2020-07-19 15:25:21 +08:00
|
|
|
/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
|
2017-08-03 21:06:55 +08:00
|
|
|
/*
|
|
|
|
* Copyright (c) 2017, Mellanox Technologies inc. All rights reserved.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _UVERBS_IOCTL_
|
|
|
|
#define _UVERBS_IOCTL_
|
|
|
|
|
|
|
|
#include <rdma/uverbs_types.h>
|
2017-08-03 21:07:01 +08:00
|
|
|
#include <linux/uaccess.h>
|
|
|
|
#include <rdma/rdma_user_ioctl.h>
|
2017-08-03 21:07:04 +08:00
|
|
|
#include <rdma/ib_user_ioctl_verbs.h>
|
2018-03-19 21:02:33 +08:00
|
|
|
#include <rdma/ib_user_ioctl_cmds.h>
|
2017-08-03 21:06:55 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* =======================================
|
|
|
|
* Verbs action specifications
|
|
|
|
* =======================================
|
|
|
|
*/
|
|
|
|
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
enum uverbs_attr_type {
|
|
|
|
UVERBS_ATTR_TYPE_NA,
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
UVERBS_ATTR_TYPE_PTR_IN,
|
|
|
|
UVERBS_ATTR_TYPE_PTR_OUT,
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
UVERBS_ATTR_TYPE_IDR,
|
|
|
|
UVERBS_ATTR_TYPE_FD,
|
2018-03-28 14:27:42 +08:00
|
|
|
UVERBS_ATTR_TYPE_ENUM_IN,
|
2018-09-06 22:27:01 +08:00
|
|
|
UVERBS_ATTR_TYPE_IDRS_ARRAY,
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
};
|
|
|
|
|
2017-08-03 21:06:55 +08:00
|
|
|
enum uverbs_obj_access {
|
|
|
|
UVERBS_ACCESS_READ,
|
|
|
|
UVERBS_ACCESS_WRITE,
|
|
|
|
UVERBS_ACCESS_NEW,
|
|
|
|
UVERBS_ACCESS_DESTROY
|
|
|
|
};
|
|
|
|
|
2018-03-19 21:02:35 +08:00
|
|
|
/* Specification of a single attribute inside the ioctl message */
|
2018-07-04 13:50:29 +08:00
|
|
|
/* good size 16 */
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
struct uverbs_attr_spec {
|
2018-07-04 13:50:25 +08:00
|
|
|
u8 type;
|
2018-07-04 13:50:29 +08:00
|
|
|
|
|
|
|
/*
|
2018-07-04 13:50:31 +08:00
|
|
|
* Support extending attributes by length. Allow the user to provide
|
|
|
|
* more bytes than ptr.len, but check that everything after is zero'd
|
|
|
|
* by the user.
|
2018-07-04 13:50:29 +08:00
|
|
|
*/
|
2018-07-04 13:50:31 +08:00
|
|
|
u8 zero_trailing:1;
|
2018-07-04 13:50:29 +08:00
|
|
|
/*
|
|
|
|
* Valid only for PTR_IN. Allocate and copy the data inside
|
|
|
|
* the parser
|
|
|
|
*/
|
|
|
|
u8 alloc_and_copy:1;
|
|
|
|
u8 mandatory:1;
|
2018-11-26 02:51:20 +08:00
|
|
|
/* True if this is from UVERBS_ATTR_UHW */
|
|
|
|
u8 is_udata:1;
|
2018-07-04 13:50:25 +08:00
|
|
|
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
union {
|
2018-03-19 21:02:35 +08:00
|
|
|
struct {
|
2018-03-19 21:02:36 +08:00
|
|
|
/* Current known size to kernel */
|
2018-07-04 13:50:25 +08:00
|
|
|
u16 len;
|
2018-03-19 21:02:36 +08:00
|
|
|
/* User isn't allowed to provide something < min_len */
|
2018-07-04 13:50:25 +08:00
|
|
|
u16 min_len;
|
2018-03-19 21:02:35 +08:00
|
|
|
} ptr;
|
2018-07-04 13:50:25 +08:00
|
|
|
|
2018-03-19 21:02:35 +08:00
|
|
|
struct {
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
/*
|
|
|
|
* higher bits mean the namespace and lower bits mean
|
|
|
|
* the type id within the namespace.
|
|
|
|
*/
|
2018-07-04 13:50:25 +08:00
|
|
|
u16 obj_type;
|
|
|
|
u8 access;
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
} obj;
|
2018-07-04 13:50:25 +08:00
|
|
|
|
|
|
|
struct {
|
|
|
|
u8 num_elems;
|
|
|
|
} enum_def;
|
|
|
|
} u;
|
|
|
|
|
2018-09-06 22:27:01 +08:00
|
|
|
/* This weird split lets us remove some padding */
|
2018-07-04 13:50:25 +08:00
|
|
|
union {
|
2018-03-28 14:27:42 +08:00
|
|
|
struct {
|
|
|
|
/*
|
|
|
|
* The enum attribute can select one of the attributes
|
|
|
|
* contained in the ids array. Currently only PTR_IN
|
|
|
|
* attributes are supported in the ids array.
|
|
|
|
*/
|
2018-07-04 13:50:25 +08:00
|
|
|
const struct uverbs_attr_spec *ids;
|
2018-03-28 14:27:42 +08:00
|
|
|
} enum_def;
|
2018-09-06 22:27:01 +08:00
|
|
|
|
|
|
|
struct {
|
|
|
|
/*
|
|
|
|
* higher bits mean the namespace and lower bits mean
|
|
|
|
* the type id within the namespace.
|
|
|
|
*/
|
|
|
|
u16 obj_type;
|
|
|
|
u16 min_len;
|
|
|
|
u16 max_len;
|
|
|
|
u8 access;
|
|
|
|
} objs_arr;
|
2018-07-04 13:50:25 +08:00
|
|
|
} u2;
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
};
|
|
|
|
|
2018-08-10 10:14:36 +08:00
|
|
|
/*
|
|
|
|
* Information about the API is loaded into a radix tree. For IOCTL we start
|
|
|
|
* with a tuple of:
|
|
|
|
* object_id, attr_id, method_id
|
|
|
|
*
|
|
|
|
* Which is a 48 bit value, with most of the bits guaranteed to be zero. Based
|
|
|
|
* on the current kernel support this is compressed into 16 bit key for the
|
|
|
|
* radix tree. Since this compression is entirely internal to the kernel the
|
|
|
|
* below limits can be revised if the kernel gains additional data.
|
|
|
|
*
|
|
|
|
* With 64 leafs per node this is a 3 level radix tree.
|
|
|
|
*
|
|
|
|
* The tree encodes multiple types, and uses a scheme where OBJ_ID,0,0 returns
|
|
|
|
* the object slot, and OBJ_ID,METH_ID,0 and returns the method slot.
|
2018-11-13 04:59:55 +08:00
|
|
|
*
|
|
|
|
* This also encodes the tables for the write() and write() extended commands
|
|
|
|
* using the coding
|
|
|
|
* OBJ_ID,UVERBS_API_METHOD_IS_WRITE,command #
|
|
|
|
* OBJ_ID,UVERBS_API_METHOD_IS_WRITE_EX,command_ex #
|
|
|
|
* ie the WRITE path is treated as a special method type in the ioctl
|
|
|
|
* framework.
