* [PATCH v4 7/7] fs/splice: full support for compiling out splice
From: Pieter Smith @ 2014-11-24 23:01 UTC (permalink / raw)
To: pieter
Cc: Josh Triplett, Alexander Duyck, Alexander Viro,
Alexei Starovoitov, Andrew Morton, Bertrand Jacquin,
Catalina Mocanu, Daniel Borkmann, David S. Miller, Eric Dumazet,
Eric W. Biederman, Fabian Frederick,
open list:FUSE: FILESYSTEM..., Geert Uytterhoeven, Hugh Dickins,
Iulia Manda, Jan Beulich, J. Bruce Fields, Jeff Layton,
open list:ABI/API, linux-fsdevel, linux-kernel
In-Reply-To: <1416870079-15254-1-git-send-email-pieter@boesman.nl>
Entirely compile out splice translation unit when the system is configured
without splice family of syscalls (i.e. CONFIG_SYSCALL_SPLICE is undefined).
Exported fs/splice functions are transparently mocked out with static inlines.
Because userspace support for splice has already been removed by this
patch-set, the exported functions cannot be called anyway. Mocking them out
prevents a maintenance burden on file system drivers.
The bloat score resulting from this patch given a tinyconfig is:
add/remove: 0/25 grow/shrink: 0/5 up/down: 0/-4845 (-4845)
function old new delta
pipe_to_null 4 - -4
generic_pipe_buf_nosteal 6 - -6
spd_release_page 10 - -10
PageUptodate 22 11 -11
lock_page 36 24 -12
page_cache_pipe_buf_release 16 - -16
splice_write_null 24 4 -20
page_cache_pipe_buf_ops 20 - -20
nosteal_pipe_buf_ops 20 - -20
default_pipe_buf_ops 20 - -20
generic_splice_sendpage 24 - -24
splice_shrink_spd 27 - -27
direct_splice_actor 47 - -47
default_file_splice_write 49 - -49
wakeup_pipe_writers 54 - -54
write_pipe_buf 71 - -71
page_cache_pipe_buf_confirm 80 - -80
splice_grow_spd 87 - -87
splice_from_pipe 93 - -93
splice_from_pipe_next 106 - -106
pipe_to_sendpage 109 - -109
page_cache_pipe_buf_steal 114 - -114
generic_file_splice_read 131 8 -123
do_splice_direct 148 - -148
__splice_from_pipe 246 - -246
splice_direct_to_actor 416 - -416
splice_to_pipe 417 - -417
default_file_splice_read 688 - -688
iter_file_splice_write 702 4 -698
__generic_file_splice_read 1109 - -1109
The bloat score for the entire CONFIG_SYSCALL_SPLICE patch-set is:
add/remove: 0/41 grow/shrink: 5/7 up/down: 23/-8422 (-8399)
function old new delta
sys_pwritev 115 122 +7
sys_preadv 115 122 +7
fdput_pos 29 36 +7
sys_pwrite64 115 116 +1
sys_pread64 115 116 +1
pipe_to_null 4 - -4
generic_pipe_buf_nosteal 6 - -6
spd_release_page 10 - -10
fdput 11 - -11
PageUptodate 22 11 -11
lock_page 36 24 -12
signal_pending 39 26 -13
fdget 56 42 -14
page_cache_pipe_buf_release 16 - -16
user_page_pipe_buf_ops 20 - -20
splice_write_null 24 4 -20
page_cache_pipe_buf_ops 20 - -20
nosteal_pipe_buf_ops 20 - -20
default_pipe_buf_ops 20 - -20
generic_splice_sendpage 24 - -24
user_page_pipe_buf_steal 25 - -25
splice_shrink_spd 27 - -27
pipe_to_user 43 - -43
direct_splice_actor 47 - -47
default_file_splice_write 49 - -49
wakeup_pipe_writers 54 - -54
wakeup_pipe_readers 54 - -54
write_pipe_buf 71 - -71
page_cache_pipe_buf_confirm 80 - -80
splice_grow_spd 87 - -87
do_splice_to 87 - -87
ipipe_prep.part 92 - -92
splice_from_pipe 93 - -93
splice_from_pipe_next 107 - -107
pipe_to_sendpage 109 - -109
page_cache_pipe_buf_steal 114 - -114
opipe_prep.part 119 - -119
sys_sendfile 122 - -122
generic_file_splice_read 131 8 -123
sys_sendfile64 126 - -126
sys_vmsplice 137 - -137
do_splice_direct 148 - -148
vmsplice_to_user 205 - -205
__splice_from_pipe 246 - -246
splice_direct_to_actor 348 - -348
splice_to_pipe 371 - -371
do_sendfile 492 - -492
sys_tee 497 - -497
vmsplice_to_pipe 558 - -558
default_file_splice_read 688 - -688
iter_file_splice_write 702 4 -698
sys_splice 1075 - -1075
__generic_file_splice_read 1109 - -1109
Signed-off-by: Pieter Smith <pieter@boesman.nl>
---
fs/Makefile | 3 ++-
fs/splice.c | 2 --
include/linux/fs.h | 26 ++++++++++++++++++++++++++
include/linux/splice.h | 42 ++++++++++++++++++++++++++++++++++++++++++
4 files changed, 70 insertions(+), 3 deletions(-)
diff --git a/fs/Makefile b/fs/Makefile
index fb7646e..9395622 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -10,7 +10,7 @@ obj-y := open.o read_write.o file_table.o super.o \
ioctl.o readdir.o select.o dcache.o inode.o \
attr.o bad_inode.o file.o filesystems.o namespace.o \
seq_file.o xattr.o libfs.o fs-writeback.o \
- pnode.o splice.o sync.o utimes.o \
+ pnode.o sync.o utimes.o \
stack.o fs_struct.o statfs.o fs_pin.o
ifeq ($(CONFIG_BLOCK),y)
@@ -22,6 +22,7 @@ endif
obj-$(CONFIG_PROC_FS) += proc_namespace.o
obj-$(CONFIG_FSNOTIFY) += notify/
+obj-$(CONFIG_SYSCALL_SPLICE) += splice.o
obj-$(CONFIG_EPOLL) += eventpoll.o
obj-$(CONFIG_ANON_INODES) += anon_inodes.o
obj-$(CONFIG_SIGNALFD) += signalfd.o
diff --git a/fs/splice.c b/fs/splice.c
index 7c4c695..44b201b 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1316,7 +1316,6 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
return ret;
}
-#ifdef CONFIG_SYSCALL_SPLICE
static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
struct pipe_inode_info *opipe,
size_t len, unsigned int flags);
@@ -2201,5 +2200,4 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
#endif
-#endif
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a957d43..138107e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2444,6 +2444,7 @@ extern int blkdev_fsync(struct file *filp, loff_t start, loff_t end,
extern void block_sync_page(struct page *page);
/* fs/splice.c */
+#ifdef CONFIG_SYSCALL_SPLICE
extern ssize_t generic_file_splice_read(struct file *, loff_t *,
struct pipe_inode_info *, size_t, unsigned int);
extern ssize_t default_file_splice_read(struct file *, loff_t *,
@@ -2452,6 +2453,31 @@ extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
struct file *, loff_t *, size_t, unsigned int);
extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
struct file *out, loff_t *, size_t len, unsigned int flags);
+#else
+static inline ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len, unsigned int flags)
+{
+ return -EPERM;
+}
+
+static inline ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len, unsigned int flags)
+{
+ return -EPERM;
+}
+
+static inline ssize_t iter_file_splice_write(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len, unsigned int flags)
+{
+ return -EPERM;
+}
+
+static inline ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
+ struct file *out, loff_t *ppos, size_t len, unsigned int flags)
+{
+ return -EPERM;
+}
+#endif
extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
diff --git a/include/linux/splice.h b/include/linux/splice.h
index da2751d..34570d8 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -65,6 +65,7 @@ typedef int (splice_actor)(struct pipe_inode_info *, struct pipe_buffer *,
typedef int (splice_direct_actor)(struct pipe_inode_info *,
struct splice_desc *);
+#ifdef CONFIG_SYSCALL_SPLICE
extern ssize_t splice_from_pipe(struct pipe_inode_info *, struct file *,
loff_t *, size_t, unsigned int,
splice_actor *);
@@ -74,13 +75,54 @@ extern ssize_t splice_to_pipe(struct pipe_inode_info *,
struct splice_pipe_desc *);
extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *,
splice_direct_actor *);
+#else
+static inline ssize_t splice_from_pipe(struct pipe_inode_info *pipe, struct file *out,
+ loff_t *ppos, size_t len, unsigned int flags,
+ splice_actor *actor)
+{
+ return -EPERM;
+}
+
+static inline ssize_t __splice_from_pipe(struct pipe_inode_info *pipe, struct splice_desc *sd,
+ splice_actor *actor)
+{
+ return -EPERM;
+}
+
+static inline ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
+ struct splice_pipe_desc *spd)
+{
+ return -EPERM;
+}
+
+static inline ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
+ splice_direct_actor *actor)
+{
+ return -EPERM;
+}
+#endif
/*
* for dynamic pipe sizing
*/
+#ifdef CONFIG_SYSCALL_SPLICE
extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *);
extern void splice_shrink_spd(struct splice_pipe_desc *);
extern void spd_release_page(struct splice_pipe_desc *, unsigned int);
+#else
+static inline int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd)
+{
+ return -EPERM;
+}
+
+static inline void splice_shrink_spd(struct splice_pipe_desc *spd)
+{
+}
+
+static inline void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
+{
+}
+#endif
extern const struct pipe_buf_operations page_cache_pipe_buf_ops;
#endif
--
2.1.0
^ permalink raw reply related
* [PATCH v4 3/7] fs/splice: support compiling out splice-family syscalls
From: Pieter Smith @ 2014-11-24 23:01 UTC (permalink / raw)
To: pieter
Cc: Josh Triplett, Alexander Duyck, Alexander Viro,
Alexei Starovoitov, Andrew Morton, Bertrand Jacquin,
Catalina Mocanu, Daniel Borkmann, David S. Miller, Eric Dumazet,
Eric W. Biederman, Fabian Frederick,
open list:FUSE: FILESYSTEM..., Geert Uytterhoeven, Hugh Dickins,
Iulia Manda, Jan Beulich, J. Bruce Fields, Jeff Layton,
open list:ABI/API, linux-fsdevel, linux-kernel
In-Reply-To: <1416870079-15254-1-git-send-email-pieter@boesman.nl>
Many embedded systems will not need the splice-family syscalls (splice,
vmsplice, tee and sendfile). Omitting them saves space. This adds a new EXPERT
config option CONFIG_SYSCALL_SPLICE (default y) to support compiling them out.
The goal is to completely compile out fs/splice along with the syscalls. To
achieve this, the remaining patch-set will deal with fs/splice exports. As far
as possible, the impact on other device drivers will be minimized so as to
reduce the overal maintenance burden of CONFIG_SYSCALL_SPLICE.
The use of exported functions will be solved by transparently mocking them out
with static inlines. Uses of the exported pipe_buf_operations struct however
require direct modification in fs/fuse and net/core. The next two patches will
deal with this. A macro is defined that will assist with NULL'ing out callbacks
when CONFIG_SYSCALL_SPLICE is undefined: __splice_p().
Once all exports are solved, fs/splice can be compiled out.
The bloat benefit of this patch given a tinyconfig is:
add/remove: 0/16 grow/shrink: 2/5 up/down: 114/-3693 (-3579)
function old new delta
splice_direct_to_actor 348 416 +68
splice_to_pipe 371 417 +46
splice_from_pipe_next 107 106 -1
fdput 11 - -11
signal_pending 39 26 -13
fdget 56 42 -14
user_page_pipe_buf_ops 20 - -20
user_page_pipe_buf_steal 25 - -25
file_end_write 58 29 -29
file_start_write 68 34 -34
pipe_to_user 43 - -43
wakeup_pipe_readers 54 - -54
do_splice_to 87 - -87
ipipe_prep.part 92 - -92
opipe_prep.part 119 - -119
sys_sendfile 122 - -122
sys_sendfile64 126 - -126
sys_vmsplice 137 - -137
vmsplice_to_user 205 - -205
sys_tee 491 - -491
do_sendfile 492 - -492
vmsplice_to_pipe 558 - -558
sys_splice 1020 - -1020
Signed-off-by: Pieter Smith <pieter@boesman.nl>
---
fs/splice.c | 2 ++
init/Kconfig | 10 ++++++++++
kernel/sys_ni.c | 8 ++++++++
3 files changed, 20 insertions(+)
diff --git a/fs/splice.c b/fs/splice.c
index 44b201b..7c4c695 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1316,6 +1316,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
return ret;
}
+#ifdef CONFIG_SYSCALL_SPLICE
static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
struct pipe_inode_info *opipe,
size_t len, unsigned int flags);
@@ -2200,4 +2201,5 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
return do_sendfile(out_fd, in_fd, NULL, count, 0);
}
#endif
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index d811d5f..dec9819 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1571,6 +1571,16 @@ config NTP
system clock to an NTP server, you can disable this option to save
space.
+config SYSCALL_SPLICE
+ bool "Enable splice/vmsplice/tee/sendfile syscalls" if EXPERT
+ default y
+ help
+ This option enables the splice, vmsplice, tee and sendfile syscalls. These
+ are used by applications to: move data between buffers and arbitrary file
+ descriptors; "copy" data between buffers; or copy data from userspace into
+ buffers. If building an embedded system where no applications use these
+ syscalls, you can disable this option to save space.
