Merge branch 'for-4.11/block' into for-4.11/linus-merge

Signed-off-by: Jens Axboe <axboe@fb.com>

4 files changed, 322 insertions, 51 deletions

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 8a3c3e32a704..138c6fa00cd5 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -784,6 +784,13 @@ static int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 		return nvme_sg_io(ns, (void __user *)arg);
 #endif
 	default:
+#ifdef CONFIG_NVM
+		if (ns->ndev)
+			return nvme_nvm_ioctl(ns, cmd, arg);
+#endif
+		if (is_sed_ioctl(cmd))
+			return sed_ioctl(ns->ctrl->opal_dev, cmd,
+					 (void __user *) arg);
 		return -ENOTTY;
 	}
 }
@@ -1051,6 +1058,28 @@ static const struct pr_ops nvme_pr_ops = {
 	.pr_clear	= nvme_pr_clear,
 };
 
+#ifdef CONFIG_BLK_SED_OPAL
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+		bool send)
+{
+	struct nvme_ctrl *ctrl = data;
+	struct nvme_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	if (send)
+		cmd.common.opcode = nvme_admin_security_send;
+	else
+		cmd.common.opcode = nvme_admin_security_recv;
+	cmd.common.nsid = 0;
+	cmd.common.cdw10[0] = cpu_to_le32(((u32)secp) << 24 | ((u32)spsp) << 8);
+	cmd.common.cdw10[1] = cpu_to_le32(len);
+
+	return __nvme_submit_sync_cmd(ctrl->admin_q, &cmd, NULL, buffer, len,
+				      ADMIN_TIMEOUT, NVME_QID_ANY, 1, 0);
+}
+EXPORT_SYMBOL_GPL(nvme_sec_submit);
+#endif /* CONFIG_BLK_SED_OPAL */
+
 static const struct block_device_operations nvme_fops = {
 	.owner		= THIS_MODULE,
 	.ioctl		= nvme_ioctl,
@@ -1230,6 +1259,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		return -EIO;
 	}
 
+	ctrl->oacs = le16_to_cpu(id->oacs);
 	ctrl->vid = le16_to_cpu(id->vid);
 	ctrl->oncs = le16_to_cpup(&id->oncs);
 	atomic_set(&ctrl->abort_limit, id->acl + 1);
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 588d4a34c083..21cac8523bd8 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -26,6 +26,8 @@
 #include <linux/bitops.h>
 #include <linux/lightnvm.h>
 #include <linux/vmalloc.h>
+#include <linux/sched/sysctl.h>
+#include <uapi/linux/lightnvm.h>
 
 enum nvme_nvm_admin_opcode {
 	nvme_nvm_admin_identity		= 0xe2,
@@ -248,50 +250,48 @@ static int init_grps(struct nvm_id *nvm_id, struct nvme_nvm_id *nvme_nvm_id)
 {
 	struct nvme_nvm_id_group *src;
 	struct nvm_id_group *dst;
-	int i, end;
-
-	end = min_t(u32, 4, nvm_id->cgrps);
-
-	for (i = 0; i < end; i++) {
-		src = &nvme_nvm_id->groups[i];
-		dst = &nvm_id->groups[i];
-
-		dst->mtype = src->mtype;
-		dst->fmtype = src->fmtype;
-		dst->num_ch = src->num_ch;
-		dst->num_lun = src->num_lun;
-		dst->num_pln = src->num_pln;
-
-		dst->num_pg = le16_to_cpu(src->num_pg);
-		dst->num_blk = le16_to_cpu(src->num_blk);
-		dst->fpg_sz = le16_to_cpu(src->fpg_sz);
-		dst->csecs = le16_to_cpu(src->csecs);
-		dst->sos = le16_to_cpu(src->sos);
-
-		dst->trdt = le32_to_cpu(src->trdt);
-		dst->trdm = le32_to_cpu(src->trdm);
-		dst->tprt = le32_to_cpu(src->tprt);
-		dst->tprm = le32_to_cpu(src->tprm);
-		dst->tbet = le32_to_cpu(src->tbet);
-		dst->tbem = le32_to_cpu(src->tbem);
-		dst->mpos = le32_to_cpu(src->mpos);
-		dst->mccap = le32_to_cpu(src->mccap);
-
-		dst->cpar = le16_to_cpu(src->cpar);
-
-		if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
-			memcpy(dst->lptbl.id, src->lptbl.id, 8);
-			dst->lptbl.mlc.num_pairs =
-					le16_to_cpu(src->lptbl.mlc.num_pairs);
-
-			if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
-				pr_err("nvm: number of MLC pairs not supported\n");
-				return -EINVAL;
-			}
 
