| Message ID | 20190703155944.9637-6-mlevitsk@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | Few fixes for userspace NVME driver | expand |
On 03.07.19 17:59, Maxim Levitsky wrote: > Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com> > --- > block/nvme.c | 69 +++++++++++++++++++++++++++++++++++++++++++- > block/trace-events | 1 + > include/block/nvme.h | 19 +++++++++++- > 3 files changed, 87 insertions(+), 2 deletions(-) > > diff --git a/block/nvme.c b/block/nvme.c > index 152d27b07f..02e0846643 100644 > --- a/block/nvme.c > +++ b/block/nvme.c [...] > @@ -469,6 +473,11 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) > s->nsze = le64_to_cpu(idns->nsze); > lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)]; > > + if (NVME_ID_NS_DLFEAT_WRITE_ZEROS(idns->dlfeat) && > + NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) == > + NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS) > + bs->supported_write_flags |= BDRV_REQ_MAY_UNMAP; > + This violates the coding style, there should be curly brackets here. > if (lbaf->ms) { > error_setg(errp, "Namespaces with metadata are not yet supported"); > goto out; > @@ -763,6 +772,8 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, > int ret; > BDRVNVMeState *s = bs->opaque; > > + bs->supported_write_flags = BDRV_REQ_FUA; > + > opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); > qemu_opts_absorb_qdict(opts, options, &error_abort); > device = qemu_opt_get(opts, NVME_BLOCK_OPT_DEVICE); > @@ -791,7 +802,6 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, > goto fail; > } > } > - bs->supported_write_flags = BDRV_REQ_FUA; Any reason for this movement? > return 0; > fail: > nvme_close(bs); > @@ -1085,6 +1095,60 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs) > } > > > +static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, > + int64_t offset, > + int bytes, > + BdrvRequestFlags flags) > +{ > + BDRVNVMeState *s = bs->opaque; > + NVMeQueuePair *ioq = s->queues[1]; > + NVMeRequest *req; > + > + if (!s->supports_write_zeros) { > + return -ENOTSUP; > + } > + > + uint32_t cdw12 = ((bytes >> s->blkshift) - 1) & 0xFFFF; Another coding style violation: Variable declarations and other code may not be mixed. > + > + NvmeCmd cmd = { > + .opcode = NVME_CMD_WRITE_ZEROS, > + .nsid = cpu_to_le32(s->nsid), > + .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), > + .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF), > + }; > + > + NVMeCoData data = { > + .ctx = bdrv_get_aio_context(bs), > + .ret = -EINPROGRESS, > + }; [...] > diff --git a/include/block/nvme.h b/include/block/nvme.h > index 3ec8efcc43..65eb65c740 100644 > --- a/include/block/nvme.h > +++ b/include/block/nvme.h > @@ -653,12 +653,29 @@ typedef struct NvmeIdNs { > uint8_t mc; > uint8_t dpc; > uint8_t dps; > - uint8_t res30[98]; > + > + uint8_t nmic; > + uint8_t rescap; > + uint8_t fpi; > + uint8_t dlfeat; > + > + uint8_t res30[94]; > NvmeLBAF lbaf[16]; > uint8_t res192[192]; > uint8_t vs[3712]; > } NvmeIdNs; > > + > +/*Deallocate Logical Block Features*/ > +#define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) > +#define NVME_ID_NS_DLFEAT_WRITE_ZEROS(dlfeat) ((dlfeat) & 0x04) Isn’t it bit 3, i.e. 0x08? Max > + > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR(dlfeat) ((dlfeat) & 0x3) > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_UNDEFINED 0 > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS 1 > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ONES 2 > + > + > #define NVME_ID_NS_NSFEAT_THIN(nsfeat) ((nsfeat & 0x1)) > #define NVME_ID_NS_FLBAS_EXTENDED(flbas) ((flbas >> 4) & 0x1) > #define NVME_ID_NS_FLBAS_INDEX(flbas) ((flbas & 0xf)) >
