| Message ID | 20210107071845.GA224876@mtl-vdi-166.wap.labs.mlnx |
|---|---|
| State | New |
| Headers | show |
| Series | [v1] vdpa/mlx5: Fix memory key MTT population | expand |
On 2021/1/7 下午3:18, Eli Cohen wrote: > map_direct_mr() assumed that the number of scatter/gather entries > returned by dma_map_sg_attrs() was equal to the number of segments in > the sgl list. This led to wrong population of the mkey object. Fix this > by properly referring to the returned value. > > The hardware expects each MTT entry to contain the DMA address of a > contiguous block of memory of size (1 << mr->log_size) bytes. > dma_map_sg_attrs() can coalesce several sg entries into a single > scatter/gather entry of contiguous DMA range so we need to scan the list > and refer to the size of each s/g entry. > > In addition, get rid of fill_sg() which effect is overwritten by > populate_mtts(). > > Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") > Signed-off-by: Eli Cohen <elic@nvidia.com> > --- > V0->V1: > 1. Fix typos > 2. Improve changelog Acked-by: Jason Wang <jasowang@redhat.com> > > drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + > drivers/vdpa/mlx5/core/mr.c | 28 ++++++++++++---------------- > 2 files changed, 13 insertions(+), 16 deletions(-) > > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > index 5c92a576edae..08f742fd2409 100644 > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { > struct sg_table sg_head; > int log_size; > int nsg; > + int nent; > struct list_head list; > u64 offset; > }; > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > index 4b6195666c58..d300f799efcd 100644 > --- a/drivers/vdpa/mlx5/core/mr.c > +++ b/drivers/vdpa/mlx5/core/mr.c > @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) > return (npages + 1) / 2; > } > > -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) > -{ > - struct scatterlist *sg; > - __be64 *pas; > - int i; > - > - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > - (*pas) = cpu_to_be64(sg_dma_address(sg)); > -} > - > static void mlx5_set_access_mode(void *mkc, int mode) > { > MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); > @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) > static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) > { > struct scatterlist *sg; > + int nsg = mr->nsg; > + u64 dma_addr; > + u64 dma_len; > + int j = 0; > int i; > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > - mtt[i] = cpu_to_be64(sg_dma_address(sg)); > + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { > + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); > + nsg && dma_len; > + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) > + mtt[j++] = cpu_to_be64(dma_addr); > + } > } > > static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) > @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct > return -ENOMEM; > > MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); > - fill_sg(mr, in); > mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); > MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); > MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); > @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr > done: > mr->log_size = log_entity_size; > mr->nsg = nsg; > - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > - if (!err) > + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > + if (!mr->nent) > goto err_map; > > err = create_direct_mr(mvdev, mr);
On Fri, Jan 08, 2021 at 04:38:55PM +0800, Jason Wang wrote: Hi Michael, this patch is a fix. Are you going to merge it? > > On 2021/1/7 下午3:18, Eli Cohen wrote: > > map_direct_mr() assumed that the number of scatter/gather entries > > returned by dma_map_sg_attrs() was equal to the number of segments in > > the sgl list. This led to wrong population of the mkey object. Fix this > > by properly referring to the returned value. > > > > The hardware expects each MTT entry to contain the DMA address of a > > contiguous block of memory of size (1 << mr->log_size) bytes. > > dma_map_sg_attrs() can coalesce several sg entries into a single > > scatter/gather entry of contiguous DMA range so we need to scan the list > > and refer to the size of each s/g entry. > > > > In addition, get rid of fill_sg() which effect is overwritten by > > populate_mtts(). > > > > Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") > > Signed-off-by: Eli Cohen <elic@nvidia.com> > > --- > > V0->V1: > > 1. Fix typos > > 2. Improve changelog > > > Acked-by: Jason Wang <jasowang@redhat.com> > > > > > > drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + > > drivers/vdpa/mlx5/core/mr.c | 28 ++++++++++++---------------- > > 2 files changed, 13 insertions(+), 16 deletions(-) > > > > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > index 5c92a576edae..08f742fd2409 100644 > > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { > > struct sg_table sg_head; > > int log_size; > > int nsg; > > + int nent; > > struct list_head list; > > u64 