* [PATCH 3/3] make sock_alloc_file() do sock_release() on failures
From: Al Viro @ 2017-12-01 0:23 UTC (permalink / raw)
To: netdev; +Cc: Al Viro
In-Reply-To: <20171201002027.GI21978@ZenIV.linux.org.uk>
This changes calling conventions (and simplifies the hell out
the callers). New rules: once struct socket had been passed
to sock_alloc_file(), it's been consumed either by struct file
or by sock_release() done by sock_alloc_file(). Either way
the caller should not do sock_release() after that point.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
drivers/staging/lustre/lnet/lnet/lib-socket.c | 8 ++------
net/9p/trans_fd.c | 1 -
net/kcm/kcmsock.c | 7 +------
net/sctp/socket.c | 1 -
net/socket.c | 25 ++++++++-----------------
5 files changed, 11 insertions(+), 31 deletions(-)
diff --git a/drivers/staging/lustre/lnet/lnet/lib-socket.c b/drivers/staging/lustre/lnet/lnet/lib-socket.c
index 539a26444f31..7d49d4865298 100644
--- a/drivers/staging/lustre/lnet/lnet/lib-socket.c
+++ b/drivers/staging/lustre/lnet/lnet/lib-socket.c
@@ -71,16 +71,12 @@ lnet_sock_ioctl(int cmd, unsigned long arg)
}
sock_filp = sock_alloc_file(sock, 0, NULL);
- if (IS_ERR(sock_filp)) {
- sock_release(sock);
- rc = PTR_ERR(sock_filp);
- goto out;
- }
+ if (IS_ERR(sock_filp))
+ return PTR_ERR(sock_filp);
rc = kernel_sock_unlocked_ioctl(sock_filp, cmd, arg);
fput(sock_filp);
-out:
return rc;
}
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 985046ae4231..80f5c79053a4 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -839,7 +839,6 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket)
if (IS_ERR(file)) {
pr_err("%s (%d): failed to map fd\n",
__func__, task_pid_nr(current));
- sock_release(csocket);
kfree(p);
return PTR_ERR(file);
}
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index c5fa634e63ca..d4e98f20fc2a 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -1629,7 +1629,6 @@ static struct file *kcm_clone(struct socket *osock)
{
struct socket *newsock;
struct sock *newsk;
- struct file *file;
newsock = sock_alloc();
if (!newsock)
@@ -1649,11 +1648,7 @@ static struct file *kcm_clone(struct socket *osock)
sock_init_data(newsock, newsk);
init_kcm_sock(kcm_sk(newsk), kcm_sk(osock->sk)->mux);
- file = sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name);
- if (IS_ERR(file))
- sock_release(newsock);
-
- return file;
+ return sock_alloc_file(newsock, 0, osock->sk->sk_prot_creator->name);
}
static int kcm_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 3204a9b29407..8bb5163d6331 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -5080,7 +5080,6 @@ static int sctp_getsockopt_peeloff_common(struct sock *sk, sctp_peeloff_arg_t *p
*newfile = sock_alloc_file(newsock, 0, NULL);
if (IS_ERR(*newfile)) {
put_unused_fd(retval);
- sock_release(newsock);
retval = PTR_ERR(*newfile);
*newfile = NULL;
return retval;
diff --git a/net/socket.c b/net/socket.c
index 2df83c0bfde9..05f361faec45 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -406,8 +406,10 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
name.len = strlen(name.name);
}
path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
- if (unlikely(!path.dentry))
+ if (unlikely(!path.dentry)) {
+ sock_release(sock);
return ERR_PTR(-ENOMEM);
+ }
path.mnt = mntget(sock_mnt);
d_instantiate(path.dentry, SOCK_INODE(sock));
@@ -415,9 +417,11 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
&socket_file_ops);
if (IS_ERR(file)) {
- /* drop dentry, keep inode */
+ /* drop dentry, keep inode for a bit */
ihold(d_inode(path.dentry));
path_put(&path);
+ /* ... and now kill it properly */
+ sock_release(sock);
return file;
}
@@ -1330,19 +1334,9 @@ SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol)
retval = sock_create(family, type, protocol, &sock);
if (retval < 0)
- goto out;
-
- retval = sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
- if (retval < 0)
- goto out_release;
-
-out:
- /* It may be already another descriptor 8) Not kernel problem. */
- return retval;
+ return retval;
-out_release:
- sock_release(sock);
- return retval;
+ return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK));
}
/*
@@ -1412,7 +1406,6 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
newfile1 = sock_alloc_file(sock1, flags, NULL);
if (IS_ERR(newfile1)) {
err = PTR_ERR(newfile1);
- sock_release(sock1);
sock_release(sock2);
goto out;
}
@@ -1420,7 +1413,6 @@ SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol,
newfile2 = sock_alloc_file(sock2, flags, NULL);
if (IS_ERR(newfile2)) {
err = PTR_ERR(newfile2);
- sock_release(sock2);
fput(newfile1);
goto out;
}
@@ -1549,7 +1541,6 @@ SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr,
if (IS_ERR(newfile)) {
err = PTR_ERR(newfile);
put_unused_fd(newfd);
- sock_release(newsock);
goto out_put;
}
--
2.11.0
^ permalink raw reply related
* Re: [PATCH net-next 2/5] rhashtable: Add rhastable_walk_peek
From: Herbert Xu @ 2017-12-01 0:38 UTC (permalink / raw)
To: Tom Herbert; +Cc: davem, netdev, rohit
In-Reply-To: <20171201000305.2392-3-tom@quantonium.net>
On Thu, Nov 30, 2017 at 04:03:02PM -0800, Tom Herbert wrote:
> This function is like rhashtable_walk_next except that it only returns
> the current element in the inter and does not advance the iter.
>
> This patch also creates __rhashtable_walk_find_next. It finds the next
> element in the table when the entry cached in iter is NULL or at the end
> of a slot. __rhashtable_walk_find_next is called from
> rhashtable_walk_next and rhastable_walk_peek.
>
> Signed-off-by: Tom Herbert <tom@quantonium.net>
Hi Tom:
Could you add some motivation for this feature into the patch
description? As it is it's difficult to deduce why we would want
to add something like this given that hashtable walks are always
unstable and there is no guarantee that two calls to peek or a
peek followed by a normal walk will see the same entry.
Thanks,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* [PATCH] netfilter: add overflow checks in xt_bpf.c
From: Jann Horn @ 2017-12-01 0:46 UTC (permalink / raw)
To: Willem de Bruijn, Pablo Neira Ayuso, Jozsef Kadlecsik,
Florian Westphal, David S. Miller
Cc: netdev, coreteam, netfilter-devel
Check whether inputs from userspace are too long (explicit length field too
big or string not null-terminated) to avoid out-of-bounds reads.
As far as I can tell, this can at worst lead to very limited kernel heap
memory disclosure or oopses.
This bug can be triggered by an unprivileged user even if the xt_bpf module
is not loaded: iptables is available in network namespaces, and the xt_bpf
module can be autoloaded.
Triggering the bug with a classic BPF filter with fake length 0x1000 causes
the following KASAN report:
==================================================================
BUG: KASAN: slab-out-of-bounds in bpf_prog_create+0x84/0xf0
Read of size 32768 at addr ffff8801eff2c494 by task test/4627
CPU: 0 PID: 4627 Comm: test Not tainted 4.15.0-rc1+ #1
[...]
Call Trace:
dump_stack+0x5c/0x85
print_address_description+0x6a/0x260
kasan_report+0x254/0x370
? bpf_prog_create+0x84/0xf0
memcpy+0x1f/0x50
bpf_prog_create+0x84/0xf0
bpf_mt_check+0x90/0xd6 [xt_bpf]
[...]
Allocated by task 4627:
kasan_kmalloc+0xa0/0xd0
__kmalloc_node+0x47/0x60
xt_alloc_table_info+0x41/0x70 [x_tables]
[...]
The buggy address belongs to the object at ffff8801eff2c3c0
which belongs to the cache kmalloc-2048 of size 2048
The buggy address is located 212 bytes inside of
2048-byte region [ffff8801eff2c3c0, ffff8801eff2cbc0)
[...]
==================================================================
Fixes: e6f30c731718 ("netfilter: x_tables: add xt_bpf match")
Signed-off-by: Jann Horn <jannh@google.com>
---
net/netfilter/xt_bpf.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/net/netfilter/xt_bpf.c b/net/netfilter/xt_bpf.c
index 041da0d9c06f..1f7fbd3c7e5a 100644
--- a/net/netfilter/xt_bpf.c
+++ b/net/netfilter/xt_bpf.c
@@ -27,6 +27,9 @@ static int __bpf_mt_check_bytecode(struct sock_filter *insns, __u16 len,
{
struct sock_fprog_kern program;
+ if (len > XT_BPF_MAX_NUM_INSTR)
+ return -EINVAL;
+
program.len = len;
program.filter = insns;
@@ -55,6 +58,9 @@ static int __bpf_mt_check_path(const char *path, struct bpf_prog **ret)
mm_segment_t oldfs = get_fs();
int retval, fd;
+ if (strnlen(path, XT_BPF_PATH_MAX) == XT_BPF_PATH_MAX)
+ return -EINVAL;
+
set_fs(KERNEL_DS);
fd = bpf_obj_get_user(path, 0);
set_fs(oldfs);
--
2.15.0.531.g2ccb3012c9-goog
^ permalink raw reply related
* Re: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
From: Kees Cook @ 2017-12-01 0:57 UTC (permalink / raw)
To: Shmulik Ladkani, Willem de Bruijn, Daniel Borkmann,
Pablo Neira Ayuso
Cc: Linus Torvalds, David Miller, LKML, Network Development, Al Viro,
Christoph Hellwig, Thomas Garnier, Jann Horn
On Mon, Oct 9, 2017 at 4:10 PM, David Miller <davem@davemloft.net> wrote:
> Shmulik Ladkani (1):
> netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
This adds a new user of set_fs(), which we're trying to eliminate (or
at least not expand):
+ set_fs(KERNEL_DS);
+ fd = bpf_obj_get_user(path);
+ set_fs(oldfs);
Can you please adjust this to not make set_fs() changes?
Thanks!
-Kees
--
Kees Cook
Pixel Security
^ permalink raw reply
* Re: [Patch net-next] act_mirred: get rid of mirred_list_lock spinlock
From: Cong Wang @ 2017-12-01 1:02 UTC (permalink / raw)
To: Eric Dumazet
Cc: Linux Kernel Network Developers, Jiri Pirko, Jamal Hadi Salim
In-Reply-To: <1512083524.19682.29.camel@gmail.com>
On Thu, Nov 30, 2017 at 3:12 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Thu, 2017-11-30 at 14:53 -0800, Cong Wang wrote:
>> @@ -55,13 +54,10 @@ static void tcf_mirred_release(struct tc_action
>> *a, int bind)
>> struct tcf_mirred *m = to_mirred(a);
>> struct net_device *dev;
>>
>> - /* We could be called either in a RCU callback or with RTNL
>> lock held. */
>> - spin_lock_bh(&mirred_list_lock);
>> list_del(&m->tcfm_list);
>> dev = rcu_dereference_protected(m->tcfm_dev, 1);
>
> If RTNL is held at this point, I suggest to use
> rtnl_dereference() instead of rcu_dereference_protected() to get proper
> lockdep coverage.
Ah, sure, I missed it. Will send v2 later.
^ permalink raw reply
* [PATCH net-next v4 0/2] add UniPhier AVE ethernet support
From: Kunihiko Hayashi @ 2017-12-01 1:03 UTC (permalink / raw)
To: netdev-u79uwXL29TY76Z2rM5mHXA, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
linux-kernel-u79uwXL29TY76Z2rM5mHXA,
devicetree-u79uwXL29TY76Z2rM5mHXA, Masahiro Yamada,
Masami Hiramatsu, Jassi Brar, Kunihiko Hayashi
This series adds support for Socionext AVE ethernet controller implemented
on UniPhier SoCs. This driver supports RGMII/RMII modes.
v3: http://www.spinics.net/lists/netdev/msg462550.html
The PHY patch included in v1 has already separated in:
http://www.spinics.net/lists/netdev/msg454595.html
Changes since v3:
- remove checking dma address and use dma_set_mask() to restirct address
- replace ave_mdio_busywait() with read_poll_timeout()
- replace functions to access to registers with readl/writel() directly
- replace a function to access to macaddr with ave_hw_write_macaddr()
- change return value of ave_dma_map() to error value
- move mdiobus_unregister() from ave_remove() to ave_uninit()
- eliminate else block at the end of ave_dma_map()
- add mask definitions for packet filter
- sort bitmap definitions in descending order
- add error check to some functions
- rename and sort functions to clear sub-categories
- fix error value consistency
- remove unneeded initializers
- change type of constant arrays
Changes since v2:
- replace clk_get() with devm_clk_get()
- replace reset_control_get() with devm_reset_control_get_optional_shared()
- add error return when the error occurs on the above *_get functions
- sort soc data and compatible strings
- remove clearly obvious comments
- modify dt-bindings document consistent with these modifications
Changes since v1:
- add/remove devicetree properties and sub-node
- remove "internal-phy-interrupt" and "desc-bits" property
- add SoC data structures based on compatible strings
- add node operation to apply "mdio" sub-node
- add support for features
- add support for {get,set}_pauseparam and pause frame operations
- add support for ndo_get_stats64 instead of ndo_get_stats
- replace with desiable functions
- replace check for valid phy_mode with phy_interface{_mode}_is_rgmii()
- replace phy attach message with phy_attached_info()
- replace 32bit operation with {upper,lower}_32_bits() on ave_wdesc_addr()
- replace nway_reset and get_link with generic functions
- move operations to proper functions
- move phy_start_aneg() to ndo_open,
and remove unnecessary PHY interrupt operations
See http://www.spinics.net/lists/netdev/msg454590.html
- move irq initialization and descriptor memory allocation to ndo_open
- move initialization of reset and clock and mdiobus to ndo_init
- fix skbuffer operations
- fix skb alignment operations and add Rx buffer adjustment for descriptor
See http://www.spinics.net/lists/netdev/msg456014.html
- add error returns when dma_map_single() failed
- clean up code structures
- clean up wait-loop and wake-queue conditions
- add ave_wdesc_addr() and offset definitions
- add ave_macaddr_init() to clean up mac-address operation
- fix checking whether Tx entry is not enough
- fix supported features of phydev
- add necessary free/disable operations
- add phydev check on ave_{get,set}_wol()
- remove netif_carrier functions, phydev initializer, and Tx budget check
- change obsolate codes
- replace ndev->{base_addr,irq} with the members of ave_private
- rename goto labels and mask definitions, and remove unused codes
Kunihiko Hayashi (2):
dt-bindings: net: add DT bindings for Socionext UniPhier AVE
net: ethernet: socionext: add AVE ethernet driver
.../bindings/net/socionext,uniphier-ave4.txt | 48 +
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/socionext/Kconfig | 22 +
drivers/net/ethernet/socionext/Makefile | 5 +
drivers/net/ethernet/socionext/sni_ave.c | 1744 ++++++++++++++++++++
6 files changed, 1821 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
create mode 100644 drivers/net/ethernet/socionext/Kconfig
create mode 100644 drivers/net/ethernet/socionext/Makefile
create mode 100644 drivers/net/ethernet/socionext/sni_ave.c
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH net-next v4 1/2] dt-bindings: net: add DT bindings for Socionext UniPhier AVE
From: Kunihiko Hayashi @ 2017-12-01 1:03 UTC (permalink / raw)
To: netdev, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Kunihiko Hayashi
In-Reply-To: <1512090230-27594-1-git-send-email-hayashi.kunihiko@socionext.com>
DT bindings for the AVE ethernet controller found on Socionext's
UniPhier platforms.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
Acked-by: Rob Herring <robh@kernel.org>
---
.../bindings/net/socionext,uniphier-ave4.txt | 48 ++++++++++++++++++++++
1 file changed, 48 insertions(+)
create mode 100644 Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
new file mode 100644
index 0000000..4700377
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt
@@ -0,0 +1,48 @@
+* Socionext AVE ethernet controller
+
+This describes the devicetree bindings for AVE ethernet controller
+implemented on Socionext UniPhier SoCs.
+
+Required properties:
+ - compatible: Should be
+ - "socionext,uniphier-pro4-ave4" : for Pro4 SoC
+ - "socionext,uniphier-pxs2-ave4" : for PXs2 SoC
+ - "socionext,uniphier-ld11-ave4" : for LD11 SoC
+ - "socionext,uniphier-ld20-ave4" : for LD20 SoC
+ - reg: Address where registers are mapped and size of region.
+ - interrupts: Should contain the MAC interrupt.
+ - phy-mode: See ethernet.txt in the same directory. Allow to choose
+ "rgmii", "rmii", or "mii" according to the PHY.
+ - phy-handle: Should point to the external phy device.
+ See ethernet.txt file in the same directory.
+ - clocks: A phandle to the clock for the MAC.
+
+Optional properties:
+ - resets: A phandle to the reset control for the MAC
+ - local-mac-address: See ethernet.txt in the same directory.
+
+Required subnode:
+ - mdio: Device tree subnode with the following required properties:
+ - #address-cells: Must be <1>.
+ - #size-cells: Must be <0>.
+ - reg: phy ID number, usually a small integer.
+
+Example:
+
+ ether: ethernet@65000000 {
+ compatible = "socionext,uniphier-ld20-ave4";
+ reg = <0x65000000 0x8500>;
+ interrupts = <0 66 4>;
+ phy-mode = "rgmii";
+ phy-handle = <ðphy>;
+ clocks = <&sys_clk 6>;
+ resets = <&sys_rst 6>;
+ local-mac-address = [00 00 00 00 00 00];
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ ethphy: ethphy@1 {
+ reg = <1>;
+ };
+ };
+ };
--
2.7.4
^ permalink raw reply related
* [PATCH net-next v4 2/2] net: ethernet: socionext: add AVE ethernet driver
From: Kunihiko Hayashi @ 2017-12-01 1:03 UTC (permalink / raw)
To: netdev, Andrew Lunn, Florian Fainelli
Cc: Rob Herring, Mark Rutland, linux-arm-kernel, linux-kernel,
devicetree, Masahiro Yamada, Masami Hiramatsu, Jassi Brar,
Kunihiko Hayashi
In-Reply-To: <1512090230-27594-1-git-send-email-hayashi.kunihiko@socionext.com>
The UniPhier platform from Socionext provides the AVE ethernet
controller that includes MAC and MDIO bus supporting RGMII/RMII
modes. The controller is named AVE.
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
drivers/net/ethernet/Kconfig | 1 +
drivers/net/ethernet/Makefile | 1 +
drivers/net/ethernet/socionext/Kconfig | 22 +
drivers/net/ethernet/socionext/Makefile | 5 +
drivers/net/ethernet/socionext/sni_ave.c | 1744 ++++++++++++++++++++++++++++++
5 files changed, 1773 insertions(+)
create mode 100644 drivers/net/ethernet/socionext/Kconfig
create mode 100644 drivers/net/ethernet/socionext/Makefile
create mode 100644 drivers/net/ethernet/socionext/sni_ave.c
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index c604213..d50519e 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -170,6 +170,7 @@ source "drivers/net/ethernet/sis/Kconfig"
source "drivers/net/ethernet/sfc/Kconfig"
source "drivers/net/ethernet/sgi/Kconfig"
source "drivers/net/ethernet/smsc/Kconfig"
+source "drivers/net/ethernet/socionext/Kconfig"
source "drivers/net/ethernet/stmicro/Kconfig"
source "drivers/net/ethernet/sun/Kconfig"
source "drivers/net/ethernet/tehuti/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 39f62733..6cf5ade 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_SFC) += sfc/
obj-$(CONFIG_SFC_FALCON) += sfc/falcon/
obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
+obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
obj-$(CONFIG_NET_VENDOR_STMICRO) += stmicro/
obj-$(CONFIG_NET_VENDOR_SUN) += sun/
obj-$(CONFIG_NET_VENDOR_TEHUTI) += tehuti/
diff --git a/drivers/net/ethernet/socionext/Kconfig b/drivers/net/ethernet/socionext/Kconfig
new file mode 100644
index 0000000..3a1829e
--- /dev/null
+++ b/drivers/net/ethernet/socionext/Kconfig
@@ -0,0 +1,22 @@
+config NET_VENDOR_SOCIONEXT
+ bool "Socionext ethernet drivers"
+ default y
+ ---help---
+ Option to select ethernet drivers for Socionext platforms.
+
+ Note that the answer to this question doesn't directly affect the
+ kernel: saying N will just cause the configurator to skip all
+ the questions about Socionext devices. If you say Y, you will be asked
+ for your specific card in the following questions.
+
+if NET_VENDOR_SOCIONEXT
+
+config SNI_AVE
+ tristate "Socionext AVE ethernet support"
+ depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+ select PHYLIB
+ ---help---
+ Driver for gigabit ethernet MACs, called AVE, in the
+ Socionext UniPhier family.
+
+endif #NET_VENDOR_SOCIONEXT
diff --git a/drivers/net/ethernet/socionext/Makefile b/drivers/net/ethernet/socionext/Makefile
new file mode 100644
index 0000000..ab83df6
--- /dev/null
+++ b/drivers/net/ethernet/socionext/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for all ethernet ip drivers on Socionext platforms
+#
+obj-$(CONFIG_SNI_AVE) += sni_ave.o
diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c
new file mode 100644
index 0000000..6f42f12
--- /dev/null
+++ b/drivers/net/ethernet/socionext/sni_ave.c
@@ -0,0 +1,1744 @@
+/**
+ * sni_ave.c - Socionext UniPhier AVE ethernet driver
+ *
+ * Copyright 2014 Panasonic Corporation
+ * Copyright 2015-2017 Socionext Inc.
