[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <29dea17e8e4dbbd839f14d3b248f5f3d06d251fa.1726138681.git.leon@kernel.org>
Date: Thu, 12 Sep 2024 14:15:49 +0300
From: Leon Romanovsky <leon@...nel.org>
To: Jens Axboe <axboe@...nel.dk>,
Jason Gunthorpe <jgg@...pe.ca>,
Robin Murphy <robin.murphy@....com>,
Joerg Roedel <joro@...tes.org>,
Will Deacon <will@...nel.org>,
Keith Busch <kbusch@...nel.org>,
Christoph Hellwig <hch@....de>,
"Zeng, Oak" <oak.zeng@...el.com>,
Chaitanya Kulkarni <kch@...dia.com>
Cc: Leon Romanovsky <leonro@...dia.com>,
Sagi Grimberg <sagi@...mberg.me>,
Bjorn Helgaas <bhelgaas@...gle.com>,
Logan Gunthorpe <logang@...tatee.com>,
Yishai Hadas <yishaih@...dia.com>,
Shameer Kolothum <shameerali.kolothum.thodi@...wei.com>,
Kevin Tian <kevin.tian@...el.com>,
Alex Williamson <alex.williamson@...hat.com>,
Marek Szyprowski <m.szyprowski@...sung.com>,
Jérôme Glisse <jglisse@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
linux-block@...r.kernel.org,
linux-kernel@...r.kernel.org,
linux-rdma@...r.kernel.org,
iommu@...ts.linux.dev,
linux-nvme@...ts.infradead.org,
linux-pci@...r.kernel.org,
kvm@...r.kernel.org,
linux-mm@...ck.org
Subject: [RFC v2 14/21] vfio/mlx5: Explicitly use number of pages instead of allocated length
From: Leon Romanovsky <leonro@...dia.com>
allocated_length is a multiple of page size and number of pages,
so let's change the functions to accept number of pages. It opens
us a venue to combine receive and send paths together with code
readability improvement.
Signed-off-by: Leon Romanovsky <leonro@...dia.com>
---
drivers/vfio/pci/mlx5/cmd.c | 32 ++++++++++-----------
drivers/vfio/pci/mlx5/cmd.h | 10 +++----
drivers/vfio/pci/mlx5/main.c | 56 +++++++++++++++++++++++-------------
3 files changed, 57 insertions(+), 41 deletions(-)
diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 41a4b0cf4297..fdc3e515741f 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -318,8 +318,7 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn,
struct mlx5_vhca_recv_buf *recv_buf,
u32 *mkey)
{
- size_t npages = buf ? DIV_ROUND_UP(buf->allocated_length, PAGE_SIZE) :
- recv_buf->npages;
+ size_t npages = buf ? buf->npages : recv_buf->npages;
int err = 0, inlen;
__be64 *mtt;
void *mkc;
@@ -375,7 +374,7 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
if (mvdev->mdev_detach)
return -ENOTCONN;
- if (buf->dmaed || !buf->allocated_length)
+ if (buf->dmaed || !buf->npages)
return -EINVAL;
ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
@@ -444,7 +443,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
if (ret)
goto err;
- buf->allocated_length += filled * PAGE_SIZE;
+ buf->npages += filled;
/* clean input for another bulk allocation */
memset(page_list, 0, filled * sizeof(*page_list));
to_fill = min_t(unsigned int, to_alloc,
@@ -460,8 +459,7 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
}
struct mlx5_vhca_data_buffer *
-mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
- size_t length,
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
enum dma_data_direction dma_dir)
{
struct mlx5_vhca_data_buffer *buf;
@@ -473,9 +471,8 @@ mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
buf->dma_dir = dma_dir;
buf->migf = migf;
- if (length) {
- ret = mlx5vf_add_migration_pages(buf,
- DIV_ROUND_UP_ULL(length, PAGE_SIZE));
+ if (npages) {
+ ret = mlx5vf_add_migration_pages(buf, npages);
if (ret)
goto end;
@@ -501,8 +498,8 @@ void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf)
}
struct mlx5_vhca_data_buffer *
-mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
- size_t length, enum dma_data_direction dma_dir)
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+ enum dma_data_direction dma_dir)
{
struct mlx5_vhca_data_buffer *buf, *temp_buf;
struct list_head free_list;
@@ -517,7 +514,7 @@ mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
list_for_each_entry_safe(buf, temp_buf, &migf->avail_list, buf_elm) {
if (buf->dma_dir == dma_dir) {
list_del_init(&buf->buf_elm);
- if (buf->allocated_length >= length) {
+ if (buf->npages >= npages) {
spin_unlock_irq(&migf->list_lock);
goto found;
}
@@ -531,7 +528,7 @@ mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
}
}
spin_unlock_irq(&migf->list_lock);
- buf = mlx5vf_alloc_data_buffer(migf, length, dma_dir);
+ buf = mlx5vf_alloc_data_buffer(migf, npages, dma_dir);
found:
while ((temp_buf = list_first_entry_or_null(&free_list,
@@ -712,7 +709,7 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
MLX5_SET(save_vhca_state_in, in, op_mod, 0);