|
2018-08-10 10:14:36 +08:00
|
|
|
*/
|
|
|
|
enum uapi_radix_data {
|
|
|
|
UVERBS_API_NS_FLAG = 1U << UVERBS_ID_NS_SHIFT,
|
|
|
|
|
|
|
|
UVERBS_API_ATTR_KEY_BITS = 6,
|
|
|
|
UVERBS_API_ATTR_KEY_MASK = GENMASK(UVERBS_API_ATTR_KEY_BITS - 1, 0),
|
|
|
|
UVERBS_API_ATTR_BKEY_LEN = (1 << UVERBS_API_ATTR_KEY_BITS) - 1,
|
2018-11-13 04:59:55 +08:00
|
|
|
UVERBS_API_WRITE_KEY_NUM = 1 << UVERBS_API_ATTR_KEY_BITS,
|
2018-08-10 10:14:36 +08:00
|
|
|
|
|
|
|
UVERBS_API_METHOD_KEY_BITS = 5,
|
|
|
|
UVERBS_API_METHOD_KEY_SHIFT = UVERBS_API_ATTR_KEY_BITS,
|
2018-11-13 04:59:55 +08:00
|
|
|
UVERBS_API_METHOD_KEY_NUM_CORE = 22,
|
|
|
|
UVERBS_API_METHOD_IS_WRITE = 30 << UVERBS_API_METHOD_KEY_SHIFT,
|
|
|
|
UVERBS_API_METHOD_IS_WRITE_EX = 31 << UVERBS_API_METHOD_KEY_SHIFT,
|
|
|
|
UVERBS_API_METHOD_KEY_NUM_DRIVER =
|
|
|
|
(UVERBS_API_METHOD_IS_WRITE >> UVERBS_API_METHOD_KEY_SHIFT) -
|
|
|
|
UVERBS_API_METHOD_KEY_NUM_CORE,
|
2018-08-10 10:14:36 +08:00
|
|
|
UVERBS_API_METHOD_KEY_MASK = GENMASK(
|
|
|
|
UVERBS_API_METHOD_KEY_BITS + UVERBS_API_METHOD_KEY_SHIFT - 1,
|
|
|
|
UVERBS_API_METHOD_KEY_SHIFT),
|
|
|
|
|
|
|
|
UVERBS_API_OBJ_KEY_BITS = 5,
|
|
|
|
UVERBS_API_OBJ_KEY_SHIFT =
|
|
|
|
UVERBS_API_METHOD_KEY_BITS + UVERBS_API_METHOD_KEY_SHIFT,
|
2020-03-24 14:01:39 +08:00
|
|
|
UVERBS_API_OBJ_KEY_NUM_CORE = 20,
|
2018-08-10 10:14:36 +08:00
|
|
|
UVERBS_API_OBJ_KEY_NUM_DRIVER =
|
|
|
|
(1 << UVERBS_API_OBJ_KEY_BITS) - UVERBS_API_OBJ_KEY_NUM_CORE,
|
|
|
|
UVERBS_API_OBJ_KEY_MASK = GENMASK(31, UVERBS_API_OBJ_KEY_SHIFT),
|
|
|
|
|
|
|
|
/* This id guaranteed to not exist in the radix tree */
|
|
|
|
UVERBS_API_KEY_ERR = 0xFFFFFFFF,
|
|
|
|
};
|
|
|
|
|
|
|
|
static inline __attribute_const__ u32 uapi_key_obj(u32 id)
|
|
|
|
{
|
|
|
|
if (id & UVERBS_API_NS_FLAG) {
|
|
|
|
id &= ~UVERBS_API_NS_FLAG;
|
|
|
|
if (id >= UVERBS_API_OBJ_KEY_NUM_DRIVER)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
id = id + UVERBS_API_OBJ_KEY_NUM_CORE;
|
|
|
|
} else {
|
|
|
|
if (id >= UVERBS_API_OBJ_KEY_NUM_CORE)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
}
|
|
|
|
|
|
|
|
return id << UVERBS_API_OBJ_KEY_SHIFT;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ bool uapi_key_is_object(u32 key)
|
|
|
|
{
|
|
|
|
return (key & ~UVERBS_API_OBJ_KEY_MASK) == 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ u32 uapi_key_ioctl_method(u32 id)
|
|
|
|
{
|
|
|
|
if (id & UVERBS_API_NS_FLAG) {
|
|
|
|
id &= ~UVERBS_API_NS_FLAG;
|
|
|
|
if (id >= UVERBS_API_METHOD_KEY_NUM_DRIVER)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
id = id + UVERBS_API_METHOD_KEY_NUM_CORE;
|
|
|
|
} else {
|
|
|
|
id++;
|
|
|
|
if (id >= UVERBS_API_METHOD_KEY_NUM_CORE)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
}
|
|
|
|
|
|
|
|
return id << UVERBS_API_METHOD_KEY_SHIFT;
|
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:55 +08:00
|
|
|
static inline __attribute_const__ u32 uapi_key_write_method(u32 id)
|
|
|
|
{
|
|
|
|
if (id >= UVERBS_API_WRITE_KEY_NUM)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
return UVERBS_API_METHOD_IS_WRITE | id;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ u32 uapi_key_write_ex_method(u32 id)
|
|
|
|
{
|
|
|
|
if (id >= UVERBS_API_WRITE_KEY_NUM)
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
return UVERBS_API_METHOD_IS_WRITE_EX | id;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ u32
|
|
|
|
uapi_key_attr_to_ioctl_method(u32 attr_key)
|
2018-08-10 10:14:36 +08:00
|
|
|
{
|
|
|
|
return attr_key &
|
|
|
|
(UVERBS_API_OBJ_KEY_MASK | UVERBS_API_METHOD_KEY_MASK);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ bool uapi_key_is_ioctl_method(u32 key)
|
|
|
|
{
|
2018-11-13 04:59:55 +08:00
|
|
|
unsigned int method = key & UVERBS_API_METHOD_KEY_MASK;
|
|
|
|
|
|
|
|
return method != 0 && method < UVERBS_API_METHOD_IS_WRITE &&
|
2018-08-10 10:14:36 +08:00
|
|
|
(key & UVERBS_API_ATTR_KEY_MASK) == 0;
|
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:55 +08:00
|
|
|
static inline __attribute_const__ bool uapi_key_is_write_method(u32 key)
|
|
|
|
{
|
|
|
|
return (key & UVERBS_API_METHOD_KEY_MASK) == UVERBS_API_METHOD_IS_WRITE;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ bool uapi_key_is_write_ex_method(u32 key)
|
|
|
|
{
|
|
|
|
return (key & UVERBS_API_METHOD_KEY_MASK) ==
|
|
|
|
UVERBS_API_METHOD_IS_WRITE_EX;
|
|
|
|
}
|
|
|
|
|
2018-08-10 10:14:36 +08:00
|
|
|
static inline __attribute_const__ u32 uapi_key_attrs_start(u32 ioctl_method_key)
|
|
|
|
{
|
|
|
|
/* 0 is the method slot itself */
|
|
|
|
return ioctl_method_key + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __attribute_const__ u32 uapi_key_attr(u32 id)
|
|
|
|
{
|
|
|
|
/*
|
|
|
|
* The attr is designed to fit in the typical single radix tree node
|
|
|
|
* of 64 entries. Since allmost all methods have driver attributes we
|
|
|
|
* organize things so that the driver and core attributes interleave to
|
|
|
|
* reduce the length of the attributes array in typical cases.
