[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v2 08/18] hw/block/nvme: Make Zoned NS Command Set definition
|
From: |
Alistair Francis |
|
Subject: |
Re: [PATCH v2 08/18] hw/block/nvme: Make Zoned NS Command Set definitions |
|
Date: |
Tue, 30 Jun 2020 15:11:59 -0700 |
On Wed, Jun 17, 2020 at 2:51 PM Dmitry Fomichev <dmitry.fomichev@wdc.com> wrote:
>
> Define values and structures that are needed to support Zoned
> Namespace Command Set (NVMe TP 4053) in PCI NVMe controller emulator.
>
> All new protocol definitions are located in include/block/nvme.h
> and everything added that is specific to this implementation is kept
> in hw/block/nvme.h.
>
> 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. Zone lists are designed to be
> position-independent as they can be persisted to the backing file
> as a part of zone metadata. NvmeZoneList struct defined in this patch
> serves as a head of every zone list.
>
> NvmeZone structure encapsulates NvmeZoneDescriptor defined in Zoned
> Command Set specification and adds a few more fields that are
> internal to this implementation.
>
> 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: Matias Bjorling <matias.bjorling@wdc.com>
> Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
> Signed-off-by: Alexey Bogoslavsky <alexey.bogoslavsky@wdc.com>
> Signed-off-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
> ---
> hw/block/nvme.h | 130 +++++++++++++++++++++++++++++++++++++++++++
> include/block/nvme.h | 119 ++++++++++++++++++++++++++++++++++++++-
> 2 files changed, 248 insertions(+), 1 deletion(-)
>
> diff --git a/hw/block/nvme.h b/hw/block/nvme.h
> index 0d29f75475..2c932b5e29 100644
> --- a/hw/block/nvme.h
> +++ b/hw/block/nvme.h
> @@ -3,12 +3,22 @@
>
> #include "block/nvme.h"
>
> +#define NVME_DEFAULT_ZONE_SIZE 128 /* MiB */
> +#define NVME_DEFAULT_MAX_ZA_SIZE 128 /* KiB */
> +
> 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;
> +
> + bool zoned;
> + bool cross_zone_read;
> + uint8_t fill_pattern;
> + uint32_t zamds_bs;
> + uint64_t zone_size;
> + uint64_t zone_capacity;
> } NvmeParams;
>
> typedef struct NvmeAsyncEvent {
> @@ -17,6 +27,8 @@ typedef struct NvmeAsyncEvent {
>
> enum NvmeRequestFlags {
> NVME_REQ_FLG_HAS_SG = 1 << 0,
> + NVME_REQ_FLG_FILL = 1 << 1,
> + NVME_REQ_FLG_APPEND = 1 << 2,
> };
>
> typedef struct NvmeRequest {
> @@ -24,6 +36,7 @@ typedef struct NvmeRequest {
> BlockAIOCB *aiocb;
> uint16_t status;
> uint16_t flags;
> + uint64_t fill_ofs;
> NvmeCqe cqe;
> BlockAcctCookie acct;
> QEMUSGList qsg;
> @@ -61,11 +74,35 @@ typedef struct NvmeCQueue {
> QTAILQ_HEAD(, NvmeRequest) req_list;
> } NvmeCQueue;
>
> +typedef struct NvmeZone {
> + NvmeZoneDescr d;
> + uint64_t tstamp;
> + uint32_t next;
> + uint32_t prev;
> + uint8_t rsvd80[8];
> +} NvmeZone;
> +
> +#define NVME_ZONE_LIST_NIL UINT_MAX
> +
> +typedef struct NvmeZoneList {
> + uint32_t head;
> + uint32_t tail;
> + uint32_t size;
> + uint8_t rsvd12[4];
> +} NvmeZoneList;
> +
> typedef struct NvmeNamespace {
> NvmeIdNs id_ns;
> uint32_t nsid;
> uint8_t csi;
> QemuUUID uuid;
> +
> + NvmeIdNsZoned *id_ns_zoned;
> + NvmeZone *zone_array;
> + NvmeZoneList *exp_open_zones;
> + NvmeZoneList *imp_open_zones;
> + NvmeZoneList *closed_zones;