MLX5_SET(save_vhca_state_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(save_vhca_state_in, in, mkey, buf->mkey);
- MLX5_SET(save_vhca_state_in, in, size, buf->allocated_length);
+ MLX5_SET(save_vhca_state_in, in, size, buf->npages * PAGE_SIZE);
MLX5_SET(save_vhca_state_in, in, incremental, inc);
MLX5_SET(save_vhca_state_in, in, set_track, track);
@@ -734,8 +731,11 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
}
if (!header_buf) {
- header_buf = mlx5vf_get_data_buffer(migf,
- sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ header_buf = mlx5vf_get_data_buffer(
+ migf,
+ DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+ PAGE_SIZE),
+ DMA_NONE);
if (IS_ERR(header_buf)) {
err = PTR_ERR(header_buf);
goto err_free;
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index df421dc6de04..7d4a833b6900 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -56,7 +56,7 @@ struct mlx5_vhca_data_buffer {
struct sg_append_table table;
loff_t start_pos;
u64 length;
- u64 allocated_length;
+ u32 npages;
u32 mkey;
enum dma_data_direction dma_dir;
u8 dmaed:1;
@@ -217,12 +217,12 @@ int mlx5vf_cmd_alloc_pd(struct mlx5_vf_migration_file *migf);
void mlx5vf_cmd_dealloc_pd(struct mlx5_vf_migration_file *migf);
void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf);
struct mlx5_vhca_data_buffer *
-mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
- size_t length, enum dma_data_direction dma_dir);
+mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+ enum dma_data_direction dma_dir);
void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf);
struct mlx5_vhca_data_buffer *
-mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
- size_t length, enum dma_data_direction dma_dir);
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf, u32 npages,
+ enum dma_data_direction dma_dir);
void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
struct page *mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
unsigned long offset);
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 61d9b0f9146d..d899cd499e27 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -308,6 +308,7 @@ static struct mlx5_vhca_data_buffer *
mlx5vf_mig_file_get_stop_copy_buf(struct mlx5_vf_migration_file *migf,
u8 index, size_t required_length)
{
+ u32 npages = DIV_ROUND_UP(required_length, PAGE_SIZE);
struct mlx5_vhca_data_buffer *buf = migf->buf[index];
u8 chunk_num;
@@ -315,12 +316,11 @@ mlx5vf_mig_file_get_stop_copy_buf(struct mlx5_vf_migration_file *migf,
chunk_num = buf->stop_copy_chunk_num;
buf->migf->buf[index] = NULL;
/* Checking whether the pre-allocated buffer can fit */
- if (buf->allocated_length >= required_length)
+ if (buf->npages >= npages)
return buf;
mlx5vf_put_data_buffer(buf);
- buf = mlx5vf_get_data_buffer(buf->migf, required_length,
- DMA_FROM_DEVICE);
+ buf = mlx5vf_get_data_buffer(buf->migf, npages, DMA_FROM_DEVICE);
if (IS_ERR(buf))
return buf;
@@ -373,7 +373,8 @@ static int mlx5vf_add_stop_copy_header(struct mlx5_vf_migration_file *migf,
u8 *to_buff;
int ret;
- header_buf = mlx5vf_get_data_buffer(migf, size, DMA_NONE);
+ header_buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(size, PAGE_SIZE),
+ DMA_NONE);
if (IS_ERR(header_buf))
return PTR_ERR(header_buf);
@@ -388,7 +389,7 @@ static int mlx5vf_add_stop_copy_header(struct mlx5_vf_migration_file *migf,
to_buff = kmap_local_page(page);
memcpy(to_buff, &header, sizeof(header));
header_buf->length = sizeof(header);
- data.stop_copy_size = cpu_to_le64(migf->buf[0]->allocated_length);
+ data.stop_copy_size = cpu_to_le64(migf->buf[0]->npages * PAGE_SIZE);
memcpy(to_buff + sizeof(header), &data, sizeof(data));
header_buf->length += sizeof(data);
kunmap_local(to_buff);
@@ -437,15 +438,20 @@ static int mlx5vf_prep_stop_copy(struct mlx5vf_pci_core_device *mvdev,
num_chunks = mvdev->chunk_mode ? MAX_NUM_CHUNKS : 1;
for (i = 0; i < num_chunks; i++) {
- buf = mlx5vf_get_data_buffer(migf, inc_state_size, DMA_FROM_DEVICE);
+ buf = mlx5vf_get_data_buffer(
+ migf, DIV_ROUND_UP(inc_state_size, PAGE_SIZE),
+ DMA_FROM_DEVICE);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
goto err;
}
migf->buf[i] = buf;
- buf = mlx5vf_get_data_buffer(migf,
- sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ buf = mlx5vf_get_data_buffer(
+ migf,
+ DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+ PAGE_SIZE),
+ DMA_NONE);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
goto err;
@@ -553,7 +559,8 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd,
* We finished transferring the current state and the device has a
* dirty state, save a new state to be ready for.
