On Thu, Sep 10, 2020 at 05:22:04PM +0300, Leon Romanovsky wrote:
> From: Avihai Horon <avihaih@xxxxxxxxxx>
>
> Expose the query GID table and entry API to user space by adding
> two new methods and method handlers to the device object.
>
> This API provides a faster way to query a GID table using single call and
> will be used in libibverbs to improve current approach that requires
> multiple calls to open, close and read multiple sysfs files for a single
> GID table entry.
>
> Signed-off-by: Avihai Horon <avihaih@xxxxxxxxxx>
> Signed-off-by: Leon Romanovsky <leonro@xxxxxxxxxx>
> .../infiniband/core/uverbs_std_types_device.c | 180 +++++++++++++++++-
> include/rdma/ib_verbs.h | 6 +-
> include/uapi/rdma/ib_user_ioctl_cmds.h | 16 ++
> include/uapi/rdma/ib_user_ioctl_verbs.h | 6 +
> 4 files changed, 204 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/infiniband/core/uverbs_std_types_device.c b/drivers/infiniband/core/uverbs_std_types_device.c
> index 7b03446b6936..beba1e284264 100644
> +++ b/drivers/infiniband/core/uverbs_std_types_device.c
> @@ -8,6 +8,7 @@
> #include "uverbs.h"
> #include <rdma/uverbs_ioctl.h>
> #include <rdma/opa_addr.h>
> +#include <rdma/ib_cache.h>
>
> /*
> * This ioctl method allows calling any defined write or write_ex
> @@ -266,6 +267,157 @@ static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_CONTEXT)(
> return ucontext->device->ops.query_ucontext(ucontext, attrs);
> }
>
> +static int copy_gid_entries_to_user(struct uverbs_attr_bundle *attrs,
> + struct ib_uverbs_gid_entry *entries,
> + size_t num_entries, size_t user_entry_size)
> +{
> + const struct uverbs_attr *attr;
> + void __user *user_entries;
> + size_t copy_len;
> + int ret;
> + int i;
> +
> + if (user_entry_size == sizeof(*entries)) {
> + ret = uverbs_copy_to(attrs,
> + UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
> + entries, sizeof(*entries) * num_entries);
> + return ret;
> + }
> +
> + copy_len = min_t(size_t, user_entry_size, sizeof(*entries));
> + attr = uverbs_attr_get(attrs, UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES);
> + if (IS_ERR(attr))
> + return PTR_ERR(attr);
> +
> + user_entries = u64_to_user_ptr(attr->ptr_attr.data);
> + for (i = 0; i < num_entries; i++) {
> + if (copy_to_user(user_entries, entries, copy_len))
> + return -EFAULT;
> +
> + if (user_entry_size > sizeof(*entries)) {
> + if (clear_user(user_entries + sizeof(*entries),
> + user_entry_size - sizeof(*entries)))
> + return -EFAULT;
> + }
> +
> + entries++;
> + user_entries += user_entry_size;
> + }
> +
> + return uverbs_output_written(attrs,
> + UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES);
> +}
> +
> +static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_GID_TABLE)(
> + struct uverbs_attr_bundle *attrs)
> +{
> + struct ib_uverbs_gid_entry *entries;
> + struct ib_ucontext *ucontext;
> + struct ib_device *ib_dev;
> + size_t user_entry_size;
> + size_t max_entries;
> + size_t num_entries;
> + u32 flags;
> + int ret;
> +
> + ret = uverbs_get_flags32(&flags, attrs,
> + UVERBS_ATTR_QUERY_GID_TABLE_FLAGS, 0);
> + if (ret)
> + return ret;
> +
> + ret = uverbs_get_const(&user_entry_size, attrs,
> + UVERBS_ATTR_QUERY_GID_TABLE_ENTRY_SIZE);
> + if (ret)
> + return ret;
> +
> + max_entries = uverbs_attr_ptr_get_array_size(
> + attrs, UVERBS_ATTR_QUERY_GID_TABLE_RESP_ENTRIES,
> + user_entry_size);
> + if (max_entries <= 0)
> + return -EINVAL;
> +
> + ucontext = ib_uverbs_get_ucontext(attrs);
> + if (IS_ERR(ucontext))
> + return PTR_ERR(ucontext);
> + ib_dev = ucontext->device;
> +
> + entries = uverbs_zalloc(attrs, max_entries * sizeof(*entries));
This multiplication could overflow
> +
> +static int UVERBS_HANDLER(UVERBS_METHOD_QUERY_GID_ENTRY)(
> + struct uverbs_attr_bundle *attrs)
> +{
> + const struct ib_gid_attr *gid_attr;
> + struct ib_uverbs_gid_entry entry;
> + struct ib_ucontext *ucontext;
> + struct ib_device *ib_dev;
> + u32 gid_index;
> + u32 port_num;
> + u32 flags;
> + int ret;
> +
> + ret = uverbs_get_flags32(&flags, attrs,
> + UVERBS_ATTR_QUERY_GID_ENTRY_FLAGS, 0);
> + if (ret)
> + return ret;
> +
> + ret = uverbs_get_const(&port_num, attrs,
> + UVERBS_ATTR_QUERY_GID_ENTRY_PORT);
> + if (ret)
> + return ret;
> +
> + ret = uverbs_get_const(&gid_index, attrs,
> + UVERBS_ATTR_QUERY_GID_ENTRY_GID_INDEX);
> + if (ret)
> + return ret;
> +
> + ucontext = ib_uverbs_get_ucontext(attrs);
> + if (IS_ERR(ucontext))
> + return PTR_ERR(ucontext);
> + ib_dev = ucontext->device;
> + if (!rdma_is_port_valid(ib_dev, port_num))
> + return -EINVAL;
> +
> + if (!rdma_ib_or_roce(ib_dev, port_num))
> + return -EINVAL;
Why these two tests? I would expect rdma_get_gid_attr() to do them
> + gid_attr = rdma_get_gid_attr(ib_dev, port_num, gid_index);
> + if (IS_ERR(gid_attr))
> + return PTR_ERR(gid_attr);
> +
> + memcpy(&entry.gid, &gid_attr->gid, sizeof(gid_attr->gid));
> + entry.gid_index = gid_attr->index;
> + entry.port_num = gid_attr->port_num;
> + entry.gid_type = gid_attr->gid_type;
> + ret = rdma_get_ndev_ifindex(gid_attr, &entry.netdev_ifindex);
Use rdma_read_gid_attr_ndev_rcu()
Jason