> + NvmeZoneList *full_zones;
> } NvmeNamespace;
>
> static inline NvmeLBAF *nvme_ns_lbaf(NvmeNamespace *ns)
> @@ -100,6 +137,7 @@ typedef struct NvmeCtrl {
> uint32_t num_namespaces;
> uint32_t max_q_ents;
> uint64_t ns_size;
> +
> uint8_t *cmbuf;
> uint32_t irq_status;
> uint64_t host_timestamp; /* Timestamp sent by the
> host */
> @@ -107,6 +145,12 @@ typedef struct NvmeCtrl {
>
> HostMemoryBackend *pmrdev;
>
> + int zone_file_fd;
> + uint32_t num_zones;
> + uint64_t zone_size_bs;
> + uint64_t zone_array_size;
> + uint8_t zamds;
> +
> NvmeNamespace *namespaces;
> NvmeSQueue **sq;
> NvmeCQueue **cq;
> @@ -121,6 +165,86 @@ static inline uint64_t nvme_ns_nlbas(NvmeCtrl *n,
> NvmeNamespace *ns)
> return n->ns_size >> nvme_ns_lbads(ns);
> }
>
> +static inline uint8_t nvme_get_zone_state(NvmeZone *zone)
> +{
> + return zone->d.zs >> 4;
> +}
> +
> +static inline void nvme_set_zone_state(NvmeZone *zone, enum NvmeZoneState
> state)
> +{
> + zone->d.zs = state << 4;
> +}
> +
> +static inline uint64_t nvme_zone_rd_boundary(NvmeCtrl *n, NvmeZone *zone)
> +{
> + return zone->d.zslba + n->params.zone_size;
> +}
> +
> +static inline uint64_t nvme_zone_wr_boundary(NvmeZone *zone)
> +{
> + return zone->d.zslba + zone->d.zcap;
> +}
> +
> +static inline bool nvme_wp_is_valid(NvmeZone *zone)
> +{
> + uint8_t st = nvme_get_zone_state(zone);
> +
> + return st != NVME_ZONE_STATE_FULL &&
> + st != NVME_ZONE_STATE_READ_ONLY &&
> + st != NVME_ZONE_STATE_OFFLINE;
> +}
> +
> +/*
> + * Initialize a zone list head.
> + */
> +static inline void nvme_init_zone_list(NvmeZoneList *zl)
> +{
> + zl->head = NVME_ZONE_LIST_NIL;
> + zl->tail = NVME_ZONE_LIST_NIL;
> + zl->size = 0;
> +}
> +
> +/*
> + * Initialize the number of entries contained in a zone list.
> + */
This should be retrieve (or something similar) instead of initialise.
> +static inline uint32_t nvme_zone_list_size(NvmeZoneList *zl)
> +{
> + return zl->size;
> +}
> +
> +/*
> + * Check if the zone is not currently included into any zone list.
> + */
> +static inline bool nvme_zone_not_in_list(NvmeZone *zone)
> +{
> + return (bool)(zone->prev == 0 && zone->next == 0);
You don't need the cast to bool.
Besides that it looks good. I didn't check every value against the spec though.
Acked-by: Alistair Francis <alistair.francis@wdc.com>
Alistair
> +}
> +
> +/*
> + * Return the zone at the head of zone list or NULL if the list is empty.
> + */
> +static inline NvmeZone *nvme_peek_zone_head(NvmeNamespace *ns, NvmeZoneList
> *zl)
> +{
> + if (zl->head == NVME_ZONE_LIST_NIL) {
> + return NULL;
> + }
> + return &ns->zone_array[zl->head];
> +}
> +
> +/*
> + * Return the next zone in the list.
> + */
> +static inline NvmeZone *nvme_next_zone_in_list(NvmeNamespace *ns, NvmeZone
> *z,
> + NvmeZoneList *zl)
> +{
> + assert(!nvme_zone_not_in_list(z));
> +
> + if (z->next == NVME_ZONE_LIST_NIL) {
> + return NULL;
> + }
> + return &ns->zone_array[z->next];
> +}
> +
> static inline int nvme_ilog2(uint64_t i)
> {
> int log = -1;
> @@ -132,4 +256,10 @@ static inline int nvme_ilog2(uint64_t i)
> return log;
> }
>
> +static inline void _hw_nvme_check_size(void)
> +{
> + QEMU_BUILD_BUG_ON(sizeof(NvmeZoneList) != 16);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeZone) != 88);