+
config PCI_QUIRKS
default y
bool "Enable PCI quirk workarounds" if EXPERT
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index d2f5b00..25d5551 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -170,6 +170,14 @@ cond_syscall(sys_fstat);
cond_syscall(sys_stat);
cond_syscall(sys_uname);
cond_syscall(sys_olduname);
+cond_syscall(sys_vmsplice);
+cond_syscall(sys_splice);
+cond_syscall(sys_tee);
+cond_syscall(sys_sendfile);
+cond_syscall(sys_sendfile64);
+cond_syscall(compat_sys_vmsplice);
+cond_syscall(compat_sys_sendfile);
+cond_syscall(compat_sys_sendfile64);
/* arch-specific weak syscall entries */
cond_syscall(sys_pciconfig_read);
--
2.1.0
^ permalink raw reply related
* [PATCH net-next 0/3] net: Remote checksum offload for VXLAN
From: Tom Herbert @ 2014-11-24 23:52 UTC (permalink / raw)
To: davem, netdev
This patch set adds support for remote checksum offload in VXLAN.
The remote checksum offload is generalized by creating a common
function (remcsum_adjust) that does the work of modifying the
checksum in remote checksum offload. This function can be called
from normal or GRO path. GUE was modified to use this function.
To support RCO is VXLAN we use the 9th bit in the reserved
flags to indicated remote checksum offload. The start and offset
values are encoded n a compressed form in the low order (reserved)
byte of the vni field.
Remote checksum offload is described in
https://tools.ietf.org/html/draft-herbert-remotecsumoffload-01
Tested by running 200 TCP_STREAM connections with VXLAN (over IPv4).
With UDP checksums and Remote Checksum Offload
IPv4
Client
11.84% CPU utilization
Server
12.96% CPU utilization
9197 Mbps
IPv6
Client
12.46% CPU utilization
Server
14.48% CPU utilization
8963 Mbps
With UDP checksums, no remote checksum offload
IPv4
Client
15.67% CPU utilization
Server
14.83% CPU utilization
9094 Mbps
IPv6
Client
16.21% CPU utilization
Server
14.32% CPU utilization
9058 Mbps
No UDP checksums
IPv4
Client
15.03% CPU utilization
Server
23.09% CPU utilization
9089 Mbps
IPv6
Client
16.18% CPU utilization
Server
26.57% CPU utilization
8954 Mbps
Tom Herbert (3):
net: Add remcsum_adjust as common function for remote checksum offload
gue: Call remcsum_adjust
vxlan: Remote checksum offload
drivers/net/vxlan.c | 188 +++++++++++++++++++++++++++++++++++++++++--
include/net/checksum.h | 16 ++++
include/net/vxlan.h | 2 +
include/uapi/linux/if_link.h | 1 +
net/ipv4/fou.c | 84 ++++---------------
5 files changed, 216 insertions(+), 75 deletions(-)
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply
* [PATCH net-next 1/3] net: Add remcsum_adjust as common function for remote checksum offload
From: Tom Herbert @ 2014-11-24 23:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1416873150-12260-1-git-send-email-therbert@google.com>
This function does the work to update a checksum field as part of
remote checksum offload.
remcsum_adjust does the following:
1) Subtract out the calculated checksum from the beginning of the
packet (ptr arg) to the start offset.
2) Adjust the checksum field indicated by offset based on the modified
checksum value from above step.
3) Return the difference in the old checksum field value and the
new one. The caller will use this to update skb->csum and NAPI csum.
Signed-off-by: Tom Herbert <therbert@google.com>
---
include/net/checksum.h | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/include/net/checksum.h b/include/net/checksum.h
index 6465bae..e339a95 100644
--- a/include/net/checksum.h
+++ b/include/net/checksum.h
@@ -151,4 +151,20 @@ static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb,
(__force __be32)to, pseudohdr);
}
+static inline __wsum remcsum_adjust(void *ptr, __wsum csum,
+ int start, int offset)
+{
+ __sum16 *psum = (__sum16 *)(ptr + offset);
+ __wsum delta;
+
+ /* Subtract out checksum up to start */
+ csum = csum_sub(csum, csum_partial(ptr, start, 0));
+
+ /* Set derived checksum in packet */
+ delta = csum_sub(csum_fold(csum), *psum);
+ *psum = csum_fold(csum);
+
+ return delta;
+}
+
#endif
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* [PATCH net-next 2/3] gue: Call remcsum_adjust
From: Tom Herbert @ 2014-11-24 23:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1416873150-12260-1-git-send-email-therbert@google.com>
Change remote checksum offload to call remcsum_adjust. This also
eliminates the optimization to skip an IP header as part of the
adjustment (really does not seem to be much of a win).
Signed-off-by: Tom Herbert <therbert@google.com>
---
net/ipv4/fou.c | 84 ++++++++++++----------------------------------------------
1 file changed, 17 insertions(+), 67 deletions(-)
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 3dfe982..b986298 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -64,15 +64,13 @@ static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
}
static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
- void *data, int hdrlen, u8 ipproto)
+ void *data, size_t hdrlen, u8 ipproto)
{
__be16 *pd = data;
- u16 start = ntohs(pd[0]);
- u16 offset = ntohs(pd[1]);
- u16 poffset = 0;
- u16 plen;
- __wsum csum, delta;
- __sum16 *psum;
+ size_t start = ntohs(pd[0]);
+ size_t offset = ntohs(pd[1]);
+ size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+ __wsum delta;
if (skb->remcsum_offload) {
/* Already processed in GRO path */
@@ -80,35 +78,15 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
return guehdr;
}
- if (start > skb->len - hdrlen ||
- offset > skb->len - hdrlen - sizeof(u16))
- return NULL;
-
- if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
- __skb_checksum_complete(skb);
-
- plen = hdrlen + offset + sizeof(u16);
if (!pskb_may_pull(skb, plen))
return NULL;
guehdr = (struct guehdr *)&udp_hdr(skb)[1];
- if (ipproto == IPPROTO_IP && sizeof(struct iphdr) < plen) {
- struct iphdr *ip = (struct iphdr *)(skb->data + hdrlen);
-
- /* If next header happens to be IP we can skip that for the
- * checksum calculation since the IP header checksum is zero
- * if correct.
- */
- poffset = ip->ihl * 4;
- }
-
- csum = csum_sub(skb->csum, skb_checksum(skb, poffset + hdrlen,
- start - poffset - hdrlen, 0));
+ if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
+ __skb_checksum_complete(skb);
- /* Set derived checksum in packet */
- psum = (__sum16 *)(skb->data + hdrlen + offset);
- delta = csum_sub(csum_fold(csum), *psum);
- *psum = csum_fold(csum);
+ delta = remcsum_adjust((void *)guehdr + hdrlen,
+ skb->csum, start, offset);
/* Adjust skb->csum since we changed the packet */
skb->csum = csum_add(skb->csum, delta);
@@ -158,9 +136,6 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);
- /* Pull UDP header now, skb->data points to guehdr */
- __skb_pull(skb, sizeof(struct udphdr));
-
/* Pull csum through the guehdr now . This can be used if
* there is a remote checksum offload.
*/
@@ -188,7 +163,7 @@ static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
if (unlikely(guehdr->control))
return gue_control_message(skb, guehdr);
- __skb_pull(skb, hdrlen);
+ __skb_pull(skb, sizeof(struct udphdr) + hdrlen);
skb_reset_transport_header(skb);
return -guehdr->proto_ctype;
@@ -248,24 +223,17 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
size_t hdrlen, u8 ipproto)
{
__be16 *pd = data;
- u16 start = ntohs(pd[0]);
- u16 offset = ntohs(pd[1]);
- u16 poffset = 0;
- u16 plen;
- void *ptr;
- __wsum csum, delta;
- __sum16 *psum;
+ size_t start = ntohs(pd[0]);
+ size_t offset = ntohs(pd[1]);
+ size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+ __wsum delta;
if (skb->remcsum_offload)
return guehdr;
- if (start > skb_gro_len(skb) - hdrlen ||
- offset > skb_gro_len(skb) - hdrlen - sizeof(u16) ||
- !NAPI_GRO_CB(skb)->csum_valid || skb->remcsum_offload)
+ if (!NAPI_GRO_CB(skb)->csum_valid)
return NULL;
- plen = hdrlen + offset + sizeof(u16);
-
/* Pull checksum that will be written */
if (skb_gro_header_hard(skb, off + plen)) {
guehdr = skb_gro_header_slow(skb, off + plen, off);
@@ -273,26 +241,8 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
return NULL;
}
- ptr = (void *)guehdr + hdrlen;
-
- if (ipproto == IPPROTO_IP &&
- (hdrlen + sizeof(struct iphdr) < plen)) {
- struct iphdr *ip = (struct iphdr *)(ptr + hdrlen);
-
- /* If next header happens to be IP we can skip
- * that for the checksum calculation since the
- * IP header checksum is zero if correct.
- */
- poffset = ip->ihl * 4;
- }
-
- csum = csum_sub(NAPI_GRO_CB(skb)->csum,
- csum_partial(ptr + poffset, start - poffset, 0));
-
- /* Set derived checksum in packet */
- psum = (__sum16 *)(ptr + offset);
- delta = csum_sub(csum_fold(csum), *psum);
- *psum = csum_fold(csum);
+ delta = remcsum_adjust((void *)guehdr + hdrlen,
+ NAPI_GRO_CB(skb)->csum, start, offset);
/* Adjust skb->csum since we changed the packet */
skb->csum = csum_add(skb->csum, delta);
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* [PATCH net-next 3/3] vxlan: Remote checksum offload
From: Tom Herbert @ 2014-11-24 23:52 UTC (permalink / raw)
To: davem, netdev
In-Reply-To: <1416873150-12260-1-git-send-email-therbert@google.com>
Add support for remote checksum offload in VXLAN. This commandeers a
reserved bit to indicate that RCO is being done, and uses the low order
reserved eight bits of the VNI to hold the start and offset values in a
compressed manner.
Start is encoded in the low order seven bits of VNI. This is start >> 1
so that the checksum start offset is 0-254 using even values only.
Checksum offset (transport checksum field) is indicated in the high
order bit in the low order byte of the VNI. If the bit is set, the
checksum field is for UDP (so offset = start + 6), else checksum
field is for TCP (so offset = start + 16). Only TCP and UDP are
supported in this implementation.
Signed-off-by: Tom Herbert <therbert@google.com>
---
drivers/net/vxlan.c | 188 +++++++++++++++++++++++++++++++++++++++++--
include/net/vxlan.h | 2 +
include/uapi/linux/if_link.h | 1 +
3 files changed, 183 insertions(+), 8 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e9f81d4..763f95e 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -65,7 +65,17 @@
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
#define VXLAN_HLEN (sizeof(struct udphdr) + sizeof(struct vxlanhdr))
-#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
+#define VXLAN_F_REQ htonl(0x08000000) /* Required VXLAN flag */
+#define VXLAN_F_RCO htonl(0x00400000) /* Remote checksum offload */
+
+#define VXLAN_MANDATORY_FLAGS (VXLAN_F_REQ)
+#define VXLAN_ALL_FLAGS (VXLAN_F_REQ | VXLAN_F_RCO)
+
+#define VXLAN_RCO_MASK 0x7f /* Last byte of vni field */
+#define VXLAN_RCO_UDP 0x80 /* Indicate UDP RCO (TCP when not set *) */
+#define VXLAN_RCO_SHIFT 1 /* Left shift of start */
+#define VXLAN_RCO_SHIFT_MASK ((1 << VXLAN_RCO_SHIFT) - 1)
+#define VXLAN_MAX_REMCSUM_START (VXLAN_RCO_MASK << VXLAN_RCO_SHIFT)
/* UDP port for VXLAN traffic.
* The IANA assigned port is 4789, but the Linux default is 8472
@@ -545,6 +555,46 @@ static int vxlan_fdb_append(struct vxlan_fdb *f,
return 1;
}
+static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
+ unsigned int off,
+ struct vxlanhdr *vh, size_t hdrlen,
+ u32 data)
+{
+ size_t start, offset, plen;
+ __wsum delta;
+
+ if (skb->remcsum_offload)
+ return vh;
+
+ if (!NAPI_GRO_CB(skb)->csum_valid)
+ return NULL;
+
+ start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+ offset = start + ((data & VXLAN_RCO_UDP) ?