+ *
+ * This program is free software: you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 of
+ * the License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/mii.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/of_net.h>
+#include <linux/of_mdio.h>
+#include <linux/of_platform.h>
+#include <linux/phy.h>
+#include <linux/reset.h>
+#include <linux/types.h>
+#include <linux/u64_stats_sync.h>
+
+/* General Register Group */
+#define AVE_IDR 0x000 /* ID */
+#define AVE_VR 0x004 /* Version */
+#define AVE_GRR 0x008 /* Global Reset */
+#define AVE_CFGR 0x00c /* Configuration */
+
+/* Interrupt Register Group */
+#define AVE_GIMR 0x100 /* Global Interrupt Mask */
+#define AVE_GISR 0x104 /* Global Interrupt Status */
+
+/* MAC Register Group */
+#define AVE_TXCR 0x200 /* TX Setup */
+#define AVE_RXCR 0x204 /* RX Setup */
+#define AVE_RXMAC1R 0x208 /* MAC address (lower) */
+#define AVE_RXMAC2R 0x20c /* MAC address (upper) */
+#define AVE_MDIOCTR 0x214 /* MDIO Control */
+#define AVE_MDIOAR 0x218 /* MDIO Address */
+#define AVE_MDIOWDR 0x21c /* MDIO Data */
+#define AVE_MDIOSR 0x220 /* MDIO Status */
+#define AVE_MDIORDR 0x224 /* MDIO Rd Data */
+
+/* Descriptor Control Register Group */
+#define AVE_DESCC 0x300 /* Descriptor Control */
+#define AVE_TXDC 0x304 /* TX Descriptor Configuration */
+#define AVE_RXDC0 0x308 /* RX Descriptor Ring0 Configuration */
+#define AVE_IIRQC 0x34c /* Interval IRQ Control */
+
+/* Packet Filter Register Group */
+#define AVE_PKTF_BASE 0x800 /* PF Base Address */
+#define AVE_PFMBYTE_BASE 0xd00 /* PF Mask Byte Base Address */
+#define AVE_PFMBIT_BASE 0xe00 /* PF Mask Bit Base Address */
+#define AVE_PFSEL_BASE 0xf00 /* PF Selector Base Address */
+#define AVE_PFEN 0xffc /* Packet Filter Enable */
+#define AVE_PKTF(ent) (AVE_PKTF_BASE + (ent) * 0x40)
+#define AVE_PFMBYTE(ent) (AVE_PFMBYTE_BASE + (ent) * 8)
+#define AVE_PFMBIT(ent) (AVE_PFMBIT_BASE + (ent) * 4)
+#define AVE_PFSEL(ent) (AVE_PFSEL_BASE + (ent) * 4)
+
+/* 64bit descriptor memory */
+#define AVE_DESC_SIZE_64 12 /* Descriptor Size */
+
+#define AVE_TXDM_64 0x1000 /* Tx Descriptor Memory */
+#define AVE_RXDM_64 0x1c00 /* Rx Descriptor Memory */
+
+#define AVE_TXDM_SIZE_64 0x0ba0 /* Tx Descriptor Memory Size 3KB */
+#define AVE_RXDM_SIZE_64 0x6000 /* Rx Descriptor Memory Size 24KB */
+
+/* 32bit descriptor memory */
+#define AVE_DESC_SIZE_32 8 /* Descriptor Size */
+
+#define AVE_TXDM_32 0x1000 /* Tx Descriptor Memory */
+#define AVE_RXDM_32 0x1800 /* Rx Descriptor Memory */
+
+#define AVE_TXDM_SIZE_32 0x07c0 /* Tx Descriptor Memory Size 2KB */
+#define AVE_RXDM_SIZE_32 0x4000 /* Rx Descriptor Memory Size 16KB */
+
+/* RMII Bridge Register Group */
+#define AVE_RSTCTRL 0x8028 /* Reset control */
+#define AVE_RSTCTRL_RMIIRST BIT(16)
+#define AVE_LINKSEL 0x8034 /* Link speed setting */
+#define AVE_LINKSEL_100M BIT(0)
+
+/* AVE_GRR */
+#define AVE_GRR_RXFFR BIT(5) /* Reset RxFIFO */
+#define AVE_GRR_PHYRST BIT(4) /* Reset external PHY */
+#define AVE_GRR_GRST BIT(0) /* Reset all MAC */
+
+/* AVE_CFGR */
+#define AVE_CFGR_FLE BIT(31) /* Filter Function */
+#define AVE_CFGR_CHE BIT(30) /* Checksum Function */
+#define AVE_CFGR_MII BIT(27) /* Func mode (1:MII/RMII, 0:RGMII) */
+#define AVE_CFGR_IPFCEN BIT(24) /* IP fragment sum Enable */
+
+/* AVE_GISR (common with GIMR) */
+#define AVE_GI_PHY BIT(24) /* PHY interrupt */
+#define AVE_GI_TX BIT(16) /* Tx complete */
+#define AVE_GI_RXERR BIT(8) /* Receive frame more than max size */
+#define AVE_GI_RXOVF BIT(7) /* Overflow at the RxFIFO */
+#define AVE_GI_RXDROP BIT(6) /* Drop packet */
+#define AVE_GI_RXIINT BIT(5) /* Interval interrupt */
+
+/* AVE_TXCR */
+#define AVE_TXCR_FLOCTR BIT(18) /* Flow control */
+#define AVE_TXCR_TXSPD_1G BIT(17)
+#define AVE_TXCR_TXSPD_100 BIT(16)
+
+/* AVE_RXCR */
+#define AVE_RXCR_RXEN BIT(30) /* Rx enable */
+#define AVE_RXCR_FDUPEN BIT(22) /* Interface mode */
+#define AVE_RXCR_FLOCTR BIT(21) /* Flow control */
+#define AVE_RXCR_AFEN BIT(19) /* MAC address filter */
+#define AVE_RXCR_DRPEN BIT(18) /* Drop pause frame */
+#define AVE_RXCR_MPSIZ_MASK GENMASK(10, 0)
+
+/* AVE_MDIOCTR */
+#define AVE_MDIOCTR_RREQ BIT(3) /* Read request */
+#define AVE_MDIOCTR_WREQ BIT(2) /* Write request */
+
+/* AVE_MDIOSR */
+#define AVE_MDIOSR_STS BIT(0) /* access status */
+
+/* AVE_DESCC */
+#define AVE_DESCC_STATUS_MASK GENMASK(31, 16)
+#define AVE_DESCC_RD0 BIT(8) /* Enable Rx descriptor Ring0 */
+#define AVE_DESCC_RDSTP BIT(4) /* Pause Rx descriptor */
+#define AVE_DESCC_TD BIT(0) /* Enable Tx descriptor */
+
+/* AVE_TXDC */
+#define AVE_TXDC_SIZE GENMASK(27, 16) /* Size of Tx descriptor */
+#define AVE_TXDC_ADDR GENMASK(11, 0) /* Start address */
+#define AVE_TXDC_ADDR_START 0
+
+/* AVE_RXDC0 */
+#define AVE_RXDC0_SIZE GENMASK(30, 16) /* Size of Rx descriptor */
+#define AVE_RXDC0_ADDR GENMASK(14, 0) /* Start address */
+#define AVE_RXDC0_ADDR_START 0
+
+/* AVE_IIRQC */
+#define AVE_IIRQC_EN0 BIT(27) /* Enable interval interrupt Ring0 */
+#define AVE_IIRQC_BSCK GENMASK(15, 0) /* Interval count unit */
+
+/* Command status for descriptor */
+#define AVE_STS_OWN BIT(31) /* Descriptor ownership */
+#define AVE_STS_INTR BIT(29) /* Request for interrupt */
+#define AVE_STS_OK BIT(27) /* Normal transmit */
+/* TX */
+#define AVE_STS_NOCSUM BIT(28) /* No use HW checksum */
+#define AVE_STS_1ST BIT(26) /* Head of buffer chain */
+#define AVE_STS_LAST BIT(25) /* Tail of buffer chain */
+#define AVE_STS_OWC BIT(21) /* Out of window,Late Collision */
+#define AVE_STS_EC BIT(20) /* Excess collision occurred */
+#define AVE_STS_PKTLEN_TX_MASK GENMASK(15, 0)
+/* RX */
+#define AVE_STS_CSSV BIT(21) /* Checksum check performed */
+#define AVE_STS_CSER BIT(20) /* Checksum error detected */
+#define AVE_STS_PKTLEN_RX_MASK GENMASK(10, 0)
+
+/* Packet filter */
+#define AVE_PFMBYTE_MASK0 (~GENMASK(7, 6))
+#define AVE_PFMBYTE_MASK1 GENMASK(25, 0)
+#define AVE_PFMBIT_MASK GENMASK(15, 0)
+
+#define AVE_PF_SIZE 17 /* Number of all packet filter */
+#define AVE_PF_MULTICAST_SIZE 7 /* Number of multicast filter */
+
+#define AVE_PFNUM_FILTER 0 /* No.0 */
+#define AVE_PFNUM_UNICAST 1 /* No.1 */
+#define AVE_PFNUM_BROADCAST 2 /* No.2 */
+#define AVE_PFNUM_MULTICAST 11 /* No.11-17 */
+
+/* NETIF Message control */
+#define AVE_DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | \
+ NETIF_MSG_PROBE | \
+ NETIF_MSG_LINK | \
+ NETIF_MSG_TIMER | \
+ NETIF_MSG_IFDOWN | \
+ NETIF_MSG_IFUP | \
+ NETIF_MSG_RX_ERR | \
+ NETIF_MSG_TX_ERR)
+
+/* Parameter for descriptor */
+#define AVE_NR_TXDESC 32 /* Tx descriptor */
+#define AVE_NR_RXDESC 64 /* Rx descriptor */
+
+#define AVE_DESC_OFS_CMDSTS 0
+#define AVE_DESC_OFS_ADDRL 4
+#define AVE_DESC_OFS_ADDRU 8
+
+/* Parameter for ethernet frame */
+#define AVE_MAX_ETHFRAME 1518
+
+/* Parameter for interrupt */
+#define AVE_INTM_COUNT 20
+#define AVE_FORCE_TXINTCNT 1
+
+#define IS_DESC_64BIT(p) ((p)->data->is_desc_64bit)
+
+enum desc_id {
+ AVE_DESCID_RX,
+ AVE_DESCID_TX,
+};
+
+enum desc_state {
+ AVE_DESC_RX_PERMIT,
+ AVE_DESC_RX_SUSPEND,
+ AVE_DESC_START,
+ AVE_DESC_STOP,
+};
+
+struct ave_desc {
+ struct sk_buff *skbs;
+ dma_addr_t skbs_dma;
+ size_t skbs_dmalen;
+};
+
+struct ave_desc_info {
+ u32 ndesc; /* number of descriptor */
+ u32 daddr; /* start address of descriptor */
+ u32 proc_idx; /* index of processing packet */
+ u32 done_idx; /* index of processed packet */
+ struct ave_desc *desc; /* skb info related descriptor */
+};
+
+struct ave_soc_data {
+ bool is_desc_64bit;
+};
+
+struct ave_stats {
+ struct u64_stats_sync syncp;
+ u64 packets;
+ u64 bytes;
+ u64 errors;
+ u64 dropped;
+ u64 collisions;
+ u64 fifo_errors;
+};
+
+struct ave_private {
+ void __iomem *base;
+ int irq;
+ int phy_id;
+ unsigned int desc_size;
+ u32 msg_enable;
+ struct clk *clk;
+ struct reset_control *rst;
+ phy_interface_t phy_mode;
+ struct phy_device *phydev;
+ struct mii_bus *mdio;
+
+ /* stats */
+ struct ave_stats stats_rx;
+ struct ave_stats stats_tx;
+
+ /* NAPI support */
+ struct net_device *ndev;
+ struct napi_struct napi_rx;
+ struct napi_struct napi_tx;
+
+ /* descriptor */
+ struct ave_desc_info rx;
+ struct ave_desc_info tx;
+
+ /* flow control */
+ int pause_auto;
+ int pause_rx;
+ int pause_tx;
+
+ const struct ave_soc_data *data;
+};
+
+static inline u32 ave_desc_read(struct net_device *ndev, enum desc_id id,
+ int entry, int offset)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 addr = (id == AVE_DESCID_TX) ? priv->tx.daddr : priv->rx.daddr;
+
+ addr += entry * priv->desc_size + offset;
+
+ return readl(priv->base + addr);
+}
+
+static inline u32 ave_desc_read_cmdsts(struct net_device *ndev, enum desc_id id,
+ int entry)
+{
+ return ave_desc_read(ndev, id, entry, AVE_DESC_OFS_CMDSTS);
+}
+
+static inline void ave_desc_write(struct net_device *ndev, enum desc_id id,
+ int entry, int offset, u32 val)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 addr = (id == AVE_DESCID_TX) ? priv->tx.daddr : priv->rx.daddr;
+
+ addr += entry * priv->desc_size + offset;
+
+ writel(val, priv->base + addr);
+}
+
+static inline void ave_desc_write_cmdsts(struct net_device *ndev,
+ enum desc_id id, int entry, u32 val)
+{
+ ave_desc_write(ndev, id, entry, AVE_DESC_OFS_CMDSTS, val);
+}
+
+static inline void ave_desc_write_addr(struct net_device *ndev,
+ enum desc_id id, int entry,
+ dma_addr_t paddr)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ ave_desc_write(ndev, id, entry, AVE_DESC_OFS_ADDRL,
+ lower_32_bits(paddr));
+ if (IS_DESC_64BIT(priv))
+ ave_desc_write(ndev, id,
+ entry, AVE_DESC_OFS_ADDRU,
+ upper_32_bits(paddr));
+}
+
+static inline u32 ave_irq_disable_all(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 ret;
+
+ ret = readl(priv->base + AVE_GIMR);
+ writel(0, priv->base + AVE_GIMR);
+
+ return ret;
+}
+
+static inline void ave_irq_restore(struct net_device *ndev, u32 val)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ writel(val, priv->base + AVE_GIMR);
+}
+
+static inline void ave_irq_enable(struct net_device *ndev, u32 bitflag)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ writel(readl(priv->base + AVE_GIMR) | bitflag, priv->base + AVE_GIMR);
+ writel(bitflag, priv->base + AVE_GISR);
+}
+
+static inline void ave_irq_disable(struct net_device *ndev, u32 bitflag)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ writel(readl(priv->base + AVE_GIMR) & ~bitflag, priv->base + AVE_GIMR);
+}
+
+static void ave_hw_write_macaddr(struct net_device *ndev,
+ const unsigned char *mac_addr,
+ int reg1, int reg2)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ writel(mac_addr[0] | mac_addr[1] << 8 |
+ mac_addr[2] << 16 | mac_addr[3] << 24, priv->base + reg1);
+ writel(mac_addr[4] | mac_addr[5] << 8, priv->base + reg2);
+}
+
+static void ave_hw_read_version(struct net_device *ndev, char *buf, int len)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 major, minor, vr;
+
+ vr = readl(priv->base + AVE_VR);
+ major = (vr & GENMASK(15, 8)) >> 8;
+ minor = (vr & GENMASK(7, 0));
+ snprintf(buf, len, "v%u.%u", major, minor);
+}
+
+static void ave_ethtool_get_drvinfo(struct net_device *ndev,
+ struct ethtool_drvinfo *info)
+{
+ struct device *dev = ndev->dev.parent;
+
+ strlcpy(info->driver, dev->driver->name, sizeof(info->driver));
+ strlcpy(info->bus_info, dev_name(dev), sizeof(info->bus_info));
+ ave_hw_read_version(ndev, info->fw_version, sizeof(info->fw_version));
+}
+
+static u32 ave_ethtool_get_msglevel(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ return priv->msg_enable;
+}
+
+static void ave_ethtool_set_msglevel(struct net_device *ndev, u32 val)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ priv->msg_enable = val;
+}
+
+static void ave_ethtool_get_wol(struct net_device *ndev,
+ struct ethtool_wolinfo *wol)
+{
+ wol->supported = 0;
+ wol->wolopts = 0;
+
+ if (ndev->phydev)
+ phy_ethtool_get_wol(ndev->phydev, wol);
+}
+
+static int ave_ethtool_set_wol(struct net_device *ndev,
+ struct ethtool_wolinfo *wol)
+{
+ int ret;
+
+ if (!ndev->phydev ||
+ (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)))
+ return -EOPNOTSUPP;
+
+ ret = phy_ethtool_set_wol(ndev->phydev, wol);
+ if (!ret)
+ device_set_wakeup_enable(&ndev->dev, !!wol->wolopts);
+
+ return ret;
+}
+
+static void ave_ethtool_get_pauseparam(struct net_device *ndev,
+ struct ethtool_pauseparam *pause)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ pause->autoneg = priv->pause_auto;
+ pause->rx_pause = priv->pause_rx;
+ pause->tx_pause = priv->pause_tx;
+}
+
+static int ave_ethtool_set_pauseparam(struct net_device *ndev,
+ struct ethtool_pauseparam *pause)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct phy_device *phydev = ndev->phydev;
+
+ if (!phydev)
+ return -EINVAL;
+
+ priv->pause_auto = pause->autoneg;
+ priv->pause_rx = pause->rx_pause;
+ priv->pause_tx = pause->tx_pause;
+
+ phydev->advertising &= ~(ADVERTISED_Pause | ADVERTISED_Asym_Pause);
+ if (pause->rx_pause)
+ phydev->advertising |= ADVERTISED_Pause | ADVERTISED_Asym_Pause;
+ if (pause->tx_pause)
+ phydev->advertising ^= ADVERTISED_Asym_Pause;
+
+ if (pause->autoneg) {
+ if (netif_running(ndev))
+ phy_start_aneg(phydev);
+ }
+
+ return 0;
+}
+
+static const struct ethtool_ops ave_ethtool_ops = {
+ .get_link_ksettings = phy_ethtool_get_link_ksettings,
+ .set_link_ksettings = phy_ethtool_set_link_ksettings,
+ .get_drvinfo = ave_ethtool_get_drvinfo,
+ .nway_reset = phy_ethtool_nway_reset,
+ .get_link = ethtool_op_get_link,
+ .get_msglevel = ave_ethtool_get_msglevel,
+ .set_msglevel = ave_ethtool_set_msglevel,
+ .get_wol = ave_ethtool_get_wol,
+ .set_wol = ave_ethtool_set_wol,
+ .get_pauseparam = ave_ethtool_get_pauseparam,
+ .set_pauseparam = ave_ethtool_set_pauseparam,
+};
+
+static int ave_mdiobus_read(struct mii_bus *bus, int phyid, int regnum)
+{
+ struct net_device *ndev = bus->priv;
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 mdioctl, mdiosr;
+ int ret;
+
+ /* write address */
+ writel((phyid << 8) | regnum, priv->base + AVE_MDIOAR);
+
+ /* read request */
+ mdioctl = readl(priv->base + AVE_MDIOCTR);
+ writel((mdioctl | AVE_MDIOCTR_RREQ) & ~AVE_MDIOCTR_WREQ,
+ priv->base + AVE_MDIOCTR);
+
+ ret = readl_poll_timeout(priv->base + AVE_MDIOSR, mdiosr,
+ !(mdiosr & AVE_MDIOSR_STS), 20, 2000);
+ if (ret) {
+ netdev_err(ndev, "failed to read (phy:%d reg:%x)\n",
+ phyid, regnum);
+ return ret;
+ }
+
+ return readl(priv->base + AVE_MDIORDR) & GENMASK(15, 0);
+}
+
+static int ave_mdiobus_write(struct mii_bus *bus,
+ int phyid, int regnum, u16 val)
+{
+ struct net_device *ndev = bus->priv;
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 mdioctl, mdiosr;
+ int ret;
+
+ /* write address */
+ writel((phyid << 8) | regnum, priv->base + AVE_MDIOAR);
+
+ /* write data */
+ writel(val, priv->base + AVE_MDIOWDR);
+
+ /* write request */
+ mdioctl = readl(priv->base + AVE_MDIOCTR);
+ writel((mdioctl | AVE_MDIOCTR_WREQ) & ~AVE_MDIOCTR_RREQ,
+ priv->base + AVE_MDIOCTR);
+
+ ret = readl_poll_timeout(priv->base + AVE_MDIOSR, mdiosr,
+ !(mdiosr & AVE_MDIOSR_STS), 20, 2000);
+ if (ret)
+ netdev_err(ndev, "failed to write (phy:%d reg:%x)\n",
+ phyid, regnum);
+
+ return ret;
+}
+
+static int ave_dma_map(struct net_device *ndev, struct ave_desc *desc,
+ void *ptr, size_t len,
+ enum dma_data_direction dir, dma_addr_t *paddr)
+{
+ dma_addr_t map_addr;
+
+ map_addr = dma_map_single(ndev->dev.parent, ptr, len, dir);
+ if (unlikely(dma_mapping_error(ndev->dev.parent, map_addr)))
+ return -ENOMEM;
+
+ desc->skbs_dma = map_addr;
+ desc->skbs_dmalen = len;
+ *paddr = map_addr;
+
+ return 0;
+}
+
+static void ave_dma_unmap(struct net_device *ndev, struct ave_desc *desc,
+ enum dma_data_direction dir)
+{
+ if (!desc->skbs_dma)
+ return;
+
+ dma_unmap_single(ndev->dev.parent,
+ desc->skbs_dma, desc->skbs_dmalen, dir);
+ desc->skbs_dma = 0;
+}
+
+/* Prepare Rx descriptor and memory */
+static int ave_rxdesc_prepare(struct net_device *ndev, int entry)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct sk_buff *skb;
+ dma_addr_t paddr;
+ int ret;
+
+ skb = priv->rx.desc[entry].skbs;
+ if (!skb) {
+ skb = netdev_alloc_skb_ip_align(ndev,
+ AVE_MAX_ETHFRAME);
+ if (!skb) {
+ netdev_err(ndev, "can't allocate skb for Rx\n");
+ return -ENOMEM;
+ }
+ }
+
+ /* set disable to cmdsts */
+ ave_desc_write_cmdsts(ndev, AVE_DESCID_RX, entry,
+ AVE_STS_INTR | AVE_STS_OWN);
+
+ /* map Rx buffer
+ * Rx buffer set to the Rx descriptor has two restrictions:
+ * - Rx buffer address is 4 byte aligned.
+ * - Rx buffer begins with 2 byte headroom, and data will be put from
+ * (buffer + 2).
+ * To satisfy this, specify the address to put back the buffer
+ * pointer advanced by NET_IP_ALIGN by netdev_alloc_skb_ip_align(),
+ * and expand the map size by NET_IP_ALIGN.
