL; diff --git a/drivers/scsi/cxlflash/sislite.h b/drivers/scsi/cxlflash/sislite.h index 66b889151a4c..63bf394fe78c 100644 --- a/drivers/scsi/cxlflash/sislite.h +++ b/drivers/scsi/cxlflash/sislite.h @@ -397,16 +397,17 @@ struct cxlflash_afu_map { }; }; -/* LBA translation control blocks */ - +/* + * LXT - LBA Translation Table + * LXT control blocks + */ struct sisl_lxt_entry { u64 rlba_base; /* bits 0:47 is base - * b48:55 is lun index - * b58:59 is write & read perms - * (if no perm, afu_rc=0x15) - * b60:63 is port_sel mask - */ - + * b48:55 is lun index + * b58:59 is write & read perms + * (if no perm, afu_rc=0x15) + * b60:63 is port_sel mask + */ }; /* @@ -465,4 +466,7 @@ struct sisl_rht_entry_f1 { #define TMF_LUN_RESET 0x1U #define TMF_CLEAR_ACA 0x2U + +#define SISLITE_MAX_WS_BLOCKS 512 + #endif /* _SISLITE_H */ diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c index 3c8bce8bbb0b..f1b62cea75b1 100644 --- a/drivers/scsi/cxlflash/superpipe.c +++ b/drivers/scsi/cxlflash/superpipe.c @@ -26,10 +26,24 @@ #include "sislite.h" #include "common.h" +#include "vlun.h" #include "superpipe.h" struct cxlflash_global global; +/** + * marshal_rele_to_resize() - translate release to resize structure + * @rele: Source structure from which to translate/copy. + * @resize: Destination structure for the translate/copy. + */ +static void marshal_rele_to_resize(struct dk_cxlflash_release *release, + struct dk_cxlflash_resize *resize) +{ + resize->hdr = release->hdr; + resize->context_id = release->context_id; + resize->rsrc_handle = release->rsrc_handle; +} + /** * marshal_det_to_rele() - translate detach to release structure * @detach: Destination structure for the translate/copy. @@ -449,6 +463,7 @@ void rhte_checkin(struct ctx_info *ctxi, rhte->fp = 0; ctxi->rht_out--; ctxi->rht_lun[rsrc_handle] = NULL; + ctxi->rht_needs_ws[rsrc_handle] = false; } /** @@ -526,13 +541,21 @@ out: /** * cxlflash_lun_detach() - detaches a user from a LUN and resets the LUN's mode * @gli: LUN to detach. + * + * When resetting the mode, terminate block allocation resources as they + * are no longer required (service is safe to call even when block allocation + * resources were not present - such as when transitioning from physical mode). + * These resources will be reallocated when needed (subsequent transition to + * virtual mode). */ void cxlflash_lun_detach(struct glun_info *gli) { mutex_lock(&gli->mutex); WARN_ON(gli->mode == MODE_NONE); - if (--gli->users == 0) + if (--gli->users == 0) { gli->mode = MODE_NONE; + cxlflash_ba_terminate(&gli->blka.ba_lun); + } pr_debug("%s: gli->users=%u\n", __func__, gli->users); WARN_ON(gli->users < 0); mutex_unlock(&gli->mutex); @@ -544,10 +567,12 @@ void cxlflash_lun_detach(struct glun_info *gli) * @ctxi: Context owning resources. * @release: Release ioctl data structure. * - * Note that the AFU sync should _not_ be performed when the context is sitting - * on the error recovery list. A context on the error recovery list is not known - * to the AFU due to reset. When the context is recovered, it will be reattached - * and made known again to the AFU. + * For LUNs in virtual mode, the virtual LUN associated with the specified + * resource handle is resized to 0 prior to releasing the RHTE. Note that the + * AFU sync should _not_ be performed when the context is sitting on the error + * recovery list. A context on the error recovery list is not known to the AFU + * due to reset. When the context is recovered, it will be reattached and made + * known again to the AFU. * * Return: 0 on success, -errno on failure */ @@ -562,6 +587,7 @@ int _cxlflash_disk_release(struct scsi_device *sdev, struct afu *afu = cfg->afu; bool put_ctx = false; + struct dk_cxlflash_resize size; res_hndl_t rhndl = release->rsrc_handle; int rc = 0; @@ -594,7 +620,24 @@ int _cxlflash_disk_release(struct scsi_device *sdev, goto out; } + /* + * Resize to 0 for virtual LUNS by setting the size + * to 0. This will clear LXT_START and LXT_CNT fields + * in the RHT entry and properly sync with the AFU. + * + * Afterwards we clear the remaining fields. + */ switch (gli->mode) { + case MODE_VIRTUAL: + marshal_rele_to_resize(release, &size); + size.req_size = 0; + rc = _cxlflash_vlun_resize(sdev, ctxi, &size); + if (rc) { + dev_dbg(dev, "%s: resize failed rc %d\n", __func__, rc); + goto out; + } + + break; case MODE_PHYSICAL: /* * Clear the Format 1 RHT entry for direct access @@ -666,6 +709,7 @@ static void destroy_context(struct cxlflash_cfg *cfg, /* Free memory associated with context */ free_page((ulong)ctxi->rht_start); + kfree(ctxi->rht_needs_ws); kfree(ctxi->rht_lun); kfree(ctxi); atomic_dec_if_positive(&cfg->num_user_contexts); @@ -693,11 +737,13 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg, struct afu *afu = cfg->afu; struct ctx_info *ctxi = NULL; struct llun_info **lli = NULL; + bool *ws = NULL; struct sisl_rht_entry *rhte; ctxi = kzalloc(sizeof(*ctxi), GFP_KERNEL); lli = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*lli)), GFP_KERNEL); - if (unlikely(!ctxi || !lli)) { + ws = kzalloc((MAX_RHT_PER_CONTEXT * sizeof(*ws)), GFP_KERNEL); + if (unlikely(!ctxi || !lli || !ws)) { dev_err(dev, "%s: Unable to allocate context!\n", __func__); goto err; } @@ -709,6 +755,7 @@ static struct ctx_info *create_context(struct cxlflash_cfg *cfg, } ctxi->rht_lun = lli; + ctxi->rht_needs_ws = ws; ctxi->rht_start = rhte; ctxi->rht_perms = perms; @@ -728,6 +775,7 @@ out: return ctxi; err: + kfree(ws); kfree(lli); kfree(ctxi); ctxi = NULL; @@ -1729,6 +1777,12 @@ static int cxlflash_disk_verify(struct scsi_device *sdev, case MODE_PHYSICAL: last_lba = gli->max_lba; break; + case MODE_VIRTUAL: + /* Cast lxt_cnt to u64 for multiply to be treated as 64bit op */ + last_lba = ((u64)rhte->lxt_cnt * MC_CHUNK_SIZE * gli->blk_len); + last_lba /= CXLFLASH_BLOCK_SIZE; + last_lba--; + break; default: WARN(1, "Unsupported LUN mode!"); } @@ -1756,12 +1810,18 @@ static char *decode_ioctl(int cmd) return __stringify_1(DK_CXLFLASH_ATTACH); case DK_CXLFLASH_USER_DIRECT: return __stringify_1(DK_CXLFLASH_USER_DIRECT); + case DK_CXLFLASH_USER_VIRTUAL: + return __stringify_1(DK_CXLFLASH_USER_VIRTUAL); + case DK_CXLFLASH_VLUN_RESIZE: + return __stringify_1(DK_CXLFLASH_VLUN_RESIZE); case DK_CXLFLASH_RELEASE: return __stringify_1(DK_CXLFLASH_RELEASE); case DK_CXLFLASH_DETACH: return __stringify_1(DK_CXLFLASH_DETACH); case DK_CXLFLASH_VERIFY: return __stringify_1(DK_CXLFLASH_VERIFY); + case DK_CXLFLASH_VLUN_CLONE: + return __stringify_1(DK_CXLFLASH_VLUN_CLONE); case DK_CXLFLASH_RECOVER_AFU: return __stringify_1(DK_CXLFLASH_RECOVER_AFU); case DK_CXLFLASH_MANAGE_LUN: @@ -1876,6 +1936,7 @@ static int ioctl_common(struct scsi_device *sdev, int cmd) rc = check_state(cfg); if (unlikely(rc) && (cfg->state == STATE_FAILTERM)) { switch (cmd) { + case DK_CXLFLASH_VLUN_RESIZE: case DK_CXLFLASH_RELEASE: case DK_CXLFLASH_DETACH: dev_dbg(dev, "%s: Command override! (%d)\n", @@ -1923,12 +1984,18 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg) {sizeof(struct dk_cxlflash_verify), (sioctl)cxlflash_disk_verify}, {sizeof(struct dk_cxlflash_recover_afu), (sioctl)cxlflash_afu_recover}, {sizeof(struct dk_cxlflash_manage_lun), (sioctl)cxlflash_manage_lun}, + {sizeof(struct dk_cxlflash_uvirtual), cxlflash_disk_virtual_open}, + {sizeof(struct dk_cxlflash_resize), (sioctl)cxlflash_vlun_resize}, + {sizeof(struct dk_cxlflash_clone), (sioctl)cxlflash_disk_clone}, }; /* Restrict command set to physical support only for internal LUN */ if (afu->internal_lun) switch (cmd) { case DK_CXLFLASH_RELEASE: + case DK_CXLFLASH_USER_VIRTUAL: + case DK_CXLFLASH_VLUN_RESIZE: + case DK_CXLFLASH_VLUN_CLONE: dev_dbg(dev, "%s: %s not supported for lun_mode=%d\n", __func__, decode_ioctl(cmd), afu->internal_lun); rc = -EINVAL; @@ -1942,6 +2009,9 @@ int cxlflash_ioctl(struct scsi_device *sdev, int cmd, void __user *arg) case DK_CXLFLASH_DETACH: case DK_CXLFLASH_VERIFY: case DK_CXLFLASH_RECOVER_AFU: + case DK_CXLFLASH_USER_VIRTUAL: + case DK_CXLFLASH_VLUN_RESIZE: + case DK_CXLFLASH_VLUN_CLONE: dev_dbg(dev, "%s: %s (%08X) on dev(%d/%d/%d/%llu)\n", __func__, decode_ioctl(cmd), cmd, shost->host_no, sdev->channel, sdev->id, sdev->lun); diff --git a/drivers/scsi/cxlflash/superpipe.h b/drivers/scsi/cxlflash/superpipe.h index ae39b9627118..d7dc88bc64a4 100644 --- a/drivers/scsi/cxlflash/superpipe.h +++ b/drivers/scsi/cxlflash/superpipe.h @@ -31,9 +31,11 @@ extern struct cxlflash_global global; #define MC_DISCOVERY_TIMEOUT 5 /* 5 secs */ #define CHAN2PORT(_x) ((_x) + 1) +#define PORT2CHAN(_x) ((_x) - 1) enum lun_mode { MODE_NONE = 0, + MODE_VIRTUAL, MODE_PHYSICAL }; @@ -41,13 +43,14 @@ enum lun_mode { struct glun_info { u64 max_lba; /* from read cap(16) */ u32 blk_len; /* from read cap(16) */ - enum lun_mode mode; /* NONE, PHYSICAL */ + enum lun_mode mode; /* NONE, VIRTUAL, PHYSICAL */ int users; /* Number of users w/ references to LUN */ u8 wwid[16]; struct mutex mutex; + struct blka blka; struct list_head list; }; @@ -58,6 +61,7 @@ struct llun_info { u32 host_no; /* host_no from Scsi_host */ u32 port_sel; /* What port to use for this LUN */ bool newly_created; /* Whether the LUN was just discovered */ + bool in_table; /* Whether a LUN table entry was created */ u8 wwid[16]; /* Keep a duplicate copy here? */ @@ -90,6 +94,7 @@ struct ctx_info { u32 rht_out; /* Number of checked out RHT entries */ u32 rht_perms; /* User-defined permissions for RHT entries */ struct llun_info **rht_lun; /* Mapping of RHT entries to LUNs */ + bool *rht_needs_ws; /* User-desired write-same function per RHTE */ struct cxl_ioctl_start_work work; u64 ctxid; @@ -111,10 +116,18 @@ struct cxlflash_global { struct page *err_page; /* One page of all 0xF for error notification */ }; +int cxlflash_vlun_resize(struct scsi_device *, struct dk_cxlflash_resize *); +int _cxlflash_vlun_resize(struct scsi_device *, struct ctx_info *, + struct dk_cxlflash_resize *); + int cxlflash_disk_release(struct scsi_device *, struct dk_cxlflash_release *); int _cxlflash_disk_release(struct scsi_device *, struct ctx_info *, struct dk_cxlflash_release *); +int cxlflash_disk_clone(struct scsi_device *, struct dk_cxlflash_clone *); + +int cxlflash_disk_virtual_open(struct scsi_device *, void *); + int cxlflash_lun_attach(struct glun_info *, enum lun_mode, bool); void cxlflash_lun_detach(struct glun_info *); @@ -127,6 +140,8 @@ struct sisl_rht_entry *get_rhte(struct ctx_info *, res_hndl_t, struct sisl_rht_entry *rhte_checkout(struct ctx_info *, struct llun_info *); void rhte_checkin(struct ctx_info *, struct sisl_rht_entry *); +void cxlflash_ba_terminate(struct ba_lun *); + int cxlflash_manage_lun(struct scsi_device *, struct dk_cxlflash_manage_lun *); #endif /* ifndef _CXLFLASH_SUPERPIPE_H */ diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c new file mode 100644 index 000000000000..6155cb1d4ed3 --- /dev/null +++ b/drivers/scsi/cxlflash/vlun.c @@ -0,0 +1,1243 @@ +/* + * CXL Flash Device Driver + * + * Written by: Manoj N. Kumar , IBM Corporation + * Matthew R. Ochs , 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 +#include +#include +#include + +#include +#include +#include + +#include "sislite.h" +#include "common.h" +#include "vlun.h" +#include "superpipe.h" + +/** + * marshal_virt_to_resize() - translate uvirtual to resize structure + * @virt: Source structure from which to translate/copy. + * @resize: Destination structure for the translate/copy. + */ +static void marshal_virt_to_resize(struct dk_cxlflash_uvirtual *virt, + struct dk_cxlflash_resize *resize) +{ + resize->hdr = virt->hdr; + resize->context_id = virt->context_id; + resize->rsrc_handle = virt->rsrc_handle; + resize->req_size = virt->lun_size; + resize->last_lba = virt->last_lba; +} + +/** + * marshal_clone_to_rele() - translate clone to release structure + * @clone: Source structure from which to translate/copy. + * @rele: Destination structure for the translate/copy. + */ +static void marshal_clone_to_rele(struct dk_cxlflash_clone *clone, + struct dk_cxlflash_release *release) +{ + release->hdr = clone->hdr; + release->context_id = clone->context_id_dst; +} + +/** + * ba_init() - initializes a block allocator + * @ba_lun: Block allocator to initialize. + * + * Return: 0 on success, -errno on failure + */ +static int ba_init(struct ba_lun *ba_lun) +{ + struct ba_lun_info *bali = NULL; + int lun_size_au = 0, i = 0; + int last_word_underflow = 0; + u64 *lam; + + pr_debug("%s: Initializing LUN: lun_id = %llX, " + "ba_lun->lsize = %lX, ba_lun->au_size = %lX\n", + __func__, ba_lun->lun_id, ba_lun->lsize, ba_lun->au_size); + + /* Calculate bit map size */ + lun_size_au = ba_lun->lsize / ba_lun->au_size; + if (lun_size_au == 0) { + pr_debug("%s: Requested LUN size of 0!