On Fri, 2019-07-05 at 15:33 +0200, Max Reitz wrote: > On 03.07.19 17:59, Maxim Levitsky wrote: > > Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com> > > --- > > block/nvme.c | 69 +++++++++++++++++++++++++++++++++++++++++++- > > block/trace-events | 1 + > > include/block/nvme.h | 19 +++++++++++- > > 3 files changed, 87 insertions(+), 2 deletions(-) > > > > diff --git a/block/nvme.c b/block/nvme.c > > index 152d27b07f..02e0846643 100644 > > --- a/block/nvme.c > > +++ b/block/nvme.c > > [...] > > > @@ -469,6 +473,11 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) > > s->nsze = le64_to_cpu(idns->nsze); > > lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)]; > > > > + if (NVME_ID_NS_DLFEAT_WRITE_ZEROS(idns->dlfeat) && > > + NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) == > > + NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS) > > + bs->supported_write_flags |= BDRV_REQ_MAY_UNMAP; > > + > > This violates the coding style, there should be curly brackets here. 100% agree + I need to see if we can update the checkpatch.pl to catch this. > > > if (lbaf->ms) { > > error_setg(errp, "Namespaces with metadata are not yet supported"); > > goto out; > > @@ -763,6 +772,8 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, > > int ret; > > BDRVNVMeState *s = bs->opaque; > > > > + bs->supported_write_flags = BDRV_REQ_FUA; > > + > > opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); > > qemu_opts_absorb_qdict(opts, options, &error_abort); > > device = qemu_opt_get(opts, NVME_BLOCK_OPT_DEVICE); > > @@ -791,7 +802,6 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, > > goto fail; > > } > > } > > - bs->supported_write_flags = BDRV_REQ_FUA; > > Any reason for this movement? This is because the nvme_identify checks if the underlying namespace supports 'discarded data reads back as zeros', and in which case it sets the BDRV_REQ_MAY_UNMAP in bs->supported_write_flags which later allow me to set 'deallocate' bit in the write zeros command which hints the controller to discard the area. This was moved to avoid overwriting the value. I could have instead just ored the value, but this way I think is cleaner a bit. > > > return 0; > > fail: > > nvme_close(bs); > > @@ -1085,6 +1095,60 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs) > > } > > > > > > +static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, > > + int64_t offset, > > + int bytes, > > + BdrvRequestFlags flags) > > +{ > > + BDRVNVMeState *s = bs->opaque; > > + NVMeQueuePair *ioq = s->queues[1]; > > + NVMeRequest *req; > > + > > + if (!s->supports_write_zeros) { > > + return -ENOTSUP; > > + } > > + > > + uint32_t cdw12 = ((bytes >> s->blkshift) - 1) & 0xFFFF; > > Another coding style violation: Variable declarations and other code may > not be mixed. Another bug in checkpatch.pl :-) > > > + > > + NvmeCmd cmd = { > > + .opcode = NVME_CMD_WRITE_ZEROS, > > + .nsid = cpu_to_le32(s->nsid), > > + .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), > > + .