hw/block/nvme: AIO and address mapping refactoring
cover hw/block/nvme: AIO and address mapping refactoring
From: Klaus Jensen <[email protected]>
This series is based on "[PATCH 00/17] hw/block/nvme: bump to v1.3" and mostly consists of patches that refactors and clean up dma/cmb address mappings.
The "hw/block/nvme: allow multiple aios per command" patch does what it says on the tin and is in preparation for metadata, dulbe, write uncorrectable and any upcoming feature that requires additional persistent state to be modified per command in an asynchronous manner.
Based-on: <[email protected]> ([PATCH 00/17] hw/block/nvme: bump to v1.3)
Klaus Jensen (17):
hw/block/nvme: memset preallocated requests structures hw/block/nvme: add mapping helpers hw/block/nvme: replace dma_acct with blk_acct equivalent hw/block/nvme: remove redundant has_sg member hw/block/nvme: refactor dma read/write hw/block/nvme: pass request along for tracing hw/block/nvme: add request mapping helper hw/block/nvme: verify validity of prp lists in the cmb hw/block/nvme: refactor request bounds checking hw/block/nvme: add check for mdts hw/block/nvme: be consistent about zeros vs zeroes hw/block/nvme: refactor NvmeRequest clearing hw/block/nvme: consolidate qsg/iov clearing hw/block/nvme: remove NvmeCmd parameter hw/block/nvme: allow multiple aios per command hw/block/nvme: add nvme_check_rw helper hw/block/nvme: use preallocated qsg/iov in nvme_dma_prp
block/nvme.c | 4 +- hw/block/nvme.c | 834 ++++++++++++++++++++++++++++++------------ hw/block/nvme.h | 104 +++++- hw/block/trace-events | 7 + include/block/nvme.h | 4 +- 5 files changed, 699 insertions(+), 254 deletions(-)
Signature · 1 line
2.27.0
PATCH 1/17 hw/block/nvme: memset preallocated requests structures
From: Klaus Jensen <[email protected]>
This is preparatory to subsequent patches that change how QSGs/IOVs are handled. It is important that the qsg and iov members of the NvmeRequest are initially zeroed.
--- hw/block/nvme.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
hw/block/nvme.c +1 -1
@@ -618,7 +618,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr, sq->size = size; sq->cqid = cqid; sq->head = sq->tail =0 ; - sq->io_req =g_new (NvmeRequest, sq->size); + sq->io_req =g_new0 (NvmeRequest, sq->size);QTAILQ_INIT (&sq->req_list);QTAILQ_INIT (&sq->out_req_list);
Signature · 1 line
2.27.0
PATCH 2/17 hw/block/nvme: add mapping helpers
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Add nvme_map_addr, nvme_map_addr_cmb and nvme_addr_to_cmb helpers and use them in nvme_map_prp.
This fixes a bug where in the case of a CMB transfer, the device would map to the buffer with a wrong length.
--- hw/block/nvme.c | 109 +++++++++++++++++++++++++++++++++++------- hw/block/trace-events | 2 + 2 files changed, 94 insertions(+), 17 deletions(-)
hw/block/nvme.c +92 -17
@@ -74,6 +74,11 @@static void nvme_process_sq (void *opaque); +static inline void *nvme_addr_to_cmb (NvmeCtrl *n,hwaddr addr) +{ +return &n->cmbuf[addr - n->ctrl_mem.addr]; +} +static bool nvme_addr_is_cmb (NvmeCtrl *n,hwaddr addr) {hwaddr low = n->ctrl_mem.addr;
@@ -85,7 +90,7 @@ static bool nvme_addr_is_cmb(NvmeCtrl *n, hwaddr addr)static void nvme_addr_read (NvmeCtrl *n,hwaddr addr,void *buf,int size) {if (n->bar.cmbsz &&nvme_addr_is_cmb (n, addr)) { -memcpy (buf, (void *)&n->cmbuf[addr - n->ctrl_mem.addr], size); +memcpy (buf,nvme_addr_to_cmb (n, addr), size);return ; }
@@ -168,29 +173,91 @@ static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq) } } +static uint16_t nvme_map_addr_cmb (NvmeCtrl *n,QEMUIOVector *iov,hwaddr addr, +size_t len) +{ +if (!len) { +return NVME_SUCCESS ; + } + +trace_pci_nvme_map_addr_cmb (addr, len); + +if (!nvme_addr_is_cmb (n, addr) || !nvme_addr_is_cmb (n, addr + len -1 )) { +return NVME_DATA_TRAS_ERROR ; + } + +qemu_iovec_add (iov,nvme_addr_to_cmb (n, addr), len); + +return NVME_SUCCESS ; +} + +static uint16_t nvme_map_addr (NvmeCtrl *n,QEMUSGList *qsg,QEMUIOVector *iov, +hwaddr addr,size_t len) +{ +if (!len) { +return NVME_SUCCESS ; + } + +trace_pci_nvme_map_addr (addr, len); + +if (nvme_addr_is_cmb (n, addr)) { +if (qsg && qsg->sg) { +return NVME_INVALID_USE_OF_CMB |NVME_DNR ; + } + +assert (iov); + +if (!iov->iov) { +qemu_iovec_init (iov,1 ); + } + +return nvme_map_addr_cmb (n, iov, addr, len); + } + +if (iov && iov->iov) { +return NVME_INVALID_USE_OF_CMB |NVME_DNR ; + } + +assert (qsg); + +if (!qsg->sg) { +pci_dma_sglist_init (qsg, &n->parent_obj,1 ); + } + +qemu_sglist_add (qsg, addr, len); + +return NVME_SUCCESS ; +} +static uint16_t nvme_map_prp (QEMUSGList *qsg,QEMUIOVector *iov,uint64_t prp1,uint64_t prp2,uint32_t len,NvmeCtrl *n) {hwaddr trans_len = n->page_size - (prp1 % n->page_size); trans_len =MIN (len, trans_len);int num_prps = (len >> n->page_bits) +1 ; +uint16_t status;if (unlikely (!prp1)) {trace_pci_nvme_err_invalid_prp ();return NVME_INVALID_FIELD |NVME_DNR ; - }else if (n->bar.cmbsz && prp1 >= n->ctrl_mem.addr && - prp1 < n->ctrl_mem.addr +int128_get64 (n->ctrl_mem.size)) { - qsg->nsg =0 ; + } + +if (nvme_addr_is_cmb (n, prp1)) {qemu_iovec_init (iov, num_prps); -qemu_iovec_add (iov, (void *)&n->cmbuf[prp1 - n->ctrl_mem.addr], trans_len); }else {pci_dma_sglist_init (qsg, &n->parent_obj, num_prps); -qemu_sglist_add (qsg, prp1, trans_len); } + + status =nvme_map_addr (n, qsg, iov, prp1, trans_len); +if (status) { + goto unmap; + } + len -= trans_len;if (len) {if (unlikely (!prp2)) {trace_pci_nvme_err_invalid_prp2_missing (); + status =NVME_INVALID_FIELD |NVME_DNR ; goto unmap; }if (len > n->page_size) {
@@ -207,6 +274,7 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,if (i == n->max_prp_ents -1 && len > n->page_size) {if (unlikely (!prp_ent || prp_ent & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prplist_ent (prp_ent); + status =NVME_INVALID_FIELD |NVME_DNR ; goto unmap; }
@@ -220,14 +288,14 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1,if (unlikely (!prp_ent || prp_ent & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prplist_ent (prp_ent); + status =NVME_INVALID_FIELD |NVME_DNR ; goto unmap; } trans_len =MIN (len, n->page_size); -if (qsg->nsg){ -qemu_sglist_add (qsg, prp_ent, trans_len); - }else { -qemu_iovec_add (iov, (void *)&n->cmbuf[prp_ent - n->ctrl_mem.addr], trans_len); + status =nvme_map_addr (n, qsg, iov, prp_ent, trans_len); +if (status) { + goto unmap; } len -= trans_len; i++;
@@ -235,20 +303,27 @@ static uint16_t nvme_map_prp(QEMUSGList *qsg, QEMUIOVector *iov, uint64_t prp1, }else {if (unlikely (prp2 & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prp2_align (prp2); + status =NVME_INVALID_FIELD |NVME_DNR ; goto unmap; } -if (qsg->nsg) { -qemu_sglist_add (qsg, prp2, len); - }else { -qemu_iovec_add (iov, (void *)&n->cmbuf[prp2 - n->ctrl_mem.addr], trans_len); + status =nvme_map_addr (n, qsg, iov, prp2, len); +if (status) { + goto unmap; } } }return NVME_SUCCESS ; - unmap: -qemu_sglist_destroy (qsg); -return NVME_INVALID_FIELD |NVME_DNR ; +unmap: +if (iov && iov->iov) { +qemu_iovec_destroy (iov); + } + +if (qsg && qsg->sg) { +qemu_sglist_destroy (qsg); + } + +return status; } static uint16_t nvme_dma_write_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
hw/block/trace-events +2 -0
@@ -33,6 +33,8 @@ pci_nvme_irq_msix(uint32_t vector) "raising MSI-X IRQ vector %u" pci_nvme_irq_pin(void) "pulsing IRQ pin" pci_nvme_irq_masked(void) "IRQ is masked" pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" +pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" +pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
Signature · 1 line
2.27.0
PATCH 3/17 hw/block/nvme: replace dma_acct with blk_acct equivalent
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
The QSG isn't always initialized, so accounting could be wrong. Issue a call to blk_acct_start instead with the size taken from the QSG or IOV depending on the kind of I/O.
--- hw/block/nvme.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)
hw/block/nvme.c +4 -1
@@ -585,9 +585,10 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_INVALID_FIELD |NVME_DNR ; } -dma_acct_start (n->conf.blk, &req->acct, &req->qsg, acct);if (req->qsg.nsg >0 ) { req->has_sg = true; +block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->qsg.size, + acct); req->aiocb = is_write ?dma_blk_write (n->conf.blk, &req->qsg, data_offset,BDRV_SECTOR_SIZE , nvme_rw_cb, req) :
@@ -595,6 +596,8 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, nvme_rw_cb, req); }else { req->has_sg = false; +block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->iov.size, + acct); req->aiocb = is_write ?blk_aio_pwritev (n->conf.blk, data_offset, &req->iov,0 , nvme_rw_cb, req) :
Signature · 1 line
2.27.0
PATCH 4/17 hw/block/nvme: remove redundant has_sg member
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Remove the has_sg member from NvmeRequest since it's redundant.
Also, make sure the request iov is destroyed at completion time.
--- hw/block/nvme.c | 11 ++++++----- hw/block/nvme.h | 1 - 2 files changed, 6 insertions(+), 6 deletions(-)
hw/block/nvme.c +6 -5
@@ -513,16 +513,20 @@ static void nvme_rw_cb(void *opaque, int ret)block_acct_failed (blk_get_stats (n->conf.blk), &req->acct); req->status =NVME_INTERNAL_DEV_ERROR ; } -if (req->has_sg) { + +if (req->qsg.nalloc) {qemu_sglist_destroy (&req->qsg); } +if (req->iov.nalloc) { +qemu_iovec_destroy (&req->iov); + } +nvme_enqueue_req_completion (cq, req); }static uint16_t nvme_flush (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd,NvmeRequest *req) { - req->has_sg = false;block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 ,BLOCK_ACCT_FLUSH ); req->aiocb =blk_aio_flush (n->conf.blk, nvme_rw_cb, req);
@@ -548,7 +552,6 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_LBA_RANGE |NVME_DNR ; } - req->has_sg = false;block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 ,BLOCK_ACCT_WRITE ); req->aiocb = blk_aio_pwrite_zeroes(n->conf.blk, offset, count,
@@ -586,7 +589,6 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd, }if (req->qsg.nsg >0 ) { - req->has_sg = true;block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->qsg.size, acct); req->aiocb = is_write ?