+ offsetof(struct udphdr, check) :
+ offsetof(struct tcphdr, check));
+
+ plen = hdrlen + offset + sizeof(u16);
+
+ /* Pull checksum that will be written */
+ if (skb_gro_header_hard(skb, off + plen)) {
+ vh = skb_gro_header_slow(skb, off + plen, off);
+ if (!vh)
+ return NULL;
+ }
+
+ delta = remcsum_adjust((void *)vh + hdrlen,
+ NAPI_GRO_CB(skb)->csum, start, offset);
+
+ /* Adjust skb->csum since we changed the packet */
+ skb->csum = csum_add(skb->csum, delta);
+ NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+ skb->remcsum_offload = 1;
+
+ return vh;
+}
+
static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
struct sk_buff *p, **pp = NULL;
@@ -566,6 +616,14 @@ static struct sk_buff **vxlan_gro_receive(struct sk_buff **head, struct sk_buff
skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
+ if (vh->vx_flags & VXLAN_F_RCO) {
+ vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
+ ntohl(vh->vx_vni));
+
+ if (!vh)
+ goto out;
+ }
+
off_eth = skb_gro_offset(skb);
hlen = off_eth + sizeof(*eh);
eh = skb_gro_header_fast(skb, off_eth);
@@ -1131,6 +1189,42 @@ static void vxlan_igmp_leave(struct work_struct *work)
dev_put(vxlan->dev);
}
+static struct vxlanhdr *vxlan_remcsum(struct sk_buff *skb, struct vxlanhdr *vh,
+ size_t hdrlen, u32 data)
+{
+ size_t start, offset, plen;
+ __wsum delta;
+
+ if (skb->remcsum_offload) {
+ /* Already processed in GRO path */
+ skb->remcsum_offload = 0;
+ return vh;
+ }
+
+ start = (data & VXLAN_RCO_MASK) << VXLAN_RCO_SHIFT;
+ offset = start + ((data & VXLAN_RCO_UDP) ?
+ offsetof(struct udphdr, check) :
+ offsetof(struct tcphdr, check));
+
+ plen = hdrlen + offset + sizeof(u16);
+
+ if (!pskb_may_pull(skb, plen))
+ return NULL;
+
+ vh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
+
+ if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
+ __skb_checksum_complete(skb);
+
+ delta = remcsum_adjust((void *)vh + hdrlen,
+ skb->csum, start, offset);
+
+ /* Adjust skb->csum since we changed the packet */
+ skb->csum = csum_add(skb->csum, delta);
+
+ return vh;
+}
+
/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
@@ -1143,8 +1237,8 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
/* Return packets with reserved bits set */
vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
- if (vxh->vx_flags != htonl(VXLAN_FLAGS) ||
- (vxh->vx_vni & htonl(0xff))) {
+ if ((vxh->vx_flags & VXLAN_MANDATORY_FLAGS) != VXLAN_MANDATORY_FLAGS ||
+ (vxh->vx_flags & ~VXLAN_ALL_FLAGS)) {
netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
goto error;
@@ -1152,6 +1246,14 @@ static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
if (iptunnel_pull_header(skb, VXLAN_HLEN, htons(ETH_P_TEB)))
goto drop;
+ vxh = (struct vxlanhdr *)(udp_hdr(skb) + 1);
+
+ if (vxh->vx_flags & VXLAN_F_RCO) {
+ vxh = vxlan_remcsum(skb, vxh, sizeof(struct vxlanhdr),
+ ntohl(vxh->vx_vni));
+ if (!vxh)
+ goto drop;
+ }
vs = rcu_dereference_sk_user_data(sk);
if (!vs)
@@ -1577,8 +1679,23 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
int min_headroom;
int err;
bool udp_sum = !udp_get_no_check6_tx(vs->sock->sk);
+ int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+ u16 hdrlen = sizeof(struct vxlanhdr);
+
+ if ((vs->flags & VXLAN_F_REMCSUM) &&
+ skb->ip_summed == CHECKSUM_PARTIAL) {
+ int csum_start = skb_checksum_start_offset(skb);
+
+ if (csum_start <= VXLAN_MAX_REMCSUM_START &&
+ !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
+ (skb->csum_offset == offsetof(struct udphdr, check) ||
+ skb->csum_offset == offsetof(struct tcphdr, check))) {
+ udp_sum = false;
+ type |= SKB_GSO_TUNNEL_REMCSUM;
+ }
+ }
- skb = udp_tunnel_handle_offloads(skb, udp_sum);
+ skb = iptunnel_handle_offloads(skb, udp_sum, type);
if (IS_ERR(skb))
return -EINVAL;
@@ -1598,9 +1715,25 @@ static int vxlan6_xmit_skb(struct vxlan_sock *vs,
return -ENOMEM;
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
- vxh->vx_flags = htonl(VXLAN_FLAGS);
+ vxh->vx_flags = VXLAN_MANDATORY_FLAGS;
vxh->vx_vni = vni;
+ if (type & SKB_GSO_TUNNEL_REMCSUM) {
+ u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
+ VXLAN_RCO_SHIFT;
+
+ if (skb->csum_offset == offsetof(struct udphdr, check))
+ data |= VXLAN_RCO_UDP;
+
+ vxh->vx_vni |= htonl(data);
+ vxh->vx_flags |= VXLAN_F_RCO;
+
+ if (!skb_is_gso(skb)) {
+ skb->ip_summed = CHECKSUM_NONE;
+ skb->encapsulation = 0;
+ }
+ }
+
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
udp_tunnel6_xmit_skb(vs->sock, dst, skb, dev, saddr, daddr, prio,
@@ -1618,8 +1751,23 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
int min_headroom;
int err;
bool udp_sum = !vs->sock->sk->sk_no_check_tx;
+ int type = udp_sum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
+ u16 hdrlen = sizeof(struct vxlanhdr);
+
+ if ((vs->flags & VXLAN_F_REMCSUM) &&
+ skb->ip_summed == CHECKSUM_PARTIAL) {
+ int csum_start = skb_checksum_start_offset(skb);
+
+ if (csum_start <= VXLAN_MAX_REMCSUM_START &&
+ !(csum_start & VXLAN_RCO_SHIFT_MASK) &&
+ (skb->csum_offset == offsetof(struct udphdr, check) ||
+ skb->csum_offset == offsetof(struct tcphdr, check))) {
+ udp_sum = false;
+ type |= SKB_GSO_TUNNEL_REMCSUM;
+ }
+ }
- skb = udp_tunnel_handle_offloads(skb, udp_sum);
+ skb = iptunnel_handle_offloads(skb, udp_sum, type);
if (IS_ERR(skb))
return -EINVAL;
@@ -1637,9 +1785,25 @@ int vxlan_xmit_skb(struct vxlan_sock *vs,
return -ENOMEM;
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
- vxh->vx_flags = htonl(VXLAN_FLAGS);
+ vxh->vx_flags = VXLAN_MANDATORY_FLAGS;
vxh->vx_vni = vni;
+ if (type & SKB_GSO_TUNNEL_REMCSUM) {
+ u32 data = (skb_checksum_start_offset(skb) - hdrlen) >>
+ VXLAN_RCO_SHIFT;
+
+ if (skb->csum_offset == offsetof(struct udphdr, check))
+ data |= VXLAN_RCO_UDP;
+
+ vxh->vx_vni |= htonl(data);
+ vxh->vx_flags |= VXLAN_F_RCO;
+
+ if (!skb_is_gso(skb)) {
+ skb->ip_summed = CHECKSUM_NONE;
+ skb->encapsulation = 0;
+ }
+ }
+
skb_set_inner_protocol(skb, htons(ETH_P_TEB));
return udp_tunnel_xmit_skb(vs->sock, rt, skb, src, dst, tos,
@@ -2229,6 +2393,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = {
[IFLA_VXLAN_UDP_CSUM] = { .type = NLA_U8 },
[IFLA_VXLAN_UDP_ZERO_CSUM6_TX] = { .type = NLA_U8 },
[IFLA_VXLAN_UDP_ZERO_CSUM6_RX] = { .type = NLA_U8 },
+ [IFLA_VXLAN_REMCSUM] = { .type = NLA_U8 },
};
static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[])
@@ -2350,6 +2515,7 @@ static struct vxlan_sock *vxlan_socket_create(struct net *net, __be16 port,
atomic_set(&vs->refcnt, 1);
vs->rcv = rcv;
vs->data = data;
+ vs->flags = flags;
/* Initialize the vxlan udp offloads structure */
vs->udp_offloads.port = port;
@@ -2547,6 +2713,9 @@ static int vxlan_newlink(struct net *net, struct net_device *dev,
nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
+ if (data[IFLA_VXLAN_REMCSUM] && nla_get_u8(data[IFLA_VXLAN_REMCSUM]))
+ vxlan->flags |= VXLAN_F_REMCSUM;
+
if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
vxlan->dst_port)) {
pr_info("duplicate VNI %u\n", vni);
@@ -2615,6 +2784,7 @@ static size_t vxlan_get_size(const struct net_device *dev)
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_CSUM */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_TX */
nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_UDP_ZERO_CSUM6_RX */
+ nla_total_size(sizeof(__u8)) + /* IFLA_VXLAN_REMCSUM */
0;
}
@@ -2680,7 +2850,9 @@ static int vxlan_fill_info(struct sk_buff *skb, const struct net_device *dev)
nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
!!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_TX)) ||
nla_put_u8(skb, IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
- !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)))
+ !!(vxlan->flags & VXLAN_F_UDP_ZERO_CSUM6_RX)) ||
+ nla_put_u8(skb, IFLA_VXLAN_REMCSUM,
+ !!(vxlan->flags & VXLAN_F_REMCSUM)))
goto nla_put_failure;
if (nla_put(skb, IFLA_VXLAN_PORT_RANGE, sizeof(ports), &ports))
diff --git a/include/net/vxlan.h b/include/net/vxlan.h
index 57cccd0..652e0dc 100644
--- a/include/net/vxlan.h
+++ b/include/net/vxlan.h
@@ -28,6 +28,7 @@ struct vxlan_sock {
struct hlist_head vni_list[VNI_HASH_SIZE];
atomic_t refcnt;
struct udp_offload udp_offloads;
+ u32 flags;
};
#define VXLAN_F_LEARN 0x01
@@ -39,6 +40,7 @@ struct vxlan_sock {
#define VXLAN_F_UDP_CSUM 0x40
#define VXLAN_F_UDP_ZERO_CSUM6_TX 0x80
#define VXLAN_F_UDP_ZERO_CSUM6_RX 0x100
+#define VXLAN_F_REMCSUM 0x200
struct vxlan_sock *vxlan_sock_add(struct net *net, __be16 port,
vxlan_rcv_t *rcv, void *data,
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 7072d83..d9e31e2 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -353,6 +353,7 @@ enum {
IFLA_VXLAN_UDP_CSUM,
IFLA_VXLAN_UDP_ZERO_CSUM6_TX,
IFLA_VXLAN_UDP_ZERO_CSUM6_RX,
+ IFLA_VXLAN_REMCSUM,
__IFLA_VXLAN_MAX
};
#define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1)
--
2.1.0.rc2.206.gedb03e5
^ permalink raw reply related
* Re: [PATCH 2/2] sh_eth: Fix asynchronous external abort
From: Simon Horman @ 2014-11-25 0:10 UTC (permalink / raw)
To: Geert Uytterhoeven
Cc: Yoshihiro Kaneko, netdev@vger.kernel.org, David S. Miller,
Magnus Damm, Linux-sh list
In-Reply-To: <CAMuHMdVeB0DmTr-xNHnZsHWao78Mdfk87+hThmiRu7qyZHMKWA@mail.gmail.com>
On Mon, Nov 24, 2014 at 09:41:18AM +0100, Geert Uytterhoeven wrote:
> On Mon, Nov 24, 2014 at 2:18 AM, Simon Horman <horms@verge.net.au> wrote:
> > On Thu, Nov 13, 2014 at 04:02:15PM +0900, Yoshihiro Kaneko wrote:
> >> From: Mitsuhiro Kimura <mitsuhiro.kimura.kc@renesas.com>
> >>
> >> When clock is disabled, Ethernet register access raise Bus error.
> >
> > I have spoken with Kimura-san and the problem may be reproduced by
> > calling ethtool with -s of -G while the network interface is down.
> >
> > e.g.:
> > ifconfig eth0 down
> > ethtool -G eth0 rx 512
>
> That makes sense.
>
> I think it would be good to add the reproduction steps to the commit message.
Yes, I agree entirely.
> > I have confirmed that the problem above appears in net-next
> > and appears to be resolved with this patch and the previous on
> > in this series (which seems to be a dependency) applied.
>
> Gr{oetje,eeting}s,
>
> Geert
>
> --
> Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org
>
> In personal conversations with technical people, I call myself a hacker. But
> when I'm talking to journalists I just say "programmer" or something like that.
> -- Linus Torvalds
> --
> To unsubscribe from this list: send the line "unsubscribe linux-sh" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
>
^ permalink raw reply
* Re: [PATCH v4 3/7] fs/splice: support compiling out splice-family syscalls
From: Josh Triplett @ 2014-11-25 0:49 UTC (permalink / raw)
To: Pieter Smith
Cc: Alexander Duyck, Alexander Viro, Alexei Starovoitov,
Andrew Morton, Bertrand Jacquin, Catalina Mocanu, Daniel Borkmann,
David S. Miller, Eric Dumazet, Eric W. Biederman,
Fabian Frederick, open list:FUSE: FILESYSTEM...,
Geert Uytterhoeven, Hugh Dickins, Iulia Manda, Jan Beulich,
J. Bruce Fields, Jeff Layton, open list:ABI/API, linux-fsdevel,
open list, "open
In-Reply-To: <1416870079-15254-4-git-send-email-pieter@boesman.nl>
On Tue, Nov 25, 2014 at 12:01:02AM +0100, Pieter Smith wrote:
> Many embedded systems will not need the splice-family syscalls (splice,
> vmsplice, tee and sendfile). Omitting them saves space. This adds a new EXPERT
> config option CONFIG_SYSCALL_SPLICE (default y) to support compiling them out.
>
> The goal is to completely compile out fs/splice along with the syscalls. To
> achieve this, the remaining patch-set will deal with fs/splice exports. As far
> as possible, the impact on other device drivers will be minimized so as to
> reduce the overal maintenance burden of CONFIG_SYSCALL_SPLICE.