+ */
+ ret = ave_dma_map(ndev, &priv->rx.desc[entry],
+ skb->data - NET_IP_ALIGN,
+ AVE_MAX_ETHFRAME + NET_IP_ALIGN,
+ DMA_FROM_DEVICE, &paddr);
+ if (ret) {
+ netdev_err(ndev, "can't map skb for Rx\n");
+ dev_kfree_skb_any(skb);
+ return ret;
+ }
+ priv->rx.desc[entry].skbs = skb;
+
+ /* set buffer pointer */
+ ave_desc_write_addr(ndev, AVE_DESCID_RX, entry, paddr);
+
+ /* set enable to cmdsts */
+ ave_desc_write_cmdsts(ndev, AVE_DESCID_RX, entry,
+ AVE_STS_INTR | AVE_MAX_ETHFRAME);
+
+ return ret;
+}
+
+/* Switch state of descriptor */
+static int ave_desc_switch(struct net_device *ndev, enum desc_state state)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ int ret = 0;
+ u32 val;
+
+ switch (state) {
+ case AVE_DESC_START:
+ writel(AVE_DESCC_TD | AVE_DESCC_RD0, priv->base + AVE_DESCC);
+ break;
+
+ case AVE_DESC_STOP:
+ writel(0, priv->base + AVE_DESCC);
+ if (readl_poll_timeout(priv->base + AVE_DESCC, val, !val,
+ 150, 15000)) {
+ netdev_err(ndev, "can't stop descriptor\n");
+ ret = -EBUSY;
+ }
+ break;
+
+ case AVE_DESC_RX_SUSPEND:
+ val = readl(priv->base + AVE_DESCC);
+ val |= AVE_DESCC_RDSTP;
+ val &= ~AVE_DESCC_STATUS_MASK;
+ writel(val, priv->base + AVE_DESCC);
+ if (readl_poll_timeout(priv->base + AVE_DESCC, val,
+ val & (AVE_DESCC_RDSTP << 16),
+ 150, 150000)) {
+ netdev_err(ndev, "can't suspend descriptor\n");
+ ret = -EBUSY;
+ }
+ break;
+
+ case AVE_DESC_RX_PERMIT:
+ val = readl(priv->base + AVE_DESCC);
+ val &= ~AVE_DESCC_RDSTP;
+ val &= ~AVE_DESCC_STATUS_MASK;
+ writel(val, priv->base + AVE_DESCC);
+ break;
+
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+static int ave_tx_complete(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 proc_idx, done_idx, ndesc, cmdsts;
+ unsigned int nr_freebuf = 0;
+ unsigned int tx_packets = 0;
+ unsigned int tx_bytes = 0;
+
+ proc_idx = priv->tx.proc_idx;
+ done_idx = priv->tx.done_idx;
+ ndesc = priv->tx.ndesc;
+
+ /* free pre-stored skb from done_idx to proc_idx */
+ while (proc_idx != done_idx) {
+ cmdsts = ave_desc_read_cmdsts(ndev, AVE_DESCID_TX, done_idx);
+
+ /* do nothing if owner is HW (==1 for Tx) */
+ if (cmdsts & AVE_STS_OWN)
+ break;
+
+ /* check Tx status and updates statistics */
+ if (cmdsts & AVE_STS_OK) {
+ tx_bytes += cmdsts & AVE_STS_PKTLEN_TX_MASK;
+ /* success */
+ if (cmdsts & AVE_STS_LAST)
+ tx_packets++;
+ } else {
+ /* error */
+ if (cmdsts & AVE_STS_LAST) {
+ priv->stats_tx.errors++;
+ if (cmdsts & (AVE_STS_OWC | AVE_STS_EC))
+ priv->stats_tx.collisions++;
+ }
+ }
+
+ /* release skb */
+ if (priv->tx.desc[done_idx].skbs) {
+ ave_dma_unmap(ndev, &priv->tx.desc[done_idx],
+ DMA_TO_DEVICE);
+ dev_consume_skb_any(priv->tx.desc[done_idx].skbs);
+ priv->tx.desc[done_idx].skbs = NULL;
+ nr_freebuf++;
+ }
+ done_idx = (done_idx + 1) % ndesc;
+ }
+
+ priv->tx.done_idx = done_idx;
+
+ /* update stats */
+ u64_stats_update_begin(&priv->stats_tx.syncp);
+ priv->stats_tx.packets += tx_packets;
+ priv->stats_tx.bytes += tx_bytes;
+ u64_stats_update_end(&priv->stats_tx.syncp);
+
+ /* wake queue for freeing buffer */
+ if (unlikely(netif_queue_stopped(ndev)) && nr_freebuf)
+ netif_wake_queue(ndev);
+
+ return nr_freebuf;
+}
+
+static int ave_rx_receive(struct net_device *ndev, int num)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct sk_buff *skb;
+ u32 proc_idx, done_idx, ndesc, cmdsts;
+ int restpkt, npkts;
+ unsigned int pktlen;
+ unsigned int rx_packets = 0;
+ unsigned int rx_bytes = 0;
+
+ proc_idx = priv->rx.proc_idx;
+ done_idx = priv->rx.done_idx;
+ ndesc = priv->rx.ndesc;
+ restpkt = ((proc_idx + ndesc - 1) - done_idx) % ndesc;
+
+ for (npkts = 0; npkts < num; npkts++) {
+ /* we can't receive more packet, so fill desc quickly */
+ if (--restpkt < 0)
+ break;
+
+ cmdsts = ave_desc_read_cmdsts(ndev, AVE_DESCID_RX, proc_idx);
+
+ /* do nothing if owner is HW (==0 for Rx) */
+ if (!(cmdsts & AVE_STS_OWN))
+ break;
+
+ if (!(cmdsts & AVE_STS_OK)) {
+ priv->stats_rx.errors++;
+ proc_idx = (proc_idx + 1) % ndesc;
+ continue;
+ }
+
+ pktlen = cmdsts & AVE_STS_PKTLEN_RX_MASK;
+
+ /* get skbuff for rx */
+ skb = priv->rx.desc[proc_idx].skbs;
+ priv->rx.desc[proc_idx].skbs = NULL;
+
+ ave_dma_unmap(ndev, &priv->rx.desc[proc_idx], DMA_FROM_DEVICE);
+
+ skb->dev = ndev;
+ skb_put(skb, pktlen);
+ skb->protocol = eth_type_trans(skb, ndev);
+
+ if ((cmdsts & AVE_STS_CSSV) && (!(cmdsts & AVE_STS_CSER)))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+ rx_packets++;
+ rx_bytes += pktlen;
+
+ netif_receive_skb(skb);
+
+ proc_idx = (proc_idx + 1) % ndesc;
+ }
+
+ priv->rx.proc_idx = proc_idx;
+
+ /* update stats */
+ u64_stats_update_begin(&priv->stats_rx.syncp);
+ priv->stats_rx.packets += rx_packets;
+ priv->stats_rx.bytes += rx_bytes;
+ u64_stats_update_end(&priv->stats_rx.syncp);
+
+ /* refill the Rx buffers */
+ while (proc_idx != done_idx) {
+ if (ave_rxdesc_prepare(ndev, done_idx))
+ break;
+ done_idx = (done_idx + 1) % ndesc;
+ }
+
+ priv->rx.done_idx = done_idx;
+
+ return npkts;
+}
+
+static int ave_napi_poll_rx(struct napi_struct *napi, int budget)
+{
+ struct ave_private *priv;
+ struct net_device *ndev;
+ int num;
+
+ priv = container_of(napi, struct ave_private, napi_rx);
+ ndev = priv->ndev;
+
+ num = ave_rx_receive(ndev, budget);
+ if (num < budget) {
+ napi_complete_done(napi, num);
+
+ /* enable Rx interrupt when NAPI finishes */
+ ave_irq_enable(ndev, AVE_GI_RXIINT);
+ }
+
+ return num;
+}
+
+static int ave_napi_poll_tx(struct napi_struct *napi, int budget)
+{
+ struct ave_private *priv;
+ struct net_device *ndev;
+ int num;
+
+ priv = container_of(napi, struct ave_private, napi_tx);
+ ndev = priv->ndev;
+
+ num = ave_tx_complete(ndev);
+ napi_complete(napi);
+
+ /* enable Tx interrupt when NAPI finishes */
+ ave_irq_enable(ndev, AVE_GI_TX);
+
+ return num;
+}
+
+static void ave_global_reset(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 val;
+
+ /* set config register */
+ val = AVE_CFGR_FLE | AVE_CFGR_IPFCEN | AVE_CFGR_CHE;
+ if (!phy_interface_mode_is_rgmii(priv->phy_mode))
+ val |= AVE_CFGR_MII;
+ writel(val, priv->base + AVE_CFGR);
+
+ /* reset RMII register */
+ val = readl(priv->base + AVE_RSTCTRL);
+ val &= ~AVE_RSTCTRL_RMIIRST;
+ writel(val, priv->base + AVE_RSTCTRL);
+
+ /* assert reset */
+ writel(AVE_GRR_GRST | AVE_GRR_PHYRST, priv->base + AVE_GRR);
+ msleep(20);
+
+ /* 1st, negate PHY reset only */
+ writel(AVE_GRR_GRST, priv->base + AVE_GRR);
+ msleep(40);
+
+ /* negate reset */
+ writel(0, priv->base + AVE_GRR);
+ msleep(40);
+
+ /* negate RMII register */
+ val = readl(priv->base + AVE_RSTCTRL);
+ val |= AVE_RSTCTRL_RMIIRST;
+ writel(val, priv->base + AVE_RSTCTRL);
+
+ ave_irq_disable_all(ndev);
+}
+
+static void ave_rxfifo_reset(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 rxcr_org;
+
+ /* save and disable MAC receive op */
+ rxcr_org = readl(priv->base + AVE_RXCR);
+ writel(rxcr_org & (~AVE_RXCR_RXEN), priv->base + AVE_RXCR);
+
+ /* suspend Rx descriptor */
+ ave_desc_switch(ndev, AVE_DESC_RX_SUSPEND);
+
+ /* receive all packets before descriptor starts */
+ ave_rx_receive(ndev, priv->rx.ndesc);
+
+ /* assert reset */
+ writel(AVE_GRR_RXFFR, priv->base + AVE_GRR);
+ usleep_range(40, 50);
+
+ /* negate reset */
+ writel(0, priv->base + AVE_GRR);
+ usleep_range(10, 20);
+
+ /* negate interrupt status */
+ writel(AVE_GI_RXOVF, priv->base + AVE_GISR);
+
+ /* permit descriptor */
+ ave_desc_switch(ndev, AVE_DESC_RX_PERMIT);
+
+ /* restore MAC reccieve op */
+ writel(rxcr_org, priv->base + AVE_RXCR);
+}
+
+static irqreturn_t ave_irq_handler(int irq, void *netdev)
+{
+ struct net_device *ndev = (struct net_device *)netdev;
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 gimr_val, gisr_val;
+
+ gimr_val = ave_irq_disable_all(ndev);
+
+ /* get interrupt status */
+ gisr_val = readl(priv->base + AVE_GISR);
+
+ /* PHY */
+ if (gisr_val & AVE_GI_PHY)
+ writel(AVE_GI_PHY, priv->base + AVE_GISR);
+
+ /* check exceeding packet */
+ if (gisr_val & AVE_GI_RXERR) {
+ writel(AVE_GI_RXERR, priv->base + AVE_GISR);
+ netdev_err(ndev, "receive a packet exceeding frame buffer\n");
+ }
+
+ gisr_val &= gimr_val;
+ if (!gisr_val)
+ goto exit_isr;
+
+ /* RxFIFO overflow */
+ if (gisr_val & AVE_GI_RXOVF) {
+ priv->stats_rx.fifo_errors++;
+ ave_rxfifo_reset(ndev);
+ goto exit_isr;
+ }
+
+ /* Rx drop */
+ if (gisr_val & AVE_GI_RXDROP) {
+ priv->stats_rx.dropped++;
+ writel(AVE_GI_RXDROP, priv->base + AVE_GISR);
+ }
+
+ /* Rx interval */
+ if (gisr_val & AVE_GI_RXIINT) {
+ napi_schedule(&priv->napi_rx);
+ /* still force to disable Rx interrupt until NAPI finishes */
+ gimr_val &= ~AVE_GI_RXIINT;
+ }
+
+ /* Tx completed */
+ if (gisr_val & AVE_GI_TX) {
+ napi_schedule(&priv->napi_tx);
+ /* still force to disable Tx interrupt until NAPI finishes */
+ gimr_val &= ~AVE_GI_TX;
+ }
+
+exit_isr:
+ ave_irq_restore(ndev, gimr_val);
+
+ return IRQ_HANDLED;
+}
+
+static int ave_pfsel_start(struct net_device *ndev, unsigned int entry)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 val;
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+
+ val = readl(priv->base + AVE_PFEN);
+ writel(val | BIT(entry), priv->base + AVE_PFEN);
+
+ return 0;
+}
+
+static int ave_pfsel_stop(struct net_device *ndev, unsigned int entry)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 val;
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+
+ val = readl(priv->base + AVE_PFEN);
+ writel(val & ~BIT(entry), priv->base + AVE_PFEN);
+
+ return 0;
+}
+
+static int ave_pfsel_set_macaddr(struct net_device *ndev,
+ unsigned int entry,
+ const unsigned char *mac_addr,
+ unsigned int set_size)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return -EINVAL;
+ if (WARN_ON(set_size > 6))
+ return -EINVAL;
+
+ ave_pfsel_stop(ndev, entry);
+
+ /* set MAC address for the filter */
+ ave_hw_write_macaddr(ndev, mac_addr,
+ AVE_PKTF(entry), AVE_PKTF(entry) + 4);
+
+ /* set byte mask */
+ writel(GENMASK(31, set_size) & AVE_PFMBYTE_MASK0,
+ priv->base + AVE_PFMBYTE(entry));
+ writel(AVE_PFMBYTE_MASK1, priv->base + AVE_PFMBYTE(entry) + 4);
+
+ /* set bit mask filter */
+ writel(AVE_PFMBIT_MASK, priv->base + AVE_PFMBIT(entry));
+
+ /* set selector to ring 0 */
+ writel(0, priv->base + AVE_PFSEL(entry));
+
+ /* restart filter */
+ ave_pfsel_start(ndev, entry);
+
+ return 0;
+}
+
+static void ave_pfsel_set_promisc(struct net_device *ndev,
+ unsigned int entry, u32 rxring)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ if (WARN_ON(entry > AVE_PF_SIZE))
+ return;
+
+ ave_pfsel_stop(ndev, entry);
+
+ /* set byte mask */
+ writel(AVE_PFMBYTE_MASK0, priv->base + AVE_PFMBYTE(entry));
+ writel(AVE_PFMBYTE_MASK1, priv->base + AVE_PFMBYTE(entry) + 4);
+
+ /* set bit mask filter */
+ writel(AVE_PFMBIT_MASK, priv->base + AVE_PFMBIT(entry));
+
+ /* set selector to rxring */
+ writel(rxring, priv->base + AVE_PFSEL(entry));
+
+ ave_pfsel_start(ndev, entry);
+}
+
+static void ave_pfsel_init(struct net_device *ndev)
+{
+ int i;
+ unsigned char bcast_mac[ETH_ALEN];
+
+ eth_broadcast_addr(bcast_mac);
+
+ for (i = 0; i < AVE_PF_SIZE; i++)
+ ave_pfsel_stop(ndev, i);
+
+ /* promiscious entry, select ring 0 */
+ ave_pfsel_set_promisc(ndev, AVE_PFNUM_FILTER, 0);
+
+ /* unicast entry */
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_UNICAST, ndev->dev_addr, 6);
+
+ /* broadcast entry */
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_BROADCAST, bcast_mac, 6);
+}
+
+static void ave_phy_adjust_link(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct phy_device *phydev = ndev->phydev;
+ u32 val, txcr, rxcr, rxcr_org;
+ u16 rmt_adv = 0, lcl_adv = 0;
+ u8 cap;
+
+ /* set RGMII speed */
+ val = readl(priv->base + AVE_TXCR);
+ val &= ~(AVE_TXCR_TXSPD_100 | AVE_TXCR_TXSPD_1G);
+
+ if (phy_interface_is_rgmii(phydev) && phydev->speed == SPEED_1000)
+ val |= AVE_TXCR_TXSPD_1G;
+ else if (phydev->speed == SPEED_100)
+ val |= AVE_TXCR_TXSPD_100;
+
+ writel(val, priv->base + AVE_TXCR);
+
+ /* set RMII speed (100M/10M only) */
+ if (!phy_interface_is_rgmii(phydev)) {
+ val = readl(priv->base + AVE_LINKSEL);
+ if (phydev->speed == SPEED_10)
+ val &= ~AVE_LINKSEL_100M;
+ else
+ val |= AVE_LINKSEL_100M;
+ writel(val, priv->base + AVE_LINKSEL);
+ }
+
+ /* check current RXCR/TXCR */
+ rxcr = readl(priv->base + AVE_RXCR);
+ txcr = readl(priv->base + AVE_TXCR);
+ rxcr_org = rxcr;
+
+ if (phydev->duplex) {
+ rxcr |= AVE_RXCR_FDUPEN;
+
+ if (phydev->pause)
+ rmt_adv |= LPA_PAUSE_CAP;
+ if (phydev->asym_pause)
+ rmt_adv |= LPA_PAUSE_ASYM;
+ if (phydev->advertising & ADVERTISED_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_CAP;
+ if (phydev->advertising & ADVERTISED_Asym_Pause)
+ lcl_adv |= ADVERTISE_PAUSE_ASYM;
+
+ cap = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv);
+ if (cap & FLOW_CTRL_TX)
+ txcr |= AVE_TXCR_FLOCTR;
+ else
+ txcr &= ~AVE_TXCR_FLOCTR;
+ if (cap & FLOW_CTRL_RX)
+ rxcr |= AVE_RXCR_FLOCTR;
+ else
+ rxcr &= ~AVE_RXCR_FLOCTR;
+ } else {
+ rxcr &= ~AVE_RXCR_FDUPEN;
+ rxcr &= ~AVE_RXCR_FLOCTR;
+ txcr &= ~AVE_TXCR_FLOCTR;
+ }
+
+ if (rxcr_org != rxcr) {
+ /* disable Rx mac */
+ writel(rxcr & ~AVE_RXCR_RXEN, priv->base + AVE_RXCR);
+ /* change and enable TX/Rx mac */
+ writel(txcr, priv->base + AVE_TXCR);
+ writel(rxcr, priv->base + AVE_RXCR);
+ }
+
+ phy_print_status(phydev);
+}
+
+static void ave_macaddr_init(struct net_device *ndev)
+{
+ ave_hw_write_macaddr(ndev, ndev->dev_addr, AVE_RXMAC1R, AVE_RXMAC2R);
+
+ /* pfsel unicast entry */
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_UNICAST, ndev->dev_addr, 6);
+}
+
+static int ave_init(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct device *dev = ndev->dev.parent;
+ struct device_node *np = dev->of_node, *mdio_np;
+ struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL };
+ struct phy_device *phydev;
+ int ret;
+
+ /* enable clk because of hw access until ndo_open */
+ ret = clk_prepare_enable(priv->clk);
+ if (ret) {
+ dev_err(dev, "can't enable clock\n");
+ return ret;
+ }
+ ret = reset_control_deassert(priv->rst);
+ if (ret) {
+ dev_err(dev, "can't deassert reset\n");
+ goto out_clk_disable;
+ }
+
+ ave_global_reset(ndev);
+
+ mdio_np = of_get_child_by_name(np, "mdio");
+ if (!mdio_np) {
+ dev_err(dev, "mdio node not found\n");
+ ret = -EINVAL;
+ goto out_reset_assert;
+ }
+ ret = of_mdiobus_register(priv->mdio, mdio_np);
+ of_node_put(mdio_np);
+ if (ret) {
+ dev_err(dev, "failed to register mdiobus\n");
+ goto out_reset_assert;
+ }
+
+ phydev = of_phy_get_and_connect(ndev, np, ave_phy_adjust_link);
+ if (!phydev) {
+ dev_err(dev, "could not attach to PHY\n");
+ ret = -ENODEV;
+ goto out_mdio_unregister;
+ }
+
+ priv->phydev = phydev;
+
+ phy_ethtool_get_wol(phydev, &wol);
+ device_set_wakeup_capable(&ndev->dev, !!wol.supported);
+
+ if (!phy_interface_is_rgmii(phydev)) {
+ phydev->supported &= ~PHY_GBIT_FEATURES;
+ phydev->supported |= PHY_BASIC_FEATURES;
+ }
+ phydev->supported |= SUPPORTED_Pause | SUPPORTED_Asym_Pause;
+
+ phy_attached_info(phydev);
+
+ return 0;
+
+out_mdio_unregister:
+ mdiobus_unregister(priv->mdio);
+out_reset_assert:
+ reset_control_assert(priv->rst);
+out_clk_disable:
+ clk_disable_unprepare(priv->clk);
+
+ return ret;
+}
+
+static void ave_uninit(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+
+ phy_disconnect(priv->phydev);
+ mdiobus_unregister(priv->mdio);
+
+ /* disable clk because of hw access after ndo_stop */
+ reset_control_assert(priv->rst);
+ clk_disable_unprepare(priv->clk);
+}
+
+static int ave_open(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ int entry;
+ int ret;
+ u32 val;
+
+ ret = request_irq(priv->irq, ave_irq_handler, IRQF_SHARED, ndev->name,
+ ndev);
+ if (ret)
+ return ret;
+
+ priv->tx.desc = kcalloc(priv->tx.ndesc, sizeof(*priv->tx.desc),
+ GFP_KERNEL);
+ if (!priv->tx.desc) {
+ ret = -ENOMEM;
+ goto out_free_irq;
+ }
+
+ priv->rx.desc = kcalloc(priv->rx.ndesc, sizeof(*priv->rx.desc),
+ GFP_KERNEL);
+ if (!priv->rx.desc) {
+ kfree(priv->tx.desc);
+ ret = -ENOMEM;
+ goto out_free_irq;
+ }
+
+ /* initialize Tx work and descriptor */
+ priv->tx.proc_idx = 0;
+ priv->tx.done_idx = 0;
+ for (entry = 0; entry < priv->tx.ndesc; entry++) {
+ ave_desc_write_cmdsts(ndev, AVE_DESCID_TX, entry, 0);
+ ave_desc_write_addr(ndev, AVE_DESCID_TX, entry, 0);
+ }
+ writel(AVE_TXDC_ADDR_START
+ | (((priv->tx.ndesc * priv->desc_size) << 16) & AVE_TXDC_SIZE),
+ priv->base + AVE_TXDC);
+
+ /* initialize Rx work and descriptor */
+ priv->rx.proc_idx = 0;
+ priv->rx.done_idx = 0;
+ for (entry = 0; entry < priv->rx.ndesc; entry++) {
+ if (ave_rxdesc_prepare(ndev, entry))
+ break;
+ }
+ writel(AVE_RXDC0_ADDR_START
+ | (((priv->rx.ndesc * priv->desc_size) << 16) & AVE_RXDC0_SIZE),
+ priv->base + AVE_RXDC0);
+
+ ave_desc_switch(ndev, AVE_DESC_START);
+
+ ave_pfsel_init(ndev);
+ ave_macaddr_init(ndev);
+
+ /* set Rx configuration */
+ /* full duplex, enable pause drop, enalbe flow control */
+ val = AVE_RXCR_RXEN | AVE_RXCR_FDUPEN | AVE_RXCR_DRPEN |
+ AVE_RXCR_FLOCTR | (AVE_MAX_ETHFRAME & AVE_RXCR_MPSIZ_MASK);
+ writel(val, priv->base + AVE_RXCR);
+
+ /* set Tx configuration */
+ /* enable flow control, disable loopback */
+ writel(AVE_TXCR_FLOCTR, priv->base + AVE_TXCR);
+
+ /* enable timer, clear EN,INTM, and mask interval unit(BSCK) */
+ val = readl(priv->base + AVE_IIRQC) & AVE_IIRQC_BSCK;
+ val |= AVE_IIRQC_EN0 | (AVE_INTM_COUNT << 16);
+ writel(val, priv->base + AVE_IIRQC);
+
+ val = AVE_GI_RXIINT | AVE_GI_RXOVF | AVE_GI_TX;
+ ave_irq_restore(ndev, val);
+
+ napi_enable(&priv->napi_rx);
+ napi_enable(&priv->napi_tx);
+
+ phy_start(ndev->phydev);
+ phy_start_aneg(ndev->phydev);
+ netif_start_queue(ndev);
+
+ return 0;
+
+out_free_irq:
+ disable_irq(priv->irq);
+ free_irq(priv->irq, ndev);
+
+ return ret;
+}
+
+static int ave_stop(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ int entry;
+
+ ave_irq_disable_all(ndev);
+ disable_irq(priv->irq);
+ free_irq(priv->irq, ndev);
+
+ netif_tx_disable(ndev);
+ phy_stop(ndev->phydev);
+ napi_disable(&priv->napi_tx);
+ napi_disable(&priv->napi_rx);
+
+ ave_desc_switch(ndev, AVE_DESC_STOP);
+
+ /* free Tx buffer */
+ for (entry = 0; entry < priv->tx.ndesc; entry++) {
+ if (!priv->tx.desc[entry].skbs)
+ continue;
+
+ ave_dma_unmap(ndev, &priv->tx.desc[entry], DMA_TO_DEVICE);
+ dev_kfree_skb_any(priv->tx.desc[entry].skbs);
+ priv->tx.desc[entry].skbs = NULL;
+ }
+ priv->tx.proc_idx = 0;
+ priv->tx.done_idx = 0;
+
+ /* free Rx buffer */
+ for (entry = 0; entry < priv->rx.ndesc; entry++) {
+ if (!priv->rx.desc[entry].skbs)
+ continue;
+
+ ave_dma_unmap(ndev, &priv->rx.desc[entry], DMA_FROM_DEVICE);
+ dev_kfree_skb_any(priv->rx.desc[entry].skbs);
+ priv->rx.desc[entry].skbs = NULL;
+ }
+ priv->rx.proc_idx = 0;
+ priv->rx.done_idx = 0;
+
+ kfree(priv->tx.desc);
+ kfree(priv->rx.desc);
+
+ return 0;
+}
+
+static int ave_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ u32 proc_idx, done_idx, ndesc, cmdsts;
+ int ret, freepkt;
+ dma_addr_t paddr;
+
+ proc_idx = priv->tx.proc_idx;
+ done_idx = priv->tx.done_idx;
+ ndesc = priv->tx.ndesc;
+ freepkt = ((done_idx + ndesc - 1) - proc_idx) % ndesc;
+
+ /* stop queue when not enough entry */
+ if (unlikely(freepkt < 1)) {
+ netif_stop_queue(ndev);
+ return NETDEV_TX_BUSY;
+ }
+
+ /* add padding for short packet */
+ if (skb_put_padto(skb, ETH_ZLEN)) {
+ priv->stats_tx.dropped++;
+ return NETDEV_TX_OK;
+ }
+
+ /* map Tx buffer
+ * Tx buffer set to the Tx descriptor doesn't have any restriction.