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF), > > + }; > > + > > + NVMeCoData data = { > > + .ctx = bdrv_get_aio_context(bs), > > + .ret = -EINPROGRESS, > > + }; > > [...] > > > diff --git a/include/block/nvme.h b/include/block/nvme.h > > index 3ec8efcc43..65eb65c740 100644 > > --- a/include/block/nvme.h > > +++ b/include/block/nvme.h > > @@ -653,12 +653,29 @@ typedef struct NvmeIdNs { > > uint8_t mc; > > uint8_t dpc; > > uint8_t dps; > > - uint8_t res30[98]; > > + > > + uint8_t nmic; > > + uint8_t rescap; > > + uint8_t fpi; > > + uint8_t dlfeat; > > + > > + uint8_t res30[94]; > > NvmeLBAF lbaf[16]; > > uint8_t res192[192]; > > uint8_t vs[3712]; > > } NvmeIdNs; > > > > + > > +/*Deallocate Logical Block Features*/ > > +#define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) > > +#define NVME_ID_NS_DLFEAT_WRITE_ZEROS(dlfeat) ((dlfeat) & 0x04) > > Isn’t it bit 3, i.e. 0x08? Oops, I haven't noticed that 'read behavier' field is 3 bits and not 2! Thank you very much. I haven't caught this since my device I tested on doesn't support this anyway (dlfeat == 0) > > Max > > > + > > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR(dlfeat) ((dlfeat) & 0x3) > > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_UNDEFINED 0 > > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS 1 > > +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ONES 2 > > + > > + > > #define NVME_ID_NS_NSFEAT_THIN(nsfeat) ((nsfeat & 0x1)) > > #define NVME_ID_NS_FLBAS_EXTENDED(flbas) ((flbas >> 4) & 0x1) > > #define NVME_ID_NS_FLBAS_INDEX(flbas) ((flbas & 0xf)) > > > Thank you very very much for the review, Best regards, Maxim Levitsky
diff --git a/block/nvme.c b/block/nvme.c index 152d27b07f..02e0846643 100644 --- a/block/nvme.c +++ b/block/nvme.c @@ -110,6 +110,8 @@ typedef struct { uint64_t max_transfer; bool plugged; + bool supports_write_zeros; + CoMutex dma_map_lock; CoQueue dma_flush_queue; @@ -457,6 +459,8 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->max_transfer = MIN_NON_ZERO(s->max_transfer, s->page_size / sizeof(uint64_t) * s->page_size); + s->supports_write_zeros = (idctrl->oncs & NVME_ONCS_WRITE_ZEROS) != 0; + memset(resp, 0, 4096); cmd.cdw10 = 0; @@ -469,6 +473,11 @@ static void nvme_identify(BlockDriverState *bs, int namespace, Error **errp) s->nsze = le64_to_cpu(idns->nsze); lbaf = &idns->lbaf[NVME_ID_NS_FLBAS_INDEX(idns->flbas)]; + if (NVME_ID_NS_DLFEAT_WRITE_ZEROS(idns->dlfeat) && + NVME_ID_NS_DLFEAT_READ_BEHAVIOR(idns->dlfeat) == + NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS) + bs->supported_write_flags |= BDRV_REQ_MAY_UNMAP; + if (lbaf->ms) { error_setg(errp, "Namespaces with metadata are not yet supported"); goto out; @@ -763,6 +772,8 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, int ret; BDRVNVMeState *s = bs->opaque; + bs->supported_write_flags = BDRV_REQ_FUA; + opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort); qemu_opts_absorb_qdict(opts, options, &error_abort); device = qemu_opt_get(opts, NVME_BLOCK_OPT_DEVICE); @@ -791,7 +802,6 @@ static int nvme_file_open(BlockDriverState *bs, QDict *options, int flags, goto fail; } } - bs->supported_write_flags = BDRV_REQ_FUA; return 0; fail: nvme_close(bs); @@ -1085,6 +1095,60 @@ static coroutine_fn int nvme_co_flush(BlockDriverState *bs) } +static coroutine_fn int nvme_co_pwrite_zeroes(BlockDriverState *bs, + int64_t offset, + int bytes, + BdrvRequestFlags flags) +{ + BDRVNVMeState *s = bs->opaque; + NVMeQueuePair *ioq = s->queues[1]; + NVMeRequest *req; + + if (!s->supports_write_zeros) { + return -ENOTSUP; + } + + uint32_t cdw12 = ((bytes >> s->blkshift) - 1) & 0xFFFF; + + NvmeCmd