>
> The use of exported functions will be solved by transparently mocking them out
> with static inlines. Uses of the exported pipe_buf_operations struct however
> require direct modification in fs/fuse and net/core. The next two patches will
> deal with this. A macro is defined that will assist with NULL'ing out callbacks
> when CONFIG_SYSCALL_SPLICE is undefined: __splice_p().
This message needs updating, since the patch series doesn't introduce or
use __splice_p anymore.
> Once all exports are solved, fs/splice can be compiled out.
>
> The bloat benefit of this patch given a tinyconfig is:
>
> add/remove: 0/16 grow/shrink: 2/5 up/down: 114/-3693 (-3579)
> function old new delta
> splice_direct_to_actor 348 416 +68
> splice_to_pipe 371 417 +46
> splice_from_pipe_next 107 106 -1
> fdput 11 - -11
> signal_pending 39 26 -13
> fdget 56 42 -14
> user_page_pipe_buf_ops 20 - -20
> user_page_pipe_buf_steal 25 - -25
> file_end_write 58 29 -29
> file_start_write 68 34 -34
> pipe_to_user 43 - -43
> wakeup_pipe_readers 54 - -54
> do_splice_to 87 - -87
> ipipe_prep.part 92 - -92
> opipe_prep.part 119 - -119
> sys_sendfile 122 - -122
> sys_sendfile64 126 - -126
> sys_vmsplice 137 - -137
> vmsplice_to_user 205 - -205
> sys_tee 491 - -491
> do_sendfile 492 - -492
> vmsplice_to_pipe 558 - -558
> sys_splice 1020 - -1020
>
> Signed-off-by: Pieter Smith <pieter@boesman.nl>
> ---
> fs/splice.c | 2 ++
> init/Kconfig | 10 ++++++++++
> kernel/sys_ni.c | 8 ++++++++
> 3 files changed, 20 insertions(+)
>
> diff --git a/fs/splice.c b/fs/splice.c
> index 44b201b..7c4c695 100644
> --- a/fs/splice.c
> +++ b/fs/splice.c
> @@ -1316,6 +1316,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
> return ret;
> }
>
> +#ifdef CONFIG_SYSCALL_SPLICE
> static int splice_pipe_to_pipe(struct pipe_inode_info *ipipe,
> struct pipe_inode_info *opipe,
> size_t len, unsigned int flags);
> @@ -2200,4 +2201,5 @@ COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
> return do_sendfile(out_fd, in_fd, NULL, count, 0);
> }
> #endif
> +#endif
>
> diff --git a/init/Kconfig b/init/Kconfig
> index d811d5f..dec9819 100644
> --- a/init/Kconfig
> +++ b/init/Kconfig
> @@ -1571,6 +1571,16 @@ config NTP
> system clock to an NTP server, you can disable this option to save
> space.
>
> +config SYSCALL_SPLICE
> + bool "Enable splice/vmsplice/tee/sendfile syscalls" if EXPERT
> + default y
> + help
> + This option enables the splice, vmsplice, tee and sendfile syscalls. These
> + are used by applications to: move data between buffers and arbitrary file
> + descriptors; "copy" data between buffers; or copy data from userspace into
> + buffers. If building an embedded system where no applications use these
> + syscalls, you can disable this option to save space.
> +
> config PCI_QUIRKS
> default y
> bool "Enable PCI quirk workarounds" if EXPERT
> diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
> index d2f5b00..25d5551 100644
> --- a/kernel/sys_ni.c
> +++ b/kernel/sys_ni.c
> @@ -170,6 +170,14 @@ cond_syscall(sys_fstat);
> cond_syscall(sys_stat);
> cond_syscall(sys_uname);
> cond_syscall(sys_olduname);
> +cond_syscall(sys_vmsplice);
> +cond_syscall(sys_splice);
> +cond_syscall(sys_tee);
> +cond_syscall(sys_sendfile);
> +cond_syscall(sys_sendfile64);
> +cond_syscall(compat_sys_vmsplice);
> +cond_syscall(compat_sys_sendfile);
> +cond_syscall(compat_sys_sendfile64);
>
> /* arch-specific weak syscall entries */
> cond_syscall(sys_pciconfig_read);
> --
> 2.1.0
>
^ permalink raw reply
* Re: [PATCH v4 0/7] kernel tinification: optionally compile out splice family of syscalls (splice, vmsplice, tee and sendfile)
From: Josh Triplett @ 2014-11-25 0:52 UTC (permalink / raw)
To: Pieter Smith
Cc: Alexander Duyck, Alexander Viro, Alexei Starovoitov,
Andrew Morton, Bertrand Jacquin, Catalina Mocanu, Daniel Borkmann,
David S. Miller, Eric Dumazet, Eric W. Biederman,
Fabian Frederick, open list:FUSE: FILESYSTEM...,
Geert Uytterhoeven, Hugh Dickins, Iulia Manda, Jan Beulich,
J. Bruce Fields, Jeff Layton, open list:ABI/API, linux-fsdevel,
open list, "open
In-Reply-To: <1416870079-15254-1-git-send-email-pieter@boesman.nl>
On Tue, Nov 25, 2014 at 12:00:59AM +0100, Pieter Smith wrote:
> REPO: https://github.com/smipi1/linux-tinification.git
>
> BRANCH: tiny/config-syscall-splice
>
> BACKGROUND: This patch-set forms part of the Linux Kernel Tinification effort (
> https://tiny.wiki.kernel.org/).
>
> GOAL: Support compiling out the splice family of syscalls (splice, vmsplice,
> tee and sendfile) along with all supporting infrastructure if not needed.
> Many embedded systems will not need the splice-family syscalls. Omitting them
> saves space.
>
> HISTORY:
> PATCH v4:
> - Drops __splice_p()
> - Let nfsd fall back to non-splice support when splice is compiled out
> - Style fixes
[...]
> RESULTS: A tinyconfig bloat-o-meter score for the entire patch-set:
>
> add/remove: 0/41 grow/shrink: 5/7 up/down: 23/-8422 (-8399)
I replied to one patch with a minor nit in the commit message. Other
than that, I don't see any obvious issues with this.
- Josh Triplett
^ permalink raw reply
* Re: Network throughput is reducedof in total bandwidth in Mips.
From: Eric Dumazet @ 2014-11-25 0:55 UTC (permalink / raw)
To: Sadasivan Shaiju; +Cc: linux-kernel, netdev
In-Reply-To: <d1b4ee5706f2dcb796b53ffb41cad1f8@mail.gmail.com>
On Mon, 2014-11-24 at 14:31 -0800, Sadasivan Shaiju wrote:
> HI,
>
> When using iperf with small buffers there is a performance
> degradation for 3.10 kernel from 2.6.32 kernel . Using
> profiling tools I am getting the following data.
>
> 2.6.32 kerne data
> ........
> samples % symbol name
> 160321 39.1122 r4k_wait
> 43731 10.6687 __do_softirq
> 27547 6.7204 cvm_oct_napi_poll_68
> 16569 4.0422 _raw_spin_unlock_irqrestore
> 12537 3.0586 cvm_oct_xmit
> 7362 1.7960 kfree
> 5916 1.4433 tcp_ack
> 5480 1.3369 net_rx_action
> 5353 1.3059 __copy_user_common
> 5097 1.2435 put_page
> 4447 1.0849 __kmalloc
> 4361 1.0639 kmem_cache_alloc
> 4359 1.0634 skb_segment
> 4309 1.0512 tcp_v4_rcv
> 4120 1.0051 __inet_lookup_established
> 4016 0.9798 ip_route_input
> 4010 0.9783 napi_complete
> 3766 0.9188 tcp_write_xmit
> 3297 0.8043 free_hot_cold_page
> 3189 0.7780 kmem_cache_free
>
> 3.10 kernel data
> .......
> samples % symbol name
> 186 8.6431 __do_softirq
> 127 5.9015 cvm_oct_napi_poll_68
> 80 3.7175 tcp_sendmsg
> 76 3.5316 tcp_write_xmit
> 72 3.3457 cvm_oct_xmit_lockless
> 71 3.2993 _raw_spin_lock_bh
> 48 2.2305 tcp_release_cb
> 47 2.1840 release_sock
> 44 2.0446 add_preempt_count
> 44 2.0446 tcp_transmit_skb
> 34 1.5799 skb_split
> 31 1.4405 sub_preempt_count
> 27 1.2546 dev_hard_start_xmit
> 25 1.1617 __srcu_read_lock
> 25 1.1617 skb_release_data
> 24 1.1152 tcp_ack
> 23 1.0688 __bzero
> 23 1.0688 _raw_spin_unlock_irqrestore
> 23 1.0688 ip_finish_output
> 22 1.0223 __copy_skb_header
> 21 0.9758 __kfree_skb
> 21 0.9758 ip_queue_xmit
>
> Looks like mainly the delay is causing by tcp_sendmsg() and
> tcp_write_xmit() from the stack . However if the buffer is
> increased to default (128k) there is no performance
> Degradation . This is happening only for small buffers.
>
> When iperf is used as below the bandwidth on 3.10 kernel is
> only around 600Mbps compared to 900Mbps in 2.6.32 kernel.
>
> ./iperf3 -c 10.162.103.131 -l 1500
>
> When iperf is ran with default buffers as follows the bandwidth
> is same in 3.10 kernel and 2.6.32 kernel.
>
> ./iperf3 -c 10.162.103.131
>
> Please let me know if there is any fixes available for this .
> --
CC netdev, where you can actually find some help ;)
Quite frankly, there are probably some reasons Octeon ethernet driver is
still in staging.
1) This REUSE_SKBUFFS_WITHOUT_FREE kludge is quite horrible... Dont know
if it was used in 2.6.32 and still used in 3.10 on your config.
2) TX completions seem to be delayed by undefined amount of time.
TCP Small Queues was added in 3.6 so this driver problem could
explain a lower throughput.
You could try adding skb_orphan() into this driver...
diff --git a/drivers/staging/octeon/ethernet-tx.c b/drivers/staging/octeon/ethernet-tx.c
index 4e54d854021955868e2c602ac829b9b217960efd..85f42f32419aabcda28f1b2aa44e396a462b3fb2 100644
--- a/drivers/staging/octeon/ethernet-tx.c
+++ b/drivers/staging/octeon/ethernet-tx.c
@@ -175,6 +175,7 @@ int cvm_oct_xmit(struct sk_buff *skb, struct net_device *dev)
*/
prefetch(priv);
+ skb_orphan(skb);
/*
* The check on CVMX_PKO_QUEUES_PER_PORT_* is designed to
* completely remove "qos" in the event neither interface
^ permalink raw reply related
* Re: [PATCH net-next 3/3] vxlan: Remote checksum offload
From: Jesse Gross @ 2014-11-25 1:06 UTC (permalink / raw)
To: Tom Herbert; +Cc: David Miller, netdev
In-Reply-To: <1416873150-12260-4-git-send-email-therbert@google.com>
On Mon, Nov 24, 2014 at 3:52 PM, Tom Herbert <therbert@google.com> wrote:
> Add support for remote checksum offload in VXLAN. This commandeers a
> reserved bit to indicate that RCO is being done, and uses the low order
> reserved eight bits of the VNI to hold the start and offset values in a
> compressed manner.
Why do you think that this is OK for you to do? It's clear that there
is no consensus for this (and in fact there are other proposals that
use that bit in a different way).
^ permalink raw reply
* Re: [PATCH net_test_tools] route_bench: Fix bug in DST_ITERATE option
From: Vijay Subramanian @ 2014-11-25 1:18 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20141124.160932.1535765335085310139.davem@davemloft.net>
>> Signed-off-by: Vijay Subramanian <subramanian.vijay@gmail.com>
>
> This does not apply to the 'net' tree.
David,
The patch was targeted not against 'net' tree but against test suite
at https://git.kernel.org/pub/scm/linux/kernel/git/davem/net_test_tools.git
as indicated in subject. Would you like me to resubmit this making it
clear in commit log too?
-vijay
^ permalink raw reply
* RE: [PATCH] net: fec: init maximum receive buffer size for ring1 and ring2
From: fugang.duan @ 2014-11-25 1:27 UTC (permalink / raw)
To: David Miller
Cc: netdev@vger.kernel.org, bhutchings@solarflare.com,
stephen@networkplumber.org, festevam@gmail.com
In-Reply-To: <20141124.152250.380142287256307570.davem@davemloft.net>
From: David Miller <davem@davemloft.net> Sent: Tuesday, November 25, 2014 4:23 AM
>To: Duan Fugang-B38611
>Cc: netdev@vger.kernel.org; bhutchings@solarflare.com;
>stephen@networkplumber.org; festevam@gmail.com
>Subject: Re: [PATCH] net: fec: init maximum receive buffer size for ring1
>and ring2
>
>From: Fugang Duan <b38611@freescale.com>
>Date: Sun, 23 Nov 2014 17:23:06 +0800
>
>> i.MX6SX fec support three rx ring1, the current driver lost to init
>> ring1 and ring2 maximum receive buffer size, that cause receving frame
>> date length error. The driver reports "rcv is not +last" error log in
>> user case.
>>
>> Signed-off-by: Fugang Duan <B38611@freescale.com>
>
>This patch does not apply to the 'net' tree, although it does apply
>cleanly to the net-next tree.
