qemu/hw/block/nvme.h
Klaus Jensen 2605257a26 hw/block/nvme: add the dataset management command
Add support for the Dataset Management command and the Deallocate
attribute. Deallocation results in discards being sent to the underlying
block device. Whether of not the blocks are actually deallocated is
affected by the same factors as Write Zeroes (see previous commit).

     format | discard | dsm (512B)  dsm (4KiB)  dsm (64KiB)
    --------------------------------------------------------
      qcow2    ignore   n           n           n
      qcow2    unmap    n           n           y
      raw      ignore   n           n           n
      raw      unmap    n           y           y

Again, a raw format and 4KiB LBAs are preferable.

In order to set the Namespace Preferred Deallocate Granularity and
Alignment fields (NPDG and NPDA), choose a sane minimum discard
granularity of 4KiB. If we are using a passthru device supporting
discard at a 512B granularity, user should set the discard_granularity
property explicitly. NPDG and NPDA will also account for the
cluster_size of the block driver if required (i.e. for QCOW2).

See NVM Express 1.3d, Section 6.7 ("Dataset Management command").

Signed-off-by: Klaus Jensen <k.jensen@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
2021-02-08 18:55:48 +01:00

188 lines
5.1 KiB
C

#ifndef HW_NVME_H
#define HW_NVME_H
#include "block/nvme.h"
#include "nvme-ns.h"
#define NVME_MAX_NAMESPACES 256
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;
} NvmeParams;
typedef struct NvmeAsyncEvent {
QTAILQ_ENTRY(NvmeAsyncEvent) entry;
NvmeAerResult result;
} NvmeAsyncEvent;
typedef struct NvmeRequest {
struct NvmeSQueue *sq;
struct NvmeNamespace *ns;
BlockAIOCB *aiocb;
uint16_t status;
void *opaque;
NvmeCqe cqe;
NvmeCmd cmd;
BlockAcctCookie acct;
QEMUSGList qsg;
QEMUIOVector iov;
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_WRITE_ZEROES: return "NVME_NVM_CMD_WRITE_ZEROES";
case NVME_CMD_DSM: return "NVME_NVM_CMD_DSM";
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;
uint32_t vwc;
} NvmeFeatureVal;
typedef struct NvmeCtrl {
PCIDevice parent_obj;
MemoryRegion iomem;
MemoryRegion ctrl_mem;
NvmeBar bar;
NvmeParams params;
NvmeBus bus;
BlockConf conf;
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;
uint8_t *cmbuf;
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;
HostMemoryBackend *pmrdev;
uint8_t aer_mask;
NvmeRequest **aer_reqs;
QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
int aer_queued;
NvmeNamespace namespace;
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 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 */