-			memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
-						dst->lptbl.mlc.num_pairs);
+	if (nvme_nvm_id->cgrps != 1)
+		return -EINVAL;
+
+	src = &nvme_nvm_id->groups[0];
+	dst = &nvm_id->grp;
+
+	dst->mtype = src->mtype;
+	dst->fmtype = src->fmtype;
+	dst->num_ch = src->num_ch;
+	dst->num_lun = src->num_lun;
+	dst->num_pln = src->num_pln;
+
+	dst->num_pg = le16_to_cpu(src->num_pg);
+	dst->num_blk = le16_to_cpu(src->num_blk);
+	dst->fpg_sz = le16_to_cpu(src->fpg_sz);
+	dst->csecs = le16_to_cpu(src->csecs);
+	dst->sos = le16_to_cpu(src->sos);
+
+	dst->trdt = le32_to_cpu(src->trdt);
+	dst->trdm = le32_to_cpu(src->trdm);
+	dst->tprt = le32_to_cpu(src->tprt);
+	dst->tprm = le32_to_cpu(src->tprm);
+	dst->tbet = le32_to_cpu(src->tbet);
+	dst->tbem = le32_to_cpu(src->tbem);
+	dst->mpos = le32_to_cpu(src->mpos);
+	dst->mccap = le32_to_cpu(src->mccap);
+
+	dst->cpar = le16_to_cpu(src->cpar);
+
+	if (dst->fmtype == NVM_ID_FMTYPE_MLC) {
+		memcpy(dst->lptbl.id, src->lptbl.id, 8);
+		dst->lptbl.mlc.num_pairs =
+				le16_to_cpu(src->lptbl.mlc.num_pairs);
+
+		if (dst->lptbl.mlc.num_pairs > NVME_NVM_LP_MLC_PAIRS) {
+			pr_err("nvm: number of MLC pairs not supported\n");
+			return -EINVAL;
 		}
+
+		memcpy(dst->lptbl.mlc.pairs, src->lptbl.mlc.pairs,
+					dst->lptbl.mlc.num_pairs);
 	}
 
 	return 0;
@@ -321,7 +321,6 @@ static int nvme_nvm_identity(struct nvm_dev *nvmdev, struct nvm_id *nvm_id)
 
 	nvm_id->ver_id = nvme_nvm_id->ver_id;
 	nvm_id->vmnt = nvme_nvm_id->vmnt;
-	nvm_id->cgrps = nvme_nvm_id->cgrps;
 	nvm_id->cap = le32_to_cpu(nvme_nvm_id->cap);
 	nvm_id->dom = le32_to_cpu(nvme_nvm_id->dom);
 	memcpy(&nvm_id->ppaf, &nvme_nvm_id->ppaf,
@@ -372,7 +371,7 @@ static int nvme_nvm_get_l2p_tbl(struct nvm_dev *nvmdev, u64 slba, u32 nlb,
 		}
 
 		/* Transform physical address to target address space */
-		nvmdev->mt->part_to_tgt(nvmdev, entries, cmd_nlb);
+		nvm_part_to_tgt(nvmdev, entries, cmd_nlb);
 
 		if (update_l2p(cmd_slba, cmd_nlb, entries, priv)) {
 			ret = -EINTR;
@@ -485,7 +484,8 @@ static void nvme_nvm_end_io(struct request *rq, int error)
 	struct nvm_rq *rqd = rq->end_io_data;
 
 	rqd->ppa_status = nvme_req(rq)->result.u64;
-	nvm_end_io(rqd, error);
+	rqd->error = error;
+	nvm_end_io(rqd);
 
 	kfree(nvme_req(rq)->cmd);
 	blk_mq_free_request(rq);
@@ -586,6 +586,224 @@ static struct nvm_dev_ops nvme_nvm_dev_ops = {
 	.max_phys_sect		= 64,
 };
 