>
>Determining which tree a patch is for is not my job, it is your's.
>
>Therefore you must always explicitly state what tree your patch is
>intended to be added to, by starting your Subject line with "[PATCH net] "
>or "[PATCH net-next] ".
>
>I've applied this, but next time I will just ask you to properly submit
>the patch instead.
David, thanks. I note this the next time.
Regards,
Andy
^ permalink raw reply
* Re: [PATCH 1/2] sh_eth: Fix sleeping function called from invalid context
From: Simon Horman @ 2014-11-25 2:17 UTC (permalink / raw)
To: Sergei Shtylyov
Cc: Yoshihiro Kaneko, netdev, David S. Miller, Magnus Damm, linux-sh
In-Reply-To: <546531D6.3090009@cogentembedded.com>
Hi Sergei,
On Fri, Nov 14, 2014 at 01:33:58AM +0300, Sergei Shtylyov wrote:
> On 11/13/2014 10:02 AM, Yoshihiro Kaneko wrote:
>
> >From: Mitsuhiro Kimura <mitsuhiro.kimura.kc@renesas.com>
>
> >Fix the bug as follows:
>
> >----
> >[ 1238.161349] BUG: sleeping function called from invalid context at drivers/base/power/runtime.c:952
> >[ 1238.188279] in_atomic(): 1, irqs_disabled(): 0, pid: 1388, name: cat
> >[ 1238.207425] CPU: 0 PID: 1388 Comm: cat Not tainted 3.10.31-ltsi-00046-gefa0b46 #1087
> >[ 1238.230737] Backtrace:
> >[ 1238.238123] [<c0012e64>] (dump_backtrace+0x0/0x10c) from [<c0013000>] (show_stack+0x18/0x1c)
> >[ 1238.263499] r6:000003b8 r5:c06160c0 r4:c0669e00 r3:00404000
> >[ 1238.280583] [<c0012fe8>] (show_stack+0x0/0x1c) from [<c04515a4>] (dump_stack+0x20/0x28)
> >[ 1238.304631] [<c0451584>] (dump_stack+0x0/0x28) from [<c004970c>] (__might_sleep+0xf8/0x118)
> >[ 1238.329734] [<c0049614>] (__might_sleep+0x0/0x118) from [<c02465ac>] (__pm_runtime_resume+0x38/0x90)
> >[ 1238.357170] r7:d616f000 r6:c049c458 r5:00000004 r4:d6a17210
> >[ 1238.374251] [<c0246574>] (__pm_runtime_resume+0x0/0x90) from [<c029b1c4>] (sh_eth_get_stats+0x44/0x280)
> >[ 1238.402468] r7:d616f000 r6:c049c458 r5:d5c21000 r4:d5c21000
> >[ 1238.419552] [<c029b180>] (sh_eth_get_stats+0x0/0x280) from [<c03ae39c>] (dev_get_stats+0x54/0x88)
> >[ 1238.446204] r5:d5c21000 r4:d5ed7e08
> >[ 1238.456980] [<c03ae348>] (dev_get_stats+0x0/0x88) from [<c03c677c>] (netstat_show.isra.15+0x54/0x9c)
> >[ 1238.484413] r6:d5c21000 r5:d5c21238 r4:00000028 r3:00000001
> >[ 1238.501495] [<c03c6728>] (netstat_show.isra.15+0x0/0x9c) from [<c03c69b8>] (show_tx_errors+0x18/0x1c)
> >[ 1238.529196] r7:d5f945d8 r6:d5f945c0 r5:c049716c r4:c0650e7c
> >[ 1238.546279] [<c03c69a0>] (show_tx_errors+0x0/0x1c) from [<c023963c>] (dev_attr_show+0x24/0x50)
> >[ 1238.572157] [<c0239618>] (dev_attr_show+0x0/0x50) from [<c010c148>] (sysfs_read_file+0xb0/0x140)
> >[ 1238.598554] r5:c049716c r4:d5c21240
> >[ 1238.609326] [<c010c098>] (sysfs_read_file+0x0/0x140) from [<c00b9ee4>] (vfs_read+0xb0/0x13c)
> >[ 1238.634679] [<c00b9e34>] (vfs_read+0x0/0x13c) from [<c00ba0ac>] (SyS_read+0x44/0x74)
> >[ 1238.657944] r8:bef45bf0 r7:00000000 r6:d6ac0600 r5:00000000 r4:00000000
> >[ 1238.678172] [<c00ba068>] (SyS_read+0x0/0x74) from [<c000eec0>] (ret_fast_syscall+0x0/0x30)
> >----
>
> How to reproduce this?
I have spoken with Kimura-san and the problem may be reproduced by
building the kernel with CONFIG_DEBUG_ATOMIC_SLEEP=y and reading network
statistics while the network interface is down.
e.g.:
ifconfig eth0 down
cat /sys/class/net/eth0/statistics/tx_errors
I have confirmed that the problem above appears in net-next
and appears to be resolved by this patch.
Would you be happy with this patch if the changelog was enhanced
and the minor issue you point our below was resolved?
> >Signed-off-by: Mitsuhiro Kimura <mitsuhiro.kimura.kc@renesas.com>
> >Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
>
> [...]
>
> >diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
> >index b37c427..9a1c550 100644
> >--- a/drivers/net/ethernet/renesas/sh_eth.h
> >+++ b/drivers/net/ethernet/renesas/sh_eth.h
> >@@ -508,6 +508,7 @@ struct sh_eth_private {
> > u32 rx_buf_sz; /* Based on MTU+slack. */
> > int edmac_endian;
> > struct napi_struct napi;
> >+ bool is_opened;
>
> Placing it after 'vlan_num_ids' (and making it a bitfield?) would
> probably allow to save some space.
>
> WBR, Sergei
>
^ permalink raw reply
* Re: [RFC] situation with csum_and_copy_... API
From: Al Viro @ 2014-11-25 2:40 UTC (permalink / raw)
To: David Miller; +Cc: torvalds, netdev, linux-kernel, target-devel, nab, hch
In-Reply-To: <20141122.022444.425003630662787798.davem@davemloft.net>
On Sat, Nov 22, 2014 at 02:24:44AM -0500, David Miller wrote:
> From: Al Viro <viro@ZenIV.linux.org.uk>
> Date: Sat, 22 Nov 2014 04:28:57 +0000
>
> > OK, here's the next bunch. Sorry about the delay, iov_iter.c stuff
> > took most of the day (and it's not included in this pile). Please, review.
>
> I read over this stuff twice and this series looks fine to me.
>
> Since this is the weekend... maybe wait until Monday for other feedback
> then give me a pull request?
I'll probably repost the patches with updates folded in first...
FWIW, the current situation is
* all but one ->recvmsg() instances switched to iov_iter primitives
(the exception is one of the AF_ALG instances and I know what to do with it).
Consequently, they do not drain iovecs anymore and simply advance ->msg_iter.
* kvec-based iov_iter work just fine without set_fs(KERNEL_DS). And
so do ->recvmsg() instances that had received such iov_iter.
* memcpy_to_iovec() and skb_copy_datagram_iovec() are gone - no users
left.
I'm about to start on ->sendmsg() side of the things. The interesting
question is whether tcp_send_syn_data() is doing the right thing if it
runs into EFAULT when copying iovec from userland.
As it is, it gives up on the skb it has allocated and falls back to normal
handshake. I can duplicate that behaviour, all right, but why not simply
do skb_trim(syn_data, <actually copied>) and do fallback only if nothing
got copied at all? Is there any problem with that?
The reason why I'm asking is that it's easier to just use copy_from_iter()
and let the damn thing advance. Not a lot of pain to preserve the original
iov_iter (all 5 words of it) and copy it back in case of failure, but I'd
rather understood what's wrong with simpler approach...
Anyway, the current branch is in vfs.git#iov_iter-net. Current balance is
about -0.5KLoC and that's not counting the simplifications that will become
possible in callers of kernel_sendmg/kernel_recvmsg... I'll post the beginning
of that queue (the same 17 commits in the beginning) later tonight and wait
for review...
^ permalink raw reply
* linux-next: manual merge of the net-next tree with the vfs tree
From: Stephen Rothwell @ 2014-11-25 2:42 UTC (permalink / raw)
To: David Miller, netdev, Al Viro
Cc: linux-next, linux-kernel, Steven Rostedt (Red Hat),
Marcelo Leitner, Pablo Neira Ayuso
[-- Attachment #1: Type: text/plain, Size: 2166 bytes --]
Hi all,
Today's linux-next merge of the net-next tree got a conflict in
net/netfilter/nf_log.c between commit e71456ae9871 ("netfilter: Remove
checks of seq_printf() return values") from the vfs tree and commit
0c26ed1c07f1 ("netfilter: nf_log: Introduce nft_log_dereference()
macro") from the net-next tree.
I fixed it up (see below) and can carry the fix as necessary (no action
is required).
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
diff --cc net/netfilter/nf_log.c
index 6e3b9117db1f,49a64174f3f1..000000000000
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@@ -294,39 -303,35 +303,37 @@@ static int seq_show(struct seq_file *s
{
loff_t *pos = v;
const struct nf_logger *logger;
- int i, ret;
+ int i;
struct net *net = seq_file_net(s);
- logger = rcu_dereference_protected(net->nf.nf_loggers[*pos],
- lockdep_is_held(&nf_log_mutex));
+ logger = nft_log_dereference(net->nf.nf_loggers[*pos]);
if (!logger)
- ret = seq_printf(s, "%2lld NONE (", *pos);
+ seq_printf(s, "%2lld NONE (", *pos);
else
- ret = seq_printf(s, "%2lld %s (", *pos, logger->name);
+ seq_printf(s, "%2lld %s (", *pos, logger->name);
- if (ret < 0)
- return ret;
+ if (seq_has_overflowed(s))
+ return -ENOSPC;
for (i = 0; i < NF_LOG_TYPE_MAX; i++) {
if (loggers[*pos][i] == NULL)
continue;
- logger = rcu_dereference_protected(loggers[*pos][i],
- lockdep_is_held(&nf_log_mutex));
+ logger = nft_log_dereference(loggers[*pos][i]);
- ret = seq_printf(s, "%s", logger->name);
- if (ret < 0)
- return ret;
- if (i == 0 && loggers[*pos][i + 1] != NULL) {
- ret = seq_printf(s, ",");
- if (ret < 0)
- return ret;
- }
+ seq_printf(s, "%s", logger->name);
+ if (i == 0 && loggers[*pos][i + 1] != NULL)
+ seq_printf(s, ",");
+
+ if (seq_has_overflowed(s))
+ return -ENOSPC;
}
- return seq_printf(s, ")\n");
+ seq_printf(s, ")\n");
+
+ if (seq_has_overflowed(s))
+ return -ENOSPC;
+ return 0;
}
static const struct seq_operations nflog_seq_ops = {
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 819 bytes --]
^ permalink raw reply
* Fix Me in htc.c
From: nick @ 2014-11-25 2:45 UTC (permalink / raw)
To: kvalo; +Cc: netdev, linux-wireless, linville, ath10k, linux-kernel
Greetings Kalle and John,
I am wondering about what amount we need to reserve for amount of bytes needed for the function, ath10k_htc_build_tx_ctrl_skb in htc.c If one of you can send me the amount of bytes we need to
reserve for this to function correctly, I will gladly write a patch for this :).
Nick
^ permalink raw reply
* Re: [PATCH net-next 3/3] vxlan: Remote checksum offload
From: Tom Herbert @ 2014-11-25 2:50 UTC (permalink / raw)
To: Jesse Gross; +Cc: David Miller, netdev
In-Reply-To: <CAEP_g=9_6Rq9Ssr_2q4MKfSDxeL23rbExP5ziHbeCL0Nx-VTvw@mail.gmail.com>
On Mon, Nov 24, 2014 at 5:06 PM, Jesse Gross <jesse@nicira.com> wrote:
> On Mon, Nov 24, 2014 at 3:52 PM, Tom Herbert <therbert@google.com> wrote:
>> Add support for remote checksum offload in VXLAN. This commandeers a
>> reserved bit to indicate that RCO is being done, and uses the low order
>> reserved eight bits of the VNI to hold the start and offset values in a
>> compressed manner.
>
> Why do you think that this is OK for you to do? It's clear that there
> is no consensus for this (and in fact there are other proposals that
> use that bit in a different way).
I asked on nvo3 list (which I believe is the appropriate forum) what
the best way to do this is but haven't gotten any response. I will ask
again-- I would assume that with an implementation and data in hand
that might be better basis for discussion.
The flag bit is currently unused in the Linux implementation, so I
don't think it can break anything as of now. I suppose we could make
RCO for VXLAN a config option and possibly change to use a different
if consensus is reached on the right approach in the future.
Tom
^ permalink raw reply
* Charity Work
From: luv2charitys @ 2014-11-25 2:57 UTC (permalink / raw)
To: netdev
Hello,this is Mr Paul N,i sent you an email on charity work but i am yet to hear fom you,do reply with this code CHA-2015 to my email address paulcharity@qq.com i Look forward to hearing from you this time,God bless Brother Paul
^ permalink raw reply
* [PATCH net-next] cxgb4/cxgb4vf/csiostor: Add T4/T5 PCI ID Table
From: Hariprasad Shenai @ 2014-11-25 3:03 UTC (permalink / raw)
To: netdev, linux-scsi
Cc: davem, JBottomley, hch, leedom, anish, nirranjan, kumaras,
praveenm, varun, Hariprasad Shenai
Add a new file t4_pci_id_tbl.h that contains T4/T5 PCI ID Table so that for all
drivers that uses T4/T5 PCI functions changes can be done in one place.
checkpatch.pl script reports following error, which if tried to fix ends up in
compilation error.
