Add Support of devices that follow the NVM Express standard

basic functions: nvme init/scan nvme info - show the basic information of device nvme Read/Write

driver model: Use block device(CONFIG_BLK)'s structure to support nvme's DM. Use UCLASS_PCI as a parent uclass.

The driver code heavily copy from the NVMe driver code in Linux Kernel.

Signed-off-by: Zhikang Zhang zhikang.zhang@nxp.com Signed-off-by: Wenbin Song wenbin.song@nxp.com --- common/Makefile | 1 + common/board_r.c | 13 + common/nvme.c | 127 ++++++ doc/README.nvme | 17 + drivers/block/Kconfig | 16 + drivers/block/Makefile | 1 + drivers/block/blk-uclass.c | 2 + drivers/block/nvme.c | 1048 ++++++++++++++++++++++++++++++++++++++++++++ drivers/block/nvme.h | 114 +++++ drivers/block/nvme_uapi.h | 570 ++++++++++++++++++++++++ include/blk.h | 1 + include/nvme.h | 50 +++ 12 files changed, 1960 insertions(+) create mode 100644 common/nvme.c create mode 100644 doc/README.nvme create mode 100644 drivers/block/nvme.c create mode 100644 drivers/block/nvme.h create mode 100644 drivers/block/nvme_uapi.h create mode 100644 include/nvme.h

diff --git a/common/Makefile b/common/Makefile index ecc23e6..70c539b 100644 --- a/common/Makefile +++ b/common/Makefile @@ -81,6 +81,7 @@ obj-$(CONFIG_LCD_DT_SIMPLEFB) += lcd_simplefb.o obj-$(CONFIG_LYNXKDI) += lynxkdi.o obj-$(CONFIG_MENU) += menu.o obj-$(CONFIG_CMD_SATA) += sata.o +obj-$(CONFIG_NVME) += nvme.o obj-$(CONFIG_SCSI) += scsi.o obj-$(CONFIG_UPDATE_TFTP) += update.o obj-$(CONFIG_DFU_TFTP) += update.o diff --git a/common/board_r.c b/common/board_r.c index 48fa4ee..843f4e5 100644 --- a/common/board_r.c +++ b/common/board_r.c @@ -49,6 +49,7 @@ #include <timer.h> #include <trace.h> #include <watchdog.h> +#include <nvme.h> #ifdef CONFIG_CMD_AMBAPP #include <ambapp.h> #endif @@ -458,6 +459,15 @@ static int initr_dataflash(void) } #endif

+#ifdef CONFIG_NVME +static int initr_nvme(void) +{ + puts("NVMe: "); + nvme_initialize(); + return 0; +} +#endif + /* * Tell if it's OK to load the environment early in boot. * @@ -942,6 +952,9 @@ init_fnc_t init_sequence_r[] = { #if defined(CONFIG_SPARC) prom_init, #endif +#ifdef CONFIG_NVME + initr_nvme, +#endif run_main_loop, };

diff --git a/common/nvme.c b/common/nvme.c new file mode 100644 index 0000000..ed3250f --- /dev/null +++ b/common/nvme.c @@ -0,0 +1,127 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#include <common.h> +#include <dm.h> +#include <nvme.h> + +struct blk_desc nvme_dev_desc[CONFIG_SYS_NVME_MAX_DEVICE]; + +struct pci_device_id nvme_supported[] = { + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0953) }, + {} +}; +#ifdef CONFIG_PARTITIONS +struct blk_desc *nvme_get_dev(int dev) +{ + return (dev < CONFIG_SYS_NVME_MAX_DEVICE) ? &nvme_dev_desc[dev] : NULL; +} +#endif + +#ifdef CONFIG_BLK +struct udevice *udev; +static unsigned long nvme_bread(struct udevice *dev, lbaint_t start, + lbaint_t blkcnt, void *dst) +{ + return nvme_read(dev, start, blkcnt, dst); +} + +static unsigned long nvme_bwrite(struct udevice *dev, lbaint_t start, + lbaint_t blkcnt, const void *buffer) +{ + return nvme_write(dev, start, blkcnt, buffer); +} +#else +static unsigned long nvme_bread(struct blk_desc *block_dev, lbaint_t start, + lbaint_t blkcnt, void *dst) +{ + return nvme_read(block_dev->devnum, start, blkcnt, dst); +} + +static unsigned long nvme_bwrite(struct blk_desc *block_dev, lbaint_t start, + lbaint_t blkcnt, const void *buffer) +{ + return nvme_write(block_dev->devnum, start, blkcnt, buffer); +} +#endif + +int __nvme_initialize(void) +{ + int rc, ret = -1; + int i; + + for (i = 0; i < CONFIG_SYS_NVME_MAX_DEVICE; i++) { +#ifdef CONFIG_BLK + rc = init_nvme(udev); + if (!rc) + rc = scan_nvme(udev); +#else + rc = init_nvme(i); + if (!rc) + rc = scan_nvme(i); +#endif + + if (!rc && nvme_dev_desc[i].lba > 0) { + nvme_dev_desc[i].if_type = IF_TYPE_NVME; + nvme_dev_desc[i].devnum = i; + nvme_dev_desc[i].part_type = PART_TYPE_UNKNOWN; + nvme_dev_desc[i].type = DEV_TYPE_HARDDISK; +#ifndef CONFIG_BLK + nvme_dev_desc[i].block_read = nvme_bread; + nvme_dev_desc[i].block_write = nvme_bwrite; +#endif + + part_init(&nvme_dev_desc[i]); + ret = i; + } else { + memset(&nvme_dev_desc[i], 0, sizeof(struct blk_desc)); + } + printf("devnum: %d Vendor: %s Prod: %s\n", + i, + nvme_dev_desc[i].vendor, + nvme_dev_desc[i].product); + } + return ret; +} +int nvme_initialize(void) __attribute__((weak, alias("__nvme_initialize"))); + +#ifdef CONFIG_BLK +static void nvme_name(char *str, int cardnum) +{ + sprintf(str, "nvme#%u", cardnum); +} + +static int nvme_bind(struct udevice *dev) +{ + udev = dev; + int num_cards = 0; + char name[20]; + nvme_name(name, num_cards++); + + return device_set_name(udev, name); +} + +static const struct blk_ops nvme_ops = { + .read = nvme_bread, + .write = nvme_bwrite, +}; + +U_BOOT_DRIVER(nvme) = { + .name = "nvme", + .id = UCLASS_BLK, + .bind = nvme_bind, + .ops = &nvme_ops, + .priv_auto_alloc_size = sizeof(struct nvme_ns), +}; +U_BOOT_PCI_DEVICE(nvme, nvme_supported); +#else +U_BOOT_LEGACY_BLK(nvme) = { + .if_typename = "nvme", + .if_type = IF_TYPE_NVME, + .max_devs = CONFIG_SYS_NVME_MAX_DEVICE, + .desc = nvme_dev_desc, +}; +#endif diff --git a/doc/README.nvme b/doc/README.nvme new file mode 100644 index 0000000..892e0fb --- /dev/null +++ b/doc/README.nvme @@ -0,0 +1,17 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +1. NVMe Config Switches: + +CONFIG_NVME enables basic NVMe device support + NVMe is a basic device which mounted on PCIe bus, + so is depends on CONFIG_PCI. +CONFIG_SYS_NVME_MAX_DEVICE configs the max num of NVMe devices + +2. Driver Model Support: + +Use block device(CONFIG_BLK)'s structure to support nvme's DM. +Use UCLASS_PCI as a parent uclass. diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 88e66e2..665d471 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -49,3 +49,19 @@ config SATA_CEVA AHCI 1.3 specifications with hot-plug detect feature.