+ */
+ ret = ave_dma_map(ndev, &priv->tx.desc[proc_idx],
+ skb->data, skb->len, DMA_TO_DEVICE, &paddr);
+ if (ret) {
+ dev_kfree_skb_any(skb);
+ priv->stats_tx.dropped++;
+ return NETDEV_TX_OK;
+ }
+
+ priv->tx.desc[proc_idx].skbs = skb;
+
+ ave_desc_write_addr(ndev, AVE_DESCID_TX, proc_idx, paddr);
+
+ cmdsts = AVE_STS_OWN | AVE_STS_1ST | AVE_STS_LAST
+ | (skb->len & AVE_STS_PKTLEN_TX_MASK);
+
+ /* set interrupt per AVE_FORCE_TXINTCNT or when queue is stopped */
+ if (!(proc_idx % AVE_FORCE_TXINTCNT) || netif_queue_stopped(ndev))
+ cmdsts |= AVE_STS_INTR;
+
+ /* disable checksum calculation when skb doesn't calurate checksum */
+ if (skb->ip_summed == CHECKSUM_NONE ||
+ skb->ip_summed == CHECKSUM_UNNECESSARY)
+ cmdsts |= AVE_STS_NOCSUM;
+
+ ave_desc_write_cmdsts(ndev, AVE_DESCID_TX, proc_idx, cmdsts);
+
+ priv->tx.proc_idx = (proc_idx + 1) % ndesc;
+
+ return NETDEV_TX_OK;
+}
+
+static int ave_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd)
+{
+ return phy_mii_ioctl(ndev->phydev, ifr, cmd);
+}
+
+static void ave_set_rx_mode(struct net_device *ndev)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ struct netdev_hw_addr *hw_adr;
+ int count, mc_cnt = netdev_mc_count(ndev);
+ u32 val;
+ static const u8 v4multi_macadr[6] = {
+ 0x01, 0x00, 0x00, 0x00, 0x00, 0x00 };
+ static const u8 v6multi_macadr[6] = {
+ 0x33, 0x00, 0x00, 0x00, 0x00, 0x00 };
+
+ /* MAC addr filter enable for promiscious mode */
+ val = readl(priv->base + AVE_RXCR);
+ if (ndev->flags & IFF_PROMISC || !mc_cnt)
+ val &= ~AVE_RXCR_AFEN;
+ else
+ val |= AVE_RXCR_AFEN;
+ writel(val, priv->base + AVE_RXCR);
+
+ /* set all multicast address */
+ if ((ndev->flags & IFF_ALLMULTI) || mc_cnt > AVE_PF_MULTICAST_SIZE) {
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_MULTICAST,
+ v4multi_macadr, 1);
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_MULTICAST + 1,
+ v6multi_macadr, 1);
+ } else {
+ /* stop all multicast filter */
+ for (count = 0; count < AVE_PF_MULTICAST_SIZE; count++)
+ ave_pfsel_stop(ndev, AVE_PFNUM_MULTICAST + count);
+
+ /* set multicast addresses */
+ count = 0;
+ netdev_for_each_mc_addr(hw_adr, ndev) {
+ if (count == mc_cnt)
+ break;
+ ave_pfsel_set_macaddr(ndev, AVE_PFNUM_MULTICAST + count,
+ hw_adr->addr, 6);
+ count++;
+ }
+ }
+}
+
+static void ave_get_stats64(struct net_device *ndev,
+ struct rtnl_link_stats64 *stats)
+{
+ struct ave_private *priv = netdev_priv(ndev);
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin_irq(&priv->stats_rx.syncp);
+ stats->rx_packets = priv->stats_rx.packets;
+ stats->rx_bytes = priv->stats_rx.bytes;
+ } while (u64_stats_fetch_retry_irq(&priv->stats_rx.syncp, start));
+
+ do {
+ start = u64_stats_fetch_begin_irq(&priv->stats_tx.syncp);
+ stats->tx_packets = priv->stats_tx.packets;
+ stats->tx_bytes = priv->stats_tx.bytes;
+ } while (u64_stats_fetch_retry_irq(&priv->stats_tx.syncp, start));
+
+ stats->rx_errors = priv->stats_rx.errors;
+ stats->tx_errors = priv->stats_tx.errors;
+ stats->rx_dropped = priv->stats_rx.dropped;
+ stats->tx_dropped = priv->stats_tx.dropped;
+ stats->rx_fifo_errors = priv->stats_rx.fifo_errors;
+ stats->collisions = priv->stats_tx.collisions;
+}
+
+static int ave_set_mac_address(struct net_device *ndev, void *p)
+{
+ int ret = eth_mac_addr(ndev, p);
+
+ if (ret)
+ return ret;
+
+ ave_macaddr_init(ndev);
+
+ return 0;
+}
+
+static const struct net_device_ops ave_netdev_ops = {
+ .ndo_init = ave_init,
+ .ndo_uninit = ave_uninit,
+ .ndo_open = ave_open,
+ .ndo_stop = ave_stop,
+ .ndo_start_xmit = ave_start_xmit,
+ .ndo_do_ioctl = ave_ioctl,
+ .ndo_set_rx_mode = ave_set_rx_mode,
+ .ndo_get_stats64 = ave_get_stats64,
+ .ndo_set_mac_address = ave_set_mac_address,
+};
+
+static int ave_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct ave_private *priv;
+ struct net_device *ndev;
+ struct resource *res;
+ const struct ave_soc_data *data;
+ const void *mac_addr;
+ phy_interface_t phy_mode;
+ void __iomem *base;
+ u32 ave_id;
+ u64 dma_mask;
+ int irq, ret;
+ char buf[ETHTOOL_FWVERS_LEN];
+
+ data = of_device_get_match_data(dev);
+ if (WARN_ON(!data))
+ return -EINVAL;
+
+ phy_mode = of_get_phy_mode(np);
+ if (phy_mode < 0) {
+ dev_err(dev, "phy-mode not found\n");
+ return -EINVAL;
+ }
+ if ((!phy_interface_mode_is_rgmii(phy_mode)) &&
+ phy_mode != PHY_INTERFACE_MODE_RMII &&
+ phy_mode != PHY_INTERFACE_MODE_MII) {
+ dev_err(dev, "phy-mode is invalid\n");
+ return -EINVAL;
+ }
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0) {
+ dev_err(dev, "IRQ not found\n");
+ return irq;
+ }
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ base = devm_ioremap_resource(dev, res);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ ndev = alloc_etherdev(sizeof(struct ave_private));
+ if (!ndev) {
+ dev_err(dev, "can't allocate ethernet device\n");
+ return -ENOMEM;
+ }
+
+ ndev->netdev_ops = &ave_netdev_ops;
+ ndev->ethtool_ops = &ave_ethtool_ops;
+ SET_NETDEV_DEV(ndev, dev);
+
+ ndev->features |= (NETIF_F_IP_CSUM | NETIF_F_RXCSUM);
+ ndev->hw_features |= (NETIF_F_IP_CSUM | NETIF_F_RXCSUM);
+
+ ndev->max_mtu = AVE_MAX_ETHFRAME - (ETH_HLEN + ETH_FCS_LEN);
+
+ mac_addr = of_get_mac_address(np);
+ if (mac_addr)
+ ether_addr_copy(ndev->dev_addr, mac_addr);
+
+ /* if the mac address is invalid, use random mac address */
+ if (!is_valid_ether_addr(ndev->dev_addr)) {
+ eth_hw_addr_random(ndev);
+ dev_warn(dev, "Using random MAC address: %pM\n",
+ ndev->dev_addr);
+ }
+
+ priv = netdev_priv(ndev);
+ priv->base = base;
+ priv->irq = irq;
+ priv->ndev = ndev;
+ priv->msg_enable = netif_msg_init(-1, AVE_DEFAULT_MSG_ENABLE);
+ priv->phy_mode = phy_mode;
+ priv->data = data;
+
+ if (IS_DESC_64BIT(priv)) {
+ priv->desc_size = AVE_DESC_SIZE_64;
+ priv->tx.daddr = AVE_TXDM_64;
+ priv->rx.daddr = AVE_RXDM_64;
+ dma_mask = DMA_BIT_MASK(64);
+ } else {
+ priv->desc_size = AVE_DESC_SIZE_32;
+ priv->tx.daddr = AVE_TXDM_32;
+ priv->rx.daddr = AVE_RXDM_32;
+ dma_mask = DMA_BIT_MASK(32);
+ }
+ ret = dma_set_mask(dev, dma_mask);
+ if (ret)
+ goto out_free_netdev;
+
+ priv->tx.ndesc = AVE_NR_TXDESC;
+ priv->rx.ndesc = AVE_NR_RXDESC;
+
+ u64_stats_init(&priv->stats_tx.syncp);
+ u64_stats_init(&priv->stats_rx.syncp);
+
+ priv->clk = devm_clk_get(dev, NULL);
+ if (IS_ERR(priv->clk)) {
+ ret = PTR_ERR(priv->clk);
+ goto out_free_netdev;
+ }
+
+ priv->rst = devm_reset_control_get_optional_shared(dev, NULL);
+ if (IS_ERR(priv->rst)) {
+ ret = PTR_ERR(priv->rst);
+ goto out_free_netdev;
+ }
+
+ priv->mdio = devm_mdiobus_alloc(dev);
+ if (!priv->mdio) {
+ ret = -ENOMEM;
+ goto out_free_netdev;
+ }
+ priv->mdio->priv = ndev;
+ priv->mdio->parent = dev;
+ priv->mdio->read = ave_mdiobus_read;
+ priv->mdio->write = ave_mdiobus_write;
+ priv->mdio->name = "uniphier-mdio";
+ snprintf(priv->mdio->id, MII_BUS_ID_SIZE, "%s-%x",
+ pdev->name, pdev->id);
+
+ /* Register as a NAPI supported driver */
+ netif_napi_add(ndev, &priv->napi_rx, ave_napi_poll_rx, priv->rx.ndesc);
+ netif_tx_napi_add(ndev, &priv->napi_tx, ave_napi_poll_tx,
+ priv->tx.ndesc);
+
+ ret = register_netdev(ndev);
+ if (ret) {
+ dev_err(dev, "failed to register netdevice\n");
+ goto out_del_napi;
+ }
+
+ platform_set_drvdata(pdev, ndev);
+
+ /* get ID and version */
+ ave_id = readl(priv->base + AVE_IDR);
+ ave_hw_read_version(ndev, buf, sizeof(buf));
+
+ dev_info(dev, "Socionext %c%c%c%c Ethernet IP %s (irq=%d, phy=%s)\n",
+ (ave_id >> 24) & 0xff, (ave_id >> 16) & 0xff,
+ (ave_id >> 8) & 0xff, (ave_id >> 0) & 0xff,
+ buf, priv->irq, phy_modes(phy_mode));
+
+ return 0;
+
+out_del_napi:
+ netif_napi_del(&priv->napi_rx);
+ netif_napi_del(&priv->napi_tx);
+out_free_netdev:
+ free_netdev(ndev);
+
+ return ret;
+}
+
+static int ave_remove(struct platform_device *pdev)
+{
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct ave_private *priv = netdev_priv(ndev);
+
+ unregister_netdev(ndev);
+ netif_napi_del(&priv->napi_rx);
+ netif_napi_del(&priv->napi_tx);
+ free_netdev(ndev);
+
+ return 0;
+}
+
+static const struct ave_soc_data ave_pro4_data = {
+ .is_desc_64bit = false,
+};
+
+static const struct ave_soc_data ave_pxs2_data = {
+ .is_desc_64bit = false,
+};
+
+static const struct ave_soc_data ave_ld11_data = {
+ .is_desc_64bit = false,
+};
+
+static const struct ave_soc_data ave_ld20_data = {
+ .is_desc_64bit = true,
+};
+
+static const struct of_device_id of_ave_match[] = {
+ {
+ .compatible = "socionext,uniphier-pro4-ave4",
+ .data = &ave_pro4_data,
+ },
+ {
+ .compatible = "socionext,uniphier-pxs2-ave4",
+ .data = &ave_pxs2_data,
+ },
+ {
+ .compatible = "socionext,uniphier-ld11-ave4",
+ .data = &ave_ld11_data,
+ },
+ {
+ .compatible = "socionext,uniphier-ld20-ave4",
+ .data = &ave_ld20_data,
+ },
+ { /* Sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, of_ave_match);
+
+static struct platform_driver ave_driver = {
+ .probe = ave_probe,
+ .remove = ave_remove,
+ .driver = {
+ .name = "ave",
+ .of_match_table = of_ave_match,
+ },
+};
+module_platform_driver(ave_driver);
+
+MODULE_DESCRIPTION("Socionext UniPhier AVE ethernet driver");
+MODULE_LICENSE("GPL v2");
--
2.7.4
^ permalink raw reply related
* Re: [PATCH net-next 2/5] rhashtable: Add rhastable_walk_peek
From: Tom Herbert @ 2017-12-01 1:15 UTC (permalink / raw)
To: Herbert Xu
Cc: David S . Miller, Linux Kernel Network Developers, Rohit LastName
In-Reply-To: <20171201003841.GA26474@gondor.apana.org.au>
On Thu, Nov 30, 2017 at 4:38 PM, Herbert Xu <herbert@gondor.apana.org.au> wrote:
> On Thu, Nov 30, 2017 at 04:03:02PM -0800, Tom Herbert wrote:
>> This function is like rhashtable_walk_next except that it only returns
>> the current element in the inter and does not advance the iter.
>>
>> This patch also creates __rhashtable_walk_find_next. It finds the next
>> element in the table when the entry cached in iter is NULL or at the end
>> of a slot. __rhashtable_walk_find_next is called from
>> rhashtable_walk_next and rhastable_walk_peek.
>>
>> Signed-off-by: Tom Herbert <tom@quantonium.net>
>
> Hi Tom:
>
> Could you add some motivation for this feature into the patch
> description? As it is it's difficult to deduce why we would want
> to add something like this given that hashtable walks are always
> unstable and there is no guarantee that two calls to peek or a
> peek followed by a normal walk will see the same entry.
>
Hi Herbert,
We don't need a guarantee of stability, but what I am seeing is that
we're consisitently dropping entries on when doing a multi-part
netlink walk. We start iterating over the table filling in the netlink
info. But eventually the netlink info fills up and returns an error.
netlink dump gets called again but now the iter of the table returns
the object following the one that would have overflowed the netlink
buffer. So the result I was seeing is that we dropped one object in in
each pass.
This fixes the nldump for ila which will be in a follow on patch set.
In pseudo code it looks something like this:
rhashtable_walk_start(rhiter);
/* Get first entty */
ila = rhashtable_walk_peek(rhiter);
while (ila) {
if (ila_dump_info(ila) < 0)
break;
ila = rhashtable_walk_next(rhiter);
}
rhashtable_walk_stop(rhiter);
return;
So peek is only called one and we only advance iter once the current
entry is successfully processed.
Tom
> Thanks,
> --
> Email: Herbert Xu <herbert@gondor.apana.org.au>
> Home Page: http://gondor.apana.org.au/~herbert/
> PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH net-next 2/5] rhashtable: Add rhastable_walk_peek
From: Herbert Xu @ 2017-12-01 1:21 UTC (permalink / raw)
To: Tom Herbert
Cc: David S . Miller, Linux Kernel Network Developers, Rohit LastName
In-Reply-To: <CAPDqMeoWg_mvTnMJscbSWxnm4kA2h28Ggxn4zjYzTm_RccMi0g@mail.gmail.com>
On Thu, Nov 30, 2017 at 05:15:16PM -0800, Tom Herbert wrote:
>
> We don't need a guarantee of stability, but what I am seeing is that
> we're consisitently dropping entries on when doing a multi-part
> netlink walk. We start iterating over the table filling in the netlink
> info. But eventually the netlink info fills up and returns an error.
> netlink dump gets called again but now the iter of the table returns
> the object following the one that would have overflowed the netlink
> buffer. So the result I was seeing is that we dropped one object in in
> each pass.
Thanks Tom! This information is very useful.
It sounds like this problem isn't specific to ila and would exist
for all rhashtable users that dump through netlink. Let me think
about this a little bit more.
Cheers,
--
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
From: Al Viro @ 2017-12-01 1:33 UTC (permalink / raw)
To: Kees Cook
Cc: Shmulik Ladkani, Willem de Bruijn, Daniel Borkmann,
Pablo Neira Ayuso, Linus Torvalds, David Miller, LKML,
Network Development, Christoph Hellwig, Thomas Garnier, Jann Horn
In-Reply-To: <CAGXu5j+ZCJ8rRK=DAKaeuNmGzVY7xo1o9uJyWPEijmg9gw4fKA@mail.gmail.com>
On Thu, Nov 30, 2017 at 04:57:30PM -0800, Kees Cook wrote:
> On Mon, Oct 9, 2017 at 4:10 PM, David Miller <davem@davemloft.net> wrote:
> > Shmulik Ladkani (1):
> > netfilter: xt_bpf: Fix XT_BPF_MODE_FD_PINNED mode of 'xt_bpf_info_v1'
>
> This adds a new user of set_fs(), which we're trying to eliminate (or
> at least not expand):
>
> + set_fs(KERNEL_DS);
> + fd = bpf_obj_get_user(path);
> + set_fs(oldfs);
>
> Can you please adjust this to not make set_fs() changes?
That's not the worst problem there. Messing with descriptor table is much
worse. It can be shared between threads; by the time you get to fdget()
the damn thing might have nothing to do with what bpf_obj_get_user() has
put there, ditto for sys_close().
Use of file descriptors should be limited to "got a number from userland,
convert to struct file *" on the way in and "install struct file * into
descriptor table and return the descriptor to userland" on the way out.
And the latter - *ONLY* after the last possible point of failure. Once
a file reference is inserted into descriptor table, that's it - you
can't undo that.
The only way to use bpf_obj_get_user() is to pass its return value to
userland. As return value of syscall - not even put_user() (for that
you'd need to reserve the descriptor, copy it to userland and only
then attach struct file * to it).
The whole approach stinks - what it needs is something that would
take struct filename * and return struct bpf_prog * or struct file *
reference. With bpf_obj_get_user() and this thing implemented
via that.
I'm looking into that thing...
^ permalink raw reply
* [PATCH net-next v2 0/8] xdp: make stack perform remove and tests
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
Hi!
The purpose of this series is to add a software model of BPF offloads
to make it easier for everyone to test them and make some of the more
arcane rules and assumptions more clear.
The series starts with 3 patches aiming to make XDP handling in the
drivers less error prone. Currently driver authors have to remember
to free XDP programs if XDP is active during unregister. With this
series the core will disable XDP on its own. It will take place
after close, drivers are not expected to perform reconfiguration
when disabling XDP on a downed device.
Next two patches add the software netdev driver, followed by a python
test which exercises all the corner cases which came to my mind.
Test needs to be run as root. It will print basic information to
stdout, but can also create a more detailed log of all commands
when --log option is passed. Log is in Emacs Org-mode format.
./tools/testing/selftests/bpf/test_offload.py --log /tmp/log
Last two patches replace the SR-IOV API implementation of dummy.
v2:
- free device from the release function;
- use bus-based name generatin instead of netdev name.
v1:
- replace the SR-IOV API implementation of dummy;
- make the dev_xdp_uninstall() also handle the XDP generic (Daniel).