ERROR: Macros with complex values should be enclosed in parentheses
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END \
+ { 0, } \
+ }
WARNING: added, moved or deleted file(s), does MAINTAINERS need updating?
new file mode 100644
ERROR: Macros with complex values should be enclosed in parentheses
+#define CH_PCI_ID_TABLE_FENTRY(devid) \
+ CH_PCI_ID_TABLE_ENTRY((devid) | \
+ ((CH_PCI_DEVICE_ID_FUNCTION) << 8)), \
+ CH_PCI_ID_TABLE_ENTRY((devid) | \
+ ((CH_PCI_DEVICE_ID_FUNCTION2) << 8))
ERROR: Macros with complex values should be enclosed in parentheses
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END { 0, } }
ERROR: Macros with complex values should be enclosed in parentheses
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END { 0, } }
Signed-off-by: Hariprasad Shenai <hariprasad@chelsio.com>
---
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 125 +++-------------
drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 160 ++++++++++++++++++++
.../net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c | 73 ++--------
drivers/scsi/csiostor/csio_hw_chip.h | 49 +------
drivers/scsi/csiostor/csio_init.c | 64 +++------
5 files changed, 209 insertions(+), 262 deletions(-)
create mode 100644 drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index a576da1..3aea82b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -210,114 +210,25 @@ struct filter_entry {
NETIF_MSG_TIMER | NETIF_MSG_IFDOWN | NETIF_MSG_IFUP |\
NETIF_MSG_RX_ERR | NETIF_MSG_TX_ERR)
-#define CH_DEVICE(devid, data) { PCI_VDEVICE(CHELSIO, devid), (data) }
-
-static const struct pci_device_id cxgb4_pci_tbl[] = {
- CH_DEVICE(0xa000, 0), /* PE10K */
- CH_DEVICE(0x4001, -1),
- CH_DEVICE(0x4002, -1),
- CH_DEVICE(0x4003, -1),
- CH_DEVICE(0x4004, -1),
- CH_DEVICE(0x4005, -1),
- CH_DEVICE(0x4006, -1),
- CH_DEVICE(0x4007, -1),
- CH_DEVICE(0x4008, -1),
- CH_DEVICE(0x4009, -1),
- CH_DEVICE(0x400a, -1),
- CH_DEVICE(0x400d, -1),
- CH_DEVICE(0x400e, -1),
- CH_DEVICE(0x4080, -1),
- CH_DEVICE(0x4081, -1),
- CH_DEVICE(0x4082, -1),
- CH_DEVICE(0x4083, -1),
- CH_DEVICE(0x4084, -1),
- CH_DEVICE(0x4085, -1),
- CH_DEVICE(0x4086, -1),
- CH_DEVICE(0x4087, -1),
- CH_DEVICE(0x4088, -1),
- CH_DEVICE(0x4401, 4),
- CH_DEVICE(0x4402, 4),
- CH_DEVICE(0x4403, 4),
- CH_DEVICE(0x4404, 4),
- CH_DEVICE(0x4405, 4),
- CH_DEVICE(0x4406, 4),
- CH_DEVICE(0x4407, 4),
- CH_DEVICE(0x4408, 4),
- CH_DEVICE(0x4409, 4),
- CH_DEVICE(0x440a, 4),
- CH_DEVICE(0x440d, 4),
- CH_DEVICE(0x440e, 4),
- CH_DEVICE(0x4480, 4),
- CH_DEVICE(0x4481, 4),
- CH_DEVICE(0x4482, 4),
- CH_DEVICE(0x4483, 4),
- CH_DEVICE(0x4484, 4),
- CH_DEVICE(0x4485, 4),
- CH_DEVICE(0x4486, 4),
- CH_DEVICE(0x4487, 4),
- CH_DEVICE(0x4488, 4),
- CH_DEVICE(0x5001, 4),
- CH_DEVICE(0x5002, 4),
- CH_DEVICE(0x5003, 4),
- CH_DEVICE(0x5004, 4),
- CH_DEVICE(0x5005, 4),
- CH_DEVICE(0x5006, 4),
- CH_DEVICE(0x5007, 4),
- CH_DEVICE(0x5008, 4),
- CH_DEVICE(0x5009, 4),
- CH_DEVICE(0x500A, 4),
- CH_DEVICE(0x500B, 4),
- CH_DEVICE(0x500C, 4),
- CH_DEVICE(0x500D, 4),
- CH_DEVICE(0x500E, 4),
- CH_DEVICE(0x500F, 4),
- CH_DEVICE(0x5010, 4),
- CH_DEVICE(0x5011, 4),
- CH_DEVICE(0x5012, 4),
- CH_DEVICE(0x5013, 4),
- CH_DEVICE(0x5014, 4),
- CH_DEVICE(0x5015, 4),
- CH_DEVICE(0x5080, 4),
- CH_DEVICE(0x5081, 4),
- CH_DEVICE(0x5082, 4),
- CH_DEVICE(0x5083, 4),
- CH_DEVICE(0x5084, 4),
- CH_DEVICE(0x5085, 4),
- CH_DEVICE(0x5086, 4),
- CH_DEVICE(0x5087, 4),
- CH_DEVICE(0x5088, 4),
- CH_DEVICE(0x5401, 4),
- CH_DEVICE(0x5402, 4),
- CH_DEVICE(0x5403, 4),
- CH_DEVICE(0x5404, 4),
- CH_DEVICE(0x5405, 4),
- CH_DEVICE(0x5406, 4),
- CH_DEVICE(0x5407, 4),
- CH_DEVICE(0x5408, 4),
- CH_DEVICE(0x5409, 4),
- CH_DEVICE(0x540A, 4),
- CH_DEVICE(0x540B, 4),
- CH_DEVICE(0x540C, 4),
- CH_DEVICE(0x540D, 4),
- CH_DEVICE(0x540E, 4),
- CH_DEVICE(0x540F, 4),
- CH_DEVICE(0x5410, 4),
- CH_DEVICE(0x5411, 4),
- CH_DEVICE(0x5412, 4),
- CH_DEVICE(0x5413, 4),
- CH_DEVICE(0x5414, 4),
- CH_DEVICE(0x5415, 4),
- CH_DEVICE(0x5480, 4),
- CH_DEVICE(0x5481, 4),
- CH_DEVICE(0x5482, 4),
- CH_DEVICE(0x5483, 4),
- CH_DEVICE(0x5484, 4),
- CH_DEVICE(0x5485, 4),
- CH_DEVICE(0x5486, 4),
- CH_DEVICE(0x5487, 4),
- CH_DEVICE(0x5488, 4),
- { 0, }
-};
+/* Macros needed to support the PCI Device ID Table ...
+ */
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \
+ static struct pci_device_id cxgb4_pci_tbl[] = {
+#define CH_PCI_DEVICE_ID_FUNCTION 0x4
+
+/* Include PCI Device IDs for both PF4 and PF0-3 so our PCI probe() routine is
+ * called for both.
+ */
+#define CH_PCI_DEVICE_ID_FUNCTION2 0x0
+
+#define CH_PCI_ID_TABLE_ENTRY(devid) \
+ {PCI_VDEVICE(CHELSIO, (devid)), 4}
+
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END \
+ { 0, } \
+ }
+
+#include "t4_pci_id_tbl.h"
#define FW4_FNAME "cxgb4/t4fw.bin"
#define FW5_FNAME "cxgb4/t5fw.bin"
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
new file mode 100644
index 0000000..9e4f95a
--- /dev/null
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -0,0 +1,160 @@
+/*
+ * This file is part of the Chelsio T4/T5 Ethernet driver for Linux.
+ *
+ * Copyright (c) 2003-2014 Chelsio Communications, Inc. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses. You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or
+ * without modification, are permitted provided that the following
+ * conditions are met:
+ *
+ * - Redistributions of source code must retain the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above
+ * copyright notice, this list of conditions and the following
+ * disclaimer in the documentation and/or other materials
+ * provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __T4_PCI_ID_TBL_H__
+#define __T4_PCI_ID_TBL_H__
+
+/* The code can defined cpp macros for creating a PCI Device ID Table. This is
+ * useful because it allows the PCI ID Table to be maintained in a single place.
+ *
+ * The macros are:
+ *
+ * CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
+ * -- Used to start the definition of the PCI ID Table.
+ *
+ * CH_PCI_DEVICE_ID_FUNCTION
+ * -- The PCI Function Number to use in the PCI Device ID Table. "0"
+ * -- for drivers attaching to PF0-3, "4" for drivers attaching to PF4,
+ * -- "8" for drivers attaching to SR-IOV Virtual Functions, etc.
+ *
+ * CH_PCI_DEVICE_ID_FUNCTION2 [optional]
+ * -- If defined, create a PCI Device ID Table with both
+ * -- CH_PCI_DEVICE_ID_FUNCTION and CH_PCI_DEVICE_ID_FUNCTION2 populated.
+ *
+ * CH_PCI_ID_TABLE_ENTRY(DeviceID)
+ * -- Used for the individual PCI Device ID entries. Note that we will
+ * -- be adding a trailing comma (",") after all of the entries (and
+ * -- between the pairs of entries if CH_PCI_DEVICE_ID_FUNCTION2 is defined).
+ *
+ * CH_PCI_DEVICE_ID_TABLE_DEFINE_END
+ * -- Used to finish the definition of the PCI ID Table. Note that we
+ * -- will be adding a trailing semi-colon (";") here.
+ */
+#ifdef CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
+
+#ifndef CH_PCI_DEVICE_ID_FUNCTION
+#error CH_PCI_DEVICE_ID_FUNCTION not defined!
+#endif
+#ifndef CH_PCI_ID_TABLE_ENTRY
+#error CH_PCI_ID_TABLE_ENTRY not defined!
+#endif
+#ifndef CH_PCI_DEVICE_ID_TABLE_DEFINE_END
+#error CH_PCI_DEVICE_ID_TABLE_DEFINE_END not defined!
+#endif
+
+/* T4 and later ASICs use a PCI Device ID scheme of 0xVFPP where:
+ *
+ * V = "4" for T4; "5" for T5, etc.
+ * F = "0" for PF 0..3; "4".."7" for PF4..7; and "8" for VFs
+ * PP = adapter product designation
+ *
+ * We use this consistency in order to create the proper PCI Device IDs
+ * for the specified CH_PCI_DEVICE_ID_FUNCTION.
+ */
+#ifndef CH_PCI_DEVICE_ID_FUNCTION2
+#define CH_PCI_ID_TABLE_FENTRY(devid) \
+ CH_PCI_ID_TABLE_ENTRY((devid) | \
+ ((CH_PCI_DEVICE_ID_FUNCTION) << 8))
+#else
+#define CH_PCI_ID_TABLE_FENTRY(devid) \
+ CH_PCI_ID_TABLE_ENTRY((devid) | \
+ ((CH_PCI_DEVICE_ID_FUNCTION) << 8)), \
+ CH_PCI_ID_TABLE_ENTRY((devid) | \
+ ((CH_PCI_DEVICE_ID_FUNCTION2) << 8))
+#endif
+
+CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
+ /* T4 adapters:
+ */
+ CH_PCI_ID_TABLE_FENTRY(0x4000), /* T440-dbg */
+ CH_PCI_ID_TABLE_FENTRY(0x4001), /* T420-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4002), /* T422-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4003), /* T440-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4004), /* T420-bch */
+ CH_PCI_ID_TABLE_FENTRY(0x4005), /* T440-bch */
+ CH_PCI_ID_TABLE_FENTRY(0x4006), /* T440-ch */
+ CH_PCI_ID_TABLE_FENTRY(0x4007), /* T420-so */
+ CH_PCI_ID_TABLE_FENTRY(0x4008), /* T420-cx */
+ CH_PCI_ID_TABLE_FENTRY(0x4009), /* T420-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x400a), /* T404-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x400b), /* B420-sr */
+ CH_PCI_ID_TABLE_FENTRY(0x400c), /* B404-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x400d), /* T480-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x400e), /* T440-LP-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4080), /* Custom T480-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4081), /* Custom T440-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4082), /* Custom T420-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4083), /* Custom T420-xaui */
+ CH_PCI_ID_TABLE_FENTRY(0x4084), /* Custom T440-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4085), /* Custom T420-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4086), /* Custom T440-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x4087), /* Custom T440-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x4088), /* Custom T440 2-xaui, 2-xfi */
+
+ /* T5 adapters:
+ */
+ CH_PCI_ID_TABLE_FENTRY(0x5000), /* T580-dbg */
+ CH_PCI_ID_TABLE_FENTRY(0x5001), /* T520-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5002), /* T522-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5003), /* T540-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5004), /* T520-bch */
+ CH_PCI_ID_TABLE_FENTRY(0x5005), /* T540-bch */
+ CH_PCI_ID_TABLE_FENTRY(0x5006), /* T540-ch */
+ CH_PCI_ID_TABLE_FENTRY(0x5007), /* T520-so */
+ CH_PCI_ID_TABLE_FENTRY(0x5008), /* T520-cx */
+ CH_PCI_ID_TABLE_FENTRY(0x5009), /* T520-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x500a), /* T504-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x500b), /* B520-sr */
+ CH_PCI_ID_TABLE_FENTRY(0x500c), /* B504-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x500d), /* T580-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x500e), /* T540-LP-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5010), /* T580-LP-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5011), /* T520-LL-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5012), /* T560-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5013), /* T580-chr */
+ CH_PCI_ID_TABLE_FENTRY(0x5014), /* T580-so */
+ CH_PCI_ID_TABLE_FENTRY(0x5015), /* T502-bt */
+ CH_PCI_ID_TABLE_FENTRY(0x5080), /* Custom T540-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5081), /* Custom T540-LL-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5082), /* Custom T504-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5083), /* Custom T540-LP-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x5084), /* Custom T580-cr */
+ CH_PCI_ID_TABLE_FENTRY(0x5085), /* Custom 3x T580-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x5086), /* Custom 2x T580-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x5087), /* Custom T580-CR */
+ CH_PCI_ID_TABLE_FENTRY(0x5088), /* Custom T570-CR */
+CH_PCI_DEVICE_ID_TABLE_DEFINE_END;
+
+#endif /* CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN */
+
+#endif /* __T4_PCI_ID_TBL_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
index 099f7ce..ad88246 100644
--- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c
@@ -2908,67 +2908,18 @@ static void cxgb4vf_pci_shutdown(struct pci_dev *pdev)
pci_set_drvdata(pdev, NULL);
}
-/*
- * PCI Device registration data structures.