|
|
|
|
*/
|
|
|
|
if (id & UVERBS_API_NS_FLAG) {
|
|
|
|
id &= ~UVERBS_API_NS_FLAG;
|
|
|
|
id++;
|
|
|
|
if (id >= 1 << (UVERBS_API_ATTR_KEY_BITS - 1))
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
id = (id << 1) | 0;
|
|
|
|
} else {
|
|
|
|
if (id >= 1 << (UVERBS_API_ATTR_KEY_BITS - 1))
|
|
|
|
return UVERBS_API_KEY_ERR;
|
|
|
|
id = (id << 1) | 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return id;
|
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:55 +08:00
|
|
|
/* Only true for ioctl methods */
|
2018-08-10 10:14:36 +08:00
|
|
|
static inline __attribute_const__ bool uapi_key_is_attr(u32 key)
|
|
|
|
{
|
2018-11-13 04:59:55 +08:00
|
|
|
unsigned int method = key & UVERBS_API_METHOD_KEY_MASK;
|
|
|
|
|
|
|
|
return method != 0 && method < UVERBS_API_METHOD_IS_WRITE &&
|
2018-08-10 10:14:36 +08:00
|
|
|
(key & UVERBS_API_ATTR_KEY_MASK) != 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* This returns a value in the range [0 to UVERBS_API_ATTR_BKEY_LEN),
|
|
|
|
* basically it undoes the reservation of 0 in the ID numbering. attr_key
|
|
|
|
* must already be masked with UVERBS_API_ATTR_KEY_MASK, or be the output of
|
|
|
|
* uapi_key_attr().
|
|
|
|
*/
|
|
|
|
static inline __attribute_const__ u32 uapi_bkey_attr(u32 attr_key)
|
|
|
|
{
|
|
|
|
return attr_key - 1;
|
|
|
|
}
|
|
|
|
|
2018-09-06 22:27:01 +08:00
|
|
|
static inline __attribute_const__ u32 uapi_bkey_to_key_attr(u32 attr_bkey)
|
|
|
|
{
|
|
|
|
return attr_bkey + 1;
|
|
|
|
}
|
|
|
|
|
2017-08-03 21:06:58 +08:00
|
|
|
/*
|
|
|
|
* =======================================
|
|
|
|
* Verbs definitions
|
|
|
|
* =======================================
|
|
|
|
*/
|
|
|
|
|
2017-08-03 21:06:59 +08:00
|
|
|
struct uverbs_attr_def {
|
|
|
|
u16 id;
|
|
|
|
struct uverbs_attr_spec attr;
|
|
|
|
};
|
|
|
|
|
|
|
|
struct uverbs_method_def {
|
|
|
|
u16 id;
|
|
|
|
/* Combination of bits from enum UVERBS_ACTION_FLAG_XXXX */
|
|
|
|
u32 flags;
|
|
|
|
size_t num_attrs;
|
|
|
|
const struct uverbs_attr_def * const (*attrs)[];
|
2018-11-26 02:51:15 +08:00
|
|
|
int (*handler)(struct uverbs_attr_bundle *attrs);
|
2017-08-03 21:06:59 +08:00
|
|
|
};
|
|
|
|
|
2017-08-03 21:06:58 +08:00
|
|
|
struct uverbs_object_def {
|
2017-08-03 21:06:59 +08:00
|
|
|
u16 id;
|
2017-08-03 21:06:58 +08:00
|
|
|
const struct uverbs_obj_type *type_attrs;
|
2017-08-03 21:06:59 +08:00
|
|
|
size_t num_methods;
|
|
|
|
const struct uverbs_method_def * const (*methods)[];
|
|
|
|
};
|
|
|
|
|
2018-11-13 04:59:50 +08:00
|
|
|
enum uapi_definition_kind {
|
|
|
|
UAPI_DEF_END = 0,
|
2018-11-13 04:59:55 +08:00
|
|
|
UAPI_DEF_OBJECT_START,
|
|
|
|
UAPI_DEF_WRITE,
|
2018-11-13 04:59:50 +08:00
|
|
|
UAPI_DEF_CHAIN_OBJ_TREE,
|
|
|
|
UAPI_DEF_CHAIN,
|
2018-11-13 04:59:52 +08:00
|
|
|
UAPI_DEF_IS_SUPPORTED_FUNC,
|
|
|
|
UAPI_DEF_IS_SUPPORTED_DEV_FN,
|
|
|
|
};
|
|
|
|
|
|
|
|
enum uapi_definition_scope {
|
|
|
|
UAPI_SCOPE_OBJECT = 1,
|
2018-11-13 04:59:58 +08:00
|
|
|
UAPI_SCOPE_METHOD = 2,
|
2017-08-03 21:06:58 +08:00
|
|
|
};
|
|
|
|
|
2018-11-13 04:59:50 +08:00
|
|
|
struct uapi_definition {
|
|
|
|
u8 kind;
|
2018-11-13 04:59:52 +08:00
|
|
|
u8 scope;
|
2018-11-13 04:59:50 +08:00
|
|
|
union {
|
|
|
|
struct {
|
|
|
|
u16 object_id;
|
|
|
|
} object_start;
|
2018-11-13 04:59:55 +08:00
|
|
|
struct {
|
|
|
|
u16 command_num;
|
2018-11-26 02:51:16 +08:00
|
|
|
u8 is_ex:1;
|
|
|
|
u8 has_udata:1;
|
|
|
|
u8 has_resp:1;
|
|
|
|
u8 req_size;
|
|
|
|
u8 resp_size;
|
2018-11-13 04:59:55 +08:00
|
|
|
} write;
|
2018-11-13 04:59:50 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
union {
|
2018-11-13 04:59:52 +08:00
|
|
|
bool (*func_is_supported)(struct ib_device *device);
|
2018-11-26 02:58:45 +08:00
|
|
|
int (*func_write)(struct uverbs_attr_bundle *attrs);
|
2018-11-13 04:59:50 +08:00
|
|
|
const struct uapi_definition *chain;
|
|
|
|
const struct uverbs_object_def *chain_obj_tree;
|
2018-11-13 04:59:52 +08:00
|
|
|
size_t needs_fn_offset;
|
2018-11-13 04:59:50 +08:00
|
|
|
};
|
|
|
|
};
|
|
|
|
|
2018-11-13 04:59:55 +08:00
|
|
|
/* Define things connected to object_id */
|
|
|
|
#define DECLARE_UVERBS_OBJECT(_object_id, ...) \
|
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_OBJECT_START, \
|
|
|
|
.object_start = { .object_id = _object_id }, \
|
|
|
|
}, \
|
|
|
|
##__VA_ARGS__
|
|
|
|
|
|
|
|
/* Use in a var_args of DECLARE_UVERBS_OBJECT */
|
2018-11-26 02:51:16 +08:00
|
|
|
#define DECLARE_UVERBS_WRITE(_command_num, _func, _cmd_desc, ...) \
|
2018-11-13 04:59:55 +08:00
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_WRITE, \
|
|
|
|
.scope = UAPI_SCOPE_OBJECT, \
|
|
|
|
.write = { .is_ex = 0, .command_num = _command_num }, \
|
|
|
|
.func_write = _func, \
|
2018-11-26 02:51:16 +08:00
|
|
|
_cmd_desc, \
|
2018-11-13 04:59:55 +08:00
|
|
|
}, \
|
|
|
|
##__VA_ARGS__
|
|
|
|
|
|
|
|
/* Use in a var_args of DECLARE_UVERBS_OBJECT */
|
2018-11-26 02:51:16 +08:00
|
|
|
#define DECLARE_UVERBS_WRITE_EX(_command_num, _func, _cmd_desc, ...) \
|
2018-11-13 04:59:55 +08:00
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_WRITE, \
|
|
|
|
.scope = UAPI_SCOPE_OBJECT, \
|
|
|
|
.write = { .is_ex = 1, .command_num = _command_num }, \
|
2018-11-26 02:58:45 +08:00
|
|
|
.func_write = _func, \
|
2018-11-26 02:51:16 +08:00
|
|
|
_cmd_desc, \
|
2018-11-13 04:59:55 +08:00
|
|
|
}, \
|
|
|
|
##__VA_ARGS__
|
|
|
|
|
2018-11-13 04:59:52 +08:00
|
|
|
/*
|
|
|
|
* Object is only supported if the function pointer named ibdev_fn in struct
|
|
|
|
* ib_device is not NULL.