@@ -595,7 +597,6 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,dma_blk_read (n->conf.blk, &req->qsg, data_offset,BDRV_SECTOR_SIZE , nvme_rw_cb, req); }else { - req->has_sg = false;block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->iov.size, acct); req->aiocb = is_write ?
hw/block/nvme.h +0 -1
@@ -22,7 +22,6 @@ typedef struct NvmeRequest {struct NvmeSQueue *sq;BlockAIOCB *aiocb;uint16_t status; -bool has_sg;NvmeCqe cqe;BlockAcctCookie acct;QEMUSGList qsg;
Signature · 1 line
2.27.0
PATCH 5/17 hw/block/nvme: refactor dma read/write
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Refactor the nvme_dma_{read,write}_prp functions into a common function taking a DMADirection parameter.
--- hw/block/nvme.c | 88 ++++++++++++++++++++++++------------------------- 1 file changed, 43 insertions(+), 45 deletions(-)
hw/block/nvme.c +43 -45
@@ -326,55 +326,50 @@ unmap:return status; } -static uint16_t nvme_dma_write_prp (NvmeCtrl *n,uint8_t *ptr,uint32_t len, -uint64_t prp1,uint64_t prp2) +static uint16_t nvme_dma_prp (NvmeCtrl *n,uint8_t *ptr,uint32_t len, +uint64_t prp1,uint64_t prp2,DMADirection dir) {QEMUSGList qsg;QEMUIOVector iov;uint16_t status =NVME_SUCCESS ; -if (nvme_map_prp (&qsg, &iov, prp1, prp2, len, n)) { -return NVME_INVALID_FIELD |NVME_DNR ; + status =nvme_map_prp (&qsg, &iov, prp1, prp2, len, n); +if (status) { +return status; } +if (qsg.nsg >0 ) { -if (dma_buf_write (ptr, len, &qsg)) { - status =NVME_INVALID_FIELD |NVME_DNR ; +uint64_t residual; + +if (dir ==DMA_DIRECTION_TO_DEVICE ) { + residual =dma_buf_write (ptr, len, &qsg); + }else { + residual =dma_buf_read (ptr, len, &qsg); } -qemu_sglist_destroy (&qsg); - }else { -if (qemu_iovec_to_buf (&iov,0 , ptr, len) != len) { - status =NVME_INVALID_FIELD |NVME_DNR ; - } -qemu_iovec_destroy (&iov); - } -return status; -} -static uint16_t nvme_dma_read_prp (NvmeCtrl *n,uint8_t *ptr,uint32_t len, -uint64_t prp1,uint64_t prp2) -{ -QEMUSGList qsg; -QEMUIOVector iov; -uint16_t status =NVME_SUCCESS ; - -trace_pci_nvme_dma_read (prp1, prp2); - -if (nvme_map_prp (&qsg, &iov, prp1, prp2, len, n)) { -return NVME_INVALID_FIELD |NVME_DNR ; - } -if (qsg.nsg >0 ) { -if (unlikely (dma_buf_read (ptr, len, &qsg))) { +if (unlikely (residual)) {trace_pci_nvme_err_invalid_dma (); status =NVME_INVALID_FIELD |NVME_DNR ; } +qemu_sglist_destroy (&qsg); }else { -if (unlikely (qemu_iovec_from_buf (&iov,0 , ptr, len) != len)) { +size_t bytes; + +if (dir ==DMA_DIRECTION_TO_DEVICE ) { + bytes =qemu_iovec_to_buf (&iov,0 , ptr, len); + }else { + bytes =qemu_iovec_from_buf (&iov,0 , ptr, len); + } + +if (unlikely (bytes != len)) {trace_pci_nvme_err_invalid_dma (); status =NVME_INVALID_FIELD |NVME_DNR ; } +qemu_iovec_destroy (&iov); } +return status; }
@@ -806,8 +801,8 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,nvme_clear_events (n,NVME_AER_TYPE_SMART ); } -return nvme_dma_read_prp (n, (uint8_t *) &smart + off, trans_len, prp1, - prp2); +return nvme_dma_prp (n, (uint8_t *) &smart + off, trans_len, prp1, prp2, +DMA_DIRECTION_FROM_DEVICE ); } static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
@@ -828,8 +823,8 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len, trans_len =MIN (sizeof (fw_log) - off, buf_len); -return nvme_dma_read_prp (n, (uint8_t *) &fw_log + off, trans_len, prp1, - prp2); +return nvme_dma_prp (n, (uint8_t *) &fw_log + off, trans_len, prp1, prp2, +DMA_DIRECTION_FROM_DEVICE ); } static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
@@ -853,7 +848,8 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae, trans_len =MIN (sizeof (errlog) - off, buf_len); -return nvme_dma_read_prp (n, (uint8_t *)&errlog, trans_len, prp1, prp2); +return nvme_dma_prp (n, (uint8_t *)&errlog, trans_len, prp1, prp2, +DMA_DIRECTION_FROM_DEVICE ); }static uint16_t nvme_get_log (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req)
@@ -1008,8 +1004,8 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)trace_pci_nvme_identify_ctrl (); -return nvme_dma_read_prp (n, (uint8_t *)&n->id_ctrl,sizeof (n->id_ctrl), - prp1, prp2); +return nvme_dma_prp (n, (uint8_t *)&n->id_ctrl,sizeof (n->id_ctrl), prp1, + prp2,DMA_DIRECTION_FROM_DEVICE ); }static uint16_t nvme_identify_ns (NvmeCtrl *n,NvmeIdentify *c)
@@ -1028,8 +1024,8 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) ns = &n->namespaces[nsid -1 ]; -return nvme_dma_read_prp (n, (uint8_t *)&ns->id_ns,sizeof (ns->id_ns), - prp1, prp2); +return nvme_dma_prp (n, (uint8_t *)&ns->id_ns,sizeof (ns->id_ns), prp1, + prp2,DMA_DIRECTION_FROM_DEVICE ); }static uint16_t nvme_identify_nslist (NvmeCtrl *n,NvmeIdentify *c)
@@ -1054,7 +1050,8 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c)break ; } } - ret =nvme_dma_read_prp (n, (uint8_t *)list, data_len, prp1, prp2); + ret =nvme_dma_prp (n, (uint8_t *)list, data_len, prp1, prp2, +DMA_DIRECTION_FROM_DEVICE );g_free (list);return ret; }
@@ -1095,7 +1092,8 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c) ns_descrs->uuid.hdr.nidl =NVME_NIDT_UUID_LEN ;stl_be_p (&ns_descrs->uuid.v, nsid); -return nvme_dma_read_prp (n, list,NVME_IDENTIFY_DATA_SIZE , prp1, prp2); +return nvme_dma_prp (n, list,NVME_IDENTIFY_DATA_SIZE , prp1, prp2, +DMA_DIRECTION_FROM_DEVICE ); }static uint16_t nvme_identify (NvmeCtrl *n,NvmeCmd *cmd)
@@ -1176,8 +1174,8 @@ static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)uint64_t timestamp =nvme_get_timestamp (n); -return nvme_dma_read_prp (n, (uint8_t *)×tamp, -sizeof (timestamp), prp1, prp2); +return nvme_dma_prp (n, (uint8_t *)×tamp,sizeof (timestamp), prp1, + prp2,DMA_DIRECTION_FROM_DEVICE ); }static uint16_t nvme_get_feature (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req)
@@ -1305,8 +1303,8 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2); - ret =nvme_dma_write_prp (n, (uint8_t *)×tamp, -sizeof (timestamp), prp1, prp2); + ret =nvme_dma_prp (n, (uint8_t *)×tamp,sizeof (timestamp), prp1, + prp2,DMA_DIRECTION_TO_DEVICE );if (ret !=NVME_SUCCESS ) {return ret; }
Signature · 1 line
2.27.0
PATCH 6/17 hw/block/nvme: pass request along for tracing
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Pass along the NvmeRequest in various functions since it is very useful for tracing.
--- hw/block/nvme.c | 67 +++++++++++++++++++++++++------------------ hw/block/trace-events | 1 + 2 files changed, 40 insertions(+), 28 deletions(-)
hw/block/nvme.c +39 -28
@@ -229,14 +229,18 @@ static uint16_t nvme_map_addr(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov,return NVME_SUCCESS ; } -static uint16_t nvme_map_prp (QEMUSGList *qsg,QEMUIOVector *iov,uint64_t prp1, -uint64_t prp2,uint32_t len,NvmeCtrl *n) +static uint16_t nvme_map_prp (NvmeCtrl *n,QEMUSGList *qsg,QEMUIOVector *iov, +uint64_t prp1,uint64_t prp2,uint32_t len, +NvmeRequest *req) {hwaddr trans_len = n->page_size - (prp1 % n->page_size); trans_len =MIN (len, trans_len);int num_prps = (len >> n->page_bits) +1 ;uint16_t status; +trace_pci_nvme_map_prp (nvme_cid (req), trans_len, len, prp1, prp2, + num_prps); +if (unlikely (!prp1)) {trace_pci_nvme_err_invalid_prp ();return NVME_INVALID_FIELD |NVME_DNR ;
@@ -327,13 +331,14 @@ unmap: }static uint16_t nvme_dma_prp (NvmeCtrl *n,uint8_t *ptr,uint32_t len, -uint64_t prp1,uint64_t prp2,DMADirection dir) +uint64_t prp1,uint64_t prp2,DMADirection dir, +NvmeRequest *req) {QEMUSGList qsg;QEMUIOVector iov;uint16_t status =NVME_SUCCESS ; - status =nvme_map_prp (&qsg, &iov, prp1, prp2, len, n); + status =nvme_map_prp (n, &qsg, &iov, prp1, prp2, len, req);if (status) {return status; }
@@ -578,7 +583,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_LBA_RANGE |NVME_DNR ; } -if (nvme_map_prp (&req->qsg, &req->iov, prp1, prp2, data_size, n)) { +if (nvme_map_prp (n, &req->qsg, &req->iov, prp1, prp2, data_size, req)) {block_acct_invalid (blk_get_stats (n->conf.blk), acct);return NVME_INVALID_FIELD |NVME_DNR ; }
@@ -802,7 +807,7 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae, }return nvme_dma_prp (n, (uint8_t *) &smart + off, trans_len, prp1, prp2, -DMA_DIRECTION_FROM_DEVICE ); +DMA_DIRECTION_FROM_DEVICE , req); } static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len,
@@ -824,7 +829,7 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len, trans_len =MIN (sizeof (fw_log) - off, buf_len);return nvme_dma_prp (n, (uint8_t *) &fw_log + off, trans_len, prp1, prp2, -DMA_DIRECTION_FROM_DEVICE ); +DMA_DIRECTION_FROM_DEVICE , req); } static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae,
@@ -849,7 +854,7 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae, trans_len =MIN (sizeof (errlog) - off, buf_len);return nvme_dma_prp (n, (uint8_t *)&errlog, trans_len, prp1, prp2, -DMA_DIRECTION_FROM_DEVICE ); +DMA_DIRECTION_FROM_DEVICE , req); }static uint16_t nvme_get_log (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req)
@@ -997,7 +1002,8 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)return NVME_SUCCESS ; } -static uint16_t nvme_identify_ctrl (NvmeCtrl *n,NvmeIdentify *c) +static uint16_t nvme_identify_ctrl (NvmeCtrl *n,NvmeIdentify *c, +NvmeRequest *req) {uint64_t prp1 =le64_to_cpu (c->prp1);uint64_t prp2 =le64_to_cpu (c->prp2);
@@ -1005,10 +1011,11 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c)trace_pci_nvme_identify_ctrl ();return nvme_dma_prp (n, (uint8_t *)&n->id_ctrl,sizeof (n->id_ctrl), prp1, - prp2,DMA_DIRECTION_FROM_DEVICE ); + prp2,DMA_DIRECTION_FROM_DEVICE , req); } -static uint16_t nvme_identify_ns (NvmeCtrl *n,NvmeIdentify *c) +static uint16_t nvme_identify_ns (NvmeCtrl *n,NvmeIdentify *c, +NvmeRequest *req) {NvmeNamespace *ns;uint32_t nsid =le32_to_cpu (c->nsid);
@@ -1025,10 +1032,11 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c) ns = &n->namespaces[nsid -1 ];return nvme_dma_prp (n, (uint8_t *)&ns->id_ns,sizeof (ns->id_ns), prp1, - prp2,DMA_DIRECTION_FROM_DEVICE ); + prp2,DMA_DIRECTION_FROM_DEVICE , req); } -static uint16_t nvme_identify_nslist (NvmeCtrl *n,NvmeIdentify *c) +static uint16_t nvme_identify_nslist (NvmeCtrl *n,NvmeIdentify *c, +NvmeRequest *req) {static const int data_len =NVME_IDENTIFY_DATA_SIZE ;uint32_t min_nsid =le32_to_cpu (c->nsid);