+static void nvme_nvm_end_user_vio(struct request *rq, int error)
+{
+	struct completion *waiting = rq->end_io_data;
+
+	complete(waiting);
+}
+
+static int nvme_nvm_submit_user_cmd(struct request_queue *q,
+				struct nvme_ns *ns,
+				struct nvme_nvm_command *vcmd,
+				void __user *ubuf, unsigned int bufflen,
+				void __user *meta_buf, unsigned int meta_len,
+				void __user *ppa_buf, unsigned int ppa_len,
+				u32 *result, u64 *status, unsigned int timeout)
+{
+	bool write = nvme_is_write((struct nvme_command *)vcmd);
+	struct nvm_dev *dev = ns->ndev;
+	struct gendisk *disk = ns->disk;
+	struct request *rq;
+	struct bio *bio = NULL;
+	__le64 *ppa_list = NULL;
+	dma_addr_t ppa_dma;
+	__le64 *metadata = NULL;
+	dma_addr_t metadata_dma;
+	DECLARE_COMPLETION_ONSTACK(wait);
+	int ret;
+
+	rq = nvme_alloc_request(q, (struct nvme_command *)vcmd, 0,
+			NVME_QID_ANY);
+	if (IS_ERR(rq)) {
+		ret = -ENOMEM;
+		goto err_cmd;
+	}
+
+	rq->timeout = timeout ? timeout : ADMIN_TIMEOUT;
+
+	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
+	rq->end_io_data = &wait;
+
+	if (ppa_buf && ppa_len) {
+		ppa_list = dma_pool_alloc(dev->dma_pool, GFP_KERNEL, &ppa_dma);
+		if (!ppa_list) {
+			ret = -ENOMEM;
+			goto err_rq;
+		}
+		if (copy_from_user(ppa_list, (void __user *)ppa_buf,
+						sizeof(u64) * (ppa_len + 1))) {
+			ret = -EFAULT;
+			goto err_ppa;
+		}
+		vcmd->ph_rw.spba = cpu_to_le64(ppa_dma);
+	} else {
+		vcmd->ph_rw.spba = cpu_to_le64((uintptr_t)ppa_buf);
+	}
+
+	if (ubuf && bufflen) {
+		ret = blk_rq_map_user(q, rq, NULL, ubuf, bufflen, GFP_KERNEL);
+		if (ret)
+			goto err_ppa;
+		bio = rq->bio;
+
+		if (meta_buf && meta_len) {
+			metadata = dma_pool_alloc(dev->dma_pool, GFP_KERNEL,
+								&metadata_dma);
+			if (!metadata) {
+				ret = -ENOMEM;
+				goto err_map;
+			}
+
+			if (write) {
+				if (copy_from_user(metadata,
+						(void __user *)meta_buf,
+						meta_len)) {
+					ret = -EFAULT;
+					goto err_meta;
+				}
+			}
+			vcmd->ph_rw.metadata = cpu_to_le64(metadata_dma);
+		}
+
+		if (!disk)
+			goto submit;
+
+		bio->bi_bdev = bdget_disk(disk, 0);
+		if (!bio->bi_bdev) {
+			ret = -ENODEV;
+			goto err_meta;
+		}
+	}
+
+submit:
+	blk_execute_rq_nowait(q, NULL, rq, 0, nvme_nvm_end_user_vio);
+
+	wait_for_completion_io(&wait);
+
+	ret = nvme_error_status(rq->errors);
+	if (result)
+		*result = rq->errors & 0x7ff;
+	if (status)
+		*status = le64_to_cpu(nvme_req(rq)->result.u64);
+
+	if (metadata && !ret && !write) {
+		if (copy_to_user(meta_buf, (void *)metadata, meta_len))
+			ret = -EFAULT;
+	}
+err_meta:
+	if (meta_buf && meta_len)
+		dma_pool_free(dev->dma_pool, metadata, metadata_dma);
+err_map:
+	if (bio) {
+		if (disk && bio->bi_bdev)
+			bdput(bio->bi_bdev);
+		blk_rq_unmap_user(bio);
+	}
+err_ppa:
+	if (ppa_buf && ppa_len)
+		dma_pool_free(dev->dma_pool, ppa_list, ppa_dma);
+err_rq:
+	blk_mq_free_request(rq);
+err_cmd:
+	return ret;
+}
+
+static int nvme_nvm_submit_vio(struct nvme_ns *ns,
+					struct nvm_user_vio __user *uvio)
+{
+	struct nvm_user_vio vio;
+	struct nvme_nvm_command c;
+	unsigned int length;
+	int ret;
+
+	if (copy_from_user(&vio, uvio, sizeof(vio)))
+		return -EFAULT;
+	if (vio.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.ph_rw.opcode = vio.opcode;
+	c.ph_rw.nsid = cpu_to_le32(ns->ns_id);
+	c.ph_rw.control = cpu_to_le16(vio.control);
+	c.ph_rw.length = cpu_to_le16(vio.nppas);
+
+	length = (vio.nppas + 1) << ns->lba_shift;
+
+	ret = nvme_nvm_submit_user_cmd(ns->queue, ns, &c,
+			(void __user *)(uintptr_t)vio.addr, length,
+			(void __user *)(uintptr_t)vio.metadata,
+							vio.metadata_len,
+			(void __user *)(uintptr_t)vio.ppa_list, vio.nppas,
+			&vio.result, &vio.status, 0);
+
+	if (ret && copy_to_user(uvio, &vio, sizeof(vio)))
+		return -EFAULT;
+
+	return ret;
+}
+
+static int nvme_nvm_user_vcmd(struct nvme_ns *ns, int admin,
+					struct nvm_passthru_vio __user *uvcmd)
+{
+	struct nvm_passthru_vio vcmd;
+	struct nvme_nvm_command c;
+	struct request_queue *q;
+	unsigned int timeout = 0;
+	int ret;
+
+	if (copy_from_user(&vcmd, uvcmd, sizeof(vcmd)))
+		return -EFAULT;
+	if ((vcmd.opcode != 0xF2) && (!capable(CAP_SYS_ADMIN)))
+		return -EACCES;
+	if (vcmd.flags)
+		return -EINVAL;
+
+	memset(&c, 0, sizeof(c));
+	c.common.opcode = vcmd.opcode;
+	c.common.nsid = cpu_to_le32(ns->ns_id);
+	c.common.cdw2[0] = cpu_to_le32(vcmd.cdw2);
+	c.common.cdw2[1] = cpu_to_le32(vcmd.cdw3);
+	/* cdw11-12 */
+	c.ph_rw.length = cpu_to_le16(vcmd.nppas);
+	c.ph_rw.control  = cpu_to_le32(vcmd.control);
+	c.common.cdw10[3] = cpu_to_le32(vcmd.cdw13);
+	c.common.cdw10[4] = cpu_to_le32(vcmd.cdw14);
+	c.common.cdw10[5] = cpu_to_le32(vcmd.cdw15);
+
+	if (vcmd.timeout_ms)
+		timeout = msecs_to_jiffies(vcmd.timeout_ms);
+
+	q = admin ? ns->ctrl->admin_q : ns->queue;
+
+	ret = nvme_nvm_submit_user_cmd(q, ns,
+			(struct nvme_nvm_command *)&c,
+			(void __user *)(uintptr_t)vcmd.addr, vcmd.data_len,
+			(void __user *)(uintptr_t)vcmd.metadata,
+							vcmd.metadata_len,
+			(void __user *)(uintptr_t)vcmd.ppa_list, vcmd.nppas,
+			&vcmd.result, &vcmd.status, timeout);
+
+	if (ret && copy_to_user(uvcmd, &vcmd, sizeof(vcmd)))
+		return -EFAULT;
+
+	return ret;
+}
+
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg)
+{
+	switch (cmd) {
+	case NVME_NVM_IOCTL_ADMIN_VIO:
+		return nvme_nvm_user_vcmd(ns, 1, (void __user *)arg);
+	case NVME_NVM_IOCTL_IO_VIO:
+		return nvme_nvm_user_vcmd(ns, 0, (void __user *)arg);
+	case NVME_NVM_IOCTL_SUBMIT_VIO:
+		return nvme_nvm_submit_vio(ns, (void __user *)arg);
+	default:
+		return -ENOTTY;
+	}
+}
+
 int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node)
 {
 	struct request_queue *q = ns->queue;
@@ -622,7 +840,7 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
 		return 0;
 