offset; > > }; > > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > > index 4b6195666c58..d300f799efcd 100644 > > --- a/drivers/vdpa/mlx5/core/mr.c > > +++ b/drivers/vdpa/mlx5/core/mr.c > > @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) > > return (npages + 1) / 2; > > } > > -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) > > -{ > > - struct scatterlist *sg; > > - __be64 *pas; > > - int i; > > - > > - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > - (*pas) = cpu_to_be64(sg_dma_address(sg)); > > -} > > - > > static void mlx5_set_access_mode(void *mkc, int mode) > > { > > MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); > > @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) > > static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) > > { > > struct scatterlist *sg; > > + int nsg = mr->nsg; > > + u64 dma_addr; > > + u64 dma_len; > > + int j = 0; > > int i; > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > - mtt[i] = cpu_to_be64(sg_dma_address(sg)); > > + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { > > + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); > > + nsg && dma_len; > > + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) > > + mtt[j++] = cpu_to_be64(dma_addr); > > + } > > } > > static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) > > @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct > > return -ENOMEM; > > MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); > > - fill_sg(mr, in); > > mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); > > MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); > > MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); > > @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr > > done: > > mr->log_size = log_entity_size; > > mr->nsg = nsg; > > - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > - if (!err) > > + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > + if (!mr->nent) > > goto err_map; > > err = create_direct_mr(mvdev, mr); >
On Wed, Jan 20, 2021 at 07:36:19AM +0200, Eli Cohen wrote: > On Fri, Jan 08, 2021 at 04:38:55PM +0800, Jason Wang wrote: > > Hi Michael, > this patch is a fix. Are you going to merge it? yes - in the next pull request. > > > > On 2021/1/7 下午3:18, Eli Cohen wrote: > > > map_direct_mr() assumed that the number of scatter/gather entries > > > returned by dma_map_sg_attrs() was equal to the number of segments in > > > the sgl list. This led to wrong population of the mkey object. Fix this > > > by properly referring to the returned value. > > > > > > The hardware expects each MTT entry to contain the DMA address of a > > > contiguous block of memory of size (1 << mr->log_size) bytes. > > > dma_map_sg_attrs() can coalesce several sg entries into a single > > > scatter/gather entry of contiguous DMA range so we need to scan the list > > > and refer to the size of each s/g entry. > > > > > > In addition, get rid of fill_sg() which effect is overwritten by > > > populate_mtts(). > > > > > > Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") > > > Signed-off-by: Eli Cohen <elic@nvidia.com> > > > --- > > > V0->V1: > > > 1. Fix typos > > > 2. Improve changelog > > > > > > Acked-by: Jason Wang <jasowang@redhat.com> > > > > > > > > > > drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + > > > drivers/vdpa/mlx5/core/mr.c | 28 ++++++++++++---------------- > > > 2 files changed, 13 insertions(+), 16 deletions(-) > > > > > > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > index 5c92a576edae..08f742fd2409 100644 > > > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { > > > struct sg_table sg_head; > > > int log_size; > > > int nsg; > > > + int nent; > > > struct list_head list; > > > u64 offset; > > > }; > > > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > > > index 4b6195666c58..d300f799efcd 100644 > > > --- a/drivers/vdpa/mlx5/core/mr.c > > > +++ b/drivers/vdpa/mlx5/core/mr.c > > > @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) > > > return (npages + 1) / 2; > > > } > > > -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) > > > -{ > > > - struct scatterlist *sg; > > > - __be64 *pas; > > > - int i; > > > - > > > - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); > > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > > - (*pas) = cpu_to_be64(sg_dma_address(sg)); > > > -} > > > - > > > static void mlx5_set_access_mode(void *mkc, int mode) > > > { > > > MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); > > > @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) > > > static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) > > > { > > > struct scatterlist *sg; > > > + int nsg = mr->nsg; > > > + u64 dma_addr; > > > + u64 dma_len; > > > + int j = 0; > > > int i; > > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > > - mtt[i] = cpu_to_be64(sg_dma_address(sg)); > > > + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { > > > + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); > > > + nsg && dma_len; > > > + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) > > > + mtt[j++] = cpu_to_be64(dma_addr); > > > + } > > > } > > > static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) > > > @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct > > > return -ENOMEM; > > > MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); > > > - fill_sg(mr, in); > > > mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); > > > MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); > > > MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); > > > @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr > > > done: > > > mr->log_size = log_entity_size; > > > mr->nsg = nsg; > > > - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > > - if (!err) > > > + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > > + if (!mr->nent) > > > goto err_map; > > > err = create_direct_mr(mvdev, mr); > >
On Wed, Jan 20, 2021 at 02:57:05AM -0500, Michael S. Tsirkin wrote: > On Wed, Jan 20, 2021 at 07:36:19AM +0200, Eli Cohen wrote: > > On Fri, Jan 08, 2021 at 04:38:55PM +0800, Jason Wang wrote: > > > > Hi Michael, > > this patch is a fix. Are you going to merge it? > > yes - in the next pull request. > Great thanks. Can you send the path to your git tree where you keep the patches you intend to merge? > > > > > > On 2021/1/7 下午3:18, Eli Cohen wrote: > > > > map_direct_mr() assumed that the number of scatter/gather entries > > > > returned by dma_map_sg_attrs() was equal to the number of segments in > > > > the sgl list. This led to wrong population of the mkey object. Fix this > > > > by properly referring to the returned value. > > > > > > > > The hardware expects each MTT entry to contain the DMA address of a > > > > contiguous block of memory of size (1 << mr->log_size) bytes. > > > > dma_map_sg_attrs() can coalesce several sg entries into a single > > > > scatter/gather entry of contiguous DMA range so we need to scan the list > > > > and refer to the size of each s/g entry. > > > > > > > > In addition, get rid of fill_sg() which effect is overwritten by > > > > populate_mtts(). > > > > > > > > Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") > > > > Signed-off-by: Eli Cohen <elic@nvidia.com> > > > > --- > > > > V0->V1: > > > > 1. Fix typos > > > > 2. Improve changelog > > > > > > > > > Acked-by: Jason Wang <jasowang@redhat.com> > > > > > > > > > > > > > > drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + > > > > drivers/vdpa/mlx5/core/mr.c | 28 ++++++++++++---------------- > > > > 2 files changed, 13 insertions(+), 16 deletions(-) > > > > > > > > diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > > index 5c92a576edae..08f742fd2409 100644 > > > > --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > > +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h > > > > @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { > > > > struct sg_table sg_head; > > > > int log_size; > > > > int nsg; > > > > + int nent; > > > > struct list_head list; > > > > u64 offset; > > > > }; > > > > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > > > > index 4b6195666c58..d300f799efcd 100644 > > > > --- a/drivers/vdpa/mlx5/core/mr.c > > > > +++ b/drivers/vdpa/mlx5/core/mr.c > > > > @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) > > > > return (npages + 1) / 2; > > > > } > > > > -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) > > > > -{ > > > > - struct scatterlist *sg; > > > > - __be64 *pas; > > > > - int i; > > > > - > > > > - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); > > > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > > > - (*pas) = cpu_to_be64(sg_dma_address(sg)); > > > > -} > > > > - > > > > static void mlx5_set_access_mode(void *mkc, int mode) > > > > { > > > > MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); > > > > @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) > > > > static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) > > > > { > > > > struct scatterlist *sg; > > > > + int nsg = mr->nsg; > > > > + u64 dma_addr; > > > > + u64 dma_len; > > > > + int j = 0; > > > > int i; > > > > - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) > > > > - mtt[i] = cpu_to_be64(sg_dma_address(sg)); > > > > + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { > > > > + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); > > > > + nsg && dma_len; > > > > + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) > > > > + mtt[j++] = cpu_to_be64(dma_addr); > > > > + } > > > > } > > > > static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) > > > > @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct > > > > return -ENOMEM; > > > > MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); > > > > - fill_sg(mr, in); > > > > mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); > > > > MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); > > > > MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); > > > > @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr > > > > done: > > > > mr->log_size = log_entity_size; > > > > mr->nsg = nsg; > > > > - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > > > - if (!err) > > > > + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); > > > > + if (!mr->nent) > > > > goto err_map; > > > > err = create_direct_mr(mvdev, mr); > > > >