@@ -1051,12 +1059,13 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c) } } ret =nvme_dma_prp (n, (uint8_t *)list, data_len, prp1, prp2, -DMA_DIRECTION_FROM_DEVICE ); +DMA_DIRECTION_FROM_DEVICE , req);g_free (list);return ret; } -static uint16_t nvme_identify_ns_descr_list (NvmeCtrl *n,NvmeIdentify *c) +static uint16_t nvme_identify_ns_descr_list (NvmeCtrl *n,NvmeIdentify *c, +NvmeRequest *req) {uint32_t nsid =le32_to_cpu (c->nsid);uint64_t prp1 =le64_to_cpu (c->prp1);
@@ -1093,22 +1102,22 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c)stl_be_p (&ns_descrs->uuid.v, nsid);return nvme_dma_prp (n, list,NVME_IDENTIFY_DATA_SIZE , prp1, prp2, -DMA_DIRECTION_FROM_DEVICE ); +DMA_DIRECTION_FROM_DEVICE , req); } -static uint16_t nvme_identify (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_identify (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) {NvmeIdentify *c = (NvmeIdentify *)cmd;switch (le32_to_cpu (c->cns)) {case NVME_ID_CNS_NS : -return nvme_identify_ns (n, c); +return nvme_identify_ns (n, c, req);case NVME_ID_CNS_CTRL : -return nvme_identify_ctrl (n, c); +return nvme_identify_ctrl (n, c, req);case NVME_ID_CNS_NS_ACTIVE_LIST : -return nvme_identify_nslist (n, c); +return nvme_identify_nslist (n, c, req);case NVME_ID_CNS_NS_DESCR_LIST : -return nvme_identify_ns_descr_list (n, c); +return nvme_identify_ns_descr_list (n, c, req);default :trace_pci_nvme_err_invalid_identify_cns (le32_to_cpu (c->cns));return NVME_INVALID_FIELD |NVME_DNR ;
@@ -1167,7 +1176,8 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)return cpu_to_le64 (ts.all); } -static uint16_t nvme_get_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_get_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd, +NvmeRequest *req) {uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);
@@ -1175,7 +1185,7 @@ static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)uint64_t timestamp =nvme_get_timestamp (n);return nvme_dma_prp (n, (uint8_t *)×tamp,sizeof (timestamp), prp1, - prp2,DMA_DIRECTION_FROM_DEVICE ); + prp2,DMA_DIRECTION_FROM_DEVICE , req); }static uint16_t nvme_get_feature (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req)
@@ -1249,7 +1259,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) result =cpu_to_le32 (n->features.async_config);break ;case NVME_TIMESTAMP : -return nvme_get_feature_timestamp (n, cmd); +return nvme_get_feature_timestamp (n, cmd, req);default :break ; }
@@ -1296,7 +1306,8 @@ out:return NVME_SUCCESS ; } -static uint16_t nvme_set_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_set_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd, +NvmeRequest *req) {uint16_t ret;uint64_t timestamp;
@@ -1304,7 +1315,7 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd)uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2); ret =nvme_dma_prp (n, (uint8_t *)×tamp,sizeof (timestamp), prp1, - prp2,DMA_DIRECTION_TO_DEVICE ); + prp2,DMA_DIRECTION_TO_DEVICE , req);if (ret !=NVME_SUCCESS ) {return ret; }
@@ -1406,7 +1417,7 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) n->features.async_config = dw11;break ;case NVME_TIMESTAMP : -return nvme_set_feature_timestamp (n, cmd); +return nvme_set_feature_timestamp (n, cmd, req);default :return NVME_FEAT_NOT_CHANGABLE |NVME_DNR ; }
@@ -1448,7 +1459,7 @@ static uint16_t nvme_admin_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)case NVME_ADM_CMD_CREATE_CQ :return nvme_create_cq (n, cmd);case NVME_ADM_CMD_IDENTIFY : -return nvme_identify (n, cmd); +return nvme_identify (n, cmd, req);case NVME_ADM_CMD_ABORT :return nvme_abort (n, cmd, req);case NVME_ADM_CMD_SET_FEATURES :
hw/block/trace-events +1 -0
@@ -35,6 +35,7 @@ pci_nvme_irq_masked(void) "IRQ is masked" pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2=0x%"PRIx64"" pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" +pci_nvme_map_prp(uint16_t cid, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d" pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
Signature · 1 line
2.27.0
PATCH 7/17 hw/block/nvme: add request mapping helper
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Introduce the nvme_map helper to remove some noise in the main nvme_rw function.
--- hw/block/nvme.c | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-)
hw/block/nvme.c +10 -3
@@ -378,6 +378,15 @@ static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,return status; } +static uint16_t nvme_map (NvmeCtrl *n,NvmeCmd *cmd,size_t len, +NvmeRequest *req) +{ +uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1); +uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2); + +return nvme_map_prp (n, &req->qsg, &req->iov, prp1, prp2, len, req); +} +static void nvme_post_cqes (void *opaque) {NvmeCQueue *cq = opaque;
@@ -565,8 +574,6 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,NvmeRwCmd *rw = (NvmeRwCmd *)cmd;uint32_t nlb =le32_to_cpu (rw->nlb) +1 ;uint64_t slba =le64_to_cpu (rw->slba); -uint64_t prp1 =le64_to_cpu (rw->dptr.prp1); -uint64_t prp2 =le64_to_cpu (rw->dptr.prp2);uint8_t lba_index =NVME_ID_NS_FLBAS_INDEX (ns->id_ns.flbas);uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
@@ -583,7 +590,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_LBA_RANGE |NVME_DNR ; } -if (nvme_map_prp (n, &req->qsg, &req->iov, prp1, prp2, data_size, req)) { +if (nvme_map (n, cmd, data_size, req)) {block_acct_invalid (blk_get_stats (n->conf.blk), acct);return NVME_INVALID_FIELD |NVME_DNR ; }
Signature · 1 line
2.27.0
PATCH 8/17 hw/block/nvme: verify validity of prp lists in the cmb
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Before this patch the device already supported PRP lists in the CMB, but it did not check for the validity of it nor announced the support in the Identify Controller data structure LISTS field.
If some of the PRPs in a PRP list are in the CMB, then ALL entries must be there. This patch makes sure that requirement is verified as well as properly announcing support for PRP lists in the CMB.
--- hw/block/nvme.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-)
hw/block/nvme.c +13 -1
@@ -237,6 +237,7 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, trans_len =MIN (len, trans_len);int num_prps = (len >> n->page_bits) +1 ;uint16_t status; +bool prp_list_in_cmb = false;trace_pci_nvme_map_prp (nvme_cid (req), trans_len, len, prp1, prp2, num_prps);
@@ -264,11 +265,16 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, status =NVME_INVALID_FIELD |NVME_DNR ; goto unmap; } +if (len > n->page_size) {uint64_t prp_list[n->max_prp_ents];uint32_t nents, prp_trans;int i =0 ; +if (nvme_addr_is_cmb (n, prp2)) { + prp_list_in_cmb = true; + } + nents = (len + n->page_size -1 ) >> n->page_bits; prp_trans =MIN (n->max_prp_ents, nents) *sizeof (uint64_t );nvme_addr_read (n, prp2, (void *)prp_list, prp_trans);
@@ -282,6 +288,11 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, goto unmap; } +if (prp_list_in_cmb !=nvme_addr_is_cmb (n, prp_ent)) { + status =NVME_INVALID_USE_OF_CMB |NVME_DNR ; + goto unmap; + } + i =0 ; nents = (len + n->page_size -1 ) >> n->page_bits; prp_trans =MIN (n->max_prp_ents, nents) *sizeof (uint64_t );
@@ -301,6 +312,7 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov,if (status) { goto unmap; } + len -= trans_len; i++; }
@@ -2097,7 +2109,7 @@ static void nvme_init_cmb(NvmeCtrl *n, PCIDevice *pci_dev)NVME_CMBSZ_SET_SQS (n->bar.cmbsz,1 );NVME_CMBSZ_SET_CQS (n->bar.cmbsz,0 ); -NVME_CMBSZ_SET_LISTS (n->bar.cmbsz,0 ); +NVME_CMBSZ_SET_LISTS (n->bar.cmbsz,1 );NVME_CMBSZ_SET_RDS (n->bar.cmbsz,1 );NVME_CMBSZ_SET_WDS (n->bar.cmbsz,1 );NVME_CMBSZ_SET_SZU (n->bar.cmbsz,2 );/* MBs */
Signature · 1 line
2.27.0
PATCH 9/17 hw/block/nvme: refactor request bounds checking
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Hoist bounds checking into its own function.
--- hw/block/nvme.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-)
hw/block/nvme.c +21 -5
@@ -518,6 +518,18 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type) } } +static inline uint16_t nvme_check_bounds (NvmeCtrl *n,NvmeNamespace *ns, +uint64_t slba,uint32_t nlb) +{ +uint64_t nsze =le64_to_cpu (ns->id_ns.nsze); + +if (unlikely (UINT64_MAX - slba < nlb || slba + nlb > nsze)) { +return NVME_LBA_RANGE |NVME_DNR ; + } + +return NVME_SUCCESS ; +} +static void nvme_rw_cb (void *opaque,int ret) {NvmeRequest *req = opaque;
@@ -565,12 +577,14 @@ static uint16_t nvme_write_zeros(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,uint32_t nlb =le16_to_cpu (rw->nlb) +1 ;uint64_t offset = slba << data_shift;uint32_t count = nlb << data_shift; +uint16_t status;trace_pci_nvme_write_zeroes (nvme_cid (req), slba, nlb); -if (unlikely (slba + nlb > ns->id_ns.nsze)) { + status =nvme_check_bounds (n, ns, slba, nlb); +if (status) {trace_pci_nvme_err_invalid_lba_range (slba, nlb, ns->id_ns.nsze); -return NVME_LBA_RANGE |NVME_DNR ; +return status; } block_acct_start(blk_get_stats(n->conf.blk), &req->acct, 0,
@@ -593,13 +607,15 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,uint64_t data_offset = slba << data_shift;int is_write = rw->opcode ==NVME_CMD_WRITE ?1 :0 ;enum BlockAcctType acct = is_write ?BLOCK_ACCT_WRITE :BLOCK_ACCT_READ ; +uint16_t status;trace_pci_nvme_rw (is_write ?"write" :"read" , nlb, data_size, slba); -if (unlikely ((slba + nlb) > ns->id_ns.nsze)) { -block_acct_invalid (blk_get_stats (n->conf.blk), acct); + status =nvme_check_bounds (n, ns, slba, nlb); +if (status) {trace_pci_nvme_err_invalid_lba_range (slba, nlb, ns->id_ns.nsze); -return NVME_LBA_RANGE |NVME_DNR ; +block_acct_invalid (blk_get_stats (n->conf.blk), acct); +return status; }if (nvme_map (n, cmd, data_size, req)) {
Signature · 1 line
2.27.0
PATCH 10/17 hw/block/nvme: add check for mdts
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Add 'mdts' device parameter to control the Maximum Data Transfer Size of the controller and check that it is respected.