cmd = { + .opcode = NVME_CMD_WRITE_ZEROS, + .nsid = cpu_to_le32(s->nsid), + .cdw10 = cpu_to_le32((offset >> s->blkshift) & 0xFFFFFFFF), + .cdw11 = cpu_to_le32(((offset >> s->blkshift) >> 32) & 0xFFFFFFFF), + }; + + NVMeCoData data = { + .ctx = bdrv_get_aio_context(bs), + .ret = -EINPROGRESS, + }; + + if (flags & BDRV_REQ_MAY_UNMAP) { + cdw12 |= (1 << 25); + } + + if (flags & BDRV_REQ_FUA) { + cdw12 |= (1 << 30); + } + + cmd.cdw12 = cpu_to_le32(cdw12); + + trace_nvme_write_zeros(s, offset, bytes, flags); + assert(s->nr_queues > 1); + req = nvme_get_free_req(ioq); + assert(req); + + nvme_submit_command(s, ioq, req, &cmd, nvme_rw_cb, &data); + + data.co = qemu_coroutine_self(); + while (data.ret == -EINPROGRESS) { + qemu_coroutine_yield(); + } + + trace_nvme_rw_done(s, true, offset, bytes, data.ret); + return data.ret; +} + + static int nvme_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue, Error **errp) { @@ -1297,6 +1361,9 @@ static BlockDriver bdrv_nvme = { .bdrv_co_preadv = nvme_co_preadv, .bdrv_co_pwritev = nvme_co_pwritev, + + .bdrv_co_pwrite_zeroes = nvme_co_pwrite_zeroes, + .bdrv_co_flush_to_disk = nvme_co_flush, .bdrv_reopen_prepare = nvme_reopen_prepare, diff --git a/block/trace-events b/block/trace-events index 9ccea755da..12f363bb44 100644 --- a/block/trace-events +++ b/block/trace-events @@ -148,6 +148,7 @@ nvme_submit_command_raw(int c0, int c1, int c2, int c3, int c4, int c5, int c6, nvme_handle_event(void *s) "s %p" nvme_poll_cb(void *s) "s %p" nvme_prw_aligned(void *s, int is_write, uint64_t offset, uint64_t bytes, int flags, int niov) "s %p is_write %d offset %"PRId64" bytes %"PRId64" flags %d niov %d" +nvme_write_zeros(void *s, uint64_t offset, uint64_t bytes, int flags) "s %p offset %"PRId64" bytes %"PRId64" flags %d" nvme_qiov_unaligned(const void *qiov, int n, void *base, size_t size, int align) "qiov %p n %d base %p size 0x%zx align 0x%x" nvme_prw_buffered(void *s, uint64_t offset, uint64_t bytes, int niov, int is_write) "s %p offset %"PRId64" bytes %"PRId64" niov %d is_write %d" nvme_rw_done(void *s, int is_write, uint64_t offset, uint64_t bytes, int ret) "s %p is_write %d offset %"PRId64" bytes %"PRId64" ret %d" diff --git a/include/block/nvme.h b/include/block/nvme.h index 3ec8efcc43..65eb65c740 100644 --- a/include/block/nvme.h +++ b/include/block/nvme.h @@ -653,12 +653,29 @@ typedef struct NvmeIdNs { uint8_t mc; uint8_t dpc; uint8_t dps; - uint8_t res30[98]; + + uint8_t nmic; + uint8_t rescap; + uint8_t fpi; + uint8_t dlfeat; + + uint8_t res30[94]; NvmeLBAF lbaf[16]; uint8_t res192[192]; uint8_t vs[3712]; } NvmeIdNs; + +/*Deallocate Logical Block Features*/ +#define NVME_ID_NS_DLFEAT_GUARD_CRC(dlfeat) ((dlfeat) & 0x10) +#define NVME_ID_NS_DLFEAT_WRITE_ZEROS(dlfeat) ((dlfeat) & 0x04) + +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR(dlfeat) ((dlfeat) & 0x3) +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_UNDEFINED 0 +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ZEROS 1 +#define NVME_ID_NS_DLFEAT_READ_BEHAVIOR_ONES 2 + + #define NVME_ID_NS_NSFEAT_THIN(nsfeat) ((nsfeat & 0x1)) #define NVME_ID_NS_FLBAS_EXTENDED(flbas) ((flbas >> 4) & 0x1) #define NVME_ID_NS_FLBAS_INDEX(flbas) ((flbas & 0xf))
Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com> --- block/nvme.c | 69 +++++++++++++++++++++++++++++++++++++++++++- block/trace-events | 1 + include/block/nvme.h | 19 +++++++++++- 3 files changed, 87 insertions(+), 2 deletions(-)