qemu/hw/block/nvme.h

260 lines
6.8 KiB
C
Raw Normal View History

#ifndef HW_NVME_H
#define HW_NVME_H
#include "block/nvme.h"
#include "nvme-subsys.h"
#include "nvme-ns.h"
#define NVME_MAX_NAMESPACES 256
hw/block/nvme: Support Zoned Namespace Command Set The emulation code has been changed to advertise NVM Command Set when "zoned" device property is not set (default) and Zoned Namespace Command Set otherwise. Define values and structures that are needed to support Zoned Namespace Command Set (NVMe TP 4053) in PCI NVMe controller emulator. Define trace events where needed in newly introduced code. In order to improve scalability, all open, closed and full zones are organized in separate linked lists. Consequently, almost all zone operations don't require scanning of the entire zone array (which potentially can be quite large) - it is only necessary to enumerate one or more zone lists. Handlers for three new NVMe commands introduced in Zoned Namespace Command Set specification are added, namely for Zone Management Receive, Zone Management Send and Zone Append. Device initialization code has been extended to create a proper configuration for zoned operation using device properties. Read/Write command handler is modified to only allow writes at the write pointer if the namespace is zoned. For Zone Append command, writes implicitly happen at the write pointer and the starting write pointer value is returned as the result of the command. Write Zeroes handler is modified to add zoned checks that are identical to those done as a part of Write flow. Subsequent commits in this series add ZDE support and checks for active and open zone limits. Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com> Signed-off-by: Hans Holmberg <hans.holmberg@wdc.com> Signed-off-by: Ajay Joshi <ajay.joshi@wdc.com> Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com> Signed-off-by: Matias Bjorling <matias.bjorling@wdc.com> Signed-off-by: Aravind Ramesh <aravind.ramesh@wdc.com> Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com> Signed-off-by: Adam Manzanares <adam.manzanares@wdc.com> Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com> Reviewed-by: Niklas Cassel <Niklas.Cassel@wdc.com> Reviewed-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
2020-12-08 23:04:06 +03:00
#define NVME_DEFAULT_ZONE_SIZE (128 * MiB)
#define NVME_DEFAULT_MAX_ZA_SIZE (128 * KiB)
/*
* Subsystem namespace list for allocated namespaces should be larger than
* attached namespace list in a controller.
*/
QEMU_BUILD_BUG_ON(NVME_MAX_NAMESPACES > NVME_SUBSYS_MAX_NAMESPACES);
typedef struct NvmeParams {
char *serial;
uint32_t num_queues; /* deprecated since 5.1 */
uint32_t max_ioqpairs;
uint16_t msix_qsize;
uint32_t cmb_size_mb;
uint8_t aerl;
uint32_t aer_max_queued;
uint8_t mdts;
bool use_intel_id;
uint8_t zasl;
bool legacy_cmb;
} NvmeParams;
typedef struct NvmeAsyncEvent {
QTAILQ_ENTRY(NvmeAsyncEvent) entry;
NvmeAerResult result;
} NvmeAsyncEvent;
enum {
NVME_SG_ALLOC = 1 << 0,
NVME_SG_DMA = 1 << 1,
};
typedef struct NvmeSg {
int flags;
union {
QEMUSGList qsg;
QEMUIOVector iov;
};
} NvmeSg;
typedef struct NvmeRequest {
struct NvmeSQueue *sq;
struct NvmeNamespace *ns;
BlockAIOCB *aiocb;
uint16_t status;
void *opaque;
NvmeCqe cqe;
NvmeCmd cmd;
BlockAcctCookie acct;
NvmeSg sg;
QTAILQ_ENTRY(NvmeRequest)entry;
} NvmeRequest;
static inline const char *nvme_adm_opc_str(uint8_t opc)
{
switch (opc) {
case NVME_ADM_CMD_DELETE_SQ: return "NVME_ADM_CMD_DELETE_SQ";
case NVME_ADM_CMD_CREATE_SQ: return "NVME_ADM_CMD_CREATE_SQ";
case NVME_ADM_CMD_GET_LOG_PAGE: return "NVME_ADM_CMD_GET_LOG_PAGE";
case NVME_ADM_CMD_DELETE_CQ: return "NVME_ADM_CMD_DELETE_CQ";
case NVME_ADM_CMD_CREATE_CQ: return "NVME_ADM_CMD_CREATE_CQ";
case NVME_ADM_CMD_IDENTIFY: return "NVME_ADM_CMD_IDENTIFY";
case NVME_ADM_CMD_ABORT: return "NVME_ADM_CMD_ABORT";
case NVME_ADM_CMD_SET_FEATURES: return "NVME_ADM_CMD_SET_FEATURES";