|
|
|
|
*/
|
|
|
|
#define UAPI_DEF_OBJ_NEEDS_FN(ibdev_fn) \
|
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_IS_SUPPORTED_DEV_FN, \
|
|
|
|
.scope = UAPI_SCOPE_OBJECT, \
|
|
|
|
.needs_fn_offset = \
|
2018-12-11 03:09:48 +08:00
|
|
|
offsetof(struct ib_device_ops, ibdev_fn) + \
|
2020-05-27 22:41:52 +08:00
|
|
|
BUILD_BUG_ON_ZERO(sizeof_field(struct ib_device_ops, \
|
|
|
|
ibdev_fn) != \
|
|
|
|
sizeof(void *)), \
|
2018-11-13 04:59:52 +08:00
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:58 +08:00
|
|
|
/*
|
|
|
|
* Method is only supported if the function pointer named ibdev_fn in struct
|
|
|
|
* ib_device is not NULL.
|
|
|
|
*/
|
|
|
|
#define UAPI_DEF_METHOD_NEEDS_FN(ibdev_fn) \
|
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_IS_SUPPORTED_DEV_FN, \
|
|
|
|
.scope = UAPI_SCOPE_METHOD, \
|
|
|
|
.needs_fn_offset = \
|
2018-12-11 03:09:48 +08:00
|
|
|
offsetof(struct ib_device_ops, ibdev_fn) + \
|
2020-05-27 22:41:52 +08:00
|
|
|
BUILD_BUG_ON_ZERO(sizeof_field(struct ib_device_ops, \
|
|
|
|
ibdev_fn) != \
|
|
|
|
sizeof(void *)), \
|
2018-11-13 04:59:58 +08:00
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:52 +08:00
|
|
|
/* Call a function to determine if the entire object is supported or not */
|
|
|
|
#define UAPI_DEF_IS_OBJ_SUPPORTED(_func) \
|
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_IS_SUPPORTED_FUNC, \
|
|
|
|
.scope = UAPI_SCOPE_OBJECT, .func_is_supported = _func, \
|
|
|
|
}
|
|
|
|
|
2018-11-13 04:59:50 +08:00
|
|
|
/* Include another struct uapi_definition in this one */
|
|
|
|
#define UAPI_DEF_CHAIN(_def_var) \
|
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_CHAIN, .chain = _def_var, \
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Temporary until the tree base description is replaced */
|
2018-12-10 17:19:49 +08:00
|
|
|
#define UAPI_DEF_CHAIN_OBJ_TREE(_object_enum, _object_ptr, ...) \
|
2018-11-13 04:59:50 +08:00
|
|
|
{ \
|
|
|
|
.kind = UAPI_DEF_CHAIN_OBJ_TREE, \
|
|
|
|
.object_start = { .object_id = _object_enum }, \
|
|
|
|
.chain_obj_tree = _object_ptr, \
|
2018-12-10 17:19:49 +08:00
|
|
|
}, \
|
2018-11-13 04:59:50 +08:00
|
|
|
##__VA_ARGS__
|
2018-12-10 17:19:49 +08:00
|
|
|
#define UAPI_DEF_CHAIN_OBJ_TREE_NAMED(_object_enum, ...) \
|
|
|
|
UAPI_DEF_CHAIN_OBJ_TREE(_object_enum, &UVERBS_OBJECT(_object_enum), \
|
|
|
|
##__VA_ARGS__)
|
2018-11-13 04:59:50 +08:00
|
|
|
|
2018-07-04 13:50:25 +08:00
|
|
|
/*
|
|
|
|
* =======================================
|
|
|
|
* Attribute Specifications
|
|
|
|
* =======================================
|
|
|
|
*/
|
2018-03-19 21:02:36 +08:00
|
|
|
|
|
|
|
#define UVERBS_ATTR_SIZE(_min_len, _len) \
|
2018-07-04 13:50:25 +08:00
|
|
|
.u.ptr.min_len = _min_len, .u.ptr.len = _len
|
2018-07-04 13:50:31 +08:00
|
|
|
|
2018-07-23 20:25:07 +08:00
|
|
|
#define UVERBS_ATTR_NO_DATA() UVERBS_ATTR_SIZE(0, 0)
|
|
|
|
|
2018-07-04 13:50:31 +08:00
|
|
|
/*
|
|
|
|
* Specifies a uapi structure that cannot be extended. The user must always
|
|
|
|
* supply the whole structure and nothing more. The structure must be declared
|
|
|
|
* in a header under include/uapi/rdma.
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_TYPE(_type) \
|
|
|
|
.u.ptr.min_len = sizeof(_type), .u.ptr.len = sizeof(_type)
|
|
|
|
/*
|
|
|
|
* Specifies a uapi structure where the user must provide at least up to
|
|
|
|
* member 'last'. Anything after last and up until the end of the structure
|
|
|
|
* can be non-zero, anything longer than the end of the structure must be
|
|
|
|
* zero. The structure must be declared in a header under include/uapi/rdma.
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_STRUCT(_type, _last) \
|
|
|
|
.zero_trailing = 1, \
|
2020-05-28 01:18:45 +08:00
|
|
|
UVERBS_ATTR_SIZE(offsetofend(_type, _last), sizeof(_type))
|
2018-07-04 13:50:30 +08:00
|
|
|
/*
|
|
|
|
* Specifies at least min_len bytes must be passed in, but the amount can be
|
|
|
|
* larger, up to the protocol maximum size. No check for zeroing is done.
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_MIN_SIZE(_min_len) UVERBS_ATTR_SIZE(_min_len, USHRT_MAX)
|
2018-03-19 21:02:36 +08:00
|
|
|
|
2018-07-04 13:50:25 +08:00
|
|
|
/* Must be used in the '...' of any UVERBS_ATTR */
|
2018-07-04 13:50:29 +08:00
|
|
|
#define UA_ALLOC_AND_COPY .alloc_and_copy = 1
|
|
|
|
#define UA_MANDATORY .mandatory = 1
|
|
|
|
#define UA_OPTIONAL .mandatory = 0
|
2018-07-04 13:50:25 +08:00
|
|
|
|
2018-09-06 22:27:01 +08:00
|
|
|
/*
|
|
|
|
* min_len must be bigger than 0 and _max_len must be smaller than 4095. Only
|
|
|
|
* READ\WRITE accesses are supported.
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_IDRS_ARR(_attr_id, _idr_type, _access, _min_len, _max_len, \
|
|
|
|
...) \
|
|
|
|
(&(const struct uverbs_attr_def){ \
|
|
|
|
.id = (_attr_id) + \
|
|
|
|
BUILD_BUG_ON_ZERO((_min_len) == 0 || \
|
|
|
|
(_max_len) > \
|
|
|
|
PAGE_SIZE / sizeof(void *) || \
|
|
|
|
(_min_len) > (_max_len) || \
|
|
|
|
(_access) == UVERBS_ACCESS_NEW || \
|
|
|
|
(_access) == UVERBS_ACCESS_DESTROY), \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_IDRS_ARRAY, \
|
|
|
|
.u2.objs_arr.obj_type = _idr_type, \
|
|
|
|
.u2.objs_arr.access = _access, \
|
|
|
|
.u2.objs_arr.min_len = _min_len, \
|
|
|
|
.u2.objs_arr.max_len = _max_len, \
|
|
|
|
__VA_ARGS__ } })
|
|
|
|
|
2018-11-26 14:28:33 +08:00
|
|
|
/*
|
|
|
|
* Only for use with UVERBS_ATTR_IDR, allows any uobject type to be accepted,
|
|
|
|
* the user must validate the type of the uobject instead.