--- hw/block/nvme.c | 32 ++++++++++++++++++++++++++++++-- hw/block/nvme.h | 1 + hw/block/trace-events | 1 + 3 files changed, 32 insertions(+), 2 deletions(-)
hw/block/nvme.c +30 -2
@@ -18,9 +18,10 @@* Usage: add options: * -drive file=<file>,if=none,id=<drive_id> * -device nvme,drive=<drive_id>,serial=<serial>,id=<id[optional]>, \ -* cmb_size_mb=<cmb_size_mb[optional]>, \ +* [cmb_size_mb=<cmb_size_mb>,] \ * [pmrdev=<mem_backend_file_id>,] \ -* max_ioqpairs=<N[optional]> +* [max_ioqpairs=<N>,] \ +* [mdts=<N>] * * Note cmb_size_mb denotes size of CMB in MB. CMB is assumed to be at * offset 0 in BAR2 and supports only WDS, RDS and SQS for now.
@@ -518,6 +519,17 @@ static void nvme_clear_events(NvmeCtrl *n, uint8_t event_type) } } +static inline uint16_t nvme_check_mdts (NvmeCtrl *n,size_t len) +{ +uint8_t mdts = n->params.mdts; + +if (mdts && len > n->page_size << mdts) { +return NVME_INVALID_FIELD |NVME_DNR ; + } + +return NVME_SUCCESS ; +} +static inline uint16_t nvme_check_bounds (NvmeCtrl *n,NvmeNamespace *ns,uint64_t slba,uint32_t nlb) {
@@ -611,6 +623,13 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,trace_pci_nvme_rw (is_write ?"write" :"read" , nlb, data_size, slba); + status =nvme_check_mdts (n, data_size); +if (status) { +trace_pci_nvme_err_mdts (nvme_cid (req), data_size); +block_acct_invalid (blk_get_stats (n->conf.blk), acct); +return status; + } + status =nvme_check_bounds (n, ns, slba, nlb);if (status) {trace_pci_nvme_err_invalid_lba_range (slba, nlb, ns->id_ns.nsze);
@@ -904,6 +923,7 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)uint32_t numdl, numdu;uint64_t off, lpol, lpou;size_t len; +uint16_t status; numdl = (dw10 >>16 ); numdu = (dw11 &0xffff );
@@ -919,6 +939,12 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)trace_pci_nvme_get_log (nvme_cid (req), lid, lsp, rae, len, off); + status =nvme_check_mdts (n, len); +if (status) { +trace_pci_nvme_err_mdts (nvme_cid (req), len); +return status; + } +switch (lid) {case NVME_LOG_ERROR_INFO :return nvme_error_info (n, cmd, rae, len, off, req);
@@ -2227,6 +2253,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->ieee[0 ] =0x00 ; id->ieee[1 ] =0x02 ; id->ieee[2 ] =0xb3 ; + id->mdts = n->params.mdts; id->ver =cpu_to_le32 (NVME_SPEC_VER ); id->oacs =cpu_to_le16 (0 );
@@ -2345,6 +2372,7 @@ static Property nvme_props[] = {DEFINE_PROP_UINT16 ("msix_qsize" , NvmeCtrl, params.msix_qsize,65 ),DEFINE_PROP_UINT8 ("aerl" , NvmeCtrl, params.aerl,3 ),DEFINE_PROP_UINT32 ("aer_max_queued" , NvmeCtrl, params.aer_max_queued,64 ), +DEFINE_PROP_UINT8 ("mdts" , NvmeCtrl, params.mdts,7 ), DEFINE_PROP_END_OF_LIST(), };
hw/block/nvme.h +1 -0
@@ -11,6 +11,7 @@ typedef struct NvmeParams {uint32_t cmb_size_mb;uint8_t aerl;uint32_t aer_max_queued; +uint8_t mdts; } NvmeParams; typedef struct NvmeAsyncEvent {
hw/block/trace-events +1 -0
@@ -85,6 +85,7 @@ pci_nvme_mmio_shutdown_set(void) "shutdown bit set" pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" # nvme traces for error conditions +pci_nvme_err_mdts(uint16_t cid, size_t len) "cid %"PRIu16" len %"PRIu64"" pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
Signature · 1 line
2.27.0
PATCH 11/17 hw/block/nvme: be consistent about zeros vs zeroes
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
The NVM Express specification generally uses 'zeroes' and not 'zeros'. It might very well be wrong, but let us align with it.
--- block/nvme.c | 4 ++-- hw/block/nvme.c | 8 ++++---- include/block/nvme.h | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-)
block/nvme.c +2 -2
@@ -465,7 +465,7 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->page_size / sizeof(uint64_t) * s->page_size); oncs =le16_to_cpu (idctrl->oncs); - s->supports_write_zeroes = !!(oncs &NVME_ONCS_WRITE_ZEROS ); + s->supports_write_zeroes = !!(oncs &NVME_ONCS_WRITE_ZEROES ); s->supports_discard = !!(oncs &NVME_ONCS_DSM );memset (resp,0 ,4096 );
@@ -1117,7 +1117,7 @@ static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, }NvmeCmd cmd = { - .opcode =NVME_CMD_WRITE_ZEROS , + .opcode =NVME_CMD_WRITE_ZEROES , .nsid =cpu_to_le32 (s->nsid), .cdw10 =cpu_to_le32 ((offset >> s->blkshift) &0xFFFFFFFF ), .cdw11 =cpu_to_le32 (((offset >> s->blkshift) >>32 ) &0xFFFFFFFF ),
hw/block/nvme.c +4 -4
@@ -579,7 +579,7 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_NO_COMPLETE ; } -static uint16_t nvme_write_zeros (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd, +static uint16_t nvme_write_zeroes (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd,NvmeRequest *req) {NvmeRwCmd *rw = (NvmeRwCmd *)cmd;
@@ -679,8 +679,8 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)switch (cmd->opcode) {case NVME_CMD_FLUSH :return nvme_flush (n, ns, cmd, req); -case NVME_CMD_WRITE_ZEROS : -return nvme_write_zeros (n, ns, cmd, req); +case NVME_CMD_WRITE_ZEROES : +return nvme_write_zeroes (n, ns, cmd, req);case NVME_CMD_WRITE :case NVME_CMD_READ :return nvme_rw (n, ns, cmd, req);
@@ -2280,7 +2280,7 @@ static void nvme_init_ctrl(NvmeCtrl *n, PCIDevice *pci_dev) id->sqes = (0x6 <<4 ) |0x6 ; id->cqes = (0x4 <<4 ) |0x4 ; id->nn =cpu_to_le32 (n->num_namespaces); - id->oncs =cpu_to_le16 (NVME_ONCS_WRITE_ZEROS |NVME_ONCS_TIMESTAMP | + id->oncs =cpu_to_le16 (NVME_ONCS_WRITE_ZEROES |NVME_ONCS_TIMESTAMP |NVME_ONCS_FEATURES );pstrcpy ((char *) id->subnqn,sizeof (id->subnqn),"nqn.2019-08.org.qemu:" );
include/block/nvme.h +2 -2
@@ -459,7 +459,7 @@ enum NvmeIoCommands {NVME_CMD_READ =0x02 ,NVME_CMD_WRITE_UNCOR =0x04 ,NVME_CMD_COMPARE =0x05 , -NVME_CMD_WRITE_ZEROS =0x08 , +NVME_CMD_WRITE_ZEROES =0x08 , NVME_CMD_DSM = 0x09, };
@@ -837,7 +837,7 @@ enum NvmeIdCtrlOncs {NVME_ONCS_COMPARE =1 <<0 ,NVME_ONCS_WRITE_UNCORR =1 <<1 ,NVME_ONCS_DSM =1 <<2 , -NVME_ONCS_WRITE_ZEROS =1 <<3 , +NVME_ONCS_WRITE_ZEROES =1 <<3 ,NVME_ONCS_FEATURES =1 <<4 ,NVME_ONCS_RESRVATIONS =1 <<5 , NVME_ONCS_TIMESTAMP = 1 << 6,
Signature · 1 line
2.27.0
PATCH 12/17 hw/block/nvme: refactor NvmeRequest clearing
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Move clearing of the structure from "clear before use" to "clear after use". Also, carry a reference to the namespace the (I/O) command is acting on instead of passing it around explicitly.
--- hw/block/nvme.c | 28 ++++++++++++++++------------ hw/block/nvme.h | 1 + 2 files changed, 17 insertions(+), 12 deletions(-)
hw/block/nvme.c +16 -12
@@ -174,6 +174,12 @@ static void nvme_irq_deassert(NvmeCtrl *n, NvmeCQueue *cq) } } +static void nvme_req_clear (NvmeRequest *req) +{ + req->ns =NULL ; +memset (&req->cqe,0x0 ,sizeof (req->cqe)); +} +static uint16_t nvme_map_addr_cmb (NvmeCtrl *n,QEMUIOVector *iov,hwaddr addr,size_t len) {
@@ -423,6 +429,7 @@ static void nvme_post_cqes(void *opaque)nvme_inc_cq_tail (cq);pci_dma_write (&n->parent_obj, addr, (void *)&req->cqe,sizeof (req->cqe)); +nvme_req_clear (req);QTAILQ_INSERT_TAIL (&sq->req_list, req, entry); }if (cq->tail != cq->head) {
@@ -569,8 +576,7 @@ static void nvme_rw_cb(void *opaque, int ret)nvme_enqueue_req_completion (cq, req); } -static uint16_t nvme_flush (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd, -NvmeRequest *req) +static uint16_t nvme_flush (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) {block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 ,BLOCK_ACCT_FLUSH );
@@ -579,10 +585,10 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_NO_COMPLETE ; } -static uint16_t nvme_write_zeroes (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd, -NvmeRequest *req) +static uint16_t nvme_write_zeroes (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) {NvmeRwCmd *rw = (NvmeRwCmd *)cmd; +NvmeNamespace *ns = req->ns;const uint8_t lba_index =NVME_ID_NS_FLBAS_INDEX (ns->id_ns.flbas);const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;uint64_t slba =le64_to_cpu (rw->slba);
@@ -606,10 +612,10 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,return NVME_NO_COMPLETE ; } -static uint16_t nvme_rw (NvmeCtrl *n,NvmeNamespace *ns,NvmeCmd *cmd, -NvmeRequest *req) +static uint16_t nvme_rw (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) {NvmeRwCmd *rw = (NvmeRwCmd *)cmd; +NvmeNamespace *ns = req->ns;uint32_t nlb =le32_to_cpu (rw->nlb) +1 ;uint64_t slba =le64_to_cpu (rw->slba);
@@ -665,7 +671,6 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeNamespace *ns, NvmeCmd *cmd,static uint16_t nvme_io_cmd (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) { -NvmeNamespace *ns;uint32_t nsid =le32_to_cpu (cmd->nsid);trace_pci_nvme_io_cmd (nvme_cid (req), nsid,nvme_sqid (req), cmd->opcode);
@@ -675,15 +680,15 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return NVME_INVALID_NSID |NVME_DNR ; } - ns = &n->namespaces[nsid -1 ]; + req->ns = &n->namespaces[nsid -1 ];switch (cmd->opcode) {case NVME_CMD_FLUSH : -return nvme_flush (n, ns, cmd, req); +return nvme_flush (n, cmd, req);case NVME_CMD_WRITE_ZEROES : -return nvme_write_zeroes (n, ns, cmd, req); +return nvme_write_zeroes (n, cmd, req);case NVME_CMD_WRITE :case NVME_CMD_READ : -return nvme_rw (n, ns, cmd, req); +return nvme_rw (n, cmd, req);default :trace_pci_nvme_err_invalid_opc (cmd->opcode);return NVME_INVALID_OPCODE |NVME_DNR ;
@@ -1554,7 +1559,6 @@ static void nvme_process_sq(void *opaque) req =QTAILQ_FIRST (&sq->req_list);QTAILQ_REMOVE (&sq->req_list, req, entry);QTAILQ_INSERT_TAIL (&sq->out_req_list, req, entry); -memset (&req->cqe,0 ,sizeof (req->cqe)); req->cqe.cid = cmd.cid; status = sq->sqid ? nvme_io_cmd(n, &cmd, req) :
hw/block/nvme.h +1 -0
@@ -21,6 +21,7 @@ typedef struct NvmeAsyncEvent { typedef struct NvmeRequest { struct NvmeSQueue *sq; + struct NvmeNamespace *ns; BlockAIOCB *aiocb; uint16_t status; NvmeCqe cqe;
Signature · 1 line
2.27.0
PATCH 13/17 hw/block/nvme: consolidate qsg/iov clearing
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Always destroy the request qsg/iov at the end of request use.