 	id = &ndev->identity;
-	grp = &id->groups[0];
+	grp = &id->grp;
 	attr = &dattr->attr;
 
 	if (strcmp(attr->name, "version") == 0) {
@@ -633,10 +851,9 @@ static ssize_t nvm_dev_attr_show(struct device *dev,
 		return scnprintf(page, PAGE_SIZE, "%u\n", id->cap);
 	} else if (strcmp(attr->name, "device_mode") == 0) {
 		return scnprintf(page, PAGE_SIZE, "%u\n", id->dom);
+	/* kept for compatibility */
 	} else if (strcmp(attr->name, "media_manager") == 0) {
-		if (!ndev->mt)
-			return scnprintf(page, PAGE_SIZE, "%s\n", "none");
-		return scnprintf(page, PAGE_SIZE, "%s\n", ndev->mt->name);
+		return scnprintf(page, PAGE_SIZE, "%s\n", "gennvm");
 	} else if (strcmp(attr->name, "ppa_format") == 0) {
 		return scnprintf(page, PAGE_SIZE,
 			"0x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x%02x\n",
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index aead6d08ed2c..14cfc6f7facb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -19,6 +19,7 @@
 #include <linux/kref.h>
 #include <linux/blk-mq.h>
 #include <linux/lightnvm.h>
+#include <linux/sed-opal.h>
 
 enum {
 	/*
@@ -125,6 +126,8 @@ struct nvme_ctrl {
 	struct list_head node;
 	struct ida ns_ida;
 