- */
-#define CH_DEVICE(devid) \
- { PCI_VENDOR_ID_CHELSIO, devid, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }
-
-static const struct pci_device_id cxgb4vf_pci_tbl[] = {
- CH_DEVICE(0xb000), /* PE10K FPGA */
- CH_DEVICE(0x4801), /* T420-cr */
- CH_DEVICE(0x4802), /* T422-cr */
- CH_DEVICE(0x4803), /* T440-cr */
- CH_DEVICE(0x4804), /* T420-bch */
- CH_DEVICE(0x4805), /* T440-bch */
- CH_DEVICE(0x4806), /* T460-ch */
- CH_DEVICE(0x4807), /* T420-so */
- CH_DEVICE(0x4808), /* T420-cx */
- CH_DEVICE(0x4809), /* T420-bt */
- CH_DEVICE(0x480a), /* T404-bt */
- CH_DEVICE(0x480d), /* T480-cr */
- CH_DEVICE(0x480e), /* T440-lp-cr */
- CH_DEVICE(0x4880),
- CH_DEVICE(0x4881),
- CH_DEVICE(0x4882),
- CH_DEVICE(0x4883),
- CH_DEVICE(0x4884),
- CH_DEVICE(0x4885),
- CH_DEVICE(0x4886),
- CH_DEVICE(0x4887),
- CH_DEVICE(0x4888),
- CH_DEVICE(0x5801), /* T520-cr */
- CH_DEVICE(0x5802), /* T522-cr */
- CH_DEVICE(0x5803), /* T540-cr */
- CH_DEVICE(0x5804), /* T520-bch */
- CH_DEVICE(0x5805), /* T540-bch */
- CH_DEVICE(0x5806), /* T540-ch */
- CH_DEVICE(0x5807), /* T520-so */
- CH_DEVICE(0x5808), /* T520-cx */
- CH_DEVICE(0x5809), /* T520-bt */
- CH_DEVICE(0x580a), /* T504-bt */
- CH_DEVICE(0x580b), /* T520-sr */
- CH_DEVICE(0x580c), /* T504-bt */
- CH_DEVICE(0x580d), /* T580-cr */
- CH_DEVICE(0x580e), /* T540-lp-cr */
- CH_DEVICE(0x580f), /* Amsterdam */
- CH_DEVICE(0x5810), /* T580-lp-cr */
- CH_DEVICE(0x5811), /* T520-lp-cr */
- CH_DEVICE(0x5812), /* T560-cr */
- CH_DEVICE(0x5813), /* T580-cr */
- CH_DEVICE(0x5814), /* T580-so-cr */
- CH_DEVICE(0x5815), /* T502-bt */
- CH_DEVICE(0x5880),
- CH_DEVICE(0x5881),
- CH_DEVICE(0x5882),
- CH_DEVICE(0x5883),
- CH_DEVICE(0x5884),
- CH_DEVICE(0x5885),
- CH_DEVICE(0x5886),
- CH_DEVICE(0x5887),
- CH_DEVICE(0x5888),
- { 0, }
-};
+/* Macros needed to support the PCI Device ID Table ...
+ */
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \
+ static struct pci_device_id cxgb4vf_pci_tbl[] = {
+#define CH_PCI_DEVICE_ID_FUNCTION 0x8
+
+#define CH_PCI_ID_TABLE_ENTRY(devid) \
+ { PCI_VDEVICE(CHELSIO, (devid)), 0 }
+
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END { 0, } }
+
+#include "../cxgb4/t4_pci_id_tbl.h"
MODULE_DESCRIPTION(DRV_DESC);
MODULE_AUTHOR("Chelsio Communications");
diff --git a/drivers/scsi/csiostor/csio_hw_chip.h b/drivers/scsi/csiostor/csio_hw_chip.h
index bca0de6..4752fed 100644
--- a/drivers/scsi/csiostor/csio_hw_chip.h
+++ b/drivers/scsi/csiostor/csio_hw_chip.h
@@ -36,60 +36,13 @@
#include "csio_defs.h"
-/* FCoE device IDs for T4 */
-#define CSIO_DEVID_T440DBG_FCOE 0x4600
-#define CSIO_DEVID_T420CR_FCOE 0x4601
-#define CSIO_DEVID_T422CR_FCOE 0x4602
-#define CSIO_DEVID_T440CR_FCOE 0x4603
-#define CSIO_DEVID_T420BCH_FCOE 0x4604
-#define CSIO_DEVID_T440BCH_FCOE 0x4605
-#define CSIO_DEVID_T440CH_FCOE 0x4606
-#define CSIO_DEVID_T420SO_FCOE 0x4607
-#define CSIO_DEVID_T420CX_FCOE 0x4608
-#define CSIO_DEVID_T420BT_FCOE 0x4609
-#define CSIO_DEVID_T404BT_FCOE 0x460A
-#define CSIO_DEVID_B420_FCOE 0x460B
-#define CSIO_DEVID_B404_FCOE 0x460C
-#define CSIO_DEVID_T480CR_FCOE 0x460D
-#define CSIO_DEVID_T440LPCR_FCOE 0x460E
-#define CSIO_DEVID_AMSTERDAM_T4_FCOE 0x460F
-#define CSIO_DEVID_HUAWEI_T480_FCOE 0x4680
-#define CSIO_DEVID_HUAWEI_T440_FCOE 0x4681
-#define CSIO_DEVID_HUAWEI_STG310_FCOE 0x4682
-#define CSIO_DEVID_ACROMAG_XMC_XAUI 0x4683
-#define CSIO_DEVID_ACROMAG_XMC_SFP_FCOE 0x4684
-#define CSIO_DEVID_QUANTA_MEZZ_SFP_FCOE 0x4685
-#define CSIO_DEVID_HUAWEI_10GT_FCOE 0x4686
-#define CSIO_DEVID_HUAWEI_T440_TOE_FCOE 0x4687
-
-/* FCoE device IDs for T5 */
-#define CSIO_DEVID_T580DBG_FCOE 0x5600
-#define CSIO_DEVID_T520CR_FCOE 0x5601
-#define CSIO_DEVID_T522CR_FCOE 0x5602
-#define CSIO_DEVID_T540CR_FCOE 0x5603
-#define CSIO_DEVID_T520BCH_FCOE 0x5604
-#define CSIO_DEVID_T540BCH_FCOE 0x5605
-#define CSIO_DEVID_T540CH_FCOE 0x5606
-#define CSIO_DEVID_T520SO_FCOE 0x5607
-#define CSIO_DEVID_T520CX_FCOE 0x5608
-#define CSIO_DEVID_T520BT_FCOE 0x5609
-#define CSIO_DEVID_T504BT_FCOE 0x560A
-#define CSIO_DEVID_B520_FCOE 0x560B
-#define CSIO_DEVID_B504_FCOE 0x560C
-#define CSIO_DEVID_T580CR2_FCOE 0x560D
-#define CSIO_DEVID_T540LPCR_FCOE 0x560E
-#define CSIO_DEVID_AMSTERDAM_T5_FCOE 0x560F
-#define CSIO_DEVID_T580LPCR_FCOE 0x5610
-#define CSIO_DEVID_T520LLCR_FCOE 0x5611
-#define CSIO_DEVID_T560CR_FCOE 0x5612
-#define CSIO_DEVID_T580CR_FCOE 0x5613
-
/* Define MACRO values */
#define CSIO_HW_T4 0x4000
#define CSIO_T4_FCOE_ASIC 0x4600
#define CSIO_HW_T5 0x5000
#define CSIO_T5_FCOE_ASIC 0x5600
#define CSIO_HW_CHIP_MASK 0xF000
+
#define T4_REGMAP_SIZE (160 * 1024)
#define T5_REGMAP_SIZE (332 * 1024)
#define FW_FNAME_T4 "cxgb4/t4fw.bin"
diff --git a/drivers/scsi/csiostor/csio_init.c b/drivers/scsi/csiostor/csio_init.c
index 1ed5b21..34d20cc 100644
--- a/drivers/scsi/csiostor/csio_init.c
+++ b/drivers/scsi/csiostor/csio_init.c
@@ -955,6 +955,10 @@ static int csio_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
struct csio_hw *hw;
struct csio_lnode *ln;
+ /* probe only T5 cards */
+ if (!csio_is_t5((pdev->device & CSIO_HW_CHIP_MASK)))
+ return -ENODEV;
+
rv = csio_pci_init(pdev, &bars);
if (rv)
goto err;
@@ -1167,53 +1171,21 @@ static struct pci_error_handlers csio_err_handler = {
.resume = csio_pci_resume,
};
-static const struct pci_device_id csio_pci_tbl[] = {
- CSIO_DEVICE(CSIO_DEVID_T440DBG_FCOE, 0), /* T4 DEBUG FCOE */
- CSIO_DEVICE(CSIO_DEVID_T420CR_FCOE, 0), /* T420CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T422CR_FCOE, 0), /* T422CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T440CR_FCOE, 0), /* T440CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T420BCH_FCOE, 0), /* T420BCH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T440BCH_FCOE, 0), /* T440BCH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T440CH_FCOE, 0), /* T440CH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T420SO_FCOE, 0), /* T420SO FCOE */
- CSIO_DEVICE(CSIO_DEVID_T420CX_FCOE, 0), /* T420CX FCOE */
- CSIO_DEVICE(CSIO_DEVID_T420BT_FCOE, 0), /* T420BT FCOE */
- CSIO_DEVICE(CSIO_DEVID_T404BT_FCOE, 0), /* T404BT FCOE */
- CSIO_DEVICE(CSIO_DEVID_B420_FCOE, 0), /* B420 FCOE */
- CSIO_DEVICE(CSIO_DEVID_B404_FCOE, 0), /* B404 FCOE */
- CSIO_DEVICE(CSIO_DEVID_T480CR_FCOE, 0), /* T480 CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T440LPCR_FCOE, 0), /* T440 LP-CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_AMSTERDAM_T4_FCOE, 0), /* AMSTERDAM T4 FCOE */
- CSIO_DEVICE(CSIO_DEVID_HUAWEI_T480_FCOE, 0), /* HUAWEI T480 FCOE */
- CSIO_DEVICE(CSIO_DEVID_HUAWEI_T440_FCOE, 0), /* HUAWEI T440 FCOE */
- CSIO_DEVICE(CSIO_DEVID_HUAWEI_STG310_FCOE, 0), /* HUAWEI STG FCOE */
- CSIO_DEVICE(CSIO_DEVID_ACROMAG_XMC_XAUI, 0), /* ACROMAG XAUI FCOE */
- CSIO_DEVICE(CSIO_DEVID_QUANTA_MEZZ_SFP_FCOE, 0),/* QUANTA MEZZ FCOE */
- CSIO_DEVICE(CSIO_DEVID_HUAWEI_10GT_FCOE, 0), /* HUAWEI 10GT FCOE */
- CSIO_DEVICE(CSIO_DEVID_HUAWEI_T440_TOE_FCOE, 0),/* HUAWEI T4 TOE FCOE */
- CSIO_DEVICE(CSIO_DEVID_T580DBG_FCOE, 0), /* T5 DEBUG FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520CR_FCOE, 0), /* T520CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T522CR_FCOE, 0), /* T522CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T540CR_FCOE, 0), /* T540CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520BCH_FCOE, 0), /* T520BCH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T540BCH_FCOE, 0), /* T540BCH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T540CH_FCOE, 0), /* T540CH FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520SO_FCOE, 0), /* T520SO FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520CX_FCOE, 0), /* T520CX FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520BT_FCOE, 0), /* T520BT FCOE */
- CSIO_DEVICE(CSIO_DEVID_T504BT_FCOE, 0), /* T504BT FCOE */
- CSIO_DEVICE(CSIO_DEVID_B520_FCOE, 0), /* B520 FCOE */
- CSIO_DEVICE(CSIO_DEVID_B504_FCOE, 0), /* B504 FCOE */
- CSIO_DEVICE(CSIO_DEVID_T580CR2_FCOE, 0), /* T580 CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T540LPCR_FCOE, 0), /* T540 LP-CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_AMSTERDAM_T5_FCOE, 0), /* AMSTERDAM T5 FCOE */
- CSIO_DEVICE(CSIO_DEVID_T580LPCR_FCOE, 0), /* T580 LP-CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T520LLCR_FCOE, 0), /* T520 LL-CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T560CR_FCOE, 0), /* T560 CR FCOE */
- CSIO_DEVICE(CSIO_DEVID_T580CR_FCOE, 0), /* T580 CR FCOE */
- { 0, 0, 0, 0, 0, 0, 0 }
-};
+/*
+ * Macros needed to support the PCI Device ID Table ...