--- hw/block/nvme.c | 48 +++++++++++++++++------------------------------- 1 file changed, 17 insertions(+), 31 deletions(-)
hw/block/nvme.c +17 -31
@@ -178,6 +178,14 @@ static void nvme_req_clear(NvmeRequest *req) { req->ns =NULL ;memset (&req->cqe,0x0 ,sizeof (req->cqe)); + +if (req->qsg.sg) { +qemu_sglist_destroy (&req->qsg); + } + +if (req->iov.iov) { +qemu_iovec_destroy (&req->iov); + } } static uint16_t nvme_map_addr_cmb(NvmeCtrl *n, QEMUIOVector *iov, hwaddr addr,
@@ -262,15 +270,14 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, status =nvme_map_addr (n, qsg, iov, prp1, trans_len);if (status) { - goto unmap; +return status; } len -= trans_len;if (len) {if (unlikely (!prp2)) {trace_pci_nvme_err_invalid_prp2_missing (); - status =NVME_INVALID_FIELD |NVME_DNR ; - goto unmap; +return NVME_INVALID_FIELD |NVME_DNR ; }if (len > n->page_size) {
@@ -291,13 +298,11 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov,if (i == n->max_prp_ents -1 && len > n->page_size) {if (unlikely (!prp_ent || prp_ent & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prplist_ent (prp_ent); - status =NVME_INVALID_FIELD |NVME_DNR ; - goto unmap; +return NVME_INVALID_FIELD |NVME_DNR ; }if (prp_list_in_cmb !=nvme_addr_is_cmb (n, prp_ent)) { - status =NVME_INVALID_USE_OF_CMB |NVME_DNR ; - goto unmap; +return NVME_INVALID_USE_OF_CMB |NVME_DNR ; } i =0 ;
@@ -310,14 +315,13 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov,if (unlikely (!prp_ent || prp_ent & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prplist_ent (prp_ent); - status =NVME_INVALID_FIELD |NVME_DNR ; - goto unmap; +return NVME_INVALID_FIELD |NVME_DNR ; } trans_len =MIN (len, n->page_size); status =nvme_map_addr (n, qsg, iov, prp_ent, trans_len);if (status) { - goto unmap; +return status; } len -= trans_len;
@@ -326,27 +330,16 @@ static uint16_t nvme_map_prp(NvmeCtrl *n, QEMUSGList *qsg, QEMUIOVector *iov, }else {if (unlikely (prp2 & (n->page_size -1 ))) {trace_pci_nvme_err_invalid_prp2_align (prp2); - status =NVME_INVALID_FIELD |NVME_DNR ; - goto unmap; +return NVME_INVALID_FIELD |NVME_DNR ; } status =nvme_map_addr (n, qsg, iov, prp2, len);if (status) { - goto unmap; +return status; } } } +return NVME_SUCCESS ; - -unmap: -if (iov && iov->iov) { -qemu_iovec_destroy (iov); - } - -if (qsg && qsg->sg) { -qemu_sglist_destroy (qsg); - } - -return status; } static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,
@@ -566,13 +559,6 @@ static void nvme_rw_cb(void *opaque, int ret) req->status =NVME_INTERNAL_DEV_ERROR ; } -if (req->qsg.nalloc) { -qemu_sglist_destroy (&req->qsg); - } -if (req->iov.nalloc) { -qemu_iovec_destroy (&req->iov); - } -nvme_enqueue_req_completion (cq, req); }
Signature · 1 line
2.27.0
PATCH 14/17 hw/block/nvme: remove NvmeCmd parameter
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Keep a copy of the raw nvme command in the NvmeRequest and remove the now redundant NvmeCmd parameter.
--- hw/block/nvme.c | 177 +++++++++++++++++++++++++----------------------- hw/block/nvme.h | 1 + 2 files changed, 93 insertions(+), 85 deletions(-)
hw/block/nvme.c +92 -85
@@ -390,9 +390,9 @@ static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len,return status; } -static uint16_t nvme_map (NvmeCtrl *n,NvmeCmd *cmd,size_t len, -NvmeRequest *req) +static uint16_t nvme_map (NvmeCtrl *n,size_t len,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);
@@ -562,7 +562,7 @@ static void nvme_rw_cb(void *opaque, int ret)nvme_enqueue_req_completion (cq, req); } -static uint16_t nvme_flush (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_flush (NvmeCtrl *n,NvmeRequest *req) {block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 ,BLOCK_ACCT_FLUSH );
@@ -571,9 +571,9 @@ static uint16_t nvme_flush(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return NVME_NO_COMPLETE ; } -static uint16_t nvme_write_zeroes (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_write_zeroes (NvmeCtrl *n,NvmeRequest *req) { -NvmeRwCmd *rw = (NvmeRwCmd *)cmd; +NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;NvmeNamespace *ns = req->ns;const uint8_t lba_index =NVME_ID_NS_FLBAS_INDEX (ns->id_ns.flbas);const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds;
@@ -598,9 +598,9 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return NVME_NO_COMPLETE ; } -static uint16_t nvme_rw (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_rw (NvmeCtrl *n,NvmeRequest *req) { -NvmeRwCmd *rw = (NvmeRwCmd *)cmd; +NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;NvmeNamespace *ns = req->ns;uint32_t nlb =le32_to_cpu (rw->nlb) +1 ;uint64_t slba =le64_to_cpu (rw->slba);
@@ -629,7 +629,7 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return status; } -if (nvme_map (n, cmd, data_size, req)) { +if (nvme_map (n, data_size, req)) {block_acct_invalid (blk_get_stats (n->conf.blk), acct);return NVME_INVALID_FIELD |NVME_DNR ; }
@@ -655,11 +655,12 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return NVME_NO_COMPLETE ; } -static uint16_t nvme_io_cmd (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_io_cmd (NvmeCtrl *n,NvmeRequest *req) { -uint32_t nsid =le32_to_cpu (cmd->nsid); +uint32_t nsid =le32_to_cpu (req->cmd.nsid); -trace_pci_nvme_io_cmd (nvme_cid (req), nsid,nvme_sqid (req), cmd->opcode); +trace_pci_nvme_io_cmd (nvme_cid (req), nsid,nvme_sqid (req), + req->cmd.opcode);if (unlikely (nsid ==0 || nsid > n->num_namespaces)) {trace_pci_nvme_err_invalid_ns (nsid, n->num_namespaces);
@@ -667,16 +668,16 @@ static uint16_t nvme_io_cmd(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) } req->ns = &n->namespaces[nsid -1 ]; -switch (cmd->opcode) { +switch (req->cmd.opcode) {case NVME_CMD_FLUSH : -return nvme_flush (n, cmd, req); +return nvme_flush (n, req);case NVME_CMD_WRITE_ZEROES : -return nvme_write_zeroes (n, cmd, req); +return nvme_write_zeroes (n, req);case NVME_CMD_WRITE :case NVME_CMD_READ : -return nvme_rw (n, cmd, req); +return nvme_rw (n, req);default : -trace_pci_nvme_err_invalid_opc (cmd->opcode); +trace_pci_nvme_err_invalid_opc (req->cmd.opcode);return NVME_INVALID_OPCODE |NVME_DNR ; } }
@@ -692,10 +693,10 @@ static void nvme_free_sq(NvmeSQueue *sq, NvmeCtrl *n) } } -static uint16_t nvme_del_sq (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_del_sq (NvmeCtrl *n,NvmeRequest *req) { -NvmeDeleteQ *c = (NvmeDeleteQ *)cmd; -NvmeRequest *req, *next; +NvmeDeleteQ *c = (NvmeDeleteQ *)&req->cmd; +NvmeRequest *r, *next;NvmeSQueue *sq;NvmeCQueue *cq;uint16_t qid =le16_to_cpu (c->qid);
@@ -709,19 +710,19 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeCmd *cmd) sq = n->sq[qid];while (!QTAILQ_EMPTY (&sq->out_req_list)) { - req =QTAILQ_FIRST (&sq->out_req_list); -assert (req->aiocb); -blk_aio_cancel (req->aiocb); + r =QTAILQ_FIRST (&sq->out_req_list); +assert (r->aiocb); +blk_aio_cancel (r->aiocb); }if (!nvme_check_cqid (n, sq->cqid)) { cq = n->cq[sq->cqid];QTAILQ_REMOVE (&cq->sq_list, sq, entry);nvme_post_cqes (cq); - QTAILQ_FOREACH_SAFE(req, &cq->req_list, entry, next) { -if (req->sq == sq) { -QTAILQ_REMOVE (&cq->req_list, req, entry); -QTAILQ_INSERT_TAIL (&sq->req_list, req, entry); + QTAILQ_FOREACH_SAFE(r, &cq->req_list, entry, next) { +if (r->sq == sq) { +QTAILQ_REMOVE (&cq->req_list, r, entry); +QTAILQ_INSERT_TAIL (&sq->req_list, r, entry); } } }
@@ -758,10 +759,10 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr, n->sq[sqid] = sq; } -static uint16_t nvme_create_sq (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_create_sq (NvmeCtrl *n,NvmeRequest *req) {NvmeSQueue *sq; -NvmeCreateSq *c = (NvmeCreateSq *)cmd; +NvmeCreateSq *c = (NvmeCreateSq *)&req->cmd;uint16_t cqid =le16_to_cpu (c->cqid);uint16_t sqid =le16_to_cpu (c->sqid);
@@ -796,10 +797,10 @@ static uint16_t nvme_create_sq(NvmeCtrl *n, NvmeCmd *cmd)return NVME_SUCCESS ; } -static uint16_t nvme_smart_info (NvmeCtrl *n,NvmeCmd *cmd,uint8_t rae, -uint32_t buf_len,uint64_t off, -NvmeRequest *req) +static uint16_t nvme_smart_info (NvmeCtrl *n,uint8_t rae,uint32_t buf_len, +uint64_t off,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);uint32_t nsid =le32_to_cpu (cmd->nsid);
@@ -855,10 +856,11 @@ static uint16_t nvme_smart_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_fw_log_info (NvmeCtrl *n,NvmeCmd *cmd,uint32_t buf_len, -uint64_t off,NvmeRequest *req) +static uint16_t nvme_fw_log_info (NvmeCtrl *n,uint32_t buf_len,uint64_t off, +NvmeRequest *req) {uint32_t trans_len; +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);NvmeFwSlotInfoLog fw_log = {
@@ -877,11 +879,11 @@ static uint16_t nvme_fw_log_info(NvmeCtrl *n, NvmeCmd *cmd, uint32_t buf_len, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_error_info (NvmeCtrl *n,NvmeCmd *cmd,uint8_t rae, -uint32_t buf_len,uint64_t off, -NvmeRequest *req) +static uint16_t nvme_error_info (NvmeCtrl *n,uint8_t rae,uint32_t buf_len, +uint64_t off,NvmeRequest *req) {uint32_t trans_len; +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);NvmeErrorLog errlog;
@@ -902,8 +904,10 @@ static uint16_t nvme_error_info(NvmeCtrl *n, NvmeCmd *cmd, uint8_t rae, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_get_log (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_get_log (NvmeCtrl *n,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd; +uint32_t dw10 =le32_to_cpu (cmd->cdw10);uint32_t dw11 =le32_to_cpu (cmd->cdw11);uint32_t dw12 =le32_to_cpu (cmd->cdw12);