|
|
|
|
*/
|
|
|
|
#define UVERBS_IDR_ANY_OBJECT 0xFFFF
|
|
|
|
|
2018-07-04 13:50:25 +08:00
|
|
|
#define UVERBS_ATTR_IDR(_attr_id, _idr_type, _access, ...) \
|
2018-07-04 13:50:28 +08:00
|
|
|
(&(const struct uverbs_attr_def){ \
|
2018-07-04 13:50:25 +08:00
|
|
|
.id = _attr_id, \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_IDR, \
|
|
|
|
.u.obj.obj_type = _idr_type, \
|
|
|
|
.u.obj.access = _access, \
|
|
|
|
__VA_ARGS__ } })
|
|
|
|
|
|
|
|
#define UVERBS_ATTR_FD(_attr_id, _fd_type, _access, ...) \
|
2018-07-04 13:50:28 +08:00
|
|
|
(&(const struct uverbs_attr_def){ \
|
2018-07-04 13:50:25 +08:00
|
|
|
.id = (_attr_id) + \
|
|
|
|
BUILD_BUG_ON_ZERO((_access) != UVERBS_ACCESS_NEW && \
|
|
|
|
(_access) != UVERBS_ACCESS_READ), \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_FD, \
|
|
|
|
.u.obj.obj_type = _fd_type, \
|
|
|
|
.u.obj.access = _access, \
|
|
|
|
__VA_ARGS__ } })
|
|
|
|
|
|
|
|
#define UVERBS_ATTR_PTR_IN(_attr_id, _type, ...) \
|
2018-07-04 13:50:28 +08:00
|
|
|
(&(const struct uverbs_attr_def){ \
|
2018-07-04 13:50:25 +08:00
|
|
|
.id = _attr_id, \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_PTR_IN, \
|
|
|
|
_type, \
|
|
|
|
__VA_ARGS__ } })
|
|
|
|
|
|
|
|
#define UVERBS_ATTR_PTR_OUT(_attr_id, _type, ...) \
|
2018-07-04 13:50:28 +08:00
|
|
|
(&(const struct uverbs_attr_def){ \
|
2018-07-04 13:50:25 +08:00
|
|
|
.id = _attr_id, \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_PTR_OUT, \
|
|
|
|
_type, \
|
|
|
|
__VA_ARGS__ } })
|
|
|
|
|
|
|
|
/* _enum_arry should be a 'static const union uverbs_attr_spec[]' */
|
|
|
|
#define UVERBS_ATTR_ENUM_IN(_attr_id, _enum_arr, ...) \
|
2018-07-04 13:50:28 +08:00
|
|
|
(&(const struct uverbs_attr_def){ \
|
2018-07-04 13:50:25 +08:00
|
|
|
.id = _attr_id, \
|
|
|
|
.attr = { .type = UVERBS_ATTR_TYPE_ENUM_IN, \
|
|
|
|
.u2.enum_def.ids = _enum_arr, \
|
|
|
|
.u.enum_def.num_elems = ARRAY_SIZE(_enum_arr), \
|
|
|
|
__VA_ARGS__ }, \
|
|
|
|
})
|
2017-08-03 21:07:01 +08:00
|
|
|
|
2018-08-28 19:18:50 +08:00
|
|
|
/* An input value that is a member in the enum _enum_type. */
|
|
|
|
#define UVERBS_ATTR_CONST_IN(_attr_id, _enum_type, ...) \
|
|
|
|
UVERBS_ATTR_PTR_IN( \
|
|
|
|
_attr_id, \
|
|
|
|
UVERBS_ATTR_SIZE( \
|
|
|
|
sizeof(u64) + BUILD_BUG_ON_ZERO(!sizeof(_enum_type)), \
|
|
|
|
sizeof(u64)), \
|
|
|
|
__VA_ARGS__)
|
|
|
|
|
2018-07-27 06:37:14 +08:00
|
|
|
/*
|
|
|
|
* An input value that is a bitwise combination of values of _enum_type.
|
|
|
|
* This permits the flag value to be passed as either a u32 or u64, it must
|
|
|
|
* be retrieved via uverbs_get_flag().
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_FLAGS_IN(_attr_id, _enum_type, ...) \
|
|
|
|
UVERBS_ATTR_PTR_IN( \
|
|
|
|
_attr_id, \
|
|
|
|
UVERBS_ATTR_SIZE(sizeof(u32) + BUILD_BUG_ON_ZERO( \
|
|
|
|
!sizeof(_enum_type *)), \
|
|
|
|
sizeof(u64)), \
|
|
|
|
__VA_ARGS__)
|
|
|
|
|
2018-07-04 13:50:27 +08:00
|
|
|
/*
|
|
|
|
* This spec is used in order to pass information to the hardware driver in a
|
|
|
|
* legacy way. Every verb that could get driver specific data should get this
|
|
|
|
* spec.
|
|
|
|
*/
|
|
|
|
#define UVERBS_ATTR_UHW() \
|
2018-07-04 13:50:28 +08:00
|
|
|
UVERBS_ATTR_PTR_IN(UVERBS_ATTR_UHW_IN, \
|
2018-07-04 13:50:30 +08:00
|
|
|
UVERBS_ATTR_MIN_SIZE(0), \
|
2018-11-26 02:51:20 +08:00
|
|
|
UA_OPTIONAL, \
|
|
|
|
.is_udata = 1), \
|
2018-07-04 13:50:28 +08:00
|
|
|
UVERBS_ATTR_PTR_OUT(UVERBS_ATTR_UHW_OUT, \
|
2018-07-04 13:50:30 +08:00
|
|
|
UVERBS_ATTR_MIN_SIZE(0), \
|
2018-11-26 02:51:20 +08:00
|
|
|
UA_OPTIONAL, \
|
|
|
|
.is_udata = 1)
|
2018-07-04 13:50:27 +08:00
|
|
|
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
/* =================================================
|
|
|
|
* Parsing infrastructure
|
|
|
|
* =================================================
|
|
|
|
*/
|
|
|
|
|
2018-08-10 10:14:42 +08:00
|
|
|
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
struct uverbs_ptr_attr {
|
2018-06-17 17:59:52 +08:00
|
|
|
/*
|
|
|
|
* If UVERBS_ATTR_SPEC_F_ALLOC_AND_COPY is set then the 'ptr' is
|
|
|
|
* used.
|
|
|
|
*/
|
|
|
|
union {
|
|
|
|
void *ptr;
|
|
|
|
u64 data;
|
|
|
|
};
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
u16 len;
|
2018-08-10 10:14:39 +08:00
|
|
|
u16 uattr_idx;
|
2018-03-28 14:27:42 +08:00
|
|
|
u8 enum_id;
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
};
|
|
|
|
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
struct uverbs_obj_attr {
|
|
|
|
struct ib_uobject *uobject;
|
2018-08-10 10:14:42 +08:00
|
|
|
const struct uverbs_api_attr *attr_elm;
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
};
|
|
|
|
|
2018-09-06 22:27:01 +08:00
|
|
|
struct uverbs_objs_arr_attr {
|
|
|
|
struct ib_uobject **uobjects;
|
|
|
|
u16 len;
|
|
|
|
};
|
|
|
|
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
struct uverbs_attr {
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
union {
|
|
|
|
struct uverbs_ptr_attr ptr_attr;
|
|
|
|
struct uverbs_obj_attr obj_attr;
|
2018-09-06 22:27:01 +08:00
|
|
|
struct uverbs_objs_arr_attr objs_arr_attr;
|
IB/core: Add new ioctl interface
In this ioctl interface, processing the command starts from
properties of the command and fetching the appropriate user objects
before calling the handler.