endmenu + +config NVME + bool "Support NVMe devices" + depends on PCI + help + This option enables supporting for all NVMe devices. + It supports the basic functions before using NVMe devices + such as "nvme init" "nvme scan" and R/W. + It also contains other functions to use the devices. + +config SYS_NVME_MAX_DEVICE + int "Config the Max Num of NVMe Devices" + depends on NVME + default 1 + help + Set the max num of NVMe Devices. diff --git a/drivers/block/Makefile b/drivers/block/Makefile index a72feec..65d4bde 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -31,3 +31,4 @@ obj-$(CONFIG_SANDBOX) += sandbox.o sandbox_scsi.o sata_sandbox.o obj-$(CONFIG_SCSI_SYM53C8XX) += sym53c8xx.o obj-$(CONFIG_SYSTEMACE) += systemace.o obj-$(CONFIG_BLOCK_CACHE) += blkcache.o +obj-$(CONFIG_NVME) += nvme.o diff --git a/drivers/block/blk-uclass.c b/drivers/block/blk-uclass.c index 38cb938..25e3d90 100644 --- a/drivers/block/blk-uclass.c +++ b/drivers/block/blk-uclass.c @@ -22,6 +22,7 @@ static const char *if_typename_str[IF_TYPE_COUNT] = { [IF_TYPE_SATA] = "sata", [IF_TYPE_HOST] = "host", [IF_TYPE_SYSTEMACE] = "ace", + [IF_TYPE_NVME] = "nvme", };

static enum uclass_id if_type_uclass_id[IF_TYPE_COUNT] = { @@ -34,6 +35,7 @@ static enum uclass_id if_type_uclass_id[IF_TYPE_COUNT] = { [IF_TYPE_SD] = UCLASS_INVALID, [IF_TYPE_SATA] = UCLASS_AHCI, [IF_TYPE_HOST] = UCLASS_ROOT, + [IF_TYPE_NVME] = UCLASS_PCI, [IF_TYPE_SYSTEMACE] = UCLASS_INVALID, };

diff --git a/drivers/block/nvme.c b/drivers/block/nvme.c new file mode 100644 index 0000000..2e06477 --- /dev/null +++ b/drivers/block/nvme.c @@ -0,0 +1,1048 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#include <common.h> +#include <errno.h> +#include <linux/compat.h> +#include <dm.h> +#include <pci.h> +#include <memalign.h> +#include <linux/err.h> +#include <linux/ioport.h> +#include <console.h> +#include <asm/armv8/mmu.h> +#include "nvme.h" + +#define NVME_Q_DEPTH 2 +#define NVME_AQ_DEPTH 2 +#define SQ_SIZE(depth) (depth * sizeof(struct nvme_command)) +#define CQ_SIZE(depth) (depth * sizeof(struct nvme_completion)) +#define ADMIN_TIMEOUT 60 +#define MAX_PRP_POOL 512 + +static struct nvme_info nvme_info = {.maxport = 0, .idx = 0, + .dev_list = LIST_HEAD_INIT(nvme_info.dev_list)}; + +/* + *An NVM Express queue. Each device has at least two(one for admin + *commands and one for I/O commands). + */ +struct nvme_queue { + struct nvme_dev *dev; + struct nvme_command *sq_cmds; + struct nvme_completion *cqes; + wait_queue_head_t sq_full; + u32 __iomem *q_db; + u16 q_depth; + s16 cq_vector; + u16 sq_head; + u16 sq_tail; + u16 cq_head; + u16 qid; + u8 cq_phase; + u8 cqe_seen; + unsigned long cmdid_data[]; +}; + +static int nvme_wait_ready(struct nvme_dev *dev, u64 cap, bool enabled) +{ + u32 bit = enabled ? NVME_CSTS_RDY : 0; + while ((readl(&dev->bar->csts) & NVME_CSTS_RDY) != bit) + udelay(10000); + + return 0; +} + +static int nvme_setup_prps(struct nvme_dev *dev, u64 *prp2, + int total_len, u64 dma_addr) +{ + u32 page_size = dev->page_size; + int offset = dma_addr & (page_size - 1); + u64 *prp_pool; + int length = total_len; + int i, nprps; + length -= (page_size - offset); + + if (length <= 0) { + *prp2 = 0; + return 0; + } + + if (length) + dma_addr += (page_size - offset); + + if (length <= page_size) { + *prp2 = dma_addr; + return 0; + } + + nprps = DIV_ROUND_UP(length, page_size); + + if (nprps > dev->prp_entry_num) { + free(dev->prp_pool); + dev->prp_pool = malloc(nprps << 3); + if (!dev->prp_pool) { + printf("Error: malloc prp_pool fail\n"); + return -ENOMEM; + } + dev->prp_entry_num = nprps; + } + prp_pool = dev->prp_pool; + i = 0; + while (nprps) { + if (i == ((page_size >> 3) - 1)) { + *(prp_pool + i) = cpu_to_le64((u64)prp_pool + + page_size); + i = 0; + prp_pool += page_size; + } + *(prp_pool + i++) = cpu_to_le64(dma_addr); + dma_addr += page_size; + nprps--; + } + *prp2 = (u64)dev->prp_pool; + return 0; +} + +static __le16 get_cmdid(void) +{ + static unsigned short cmdid; + return cpu_to_le16((cmdid < USHRT_MAX) ? cmdid++ : 0); +} + +static u16 read_completion_status(struct nvme_queue *nvmeq, u16 index) +{ + u64 start = (u64)&nvmeq->cqes[index]; + u64 stop = start + sizeof(struct nvme_completion); + invalidate_dcache_range(start, stop); + return le16_to_cpu(readw(&(nvmeq->cqes[index].status))); +} + +/** + * nvme_submit_cmd() - Copy a command into a queue and ring the doorbell + * @nvmeq: The queue to use + * @cmd: The command to send + * + * Safe to use from interrupt context + */ +static int nvme_submit_cmd(struct nvme_queue *nvmeq, struct nvme_command *cmd) +{ + u16 tail = nvmeq->sq_tail; + flush_dcache_all(); + memcpy(&nvmeq->sq_cmds[tail], cmd, sizeof(*cmd)); + flush_dcache_range((ulong)&nvmeq->sq_cmds[tail], + (ulong)&nvmeq->sq_cmds[tail] + sizeof(*cmd)); + if (++tail == nvmeq->q_depth) + tail = 0; + writel(tail, nvmeq->q_db); + nvmeq->sq_tail = tail; + + return 0; +} + +static int nvme_submit_sync_cmd(struct nvme_queue *nvmeq, + struct nvme_command *cmd, u32 *result, unsigned timeout) +{ + u16 head = nvmeq->cq_head; + u16 phase = nvmeq->cq_phase; + u16 status; + ulong start_time; + ulong timeout_us = timeout * 100000; + + cmd->common.command_id = get_cmdid(); + nvme_submit_cmd(nvmeq, cmd); + + start_time = timer_get_us(); + + for (;;) { + status = read_completion_status(nvmeq, head); + if ((status & 0x01) == phase) + break; + if (timeout_us > 0 && (timer_get_us() - start_time) + >= timeout_us) + return -ETIMEDOUT; + } + status >>= 1; + if (status) { + printf("ERROR: status = %d, phase = %d, head = %d\n", + status, phase, head); + status = 0; + if (++head == nvmeq->q_depth) { + head = 0; + phase = !phase; + } + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); + nvmeq->cq_head = head; + nvmeq->cq_phase = phase; + return -1; + } + + if (result) + *result = le32_to_cpu(readl(&(nvmeq->cqes[head].result))); + + if (++head == nvmeq->q_depth) { + head = 0; + phase = !phase; + } + writel(head, nvmeq->q_db + nvmeq->dev->db_stride); + nvmeq->cq_head = head; + nvmeq->cq_phase = phase; + + return status; +} + +static int nvme_submit_admin_cmd(struct nvme_dev *dev, + struct nvme_command *cmd, u32 *result) +{ + return nvme_submit_sync_cmd(dev->queues[0], cmd, result, ADMIN_TIMEOUT); +} + +static struct nvme_queue *nvme_alloc_queue(struct nvme_dev *dev, + int qid, int depth) +{ + struct nvme_queue *nvmeq = malloc(sizeof(*nvmeq)); + if (!nvmeq) + return NULL; + memset(nvmeq, 0, sizeof(*nvmeq)); + + nvmeq->cqes = (void *)memalign(4096, CQ_SIZE(depth)); + if (!nvmeq->cqes) + goto free_nvmeq; + memset((void *)nvmeq->cqes, 0, CQ_SIZE(depth)); + + nvmeq->sq_cmds = (void *)memalign(4096, SQ_SIZE(depth)); + if (!nvmeq->sq_cmds) + goto free_queue; + memset((void *)nvmeq->sq_cmds, 0, SQ_SIZE(depth)); + + nvmeq->dev = dev; + + nvmeq->cq_head = 0; + nvmeq->cq_phase = 1; + nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; + nvmeq->q_depth = depth; + nvmeq->qid = qid; + dev->queue_count++; + dev->queues[qid] = nvmeq; + + return nvmeq; + free_queue: + free((void *)nvmeq->cqes); + free_nvmeq: + free(nvmeq); + return NULL; +} + +static int adapter_delete_queue(struct nvme_dev *dev, u8 opcode, u16 id) +{ + struct nvme_command c; + memset(&c, 0, sizeof(c)); + c.delete_queue.opcode = opcode; + c.delete_queue.qid = cpu_to_le16(id); + return nvme_submit_admin_cmd(dev, &c, NULL); +} + +static int adapter_delete_sq(struct nvme_dev *dev, u16 sqid) +{ + return adapter_delete_queue(dev, nvme_admin_delete_sq, sqid); +} + +static int adapter_delete_cq(struct nvme_dev *dev, u16 cqid) +{ + return adapter_delete_queue(dev, nvme_admin_delete_cq, cqid); +} + +static int nvme_enable_ctrl(struct nvme_dev *dev, u64 cap) +{ + dev->ctrl_config &= ~NVME_CC_SHN_MASK; + dev->ctrl_config |= NVME_CC_ENABLE; + writel(cpu_to_le32(dev->ctrl_config), &dev->bar->cc); + return nvme_wait_ready(dev, cap, true); +} + +static int nvme_disable_ctrl(struct nvme_dev *dev, u64 cap) +{ + dev->ctrl_config &= ~NVME_CC_SHN_MASK; + dev->ctrl_config &= ~NVME_CC_ENABLE; + writel(cpu_to_le32(dev->ctrl_config), &dev->bar->cc); + return nvme_wait_ready(dev, cap, false); +} + +static void nvme_free_queue(struct nvme_queue *nvmeq) +{ + free((void *)nvmeq->cqes); + free(nvmeq->sq_cmds); + free(nvmeq); +} + +static void nvme_free_queues(struct nvme_dev *dev, int lowest) +{ + int i; + for (i = dev->queue_count - 1; i >= lowest; i--) { + struct nvme_queue *nvmeq = dev->queues[i]; + dev->queue_count--; + dev->queues[i] = NULL; + nvme_free_queue(nvmeq); + } +} + +static void nvme_init_queue(struct nvme_queue *nvmeq, u16 qid) +{ + struct nvme_dev *dev = nvmeq->dev; + nvmeq->sq_tail = 0; + nvmeq->cq_head = 0; + nvmeq->cq_phase = 1; + nvmeq->q_db = &dev->dbs[qid * 2 * dev->db_stride]; + memset((void *)nvmeq->cqes, 0, CQ_SIZE(nvmeq->q_depth)); + flush_dcache_range((u64)nvmeq->cqes, + (u64)nvmeq->cqes + CQ_SIZE(nvmeq->q_depth)); + dev->online_queues++; +} + +static int nvme_configure_admin_queue(struct nvme_dev *dev) +{ + int result; + u32 aqa; + u64 cap = readq(&dev->bar->cap); + struct nvme_queue *nvmeq; + unsigned page_shift = PAGE_SHIFT; + unsigned dev_page_min = NVME_CAP_MPSMIN(cap) + 12; + unsigned dev_page_max = NVME_CAP_MPSMAX(cap) + 12; + if (page_shift < dev_page_min) { + dev_err(&dev->pci_dev->dev, + "Minimum device page size (%u) too large for host (%u)\n", + 1 << dev_page_min, + 1 << page_shift); + return -ENODEV; + } + + if (page_shift > dev_page_max) { + dev_info(&dev->pci_dev->dev, + "Device maximum page size (%u) smaller than host (%u); enabling work-around\n", + 1 << dev_page_max, + 1 << page_shift); + page_shift = dev_page_max; + } + + result = nvme_disable_ctrl(dev, cap); + if (result < 0) + return result; + + nvmeq = dev->queues[0]; + if (!nvmeq) { + nvmeq = nvme_alloc_queue(dev, 0, NVME_AQ_DEPTH); + if (!nvmeq) + return -ENOMEM; + } + + aqa = nvmeq->q_depth - 1; + aqa |= aqa << 16; + aqa |= aqa << 16; + + dev->page_size = 1 << page_shift; + + dev->ctrl_config = NVME_CC_CSS_NVM; + dev->ctrl_config |= (page_shift - 12) << NVME_CC_MPS_SHIFT; + dev->ctrl_config |= NVME_CC_ARB_RR | NVME_CC_SHN_NONE; + dev->ctrl_config |= NVME_CC_IOSQES | NVME_CC_IOCQES; + + writel(aqa, &dev->bar->aqa); + writeq((u64)nvmeq->sq_cmds, &dev->bar->asq); + writeq((u64)nvmeq->cqes, &dev->bar->acq); + + result = nvme_enable_ctrl(dev, cap); + if (result) + goto free_nvmeq; + + nvmeq->cq_vector = 0; + + nvme_init_queue(dev->queues[0], 0); + return result; + + free_nvmeq: + nvme_free_queues(dev, 0); + return result; +} + +static int adapter_alloc_cq(struct nvme_dev *dev, + u16 qid, struct nvme_queue *nvmeq) +{ + struct nvme_command c; + int flags = NVME_QUEUE_PHYS_CONTIG | NVME_CQ_IRQ_ENABLED; + memset(&c, 0, sizeof(c)); + c.create_cq.opcode = nvme_admin_create_cq; + c.create_cq.prp1 = cpu_to_le64(nvmeq->cqes); + c.create_cq.cqid = cpu_to_le16(qid); + c.create_cq.qsize = cpu_to_le16(nvmeq->q_depth - 1); + c.create_cq.cq_flags = cpu_to_le16(flags); + c.create_cq.irq_vector = cpu_to_le16(nvmeq->cq_vector); + + return nvme_submit_admin_cmd(dev, &c, NULL); +} + +static int adapter_alloc_sq(struct nvme_dev *dev, + u16 qid, struct nvme_queue *nvmeq) +{ + struct nvme_command c; + int flags = NVME_QUEUE_PHYS_CONTIG | NVME_SQ_PRIO_MEDIUM; + memset(&c, 0, sizeof(c)); + c.create_sq.opcode = nvme_admin_create_sq; + c.create_sq.prp1 = cpu_to_le64(nvmeq->sq_cmds); + c.create_sq.sqid = cpu_to_le16(qid); + c.create_sq.qsize = cpu_to_le16(nvmeq->q_depth - 1); + c.create_sq.sq_flags = cpu_to_le16(flags); + c.create_sq.cqid = cpu_to_le16(qid); + + return nvme_submit_admin_cmd(dev, &c, NULL); +} + +static int nvme_identify(struct nvme_dev *dev, unsigned nsid, + unsigned cns, dma_addr_t dma_addr) +{ + struct nvme_command c; + memset(&c, 0, sizeof(c)); + u32 page_size = dev->page_size; + int offset = dma_addr & (page_size - 1); + int length = sizeof(struct nvme_id_ctrl); + + c.identify.opcode = nvme_admin_identify; + c.identify.nsid = cpu_to_le32(nsid); + c.identify.prp1 = cpu_to_le64(dma_addr); + + length -= (page_size - offset); + if (length <= 0) { + c.identify.prp2 = 0; + } else { + dma_addr += (page_size - offset); + c.identify.prp2 = dma_addr; + } + + c.identify.cns = cpu_to_le32(cns); + + return nvme_submit_admin_cmd(dev, &c, NULL); +} + +static __maybe_unused int nvme_get_features(struct nvme_dev *dev, unsigned fid, + unsigned nsid, dma_addr_t dma_addr, u32 *result) +{ + struct nvme_command c; + memset(&c, 0, sizeof(c)); + + c.features.opcode = nvme_admin_get_features; + c.features.nsid = cpu_to_le32(nsid); + c.features.prp1 = cpu_to_le64(dma_addr); + c.features.fid = cpu_to_le32(fid); + + return nvme_submit_admin_cmd(dev, &c, result); +} + +static __maybe_unused int nvme_set_features(struct nvme_dev *dev, unsigned fid, + unsigned dword11, dma_addr_t dma_addr, u32 *result) +{ + struct nvme_command c; + memset(&c, 0, sizeof(c)); + + c.features.opcode = nvme_admin_set_features; + c.features.prp1 = cpu_to_le64(dma_addr); + c.features.fid = cpu_to_le32(fid); + c.features.dword11 = cpu_to_le32(dword11); + + return nvme_submit_admin_cmd(dev, &c, result); +} + +static int nvme_create_queue(struct nvme_queue *nvmeq, int qid) +{ + struct nvme_dev *dev = nvmeq->dev; + int result; + + nvmeq->cq_vector = qid - 1; + result = adapter_alloc_cq(dev, qid, nvmeq); + if (result < 0) + goto release_cq; + + result = adapter_alloc_sq(dev, qid, nvmeq); + if (result < 0) + goto release_sq; + + nvme_init_queue(nvmeq, qid); + return result; + + release_sq: + adapter_delete_sq(dev, qid); + release_cq: + adapter_delete_cq(dev, qid); + return result; +} + +static int set_queue_count(struct nvme_dev *dev, int count) +{ + int status; + u32 result; + u32 q_count = (count - 1) | ((count - 1) << 16); + + status = nvme_set_features(dev, NVME_FEAT_NUM_QUEUES, + q_count, 0, &result); + + if (status < 0) + return status; + if (status > 1) + return 0; + + return min(result & 0xffff, result >> 16) + 1; +} + +static void nvme_create_io_queues(struct nvme_dev *dev) +{ + unsigned int i; + + for (i = dev->queue_count; i <= dev->max_qid; i++) + if (!nvme_alloc_queue(dev, i, dev->q_depth)) + break; + + for (i = dev->online_queues; i <= dev->queue_count - 1; i++) + if (nvme_create_queue(dev->queues[i], i)) + break; +} + +static int nvme_setup_io_queues(struct nvme_dev *dev) +{ + int nr_io_queues; + int result; + nr_io_queues = 1; + result = set_queue_count(dev, nr_io_queues); + if (result <= 0) + return result; + + if (result < nr_io_queues) + nr_io_queues = result; + + dev->max_qid = nr_io_queues; + + /* Free previously allocated queues*/ + nvme_free_queues(dev, nr_io_queues + 1); + nvme_create_io_queues(dev); + + return 0; +} + +static int nvme_get_info_from_identify(struct nvme_dev *dev) +{ + u16 vendor, device; + struct nvme_id_ctrl buf, *ctrl = &buf; + int ret; + int shift = NVME_CAP_MPSMIN(readq(&dev->bar->cap)) + 12; + + ret = nvme_identify(dev, 0, 1, (dma_addr_t)ctrl); + if (ret) { + printf("Error: nvme%d get identify error\n", dev->instance); + return -EIO; + } + + dev->nn = le32_to_cpu(ctrl->nn); + dev->vwc = ctrl->vwc; + memcpy(dev->serial, ctrl->sn, sizeof(ctrl->sn)); + memcpy(dev->model, ctrl->mn, sizeof(ctrl->mn)); + memcpy(dev->firmware_rev, ctrl->fr, sizeof(ctrl->fr)); + if (ctrl->mdts) + dev->max_transfer_shift = (ctrl->mdts + shift); + +#ifdef CONFIG_BLK + dm_pci_read_config16(dev->pdev, PCI_VENDOR_ID, &vendor); + dm_pci_read_config16(dev->pdev, PCI_DEVICE_ID, &device); +#else + pci_read_config_word(dev->pci_dev, PCI_VENDOR_ID, &vendor); + pci_read_config_word(dev->pci_dev, PCI_DEVICE_ID, &device); +#endif + if ((vendor == PCI_VENDOR_ID_INTEL) && + (device == 0x0953) && ctrl->vs[3]) { + unsigned int max_transfer_shift; + dev->stripe_size = (ctrl->vs[3] + shift); + max_transfer_shift = (ctrl->vs[3] + 18); + if (dev->max_transfer_shift) { + dev->max_transfer_shift = min(max_transfer_shift, + dev->max_transfer_shift); + } else { + dev->max_transfer_shift = max_transfer_shift; + } + } + return 0; +} + +#ifdef CONFIG_BLK +int init_nvme(struct udevice *udev) +#else +int init_nvme(int devnum) +#endif +{ + static int init_done; + pci_dev_t pci_dev; + int ret; +#ifdef CONFIG_BLK + struct nvme_ns *ns = dev_get_priv(udev); + struct nvme_dev *dev = ns->dev; + int devnum = trailing_strtol(udev->name); +#else + struct nvme_dev *dev; +#endif + u32 val; + u64 cap; + + if (init_done == 1 && devnum < nvme_info.maxport) { + printf("devnum = %d\n", devnum); + return 0; + } + + pci_dev = pci_find_devices(nvme_supported, nvme_info.idx++); + if (pci_dev == -1) { + printf("Error: can't find pci device "nvme%d"\n", + nvme_info.idx - 1); + return -ENODEV; + } + + dev = malloc(sizeof(*dev)); + if (dev == NULL) { + printf("Error: nvme%d: Out of Memory!\n", nvme_info.idx - 1); + return -ENOMEM; + } + memset(dev, 0, sizeof(*dev)); + + dev->instance = nvme_info.idx - 1; + INIT_LIST_HEAD(&dev->namespaces); +#ifdef CONFIG_BLK + dev->pdev = udev; + dev->bar = dm_pci_map_bar(udev, PCI_BASE_ADDRESS_0, + PCI_REGION_MEM); +#else + dev->pci_dev = pci_dev; + dev->bar = pci_map_bar(dev->pci_dev, PCI_BASE_ADDRESS_0, + PCI_REGION_MEM); +#endif + if (readl(&dev->bar->csts) == -1) { + ret = -ENODEV; + printf("Error: nvme%d: Out of Memory!\n", nvme_info.idx - 1); + goto free_nvme; + } + + dev->queues = malloc(2 * sizeof(struct nvme_queue)); + if (!dev->queues) { + ret = -ENOMEM; + printf("Error: nvme%d: Out of Memory!\n", dev->instance); + goto free_nvme; + } + memset(dev->queues, 0, sizeof(2 * sizeof(struct nvme_queue))); + + dev->prp_pool = malloc(MAX_PRP_POOL); + if (!dev->prp_pool) { + ret = -ENOMEM; + printf("Error: nvme%d: Out of Memory!\n", dev->instance); + goto free_nvme; + } + dev->prp_entry_num = MAX_PRP_POOL >> 3; + + /* Try to enable I/O accesses and bus-mastering */ + val = PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; +#ifdef CONFIG_BLK + dm_pci_write_config32(udev, PCI_COMMAND, val); +#else + pci_write_config_dword(dev->pci_dev, PCI_COMMAND, val); +#endif + + /* Print a debug message with the IO base address */ +#ifdef CONFIG_BLK + dm_pci_read_config32(udev, PCI_BASE_ADDRESS_0, &val); +#else + pci_read_config_dword(dev->pci_dev, PCI_BASE_ADDRESS_0, &val); +#endif + + /* Make sure it worked */ +#ifdef CONFIG_BLK + dm_pci_read_config32(udev, PCI_COMMAND, &val); +#else + pci_read_config_dword(dev->pci_dev, PCI_COMMAND, &val); +#endif + if (!(val & PCI_COMMAND_MEMORY)) { + printf("Can't enable I/O memory\n"); + ret = -ENOSPC; + goto free_queue; + } + if (!