On Wed, Jan 20, 2021 at 10:11:54AM +0200, Eli Cohen wrote: > On Wed, Jan 20, 2021 at 02:57:05AM -0500, Michael S. Tsirkin wrote: > > On Wed, Jan 20, 2021 at 07:36:19AM +0200, Eli Cohen wrote: > > > On Fri, Jan 08, 2021 at 04:38:55PM +0800, Jason Wang wrote: > > > > > > Hi Michael, > > > this patch is a fix. Are you going to merge it? > > > > yes - in the next pull request. > > > > Great thanks. > Can you send the path to your git tree where you keep the patches you > intend to merge? https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git linux-next Note I often rebase it (e.g. just did). -- MST
On Wed, Jan 20, 2021 at 03:52:00AM -0500, Michael S. Tsirkin wrote: > On Wed, Jan 20, 2021 at 10:11:54AM +0200, Eli Cohen wrote: > > On Wed, Jan 20, 2021 at 02:57:05AM -0500, Michael S. Tsirkin wrote: > > > On Wed, Jan 20, 2021 at 07:36:19AM +0200, Eli Cohen wrote: > > > > On Fri, Jan 08, 2021 at 04:38:55PM +0800, Jason Wang wrote: > > > > > > > > Hi Michael, > > > > this patch is a fix. Are you going to merge it? > > > > > > yes - in the next pull request. > > > > > > > Great thanks. > > Can you send the path to your git tree where you keep the patches you > > intend to merge? > > https://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git linux-next > > Note I often rebase it (e.g. just did). > Great, thanks! > -- > MST >
diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h b/drivers/vdpa/mlx5/core/mlx5_vdpa.h index 5c92a576edae..08f742fd2409 100644 --- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h +++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h @@ -15,6 +15,7 @@ struct mlx5_vdpa_direct_mr { struct sg_table sg_head; int log_size; int nsg; + int nent; struct list_head list; u64 offset; }; diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c index 4b6195666c58..d300f799efcd 100644 --- a/drivers/vdpa/mlx5/core/mr.c +++ b/drivers/vdpa/mlx5/core/mr.c @@ -25,17 +25,6 @@ static int get_octo_len(u64 len, int page_shift) return (npages + 1) / 2; } -static void fill_sg(struct mlx5_vdpa_direct_mr *mr, void *in) -{ - struct scatterlist *sg; - __be64 *pas; - int i; - - pas = MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) - (*pas) = cpu_to_be64(sg_dma_address(sg)); -} - static void mlx5_set_access_mode(void *mkc, int mode) { MLX5_SET(mkc, mkc, access_mode_1_0, mode & 0x3); @@ -45,10 +34,18 @@ static void mlx5_set_access_mode(void *mkc, int mode) static void populate_mtts(struct mlx5_vdpa_direct_mr *mr, __be64 *mtt) { struct scatterlist *sg; + int nsg = mr->nsg; + u64 dma_addr; + u64 dma_len; + int j = 0; int i; - for_each_sg(mr->sg_head.sgl, sg, mr->nsg, i) - mtt[i] = cpu_to_be64(sg_dma_address(sg)); + for_each_sg(mr->sg_head.sgl, sg, mr->nent, i) { + for (dma_addr = sg_dma_address(sg), dma_len = sg_dma_len(sg); + nsg && dma_len; + nsg--, dma_addr += BIT(mr->log_size), dma_len -= BIT(mr->log_size)) + mtt[j++] = cpu_to_be64(dma_addr); + } } static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr *mr) @@ -64,7 +61,6 @@ static int create_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct return -ENOMEM; MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); - fill_sg(mr, in); mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); MLX5_SET(mkc, mkc, lw, !!(mr->perm & VHOST_MAP_WO)); MLX5_SET(mkc, mkc, lr, !!(mr->perm & VHOST_MAP_RO)); @@ -276,8 +272,8 @@ static int map_direct_mr(struct mlx5_vdpa_dev *mvdev, struct mlx5_vdpa_direct_mr done: mr->log_size = log_entity_size; mr->nsg = nsg; - err = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); - if (!err) + mr->nent = dma_map_sg_attrs(dma, mr->sg_head.sgl, mr->nsg, DMA_BIDIRECTIONAL, 0); + if (!mr->nent) goto err_map; err = create_direct_mr(mvdev, mr);
map_direct_mr() assumed that the number of scatter/gather entries returned by dma_map_sg_attrs() was equal to the number of segments in the sgl list. This led to wrong population of the mkey object. Fix this by properly referring to the returned value. The hardware expects each MTT entry to contain the DMA address of a contiguous block of memory of size (1 << mr->log_size) bytes. dma_map_sg_attrs() can coalesce several sg entries into a single scatter/gather entry of contiguous DMA range so we need to scan the list and refer to the size of each s/g entry. In addition, get rid of fill_sg() which effect is overwritten by populate_mtts(). Fixes: 94abbccdf291 ("vdpa/mlx5: Add shared memory registration code") Signed-off-by: Eli Cohen <elic@nvidia.com> --- V0->V1: 1. Fix typos 2. Improve changelog drivers/vdpa/mlx5/core/mlx5_vdpa.h | 1 + drivers/vdpa/mlx5/core/mr.c | 28 ++++++++++++---------------- 2 files changed, 13 insertions(+), 16 deletions(-)