Parsing and validation is done according to a specifier declared by
the driver's code. In the driver, all supported objects are declared.
These objects are separated to different object namepsaces. Dividing
objects to namespaces is done at initialization by using the higher
bits of the object ids. This initialization can mix objects declared
in different places to one parsing tree using in this ioctl interface.
For each object we list all supported methods. Similarly to objects,
methods are separated to method namespaces too. Namespacing is done
similarly to the objects case. This could be used in order to add
methods to an existing object.
Each method has a specific handler, which could be either a default
handler or a driver specific handler.
Along with the handler, a bunch of attributes are specified as well.
Similarly to objects and method, attributes are namespaced and hashed
by their ids at initialization too. All supported attributes are
subject to automatic fetching and validation. These attributes include
the command, response and the method's related objects' ids.
When these entities (objects, methods and attributes) are used, the
high bits of the entities ids are used in order to calculate the hash
bucket index. Then, these high bits are masked out in order to have a
zero based index. Since we use these high bits for both bucketing and
namespacing, we get a compact representation and O(1) array access.
This is mandatory for efficient dispatching.
Each attribute has a type (PTR_IN, PTR_OUT, IDR and FD) and a length.
Attributes could be validated through some attributes, like:
(*) Minimum size / Exact size
(*) Fops for FD
(*) Object type for IDR
If an IDR/fd attribute is specified, the kernel also states the object
type and the required access (NEW, WRITE, READ or DESTROY).
All uobject/fd management is done automatically by the infrastructure,
meaning - the infrastructure will fail concurrent commands that at
least one of them requires concurrent access (WRITE/DESTROY),
synchronize actions with device removals (dissociate context events)
and take care of reference counting (increase/decrease) for concurrent
actions invocation. The reference counts on the actual kernel objects
shall be handled by the handlers.
objects
+--------+
| |
| | methods +--------+
| | ns method method_spec +-----+ |len |
+--------+ +------+[d]+-------+ +----------------+[d]+------------+ |attr1+-> |type |
| object +> |method+-> | spec +-> + attr_buckets +-> |default_chain+--> +-----+ |idr_type|
+--------+ +------+ |handler| | | +------------+ |attr2| |access |
| | | | +-------+ +----------------+ |driver chain| +-----+ +--------+
| | | | +------------+
| | +------+
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
+--------+
[d] = Hash ids to groups using the high order bits
The right types table is also chosen by using the high bits from
the ids. Currently we have either default or driver specific groups.
Once validation and object fetching (or creation) completed, we call
the handler:
int (*handler)(struct ib_device *ib_dev, struct ib_uverbs_file *ufile,
struct uverbs_attr_bundle *ctx);
ctx bundles attributes of different namespaces. Each element there
is an array of attributes which corresponds to one namespaces of
attributes. For example, in the usually used case:
ctx core
+----------------------------+ +------------+
| core: +---> | valid |
+----------------------------+ | cmd_attr |
| driver: | +------------+
|----------------------------+--+ | valid |
| | cmd_attr |
| +------------+
| | valid |
| | obj_attr |
| +------------+
|
| drivers
| +------------+
+> | valid |
| cmd_attr |
+------------+
| valid |
| cmd_attr |
+------------+
| valid |
| obj_attr |
+------------+
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:57 +08:00
|
|
|
};
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
struct uverbs_attr_bundle {
|
2018-11-26 02:51:18 +08:00
|
|
|
struct ib_udata driver_udata;
|
2018-11-26 02:58:35 +08:00
|
|
|
struct ib_udata ucore;
|
2018-08-10 10:14:38 +08:00
|
|
|
struct ib_uverbs_file *ufile;
|
2019-02-08 00:44:47 +08:00
|
|
|
struct ib_ucontext *context;
|
2020-07-19 13:22:22 +08:00
|
|
|
struct ib_uobject *uobject;
|
2018-08-10 10:14:42 +08:00
|
|
|
DECLARE_BITMAP(attr_present, UVERBS_API_ATTR_BKEY_LEN);
|
|
|
|
struct uverbs_attr attrs[];
|
IB/core: Add support to finalize objects in one transaction
The new ioctl based infrastructure either commits or rollbacks
all objects of the method as one transaction. In order to do
that, we introduce a notion of dealing with a collection of
objects that are related to a specific method.
This also requires adding a notion of a method and attribute.
A method contains a hash of attributes, where each bucket
contains several attributes. The attributes are hashed according
to their namespace which resides in the four upper bits of the id.
For example, an object could be a CQ, which has an action of CREATE_CQ.
This action has multiple attributes. For example, the CQ's new handle
and the comp_channel. Each layer in this hierarchy - objects, methods
and attributes is split into namespaces. The basic example for that is
one namespace representing the default entities and another one
representing the driver specific entities.
When declaring these methods and attributes, we actually declare
their specifications. When a method is executed, we actually
allocates some space to hold auxiliary information. This auxiliary
information contains meta-data about the required objects, such
as pointers to their type information, pointers to the uobjects
themselves (if exist), etc.
The specification, along with the auxiliary information we allocated
and filled is given to the finalize_objects function.
Signed-off-by: Matan Barak <matanb@mellanox.com>
Reviewed-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
2017-08-03 21:06:56 +08:00
|
|
|
};
|
|
|
|
|
2017-08-03 21:07:01 +08:00
|
|
|
static inline bool uverbs_attr_is_valid(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
unsigned int idx)
|
|
|
|
{
|
2018-08-10 10:14:42 +08:00
|
|
|
return test_bit(uapi_bkey_attr(uapi_key_attr(idx)),
|
|
|
|
attrs_bundle->attr_present);
|
2017-08-03 21:07:01 +08:00
|
|
|
}
|
|
|
|
|
2019-02-08 00:44:48 +08:00
|
|
|
/**
|
|
|
|
* rdma_udata_to_drv_context - Helper macro to get the driver's context out of
|
|
|
|
* ib_udata which is embedded in uverbs_attr_bundle.
|
|
|
|
*
|
|
|
|
* If udata is not NULL this cannot fail. Otherwise a NULL udata will result
|
|
|
|
* in a NULL ucontext pointer, as a safety precaution. Callers should be using
|
|
|
|
* 'udata' to determine if the driver call is in user or kernel mode, not
|
|
|
|
* 'ucontext'.