@@ -938,11 +942,11 @@ static uint16_t nvme_get_log(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)switch (lid) {case NVME_LOG_ERROR_INFO : -return nvme_error_info (n, cmd, rae, len, off, req); +return nvme_error_info (n, rae, len, off, req);case NVME_LOG_SMART_INFO : -return nvme_smart_info (n, cmd, rae, len, off, req); +return nvme_smart_info (n, rae, len, off, req);case NVME_LOG_FW_SLOT_INFO : -return nvme_fw_log_info (n, cmd, len, off, req); +return nvme_fw_log_info (n, len, off, req);default :trace_pci_nvme_err_invalid_log_page (nvme_cid (req), lid);return NVME_INVALID_FIELD |NVME_DNR ;
@@ -960,9 +964,9 @@ static void nvme_free_cq(NvmeCQueue *cq, NvmeCtrl *n) } } -static uint16_t nvme_del_cq (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_del_cq (NvmeCtrl *n,NvmeRequest *req) { -NvmeDeleteQ *c = (NvmeDeleteQ *)cmd; +NvmeDeleteQ *c = (NvmeDeleteQ *)&req->cmd;NvmeCQueue *cq;uint16_t qid =le16_to_cpu (c->qid);
@@ -1003,10 +1007,10 @@ static void nvme_init_cq(NvmeCQueue *cq, NvmeCtrl *n, uint64_t dma_addr, cq->timer =timer_new_ns (QEMU_CLOCK_VIRTUAL , nvme_post_cqes, cq); } -static uint16_t nvme_create_cq (NvmeCtrl *n,NvmeCmd *cmd) +static uint16_t nvme_create_cq (NvmeCtrl *n,NvmeRequest *req) {NvmeCQueue *cq; -NvmeCreateCq *c = (NvmeCreateCq *)cmd; +NvmeCreateCq *c = (NvmeCreateCq *)&req->cmd;uint16_t cqid =le16_to_cpu (c->cqid);uint16_t vector =le16_to_cpu (c->irq_vector);uint16_t qsize =le16_to_cpu (c->qsize);
@@ -1054,9 +1058,9 @@ static uint16_t nvme_create_cq(NvmeCtrl *n, NvmeCmd *cmd)return NVME_SUCCESS ; } -static uint16_t nvme_identify_ctrl (NvmeCtrl *n,NvmeIdentify *c, -NvmeRequest *req) +static uint16_t nvme_identify_ctrl (NvmeCtrl *n,NvmeRequest *req) { +NvmeIdentify *c = (NvmeIdentify *)&req->cmd;uint64_t prp1 =le64_to_cpu (c->prp1);uint64_t prp2 =le64_to_cpu (c->prp2);
@@ -1066,10 +1070,10 @@ static uint16_t nvme_identify_ctrl(NvmeCtrl *n, NvmeIdentify *c, prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_identify_ns (NvmeCtrl *n,NvmeIdentify *c, -NvmeRequest *req) +static uint16_t nvme_identify_ns (NvmeCtrl *n,NvmeRequest *req) {NvmeNamespace *ns; +NvmeIdentify *c = (NvmeIdentify *)&req->cmd;uint32_t nsid =le32_to_cpu (c->nsid);uint64_t prp1 =le64_to_cpu (c->prp1);uint64_t prp2 =le64_to_cpu (c->prp2);
@@ -1087,9 +1091,9 @@ static uint16_t nvme_identify_ns(NvmeCtrl *n, NvmeIdentify *c, prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_identify_nslist (NvmeCtrl *n,NvmeIdentify *c, -NvmeRequest *req) +static uint16_t nvme_identify_nslist (NvmeCtrl *n,NvmeRequest *req) { +NvmeIdentify *c = (NvmeIdentify *)&req->cmd;static const int data_len =NVME_IDENTIFY_DATA_SIZE ;uint32_t min_nsid =le32_to_cpu (c->nsid);uint64_t prp1 =le64_to_cpu (c->prp1);
@@ -1116,9 +1120,9 @@ static uint16_t nvme_identify_nslist(NvmeCtrl *n, NvmeIdentify *c,return ret; } -static uint16_t nvme_identify_ns_descr_list (NvmeCtrl *n,NvmeIdentify *c, -NvmeRequest *req) +static uint16_t nvme_identify_ns_descr_list (NvmeCtrl *n,NvmeRequest *req) { +NvmeIdentify *c = (NvmeIdentify *)&req->cmd;uint32_t nsid =le32_to_cpu (c->nsid);uint64_t prp1 =le64_to_cpu (c->prp1);uint64_t prp2 =le64_to_cpu (c->prp2);
@@ -1157,28 +1161,28 @@ static uint16_t nvme_identify_ns_descr_list(NvmeCtrl *n, NvmeIdentify *c, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_identify (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_identify (NvmeCtrl *n,NvmeRequest *req) { -NvmeIdentify *c = (NvmeIdentify *)cmd; +NvmeIdentify *c = (NvmeIdentify *)&req->cmd;switch (le32_to_cpu (c->cns)) {case NVME_ID_CNS_NS : -return nvme_identify_ns (n, c, req); +return nvme_identify_ns (n, req);case NVME_ID_CNS_CTRL : -return nvme_identify_ctrl (n, c, req); +return nvme_identify_ctrl (n, req);case NVME_ID_CNS_NS_ACTIVE_LIST : -return nvme_identify_nslist (n, c, req); +return nvme_identify_nslist (n, req);case NVME_ID_CNS_NS_DESCR_LIST : -return nvme_identify_ns_descr_list (n, c, req); +return nvme_identify_ns_descr_list (n, req);default :trace_pci_nvme_err_invalid_identify_cns (le32_to_cpu (c->cns));return NVME_INVALID_FIELD |NVME_DNR ; } } -static uint16_t nvme_abort (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_abort (NvmeCtrl *n,NvmeRequest *req) { -uint16_t sqid =le32_to_cpu (cmd->cdw10) &0xffff ; +uint16_t sqid =le32_to_cpu (req->cmd.cdw10) &0xffff ; req->cqe.result =1 ;if (nvme_check_sqid (n, sqid)) {
@@ -1228,9 +1232,9 @@ static inline uint64_t nvme_get_timestamp(const NvmeCtrl *n)return cpu_to_le64 (ts.all); } -static uint16_t nvme_get_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd, -NvmeRequest *req) +static uint16_t nvme_get_feature_timestamp (NvmeCtrl *n,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);
@@ -1240,8 +1244,9 @@ static uint16_t nvme_get_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd, prp2, DMA_DIRECTION_FROM_DEVICE, req); } -static uint16_t nvme_get_feature (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_get_feature (NvmeCtrl *n,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd;uint32_t dw10 =le32_to_cpu (cmd->cdw10);uint32_t dw11 =le32_to_cpu (cmd->cdw11);uint32_t nsid =le32_to_cpu (cmd->nsid);
@@ -1311,7 +1316,7 @@ static uint16_t nvme_get_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) result =cpu_to_le32 (n->features.async_config);break ;case NVME_TIMESTAMP : -return nvme_get_feature_timestamp (n, cmd, req); +return nvme_get_feature_timestamp (n, req);default :break ; }
@@ -1358,11 +1363,11 @@ out:return NVME_SUCCESS ; } -static uint16_t nvme_set_feature_timestamp (NvmeCtrl *n,NvmeCmd *cmd, -NvmeRequest *req) +static uint16_t nvme_set_feature_timestamp (NvmeCtrl *n,NvmeRequest *req) {uint16_t ret;uint64_t timestamp; +NvmeCmd *cmd = &req->cmd;uint64_t prp1 =le64_to_cpu (cmd->dptr.prp1);uint64_t prp2 =le64_to_cpu (cmd->dptr.prp2);
@@ -1377,8 +1382,9 @@ static uint16_t nvme_set_feature_timestamp(NvmeCtrl *n, NvmeCmd *cmd,return NVME_SUCCESS ; } -static uint16_t nvme_set_feature (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_set_feature (NvmeCtrl *n,NvmeRequest *req) { +NvmeCmd *cmd = &req->cmd;uint32_t dw10 =le32_to_cpu (cmd->cdw10);uint32_t dw11 =le32_to_cpu (cmd->cdw11);uint32_t nsid =le32_to_cpu (cmd->nsid);
@@ -1469,14 +1475,14 @@ static uint16_t nvme_set_feature(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req) n->features.async_config = dw11;break ;case NVME_TIMESTAMP : -return nvme_set_feature_timestamp (n, cmd, req); +return nvme_set_feature_timestamp (n, req);default :return NVME_FEAT_NOT_CHANGABLE |NVME_DNR ; }return NVME_SUCCESS ; } -static uint16_t nvme_aer (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_aer (NvmeCtrl *n,NvmeRequest *req) {trace_pci_nvme_aer (nvme_cid (req));
@@ -1495,33 +1501,33 @@ static uint16_t nvme_aer(NvmeCtrl *n, NvmeCmd *cmd, NvmeRequest *req)return NVME_NO_COMPLETE ; } -static uint16_t nvme_admin_cmd (NvmeCtrl *n,NvmeCmd *cmd,NvmeRequest *req) +static uint16_t nvme_admin_cmd (NvmeCtrl *n,NvmeRequest *req) { -trace_pci_nvme_admin_cmd (nvme_cid (req),nvme_sqid (req), cmd->opcode); +trace_pci_nvme_admin_cmd (nvme_cid (req),nvme_sqid (req), req->cmd.opcode); -switch (cmd->opcode) { +switch (req->cmd.opcode) {case NVME_ADM_CMD_DELETE_SQ : -return nvme_del_sq (n, cmd); +return nvme_del_sq (n, req);case NVME_ADM_CMD_CREATE_SQ : -return nvme_create_sq (n, cmd); +return nvme_create_sq (n, req);case NVME_ADM_CMD_GET_LOG_PAGE : -return nvme_get_log (n, cmd, req); +return nvme_get_log (n, req);case NVME_ADM_CMD_DELETE_CQ : -return nvme_del_cq (n, cmd); +return nvme_del_cq (n, req);case NVME_ADM_CMD_CREATE_CQ : -return nvme_create_cq (n, cmd); +return nvme_create_cq (n, req);case NVME_ADM_CMD_IDENTIFY : -return nvme_identify (n, cmd, req); +return nvme_identify (n, req);case NVME_ADM_CMD_ABORT : -return nvme_abort (n, cmd, req); +return nvme_abort (n, req);case NVME_ADM_CMD_SET_FEATURES : -return nvme_set_feature (n, cmd, req); +return nvme_set_feature (n, req);case NVME_ADM_CMD_GET_FEATURES : -return nvme_get_feature (n, cmd, req); +return nvme_get_feature (n, req);case NVME_ADM_CMD_ASYNC_EV_REQ : -return nvme_aer (n, cmd, req); +return nvme_aer (n, req);default : -trace_pci_nvme_err_invalid_admin_opc (cmd->opcode); +trace_pci_nvme_err_invalid_admin_opc (req->cmd.opcode);return NVME_INVALID_OPCODE |NVME_DNR ; } }
@@ -1546,9 +1552,10 @@ static void nvme_process_sq(void *opaque)QTAILQ_REMOVE (&sq->req_list, req, entry);QTAILQ_INSERT_TAIL (&sq->out_req_list, req, entry); req->cqe.cid = cmd.cid; +memcpy (&req->cmd, &cmd,sizeof (NvmeCmd)); - status = sq->sqid ?nvme_io_cmd (n, &cmd, req) : -nvme_admin_cmd (n, &cmd, req); + status = sq->sqid ?nvme_io_cmd (n, req) : +nvme_admin_cmd (n, req);if (status !=NVME_NO_COMPLETE ) { req->status = status;nvme_enqueue_req_completion (cq, req);
hw/block/nvme.h +1 -0
@@ -25,6 +25,7 @@ typedef struct NvmeRequest {BlockAIOCB *aiocb;uint16_t status;NvmeCqe cqe; +NvmeCmd cmd;BlockAcctCookie acct;QEMUSGList qsg;QEMUIOVector iov;
Signature · 1 line
2.27.0
PATCH 15/17 hw/block/nvme: allow multiple aios per command
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
This refactors how the device issues asynchronous block backend requests. The NvmeRequest now holds a queue of NvmeAIOs that are associated with the command. This allows multiple aios to be issued for a command. Only when all requests have been completed will the device post a completion queue entry.