\n", __func__); + return -EINVAL; + } + + /* Allocate lun information container */ + bali = kzalloc(sizeof(struct ba_lun_info), GFP_KERNEL); + if (unlikely(!bali)) { + pr_err("%s: Failed to allocate lun_info for lun_id %llX\n", + __func__, ba_lun->lun_id); + return -ENOMEM; + } + + bali->total_aus = lun_size_au; + bali->lun_bmap_size = lun_size_au / BITS_PER_LONG; + + if (lun_size_au % BITS_PER_LONG) + bali->lun_bmap_size++; + + /* Allocate bitmap space */ + bali->lun_alloc_map = kzalloc((bali->lun_bmap_size * sizeof(u64)), + GFP_KERNEL); + if (unlikely(!bali->lun_alloc_map)) { + pr_err("%s: Failed to allocate lun allocation map: " + "lun_id = %llX\n", __func__, ba_lun->lun_id); + kfree(bali); + return -ENOMEM; + } + + /* Initialize the bit map size and set all bits to '1' */ + bali->free_aun_cnt = lun_size_au; + + for (i = 0; i < bali->lun_bmap_size; i++) + bali->lun_alloc_map[i] = 0xFFFFFFFFFFFFFFFFULL; + + /* If the last word not fully utilized, mark extra bits as allocated */ + last_word_underflow = (bali->lun_bmap_size * BITS_PER_LONG); + last_word_underflow -= bali->free_aun_cnt; + if (last_word_underflow > 0) { + lam = &bali->lun_alloc_map[bali->lun_bmap_size - 1]; + for (i = (HIBIT - last_word_underflow + 1); + i < BITS_PER_LONG; + i++) + clear_bit(i, (ulong *)lam); + } + + /* Initialize high elevator index, low/curr already at 0 from kzalloc */ + bali->free_high_idx = bali->lun_bmap_size; + + /* Allocate clone map */ + bali->aun_clone_map = kzalloc((bali->total_aus * sizeof(u8)), + GFP_KERNEL); + if (unlikely(!bali->aun_clone_map)) { + pr_err("%s: Failed to allocate clone map: lun_id = %llX\n", + __func__, ba_lun->lun_id); + kfree(bali->lun_alloc_map); + kfree(bali); + return -ENOMEM; + } + + /* Pass the allocated lun info as a handle to the user */ + ba_lun->ba_lun_handle = bali; + + pr_debug("%s: Successfully initialized the LUN: " + "lun_id = %llX, bitmap size = %X, free_aun_cnt = %llX\n", + __func__, ba_lun->lun_id, bali->lun_bmap_size, + bali->free_aun_cnt); + return 0; +} + +/** + * find_free_range() - locates a free bit within the block allocator + * @low: First word in block allocator to start search. + * @high: Last word in block allocator to search. + * @bali: LUN information structure owning the block allocator to search. + * @bit_word: Passes back the word in the block allocator owning the free bit. + * + * Return: The bit position within the passed back word, -1 on failure + */ +static int find_free_range(u32 low, + u32 high, + struct ba_lun_info *bali, int *bit_word) +{ + int i; + u64 bit_pos = -1; + ulong *lam, num_bits; + + for (i = low; i < high; i++) + if (bali->lun_alloc_map[i] != 0) { + lam = (ulong *)&bali->lun_alloc_map[i]; + num_bits = (sizeof(*lam) * BITS_PER_BYTE); + bit_pos = find_first_bit(lam, num_bits); + + pr_devel("%s: Found free bit %llX in lun " + "map entry %llX at bitmap index = %X\n", + __func__, bit_pos, bali->lun_alloc_map[i], + i); + + *bit_word = i; + bali->free_aun_cnt--; + clear_bit(bit_pos, lam); + break; + } + + return bit_pos; +} + +/** + * ba_alloc() - allocates a block from the block allocator + * @ba_lun: Block allocator from which to allocate a block. + * + * Return: The allocated block, -1 on failure + */ +static u64 ba_alloc(struct ba_lun *ba_lun) +{ + u64 bit_pos = -1; + int bit_word = 0; + struct ba_lun_info *bali = NULL; + + bali = ba_lun->ba_lun_handle; + + pr_debug("%s: Received block allocation request: " + "lun_id = %llX, free_aun_cnt = %llX\n", + __func__, ba_lun->lun_id, bali->free_aun_cnt); + + if (bali->free_aun_cnt == 0) { + pr_debug("%s: No space left on LUN: lun_id = %llX\n", + __func__, ba_lun->lun_id); + return -1ULL; + } + + /* Search to find a free entry, curr->high then low->curr */ + bit_pos = find_free_range(bali->free_curr_idx, + bali->free_high_idx, bali, &bit_word); + if (bit_pos == -1) { + bit_pos = find_free_range(bali->free_low_idx, + bali->free_curr_idx, + bali, &bit_word); + if (bit_pos == -1) { + pr_debug("%s: Could not find an allocation unit on LUN:" + " lun_id = %llX\n", __func__, ba_lun->lun_id); + return -1ULL; + } + } + + /* Update the free_curr_idx */ + if (bit_pos == HIBIT) + bali->free_curr_idx = bit_word + 1; + else + bali->free_curr_idx = bit_word; + + pr_debug("%s: Allocating AU number %llX, on lun_id %llX, " + "free_aun_cnt = %llX\n", __func__, + ((bit_word * BITS_PER_LONG) + bit_pos), ba_lun->lun_id, + bali->free_aun_cnt); + + return (u64) ((bit_word * BITS_PER_LONG) + bit_pos); +} + +/** + * validate_alloc() - validates the specified block has been allocated + * @ba_lun_info: LUN info owning the block allocator. + * @aun: Block to validate. + * + * Return: 0 on success, -1 on failure + */ +static int validate_alloc(struct ba_lun_info *bali, u64 aun) +{ + int idx = 0, bit_pos = 0; + + idx = aun / BITS_PER_LONG; + bit_pos = aun % BITS_PER_LONG; + + if (test_bit(bit_pos, (ulong *)&bali->lun_alloc_map[idx])) + return -1; + + return 0; +} + +/** + * ba_free() - frees a block from the block allocator + * @ba_lun: Block allocator from which to allocate a block. + * @to_free: Block to free. + * + * Return: 0 on success, -1 on failure + */ +static int ba_free(struct ba_lun *ba_lun, u64 to_free) +{ + int idx = 0, bit_pos = 0; + struct ba_lun_info *bali = NULL; + + bali = ba_lun->ba_lun_handle; + + if (validate_alloc(bali, to_free)) { + pr_debug("%s: The AUN %llX is not allocated on lun_id %llX\n", + __func__, to_free, ba_lun->lun_id); + return -1; + } + + pr_debug("%s: Received a request to free AU %llX on lun_id %llX, " + "free_aun_cnt = %llX\n", __func__, to_free, ba_lun->lun_id, + bali->free_aun_cnt); + + if (bali->aun_clone_map[to_free] > 0) { + pr_debug("%s: AUN %llX on lun_id %llX has been cloned. Clone " + "count = %X\n", __func__, to_free, ba_lun->lun_id, + bali->aun_clone_map[to_free]); + bali->aun_clone_map[to_free]--; + return 0; + } + + idx = to_free / BITS_PER_LONG; + bit_pos = to_free % BITS_PER_LONG; + + set_bit(bit_pos, (ulong *)&bali->lun_alloc_map[idx]); + bali->free_aun_cnt++; + + if (idx < bali->free_low_idx) + bali->free_low_idx = idx; + else if (idx > bali->free_high_idx) + bali->free_high_idx = idx; + + pr_debug("%s: Successfully freed AU at bit_pos %X, bit map index %X on " + "lun_id %llX, free_aun_cnt = %llX\n", __func__, bit_pos, idx, + ba_lun->lun_id, bali->free_aun_cnt); + + return 0; +} + +/** + * ba_clone() - Clone a chunk of the block allocation table + * @ba_lun: Block allocator from which to allocate a block. + * @to_free: Block to free. + * + * Return: 0 on success, -1 on failure + */ +static int ba_clone(struct ba_lun *ba_lun, u64 to_clone) +{ + struct ba_lun_info *bali = ba_lun->ba_lun_handle; + + if (validate_alloc(bali, to_clone)) { + pr_debug("%s: AUN %llX is not allocated on lun_id %llX\n", + __func__, to_clone, ba_lun->lun_id); + return -1; + } + + pr_debug("%s: Received a request to clone AUN %llX on lun_id %llX\n", + __func__, to_clone, ba_lun->lun_id); + + if (bali->aun_clone_map[to_clone] == MAX_AUN_CLONE_CNT) { + pr_debug("%s: AUN %llX on lun_id %llX hit max clones already\n", + __func__, to_clone, ba_lun->lun_id); + return -1; + } + + bali->aun_clone_map[to_clone]++; + + return 0; +} + +/** + * ba_space() - returns the amount of free space left in the block allocator + * @ba_lun: Block allocator. + * + * Return: Amount of free space in block allocator + */ +static u64 ba_space(struct ba_lun *ba_lun) +{ + struct ba_lun_info *bali = ba_lun->ba_lun_handle; + + return bali->free_aun_cnt; +} + +/** + * cxlflash_ba_terminate() - frees resources associated with the block allocator + * @ba_lun: Block allocator. + * + * Safe to call in a partially allocated state. + */ +void cxlflash_ba_terminate(struct ba_lun *ba_lun) +{ + struct ba_lun_info *bali = ba_lun->ba_lun_handle; + + if (bali) { + kfree(bali->aun_clone_map); + kfree(bali->lun_alloc_map); + kfree(bali); + ba_lun->ba_lun_handle = NULL; + } +} + +/** + * init_vlun() - initializes a LUN for virtual use + * @lun_info: LUN information structure that owns the block allocator. + * + * Return: 0 on success, -errno on failure + */ +static int init_vlun(struct llun_info *lli) +{ + int rc = 0; + struct glun_info *gli = lli->parent; + struct blka *blka = &gli->blka; + + memset(blka, 0, sizeof(*blka)); + mutex_init(&blka->mutex); + + /* LUN IDs are unique per port, save the index instead */ + blka->ba_lun.lun_id = lli->lun_index; + blka->ba_lun.lsize = gli->max_lba + 1; + blka->ba_lun.lba_size = gli->blk_len; + + blka->ba_lun.au_size = MC_CHUNK_SIZE; + blka->nchunk = blka->ba_lun.lsize / MC_CHUNK_SIZE; + + rc = ba_init(&blka->ba_lun); + if (unlikely(rc)) + pr_debug("%s: cannot init block_alloc, rc=%d\n", __func__, rc); + + pr_debug("%s: returning rc=%d lli=%p\n", __func__, rc, lli); + return rc; +} + +/** + * write_same16() - sends a SCSI WRITE_SAME16 (0) command to specified LUN + * @sdev: SCSI device associated with LUN. + * @lba: Logical block address to start write same. + * @nblks: Number of logical blocks to write same. + * + * Return: 0 on success, -errno on failure + */ +static int write_same16(struct scsi_device *sdev, + u64 lba, + u32 nblks) +{ + u8 *cmd_buf = NULL; + u8 *scsi_cmd = NULL; + u8 *sense_buf = NULL; + int rc = 0; + int result = 0; + int ws_limit = SISLITE_MAX_WS_BLOCKS; + u64 offset = lba; + int left = nblks; + u32 tout = sdev->request_queue->rq_timeout; + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + + cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL); + scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL); + sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL); + if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) { + rc = -ENOMEM; + goto out; + } + + while (left > 0) { + + scsi_cmd[0] = WRITE_SAME_16; + put_unaligned_be64(offset, &scsi_cmd[2]); + put_unaligned_be32(ws_limit < left ? ws_limit : left, + &scsi_cmd[10]); + + result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf, + CMD_BUFSIZE, sense_buf, tout, 5, 0, NULL); + if (result) { + dev_err_ratelimited(dev, "%s: command failed for " + "offset %lld result=0x%x\n", + __func__, offset, result); + rc = -EIO; + goto out; + } + left -= ws_limit; + offset += ws_limit; + } + +out: + kfree(cmd_buf); + kfree(scsi_cmd); + kfree(sense_buf); + pr_debug("%s: returning rc=%d\n", __func__, rc); + return rc; +} + +/** + * grow_lxt() - expands the translation table associated with the specified RHTE + * @afu: AFU associated with the host. + * @sdev: SCSI device associated with LUN. + * @ctxid: Context ID of context owning the RHTE. + * @rhndl: Resource handle associated with the RHTE. + * @rhte: Resource handle entry (RHTE). + * @new_size: Number of translation entries associated with RHTE. + * + * By design, this routine employs a 'best attempt' allocation and will + * truncate the requested size down if there is not sufficient space in + * the block allocator to satisfy the request but there does exist some + * amount of space. The user is made aware of this by returning the size + * allocated. + * + * Return: 0 on success, -errno on failure + */ +static int grow_lxt(struct afu *afu, + struct scsi_device *sdev, + ctx_hndl_t ctxid, + res_hndl_t rhndl, + struct sisl_rht_entry *rhte, + u64 *new_size) +{ + struct sisl_lxt_entry *lxt = NULL, *lxt_old = NULL; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct blka *blka = &gli->blka; + u32 av_size; + u32 ngrps, ngrps_old; + u64 aun; /* chunk# allocated by block allocator */ + u64 delta = *new_size - rhte->lxt_cnt; + u64 my_new_size; + int i, rc = 0; + + /* + * Check what is available in the block allocator before re-allocating + * LXT array. This is done up front under the mutex which must not be + * released until after allocation is complete. + */ + mutex_lock(&blka->mutex); + av_size = ba_space(&blka->ba_lun); + if (unlikely(av_size <= 0)) { + pr_debug("%s: ba_space error: av_size %d\n", __func__, av_size); + mutex_unlock(&blka->mutex); + rc = -ENOSPC; + goto out; + } + + if (av_size < delta) + delta = av_size; + + lxt_old = rhte->lxt_start; + ngrps_old = LXT_NUM_GROUPS(rhte->lxt_cnt); + ngrps = LXT_NUM_GROUPS(rhte->lxt_cnt + delta); + + if (ngrps != ngrps_old) { + /* reallocate to fit new size */ + lxt = kzalloc((sizeof(*lxt) * LXT_GROUP_SIZE * ngrps), + GFP_KERNEL); + if (unlikely(!lxt)) { + mutex_unlock(&blka->mutex); + rc = -ENOMEM; + goto out; + } + + /* copy over all old entries */ + memcpy(lxt, lxt_old, (sizeof(*lxt) * rhte->lxt_cnt)); + } else + lxt = lxt_old; + + /* nothing can fail from now on */ + my_new_size = rhte->lxt_cnt + delta; + + /* add new entries to the end */ + for (i = rhte->lxt_cnt; i < my_new_size; i++) { + /* + * Due to the earlier check of available space, ba_alloc + * cannot fail here. If it did due to internal error, + * leave a rlba_base of -1u which will likely be a + * invalid LUN (too large). + */ + aun = ba_alloc(&blka->ba_lun); + if ((aun == -1ULL) || (aun >= blka->nchunk)) + pr_debug("%s: ba_alloc error: allocated chunk# %llX, " + "max %llX\n", __func__, aun, blka->nchunk - 1); + + /* select both ports, use r/w perms from RHT */ + lxt[i].rlba_base = ((aun << MC_CHUNK_SHIFT) | + (lli->lun_index << LXT_LUNIDX_SHIFT) | + (RHT_PERM_RW << LXT_PERM_SHIFT | + lli->port_sel)); + } + + mutex_unlock(&blka->mutex); + + /* + * The following sequence is prescribed in the SISlite spec + * for syncing up with the AFU when adding LXT entries. + */ + dma_wmb(); /* Make LXT updates are visible */ + + rhte->lxt_start = lxt; + dma_wmb(); /* Make RHT entry's LXT table update visible */ + + rhte->lxt_cnt = my_new_size; + dma_wmb(); /* Make RHT entry's LXT table size update visible */ + + cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC); + + /* free old lxt if reallocated */ + if (lxt != lxt_old) + kfree(lxt_old); + *new_size = my_new_size; +out: + pr_debug("%s: returning rc=%d\n", __func__, rc); + return rc; +} + +/** + * shrink_lxt() - reduces translation table associated with the specified RHTE + * @afu: AFU associated with the host. + * @sdev: SCSI device associated with LUN. + * @rhndl: Resource handle associated with the RHTE. + * @rhte: Resource handle entry (RHTE). + * @ctxi: Context owning resources. + * @new_size: Number of translation entries associated with RHTE. + * + * Return: 0 on success, -errno on failure + */ +static int shrink_lxt(struct afu *afu, + struct scsi_device *sdev, + res_hndl_t rhndl, + struct sisl_rht_entry *rhte, + struct ctx_info *ctxi, + u64 *new_size) +{ + struct sisl_lxt_entry *lxt, *lxt_old; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct blka *blka = &gli->blka; + ctx_hndl_t ctxid = DECODE_CTXID(ctxi->ctxid); + bool needs_ws = ctxi->rht_needs_ws[rhndl]; + bool needs_sync = !ctxi->err_recovery_active; + u32 ngrps, ngrps_old; + u64 aun; /* chunk# allocated by block allocator */ + u64 delta = rhte->lxt_cnt - *new_size; + u64 my_new_size; + int i, rc = 0; + + lxt_old = rhte->lxt_start; + ngrps_old = LXT_NUM_GROUPS(rhte->lxt_cnt); + ngrps = LXT_NUM_GROUPS(rhte->lxt_cnt - delta); + + if (ngrps != ngrps_old) { + /* Reallocate to fit new size unless new size is 0 */ + if (ngrps) { + lxt = kzalloc((sizeof(*lxt) * LXT_GROUP_SIZE * ngrps), + GFP_KERNEL); + if (unlikely(!lxt)) { + rc = -ENOMEM; + goto out; + } + + /* Copy over old entries that will remain */ + memcpy(lxt, lxt_old, + (sizeof(*lxt) * (rhte->lxt_cnt - delta))); + } else + lxt = NULL; + } else + lxt = lxt_old; + + /* Nothing can fail from now on */ + my_new_size = rhte->lxt_cnt - delta; + + /* + * The following sequence is prescribed in the SISlite spec + * for syncing up with the AFU when removing LXT entries. + */ + rhte->lxt_cnt = my_new_size; + dma_wmb(); /* Make RHT entry's LXT table size update visible */ + + rhte->lxt_start = lxt; + dma_wmb(); /* Make RHT entry's LXT table update visible */ + + if (needs_sync) + cxlflash_afu_sync(afu, ctxid, rhndl, AFU_HW_SYNC); + + if (needs_ws) { + /* + * Mark the context as unavailable, so that we can release + * the mutex safely. + */ + ctxi->unavail = true; + mutex_unlock(&ctxi->mutex); + } + + /* Free LBAs allocated to freed chunks */ + mutex_lock(&blka->mutex); + for (i = delta - 1; i >= 0; i--) { + /* Mask the higher 48 bits before shifting, even though + * it is a noop + */ + aun = (lxt_old[my_new_size + i].rlba_base & SISL_ASTATUS_MASK); + aun = (aun >> MC_CHUNK_SHIFT); + if (needs_ws) + write_same16(sdev, aun, MC_CHUNK_SIZE); + ba_free(&blka->ba_lun, aun); + } + mutex_unlock(&blka->mutex); + + if (needs_ws) { + /* Make the context visible again */ + mutex_lock(&ctxi->mutex); + ctxi->unavail = false; + } + + /* Free old lxt if reallocated */ + if (lxt != lxt_old) + kfree(lxt_old); + *new_size = my_new_size; +out: + pr_debug("%s: returning rc=%d\n", __func__, rc); + return rc; +} + +/** + * _cxlflash_vlun_resize() - changes the size of a virtual lun + * @sdev: SCSI device associated with LUN owning virtual LUN. + * @ctxi: Context owning resources. + * @resize: Resize ioctl data structure. + * + * On successful return, the user is informed of the new size (in blocks) + * of the virtual lun in last LBA format. When the size of the virtual + * lun is zero, the last LBA is reflected as -1. See comment in the + * prologue for _cxlflash_disk_release() regarding AFU syncs and contexts + * on the error recovery list. + * + * Return: 0 on success, -errno on failure + */ +int _cxlflash_vlun_resize(struct scsi_device *sdev, + struct ctx_info *ctxi, + struct dk_cxlflash_resize *resize) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct afu *afu = cfg->afu; + bool put_ctx = false; + + res_hndl_t rhndl = resize->rsrc_handle; + u64 new_size; + u64 nsectors; + u64 ctxid = DECODE_CTXID(resize->context_id), + rctxid = resize->context_id; + + struct sisl_rht_entry *rhte; + + int rc = 0; + + /* + * The requested size (req_size) is always assumed to be in 4k blocks, + * so we have to convert it here from 4k to chunk size. + */ + nsectors = (resize->req_size * CXLFLASH_BLOCK_SIZE) / gli->blk_len; + new_size = DIV_ROUND_UP(nsectors, MC_CHUNK_SIZE); + + pr_debug("%s: ctxid=%llu rhndl=0x%llx, req_size=0x%llx," + "new_size=%llx\n", __func__, ctxid, resize->rsrc_handle, + resize->req_size, new_size); + + if (unlikely(gli->mode != MODE_VIRTUAL)) { + pr_debug("%s: LUN mode does not support resize! (%d)\n", + __func__, gli->mode); + rc = -EINVAL; + goto out; + + } + + if (!ctxi) { + ctxi = get_context(cfg, rctxid, lli, CTX_CTRL_ERR_FALLBACK); + if (unlikely(!ctxi)) { + pr_debug("%s: Bad context! (%llu)\n", __func__, ctxid); + rc = -EINVAL; + goto out; + } + + put_ctx = true; + } + + rhte = get_rhte(ctxi, rhndl, lli); + if (unlikely(!rhte)) { + pr_debug("%s: Bad resource handle! (%u)\n", __func__, rhndl); + rc = -EINVAL; + goto out; + } + + if (new_size > rhte->lxt_cnt) + rc = grow_lxt(afu, sdev, ctxid, rhndl, rhte, &new_size); + else if (new_size < rhte->lxt_cnt) + rc = shrink_lxt(afu, sdev, rhndl, rhte, ctxi, &new_size); + + resize->hdr.return_flags = 0; + resize->last_lba = (new_size * MC_CHUNK_SIZE * gli->blk_len); + resize->last_lba /= CXLFLASH_BLOCK_SIZE; + resize->last_lba--; + +out: + if (put_ctx) + put_context(ctxi); + pr_debug("%s: resized to %lld returning rc=%d\n", + __func__, resize->last_lba, rc); + return rc; +} + +int cxlflash_vlun_resize(struct scsi_device *sdev, + struct dk_cxlflash_resize *resize) +{ + return _cxlflash_vlun_resize(sdev, NULL, resize); +} + +/** + * cxlflash_restore_luntable() - Restore LUN table to prior state + * @cfg: Internal structure associated with the host. + */ +void cxlflash_restore_luntable(struct cxlflash_cfg *cfg) +{ + struct llun_info *lli, *temp; + u32 chan; + u32 lind; + struct afu *afu = cfg->afu; + struct sisl_global_map *agm = &afu->afu_map->global; + + mutex_lock(&global.mutex); + + list_for_each_entry_safe(lli, temp, &cfg->lluns, list) { + if (!lli->in_table) + continue; + + lind = lli->lun_index; + + if (lli->port_sel == BOTH_PORTS) { + writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]); + writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]); + pr_debug("%s: Virtual LUN on slot %d id0=%llx, " + "id1=%llx\n", __func__, lind, + lli->lun_id[0], lli->lun_id[1]); + } else { + chan = PORT2CHAN(lli->port_sel); + writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]); + pr_debug("%s: Virtual LUN on slot %d chan=%d, " + "id=%llx\n", __func__, lind, chan, + lli->lun_id[chan]); + } + } + + mutex_unlock(&global.mutex); +} + +/** + * init_luntable() - write an entry in the LUN table + * @cfg: Internal structure associated with the host. + * @lli: Per adapter LUN information structure. + * + * On successful return, a LUN table entry is created. + * At the top for LUNs visible on both ports. + * At the bottom for LUNs visible only on one port. + * + * Return: 0 on success, -errno on failure + */ +static int init_luntable(struct cxlflash_cfg *cfg, struct llun_info *lli) +{ + u32 chan; + u32 lind; + int rc = 0; + struct afu *afu = cfg->afu; + struct sisl_global_map *agm = &afu->afu_map->global; + + mutex_lock(&global.mutex); + + if (lli->in_table) + goto out; + + if (lli->port_sel == BOTH_PORTS) { + /* + * If this LUN is visible from both ports, we will put + * it in the top half of the LUN table. + */ + if ((cfg->promote_lun_index == cfg->last_lun_index[0]) || + (cfg->promote_lun_index == cfg->last_lun_index[1])) { + rc = -ENOSPC; + goto out; + } + + lind = lli->lun_index = cfg->promote_lun_index; + writeq_be(lli->lun_id[0], &agm->fc_port[0][lind]); + writeq_be(lli->lun_id[1], &agm->fc_port[1][lind]); + cfg->promote_lun_index++; + pr_debug("%s: Virtual LUN on slot %d id0=%llx, id1=%llx\n", + __func__, lind, lli->lun_id[0], lli->lun_id[1]); + } else { + /* + * If this LUN is visible only from one port, we will put + * it in the bottom half of the LUN table. + */ + chan = PORT2CHAN(lli->port_sel); + if (cfg->promote_lun_index == cfg->last_lun_index[chan]) { + rc = -ENOSPC; + goto out; + } + + lind = lli->lun_index = cfg->last_lun_index[chan]; + writeq_be(lli->lun_id[chan], &agm->fc_port[chan][lind]); + cfg->last_lun_index[chan]--; + pr_debug("%s: Virtual LUN on slot %d chan=%d, id=%llx\n", + __func__, lind, chan, lli->lun_id[chan]); + } + + lli->in_table = true; +out: + mutex_unlock(&global.mutex); + pr_debug("%s: returning rc=%d\n", __func__, rc); + return rc; +} + +/** + * cxlflash_disk_virtual_open() - open a virtual disk of specified size + * @sdev: SCSI device associated with LUN owning virtual LUN. + * @arg: UVirtual ioctl data structure. + * + * On successful return, the user is informed of the resource handle + * to be used to identify the virtual lun and the size (in blocks) of + * the virtual lun in last LBA format. When the size of the virtual lun + * is zero, the last LBA is reflected as -1. + * + * Return: 0 on success, -errno on failure + */ +int cxlflash_disk_virtual_open(struct scsi_device *sdev, void *arg) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct device *dev = &cfg->dev->dev; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + + struct dk_cxlflash_uvirtual *virt = (struct dk_cxlflash_uvirtual *)arg; + struct dk_cxlflash_resize resize; + + u64 ctxid = DECODE_CTXID(virt->context_id), + rctxid = virt->context_id; + u64 lun_size = virt->lun_size; + u64 last_lba = 0; + u64 rsrc_handle = -1; + + int rc = 0; + + struct ctx_info *ctxi = NULL; + struct sisl_rht_entry *rhte = NULL; + + pr_debug("%s: ctxid=%llu ls=0x%llx\n", __func__, ctxid, lun_size); + + mutex_lock(&gli->mutex); + if (gli->mode == MODE_NONE) { + /* Setup the LUN table and block allocator on first call */ + rc = init_luntable(cfg, lli); + if (rc) { + dev_err(dev, "%s: call to init_luntable failed " + "rc=%d!\n", __func__, rc); + goto err0; + } + + rc = init_vlun(lli); + if (rc) { + dev_err(dev, "%s: call to init_vlun failed rc=%d!\n", + __func__, rc); + rc = -ENOMEM; + goto err0; + } + } + + rc = cxlflash_lun_attach(gli, MODE_VIRTUAL, true); + if (unlikely(rc)) { + dev_err(dev, "%s: Failed to attach to LUN! (VIRTUAL)\n", + __func__); + goto err0; + } + mutex_unlock(&gli->mutex); + + ctxi = get_context(cfg, rctxid, lli, 0); + if (unlikely(!ctxi)) { + dev_err(dev, "%s: Bad context! (%llu)\n", __func__, ctxid); + rc = -EINVAL; + goto err1; + } + + rhte = rhte_checkout(ctxi, lli); + if (unlikely(!rhte)) { + dev_err(dev, "%s: too many opens for this context\n", __func__); + rc = -EMFILE; /* too many opens */ + goto err1; + } + + rsrc_handle = (rhte - ctxi->rht_start); + + /* Populate RHT format 0 */ + rhte->nmask = MC_RHT_NMASK; + rhte->fp = SISL_RHT_FP(0U, ctxi->rht_perms); + + /* Resize even if requested size is 0 */ + marshal_virt_to_resize(virt, &resize); + resize.rsrc_handle = rsrc_handle; + rc = _cxlflash_vlun_resize(sdev, ctxi, &resize); + if (rc) { + dev_err(dev, "%s: resize failed rc %d\n", __func__, rc); + goto err2; + } + last_lba = resize.last_lba; + + if (virt->hdr.flags & DK_CXLFLASH_UVIRTUAL_NEED_WRITE_SAME) + ctxi->rht_needs_ws[rsrc_handle] = true; + + virt->hdr.return_flags = 0; + virt->last_lba = last_lba; + virt->rsrc_handle = rsrc_handle; + +out: + if (likely(ctxi)) + put_context(ctxi); + pr_debug("%s: returning handle 0x%llx rc=%d llba %lld\n", + __func__, rsrc_handle, rc, last_lba); + return rc; + +err2: + rhte_checkin(ctxi, rhte); +err1: + cxlflash_lun_detach(gli); + goto out; +err0: + /* Special common cleanup prior to successful LUN attach */ + cxlflash_ba_terminate(&gli->blka.ba_lun); + mutex_unlock(&gli->mutex); + goto out; +} + +/** + * clone_lxt() - copies translation tables from source to destination RHTE + * @afu: AFU associated with the host. + * @blka: Block allocator associated with LUN. + * @ctxid: Context ID of context owning the RHTE. + * @rhndl: Resource handle associated with the RHTE. + * @rhte: Destination resource handle entry (RHTE). + * @rhte_src: Source resource handle entry (RHTE). + * + * Return: 0 on success, -errno on failure + */ +static int clone_lxt(struct afu *afu, + struct blka *blka, + ctx_hndl_t ctxid, + res_hndl_t rhndl, + struct sisl_rht_entry *rhte, + struct sisl_rht_entry *rhte_src) +{ + struct sisl_lxt_entry *lxt; + u32 ngrps; + u64 aun; /* chunk# allocated by block allocator */ + int i, j; + + ngrps = LXT_NUM_GROUPS(rhte_src->lxt_cnt); + + if (ngrps) { + /* allocate new LXTs for clone */ + lxt = kzalloc((sizeof(*lxt) * LXT_GROUP_SIZE * ngrps), + GFP_KERNEL); + if (unlikely(!lxt)) + return -ENOMEM; + + /* copy over */ + memcpy(lxt, rhte_src->lxt_start, + (sizeof(*lxt) * rhte_src->lxt_cnt)); + + /* clone the LBAs in block allocator via ref_cnt */ + mutex_lock(&blka->mutex); + for (i = 0; i < rhte_src->lxt_cnt; i++) { + aun = (lxt[i].rlba_base >> MC_CHUNK_SHIFT); + if (ba_clone(&blka->ba_lun, aun) == -1ULL) { + /* free the clones already made */ + for (j = 0; j < i; j++) { + aun = (lxt[j].rlba_base >> + MC_CHUNK_SHIFT); + ba_free(&blka->ba_lun, aun); + } + + mutex_unlock(&blka->mutex); + kfree(lxt); + return -EIO; + } + } + mutex_unlock(&blka->mutex); + } else { + lxt = NULL; + } + + /* + * The following sequence is prescribed in the SISlite spec + * for syncing up with the AFU when adding LXT entries. + */ + dma_wmb(); /* Make LXT updates are visible */ + + rhte->lxt_start = lxt; + dma_wmb(); /* Make RHT entry's LXT table update visible */ + + rhte->lxt_cnt = rhte_src->lxt_cnt; + dma_wmb(); /* Make RHT entry's LXT table size update visible */ + + cxlflash_afu_sync(afu, ctxid, rhndl, AFU_LW_SYNC); + + pr_debug("%s: returning\n", __func__); + return 0; +} + +/** + * cxlflash_disk_clone() - clone a context by making snapshot of another + * @sdev: SCSI device associated with LUN owning virtual LUN. + * @clone: Clone ioctl data structure. + * + * This routine effectively performs cxlflash_disk_open operation for each + * in-use virtual resource in the source context. Note that the destination + * context must be in pristine state and cannot have any resource handles + * open at the time of the clone. + * + * Return: 0 on success, -errno on failure + */ +int cxlflash_disk_clone(struct scsi_device *sdev, + struct dk_cxlflash_clone *clone) +{ + struct cxlflash_cfg *cfg = (struct cxlflash_cfg *)sdev->host->hostdata; + struct llun_info *lli = sdev->hostdata; + struct glun_info *gli = lli->parent; + struct blka *blka = &gli->blka; + struct afu *afu = cfg->afu; + struct dk_cxlflash_release release = { { 0 }, 0 }; + + struct ctx_info *ctxi_src = NULL, + *ctxi_dst = NULL; + struct lun_access *lun_access_src, *lun_access_dst; + u32 perms; + u64 ctxid_src = DECODE_CTXID(clone->context_id_src), + ctxid_dst = DECODE_CTXID(clone->context_id_dst), + rctxid_src = clone->context_id_src, + rctxid_dst = clone->context_id_dst; + int adap_fd_src = clone->adap_fd_src; + int i, j; + int rc = 0; + bool found; + LIST_HEAD(sidecar); + + pr_debug("%s: ctxid_src=%llu ctxid_dst=%llu adap_fd_src=%d\n", + __func__, ctxid_src, ctxid_dst, adap_fd_src); + + /* Do not clone yourself */ + if (unlikely(rctxid_src == rctxid_dst)) { + rc = -EINVAL; + goto out; + } + + if (unlikely(gli->mode != MODE_VIRTUAL)) { + rc = -EINVAL; + pr_debug("%s: Clone not supported on physical LUNs! (%d)\n", + __func__, gli->mode); + goto out; + } + + ctxi_src = get_context(cfg, rctxid_src, lli, CTX_CTRL_CLONE); + ctxi_dst = get_context(cfg, rctxid_dst, lli, 0); + if (unlikely(!ctxi_src || !ctxi_dst)) { + pr_debug("%s: Bad context! (%llu,%llu)\n", __func__, + ctxid_src, ctxid_dst); + rc = -EINVAL; + goto out; + } + + if (unlikely(adap_fd_src != ctxi_src->lfd)) { + pr_debug("%s: Invalid source adapter fd! (%d)\n", + __func__, adap_fd_src); + rc = -EINVAL; + goto out; + } + + /* Verify there is no open resource handle in the destination context */ + for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) + if (ctxi_dst->rht_start[i].nmask != 0) { + rc = -EINVAL; + goto out; + } + + /* Clone LUN access list */ + list_for_each_entry(lun_access_src, &ctxi_src->luns, list) { + found = false; + list_for_each_entry(lun_access_dst, &ctxi_dst->luns, list) + if (lun_access_dst->sdev == lun_access_src->sdev) { + found = true; + break; + } + + if (!found) { + lun_access_dst = kzalloc(sizeof(*lun_access_dst), + GFP_KERNEL); + if (unlikely(!lun_access_dst)) { + pr_err("%s: Unable to allocate lun_access!\n", + __func__); + rc = -ENOMEM; + goto out; + } + + *lun_access_dst = *lun_access_src; + list_add(&lun_access_dst->list, &sidecar); + } + } + + if (unlikely(!ctxi_src->rht_out)) { + pr_debug("%s: Nothing to clone!\n", __func__); + goto out_success; + } + + /* User specified permission on attach */ + perms = ctxi_dst->rht_perms; + + /* + * Copy over checked-out RHT (and their associated LXT) entries by + * hand, stopping after we've copied all outstanding entries and + * cleaning up if the clone fails. + * + * Note: This loop is equivalent to performing cxlflash_disk_open and + * cxlflash_vlun_resize. As such, LUN accounting needs to be taken into + * account by attaching after each successful RHT entry clone. In the + * event that a clone failure is experienced, the LUN detach is handled + * via the cleanup performed by _cxlflash_disk_release. + */ + for (i = 0; i < MAX_RHT_PER_CONTEXT; i++) { + if (ctxi_src->rht_out == ctxi_dst->rht_out) + break; + if (ctxi_src->rht_start[i].nmask == 0) + continue; + + /* Consume a destination RHT entry */ + ctxi_dst->rht_out++; + ctxi_dst->rht_start[i].nmask = ctxi_src->rht_start[i].nmask; + ctxi_dst->rht_start[i].fp = + SISL_RHT_FP_CLONE(ctxi_src->rht_start[i].fp, perms); + ctxi_dst->rht_lun[i] = ctxi_src->rht_lun[i]; + + rc = clone_lxt(afu, blka, ctxid_dst, i, + &ctxi_dst->rht_start[i], + &ctxi_src->rht_start[i]); + if (rc) { + marshal_clone_to_rele(clone, &release); + for (j = 0; j < i; j++) { + release.rsrc_handle = j; + _cxlflash_disk_release(sdev, ctxi_dst, + &release); + } + + /* Put back the one we failed on */ + rhte_checkin(ctxi_dst, &ctxi_dst->rht_start[i]); + goto err; + } + + cxlflash_lun_attach(gli, gli->mode, false); + } + +out_success: + list_splice(&sidecar, &ctxi_dst->luns); + sys_close(adap_fd_src); + + /* fall through */ +out: + if (ctxi_src) + put_context(ctxi_src); + if (ctxi_dst) + put_context(ctxi_dst); + pr_debug("%s: returning rc=%d\n", __func__, rc); + return rc; + +err: + list_for_each_entry_safe(lun_access_src, lun_access_dst, &sidecar, list) + kfree(lun_access_src); + goto out; +} diff --git a/drivers/scsi/cxlflash/vlun.h b/drivers/scsi/cxlflash/vlun.h new file mode 100644 index 000000000000..8b29a74946e4 --- /dev/null +++ b/drivers/scsi/cxlflash/vlun.h @@ -0,0 +1,86 @@ +/* + * CXL Flash Device Driver + * + * Written by: Manoj N. Kumar , IBM Corporation + * Matthew R. Ochs , 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. + */ + +#ifndef _CXLFLASH_VLUN_H +#define _CXLFLASH_VLUN_H + +/* RHT - Resource Handle Table */ +#define MC_RHT_NMASK 16 /* in bits */ +#define MC_CHUNK_SHIFT MC_RHT_NMASK /* shift to go from LBA to chunk# */ + +#define HIBIT (BITS_PER_LONG - 1) + +#define MAX_AUN_CLONE_CNT 0xFF + +/* + * LXT - LBA Translation Table + * + * +-------+-------+-------+-------+-------+-------+-------+---+---+ + * | RLBA_BASE |LUN_IDX| P |SEL| + * +-------+-------+-------+-------+-------+-------+-------+---+---+ + * + * The LXT Entry contains the physical LBA where the chunk starts (RLBA_BASE). + * AFU ORes the low order bits from the virtual LBA (offset into the chunk) + * with RLBA_BASE. The result is the physical LBA to be sent to storage. + * The LXT Entry also contains an index to a LUN TBL and a bitmask of which + * outgoing (FC) * ports can be selected. The port select bit-mask is ANDed + * with a global port select bit-mask maintained by the driver. + * In addition, it has permission bits that are ANDed with the + * RHT permissions to arrive at the final permissions for the chunk. + * + * LXT tables are allocated dynamically in groups. This is done to avoid + * a malloc/free overhead each time the LXT has to grow or shrink. + * + * Based on the current lxt_cnt (used), it is always possible to know + * how many are allocated (used+free). The number of allocated entries is + * not stored anywhere. + * + * The LXT table is re-allocated whenever it needs to cross into another group. +*/ +#define LXT_GROUP_SIZE 8 +#define LXT_NUM_GROUPS(lxt_cnt) (((lxt_cnt) + 7)/8) /* alloc'ed groups */ +#define LXT_LUNIDX_SHIFT 8 /* LXT entry, shift for LUN index */ +#define LXT_PERM_SHIFT 4 /* LXT entry, shift for permission bits */ + +struct ba_lun_info { + u64 *lun_alloc_map; + u32 lun_bmap_size; + u32 total_aus; + u64 free_aun_cnt; + + /* indices to be used for elevator lookup of free map */ + u32 free_low_idx; + u32 free_curr_idx; + u32 free_high_idx; + + u8 *aun_clone_map; +}; + +struct ba_lun { + u64 lun_id; + u64 wwpn; + size_t lsize; /* LUN size in number of LBAs */ + size_t lba_size; /* LBA size in number of bytes */ + size_t au_size; /* Allocation Unit size in number of LBAs */ + struct ba_lun_info *ba_lun_handle; +}; + +/* Block Allocator */ +struct blka { + struct ba_lun ba_lun; + u64 nchunk; /* number of chunks */ + struct mutex mutex; +}; + +#endif /* ifndef _CXLFLASH_SUPERPIPE_H */ diff --git a/include/uapi/scsi/cxlflash_ioctl.h b/include/uapi/scsi/cxlflash_ioctl.h index 570773406531..831351b2e660 100644 --- a/include/uapi/scsi/cxlflash_ioctl.h +++ b/include/uapi/scsi/cxlflash_ioctl.h @@ -71,6 +71,17 @@ struct dk_cxlflash_udirect { __u64 reserved[8]; /* Reserved for future use */ }; +#define DK_CXLFLASH_UVIRTUAL_NEED_WRITE_SAME 0x8000000000000000ULL + +struct dk_cxlflash_uvirtual { + struct dk_cxlflash_hdr hdr; /* Common fields */ + __u64 context_id; /* Context to own virtual resources */ + __u64 lun_size; /* Requested size, in 4K blocks */ + __u64 rsrc_handle; /* Returned resource handle */ + __u64 last_lba; /* Returned last LBA of LUN */ + __u64 reserved[8]; /* Reserved for future use */ +}; + struct dk_cxlflash_release { struct dk_cxlflash_hdr hdr; /* Common fields */ __u64 context_id; /* Context owning resources */ @@ -78,6 +89,23 @@ struct dk_cxlflash_release { __u64 reserved[8]; /* Reserved for future use */ }; +struct dk_cxlflash_resize { + struct dk_cxlflash_hdr hdr; /* Common fields */ + __u64 context_id; /* Context owning resources */ + __u64 rsrc_handle; /* Resource handle of LUN to resize */ + __u64 req_size; /* New requested size, in 4K blocks */ + __u64 last_lba; /* Returned last LBA of LUN */ + __u64 reserved[8]; /* Reserved for future use */ +}; + +struct dk_cxlflash_clone { + struct dk_cxlflash_hdr hdr; /* Common fields */ + __u64 context_id_src; /* Context to clone from */ + __u64 context_id_dst; /* Context to clone to */ + __u64 adap_fd_src; /* Source context adapter fd */ + __u64 reserved[8]; /* Reserved for future use */ +}; + #define DK_CXLFLASH_VERIFY_SENSE_LEN 18 #define DK_CXLFLASH_VERIFY_HINT_SENSE 0x8000000000000000ULL @@ -118,7 +146,10 @@ union cxlflash_ioctls { struct dk_cxlflash_attach attach; struct dk_cxlflash_detach detach; struct dk_cxlflash_udirect udirect; + struct dk_cxlflash_uvirtual uvirtual; struct dk_cxlflash_release release; + struct dk_cxlflash_resize resize; + struct dk_cxlflash_clone clone; struct dk_cxlflash_verify verify; struct dk_cxlflash_recover_afu recover_afu; struct dk_cxlflash_manage_lun manage_lun; @@ -136,5 +167,8 @@ union cxlflash_ioctls { #define DK_CXLFLASH_VERIFY CXL_IOWR(0x84, dk_cxlflash_verify) #define DK_CXLFLASH_RECOVER_AFU CXL_IOWR(0x85, dk_cxlflash_recover_afu) #define DK_CXLFLASH_MANAGE_LUN CXL_IOWR(0x86, dk_cxlflash_manage_lun) +#define DK_CXLFLASH_USER_VIRTUAL CXL_IOWR(0x87, dk_cxlflash_uvirtual) +#define DK_CXLFLASH_VLUN_RESIZE CXL_IOWR(0x88, dk_cxlflash_resize) +#define DK_CXLFLASH_VLUN_CLONE CXL_IOWR(0x89, dk_cxlflash_clone) #endif /* ifndef _CXLFLASH_IOCTL_H */ -- cgit v1.2.3