|
|
|
|
*
|
|
|
|
*/
|
2020-10-27 00:15:39 +08:00
|
|
|
static inline struct uverbs_attr_bundle *
|
|
|
|
rdma_udata_to_uverbs_attr_bundle(struct ib_udata *udata)
|
|
|
|
{
|
|
|
|
return container_of(udata, struct uverbs_attr_bundle, driver_udata);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define rdma_udata_to_drv_context(udata, drv_dev_struct, member) \
|
|
|
|
(udata ? container_of(rdma_udata_to_uverbs_attr_bundle(udata)->context, \
|
|
|
|
drv_dev_struct, member) : (drv_dev_struct *)NULL)
|
2019-02-08 00:44:48 +08:00
|
|
|
|
2018-03-19 21:02:38 +08:00
|
|
|
#define IS_UVERBS_COPY_ERR(_ret) ((_ret) && (_ret) != -ENOENT)
|
|
|
|
|
2017-08-03 21:07:04 +08:00
|
|
|
static inline const struct uverbs_attr *uverbs_attr_get(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
u16 idx)
|
|
|
|
{
|
|
|
|
if (!uverbs_attr_is_valid(attrs_bundle, idx))
|
|
|
|
return ERR_PTR(-ENOENT);
|
|
|
|
|
2018-08-10 10:14:42 +08:00
|
|
|
return &attrs_bundle->attrs[uapi_bkey_attr(uapi_key_attr(idx))];
|
2017-08-03 21:07:04 +08:00
|
|
|
}
|
|
|
|
|
2018-03-28 14:27:42 +08:00
|
|
|
static inline int uverbs_attr_get_enum_id(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
u16 idx)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return PTR_ERR(attr);
|
|
|
|
|
|
|
|
return attr->ptr_attr.enum_id;
|
|
|
|
}
|
|
|
|
|
2018-04-05 23:53:25 +08:00
|
|
|
static inline void *uverbs_attr_get_obj(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
u16 idx)
|
|
|
|
{
|
2018-05-23 05:56:51 +08:00
|
|
|
const struct uverbs_attr *attr;
|
2018-04-05 23:53:25 +08:00
|
|
|
|
2018-05-23 05:56:51 +08:00
|
|
|
attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return ERR_CAST(attr);
|
2018-04-05 23:53:25 +08:00
|
|
|
|
2018-05-23 05:56:51 +08:00
|
|
|
return attr->obj_attr.uobject->object;
|
2018-04-05 23:53:25 +08:00
|
|
|
}
|
|
|
|
|
2018-05-31 21:43:28 +08:00
|
|
|
static inline struct ib_uobject *uverbs_attr_get_uobject(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
u16 idx)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return ERR_CAST(attr);
|
|
|
|
|
|
|
|
return attr->obj_attr.uobject;
|
|
|
|
}
|
|
|
|
|
2018-06-17 17:59:52 +08:00
|
|
|
static inline int
|
|
|
|
uverbs_attr_get_len(const struct uverbs_attr_bundle *attrs_bundle, u16 idx)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return PTR_ERR(attr);
|
|
|
|
|
|
|
|
return attr->ptr_attr.len;
|
|
|
|
}
|
|
|
|
|
2020-05-19 15:27:05 +08:00
|
|
|
void uverbs_finalize_uobj_create(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
u16 idx);
|
|
|
|
|
2018-12-11 19:37:51 +08:00
|
|
|
/*
|
|
|
|
* uverbs_attr_ptr_get_array_size() - Get array size pointer by a ptr
|
|
|
|
* attribute.
|
|
|
|
* @attrs: The attribute bundle
|
|
|
|
* @idx: The ID of the attribute
|
|
|
|
* @elem_size: The size of the element in the array
|
|
|
|
*/
|
|
|
|
static inline int
|
|
|
|
uverbs_attr_ptr_get_array_size(struct uverbs_attr_bundle *attrs, u16 idx,
|
|
|
|
size_t elem_size)
|
|
|
|
{
|
|
|
|
int size = uverbs_attr_get_len(attrs, idx);
|
|
|
|
|
|
|
|
if (size < 0)
|
|
|
|
return size;
|
|
|
|
|
|
|
|
if (size % elem_size)
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
return size / elem_size;
|
|
|
|
}
|
|
|
|
|
2018-09-06 22:27:01 +08:00
|
|
|
/**
|
|
|
|
* uverbs_attr_get_uobjs_arr() - Provides array's properties for attribute for
|
|
|
|
* UVERBS_ATTR_TYPE_IDRS_ARRAY.
|
|
|
|
* @arr: Returned pointer to array of pointers for uobjects or NULL if
|
|
|
|
* the attribute isn't provided.
|
|
|
|
*
|
|
|
|
* Return: The array length or 0 if no attribute was provided.
|
|
|
|
*/
|
|
|
|
static inline int uverbs_attr_get_uobjs_arr(
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle, u16 attr_idx,
|
|
|
|
struct ib_uobject ***arr)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr =
|
|
|
|
uverbs_attr_get(attrs_bundle, attr_idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr)) {
|
|
|
|
*arr = NULL;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
*arr = attr->objs_arr_attr.uobjects;
|
|
|
|
|
|
|
|
return attr->objs_arr_attr.len;
|
|
|
|
}
|
|
|
|
|
2018-02-13 18:18:29 +08:00
|
|
|
static inline bool uverbs_attr_ptr_is_inline(const struct uverbs_attr *attr)
|
|
|
|
{
|
|
|
|
return attr->ptr_attr.len <= sizeof(attr->ptr_attr.data);
|
|
|
|
}
|
|
|
|
|
2018-06-17 17:59:52 +08:00
|
|
|
static inline void *uverbs_attr_get_alloced_ptr(
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle, u16 idx)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return (void *)attr;
|
|
|
|
|
|
|
|
return uverbs_attr_ptr_is_inline(attr) ? (void *)&attr->ptr_attr.data :
|
|
|
|
attr->ptr_attr.ptr;
|
|
|
|
}
|
|
|
|
|
2018-02-13 18:18:29 +08:00
|
|
|
static inline int _uverbs_copy_from(void *to,
|
2017-08-03 21:07:04 +08:00
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
2018-02-13 18:18:29 +08:00
|
|
|
size_t idx,
|
|
|
|
size_t size)
|
2017-08-03 21:07:04 +08:00
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return PTR_ERR(attr);
|
|
|
|
|
2018-02-13 18:18:29 +08:00
|
|
|
/*
|
|
|
|
* Validation ensures attr->ptr_attr.len >= size. If the caller is
|
2018-03-19 21:02:36 +08:00
|
|
|
* using UVERBS_ATTR_SPEC_F_MIN_SZ_OR_ZERO then it must call
|
|
|
|
* uverbs_copy_from_or_zero.
|
2018-02-13 18:18:29 +08:00
|
|
|
*/
|
|
|
|
if (unlikely(size < attr->ptr_attr.len))
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (uverbs_attr_ptr_is_inline(attr))
|
2017-08-03 21:07:04 +08:00
|
|
|
memcpy(to, &attr->ptr_attr.data, attr->ptr_attr.len);
|
2018-02-13 18:18:31 +08:00
|
|
|
else if (copy_from_user(to, u64_to_user_ptr(attr->ptr_attr.data),
|
|
|
|
attr->ptr_attr.len))
|
2017-08-03 21:07:04 +08:00
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-03-19 21:02:36 +08:00
|
|
|
static inline int _uverbs_copy_from_or_zero(void *to,
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx,
|
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
const struct uverbs_attr *attr = uverbs_attr_get(attrs_bundle, idx);
|
|
|
|
size_t min_size;
|
|
|
|
|
|
|
|
if (IS_ERR(attr))
|
|
|
|
return PTR_ERR(attr);
|
|
|
|
|
|
|
|
min_size = min_t(size_t, size, attr->ptr_attr.len);
|
|
|
|
|
|
|
|
if (uverbs_attr_ptr_is_inline(attr))
|
|
|
|
memcpy(to, &attr->ptr_attr.data, min_size);
|
|
|
|
else if (copy_from_user(to, u64_to_user_ptr(attr->ptr_attr.data),
|
|
|
|
min_size))
|
|
|
|
return -EFAULT;
|
|
|
|
|
|
|
|
if (size > min_size)
|
|
|
|
memset(to + min_size, 0, size - min_size);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-08-03 21:07:04 +08:00
|
|
|
#define uverbs_copy_from(to, attrs_bundle, idx) \
|
2018-02-13 18:18:29 +08:00
|
|
|
_uverbs_copy_from(to, attrs_bundle, idx, sizeof(*to))
|
2017-08-03 21:07:04 +08:00
|
|
|
|
2018-03-19 21:02:36 +08:00
|
|
|
#define uverbs_copy_from_or_zero(to, attrs_bundle, idx) \
|
|
|
|
_uverbs_copy_from_or_zero(to, attrs_bundle, idx, sizeof(*to))
|
|
|
|
|
2018-11-26 02:51:13 +08:00
|
|
|
static inline struct ib_ucontext *
|
|
|
|
ib_uverbs_get_ucontext(const struct uverbs_attr_bundle *attrs)
|
|
|
|
{
|
|
|
|
return ib_uverbs_get_ucontext_file(attrs->ufile);
|
|
|
|
}
|
|
|
|
|
2018-07-27 06:37:14 +08:00
|
|
|
#if IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)
|
|
|
|
int uverbs_get_flags64(u64 *to, const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 allowed_bits);
|
|
|
|
int uverbs_get_flags32(u32 *to, const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 allowed_bits);
|
2018-08-10 10:14:39 +08:00
|
|
|
int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle, size_t idx,
|
|
|
|
const void *from, size_t size);
|
2018-08-10 10:14:40 +08:00
|
|
|
__malloc void *_uverbs_alloc(struct uverbs_attr_bundle *bundle, size_t size,
|
|
|
|
gfp_t flags);
|
|
|
|
|
|
|
|
static inline __malloc void *uverbs_alloc(struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
return _uverbs_alloc(bundle, size, GFP_KERNEL);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline __malloc void *uverbs_zalloc(struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
return _uverbs_alloc(bundle, size, GFP_KERNEL | __GFP_ZERO);
|
|
|
|
}
|
2020-12-08 15:35:45 +08:00
|
|
|
|
|
|
|
static inline __malloc void *uverbs_kcalloc(struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t n, size_t size)
|
|
|
|
{
|
|
|
|
size_t bytes;
|
|
|
|
|
|
|
|
if (unlikely(check_mul_overflow(n, size, &bytes)))
|
|
|
|
return ERR_PTR(-EOVERFLOW);
|
|
|
|
return uverbs_zalloc(bundle, bytes);
|
|
|
|
}
|
2021-03-04 21:05:00 +08:00
|
|
|
|
|
|
|
int _uverbs_get_const_signed(s64 *to,
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, s64 lower_bound, u64 upper_bound,
|
|
|
|
s64 *def_val);
|
|
|
|
int _uverbs_get_const_unsigned(u64 *to,
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 upper_bound, u64 *def_val);
|
2018-12-09 17:58:04 +08:00
|
|
|
int uverbs_copy_to_struct_or_zero(const struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t idx, const void *from, size_t size);
|
2018-07-27 06:37:14 +08:00
|
|
|
#else
|
|
|
|
static inline int
|
|
|
|
uverbs_get_flags64(u64 *to, const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 allowed_bits)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
static inline int
|
|
|
|
uverbs_get_flags32(u32 *to, const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 allowed_bits)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2018-08-10 10:14:39 +08:00
|
|
|
static inline int uverbs_copy_to(const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, const void *from, size_t size)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2018-08-10 10:14:40 +08:00
|
|
|
static inline __malloc void *uverbs_alloc(struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
}
|
|
|
|
static inline __malloc void *uverbs_zalloc(struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t size)
|
|
|
|
{
|
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
}
|
2018-08-28 19:18:50 +08:00
|
|
|
static inline int
|
|
|
|
_uverbs_get_const(s64 *to, const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, s64 lower_bound, u64 upper_bound,
|
|
|
|
s64 *def_val)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2018-12-09 17:58:04 +08:00
|
|
|
static inline int
|
|
|
|
uverbs_copy_to_struct_or_zero(const struct uverbs_attr_bundle *bundle,
|
|
|
|
size_t idx, const void *from, size_t size)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2021-04-01 10:10:28 +08:00
|
|
|
static inline int
|
|
|
|
_uverbs_get_const_signed(s64 *to,
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
2021-03-04 21:05:00 +08:00
|
|
|
size_t idx, s64 lower_bound, u64 upper_bound,
|
|
|
|
s64 *def_val)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2021-04-01 10:10:28 +08:00
|
|
|
static inline int
|
2021-03-04 21:05:00 +08:00
|
|
|
_uverbs_get_const_unsigned(u64 *to,
|
|
|
|
const struct uverbs_attr_bundle *attrs_bundle,
|
|
|
|
size_t idx, u64 upper_bound, u64 *def_val)
|
|
|
|
{
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
2018-07-27 06:37:14 +08:00
|
|
|
#endif
|
|
|
|
|
2021-03-04 21:05:00 +08:00
|
|
|
#define uverbs_get_const_signed(_to, _attrs_bundle, _idx) \
|
2018-08-28 19:18:50 +08:00
|
|
|
({ \
|
|
|
|
s64 _val; \
|
2021-03-04 21:05:00 +08:00
|
|
|
int _ret = \
|
|
|
|
_uverbs_get_const_signed(&_val, _attrs_bundle, _idx, \
|
|
|
|
type_min(typeof(*(_to))), \
|
|
|
|
type_max(typeof(*(_to))), NULL); \
|
|
|
|
(*(_to)) = _val; \
|
2018-08-28 19:18:50 +08:00
|
|
|
_ret; \
|
|
|
|
})
|
|
|
|
|
2021-03-04 21:05:00 +08:00
|
|
|
#define uverbs_get_const_unsigned(_to, _attrs_bundle, _idx) \
|
|
|
|
({ \
|
|
|
|
u64 _val; \
|
|
|
|
int _ret = \
|
|
|
|
_uverbs_get_const_unsigned(&_val, _attrs_bundle, _idx, \
|
|
|
|
type_max(typeof(*(_to))), NULL); \
|
|
|
|
(*(_to)) = _val; \
|
|
|
|
_ret; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define uverbs_get_const_default_signed(_to, _attrs_bundle, _idx, _default) \
|
2018-08-28 19:18:50 +08:00
|
|
|
({ \
|
|
|
|
s64 _val; \
|
|
|
|
s64 _def_val = _default; \
|
|
|
|
int _ret = \
|
2021-03-04 21:05:00 +08:00
|
|
|
_uverbs_get_const_signed(&_val, _attrs_bundle, _idx, \
|
|
|
|
type_min(typeof(*(_to))), \
|
|
|
|
type_max(typeof(*(_to))), &_def_val); \
|
|
|
|
(*(_to)) = _val; \
|
|
|
|
_ret; \
|
|
|
|
})
|
|
|
|
|
|
|
|
#define uverbs_get_const_default_unsigned(_to, _attrs_bundle, _idx, _default) \
|
|
|
|
({ \
|
|
|
|
u64 _val; \
|
|
|
|
u64 _def_val = _default; \
|
|
|
|
int _ret = \
|
|
|
|
_uverbs_get_const_unsigned(&_val, _attrs_bundle, _idx, \
|
|
|
|
type_max(typeof(*(_to))), &_def_val); \
|
|
|
|
(*(_to)) = _val; \
|
2018-08-28 19:18:50 +08:00
|
|
|
_ret; \
|
|
|
|
})
|
2021-03-04 21:05:00 +08:00
|
|
|
|
|
|
|
#define uverbs_get_const(_to, _attrs_bundle, _idx) \
|
|
|
|
(is_signed_type(typeof(*(_to))) ? \
|
|
|
|
uverbs_get_const_signed(_to, _attrs_bundle, _idx) : \
|
|
|
|
uverbs_get_const_unsigned(_to, _attrs_bundle, _idx)) \
|
|
|
|
|
|
|
|
#define uverbs_get_const_default(_to, _attrs_bundle, _idx, _default) \
|
|
|
|
(is_signed_type(typeof(*(_to))) ? \
|
|
|
|
uverbs_get_const_default_signed(_to, _attrs_bundle, _idx, \
|
|
|
|
_default) : \
|
|
|
|
uverbs_get_const_default_unsigned(_to, _attrs_bundle, _idx, \
|
|
|
|
_default))
|
|
|
|
|
2017-08-03 21:07:00 +08:00
|
|
|
#endif
|