Jakub Kicinski (8):
net: xdp: avoid output parameters when querying XDP prog
net: xdp: report flags program was installed with on query
net: xdp: make the stack take care of the tear down
netdevsim: add software driver for testing offloads
netdevsim: add bpf offload support
selftests/bpf: add offload test based on netdevsim
netdevsim: add SR-IOV functionality
net: dummy: remove fake SR-IOV functionality
MAINTAINERS | 5 +
drivers/net/Kconfig | 11 +
drivers/net/Makefile | 1 +
drivers/net/dummy.c | 215 +------
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 -
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 -
drivers/net/ethernet/netronome/nfp/bpf/main.c | 7 -
.../net/ethernet/netronome/nfp/nfp_net_common.c | 4 +-
drivers/net/ethernet/qlogic/qede/qede_main.c | 4 -
drivers/net/netdevsim/Makefile | 7 +
drivers/net/netdevsim/bpf.c | 373 +++++++++++
drivers/net/netdevsim/netdev.c | 501 +++++++++++++++
drivers/net/netdevsim/netdevsim.h | 78 +++
drivers/net/tun.c | 4 -
include/linux/netdevice.h | 5 +-
net/core/dev.c | 53 +-
net/core/rtnetlink.c | 6 +-
tools/testing/selftests/bpf/Makefile | 5 +-
tools/testing/selftests/bpf/sample_ret0.c | 7 +
tools/testing/selftests/bpf/test_offload.py | 681 +++++++++++++++++++++
20 files changed, 1714 insertions(+), 258 deletions(-)
create mode 100644 drivers/net/netdevsim/Makefile
create mode 100644 drivers/net/netdevsim/bpf.c
create mode 100644 drivers/net/netdevsim/netdev.c
create mode 100644 drivers/net/netdevsim/netdevsim.h
create mode 100644 tools/testing/selftests/bpf/sample_ret0.c
create mode 100755 tools/testing/selftests/bpf/test_offload.py
--
2.14.1
^ permalink raw reply
* [PATCH net-next v2 1/8] net: xdp: avoid output parameters when querying XDP prog
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
The output parameters will get unwieldy if we want to add more
information about the program. Simply pass the entire
struct netdev_bpf in.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
include/linux/netdevice.h | 3 ++-
net/core/dev.c | 24 ++++++++++++++----------
net/core/rtnetlink.c | 6 +++++-
3 files changed, 21 insertions(+), 12 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef789e1d679e..667bdd3ad33e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3330,7 +3330,8 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
int fd, u32 flags);
-u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t xdp_op, u32 *prog_id);
+void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
+ struct netdev_bpf *xdp);
int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 07ed21d64f92..3f271c9cb5e0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7073,17 +7073,21 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
}
EXPORT_SYMBOL(dev_change_proto_down);
-u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id)
+void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
+ struct netdev_bpf *xdp)
{
- struct netdev_bpf xdp;
-
- memset(&xdp, 0, sizeof(xdp));
- xdp.command = XDP_QUERY_PROG;
+ memset(xdp, 0, sizeof(*xdp));
+ xdp->command = XDP_QUERY_PROG;
/* Query must always succeed. */
- WARN_ON(bpf_op(dev, &xdp) < 0);
- if (prog_id)
- *prog_id = xdp.prog_id;
+ WARN_ON(bpf_op(dev, xdp) < 0);
+}
+
+static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
+{
+ struct netdev_bpf xdp;
+
+ __dev_xdp_query(dev, bpf_op, &xdp);
return xdp.prog_attached;
}
@@ -7134,10 +7138,10 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
bpf_chk = generic_xdp_install;
if (fd >= 0) {
- if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL))
+ if (bpf_chk && __dev_xdp_attached(dev, bpf_chk))
return -EEXIST;
if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
- __dev_xdp_attached(dev, bpf_op, NULL))
+ __dev_xdp_attached(dev, bpf_op))
return -EBUSY;
prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index dabba2a91fc8..9c4cb584bfb0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1261,6 +1261,7 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
{
const struct net_device_ops *ops = dev->netdev_ops;
const struct bpf_prog *generic_xdp_prog;
+ struct netdev_bpf xdp;
ASSERT_RTNL();
@@ -1273,7 +1274,10 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
if (!ops->ndo_bpf)
return XDP_ATTACHED_NONE;
- return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id);
+ __dev_xdp_query(dev, ops->ndo_bpf, &xdp);
+ *prog_id = xdp.prog_id;
+
+ return xdp.prog_attached;
}
static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 2/8] net: xdp: report flags program was installed with on query
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
Some drivers enforce that flags on program replacement and
removal must match the flags passed on install. This leaves
the possibility open to enable simultaneous loading
of XDP programs both to HW and DRV.
Allow such drivers to report the flags back to the stack.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 1 +
include/linux/netdevice.h | 2 ++
2 files changed, 3 insertions(+)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 1a603fdd9e80..ea6bbf1efefc 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3392,6 +3392,7 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
if (nn->dp.bpf_offload_xdp)
xdp->prog_attached = XDP_ATTACHED_HW;
xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
+ xdp->flags = nn->xdp_prog ? nn->xdp_flags : 0;
return 0;
case BPF_OFFLOAD_VERIFIER_PREP:
return nfp_app_bpf_verifier_prep(nn->app, nn, xdp);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 667bdd3ad33e..cc4ce7456e38 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -820,6 +820,8 @@ struct netdev_bpf {
struct {
u8 prog_attached;
u32 prog_id;
+ /* flags with which program was installed */
+ u32 prog_flags;
};
/* BPF_OFFLOAD_VERIFIER_PREP */
struct {
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 3/8] net: xdp: make the stack take care of the tear down
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev
Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski, Saeed Mahameed, Michael Chan, Ariel Elior,
John Fastabend
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
Since day one of XDP drivers had to remember to free the program
on the remove path. This leads to code duplication and is error
prone. Make the stack query the installed programs on unregister
and if something is installed, remove the program. Freeing of
program attached to XDP generic is moved from free_netdev() as well.
Because the remove will now be called before notifiers are
invoked, BPF offload state of the program will not get destroyed
before uninstall.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
CC: Saeed Mahameed <saeedm@mellanox.com>
CC: Michael Chan <michael.chan@broadcom.com>
CC: Ariel Elior <Ariel.Elior@cavium.com>
CC: John Fastabend <john.fastabend@gmail.com>
---
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 --
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 ---
drivers/net/ethernet/netronome/nfp/bpf/main.c | 7 ------
.../net/ethernet/netronome/nfp/nfp_net_common.c | 3 ---
drivers/net/ethernet/qlogic/qede/qede_main.c | 4 ---
drivers/net/tun.c | 4 ---
net/core/dev.c | 29 ++++++++++++++++------
7 files changed, 22 insertions(+), 30 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 33c49ad697e4..413ad2444ba2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7800,8 +7800,6 @@ static void bnxt_remove_one(struct pci_dev *pdev)
bnxt_dcb_free(bp);
kfree(bp->edev);
bp->edev = NULL;
- if (bp->xdp_prog)
- bpf_prog_put(bp->xdp_prog);
bnxt_cleanup_pci(bp);
free_netdev(dev);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d2b057a3e512..0f5c012de52e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4308,9 +4308,6 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
{
mlx5e_ipsec_cleanup(priv);
mlx5e_vxlan_cleanup(priv);
-
- if (priv->channels.params.xdp_prog)
- bpf_prog_put(priv->channels.params.xdp_prog);
}
static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index e379b78e86ef..54bfd7846f6d 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -82,12 +82,6 @@ static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
return nfp_net_ebpf_capable(nn) ? "BPF" : "";
}
-static void nfp_bpf_vnic_free(struct nfp_app *app, struct nfp_net *nn)
-{
- if (nn->dp.bpf_offload_xdp)
- nfp_bpf_xdp_offload(app, nn, NULL);
-}
-
static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
void *type_data, void *cb_priv)
{
@@ -168,7 +162,6 @@ const struct nfp_app_type app_bpf = {
.extra_cap = nfp_bpf_extra_cap,
.vnic_alloc = nfp_app_nic_vnic_alloc,
- .vnic_free = nfp_bpf_vnic_free,
.setup_tc = nfp_bpf_setup_tc,
.tc_busy = nfp_bpf_tc_busy,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index ea6bbf1efefc..ad3e9f6a61e5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3562,9 +3562,6 @@ struct nfp_net *nfp_net_alloc(struct pci_dev *pdev, bool needs_netdev,
*/
void nfp_net_free(struct nfp_net *nn)
{
- if (nn->xdp_prog)
- bpf_prog_put(nn->xdp_prog);
-
if (nn->dp.netdev)
free_netdev(nn->dp.netdev);
else
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 8f9b3eb82137..57332b3e5e64 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -1068,10 +1068,6 @@ static void __qede_remove(struct pci_dev *pdev, enum qede_remove_mode mode)
pci_set_drvdata(pdev, NULL);
- /* Release edev's reference to XDP's bpf if such exist */
- if (edev->xdp_prog)
- bpf_prog_put(edev->xdp_prog);
-
/* Use global ops since we've freed edev */
qed_ops->common->slowpath_stop(cdev);
if (system_state == SYSTEM_POWER_OFF)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 6a7bde9bc4b2..6f7e8e45c961 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -673,7 +673,6 @@ static void tun_detach(struct tun_file *tfile, bool clean)
static void tun_detach_all(struct net_device *dev)
{
struct tun_struct *tun = netdev_priv(dev);
- struct bpf_prog *xdp_prog = rtnl_dereference(tun->xdp_prog);
struct tun_file *tfile, *tmp;
int i, n = tun->numqueues;
@@ -708,9 +707,6 @@ static void tun_detach_all(struct net_device *dev)
}
BUG_ON(tun->numdisabled != 0);
- if (xdp_prog)
- bpf_prog_put(xdp_prog);
-
if (tun->flags & IFF_PERSIST)
module_put(THIS_MODULE);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 3f271c9cb5e0..6bea8931bb62 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7110,6 +7110,27 @@ static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
return bpf_op(dev, &xdp);
}
+static void dev_xdp_uninstall(struct net_device *dev)
+{
+ struct netdev_bpf xdp;
+ bpf_op_t ndo_bpf;
+
+ /* Remove generic XDP */
+ WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL));
+
+ /* Remove from the driver */
+ ndo_bpf = dev->netdev_ops->ndo_bpf;
+ if (!ndo_bpf)
+ return;
+
+ __dev_xdp_query(dev, ndo_bpf, &xdp);
+ if (xdp.prog_attached == XDP_ATTACHED_NONE)
+ return;
+
+ /* Program removal should always succeed */
+ WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL));
+}
+
/**
* dev_change_xdp_fd - set or clear a bpf program for a device rx path
* @dev: device
@@ -7240,6 +7261,7 @@ static void rollback_registered_many(struct list_head *head)
/* Shutdown queueing discipline. */
dev_shutdown(dev);
+ dev_xdp_uninstall(dev);
/* Notify protocols, that we are about to destroy
* this device. They should clean all the things.
@@ -8199,7 +8221,6 @@ EXPORT_SYMBOL(alloc_netdev_mqs);
void free_netdev(struct net_device *dev)
{
struct napi_struct *p, *n;
- struct bpf_prog *prog;
might_sleep();
netif_free_tx_queues(dev);
@@ -8218,12 +8239,6 @@ void free_netdev(struct net_device *dev)
free_percpu(dev->pcpu_refcnt);
dev->pcpu_refcnt = NULL;
- prog = rcu_dereference_protected(dev->xdp_prog, 1);
- if (prog) {
- bpf_prog_put(prog);
- static_key_slow_dec(&generic_xdp_needed);
- }
-
/* Compatibility with error handling in drivers */
if (dev->reg_state == NETREG_UNINITIALIZED) {
netdev_freemem(dev);
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 4/8] netdevsim: add software driver for testing offloads
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
To be able to run selftests without any hardware required we
need a software model. The model can also serve as an example
implementation for those implementing actual HW offloads.
The dummy driver have previously been extended to test SR-IOV,
but the general consensus seems to be against adding further
features to it.
Add a new driver for purposes of software modelling only.
eBPF and SR-IOV will be added here shortly, others are invited
to further extend the driver with their offload models.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
MAINTAINERS | 5 ++
drivers/net/Kconfig | 11 ++++
drivers/net/Makefile | 1 +
drivers/net/netdevsim/Makefile | 6 ++
drivers/net/netdevsim/netdev.c | 118 ++++++++++++++++++++++++++++++++++++++
drivers/net/netdevsim/netdevsim.h | 26 +++++++++
6 files changed, 167 insertions(+)
create mode 100644 drivers/net/netdevsim/Makefile
create mode 100644 drivers/net/netdevsim/netdev.c
create mode 100644 drivers/net/netdevsim/netdevsim.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 77d819b458a9..010e46a38373 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9599,6 +9599,11 @@ NETWORKING [WIRELESS]
L: linux-wireless@vger.kernel.org
Q: http://patchwork.kernel.org/project/linux-wireless/list/
+NETDEVSIM
+M: Jakub Kicinski <jakub.kicinski@netronome.com>
+S: Maintained
+F: drivers/net/netdevsim/*
+
NETXEN (1/10) GbE SUPPORT
M: Manish Chopra <manish.chopra@cavium.com>
M: Rahul Verma <rahul.verma@cavium.com>
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 0936da592e12..944ec3c9282c 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -497,4 +497,15 @@ config THUNDERBOLT_NET
source "drivers/net/hyperv/Kconfig"
+config NETDEVSIM
+ tristate "Simulated networking device"
+ depends on DEBUG_FS
+ help
+ This driver is a developer testing tool and software model that can
+ be used to test various control path networking APIs, especially
+ HW-offload related.
+
+ To compile this driver as a module, choose M here: the module
+ will be called netdevsim.
+
endif # NETDEVICES
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 766f62d02a0b..04c3b747812c 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -78,3 +78,4 @@ obj-$(CONFIG_FUJITSU_ES) += fjes/
thunderbolt-net-y += thunderbolt.o
obj-$(CONFIG_THUNDERBOLT_NET) += thunderbolt-net.o
+obj-$(CONFIG_NETDEVSIM) += netdevsim/
diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
new file mode 100644
index 000000000000..07867bfe873b
--- /dev/null
+++ b/drivers/net/netdevsim/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_NETDEVSIM) += netdevsim.o
+
+netdevsim-objs := \
+ netdev.o \
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
new file mode 100644
index 000000000000..7599c72c477a
--- /dev/null
+++ b/drivers/net/netdevsim/netdev.c
@@ -0,0 +1,118 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/slab.h>
+#include <net/netlink.h>
+#include <net/rtnetlink.h>
+
+#include "netdevsim.h"
+
+static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ u64_stats_update_begin(&ns->syncp);
+ ns->tx_packets++;
+ ns->tx_bytes += skb->len;
+ u64_stats_update_end(&ns->syncp);
+
+ dev_kfree_skb(skb);
+
+ return NETDEV_TX_OK;
+}
+
+static void nsim_set_rx_mode(struct net_device *dev)
+{
+}
+
+static void
+nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin(&ns->syncp);
+ stats->tx_bytes = ns->tx_bytes;
+ stats->tx_packets = ns->tx_packets;
+ } while (u64_stats_fetch_retry(&ns->syncp, start));
+}
+
+static const struct net_device_ops nsim_netdev_ops = {
+ .ndo_start_xmit = nsim_start_xmit,
+ .ndo_set_rx_mode = nsim_set_rx_mode,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_get_stats64 = nsim_get_stats64,
+};
+
+static void nsim_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+ eth_hw_addr_random(dev);
+
+ dev->netdev_ops = &nsim_netdev_ops;
+ dev->needs_free_netdev = true;
+
+ dev->tx_queue_len = 0;
+ dev->flags |= IFF_NOARP;
+ dev->flags &= ~IFF_MULTICAST;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE |
+ IFF_NO_QUEUE;
+ dev->features |= NETIF_F_HIGHDMA |
+ NETIF_F_SG |
+ NETIF_F_FRAGLIST |
+ NETIF_F_HW_CSUM |
+ NETIF_F_TSO;
+ dev->max_mtu = ETH_MAX_MTU;
+}
+
+static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
+ struct netlink_ext_ack *extack)
+{
+ if (tb[IFLA_ADDRESS]) {
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ return -EINVAL;
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ return -EADDRNOTAVAIL;
+ }
+ return 0;
+}
+
+static struct rtnl_link_ops nsim_link_ops __read_mostly = {
+ .kind = DRV_NAME,
+ .priv_size = sizeof(struct netdevsim),
+ .setup = nsim_setup,
+ .validate = nsim_validate,
+};
+
+static int __init nsim_module_init(void)
+{
+ return rtnl_link_register(&nsim_link_ops);
+}
+
+static void __exit nsim_module_exit(void)
+{
+ rtnl_link_unregister(&nsim_link_ops);
+}
+
+module_init(nsim_module_init);
+module_exit(nsim_module_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK(DRV_NAME);
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
new file mode 100644
index 000000000000..4558c6f11598
--- /dev/null
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/u64_stats_sync.h>
+
+#define DRV_NAME "netdevsim"
+
+struct netdevsim {
+ u64 tx_packets;
+ u64 tx_bytes;
+ struct u64_stats_sync syncp;
+};
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 5/8] netdevsim: add bpf offload support
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
Add support for loading programs for netdevsim devices and
expose the related information via DebugFS. Both offload
of XDP and cls_bpf programs is supported.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
drivers/net/netdevsim/Makefile | 1 +
drivers/net/netdevsim/bpf.c | 373 ++++++++++++++++++++++++++++++++++++++
drivers/net/netdevsim/netdev.c | 116 +++++++++++-
drivers/net/netdevsim/netdevsim.h | 40 ++++
4 files changed, 529 insertions(+), 1 deletion(-)
create mode 100644 drivers/net/netdevsim/bpf.c
diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
index 07867bfe873b..074ddebbc41d 100644
--- a/drivers/net/netdevsim/Makefile
+++ b/drivers/net/netdevsim/Makefile
@@ -4,3 +4,4 @@ obj-$(CONFIG_NETDEVSIM) += netdevsim.o
netdevsim-objs := \
netdev.o \
+ bpf.o \
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
new file mode 100644
index 000000000000..8e4398a50903
--- /dev/null
+++ b/drivers/net/netdevsim/bpf.c
@@ -0,0 +1,373 @@
+/*
+ * Copyright (C) 2017 Netronome Systems, Inc.
+ *
+ * This software is licensed under the GNU General License Version 2,
+ * June 1991 as shown in the file COPYING in the top-level directory of this
+ * source tree.