case NVME_ADM_CMD_GET_FEATURES: return "NVME_ADM_CMD_GET_FEATURES";
case NVME_ADM_CMD_ASYNC_EV_REQ: return "NVME_ADM_CMD_ASYNC_EV_REQ";
default: return "NVME_ADM_CMD_UNKNOWN";
}
}
static inline const char *nvme_io_opc_str(uint8_t opc)
{
switch (opc) {
case NVME_CMD_FLUSH: return "NVME_NVM_CMD_FLUSH";
case NVME_CMD_WRITE: return "NVME_NVM_CMD_WRITE";
case NVME_CMD_READ: return "NVME_NVM_CMD_READ";
case NVME_CMD_COMPARE: return "NVME_NVM_CMD_COMPARE";
case NVME_CMD_WRITE_ZEROES: return "NVME_NVM_CMD_WRITE_ZEROES";
case NVME_CMD_DSM: return "NVME_NVM_CMD_DSM";
case NVME_CMD_COPY: return "NVME_NVM_CMD_COPY";
case NVME_CMD_ZONE_MGMT_SEND: return "NVME_ZONED_CMD_MGMT_SEND";
case NVME_CMD_ZONE_MGMT_RECV: return "NVME_ZONED_CMD_MGMT_RECV";
case NVME_CMD_ZONE_APPEND: return "NVME_ZONED_CMD_ZONE_APPEND";
default: return "NVME_NVM_CMD_UNKNOWN";
}
}
typedef struct NvmeSQueue {
struct NvmeCtrl *ctrl;
uint16_t sqid;
uint16_t cqid;
uint32_t head;
uint32_t tail;
uint32_t size;
uint64_t dma_addr;
QEMUTimer *timer;
NvmeRequest *io_req;
QTAILQ_HEAD(, NvmeRequest) req_list;
QTAILQ_HEAD(, NvmeRequest) out_req_list;
QTAILQ_ENTRY(NvmeSQueue) entry;
} NvmeSQueue;
typedef struct NvmeCQueue {
struct NvmeCtrl *ctrl;
uint8_t phase;
uint16_t cqid;
uint16_t irq_enabled;
uint32_t head;
uint32_t tail;
uint32_t vector;
uint32_t size;
uint64_t dma_addr;
QEMUTimer *timer;
QTAILQ_HEAD(, NvmeSQueue) sq_list;
QTAILQ_HEAD(, NvmeRequest) req_list;
} NvmeCQueue;
#define TYPE_NVME_BUS "nvme-bus"
#define NVME_BUS(obj) OBJECT_CHECK(NvmeBus, (obj), TYPE_NVME_BUS)
typedef struct NvmeBus {
BusState parent_bus;
} NvmeBus;
#define TYPE_NVME "nvme"
#define NVME(obj) \
OBJECT_CHECK(NvmeCtrl, (obj), TYPE_NVME)
typedef struct NvmeFeatureVal {
struct {
uint16_t temp_thresh_hi;
uint16_t temp_thresh_low;
};
uint32_t async_config;
} NvmeFeatureVal;
typedef struct NvmeCtrl {
PCIDevice parent_obj;
MemoryRegion bar0;
MemoryRegion iomem;
NvmeBar bar;
NvmeParams params;
NvmeBus bus;
BlockConf conf;
uint16_t cntlid;
bool qs_created;
uint32_t page_size;
uint16_t page_bits;
uint16_t max_prp_ents;
uint16_t cqe_size;
uint16_t sqe_size;
uint32_t reg_size;
uint32_t num_namespaces;
uint32_t max_q_ents;
uint8_t outstanding_aers;
uint32_t irq_status;
uint64_t host_timestamp; /* Timestamp sent by the host */
uint64_t timestamp_set_qemu_clock_ms; /* QEMU clock time */
uint64_t starttime_ms;
uint16_t temperature;
uint8_t smart_critical_warning;
struct {
MemoryRegion mem;
uint8_t *buf;
bool cmse;
hwaddr cba;
} cmb;
struct {
HostMemoryBackend *dev;
bool cmse;
hwaddr cba;
} pmr;
uint8_t aer_mask;
NvmeRequest **aer_reqs;
QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
int aer_queued;
uint32_t dmrsl;
NvmeSubsystem *subsys;
NvmeNamespace namespace;
/*
* Attached namespaces to this controller. If subsys is not given, all
* namespaces in this list will always be attached.
*/
NvmeNamespace *namespaces[NVME_MAX_NAMESPACES];
NvmeSQueue **sq;
NvmeCQueue **cq;
NvmeSQueue admin_sq;
NvmeCQueue admin_cq;
NvmeIdCtrl id_ctrl;
NvmeFeatureVal features;
} NvmeCtrl;
static inline NvmeNamespace *nvme_ns(NvmeCtrl *n, uint32_t nsid)
{
if (!nsid || nsid > n->num_namespaces) {
return NULL;
}
return n->namespaces[nsid - 1];
}
static inline bool nvme_ns_is_attached(NvmeCtrl *n, NvmeNamespace *ns)
{
int nsid;
for (nsid = 1; nsid <= n->num_namespaces; nsid++) {
if (nvme_ns(n, nsid) == ns) {
return true;
}
}
return false;
}
static inline void nvme_ns_attach(NvmeCtrl *n, NvmeNamespace *ns)
{
n->namespaces[nvme_nsid(ns) - 1] = ns;
}
static inline void nvme_ns_detach(NvmeCtrl *n, NvmeNamespace *ns)
{
n->namespaces[nvme_nsid(ns) - 1] = NULL;
}
static inline NvmeCQueue *nvme_cq(NvmeRequest *req)
{
NvmeSQueue *sq = req->sq;
NvmeCtrl *n = sq->ctrl;
return n->cq[sq->cqid];
}
static inline NvmeCtrl *nvme_ctrl(NvmeRequest *req)
{
NvmeSQueue *sq = req->sq;
return sq->ctrl;
}
int nvme_register_namespace(NvmeCtrl *n, NvmeNamespace *ns, Error **errp);
#endif /* HW_NVME_H */