diff mbox series

[v2,08/15] hw/block/nvme: Make Zoned NS Command Set definitions

Message ID 20200912225430.1772-9-dmitry.fomichev@wdc.com
State New
Headers show
Series hw/block/nvme: Support Namespace Types and Zoned Namespace Command Set | expand

Commit Message

Dmitry Fomichev Sept. 12, 2020, 10:54 p.m. UTC
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      | 124 +++++++++++++++++++++++++++++++++++++++++++
 include/block/nvme.h | 107 +++++++++++++++++++++++++++++++++++++
 2 files changed, 231 insertions(+)
diff mbox series

Patch

diff --git a/hw/block/nvme.h b/hw/block/nvme.h
index dec337bbf9..9514c58919 100644
--- a/hw/block/nvme.h
+++ b/hw/block/nvme.h
@@ -3,6 +3,9 @@ 
 
 #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 */
@@ -12,6 +15,13 @@  typedef struct NvmeParams {
     uint8_t  aerl;
     uint32_t aer_max_queued;
     uint8_t  mdts;
+
+    bool        zoned;
+    bool        cross_zone_read;
+    uint8_t     fill_pattern;
+    uint32_t    zasl_kb;
+    uint64_t    zone_size_mb;
+    uint64_t    zone_capacity_mb;
 } NvmeParams;
 
 typedef struct NvmeAsyncEvent {
@@ -24,6 +34,7 @@  typedef struct NvmeRequest {
     struct NvmeNamespace    *ns;
     BlockAIOCB              *aiocb;
     uint16_t                status;
+    int64_t                 fill_ofs;
     NvmeCqe                 cqe;
     NvmeCmd                 cmd;
     BlockAcctCookie         acct;
@@ -62,12 +73,36 @@  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;
     bool            attached;
     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)
@@ -126,6 +161,15 @@  typedef struct NvmeCtrl {
     QTAILQ_HEAD(, NvmeAsyncEvent) aer_queue;
     int         aer_queued;
 
+    int             zone_file_fd;
+    uint32_t        num_zones;
+    uint64_t        zone_size;
+    uint64_t        zone_capacity;
+    uint64_t        zone_array_size;
+    uint32_t        zone_size_log2;
+    uint32_t        zasl_bs;
+    uint8_t         zasl;
+
     NvmeNamespace   *namespaces;
     NvmeSQueue      **sq;
     NvmeCQueue      **cq;
@@ -141,6 +185,86 @@  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->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.
+ */
+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);
+}
+
+/*
+ * 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;
diff --git a/include/block/nvme.h b/include/block/nvme.h
index 53b0463a2a..772659859e 100644
--- a/include/block/nvme.h
+++ b/include/block/nvme.h
@@ -488,6 +488,9 @@  enum NvmeIoCommands {
     NVME_CMD_COMPARE            = 0x05,
     NVME_CMD_WRITE_ZEROES       = 0x08,
     NVME_CMD_DSM                = 0x09,
+    NVME_CMD_ZONE_MGMT_SEND     = 0x79,
+    NVME_CMD_ZONE_MGMT_RECV     = 0x7a,
+    NVME_CMD_ZONE_APND          = 0x7d,
 };
 
 typedef struct QEMU_PACKED NvmeDeleteQ {
@@ -679,6 +682,7 @@  enum NvmeStatusCodes {
     NVME_SGL_DESCR_TYPE_INVALID = 0x0011,
     NVME_INVALID_USE_OF_CMB     = 0x0012,
     NVME_CMD_SET_CMB_REJECTED   = 0x002b,
+    NVME_INVALID_CMD_SET        = 0x002c,
     NVME_LBA_RANGE              = 0x0080,
     NVME_CAP_EXCEEDED           = 0x0081,
     NVME_NS_NOT_READY           = 0x0082,
@@ -703,6 +707,14 @@  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,
@@ -887,6 +899,11 @@  typedef struct QEMU_PACKED NvmeIdCtrl {
     uint8_t     vs[1024];
 } NvmeIdCtrl;
 
+typedef struct NvmeIdCtrlZoned {
+    uint8_t     zasl;
+    uint8_t     rsvd1[4095];
+} NvmeIdCtrlZoned;
+
 enum NvmeIdCtrlOacs {
     NVME_OACS_SECURITY  = 1 << 0,
     NVME_OACS_FORMAT    = 1 << 1,
@@ -1011,6 +1028,12 @@  typedef struct QEMU_PACKED NvmeLBAF {
     uint8_t     rp;
 } NvmeLBAF;
 
+typedef struct QEMU_PACKED NvmeLBAFE {
+    uint64_t    zsze;
+    uint8_t     zdes;
+    uint8_t     rsvd9[7];
+} NvmeLBAFE;
+
 #define NVME_NSID_BROADCAST 0xffffffff
 
 typedef struct QEMU_PACKED NvmeIdNs {
@@ -1065,10 +1088,24 @@  enum NvmeNsIdentifierType {
 
 enum NvmeCsi {
     NVME_CSI_NVM                = 0x00,
+    NVME_CSI_ZONED              = 0x02,
 };
 
 #define NVME_SET_CSI(vec, csi) (vec |= (uint8_t)(1 << (csi)))
 
+typedef struct QEMU_PACKED 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)
 #define NVME_ID_NS_DLFEAT_WRITE_ZEROES(dlfeat)    ((dlfeat) & 0x08)
@@ -1100,6 +1137,71 @@  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 QEMU_PACKED 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,
+};
+
+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,
+};
+
+typedef struct QEMU_PACKED 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,
+};
+
 static inline void _nvme_check_size(void)
 {
     QEMU_BUILD_BUG_ON(sizeof(NvmeBar) != 4096);
@@ -1119,9 +1221,14 @@  static inline void _nvme_check_size(void)
     QEMU_BUILD_BUG_ON(sizeof(NvmeSmartLog) != 512);
     QEMU_BUILD_BUG_ON(sizeof(NvmeEffectsLog) != 4096);
     QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrl) != 4096);
+    QEMU_BUILD_BUG_ON(sizeof(NvmeIdCtrlZoned) != 4096);
     QEMU_BUILD_BUG_ON(sizeof(NvmeIdNsDescr) != 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(NvmeSglDescriptor) != 16);
     QEMU_BUILD_BUG_ON(sizeof(NvmeIdNsDescr) != 4);
+    QEMU_BUILD_BUG_ON(sizeof(NvmeZoneDescr) != 64);
 }
 #endif