> +}
> +
> #endif /* HW_NVME_H */
> diff --git a/include/block/nvme.h b/include/block/nvme.h
> index 5a1e5e137c..596c39162b 100644
> --- a/include/block/nvme.h
> +++ b/include/block/nvme.h
> @@ -446,6 +446,9 @@ enum NvmeIoCommands {
> NVME_CMD_COMPARE = 0x05,
> NVME_CMD_WRITE_ZEROS = 0x08,
> NVME_CMD_DSM = 0x09,
> + NVME_CMD_ZONE_MGMT_SEND = 0x79,
> + NVME_CMD_ZONE_MGMT_RECV = 0x7a,
> + NVME_CMD_ZONE_APND = 0x7d,
> };
>
> typedef struct NvmeDeleteQ {
> @@ -539,6 +542,7 @@ enum NvmeNidLength {
>
> enum NvmeCsi {
> NVME_CSI_NVM = 0x00,
> + NVME_CSI_ZONED = 0x02,
> };
>
> #define NVME_SET_CSI(vec, csi) (vec |= (uint8_t)(1 << (csi)))
> @@ -661,6 +665,7 @@ enum NvmeStatusCodes {
> NVME_INVALID_NSID = 0x000b,
> NVME_CMD_SEQ_ERROR = 0x000c,
> NVME_CMD_SET_CMB_REJECTED = 0x002b,
> + NVME_INVALID_CMD_SET = 0x002c,
> NVME_LBA_RANGE = 0x0080,
> NVME_CAP_EXCEEDED = 0x0081,
> NVME_NS_NOT_READY = 0x0082,
> @@ -684,6 +689,14 @@ enum NvmeStatusCodes {
> NVME_CONFLICTING_ATTRS = 0x0180,
> NVME_INVALID_PROT_INFO = 0x0181,
> NVME_WRITE_TO_RO = 0x0182,
> + NVME_ZONE_BOUNDARY_ERROR = 0x01b8,
> + NVME_ZONE_FULL = 0x01b9,
> + NVME_ZONE_READ_ONLY = 0x01ba,
> + NVME_ZONE_OFFLINE = 0x01bb,
> + NVME_ZONE_INVALID_WRITE = 0x01bc,
> + NVME_ZONE_TOO_MANY_ACTIVE = 0x01bd,
> + NVME_ZONE_TOO_MANY_OPEN = 0x01be,
> + NVME_ZONE_INVAL_TRANSITION = 0x01bf,
> NVME_WRITE_FAULT = 0x0280,
> NVME_UNRECOVERED_READ = 0x0281,
> NVME_E2E_GUARD_ERROR = 0x0282,
> @@ -807,7 +820,17 @@ typedef struct NvmeIdCtrl {
> uint8_t ieee[3];
> uint8_t cmic;
> uint8_t mdts;
> - uint8_t rsvd255[178];
> + uint16_t cntlid;
> + uint32_t ver;
> + uint32_t rtd3r;
> + uint32_t rtd3e;
> + uint32_t oaes;
> + uint32_t ctratt;
> + uint8_t rsvd100[28];
> + uint16_t crdt1;
> + uint16_t crdt2;
> + uint16_t crdt3;
> + uint8_t rsvd134[122];
> uint16_t oacs;
> uint8_t acl;
> uint8_t aerl;
> @@ -832,6 +855,11 @@ typedef struct NvmeIdCtrl {
> uint8_t vs[1024];
> } NvmeIdCtrl;
>
> +typedef struct NvmeIdCtrlZoned {
> + uint8_t zamds;
> + uint8_t rsvd1[4095];
> +} NvmeIdCtrlZoned;
> +
> enum NvmeIdCtrlOacs {
> NVME_OACS_SECURITY = 1 << 0,
> NVME_OACS_FORMAT = 1 << 1,
> @@ -908,6 +936,12 @@ typedef struct NvmeLBAF {
> uint8_t rp;
> } NvmeLBAF;
>
> +typedef struct NvmeLBAFE {
> + uint64_t zsze;
> + uint8_t zdes;
> + uint8_t rsvd9[7];
> +} NvmeLBAFE;
> +
> typedef struct NvmeIdNs {
> uint64_t nsze;
> uint64_t ncap;
> @@ -930,6 +964,19 @@ typedef struct NvmeIdNs {
> uint8_t vs[3712];
> } NvmeIdNs;
>
> +typedef struct NvmeIdNsZoned {
> + uint16_t zoc;
> + uint16_t ozcs;
> + uint32_t mar;
> + uint32_t mor;
> + uint32_t rrl;
> + uint32_t frl;
> + uint8_t rsvd20[2796];
> + NvmeLBAFE lbafe[16];
> + uint8_t rsvd3072[768];
> + uint8_t vs[256];
> +} NvmeIdNsZoned;
> +
>
> /*Deallocate Logical Block Features*/
> #define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10)
> @@ -962,6 +1009,71 @@ enum NvmeIdNsDps {
> DPS_FIRST_EIGHT = 8,
> };
>
> +enum NvmeZoneAttr {
> + NVME_ZA_FINISHED_BY_CTLR = 1 << 0,
> + NVME_ZA_FINISH_RECOMMENDED = 1 << 1,
> + NVME_ZA_RESET_RECOMMENDED = 1 << 2,
> + NVME_ZA_ZD_EXT_VALID = 1 << 7,
> +};
> +
> +typedef struct NvmeZoneReportHeader {
> + uint64_t nr_zones;
> + uint8_t rsvd[56];