(val & PCI_COMMAND_MASTER)) { + printf("Can't enable bus-mastering\n"); + ret = -EPERM; + goto free_queue; + } + if (readl(&dev->bar->csts) == -1) { + ret = -ENODEV; + goto free_queue; + } + + cap = readq(&dev->bar->cap); + dev->q_depth = min_t(int, NVME_CAP_MQES(cap) + 1, NVME_Q_DEPTH); + dev->db_stride = 1 << NVME_CAP_STRIDE(cap); + dev->dbs = ((void __iomem *)dev->bar) + 4096; + + ret = nvme_configure_admin_queue(dev); + if (ret) + goto free_queue; + + ret = nvme_setup_io_queues(dev); + if (ret) + goto free_queue; + + nvme_get_info_from_identify(dev); + dev->blk_dev_start = nvme_info.maxport; + list_add(&dev->node, &nvme_info.dev_list); + + nvme_info.maxport += dev->nn; + init_done = 1; + return 0; + free_queue: + free((void *)dev->queues); + free_nvme: + free((void *)dev); + return ret; +} + +static struct nvme_dev *find_dev_by_devnum(int devnum) +{ + struct nvme_dev *dev; + list_for_each_entry(dev, &nvme_info.dev_list, node) { + if ((devnum >= dev->blk_dev_start) && + (devnum < dev->blk_dev_start + dev->nn)) + return dev; + } + return NULL; +} + +static struct nvme_ns *find_ns_by_devnum(int devnum) +{ + struct nvme_dev *dev; + struct nvme_ns *ns; + + dev = find_dev_by_devnum(devnum); + if (!dev) + return NULL; + + list_for_each_entry(ns, &dev->namespaces, list) { + if (devnum == ns->devnum) + return ns; + } + return NULL; +} + +#ifdef CONFIG_BLK +int scan_nvme(struct udevice *udev) +{ + struct nvme_ns *ns = dev_get_priv(udev); + struct nvme_dev *dev = ns->dev; + int devnum = trailing_strtol(udev->name); +#else +int scan_nvme(int devnum) +{ + struct nvme_ns *ns; + struct nvme_dev *dev; +#endif + int ret; + u8 flbas; + u16 vendor; + char vendor_c[8]; + struct nvme_id_ns buf, *id = &buf; + + if (devnum > nvme_info.maxport) { + printf("Error: devnum %d is not initialized\n", devnum); + return -ENODEV; + } + + dev = find_dev_by_devnum(devnum); + if (!dev) + return -ENODEV; + + ns = find_ns_by_devnum(devnum); + if (ns) + return 0; + + ns = malloc(sizeof(*ns)); + if (!ns) + return -ENOMEM; + memset(ns, 0, sizeof(*ns)); + ns->dev = dev; + ns->ns_id = devnum - dev->blk_dev_start + 1; + ns->devnum = devnum; + if (nvme_identify(dev, ns->ns_id, 0, (dma_addr_t)id)) { + ret = -EIO; + goto free_ns; + } + flbas = id->flbas & NVME_NS_FLBAS_LBA_MASK; + ns->flbas = flbas; + ns->lba_shift = id->lbaf[flbas].ds; + ns->mode_select_num_blocks = le64_to_cpu(id->nuse); + ns->mode_select_block_len = 1 << ns->lba_shift; + list_add(&ns->list, &dev->namespaces); + nvme_dev_desc[devnum].lba = ns->mode_select_num_blocks; + nvme_dev_desc[devnum].log2blksz = ns->lba_shift; + nvme_dev_desc[devnum].blksz = 1 << ns->lba_shift; +#ifdef CONFIG_BLK + nvme_dev_desc[devnum].bdev = dev->pdev; + dm_pci_read_config16(dev->pdev, PCI_VENDOR_ID, &vendor); + udev->priv = ns; + udev->uclass_platdata = (void *)&nvme_dev_desc[devnum]; +#else + nvme_dev_desc[devnum].priv = (void *)ns; + pci_read_config_word(dev->pci_dev, PCI_VENDOR_ID, &vendor); +#endif + sprintf(vendor_c, "0x%.4x", vendor); + memcpy(nvme_dev_desc[devnum].product, + dev->serial, sizeof(dev->serial)); + memcpy(nvme_dev_desc[devnum].vendor, + vendor_c, sizeof(vendor_c)); + memcpy(nvme_dev_desc[devnum].revision, + dev->firmware_rev, sizeof(dev->firmware_rev)); + return 0; + free_ns: + free(ns); + return ret; +} + +static void print_optional_admin_cmd(u16 oacs, int devnum) +{ + printf("Blk device %d: Optional Admin Command Support:\n", + devnum); + printf("\tNamespace Management/Attachment: %s\n", + oacs & 0x08 ? "yes" : "no"); + printf("\tFirmware Commit/Image download: %s\n", + oacs & 0x04 ? "yes" : "no"); + printf("\tFormat NVM: %s\n", + oacs & 0x02 ? "yes" : "no"); + printf("\tSecurity Send/Receive: %s\n", + oacs & 0x01 ? "yes" : "no"); +} + +static void print_optional_nvm_cmd(u16 oncs, int devnum) +{ + printf("Blk device %d: Optional NVM Command Support:\n", + devnum); + printf("\tReservation: %s\n", + oncs & 0x10 ? "yes" : "no"); + printf("\tSave/Select field in the Set/Get features: %s\n", + oncs & 0x08 ? "yes" : "no"); + printf("\tWrite Zeroes: %s\n", + oncs & 0x04 ? "yes" : "no"); + printf("\tDataset Management: %s\n", + oncs & 0x02 ? "yes" : "no"); + printf("\tWrite Uncorrectable: %s\n", + oncs & 0x01 ? "yes" : "no"); +} + +static void print_format_nvme_attributes(u8 fna, int devnum) +{ + printf("Blk device %d: Format NVM Attributes:\n", devnum); + printf("\tSupport Cryptographic Erase: %s\n", + fna & 0x04 ? "yes" : "No"); + printf("\tSupport erase a particular namespace: %s\n", + fna & 0x02 ? "No" : "Yes"); + printf("\tSupport format a particular namespace: %s\n", + fna & 0x01 ? "No" : "Yes"); +} + +static void print_format(struct nvme_lbaf *lbaf) +{ + u8 str[][10] = {"Best", "Better", "Good", "Degraded"}; + printf("\t\tMetadata Size: %d\n", le16_to_cpu(lbaf->ms)); + printf("\t\tLBA Data Size: %d\n", 1 << lbaf->ds); + printf("\t\tRelative Performance: %s\n", str[lbaf->rp & 0x03]); +} + +static void print_formats(struct nvme_id_ns *id, struct nvme_ns *ns) +{ + int i; + printf("Blk device %d: LBA Format Support:\n", ns->devnum); + for (i = 0; i < id->nlbaf; i++) { + printf("\tLBA Foramt %d Support: ", i); + if (i == ns->flbas) + printf("(current)\n"); + else + printf("\n"); + print_format(id->lbaf + i); + } +} + +static void print_data_protect_cap(u8 dpc, int devnum) +{ + printf("Blk device %d: End-to-End Data", devnum); + printf("Protect Capabilities:\n"); + printf("\tAs last eight bytes: %s\n", + dpc & 0x10 ? "yes" : "No"); + printf("\tAs first eight bytes: %s\n", + dpc & 0x08 ? "yes" : "No"); + printf("\tSupport Type3: %s\n", + dpc & 0x04 ? "yes" : "No"); + printf("\tSupport Type2: %s\n", + dpc & 0x02 ? "yes" : "No"); + printf("\tSupport Type1: %s\n", + dpc & 0x01 ? "yes" : "No"); +} + +static void print_metadata_cap(u8 mc, int devnum) +{ + printf("Blk device %d: Metadata capabilities:\n", devnum); + printf("\tAs part of a separate buffer: %s\n", + mc & 0x02 ? "yes" : "No"); + printf("\tAs part of an extended data LBA: %s\n", + mc & 0x01 ? "yes" : "No"); +} + +int nvme_print_info(int devnum) +{ +#ifdef CONFIG_BLK + struct udevice *udev; + blk_get_device(IF_TYPE_NVME, devnum, &udev); + struct nvme_ns *ns = dev_get_priv(udev); +#else + struct nvme_ns *ns = nvme_dev_desc[devnum].priv; +#endif + if (!ns) { + printf("Can not find device %d\n", devnum); + return -EINVAL; + } + + struct nvme_dev *dev = ns->dev; + struct nvme_id_ns buf_ns, *id = &buf_ns; + struct nvme_id_ctrl buf_ctrl, *ctrl = &buf_ctrl; + + if (nvme_identify(dev, 0, 1, (dma_addr_t)ctrl)) + return -EIO; + + print_optional_admin_cmd(le16_to_cpu(ctrl->oacs), devnum); + print_optional_nvm_cmd(le16_to_cpu(ctrl->oncs), devnum); + print_format_nvme_attributes(ctrl->fna, devnum); + + if (nvme_identify(dev, ns->ns_id, 0, (dma_addr_t)id)) + return -EIO; + + print_formats(id, ns); + print_data_protect_cap(id->dpc, devnum); + print_metadata_cap(id->mc, devnum); + return 0; +} + +#ifdef CONFIG_BLK +ulong nvme_write(struct udevice *udev, ulong blknr, lbaint_t blkcnt, + const void *buffer) +{ + struct nvme_ns *ns = dev_get_priv(udev); + struct nvme_dev *dev = ns->dev; + int devnum = ns->devnum; +#else +ulong nvme_write(int devnum, ulong blknr, lbaint_t blkcnt, + const void *buffer) +{ + struct nvme_ns *ns = nvme_dev_desc[devnum].priv; + struct nvme_dev *dev = ns->dev; +#endif + struct nvme_command c; + int status; + u64 prp2; + u64 total_len = blkcnt << nvme_dev_desc[devnum].log2blksz; + u64 temp_len = total_len; + + u64 slba = blknr; + u16 lbas = 1 << (dev->max_transfer_shift - ns->lba_shift); + u64 total_lbas = blkcnt; + + c.rw.opcode = nvme_cmd_write; + c.rw.flags = 0; + c.rw.nsid = cpu_to_le32(ns->ns_id); + c.rw.control = 0; + c.rw.dsmgmt = 0; + c.rw.reftag = 0; + c.rw.apptag = 0; + c.rw.appmask = 0; + c.rw.metadata = 0; + + while (total_lbas) { + if (total_lbas < lbas) { + lbas = (u16)total_lbas; + total_lbas = 0; + } else { + total_lbas -= lbas; + } + + if (nvme_setup_prps + (dev, &prp2, lbas << ns->lba_shift, (u64)buffer)) + return -EIO; + c.rw.slba = cpu_to_le64(slba); + slba += lbas; + c.rw.length = cpu_to_le16(lbas - 1); + c.rw.prp1 = cpu_to_le64(buffer); + c.rw.prp2 = cpu_to_le64(prp2); + status = nvme_submit_sync_cmd(dev->queues[1], + &c, NULL, NVME_IO_TIMEOUT); + if (status) + break; + temp_len -= lbas << ns->lba_shift; + buffer += lbas << ns->lba_shift; + } + return (total_len - temp_len) >> nvme_dev_desc[devnum].log2blksz; +} + +#ifdef CONFIG_BLK +ulong nvme_read(struct udevice *udev, ulong blknr, lbaint_t blkcnt, + void *buffer) +{ + struct nvme_ns *ns = dev_get_priv(udev); + struct nvme_dev *dev = ns->dev; + int devnum = ns->devnum; +#else +ulong nvme_read(int devnum, ulong blknr, lbaint_t blkcnt, + void *buffer) +{ + struct nvme_ns *ns = nvme_dev_desc[devnum].priv; + struct nvme_dev *dev = ns->dev; +#endif + struct nvme_command c; + int status; + u64 prp2; + u64 total_len = blkcnt << nvme_dev_desc[devnum].log2blksz; + u64 temp_len = total_len; + + u64 slba = blknr; + u16 lbas = 1 << (dev->max_transfer_shift - ns->lba_shift); + u64 total_lbas = blkcnt; + + c.rw.opcode = nvme_cmd_read; + c.rw.flags = 0; + c.rw.nsid = cpu_to_le32(ns->ns_id); + c.rw.control = 0; + c.rw.dsmgmt = 0; + c.rw.reftag = 0; + c.rw.apptag = 0; + c.rw.appmask = 0; + c.rw.metadata = 0; + + while (total_lbas) { + if (total_lbas < lbas) { + lbas = (u16)total_lbas; + total_lbas = 0; + } else { + total_lbas -= lbas; + } + + if (nvme_setup_prps + (dev, &prp2, lbas << ns->lba_shift, (u64)buffer)) + return -EIO; + c.rw.slba = cpu_to_le64(slba); + slba += lbas; + c.rw.length = cpu_to_le16(lbas - 1); + c.rw.prp1 = cpu_to_le64(buffer); + c.rw.prp2 = cpu_to_le64(prp2); + status = nvme_submit_sync_cmd(dev->queues[1], + &c, NULL, NVME_IO_TIMEOUT); + if (status) + break; + temp_len -= lbas << ns->lba_shift; + buffer += lbas << ns->lba_shift; + } + return (total_len - temp_len) >> nvme_dev_desc[devnum].log2blksz; +} diff --git a/drivers/block/nvme.h b/drivers/block/nvme.h new file mode 100644 index 0000000..9345f90 --- /dev/null +++ b/drivers/block/nvme.h @@ -0,0 +1,114 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#include <pci.h> +#include <asm/io.h> +#include "nvme_uapi.h" +#include <linux/list.h> +#include <nvme.h> + +struct nvme_bar { + __u64 cap; /* Controller Capabilities */ + __u32 vs; /* Version */ + __u32 intms; /* Interrupt Mask Set */ + __u32 intmc; /* Interrupt Mask Clear */ + __u32 cc; /* Controller Configuration */ + __u32 rsvd1; /* Reserved */ + __u32 csts; /* Controller Status */ + __u32 rsvd2; /* Reserved */ + __u32 aqa; /* Admin Queue Attributes */ + __u64 asq; /* Admin SQ Base Address */ + __u64 acq; /* Admin CQ Base Address */ +}; + +#define NVME_CAP_MQES(cap) ((cap) & 0xffff) +#define NVME_CAP_TIMEOUT(cap) (((cap) >> 24) & 0xff) +#define NVME_CAP_STRIDE(cap) (((cap) >> 32) & 0xf) +#define NVME_CAP_MPSMIN(cap) (((cap) >> 48) & 0xf) +#define NVME_CAP_MPSMAX(cap) (((cap) >> 52) & 0xf) + +enum { + NVME_CC_ENABLE = 1 << 0, + NVME_CC_CSS_NVM = 0 << 4, + NVME_CC_MPS_SHIFT = 7, + NVME_CC_ARB_RR = 0 << 11, + NVME_CC_ARB_WRRU = 1 << 11, + NVME_CC_ARB_VS = 7 << 11, + NVME_CC_SHN_NONE = 0 << 14, + NVME_CC_SHN_NORMAL = 1 << 14, + NVME_CC_SHN_ABRUPT = 2 << 14, + NVME_CC_SHN_MASK = 3 << 14, + NVME_CC_IOSQES = 6 << 16, + NVME_CC_IOCQES = 4 << 20, + NVME_CSTS_RDY = 1 << 0, + NVME_CSTS_CFS = 1 << 1, + NVME_CSTS_SHST_NORMAL = 0 << 2, + NVME_CSTS_SHST_OCCUR = 1 << 2, + NVME_CSTS_SHST_CMPLT = 2 << 2, + NVME_CSTS_SHST_MASK = 3 << 2, +}; + +#define NVME_IO_TIMEOUT 30 + +/* + * Represents an NVM Express device. Each nvme_dev is a PCI function. + */ +struct nvme_dev { + struct list_head node; + struct nvme_queue **queues; + u32 __iomem *dbs; + unsigned int cardnum; +#ifdef CONFIG_BLK + struct udevice *pdev; +#endif + pci_dev_t pci_dev; + int instance; + uint8_t *hw_addr; + unsigned queue_count; + unsigned online_queues; + unsigned max_qid; + int q_depth; + u32 db_stride; + u32 ctrl_config; + struct nvme_bar __iomem *bar; + struct list_head namespaces; + const char *name; + char serial[20]; + char model[40]; + char firmware_rev[8]; + u32 max_transfer_shift; + u32 stripe_size; + u32 page_size; + u16 oncs; + u16 abort_limit; + u8 event_limit; + u8 vwc; + u64 *prp_pool; + u32 prp_entry_num; + u32 nn; + u32 blk_dev_start; +}; + +struct nvme_info { + int maxport; + int idx; + struct list_head dev_list; +}; + +/* + * The nvme_iod describes the data in an I/O, including the list of PRP + * entries. You can't see it in this data structure because C doesn't let + * me express that. Use nvme_alloc_iod to ensure there's enough space + * allocated to store the PRP list. + */ +struct nvme_iod { + unsigned long private; /* For the use of the submitter of the I/O */ + int npages; /* In the PRP list. 0 means small pool in use */ + int offset; /* Of PRP list */ + int nents; /* Used in scatterlist */ + int length; /* Of data, in bytes */ + dma_addr_t first_dma; +}; diff --git a/drivers/block/nvme_uapi.h b/drivers/block/nvme_uapi.h new file mode 100644 index 0000000..c87d104 --- /dev/null +++ b/drivers/block/nvme_uapi.h @@ -0,0 +1,570 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#include <linux/types.h> + +struct nvme_id_power_state { + __le16 max_power; /* centiwatts */ + __u8 rsvd2; + __u8 flags; + __le32 entry_lat; /* microseconds */ + __le32 exit_lat; /* microseconds */ + __u8 read_tput; + __u8 read_lat; + __u8 write_tput; + __u8 write_lat; + __le16 idle_power; + __u8 idle_scale; + __u8 rsvd19; + __le16 active_power; + __u8 active_work_scale; + __u8 rsvd23[9]; +}; + +enum { + NVME_PS_FLAGS_MAX_POWER_SCALE = 1 << 0, + NVME_PS_FLAGS_NON_OP_STATE = 1 << 1, +}; + +struct nvme_id_ctrl { + __le16 vid; + __le16 ssvid; + char sn[20]; + char mn[40]; + char fr[8]; + __u8 rab; + __u8 ieee[3]; + __u8 mic; + __u8 mdts; + __u16 cntlid; + __u32 ver; + __u8 rsvd84[172]; + __le16 oacs; + __u8 acl; + __u8 aerl; + __u8 frmw; + __u8 lpa; + __u8 elpe; + __u8 npss; + __u8 avscc; + __u8 apsta; + __le16 wctemp; + __le16 cctemp; + __u8 rsvd270[242]; + __u8 sqes; + __u8 cqes; + __u8 rsvd514[2]; + __le32 nn; + __le16 oncs; + __le16 fuses; + __u8 fna; + __u8 vwc; + __le16 awun; + __le16 awupf; + __u8 nvscc; + __u8 rsvd531; + __le16 acwu; + __u8 rsvd534[2]; + __le32 sgls; + __u8 rsvd540[1508]; + struct nvme_id_power_state psd[32]; + __u8 vs[1024]; +}; + +enum { + NVME_CTRL_ONCS_COMPARE = 1 << 0, + NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, + NVME_CTRL_ONCS_DSM = 1 << 2, + NVME_CTRL_VWC_PRESENT = 1 << 0, +}; + +struct nvme_lbaf { + __le16 ms; + __u8 ds; + __u8 rp; +}; + +struct nvme_id_ns { + __le64 nsze; + __le64 ncap; + __le64 nuse; + __u8 nsfeat; + __u8 nlbaf; + __u8 flbas; + __u8 mc; + __u8 dpc; + __u8 dps; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __u8 rsvd33; + __le16 nawun; + __le16 nawupf; + __le16 nacwu; + __le16 nabsn; + __le16 nabo; + __le16 nabspf; + __u16 rsvd46; + __le64 nvmcap[2]; + __u8 rsvd64[40]; + __u8 nguid[16]; + __u8 eui64[8]; + struct nvme_lbaf lbaf[16]; + __u8 rsvd192[192]; + __u8 vs[3712]; +}; + +enum { + NVME_NS_FEAT_THIN = 1 << 0, + NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_META_EXT = 0x10, + NVME_LBAF_RP_BEST = 0, + NVME_LBAF_RP_BETTER = 1, + NVME_LBAF_RP_GOOD = 2, + NVME_LBAF_RP_DEGRADED = 3, + NVME_NS_DPC_PI_LAST = 1 << 4, + NVME_NS_DPC_PI_FIRST = 1 << 3, + NVME_NS_DPC_PI_TYPE3 = 1 << 2, + NVME_NS_DPC_PI_TYPE2 = 1 << 1, + NVME_NS_DPC_PI_TYPE1 = 1 << 0, + NVME_NS_DPS_PI_FIRST = 1 << 3, + NVME_NS_DPS_PI_MASK = 0x7, + NVME_NS_DPS_PI_TYPE1 = 1, + NVME_NS_DPS_PI_TYPE2 = 2, + NVME_NS_DPS_PI_TYPE3 = 3, +}; + +struct nvme_smart_log { + __u8 critical_warning; + __u8 temperature[2]; + __u8 avail_spare; + __u8 spare_thresh; + __u8 percent_used; + __u8 rsvd6[26]; + __u8 data_units_read[16]; + __u8 data_units_written[16]; + __u8 host_reads[16]; + __u8 host_writes[16]; + __u8 ctrl_busy_time[16]; + __u8 power_cycles[16]; + __u8 power_on_hours[16]; + __u8 unsafe_shutdowns[16]; + __u8 media_errors[16]; + __u8 num_err_log_entries[16]; + __le32 warning_temp_time; + __le32 critical_comp_time; + __le16 temp_sensor[8]; + __u8 rsvd216[296]; +}; + +enum { + NVME_SMART_CRIT_SPARE = 1 << 0, + NVME_SMART_CRIT_TEMPERATURE = 1 << 1, + NVME_SMART_CRIT_RELIABILITY = 1 << 2, + NVME_SMART_CRIT_MEDIA = 1 << 3, + NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, +}; + +struct nvme_lba_range_type { + __u8 type; + __u8 attributes; + __u8 rsvd2[14]; + __u64 slba; + __u64 nlb; + __u8 guid[16]; + __u8 rsvd48[16]; +}; + +enum { + NVME_LBART_TYPE_FS = 0x01, + NVME_LBART_TYPE_RAID = 0x02, + NVME_LBART_TYPE_CACHE = 0x03, + NVME_LBART_TYPE_SWAP = 0x04, + + NVME_LBART_ATTRIB_TEMP = 1 << 0, + NVME_LBART_ATTRIB_HIDE = 1 << 1, +}; + +struct nvme_reservation_status { + __le32 gen; + __u8 rtype; + __u8 regctl[2]; + __u8 resv5[2]; + __u8 ptpls; + __u8 resv10[13]; + struct { + __le16 cntlid; + __u8 rcsts; + __u8 resv3[5]; + __le64 hostid; + __le64 rkey; + } regctl_ds[]; +}; + +/* I/O commands */ + +enum nvme_opcode { + nvme_cmd_flush = 0x00, + nvme_cmd_write = 0x01, + nvme_cmd_read = 0x02, + nvme_cmd_write_uncor = 0x04, + nvme_cmd_compare = 0x05, + nvme_cmd_write_zeroes = 0x08, + nvme_cmd_dsm = 0x09, + nvme_cmd_resv_register = 0x0d, + nvme_cmd_resv_report = 0x0e, + nvme_cmd_resv_acquire = 0x11, + nvme_cmd_resv_release = 0x15, +}; + +struct nvme_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le32 cdw2[2]; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le32 cdw10[6]; +}; + +struct nvme_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le64 slba; + __le16 length; + __le16 control; + __le32 dsmgmt; + __le32 reftag; + __le16 apptag; + __le16 appmask; +}; + +enum { + NVME_RW_LR = 1 << 15, + NVME_RW_FUA = 1 << 14, + NVME_RW_DSM_FREQ_UNSPEC = 0, + NVME_RW_DSM_FREQ_TYPICAL = 1, + NVME_RW_DSM_FREQ_RARE = 2, + NVME_RW_DSM_FREQ_READS = 3, + NVME_RW_DSM_FREQ_WRITES = 4, + NVME_RW_DSM_FREQ_RW = 5, + NVME_RW_DSM_FREQ_ONCE = 6, + NVME_RW_DSM_FREQ_PREFETCH = 7, + NVME_RW_DSM_FREQ_TEMP = 8, + NVME_RW_DSM_LATENCY_NONE = 0 << 4, + NVME_RW_DSM_LATENCY_IDLE = 1 << 4, + NVME_RW_DSM_LATENCY_NORM = 2 << 4, + NVME_RW_DSM_LATENCY_LOW = 3 << 4, + NVME_RW_DSM_SEQ_REQ = 1 << 6, + NVME_RW_DSM_COMPRESSED = 1 << 7, + NVME_RW_PRINFO_PRCHK_REF = 1 << 10, + NVME_RW_PRINFO_PRCHK_APP = 1 << 11, + NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, + NVME_RW_PRINFO_PRACT = 1 << 13, +}; + +struct nvme_dsm_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 nr; + __le32 attributes; + __u32 rsvd12[4]; +}; + +enum { + NVME_DSMGMT_IDR = 1 << 0, + NVME_DSMGMT_IDW = 1 << 1, + NVME_DSMGMT_AD = 1 << 2, +}; + +struct nvme_dsm_range { + __le32 cattr; + __le32 nlb; + __le64 slba; +}; + +/* Admin commands */ + +enum nvme_admin_opcode { + nvme_admin_delete_sq = 0x00, + nvme_admin_create_sq = 0x01, + nvme_admin_get_log_page = 0x02, + nvme_admin_delete_cq = 0x04, + nvme_admin_create_cq = 0x05, + nvme_admin_identify = 0x06, + nvme_admin_abort_cmd = 0x08, + nvme_admin_set_features = 0x09, + nvme_admin_get_features = 0x0a, + nvme_admin_async_event = 0x0c, + nvme_admin_activate_fw = 0x10, + nvme_admin_download_fw = 0x11, + nvme_admin_format_nvm = 0x80, + nvme_admin_security_send = 0x81, + nvme_admin_security_recv = 0x82, +}; + +enum { + NVME_QUEUE_PHYS_CONTIG = (1 << 0), + NVME_CQ_IRQ_ENABLED = (1 << 1), + NVME_SQ_PRIO_URGENT = (0 << 1), + NVME_SQ_PRIO_HIGH = (1 << 1), + NVME_SQ_PRIO_MEDIUM = (2 << 1), + NVME_SQ_PRIO_LOW = (3 << 1), + NVME_FEAT_ARBITRATION = 0x01, + NVME_FEAT_POWER_MGMT = 0x02, + NVME_FEAT_LBA_RANGE = 0x03, + NVME_FEAT_TEMP_THRESH = 0x04, + NVME_FEAT_ERR_RECOVERY = 0x05, + NVME_FEAT_VOLATILE_WC = 0x06, + NVME_FEAT_NUM_QUEUES = 0x07, + NVME_FEAT_IRQ_COALESCE = 0x08, + NVME_FEAT_IRQ_CONFIG = 0x09, + NVME_FEAT_WRITE_ATOMIC = 0x0a, + NVME_FEAT_ASYNC_EVENT = 0x0b, + NVME_FEAT_AUTO_PST = 0x0c, + NVME_FEAT_SW_PROGRESS = 0x80, + NVME_FEAT_HOST_ID = 0x81, + NVME_FEAT_RESV_MASK = 0x82, + NVME_FEAT_RESV_PERSIST = 0x83, + NVME_LOG_ERROR = 0x01, + NVME_LOG_SMART = 0x02, + NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_RESERVATION = 0x80, + NVME_FWACT_REPL = (0 << 3), + NVME_FWACT_REPL_ACTV = (1 << 3), + NVME_FWACT_ACTV = (2 << 3), +}; + +struct nvme_identify { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 cns; + __u32 rsvd11[5]; +}; + +struct nvme_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 fid; + __le32 dword11; + __u32 rsvd12[4]; +}; + +struct nvme_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct nvme_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct nvme_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct nvme_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 sqid; + __u16 cid; + __u32 rsvd11[5]; +}; + +struct nvme_download_firmware { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __le64 prp2; + __le32 numd; + __le32 offset; + __u32 rsvd12[4]; +}; + +struct nvme_format_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[4]; + __le32 cdw10; + __u32 rsvd11[5]; +}; + +struct nvme_command { + union { + struct nvme_common_command common; + struct nvme_rw_command rw; + struct nvme_identify identify; + struct nvme_features features; + struct nvme_create_cq create_cq; + struct nvme_create_sq create_sq; + struct nvme_delete_queue delete_queue; + struct nvme_download_firmware dlfw; + struct nvme_format_cmd format; + struct nvme_dsm_cmd dsm; + struct nvme_abort_cmd abort; + }; +}; + +enum { + NVME_SC_SUCCESS = 0x0, + NVME_SC_INVALID_OPCODE = 0x1, + NVME_SC_INVALID_FIELD = 0x2, + NVME_SC_CMDID_CONFLICT = 0x3, + NVME_SC_DATA_XFER_ERROR = 0x4, + NVME_SC_POWER_LOSS = 0x5, + NVME_SC_INTERNAL = 0x6, + NVME_SC_ABORT_REQ = 0x7, + NVME_SC_ABORT_QUEUE = 0x8, + NVME_SC_FUSED_FAIL = 0x9, + NVME_SC_FUSED_MISSING = 0xa, + NVME_SC_INVALID_NS = 0xb, + NVME_SC_CMD_SEQ_ERROR = 0xc, + NVME_SC_SGL_INVALID_LAST = 0xd, + NVME_SC_SGL_INVALID_COUNT = 0xe, + NVME_SC_SGL_INVALID_DATA = 0xf, + NVME_SC_SGL_INVALID_METADATA = 0x10, + NVME_SC_SGL_INVALID_TYPE = 0x11, + NVME_SC_LBA_RANGE = 0x80, + NVME_SC_CAP_EXCEEDED = 0x81, + NVME_SC_NS_NOT_READY = 0x82, + NVME_SC_RESERVATION_CONFLICT = 0x83, + NVME_SC_CQ_INVALID = 0x100, + NVME_SC_QID_INVALID = 0x101, + NVME_SC_QUEUE_SIZE = 0x102, + NVME_SC_ABORT_LIMIT = 0x103, + NVME_SC_ABORT_MISSING = 0x104, + NVME_SC_ASYNC_LIMIT = 0x105, + NVME_SC_FIRMWARE_SLOT = 0x106, + NVME_SC_FIRMWARE_IMAGE = 0x107, + NVME_SC_INVALID_VECTOR = 0x108, + NVME_SC_INVALID_LOG_PAGE = 0x109, + NVME_SC_INVALID_FORMAT = 0x10a, + NVME_SC_FIRMWARE_NEEDS_RESET = 0x10b, + NVME_SC_INVALID_QUEUE = 0x10c, + NVME_SC_FEATURE_NOT_SAVEABLE = 0x10d, + NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, + NVME_SC_FEATURE_NOT_PER_NS = 0x10f, + NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, + NVME_SC_BAD_ATTRIBUTES = 0x180, + NVME_SC_INVALID_PI = 0x181, + NVME_SC_READ_ONLY = 0x182, + NVME_SC_WRITE_FAULT = 0x280, + NVME_SC_READ_ERROR = 0x281, + NVME_SC_GUARD_CHECK = 0x282, + NVME_SC_APPTAG_CHECK = 0x283, + NVME_SC_REFTAG_CHECK = 0x284, + NVME_SC_COMPARE_FAILED = 0x285, + NVME_SC_ACCESS_DENIED = 0x286, + NVME_SC_DNR = 0x4000, +}; + +struct nvme_completion { + __le32 result; /* Used by admin commands to return data */ + __u32 rsvd; + __le16 sq_head; /* how much of this queue may be reclaimed */ + __le16 sq_id; /* submission queue that generated this entry */ + __u16 command_id; /* of the command which completed */ + __le16 status; /* did the command fail, and if so, why? */ +}; + +struct nvme_user_io { + __u8 opcode; + __u8 flags; + __u16 control; + __u16 nblocks; + __u16 rsvd; + __u64 metadata; + __u64 addr; + __u64 slba; + __u32 dsmgmt; + __u32 reftag; + __u16 apptag; + __u16 appmask; +}; + +struct nvme_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result; +}; + +#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8)) + +#define nvme_admin_cmd nvme_passthru_cmd + +#define NVME_IOCTL_ID _IO('N', 0x40) +#define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) +#define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) +#define NVME_IOCTL_IO_CMD _IOWR('N', 0x43, struct nvme_passthru_cmd) diff --git a/include/blk.h b/include/blk.h index 66a1c55..7f1e573 100644 --- a/include/blk.h +++ b/include/blk.h @@ -31,6 +31,7 @@ enum if_type { IF_TYPE_SATA, IF_TYPE_HOST, IF_TYPE_SYSTEMACE, + IF_TYPE_NVME,

IF_TYPE_COUNT, /* Number of interface types */ }; diff --git a/include/nvme.h b/include/nvme.h new file mode 100644 index 0000000..3f8f94f --- /dev/null +++ b/include/nvme.h @@ -0,0 +1,50 @@ +/* + * Copyright (C) 2017 NXP Semiconductors + * + * SPDX-License-Identifier: GPL-2.0+ + */ + +#ifndef __NVME_H__ +#define __NVME_H__ +#include <part.h> + +#ifdef CONFIG_BLK +int init_nvme(struct udevice *udev); +int scan_nvme(struct udevice *udev); +ulong nvme_read(struct udevice *udev, ulong blknr, lbaint_t blkcnt, + void *buffer); +ulong nvme_write(struct udevice *udev, ulong blknr, lbaint_t blkcnt, + const void *buffer); +#else +int init_nvme(int devnum); +int scan_nvme(int devnum); +ulong nvme_read(int devnum, ulong blknr, lbaint_t blkcnt, + void *buffer); +ulong nvme_write(int devnum, ulong blknr, lbaint_t blkcnt, + const void *buffer); +#endif +int nvme_print_info(int devnum); +int nvme_initialize(void); +int __nvme_initialize(void); + +extern struct blk_desc nvme_dev_desc[]; + +/* + * An NVM Express namespace is equivalent to a SCSI LUN + * Each namespace is operated as an independent "device". + */ +struct nvme_ns { + struct list_head list; + struct nvme_dev *dev; + unsigned ns_id; + int devnum; + int lba_shift; + u16 ms; + u8 flbas; + u8 pi_type; + u64 mode_select_num_blocks; + u32 mode_select_block_len; +}; + +extern struct pci_device_id nvme_supported[]; +#endif