Because the device is currently guaranteed to only issue a single aio request per command, the benefit is not immediately obvious. But this functionality is required to support metadata, the dataset management command as well as zoned namespaces and other features that require additional persistent state.
--- hw/block/nvme.c | 330 +++++++++++++++++++++++++++++++++--------- hw/block/nvme.h | 104 +++++++++++-- hw/block/trace-events | 3 + 3 files changed, 360 insertions(+), 77 deletions(-)
hw/block/nvme.c +265 -65
@@ -74,6 +74,7 @@ }while (0 ) static void nvme_process_sq(void *opaque); +static void nvme_aio_cb (void *opaque,int ret);static inline void *nvme_addr_to_cmb (NvmeCtrl *n,hwaddr addr) {
@@ -178,6 +179,9 @@ static void nvme_req_clear(NvmeRequest *req) { req->ns =NULL ;memset (&req->cqe,0x0 ,sizeof (req->cqe)); + req->status =NVME_SUCCESS ; + req->slba = req->nlb =0x0 ; + req->cb = req->cb_arg =NULL ;if (req->qsg.sg) {qemu_sglist_destroy (&req->qsg);
@@ -399,6 +403,91 @@ static uint16_t nvme_map(NvmeCtrl *n, size_t len, NvmeRequest *req)return nvme_map_prp (n, &req->qsg, &req->iov, prp1, prp2, len, req); } +static void nvme_aio_destroy (NvmeAIO *aio) +{ +g_free (aio); +} + +/* +* Submit an asynchronous I/O operation as described by the given NvmeAIO. This +* function takes care of accounting and special handling of reads and writes +* going to the Controller Memory Buffer. +*/ +static void nvme_submit_aio (NvmeAIO *aio) +{ +BlockBackend *blk = aio->blk; +BlockAcctCookie *acct = &aio->acct; +BlockAcctStats *stats =blk_get_stats (blk); + +bool is_write; + +switch (aio->opc) { +case NVME_AIO_OPC_NONE : +break ; + +case NVME_AIO_OPC_FLUSH : +block_acct_start (stats, acct,0 ,BLOCK_ACCT_FLUSH ); + aio->aiocb =blk_aio_flush (blk, nvme_aio_cb, aio); +break ; + +case NVME_AIO_OPC_WRITE_ZEROES : +block_acct_start (stats, acct, aio->len,BLOCK_ACCT_WRITE ); + aio->aiocb =blk_aio_pwrite_zeroes (blk, aio->offset, aio->len, +BDRV_REQ_MAY_UNMAP , nvme_aio_cb, + aio); +break ; + +case NVME_AIO_OPC_READ : +case NVME_AIO_OPC_WRITE : + is_write = (aio->opc ==NVME_AIO_OPC_WRITE ); + +block_acct_start (stats, acct, aio->len, + is_write ?BLOCK_ACCT_WRITE :BLOCK_ACCT_READ ); + +if (aio->flags &NVME_AIO_DMA ) { +QEMUSGList *qsg = (QEMUSGList *)aio->payload; + +if (is_write) { + aio->aiocb =dma_blk_write (blk, qsg, aio->offset, +BDRV_SECTOR_SIZE , nvme_aio_cb, aio); + }else { + aio->aiocb =dma_blk_read (blk, qsg, aio->offset, +BDRV_SECTOR_SIZE , nvme_aio_cb, aio); + } + }else { +QEMUIOVector *iov = (QEMUIOVector *)aio->payload; + +if (is_write) { + aio->aiocb =blk_aio_pwritev (blk, aio->offset, iov,0 , + nvme_aio_cb, aio); + }else { + aio->aiocb =blk_aio_preadv (blk, aio->offset, iov,0 , + nvme_aio_cb, aio); + } + } + +break ; + } +} + +/* +* Register an asynchronous I/O operation with the NvmeRequest. The NvmeRequest +* will not complete until all registered AIO's have completed and the +* aio_tailq goes empty. +*/ +static inline void nvme_req_add_aio (NvmeRequest *req,NvmeAIO *aio) +{ +assert (req); + +trace_pci_nvme_req_add_aio (nvme_cid (req), aio,blk_name (aio->blk), + aio->offset, aio->len, +nvme_aio_opc_str (aio), req); + +QTAILQ_INSERT_TAIL (&req->aio_tailq, aio, tailq_entry); + +nvme_submit_aio (aio); +} +static void nvme_post_cqes (void *opaque) {NvmeCQueue *cq = opaque;
@@ -435,6 +524,7 @@ static void nvme_enqueue_req_completion(NvmeCQueue *cq, NvmeRequest *req)assert (cq->cqid == req->sq->cqid);trace_pci_nvme_enqueue_req_completion (nvme_cid (req), cq->cqid, req->status); +QTAILQ_REMOVE (&req->sq->out_req_list, req, entry);QTAILQ_INSERT_TAIL (&cq->req_list, req, entry);timer_mod (cq->timer,qemu_clock_get_ns (QEMU_CLOCK_VIRTUAL ) +500 );
@@ -542,31 +632,128 @@ static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeNamespace *ns,return NVME_SUCCESS ; } -static void nvme_rw_cb (void *opaque,int ret) +static void nvme_rw_cb (NvmeRequest *req,void *opaque) { -NvmeRequest *req = opaque;NvmeSQueue *sq = req->sq;NvmeCtrl *n = sq->ctrl;NvmeCQueue *cq = n->cq[sq->cqid];trace_pci_nvme_rw_cb (nvme_cid (req)); -if (!ret) { -block_acct_done (blk_get_stats (n->conf.blk), &req->acct); - req->status =NVME_SUCCESS ; - }else { -block_acct_failed (blk_get_stats (n->conf.blk), &req->acct); - req->status =NVME_INTERNAL_DEV_ERROR ; +nvme_enqueue_req_completion (cq, req); +} + +static void nvme_aio_cb (void *opaque,int ret) +{ +NvmeAIO *aio = opaque; +NvmeRequest *req = aio->req; + +BlockBackend *blk = aio->blk; +BlockAcctCookie *acct = &aio->acct; +BlockAcctStats *stats =blk_get_stats (blk); + +Error *local_err =NULL ; + +trace_pci_nvme_aio_cb (nvme_cid (req), aio,blk_name (blk), aio->offset, +nvme_aio_opc_str (aio), req); + +if (req) { +QTAILQ_REMOVE (&req->aio_tailq, aio, tailq_entry); } -nvme_enqueue_req_completion (cq, req); +if (!ret) { +block_acct_done (stats, acct); + }else { +block_acct_failed (stats, acct); + +if (req) { +uint16_t status; + +switch (aio->opc) { +case NVME_AIO_OPC_READ : + status =NVME_UNRECOVERED_READ ; +break ; +case NVME_AIO_OPC_WRITE : +case NVME_AIO_OPC_WRITE_ZEROES : + status =NVME_WRITE_FAULT ; +break ; +default : + status =NVME_INTERNAL_DEV_ERROR ; +break ; + } + +trace_pci_nvme_err_aio (nvme_cid (req), aio,blk_name (blk), + aio->offset,nvme_aio_opc_str (aio), req, + status); + +error_setg_errno (&local_err, -ret,"aio failed" ); +error_report_err (local_err); + +/* +* An Internal Error trumps all other errors. For other errors, +* only set the first error encountered. Any additional errors will +* be recorded in the error information log page. +*/ +if (!req->status || (status &0xfff ) ==NVME_INTERNAL_DEV_ERROR ) { + req->status = status; + } + } + } + +if (aio->cb) { + aio->cb (aio, aio->cb_arg, ret); + } + +if (req &&QTAILQ_EMPTY (&req->aio_tailq)) { +if (req->cb) { + req->cb (req, req->cb_arg); + }else { +NvmeSQueue *sq = req->sq; +NvmeCtrl *n = sq->ctrl; +NvmeCQueue *cq = n->cq[sq->cqid]; + +nvme_enqueue_req_completion (cq, req); + } + } + +nvme_aio_destroy (aio); +} + +static void nvme_aio_rw (NvmeNamespace *ns,BlockBackend *blk,NvmeAIOOp opc, +NvmeRequest *req) +{ +NvmeAIO *aio =g_new (NvmeAIO,1 ); + + *aio = (NvmeAIO ) { + .opc = opc, + .blk = blk, + .offset = req->slba <<nvme_ns_lbads (ns), + .req = req, + }; + +if (req->qsg.sg) { + aio->payload = &req->qsg; + aio->len = req->qsg.size; + aio->flags |=NVME_AIO_DMA ; + }else { + aio->payload = &req->iov; + aio->len = req->iov.size; + } + +nvme_req_add_aio (req, aio); }static uint16_t nvme_flush (NvmeCtrl *n,NvmeRequest *req) { -block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 , -BLOCK_ACCT_FLUSH ); - req->aiocb =blk_aio_flush (n->conf.blk, nvme_rw_cb, req); +NvmeAIO *aio =g_new0 (NvmeAIO,1 ); + + *aio = (NvmeAIO ) { + .opc =NVME_AIO_OPC_FLUSH , + .blk = n->conf.blk, + .req = req, + }; + +nvme_req_add_aio (req, aio);return NVME_NO_COMPLETE ; }
@@ -575,26 +762,39 @@ static uint16_t nvme_write_zeroes(NvmeCtrl *n, NvmeRequest *req) {NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;NvmeNamespace *ns = req->ns; -const uint8_t lba_index =NVME_ID_NS_FLBAS_INDEX (ns->id_ns.flbas); -const uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds; -uint64_t slba =le64_to_cpu (rw->slba); -uint32_t nlb =le16_to_cpu (rw->nlb) +1 ; -uint64_t offset = slba << data_shift; -uint32_t count = nlb << data_shift; +NvmeAIO *aio; + +int64_t offset; +size_t count;uint16_t status; -trace_pci_nvme_write_zeroes (nvme_cid (req), slba, nlb); + req->slba =le64_to_cpu (rw->slba); + req->nlb =le16_to_cpu (rw->nlb) +1 ; - status =nvme_check_bounds (n, ns, slba, nlb); +trace_pci_nvme_write_zeroes (nvme_cid (req), req->slba, req->nlb); + + status =nvme_check_bounds (n, ns, req->slba, req->nlb);if (status) { -trace_pci_nvme_err_invalid_lba_range (slba, nlb, ns->id_ns.nsze); +trace_pci_nvme_err_invalid_lba_range (req->slba, req->nlb, + ns->id_ns.nsze);return status; } -block_acct_start (blk_get_stats (n->conf.blk), &req->acct,0 , -BLOCK_ACCT_WRITE ); - req->aiocb =blk_aio_pwrite_zeroes (n->conf.blk, offset, count, -BDRV_REQ_MAY_UNMAP , nvme_rw_cb, req); + offset = req->slba <<nvme_ns_lbads (ns); + count = req->nlb <<nvme_ns_lbads (ns); + + aio =g_new0 (NvmeAIO,1 ); + + *aio = (NvmeAIO ) { + .opc =NVME_AIO_OPC_WRITE_ZEROES , + .blk = n->conf.blk, + .offset = offset, + .len = count, + .req = req, + }; + +nvme_req_add_aio (req, aio); +return NVME_NO_COMPLETE ; }