+ *
+ * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+ * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+ * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+ * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+ * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+ * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+ */
+
+#include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
+#include <linux/debugfs.h>
+#include <linux/kernel.h>
+#include <linux/rtnetlink.h>
+#include <net/pkt_cls.h>
+
+#include "netdevsim.h"
+
+struct nsim_bpf_bound_prog {
+ struct netdevsim *ns;
+ struct bpf_prog *prog;
+ struct dentry *ddir;
+ const char *state;
+ bool is_loaded;
+ struct list_head l;
+};
+
+static int nsim_debugfs_bpf_string_read(struct seq_file *file, void *data)
+{
+ const char **str = file->private;
+
+ if (*str)
+ seq_printf(file, "%s\n", *str);
+
+ return 0;
+}
+
+static int nsim_debugfs_bpf_string_open(struct inode *inode, struct file *f)
+{
+ return single_open(f, nsim_debugfs_bpf_string_read, inode->i_private);
+}
+
+static const struct file_operations nsim_bpf_string_fops = {
+ .owner = THIS_MODULE,
+ .open = nsim_debugfs_bpf_string_open,
+ .release = single_release,
+ .read = seq_read,
+ .llseek = seq_lseek
+};
+
+static int
+nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn)
+{
+ struct nsim_bpf_bound_prog *state;
+
+ state = env->prog->aux->offload->dev_priv;
+ if (state->ns->bpf_bind_verifier_delay && !insn_idx)
+ msleep(state->ns->bpf_bind_verifier_delay);
+
+ return 0;
+}
+
+static const struct bpf_ext_analyzer_ops nsim_bpf_analyzer_ops = {
+ .insn_hook = nsim_bpf_verify_insn,
+};
+
+static bool nsim_xdp_offload_active(struct netdevsim *ns)
+{
+ return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+}
+
+static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
+{
+ struct nsim_bpf_bound_prog *state;
+
+ if (!prog || !prog->aux->offload)
+ return;
+
+ state = prog->aux->offload->dev_priv;
+ state->is_loaded = loaded;
+}
+
+static int
+nsim_bpf_offload(struct netdevsim *ns, struct bpf_prog *prog, bool oldprog)
+{
+ nsim_prog_set_loaded(ns->bpf_offloaded, false);
+
+ WARN(!!ns->bpf_offloaded != oldprog,
+ "bad offload state, expected offload %sto be active",
+ oldprog ? "" : "not ");
+ ns->bpf_offloaded = prog;
+ ns->bpf_offloaded_id = prog ? prog->aux->id : 0;
+ nsim_prog_set_loaded(prog, true);
+
+ return 0;
+}
+
+int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type,
+ void *type_data, void *cb_priv)
+{
+ struct tc_cls_bpf_offload *cls_bpf = type_data;
+ struct bpf_prog *prog = cls_bpf->prog;
+ struct netdevsim *ns = cb_priv;
+ bool skip_sw;
+
+ if (type != TC_SETUP_CLSBPF ||
+ !tc_can_offload(ns->netdev) ||
+ cls_bpf->common.protocol != htons(ETH_P_ALL) ||
+ cls_bpf->common.chain_index)
+ return -EOPNOTSUPP;
+
+ skip_sw = cls_bpf->gen_flags & TCA_CLS_FLAGS_SKIP_SW;
+
+ if (nsim_xdp_offload_active(ns))
+ return -EBUSY;
+
+ if (!ns->bpf_tc_accept)
+ return -EOPNOTSUPP;
+ /* Note: progs without skip_sw will probably not be dev bound */
+ if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept)
+ return -EOPNOTSUPP;
+
+ switch (cls_bpf->command) {
+ case TC_CLSBPF_REPLACE:
+ return nsim_bpf_offload(ns, prog, true);
+ case TC_CLSBPF_ADD:
+ return nsim_bpf_offload(ns, prog, false);
+ case TC_CLSBPF_DESTROY:
+ return nsim_bpf_offload(ns, NULL, true);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+int nsim_bpf_disable_tc(struct netdevsim *ns)
+{
+ if (ns->bpf_offloaded && !nsim_xdp_offload_active(ns))
+ return -EBUSY;
+ return 0;
+}
+
+static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+ if (!nsim_xdp_offload_active(ns) && !bpf->prog)
+ return 0;
+ if (!nsim_xdp_offload_active(ns) && bpf->prog && ns->bpf_offloaded) {
+ NSIM_EA(bpf->extack, "TC program is already loaded");
+ return -EBUSY;
+ }
+
+ return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
+}
+
+static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+ int err;
+
+ if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
+ NSIM_EA(bpf->extack, "program loaded with different flags");
+ return -EBUSY;
+ }
+
+ if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
+ NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
+ return -EOPNOTSUPP;
+ }
+ if (bpf->command == XDP_SETUP_PROG_HW && !ns->bpf_xdpoffload_accept) {
+ NSIM_EA(bpf->extack, "XDP offload disabled in DebugFS");
+ return -EOPNOTSUPP;
+ }
+
+ if (bpf->command == XDP_SETUP_PROG_HW) {
+ err = nsim_xdp_offload_prog(ns, bpf);
+ if (err)
+ return err;
+ }
+
+ if (ns->xdp_prog)
+ bpf_prog_put(ns->xdp_prog);
+
+ ns->xdp_prog = bpf->prog;
+ ns->xdp_flags = bpf->flags;
+
+ if (!bpf->prog)
+ ns->xdp_prog_mode = XDP_ATTACHED_NONE;
+ else if (bpf->command == XDP_SETUP_PROG)
+ ns->xdp_prog_mode = XDP_ATTACHED_DRV;
+ else
+ ns->xdp_prog_mode = XDP_ATTACHED_HW;
+
+ return 0;
+}
+
+int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
+{
+ struct nsim_bpf_bound_prog *state;
+ char name[16];
+ int err;
+
+ state = kzalloc(sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ state->ns = ns;
+ state->prog = prog;
+ state->state = "verify";
+
+ /* Program id is not populated yet when we create the state. */
+ sprintf(name, "%u", ns->prog_id_gen++);
+ state->ddir = debugfs_create_dir(name, ns->ddir_bpf_bound_progs);
+ if (IS_ERR(state->ddir)) {
+ err = PTR_ERR(state->ddir);
+ kfree(state);
+ return err;
+ }
+
+ debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id);
+ debugfs_create_file("state", 0400, state->ddir,
+ &state->state, &nsim_bpf_string_fops);
+ debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
+
+ list_add_tail(&state->l, &ns->bpf_bound_progs);
+
+ prog->aux->offload->dev_priv = state;
+
+ return 0;
+}
+
+void nsim_bpf_destroy_prog(struct bpf_prog *prog)
+{
+ struct nsim_bpf_bound_prog *state;
+
+ state = prog->aux->offload->dev_priv;
+ WARN(state->is_loaded,
+ "offload state destroyed while program still bound");
+ debugfs_remove_recursive(state->ddir);
+ list_del(&state->l);
+ kfree(state);
+}
+
+static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+ if (bpf->prog && bpf->prog->aux->offload) {
+ NSIM_EA(bpf->extack, "attempt to load offloaded prog to drv");
+ return -EINVAL;
+ }
+ if (ns->netdev->mtu > NSIM_XDP_MAX_MTU) {
+ NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
+ return -EINVAL;
+ }
+ if (nsim_xdp_offload_active(ns)) {
+ NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
+ return -EBUSY;
+ }
+ return 0;
+}
+
+static int
+nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
+{
+ struct nsim_bpf_bound_prog *state;
+
+ if (!bpf->prog)
+ return 0;
+
+ if (!bpf->prog->aux->offload) {
+ NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
+ return -EINVAL;
+ }
+ if (bpf->prog->aux->offload->netdev != ns->netdev) {
+ NSIM_EA(bpf->extack, "program bound to different dev");
+ return -EINVAL;
+ }
+
+ state = bpf->prog->aux->offload->dev_priv;
+ if (WARN_ON(strcmp(state->state, "xlated"))) {
+ NSIM_EA(bpf->extack, "offloading program in bad state");
+ return -EINVAL;
+ }
+ return 0;
+}
+
+int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+ struct nsim_bpf_bound_prog *state;
+ int err;
+
+ ASSERT_RTNL();
+
+ switch (bpf->command) {
+ case BPF_OFFLOAD_VERIFIER_PREP:
+ if (!ns->bpf_bind_accept)
+ return -EOPNOTSUPP;
+
+ err = nsim_bpf_create_prog(ns, bpf->verifier.prog);
+ if (err)
+ return err;
+
+ bpf->verifier.ops = &nsim_bpf_analyzer_ops;
+ return 0;
+ case BPF_OFFLOAD_TRANSLATE:
+ state = bpf->offload.prog->aux->offload->dev_priv;
+
+ state->state = "xlated";
+ return 0;
+ case BPF_OFFLOAD_DESTROY:
+ nsim_bpf_destroy_prog(bpf->offload.prog);
+ return 0;
+ case XDP_QUERY_PROG:
+ bpf->prog_attached = ns->xdp_prog_mode;
+ bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
+ bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
+ return 0;
+ case XDP_SETUP_PROG:
+ err = nsim_setup_prog_checks(ns, bpf);
+ if (err)
+ return err;
+
+ return nsim_xdp_set_prog(ns, bpf);
+ case XDP_SETUP_PROG_HW:
+ err = nsim_setup_prog_hw_checks(ns, bpf);
+ if (err)
+ return err;
+
+ return nsim_xdp_set_prog(ns, bpf);
+ default:
+ return -EINVAL;
+ }
+}
+
+int nsim_bpf_init(struct netdevsim *ns)
+{
+ INIT_LIST_HEAD(&ns->bpf_bound_progs);
+
+ debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
+ &ns->bpf_offloaded_id);
+
+ ns->bpf_bind_accept = true;
+ debugfs_create_bool("bpf_bind_accept", 0600, ns->ddir,
+ &ns->bpf_bind_accept);
+ debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
+ &ns->bpf_bind_verifier_delay);
+ ns->ddir_bpf_bound_progs =
+ debugfs_create_dir("bpf_bound_progs", ns->ddir);
+
+ ns->bpf_tc_accept = true;
+ debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
+ &ns->bpf_tc_accept);
+ debugfs_create_bool("bpf_tc_non_bound_accept", 0600, ns->ddir,
+ &ns->bpf_tc_non_bound_accept);
+ ns->bpf_xdpdrv_accept = true;
+ debugfs_create_bool("bpf_xdpdrv_accept", 0600, ns->ddir,
+ &ns->bpf_xdpdrv_accept);
+ ns->bpf_xdpoffload_accept = true;
+ debugfs_create_bool("bpf_xdpoffload_accept", 0600, ns->ddir,
+ &ns->bpf_xdpoffload_accept);
+
+ return 0;
+}
+
+void nsim_bpf_uninit(struct netdevsim *ns)
+{
+ WARN_ON(!list_empty(&ns->bpf_bound_progs));
+ WARN_ON(ns->xdp_prog);
+ WARN_ON(ns->bpf_offloaded);
+}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 7599c72c477a..828c1ce49a8b 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -13,16 +13,45 @@
* THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
*/
+#include <linux/debugfs.h>
#include <linux/etherdevice.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/netlink.h>
+#include <net/pkt_cls.h>
#include <net/rtnetlink.h>
#include "netdevsim.h"
+static int nsim_init(struct net_device *dev)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+ int err;
+
+ ns->netdev = dev;
+ ns->ddir = debugfs_create_dir(netdev_name(dev), nsim_ddir);
+
+ err = nsim_bpf_init(ns);
+ if (err)
+ goto err_debugfs_destroy;
+
+ return 0;
+
+err_debugfs_destroy:
+ debugfs_remove_recursive(ns->ddir);
+ return err;
+}
+
+static void nsim_uninit(struct net_device *dev)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ debugfs_remove_recursive(ns->ddir);
+ nsim_bpf_uninit(ns);
+}
+
static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct netdevsim *ns = netdev_priv(dev);
@@ -41,6 +70,19 @@ static void nsim_set_rx_mode(struct net_device *dev)
{
}
+static int nsim_change_mtu(struct net_device *dev, int new_mtu)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
+ new_mtu > NSIM_XDP_MAX_MTU)
+ return -EBUSY;
+
+ dev->mtu = new_mtu;
+
+ return 0;
+}
+
static void
nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
{
@@ -54,12 +96,66 @@ nsim_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats)
} while (u64_stats_fetch_retry(&ns->syncp, start));
}
+static int
+nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
+{
+ return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
+}
+
+static int
+nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ return -EOPNOTSUPP;
+
+ switch (f->command) {
+ case TC_BLOCK_BIND:
+ return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
+ ns, ns);
+ case TC_BLOCK_UNBIND:
+ tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int
+nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
+{
+ switch (type) {
+ case TC_SETUP_BLOCK:
+ return nsim_setup_tc_block(dev, type_data);
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
+static int
+nsim_set_features(struct net_device *dev, netdev_features_t features)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if ((dev->features & NETIF_F_HW_TC) > (features & NETIF_F_HW_TC))
+ return nsim_bpf_disable_tc(ns);
+
+ return 0;
+}
+
static const struct net_device_ops nsim_netdev_ops = {
+ .ndo_init = nsim_init,
+ .ndo_uninit = nsim_uninit,
.ndo_start_xmit = nsim_start_xmit,
.ndo_set_rx_mode = nsim_set_rx_mode,
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = nsim_change_mtu,
.ndo_get_stats64 = nsim_get_stats64,
+ .ndo_setup_tc = nsim_setup_tc,
+ .ndo_set_features = nsim_set_features,
+ .ndo_bpf = nsim_bpf,
};
static void nsim_setup(struct net_device *dev)
@@ -80,6 +176,7 @@ static void nsim_setup(struct net_device *dev)
NETIF_F_FRAGLIST |
NETIF_F_HW_CSUM |
NETIF_F_TSO;
+ dev->hw_features |= NETIF_F_HW_TC;
dev->max_mtu = ETH_MAX_MTU;
}
@@ -102,14 +199,31 @@ static struct rtnl_link_ops nsim_link_ops __read_mostly = {
.validate = nsim_validate,
};
+struct dentry *nsim_ddir;
+
static int __init nsim_module_init(void)
{
- return rtnl_link_register(&nsim_link_ops);
+ int err;
+
+ nsim_ddir = debugfs_create_dir(DRV_NAME, NULL);
+ if (IS_ERR(nsim_ddir))
+ return PTR_ERR(nsim_ddir);
+
+ err = rtnl_link_register(&nsim_link_ops);
+ if (err)
+ goto err_debugfs_destroy;
+
+ return 0;
+
+err_debugfs_destroy:
+ debugfs_remove_recursive(nsim_ddir);
+ return err;
}
static void __exit nsim_module_exit(void)
{
rtnl_link_unregister(&nsim_link_ops);
+ debugfs_remove_recursive(nsim_ddir);
}
module_init(nsim_module_init);
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 4558c6f11598..8779e6a8f885 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -14,13 +14,53 @@
*/
#include <linux/kernel.h>
+#include <linux/list.h>
#include <linux/netdevice.h>
#include <linux/u64_stats_sync.h>
#define DRV_NAME "netdevsim"
+#define NSIM_XDP_MAX_MTU 4000
+
+#define NSIM_EA(extack, msg) NL_SET_ERR_MSG_MOD((extack), msg)
+
+struct bpf_prog;
+struct dentry;
+
struct netdevsim {
+ struct net_device *netdev;
+
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
+
+ struct dentry *ddir;
+
+ struct bpf_prog *bpf_offloaded;
+ u32 bpf_offloaded_id;
+
+ u32 xdp_flags;
+ int xdp_prog_mode;
+ struct bpf_prog *xdp_prog;
+
+ u32 prog_id_gen;
+
+ bool bpf_bind_accept;
+ u32 bpf_bind_verifier_delay;
+ struct dentry *ddir_bpf_bound_progs;
+ struct list_head bpf_bound_progs;
+
+ bool bpf_tc_accept;
+ bool bpf_tc_non_bound_accept;
+ bool bpf_xdpdrv_accept;
+ bool bpf_xdpoffload_accept;
};
+
+extern struct dentry *nsim_ddir;
+
+int nsim_bpf_init(struct netdevsim *ns);
+void nsim_bpf_uninit(struct netdevsim *ns);
+int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf);
+int nsim_bpf_disable_tc(struct netdevsim *ns);
+int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type,
+ void *type_data, void *cb_priv);
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 6/8] selftests/bpf: add offload test based on netdevsim
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev; +Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
Add a test of BPF offload control path interfaces based on
just-added netdevsim driver. Perform various checks of both
the stack and the expected driver behaviour.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
tools/testing/selftests/bpf/Makefile | 5 +-
tools/testing/selftests/bpf/sample_ret0.c | 7 +
tools/testing/selftests/bpf/test_offload.py | 681 ++++++++++++++++++++++++++++
3 files changed, 691 insertions(+), 2 deletions(-)
create mode 100644 tools/testing/selftests/bpf/sample_ret0.c
create mode 100755 tools/testing/selftests/bpf/test_offload.py
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 333a48655ee0..2c9d8c63c6fa 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -17,9 +17,10 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \
- sockmap_verdict_prog.o dev_cgroup.o
+ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o
-TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh
+TEST_PROGS := test_kmod.sh test_xdp_redirect.sh test_xdp_meta.sh \
+ test_offload.py
include ../lib.mk
diff --git a/tools/testing/selftests/bpf/sample_ret0.c b/tools/testing/selftests/bpf/sample_ret0.c
new file mode 100644
index 000000000000..fec99750d6ea
--- /dev/null
+++ b/tools/testing/selftests/bpf/sample_ret0.c
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause) */
+
+/* Sample program which should always load for testing control paths. */
+int func()
+{
+ return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
new file mode 100755
index 000000000000..3914f7a4585a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -0,0 +1,681 @@
+#!/usr/bin/python3
+
+# Copyright (C) 2017 Netronome Systems, Inc.
+#
+# This software is licensed under the GNU General License Version 2,
+# June 1991 as shown in the file COPYING in the top-level directory of this
+# source tree.
+#
+# THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS"
+# WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING,
+# BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
+# FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE
+# OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME
+# THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+from datetime import datetime
+import argparse
+import json
+import os
+import pprint
+import subprocess
+import time
+
+logfile = None
+log_level = 1
+bpf_test_dir = os.path.dirname(os.path.realpath(__file__))
+pp = pprint.PrettyPrinter()
+devs = [] # devices we created for clean up
+files = [] # files to be removed
+
+def log_get_sec(level=0):
+ return "*" * (log_level + level)
+
+def log_level_inc(add=1):
+ global log_level
+ log_level += add
+
+def log_level_dec(sub=1):
+ global log_level
+ log_level -= sub
+
+def log_level_set(level):
+ global log_level
+ log_level = level
+
+def log(header, data, level=None):
+ """
+ Output to an optional log.
+ """
+ if logfile is None:
+ return
+ if level is not None:
+ log_level_set(level)
+
+ if not isinstance(data, str):
+ data = pp.pformat(data)
+
+ if len(header):
+ logfile.write("\n" + log_get_sec() + " ")
+ logfile.write(header)
+ if len(header) and len(data.strip()):
+ logfile.write("\n")
+ logfile.write(data)
+
+def skip(cond, msg):
+ if not cond:
+ return
+ print("SKIP: " + msg)
+ log("SKIP: " + msg, "", level=1)
+ os.sys.exit(0)
+
+def fail(cond, msg):
+ if not cond:
+ return
+ print("FAIL: " + msg)
+ log("FAIL: " + msg, "", level=1)
+ os.sys.exit(1)
+
+def start_test(msg):
+ log(msg, "", level=1)
+ log_level_inc()
+ print(msg)
+
+def cmd(cmd, shell=True, include_stderr=False, background=False, fail=True):
+ """
+ Run a command in subprocess and return tuple of (retval, stdout);
+ optionally return stderr as well as third value.
+ """
+ proc = subprocess.Popen(cmd, shell=shell, stdout=subprocess.PIPE,
+ stderr=subprocess.PIPE)
+ if background:
+ msg = "%s START: %s" % (log_get_sec(1),
+ datetime.now().strftime("%H:%M:%S.%f"))
+ log("BKG " + proc.args, msg)
+ return proc
+
+ return cmd_result(proc, include_stderr=include_stderr, fail=fail)
+
+def cmd_result(proc, include_stderr=False, fail=False):
+ stdout, stderr = proc.communicate()
+ stdout = stdout.decode("utf-8")
+ stderr = stderr.decode("utf-8")
+ proc.stdout.close()
+ proc.stderr.close()
+
+ stderr = "\n" + stderr
+ if stderr[-1] == "\n":
+ stderr = stderr[:-1]
+
+ sec = log_get_sec(1)
+ log("CMD " + proc.args,
+ "RETCODE: %d\n%s STDOUT:\n%s%s STDERR:%s\n%s END: %s" %
+ (proc.returncode, sec, stdout, sec, stderr,
+ sec, datetime.now().strftime("%H:%M:%S.%f")))
+
+ if proc.returncode != 0 and fail:
+ if len(stderr) > 0 and stderr[-1] == "\n":
+ stderr = stderr[:-1]
+ raise Exception("Command failed: %s\n%s" % (proc.args, stderr))
+
+ if include_stderr:
+ return proc.returncode, stdout, stderr
+ else:
+ return proc.returncode, stdout
+
+def rm(f):
+ cmd("rm -f %s" % (f))
+ if f in files:
+ files.remove(f)
+
+def tool(name, args, flags, JSON=True, fail=True):
+ params = ""
+ if JSON:
+ params += "%s " % (flags["json"])
+
+ ret, out = cmd(name + " " + params + args, fail=fail)
+ if JSON and len(out.strip()) != 0:
+ return ret, json.loads(out)
+ else:
+ return ret, out
+
+def bpftool(args, JSON=True, fail=True):
+ return tool("bpftool", args, {"json":"-p"}, JSON=JSON, fail=fail)
+
+def bpftool_prog_list(expected=None):
+ _, progs = bpftool("prog show", JSON=True, fail=True)
+ if expected is not None:
+ if len(progs) != expected:
+ fail(True, "%d BPF programs loaded, expected %d" %
+ (len(progs), expected))
+ return progs
+
+def bpftool_prog_list_wait(expected=0, n_retry=20):
+ for i in range(n_retry):
+ nprogs = len(bpftool_prog_list())
+ if nprogs == expected:
+ return
+ time.sleep(0.05)
+ raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
+
+def ip(args, force=False, JSON=True, fail=True):
+ if force:
+ args = "-force " + args
+ return tool("ip", args, {"json":"-j"}, JSON=JSON, fail=fail)
+
+def tc(args, JSON=True, fail=True):
+ return tool("tc", args, {"json":"-p"}, JSON=JSON, fail=fail)
+
+def ethtool(dev, opt, args, fail=True):
+ return cmd("ethtool %s %s %s" % (opt, dev["ifname"], args), fail=fail)
+
+def bpf_obj(name, sec=".text", path=bpf_test_dir,):
+ return "obj %s sec %s" % (os.path.join(path, name), sec)
+
+def bpf_pinned(name):
+ return "pinned %s" % (name)
+
+def bpf_bytecode(bytecode):
+ return "bytecode \"%s\"" % (bytecode)
+
+class DebugfsDir:
+ """
+ Class for accessing DebugFS directories as a dictionary.
+ """
+
+ def __init__(self, path):
+ self.path = path
+ self._dict = self._debugfs_dir_read(path)
+
+ def __len__(self):
+ return len(self._dict.keys())
+
+ def __getitem__(self, key):
+ if type(key) is int:
+ key = list(self._dict.keys())[key]
+ return self._dict[key]
+
+ def __setitem__(self, key, value):
+ log("DebugFS set %s = %s" % (key, value), "")
+ log_level_inc()
+
+ cmd("echo '%s' > %s/%s" % (value, self.path, key))
+ log_level_dec()
+
+ _, out = cmd('cat %s/%s' % (self.path, key))
+ self._dict[key] = out.strip()
+
+ def _debugfs_dir_read(self, path):
+ dfs = {}
+
+ log("DebugFS state for %s" % (path), "")
+ log_level_inc(add=2)
+
+ _, out = cmd('ls ' + path)
+ for f in out.split():
+ p = os.path.join(path, f)
+ if os.path.isfile(p):
+ _, out = cmd('cat %s/%s' % (path, f))
+ dfs[f] = out.strip()
+ elif os.path.isdir(p):
+ dfs[f] = DebugfsDir(p)
+ else:
+ raise Exception("%s is neither file nor directory" % (p))
+
+ log_level_dec()
+ log("DebugFS state", dfs)
+ log_level_dec()
+
+ return dfs
+
+class NetdevSim:
+ """
+ Class for netdevsim netdevice and its attributes.
+ """
+
+ def __init__(self):
+ self.dev = self._netdevsim_create()
+ devs.append(self)
+
+ self.dfs_dir = '/sys/kernel/debug/netdevsim/%s' % (self.dev['ifname'])
+ self.dfs_refresh()
+
+ def __getitem__(self, key):
+ return self.dev[key]
+
+ def _netdevsim_create(self):
+ _, old = ip("link show")
+ ip("link add sim%d type netdevsim")
+ _, new = ip("link show")
+
+ for dev in new:
+ f = filter(lambda x: x["ifname"] == dev["ifname"], old)
+ if len(list(f)) == 0:
+ return dev
+
+ raise Exception("failed to create netdevsim device")
+
+ def remove(self):
+ devs.remove(self)
+ ip("link del dev %s" % (self.dev["ifname"]))
+
+ def dfs_refresh(self):
+ self.dfs = DebugfsDir(self.dfs_dir)
+ return self.dfs
+
+ def dfs_num_bound_progs(self):
+ path = os.path.join(self.dfs_dir, "bpf_bound_progs")
+ _, progs = cmd('ls %s' % (path))
+ return len(progs.split())
+
+ def dfs_get_bound_progs(self, expected):
+ progs = DebugfsDir(os.path.join(self.dfs_dir, "bpf_bound_progs"))
+ if expected is not None:
+ if len(progs) != expected:
+ fail(True, "%d BPF programs bound, expected %d" %
+ (len(progs), expected))
+ return progs
+
+ def wait_for_flush(self, bound=0, total=0, n_retry=20):
+ for i in range(n_retry):
+ nbound = self.dfs_num_bound_progs()
+ nprogs = len(bpftool_prog_list())
+ if nbound == bound and nprogs == total:
+ return
+ time.sleep(0.05)
+ raise Exception("Time out waiting for program counts to stabilize want %d/%d, have %d bound, %d loaded" % (bound, total, nbound, nprogs))
+
+ def set_mtu(self, mtu, fail=True):
+ return ip("link set dev %s mtu %d" % (self.dev["ifname"], mtu),
+ fail=fail)
+
+ def set_xdp(self, bpf, mode, force=False, fail=True):
+ return ip("link set dev %s xdp%s %s" % (self.dev["ifname"], mode, bpf),
+ force=force, fail=fail)
+
+ def unset_xdp(self, mode, force=False, fail=True):
+ return ip("link set dev %s xdp%s off" % (self.dev["ifname"], mode),
+ force=force, fail=fail)
+
+ def ip_link_show(self, xdp):
+ _, link = ip("link show dev %s" % (self['ifname']))
+ if len(link) > 1:
+ raise Exception("Multiple objects on ip link show")
+ if len(link) < 1:
+ return {}
+ fail(xdp != "xdp" in link,
+ "XDP program not reporting in iplink (reported %s, expected %s)" %
+ ("xdp" in link, xdp))
+ return link[0]
+
+ def tc_add_ingress(self):
+ tc("qdisc add dev %s ingress" % (self['ifname']))
+
+ def tc_del_ingress(self):
+ tc("qdisc del dev %s ingress" % (self['ifname']))
+
+ def tc_flush_filters(self, bound=0, total=0):
+ self.tc_del_ingress()
+ self.tc_add_ingress()
+ self.wait_for_flush(bound=bound, total=total)
+
+ def tc_show_ingress(self, expected=None):
+ # No JSON support, oh well...