> +} NvmeZoneReportHeader;
> +
> +enum NvmeZoneReceiveAction {
> + NVME_ZONE_REPORT = 0,
> + NVME_ZONE_REPORT_EXTENDED = 1,
> +};
> +
> +enum NvmeZoneReportType {
> + NVME_ZONE_REPORT_ALL = 0,
> + NVME_ZONE_REPORT_EMPTY = 1,
> + NVME_ZONE_REPORT_IMPLICITLY_OPEN = 2,
> + NVME_ZONE_REPORT_EXPLICITLY_OPEN = 3,
> + NVME_ZONE_REPORT_CLOSED = 4,
> + NVME_ZONE_REPORT_FULL = 5,
> + NVME_ZONE_REPORT_READ_ONLY = 6,
> + NVME_ZONE_REPORT_OFFLINE = 7,
> +};
> +
> +typedef struct NvmeZoneDescr {
> + uint8_t zt;
> + uint8_t zs;
> + uint8_t za;
> + uint8_t rsvd3[5];
> + uint64_t zcap;
> + uint64_t zslba;
> + uint64_t wp;
> + uint8_t rsvd32[32];
> +} NvmeZoneDescr;
> +
> +enum NvmeZoneState {
> + NVME_ZONE_STATE_RESERVED = 0x00,
> + NVME_ZONE_STATE_EMPTY = 0x01,
> + NVME_ZONE_STATE_IMPLICITLY_OPEN = 0x02,
> + NVME_ZONE_STATE_EXPLICITLY_OPEN = 0x03,
> + NVME_ZONE_STATE_CLOSED = 0x04,
> + NVME_ZONE_STATE_READ_ONLY = 0x0D,
> + NVME_ZONE_STATE_FULL = 0x0E,
> + NVME_ZONE_STATE_OFFLINE = 0x0F,
> +};
> +
> +enum NvmeZoneType {
> + NVME_ZONE_TYPE_RESERVED = 0x00,
> + NVME_ZONE_TYPE_SEQ_WRITE = 0x02,
> +};
> +
> +enum NvmeZoneSendAction {
> + NVME_ZONE_ACTION_RSD = 0x00,
> + NVME_ZONE_ACTION_CLOSE = 0x01,
> + NVME_ZONE_ACTION_FINISH = 0x02,
> + NVME_ZONE_ACTION_OPEN = 0x03,
> + NVME_ZONE_ACTION_RESET = 0x04,
> + NVME_ZONE_ACTION_OFFLINE = 0x05,
> + NVME_ZONE_ACTION_SET_ZD_EXT = 0x10,
> +};
> +
> static inline void _nvme_check_size(void)
> {
> QEMU_BUILD_BUG_ON(sizeof(NvmeCqe) != 16);
> @@ -978,8 +1090,13 @@ static inline void _nvme_check_size(void)
> QEMU_BUILD_BUG_ON(sizeof(NvmeFwSlotInfoLog) != 512);
> QEMU_BUILD_BUG_ON(sizeof(NvmeSmartLog) != 512);
> QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrl) != 4096);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrlZoned) != 4096);
> QEMU_BUILD_BUG_ON(sizeof(NvmeNsIdDesc) != 4);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeLBAF) != 4);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeLBAFE) != 16);
> QEMU_BUILD_BUG_ON(sizeof(NvmeIdNs) != 4096);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeIdNsZoned) != 4096);
> QEMU_BUILD_BUG_ON(sizeof(NvmeEffectsLog) != 4096);
> + QEMU_BUILD_BUG_ON(sizeof(NvmeZoneDescr) != 64);
> }
> #endif
> --
> 2.21.0
>
>
- Re: [PATCH v2 05/18] hw/block/nvme: Introduce the Namespace Types definitions, (continued)
- [PATCH v2 06/18] hw/block/nvme: Define trace events related to NS Types, Dmitry Fomichev, 2020/06/17
- [PATCH v2 07/18] hw/block/nvme: Add support for Namespace Types, Dmitry Fomichev, 2020/06/17
- [PATCH v2 08/18] hw/block/nvme: Make Zoned NS Command Set definitions, Dmitry Fomichev, 2020/06/17
- [PATCH v2 09/18] hw/block/nvme: Define Zoned NS Command Set trace events, Dmitry Fomichev, 2020/06/17
- [PATCH v2 10/18] hw/block/nvme: Support Zoned Namespace Command Set, Dmitry Fomichev, 2020/06/17
- [PATCH v2 12/18] hw/block/nvme: Simulate Zone Active excursions, Dmitry Fomichev, 2020/06/17
- [PATCH v2 11/18] hw/block/nvme: Introduce max active and open zone limits, Dmitry Fomichev, 2020/06/17
- [PATCH v2 13/18] hw/block/nvme: Set Finish/Reset Zone Recommended attributes, Dmitry Fomichev, 2020/06/17
- [PATCH v2 15/18] hw/block/nvme: Support Zone Descriptor Extensions, Dmitry Fomichev, 2020/06/17