+	struct opal_dev *opal_dev;
+
 	char name[12];
 	char serial[20];
 	char model[40];
@@ -137,6 +140,7 @@ struct nvme_ctrl {
 	u32 max_hw_sectors;
 	u16 oncs;
 	u16 vid;
+	u16 oacs;
 	atomic_t abort_limit;
 	u8 event_limit;
 	u8 vwc;
@@ -267,6 +271,9 @@ int nvme_init_identify(struct nvme_ctrl *ctrl);
 void nvme_queue_scan(struct nvme_ctrl *ctrl);
 void nvme_remove_namespaces(struct nvme_ctrl *ctrl);
 
+int nvme_sec_submit(void *data, u16 spsp, u8 secp, void *buffer, size_t len,
+		bool send);
+
 #define NVME_NR_AERS	1
 void nvme_complete_async_event(struct nvme_ctrl *ctrl, __le16 status,
 		union nvme_result *res);
@@ -318,6 +325,7 @@ int nvme_nvm_register(struct nvme_ns *ns, char *disk_name, int node);
 void nvme_nvm_unregister(struct nvme_ns *ns);
 int nvme_nvm_register_sysfs(struct nvme_ns *ns);
 void nvme_nvm_unregister_sysfs(struct nvme_ns *ns);
+int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd, unsigned long arg);
 #else
 static inline int nvme_nvm_register(struct nvme_ns *ns, char *disk_name,
 				    int node)
@@ -335,6 +343,11 @@ static inline int nvme_nvm_ns_supported(struct nvme_ns *ns, struct nvme_id_ns *i
 {
 	return 0;
 }
+static inline int nvme_nvm_ioctl(struct nvme_ns *ns, unsigned int cmd,
+							unsigned long arg)
+{
+	return -ENOTTY;
+}
 #endif /* CONFIG_NVM */
 
 static inline struct nvme_ns *nvme_get_ns_from_dev(struct device *dev)
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 3faefabf339c..d67d0d0a3bc0 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -43,6 +43,7 @@
 #include <linux/types.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <asm/unaligned.h>
+#include <linux/sed-opal.h>
 
 #include "nvme.h"
 
@@ -895,12 +896,11 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req, bool reserved)
 		return BLK_EH_HANDLED;
 	}
 
-	iod->aborted = 1;
-
 	if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) {
 		atomic_inc(&dev->ctrl.abort_limit);
 		return BLK_EH_RESET_TIMER;
 	}
+	iod->aborted = 1;
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.abort.opcode = nvme_admin_abort_cmd;
@@ -1178,6 +1178,7 @@ static int nvme_alloc_admin_tags(struct nvme_dev *dev)
 		dev->admin_tagset.timeout = ADMIN_TIMEOUT;
 		dev->admin_tagset.numa_node = dev_to_node(dev->dev);
 		dev->admin_tagset.cmd_size = nvme_cmd_size(dev);
+		dev->admin_tagset.flags = BLK_MQ_F_NO_SCHED;
 		dev->admin_tagset.driver_data = dev;
 
 		if (blk_mq_alloc_tag_set(&dev->admin_tagset))
@@ -1738,6 +1739,7 @@ static void nvme_pci_free_ctrl(struct nvme_ctrl *ctrl)
 	if (dev->ctrl.admin_q)
 		blk_put_queue(dev->ctrl.admin_q);
 	kfree(dev->queues);
+	kfree(dev->ctrl.opal_dev);
 	kfree(dev);
 }
 
@@ -1754,6 +1756,7 @@ static void nvme_remove_dead_ctrl(struct nvme_dev *dev, int status)
 static void nvme_reset_work(struct work_struct *work)
 {
 	struct nvme_dev *dev = container_of(work, struct nvme_dev, reset_work);
+	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result = -ENODEV;
 
 	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
@@ -1786,6 +1789,14 @@ static void nvme_reset_work(struct work_struct *work)
 	if (result)
 		goto out;
 
+	if ((dev->ctrl.oacs & NVME_CTRL_OACS_SEC_SUPP) && !dev->ctrl.opal_dev) {
+		dev->ctrl.opal_dev =
+			init_opal_dev(&dev->ctrl, &nvme_sec_submit);
+	}
+
+	if (was_suspend)
+		opal_unlock_from_suspend(dev->ctrl.opal_dev);
+
 	result = nvme_setup_io_queues(dev);
 	if (result)
 		goto out;