+ flags = ["skip_sw", "skip_hw", "in_hw"]
+ named = ["protocol", "pref", "chain", "handle", "id", "tag"]
+
+ args = "-s filter show dev %s ingress" % (self['ifname'])
+ _, out = tc(args, JSON=False)
+
+ filters = []
+ lines = out.split('\n')
+ for line in lines:
+ words = line.split()
+ if "handle" not in words:
+ continue
+ fltr = {}
+ for flag in flags:
+ fltr[flag] = flag in words
+ for name in named:
+ try:
+ idx = words.index(name)
+ fltr[name] = words[idx + 1]
+ except ValueError:
+ pass
+ filters.append(fltr)
+
+ if expected is not None:
+ fail(len(filters) != expected,
+ "%d ingress filters loaded, expected %d" %
+ (len(filters), expected))
+ return filters
+
+ def cls_bpf_add_filter(self, bpf, da=False, skip_sw=False, skip_hw=False,
+ fail=True):
+ params = ""
+ if da:
+ params += " da"
+ if skip_sw:
+ params += " skip_sw"
+ if skip_hw:
+ params += " skip_hw"
+ return tc("filter add dev %s ingress bpf %s %s" %
+ (self['ifname'], bpf, params), fail=fail)
+
+ def set_ethtool_tc_offloads(self, enable, fail=True):
+ args = "hw-tc-offload %s" % ("on" if enable else "off")
+ return ethtool(self, "-K", args, fail=fail)
+
+################################################################################
+def clean_up():
+ for dev in devs:
+ dev.remove()
+ for f in files:
+ cmd("rm -f %s" % (f))
+
+def pin_prog(file_name, idx=0):
+ progs = bpftool_prog_list(expected=(idx + 1))
+ prog = progs[idx]
+ bpftool("prog pin id %d %s" % (prog["id"], file_name))
+ files.append(file_name)
+
+ return file_name, bpf_pinned(file_name)
+
+# Parse command line
+parser = argparse.ArgumentParser()
+parser.add_argument("--log", help="output verbose log to given file")
+args = parser.parse_args()
+if args.log:
+ logfile = open(args.log, 'w+')
+ logfile.write("# -*-Org-*-")
+
+log("Prepare...", "", level=1)
+log_level_inc()
+
+# Check permissions
+skip(os.getuid() != 0, "test must be run as root")
+
+# Check tools
+ret, progs = bpftool("prog", fail=False)
+skip(ret != 0, "bpftool not installed")
+# Check no BPF programs are loaded
+skip(len(progs) != 0, "BPF programs already loaded on the system")
+
+# Check netdevsim
+ret, out = cmd("modprobe netdevsim", fail=False)
+skip(ret != 0, "netdevsim module could not be loaded")
+
+# Check debugfs
+_, out = cmd("mount")
+if out.find("/sys/kernel/debug type debugfs") == -1:
+ cmd("mount -t debugfs none /sys/kernel/debug")
+
+# Check samples are compiled
+samples = ["sample_ret0.o"]
+for s in samples:
+ ret, out = cmd("ls %s/%s" % (bpf_test_dir, s), fail=False)
+ skip(ret != 0, "sample %s/%s not found, please compile it" %
+ (bpf_test_dir, s))
+
+try:
+ obj = bpf_obj("sample_ret0.o")
+ bytecode = bpf_bytecode("1,6 0 0 4294967295,")
+
+ start_test("Test destruction of generic XDP...")
+ sim = NetdevSim()
+ sim.set_xdp(obj, "generic")
+ sim.remove()
+ bpftool_prog_list_wait(expected=0)
+
+ sim = NetdevSim()
+ sim.tc_add_ingress()
+
+ start_test("Test TC non-offloaded...")
+ ret, _ = sim.cls_bpf_add_filter(obj, skip_hw=True, fail=False)
+ fail(ret != 0, "Software TC filter did not load")
+
+ start_test("Test TC non-offloaded isn't getting bound...")
+ ret, _ = sim.cls_bpf_add_filter(obj, fail=False)
+ fail(ret != 0, "Software TC filter did not load")
+ sim.dfs_get_bound_progs(expected=0)
+
+ sim.tc_flush_filters()
+
+ start_test("Test TC offloads are off by default...")
+ ret, _ = sim.cls_bpf_add_filter(obj, skip_sw=True, fail=False)
+ fail(ret == 0, "TC filter loaded without enabling TC offloads")
+ sim.wait_for_flush()
+
+ sim.set_ethtool_tc_offloads(True)
+ sim.dfs["bpf_tc_non_bound_accept"] = "Y"
+
+ start_test("Test TC offload by default...")
+ ret, _ = sim.cls_bpf_add_filter(obj, fail=False)
+ fail(ret != 0, "Software TC filter did not load")
+ sim.dfs_get_bound_progs(expected=0)
+ ingress = sim.tc_show_ingress(expected=1)
+ fltr = ingress[0]
+ fail(not fltr["in_hw"], "Filter not offloaded by default")
+
+ sim.tc_flush_filters()
+
+ start_test("Test TC cBPF bytcode tries offload by default...")
+ ret, _ = sim.cls_bpf_add_filter(bytecode, fail=False)
+ fail(ret != 0, "Software TC filter did not load")
+ sim.dfs_get_bound_progs(expected=0)
+ ingress = sim.tc_show_ingress(expected=1)
+ fltr = ingress[0]
+ fail(not fltr["in_hw"], "Bytecode not offloaded by default")
+
+ sim.tc_flush_filters()
+ sim.dfs["bpf_tc_non_bound_accept"] = "N"
+
+ start_test("Test TC cBPF unbound bytecode doesn't offload...")
+ ret, _ = sim.cls_bpf_add_filter(bytecode, skip_sw=True, fail=False)
+ fail(ret == 0, "TC bytecode loaded for offload")
+ sim.wait_for_flush()
+
+ start_test("Test TC offloads work...")
+ ret, _ = sim.cls_bpf_add_filter(obj, skip_sw=True, fail=False)
+ fail(ret != 0, "TC filter did not load with TC offloads enabled")
+
+ start_test("Test TC offload basics...")
+ dfs = sim.dfs_get_bound_progs(expected=1)
+ progs = bpftool_prog_list(expected=1)
+ ingress = sim.tc_show_ingress(expected=1)
+
+ dprog = dfs[0]
+ prog = progs[0]
+ fltr = ingress[0]
+ fail(fltr["skip_hw"], "TC does reports 'skip_hw' on offloaded filter")
+ fail(not fltr["in_hw"], "TC does not report 'in_hw' for offloaded filter")
+ fail(not fltr["skip_sw"], "TC does not report 'skip_sw' back")
+
+ start_test("Test TC offload is device-bound...")
+ fail(str(prog["id"]) != fltr["id"], "Program IDs don't match")
+ fail(prog["tag"] != fltr["tag"], "Program tags don't match")
+ fail(fltr["id"] != dprog["id"], "Program IDs don't match")
+ fail(dprog["state"] != "xlated", "Offloaded program state not translated")
+ fail(dprog["loaded"] != "Y", "Offloaded program is not loaded")
+
+ start_test("Test disabling TC offloads is rejected while filters installed...")
+ ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
+ fail(ret == 0, "Driver should refuse to disable TC offloads with filters installed...")
+
+ start_test("Test qdisc removal frees things...")
+ sim.tc_flush_filters()
+ sim.tc_show_ingress(expected=0)
+
+ start_test("Test disabling TC offloads is OK without filters...")
+ ret, _ = sim.set_ethtool_tc_offloads(False, fail=False)
+ fail(ret != 0,
+ "Driver refused to disable TC offloads without filters installed...")
+
+ sim.set_ethtool_tc_offloads(True)
+
+ start_test("Test destroying device gets rid of TC filters...")
+ sim.cls_bpf_add_filter(obj, skip_sw=True)
+ sim.remove()
+ bpftool_prog_list_wait(expected=0)
+
+ sim = NetdevSim()
+ sim.set_ethtool_tc_offloads(True)
+
+ start_test("Test destroying device gets rid of XDP...")
+ sim.set_xdp(obj, "offload")
+ sim.remove()
+ bpftool_prog_list_wait(expected=0)
+
+ sim = NetdevSim()
+ sim.set_ethtool_tc_offloads(True)
+
+ start_test("Test XDP prog reporting...")
+ sim.set_xdp(obj, "drv")
+ ipl = sim.ip_link_show(xdp=True)
+ progs = bpftool_prog_list(expected=1)
+ fail(ipl["xdp"]["prog"]["id"] != progs[0]["id"],
+ "Loaded program has wrong ID")
+
+ start_test("Test XDP prog replace without force...")
+ ret, _ = sim.set_xdp(obj, "drv", fail=False)
+ fail(ret == 0, "Replaced XDP program without -force")
+ sim.wait_for_flush(total=1)
+
+ start_test("Test XDP prog replace with force...")
+ ret, _ = sim.set_xdp(obj, "drv", force=True, fail=False)
+ fail(ret != 0, "Could not replace XDP program with -force")
+ bpftool_prog_list_wait(expected=1)
+ ipl = sim.ip_link_show(xdp=True)
+ progs = bpftool_prog_list(expected=1)
+ fail(ipl["xdp"]["prog"]["id"] != progs[0]["id"],
+ "Loaded program has wrong ID")
+
+ start_test("Test XDP prog replace with bad flags...")
+ ret, _ = sim.set_xdp(obj, "offload", force=True, fail=False)
+ fail(ret == 0, "Replaced XDP program with a program in different mode")
+ ret, _ = sim.set_xdp(obj, "", force=True, fail=False)
+ fail(ret == 0, "Replaced XDP program with a program in different mode")
+
+ start_test("Test XDP prog remove with bad flags...")
+ ret, _ = sim.unset_xdp("offload", force=True, fail=False)
+ fail(ret == 0, "Removed program with a bad mode mode")
+ ret, _ = sim.unset_xdp("", force=True, fail=False)
+ fail(ret == 0, "Removed program with a bad mode mode")
+
+ start_test("Test MTU restrictions...")
+ ret, _ = sim.set_mtu(9000, fail=False)
+ fail(ret == 0,
+ "Driver should refuse to increase MTU to 9000 with XDP loaded...")
+ sim.unset_xdp("drv")
+ bpftool_prog_list_wait(expected=0)
+ sim.set_mtu(9000)
+ ret, _ = sim.set_xdp(obj, "drv", fail=False)
+ fail(ret == 0, "Driver should refuse to load program with MTU of 9000...")
+ sim.set_mtu(1500)
+
+ sim.wait_for_flush()
+ start_test("Test XDP offload...")
+ sim.set_xdp(obj, "offload")
+ ipl = sim.ip_link_show(xdp=True)
+ link_xdp = ipl["xdp"]["prog"]
+ progs = bpftool_prog_list(expected=1)
+ prog = progs[0]
+ fail(link_xdp["id"] != prog["id"], "Loaded program has wrong ID")
+
+ start_test("Test XDP offload is device bound...")
+ dfs = sim.dfs_get_bound_progs(expected=1)
+ dprog = dfs[0]
+
+ fail(prog["id"] != link_xdp["id"], "Program IDs don't match")
+ fail(prog["tag"] != link_xdp["tag"], "Program tags don't match")
+ fail(str(link_xdp["id"]) != dprog["id"], "Program IDs don't match")
+ fail(dprog["state"] != "xlated", "Offloaded program state not translated")
+ fail(dprog["loaded"] != "Y", "Offloaded program is not loaded")
+
+ start_test("Test removing XDP program many times...")
+ sim.unset_xdp("offload")
+ sim.unset_xdp("offload")
+ sim.unset_xdp("drv")
+ sim.unset_xdp("drv")
+ sim.unset_xdp("")
+ sim.unset_xdp("")
+ bpftool_prog_list_wait(expected=0)
+
+ start_test("Test attempt to use a program for a wrong device...")
+ sim2 = NetdevSim()
+ sim2.set_xdp(obj, "offload")
+ pin_file, pinned = pin_prog("/sys/fs/bpf/tmp")
+
+ ret, _ = sim.set_xdp(pinned, "offload", fail=False)
+ fail(ret == 0, "Pinned program loaded for a different device accepted")
+ sim2.remove()
+ ret, _ = sim.set_xdp(pinned, "offload", fail=False)
+ fail(ret == 0, "Pinned program loaded for a removed device accepted")
+ rm(pin_file)
+ bpftool_prog_list_wait(expected=0)
+
+ start_test("Test mixing of TC and XDP...")
+ sim.tc_add_ingress()
+ sim.set_xdp(obj, "offload")
+ ret, _ = sim.cls_bpf_add_filter(obj, skip_sw=True, fail=False)
+ fail(ret == 0, "Loading TC when XDP active should fail")
+ sim.unset_xdp("offload")
+ sim.wait_for_flush()
+
+ sim.cls_bpf_add_filter(obj, skip_sw=True)
+ ret, _ = sim.set_xdp(obj, "offload", fail=False)
+ fail(ret == 0, "Loading XDP when TC active should fail")
+
+ start_test("Test binding TC from pinned...")
+ pin_file, pinned = pin_prog("/sys/fs/bpf/tmp")
+ sim.tc_flush_filters(bound=1, total=1)
+ sim.cls_bpf_add_filter(pinned, da=True, skip_sw=True)
+ sim.tc_flush_filters(bound=1, total=1)
+
+ start_test("Test binding XDP from pinned...")
+ sim.set_xdp(obj, "offload")
+ pin_file, pinned = pin_prog("/sys/fs/bpf/tmp2", idx=1)
+
+ sim.set_xdp(pinned, "offload", force=True)
+ sim.unset_xdp("offload")
+ sim.set_xdp(pinned, "offload", force=True)
+ sim.unset_xdp("offload")
+
+ start_test("Test offload of wrong type fails...")
+ ret, _ = sim.cls_bpf_add_filter(pinned, da=True, skip_sw=True, fail=False)
+ fail(ret == 0, "Managed to attach XDP program to TC")
+
+ start_test("Test asking for TC offload of two filters...")
+ sim.cls_bpf_add_filter(obj, da=True, skip_sw=True)
+ sim.cls_bpf_add_filter(obj, da=True, skip_sw=True)
+ # The above will trigger a splat until TC cls_bpf drivers are fixed
+
+ sim.tc_flush_filters(bound=2, total=2)
+
+ start_test("Test if netdev removal waits for translation...")
+ delay_msec = 500
+ sim.dfs["bpf_bind_verifier_delay"] = delay_msec
+ start = time.time()
+ cmd_line = "tc filter add dev %s ingress bpf %s da skip_sw" % \
+ (sim['ifname'], obj)
+ tc_proc = cmd(cmd_line, background=True, fail=False)
+ # Wait for the verifier to start
+ while sim.dfs_num_bound_progs() <= 2:
+ pass
+ sim.remove()
+ end = time.time()
+ ret, _ = cmd_result(tc_proc, fail=False)
+ time_diff = end - start
+ log("Time", "start:\t%s\nend:\t%s\ndiff:\t%s" % (start, end, time_diff))
+
+ fail(ret == 0, "Managed to load TC filter on a unregistering device")
+ delay_sec = delay_msec * 0.001
+ fail(time_diff < delay_sec, "Removal process took %s, expected %s" %
+ (time_diff, delay_sec))
+
+ print("%s: OK" % (os.path.basename(__file__)))
+
+finally:
+ log("Clean up...", "", level=1)
+ log_level_inc()
+ clean_up()
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 7/8] netdevsim: add SR-IOV functionality
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev
Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski, Phil Sutter, Sabrina Dubroca
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
dummy driver was extended with VF-related netdev APIs for testing
SR-IOV-related software. netdevsim did not exist back then.
Implement SR-IOV functionality in netdevsim. Notable difference
is that since netdevsim has no module parameters, we will actually
create a device with sriov_numvfs attribute for each netdev.
The zero MAC address is accepted as some HW use it to mean any
address is allowed. Link state is also now validated.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
CC: Phil Sutter <phil@nwl.cc>
CC: Sabrina Dubroca <sd@queasysnail.net>
---
drivers/net/netdevsim/netdev.c | 273 +++++++++++++++++++++++++++++++++++++-
drivers/net/netdevsim/netdevsim.h | 12 ++
2 files changed, 283 insertions(+), 2 deletions(-)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 828c1ce49a8b..a7a2a2290957 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -25,6 +25,124 @@
#include "netdevsim.h"
+struct nsim_vf_config {
+ int link_state;
+ u16 min_tx_rate;
+ u16 max_tx_rate;
+ u16 vlan;
+ __be16 vlan_proto;
+ u16 qos;
+ u8 vf_mac[ETH_ALEN];
+ bool spoofchk_enabled;
+ bool trusted;
+ bool rss_query_enabled;
+};
+
+static u32 nsim_dev_id;
+
+static int nsim_num_vf(struct device *dev)
+{
+ struct netdevsim *ns = to_nsim(dev);
+
+ return ns->num_vfs;
+}
+
+static struct bus_type nsim_bus = {
+ .name = DRV_NAME,
+ .dev_name = DRV_NAME,
+ .num_vf = nsim_num_vf,
+};
+
+static int nsim_vfs_enable(struct netdevsim *ns, unsigned int num_vfs)
+{
+ ns->vfconfigs = kcalloc(num_vfs, sizeof(struct nsim_vf_config),
+ GFP_KERNEL);
+ if (!ns->vfconfigs)
+ return -ENOMEM;
+ ns->num_vfs = num_vfs;
+
+ return 0;
+}
+
+static void nsim_vfs_disable(struct netdevsim *ns)
+{
+ kfree(ns->vfconfigs);
+ ns->vfconfigs = NULL;
+ ns->num_vfs = 0;
+}
+
+static ssize_t
+nsim_numvfs_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct netdevsim *ns = to_nsim(dev);
+ unsigned int num_vfs;
+ int ret;
+
+ ret = kstrtouint(buf, 0, &num_vfs);
+ if (ret)
+ return ret;
+
+ rtnl_lock();
+ if (ns->num_vfs == num_vfs)
+ goto exit_good;
+ if (ns->num_vfs && num_vfs) {
+ ret = -EBUSY;
+ goto exit_unlock;
+ }
+
+ if (num_vfs) {
+ ret = nsim_vfs_enable(ns, num_vfs);
+ if (ret)
+ goto exit_unlock;
+ } else {
+ nsim_vfs_disable(ns);
+ }
+exit_good:
+ ret = count;
+exit_unlock:
+ rtnl_unlock();
+
+ return ret;
+}
+
+static ssize_t
+nsim_numvfs_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ struct netdevsim *ns = to_nsim(dev);
+
+ return sprintf(buf, "%u\n", ns->num_vfs);
+}
+
+static struct device_attribute nsim_numvfs_attr =
+ __ATTR(sriov_numvfs, 0664, nsim_numvfs_show, nsim_numvfs_store);
+
+static struct attribute *nsim_dev_attrs[] = {
+ &nsim_numvfs_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group nsim_dev_attr_group = {
+ .attrs = nsim_dev_attrs,
+};
+
+static const struct attribute_group *nsim_dev_attr_groups[] = {
+ &nsim_dev_attr_group,
+ NULL,
+};
+
+static void nsim_dev_release(struct device *dev)
+{
+ struct netdevsim *ns = to_nsim(dev);
+
+ free_netdev(ns->netdev);
+}
+
+struct device_type nsim_dev_type = {
+ .groups = nsim_dev_attr_groups,
+ .release = nsim_dev_release,
+};
+
static int nsim_init(struct net_device *dev)
{
struct netdevsim *ns = netdev_priv(dev);
@@ -37,8 +155,19 @@ static int nsim_init(struct net_device *dev)
if (err)
goto err_debugfs_destroy;
+ ns->dev.id = nsim_dev_id++;
+ ns->dev.bus = &nsim_bus;
+ ns->dev.type = &nsim_dev_type;
+ err = device_register(&ns->dev);
+ if (err)
+ goto err_bpf_uninit;
+
+ SET_NETDEV_DEV(dev, &ns->dev);
+
return 0;
+err_bpf_uninit:
+ nsim_bpf_uninit(ns);
err_debugfs_destroy:
debugfs_remove_recursive(ns->ddir);
return err;
@@ -50,6 +179,14 @@ static void nsim_uninit(struct net_device *dev)
debugfs_remove_recursive(ns->ddir);
nsim_bpf_uninit(ns);
+ nsim_vfs_disable(ns);
+}
+
+static void nsim_free(struct net_device *dev)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ device_unregister(&ns->dev);
}
static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
@@ -122,6 +259,123 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
}
}
+static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ /* Only refuse multicast addresses, zero address can mean unset/any. */
+ if (vf >= ns->num_vfs || is_multicast_ether_addr(mac))
+ return -EINVAL;
+ memcpy(ns->vfconfigs[vf].vf_mac, mac, ETH_ALEN);
+
+ return 0;
+}
+
+static int nsim_set_vf_vlan(struct net_device *dev, int vf,
+ u16 vlan, u8 qos, __be16 vlan_proto)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs || vlan > 4095 || qos > 7)
+ return -EINVAL;
+
+ ns->vfconfigs[vf].vlan = vlan;
+ ns->vfconfigs[vf].qos = qos;
+ ns->vfconfigs[vf].vlan_proto = vlan_proto;
+
+ return 0;
+}
+
+static int nsim_set_vf_rate(struct net_device *dev, int vf, int min, int max)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+
+ ns->vfconfigs[vf].min_tx_rate = min;
+ ns->vfconfigs[vf].max_tx_rate = max;
+
+ return 0;
+}
+
+static int nsim_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+ ns->vfconfigs[vf].spoofchk_enabled = val;
+
+ return 0;
+}
+
+static int nsim_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+ ns->vfconfigs[vf].rss_query_enabled = val;
+
+ return 0;
+}
+
+static int nsim_set_vf_trust(struct net_device *dev, int vf, bool val)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+ ns->vfconfigs[vf].trusted = val;
+
+ return 0;
+}
+
+static int
+nsim_get_vf_config(struct net_device *dev, int vf, struct ifla_vf_info *ivi)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+
+ ivi->vf = vf;
+ ivi->linkstate = ns->vfconfigs[vf].link_state;
+ ivi->min_tx_rate = ns->vfconfigs[vf].min_tx_rate;
+ ivi->max_tx_rate = ns->vfconfigs[vf].max_tx_rate;
+ ivi->vlan = ns->vfconfigs[vf].vlan;
+ ivi->vlan_proto = ns->vfconfigs[vf].vlan_proto;
+ ivi->qos = ns->vfconfigs[vf].qos;
+ memcpy(&ivi->mac, ns->vfconfigs[vf].vf_mac, ETH_ALEN);
+ ivi->spoofchk = ns->vfconfigs[vf].spoofchk_enabled;
+ ivi->trusted = ns->vfconfigs[vf].trusted;
+ ivi->rss_query_en = ns->vfconfigs[vf].rss_query_enabled;
+
+ return 0;
+}
+
+static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
+{
+ struct netdevsim *ns = netdev_priv(dev);
+
+ if (vf >= ns->num_vfs)
+ return -EINVAL;
+
+ switch (state) {
+ case IFLA_VF_LINK_STATE_AUTO:
+ case IFLA_VF_LINK_STATE_ENABLE:
+ case IFLA_VF_LINK_STATE_DISABLE:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ ns->vfconfigs[vf].link_state = state;
+
+ return 0;
+}
+
static int
nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
{
@@ -153,6 +407,14 @@ static const struct net_device_ops nsim_netdev_ops = {
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = nsim_change_mtu,
.ndo_get_stats64 = nsim_get_stats64,
+ .ndo_set_vf_mac = nsim_set_vf_mac,
+ .ndo_set_vf_vlan = nsim_set_vf_vlan,
+ .ndo_set_vf_rate = nsim_set_vf_rate,
+ .ndo_set_vf_spoofchk = nsim_set_vf_spoofchk,
+ .ndo_set_vf_trust = nsim_set_vf_trust,
+ .ndo_get_vf_config = nsim_get_vf_config,
+ .ndo_set_vf_link_state = nsim_set_vf_link_state,
+ .ndo_set_vf_rss_query_en = nsim_set_vf_rss_query_en,
.ndo_setup_tc = nsim_setup_tc,
.ndo_set_features = nsim_set_features,
.ndo_bpf = nsim_bpf,
@@ -164,7 +426,7 @@ static void nsim_setup(struct net_device *dev)
eth_hw_addr_random(dev);
dev->netdev_ops = &nsim_netdev_ops;
- dev->needs_free_netdev = true;
+ dev->priv_destructor = nsim_free;
dev->tx_queue_len = 0;
dev->flags |= IFF_NOARP;
@@ -209,12 +471,18 @@ static int __init nsim_module_init(void)
if (IS_ERR(nsim_ddir))
return PTR_ERR(nsim_ddir);
- err = rtnl_link_register(&nsim_link_ops);
+ err = bus_register(&nsim_bus);
if (err)
goto err_debugfs_destroy;
+ err = rtnl_link_register(&nsim_link_ops);
+ if (err)
+ goto err_unreg_bus;
+
return 0;
+err_unreg_bus:
+ bus_unregister(&nsim_bus);
err_debugfs_destroy:
debugfs_remove_recursive(nsim_ddir);
return err;
@@ -223,6 +491,7 @@ static int __init nsim_module_init(void)
static void __exit nsim_module_exit(void)
{
rtnl_link_unregister(&nsim_link_ops);
+ bus_unregister(&nsim_bus);
debugfs_remove_recursive(nsim_ddir);
}
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 8779e6a8f885..32270de9395a 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -13,6 +13,7 @@
* THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
*/
+#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/netdevice.h>
@@ -26,6 +27,7 @@
struct bpf_prog;
struct dentry;
+struct nsim_vf_config;
struct netdevsim {
struct net_device *netdev;
@@ -34,8 +36,13 @@ struct netdevsim {
u64 tx_bytes;
struct u64_stats_sync syncp;
+ struct device dev;
+
struct dentry *ddir;
+ unsigned int num_vfs;
+ struct nsim_vf_config *vfconfigs;
+
struct bpf_prog *bpf_offloaded;
u32 bpf_offloaded_id;
@@ -64,3 +71,8 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf);
int nsim_bpf_disable_tc(struct netdevsim *ns);
int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type,
void *type_data, void *cb_priv);
+
+static inline struct netdevsim *to_nsim(struct device *ptr)
+{
+ return container_of(ptr, struct netdevsim, dev);
+}
--
2.14.1
^ permalink raw reply related
* [PATCH net-next v2 8/8] net: dummy: remove fake SR-IOV functionality
From: Jakub Kicinski @ 2017-12-01 1:35 UTC (permalink / raw)
To: netdev
Cc: davem, daniel, alexei.starovoitov, jiri, oss-drivers,
Jakub Kicinski, Phil Sutter, Sabrina Dubroca
In-Reply-To: <20171201013540.18106-1-jakub.kicinski@netronome.com>
netdevsim driver seems like a better place for fake SR-IOV
functionality. Remove the code previously added to dummy.