@@ -602,57 +802,52 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req) {NvmeRwCmd *rw = (NvmeRwCmd *)&req->cmd;NvmeNamespace *ns = req->ns; -uint32_t nlb =le32_to_cpu (rw->nlb) +1 ; -uint64_t slba =le64_to_cpu (rw->slba); -uint8_t lba_index =NVME_ID_NS_FLBAS_INDEX (ns->id_ns.flbas); -uint8_t data_shift = ns->id_ns.lbaf[lba_index].ds; -uint64_t data_size = (uint64_t )nlb << data_shift; -uint64_t data_offset = slba << data_shift; -int is_write = rw->opcode ==NVME_CMD_WRITE ?1 :0 ; -enum BlockAcctType acct = is_write ?BLOCK_ACCT_WRITE :BLOCK_ACCT_READ ; -uint16_t status; +uint32_t len; +int status; -trace_pci_nvme_rw (is_write ?"write" :"read" , nlb, data_size, slba); +enum BlockAcctType acct =BLOCK_ACCT_READ ; +NvmeAIOOp opc =NVME_AIO_OPC_READ ; - status =nvme_check_mdts (n, data_size); +if (nvme_req_is_write (req)) { + acct =BLOCK_ACCT_WRITE ; + opc =NVME_AIO_OPC_WRITE ; + } + + req->nlb =le16_to_cpu (rw->nlb) +1 ; + req->slba =le64_to_cpu (rw->slba); + + len = req->nlb <<nvme_ns_lbads (ns); + +trace_pci_nvme_rw (nvme_req_is_write (req) ?"write" :"read" , req->nlb, + len, req->slba); + + status =nvme_check_mdts (n, len);if (status) { -trace_pci_nvme_err_mdts (nvme_cid (req), data_size); -block_acct_invalid (blk_get_stats (n->conf.blk), acct); -return status; +trace_pci_nvme_err_mdts (nvme_cid (req), len); + goto invalid; } - status =nvme_check_bounds (n, ns, slba, nlb); + status =nvme_check_bounds (n, ns, req->slba, req->nlb);if (status) { -trace_pci_nvme_err_invalid_lba_range (slba, nlb, ns->id_ns.nsze); -block_acct_invalid (blk_get_stats (n->conf.blk), acct); -return status; +trace_pci_nvme_err_invalid_lba_range (req->slba, req->nlb, + ns->id_ns.nsze); + goto invalid; } -if (nvme_map (n, data_size, req)) { -block_acct_invalid (blk_get_stats (n->conf.blk), acct); -return NVME_INVALID_FIELD |NVME_DNR ; + status =nvme_map (n, len, req); +if (status) { + goto invalid; } -if (req->qsg.nsg >0 ) { -block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->qsg.size, - acct); - req->aiocb = is_write ? -dma_blk_write (n->conf.blk, &req->qsg, data_offset,BDRV_SECTOR_SIZE , - nvme_rw_cb, req) : -dma_blk_read (n->conf.blk, &req->qsg, data_offset,BDRV_SECTOR_SIZE , - nvme_rw_cb, req); - }else { -block_acct_start (blk_get_stats (n->conf.blk), &req->acct, req->iov.size, - acct); - req->aiocb = is_write ? -blk_aio_pwritev (n->conf.blk, data_offset, &req->iov,0 , nvme_rw_cb, - req) : -blk_aio_preadv (n->conf.blk, data_offset, &req->iov,0 , nvme_rw_cb, - req); - } +nvme_aio_rw (ns, n->conf.blk, opc, req); +nvme_req_set_cb (req, nvme_rw_cb,NULL );return NVME_NO_COMPLETE ; + +invalid: +block_acct_invalid (blk_get_stats (n->conf.blk), acct); +return status; }static uint16_t nvme_io_cmd (NvmeCtrl *n,NvmeRequest *req)
@@ -699,6 +894,7 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req)NvmeRequest *r, *next;NvmeSQueue *sq;NvmeCQueue *cq; +NvmeAIO *aio;uint16_t qid =le16_to_cpu (c->qid);if (unlikely (!qid ||nvme_check_sqid (n, qid))) {
@@ -711,8 +907,11 @@ static uint16_t nvme_del_sq(NvmeCtrl *n, NvmeRequest *req) sq = n->sq[qid];while (!QTAILQ_EMPTY (&sq->out_req_list)) { r =QTAILQ_FIRST (&sq->out_req_list); -assert (r->aiocb); -blk_aio_cancel (r->aiocb); +while (!QTAILQ_EMPTY (&r->aio_tailq)) { + aio =QTAILQ_FIRST (&r->aio_tailq); +assert (aio->aiocb); +blk_aio_cancel (aio->aiocb); + } }if (!nvme_check_cqid (n, sq->cqid)) { cq = n->cq[sq->cqid];
@@ -749,6 +948,7 @@ static void nvme_init_sq(NvmeSQueue *sq, NvmeCtrl *n, uint64_t dma_addr,QTAILQ_INIT (&sq->out_req_list);for (i =0 ; i < sq->size; i++) { sq->io_req[i].sq = sq; +QTAILQ_INIT (&(sq->io_req[i].aio_tailq));QTAILQ_INSERT_TAIL (&(sq->req_list), &sq->io_req[i], entry); } sq->timer =timer_new_ns (QEMU_CLOCK_VIRTUAL , nvme_process_sq, sq);
hw/block/nvme.h +92 -12
116 lines not on this page · raw message
hw/block/trace-events +3 -0
@@ -36,6 +36,8 @@ pci_nvme_dma_read(uint64_t prp1, uint64_t prp2) "DMA read, prp1=0x%"PRIx64" prp2 pci_nvme_map_addr(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_map_addr_cmb(uint64_t addr, uint64_t len) "addr 0x%"PRIx64" len %"PRIu64"" pci_nvme_map_prp(uint16_t cid, uint64_t trans_len, uint32_t len, uint64_t prp1, uint64_t prp2, int num_prps) "cid %"PRIu16" trans_len %"PRIu64" len %"PRIu32" prp1 0x%"PRIx64" prp2 0x%"PRIx64" num_prps %d" +pci_nvme_req_add_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, uint64_t count, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" count %"PRIu64" opc \"%s\" req %p" +pci_nvme_aio_cb(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p" pci_nvme_io_cmd(uint16_t cid, uint32_t nsid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" nsid %"PRIu32" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_admin_cmd(uint16_t cid, uint16_t sqid, uint8_t opcode) "cid %"PRIu16" sqid %"PRIu16" opc 0x%"PRIx8"" pci_nvme_rw(const char *verb, uint32_t blk_count, uint64_t byte_count, uint64_t lba) "%s %"PRIu32" blocks (%"PRIu64" bytes) from LBA %"PRIu64""
@@ -86,6 +88,7 @@ pci_nvme_mmio_shutdown_cleared(void) "shutdown bit cleared" # nvme traces for error conditions pci_nvme_err_mdts(uint16_t cid, size_t len) "cid %"PRIu16" len %"PRIu64"" +pci_nvme_err_aio(uint16_t cid, void *aio, const char *blkname, uint64_t offset, const char *opc, void *req, uint16_t status) "cid %"PRIu16" aio %p blk \"%s\" offset %"PRIu64" opc \"%s\" req %p status 0x%"PRIx16"" pci_nvme_err_invalid_dma(void) "PRP/SGL is too small for transfer size" pci_nvme_err_invalid_prplist_ent(uint64_t prplist) "PRP list entry is null or not page aligned: 0x%"PRIx64"" pci_nvme_err_invalid_prp2_align(uint64_t prp2) "PRP2 is not page aligned: 0x%"PRIx64""
Signature · 1 line
2.27.0
PATCH 16/17 hw/block/nvme: add nvme_check_rw helper
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Move various request checks to a separate function.
--- hw/block/nvme.c | 32 +++++++++++++++++++++++--------- 1 file changed, 23 insertions(+), 9 deletions(-)
hw/block/nvme.c +23 -9
@@ -632,6 +632,28 @@ static inline uint16_t nvme_check_bounds(NvmeCtrl *n, NvmeNamespace *ns,return NVME_SUCCESS ; } +static uint16_t nvme_check_rw (NvmeCtrl *n,NvmeRequest *req) +{ +NvmeNamespace *ns = req->ns; +size_t len = req->nlb <<nvme_ns_lbads (ns); +uint16_t status; + + status =nvme_check_mdts (n, len); +if (status) { +trace_pci_nvme_err_mdts (nvme_cid (req), len); +return status; + } + + status =nvme_check_bounds (n, ns, req->slba, req->nlb); +if (status) { +trace_pci_nvme_err_invalid_lba_range (req->slba, req->nlb, + ns->id_ns.nsze); +return status; + } + +return NVME_SUCCESS ; +} +static void nvme_rw_cb (NvmeRequest *req,void *opaque) {NvmeSQueue *sq = req->sq;
@@ -822,16 +844,8 @@ static uint16_t nvme_rw(NvmeCtrl *n, NvmeRequest *req)trace_pci_nvme_rw (nvme_req_is_write (req) ?"write" :"read" , req->nlb, len, req->slba); - status =nvme_check_mdts (n, len); + status =nvme_check_rw (n, req);if (status) { -trace_pci_nvme_err_mdts (nvme_cid (req), len); - goto invalid; - } - - status =nvme_check_bounds (n, ns, req->slba, req->nlb); -if (status) { -trace_pci_nvme_err_invalid_lba_range (req->slba, req->nlb, - ns->id_ns.nsze); goto invalid; }
Signature · 1 line
2.27.0
PATCH 17/17 hw/block/nvme: use preallocated qsg/iov in nvme_dma_prp
In reply to Klaus JensenFrom: Klaus Jensen <[email protected]>
Since clean up of the request qsg/iov is now always done post-use, there is no need to use a stack-allocated qsg/iov in nvme_dma_prp.
--- hw/block/nvme.c | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-)
hw/block/nvme.c +6 -12
@@ -350,45 +350,39 @@ static uint16_t nvme_dma_prp(NvmeCtrl *n, uint8_t *ptr, uint32_t len, uint64_t prp1, uint64_t prp2, DMADirection dir, NvmeRequest *req) { - QEMUSGList qsg; -QEMUIOVector iov; uint16_t status = NVME_SUCCESS; - status =nvme_map_prp (n, &qsg, &iov, prp1, prp2, len, req); + status =nvme_map_prp (n, &req->qsg, &req->iov, prp1, prp2, len, req);if (status) {return status; } -if (qsg.nsg >0 ) { +if (req->qsg.nsg >0 ) {uint64_t residual;if (dir ==DMA_DIRECTION_TO_DEVICE ) { - residual =dma_buf_write (ptr, len, &qsg); + residual =dma_buf_write (ptr, len, &req->qsg); }else { - residual =dma_buf_read (ptr, len, &qsg); + residual =dma_buf_read (ptr, len, &req->qsg); }if (unlikely (residual)) {trace_pci_nvme_err_invalid_dma (); status =NVME_INVALID_FIELD |NVME_DNR ; } - -qemu_sglist_destroy (&qsg); }else {size_t bytes;if (dir ==DMA_DIRECTION_TO_DEVICE ) { - bytes =qemu_iovec_to_buf (&iov,0 , ptr, len); + bytes =qemu_iovec_to_buf (&req->iov,0 , ptr, len); }else { - bytes =qemu_iovec_from_buf (&iov,0 , ptr, len); + bytes =qemu_iovec_from_buf (&req->iov,0 , ptr, len); }if (unlikely (bytes != len)) {trace_pci_nvme_err_invalid_dma (); status =NVME_INVALID_FIELD |NVME_DNR ; } - -qemu_iovec_destroy (&iov); }return status;
Signature · 1 line
2.27.0