*/
- buf = mlx5vf_get_data_buffer(migf, inc_length, DMA_FROM_DEVICE);
+ buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(inc_length, PAGE_SIZE),
+ DMA_FROM_DEVICE);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
mlx5vf_mark_err(migf);
@@ -674,8 +681,8 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
if (track) {
/* leave the allocated buffer ready for the stop-copy phase */
- buf = mlx5vf_alloc_data_buffer(migf,
- migf->buf[0]->allocated_length, DMA_FROM_DEVICE);
+ buf = mlx5vf_alloc_data_buffer(migf, migf->buf[0]->npages,
+ DMA_FROM_DEVICE);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
goto out_pd;
@@ -918,11 +925,14 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
goto out_unlock;
break;
case MLX5_VF_LOAD_STATE_PREP_HEADER_DATA:
- if (vhca_buf_header->allocated_length < migf->record_size) {
+ {
+ u32 npages = DIV_ROUND_UP(migf->record_size, PAGE_SIZE);
+
+ if (vhca_buf_header->npages < npages) {
mlx5vf_free_data_buffer(vhca_buf_header);
- migf->buf_header[0] = mlx5vf_alloc_data_buffer(migf,
- migf->record_size, DMA_NONE);
+ migf->buf_header[0] = mlx5vf_alloc_data_buffer(
+ migf, npages, DMA_NONE);
if (IS_ERR(migf->buf_header[0])) {
ret = PTR_ERR(migf->buf_header[0]);
migf->buf_header[0] = NULL;
@@ -935,6 +945,7 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
vhca_buf_header->start_pos = migf->max_pos;
migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER_DATA;
break;
+ }
case MLX5_VF_LOAD_STATE_READ_HEADER_DATA:
ret = mlx5vf_resume_read_header_data(migf, vhca_buf_header,
&buf, &len, pos, &done);
@@ -945,12 +956,13 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
{
u64 size = max(migf->record_size,
migf->stop_copy_prep_size);
+ u32 npages = DIV_ROUND_UP(size, PAGE_SIZE);
- if (vhca_buf->allocated_length < size) {
+ if (vhca_buf->npages < npages) {
mlx5vf_free_data_buffer(vhca_buf);
- migf->buf[0] = mlx5vf_alloc_data_buffer(migf,
- size, DMA_TO_DEVICE);
+ migf->buf[0] = mlx5vf_alloc_data_buffer(
+ migf, npages, DMA_TO_DEVICE);
if (IS_ERR(migf->buf[0])) {
ret = PTR_ERR(migf->buf[0]);
migf->buf[0] = NULL;
@@ -1033,8 +1045,11 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
}
migf->buf[0] = buf;
- buf = mlx5vf_alloc_data_buffer(migf,
- sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ buf = mlx5vf_alloc_data_buffer(
+ migf,
+ DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+ PAGE_SIZE),
+ DMA_NONE);
if (IS_ERR(buf)) {
ret = PTR_ERR(buf);
goto out_buf;
@@ -1151,7 +1166,8 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
MLX5VF_QUERY_INC | MLX5VF_QUERY_CLEANUP);
if (ret)
return ERR_PTR(ret);
- buf = mlx5vf_get_data_buffer(migf, size, DMA_FROM_DEVICE);
+ buf = mlx5vf_get_data_buffer(migf,
+ DIV_ROUND_UP(size, PAGE_SIZE), DMA_FROM_DEVICE);
if (IS_ERR(buf))
return ERR_CAST(buf);
/* pre_copy cleanup */
--
2.46.0
Powered by blists - more mailing lists