+ */
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN \
+ static struct pci_device_id csio_pci_tbl[] = {
+/* Define for iSCSI uses PF5, FCoE uses PF6 */
+#define CH_PCI_DEVICE_ID_FUNCTION 0x5
+#define CH_PCI_DEVICE_ID_FUNCTION2 0x6
+
+#define CH_PCI_ID_TABLE_ENTRY(devid) \
+ { PCI_VDEVICE(CHELSIO, (devid)), 0 }
+
+#define CH_PCI_DEVICE_ID_TABLE_DEFINE_END { 0, } }
+#include "t4_pci_id_tbl.h"
static struct pci_driver csio_pci_driver = {
.name = KBUILD_MODNAME,
--
1.7.1
^ permalink raw reply related
* Re: [RFC PATCH 0/4] switch device: offload policy attributes
From: Ronen Arad @ 2014-11-25 3:10 UTC (permalink / raw)
To: netdev
In-Reply-To: <CAE4R7bAY2zMy4SiuwhdXyH2Swqv1KfkrBJ_ZwU_RYdCW3k+Mvg@mail.gmail.com>
Scott Feldman <sfeldma <at> gmail.com> writes:
>
> On Mon, Nov 24, 2014 at 4:55 AM, Roopa Prabhu <roopa <at>
cumulusnetworks.com> wrote:
> > On 11/24/14, 2:18 AM, Scott Feldman wrote:
> >>
> >> Hi Roopa,
> >>
> >> I have a patch pending against Jiri's v2 that's uses existing
> >> ndo_bridge_setlink/getlink to push policy settings down to port driver
> >> for controlling HW offload. I had to make a few tweaks, but for the
> >> most part setlink/getlink already has the master/self semantics so
> >> users can set policy flags on bridge's SW version of the port (master)
> >> or on the offloaded version of the port (self).
> >> I added the new
> >> hwmode option "swdev" to the existing "vepa"|"veb" choices. When you
> >> specify hwmode, SELF is set and the port driver's setlink get's
> >> called. Did you look at setlink/getlink? It looks like the kernel
> >> and iproute2 where going down this route of using setlink/getlink for
> >> SELF policy, so I'm wondering if we need more?
> >
> > If i understand you correctly, this will mean the port driver implements
the
> > setlink/getlink with the bridge port flags and attributes. And, it also
> > means
> > the port driver will parse the netlink msg instead of the bridge driver
> > parsing all attributes and then calling offloads.
>
> Yes, exactly, the port driver parses/fills bridge_setlink/getlink
> netlink msg to set/get port settings. It's basically a passthru for
> rtnl_bridge_setlink/getlink handling RTM_GETLNK/RTM_SETLINK on
> PF_BRIDGE.
>
> > But, in cases where we want bridge port flags and attributes set both in
hw
> > and sw,
> > the user (iproute2) will have to set both MASTER and SELF flags, and the
> > netlink parsing will now happen in two places, the bridge driver and the
> > bridge port
> > driver ?
>
How does VLAN filtering is expected to work with an HW-offloaded bridge?
When MASTER flag is set by iproute2 in the netlink message (or no flag is
set), br_setlink - the ndo_bridge_setlink function of the port's master
bridge is called. It takes care of setting the VLAN policy in the
net_port_vlans of the net_bridge_port. During this sequence the
ndo_vlan_rx_add_vid function of the port dev is called. However, it only gets
the vid. It does not have access to the flags (PVID, UNTAGGED) and those are
not set in the net_port_vlans struct at that time.
Giving the port driver access to the VLAN policy requires both MASTER and
SLAVE flags to be set in the IFLA_BRIDGE_FLAGS attribute.
Is the end user is expected to set both flags in the "bridge vlan add"
command (Failing to do that will prevent the bridge and HW from being in
sync)?
Even with both MASTER and SLAVE flags being set in a single netlink request,
the HW and bridge could get out of sync if adding the VLAN policy to the port
driver would fail after it was added to the bridge netdev.
Is there any mechanism for keeping both software and HW in-sync?
-Ronen
^ permalink raw reply
* Re: [PATCH] mdio-mux-gpio: Use GPIO descriptor interface and new gpiod_set_array function
From: Alexandre Courbot @ 2014-11-25 3:39 UTC (permalink / raw)
To: Rojhalat Ibrahim
Cc: Florian Fainelli, netdev, David Daney, linux-gpio@vger.kernel.org,
Linus Walleij, Alexandre Courbot
In-Reply-To: <6441674.xrJo8HXDvD@pcimr>
On Thu, Nov 20, 2014 at 9:24 PM, Rojhalat Ibrahim <imr@rtschenk.de> wrote:
> Convert mdio-mux-gpio to the GPIO descriptor interface and use the new
> gpiod_set_array function to set all output signals simultaneously.
>
> Signed-off-by: Rojhalat Ibrahim <imr@rtschenk.de>
> --
> This patch depends on the gpiod_set_array function, which is available in
> the linux-gpio devel tree.
>
> drivers/net/phy/mdio-mux-gpio.c | 35 +++++++++++++++--------------------
> 1 file changed, 15 insertions(+), 20 deletions(-)
>
> diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
> index 0966951..3fdea96 100644
> --- a/drivers/net/phy/mdio-mux-gpio.c
> +++ b/drivers/net/phy/mdio-mux-gpio.c
> @@ -14,13 +14,13 @@
> #include <linux/mdio-mux.h>
> #include <linux/of_gpio.h>
>
> -#define DRV_VERSION "1.0"
> +#define DRV_VERSION "1.1"
> #define DRV_DESCRIPTION "GPIO controlled MDIO bus multiplexer driver"
>
> #define MDIO_MUX_GPIO_MAX_BITS 8
>
> struct mdio_mux_gpio_state {
> - int gpio[MDIO_MUX_GPIO_MAX_BITS];
> + struct gpio_desc *gpio[MDIO_MUX_GPIO_MAX_BITS];
> unsigned int num_gpios;
> void *mux_handle;
> };
> @@ -28,29 +28,23 @@ struct mdio_mux_gpio_state {
> static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
> void *data)
> {
> - int change;
> + int values[MDIO_MUX_GPIO_MAX_BITS];
> unsigned int n;
> struct mdio_mux_gpio_state *s = data;
>
> if (current_child == desired_child)
> return 0;
>
> - change = current_child == -1 ? -1 : current_child ^ desired_child;
> -
> for (n = 0; n < s->num_gpios; n++) {
> - if (change & 1)
> - gpio_set_value_cansleep(s->gpio[n],
> - (desired_child & 1) != 0);
> - change >>= 1;
> - desired_child >>= 1;
> + values[n] = (desired_child >> n) & 1;
> }
> + gpiod_set_array_cansleep(s->num_gpios, s->gpio, values);
>
> return 0;
> }
>
> static int mdio_mux_gpio_probe(struct platform_device *pdev)
> {
> - enum of_gpio_flags f;
> struct mdio_mux_gpio_state *s;
> int num_gpios;
> unsigned int n;
> @@ -70,20 +64,17 @@ static int mdio_mux_gpio_probe(struct platform_device *pdev)
> s->num_gpios = num_gpios;
>
> for (n = 0; n < num_gpios; ) {
> - int gpio = of_get_gpio_flags(pdev->dev.of_node, n, &f);
> - if (gpio < 0) {
> - r = (gpio == -ENODEV) ? -EPROBE_DEFER : gpio;
> + struct gpio_desc *gpio = gpiod_get_index(&pdev->dev,
> + "mdio-mux-gpio", n);
Doesn't this change introduce some incompatibility against the current
DT bindings? of_get_gpio_flags() looks for a "gpios" property, while
your call to gpiod_get_index() will look for "mdio-mux-gpio-gpios". It
should probably be changed to gpiod_get_index(&pdev->dev, NULL, n).
... or even be changed to gpiod_get_index(&pdev->dev, NULL, n,
GPIOD_OUT_LOW) as the calls to gpiod_get() functions are being updated
to take an initial state (both variants are currently usable but the
former one will disappear in the future). This will also allow you to
get rid of your call to gpiod_direction_output().
Side-note: it would be nice to have a gpiod_get_array() call that does
exactly what this loop does, and returns an array of gpios directly
usable by gpiod_set_array*(). And a matching gpiod_put_array() of
course.
^ permalink raw reply
* [net PATCH 0/2] Fix outer UDP checksums for IPv6 VXLAN tunnels
From: alexander.duyck @ 2014-11-25 4:08 UTC (permalink / raw)
To: netdev; +Cc: davem
In testing against an older kernel I found a couple issues in the IPv6
VXLAN tunnel checksum logic for the outer UDP checksum.
First the default transitioned from using an outer checksum to not using
one. Second, sometime after that the checksum inputs were changed
resulting the checksum not being correct if it were computed.
These two issues prevented a ping from the newer kernel to the older one.
With these two changes applied I verified I was able to send traffic over
the VXLAN tunnel to a link partner on an older kernel.
The boolean flip fix can be submitted for 3.17 stable as well since the
patch that introduced the issue was included in that kernel.
---
Alexander Duyck (2):
ip6_udp_tunnel: Fix checksum calculation
vxlan: Fix boolean flip in VXLAN_F_UDP_ZERO_CSUM6_[TX|RX]
drivers/net/vxlan.c | 4 ++--
net/ipv6/ip6_udp_tunnel.c | 4 +---
2 files changed, 3 insertions(+), 5 deletions(-)
--
^ permalink raw reply
* [net PATCH 1/2] ip6_udp_tunnel: Fix checksum calculation
From: alexander.duyck @ 2014-11-25 4:08 UTC (permalink / raw)
To: netdev; +Cc: Alexander Duyck, Andy Zhou, davem
In-Reply-To: <20141125035808.13612.52556.stgit@ahduyck-workstation.home>
From: Alexander Duyck <alexander.h.duyck@redhat.com>
The UDP checksum calculation for VXLAN tunnels is currently using the
socket addresses instead of the actual packet source and destination
addresses. As a result the checksum calculated is incorrect in some
cases.
Also uh->check was being set twice, first it was set to 0, and then it is
set again in udp6_set_csum. This change removes the redundant assignment
to 0.
Fixes: acbf74a7 ("vxlan: Refactor vxlan driver to make use of the common UDP tunnel functions.")
Cc: Andy Zhou <azhou@nicira.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
---
net/ipv6/ip6_udp_tunnel.c | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c
index b04ed72..8db6c98 100644
--- a/net/ipv6/ip6_udp_tunnel.c
+++ b/net/ipv6/ip6_udp_tunnel.c
@@ -79,15 +79,13 @@ int udp_tunnel6_xmit_skb(struct socket *sock, struct dst_entry *dst,
uh->source = src_port;
uh->len = htons(skb->len);
- uh->check = 0;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED
| IPSKB_REROUTED);
skb_dst_set(skb, dst);
- udp6_set_csum(udp_get_no_check6_tx(sk), skb, &inet6_sk(sk)->saddr,
- &sk->sk_v6_daddr, skb->len);
+ udp6_set_csum(udp_get_no_check6_tx(sk), skb, saddr, daddr, skb->len);
__skb_push(skb, sizeof(*ip6h));
skb_reset_network_header(skb);
^ permalink raw reply related
* [net PATCH 2/2] vxlan: Fix boolean flip in VXLAN_F_UDP_ZERO_CSUM6_[TX|RX]
From: alexander.duyck @ 2014-11-25 4:08 UTC (permalink / raw)
To: netdev; +Cc: Alexander Duyck, davem, Tom Herbert
In-Reply-To: <20141125035808.13612.52556.stgit@ahduyck-workstation.home>
From: Alexander Duyck <alexander.h.duyck@redhat.com>
In "vxlan: Call udp_sock_create" there was a logic error that resulted in
the default for IPv6 VXLAN tunnels going from using checksums to not using
checksums. Since there is currently no support in iproute2 for setting
these values it means that a kernel after the change cannot talk over a IPv6
VXLAN tunnel to a kernel prior the change.
Fixes: 3ee64f3 ("vxlan: Call udp_sock_create")
Cc: Tom Herbert <therbert@google.com>
Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com>
---
drivers/net/vxlan.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e1e335c..be4649a 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2306,9 +2306,9 @@ static struct socket *vxlan_create_sock(struct net *net, bool ipv6,
if (ipv6) {
udp_conf.family = AF_INET6;
udp_conf.use_udp6_tx_checksums =
- !!(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
+ !(flags & VXLAN_F_UDP_ZERO_CSUM6_TX);
udp_conf.use_udp6_rx_checksums =
- !!(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
+ !(flags & VXLAN_F_UDP_ZERO_CSUM6_RX);
} else {
udp_conf.family = AF_INET;
udp_conf.local_ip.s_addr = INADDR_ANY;
^ permalink raw reply related
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