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
---
CC: Phil Sutter <phil@nwl.cc>
CC: Sabrina Dubroca <sd@queasysnail.net>
---
drivers/net/dummy.c | 215 +---------------------------------------------------
1 file changed, 1 insertion(+), 214 deletions(-)
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 58483af80bdb..30b1c8512049 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -42,48 +42,7 @@
#define DRV_NAME "dummy"
#define DRV_VERSION "1.0"
-#undef pr_fmt
-#define pr_fmt(fmt) DRV_NAME ": " fmt
-
static int numdummies = 1;
-static int num_vfs;
-
-struct vf_data_storage {
- u8 vf_mac[ETH_ALEN];
- u16 pf_vlan; /* When set, guest VLAN config not allowed. */
- u16 pf_qos;
- __be16 vlan_proto;
- u16 min_tx_rate;
- u16 max_tx_rate;
- u8 spoofchk_enabled;
- bool rss_query_enabled;
- u8 trusted;
- int link_state;
-};
-
-struct dummy_priv {
- struct vf_data_storage *vfinfo;
-};
-
-static int dummy_num_vf(struct device *dev)
-{
- return num_vfs;
-}
-
-static struct bus_type dummy_bus = {
- .name = "dummy",
- .num_vf = dummy_num_vf,
-};
-
-static void release_dummy_parent(struct device *dev)
-{
-}
-
-static struct device dummy_parent = {
- .init_name = "dummy",
- .bus = &dummy_bus,
- .release = release_dummy_parent,
-};
/* fake multicast ability */
static void set_multicast_list(struct net_device *dev)
@@ -133,25 +92,10 @@ static netdev_tx_t dummy_xmit(struct sk_buff *skb, struct net_device *dev)
static int dummy_dev_init(struct net_device *dev)
{
- struct dummy_priv *priv = netdev_priv(dev);
-
dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
if (!dev->dstats)
return -ENOMEM;
- priv->vfinfo = NULL;
-
- if (!num_vfs)
- return 0;
-
- dev->dev.parent = &dummy_parent;
- priv->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
- GFP_KERNEL);
- if (!priv->vfinfo) {
- free_percpu(dev->dstats);
- return -ENOMEM;
- }
-
return 0;
}
@@ -169,117 +113,6 @@ static int dummy_change_carrier(struct net_device *dev, bool new_carrier)
return 0;
}
-static int dummy_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (!is_valid_ether_addr(mac) || (vf >= num_vfs))
- return -EINVAL;
-
- memcpy(priv->vfinfo[vf].vf_mac, mac, ETH_ALEN);
-
- return 0;
-}
-
-static int dummy_set_vf_vlan(struct net_device *dev, int vf,
- u16 vlan, u8 qos, __be16 vlan_proto)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if ((vf >= num_vfs) || (vlan > 4095) || (qos > 7))
- return -EINVAL;
-
- priv->vfinfo[vf].pf_vlan = vlan;
- priv->vfinfo[vf].pf_qos = qos;
- priv->vfinfo[vf].vlan_proto = vlan_proto;
-
- return 0;
-}
-
-static int dummy_set_vf_rate(struct net_device *dev, int vf, int min, int max)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- priv->vfinfo[vf].min_tx_rate = min;
- priv->vfinfo[vf].max_tx_rate = max;
-
- return 0;
-}
-
-static int dummy_set_vf_spoofchk(struct net_device *dev, int vf, bool val)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- priv->vfinfo[vf].spoofchk_enabled = val;
-
- return 0;
-}
-
-static int dummy_set_vf_rss_query_en(struct net_device *dev, int vf, bool val)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- priv->vfinfo[vf].rss_query_enabled = val;
-
- return 0;
-}
-
-static int dummy_set_vf_trust(struct net_device *dev, int vf, bool val)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- priv->vfinfo[vf].trusted = val;
-
- return 0;
-}
-
-static int dummy_get_vf_config(struct net_device *dev,
- int vf, struct ifla_vf_info *ivi)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- ivi->vf = vf;
- memcpy(&ivi->mac, priv->vfinfo[vf].vf_mac, ETH_ALEN);
- ivi->vlan = priv->vfinfo[vf].pf_vlan;
- ivi->qos = priv->vfinfo[vf].pf_qos;
- ivi->spoofchk = priv->vfinfo[vf].spoofchk_enabled;
- ivi->linkstate = priv->vfinfo[vf].link_state;
- ivi->min_tx_rate = priv->vfinfo[vf].min_tx_rate;
- ivi->max_tx_rate = priv->vfinfo[vf].max_tx_rate;
- ivi->rss_query_en = priv->vfinfo[vf].rss_query_enabled;
- ivi->trusted = priv->vfinfo[vf].trusted;
- ivi->vlan_proto = priv->vfinfo[vf].vlan_proto;
-
- return 0;
-}
-
-static int dummy_set_vf_link_state(struct net_device *dev, int vf, int state)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- if (vf >= num_vfs)
- return -EINVAL;
-
- priv->vfinfo[vf].link_state = state;
-
- return 0;
-}
-
static const struct net_device_ops dummy_netdev_ops = {
.ndo_init = dummy_dev_init,
.ndo_uninit = dummy_dev_uninit,
@@ -289,14 +122,6 @@ static const struct net_device_ops dummy_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_get_stats64 = dummy_get_stats64,
.ndo_change_carrier = dummy_change_carrier,
- .ndo_set_vf_mac = dummy_set_vf_mac,
- .ndo_set_vf_vlan = dummy_set_vf_vlan,
- .ndo_set_vf_rate = dummy_set_vf_rate,
- .ndo_set_vf_spoofchk = dummy_set_vf_spoofchk,
- .ndo_set_vf_trust = dummy_set_vf_trust,
- .ndo_get_vf_config = dummy_get_vf_config,
- .ndo_set_vf_link_state = dummy_set_vf_link_state,
- .ndo_set_vf_rss_query_en = dummy_set_vf_rss_query_en,
};
static void dummy_get_drvinfo(struct net_device *dev,
@@ -323,13 +148,6 @@ static const struct ethtool_ops dummy_ethtool_ops = {
.get_ts_info = dummy_get_ts_info,
};
-static void dummy_free_netdev(struct net_device *dev)
-{
- struct dummy_priv *priv = netdev_priv(dev);
-
- kfree(priv->vfinfo);
-}
-
static void dummy_setup(struct net_device *dev)
{
ether_setup(dev);
@@ -338,7 +156,6 @@ static void dummy_setup(struct net_device *dev)
dev->netdev_ops = &dummy_netdev_ops;
dev->ethtool_ops = &dummy_ethtool_ops;
dev->needs_free_netdev = true;
- dev->priv_destructor = dummy_free_netdev;
/* Fill in device structure with ethernet-generic values. */
dev->flags |= IFF_NOARP;
@@ -370,7 +187,6 @@ static int dummy_validate(struct nlattr *tb[], struct nlattr *data[],
static struct rtnl_link_ops dummy_link_ops __read_mostly = {
.kind = DRV_NAME,
- .priv_size = sizeof(struct dummy_priv),
.setup = dummy_setup,
.validate = dummy_validate,
};
@@ -379,16 +195,12 @@ static struct rtnl_link_ops dummy_link_ops __read_mostly = {
module_param(numdummies, int, 0);
MODULE_PARM_DESC(numdummies, "Number of dummy pseudo devices");
-module_param(num_vfs, int, 0);
-MODULE_PARM_DESC(num_vfs, "Number of dummy VFs per dummy device");
-
static int __init dummy_init_one(void)
{
struct net_device *dev_dummy;
int err;
- dev_dummy = alloc_netdev(sizeof(struct dummy_priv),
- "dummy%d", NET_NAME_ENUM, dummy_setup);
+ dev_dummy = alloc_netdev(0, "dummy%d", NET_NAME_ENUM, dummy_setup);
if (!dev_dummy)
return -ENOMEM;
@@ -407,21 +219,6 @@ static int __init dummy_init_module(void)
{
int i, err = 0;
- if (num_vfs) {
- err = bus_register(&dummy_bus);
- if (err < 0) {
- pr_err("registering dummy bus failed\n");
- return err;
- }
-
- err = device_register(&dummy_parent);
- if (err < 0) {
- pr_err("registering dummy parent device failed\n");
- bus_unregister(&dummy_bus);
- return err;
- }
- }
-
rtnl_lock();
err = __rtnl_link_register(&dummy_link_ops);
if (err < 0)
@@ -437,22 +234,12 @@ static int __init dummy_init_module(void)
out:
rtnl_unlock();
- if (err && num_vfs) {
- device_unregister(&dummy_parent);
- bus_unregister(&dummy_bus);
- }
-
return err;
}
static void __exit dummy_cleanup_module(void)
{
rtnl_link_unregister(&dummy_link_ops);
-
- if (num_vfs) {
- device_unregister(&dummy_parent);
- bus_unregister(&dummy_bus);
- }
}
module_init(dummy_init_module);
--
2.14.1
^ permalink raw reply related
* Re: [PATCH v4 3/8] MIPS: Octeon: Add a global resource manager.
From: David Daney @ 2017-12-01 1:51 UTC (permalink / raw)
To: James Hogan, David Daney
Cc: Mark Rutland, linux-mips, devel, devicetree, netdev, linux-kernel,
ralf, Carlos Munoz, Rob Herring, Andrew Lunn, Steven J. Hill,
Greg Kroah-Hartman, Florian Fainelli, David S. Miller
In-Reply-To: <20171130225333.GI27409@jhogan-linux.mipstec.com>
On 11/30/2017 02:53 PM, James Hogan wrote:
> On Tue, Nov 28, 2017 at 04:55:35PM -0800, David Daney wrote:
>> From: Carlos Munoz <cmunoz@cavium.com>
>>
>> Add a global resource manager to manage tagged pointers within
>> bootmem allocated memory. This is used by various functional
>> blocks in the Octeon core like the FPA, Ethernet nexus, etc.
>>
>> Signed-off-by: Carlos Munoz <cmunoz@cavium.com>
>> Signed-off-by: Steven J. Hill <Steven.Hill@cavium.com>
>> Signed-off-by: David Daney <david.daney@cavium.com>
>> ---
>> arch/mips/cavium-octeon/Makefile | 3 +-
>> arch/mips/cavium-octeon/resource-mgr.c | 371 +++++++++++++++++++++++++++++++++
>> arch/mips/include/asm/octeon/octeon.h | 18 ++
>> 3 files changed, 391 insertions(+), 1 deletion(-)
>> create mode 100644 arch/mips/cavium-octeon/resource-mgr.c
>>
>> diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
>> index 7c02e542959a..0a299ab8719f 100644
>> --- a/arch/mips/cavium-octeon/Makefile
>> +++ b/arch/mips/cavium-octeon/Makefile
>> @@ -9,7 +9,8 @@
>> # Copyright (C) 2005-2009 Cavium Networks
>> #
>>
>> -obj-y := cpu.o setup.o octeon-platform.o octeon-irq.o csrc-octeon.o
>> +obj-y := cpu.o setup.o octeon-platform.o octeon-irq.o csrc-octeon.o \
>> + resource-mgr.o
>
> Maybe put that on a separate line like below.
OK
>
>> obj-y += dma-octeon.o
>> obj-y += octeon-memcpy.o
>> obj-y += executive/
>> diff --git a/arch/mips/cavium-octeon/resource-mgr.c b/arch/mips/cavium-octeon/resource-mgr.c
>> new file mode 100644
>> index 000000000000..ca25fa953402
>> --- /dev/null
>> +++ b/arch/mips/cavium-octeon/resource-mgr.c
>> @@ -0,0 +1,371 @@
>> +// SPDX-License-Identifier: GPL-2.0
>> +/*
>> + * Resource manager for Octeon.
>> + *
>> + * This file is subject to the terms and conditions of the GNU General Public
>> + * License. See the file "COPYING" in the main directory of this archive
>> + * for more details.
>> + *
>> + * Copyright (C) 2017 Cavium, Inc.
>> + */
>> +#include <linux/module.h>
>> +
>> +#include <asm/octeon/octeon.h>
>> +#include <asm/octeon/cvmx-bootmem.h>
>> +
>> +#define RESOURCE_MGR_BLOCK_NAME "cvmx-global-resources"
>> +#define MAX_RESOURCES 128
>> +#define INST_AVAILABLE -88
>> +#define OWNER 0xbadc0de
>> +
>> +struct global_resource_entry {
>> + struct global_resource_tag tag;
>> + u64 phys_addr;
>> + u64 size;
>> +};
>> +
>> +struct global_resources {
>> +#ifdef __LITTLE_ENDIAN_BITFIELD
>> + u32 rlock;
>> + u32 pad;
>> +#else
>> + u32 pad;
>> + u32 rlock;
>> +#endif
>> + u64 entry_cnt;
>> + struct global_resource_entry resource_entry[];
>> +};
>> +
>> +static struct global_resources *res_mgr_info;
>> +
>> +
>> +/*
>> + * The resource manager interacts with software running outside of the
>> + * Linux kernel, which necessitates locking to maintain data structure
>> + * consistency. These custom locking functions implement the locking
>> + * protocol, and cannot be replaced by kernel locking functions that
>> + * may use different in-memory structures.
>> + */
>> +
>> +static void res_mgr_lock(void)
>> +{
>> + unsigned int tmp;
>> + u64 lock = (u64)&res_mgr_info->rlock;
>
> presumably this could be a u32 *, avoid the cast to u64, and still work
> just fine below.
I will rewrite to just use cmpxchg()
>
>> +
>> + __asm__ __volatile__(
>> + ".set noreorder\n"
>> + "1: ll %[tmp], 0(%[addr])\n"
>> + " bnez %[tmp], 1b\n"
>> + " li %[tmp], 1\n"
>
> I believe the convention for .S files is for instructions in branch
> delay slots to be indented an additional space for readability. Maybe
> that would be worthwhile here.
>
>> + " sc %[tmp], 0(%[addr])\n"
>> + " beqz %[tmp], 1b\n"
>> + " nop\n"
>
> and here also.
>
>> + ".set reorder\n" :
>
> nit: strictly speaking there's no need for \n on the last line.
>
>> + [tmp] "=&r"(tmp) :
>> + [addr] "r"(lock) :
>> + "memory");
>
> minor style thing: its far more common to have : at the beginning of the
> line rather than the end.
>
>> +}
>> +
>> +static void res_mgr_unlock(void)
>> +{
>> + u64 lock = (u64)&res_mgr_info->rlock;
>
> same again
>
Will rewrite to use WRITE_ONCE().
>> +
>> + /* Wait until all resource operations finish before unlocking. */
>> + mb();
>> + __asm__ __volatile__(
>> + "sw $0, 0(%[addr])\n" : :
>> + [addr] "r"(lock) :
>> + "memory");
>> +
>> + /* Force a write buffer flush. */
>> + mb();
>> +}
>> +
>> +static int res_mgr_find_resource(struct global_resource_tag tag)
>> +{
>> + struct global_resource_entry *res_entry;
>> + int i;
>> +
>> + for (i = 0; i < res_mgr_info->entry_cnt; i++) {
>> + res_entry = &res_mgr_info->resource_entry[i];
>> + if (res_entry->tag.lo == tag.lo && res_entry->tag.hi == tag.hi)
>> + return i;
>> + }
>> + return -1;
>> +}
>> +
>> +/**
>> + * res_mgr_create_resource - Create a resource.
>> + * @tag: Identifies the resource.
>> + * @inst_cnt: Number of resource instances to create.
>> + *
>> + * Returns 0 if the source was created successfully.
>> + * Returns <0 for error codes.
>
> Only -1 seems to be returned. Is it worth returning some standard Linux
> error codes instead?
Yep. I fixed this and everything below for the next version of the
patch set.
Thanks,
David Daney
^ permalink raw reply
* Re: [BUG] kernel stack corruption during/after Netlabel error
From: James Morris @ 2017-12-01 1:55 UTC (permalink / raw)
To: Eric Dumazet
Cc: Casey Schaufler, Paul Moore, netdev, Stephen Smalley, selinux,
LSM
In-Reply-To: <1512039044.19682.12.camel@gmail.com>
On Thu, 30 Nov 2017, Eric Dumazet wrote:
> On Wed, 2017-11-29 at 19:16 -0800, Casey Schaufler wrote:
> > On 11/29/2017 4:31 PM, James Morris wrote:
> > > On Wed, 29 Nov 2017, Casey Schaufler wrote:
> > >
> > > > I see that there is a proposed fix later in the thread, but I
> > > > don't see
> > > > the patch. Could you send it to me, so I can try it on my
> > > > problem?
> > >
> > > Forwarded off-list.
> >
> > The patch does fix the problem I was seeing in Smack.
>
> Can you guys test the following more complete patch ?
>
> It should cover IPv4 and IPv6, and also the corner cases.
Tested-by: James Morris <james.l.morris@oracle.com>
--
James Morris
<james.l.morris@oracle.com>
^ permalink raw reply
* [PATCH net] ipvlan: Add the skb->mark as flow4's member to lookup route
From: gfree.wind @ 2017-12-01 1:58 UTC (permalink / raw)
To: davem, maheshb, netdev; +Cc: Gao Feng
From: Gao Feng <gfree.wind@vip.163.com>
Current codes don't use skb->mark to assign flowi4_mark, it would
make the policy route rule with fwmark doesn't work as expected.
Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
---
drivers/net/ipvlan/ipvlan_core.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 11c1e79..77cc4fb 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -393,6 +393,7 @@ static int ipvlan_process_v4_outbound(struct sk_buff *skb)
.flowi4_oif = dev->ifindex,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC,
+ .flowi4_mark = skb->mark,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
--
1.9.1
^ permalink raw reply related
* Re: [RFC] bpf: offload: report device information for offloaded programs
From: Jakub Kicinski @ 2017-12-01 2:05 UTC (permalink / raw)
To: Kirill Tkhai
Cc: netdev, linux-kernel, oss-drivers, alexei.starovoitov, daniel,
Eric W . Biederman
In-Reply-To: <85513945-bcd2-b2b4-24e7-5fbb3e695419@virtuozzo.com>
Hi Kirill,
On Thu, 30 Nov 2017 16:19:13 +0300, Kirill Tkhai wrote:
> > @@ -164,6 +166,38 @@ int bpf_prog_offload_compile(struct bpf_prog *prog)
> > return bpf_prog_offload_translate(prog);
> > }
> >
> > +int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
> > + struct bpf_prog *prog)
> > +{
> > + struct bpf_dev_offload *offload = prog->aux->offload;
> > + struct inode *ns_inode;
> > + struct path ns_path;
> > + struct net *net;
> > + int ret = 0;
> > + void *ptr;
> > +
> > + info->dev_bound = 1;
> > +
> > + rtnl_lock();
>
> rtnl_lock() is too big lock and it is already overused in kernel.
> Can't we use smaller lock in this driver to protect bpf_prog_offload_devs?
> I suppose rwlock would be appropriate for that.
>
> (Then, we may completely remove rtnl_lock() from bpf_prog_offload_init()
> and use readlocked dev_base_lock for __dev_get_by_index() instead and
> the new small_rwlock to link in the list.
>
> Not sure about bpf_prog_offload_verifier_prep() and bpf_prog_offload_translate()
> and which context expect net_device_ops->ndo_bpf users. Either they need rtnl
> or not).
Thanks for the comments, removing the use of rtnl_lock is definitely on
my todo list!
^ permalink raw reply
* Re: [PATCH net 1/2] bpf: set maximum number of attached progs to 64 for a single perf tp
From: Daniel Borkmann @ 2017-12-01 2:07 UTC (permalink / raw)
To: Yonghong Song, ast, netdev; +Cc: kernel-team
In-Reply-To: <20171130214755.3022117-1-yhs@fb.com>
On 11/30/2017 10:47 PM, Yonghong Song wrote:
> cgropu+bpf prog array has a maximum number of 64 programs.
> Let us apply the same limit here.
>
> Signed-off-by: Yonghong Song <yhs@fb.com>
Both applied to bpf tree, thanks! Please add a proper Fixes tags in the
future; took care of it this time.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox