diff options
265 files changed, 7085 insertions, 3878 deletions
diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX index 32dfbd924121..18b64b2b8a68 100644 --- a/Documentation/networking/00-INDEX +++ b/Documentation/networking/00-INDEX @@ -124,6 +124,8 @@ multiqueue.txt - HOWTO for multiqueue network device support. netconsole.txt - The network console module netconsole.ko: configuration and notes. +netdev-FAQ.txt + - FAQ describing how to submit net changes to netdev mailing list. netdev-features.txt - Network interface features API description. netdevices.txt diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 10742902146f..36be26b2ef7a 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -440,6 +440,10 @@ tcp_syncookies - BOOLEAN SYN flood warnings in logs not being really flooded, your server is seriously misconfigured. + If you want to test which effects syncookies have to your + network connections you can set this knob to 2 to enable + unconditionally generation of syncookies. + tcp_fastopen - INTEGER Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data in the opening SYN packet. To use this feature, the client application @@ -516,6 +520,19 @@ tcp_wmem - vector of 3 INTEGERs: min, default, max this value is ignored. Default: between 64K and 4MB, depending on RAM size. +tcp_notsent_lowat - UNSIGNED INTEGER + A TCP socket can control the amount of unsent bytes in its write queue, + thanks to TCP_NOTSENT_LOWAT socket option. poll()/select()/epoll() + reports POLLOUT events if the amount of unsent bytes is below a per + socket value, and if the write queue is not full. sendmsg() will + also not add new buffers if the limit is hit. + + This global variable controls the amount of unsent data for + sockets not using TCP_NOTSENT_LOWAT. For these sockets, a change + to the global variable has immediate effect. + + Default: UINT_MAX (0xFFFFFFFF) + tcp_workaround_signed_windows - BOOLEAN If set, assume no receipt of a window scaling option means the remote TCP is broken and treats the window as a signed quantity. diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt new file mode 100644 index 000000000000..d9112f01c44a --- /dev/null +++ b/Documentation/networking/netdev-FAQ.txt @@ -0,0 +1,224 @@ + +Information you need to know about netdev +----------------------------------------- + +Q: What is netdev? + +A: It is a mailing list for all network related linux stuff. This includes + anything found under net/ (i.e. core code like IPv6) and drivers/net + (i.e. hardware specific drivers) in the linux source tree. + + Note that some subsystems (e.g. wireless drivers) which have a high volume + of traffic have their own specific mailing lists. + + The netdev list is managed (like many other linux mailing lists) through + VGER ( http://vger.kernel.org/ ) and archives can be found below: + + http://marc.info/?l=linux-netdev + http://www.spinics.net/lists/netdev/ + + Aside from subsystems like that mentioned above, all network related linux + development (i.e. RFC, review, comments, etc) takes place on netdev. + +Q: How do the changes posted to netdev make their way into linux? + +A: There are always two trees (git repositories) in play. Both are driven + by David Miller, the main network maintainer. There is the "net" tree, + and the "net-next" tree. As you can probably guess from the names, the + net tree is for fixes to existing code already in the mainline tree from + Linus, and net-next is where the new code goes for the future release. + You can find the trees here: + + http://git.kernel.org/?p=linux/kernel/git/davem/net.git + http://git.kernel.org/?p=linux/kernel/git/davem/net-next.git + +Q: How often do changes from these trees make it to the mainline Linus tree? + +A: To understand this, you need to know a bit of background information + on the cadence of linux development. Each new release starts off with + a two week "merge window" where the main maintainers feed their new + stuff to Linus for merging into the mainline tree. After the two weeks, + the merge window is closed, and it is called/tagged "-rc1". No new + features get mainlined after this -- only fixes to the rc1 content + are expected. After roughly a week of collecting fixes to the rc1 + content, rc2 is released. This repeats on a roughly weekly basis + until rc7 (typically; sometimes rc6 if things are quiet, or rc8 if + things are in a state of churn), and a week after the last vX.Y-rcN + was done, the official "vX.Y" is released. + + Relating that to netdev: At the beginning of the 2 week merge window, + the net-next tree will be closed - no new changes/features. The + accumulated new content of the past ~10 weeks will be passed onto + mainline/Linus via a pull request for vX.Y -- at the same time, + the "net" tree will start accumulating fixes for this pulled content + relating to vX.Y + + An announcement indicating when net-next has been closed is usually + sent to netdev, but knowing the above, you can predict that in advance. + + IMPORTANT: Do not send new net-next content to netdev during the + period during which net-next tree is closed. + + Shortly after the two weeks have passed, (and vX.Y-rc1 is released) the + tree for net-next reopens to collect content for the next (vX.Y+1) release. + + If you aren't subscribed to netdev and/or are simply unsure if net-next + has re-opened yet, simply check the net-next git repository link above for + any new networking related commits. + + The "net" tree continues to collect fixes for the vX.Y content, and + is fed back to Linus at regular (~weekly) intervals. Meaning that the + focus for "net" is on stablilization and bugfixes. + + Finally, the vX.Y gets released, and the whole cycle starts over. + +Q: So where are we now in this cycle? + +A: Load the mainline (Linus) page here: + + http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git + + and note the top of the "tags" section. If it is rc1, it is early + in the dev cycle. If it was tagged rc7 a week ago, then a release + is probably imminent. + +Q: How do I indicate which tree (net vs. net-next) my patch should be in? + +A: Firstly, think whether you have a bug fix or new "next-like" content. + Then once decided, assuming that you use git, use the prefix flag, i.e. + + git format-patch --subject-prefix='PATCH net-next' start..finish + + Use "net" instead of "net-next" (always lower case) in the above for + bug-fix net content. If you don't use git, then note the only magic in + the above is just the subject text of the outgoing e-mail, and you can + manually change it yourself with whatever MUA you are comfortable with. + +Q: I sent a patch and I'm wondering what happened to it. How can I tell + whether it got merged? + +A: Start by looking at the main patchworks queue for netdev: + + http://patchwork.ozlabs.org/project/netdev/list/ + + The "State" field will tell you exactly where things are at with + your patch. + +Q: The above only says "Under Review". How can I find out more? + +A: Generally speaking, the patches get triaged quickly (in less than 48h). + So be patient. Asking the maintainer for status updates on your + patch is a good way to ensure your patch is ignored or pushed to + the bottom of the priority list. + +Q: How can I tell what patches are queued up for backporting to the + various stable releases? + +A: Normally Greg Kroah-Hartman collects stable commits himself, but + for networking, Dave collects up patches he deems critical for the + networking subsystem, and then hands them off to Greg. + + There is a patchworks queue that you can see here: + http://patchwork.ozlabs.org/bundle/davem/stable/?state=* + + It contains the patches which Dave has selected, but not yet handed + off to Greg. If Greg already has the patch, then it will be here: + http://git.kernel.org/cgit/linux/kernel/git/stable/stable-queue.git + + A quick way to find whether the patch is in this stable-queue is + to simply clone the repo, and then git grep the mainline commit ID, e.g. + + stable-queue$ git grep -l 284041ef21fdf2e + releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch + stable/stable-queue$ + +Q: I see a network patch and I think it should be backported to stable. + Should I request it via "stable@vger.kernel.org" like the references in + the kernel's Documentation/stable_kernel_rules.txt file say? + +A: No, not for networking. Check the stable queues as per above 1st to see + if it is already queued. If not, then send a mail to netdev, listing + the upstream commit ID and why you think it should be a stable candidate. + + Before you jump to go do the above, do note that the normal stable rules + in Documentation/stable_kernel_rules.txt still apply. So you need to + explicitly indicate why it is a critical fix and exactly what users are + impacted. In addition, you need to convince yourself that you _really_ + think it has been overlooked, vs. having been considered and rejected. + + Generally speaking, the longer it has had a chance to "soak" in mainline, + the better the odds that it is an OK candidate for stable. So scrambling + to request a commit be added the day after it appears should be avoided. + +Q: I have created a network patch and I think it should be backported to + stable. Should I add a "Cc: stable@vger.kernel.org" like the references + in the kernel's Documentation/ directory say? + +A: No. See above answer. In short, if you think it really belongs in + stable, then ensure you write a decent commit log that describes who + gets impacted by the bugfix and how it manifests itself, and when the + bug was introduced. If you do that properly, then the commit will + get handled appropriately and most likely get put in the patchworks + stable queue if it really warrants it. + + If you think there is some valid information relating to it being in + stable that does _not_ belong in the commit log, then use the three + dash marker line as described in Documentation/SubmittingPatches to + temporarily embed that information into the patch that you send. + +Q: Someone said that the comment style and coding convention is different + for the networking content. Is this true? + +A: Yes, in a largely trivial way. Instead of this: + + /* + * foobar blah blah blah + * another line of text + */ + + it is requested that you make it look like this: + + /* foobar blah blah blah + * another line of text + */ + +Q: I am working in existing code that has the former comment style and not the + latter. Should I submit new code in the former style or the latter? + +A: Make it the latter style, so that eventually all code in the domain of + netdev is of this format. + +Q: I found a bug that might have possible security implications or similar. + Should I mail the main netdev maintainer off-list? + +A: No. The current netdev maintainer has consistently requested that people + use the mailing lists and not reach out directly. If you aren't OK with + that, then perhaps consider mailing "security@kernel.org" or reading about + http://oss-security.openwall.org/wiki/mailing-lists/distros + as possible alternative mechanisms. + +Q: What level of testing is expected before I submit my change? + +A: If your changes are against net-next, the expectation is that you + have tested by layering your changes on top of net-next. Ideally you + will have done run-time testing specific to your change, but at a + minimum, your changes should survive an "allyesconfig" and an + "allmodconfig" build without new warnings or failures. + +Q: Any other tips to help ensure my net/net-next patch gets OK'd? + +A: Attention to detail. Re-read your own work as if you were the + reviewer. You can start with using checkpatch.pl, perhaps even + with the "--strict" flag. But do not be mindlessly robotic in + doing so. If your change is a bug-fix, make sure your commit log + indicates the end-user visible symptom, the underlying reason as + to why it happens, and then if necessary, explain why the fix proposed + is the best way to get things done. Don't mangle whitespace, and as + is common, don't mis-indent function arguments that span multiple lines. + If it is your 1st patch, mail it to yourself so you can test apply + it to an unpatched tree to confirm infrastructure didn't mangle it. + + Finally, go back and read Documentation/SubmittingPatches to be + sure you are not repeating some common mistake documented there. diff --git a/Documentation/networking/sctp.txt b/Documentation/networking/sctp.txt index 0c790a76910e..97b810ca9082 100644 --- a/Documentation/networking/sctp.txt +++ b/Documentation/networking/sctp.txt @@ -19,7 +19,6 @@ of SCTP that is RFC 2960 compliant and provides an programming interface referred to as the UDP-style API of the Sockets Extensions for SCTP, as proposed in IETF Internet-Drafts. - Caveats: -lksctp can be built as statically or as a module. However, be aware that @@ -33,6 +32,4 @@ For more information, please visit the lksctp project website: http://www.sf.net/projects/lksctp Or contact the lksctp developers through the mailing list: - <lksctp-developers@lists.sourceforge.net> - - + <linux-sctp@vger.kernel.org> diff --git a/MAINTAINERS b/MAINTAINERS index defc05383f83..b57ecb115c14 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7231,6 +7231,7 @@ W: http://lksctp.sourceforge.net S: Maintained F: Documentation/networking/sctp.txt F: include/linux/sctp.h +F: include/uapi/linux/sctp.h F: include/net/sctp/ F: net/sctp/ diff --git a/arch/tile/gxio/iorpc_mpipe.c b/arch/tile/gxio/iorpc_mpipe.c index 31b87bf8c027..4f8f3d619c4a 100644 --- a/arch/tile/gxio/iorpc_mpipe.c +++ b/arch/tile/gxio/iorpc_mpipe.c @@ -387,6 +387,27 @@ int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac) EXPORT_SYMBOL(gxio_mpipe_link_close_aux); +struct link_set_attr_aux_param { + int mac; + uint32_t attr; + int64_t val; +}; + +int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t * context, int mac, + uint32_t attr, int64_t val) +{ + struct link_set_attr_aux_param temp; + struct link_set_attr_aux_param *params = &temp; + + params->mac = mac; + params->attr = attr; + params->val = val; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_OP_LINK_SET_ATTR_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_link_set_attr_aux); struct get_timestamp_aux_param { uint64_t sec; @@ -454,6 +475,51 @@ int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context, EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_aux); +struct adjust_timestamp_freq_param { + int32_t ppb; +}; + +int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t * context, + int32_t ppb) +{ + struct adjust_timestamp_freq_param temp; + struct adjust_timestamp_freq_param *params = &temp; + + params->ppb = ppb; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ); +} + +EXPORT_SYMBOL(gxio_mpipe_adjust_timestamp_freq); + +struct config_edma_ring_blks_param { + unsigned int ering; + unsigned int max_blks; + unsigned int min_snf_blks; + unsigned int db; +}; + +int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t * context, + unsigned int ering, unsigned int max_blks, + unsigned int min_snf_blks, unsigned int db) +{ + struct config_edma_ring_blks_param temp; + struct config_edma_ring_blks_param *params = &temp; + + params->ering = ering; + params->max_blks = max_blks; + params->min_snf_blks = min_snf_blks; + params->db = db; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), + GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS); +} + +EXPORT_SYMBOL(gxio_mpipe_config_edma_ring_blks); + struct arm_pollfd_param { union iorpc_pollfd pollfd; }; diff --git a/arch/tile/gxio/iorpc_mpipe_info.c b/arch/tile/gxio/iorpc_mpipe_info.c index d0254aa60cba..64883aabeb9c 100644 --- a/arch/tile/gxio/iorpc_mpipe_info.c +++ b/arch/tile/gxio/iorpc_mpipe_info.c @@ -16,6 +16,24 @@ #include "gxio/iorpc_mpipe_info.h" +struct instance_aux_param { + _gxio_mpipe_link_name_t name; +}; + +int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t * context, + _gxio_mpipe_link_name_t name) +{ + struct instance_aux_param temp; + struct instance_aux_param *params = &temp; + + params->name = name; + + return hv_dev_pwrite(context->fd, 0, (HV_VirtAddr) params, + sizeof(*params), GXIO_MPIPE_INFO_OP_INSTANCE_AUX); +} + +EXPORT_SYMBOL(gxio_mpipe_info_instance_aux); + struct enumerate_aux_param { _gxio_mpipe_link_name_t name; _gxio_mpipe_link_mac_t mac; diff --git a/arch/tile/gxio/mpipe.c b/arch/tile/gxio/mpipe.c index e71c63390acc..5301a9ffbae1 100644 --- a/arch/tile/gxio/mpipe.c +++ b/arch/tile/gxio/mpipe.c @@ -36,8 +36,14 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index) int fd; int i; + if (mpipe_index >= GXIO_MPIPE_INSTANCE_MAX) + return -EINVAL; + snprintf(file, sizeof(file), "mpipe/%d/iorpc", mpipe_index); fd = hv_dev_open((HV_VirtAddr) file, 0); + + context->fd = fd; + if (fd < 0) { if (fd >= GXIO_ERR_MIN && fd <= GXIO_ERR_MAX) return fd; @@ -45,8 +51,6 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index) return -ENODEV; } - context->fd = fd; - /* Map in the MMIO space. */ context->mmio_cfg_base = (void __force *) iorpc_ioremap(fd, HV_MPIPE_CONFIG_MMIO_OFFSET, @@ -64,12 +68,15 @@ int gxio_mpipe_init(gxio_mpipe_context_t *context, unsigned int mpipe_index) for (i = 0; i < 8; i++) context->__stacks.stacks[i] = 255; + context->instance = mpipe_index; + return 0; fast_failed: iounmap((void __force __iomem *)(context->mmio_cfg_base)); cfg_failed: hv_dev_close(context->fd); + context->fd = -1; return -ENODEV; } @@ -383,7 +390,7 @@ EXPORT_SYMBOL_GPL(gxio_mpipe_iqueue_init); int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, gxio_mpipe_context_t *context, - unsigned int edma_ring_id, + unsigned int ering, unsigned int channel, void *mem, unsigned int mem_size, unsigned int mem_flags) @@ -394,7 +401,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, /* Offset used to read number of completed commands. */ MPIPE_EDMA_POST_REGION_ADDR_t offset; - int result = gxio_mpipe_init_edma_ring(context, edma_ring_id, channel, + int result = gxio_mpipe_init_edma_ring(context, ering, channel, mem, mem_size, mem_flags); if (result < 0) return result; @@ -405,7 +412,7 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, offset.region = MPIPE_MMIO_ADDR__REGION_VAL_EDMA - MPIPE_MMIO_ADDR__REGION_VAL_IDMA; - offset.ring = edma_ring_id; + offset.ring = ering; __gxio_dma_queue_init(&equeue->dma_queue, context->mmio_fast_base + offset.word, @@ -413,6 +420,9 @@ int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, equeue->edescs = mem; equeue->mask_num_entries = num_entries - 1; equeue->log2_num_entries = __builtin_ctz(num_entries); + equeue->context = context; + equeue->ering = ering; + equeue->channel = channel; return 0; } @@ -493,6 +503,20 @@ static gxio_mpipe_context_t *_gxio_get_link_context(void) return contextp; } +int gxio_mpipe_link_instance(const char *link_name) +{ + _gxio_mpipe_link_name_t name; + gxio_mpipe_context_t *context = _gxio_get_link_context(); + + if (!context) + return GXIO_ERR_NO_DEVICE; + + strncpy(name.name, link_name, sizeof(name.name)); + name.name[GXIO_MPIPE_LINK_NAME_LEN - 1] = '\0'; + + return gxio_mpipe_info_instance_aux(context, name); +} + int gxio_mpipe_link_enumerate_mac(int idx, char *link_name, uint8_t *link_mac) { int rv; @@ -543,3 +567,12 @@ int gxio_mpipe_link_close(gxio_mpipe_link_t *link) } EXPORT_SYMBOL_GPL(gxio_mpipe_link_close); + +int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr, + int64_t val) +{ + return gxio_mpipe_link_set_attr_aux(link->context, link->mac, attr, + val); +} + +EXPORT_SYMBOL_GPL(gxio_mpipe_link_set_attr); diff --git a/arch/tile/include/gxio/iorpc_mpipe.h b/arch/tile/include/gxio/iorpc_mpipe.h index 9d50fce1b1a7..fdd07f88cfd7 100644 --- a/arch/tile/include/gxio/iorpc_mpipe.h +++ b/arch/tile/include/gxio/iorpc_mpipe.h @@ -44,10 +44,13 @@ #define GXIO_MPIPE_OP_REGISTER_CLIENT_MEMORY IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1210) #define GXIO_MPIPE_OP_LINK_OPEN_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1211) #define GXIO_MPIPE_OP_LINK_CLOSE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1212) +#define GXIO_MPIPE_OP_LINK_SET_ATTR_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1213) -#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121e) -#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x121f) -#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x1220) +#define GXIO_MPIPE_OP_GET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121e) +#define GXIO_MPIPE_OP_SET_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x121f) +#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1220) +#define GXIO_MPIPE_OP_CONFIG_EDMA_RING_BLKS IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1221) +#define GXIO_MPIPE_OP_ADJUST_TIMESTAMP_FREQ IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1222) #define GXIO_MPIPE_OP_ARM_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9000) #define GXIO_MPIPE_OP_CLOSE_POLLFD IORPC_OPCODE(IORPC_FORMAT_KERNEL_POLLFD, 0x9001) #define GXIO_MPIPE_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) @@ -114,6 +117,8 @@ int gxio_mpipe_link_open_aux(gxio_mpipe_context_t * context, int gxio_mpipe_link_close_aux(gxio_mpipe_context_t * context, int mac); +int gxio_mpipe_link_set_attr_aux(gxio_mpipe_context_t * context, int mac, + uint32_t attr, int64_t val); int gxio_mpipe_get_timestamp_aux(gxio_mpipe_context_t * context, uint64_t * sec, uint64_t * nsec, uint64_t * cycles); @@ -124,6 +129,9 @@ int gxio_mpipe_set_timestamp_aux(gxio_mpipe_context_t * context, uint64_t sec, int gxio_mpipe_adjust_timestamp_aux(gxio_mpipe_context_t * context, int64_t nsec); +int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t * context, + int32_t ppb); + int gxio_mpipe_arm_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie); int gxio_mpipe_close_pollfd(gxio_mpipe_context_t * context, int pollfd_cookie); diff --git a/arch/tile/include/gxio/iorpc_mpipe_info.h b/arch/tile/include/gxio/iorpc_mpipe_info.h index 0bcf3f71ce8b..476c5e5ca22c 100644 --- a/arch/tile/include/gxio/iorpc_mpipe_info.h +++ b/arch/tile/include/gxio/iorpc_mpipe_info.h @@ -27,11 +27,15 @@ #include <asm/pgtable.h> +#define GXIO_MPIPE_INFO_OP_INSTANCE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1250) #define GXIO_MPIPE_INFO_OP_ENUMERATE_AUX IORPC_OPCODE(IORPC_FORMAT_NONE, 0x1251) #define GXIO_MPIPE_INFO_OP_GET_MMIO_BASE IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8000) #define GXIO_MPIPE_INFO_OP_CHECK_MMIO_OFFSET IORPC_OPCODE(IORPC_FORMAT_NONE_NOUSER, 0x8001) +int gxio_mpipe_info_instance_aux(gxio_mpipe_info_context_t * context, + _gxio_mpipe_link_name_t name); + int gxio_mpipe_info_enumerate_aux(gxio_mpipe_info_context_t * context, unsigned int idx, _gxio_mpipe_link_name_t * name, diff --git a/arch/tile/include/gxio/mpipe.h b/arch/tile/include/gxio/mpipe.h index b74f470ed11e..e37cf4f0cffd 100644 --- a/arch/tile/include/gxio/mpipe.h +++ b/arch/tile/include/gxio/mpipe.h @@ -220,6 +220,13 @@ typedef MPIPE_PDESC_t gxio_mpipe_idesc_t; */ typedef MPIPE_EDMA_DESC_t gxio_mpipe_edesc_t; +/* + * Max # of mpipe instances. 2 currently. + */ +#define GXIO_MPIPE_INSTANCE_MAX HV_MPIPE_INSTANCE_MAX + +#define NR_MPIPE_MAX GXIO_MPIPE_INSTANCE_MAX + /* Get the "va" field from an "idesc". * * This is the address at which the ingress hardware copied the first @@ -311,6 +318,9 @@ typedef struct { /* File descriptor for calling up to Linux (and thus the HV). */ int fd; + /* Corresponding mpipe instance #. */ + int instance; + /* The VA at which configuration registers are mapped. */ char *mmio_cfg_base; @@ -810,7 +820,7 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context, /* Initialize an eDMA ring, using the given memory and size. * * @param context An initialized mPIPE context. - * @param ring The eDMA ring index. + * @param ering The eDMA ring index. * @param channel The channel to use. This must be one of the channels * associated with the context's set of open links. * @param mem A physically contiguous region of memory to be filled @@ -823,10 +833,37 @@ extern int gxio_mpipe_alloc_edma_rings(gxio_mpipe_context_t *context, * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure. */ extern int gxio_mpipe_init_edma_ring(gxio_mpipe_context_t *context, - unsigned int ring, unsigned int channel, + unsigned int ering, unsigned int channel, void *mem, size_t mem_size, unsigned int mem_flags); +/* Set the "max_blks", "min_snf_blks", and "db" fields of + * ::MPIPE_EDMA_RG_INIT_DAT_THRESH_t for a given edma ring. + * + * The global pool of dynamic blocks will be automatically adjusted. + * + * This function should not be called after any egress has been done + * on the edma ring. + * + * Most applications should just use gxio_mpipe_equeue_set_snf_size(). + * + * @param context An initialized mPIPE context. + * @param ering The eDMA ring index. + * @param max_blks The number of blocks to dedicate to the ring + * (normally min_snf_blks + 1). Must be greater than min_snf_blocks. + * @param min_snf_blks The number of blocks which must be stored + * prior to starting to send the packet (normally 12). + * @param db Whether to allow use of dynamic blocks by the ring + * (normally 1). + * + * @return 0 on success, negative on error. + */ +extern int gxio_mpipe_config_edma_ring_blks(gxio_mpipe_context_t *context, + unsigned int ering, + unsigned int max_blks, + unsigned int min_snf_blks, + unsigned int db); + /***************************************************************** * Classifier Program * ******************************************************************/ @@ -1288,15 +1325,39 @@ typedef struct { /* The log2() of the number of entries. */ unsigned long log2_num_entries; + /* The context. */ + gxio_mpipe_context_t *context; + + /* The ering. */ + unsigned int ering; + + /* The channel. */ + unsigned int channel; + } gxio_mpipe_equeue_t; /* Initialize an "equeue". * - * Takes the equeue plus the same args as gxio_mpipe_init_edma_ring(). + * This function uses gxio_mpipe_init_edma_ring() to initialize the + * underlying edma_ring using the provided arguments. + * + * @param equeue An egress queue to be initialized. + * @param context An initialized mPIPE context. + * @param ering The eDMA ring index. + * @param channel The channel to use. This must be one of the channels + * associated with the context's set of open links. + * @param mem A physically contiguous region of memory to be filled + * with a ring of ::gxio_mpipe_edesc_t structures. + * @param mem_size Number of bytes in the ring. Must be 512, 2048, + * 8192 or 65536, times 16 (i.e. sizeof(gxio_mpipe_edesc_t)). + * @param mem_flags ::gxio_mpipe_mem_flags_e memory flags. + * + * @return 0 on success, ::GXIO_MPIPE_ERR_BAD_EDMA_RING or + * ::GXIO_ERR_INVAL_MEMORY_SIZE on failure. */ extern int gxio_mpipe_equeue_init(gxio_mpipe_equeue_t *equeue, gxio_mpipe_context_t *context, - unsigned int edma_ring_id, + unsigned int ering, unsigned int channel, void *mem, unsigned int mem_size, unsigned int mem_flags); @@ -1494,6 +1555,37 @@ static inline int gxio_mpipe_equeue_is_complete(gxio_mpipe_equeue_t *equeue, completion_slot, update); } +/* Set the snf (store and forward) size for an equeue. + * + * The snf size for an equeue defaults to 1536, and encodes the size + * of the largest packet for which egress is guaranteed to avoid + * transmission underruns and/or corrupt checksums under heavy load. + * + * The snf size affects a global resource pool which cannot support, + * for example, all 24 equeues each requesting an snf size of 8K. + * + * To ensure that jumbo packets can be egressed properly, the snf size + * should be set to the size of the largest possible packet, which + * will usually be limited by the size of the app's largest buffer. + * + * This is a convenience wrapper around + * gxio_mpipe_config_edma_ring_blks(). + * + * This function should not be called after any egress has been done + * on the equeue. + * + * @param equeue An egress queue initialized via gxio_mpipe_equeue_init(). + * @param size The snf size, in bytes. + * @return Zero on success, negative error otherwise. + */ +static inline int gxio_mpipe_equeue_set_snf_size(gxio_mpipe_equeue_t *equeue, + size_t size) +{ + int blks = (size + 127) / 128; + return gxio_mpipe_config_edma_ring_blks(equeue->context, equeue->ering, + blks + 1, blks, 1); +} + /***************************************************************** * Link Management * ******************************************************************/ @@ -1634,6 +1726,24 @@ typedef struct { uint8_t mac; } gxio_mpipe_link_t; +/* Translate a link name to the instance number of the mPIPE shim which is + * connected to that link. This call does not verify whether the link is + * currently available, and does not reserve any link resources; + * gxio_mpipe_link_open() must be called to perform those functions. + * + * Typically applications will call this function to translate a link name + * to an mPIPE instance number; call gxio_mpipe_init(), passing it that + * instance number, to initialize the mPIPE shim; and then call + * gxio_mpipe_link_open(), passing it the same link name plus the mPIPE + * context, to configure the link. + * + * @param link_name Name of the link; see @ref gxio_mpipe_link_names. + * @return The mPIPE instance number which is associated with the named + * link, or a negative error code (::GXIO_ERR_NO_DEVICE) if the link does + * not exist. + */ +extern int gxio_mpipe_link_instance(const char *link_name); + /* Retrieve one of this system's legal link names, and its MAC address. * * @param index Link name index. If a system supports N legal link names, @@ -1697,6 +1807,17 @@ static inline int gxio_mpipe_link_channel(gxio_mpipe_link_t *link) return link->channel; } +/* Set a link attribute. + * + * @param link A properly initialized link state object. + * @param attr An attribute from the set of @ref gxio_mpipe_link_attrs. + * @param val New value of the attribute. + * @return 0 if the attribute was successfully set, or a negative error + * code. + */ +extern int gxio_mpipe_link_set_attr(gxio_mpipe_link_t *link, uint32_t attr, + int64_t val); + /////////////////////////////////////////////////////////////////// // Timestamp // /////////////////////////////////////////////////////////////////// @@ -1733,4 +1854,18 @@ extern int gxio_mpipe_set_timestamp(gxio_mpipe_context_t *context, extern int gxio_mpipe_adjust_timestamp(gxio_mpipe_context_t *context, int64_t delta); +/** Adjust the mPIPE timestamp clock frequency. + * + * @param context An initialized mPIPE context. + * @param ppb A 32-bit signed PPB (Parts Per Billion) value to adjust. + * The absolute value of ppb must be less than or equal to 1000000000. + * Values less than about 30000 will generally cause a GXIO_ERR_INVAL + * return due to the granularity of the hardware that converts reference + * clock cycles into seconds and nanoseconds. + * @return If the call was successful, zero; otherwise, a negative error + * code. + */ +extern int gxio_mpipe_adjust_timestamp_freq(gxio_mpipe_context_t* context, + int32_t ppb); + #endif /* !_GXIO_MPIPE_H_ */ diff --git a/arch/tile/include/hv/drv_mpipe_intf.h b/arch/tile/include/hv/drv_mpipe_intf.h index 6cdae3bf046e..c97e416dd963 100644 --- a/arch/tile/include/hv/drv_mpipe_intf.h +++ b/arch/tile/include/hv/drv_mpipe_intf.h @@ -23,6 +23,9 @@ #include <arch/mpipe_constants.h> +/** Number of mPIPE instances supported */ +#define HV_MPIPE_INSTANCE_MAX (2) + /** Number of buffer stacks (32). */ #define HV_MPIPE_NUM_BUFFER_STACKS \ (MPIPE_MMIO_INIT_DAT_GX36_1__BUFFER_STACK_MASK_WIDTH) diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c index a7e4939787c9..7f910c76ca0a 100644 --- a/drivers/isdn/hardware/mISDN/hfcpci.c +++ b/drivers/isdn/hardware/mISDN/hfcpci.c @@ -1307,11 +1307,11 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol) } if (fifo2 & 2) { hc->hw.fifo_en &= ~HFCPCI_FIFOEN_B2; - hc->hw.int_m1 &= ~(HFCPCI_INTS_B2TRANS + + hc->hw.int_m1 &= ~(HFCPCI_INTS_B2TRANS | HFCPCI_INTS_B2REC); } else { hc->hw.fifo_en &= ~HFCPCI_FIFOEN_B1; - hc->hw.int_m1 &= ~(HFCPCI_INTS_B1TRANS + + hc->hw.int_m1 &= ~(HFCPCI_INTS_B1TRANS | HFCPCI_INTS_B1REC); } #ifdef REVERSE_BITORDER @@ -1346,14 +1346,14 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol) if (fifo2 & 2) { hc->hw.fifo_en |= HFCPCI_FIFOEN_B2; if (!tics) - hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS + + hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS | HFCPCI_INTS_B2REC); hc->hw.ctmt |= 2; hc->hw.conn &= ~0x18; } else { hc->hw.fifo_en |= HFCPCI_FIFOEN_B1; if (!tics) - hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS + + hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS | HFCPCI_INTS_B1REC); hc->hw.ctmt |= 1; hc->hw.conn &= ~0x03; @@ -1375,14 +1375,14 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol) if (fifo2 & 2) { hc->hw.last_bfifo_cnt[1] = 0; hc->hw.fifo_en |= HFCPCI_FIFOEN_B2; - hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS + + hc->hw.int_m1 |= (HFCPCI_INTS_B2TRANS | HFCPCI_INTS_B2REC); hc->hw.ctmt &= ~2; hc->hw.conn &= ~0x18; } else { hc->hw.last_bfifo_cnt[0] = 0; hc->hw.fifo_en |= HFCPCI_FIFOEN_B1; - hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS + + hc->hw.int_m1 |= (HFCPCI_INTS_B1TRANS | HFCPCI_INTS_B1REC); hc->hw.ctmt &= ~1; hc->hw.conn &= ~0x03; diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c index 390061d09693..90102652c82a 100644 --- a/drivers/net/bonding/bond_3ad.c +++ b/drivers/net/bonding/bond_3ad.c @@ -143,10 +143,9 @@ static inline struct bonding *__get_bond_by_port(struct port *port) */ static inline struct port *__get_first_port(struct bonding *bond) { - if (bond->slave_cnt == 0) - return NULL; + struct slave *first_slave = bond_first_slave(bond); - return &(SLAVE_AD_INFO(bond->first_slave).port); + return first_slave ? &(SLAVE_AD_INFO(first_slave).port) : NULL; } /** @@ -159,13 +158,16 @@ static inline struct port *__get_first_port(struct bonding *bond) static inline struct port *__get_next_port(struct port *port) { struct bonding *bond = __get_bond_by_port(port); - struct slave *slave = port->slave; + struct slave *slave = port->slave, *slave_next; // If there's no bond for this port, or this is the last slave - if ((bond == NULL) || (slave->next == bond->first_slave)) + if (bond == NULL) + return NULL; + slave_next = bond_next_slave(bond, slave); + if (!slave_next || bond_is_first_slave(bond, slave_next)) return NULL; - return &(SLAVE_AD_INFO(slave->next).port); + return &(SLAVE_AD_INFO(slave_next).port); } /** @@ -178,12 +180,14 @@ static inline struct port *__get_next_port(struct port *port) static inline struct aggregator *__get_first_agg(struct port *port) { struct bonding *bond = __get_bond_by_port(port); + struct slave *first_slave; // If there's no bond for this port, or bond has no slaves - if ((bond == NULL) || (bond->slave_cnt == 0)) + if (bond == NULL) return NULL; + first_slave = bond_first_slave(bond); - return &(SLAVE_AD_INFO(bond->first_slave).aggregator); + return first_slave ? &(SLAVE_AD_INFO(first_slave).aggregator) : NULL; } /** @@ -195,14 +199,17 @@ static inline struct aggregator *__get_first_agg(struct port *port) */ static inline struct aggregator *__get_next_agg(struct aggregator *aggregator) { - struct slave *slave = aggregator->slave; + struct slave *slave = aggregator->slave, *slave_next; struct bonding *bond = bond_get_bond_by_slave(slave); // If there's no bond for this aggregator, or this is the last slave - if ((bond == NULL) || (slave->next == bond->first_slave)) + if (bond == NULL) + return NULL; + slave_next = bond_next_slave(bond, slave); + if (!slave_next || bond_is_first_slave(bond, slave_next)) return NULL; - return &(SLAVE_AD_INFO(slave->next).aggregator); + return &(SLAVE_AD_INFO(slave_next).aggregator); } /* @@ -2110,7 +2117,7 @@ void bond_3ad_state_machine_handler(struct work_struct *work) read_lock(&bond->lock); //check if there are any slaves - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; // check if agg_select_timer timer after initialize is timed out @@ -2336,8 +2343,12 @@ void bond_3ad_handle_link_change(struct slave *slave, char link) int bond_3ad_set_carrier(struct bonding *bond) { struct aggregator *active; + struct slave *first_slave; - active = __get_active_agg(&(SLAVE_AD_INFO(bond->first_slave).aggregator)); + first_slave = bond_first_slave(bond); + if (!first_slave) + return 0; + active = __get_active_agg(&(SLAVE_AD_INFO(first_slave).aggregator)); if (active) { /* are enough slaves available to consider link up? */ if (active->num_of_ports < bond->params.min_links) { @@ -2415,6 +2426,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) struct ad_info ad_info; int res = 1; + read_lock(&bond->lock); if (__bond_3ad_get_active_agg_info(bond, &ad_info)) { pr_debug("%s: Error: __bond_3ad_get_active_agg_info failed\n", dev->name); @@ -2432,7 +2444,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) slave_agg_no = bond->xmit_hash_policy(skb, slaves_in_agg); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { struct aggregator *agg = SLAVE_AD_INFO(slave).port.aggregator; if (agg && (agg->aggregator_identifier == agg_id)) { @@ -2464,6 +2476,7 @@ int bond_3ad_xmit_xor(struct sk_buff *skb, struct net_device *dev) } out: + read_unlock(&bond->lock); if (res) { /* no suitable interface, frame not sent */ kfree_skb(skb); @@ -2501,7 +2514,6 @@ int bond_3ad_lacpdu_recv(const struct sk_buff *skb, struct bonding *bond, */ void bond_3ad_update_lacp_rate(struct bonding *bond) { - int i; struct slave *slave; struct port *port = NULL; int lacp_fast; @@ -2509,7 +2521,7 @@ void bond_3ad_update_lacp_rate(struct bonding *bond) write_lock_bh(&bond->lock); lacp_fast = bond->params.lacp_fast; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { port = &(SLAVE_AD_INFO(slave).port); if (port->slave == NULL) continue; diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 4ea8ed150d46..3a5db7b1df68 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -224,13 +224,12 @@ static struct slave *tlb_get_least_loaded_slave(struct bonding *bond) { struct slave *slave, *least_loaded; long long max_gap; - int i; least_loaded = NULL; max_gap = LLONG_MIN; /* Find the slave with the largest gap */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (SLAVE_IS_OK(slave)) { long long gap = compute_gap(slave); @@ -386,11 +385,10 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond) struct slave *rx_slave, *slave, *start_at; int i = 0; - if (bond_info->next_rx_slave) { + if (bond_info->next_rx_slave) start_at = bond_info->next_rx_slave; - } else { - start_at = bond->first_slave; - } + else + start_at = bond_first_slave(bond); rx_slave = NULL; @@ -405,7 +403,8 @@ static struct slave *rlb_next_rx_slave(struct bonding *bond) } if (rx_slave) { - bond_info->next_rx_slave = rx_slave->next; + slave = bond_next_slave(bond, rx_slave); + bond_info->next_rx_slave = slave; } return rx_slave; @@ -1173,9 +1172,8 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav { struct slave *tmp_slave1, *free_mac_slave = NULL; struct slave *has_bond_addr = bond->curr_active_slave; - int i; - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { /* this is the first slave */ return 0; } @@ -1196,7 +1194,7 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav /* The slave's address is equal to the address of the bond. * Search for a spare address in the bond for this slave. */ - bond_for_each_slave(bond, tmp_slave1, i) { + bond_for_each_slave(bond, tmp_slave1) { if (!bond_slave_has_mac(bond, tmp_slave1->perm_hwaddr)) { /* no slave has tmp_slave1's perm addr * as its curr addr @@ -1246,17 +1244,15 @@ static int alb_handle_addr_collision_on_attach(struct bonding *bond, struct slav */ static int alb_set_mac_address(struct bonding *bond, void *addr) { - struct sockaddr sa; - struct slave *slave, *stop_at; char tmp_addr[ETH_ALEN]; + struct slave *slave; + struct sockaddr sa; int res; - int i; - if (bond->alb_info.rlb_enabled) { + if (bond->alb_info.rlb_enabled) return 0; - } - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { /* save net_device's current hw address */ memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); @@ -1276,8 +1272,7 @@ unwind: sa.sa_family = bond->dev->type; /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + bond_for_each_slave_continue_reverse(bond, slave) { memcpy(tmp_addr, slave->dev->dev_addr, ETH_ALEN); dev_set_mac_address(slave->dev, &sa); memcpy(slave->dev->dev_addr, tmp_addr, ETH_ALEN); @@ -1342,6 +1337,7 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) /* make sure that the curr_active_slave do not change during tx */ + read_lock(&bond->lock); read_lock(&bond->curr_slave_lock); switch (ntohs(skb->protocol)) { @@ -1446,11 +1442,12 @@ int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) } read_unlock(&bond->curr_slave_lock); - + read_unlock(&bond->lock); if (res) { /* no suitable interface, frame not sent */ kfree_skb(skb); } + return NETDEV_TX_OK; } @@ -1460,11 +1457,10 @@ void bond_alb_monitor(struct work_struct *work) alb_work.work); struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); struct slave *slave; - int i; read_lock(&bond->lock); - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { bond_info->tx_rebalance_counter = 0; bond_info->lp_counter = 0; goto re_arm; @@ -1482,9 +1478,8 @@ void bond_alb_monitor(struct work_struct *work) */ read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) alb_send_learning_packets(slave, slave->dev->dev_addr); - } read_unlock(&bond->curr_slave_lock); @@ -1496,7 +1491,7 @@ void bond_alb_monitor(struct work_struct *work) read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { tlb_clear_slave(bond, slave, 1); if (slave == bond->curr_active_slave) { SLAVE_TLB_INFO(slave).load = @@ -1602,9 +1597,8 @@ int bond_alb_init_slave(struct bonding *bond, struct slave *slave) */ void bond_alb_deinit_slave(struct bonding *bond, struct slave *slave) { - if (bond->slave_cnt > 1) { + if (!list_empty(&bond->slave_list)) alb_change_hw_addr_on_detach(bond, slave); - } tlb_clear_slave(bond, slave, 0); @@ -1661,9 +1655,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave { struct slave *swap_slave; - if (bond->curr_active_slave == new_slave) { + if (bond->curr_active_slave == new_slave) return; - } if (bond->curr_active_slave && bond->alb_info.primary_is_promisc) { dev_set_promiscuity(bond->curr_active_slave->dev, -1); @@ -1672,11 +1665,10 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave } swap_slave = bond->curr_active_slave; - bond->curr_active_slave = new_slave; + rcu_assign_pointer(bond->curr_active_slave, new_slave); - if (!new_slave || (bond->slave_cnt == 0)) { + if (!new_slave || list_empty(&bond->slave_list)) return; - } /* set the new curr_active_slave to the bonds mac address * i.e. swap mac addresses of old curr_active_slave and new curr_active_slave @@ -1689,9 +1681,8 @@ void bond_alb_handle_active_change(struct bonding *bond, struct slave *new_slave * ignored so we can mess with their MAC addresses without * fear of interference from transmit activity. */ - if (swap_slave) { + if (swap_slave) tlb_clear_slave(bond, swap_slave, 1); - } tlb_clear_slave(bond, new_slave, 1); write_unlock_bh(&bond->curr_slave_lock); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 07f257d44a1e..476df7d2a354 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -77,6 +77,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/pkt_sched.h> +#include <linux/rculist.h> #include "bonding.h" #include "bond_3ad.h" #include "bond_alb.h" @@ -106,7 +107,7 @@ static char *arp_ip_target[BOND_MAX_ARP_TARGETS]; static char *arp_validate; static char *arp_all_targets; static char *fail_over_mac; -static int all_slaves_active = 0; +static int all_slaves_active; static struct bond_params bonding_defaults; static int resend_igmp = BOND_DEFAULT_RESEND_IGMP; @@ -273,7 +274,7 @@ const char *bond_mode_name(int mode) [BOND_MODE_ALB] = "adaptive load balancing", }; - if (mode < 0 || mode > BOND_MODE_ALB) + if (mode < BOND_MODE_ROUNDROBIN || mode > BOND_MODE_ALB) return "unknown"; return names[mode]; @@ -441,10 +442,10 @@ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, __be16 proto, u16 vid) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; - int i, res; + struct slave *slave; + int res; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { res = vlan_vid_add(slave->dev, proto, vid); if (res) goto unwind; @@ -461,8 +462,7 @@ static int bond_vlan_rx_add_vid(struct net_device *bond_dev, unwind: /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) + bond_for_each_slave_continue_reverse(bond, slave) vlan_vid_del(slave->dev, proto, vid); return res; @@ -478,9 +478,9 @@ static int bond_vlan_rx_kill_vid(struct net_device *bond_dev, { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i, res; + int res; - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) vlan_vid_del(slave->dev, proto, vid); res = bond_del_vlan(bond, vid); @@ -532,15 +532,14 @@ static void bond_del_vlans_from_slave(struct bonding *bond, static int bond_set_carrier(struct bonding *bond) { struct slave *slave; - int i; - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto down; if (bond->params.mode == BOND_MODE_8023AD) return bond_3ad_set_carrier(bond); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (slave->link == BOND_LINK_UP) { if (!netif_carrier_ok(bond->dev)) { netif_carrier_on(bond->dev); @@ -681,8 +680,8 @@ static int bond_set_promiscuity(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave) { err = dev_set_promiscuity(slave->dev, inc); if (err) return err; @@ -705,8 +704,8 @@ static int bond_set_allmulti(struct bonding *bond, int inc) } } else { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + + bond_for_each_slave(bond, slave) { err = dev_set_allmulti(slave->dev, inc); if (err) return err; @@ -715,15 +714,6 @@ static int bond_set_allmulti(struct bonding *bond, int inc) return err; } -static void __bond_resend_igmp_join_requests(struct net_device *dev) -{ - struct in_device *in_dev; - - in_dev = __in_dev_get_rcu(dev); - if (in_dev) - ip_mc_rejoin_groups(in_dev); -} - /* * Retrieve the list of registered multicast addresses for the bonding * device and retransmit an IGMP JOIN request to the current active @@ -731,33 +721,12 @@ static void __bond_resend_igmp_join_requests(struct net_device *dev) */ static void bond_resend_igmp_join_requests(struct bonding *bond) { - struct net_device *bond_dev, *vlan_dev, *upper_dev; - struct vlan_entry *vlan; - - read_lock(&bond->lock); - rcu_read_lock(); - - bond_dev = bond->dev; - - /* rejoin all groups on bond device */ - __bond_resend_igmp_join_requests(bond_dev); - - /* - * if bond is enslaved to a bridge, - * then rejoin all groups on its master - */ - upper_dev = netdev_master_upper_dev_get_rcu(bond_dev); - if (upper_dev && upper_dev->priv_flags & IFF_EBRIDGE) - __bond_resend_igmp_join_requests(upper_dev); - - /* rejoin all groups on vlan devices */ - list_for_each_entry(vlan, &bond->vlan_list, vlan_list) { - vlan_dev = __vlan_find_dev_deep(bond_dev, htons(ETH_P_8021Q), - vlan->vlan_id); - if (vlan_dev) - __bond_resend_igmp_join_requests(vlan_dev); + if (!rtnl_trylock()) { + queue_delayed_work(bond->wq, &bond->mcast_work, 1); + return; } - rcu_read_unlock(); + call_netdevice_notifiers(NETDEV_RESEND_IGMP, bond->dev); + rtnl_unlock(); /* We use curr_slave_lock to protect against concurrent access to * igmp_retrans from multiple running instances of this function and @@ -769,7 +738,6 @@ static void bond_resend_igmp_join_requests(struct bonding *bond) queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5); } write_unlock_bh(&bond->curr_slave_lock); - read_unlock(&bond->lock); } static void bond_resend_igmp_join_requests_delayed(struct work_struct *work) @@ -966,9 +934,8 @@ static struct slave *bond_find_best_slave(struct bonding *bond) new_active = bond->curr_active_slave; if (!new_active) { /* there were no active slaves left */ - if (bond->slave_cnt > 0) /* found one slave */ - new_active = bond->first_slave; - else + new_active = bond_first_slave(bond); + if (!new_active) return NULL; /* still no slave, return NULL */ } @@ -1071,7 +1038,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) if (new_active) bond_set_slave_active_flags(new_active); } else { - bond->curr_active_slave = new_active; + rcu_assign_pointer(bond->curr_active_slave, new_active); } if (bond->params.mode == BOND_MODE_ACTIVEBACKUP) { @@ -1115,7 +1082,7 @@ void bond_change_active_slave(struct bonding *bond, struct slave *new_active) ((USES_PRIMARY(bond->params.mode) && new_active) || bond->params.mode == BOND_MODE_ROUNDROBIN)) { bond->igmp_retrans = bond->params.resend_igmp; - queue_delayed_work(bond->wq, &bond->mcast_work, 0); + queue_delayed_work(bond->wq, &bond->mcast_work, 1); } } @@ -1161,17 +1128,7 @@ void bond_select_active_slave(struct bonding *bond) */ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) { - if (bond->first_slave == NULL) { /* attaching the first slave */ - new_slave->next = new_slave; - new_slave->prev = new_slave; - bond->first_slave = new_slave; - } else { - new_slave->next = bond->first_slave; - new_slave->prev = bond->first_slave->prev; - new_slave->next->prev = new_slave; - new_slave->prev->next = new_slave; - } - + list_add_tail_rcu(&new_slave->list, &bond->slave_list); bond->slave_cnt++; } @@ -1187,22 +1144,7 @@ static void bond_attach_slave(struct bonding *bond, struct slave *new_slave) */ static void bond_detach_slave(struct bonding *bond, struct slave *slave) { - if (slave->next) - slave->next->prev = slave->prev; - - if (slave->prev) - slave->prev->next = slave->next; - - if (bond->first_slave == slave) { /* slave is the first slave */ - if (bond->slave_cnt > 1) { /* there are more slave */ - bond->first_slave = slave->next; - } else { - bond->first_slave = NULL; /* slave was the last one */ - } - } - - slave->next = NULL; - slave->prev = NULL; + list_del_rcu(&slave->list); bond->slave_cnt--; } @@ -1249,47 +1191,31 @@ static void bond_poll_controller(struct net_device *bond_dev) { } -static void __bond_netpoll_cleanup(struct bonding *bond) +static void bond_netpoll_cleanup(struct net_device *bond_dev) { + struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) if (IS_UP(slave->dev)) slave_disable_netpoll(slave); } -static void bond_netpoll_cleanup(struct net_device *bond_dev) -{ - struct bonding *bond = netdev_priv(bond_dev); - - read_lock(&bond->lock); - __bond_netpoll_cleanup(bond); - read_unlock(&bond->lock); -} static int bond_netpoll_setup(struct net_device *dev, struct netpoll_info *ni, gfp_t gfp) { struct bonding *bond = netdev_priv(dev); struct slave *slave; - int i, err = 0; + int err = 0; - read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { err = slave_enable_netpoll(slave); if (err) { - __bond_netpoll_cleanup(bond); + bond_netpoll_cleanup(dev); break; } } - read_unlock(&bond->lock); return err; } - -static struct netpoll_info *bond_netpoll_info(struct bonding *bond) -{ - return bond->dev->npinfo; -} - #else static inline int slave_enable_netpoll(struct slave *slave) { @@ -1311,11 +1237,10 @@ static netdev_features_t bond_fix_features(struct net_device *dev, struct slave *slave; struct bonding *bond = netdev_priv(dev); netdev_features_t mask; - int i; read_lock(&bond->lock); - if (!bond->first_slave) { + if (list_empty(&bond->slave_list)) { /* Disable adding VLANs to empty bond. But why? --mq */ features |= NETIF_F_VLAN_CHALLENGED; goto out; @@ -1325,7 +1250,7 @@ static netdev_features_t bond_fix_features(struct net_device *dev, features &= ~NETIF_F_ONE_FOR_ALL; features |= NETIF_F_ALL_FOR_ALL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { features = netdev_increment_features(features, slave->dev->features, mask); @@ -1349,15 +1274,14 @@ static void bond_compute_features(struct bonding *bond) unsigned short max_hard_header_len = ETH_HLEN; unsigned int gso_max_size = GSO_MAX_SIZE; u16 gso_max_segs = GSO_MAX_SEGS; - int i; unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE; read_lock(&bond->lock); - if (!bond->first_slave) + if (list_empty(&bond->slave_list)) goto done; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { vlan_features = netdev_increment_features(vlan_features, slave->dev->vlan_features, BOND_VLAN_FEATURES); @@ -1545,7 +1469,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * bond ether type mutual exclusion - don't allow slaves of dissimilar * ether type (eg ARPHRD_ETHER and ARPHRD_INFINIBAND) share the same bond */ - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { if (bond_dev->type != slave_dev->type) { pr_debug("%s: change device type from %d to %d\n", bond_dev->name, @@ -1584,7 +1508,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) } if (slave_ops->ndo_set_mac_address == NULL) { - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { pr_warning("%s: Warning: The first slave device specified does not support setting the MAC address. Setting fail_over_mac to active.", bond_dev->name); bond->params.fail_over_mac = BOND_FOM_ACTIVE; @@ -1600,7 +1524,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) /* If this is the first slave, then we need to set the master's hardware * address to be the same as the slave's. */ - if (!bond->slave_cnt && bond->dev->addr_assign_type == NET_ADDR_RANDOM) + if (list_empty(&bond->slave_list) && + bond->dev->addr_assign_type == NET_ADDR_RANDOM) bond_set_dev_addr(bond->dev, slave_dev); new_slave = kzalloc(sizeof(struct slave), GFP_KERNEL); @@ -1608,7 +1533,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) res = -ENOMEM; goto err_undo_flags; } - + INIT_LIST_HEAD(&new_slave->list); /* * Set the new_slave's queue_id to be zero. Queue ID mapping * is set via sysfs or module option if desired. @@ -1794,15 +1719,18 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) */ bond_set_slave_inactive_flags(new_slave); /* if this is the first slave */ - if (bond->slave_cnt == 1) { + if (bond_first_slave(bond) == new_slave) { SLAVE_AD_INFO(new_slave).id = 1; /* Initialize AD with the number of times that the AD timer is called in 1 second * can be called only after the mac address of the bond is set */ bond_3ad_initialize(bond, 1000/AD_TIMER_INTERVAL); } else { + struct slave *prev_slave; + + prev_slave = bond_prev_slave(bond, new_slave); SLAVE_AD_INFO(new_slave).id = - SLAVE_AD_INFO(new_slave->prev).id + 1; + SLAVE_AD_INFO(prev_slave).id + 1; } bond_3ad_bind_slave(new_slave); @@ -1824,7 +1752,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) * so we can change it without calling change_active_interface() */ if (!bond->curr_active_slave && new_slave->link == BOND_LINK_UP) - bond->curr_active_slave = new_slave; + rcu_assign_pointer(bond->curr_active_slave, new_slave); break; } /* switch(bond_mode) */ @@ -1834,7 +1762,7 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) bond_set_carrier(bond); #ifdef CONFIG_NET_POLL_CONTROLLER - slave_dev->npinfo = bond_netpoll_info(bond); + slave_dev->npinfo = bond->dev->npinfo; if (slave_dev->npinfo) { if (slave_enable_netpoll(new_slave)) { read_unlock(&bond->lock); @@ -1921,7 +1849,7 @@ err_free: err_undo_flags: bond_compute_features(bond); /* Enslave of first slave has failed and we need to fix master's mac */ - if (bond->slave_cnt == 0 && + if (list_empty(&bond->slave_list) && ether_addr_equal(bond_dev->dev_addr, slave_dev->dev_addr)) eth_hw_addr_random(bond_dev); @@ -1977,15 +1905,6 @@ static int __bond_release_one(struct net_device *bond_dev, netdev_rx_handler_unregister(slave_dev); write_lock_bh(&bond->lock); - if (!all && !bond->params.fail_over_mac) { - if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) && - bond->slave_cnt > 1) - pr_warning("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", - bond_dev->name, slave_dev->name, - slave->perm_hwaddr, - bond_dev->name, slave_dev->name); - } - /* Inform AD package of unbinding of slave. */ if (bond->params.mode == BOND_MODE_8023AD) { /* must be called before the slave is @@ -2006,6 +1925,15 @@ static int __bond_release_one(struct net_device *bond_dev, /* release the slave from its bond */ bond_detach_slave(bond, slave); + if (!all && !bond->params.fail_over_mac) { + if (ether_addr_equal(bond_dev->dev_addr, slave->perm_hwaddr) && + !list_empty(&bond->slave_list)) + pr_warn("%s: Warning: the permanent HWaddr of %s - %pM - is still in use by %s. Set the HWaddr of %s to a different address to avoid conflicts.\n", + bond_dev->name, slave_dev->name, + slave->perm_hwaddr, + bond_dev->name, slave_dev->name); + } + if (bond->primary_slave == slave) bond->primary_slave = NULL; @@ -2024,7 +1952,7 @@ static int __bond_release_one(struct net_device *bond_dev, } if (all) { - bond->curr_active_slave = NULL; + rcu_assign_pointer(bond->curr_active_slave, NULL); } else if (oldcurrent == slave) { /* * Note that we hold RTNL over this sequence, so there @@ -2042,7 +1970,7 @@ static int __bond_release_one(struct net_device *bond_dev, write_lock_bh(&bond->lock); } - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { bond_set_carrier(bond); eth_hw_addr_random(bond_dev); @@ -2056,8 +1984,9 @@ static int __bond_release_one(struct net_device *bond_dev, write_unlock_bh(&bond->lock); unblock_netpoll_tx(); + synchronize_rcu(); - if (bond->slave_cnt == 0) { + if (list_empty(&bond->slave_list)) { call_netdevice_notifiers(NETDEV_CHANGEADDR, bond->dev); call_netdevice_notifiers(NETDEV_RELEASE, bond->dev); } @@ -2128,7 +2057,7 @@ static int bond_release_and_destroy(struct net_device *bond_dev, int ret; ret = bond_release(bond_dev, slave_dev); - if ((ret == 0) && (bond->slave_cnt == 0)) { + if (ret == 0 && list_empty(&bond->slave_list)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; pr_info("%s: destroying bond %s.\n", bond_dev->name, bond_dev->name); @@ -2165,23 +2094,19 @@ static int bond_ioctl_change_active(struct net_device *bond_dev, struct net_devi read_lock(&bond->lock); - read_lock(&bond->curr_slave_lock); old_active = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - new_active = bond_get_slave_by_dev(bond, slave_dev); - /* * Changing to the current active: do nothing; return success. */ - if (new_active && (new_active == old_active)) { + if (new_active && new_active == old_active) { read_unlock(&bond->lock); return 0; } - if ((new_active) && - (old_active) && - (new_active->link == BOND_LINK_UP) && + if (new_active && + old_active && + new_active->link == BOND_LINK_UP && IS_UP(new_active->dev)) { block_netpoll_tx(); write_lock_bh(&bond->curr_slave_lock); @@ -2213,13 +2138,12 @@ static int bond_info_query(struct net_device *bond_dev, struct ifbond *info) static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *info) { struct bonding *bond = netdev_priv(bond_dev); + int i = 0, res = -ENODEV; struct slave *slave; - int i, res = -ENODEV; read_lock(&bond->lock); - - bond_for_each_slave(bond, slave, i) { - if (i == (int)info->slave_id) { + bond_for_each_slave(bond, slave) { + if (i++ == (int)info->slave_id) { res = 0; strcpy(info->slave_name, slave->dev->name); info->link = slave->link; @@ -2228,7 +2152,6 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in break; } } - read_unlock(&bond->lock); return res; @@ -2239,13 +2162,13 @@ static int bond_slave_info_query(struct net_device *bond_dev, struct ifslave *in static int bond_miimon_inspect(struct bonding *bond) { + int link_state, commit = 0; struct slave *slave; - int i, link_state, commit = 0; bool ignore_updelay; ignore_updelay = !bond->curr_active_slave ? true : false; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { slave->new_link = BOND_LINK_NOCHANGE; link_state = bond_check_dev_link(bond, slave->dev, 0); @@ -2340,9 +2263,8 @@ static int bond_miimon_inspect(struct bonding *bond) static void bond_miimon_commit(struct bonding *bond) { struct slave *slave; - int i; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; @@ -2447,7 +2369,7 @@ void bond_mii_monitor(struct work_struct *work) delay = msecs_to_jiffies(bond->params.miimon); - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); @@ -2727,20 +2649,16 @@ void bond_loadbalance_arp_mon(struct work_struct *work) struct slave *slave, *oldcurrent; int do_failover = 0; int delta_in_ticks, extra_ticks; - int i; read_lock(&bond->lock); delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); extra_ticks = delta_in_ticks / 2; - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; - read_lock(&bond->curr_slave_lock); oldcurrent = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - /* see if any of the previous devices are up now (i.e. they have * xmt and rcv traffic). the curr_active_slave does not come into * the picture unless it is null. also, slave->jiffies is not needed @@ -2749,7 +2667,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * TODO: what about up/down delay in arp mode? it wasn't here before * so it can wait */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { unsigned long trans_start = dev_trans_start(slave->dev); if (slave->link != BOND_LINK_UP) { @@ -2846,10 +2764,10 @@ re_arm: */ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) { - struct slave *slave; - int i, commit = 0; unsigned long trans_start; + struct slave *slave; int extra_ticks; + int commit = 0; /* All the time comparisons below need some extra time. Otherwise, on * fast networks the ARP probe/reply may arrive within the same jiffy @@ -2858,7 +2776,7 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ extra_ticks = delta_in_ticks / 2; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { slave->new_link = BOND_LINK_NOCHANGE; if (slave->link != BOND_LINK_UP) { @@ -2937,11 +2855,10 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) { - struct slave *slave; - int i; unsigned long trans_start; + struct slave *slave; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { switch (slave->new_link) { case BOND_LINK_NOCHANGE: continue; @@ -3014,7 +2931,7 @@ do_failover: */ static void bond_ab_arp_probe(struct bonding *bond) { - struct slave *slave; + struct slave *slave, *next_slave; int i; read_lock(&bond->curr_slave_lock); @@ -3038,7 +2955,7 @@ static void bond_ab_arp_probe(struct bonding *bond) */ if (!bond->current_arp_slave) { - bond->current_arp_slave = bond->first_slave; + bond->current_arp_slave = bond_first_slave(bond); if (!bond->current_arp_slave) return; } @@ -3046,7 +2963,8 @@ static void bond_ab_arp_probe(struct bonding *bond) bond_set_slave_inactive_flags(bond->current_arp_slave); /* search for next candidate */ - bond_for_each_slave_from(bond, slave, i, bond->current_arp_slave->next) { + next_slave = bond_next_slave(bond, bond->current_arp_slave); + bond_for_each_slave_from(bond, slave, i, next_slave) { if (IS_UP(slave->dev)) { slave->link = BOND_LINK_BACK; bond_set_slave_active_flags(slave); @@ -3087,7 +3005,7 @@ void bond_activebackup_arp_mon(struct work_struct *work) delta_in_ticks = msecs_to_jiffies(bond->params.arp_interval); - if (bond->slave_cnt == 0) + if (list_empty(&bond->slave_list)) goto re_arm; should_notify_peers = bond_should_notify_peers(bond); @@ -3234,6 +3152,10 @@ static int bond_slave_netdev_event(unsigned long event, case NETDEV_FEAT_CHANGE: bond_compute_features(bond); break; + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, slave->bond->dev); + break; default: break; } @@ -3403,13 +3325,12 @@ static int bond_open(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; /* reset slave->backup and slave->inactive */ read_lock(&bond->lock); - if (bond->slave_cnt > 0) { + if (!list_empty(&bond->slave_list)) { read_lock(&bond->curr_slave_lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if ((bond->params.mode == BOND_MODE_ACTIVEBACKUP) && (slave != bond->curr_active_slave)) { bond_set_slave_inactive_flags(slave); @@ -3477,13 +3398,11 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, struct bonding *bond = netdev_priv(bond_dev); struct rtnl_link_stats64 temp; struct slave *slave; - int i; memset(stats, 0, sizeof(*stats)); read_lock_bh(&bond->lock); - - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { const struct rtnl_link_stats64 *sstats = dev_get_stats(slave->dev, &temp); @@ -3513,7 +3432,6 @@ static struct rtnl_link_stats64 *bond_get_stats(struct net_device *bond_dev, stats->tx_heartbeat_errors += sstats->tx_heartbeat_errors; stats->tx_window_errors += sstats->tx_window_errors; } - read_unlock_bh(&bond->lock); return stats; @@ -3652,7 +3570,6 @@ static void bond_set_rx_mode(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; - int i; read_lock(&bond->lock); @@ -3665,7 +3582,7 @@ static void bond_set_rx_mode(struct net_device *bond_dev) } read_unlock(&bond->curr_slave_lock); } else { - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { dev_uc_sync_multiple(slave->dev, bond_dev); dev_mc_sync_multiple(slave->dev, bond_dev); } @@ -3677,16 +3594,15 @@ static void bond_set_rx_mode(struct net_device *bond_dev) static int bond_neigh_init(struct neighbour *n) { struct bonding *bond = netdev_priv(n->dev); - struct slave *slave = bond->first_slave; const struct net_device_ops *slave_ops; struct neigh_parms parms; + struct slave *slave; int ret; + slave = bond_first_slave(bond); if (!slave) return 0; - slave_ops = slave->dev->netdev_ops; - if (!slave_ops->ndo_neigh_setup) return 0; @@ -3714,11 +3630,17 @@ static int bond_neigh_init(struct neighbour *n) * The bonding ndo_neigh_setup is called at init time beofre any * slave exists. So we must declare proxy setup function which will * be used at run time to resolve the actual slave neigh param setup. + * + * It's also called by master devices (such as vlans) to setup their + * underlying devices. In that case - do nothing, we're already set up from + * our init. */ static int bond_neigh_setup(struct net_device *dev, struct neigh_parms *parms) { - parms->neigh_setup = bond_neigh_init; + /* modify only our neigh_parms */ + if (parms->dev == dev) + parms->neigh_setup = bond_neigh_init; return 0; } @@ -3729,9 +3651,8 @@ static int bond_neigh_setup(struct net_device *dev, static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *stop_at; + struct slave *slave; int res = 0; - int i; pr_debug("bond=%p, name=%s, new_mtu=%d\n", bond, (bond_dev ? bond_dev->name : "None"), new_mtu); @@ -3751,10 +3672,10 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { pr_debug("s %p s->p %p c_m %p\n", slave, - slave->prev, + bond_prev_slave(bond, slave), slave->dev->netdev_ops->ndo_change_mtu); res = dev_set_mtu(slave->dev, new_mtu); @@ -3779,8 +3700,7 @@ static int bond_change_mtu(struct net_device *bond_dev, int new_mtu) unwind: /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + bond_for_each_slave_continue_reverse(bond, slave) { int tmp_res; tmp_res = dev_set_mtu(slave->dev, bond_dev->mtu); @@ -3804,9 +3724,8 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) { struct bonding *bond = netdev_priv(bond_dev); struct sockaddr *sa = addr, tmp_sa; - struct slave *slave, *stop_at; + struct slave *slave; int res = 0; - int i; if (bond->params.mode == BOND_MODE_ALB) return bond_alb_set_mac_address(bond_dev, addr); @@ -3839,7 +3758,7 @@ static int bond_set_mac_address(struct net_device *bond_dev, void *addr) * call to the base driver. */ - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { const struct net_device_ops *slave_ops = slave->dev->netdev_ops; pr_debug("slave %p %s\n", slave, slave->dev->name); @@ -3871,8 +3790,7 @@ unwind: tmp_sa.sa_family = bond_dev->type; /* unwind from head to the slave that failed */ - stop_at = slave; - bond_for_each_slave_from_to(bond, slave, i, bond->first_slave, stop_at) { + bond_for_each_slave_continue_reverse(bond, slave) { int tmp_res; tmp_res = dev_set_mac_address(slave->dev, &tmp_sa); @@ -3885,12 +3803,50 @@ unwind: return res; } +/** + * bond_xmit_slave_id - transmit skb through slave with slave_id + * @bond: bonding device that is transmitting + * @skb: buffer to transmit + * @slave_id: slave id up to slave_cnt-1 through which to transmit + * + * This function tries to transmit through slave with slave_id but in case + * it fails, it tries to find the first available slave for transmission. + * The skb is consumed in all cases, thus the function is void. + */ +void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id) +{ + struct slave *slave; + int i = slave_id; + + /* Here we start from the slave with slave_id */ + bond_for_each_slave_rcu(bond, slave) { + if (--i < 0) { + if (slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + } + + /* Here we start from the first slave up to slave_id */ + i = slave_id; + bond_for_each_slave_rcu(bond, slave) { + if (--i < 0) + break; + if (slave_can_tx(slave)) { + bond_dev_queue_xmit(bond, skb, slave->dev); + return; + } + } + /* no slave that can tx has been found */ + kfree_skb(skb); +} + static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int i, slave_no, res = 1; struct iphdr *iph = ip_hdr(skb); + struct slave *slave; /* * Start with the curr_active_slave that joined the bond as the @@ -3899,50 +3855,20 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if ((iph->protocol == IPPROTO_IGMP) && - (skb->protocol == htons(ETH_P_IP))) { - - read_lock(&bond->curr_slave_lock); - slave = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!slave) - goto out; + if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave && slave_can_tx(slave)) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); } else { - /* - * Concurrent TX may collide on rr_tx_counter; we accept - * that as being rare enough not to justify using an - * atomic op here. - */ - slave_no = bond->rr_tx_counter++ % bond->slave_cnt; - - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - } - - start_at = slave; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - -out: - if (res) { - /* no suitable interface, frame not sent */ - kfree_skb(skb); + bond_xmit_slave_id(bond, skb, + bond->rr_tx_counter++ % bond->slave_cnt); } return NETDEV_TX_OK; } - /* * in active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. @@ -3950,18 +3876,12 @@ out: static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - int res = 1; - - read_lock(&bond->curr_slave_lock); - - if (bond->curr_active_slave) - res = bond_dev_queue_xmit(bond, skb, - bond->curr_active_slave->dev); - - read_unlock(&bond->curr_slave_lock); + struct slave *slave; - if (res) - /* no suitable interface, frame not sent */ + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else kfree_skb(skb); return NETDEV_TX_OK; @@ -3975,87 +3895,39 @@ static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_d static int bond_xmit_xor(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - int slave_no; - int i; - int res = 1; - - slave_no = bond->xmit_hash_policy(skb, bond->slave_cnt); - bond_for_each_slave(bond, slave, i) { - slave_no--; - if (slave_no < 0) - break; - } - - start_at = slave; - - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - res = bond_dev_queue_xmit(bond, skb, slave->dev); - break; - } - } - - if (res) { - /* no suitable interface, frame not sent */ - kfree_skb(skb); - } + bond_xmit_slave_id(bond, skb, + bond->xmit_hash_policy(skb, bond->slave_cnt)); return NETDEV_TX_OK; } -/* - * in broadcast mode, we send everything to all usable interfaces. - */ +/* in broadcast mode, we send everything to all usable interfaces. */ static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave, *start_at; - struct net_device *tx_dev = NULL; - int i; - int res = 1; - - read_lock(&bond->curr_slave_lock); - start_at = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - if (!start_at) - goto out; + struct slave *slave = NULL; - bond_for_each_slave_from(bond, slave, i, start_at) { - if (IS_UP(slave->dev) && - (slave->link == BOND_LINK_UP) && - bond_is_active_slave(slave)) { - if (tx_dev) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - if (!skb2) { - pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", - bond_dev->name); - continue; - } + bond_for_each_slave_rcu(bond, slave) { + if (bond_is_last_slave(bond, slave)) + break; + if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP) { + struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); - res = bond_dev_queue_xmit(bond, skb2, tx_dev); - if (res) { - kfree_skb(skb2); - continue; - } + if (!skb2) { + pr_err("%s: Error: bond_xmit_broadcast(): skb_clone() failed\n", + bond_dev->name); + continue; } - tx_dev = slave->dev; + /* bond_dev_queue_xmit always returns 0 */ + bond_dev_queue_xmit(bond, skb2, slave->dev); } } - - if (tx_dev) - res = bond_dev_queue_xmit(bond, skb, tx_dev); - -out: - if (res) - /* no suitable interface, frame not sent */ + if (slave && IS_UP(slave->dev) && slave->link == BOND_LINK_UP) + bond_dev_queue_xmit(bond, skb, slave->dev); + else kfree_skb(skb); - /* frame sent to all suitable interfaces */ return NETDEV_TX_OK; } @@ -4083,15 +3955,15 @@ static void bond_set_xmit_hash_policy(struct bonding *bond) static inline int bond_slave_override(struct bonding *bond, struct sk_buff *skb) { - int i, res = 1; struct slave *slave = NULL; struct slave *check_slave; + int res = 1; if (!skb->queue_mapping) return 1; /* Find out if any slaves have the same mapping as this skb. */ - bond_for_each_slave(bond, check_slave, i) { + bond_for_each_slave_rcu(bond, check_slave) { if (check_slave->queue_id == skb->queue_mapping) { slave = check_slave; break; @@ -4176,14 +4048,12 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev) if (is_netpoll_tx_blocked(dev)) return NETDEV_TX_BUSY; - read_lock(&bond->lock); - - if (bond->slave_cnt) + rcu_read_lock(); + if (!list_empty(&bond->slave_list)) ret = __bond_start_xmit(skb, dev); else kfree_skb(skb); - - read_unlock(&bond->lock); + rcu_read_unlock(); return ret; } @@ -4224,9 +4094,8 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, struct ethtool_cmd *ecmd) { struct bonding *bond = netdev_priv(bond_dev); - struct slave *slave; - int i; unsigned long speed = 0; + struct slave *slave; ecmd->duplex = DUPLEX_UNKNOWN; ecmd->port = PORT_OTHER; @@ -4237,7 +4106,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, * this is an accurate maximum. */ read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (SLAVE_IS_OK(slave)) { if (slave->speed != SPEED_UNKNOWN) speed += slave->speed; @@ -4248,6 +4117,7 @@ static int bond_ethtool_get_settings(struct net_device *bond_dev, } ethtool_cmd_speed_set(ecmd, speed ? : SPEED_UNKNOWN); read_unlock(&bond->lock); + return 0; } @@ -4311,7 +4181,7 @@ static void bond_setup(struct net_device *bond_dev) /* initialize rwlocks */ rwlock_init(&bond->lock); rwlock_init(&bond->curr_slave_lock); - + INIT_LIST_HEAD(&bond->slave_list); bond->params = bonding_defaults; /* Initialize pointers */ @@ -4368,13 +4238,14 @@ static void bond_setup(struct net_device *bond_dev) static void bond_uninit(struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); + struct slave *slave, *tmp_slave; struct vlan_entry *vlan, *tmp; bond_netpoll_cleanup(bond_dev); /* Release the bonded slaves */ - while (bond->first_slave != NULL) - __bond_release_one(bond_dev, bond->first_slave->dev, true); + list_for_each_entry_safe(slave, tmp_slave, &bond->slave_list, list) + __bond_release_one(bond_dev, slave->dev, true); pr_info("%s: released all slaves\n", bond_dev->name); list_del(&bond->bond_list); diff --git a/drivers/net/bonding/bond_procfs.c b/drivers/net/bonding/bond_procfs.c index 4060d41f0ee7..20a6ee25bb63 100644 --- a/drivers/net/bonding/bond_procfs.c +++ b/drivers/net/bonding/bond_procfs.c @@ -12,7 +12,6 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) struct bonding *bond = seq->private; loff_t off = 0; struct slave *slave; - int i; /* make sure the bond won't be taken away */ rcu_read_lock(); @@ -21,10 +20,9 @@ static void *bond_info_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) return SEQ_START_TOKEN; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) if (++off == *pos) return slave; - } return NULL; } @@ -36,11 +34,13 @@ static void *bond_info_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; if (v == SEQ_START_TOKEN) - return bond->first_slave; + return bond_first_slave(bond); - slave = slave->next; + if (bond_is_last_slave(bond, slave)) + return NULL; + slave = bond_next_slave(bond, slave); - return (slave == bond->first_slave) ? NULL : slave; + return slave; } static void bond_info_seq_stop(struct seq_file *seq, void *v) diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index dc36a3d7d9e9..0f539de640dc 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -209,12 +209,12 @@ void bond_destroy_slave_symlinks(struct net_device *master, static ssize_t bonding_show_slaves(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *slave; - int i, res = 0; struct bonding *bond = to_bond(d); + struct slave *slave; + int res = 0; read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (res > (PAGE_SIZE - IFNAMSIZ)) { /* not enough space for another interface name */ if ((PAGE_SIZE - res) > 10) @@ -227,6 +227,7 @@ static ssize_t bonding_show_slaves(struct device *d, read_unlock(&bond->lock); if (res) buf[res-1] = '\n'; /* eat the leftover space */ + return res; } @@ -325,7 +326,7 @@ static ssize_t bonding_store_mode(struct device *d, goto out; } - if (bond->slave_cnt > 0) { + if (!list_empty(&bond->slave_list)) { pr_err("unable to update mode of %s because it has slaves.\n", bond->dev->name); ret = -EPERM; @@ -501,20 +502,25 @@ static ssize_t bonding_store_fail_over_mac(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int new_value; + int new_value, ret = count; struct bonding *bond = to_bond(d); - if (bond->slave_cnt != 0) { + if (!rtnl_trylock()) + return restart_syscall(); + + if (!list_empty(&bond->slave_list)) { pr_err("%s: Can't alter fail_over_mac with slaves in bond.\n", bond->dev->name); - return -EPERM; + ret = -EPERM; + goto out; } new_value = bond_parse_parm(buf, fail_over_mac_tbl); if (new_value < 0) { pr_err("%s: Ignoring invalid fail_over_mac value %s.\n", bond->dev->name, buf); - return -EINVAL; + ret = -EINVAL; + goto out; } bond->params.fail_over_mac = new_value; @@ -522,7 +528,9 @@ static ssize_t bonding_store_fail_over_mac(struct device *d, bond->dev->name, fail_over_mac_tbl[new_value].modename, new_value); - return count; +out: + rtnl_unlock(); + return ret; } static DEVICE_ATTR(fail_over_mac, S_IRUGO | S_IWUSR, @@ -661,7 +669,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, &newtarget); /* not to race with bond_arp_rcv */ write_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) + bond_for_each_slave(bond, slave) slave->target_last_arp_rx[ind] = jiffies; targets[ind] = newtarget; write_unlock_bh(&bond->lock); @@ -687,7 +695,7 @@ static ssize_t bonding_store_arp_targets(struct device *d, &newtarget); write_lock_bh(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { targets_rx = slave->target_last_arp_rx; j = ind; for (; (j < BOND_MAX_ARP_TARGETS-1) && targets[j+1]; j++) @@ -1078,10 +1086,9 @@ static ssize_t bonding_store_primary(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i; - struct slave *slave; struct bonding *bond = to_bond(d); char ifname[IFNAMSIZ]; + struct slave *slave; if (!rtnl_trylock()) return restart_syscall(); @@ -1107,7 +1114,7 @@ static ssize_t bonding_store_primary(struct device *d, goto out; } - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { pr_info("%s: Setting %s as primary slave.\n", bond->dev->name, slave->dev->name); @@ -1236,16 +1243,16 @@ static ssize_t bonding_show_active_slave(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *curr; struct bonding *bond = to_bond(d); + struct slave *curr; int count = 0; - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - + rcu_read_lock(); + curr = rcu_dereference(bond->curr_active_slave); if (USES_PRIMARY(bond->params.mode) && curr) count = sprintf(buf, "%s\n", curr->dev->name); + rcu_read_unlock(); + return count; } @@ -1253,16 +1260,14 @@ static ssize_t bonding_store_active_slave(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i; - struct slave *slave; - struct slave *old_active = NULL; - struct slave *new_active = NULL; + struct slave *slave, *old_active, *new_active; struct bonding *bond = to_bond(d); char ifname[IFNAMSIZ]; if (!rtnl_trylock()) return restart_syscall(); + old_active = new_active = NULL; block_netpoll_tx(); read_lock(&bond->lock); write_lock_bh(&bond->curr_slave_lock); @@ -1279,12 +1284,12 @@ static ssize_t bonding_store_active_slave(struct device *d, if (!strlen(ifname) || buf[0] == '\n') { pr_info("%s: Clearing current active slave.\n", bond->dev->name); - bond->curr_active_slave = NULL; + rcu_assign_pointer(bond->curr_active_slave, NULL); bond_select_active_slave(bond); goto out; } - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (strncmp(slave->dev->name, ifname, IFNAMSIZ) == 0) { old_active = bond->curr_active_slave; new_active = slave; @@ -1295,8 +1300,7 @@ static ssize_t bonding_store_active_slave(struct device *d, bond->dev->name, slave->dev->name); goto out; - } - else { + } else { if ((new_active) && (old_active) && (new_active->link == BOND_LINK_UP) && @@ -1307,8 +1311,7 @@ static ssize_t bonding_store_active_slave(struct device *d, slave->dev->name); bond_change_active_slave(bond, new_active); - } - else { + } else { pr_info("%s: Could not set %s as" " active slave; either %s is" " down or the link is down.\n", @@ -1344,14 +1347,9 @@ static ssize_t bonding_show_mii_status(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *curr; struct bonding *bond = to_bond(d); - read_lock(&bond->curr_slave_lock); - curr = bond->curr_active_slave; - read_unlock(&bond->curr_slave_lock); - - return sprintf(buf, "%s\n", curr ? "up" : "down"); + return sprintf(buf, "%s\n", bond->curr_active_slave ? "up" : "down"); } static DEVICE_ATTR(mii_status, S_IRUGO, bonding_show_mii_status, NULL); @@ -1470,15 +1468,15 @@ static ssize_t bonding_show_queue_id(struct device *d, struct device_attribute *attr, char *buf) { - struct slave *slave; - int i, res = 0; struct bonding *bond = to_bond(d); + struct slave *slave; + int res = 0; if (!rtnl_trylock()) return restart_syscall(); read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (res > (PAGE_SIZE - IFNAMSIZ - 6)) { /* not enough space for another interface_name:queue_id pair */ if ((PAGE_SIZE - res) > 10) @@ -1493,6 +1491,7 @@ static ssize_t bonding_show_queue_id(struct device *d, if (res) buf[res-1] = '\n'; /* eat the leftover space */ rtnl_unlock(); + return res; } @@ -1507,7 +1506,7 @@ static ssize_t bonding_store_queue_id(struct device *d, struct slave *slave, *update_slave; struct bonding *bond = to_bond(d); u16 qid; - int i, ret = count; + int ret = count; char *delim; struct net_device *sdev = NULL; @@ -1542,7 +1541,7 @@ static ssize_t bonding_store_queue_id(struct device *d, /* Search for thes slave and check for duplicate qids */ update_slave = NULL; - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (sdev == slave->dev) /* * We don't need to check the matching @@ -1594,8 +1593,8 @@ static ssize_t bonding_store_slaves_active(struct device *d, struct device_attribute *attr, const char *buf, size_t count) { - int i, new_value, ret = count; struct bonding *bond = to_bond(d); + int new_value, ret = count; struct slave *slave; if (sscanf(buf, "%d", &new_value) != 1) { @@ -1618,7 +1617,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, } read_lock(&bond->lock); - bond_for_each_slave(bond, slave, i) { + bond_for_each_slave(bond, slave) { if (!bond_is_active_slave(slave)) { if (new_value) slave->inactive = 0; diff --git a/drivers/net/bonding/bonding.h b/drivers/net/bonding/bonding.h index 42d1c6599cba..4bf52d5f637e 100644 --- a/drivers/net/bonding/bonding.h +++ b/drivers/net/bonding/bonding.h @@ -71,6 +71,28 @@ set_fs(fs); \ res; }) +/* slave list primitives */ +#define bond_to_slave(ptr) list_entry(ptr, struct slave, list) + +/* IMPORTANT: bond_first/last_slave can return NULL in case of an empty list */ +#define bond_first_slave(bond) \ + list_first_entry_or_null(&(bond)->slave_list, struct slave, list) +#define bond_last_slave(bond) \ + (list_empty(&(bond)->slave_list) ? NULL : \ + bond_to_slave((bond)->slave_list.prev)) + +#define bond_is_first_slave(bond, pos) ((pos)->list.prev == &(bond)->slave_list) +#define bond_is_last_slave(bond, pos) ((pos)->list.next == &(bond)->slave_list) + +/* Since bond_first/last_slave can return NULL, these can return NULL too */ +#define bond_next_slave(bond, pos) \ + (bond_is_last_slave(bond, pos) ? bond_first_slave(bond) : \ + bond_to_slave((pos)->list.next)) + +#define bond_prev_slave(bond, pos) \ + (bond_is_first_slave(bond, pos) ? bond_last_slave(bond) : \ + bond_to_slave((pos)->list.prev)) + /** * bond_for_each_slave_from - iterate the slaves list from a starting point * @bond: the bond holding this list. @@ -80,37 +102,33 @@ * * Caller must hold bond->lock */ -#define bond_for_each_slave_from(bond, pos, cnt, start) \ - for (cnt = 0, pos = start; \ - cnt < (bond)->slave_cnt; \ - cnt++, pos = (pos)->next) +#define bond_for_each_slave_from(bond, pos, cnt, start) \ + for (cnt = 0, pos = start; pos && cnt < (bond)->slave_cnt; \ + cnt++, pos = bond_next_slave(bond, pos)) /** - * bond_for_each_slave_from_to - iterate the slaves list from start point to stop point - * @bond: the bond holding this list. - * @pos: current slave. - * @cnt: counter for number max of moves - * @start: start point. - * @stop: stop point. + * bond_for_each_slave - iterate over all slaves + * @bond: the bond holding this list + * @pos: current slave * * Caller must hold bond->lock */ -#define bond_for_each_slave_from_to(bond, pos, cnt, start, stop) \ - for (cnt = 0, pos = start; \ - ((cnt < (bond)->slave_cnt) && (pos != (stop)->next)); \ - cnt++, pos = (pos)->next) +#define bond_for_each_slave(bond, pos) \ + list_for_each_entry(pos, &(bond)->slave_list, list) + +/* Caller must have rcu_read_lock */ +#define bond_for_each_slave_rcu(bond, pos) \ + list_for_each_entry_rcu(pos, &(bond)->slave_list, list) /** - * bond_for_each_slave - iterate the slaves list from head - * @bond: the bond holding this list. - * @pos: current slave. - * @cnt: counter for max number of moves + * bond_for_each_slave_reverse - iterate in reverse from a given position + * @bond: the bond holding this list + * @pos: slave to continue from * * Caller must hold bond->lock */ -#define bond_for_each_slave(bond, pos, cnt) \ - bond_for_each_slave_from(bond, pos, cnt, (bond)->first_slave) - +#define bond_for_each_slave_continue_reverse(bond, pos) \ + list_for_each_entry_continue_reverse(pos, &(bond)->slave_list, list) #ifdef CONFIG_NET_POLL_CONTROLLER extern atomic_t netpoll_block_tx; @@ -174,8 +192,7 @@ struct vlan_entry { struct slave { struct net_device *dev; /* first - useful for panic debug */ - struct slave *next; - struct slave *prev; + struct list_head list; struct bonding *bond; /* our master */ int delay; unsigned long jiffies; @@ -215,7 +232,7 @@ struct slave { */ struct bonding { struct net_device *dev; /* first - useful for panic debug */ - struct slave *first_slave; + struct list_head slave_list; struct slave *curr_active_slave; struct slave *current_arp_slave; struct slave *primary_slave; @@ -270,13 +287,10 @@ static inline struct slave *bond_get_slave_by_dev(struct bonding *bond, struct net_device *slave_dev) { struct slave *slave = NULL; - int i; - bond_for_each_slave(bond, slave, i) { - if (slave->dev == slave_dev) { + bond_for_each_slave(bond, slave) + if (slave->dev == slave_dev) return slave; - } - } return NULL; } @@ -416,10 +430,20 @@ static inline __be32 bond_confirm_addr(struct net_device *dev, __be32 dst, __be3 return addr; } +static inline bool slave_can_tx(struct slave *slave) +{ + if (IS_UP(slave->dev) && slave->link == BOND_LINK_UP && + bond_is_active_slave(slave)) + return true; + else + return false; +} + struct bond_net; struct vlan_entry *bond_next_vlan(struct bonding *bond, struct vlan_entry *curr); int bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, struct net_device *slave_dev); +void bond_xmit_slave_id(struct bonding *bond, struct sk_buff *skb, int slave_id); int bond_create(struct net *net, const char *name); int bond_create_sysfs(struct bond_net *net); void bond_destroy_sysfs(struct bond_net *net); @@ -477,10 +501,9 @@ static inline void bond_destroy_proc_dir(struct bond_net *bn) static inline struct slave *bond_slave_has_mac(struct bonding *bond, const u8 *mac) { - int i = 0; struct slave *tmp; - bond_for_each_slave(bond, tmp, i) + bond_for_each_slave(bond, tmp) if (ether_addr_equal_64bits(mac, tmp->dev->dev_addr)) return tmp; diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c index 7b0be0910f4b..c48174ed49cc 100644 --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@ -850,12 +850,17 @@ static int flexcan_open(struct net_device *dev) struct flexcan_priv *priv = netdev_priv(dev); int err; - clk_prepare_enable(priv->clk_ipg); - clk_prepare_enable(priv->clk_per); + err = clk_prepare_enable(priv->clk_ipg); + if (err) + return err; + + err = clk_prepare_enable(priv->clk_per); + if (err) + goto out_disable_ipg; err = open_candev(dev); if (err) - goto out; + goto out_disable_per; err = request_irq(dev->irq, flexcan_irq, IRQF_SHARED, dev->name, dev); if (err) @@ -875,8 +880,9 @@ static int flexcan_open(struct net_device *dev) out_close: close_candev(dev); - out: + out_disable_per: clk_disable_unprepare(priv->clk_per); + out_disable_ipg: clk_disable_unprepare(priv->clk_ipg); return err; @@ -933,8 +939,13 @@ static int register_flexcandev(struct net_device *dev) struct flexcan_regs __iomem *regs = priv->base; u32 reg, err; - clk_prepare_enable(priv->clk_ipg); - clk_prepare_enable(priv->clk_per); + err = clk_prepare_enable(priv->clk_ipg); + if (err) + return err; + + err = clk_prepare_enable(priv->clk_per); + if (err) + goto out_disable_ipg; /* select "bus clock", chip must be disabled */ flexcan_chip_disable(priv); @@ -959,15 +970,16 @@ static int register_flexcandev(struct net_device *dev) if (!(reg & FLEXCAN_MCR_FEN)) { netdev_err(dev, "Could not enable RX FIFO, unsupported core\n"); err = -ENODEV; - goto out; + goto out_disable_per; } err = register_candev(dev); - out: + out_disable_per: /* disable core and turn off clocks */ flexcan_chip_disable(priv); clk_disable_unprepare(priv->clk_per); + out_disable_ipg: clk_disable_unprepare(priv->clk_ipg); return err; @@ -1001,7 +1013,6 @@ static int flexcan_probe(struct platform_device *pdev) struct resource *mem; struct clk *clk_ipg = NULL, *clk_per = NULL; void __iomem *base; - resource_size_t mem_size; int err, irq; u32 clock_freq = 0; @@ -1013,43 +1024,25 @@ static int flexcan_probe(struct platform_device *pdev) clk_ipg = devm_clk_get(&pdev->dev, "ipg"); if (IS_ERR(clk_ipg)) { dev_err(&pdev->dev, "no ipg clock defined\n"); - err = PTR_ERR(clk_ipg); - goto failed_clock; + return PTR_ERR(clk_ipg); } clock_freq = clk_get_rate(clk_ipg); clk_per = devm_clk_get(&pdev->dev, "per"); if (IS_ERR(clk_per)) { dev_err(&pdev->dev, "no per clock defined\n"); - err = PTR_ERR(clk_per); - goto failed_clock; + return PTR_ERR(clk_per); } } mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); irq = platform_get_irq(pdev, 0); - if (!mem || irq <= 0) { - err = -ENODEV; - goto failed_get; - } + if (irq <= 0) + return -ENODEV; - mem_size = resource_size(mem); - if (!request_mem_region(mem->start, mem_size, pdev->name)) { - err = -EBUSY; - goto failed_get; - } - - base = ioremap(mem->start, mem_size); - if (!base) { - err = -ENOMEM; - goto failed_map; - } - - dev = alloc_candev(sizeof(struct flexcan_priv), 1); - if (!dev) { - err = -ENOMEM; - goto failed_alloc; - } + base = devm_ioremap_resource(&pdev->dev, mem); + if (IS_ERR(base)) + return PTR_ERR(base); of_id = of_match_device(flexcan_of_match, &pdev->dev); if (of_id) { @@ -1058,10 +1051,13 @@ static int flexcan_probe(struct platform_device *pdev) devtype_data = (struct flexcan_devtype_data *) pdev->id_entry->driver_data; } else { - err = -ENODEV; - goto failed_devtype; + return -ENODEV; } + dev = alloc_candev(sizeof(struct flexcan_priv), 1); + if (!dev) + return -ENOMEM; + dev->netdev_ops = &flexcan_netdev_ops; dev->irq = irq; dev->flags |= IFF_ECHO; @@ -1104,28 +1100,15 @@ static int flexcan_probe(struct platform_device *pdev) return 0; failed_register: - failed_devtype: free_candev(dev); - failed_alloc: - iounmap(base); - failed_map: - release_mem_region(mem->start, mem_size); - failed_get: - failed_clock: return err; } static int flexcan_remove(struct platform_device *pdev) { struct net_device *dev = platform_get_drvdata(pdev); - struct flexcan_priv *priv = netdev_priv(dev); - struct resource *mem; unregister_flexcandev(dev); - iounmap(priv->base); - - mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - release_mem_region(mem->start, resource_size(mem)); free_candev(dev); diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index e1d26433d619..b7232a9b7756 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -707,7 +707,7 @@ static int ax_init_dev(struct net_device *dev) #ifdef CONFIG_AX88796_93CX6 if (ax->plat->flags & AXFLG_HAS_93CX6) { - unsigned char mac_addr[6]; + unsigned char mac_addr[ETH_ALEN]; struct eeprom_93cx6 eeprom; eeprom.data = ei_local; @@ -719,7 +719,7 @@ static int ax_init_dev(struct net_device *dev) (__le16 __force *)mac_addr, sizeof(mac_addr) >> 1); - memcpy(dev->dev_addr, mac_addr, 6); + memcpy(dev->dev_addr, mac_addr, ETH_ALEN); } #endif if (ax->plat->wordlength == 2) { diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c index ed2130727643..2d8e28819779 100644 --- a/drivers/net/ethernet/amd/pcnet32.c +++ b/drivers/net/ethernet/amd/pcnet32.c @@ -1521,7 +1521,7 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) char *chipname; struct net_device *dev; const struct pcnet32_access *a = NULL; - u8 promaddr[6]; + u8 promaddr[ETH_ALEN]; int ret = -ENODEV; /* reset the chip */ @@ -1665,10 +1665,10 @@ pcnet32_probe1(unsigned long ioaddr, int shared, struct pci_dev *pdev) } /* read PROM address and compare with CSR address */ - for (i = 0; i < 6; i++) + for (i = 0; i < ETH_ALEN; i++) promaddr[i] = inb(ioaddr + i); - if (memcmp(promaddr, dev->dev_addr, 6) || + if (memcmp(promaddr, dev->dev_addr, ETH_ALEN) || !is_valid_ether_addr(dev->dev_addr)) { if (is_valid_ether_addr(promaddr)) { if (pcnet32_debug & NETIF_MSG_PROBE) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index d80e34b8285f..7ecb44ad24fb 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -1331,7 +1331,7 @@ enum { BNX2X_SP_RTNL_ENABLE_SRIOV, BNX2X_SP_RTNL_VFPF_MCAST, BNX2X_SP_RTNL_VFPF_CHANNEL_DOWN, - BNX2X_SP_RTNL_VFPF_STORM_RX_MODE, + BNX2X_SP_RTNL_RX_MODE, BNX2X_SP_RTNL_HYPERVISOR_VLAN, }; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index f2d1ff10054b..2e90868a9276 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -2060,7 +2060,11 @@ void bnx2x_squeeze_objects(struct bnx2x *bp) rparam.mcast_obj = &bp->mcast_obj; __set_bit(RAMROD_DRV_CLR_ONLY, &rparam.ramrod_flags); - /* Add a DEL command... */ + /* Add a DEL command... - Since we're doing a driver cleanup only, + * we take a lock surrounding both the initial send and the CONTs, + * as we don't want a true completion to disrupt us in the middle. + */ + netif_addr_lock_bh(bp->dev); rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_DEL); if (rc < 0) BNX2X_ERR("Failed to add a new DEL command to a multi-cast object: %d\n", @@ -2072,11 +2076,13 @@ void bnx2x_squeeze_objects(struct bnx2x *bp) if (rc < 0) { BNX2X_ERR("Failed to clean multi-cast object: %d\n", rc); + netif_addr_unlock_bh(bp->dev); return; } rc = bnx2x_config_mcast(bp, &rparam, BNX2X_MCAST_CMD_CONT); } + netif_addr_unlock_bh(bp->dev); } #ifndef BNX2X_STOP_ON_ERROR @@ -2432,9 +2438,7 @@ int bnx2x_load_cnic(struct bnx2x *bp) } /* Initialize Rx filter. */ - netif_addr_lock_bh(bp->dev); - bnx2x_set_rx_mode(bp->dev); - netif_addr_unlock_bh(bp->dev); + bnx2x_set_rx_mode_inner(bp); /* re-read iscsi info */ bnx2x_get_iscsi_info(bp); @@ -2704,9 +2708,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode) /* Start fast path */ /* Initialize Rx filter. */ - netif_addr_lock_bh(bp->dev); - bnx2x_set_rx_mode(bp->dev); - netif_addr_unlock_bh(bp->dev); + bnx2x_set_rx_mode_inner(bp); /* Start the Tx */ switch (load_mode) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h index c07a6d054cfe..38be494ffa6e 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h @@ -418,6 +418,7 @@ int bnx2x_set_eth_mac(struct bnx2x *bp, bool set); * netif_addr_lock_bh() */ void bnx2x_set_rx_mode(struct net_device *dev); +void bnx2x_set_rx_mode_inner(struct bnx2x *bp); /** * bnx2x_set_storm_rx_mode - configure MAC filtering rules in a FW. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index e06186c305d8..ab5bd6c319d3 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -9628,11 +9628,9 @@ sp_rtnl_not_reset: } } - if (test_and_clear_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE, - &bp->sp_rtnl_state)) { - DP(BNX2X_MSG_SP, - "sending set storm rx mode vf pf channel message from rtnl sp-task\n"); - bnx2x_vfpf_storm_rx_mode(bp); + if (test_and_clear_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state)) { + DP(BNX2X_MSG_SP, "Handling Rx Mode setting\n"); + bnx2x_set_rx_mode_inner(bp); } if (test_and_clear_bit(BNX2X_SP_RTNL_HYPERVISOR_VLAN, @@ -11849,34 +11847,48 @@ static int bnx2x_set_mc_list(struct bnx2x *bp) void bnx2x_set_rx_mode(struct net_device *dev) { struct bnx2x *bp = netdev_priv(dev); - u32 rx_mode = BNX2X_RX_MODE_NORMAL; if (bp->state != BNX2X_STATE_OPEN) { DP(NETIF_MSG_IFUP, "state is %x, returning\n", bp->state); return; + } else { + /* Schedule an SP task to handle rest of change */ + DP(NETIF_MSG_IFUP, "Scheduling an Rx mode change\n"); + smp_mb__before_clear_bit(); + set_bit(BNX2X_SP_RTNL_RX_MODE, &bp->sp_rtnl_state); + smp_mb__after_clear_bit(); + schedule_delayed_work(&bp->sp_rtnl_task, 0); } +} + +void bnx2x_set_rx_mode_inner(struct bnx2x *bp) +{ + u32 rx_mode = BNX2X_RX_MODE_NORMAL; DP(NETIF_MSG_IFUP, "dev->flags = %x\n", bp->dev->flags); - if (dev->flags & IFF_PROMISC) + netif_addr_lock_bh(bp->dev); + + if (bp->dev->flags & IFF_PROMISC) { rx_mode = BNX2X_RX_MODE_PROMISC; - else if ((dev->flags & IFF_ALLMULTI) || - ((netdev_mc_count(dev) > BNX2X_MAX_MULTICAST) && - CHIP_IS_E1(bp))) + } else if ((bp->dev->flags & IFF_ALLMULTI) || + ((netdev_mc_count(bp->dev) > BNX2X_MAX_MULTICAST) && + CHIP_IS_E1(bp))) { rx_mode = BNX2X_RX_MODE_ALLMULTI; - else { + } else { if (IS_PF(bp)) { /* some multicasts */ if (bnx2x_set_mc_list(bp) < 0) rx_mode = BNX2X_RX_MODE_ALLMULTI; + /* release bh lock, as bnx2x_set_uc_list might sleep */ + netif_addr_unlock_bh(bp->dev); if (bnx2x_set_uc_list(bp) < 0) rx_mode = BNX2X_RX_MODE_PROMISC; + netif_addr_lock_bh(bp->dev); } else { /* configuring mcast to a vf involves sleeping (when we - * wait for the pf's response). Since this function is - * called from non sleepable context we must schedule - * a work item for this purpose + * wait for the pf's response). */ smp_mb__before_clear_bit(); set_bit(BNX2X_SP_RTNL_VFPF_MCAST, @@ -11894,22 +11906,20 @@ void bnx2x_set_rx_mode(struct net_device *dev) /* Schedule the rx_mode command */ if (test_bit(BNX2X_FILTER_RX_MODE_PENDING, &bp->sp_state)) { set_bit(BNX2X_FILTER_RX_MODE_SCHED, &bp->sp_state); + netif_addr_unlock_bh(bp->dev); return; } if (IS_PF(bp)) { bnx2x_set_storm_rx_mode(bp); + netif_addr_unlock_bh(bp->dev); } else { - /* configuring rx mode to storms in a vf involves sleeping (when - * we wait for the pf's response). Since this function is - * called from non sleepable context we must schedule - * a work item for this purpose + /* VF will need to request the PF to make this change, and so + * the VF needs to release the bottom-half lock prior to the + * request (as it will likely require sleep on the VF side) */ - smp_mb__before_clear_bit(); - set_bit(BNX2X_SP_RTNL_VFPF_STORM_RX_MODE, - &bp->sp_rtnl_state); - smp_mb__after_clear_bit(); - schedule_delayed_work(&bp->sp_rtnl_task, 0); + netif_addr_unlock_bh(bp->dev); + bnx2x_vfpf_storm_rx_mode(bp); } } diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c index 8f03c984550f..1d46b68fb766 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c @@ -159,16 +159,6 @@ static inline void __bnx2x_exe_queue_reset_pending( } } -static inline void bnx2x_exe_queue_reset_pending(struct bnx2x *bp, - struct bnx2x_exe_queue_obj *o) -{ - spin_lock_bh(&o->lock); - - __bnx2x_exe_queue_reset_pending(bp, o); - - spin_unlock_bh(&o->lock); -} - /** * bnx2x_exe_queue_step - execute one execution chunk atomically * @@ -176,7 +166,7 @@ static inline void bnx2x_exe_queue_reset_pending(struct bnx2x *bp, * @o: queue * @ramrod_flags: flags * - * (Atomicity is ensured using the exe_queue->lock). + * (Should be called while holding the exe_queue->lock). */ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, struct bnx2x_exe_queue_obj *o, @@ -187,8 +177,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, memset(&spacer, 0, sizeof(spacer)); - spin_lock_bh(&o->lock); - /* Next step should not be performed until the current is finished, * unless a DRV_CLEAR_ONLY bit is set. In this case we just want to * properly clear object internals without sending any command to the FW @@ -200,7 +188,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, DP(BNX2X_MSG_SP, "RAMROD_DRV_CLR_ONLY requested: resetting a pending_comp list\n"); __bnx2x_exe_queue_reset_pending(bp, o); } else { - spin_unlock_bh(&o->lock); return 1; } } @@ -228,10 +215,8 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, } /* Sanity check */ - if (!cur_len) { - spin_unlock_bh(&o->lock); + if (!cur_len) return 0; - } rc = o->execute(bp, o->owner, &o->pending_comp, ramrod_flags); if (rc < 0) @@ -245,7 +230,6 @@ static inline int bnx2x_exe_queue_step(struct bnx2x *bp, */ __bnx2x_exe_queue_reset_pending(bp, o); - spin_unlock_bh(&o->lock); return rc; } @@ -432,12 +416,219 @@ static bool bnx2x_put_credit_vlan_mac(struct bnx2x_vlan_mac_obj *o) return true; } +/** + * __bnx2x_vlan_mac_h_write_trylock - try getting the vlan mac writer lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details: Non-blocking implementation; should be called under execution + * queue lock. + */ +static int __bnx2x_vlan_mac_h_write_trylock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + if (o->head_reader) { + DP(BNX2X_MSG_SP, "vlan_mac_lock writer - There are readers; Busy\n"); + return -EBUSY; + } + + DP(BNX2X_MSG_SP, "vlan_mac_lock writer - Taken\n"); + return 0; +} + +/** + * __bnx2x_vlan_mac_h_exec_pending - execute step instead of a previous step + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Should be called under execution queue lock; notice it might release + * and reclaim it during its run. + */ +static void __bnx2x_vlan_mac_h_exec_pending(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + int rc; + unsigned long ramrod_flags = o->saved_ramrod_flags; + + DP(BNX2X_MSG_SP, "vlan_mac_lock execute pending command with ramrod flags %lu\n", + ramrod_flags); + o->head_exe_request = false; + o->saved_ramrod_flags = 0; + rc = bnx2x_exe_queue_step(bp, &o->exe_queue, &ramrod_flags); + if (rc != 0) { + BNX2X_ERR("execution of pending commands failed with rc %d\n", + rc); +#ifdef BNX2X_STOP_ON_ERROR + bnx2x_panic(); +#endif + } +} + +/** + * __bnx2x_vlan_mac_h_pend - Pend an execution step which couldn't run + * + * @bp: device handle + * @o: vlan_mac object + * @ramrod_flags: ramrod flags of missed execution + * + * @details Should be called under execution queue lock. + */ +static void __bnx2x_vlan_mac_h_pend(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o, + unsigned long ramrod_flags) +{ + o->head_exe_request = true; + o->saved_ramrod_flags = ramrod_flags; + DP(BNX2X_MSG_SP, "Placing pending execution with ramrod flags %lu\n", + ramrod_flags); +} + +/** + * __bnx2x_vlan_mac_h_write_unlock - unlock the vlan mac head list writer lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Should be called under execution queue lock. Notice if a pending + * execution exists, it would perform it - possibly releasing and + * reclaiming the execution queue lock. + */ +static void __bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + /* It's possible a new pending execution was added since this writer + * executed. If so, execute again. [Ad infinitum] + */ + while (o->head_exe_request) { + DP(BNX2X_MSG_SP, "vlan_mac_lock - writer release encountered a pending request\n"); + __bnx2x_vlan_mac_h_exec_pending(bp, o); + } +} + +/** + * bnx2x_vlan_mac_h_write_unlock - unlock the vlan mac head list writer lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Notice if a pending execution exists, it would perform it - + * possibly releasing and reclaiming the execution queue lock. + */ +void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + spin_lock_bh(&o->exe_queue.lock); + __bnx2x_vlan_mac_h_write_unlock(bp, o); + spin_unlock_bh(&o->exe_queue.lock); +} + +/** + * __bnx2x_vlan_mac_h_read_lock - lock the vlan mac head list reader lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Should be called under the execution queue lock. May sleep. May + * release and reclaim execution queue lock during its run. + */ +static int __bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + /* If we got here, we're holding lock --> no WRITER exists */ + o->head_reader++; + DP(BNX2X_MSG_SP, "vlan_mac_lock - locked reader - number %d\n", + o->head_reader); + + return 0; +} + +/** + * bnx2x_vlan_mac_h_read_lock - lock the vlan mac head list reader lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details May sleep. Claims and releases execution queue lock during its run. + */ +int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + int rc; + + spin_lock_bh(&o->exe_queue.lock); + rc = __bnx2x_vlan_mac_h_read_lock(bp, o); + spin_unlock_bh(&o->exe_queue.lock); + + return rc; +} + +/** + * __bnx2x_vlan_mac_h_read_unlock - unlock the vlan mac head list reader lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Should be called under execution queue lock. Notice if a pending + * execution exists, it would be performed if this was the last + * reader. possibly releasing and reclaiming the execution queue lock. + */ +static void __bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + if (!o->head_reader) { + BNX2X_ERR("Need to release vlan mac reader lock, but lock isn't taken\n"); +#ifdef BNX2X_STOP_ON_ERROR + bnx2x_panic(); +#endif + } else { + o->head_reader--; + DP(BNX2X_MSG_SP, "vlan_mac_lock - decreased readers to %d\n", + o->head_reader); + } + + /* It's possible a new pending execution was added, and that this reader + * was last - if so we need to execute the command. + */ + if (!o->head_reader && o->head_exe_request) { + DP(BNX2X_MSG_SP, "vlan_mac_lock - reader release encountered a pending request\n"); + + /* Writer release will do the trick */ + __bnx2x_vlan_mac_h_write_unlock(bp, o); + } +} + +/** + * bnx2x_vlan_mac_h_read_unlock - unlock the vlan mac head list reader lock + * + * @bp: device handle + * @o: vlan_mac object + * + * @details Notice if a pending execution exists, it would be performed if this + * was the last reader. Claims and releases the execution queue lock + * during its run. + */ +void bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o) +{ + spin_lock_bh(&o->exe_queue.lock); + __bnx2x_vlan_mac_h_read_unlock(bp, o); + spin_unlock_bh(&o->exe_queue.lock); +} + static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o, int n, u8 *base, u8 stride, u8 size) { struct bnx2x_vlan_mac_registry_elem *pos; u8 *next = base; int counter = 0; + int read_lock; + + DP(BNX2X_MSG_SP, "get_n_elements - taking vlan_mac_lock (reader)\n"); + read_lock = bnx2x_vlan_mac_h_read_lock(bp, o); + if (read_lock != 0) + BNX2X_ERR("get_n_elements failed to get vlan mac reader lock; Access without lock\n"); /* traverse list */ list_for_each_entry(pos, &o->head, link) { @@ -449,6 +640,12 @@ static int bnx2x_get_n_elements(struct bnx2x *bp, struct bnx2x_vlan_mac_obj *o, next += stride + size; } } + + if (read_lock == 0) { + DP(BNX2X_MSG_SP, "get_n_elements - releasing vlan_mac_lock (reader)\n"); + bnx2x_vlan_mac_h_read_unlock(bp, o); + } + return counter * ETH_ALEN; } @@ -1397,6 +1594,32 @@ static int bnx2x_wait_vlan_mac(struct bnx2x *bp, return -EBUSY; } +static int __bnx2x_vlan_mac_execute_step(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o, + unsigned long *ramrod_flags) +{ + int rc = 0; + + spin_lock_bh(&o->exe_queue.lock); + + DP(BNX2X_MSG_SP, "vlan_mac_execute_step - trying to take writer lock\n"); + rc = __bnx2x_vlan_mac_h_write_trylock(bp, o); + + if (rc != 0) { + __bnx2x_vlan_mac_h_pend(bp, o, *ramrod_flags); + + /* Calling function should not diffrentiate between this case + * and the case in which there is already a pending ramrod + */ + rc = 1; + } else { + rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags); + } + spin_unlock_bh(&o->exe_queue.lock); + + return rc; +} + /** * bnx2x_complete_vlan_mac - complete one VLAN-MAC ramrod * @@ -1414,19 +1637,27 @@ static int bnx2x_complete_vlan_mac(struct bnx2x *bp, struct bnx2x_raw_obj *r = &o->raw; int rc; + /* Clearing the pending list & raw state should be made + * atomically (as execution flow assumes they represent the same). + */ + spin_lock_bh(&o->exe_queue.lock); + /* Reset pending list */ - bnx2x_exe_queue_reset_pending(bp, &o->exe_queue); + __bnx2x_exe_queue_reset_pending(bp, &o->exe_queue); /* Clear pending */ r->clear_pending(r); + spin_unlock_bh(&o->exe_queue.lock); + /* If ramrod failed this is most likely a SW bug */ if (cqe->message.error) return -EINVAL; /* Run the next bulk of pending commands if requested */ if (test_bit(RAMROD_CONT, ramrod_flags)) { - rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags); + rc = __bnx2x_vlan_mac_execute_step(bp, o, ramrod_flags); + if (rc < 0) return rc; } @@ -1719,9 +1950,8 @@ static inline int bnx2x_vlan_mac_push_new_cmd( * @p: * */ -int bnx2x_config_vlan_mac( - struct bnx2x *bp, - struct bnx2x_vlan_mac_ramrod_params *p) +int bnx2x_config_vlan_mac(struct bnx2x *bp, + struct bnx2x_vlan_mac_ramrod_params *p) { int rc = 0; struct bnx2x_vlan_mac_obj *o = p->vlan_mac_obj; @@ -1752,7 +1982,8 @@ int bnx2x_config_vlan_mac( /* Execute commands if required */ if (cont || test_bit(RAMROD_EXEC, ramrod_flags) || test_bit(RAMROD_COMP_WAIT, ramrod_flags)) { - rc = bnx2x_exe_queue_step(bp, &o->exe_queue, ramrod_flags); + rc = __bnx2x_vlan_mac_execute_step(bp, p->vlan_mac_obj, + &p->ramrod_flags); if (rc < 0) return rc; } @@ -1775,8 +2006,9 @@ int bnx2x_config_vlan_mac( return rc; /* Make a next step */ - rc = bnx2x_exe_queue_step(bp, &o->exe_queue, - ramrod_flags); + rc = __bnx2x_vlan_mac_execute_step(bp, + p->vlan_mac_obj, + &p->ramrod_flags); if (rc < 0) return rc; } @@ -1806,10 +2038,11 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp, unsigned long *ramrod_flags) { struct bnx2x_vlan_mac_registry_elem *pos = NULL; - int rc = 0; struct bnx2x_vlan_mac_ramrod_params p; struct bnx2x_exe_queue_obj *exeq = &o->exe_queue; struct bnx2x_exeq_elem *exeq_pos, *exeq_pos_n; + int read_lock; + int rc = 0; /* Clear pending commands first */ @@ -1844,6 +2077,11 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp, __clear_bit(RAMROD_EXEC, &p.ramrod_flags); __clear_bit(RAMROD_CONT, &p.ramrod_flags); + DP(BNX2X_MSG_SP, "vlan_mac_del_all -- taking vlan_mac_lock (reader)\n"); + read_lock = bnx2x_vlan_mac_h_read_lock(bp, o); + if (read_lock != 0) + return read_lock; + list_for_each_entry(pos, &o->head, link) { if (pos->vlan_mac_flags == *vlan_mac_flags) { p.user_req.vlan_mac_flags = pos->vlan_mac_flags; @@ -1851,11 +2089,15 @@ static int bnx2x_vlan_mac_del_all(struct bnx2x *bp, rc = bnx2x_config_vlan_mac(bp, &p); if (rc < 0) { BNX2X_ERR("Failed to add a new DEL command\n"); + bnx2x_vlan_mac_h_read_unlock(bp, o); return rc; } } } + DP(BNX2X_MSG_SP, "vlan_mac_del_all -- releasing vlan_mac_lock (reader)\n"); + bnx2x_vlan_mac_h_read_unlock(bp, o); + p.ramrod_flags = *ramrod_flags; __set_bit(RAMROD_CONT, &p.ramrod_flags); @@ -1887,6 +2129,9 @@ static inline void bnx2x_init_vlan_mac_common(struct bnx2x_vlan_mac_obj *o, struct bnx2x_credit_pool_obj *vlans_pool) { INIT_LIST_HEAD(&o->head); + o->head_reader = 0; + o->head_exe_request = false; + o->saved_ramrod_flags = 0; o->macs_pool = macs_pool; o->vlans_pool = vlans_pool; diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h index 798dfe996733..533a3abd8c82 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.h @@ -285,6 +285,12 @@ struct bnx2x_vlan_mac_obj { * entries. */ struct list_head head; + /* Implement a simple reader/writer lock on the head list. + * all these fields should only be accessed under the exe_queue lock + */ + u8 head_reader; /* Num. of readers accessing head list */ + bool head_exe_request; /* Pending execution request. */ + unsigned long saved_ramrod_flags; /* Ramrods of pending execution */ /* TODO: Add it's initialization in the init functions */ struct bnx2x_exe_queue_obj exe_queue; @@ -1302,8 +1308,16 @@ void bnx2x_init_vlan_mac_obj(struct bnx2x *bp, struct bnx2x_credit_pool_obj *macs_pool, struct bnx2x_credit_pool_obj *vlans_pool); +int bnx2x_vlan_mac_h_read_lock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o); +void bnx2x_vlan_mac_h_read_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o); +int bnx2x_vlan_mac_h_write_lock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o); +void bnx2x_vlan_mac_h_write_unlock(struct bnx2x *bp, + struct bnx2x_vlan_mac_obj *o); int bnx2x_config_vlan_mac(struct bnx2x *bp, - struct bnx2x_vlan_mac_ramrod_params *p); + struct bnx2x_vlan_mac_ramrod_params *p); int bnx2x_vlan_mac_move(struct bnx2x *bp, struct bnx2x_vlan_mac_ramrod_params *p, diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 95861efb5051..6291324913e9 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -491,12 +491,20 @@ static inline void bnx2x_vfop_credit(struct bnx2x *bp, * and a valid credit counter */ if (!vfop->rc && args->credit) { - int cnt = 0; struct list_head *pos; + int read_lock; + int cnt = 0; + + read_lock = bnx2x_vlan_mac_h_read_lock(bp, obj); + if (read_lock) + DP(BNX2X_MSG_SP, "Failed to take vlan mac read head; continuing anyway\n"); list_for_each(pos, &obj->head) cnt++; + if (!read_lock) + bnx2x_vlan_mac_h_read_unlock(bp, obj); + atomic_set(args->credit, cnt); } } diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index d78d4cf140ed..4f8a5357cedc 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -1,6 +1,6 @@ /* cnic.c: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2012 Broadcom Corporation + * Copyright (c) 2006-2013 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -1427,6 +1427,28 @@ static void cnic_reply_bnx2x_kcqes(struct cnic_dev *dev, int ulp_type, rcu_read_unlock(); } +static void cnic_bnx2x_set_tcp_options(struct cnic_dev *dev, int time_stamps, + int en_tcp_dack) +{ + struct cnic_local *cp = dev->cnic_priv; + struct bnx2x *bp = netdev_priv(dev->netdev); + u8 xstorm_flags = XSTORM_L5CM_TCP_FLAGS_WND_SCL_EN; + u16 tstorm_flags = 0; + + if (time_stamps) { + xstorm_flags |= XSTORM_L5CM_TCP_FLAGS_TS_ENABLED; + tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_TS_ENABLED; + } + if (en_tcp_dack) + tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_EN; + + CNIC_WR8(dev, BAR_XSTRORM_INTMEM + + XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), xstorm_flags); + + CNIC_WR16(dev, BAR_TSTRORM_INTMEM + + TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), tstorm_flags); +} + static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) { struct cnic_local *cp = dev->cnic_priv; @@ -1506,6 +1528,10 @@ static int cnic_bnx2x_iscsi_init1(struct cnic_dev *dev, struct kwqe *kwqe) CNIC_WR16(dev, BAR_CSTRORM_INTMEM + CSTORM_ISCSI_HQ_SIZE_OFFSET(pfid), hq_bds); + cnic_bnx2x_set_tcp_options(dev, + req1->flags & ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE, + req1->flags & ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE); + return 0; } @@ -2035,9 +2061,6 @@ static void cnic_init_storm_conn_bufs(struct cnic_dev *dev, xstorm_buf->pseudo_header_checksum = swab16(~csum_ipv6_magic(&src_ip, &dst_ip, 0, IPPROTO_TCP, 0)); - if (!(kwqe1->tcp_flags & L4_KWQ_CONNECT_REQ1_NO_DELAY_ACK)) - tstorm_buf->params |= - L5CM_TSTORM_CONN_BUFFER_DELAYED_ACK_ENABLE; if (kwqe3->ka_timeout) { tstorm_buf->ka_enable = 1; tstorm_buf->ka_timeout = kwqe3->ka_timeout; @@ -2084,25 +2107,6 @@ static void cnic_init_bnx2x_mac(struct cnic_dev *dev) mac[0]); } -static void cnic_bnx2x_set_tcp_timestamp(struct cnic_dev *dev, int tcp_ts) -{ - struct cnic_local *cp = dev->cnic_priv; - struct bnx2x *bp = netdev_priv(dev->netdev); - u8 xstorm_flags = XSTORM_L5CM_TCP_FLAGS_WND_SCL_EN; - u16 tstorm_flags = 0; - - if (tcp_ts) { - xstorm_flags |= XSTORM_L5CM_TCP_FLAGS_TS_ENABLED; - tstorm_flags |= TSTORM_L5CM_TCP_FLAGS_TS_ENABLED; - } - - CNIC_WR8(dev, BAR_XSTRORM_INTMEM + - XSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), xstorm_flags); - - CNIC_WR16(dev, BAR_TSTRORM_INTMEM + - TSTORM_ISCSI_TCP_VARS_FLAGS_OFFSET(cp->pfid), tstorm_flags); -} - static int cnic_bnx2x_connect(struct cnic_dev *dev, struct kwqe *wqes[], u32 num, int *work) { @@ -2178,9 +2182,6 @@ static int cnic_bnx2x_connect(struct cnic_dev *dev, struct kwqe *wqes[], CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_LOCAL_VLAN_OFFSET(cp->pfid), csk->vlan_id); - cnic_bnx2x_set_tcp_timestamp(dev, - kwqe1->tcp_flags & L4_KWQ_CONNECT_REQ1_TIME_STAMP); - ret = cnic_submit_kwqe_16(dev, L5CM_RAMROD_CMD_ID_TCP_CONNECT, kwqe1->cid, ISCSI_CONNECTION_TYPE, &l5_data); if (!ret) @@ -3603,6 +3604,7 @@ static int cnic_cm_create(struct cnic_dev *dev, int ulp_type, u32 cid, csk1->rcv_buf = DEF_RCV_BUF; csk1->snd_buf = DEF_SND_BUF; csk1->seed = DEF_SEED; + csk1->tcp_flags = 0; *csk = csk1; return 0; @@ -4020,15 +4022,18 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe) cnic_cm_upcall(cp, csk, opcode); break; - case L5CM_RAMROD_CMD_ID_CLOSE: - if (l4kcqe->status != 0) { - netdev_warn(dev->netdev, "RAMROD CLOSE compl with " - "status 0x%x\n", l4kcqe->status); + case L5CM_RAMROD_CMD_ID_CLOSE: { + struct iscsi_kcqe *l5kcqe = (struct iscsi_kcqe *) kcqe; + + if (l4kcqe->status != 0 || l5kcqe->completion_status != 0) { + netdev_warn(dev->netdev, "RAMROD CLOSE compl with status 0x%x completion status 0x%x\n", + l4kcqe->status, l5kcqe->completion_status); opcode = L4_KCQE_OPCODE_VALUE_CLOSE_COMP; /* Fall through */ } else { break; } + } case L4_KCQE_OPCODE_VALUE_RESET_RECEIVED: case L4_KCQE_OPCODE_VALUE_CLOSE_COMP: case L4_KCQE_OPCODE_VALUE_RESET_COMP: @@ -4219,7 +4224,7 @@ static int cnic_cm_init_bnx2x_hw(struct cnic_dev *dev) u32 port = CNIC_PORT(cp); cnic_init_bnx2x_mac(dev); - cnic_bnx2x_set_tcp_timestamp(dev, 1); + cnic_bnx2x_set_tcp_options(dev, 0, 1); CNIC_WR16(dev, BAR_XSTRORM_INTMEM + XSTORM_ISCSI_LOCAL_VLAN_OFFSET(pfid), 0); @@ -5271,6 +5276,13 @@ static int cnic_register_netdev(struct cnic_dev *dev) if (err) netdev_err(dev->netdev, "register_cnic failed\n"); + /* Read iSCSI config again. On some bnx2x device, iSCSI config + * can change after firmware is downloaded. + */ + dev->max_iscsi_conn = ethdev->max_iscsi_conn; + if (ethdev->drv_state & CNIC_DRV_STATE_NO_ISCSI) + dev->max_iscsi_conn = 0; + return err; } @@ -5628,7 +5640,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event, dev = cnic_from_netdev(netdev); - if (!dev && (event == NETDEV_REGISTER || netif_running(netdev))) { + if (!dev && event == NETDEV_REGISTER) { /* Check for the hot-plug device */ dev = is_cnic_dev(netdev); if (dev) { @@ -5644,7 +5656,7 @@ static int cnic_netdev_event(struct notifier_block *this, unsigned long event, else if (event == NETDEV_UNREGISTER) cnic_ulp_exit(dev); - if (event == NETDEV_UP || (new_dev && netif_running(netdev))) { + if (event == NETDEV_UP) { if (cnic_register_netdev(dev) != 0) { cnic_put(dev); goto done; @@ -5693,21 +5705,8 @@ static struct notifier_block cnic_netdev_notifier = { static void cnic_release(void) { - struct cnic_dev *dev; struct cnic_uio_dev *udev; - while (!list_empty(&cnic_dev_list)) { - dev = list_entry(cnic_dev_list.next, struct cnic_dev, list); - if (test_bit(CNIC_F_CNIC_UP, &dev->flags)) { - cnic_ulp_stop(dev); - cnic_stop_hw(dev); - } - - cnic_ulp_exit(dev); - cnic_unregister_netdev(dev); - list_del_init(&dev->list); - cnic_free_dev(dev); - } while (!list_empty(&cnic_udev_list)) { udev = list_entry(cnic_udev_list.next, struct cnic_uio_dev, list); diff --git a/drivers/net/ethernet/broadcom/cnic.h b/drivers/net/ethernet/broadcom/cnic.h index 62c670619ae6..e7a247473596 100644 --- a/drivers/net/ethernet/broadcom/cnic.h +++ b/drivers/net/ethernet/broadcom/cnic.h @@ -1,6 +1,6 @@ /* cnic.h: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2011 Broadcom Corporation + * Copyright (c) 2006-2013 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by diff --git a/drivers/net/ethernet/broadcom/cnic_defs.h b/drivers/net/ethernet/broadcom/cnic_defs.h index ede3db35d757..95a8e4b11c9f 100644 --- a/drivers/net/ethernet/broadcom/cnic_defs.h +++ b/drivers/net/ethernet/broadcom/cnic_defs.h @@ -1,7 +1,7 @@ /* cnic.c: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2012 Broadcom Corporation + * Copyright (c) 2006-2013 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -5400,8 +5400,8 @@ struct tstorm_l5cm_tcp_flags { u16 flags; #define TSTORM_L5CM_TCP_FLAGS_VLAN_ID (0xFFF<<0) #define TSTORM_L5CM_TCP_FLAGS_VLAN_ID_SHIFT 0 -#define TSTORM_L5CM_TCP_FLAGS_RSRV0 (0x1<<12) -#define TSTORM_L5CM_TCP_FLAGS_RSRV0_SHIFT 12 +#define TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_EN (0x1<<12) +#define TSTORM_L5CM_TCP_FLAGS_DELAYED_ACK_SHIFT 12 #define TSTORM_L5CM_TCP_FLAGS_TS_ENABLED (0x1<<13) #define TSTORM_L5CM_TCP_FLAGS_TS_ENABLED_SHIFT 13 #define TSTORM_L5CM_TCP_FLAGS_RSRV1 (0x3<<14) diff --git a/drivers/net/ethernet/broadcom/cnic_if.h b/drivers/net/ethernet/broadcom/cnic_if.h index ec9bb9ad4bb3..95aff7642b85 100644 --- a/drivers/net/ethernet/broadcom/cnic_if.h +++ b/drivers/net/ethernet/broadcom/cnic_if.h @@ -1,6 +1,6 @@ /* cnic_if.h: Broadcom CNIC core network driver. * - * Copyright (c) 2006-2012 Broadcom Corporation + * Copyright (c) 2006-2013 Broadcom Corporation * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -14,8 +14,8 @@ #include "bnx2x/bnx2x_mfw_req.h" -#define CNIC_MODULE_VERSION "2.5.16" -#define CNIC_MODULE_RELDATE "Dec 05, 2012" +#define CNIC_MODULE_VERSION "2.5.17" +#define CNIC_MODULE_RELDATE "July 28, 2013" #define CNIC_ULP_RDMA 0 #define CNIC_ULP_ISCSI 1 @@ -238,8 +238,8 @@ struct cnic_sock { u16 src_port; u16 dst_port; u16 vlan_id; - unsigned char old_ha[6]; - unsigned char ha[6]; + unsigned char old_ha[ETH_ALEN]; + unsigned char ha[ETH_ALEN]; u32 mtu; u32 cid; u32 l5_cid; @@ -308,7 +308,7 @@ struct cnic_dev { #define CNIC_F_BNX2_CLASS 3 #define CNIC_F_BNX2X_CLASS 4 atomic_t ref_count; - u8 mac_addr[6]; + u8 mac_addr[ETH_ALEN]; int max_iscsi_conn; int max_fcoe_conn; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index ddebc7a5dda0..51bf9ca42faf 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -94,10 +94,10 @@ static inline void _tg3_flag_clear(enum TG3_FLAGS flag, unsigned long *bits) #define DRV_MODULE_NAME "tg3" #define TG3_MAJ_NUM 3 -#define TG3_MIN_NUM 132 +#define TG3_MIN_NUM 133 #define DRV_MODULE_VERSION \ __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM) -#define DRV_MODULE_RELDATE "May 21, 2013" +#define DRV_MODULE_RELDATE "Jul 29, 2013" #define RESET_KIND_SHUTDOWN 0 #define RESET_KIND_INIT 1 @@ -4226,8 +4226,6 @@ static int tg3_power_down_prepare(struct tg3 *tp) static void tg3_power_down(struct tg3 *tp) { - tg3_power_down_prepare(tp); - pci_wake_from_d3(tp->pdev, tg3_flag(tp, WOL_ENABLE)); pci_set_power_state(tp->pdev, PCI_D3hot); } @@ -6095,10 +6093,12 @@ static u64 tg3_refclk_read(struct tg3 *tp) /* tp->lock must be held */ static void tg3_refclk_write(struct tg3 *tp, u64 newval) { - tw32(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_STOP); + u32 clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL); + + tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_STOP); tw32(TG3_EAV_REF_CLCK_LSB, newval & 0xffffffff); tw32(TG3_EAV_REF_CLCK_MSB, newval >> 32); - tw32_f(TG3_EAV_REF_CLCK_CTL, TG3_EAV_REF_CLCK_CTL_RESUME); + tw32_f(TG3_EAV_REF_CLCK_CTL, clock_ctl | TG3_EAV_REF_CLCK_CTL_RESUME); } static inline void tg3_full_lock(struct tg3 *tp, int irq_sync); @@ -6214,6 +6214,59 @@ static int tg3_ptp_settime(struct ptp_clock_info *ptp, static int tg3_ptp_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *rq, int on) { + struct tg3 *tp = container_of(ptp, struct tg3, ptp_info); + u32 clock_ctl; + int rval = 0; + + switch (rq->type) { + case PTP_CLK_REQ_PEROUT: + if (rq->perout.index != 0) + return -EINVAL; + + tg3_full_lock(tp, 0); + clock_ctl = tr32(TG3_EAV_REF_CLCK_CTL); + clock_ctl &= ~TG3_EAV_CTL_TSYNC_GPIO_MASK; + + if (on) { + u64 nsec; + + nsec = rq->perout.start.sec * 1000000000ULL + + rq->perout.start.nsec; + + if (rq->perout.period.sec || rq->perout.period.nsec) { + netdev_warn(tp->dev, + "Device supports only a one-shot timesync output, period must be 0\n"); + rval = -EINVAL; + goto err_out; + } + + if (nsec & (1ULL << 63)) { + netdev_warn(tp->dev, + "Start value (nsec) is over limit. Maximum size of start is only 63 bits\n"); + rval = -EINVAL; + goto err_out; + } + + tw32(TG3_EAV_WATCHDOG0_LSB, (nsec & 0xffffffff)); + tw32(TG3_EAV_WATCHDOG0_MSB, + TG3_EAV_WATCHDOG0_EN | + ((nsec >> 32) & TG3_EAV_WATCHDOG_MSB_MASK)); + + tw32(TG3_EAV_REF_CLCK_CTL, + clock_ctl | TG3_EAV_CTL_TSYNC_WDOG0); + } else { + tw32(TG3_EAV_WATCHDOG0_MSB, 0); + tw32(TG3_EAV_REF_CLCK_CTL, clock_ctl); + } + +err_out: + tg3_full_unlock(tp); + return rval; + + default: + break; + } + return -EOPNOTSUPP; } @@ -6223,7 +6276,7 @@ static const struct ptp_clock_info tg3_ptp_caps = { .max_adj = 250000000, .n_alarm = 0, .n_ext_ts = 0, - .n_per_out = 0, + .n_per_out = 1, .pps = 0, .adjfreq = tg3_ptp_adjfreq, .adjtime = tg3_ptp_adjtime, @@ -10367,6 +10420,9 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy) if (tg3_flag(tp, 5755_PLUS)) tp->rx_mode |= RX_MODE_IPV6_CSUM_ENABLE; + if (tg3_asic_rev(tp) == ASIC_REV_5762) + tp->rx_mode |= RX_MODE_IPV4_FRAG_FIX; + if (tg3_flag(tp, ENABLE_RSS)) tp->rx_mode |= RX_MODE_RSS_ENABLE | RX_MODE_RSS_ITBL_HASH_BITS_7 | @@ -11502,7 +11558,7 @@ static int tg3_close(struct net_device *dev) memset(&tp->net_stats_prev, 0, sizeof(tp->net_stats_prev)); memset(&tp->estats_prev, 0, sizeof(tp->estats_prev)); - tg3_power_down(tp); + tg3_power_down_prepare(tp); tg3_carrier_off(tp); @@ -11724,9 +11780,6 @@ static int tg3_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, if (tg3_flag(tp, NO_NVRAM)) return -EINVAL; - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) - return -EAGAIN; - offset = eeprom->offset; len = eeprom->len; eeprom->len = 0; @@ -11784,9 +11837,6 @@ static int tg3_set_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *buf; __be32 start, end; - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) - return -EAGAIN; - if (tg3_flag(tp, NO_NVRAM) || eeprom->magic != TG3_EEPROM_MAGIC) return -EINVAL; @@ -13515,7 +13565,7 @@ static void tg3_self_test(struct net_device *dev, struct ethtool_test *etest, tg3_phy_start(tp); } if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) - tg3_power_down(tp); + tg3_power_down_prepare(tp); } @@ -17547,11 +17597,6 @@ static int tg3_init_one(struct pci_dev *pdev, tg3_asic_rev(tp) == ASIC_REV_5762) tg3_flag_set(tp, PTP_CAPABLE); - if (tg3_flag(tp, 5717_PLUS)) { - /* Resume a low-power mode */ - tg3_frob_aux_power(tp, false); - } - tg3_timer_init(tp); tg3_carrier_off(tp); @@ -17755,6 +17800,23 @@ out: static SIMPLE_DEV_PM_OPS(tg3_pm_ops, tg3_suspend, tg3_resume); +static void tg3_shutdown(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + struct tg3 *tp = netdev_priv(dev); + + rtnl_lock(); + netif_device_detach(dev); + + if (netif_running(dev)) + dev_close(dev); + + if (system_state == SYSTEM_POWER_OFF) + tg3_power_down(tp); + + rtnl_unlock(); +} + /** * tg3_io_error_detected - called when PCI error is detected * @pdev: Pointer to PCI device @@ -17911,6 +17973,7 @@ static struct pci_driver tg3_driver = { .remove = tg3_remove_one, .err_handler = &tg3_err_handler, .driver.pm = &tg3_pm_ops, + .shutdown = tg3_shutdown, }; module_pci_driver(tg3_driver); diff --git a/drivers/net/ethernet/broadcom/tg3.h b/drivers/net/ethernet/broadcom/tg3.h index cd63d1189aae..ddb8be1298ea 100644 --- a/drivers/net/ethernet/broadcom/tg3.h +++ b/drivers/net/ethernet/broadcom/tg3.h @@ -532,6 +532,7 @@ #define RX_MODE_RSS_ITBL_HASH_BITS_7 0x00700000 #define RX_MODE_RSS_ENABLE 0x00800000 #define RX_MODE_IPV6_CSUM_ENABLE 0x01000000 +#define RX_MODE_IPV4_FRAG_FIX 0x02000000 #define MAC_RX_STATUS 0x0000046c #define RX_STATUS_REMOTE_TX_XOFFED 0x00000001 #define RX_STATUS_XOFF_RCVD 0x00000002 @@ -1818,12 +1819,21 @@ #define TG3_EAV_REF_CLCK_CTL 0x00006908 #define TG3_EAV_REF_CLCK_CTL_STOP 0x00000002 #define TG3_EAV_REF_CLCK_CTL_RESUME 0x00000004 +#define TG3_EAV_CTL_TSYNC_GPIO_MASK (0x3 << 16) +#define TG3_EAV_CTL_TSYNC_WDOG0 (1 << 17) + +#define TG3_EAV_WATCHDOG0_LSB 0x00006918 +#define TG3_EAV_WATCHDOG0_MSB 0x0000691c +#define TG3_EAV_WATCHDOG0_EN (1 << 31) +#define TG3_EAV_WATCHDOG_MSB_MASK 0x7fffffff + #define TG3_EAV_REF_CLK_CORRECT_CTL 0x00006928 #define TG3_EAV_REF_CLK_CORRECT_EN (1 << 31) #define TG3_EAV_REF_CLK_CORRECT_NEG (1 << 30) #define TG3_EAV_REF_CLK_CORRECT_MASK 0xffffff -/* 0x690c --> 0x7000 unused */ + +/* 0x692c --> 0x7000 unused */ /* NVRAM Control registers */ #define NVRAM_CMD 0x00007000 diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile index 9d4974bba247..e52296d9b256 100644 --- a/drivers/net/ethernet/cisco/enic/Makefile +++ b/drivers/net/ethernet/cisco/enic/Makefile @@ -1,5 +1,6 @@ obj-$(CONFIG_ENIC) := enic.o enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \ - enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o + enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \ + enic_ethtool.o diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h index afe9b1662b8c..2e37c63981c1 100644 --- a/drivers/net/ethernet/cisco/enic/enic.h +++ b/drivers/net/ethernet/cisco/enic/enic.h @@ -127,9 +127,57 @@ static inline struct device *enic_get_dev(struct enic *enic) return &(enic->pdev->dev); } +static inline unsigned int enic_cq_rq(struct enic *enic, unsigned int rq) +{ + return rq; +} + +static inline unsigned int enic_cq_wq(struct enic *enic, unsigned int wq) +{ + return enic->rq_count + wq; +} + +static inline unsigned int enic_legacy_io_intr(void) +{ + return 0; +} + +static inline unsigned int enic_legacy_err_intr(void) +{ + return 1; +} + +static inline unsigned int enic_legacy_notify_intr(void) +{ + return 2; +} + +static inline unsigned int enic_msix_rq_intr(struct enic *enic, + unsigned int rq) +{ + return enic->cq[enic_cq_rq(enic, rq)].interrupt_offset; +} + +static inline unsigned int enic_msix_wq_intr(struct enic *enic, + unsigned int wq) +{ + return enic->cq[enic_cq_wq(enic, wq)].interrupt_offset; +} + +static inline unsigned int enic_msix_err_intr(struct enic *enic) +{ + return enic->rq_count + enic->wq_count; +} + +static inline unsigned int enic_msix_notify_intr(struct enic *enic) +{ + return enic->rq_count + enic->wq_count + 1; +} + void enic_reset_addr_lists(struct enic *enic); int enic_sriov_enabled(struct enic *enic); int enic_is_valid_vf(struct enic *enic, int vf); int enic_is_dynamic(struct enic *enic); +void enic_set_ethtool_ops(struct net_device *netdev); #endif /* _ENIC_H_ */ diff --git a/drivers/net/ethernet/cisco/enic/enic_dev.h b/drivers/net/ethernet/cisco/enic/enic_dev.h index 08bded051b93..129b14a4efb0 100644 --- a/drivers/net/ethernet/cisco/enic/enic_dev.h +++ b/drivers/net/ethernet/cisco/enic/enic_dev.h @@ -20,6 +20,7 @@ #define _ENIC_DEV_H_ #include "vnic_dev.h" +#include "vnic_vic.h" /* * Calls the devcmd function given by argument vnicdevcmdfn. diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c new file mode 100644 index 000000000000..47e3562f4866 --- /dev/null +++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c @@ -0,0 +1,257 @@ +/** + * Copyright 2013 Cisco Systems, Inc. All rights reserved. + * + * This program is free software; you may redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; version 2 of the License. + * + * 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. + * + */ + +#include <linux/netdevice.h> +#include <linux/ethtool.h> + +#include "enic_res.h" +#include "enic.h" +#include "enic_dev.h" + +struct enic_stat { + char name[ETH_GSTRING_LEN]; + unsigned int index; +}; + +#define ENIC_TX_STAT(stat) { \ + .name = #stat, \ + .index = offsetof(struct vnic_tx_stats, stat) / sizeof(u64) \ +} + +#define ENIC_RX_STAT(stat) { \ + .name = #stat, \ + .index = offsetof(struct vnic_rx_stats, stat) / sizeof(u64) \ +} + +static const struct enic_stat enic_tx_stats[] = { + ENIC_TX_STAT(tx_frames_ok), + ENIC_TX_STAT(tx_unicast_frames_ok), + ENIC_TX_STAT(tx_multicast_frames_ok), + ENIC_TX_STAT(tx_broadcast_frames_ok), + ENIC_TX_STAT(tx_bytes_ok), + ENIC_TX_STAT(tx_unicast_bytes_ok), + ENIC_TX_STAT(tx_multicast_bytes_ok), + ENIC_TX_STAT(tx_broadcast_bytes_ok), + ENIC_TX_STAT(tx_drops), + ENIC_TX_STAT(tx_errors), + ENIC_TX_STAT(tx_tso), +}; + +static const struct enic_stat enic_rx_stats[] = { + ENIC_RX_STAT(rx_frames_ok), + ENIC_RX_STAT(rx_frames_total), + ENIC_RX_STAT(rx_unicast_frames_ok), + ENIC_RX_STAT(rx_multicast_frames_ok), + ENIC_RX_STAT(rx_broadcast_frames_ok), + ENIC_RX_STAT(rx_bytes_ok), + ENIC_RX_STAT(rx_unicast_bytes_ok), + ENIC_RX_STAT(rx_multicast_bytes_ok), + ENIC_RX_STAT(rx_broadcast_bytes_ok), + ENIC_RX_STAT(rx_drop), + ENIC_RX_STAT(rx_no_bufs), + ENIC_RX_STAT(rx_errors), + ENIC_RX_STAT(rx_rss), + ENIC_RX_STAT(rx_crc_errors), + ENIC_RX_STAT(rx_frames_64), + ENIC_RX_STAT(rx_frames_127), + ENIC_RX_STAT(rx_frames_255), + ENIC_RX_STAT(rx_frames_511), + ENIC_RX_STAT(rx_frames_1023), + ENIC_RX_STAT(rx_frames_1518), + ENIC_RX_STAT(rx_frames_to_max), +}; + +static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats); +static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats); + +static int enic_get_settings(struct net_device *netdev, + struct ethtool_cmd *ecmd) +{ + struct enic *enic = netdev_priv(netdev); + + ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE); + ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE); + ecmd->port = PORT_FIBRE; + ecmd->transceiver = XCVR_EXTERNAL; + + if (netif_carrier_ok(netdev)) { + ethtool_cmd_speed_set(ecmd, vnic_dev_port_speed(enic->vdev)); + ecmd->duplex = DUPLEX_FULL; + } else { + ethtool_cmd_speed_set(ecmd, -1); + ecmd->duplex = -1; + } + + ecmd->autoneg = AUTONEG_DISABLE; + + return 0; +} + +static void enic_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct enic *enic = netdev_priv(netdev); + struct vnic_devcmd_fw_info *fw_info; + + enic_dev_fw_info(enic, &fw_info); + + strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); + strlcpy(drvinfo->fw_version, fw_info->fw_version, + sizeof(drvinfo->fw_version)); + strlcpy(drvinfo->bus_info, pci_name(enic->pdev), + sizeof(drvinfo->bus_info)); +} + +static void enic_get_strings(struct net_device *netdev, u32 stringset, + u8 *data) +{ + unsigned int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < enic_n_tx_stats; i++) { + memcpy(data, enic_tx_stats[i].name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + for (i = 0; i < enic_n_rx_stats; i++) { + memcpy(data, enic_rx_stats[i].name, ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + break; + } +} + +static int enic_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return enic_n_tx_stats + enic_n_rx_stats; + default: + return -EOPNOTSUPP; + } +} + +static void enic_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct enic *enic = netdev_priv(netdev); + struct vnic_stats *vstats; + unsigned int i; + + enic_dev_stats_dump(enic, &vstats); + + for (i = 0; i < enic_n_tx_stats; i++) + *(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].index]; + for (i = 0; i < enic_n_rx_stats; i++) + *(data++) = ((u64 *)&vstats->rx)[enic_rx_stats[i].index]; +} + +static u32 enic_get_msglevel(struct net_device *netdev) +{ + struct enic *enic = netdev_priv(netdev); + return enic->msg_enable; +} + +static void enic_set_msglevel(struct net_device *netdev, u32 value) +{ + struct enic *enic = netdev_priv(netdev); + enic->msg_enable = value; +} + +static int enic_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecmd) +{ + struct enic *enic = netdev_priv(netdev); + + ecmd->tx_coalesce_usecs = enic->tx_coalesce_usecs; + ecmd->rx_coalesce_usecs = enic->rx_coalesce_usecs; + + return 0; +} + +static int enic_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ecmd) +{ + struct enic *enic = netdev_priv(netdev); + u32 tx_coalesce_usecs; + u32 rx_coalesce_usecs; + unsigned int i, intr; + + tx_coalesce_usecs = min_t(u32, ecmd->tx_coalesce_usecs, + vnic_dev_get_intr_coal_timer_max(enic->vdev)); + rx_coalesce_usecs = min_t(u32, ecmd->rx_coalesce_usecs, + vnic_dev_get_intr_coal_timer_max(enic->vdev)); + + switch (vnic_dev_get_intr_mode(enic->vdev)) { + case VNIC_DEV_INTR_MODE_INTX: + if (tx_coalesce_usecs != rx_coalesce_usecs) + return -EINVAL; + + intr = enic_legacy_io_intr(); + vnic_intr_coalescing_timer_set(&enic->intr[intr], + tx_coalesce_usecs); + break; + case VNIC_DEV_INTR_MODE_MSI: + if (tx_coalesce_usecs != rx_coalesce_usecs) + return -EINVAL; + + vnic_intr_coalescing_timer_set(&enic->intr[0], + tx_coalesce_usecs); + break; + case VNIC_DEV_INTR_MODE_MSIX: + for (i = 0; i < enic->wq_count; i++) { + intr = enic_msix_wq_intr(enic, i); + vnic_intr_coalescing_timer_set(&enic->intr[intr], + tx_coalesce_usecs); + } + + for (i = 0; i < enic->rq_count; i++) { + intr = enic_msix_rq_intr(enic, i); + vnic_intr_coalescing_timer_set(&enic->intr[intr], + rx_coalesce_usecs); + } + + break; + default: + break; + } + + enic->tx_coalesce_usecs = tx_coalesce_usecs; + enic->rx_coalesce_usecs = rx_coalesce_usecs; + + return 0; +} + +static const struct ethtool_ops enic_ethtool_ops = { + .get_settings = enic_get_settings, + .get_drvinfo = enic_get_drvinfo, + .get_msglevel = enic_get_msglevel, + .set_msglevel = enic_set_msglevel, + .get_link = ethtool_op_get_link, + .get_strings = enic_get_strings, + .get_sset_count = enic_get_sset_count, + .get_ethtool_stats = enic_get_ethtool_stats, + .get_coalesce = enic_get_coalesce, + .set_coalesce = enic_set_coalesce, +}; + +void enic_set_ethtool_ops(struct net_device *netdev) +{ + SET_ETHTOOL_OPS(netdev, &enic_ethtool_ops); +} diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 992ec2ee64d9..b12b32bc53a6 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -31,7 +31,6 @@ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> -#include <linux/ethtool.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -73,57 +72,6 @@ MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); MODULE_DEVICE_TABLE(pci, enic_id_table); -struct enic_stat { - char name[ETH_GSTRING_LEN]; - unsigned int offset; -}; - -#define ENIC_TX_STAT(stat) \ - { .name = #stat, .offset = offsetof(struct vnic_tx_stats, stat) / 8 } -#define ENIC_RX_STAT(stat) \ - { .name = #stat, .offset = offsetof(struct vnic_rx_stats, stat) / 8 } - -static const struct enic_stat enic_tx_stats[] = { - ENIC_TX_STAT(tx_frames_ok), - ENIC_TX_STAT(tx_unicast_frames_ok), - ENIC_TX_STAT(tx_multicast_frames_ok), - ENIC_TX_STAT(tx_broadcast_frames_ok), - ENIC_TX_STAT(tx_bytes_ok), - ENIC_TX_STAT(tx_unicast_bytes_ok), - ENIC_TX_STAT(tx_multicast_bytes_ok), - ENIC_TX_STAT(tx_broadcast_bytes_ok), - ENIC_TX_STAT(tx_drops), - ENIC_TX_STAT(tx_errors), - ENIC_TX_STAT(tx_tso), -}; - -static const struct enic_stat enic_rx_stats[] = { - ENIC_RX_STAT(rx_frames_ok), - ENIC_RX_STAT(rx_frames_total), - ENIC_RX_STAT(rx_unicast_frames_ok), - ENIC_RX_STAT(rx_multicast_frames_ok), - ENIC_RX_STAT(rx_broadcast_frames_ok), - ENIC_RX_STAT(rx_bytes_ok), - ENIC_RX_STAT(rx_unicast_bytes_ok), - ENIC_RX_STAT(rx_multicast_bytes_ok), - ENIC_RX_STAT(rx_broadcast_bytes_ok), - ENIC_RX_STAT(rx_drop), - ENIC_RX_STAT(rx_no_bufs), - ENIC_RX_STAT(rx_errors), - ENIC_RX_STAT(rx_rss), - ENIC_RX_STAT(rx_crc_errors), - ENIC_RX_STAT(rx_frames_64), - ENIC_RX_STAT(rx_frames_127), - ENIC_RX_STAT(rx_frames_255), - ENIC_RX_STAT(rx_frames_511), - ENIC_RX_STAT(rx_frames_1023), - ENIC_RX_STAT(rx_frames_1518), - ENIC_RX_STAT(rx_frames_to_max), -}; - -static const unsigned int enic_n_tx_stats = ARRAY_SIZE(enic_tx_stats); -static const unsigned int enic_n_rx_stats = ARRAY_SIZE(enic_rx_stats); - int enic_is_dynamic(struct enic *enic) { return enic->pdev->device == PCI_DEVICE_ID_CISCO_VIC_ENET_DYN; @@ -148,222 +96,6 @@ int enic_is_valid_vf(struct enic *enic, int vf) #endif } -static inline unsigned int enic_cq_rq(struct enic *enic, unsigned int rq) -{ - return rq; -} - -static inline unsigned int enic_cq_wq(struct enic *enic, unsigned int wq) -{ - return enic->rq_count + wq; -} - -static inline unsigned int enic_legacy_io_intr(void) -{ - return 0; -} - -static inline unsigned int enic_legacy_err_intr(void) -{ - return 1; -} - -static inline unsigned int enic_legacy_notify_intr(void) -{ - return 2; -} - -static inline unsigned int enic_msix_rq_intr(struct enic *enic, unsigned int rq) -{ - return enic->cq[enic_cq_rq(enic, rq)].interrupt_offset; -} - -static inline unsigned int enic_msix_wq_intr(struct enic *enic, unsigned int wq) -{ - return enic->cq[enic_cq_wq(enic, wq)].interrupt_offset; -} - -static inline unsigned int enic_msix_err_intr(struct enic *enic) -{ - return enic->rq_count + enic->wq_count; -} - -static inline unsigned int enic_msix_notify_intr(struct enic *enic) -{ - return enic->rq_count + enic->wq_count + 1; -} - -static int enic_get_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) -{ - struct enic *enic = netdev_priv(netdev); - - ecmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE); - ecmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE); - ecmd->port = PORT_FIBRE; - ecmd->transceiver = XCVR_EXTERNAL; - - if (netif_carrier_ok(netdev)) { - ethtool_cmd_speed_set(ecmd, vnic_dev_port_speed(enic->vdev)); - ecmd->duplex = DUPLEX_FULL; - } else { - ethtool_cmd_speed_set(ecmd, -1); - ecmd->duplex = -1; - } - - ecmd->autoneg = AUTONEG_DISABLE; - - return 0; -} - -static void enic_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) -{ - struct enic *enic = netdev_priv(netdev); - struct vnic_devcmd_fw_info *fw_info; - - enic_dev_fw_info(enic, &fw_info); - - strlcpy(drvinfo->driver, DRV_NAME, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, DRV_VERSION, sizeof(drvinfo->version)); - strlcpy(drvinfo->fw_version, fw_info->fw_version, - sizeof(drvinfo->fw_version)); - strlcpy(drvinfo->bus_info, pci_name(enic->pdev), - sizeof(drvinfo->bus_info)); -} - -static void enic_get_strings(struct net_device *netdev, u32 stringset, u8 *data) -{ - unsigned int i; - - switch (stringset) { - case ETH_SS_STATS: - for (i = 0; i < enic_n_tx_stats; i++) { - memcpy(data, enic_tx_stats[i].name, ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } - for (i = 0; i < enic_n_rx_stats; i++) { - memcpy(data, enic_rx_stats[i].name, ETH_GSTRING_LEN); - data += ETH_GSTRING_LEN; - } - break; - } -} - -static int enic_get_sset_count(struct net_device *netdev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return enic_n_tx_stats + enic_n_rx_stats; - default: - return -EOPNOTSUPP; - } -} - -static void enic_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) -{ - struct enic *enic = netdev_priv(netdev); - struct vnic_stats *vstats; - unsigned int i; - - enic_dev_stats_dump(enic, &vstats); - - for (i = 0; i < enic_n_tx_stats; i++) - *(data++) = ((u64 *)&vstats->tx)[enic_tx_stats[i].offset]; - for (i = 0; i < enic_n_rx_stats; i++) - *(data++) = ((u64 *)&vstats->rx)[enic_rx_stats[i].offset]; -} - -static u32 enic_get_msglevel(struct net_device *netdev) -{ - struct enic *enic = netdev_priv(netdev); - return enic->msg_enable; -} - -static void enic_set_msglevel(struct net_device *netdev, u32 value) -{ - struct enic *enic = netdev_priv(netdev); - enic->msg_enable = value; -} - -static int enic_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) -{ - struct enic *enic = netdev_priv(netdev); - - ecmd->tx_coalesce_usecs = enic->tx_coalesce_usecs; - ecmd->rx_coalesce_usecs = enic->rx_coalesce_usecs; - - return 0; -} - -static int enic_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ecmd) -{ - struct enic *enic = netdev_priv(netdev); - u32 tx_coalesce_usecs; - u32 rx_coalesce_usecs; - unsigned int i, intr; - - tx_coalesce_usecs = min_t(u32, ecmd->tx_coalesce_usecs, - vnic_dev_get_intr_coal_timer_max(enic->vdev)); - rx_coalesce_usecs = min_t(u32, ecmd->rx_coalesce_usecs, - vnic_dev_get_intr_coal_timer_max(enic->vdev)); - - switch (vnic_dev_get_intr_mode(enic->vdev)) { - case VNIC_DEV_INTR_MODE_INTX: - if (tx_coalesce_usecs != rx_coalesce_usecs) - return -EINVAL; - - intr = enic_legacy_io_intr(); - vnic_intr_coalescing_timer_set(&enic->intr[intr], - tx_coalesce_usecs); - break; - case VNIC_DEV_INTR_MODE_MSI: - if (tx_coalesce_usecs != rx_coalesce_usecs) - return -EINVAL; - - vnic_intr_coalescing_timer_set(&enic->intr[0], - tx_coalesce_usecs); - break; - case VNIC_DEV_INTR_MODE_MSIX: - for (i = 0; i < enic->wq_count; i++) { - intr = enic_msix_wq_intr(enic, i); - vnic_intr_coalescing_timer_set(&enic->intr[intr], - tx_coalesce_usecs); - } - - for (i = 0; i < enic->rq_count; i++) { - intr = enic_msix_rq_intr(enic, i); - vnic_intr_coalescing_timer_set(&enic->intr[intr], - rx_coalesce_usecs); - } - - break; - default: - break; - } - - enic->tx_coalesce_usecs = tx_coalesce_usecs; - enic->rx_coalesce_usecs = rx_coalesce_usecs; - - return 0; -} - -static const struct ethtool_ops enic_ethtool_ops = { - .get_settings = enic_get_settings, - .get_drvinfo = enic_get_drvinfo, - .get_msglevel = enic_get_msglevel, - .set_msglevel = enic_set_msglevel, - .get_link = ethtool_op_get_link, - .get_strings = enic_get_strings, - .get_sset_count = enic_get_sset_count, - .get_ethtool_stats = enic_get_ethtool_stats, - .get_coalesce = enic_get_coalesce, - .set_coalesce = enic_set_coalesce, -}; - static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf) { struct enic *enic = vnic_dev_priv(wq->vdev); @@ -2496,7 +2228,7 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->netdev_ops = &enic_netdev_ops; netdev->watchdog_timeo = 2 * HZ; - netdev->ethtool_ops = &enic_ethtool_ops; + enic_set_ethtool_ops(netdev); netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; if (ENIC_SETTING(enic, LOOP)) { diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c index c94152f1c6be..4e8cfa2ac803 100644 --- a/drivers/net/ethernet/dec/tulip/tulip_core.c +++ b/drivers/net/ethernet/dec/tulip/tulip_core.c @@ -1304,7 +1304,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct tulip_private *tp; /* See note below on the multiport cards. */ - static unsigned char last_phys_addr[6] = {0x00, 'L', 'i', 'n', 'u', 'x'}; + static unsigned char last_phys_addr[ETH_ALEN] = { + 0x00, 'L', 'i', 'n', 'u', 'x' + }; static int last_irq; static int multiport_cnt; /* For four-port boards w/one EEPROM */ int i, irq; @@ -1627,8 +1629,8 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->dev_addr[i] = last_phys_addr[i] + 1; #if defined(CONFIG_SPARC) addr = of_get_property(dp, "local-mac-address", &len); - if (addr && len == 6) - memcpy(dev->dev_addr, addr, 6); + if (addr && len == ETH_ALEN) + memcpy(dev->dev_addr, addr, ETH_ALEN); #endif #if defined(__i386__) || defined(__x86_64__) /* Patch up x86 BIOS bug. */ if (last_irq) diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 6e6e0a117ee2..613d8879b345 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -1339,6 +1339,10 @@ int be_cmd_if_create(struct be_adapter *adapter, u32 cap_flags, u32 en_flags, if (!status) { struct be_cmd_resp_if_create *resp = embedded_payload(wrb); *if_handle = le32_to_cpu(resp->interface_id); + + /* Hack to retrieve VF's pmac-id on BE3 */ + if (BE3_chip(adapter) && !be_physfn(adapter)) + adapter->pmac_id[0] = le32_to_cpu(resp->pmac_id); } err: @@ -2606,9 +2610,44 @@ err: return status; } -/* Uses synchronous MCCQ */ +/* Set privilege(s) for a function */ +int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges, + u32 domain) +{ + struct be_mcc_wrb *wrb; + struct be_cmd_req_set_fn_privileges *req; + int status; + + spin_lock_bh(&adapter->mcc_lock); + + wrb = wrb_from_mccq(adapter); + if (!wrb) { + status = -EBUSY; + goto err; + } + + req = embedded_payload(wrb); + be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON, + OPCODE_COMMON_SET_FN_PRIVILEGES, sizeof(*req), + wrb, NULL); + req->hdr.domain = domain; + if (lancer_chip(adapter)) + req->privileges_lancer = cpu_to_le32(privileges); + else + req->privileges = cpu_to_le32(privileges); + + status = be_mcc_notify_wait(adapter); +err: + spin_unlock_bh(&adapter->mcc_lock); + return status; +} + +/* pmac_id_valid: true => pmac_id is supplied and MAC address is requested. + * pmac_id_valid: false => pmac_id or MAC address is requested. + * If pmac_id is returned, pmac_id_valid is returned as true + */ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac, - bool *pmac_id_active, u32 *pmac_id, u8 domain) + bool *pmac_id_valid, u32 *pmac_id, u8 domain) { struct be_mcc_wrb *wrb; struct be_cmd_req_get_mac_list *req; @@ -2644,12 +2683,25 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac, get_mac_list_cmd.size, wrb, &get_mac_list_cmd); req->hdr.domain = domain; req->mac_type = MAC_ADDRESS_TYPE_NETWORK; - req->perm_override = 1; + if (*pmac_id_valid) { + req->mac_id = cpu_to_le32(*pmac_id); + req->iface_id = cpu_to_le16(adapter->if_handle); + req->perm_override = 0; + } else { + req->perm_override = 1; + } status = be_mcc_notify_wait(adapter); if (!status) { struct be_cmd_resp_get_mac_list *resp = get_mac_list_cmd.va; + + if (*pmac_id_valid) { + memcpy(mac, resp->macid_macaddr.mac_addr_id.macaddr, + ETH_ALEN); + goto out; + } + mac_count = resp->true_mac_count + resp->pseudo_mac_count; /* Mac list returned could contain one or more active mac_ids * or one or more true or pseudo permanant mac addresses. @@ -2667,14 +2719,14 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac, * is 6 bytes */ if (mac_addr_size == sizeof(u32)) { - *pmac_id_active = true; + *pmac_id_valid = true; mac_id = mac_entry->mac_addr_id.s_mac_id.mac_id; *pmac_id = le32_to_cpu(mac_id); goto out; } } /* If no active mac_id found, return first mac addr */ - *pmac_id_active = false; + *pmac_id_valid = false; memcpy(mac, resp->macaddr_list[0].mac_addr_id.macaddr, ETH_ALEN); } @@ -2686,6 +2738,41 @@ out: return status; } +int be_cmd_get_active_mac(struct be_adapter *adapter, u32 curr_pmac_id, u8 *mac) +{ + bool active = true; + + if (BEx_chip(adapter)) + return be_cmd_mac_addr_query(adapter, mac, false, + adapter->if_handle, curr_pmac_id); + else + /* Fetch the MAC address using pmac_id */ + return be_cmd_get_mac_from_list(adapter, mac, &active, + &curr_pmac_id, 0); +} + +int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac) +{ + int status; + bool pmac_valid = false; + + memset(mac, 0, ETH_ALEN); + + if (BEx_chip(adapter)) { + if (be_physfn(adapter)) + status = be_cmd_mac_addr_query(adapter, mac, true, 0, + 0); + else + status = be_cmd_mac_addr_query(adapter, mac, false, + adapter->if_handle, 0); + } else { + status = be_cmd_get_mac_from_list(adapter, mac, &pmac_valid, + NULL, 0); + } + + return status; +} + /* Uses synchronous MCCQ */ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array, u8 mac_count, u32 domain) @@ -2729,6 +2816,25 @@ err: return status; } +/* Wrapper to delete any active MACs and provision the new mac. + * Changes to MAC_LIST are allowed iff none of the MAC addresses in the + * current list are active. + */ +int be_cmd_set_mac(struct be_adapter *adapter, u8 *mac, int if_id, u32 dom) +{ + bool active_mac = false; + u8 old_mac[ETH_ALEN]; + u32 pmac_id; + int status; + + status = be_cmd_get_mac_from_list(adapter, old_mac, &active_mac, + &pmac_id, dom); + if (!status && active_mac) + be_cmd_pmac_del(adapter, if_id, pmac_id, dom); + + return be_cmd_set_mac_list(adapter, mac, mac ? 1 : 0, dom); +} + int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid, u32 domain, u16 intf_id) { diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h index 5228d88c5a02..eb541f0dfee8 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.h +++ b/drivers/net/ethernet/emulex/benet/be_cmds.h @@ -202,6 +202,7 @@ struct be_mcc_mailbox { #define OPCODE_COMMON_READ_TRANSRECV_DATA 73 #define OPCODE_COMMON_GET_PORT_NAME 77 #define OPCODE_COMMON_SET_INTERRUPT_ENABLE 89 +#define OPCODE_COMMON_SET_FN_PRIVILEGES 100 #define OPCODE_COMMON_GET_PHY_DETAILS 102 #define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP 103 #define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES 121 @@ -1474,6 +1475,11 @@ struct be_cmd_resp_get_fn_privileges { u32 privilege_mask; }; +struct be_cmd_req_set_fn_privileges { + struct be_cmd_req_hdr hdr; + u32 privileges; /* Used by BE3, SH-R */ + u32 privileges_lancer; /* Used by Lancer */ +}; /******************** GET/SET_MACLIST **************************/ #define BE_MAX_MAC 64 @@ -1921,11 +1927,18 @@ extern int be_cmd_get_reg_len(struct be_adapter *adapter, u32 *log_size); extern void be_cmd_get_regs(struct be_adapter *adapter, u32 buf_len, void *buf); extern int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege, u32 domain); +extern int be_cmd_set_fn_privileges(struct be_adapter *adapter, + u32 privileges, u32 vf_num); extern int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac, bool *pmac_id_active, u32 *pmac_id, u8 domain); +extern int be_cmd_get_active_mac(struct be_adapter *adapter, u32 pmac_id, + u8 *mac); +extern int be_cmd_get_perm_mac(struct be_adapter *adapter, u8 *mac); extern int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array, u8 mac_count, u32 domain); +extern int be_cmd_set_mac(struct be_adapter *adapter, u8 *mac, int if_id, + u32 dom); extern int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid, u32 domain, u16 intf_id); extern int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid, diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 181edb522450..3df15033b91a 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -247,54 +247,54 @@ void be_cq_notify(struct be_adapter *adapter, u16 qid, bool arm, u16 num_popped) static int be_mac_addr_set(struct net_device *netdev, void *p) { struct be_adapter *adapter = netdev_priv(netdev); + struct device *dev = &adapter->pdev->dev; struct sockaddr *addr = p; - int status = 0; - u8 current_mac[ETH_ALEN]; - u32 pmac_id = adapter->pmac_id[0]; - bool active_mac = true; + int status; + u8 mac[ETH_ALEN]; + u32 old_pmac_id = adapter->pmac_id[0], curr_pmac_id = 0; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - /* For BE VF, MAC address is already activated by PF. - * Hence only operation left is updating netdev->devaddr. - * Update it if user is passing the same MAC which was used - * during configuring VF MAC from PF(Hypervisor). + /* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT + * privilege or if PF did not provision the new MAC address. + * On BE3, this cmd will always fail if the VF doesn't have the + * FILTMGMT privilege. This failure is OK, only if the PF programmed + * the MAC for the VF. */ - if (!lancer_chip(adapter) && !be_physfn(adapter)) { - status = be_cmd_mac_addr_query(adapter, current_mac, - false, adapter->if_handle, 0); - if (!status && !memcmp(current_mac, addr->sa_data, ETH_ALEN)) - goto done; - else - goto err; - } + status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data, + adapter->if_handle, &adapter->pmac_id[0], 0); + if (!status) { + curr_pmac_id = adapter->pmac_id[0]; - if (!memcmp(addr->sa_data, netdev->dev_addr, ETH_ALEN)) - goto done; + /* Delete the old programmed MAC. This call may fail if the + * old MAC was already deleted by the PF driver. + */ + if (adapter->pmac_id[0] != old_pmac_id) + be_cmd_pmac_del(adapter, adapter->if_handle, + old_pmac_id, 0); + } - /* For Lancer check if any MAC is active. - * If active, get its mac id. + /* Decide if the new MAC is successfully activated only after + * querying the FW */ - if (lancer_chip(adapter) && !be_physfn(adapter)) - be_cmd_get_mac_from_list(adapter, current_mac, &active_mac, - &pmac_id, 0); - - status = be_cmd_pmac_add(adapter, (u8 *)addr->sa_data, - adapter->if_handle, - &adapter->pmac_id[0], 0); - + status = be_cmd_get_active_mac(adapter, curr_pmac_id, mac); if (status) goto err; - if (active_mac) - be_cmd_pmac_del(adapter, adapter->if_handle, - pmac_id, 0); -done: + /* The MAC change did not happen, either due to lack of privilege + * or PF didn't pre-provision. + */ + if (memcmp(addr->sa_data, mac, ETH_ALEN)) { + status = -EPERM; + goto err; + } + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + dev_info(dev, "MAC address changed to %pM\n", mac); return 0; err: - dev_err(&adapter->pdev->dev, "MAC %pM set Failed\n", addr->sa_data); + dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data); return status; } @@ -1146,9 +1146,6 @@ static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) struct be_adapter *adapter = netdev_priv(netdev); struct be_vf_cfg *vf_cfg = &adapter->vf_cfg[vf]; int status; - bool active_mac = false; - u32 pmac_id; - u8 old_mac[ETH_ALEN]; if (!sriov_enabled(adapter)) return -EPERM; @@ -1156,20 +1153,15 @@ static int be_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!is_valid_ether_addr(mac) || vf >= adapter->num_vfs) return -EINVAL; - if (lancer_chip(adapter)) { - status = be_cmd_get_mac_from_list(adapter, old_mac, &active_mac, - &pmac_id, vf + 1); - if (!status && active_mac) - be_cmd_pmac_del(adapter, vf_cfg->if_handle, - pmac_id, vf + 1); - - status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1); - } else { - status = be_cmd_pmac_del(adapter, vf_cfg->if_handle, - vf_cfg->pmac_id, vf + 1); + if (BEx_chip(adapter)) { + be_cmd_pmac_del(adapter, vf_cfg->if_handle, vf_cfg->pmac_id, + vf + 1); status = be_cmd_pmac_add(adapter, mac, vf_cfg->if_handle, &vf_cfg->pmac_id, vf + 1); + } else { + status = be_cmd_set_mac(adapter, mac, vf_cfg->if_handle, + vf + 1); } if (status) @@ -2735,13 +2727,13 @@ static int be_vf_eth_addr_config(struct be_adapter *adapter) be_vf_eth_addr_generate(adapter, mac); for_all_vfs(adapter, vf_cfg, vf) { - if (lancer_chip(adapter)) { - status = be_cmd_set_mac_list(adapter, mac, 1, vf + 1); - } else { + if (BEx_chip(adapter)) status = be_cmd_pmac_add(adapter, mac, vf_cfg->if_handle, &vf_cfg->pmac_id, vf + 1); - } + else + status = be_cmd_set_mac(adapter, mac, vf_cfg->if_handle, + vf + 1); if (status) dev_err(&adapter->pdev->dev, @@ -2759,7 +2751,7 @@ static int be_vfs_mac_query(struct be_adapter *adapter) int status, vf; u8 mac[ETH_ALEN]; struct be_vf_cfg *vf_cfg; - bool active; + bool active = false; for_all_vfs(adapter, vf_cfg, vf) { be_cmd_get_mac_from_list(adapter, mac, &active, @@ -2788,11 +2780,12 @@ static void be_vf_clear(struct be_adapter *adapter) pci_disable_sriov(adapter->pdev); for_all_vfs(adapter, vf_cfg, vf) { - if (lancer_chip(adapter)) - be_cmd_set_mac_list(adapter, NULL, 0, vf + 1); - else + if (BEx_chip(adapter)) be_cmd_pmac_del(adapter, vf_cfg->if_handle, vf_cfg->pmac_id, vf + 1); + else + be_cmd_set_mac(adapter, NULL, vf_cfg->if_handle, + vf + 1); be_cmd_if_destroy(adapter, vf_cfg->if_handle, vf + 1); } @@ -2803,7 +2796,7 @@ done: static int be_clear(struct be_adapter *adapter) { - int i = 1; + int i; if (adapter->flags & BE_FLAGS_WORKER_SCHEDULED) { cancel_delayed_work_sync(&adapter->work); @@ -2813,9 +2806,11 @@ static int be_clear(struct be_adapter *adapter) if (sriov_enabled(adapter)) be_vf_clear(adapter); - for (; adapter->uc_macs > 0; adapter->uc_macs--, i++) + /* delete the primary mac along with the uc-mac list */ + for (i = 0; i < (adapter->uc_macs + 1); i++) be_cmd_pmac_del(adapter, adapter->if_handle, - adapter->pmac_id[i], 0); + adapter->pmac_id[i], 0); + adapter->uc_macs = 0; be_cmd_if_destroy(adapter, adapter->if_handle, 0); @@ -2880,6 +2875,7 @@ static int be_vf_setup(struct be_adapter *adapter) u16 def_vlan, lnk_speed; int status, old_vfs, vf; struct device *dev = &adapter->pdev->dev; + u32 privileges; old_vfs = pci_num_vf(adapter->pdev); if (old_vfs) { @@ -2923,6 +2919,18 @@ static int be_vf_setup(struct be_adapter *adapter) } for_all_vfs(adapter, vf_cfg, vf) { + /* Allow VFs to programs MAC/VLAN filters */ + status = be_cmd_get_fn_privileges(adapter, &privileges, vf + 1); + if (!status && !(privileges & BE_PRIV_FILTMGMT)) { + status = be_cmd_set_fn_privileges(adapter, + privileges | + BE_PRIV_FILTMGMT, + vf + 1); + if (!status) + dev_info(dev, "VF%d has FILTMGMT privilege\n", + vf); + } + /* BE3 FW, by default, caps VF TX-rate to 100mbps. * Allow full available bandwidth */ @@ -2971,41 +2979,6 @@ static void be_setup_init(struct be_adapter *adapter) adapter->cmd_privileges = MIN_PRIVILEGES; } -static int be_get_mac_addr(struct be_adapter *adapter, u8 *mac, u32 if_handle, - bool *active_mac, u32 *pmac_id) -{ - int status = 0; - - if (!is_zero_ether_addr(adapter->netdev->perm_addr)) { - memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN); - if (!lancer_chip(adapter) && !be_physfn(adapter)) - *active_mac = true; - else - *active_mac = false; - - return status; - } - - if (lancer_chip(adapter)) { - status = be_cmd_get_mac_from_list(adapter, mac, - active_mac, pmac_id, 0); - if (*active_mac) { - status = be_cmd_mac_addr_query(adapter, mac, false, - if_handle, *pmac_id); - } - } else if (be_physfn(adapter)) { - /* For BE3, for PF get permanent MAC */ - status = be_cmd_mac_addr_query(adapter, mac, true, 0, 0); - *active_mac = false; - } else { - /* For BE3, for VF get soft MAC assigned by PF*/ - status = be_cmd_mac_addr_query(adapter, mac, false, - if_handle, 0); - *active_mac = true; - } - return status; -} - static void be_get_resources(struct be_adapter *adapter) { u16 dev_num_vfs; @@ -3111,14 +3084,38 @@ err: return status; } +static int be_mac_setup(struct be_adapter *adapter) +{ + u8 mac[ETH_ALEN]; + int status; + + if (is_zero_ether_addr(adapter->netdev->dev_addr)) { + status = be_cmd_get_perm_mac(adapter, mac); + if (status) + return status; + + memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN); + memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN); + } else { + /* Maybe the HW was reset; dev_addr must be re-programmed */ + memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN); + } + + /* On BE3 VFs this cmd may fail due to lack of privilege. + * Ignore the failure as in this case pmac_id is fetched + * in the IFACE_CREATE cmd. + */ + be_cmd_pmac_add(adapter, mac, adapter->if_handle, + &adapter->pmac_id[0], 0); + return 0; +} + static int be_setup(struct be_adapter *adapter) { struct device *dev = &adapter->pdev->dev; u32 en_flags; u32 tx_fc, rx_fc; int status; - u8 mac[ETH_ALEN]; - bool active_mac; be_setup_init(adapter); @@ -3158,36 +3155,18 @@ static int be_setup(struct be_adapter *adapter) en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS; - if (adapter->function_caps & BE_FUNCTION_CAPS_RSS) en_flags |= BE_IF_FLAGS_RSS; - en_flags = en_flags & adapter->if_cap_flags; - status = be_cmd_if_create(adapter, adapter->if_cap_flags, en_flags, &adapter->if_handle, 0); if (status != 0) goto err; - memset(mac, 0, ETH_ALEN); - active_mac = false; - status = be_get_mac_addr(adapter, mac, adapter->if_handle, - &active_mac, &adapter->pmac_id[0]); - if (status != 0) + status = be_mac_setup(adapter); + if (status) goto err; - if (!active_mac) { - status = be_cmd_pmac_add(adapter, mac, adapter->if_handle, - &adapter->pmac_id[0], 0); - if (status != 0) - goto err; - } - - if (is_zero_ether_addr(adapter->netdev->dev_addr)) { - memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN); - memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN); - } - status = be_tx_qs_create(adapter); if (status) goto err; @@ -4253,7 +4232,7 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id) status = pci_enable_pcie_error_reporting(pdev); if (status) - dev_err(&pdev->dev, "Could not use PCIe error reporting\n"); + dev_info(&pdev->dev, "Could not use PCIe error reporting\n"); status = be_ctrl_init(adapter); if (status) diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 77ea0db0bbfc..fdf9307ba9e6 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2056,10 +2056,6 @@ fec_probe(struct platform_device *pdev) if (of_id) pdev->id_entry = of_id->data; - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!r) - return -ENXIO; - /* Init network device */ ndev = alloc_etherdev(sizeof(struct fec_enet_private)); if (!ndev) @@ -2077,6 +2073,7 @@ fec_probe(struct platform_device *pdev) fep->pause_flag |= FEC_PAUSE_FLAG_AUTONEG; #endif + r = platform_get_resource(pdev, IORESOURCE_MEM, 0); fep->hwp = devm_ioremap_resource(&pdev->dev, r); if (IS_ERR(fep->hwp)) { ret = PTR_ERR(fep->hwp); @@ -2126,10 +2123,25 @@ fec_probe(struct platform_device *pdev) fep->bufdesc_ex = 0; } - clk_prepare_enable(fep->clk_ahb); - clk_prepare_enable(fep->clk_ipg); - clk_prepare_enable(fep->clk_enet_out); - clk_prepare_enable(fep->clk_ptp); + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + goto failed_clk; + + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + + if (fep->clk_enet_out) { + ret = clk_prepare_enable(fep->clk_enet_out); + if (ret) + goto failed_clk_enet_out; + } + + if (fep->clk_ptp) { + ret = clk_prepare_enable(fep->clk_ptp); + if (ret) + goto failed_clk_ptp; + } fep->reg_phy = devm_regulator_get(&pdev->dev, "phy"); if (!IS_ERR(fep->reg_phy)) { @@ -2160,14 +2172,10 @@ fec_probe(struct platform_device *pdev) ret = irq; goto failed_irq; } - ret = request_irq(irq, fec_enet_interrupt, IRQF_DISABLED, pdev->name, ndev); - if (ret) { - while (--i >= 0) { - irq = platform_get_irq(pdev, i); - free_irq(irq, ndev); - } + ret = devm_request_irq(&pdev->dev, irq, fec_enet_interrupt, + IRQF_DISABLED, pdev->name, ndev); + if (ret) goto failed_irq; - } } ret = fec_enet_mii_init(pdev); @@ -2191,19 +2199,19 @@ failed_register: fec_enet_mii_remove(fep); failed_mii_init: failed_irq: - for (i = 0; i < FEC_IRQ_NUM; i++) { - irq = platform_get_irq(pdev, i); - if (irq > 0) - free_irq(irq, ndev); - } failed_init: if (fep->reg_phy) regulator_disable(fep->reg_phy); failed_regulator: - clk_disable_unprepare(fep->clk_ahb); + if (fep->clk_ptp) + clk_disable_unprepare(fep->clk_ptp); +failed_clk_ptp: + if (fep->clk_enet_out) + clk_disable_unprepare(fep->clk_enet_out); +failed_clk_enet_out: clk_disable_unprepare(fep->clk_ipg); - clk_disable_unprepare(fep->clk_enet_out); - clk_disable_unprepare(fep->clk_ptp); +failed_clk_ipg: + clk_disable_unprepare(fep->clk_ahb); failed_clk: failed_ioremap: free_netdev(ndev); @@ -2216,25 +2224,21 @@ fec_drv_remove(struct platform_device *pdev) { struct net_device *ndev = platform_get_drvdata(pdev); struct fec_enet_private *fep = netdev_priv(ndev); - int i; cancel_delayed_work_sync(&(fep->delay_work.delay_work)); unregister_netdev(ndev); fec_enet_mii_remove(fep); del_timer_sync(&fep->time_keep); - for (i = 0; i < FEC_IRQ_NUM; i++) { - int irq = platform_get_irq(pdev, i); - if (irq > 0) - free_irq(irq, ndev); - } if (fep->reg_phy) regulator_disable(fep->reg_phy); - clk_disable_unprepare(fep->clk_ptp); + if (fep->clk_ptp) + clk_disable_unprepare(fep->clk_ptp); if (fep->ptp_clock) ptp_clock_unregister(fep->ptp_clock); - clk_disable_unprepare(fep->clk_enet_out); - clk_disable_unprepare(fep->clk_ahb); + if (fep->clk_enet_out) + clk_disable_unprepare(fep->clk_enet_out); clk_disable_unprepare(fep->clk_ipg); + clk_disable_unprepare(fep->clk_ahb); free_netdev(ndev); return 0; @@ -2251,9 +2255,12 @@ fec_suspend(struct device *dev) fec_stop(ndev); netif_device_detach(ndev); } - clk_disable_unprepare(fep->clk_enet_out); - clk_disable_unprepare(fep->clk_ahb); + if (fep->clk_ptp) + clk_disable_unprepare(fep->clk_ptp); + if (fep->clk_enet_out) + clk_disable_unprepare(fep->clk_enet_out); clk_disable_unprepare(fep->clk_ipg); + clk_disable_unprepare(fep->clk_ahb); if (fep->reg_phy) regulator_disable(fep->reg_phy); @@ -2274,15 +2281,44 @@ fec_resume(struct device *dev) return ret; } - clk_prepare_enable(fep->clk_enet_out); - clk_prepare_enable(fep->clk_ahb); - clk_prepare_enable(fep->clk_ipg); + ret = clk_prepare_enable(fep->clk_ahb); + if (ret) + goto failed_clk_ahb; + + ret = clk_prepare_enable(fep->clk_ipg); + if (ret) + goto failed_clk_ipg; + + if (fep->clk_enet_out) { + ret = clk_prepare_enable(fep->clk_enet_out); + if (ret) + goto failed_clk_enet_out; + } + + if (fep->clk_ptp) { + ret = clk_prepare_enable(fep->clk_ptp); + if (ret) + goto failed_clk_ptp; + } + if (netif_running(ndev)) { fec_restart(ndev, fep->full_duplex); netif_device_attach(ndev); } return 0; + +failed_clk_ptp: + if (fep->clk_enet_out) + clk_disable_unprepare(fep->clk_enet_out); +failed_clk_enet_out: + clk_disable_unprepare(fep->clk_ipg); +failed_clk_ipg: + clk_disable_unprepare(fep->clk_ahb); +failed_clk_ahb: + if (fep->reg_phy) + regulator_disable(fep->reg_phy); + return ret; } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 8d2db7b808b7..dbb34f7ce448 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -593,7 +593,6 @@ static int gfar_parse_group(struct device_node *np, return -EINVAL; } - grp->grp_id = priv->num_grps; grp->priv = priv; spin_lock_init(&grp->grplock); if (priv->mode == MQ_MG_MODE) { diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index 04b552cd419d..ee19f2c138a6 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -1009,7 +1009,6 @@ struct gfar_irqinfo { * @napi: the napi poll function * @priv: back pointer to the priv structure * @regs: the ioremapped register space for this group - * @grp_id: group id for this group * @irqinfo: TX/RX/ER irq data for this group */ @@ -1018,11 +1017,10 @@ struct gfar_priv_grp { struct napi_struct napi; struct gfar_private *priv; struct gfar __iomem *regs; - unsigned int grp_id; + unsigned int rstat; unsigned long num_rx_queues; unsigned long rx_bit_map; /* cacheline 3 */ - unsigned int rstat; unsigned int tstat; unsigned long num_tx_queues; unsigned long tx_bit_map; diff --git a/drivers/net/ethernet/i825xx/sun3_82586.h b/drivers/net/ethernet/i825xx/sun3_82586.h index 93346f00486b..79aef681ac85 100644 --- a/drivers/net/ethernet/i825xx/sun3_82586.h +++ b/drivers/net/ethernet/i825xx/sun3_82586.h @@ -133,8 +133,8 @@ struct rfd_struct unsigned char last; /* Bit15,Last Frame on List / Bit14,suspend */ unsigned short next; /* linkoffset to next RFD */ unsigned short rbd_offset; /* pointeroffset to RBD-buffer */ - unsigned char dest[6]; /* ethernet-address, destination */ - unsigned char source[6]; /* ethernet-address, source */ + unsigned char dest[ETH_ALEN]; /* ethernet-address, destination */ + unsigned char source[ETH_ALEN]; /* ethernet-address, source */ unsigned short length; /* 802.3 frame-length */ unsigned short zero_dummy; /* dummy */ }; diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 5115ae76a5d1..ada6e210279f 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1175,15 +1175,12 @@ static int e100_configure(struct nic *nic, struct cb *cb, struct sk_buff *skb) config->rx_discard_short_frames = 0x0; /* 1=discard, 0=save */ } - netif_printk(nic, hw, KERN_DEBUG, nic->netdev, - "[00-07]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n", - c[0], c[1], c[2], c[3], c[4], c[5], c[6], c[7]); - netif_printk(nic, hw, KERN_DEBUG, nic->netdev, - "[08-15]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n", - c[8], c[9], c[10], c[11], c[12], c[13], c[14], c[15]); - netif_printk(nic, hw, KERN_DEBUG, nic->netdev, - "[16-23]=%02X:%02X:%02X:%02X:%02X:%02X:%02X:%02X\n", - c[16], c[17], c[18], c[19], c[20], c[21], c[22], c[23]); + netif_printk(nic, hw, KERN_DEBUG, nic->netdev, "[00-07]=%8ph\n", + c + 0); + netif_printk(nic, hw, KERN_DEBUG, nic->netdev, "[08-15]=%8ph\n", + c + 8); + netif_printk(nic, hw, KERN_DEBUG, nic->netdev, "[16-23]=%8ph\n", + c + 16); return 0; } diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 4c303e2a7cb3..104fcec86af3 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -2057,6 +2057,7 @@ const struct e1000_info e1000_82583_info = { | FLAG_HAS_JUMBO_FRAMES | FLAG_HAS_CTRLEXT_ON_LOAD, .flags2 = FLAG2_DISABLE_ASPM_L0S + | FLAG2_DISABLE_ASPM_L1 | FLAG2_NO_DISABLE_RX, .pba = 32, .max_hw_frame_size = DEFAULT_JUMBO, diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index ffbc08f56c40..ad0edd11015d 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -90,9 +90,6 @@ struct e1000_info; #define E1000_MNG_VLAN_NONE (-1) -/* Number of packet split data buffers (not including the header buffer) */ -#define PS_PAGE_BUFFERS (MAX_PS_BUFFERS - 1) - #define DEFAULT_JUMBO 9234 /* Time to wait before putting the device into D3 if there's no link (in ms). */ diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 59c22bf18701..e4ebd7ddf5f2 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -173,7 +173,7 @@ static int e1000_get_settings(struct net_device *netdev, speed = adapter->link_speed; ecmd->duplex = adapter->link_duplex - 1; } - } else { + } else if (!pm_runtime_suspended(netdev->dev.parent)) { u32 status = er32(STATUS); if (status & E1000_STATUS_LU) { if (status & E1000_STATUS_SPEED_1000) @@ -264,6 +264,9 @@ static int e1000_set_settings(struct net_device *netdev, { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; + int ret_val = 0; + + pm_runtime_get_sync(netdev->dev.parent); /* When SoL/IDER sessions are active, autoneg/speed/duplex * cannot be changed @@ -271,7 +274,8 @@ static int e1000_set_settings(struct net_device *netdev, if (hw->phy.ops.check_reset_block && hw->phy.ops.check_reset_block(hw)) { e_err("Cannot change link characteristics when SoL/IDER is active.\n"); - return -EINVAL; + ret_val = -EINVAL; + goto out; } /* MDI setting is only allowed when autoneg enabled because @@ -279,13 +283,16 @@ static int e1000_set_settings(struct net_device *netdev, * duplex is forced. */ if (ecmd->eth_tp_mdix_ctrl) { - if (hw->phy.media_type != e1000_media_type_copper) - return -EOPNOTSUPP; + if (hw->phy.media_type != e1000_media_type_copper) { + ret_val = -EOPNOTSUPP; + goto out; + } if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) && (ecmd->autoneg != AUTONEG_ENABLE)) { e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n"); - return -EINVAL; + ret_val = -EINVAL; + goto out; } } @@ -307,8 +314,8 @@ static int e1000_set_settings(struct net_device *netdev, u32 speed = ethtool_cmd_speed(ecmd); /* calling this overrides forced MDI setting */ if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) { - clear_bit(__E1000_RESETTING, &adapter->state); - return -EINVAL; + ret_val = -EINVAL; + goto out; } } @@ -331,8 +338,10 @@ static int e1000_set_settings(struct net_device *netdev, e1000e_reset(adapter); } +out: + pm_runtime_put_sync(netdev->dev.parent); clear_bit(__E1000_RESETTING, &adapter->state); - return 0; + return ret_val; } static void e1000_get_pauseparam(struct net_device *netdev, @@ -366,6 +375,8 @@ static int e1000_set_pauseparam(struct net_device *netdev, while (test_and_set_bit(__E1000_RESETTING, &adapter->state)) usleep_range(1000, 2000); + pm_runtime_get_sync(netdev->dev.parent); + if (adapter->fc_autoneg == AUTONEG_ENABLE) { hw->fc.requested_mode = e1000_fc_default; if (netif_running(adapter->netdev)) { @@ -398,6 +409,7 @@ static int e1000_set_pauseparam(struct net_device *netdev, } out: + pm_runtime_put_sync(netdev->dev.parent); clear_bit(__E1000_RESETTING, &adapter->state); return retval; } @@ -428,6 +440,8 @@ static void e1000_get_regs(struct net_device *netdev, u32 *regs_buff = p; u16 phy_data; + pm_runtime_get_sync(netdev->dev.parent); + memset(p, 0, E1000_REGS_LEN * sizeof(u32)); regs->version = (1 << 24) | (adapter->pdev->revision << 16) | @@ -472,6 +486,8 @@ static void e1000_get_regs(struct net_device *netdev, e1e_rphy(hw, MII_STAT1000, &phy_data); regs_buff[24] = (u32)phy_data; /* phy local receiver status */ regs_buff[25] = regs_buff[24]; /* phy remote receiver status */ + + pm_runtime_put_sync(netdev->dev.parent); } static int e1000_get_eeprom_len(struct net_device *netdev) @@ -504,6 +520,8 @@ static int e1000_get_eeprom(struct net_device *netdev, if (!eeprom_buff) return -ENOMEM; + pm_runtime_get_sync(netdev->dev.parent); + if (hw->nvm.type == e1000_nvm_eeprom_spi) { ret_val = e1000_read_nvm(hw, first_word, last_word - first_word + 1, @@ -517,6 +535,8 @@ static int e1000_get_eeprom(struct net_device *netdev, } } + pm_runtime_put_sync(netdev->dev.parent); + if (ret_val) { /* a read error occurred, throw away the result */ memset(eeprom_buff, 0xff, sizeof(u16) * @@ -566,6 +586,8 @@ static int e1000_set_eeprom(struct net_device *netdev, ptr = (void *)eeprom_buff; + pm_runtime_get_sync(netdev->dev.parent); + if (eeprom->offset & 1) { /* need read/modify/write of first changed EEPROM word */ /* only the second byte of the word is being modified */ @@ -606,6 +628,7 @@ static int e1000_set_eeprom(struct net_device *netdev, ret_val = e1000e_update_nvm_checksum(hw); out: + pm_runtime_put_sync(netdev->dev.parent); kfree(eeprom_buff); return ret_val; } @@ -701,6 +724,8 @@ static int e1000_set_ringparam(struct net_device *netdev, } } + pm_runtime_get_sync(netdev->dev.parent); + e1000e_down(adapter); /* We can't just free everything and then setup again, because the @@ -739,6 +764,7 @@ err_setup_rx: e1000e_free_tx_resources(temp_tx); err_setup: e1000e_up(adapter); + pm_runtime_put_sync(netdev->dev.parent); free_temp: vfree(temp_tx); vfree(temp_rx); @@ -1732,6 +1758,8 @@ static void e1000_diag_test(struct net_device *netdev, u8 autoneg; bool if_running = netif_running(netdev); + pm_runtime_get_sync(netdev->dev.parent); + set_bit(__E1000_TESTING, &adapter->state); if (!if_running) { @@ -1817,6 +1845,8 @@ static void e1000_diag_test(struct net_device *netdev, } msleep_interruptible(4 * 1000); + + pm_runtime_put_sync(netdev->dev.parent); } static void e1000_get_wol(struct net_device *netdev, @@ -1891,6 +1921,8 @@ static int e1000_set_phys_id(struct net_device *netdev, switch (state) { case ETHTOOL_ID_ACTIVE: + pm_runtime_get_sync(netdev->dev.parent); + if (!hw->mac.ops.blink_led) return 2; /* cycle on/off twice per second */ @@ -1902,6 +1934,7 @@ static int e1000_set_phys_id(struct net_device *netdev, e1e_wphy(hw, IFE_PHY_SPECIAL_CONTROL_LED, 0); hw->mac.ops.led_off(hw); hw->mac.ops.cleanup_led(hw); + pm_runtime_put_sync(netdev->dev.parent); break; case ETHTOOL_ID_ON: @@ -1912,6 +1945,7 @@ static int e1000_set_phys_id(struct net_device *netdev, hw->mac.ops.led_off(hw); break; } + return 0; } @@ -1950,11 +1984,15 @@ static int e1000_set_coalesce(struct net_device *netdev, adapter->itr_setting = adapter->itr & ~3; } + pm_runtime_get_sync(netdev->dev.parent); + if (adapter->itr_setting != 0) e1000e_write_itr(adapter, adapter->itr); else e1000e_write_itr(adapter, 0); + pm_runtime_put_sync(netdev->dev.parent); + return 0; } @@ -1968,7 +2006,9 @@ static int e1000_nway_reset(struct net_device *netdev) if (!adapter->hw.mac.autoneg) return -EINVAL; + pm_runtime_get_sync(netdev->dev.parent); e1000e_reinit_locked(adapter); + pm_runtime_put_sync(netdev->dev.parent); return 0; } @@ -1982,7 +2022,12 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, int i; char *p = NULL; + pm_runtime_get_sync(netdev->dev.parent); + e1000e_get_stats64(netdev, &net_stats); + + pm_runtime_put_sync(netdev->dev.parent); + for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { switch (e1000_gstrings_stats[i].type) { case NETDEV_STATS: @@ -2033,7 +2078,11 @@ static int e1000_get_rxnfc(struct net_device *netdev, case ETHTOOL_GRXFH: { struct e1000_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; - u32 mrqc = er32(MRQC); + u32 mrqc; + + pm_runtime_get_sync(netdev->dev.parent); + mrqc = er32(MRQC); + pm_runtime_put_sync(netdev->dev.parent); if (!(mrqc & E1000_MRQC_RSS_FIELD_MASK)) return 0; @@ -2096,9 +2145,13 @@ static int e1000e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) return -EOPNOTSUPP; } + pm_runtime_get_sync(netdev->dev.parent); + ret_val = hw->phy.ops.acquire(hw); - if (ret_val) + if (ret_val) { + pm_runtime_put_sync(netdev->dev.parent); return -EBUSY; + } /* EEE Capability */ ret_val = e1000_read_emi_reg_locked(hw, cap_addr, &phy_data); @@ -2117,14 +2170,11 @@ static int e1000e_get_eee(struct net_device *netdev, struct ethtool_eee *edata) /* EEE PCS Status */ ret_val = e1000_read_emi_reg_locked(hw, pcs_stat_addr, &phy_data); + if (ret_val) + goto release; if (hw->phy.type == e1000_phy_82579) phy_data <<= 8; -release: - hw->phy.ops.release(hw); - if (ret_val) - return -ENODATA; - /* Result of the EEE auto negotiation - there is no register that * has the status of the EEE negotiation so do a best-guess based * on whether Tx or Rx LPI indications have been received. @@ -2136,7 +2186,14 @@ release: edata->tx_lpi_enabled = true; edata->tx_lpi_timer = er32(LPIC) >> E1000_LPIC_LPIET_SHIFT; - return 0; +release: + hw->phy.ops.release(hw); + if (ret_val) + ret_val = -ENODATA; + + pm_runtime_put_sync(netdev->dev.parent); + + return ret_val; } static int e1000e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) @@ -2169,12 +2226,16 @@ static int e1000e_set_eee(struct net_device *netdev, struct ethtool_eee *edata) hw->dev_spec.ich8lan.eee_disable = !edata->eee_enabled; + pm_runtime_get_sync(netdev->dev.parent); + /* reset the link */ if (netif_running(netdev)) e1000e_reinit_locked(adapter); else e1000e_reset(adapter); + pm_runtime_put_sync(netdev->dev.parent); + return 0; } @@ -2212,19 +2273,7 @@ static int e1000e_get_ts_info(struct net_device *netdev, return 0; } -static int e1000e_ethtool_begin(struct net_device *netdev) -{ - return pm_runtime_get_sync(netdev->dev.parent); -} - -static void e1000e_ethtool_complete(struct net_device *netdev) -{ - pm_runtime_put_sync(netdev->dev.parent); -} - static const struct ethtool_ops e1000_ethtool_ops = { - .begin = e1000e_ethtool_begin, - .complete = e1000e_ethtool_complete, .get_settings = e1000_get_settings, .set_settings = e1000_set_settings, .get_drvinfo = e1000_get_drvinfo, diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index a6f903a9b773..b799fd9b6aa9 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -90,6 +90,10 @@ struct e1000_hw; #define E1000_DEV_ID_PCH_LPT_I217_V 0x153B #define E1000_DEV_ID_PCH_LPTLP_I218_LM 0x155A #define E1000_DEV_ID_PCH_LPTLP_I218_V 0x1559 +#define E1000_DEV_ID_PCH_I218_LM2 0x15A0 +#define E1000_DEV_ID_PCH_I218_V2 0x15A1 +#define E1000_DEV_ID_PCH_I218_LM3 0x15A2 /* Wildcat Point PCH */ +#define E1000_DEV_ID_PCH_I218_V3 0x15A3 /* Wildcat Point PCH */ #define E1000_REVISION_4 4 @@ -227,6 +231,9 @@ union e1000_rx_desc_extended { }; #define MAX_PS_BUFFERS 4 + +/* Number of packet split data buffers (not including the header buffer) */ +#define PS_PAGE_BUFFERS (MAX_PS_BUFFERS - 1) /* Receive Descriptor - Packet Split */ union e1000_rx_desc_packet_split { struct { @@ -251,7 +258,8 @@ union e1000_rx_desc_packet_split { } middle; struct { __le16 header_status; - __le16 length[3]; /* length of buffers 1-3 */ + /* length of buffers 1-3 */ + __le16 length[PS_PAGE_BUFFERS]; } upper; __le64 reserved; } wb; /* writeback */ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 9dde390f7e71..af08188d7e62 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -185,6 +185,7 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) u32 phy_id = 0; s32 ret_val; u16 retry_count; + u32 mac_reg = 0; for (retry_count = 0; retry_count < 2; retry_count++) { ret_val = e1e_rphy_locked(hw, MII_PHYSID1, &phy_reg); @@ -203,11 +204,11 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) if (hw->phy.id) { if (hw->phy.id == phy_id) - return true; + goto out; } else if (phy_id) { hw->phy.id = phy_id; hw->phy.revision = (u32)(phy_reg & ~PHY_REVISION_MASK); - return true; + goto out; } /* In case the PHY needs to be in mdio slow mode, @@ -219,7 +220,22 @@ static bool e1000_phy_is_accessible_pchlan(struct e1000_hw *hw) ret_val = e1000e_get_phy_id(hw); hw->phy.ops.acquire(hw); - return !ret_val; + if (ret_val) + return false; +out: + if (hw->mac.type == e1000_pch_lpt) { + /* Unforce SMBus mode in PHY */ + e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg); + phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; + e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg); + + /* Unforce SMBus mode in MAC */ + mac_reg = er32(CTRL_EXT); + mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + } + + return true; } /** @@ -233,7 +249,6 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) { u32 mac_reg, fwsm = er32(FWSM); s32 ret_val; - u16 phy_reg; /* Gate automatic PHY configuration by hardware on managed and * non-managed 82579 and newer adapters. @@ -262,22 +277,16 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS; ew32(CTRL_EXT, mac_reg); + /* Wait 50 milliseconds for MAC to finish any retries + * that it might be trying to perform from previous + * attempts to acknowledge any phy read requests. + */ + msleep(50); + /* fall-through */ case e1000_pch2lan: - if (e1000_phy_is_accessible_pchlan(hw)) { - if (hw->mac.type == e1000_pch_lpt) { - /* Unforce SMBus mode in PHY */ - e1e_rphy_locked(hw, CV_SMB_CTRL, &phy_reg); - phy_reg &= ~CV_SMB_CTRL_FORCE_SMBUS; - e1e_wphy_locked(hw, CV_SMB_CTRL, phy_reg); - - /* Unforce SMBus mode in MAC */ - mac_reg = er32(CTRL_EXT); - mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, mac_reg); - } + if (e1000_phy_is_accessible_pchlan(hw)) break; - } /* fall-through */ case e1000_pchlan: @@ -287,6 +296,7 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) if (hw->phy.ops.check_reset_block(hw)) { e_dbg("Required LANPHYPC toggle blocked by ME\n"); + ret_val = -E1000_ERR_PHY; break; } @@ -298,15 +308,6 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) mac_reg |= E1000_FEXTNVM3_PHY_CFG_COUNTER_50MSEC; ew32(FEXTNVM3, mac_reg); - if (hw->mac.type == e1000_pch_lpt) { - /* Toggling LANPHYPC brings the PHY out of SMBus mode - * So ensure that the MAC is also out of SMBus mode - */ - mac_reg = er32(CTRL_EXT); - mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; - ew32(CTRL_EXT, mac_reg); - } - /* Toggle LANPHYPC Value bit */ mac_reg = er32(CTRL); mac_reg |= E1000_CTRL_LANPHYPC_OVERRIDE; @@ -325,6 +326,21 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) usleep_range(5000, 10000); } while (!(er32(CTRL_EXT) & E1000_CTRL_EXT_LPCD) && count--); + usleep_range(30000, 60000); + if (e1000_phy_is_accessible_pchlan(hw)) + break; + + /* Toggling LANPHYPC brings the PHY out of SMBus mode + * so ensure that the MAC is also out of SMBus mode + */ + mac_reg = er32(CTRL_EXT); + mac_reg &= ~E1000_CTRL_EXT_FORCE_SMBUS; + ew32(CTRL_EXT, mac_reg); + + if (e1000_phy_is_accessible_pchlan(hw)) + break; + + ret_val = -E1000_ERR_PHY; } break; default: @@ -332,13 +348,14 @@ static s32 e1000_init_phy_workarounds_pchlan(struct e1000_hw *hw) } hw->phy.ops.release(hw); - - /* Reset the PHY before any access to it. Doing so, ensures - * that the PHY is in a known good state before we read/write - * PHY registers. The generic reset is sufficient here, - * because we haven't determined the PHY type yet. - */ - ret_val = e1000e_phy_hw_reset_generic(hw); + if (!ret_val) { + /* Reset the PHY before any access to it. Doing so, ensures + * that the PHY is in a known good state before we read/write + * PHY registers. The generic reset is sufficient here, + * because we haven't determined the PHY type yet. + */ + ret_val = e1000e_phy_hw_reset_generic(hw); + } out: /* Ungate automatic PHY configuration on non-managed 82579 */ @@ -793,29 +810,31 @@ release: * When K1 is enabled for 1Gbps, the MAC can miss 2 DMA completion indications * preventing further DMA write requests. Workaround the issue by disabling * the de-assertion of the clock request when in 1Gpbs mode. + * Also, set appropriate Tx re-transmission timeouts for 10 and 100Half link + * speeds in order to avoid Tx hangs. **/ static s32 e1000_k1_workaround_lpt_lp(struct e1000_hw *hw, bool link) { u32 fextnvm6 = er32(FEXTNVM6); + u32 status = er32(STATUS); s32 ret_val = 0; + u16 reg; - if (link && (er32(STATUS) & E1000_STATUS_SPEED_1000)) { - u16 kmrn_reg; - + if (link && (status & E1000_STATUS_SPEED_1000)) { ret_val = hw->phy.ops.acquire(hw); if (ret_val) return ret_val; ret_val = e1000e_read_kmrn_reg_locked(hw, E1000_KMRNCTRLSTA_K1_CONFIG, - &kmrn_reg); + ®); if (ret_val) goto release; ret_val = e1000e_write_kmrn_reg_locked(hw, E1000_KMRNCTRLSTA_K1_CONFIG, - kmrn_reg & + reg & ~E1000_KMRNCTRLSTA_K1_ENABLE); if (ret_val) goto release; @@ -827,12 +846,45 @@ static s32 e1000_k1_workaround_lpt_lp(struct e1000_hw *hw, bool link) ret_val = e1000e_write_kmrn_reg_locked(hw, E1000_KMRNCTRLSTA_K1_CONFIG, - kmrn_reg); + reg); release: hw->phy.ops.release(hw); } else { /* clear FEXTNVM6 bit 8 on link down or 10/100 */ - ew32(FEXTNVM6, fextnvm6 & ~E1000_FEXTNVM6_REQ_PLL_CLK); + fextnvm6 &= ~E1000_FEXTNVM6_REQ_PLL_CLK; + + if (!link || ((status & E1000_STATUS_SPEED_100) && + (status & E1000_STATUS_FD))) + goto update_fextnvm6; + + ret_val = e1e_rphy(hw, I217_INBAND_CTRL, ®); + if (ret_val) + return ret_val; + + /* Clear link status transmit timeout */ + reg &= ~I217_INBAND_CTRL_LINK_STAT_TX_TIMEOUT_MASK; + + if (status & E1000_STATUS_SPEED_100) { + /* Set inband Tx timeout to 5x10us for 100Half */ + reg |= 5 << I217_INBAND_CTRL_LINK_STAT_TX_TIMEOUT_SHIFT; + + /* Do not extend the K1 entry latency for 100Half */ + fextnvm6 &= ~E1000_FEXTNVM6_ENABLE_K1_ENTRY_CONDITION; + } else { + /* Set inband Tx timeout to 50x10us for 10Full/Half */ + reg |= 50 << + I217_INBAND_CTRL_LINK_STAT_TX_TIMEOUT_SHIFT; + + /* Extend the K1 entry latency for 10 Mbps */ + fextnvm6 |= E1000_FEXTNVM6_ENABLE_K1_ENTRY_CONDITION; + } + + ret_val = e1e_wphy(hw, I217_INBAND_CTRL, reg); + if (ret_val) + return ret_val; + +update_fextnvm6: + ew32(FEXTNVM6, fextnvm6); } return ret_val; @@ -993,7 +1045,9 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) /* Work-around I218 hang issue */ if ((hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPTLP_I218_LM) || - (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPTLP_I218_V)) { + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_LPTLP_I218_V) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_LM3) || + (hw->adapter->pdev->device == E1000_DEV_ID_PCH_I218_V3)) { ret_val = e1000_k1_workaround_lpt_lp(hw, link); if (ret_val) return ret_val; @@ -4168,7 +4222,9 @@ void e1000_suspend_workarounds_ich8lan(struct e1000_hw *hw) u16 phy_reg, device_id = hw->adapter->pdev->device; if ((device_id == E1000_DEV_ID_PCH_LPTLP_I218_LM) || - (device_id == E1000_DEV_ID_PCH_LPTLP_I218_V)) { + (device_id == E1000_DEV_ID_PCH_LPTLP_I218_V) || + (device_id == E1000_DEV_ID_PCH_I218_LM3) || + (device_id == E1000_DEV_ID_PCH_I218_V3)) { u32 fextnvm6 = er32(FEXTNVM6); ew32(FEXTNVM6, fextnvm6 & ~E1000_FEXTNVM6_REQ_PLL_CLK); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 80034a2b297c..59865695b282 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -93,6 +93,7 @@ #define E1000_FEXTNVM4_BEACON_DURATION_16USEC 0x3 #define E1000_FEXTNVM6_REQ_PLL_CLK 0x00000100 +#define E1000_FEXTNVM6_ENABLE_K1_ENTRY_CONDITION 0x00000200 #define PCIE_ICH8_SNOOP_ALL PCIE_NO_SNOOP_ALL @@ -197,6 +198,11 @@ #define SW_FLAG_TIMEOUT 1000 /* SW Semaphore flag timeout in ms */ +/* Inband Control */ +#define I217_INBAND_CTRL PHY_REG(770, 18) +#define I217_INBAND_CTRL_LINK_STAT_TX_TIMEOUT_MASK 0x3F00 +#define I217_INBAND_CTRL_LINK_STAT_TX_TIMEOUT_SHIFT 8 + /* PHY Low Power Idle Control */ #define I82579_LPI_CTRL PHY_REG(772, 20) #define I82579_LPI_CTRL_100_ENABLE 0x2000 diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 77f81cbb601a..e6d2c0f8f76a 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2979,17 +2979,10 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) u32 pages = 0; /* Workaround Si errata on PCHx - configure jumbo frame flow */ - if (hw->mac.type >= e1000_pch2lan) { - s32 ret_val; - - if (adapter->netdev->mtu > ETH_DATA_LEN) - ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, true); - else - ret_val = e1000_lv_jumbo_workaround_ich8lan(hw, false); - - if (ret_val) - e_dbg("failed to enable jumbo frame workaround mode\n"); - } + if ((hw->mac.type >= e1000_pch2lan) && + (adapter->netdev->mtu > ETH_DATA_LEN) && + e1000_lv_jumbo_workaround_ich8lan(hw, true)) + e_dbg("failed to enable jumbo frame workaround mode\n"); /* Program MC offset vector base */ rctl = er32(RCTL); @@ -3826,6 +3819,8 @@ void e1000e_reset(struct e1000_adapter *adapter) break; } + pba = 14; + ew32(PBA, pba); fc->high_water = ((pba << 10) * 9 / 10) & E1000_FCRTH_RTH; fc->low_water = ((pba << 10) * 8 / 10) & E1000_FCRTL_RTL; break; @@ -4034,6 +4029,12 @@ void e1000e_down(struct e1000_adapter *adapter) adapter->link_speed = 0; adapter->link_duplex = 0; + /* Disable Si errata workaround on PCHx for jumbo frame flow */ + if ((hw->mac.type >= e1000_pch2lan) && + (adapter->netdev->mtu > ETH_DATA_LEN) && + e1000_lv_jumbo_workaround_ich8lan(hw, false)) + e_dbg("failed to disable jumbo frame workaround mode\n"); + if (!pci_channel_offline(adapter->pdev)) e1000e_reset(adapter); @@ -4683,11 +4684,11 @@ static void e1000_phy_read_status(struct e1000_adapter *adapter) struct e1000_hw *hw = &adapter->hw; struct e1000_phy_regs *phy = &adapter->phy_regs; - if ((er32(STATUS) & E1000_STATUS_LU) && + if (!pm_runtime_suspended((&adapter->pdev->dev)->parent) && + (er32(STATUS) & E1000_STATUS_LU) && (adapter->hw.phy.media_type == e1000_media_type_copper)) { int ret_val; - pm_runtime_get_sync(&adapter->pdev->dev); ret_val = e1e_rphy(hw, MII_BMCR, &phy->bmcr); ret_val |= e1e_rphy(hw, MII_BMSR, &phy->bmsr); ret_val |= e1e_rphy(hw, MII_ADVERTISE, &phy->advertise); @@ -4698,7 +4699,6 @@ static void e1000_phy_read_status(struct e1000_adapter *adapter) ret_val |= e1e_rphy(hw, MII_ESTATUS, &phy->estatus); if (ret_val) e_warn("Error reading PHY register\n"); - pm_runtime_put_sync(&adapter->pdev->dev); } else { /* Do not read PHY registers if link is not up * Set values to typical power-on defaults @@ -5995,6 +5995,8 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime) */ e1000e_release_hw_control(adapter); + pci_clear_master(pdev); + /* The pci-e switch on some quad port adapters will report a * correctable error when the MAC transitions from D0 to D3. To * prevent this we need to mask off the correctable errors on the @@ -6723,10 +6725,6 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->hw.fc.current_mode = e1000_fc_default; adapter->hw.phy.autoneg_advertised = 0x2f; - /* ring size defaults */ - adapter->rx_ring->count = E1000_DEFAULT_RXD; - adapter->tx_ring->count = E1000_DEFAULT_TXD; - /* Initial Wake on LAN setting - If APM wake is enabled in * the EEPROM, enable the ACPI Magic Packet filter */ @@ -6976,6 +6974,10 @@ static DEFINE_PCI_DEVICE_TABLE(e1000_pci_tbl) = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPT_I217_V), board_pch_lpt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_LM), board_pch_lpt }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_LPTLP_I218_V), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM2), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V2), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_LM3), board_pch_lpt }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_PCH_I218_V3), board_pch_lpt }, { 0, 0, 0, 0, 0, 0, 0 } /* terminate list */ }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index a6494e5daffe..0ac6b11c6e4e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -618,9 +618,8 @@ struct ixgbe_adapter { #define IXGBE_FLAG2_FDIR_REQUIRES_REINIT (u32)(1 << 7) #define IXGBE_FLAG2_RSS_FIELD_IPV4_UDP (u32)(1 << 8) #define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP (u32)(1 << 9) -#define IXGBE_FLAG2_PTP_ENABLED (u32)(1 << 10) -#define IXGBE_FLAG2_PTP_PPS_ENABLED (u32)(1 << 11) -#define IXGBE_FLAG2_BRIDGE_MODE_VEB (u32)(1 << 12) +#define IXGBE_FLAG2_PTP_PPS_ENABLED (u32)(1 << 10) +#define IXGBE_FLAG2_BRIDGE_MODE_VEB (u32)(1 << 11) /* Tx fast path data */ int num_tx_queues; @@ -754,7 +753,7 @@ enum ixgbe_state_t { __IXGBE_DOWN, __IXGBE_SERVICE_SCHED, __IXGBE_IN_SFP_INIT, - __IXGBE_READ_I2C, + __IXGBE_PTP_RUNNING, }; struct ixgbe_cb { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index 4a5bfb6b3af0..a26f3fee4f35 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -1018,8 +1018,17 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, u16 sfp_addr = 0; u16 sfp_data = 0; u16 sfp_stat = 0; + u16 gssr; u32 i; + if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) + gssr = IXGBE_GSSR_PHY1_SM; + else + gssr = IXGBE_GSSR_PHY0_SM; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) + return IXGBE_ERR_SWFW_SYNC; + if (hw->phy.type == ixgbe_phy_nl) { /* * phy SDA/SCL registers are at addresses 0xC30A to @@ -1028,17 +1037,17 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, */ sfp_addr = (dev_addr << 8) + byte_offset; sfp_addr = (sfp_addr | IXGBE_I2C_EEPROM_READ_MASK); - hw->phy.ops.write_reg(hw, - IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR, - MDIO_MMD_PMAPMD, - sfp_addr); + hw->phy.ops.write_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR, + MDIO_MMD_PMAPMD, + sfp_addr); /* Poll status */ for (i = 0; i < 100; i++) { - hw->phy.ops.read_reg(hw, - IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT, - MDIO_MMD_PMAPMD, - &sfp_stat); + hw->phy.ops.read_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT, + MDIO_MMD_PMAPMD, + &sfp_stat); sfp_stat = sfp_stat & IXGBE_I2C_EEPROM_STATUS_MASK; if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS) break; @@ -1052,8 +1061,8 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, } /* Read data */ - hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, - MDIO_MMD_PMAPMD, &sfp_data); + hw->phy.ops.read_reg_mdi(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, + MDIO_MMD_PMAPMD, &sfp_data); *eeprom_data = (u8)(sfp_data >> 8); } else { @@ -1061,6 +1070,7 @@ static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, } out: + hw->mac.ops.release_swfw_sync(hw, gssr); return status; } @@ -1321,11 +1331,13 @@ static struct ixgbe_eeprom_operations eeprom_ops_82598 = { static struct ixgbe_phy_operations phy_ops_82598 = { .identify = &ixgbe_identify_phy_generic, - .identify_sfp = &ixgbe_identify_sfp_module_generic, + .identify_sfp = &ixgbe_identify_module_generic, .init = &ixgbe_init_phy_ops_82598, .reset = &ixgbe_reset_phy_generic, .read_reg = &ixgbe_read_phy_reg_generic, .write_reg = &ixgbe_write_phy_reg_generic, + .read_reg_mdi = &ixgbe_read_phy_reg_mdi, + .write_reg_mdi = &ixgbe_write_phy_reg_mdi, .setup_link = &ixgbe_setup_phy_link_generic, .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_82598, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 0b82d38bc97d..207f68fbe3d3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -58,6 +58,10 @@ static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw, ixgbe_link_speed speed, bool autoneg_wait_to_complete); static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw); +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); static bool ixgbe_mng_enabled(struct ixgbe_hw *hw) { @@ -219,6 +223,25 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw) struct ixgbe_mac_info *mac = &hw->mac; struct ixgbe_phy_info *phy = &hw->phy; s32 ret_val = 0; + u32 esdp; + + if (hw->device_id == IXGBE_DEV_ID_82599_QSFP_SF_QP) { + /* Store flag indicating I2C bus access control unit. */ + hw->phy.qsfp_shared_i2c_bus = true; + + /* Initialize access to QSFP+ I2C bus */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0_DIR; + esdp &= ~IXGBE_ESDP_SDP1_DIR; + esdp &= ~IXGBE_ESDP_SDP0; + esdp &= ~IXGBE_ESDP_SDP0_NATIVE; + esdp &= ~IXGBE_ESDP_SDP1_NATIVE; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + phy->ops.read_i2c_byte = &ixgbe_read_i2c_byte_82599; + phy->ops.write_i2c_byte = &ixgbe_write_i2c_byte_82599; + } /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); @@ -397,6 +420,9 @@ static enum ixgbe_media_type ixgbe_get_media_type_82599(struct ixgbe_hw *hw) case IXGBE_DEV_ID_82599_LS: media_type = ixgbe_media_type_fiber_lco; break; + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + media_type = ixgbe_media_type_fiber_qsfp; + break; default: media_type = ixgbe_media_type_unknown; break; @@ -527,6 +553,75 @@ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) } /** + * ixgbe_set_fiber_fixed_speed - Set module link speed for fixed fiber + * @hw: pointer to hardware structure + * @speed: link speed to set + * + * We set the module speed differently for fixed fiber. For other + * multi-speed devices we don't have an error value so here if we + * detect an error we just log it and exit. + */ +static void ixgbe_set_fiber_fixed_speed(struct ixgbe_hw *hw, + ixgbe_link_speed speed) +{ + s32 status; + u8 rs, eeprom_data; + + switch (speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + /* one bit mask same as setting on */ + rs = IXGBE_SFF_SOFT_RS_SELECT_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + rs = IXGBE_SFF_SOFT_RS_SELECT_1G; + break; + default: + hw_dbg(hw, "Invalid fixed module speed\n"); + return; + } + + /* Set RS0 */ + status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + &eeprom_data); + if (status) { + hw_dbg(hw, "Failed to read Rx Rate Select RS0\n"); + goto out; + } + + eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) & rs; + + status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + eeprom_data); + if (status) { + hw_dbg(hw, "Failed to write Rx Rate Select RS0\n"); + goto out; + } + + /* Set RS1 */ + status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + &eeprom_data); + if (status) { + hw_dbg(hw, "Failed to read Rx Rate Select RS1\n"); + goto out; + } + + eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) & rs; + + status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + eeprom_data); + if (status) { + hw_dbg(hw, "Failed to write Rx Rate Select RS1\n"); + goto out; + } +out: + return; +} + +/** * ixgbe_setup_mac_link_multispeed_fiber - Set MAC link speed * @hw: pointer to hardware structure * @speed: new link speed @@ -573,9 +668,14 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, goto out; /* Set the module link speed */ - esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); - IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); - IXGBE_WRITE_FLUSH(hw); + if (hw->phy.media_type == ixgbe_media_type_fiber_fixed) { + ixgbe_set_fiber_fixed_speed(hw, + IXGBE_LINK_SPEED_10GB_FULL); + } else { + esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + } /* Allow module to change analog characteristics (1G->10G) */ msleep(40); @@ -625,10 +725,15 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, goto out; /* Set the module link speed */ - esdp_reg &= ~IXGBE_ESDP_SDP5; - esdp_reg |= IXGBE_ESDP_SDP5_DIR; - IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); - IXGBE_WRITE_FLUSH(hw); + if (hw->phy.media_type == ixgbe_media_type_fiber_fixed) { + ixgbe_set_fiber_fixed_speed(hw, + IXGBE_LINK_SPEED_1GB_FULL); + } else { + esdp_reg &= ~IXGBE_ESDP_SDP5; + esdp_reg |= IXGBE_ESDP_SDP5_DIR; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + } /* Allow module to change analog characteristics (10G->1G) */ msleep(40); @@ -1872,7 +1977,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_copper) goto out; else - status = ixgbe_identify_sfp_module_generic(hw); + status = ixgbe_identify_module_generic(hw); } /* Set PHY type none if no PHY detected */ @@ -1978,10 +2083,12 @@ sfp_check: switch (hw->phy.type) { case ixgbe_phy_sfp_passive_tyco: case ixgbe_phy_sfp_passive_unknown: + case ixgbe_phy_qsfp_passive_unknown: physical_layer = IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU; break; case ixgbe_phy_sfp_ftl_active: case ixgbe_phy_sfp_active_unknown: + case ixgbe_phy_qsfp_active_unknown: physical_layer = IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA; break; case ixgbe_phy_sfp_avago: @@ -1999,6 +2106,15 @@ sfp_check: else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_T; break; + case ixgbe_phy_qsfp_intel: + case ixgbe_phy_qsfp_unknown: + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_10GBE_COMP, &comp_codes_10g); + if (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_SR; + else if (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_LR; + break; default: break; } @@ -2236,6 +2352,112 @@ reset_pipeline_out: return ret_val; } +/** + * ixgbe_read_i2c_byte_82599 - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_read_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + +/** + * ixgbe_write_i2c_byte_82599 - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_write_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + static struct ixgbe_mac_operations mac_ops_82599 = { .init_hw = &ixgbe_init_hw_generic, .reset_hw = &ixgbe_reset_hw_82599, @@ -2300,7 +2522,7 @@ static struct ixgbe_eeprom_operations eeprom_ops_82599 = { static struct ixgbe_phy_operations phy_ops_82599 = { .identify = &ixgbe_identify_phy_82599, - .identify_sfp = &ixgbe_identify_sfp_module_generic, + .identify_sfp = &ixgbe_identify_module_generic, .init = &ixgbe_init_phy_ops_82599, .reset = &ixgbe_reset_phy_generic, .read_reg = &ixgbe_read_phy_reg_generic, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 9bcdeb89af5a..50e62a2b1a65 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -65,17 +65,42 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); * function check the device id to see if the associated phy supports * autoneg flow control. **/ -s32 ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) { + bool supported = false; + ixgbe_link_speed speed; + bool link_up; - switch (hw->device_id) { - case IXGBE_DEV_ID_X540T: - case IXGBE_DEV_ID_X540T1: - case IXGBE_DEV_ID_82599_T3_LOM: - return 0; + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber_fixed: + case ixgbe_media_type_fiber: + hw->mac.ops.check_link(hw, &speed, &link_up, false); + /* if link is down, assume supported */ + if (link_up) + supported = speed == IXGBE_LINK_SPEED_1GB_FULL ? + true : false; + else + supported = true; + break; + case ixgbe_media_type_backplane: + supported = true; + break; + case ixgbe_media_type_copper: + /* only some copper devices support flow control autoneg */ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_T3_LOM: + case IXGBE_DEV_ID_X540T: + case IXGBE_DEV_ID_X540T1: + supported = true; + break; + default: + break; + } default: - return IXGBE_ERR_FC_NOT_SUPPORTED; + break; } + + return supported; } /** @@ -114,6 +139,7 @@ static s32 ixgbe_setup_fc(struct ixgbe_hw *hw) * we link at 10G, the 1G advertisement is harmless and vice versa. */ switch (hw->phy.media_type) { + case ixgbe_media_type_fiber_fixed: case ixgbe_media_type_fiber: case ixgbe_media_type_backplane: reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); @@ -234,7 +260,7 @@ static s32 ixgbe_setup_fc(struct ixgbe_hw *hw) IXGBE_GSSR_MAC_CSR_SM); } else if ((hw->phy.media_type == ixgbe_media_type_copper) && - (ixgbe_device_supports_autoneg_fc(hw) == 0)) { + ixgbe_device_supports_autoneg_fc(hw)) { hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, reg_cu); } @@ -2380,6 +2406,7 @@ void ixgbe_fc_autoneg(struct ixgbe_hw *hw) switch (hw->phy.media_type) { /* Autoneg flow control on fiber adapters */ + case ixgbe_media_type_fiber_fixed: case ixgbe_media_type_fiber: if (speed == IXGBE_LINK_SPEED_1GB_FULL) ret_val = ixgbe_fc_autoneg_fiber(hw); @@ -2392,7 +2419,7 @@ void ixgbe_fc_autoneg(struct ixgbe_hw *hw) /* Autoneg flow control on copper adapters */ case ixgbe_media_type_copper: - if (ixgbe_device_supports_autoneg_fc(hw) == 0) + if (ixgbe_device_supports_autoneg_fc(hw)) ret_val = ixgbe_fc_autoneg_copper(hw); break; @@ -2479,42 +2506,39 @@ out: **/ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u16 mask) { - u32 gssr; + u32 gssr = 0; u32 swmask = mask; u32 fwmask = mask << 5; - s32 timeout = 200; + u32 timeout = 200; + u32 i; - while (timeout) { + for (i = 0; i < timeout; i++) { /* - * SW EEPROM semaphore bit is used for access to all - * SW_FW_SYNC/GSSR bits (not just EEPROM) + * SW NVM semaphore bit is used for access to all + * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_eeprom_semaphore(hw)) return IXGBE_ERR_SWFW_SYNC; gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); - if (!(gssr & (fwmask | swmask))) - break; - - /* - * Firmware currently using resource (fwmask) or other software - * thread currently using resource (swmask) - */ - ixgbe_release_eeprom_semaphore(hw); - usleep_range(5000, 10000); - timeout--; - } - - if (!timeout) { - hw_dbg(hw, "Driver can't access resource, SW_FW_SYNC timeout.\n"); - return IXGBE_ERR_SWFW_SYNC; + if (!(gssr & (fwmask | swmask))) { + gssr |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + ixgbe_release_eeprom_semaphore(hw); + return 0; + } else { + /* Resource is currently in use by FW or SW */ + ixgbe_release_eeprom_semaphore(hw); + usleep_range(5000, 10000); + } } - gssr |= swmask; - IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + /* If time expired clear the bits holding the lock and retry */ + if (gssr & (fwmask | swmask)) + ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); - ixgbe_release_eeprom_semaphore(hw); - return 0; + usleep_range(5000, 10000); + return IXGBE_ERR_SWFW_SYNC; } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 22eee38868f1..1315b8ac7f58 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -80,7 +80,7 @@ s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw); s32 ixgbe_enable_rx_buff_generic(struct ixgbe_hw *hw); s32 ixgbe_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval); s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw); -s32 ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw); +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw); void ixgbe_fc_autoneg(struct ixgbe_hw *hw); s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u16 mask); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 24e2e7aafda2..50c1e9b2fd80 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -355,10 +355,11 @@ static void ixgbe_get_pauseparam(struct net_device *netdev, struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - if (hw->fc.disable_fc_autoneg) - pause->autoneg = 0; - else + if (ixgbe_device_supports_autoneg_fc(hw) && + !hw->fc.disable_fc_autoneg) pause->autoneg = 1; + else + pause->autoneg = 0; if (hw->fc.current_mode == ixgbe_fc_rx_pause) { pause->rx_pause = 1; @@ -384,7 +385,7 @@ static int ixgbe_set_pauseparam(struct net_device *netdev, /* some devices do not support autoneg of link flow control */ if ((pause->autoneg == AUTONEG_ENABLE) && - (ixgbe_device_supports_autoneg_fc(hw) != 0)) + !ixgbe_device_supports_autoneg_fc(hw)) return -EINVAL; fc.disable_fc_autoneg = (pause->autoneg != AUTONEG_ENABLE); @@ -1140,11 +1141,11 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, sprintf(p, "tx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; #ifdef LL_EXTENDED_STATS - sprintf(p, "tx_q_%u_napi_yield", i); + sprintf(p, "tx_queue_%u_ll_napi_yield", i); p += ETH_GSTRING_LEN; - sprintf(p, "tx_q_%u_misses", i); + sprintf(p, "tx_queue_%u_ll_misses", i); p += ETH_GSTRING_LEN; - sprintf(p, "tx_q_%u_cleaned", i); + sprintf(p, "tx_queue_%u_ll_cleaned", i); p += ETH_GSTRING_LEN; #endif /* LL_EXTENDED_STATS */ } @@ -1154,11 +1155,11 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, sprintf(p, "rx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; #ifdef LL_EXTENDED_STATS - sprintf(p, "rx_q_%u_ll_poll_yield", i); + sprintf(p, "rx_queue_%u_ll_poll_yield", i); p += ETH_GSTRING_LEN; - sprintf(p, "rx_q_%u_misses", i); + sprintf(p, "rx_queue_%u_ll_misses", i); p += ETH_GSTRING_LEN; - sprintf(p, "rx_q_%u_cleaned", i); + sprintf(p, "rx_queue_%u_ll_cleaned", i); p += ETH_GSTRING_LEN; #endif /* LL_EXTENDED_STATS */ } @@ -2909,33 +2910,21 @@ static int ixgbe_get_module_info(struct net_device *dev, struct ixgbe_hw *hw = &adapter->hw; u32 status; u8 sff8472_rev, addr_mode; - int ret_val = 0; bool page_swap = false; - /* avoid concurent i2c reads */ - while (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) - msleep(100); - - /* used by the service task */ - set_bit(__IXGBE_READ_I2C, &adapter->state); - /* Check whether we support SFF-8472 or not */ status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_SFF_8472_COMP, &sff8472_rev); - if (status != 0) { - ret_val = -EIO; - goto err_out; - } + if (status != 0) + return -EIO; /* addressing mode is not supported */ status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_SFF_8472_SWAP, &addr_mode); - if (status != 0) { - ret_val = -EIO; - goto err_out; - } + if (status != 0) + return -EIO; if (addr_mode & IXGBE_SFF_ADDRESSING_MODE) { e_err(drv, "Address change required to access page 0xA2, but not supported. Please report the module type to the driver maintainers.\n"); @@ -2952,9 +2941,7 @@ static int ixgbe_get_module_info(struct net_device *dev, modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; } -err_out: - clear_bit(__IXGBE_READ_I2C, &adapter->state); - return ret_val; + return 0; } static int ixgbe_get_module_eeprom(struct net_device *dev, @@ -2968,48 +2955,25 @@ static int ixgbe_get_module_eeprom(struct net_device *dev, int i = 0; int ret_val = 0; - /* ixgbe_get_module_info is called before this function in all - * cases, so we do not need any checks we already do above, - * and can trust ee->len to be a known value. - */ + if (ee->len == 0) + return -EINVAL; + + for (i = ee->offset; i < ee->len; i++) { + /* I2C reads can take long time */ + if (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + return -EBUSY; - while (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) - msleep(100); - set_bit(__IXGBE_READ_I2C, &adapter->state); + if (i < ETH_MODULE_SFF_8079_LEN) + status = hw->phy.ops.read_i2c_eeprom(hw, i, &databyte); + else + status = hw->phy.ops.read_i2c_sff8472(hw, i, &databyte); - /* Read the first block, SFF-8079 */ - for (i = 0; i < ETH_MODULE_SFF_8079_LEN; i++) { - status = hw->phy.ops.read_i2c_eeprom(hw, i, &databyte); - if (status != 0) { - /* Error occured while reading module */ + if (status != 0) ret_val = -EIO; - goto err_out; - } - data[i] = databyte; - } - /* If the second block is requested, check if SFF-8472 is supported. */ - if (ee->len == ETH_MODULE_SFF_8472_LEN) { - if (data[IXGBE_SFF_SFF_8472_COMP] == IXGBE_SFF_SFF_8472_UNSUP) - return -EOPNOTSUPP; - - /* Read the second block, SFF-8472 */ - for (i = ETH_MODULE_SFF_8079_LEN; - i < ETH_MODULE_SFF_8472_LEN; i++) { - status = hw->phy.ops.read_i2c_sff8472(hw, - i - ETH_MODULE_SFF_8079_LEN, &databyte); - if (status != 0) { - /* Error occured while reading module */ - ret_val = -EIO; - goto err_out; - } - data[i] = databyte; - } + data[i - ee->offset] = databyte; } -err_out: - clear_bit(__IXGBE_READ_I2C, &adapter->state); - return ret_val; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index be4b1fb3d0d2..128d6b885326 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -63,7 +63,7 @@ char ixgbe_default_device_descr[] = static char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; #endif -#define DRV_VERSION "3.13.10-k" +#define DRV_VERSION "3.15.1-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = "Copyright (c) 1999-2013 Intel Corporation."; @@ -109,6 +109,7 @@ static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 }, @@ -195,6 +196,86 @@ static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) return 0; } +/** + * ixgbe_check_from_parent - Determine whether PCIe info should come from parent + * @hw: hw specific details + * + * This function is used by probe to determine whether a device's PCI-Express + * bandwidth details should be gathered from the parent bus instead of from the + * device. Used to ensure that various locations all have the correct device ID + * checks. + */ +static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +{ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_SFP_SF_QP: + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + return true; + default: + return false; + } +} + +static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, + int expected_gts) +{ + int max_gts = 0; + enum pci_bus_speed speed = PCI_SPEED_UNKNOWN; + enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN; + struct pci_dev *pdev; + + /* determine whether to use the the parent device + */ + if (ixgbe_pcie_from_parent(&adapter->hw)) + pdev = adapter->pdev->bus->parent->self; + else + pdev = adapter->pdev; + + if (pcie_get_minimum_link(pdev, &speed, &width) || + speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) { + e_dev_warn("Unable to determine PCI Express bandwidth.\n"); + return; + } + + switch (speed) { + case PCIE_SPEED_2_5GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 2 * width; + break; + case PCIE_SPEED_5_0GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 4 * width; + break; + case PCIE_SPEED_8_0GT: + /* 128b/130b encoding only reduces throughput by 1% */ + max_gts = 8 * width; + break; + default: + e_dev_warn("Unable to determine PCI Express bandwidth.\n"); + return; + } + + e_dev_info("PCI Express bandwidth of %dGT/s available\n", + max_gts); + e_dev_info("(Speed:%s, Width: x%d, Encoding Loss:%s)\n", + (speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : + speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : + speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : + "Unknown"), + width, + (speed == PCIE_SPEED_2_5GT ? "20%" : + speed == PCIE_SPEED_5_0GT ? "20%" : + speed == PCIE_SPEED_8_0GT ? "N/a" : + "Unknown")); + + if (max_gts < expected_gts) { + e_dev_warn("This is not sufficient for optimal performance of this card.\n"); + e_dev_warn("For optimal performance, at least %dGT/s of bandwidth is required.\n", + expected_gts); + e_dev_warn("A slot with more lanes and/or higher speed is suggested.\n"); + } +} + static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter) { if (!test_bit(__IXGBE_DOWN, &adapter->state) && @@ -3724,8 +3805,15 @@ void ixgbe_set_rx_mode(struct net_device *netdev) hw->addr_ctrl.user_set_promisc = true; fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); vmolr |= (IXGBE_VMOLR_ROPE | IXGBE_VMOLR_MPE); - /* don't hardware filter vlans in promisc mode */ - ixgbe_vlan_filter_disable(adapter); + /* Only disable hardware filter vlans in promiscuous mode + * if SR-IOV and VMDQ are disabled - otherwise ensure + * that hardware VLAN filters remain enabled. + */ + if (!(adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED))) + ixgbe_vlan_filter_disable(adapter); + else + ixgbe_vlan_filter_enable(adapter); } else { if (netdev->flags & IFF_ALLMULTI) { fctrl |= IXGBE_FCTRL_MPE; @@ -4352,7 +4440,7 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) if (hw->mac.san_mac_rar_index) hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); - if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) ixgbe_ptp_reset(adapter); } @@ -4714,8 +4802,7 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter) ixgbe_pbthresh_setup(adapter); hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE; hw->fc.send_xon = true; - hw->fc.disable_fc_autoneg = - (ixgbe_device_supports_autoneg_fc(hw) == 0) ? false : true; + hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw); #ifdef CONFIG_PCI_IOV /* assign number of SR-IOV VFs */ @@ -5681,7 +5768,7 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) adapter->last_rx_ptp_check = jiffies; - if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) ixgbe_ptp_start_cyclecounter(adapter); e_info(drv, "NIC Link is Up %s, Flow Control: %s\n", @@ -5727,7 +5814,7 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB) adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; - if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) ixgbe_ptp_start_cyclecounter(adapter); e_info(drv, "NIC Link is Down\n"); @@ -5826,10 +5913,6 @@ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) !(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET)) return; - /* concurent i2c reads are not supported */ - if (test_bit(__IXGBE_READ_I2C, &adapter->state)) - return; - /* someone else is in init, wait until next service event */ if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) return; @@ -6038,7 +6121,7 @@ static void ixgbe_service_task(struct work_struct *work) ixgbe_fdir_reinit_subtask(adapter); ixgbe_check_hang_subtask(adapter); - if (adapter->flags2 & IXGBE_FLAG2_PTP_ENABLED) { + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) { ixgbe_ptp_overflow_check(adapter); ixgbe_ptp_rx_hang(adapter); } @@ -7247,6 +7330,42 @@ static const struct net_device_ops ixgbe_netdev_ops = { }; /** + * ixgbe_enumerate_functions - Get the number of ports this device has + * @adapter: adapter structure + * + * This function enumerates the phsyical functions co-located on a single slot, + * in order to determine how many ports a device has. This is most useful in + * determining the required GT/s of PCIe bandwidth necessary for optimal + * performance. + **/ +static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct list_head *entry; + int physfns = 0; + + /* Some cards can not use the generic count PCIe functions method, and + * so must be hardcoded to the correct value. + */ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_SFP_SF_QP: + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + physfns = 4; + break; + default: + list_for_each(entry, &adapter->pdev->bus_list) { + struct pci_dev *pdev = + list_entry(entry, struct pci_dev, bus_list); + /* don't count virtual functions */ + if (!pdev->is_virtfn) + physfns++; + } + } + + return physfns; +} + +/** * ixgbe_wol_supported - Check whether device supports WoL * @hw: hw specific details * @device_id: the device ID @@ -7328,7 +7447,7 @@ static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; static int cards_found; - int i, err, pci_using_dac; + int i, err, pci_using_dac, expected_gts; unsigned int indices = MAX_TX_QUEUES; u8 part_str[IXGBE_PBANUM_LENGTH]; #ifdef IXGBE_FCOE @@ -7617,7 +7736,7 @@ skip_sriov: /* pick up the PCI bus settings for reporting later */ hw->mac.ops.get_bus_info(hw); - if (hw->device_id == IXGBE_DEV_ID_82599_SFP_SF_QP) + if (ixgbe_pcie_from_parent(hw)) ixgbe_get_parent_bus_info(adapter); /* print bus type/speed/width info */ @@ -7643,12 +7762,20 @@ skip_sriov: e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n", hw->mac.type, hw->phy.type, part_str); - if (hw->bus.width <= ixgbe_bus_width_pcie_x4) { - e_dev_warn("PCI-Express bandwidth available for this card is " - "not sufficient for optimal performance.\n"); - e_dev_warn("For optimal performance a x8 PCI-Express slot " - "is required.\n"); + /* calculate the expected PCIe bandwidth required for optimal + * performance. Note that some older parts will never have enough + * bandwidth due to being older generation PCIe parts. We clamp these + * parts to ensure no warning is displayed if it can't be fixed. + */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + expected_gts = min(ixgbe_enumerate_functions(adapter) * 10, 16); + break; + default: + expected_gts = ixgbe_enumerate_functions(adapter) * 10; + break; } + ixgbe_check_minimum_link(adapter, expected_gts); /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index e5691ccbce9d..369eef526bc1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -204,7 +204,83 @@ out: } /** + * ixgbe_read_phy_mdi - Reads a value from a specified PHY register without + * the SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit address of PHY register to read + * @phy_data: Pointer to read data from PHY register + **/ +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, + u16 *phy_data) +{ + u32 i, data, command; + + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address command did not complete.\n"); + return IXGBE_ERR_PHY; + } + + /* Address cycle complete, setup and write the read + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY read command didn't complete\n"); + return IXGBE_ERR_PHY; + } + + /* Read operation is complete. Get the data + * from MSRWD + */ + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data >>= IXGBE_MSRWD_READ_DATA_SHIFT; + *phy_data = (u16)(data); + + return 0; +} + +/** * ixgbe_read_phy_reg_generic - Reads a value from a specified PHY register + * using the SWFW lock - this function is needed in most cases * @hw: pointer to hardware structure * @reg_addr: 32 bit address of PHY register to read * @phy_data: Pointer to read data from PHY register @@ -212,10 +288,7 @@ out: s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 *phy_data) { - u32 command; - u32 i; - u32 data; - s32 status = 0; + s32 status; u16 gssr; if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) @@ -223,86 +296,93 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, else gssr = IXGBE_GSSR_PHY0_SM; - if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_read_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { status = IXGBE_ERR_SWFW_SYNC; + } - if (status == 0) { - /* Setup and write the address cycle command */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + return status; +} - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); +/** + * ixgbe_write_phy_reg_mdi - Writes a value to specified PHY register + * without SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 5 bit device type + * @phy_data: Data to write to the PHY register + **/ +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + u32 i, command; - /* - * Check every 10 usec to see if the address cycle completed. - * The MDI Command bit will clear when the operation is - * complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); + /* Put the data in the MDI single read and write data register*/ + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)phy_data); - command = IXGBE_READ_REG(hw, IXGBE_MSCA); + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address command did not complete.\n"); - status = IXGBE_ERR_PHY; - } + /* + * Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); - if (status == 0) { - /* - * Address cycle complete, setup and write the read - * command - */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << - IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle - * completed. The MDI Command bit will clear when the - * operation is complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); - - command = IXGBE_READ_REG(hw, IXGBE_MSCA); - - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY read command didn't complete\n"); - status = IXGBE_ERR_PHY; - } else { - /* - * Read operation is complete. Get the data - * from MSRWD - */ - data = IXGBE_READ_REG(hw, IXGBE_MSRWD); - data >>= IXGBE_MSRWD_READ_DATA_SHIFT; - *phy_data = (u16)(data); - } - } + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } - hw->mac.ops.release_swfw_sync(hw, gssr); + /* + * Address cycle complete, setup and write the write + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; } - return status; + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY write cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } + + return 0; } /** * ixgbe_write_phy_reg_generic - Writes a value to specified PHY register + * using SWFW lock- this function is needed in most cases * @hw: pointer to hardware structure * @reg_addr: 32 bit PHY register to write * @device_type: 5 bit device type @@ -311,9 +391,7 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 phy_data) { - u32 command; - u32 i; - s32 status = 0; + s32 status; u16 gssr; if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) @@ -321,74 +399,12 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, else gssr = IXGBE_GSSR_PHY0_SM; - if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) - status = IXGBE_ERR_SWFW_SYNC; - - if (status == 0) { - /* Put the data in the MDI single read and write data register*/ - IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)phy_data); - - /* Setup and write the address cycle command */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle completed. - * The MDI Command bit will clear when the operation is - * complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); - - command = IXGBE_READ_REG(hw, IXGBE_MSCA); - - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } - - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address cmd didn't complete\n"); - status = IXGBE_ERR_PHY; - } - - if (status == 0) { - /* - * Address cycle complete, setup and write the write - * command - */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << - IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle - * completed. The MDI Command bit will clear when the - * operation is complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); - - command = IXGBE_READ_REG(hw, IXGBE_MSCA); - - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } - - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address cmd didn't complete\n"); - status = IXGBE_ERR_PHY; - } - } - + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); + } else { + status = IXGBE_ERR_SWFW_SYNC; } return status; @@ -825,9 +841,35 @@ out: } /** - * ixgbe_identify_sfp_module_generic - Identifies SFP modules + * ixgbe_identify_module_generic - Identifies module type * @hw: pointer to hardware structure * + * Determines HW type and calls appropriate function. + **/ +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) +{ + s32 status = IXGBE_ERR_SFP_NOT_PRESENT; + + switch (hw->mac.ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + status = ixgbe_identify_sfp_module_generic(hw); + break; + case ixgbe_media_type_fiber_qsfp: + status = ixgbe_identify_qsfp_module_generic(hw); + break; + default: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + status = IXGBE_ERR_SFP_NOT_PRESENT; + break; + } + + return status; +} + +/** + * ixgbe_identify_sfp_module_generic - Identifies SFP modules + * @hw: pointer to hardware structure +* * Searches for and identifies the SFP module and assigns appropriate PHY type. **/ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) @@ -1106,6 +1148,156 @@ err_read_i2c_eeprom: } /** + * ixgbe_identify_qsfp_module_generic - Identifies QSFP modules + * @hw: pointer to hardware structure + * + * Searches for and identifies the QSFP module and assigns appropriate PHY type + **/ +s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + s32 status = IXGBE_ERR_PHY_ADDR_INVALID; + u32 vendor_oui = 0; + enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; + u8 identifier = 0; + u8 comp_codes_1g = 0; + u8 comp_codes_10g = 0; + u8 oui_bytes[3] = {0, 0, 0}; + u16 enforce_sfp = 0; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + status = IXGBE_ERR_SFP_NOT_PRESENT; + goto out; + } + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER, + &identifier); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { + hw->phy.type = ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + + hw->phy.id = identifier; + + /* LAN ID is needed for sfp_type determination */ + hw->mac.ops.set_lan_id(hw); + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_10GBE_COMP, + &comp_codes_10g); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (comp_codes_10g & IXGBE_SFF_QSFP_DA_PASSIVE_CABLE) { + hw->phy.type = ixgbe_phy_qsfp_passive_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core1; + } else if (comp_codes_10g & IXGBE_SFF_QSFP_DA_ACTIVE_CABLE) { + hw->phy.type = ixgbe_phy_qsfp_active_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_da_act_lmt_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_da_act_lmt_core1; + } else if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core1; + } else { + /* unsupported module type */ + hw->phy.type = ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + + if (hw->phy.sfp_type != stored_sfp_type) + hw->phy.sfp_setup_needed = true; + + /* Determine if the QSFP+ PHY is dual speed or not. */ + hw->phy.multispeed_fiber = false; + if (((comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE)) || + ((comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE))) + hw->phy.multispeed_fiber = true; + + /* Determine PHY vendor for optical modules */ + if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0, + &oui_bytes[0]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1, + &oui_bytes[1]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2, + &oui_bytes[2]); + + if (status != 0) + goto err_read_i2c_eeprom; + + vendor_oui = + ((oui_bytes[0] << IXGBE_SFF_VENDOR_OUI_BYTE0_SHIFT) | + (oui_bytes[1] << IXGBE_SFF_VENDOR_OUI_BYTE1_SHIFT) | + (oui_bytes[2] << IXGBE_SFF_VENDOR_OUI_BYTE2_SHIFT)); + + if (vendor_oui == IXGBE_SFF_VENDOR_OUI_INTEL) + hw->phy.type = ixgbe_phy_qsfp_intel; + else + hw->phy.type = ixgbe_phy_qsfp_unknown; + + hw->mac.ops.get_device_caps(hw, &enforce_sfp); + if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP)) { + /* Make sure we're a supported PHY type */ + if (hw->phy.type == ixgbe_phy_qsfp_intel) { + status = 0; + } else { + if (hw->allow_unsupported_sfp == true) { + e_warn(hw, "WARNING: Intel (R) Network Connections are quality tested using Intel (R) Ethernet Optics. Using untested modules is not supported and may cause unstable operation or damage to the module or the adapter. Intel Corporation is not responsible for any harm caused by using untested modules.\n"); + status = 0; + } else { + hw_dbg(hw, + "QSFP module not supported\n"); + hw->phy.type = + ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + } + } + } else { + status = 0; + } + } + +out: + return status; + +err_read_i2c_eeprom: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + + return IXGBE_ERR_SFP_NOT_PRESENT; +} + +/** * ixgbe_get_sfp_init_sequence_offsets - Provides offset of PHY init sequence * @hw: pointer to hardware structure * @list_offset: offset to the SFP ID list diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 886a3431cf5b..138dadd7cf33 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -33,17 +33,25 @@ #define IXGBE_I2C_EEPROM_DEV_ADDR2 0xA2 /* EEPROM byte offsets */ -#define IXGBE_SFF_IDENTIFIER 0x0 -#define IXGBE_SFF_IDENTIFIER_SFP 0x3 -#define IXGBE_SFF_VENDOR_OUI_BYTE0 0x25 -#define IXGBE_SFF_VENDOR_OUI_BYTE1 0x26 -#define IXGBE_SFF_VENDOR_OUI_BYTE2 0x27 -#define IXGBE_SFF_1GBE_COMP_CODES 0x6 -#define IXGBE_SFF_10GBE_COMP_CODES 0x3 -#define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 -#define IXGBE_SFF_CABLE_SPEC_COMP 0x3C -#define IXGBE_SFF_SFF_8472_SWAP 0x5C -#define IXGBE_SFF_SFF_8472_COMP 0x5E +#define IXGBE_SFF_IDENTIFIER 0x0 +#define IXGBE_SFF_IDENTIFIER_SFP 0x3 +#define IXGBE_SFF_VENDOR_OUI_BYTE0 0x25 +#define IXGBE_SFF_VENDOR_OUI_BYTE1 0x26 +#define IXGBE_SFF_VENDOR_OUI_BYTE2 0x27 +#define IXGBE_SFF_1GBE_COMP_CODES 0x6 +#define IXGBE_SFF_10GBE_COMP_CODES 0x3 +#define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 +#define IXGBE_SFF_CABLE_SPEC_COMP 0x3C +#define IXGBE_SFF_SFF_8472_SWAP 0x5C +#define IXGBE_SFF_SFF_8472_COMP 0x5E +#define IXGBE_SFF_SFF_8472_OSCB 0x6E +#define IXGBE_SFF_SFF_8472_ESCB 0x76 +#define IXGBE_SFF_IDENTIFIER_QSFP_PLUS 0xD +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0 0xA5 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1 0xA6 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2 0xA7 +#define IXGBE_SFF_QSFP_10GBE_COMP 0x83 +#define IXGBE_SFF_QSFP_1GBE_COMP 0x86 /* Bitmasks */ #define IXGBE_SFF_DA_PASSIVE_CABLE 0x4 @@ -54,7 +62,12 @@ #define IXGBE_SFF_1GBASET_CAPABLE 0x8 #define IXGBE_SFF_10GBASESR_CAPABLE 0x10 #define IXGBE_SFF_10GBASELR_CAPABLE 0x20 +#define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0 #define IXGBE_SFF_ADDRESSING_MODE 0x4 +#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1 +#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8 #define IXGBE_I2C_EEPROM_READ_MASK 0x100 #define IXGBE_I2C_EEPROM_STATUS_MASK 0x3 #define IXGBE_I2C_EEPROM_STATUS_NO_OPERATION 0x0 @@ -102,6 +115,10 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 *phy_data); s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, u16 phy_data); +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data); +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data); s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw); s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, ixgbe_link_speed speed, @@ -121,7 +138,9 @@ s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw, u16 *firmware_version); s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw); +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw); s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); +s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw); s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, u16 *list_offset, u16 *data_offset); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 331987d6815c..5184e2a1a7d8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -885,8 +885,8 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) ixgbe_ptp_reset(adapter); - /* set the flag that PTP has been enabled */ - adapter->flags2 |= IXGBE_FLAG2_PTP_ENABLED; + /* enter the IXGBE_PTP_RUNNING state */ + set_bit(__IXGBE_PTP_RUNNING, &adapter->state); return; } @@ -899,10 +899,12 @@ void ixgbe_ptp_init(struct ixgbe_adapter *adapter) */ void ixgbe_ptp_stop(struct ixgbe_adapter *adapter) { - /* stop the overflow check task */ - adapter->flags2 &= ~(IXGBE_FLAG2_PTP_ENABLED | - IXGBE_FLAG2_PTP_PPS_ENABLED); + /* Leave the IXGBE_PTP_RUNNING state. */ + if (!test_and_clear_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + return; + /* stop the PPS signal */ + adapter->flags2 &= ~IXGBE_FLAG2_PTP_PPS_ENABLED; ixgbe_ptp_setup_sdp(adapter); cancel_work_sync(&adapter->ptp_tx_work); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 1e7d587c4e57..73c8e73bb6e7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -173,39 +173,6 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) ixgbe_disable_sriov(adapter); } -static bool ixgbe_vfs_are_assigned(struct ixgbe_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - struct pci_dev *vfdev; - int dev_id; - - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - dev_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - dev_id = IXGBE_DEV_ID_X540_VF; - break; - default: - return false; - } - - /* loop through all the VFs to see if we own any that are assigned */ - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); - while (vfdev) { - /* if we don't own it we don't care */ - if (vfdev->is_virtfn && vfdev->physfn == pdev) { - /* if it is assigned we cannot release it */ - if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) - return true; - } - - vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); - } - - return false; -} - #endif /* #ifdef CONFIG_PCI_IOV */ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { @@ -235,7 +202,7 @@ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) * without causing issues, so just leave the hardware * available but disabled */ - if (ixgbe_vfs_are_assigned(adapter)) { + if (pci_vfs_assigned(adapter->pdev)) { e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n"); return -EPERM; } @@ -768,6 +735,29 @@ static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0; } +static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) +{ + u32 vlvf; + s32 regindex; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries */ + for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + /* Return a negative value if not found */ + if (regindex >= IXGBE_VLVF_ENTRIES) + regindex = -1; + + return regindex; +} + static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { @@ -775,6 +765,9 @@ static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, int add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; int vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); int err; + s32 reg_ndx; + u32 vlvf; + u32 bits; u8 tcs = netdev_get_num_tc(adapter->netdev); if (adapter->vfinfo[vf].pf_vlan || tcs) { @@ -790,10 +783,50 @@ static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, else if (adapter->vfinfo[vf].vlan_count) adapter->vfinfo[vf].vlan_count--; + /* in case of promiscuous mode any VLAN filter set for a VF must + * also have the PF pool added to it. + */ + if (add && adapter->netdev->flags & IFF_PROMISC) + err = ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + err = ixgbe_set_vf_vlan(adapter, add, vid, vf); if (!err && adapter->vfinfo[vf].spoofchk_enabled) hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + /* Go through all the checks to see if the VLAN filter should + * be wiped completely. + */ + if (!add && adapter->netdev->flags & IFF_PROMISC) { + reg_ndx = ixgbe_find_vlvf_entry(hw, vid); + if (reg_ndx < 0) + goto out; + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(reg_ndx)); + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + if (VMDQ_P(0) < 32) { + bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + bits &= ~(1 << VMDQ_P(0)); + bits |= IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + } else { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + bits &= ~(1 << (VMDQ_P(0) - 32)); + bits |= IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + } + + /* If the filter was removed then ensure PF pool bit + * is cleared if the PF only added itself to the pool + * because the PF is in promiscuous mode. + */ + if ((vlvf & VLAN_VID_MASK) == vid && + !test_bit(vid, adapter->active_vlans) && !bits) + ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + } + +out: + return err; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 70c6aa3d3f95..161ff18be775 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -69,6 +69,7 @@ #define IXGBE_DEV_ID_82599_LS 0x154F #define IXGBE_DEV_ID_X540T 0x1528 #define IXGBE_DEV_ID_82599_SFP_SF_QP 0x154A +#define IXGBE_DEV_ID_82599_QSFP_SF_QP 0x1558 #define IXGBE_DEV_ID_X540T1 0x1560 /* VF Device IDs */ @@ -1520,9 +1521,11 @@ enum { #define IXGBE_ESDP_SDP5 0x00000020 /* SDP5 Data Value */ #define IXGBE_ESDP_SDP6 0x00000040 /* SDP6 Data Value */ #define IXGBE_ESDP_SDP0_DIR 0x00000100 /* SDP0 IO direction */ +#define IXGBE_ESDP_SDP1_DIR 0x00000200 /* SDP1 IO direction */ #define IXGBE_ESDP_SDP4_DIR 0x00000004 /* SDP4 IO direction */ #define IXGBE_ESDP_SDP5_DIR 0x00002000 /* SDP5 IO direction */ #define IXGBE_ESDP_SDP0_NATIVE 0x00010000 /* SDP0 Native Function */ +#define IXGBE_ESDP_SDP1_NATIVE 0x00020000 /* SDP1 IO mode */ /* LEDCTL Bit Masks */ #define IXGBE_LED_IVRT_BASE 0x00000040 @@ -2582,6 +2585,10 @@ enum ixgbe_phy_type { ixgbe_phy_sfp_ftl_active, ixgbe_phy_sfp_unknown, ixgbe_phy_sfp_intel, + ixgbe_phy_qsfp_passive_unknown, + ixgbe_phy_qsfp_active_unknown, + ixgbe_phy_qsfp_intel, + ixgbe_phy_qsfp_unknown, ixgbe_phy_sfp_unsupported, ixgbe_phy_generic }; @@ -2622,6 +2629,8 @@ enum ixgbe_sfp_type { enum ixgbe_media_type { ixgbe_media_type_unknown = 0, ixgbe_media_type_fiber, + ixgbe_media_type_fiber_fixed, + ixgbe_media_type_fiber_qsfp, ixgbe_media_type_fiber_lco, ixgbe_media_type_copper, ixgbe_media_type_backplane, @@ -2885,6 +2894,8 @@ struct ixgbe_phy_operations { s32 (*reset)(struct ixgbe_hw *); s32 (*read_reg)(struct ixgbe_hw *, u32, u32, u16 *); s32 (*write_reg)(struct ixgbe_hw *, u32, u32, u16); + s32 (*read_reg_mdi)(struct ixgbe_hw *, u32, u32, u16 *); + s32 (*write_reg_mdi)(struct ixgbe_hw *, u32, u32, u16); s32 (*setup_link)(struct ixgbe_hw *); s32 (*setup_link_speed)(struct ixgbe_hw *, ixgbe_link_speed, bool); s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *); @@ -2953,6 +2964,7 @@ struct ixgbe_phy_info { bool smart_speed_active; bool multispeed_fiber; bool reset_if_overtemp; + bool qsfp_shared_i2c_bus; }; #include "ixgbe_mbx.h" diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index b017818bccae..2777c70c603b 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -79,10 +79,10 @@ #define MVNETA_MAC_ADDR_HIGH 0x2418 #define MVNETA_SDMA_CONFIG 0x241c #define MVNETA_SDMA_BRST_SIZE_16 4 -#define MVNETA_NO_DESC_SWAP 0x0 #define MVNETA_RX_BRST_SZ_MASK(burst) ((burst) << 1) #define MVNETA_RX_NO_DATA_SWAP BIT(4) #define MVNETA_TX_NO_DATA_SWAP BIT(5) +#define MVNETA_DESC_SWAP BIT(6) #define MVNETA_TX_BRST_SZ_MASK(burst) ((burst) << 22) #define MVNETA_PORT_STATUS 0x2444 #define MVNETA_TX_IN_PRGRS BIT(1) @@ -264,8 +264,7 @@ struct mvneta_port { * layout of the transmit and reception DMA descriptors, and their * layout is therefore defined by the hardware design */ -struct mvneta_tx_desc { - u32 command; /* Options used by HW for packet transmitting.*/ + #define MVNETA_TX_L3_OFF_SHIFT 0 #define MVNETA_TX_IP_HLEN_SHIFT 8 #define MVNETA_TX_L4_UDP BIT(16) @@ -280,15 +279,6 @@ struct mvneta_tx_desc { #define MVNETA_TX_L4_CSUM_FULL BIT(30) #define MVNETA_TX_L4_CSUM_NOT BIT(31) - u16 reserverd1; /* csum_l4 (for future use) */ - u16 data_size; /* Data size of transmitted packet in bytes */ - u32 buf_phys_addr; /* Physical addr of transmitted buffer */ - u32 reserved2; /* hw_cmd - (for future use, PMT) */ - u32 reserved3[4]; /* Reserved - (for future use) */ -}; - -struct mvneta_rx_desc { - u32 status; /* Info about received packet */ #define MVNETA_RXD_ERR_CRC 0x0 #define MVNETA_RXD_ERR_SUMMARY BIT(16) #define MVNETA_RXD_ERR_OVERRUN BIT(17) @@ -299,16 +289,57 @@ struct mvneta_rx_desc { #define MVNETA_RXD_FIRST_LAST_DESC (BIT(26) | BIT(27)) #define MVNETA_RXD_L4_CSUM_OK BIT(30) +#if defined(__LITTLE_ENDIAN) +struct mvneta_tx_desc { + u32 command; /* Options used by HW for packet transmitting.*/ + u16 reserverd1; /* csum_l4 (for future use) */ + u16 data_size; /* Data size of transmitted packet in bytes */ + u32 buf_phys_addr; /* Physical addr of transmitted buffer */ + u32 reserved2; /* hw_cmd - (for future use, PMT) */ + u32 reserved3[4]; /* Reserved - (for future use) */ +}; + +struct mvneta_rx_desc { + u32 status; /* Info about received packet */ u16 reserved1; /* pnc_info - (for future use, PnC) */ u16 data_size; /* Size of received packet in bytes */ + u32 buf_phys_addr; /* Physical address of the buffer */ u32 reserved2; /* pnc_flow_id (for future use, PnC) */ + u32 buf_cookie; /* cookie for access to RX buffer in rx path */ u16 reserved3; /* prefetch_cmd, for future use */ u16 reserved4; /* csum_l4 - (for future use, PnC) */ + + u32 reserved5; /* pnc_extra PnC (for future use, PnC) */ + u32 reserved6; /* hw_cmd (for future use, PnC and HWF) */ +}; +#else +struct mvneta_tx_desc { + u16 data_size; /* Data size of transmitted packet in bytes */ + u16 reserverd1; /* csum_l4 (for future use) */ + u32 command; /* Options used by HW for packet transmitting.*/ + u32 reserved2; /* hw_cmd - (for future use, PMT) */ + u32 buf_phys_addr; /* Physical addr of transmitted buffer */ + u32 reserved3[4]; /* Reserved - (for future use) */ +}; + +struct mvneta_rx_desc { + u16 data_size; /* Size of received packet in bytes */ + u16 reserved1; /* pnc_info - (for future use, PnC) */ + u32 status; /* Info about received packet */ + + u32 reserved2; /* pnc_flow_id (for future use, PnC) */ + u32 buf_phys_addr; /* Physical address of the buffer */ + + u16 reserved4; /* csum_l4 - (for future use, PnC) */ + u16 reserved3; /* prefetch_cmd, for future use */ + u32 buf_cookie; /* cookie for access to RX buffer in rx path */ + u32 reserved5; /* pnc_extra PnC (for future use, PnC) */ u32 reserved6; /* hw_cmd (for future use, PnC and HWF) */ }; +#endif struct mvneta_tx_queue { /* Number of this TX queue, in the range 0-7 */ @@ -908,9 +939,11 @@ static void mvneta_defaults_set(struct mvneta_port *pp) /* Default burst size */ val |= MVNETA_TX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16); val |= MVNETA_RX_BRST_SZ_MASK(MVNETA_SDMA_BRST_SIZE_16); + val |= MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP; - val |= (MVNETA_RX_NO_DATA_SWAP | MVNETA_TX_NO_DATA_SWAP | - MVNETA_NO_DESC_SWAP); +#if defined(__BIG_ENDIAN) + val |= MVNETA_DESC_SWAP; +#endif /* Assign port SDMA configuration */ mvreg_write(pp, MVNETA_SDMA_CONFIG, val); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 299d0184f983..141322c31ae9 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -809,6 +809,15 @@ int MLX4_CMD_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave, return -EPERM; } +int MLX4_CMD_GET_OP_REQ_wrapper(struct mlx4_dev *dev, int slave, + struct mlx4_vhcr *vhcr, + struct mlx4_cmd_mailbox *inbox, + struct mlx4_cmd_mailbox *outbox, + struct mlx4_cmd_info *cmd) +{ + return -EPERM; +} + int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave, struct mlx4_vhcr *vhcr, struct mlx4_cmd_mailbox *inbox, @@ -1252,6 +1261,15 @@ static struct mlx4_cmd_info cmd_info[] = { .wrapper = MLX4_CMD_UPDATE_QP_wrapper }, { + .opcode = MLX4_CMD_GET_OP_REQ, + .has_inbox = false, + .has_outbox = false, + .out_is_imm = false, + .encode_slave_id = false, + .verify = NULL, + .wrapper = MLX4_CMD_GET_OP_REQ_wrapper, + }, + { .opcode = MLX4_CMD_CONF_SPECIAL_QP, .has_inbox = false, .has_outbox = false, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 7c492382da09..6dcca9817888 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -191,6 +191,39 @@ void mlx4_en_deactivate_tx_ring(struct mlx4_en_priv *priv, MLX4_QP_STATE_RST, NULL, 0, 0, &ring->qp); } +static void mlx4_en_stamp_wqe(struct mlx4_en_priv *priv, + struct mlx4_en_tx_ring *ring, int index, + u8 owner) +{ + __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT)); + struct mlx4_en_tx_desc *tx_desc = ring->buf + index * TXBB_SIZE; + struct mlx4_en_tx_info *tx_info = &ring->tx_info[index]; + void *end = ring->buf + ring->buf_size; + __be32 *ptr = (__be32 *)tx_desc; + int i; + + /* Optimize the common case when there are no wraparounds */ + if (likely((void *)tx_desc + tx_info->nr_txbb * TXBB_SIZE <= end)) { + /* Stamp the freed descriptor */ + for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; + i += STAMP_STRIDE) { + *ptr = stamp; + ptr += STAMP_DWORDS; + } + } else { + /* Stamp the freed descriptor */ + for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; + i += STAMP_STRIDE) { + *ptr = stamp; + ptr += STAMP_DWORDS; + if ((void *)ptr >= end) { + ptr = ring->buf; + stamp ^= cpu_to_be32(0x80000000); + } + } + } +} + static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, struct mlx4_en_tx_ring *ring, @@ -205,8 +238,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, void *end = ring->buf + ring->buf_size; int frags = skb_shinfo(skb)->nr_frags; int i; - __be32 *ptr = (__be32 *)tx_desc; - __be32 stamp = cpu_to_be32(STAMP_VAL | (!!owner << STAMP_SHIFT)); struct skb_shared_hwtstamps hwts; if (timestamp) { @@ -232,12 +263,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, skb_frag_size(frag), PCI_DMA_TODEVICE); } } - /* Stamp the freed descriptor */ - for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) { - *ptr = stamp; - ptr += STAMP_DWORDS; - } - } else { if (!tx_info->inl) { if ((void *) data >= end) { @@ -263,16 +288,6 @@ static u32 mlx4_en_free_tx_desc(struct mlx4_en_priv *priv, ++data; } } - /* Stamp the freed descriptor */ - for (i = 0; i < tx_info->nr_txbb * TXBB_SIZE; i += STAMP_STRIDE) { - *ptr = stamp; - ptr += STAMP_DWORDS; - if ((void *) ptr >= end) { - ptr = ring->buf; - stamp ^= cpu_to_be32(0x80000000); - } - } - } dev_kfree_skb_any(skb); return tx_info->nr_txbb; @@ -318,8 +333,9 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) struct mlx4_en_tx_ring *ring = &priv->tx_ring[cq->ring]; struct mlx4_cqe *cqe; u16 index; - u16 new_index, ring_index; + u16 new_index, ring_index, stamp_index; u32 txbbs_skipped = 0; + u32 txbbs_stamp = 0; u32 cons_index = mcq->cons_index; int size = cq->size; u32 size_mask = ring->size_mask; @@ -335,6 +351,7 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) index = cons_index & size_mask; cqe = &buf[(index << factor) + factor]; ring_index = ring->cons & size_mask; + stamp_index = ring_index; /* Process all completed CQEs */ while (XNOR(cqe->owner_sr_opcode & MLX4_CQE_OWNER_MASK, @@ -359,6 +376,12 @@ static void mlx4_en_process_tx_cq(struct net_device *dev, struct mlx4_en_cq *cq) priv, ring, ring_index, !!((ring->cons + txbbs_skipped) & ring->size), timestamp); + + mlx4_en_stamp_wqe(priv, ring, stamp_index, + !!((ring->cons + txbbs_stamp) & + ring->size)); + stamp_index = ring_index; + txbbs_stamp = txbbs_skipped; packets++; bytes += ring->tx_info[ring_index].nr_bytes; } while (ring_index != new_index); diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index 7e042869ef0c..0416c5b3b35c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -79,6 +79,7 @@ enum { (1ull << MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE) | \ (1ull << MLX4_EVENT_TYPE_SRQ_LIMIT) | \ (1ull << MLX4_EVENT_TYPE_CMD) | \ + (1ull << MLX4_EVENT_TYPE_OP_REQUIRED) | \ (1ull << MLX4_EVENT_TYPE_COMM_CHANNEL) | \ (1ull << MLX4_EVENT_TYPE_FLR_EVENT) | \ (1ull << MLX4_EVENT_TYPE_FATAL_WARNING)) @@ -629,6 +630,14 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq) mlx4_warn(dev, "EQ overrun on EQN %d\n", eq->eqn); break; + case MLX4_EVENT_TYPE_OP_REQUIRED: + atomic_inc(&priv->opreq_count); + /* FW commands can't be executed from interrupt context + * working in deferred task + */ + queue_work(mlx4_wq, &priv->opreq_task); + break; + case MLX4_EVENT_TYPE_COMM_CHANNEL: if (!mlx4_is_master(dev)) { mlx4_warn(dev, "Received comm channel event " diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 6fc6dabc78d5..0d63daa2f422 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -1696,3 +1696,107 @@ int mlx4_wol_write(struct mlx4_dev *dev, u64 config, int port) MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE); } EXPORT_SYMBOL_GPL(mlx4_wol_write); + +enum { + ADD_TO_MCG = 0x26, +}; + + +void mlx4_opreq_action(struct work_struct *work) +{ + struct mlx4_priv *priv = container_of(work, struct mlx4_priv, + opreq_task); + struct mlx4_dev *dev = &priv->dev; + int num_tasks = atomic_read(&priv->opreq_count); + struct mlx4_cmd_mailbox *mailbox; + struct mlx4_mgm *mgm; + u32 *outbox; + u32 modifier; + u16 token; + u16 type_m; + u16 type; + int err; + u32 num_qps; + struct mlx4_qp qp; + int i; + u8 rem_mcg; + u8 prot; + +#define GET_OP_REQ_MODIFIER_OFFSET 0x08 +#define GET_OP_REQ_TOKEN_OFFSET 0x14 +#define GET_OP_REQ_TYPE_OFFSET 0x1a +#define GET_OP_REQ_DATA_OFFSET 0x20 + + mailbox = mlx4_alloc_cmd_mailbox(dev); + if (IS_ERR(mailbox)) { + mlx4_err(dev, "Failed to allocate mailbox for GET_OP_REQ\n"); + return; + } + outbox = mailbox->buf; + + while (num_tasks) { + err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, + MLX4_CMD_GET_OP_REQ, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + if (err) { + mlx4_err(dev, "Failed to retreive required operation: %d\n", + err); + return; + } + MLX4_GET(modifier, outbox, GET_OP_REQ_MODIFIER_OFFSET); + MLX4_GET(token, outbox, GET_OP_REQ_TOKEN_OFFSET); + MLX4_GET(type, outbox, GET_OP_REQ_TYPE_OFFSET); + type_m = type >> 12; + type &= 0xfff; + + switch (type) { + case ADD_TO_MCG: + if (dev->caps.steering_mode == + MLX4_STEERING_MODE_DEVICE_MANAGED) { + mlx4_warn(dev, "ADD MCG operation is not supported in DEVICE_MANAGED steering mode\n"); + err = EPERM; + break; + } + mgm = (struct mlx4_mgm *)((u8 *)(outbox) + + GET_OP_REQ_DATA_OFFSET); + num_qps = be32_to_cpu(mgm->members_count) & + MGM_QPN_MASK; + rem_mcg = ((u8 *)(&mgm->members_count))[0] & 1; + prot = ((u8 *)(&mgm->members_count))[0] >> 6; + + for (i = 0; i < num_qps; i++) { + qp.qpn = be32_to_cpu(mgm->qp[i]); + if (rem_mcg) + err = mlx4_multicast_detach(dev, &qp, + mgm->gid, + prot, 0); + else + err = mlx4_multicast_attach(dev, &qp, + mgm->gid, + mgm->gid[5] + , 0, prot, + NULL); + if (err) + break; + } + break; + default: + mlx4_warn(dev, "Bad type for required operation\n"); + err = EINVAL; + break; + } + err = mlx4_cmd(dev, 0, ((u32) err | cpu_to_be32(token) << 16), + 1, MLX4_CMD_GET_OP_REQ, MLX4_CMD_TIME_CLASS_A, + MLX4_CMD_NATIVE); + if (err) { + mlx4_err(dev, "Failed to acknowledge required request: %d\n", + err); + goto out; + } + memset(outbox, 0, 0xffc); + num_tasks = atomic_dec_return(&priv->opreq_count); + } + +out: + mlx4_free_cmd_mailbox(dev, mailbox); +} diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h index fdf41665a059..a0a368b7c939 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.h +++ b/drivers/net/ethernet/mellanox/mlx4/fw.h @@ -220,5 +220,6 @@ int mlx4_MAP_ICM_AUX(struct mlx4_dev *dev, struct mlx4_icm *icm); int mlx4_UNMAP_ICM_AUX(struct mlx4_dev *dev); int mlx4_NOP(struct mlx4_dev *dev); int mlx4_MOD_STAT_CFG(struct mlx4_dev *dev, struct mlx4_mod_stat_cfg *cfg); +void mlx4_opreq_action(struct work_struct *work); #endif /* MLX4_FW_H */ diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 36be3208786a..60c9f4f103fc 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -1692,11 +1692,19 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_xrcd_table_free; } + if (!mlx4_is_slave(dev)) { + err = mlx4_init_mcg_table(dev); + if (err) { + mlx4_err(dev, "Failed to initialize multicast group table, aborting.\n"); + goto err_mr_table_free; + } + } + err = mlx4_init_eq_table(dev); if (err) { mlx4_err(dev, "Failed to initialize " "event queue table, aborting.\n"); - goto err_mr_table_free; + goto err_mcg_table_free; } err = mlx4_cmd_use_events(dev); @@ -1746,19 +1754,10 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_srq_table_free; } - if (!mlx4_is_slave(dev)) { - err = mlx4_init_mcg_table(dev); - if (err) { - mlx4_err(dev, "Failed to initialize " - "multicast group table, aborting.\n"); - goto err_qp_table_free; - } - } - err = mlx4_init_counters_table(dev); if (err && err != -ENOENT) { mlx4_err(dev, "Failed to initialize counters table, aborting.\n"); - goto err_mcg_table_free; + goto err_qp_table_free; } if (!mlx4_is_slave(dev)) { @@ -1803,9 +1802,6 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) err_counters_table_free: mlx4_cleanup_counters_table(dev); -err_mcg_table_free: - mlx4_cleanup_mcg_table(dev); - err_qp_table_free: mlx4_cleanup_qp_table(dev); @@ -1821,6 +1817,10 @@ err_cmd_poll: err_eq_table_free: mlx4_cleanup_eq_table(dev); +err_mcg_table_free: + if (!mlx4_is_slave(dev)) + mlx4_cleanup_mcg_table(dev); + err_mr_table_free: mlx4_cleanup_mr_table(dev); @@ -2197,6 +2197,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) } } + atomic_set(&priv->opreq_count, 0); + INIT_WORK(&priv->opreq_task, mlx4_opreq_action); + /* * Now reset the HCA before we touch the PCI capabilities or * attempt a firmware command, since a boot ROM may have left @@ -2315,12 +2318,12 @@ err_port: mlx4_cleanup_port_info(&priv->port[port]); mlx4_cleanup_counters_table(dev); - mlx4_cleanup_mcg_table(dev); mlx4_cleanup_qp_table(dev); mlx4_cleanup_srq_table(dev); mlx4_cleanup_cq_table(dev); mlx4_cmd_use_polling(dev); mlx4_cleanup_eq_table(dev); + mlx4_cleanup_mcg_table(dev); mlx4_cleanup_mr_table(dev); mlx4_cleanup_xrcd_table(dev); mlx4_cleanup_pd_table(dev); @@ -2403,12 +2406,12 @@ static void mlx4_remove_one(struct pci_dev *pdev) RES_TR_FREE_SLAVES_ONLY); mlx4_cleanup_counters_table(dev); - mlx4_cleanup_mcg_table(dev); mlx4_cleanup_qp_table(dev); mlx4_cleanup_srq_table(dev); mlx4_cleanup_cq_table(dev); mlx4_cmd_use_polling(dev); mlx4_cleanup_eq_table(dev); + mlx4_cleanup_mcg_table(dev); mlx4_cleanup_mr_table(dev); mlx4_cleanup_xrcd_table(dev); mlx4_cleanup_pd_table(dev); diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index f3e804f2a35f..55f6245efb6c 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -39,19 +39,8 @@ #include "mlx4.h" -#define MGM_QPN_MASK 0x00FFFFFF -#define MGM_BLCK_LB_BIT 30 - static const u8 zero_gid[16]; /* automatically initialized to 0 */ -struct mlx4_mgm { - __be32 next_gid_index; - __be32 members_count; - u32 reserved[2]; - u8 gid[16]; - __be32 qp[MLX4_MAX_QP_PER_MGM]; -}; - int mlx4_get_mgm_entry_size(struct mlx4_dev *dev) { return 1 << dev->oper_log_mgm_entry_size; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 17d9277e33ef..348bb8c7d9a7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -554,6 +554,17 @@ struct mlx4_mfunc { struct mlx4_mfunc_master_ctx master; }; +#define MGM_QPN_MASK 0x00FFFFFF +#define MGM_BLCK_LB_BIT 30 + +struct mlx4_mgm { + __be32 next_gid_index; + __be32 members_count; + u32 reserved[2]; + u8 gid[16]; + __be32 qp[MLX4_MAX_QP_PER_MGM]; +}; + struct mlx4_cmd { struct pci_pool *pool; void __iomem *hcr; @@ -802,6 +813,8 @@ struct mlx4_priv { u8 virt2phys_pkey[MLX4_MFUNC_MAX][MLX4_MAX_PORTS][MLX4_MAX_PORT_PKEYS]; __be64 slave_node_guids[MLX4_MFUNC_MAX]; + atomic_t opreq_count; + struct work_struct opreq_task; }; static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev) diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 967bae8b85c5..d4cdf4dc4bc4 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -244,7 +244,7 @@ struct myri10ge_priv { int fw_ver_minor; int fw_ver_tiny; int adopted_rx_filter_bug; - u8 mac_addr[6]; /* eeprom mac address */ + u8 mac_addr[ETH_ALEN]; /* eeprom mac address */ unsigned long serial_number; int vendor_specific_offset; int fw_multicast_support; diff --git a/drivers/net/ethernet/nuvoton/w90p910_ether.c b/drivers/net/ethernet/nuvoton/w90p910_ether.c index e88bdb1aa669..dcfe58fa3b8a 100644 --- a/drivers/net/ethernet/nuvoton/w90p910_ether.c +++ b/drivers/net/ethernet/nuvoton/w90p910_ether.c @@ -922,7 +922,7 @@ static void __init get_mac_address(struct net_device *dev) { struct w90p910_ether *ether = netdev_priv(dev); struct platform_device *pdev; - char addr[6]; + char addr[ETH_ALEN]; pdev = ether->pdev; @@ -934,7 +934,7 @@ static void __init get_mac_address(struct net_device *dev) addr[5] = 0xa8; if (is_valid_ether_addr(addr)) - memcpy(dev->dev_addr, &addr, 0x06); + memcpy(dev->dev_addr, &addr, ETH_ALEN); else dev_err(&pdev->dev, "invalid mac address\n"); } diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h index 7779036690cc..6797b1075874 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h @@ -582,6 +582,19 @@ struct pch_gbe_hw_stats { }; /** + * struct pch_gbe_privdata - PCI Device ID driver data + * @phy_tx_clk_delay: Bool, configure the PHY TX delay in software + * @phy_disable_hibernate: Bool, disable PHY hibernation + * @platform_init: Platform initialization callback, called from + * probe, prior to PHY initialization. + */ +struct pch_gbe_privdata { + bool phy_tx_clk_delay; + bool phy_disable_hibernate; + int (*platform_init)(struct pci_dev *pdev); +}; + +/** * struct pch_gbe_adapter - board specific private data structure * @stats_lock: Spinlock structure for status * @ethtool_lock: Spinlock structure for ethtool @@ -604,6 +617,7 @@ struct pch_gbe_hw_stats { * @rx_buffer_len: Receive buffer length * @tx_queue_len: Transmit queue length * @have_msi: PCI MSI mode flag + * @pch_gbe_privdata: PCI Device ID driver_data */ struct pch_gbe_adapter { @@ -631,6 +645,7 @@ struct pch_gbe_adapter { int hwts_tx_en; int hwts_rx_en; struct pci_dev *ptp_pdev; + struct pch_gbe_privdata *pdata; }; #define pch_gbe_hw_to_adapter(hw) container_of(hw, struct pch_gbe_adapter, hw) diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c index ab1039a95bf9..e19f1be60d5e 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c @@ -23,6 +23,7 @@ #include <linux/module.h> #include <linux/net_tstamp.h> #include <linux/ptp_classify.h> +#include <linux/gpio.h> #define DRV_VERSION "1.01" const char pch_driver_version[] = DRV_VERSION; @@ -111,6 +112,8 @@ const char pch_driver_version[] = DRV_VERSION; #define PTP_L4_MULTICAST_SA "01:00:5e:00:01:81" #define PTP_L2_MULTICAST_SA "01:1b:19:00:00:00" +#define MINNOW_PHY_RESET_GPIO 13 + static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT; static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg); @@ -682,7 +685,7 @@ static int pch_gbe_init_phy(struct pch_gbe_adapter *adapter) } adapter->hw.phy.addr = adapter->mii.phy_id; netdev_dbg(netdev, "phy_addr = %d\n", adapter->mii.phy_id); - if (addr == 32) + if (addr == PCH_GBE_PHY_REGS_LEN) return -EAGAIN; /* Selected the phy and isolate the rest */ for (addr = 0; addr < PCH_GBE_PHY_REGS_LEN; addr++) { @@ -2635,6 +2638,9 @@ static int pch_gbe_probe(struct pci_dev *pdev, adapter->pdev = pdev; adapter->hw.back = adapter; adapter->hw.reg = pcim_iomap_table(pdev)[PCH_GBE_PCI_BAR]; + adapter->pdata = (struct pch_gbe_privdata *)pci_id->driver_data; + if (adapter->pdata && adapter->pdata->platform_init) + adapter->pdata->platform_init(pdev); adapter->ptp_pdev = pci_get_bus_and_slot(adapter->pdev->bus->number, PCI_DEVFN(12, 4)); @@ -2710,6 +2716,10 @@ static int pch_gbe_probe(struct pci_dev *pdev, dev_dbg(&pdev->dev, "PCH Network Connection\n"); + /* Disable hibernation on certain platforms */ + if (adapter->pdata && adapter->pdata->phy_disable_hibernate) + pch_gbe_phy_disable_hibernate(&adapter->hw); + device_set_wakeup_enable(&pdev->dev, 1); return 0; @@ -2720,9 +2730,48 @@ err_free_netdev: return ret; } +/* The AR803X PHY on the MinnowBoard requires a physical pin to be toggled to + * ensure it is awake for probe and init. Request the line and reset the PHY. + */ +static int pch_gbe_minnow_platform_init(struct pci_dev *pdev) +{ + unsigned long flags = GPIOF_DIR_OUT | GPIOF_INIT_HIGH | GPIOF_EXPORT; + unsigned gpio = MINNOW_PHY_RESET_GPIO; + int ret; + + ret = devm_gpio_request_one(&pdev->dev, gpio, flags, + "minnow_phy_reset"); + if (ret) { + dev_err(&pdev->dev, + "ERR: Can't request PHY reset GPIO line '%d'\n", gpio); + return ret; + } + + gpio_set_value(gpio, 0); + usleep_range(1250, 1500); + gpio_set_value(gpio, 1); + usleep_range(1250, 1500); + + return ret; +} + +static struct pch_gbe_privdata pch_gbe_minnow_privdata = { + .phy_tx_clk_delay = true, + .phy_disable_hibernate = true, + .platform_init = pch_gbe_minnow_platform_init, +}; + static DEFINE_PCI_DEVICE_TABLE(pch_gbe_pcidev_id) = { {.vendor = PCI_VENDOR_ID_INTEL, .device = PCI_DEVICE_ID_INTEL_IOH1_GBE, + .subvendor = PCI_VENDOR_ID_CIRCUITCO, + .subdevice = PCI_SUBSYSTEM_ID_CIRCUITCO_MINNOWBOARD, + .class = (PCI_CLASS_NETWORK_ETHERNET << 8), + .class_mask = (0xFFFF00), + .driver_data = (kernel_ulong_t)&pch_gbe_minnow_privdata + }, + {.vendor = PCI_VENDOR_ID_INTEL, + .device = PCI_DEVICE_ID_INTEL_IOH1_GBE, .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, .class = (PCI_CLASS_NETWORK_ETHERNET << 8), diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c index da079073a6c6..8b7ff75fc8e0 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c @@ -74,6 +74,15 @@ #define MII_SR_100X_FD_CAPS 0x4000 /* 100X Full Duplex Capable */ #define MII_SR_100T4_CAPS 0x8000 /* 100T4 Capable */ +/* AR8031 PHY Debug Registers */ +#define PHY_AR803X_ID 0x00001374 +#define PHY_AR8031_DBG_OFF 0x1D +#define PHY_AR8031_DBG_DAT 0x1E +#define PHY_AR8031_SERDES 0x05 +#define PHY_AR8031_HIBERNATE 0x0B +#define PHY_AR8031_SERDES_TX_CLK_DLY 0x0100 /* TX clock delay of 2.0ns */ +#define PHY_AR8031_PS_HIB_EN 0x8000 /* Hibernate enable */ + /* Phy Id Register (word 2) */ #define PHY_REVISION_MASK 0x000F @@ -249,6 +258,51 @@ void pch_gbe_phy_set_rgmii(struct pch_gbe_hw *hw) } /** + * pch_gbe_phy_tx_clk_delay - Setup TX clock delay via the PHY + * @hw: Pointer to the HW structure + * Returns + * 0: Successful. + * -EINVAL: Invalid argument. + */ +static int pch_gbe_phy_tx_clk_delay(struct pch_gbe_hw *hw) +{ + /* The RGMII interface requires a ~2ns TX clock delay. This is typically + * done in layout with a longer trace or via PHY strapping, but can also + * be done via PHY configuration registers. + */ + struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); + u16 mii_reg; + int ret = 0; + + switch (hw->phy.id) { + case PHY_AR803X_ID: + netdev_dbg(adapter->netdev, + "Configuring AR803X PHY for 2ns TX clock delay\n"); + pch_gbe_phy_read_reg_miic(hw, PHY_AR8031_DBG_OFF, &mii_reg); + ret = pch_gbe_phy_write_reg_miic(hw, PHY_AR8031_DBG_OFF, + PHY_AR8031_SERDES); + if (ret) + break; + + pch_gbe_phy_read_reg_miic(hw, PHY_AR8031_DBG_DAT, &mii_reg); + mii_reg |= PHY_AR8031_SERDES_TX_CLK_DLY; + ret = pch_gbe_phy_write_reg_miic(hw, PHY_AR8031_DBG_DAT, + mii_reg); + break; + default: + netdev_err(adapter->netdev, + "Unknown PHY (%x), could not set TX clock delay\n", + hw->phy.id); + return -EINVAL; + } + + if (ret) + netdev_err(adapter->netdev, + "Could not configure tx clock delay for PHY\n"); + return ret; +} + +/** * pch_gbe_phy_init_setting - PHY initial setting * @hw: Pointer to the HW structure */ @@ -277,4 +331,48 @@ void pch_gbe_phy_init_setting(struct pch_gbe_hw *hw) pch_gbe_phy_read_reg_miic(hw, PHY_PHYSP_CONTROL, &mii_reg); mii_reg |= PHYSP_CTRL_ASSERT_CRS_TX; pch_gbe_phy_write_reg_miic(hw, PHY_PHYSP_CONTROL, mii_reg); + + /* Setup a TX clock delay on certain platforms */ + if (adapter->pdata && adapter->pdata->phy_tx_clk_delay) + pch_gbe_phy_tx_clk_delay(hw); +} + +/** + * pch_gbe_phy_disable_hibernate - Disable the PHY low power state + * @hw: Pointer to the HW structure + * Returns + * 0: Successful. + * -EINVAL: Invalid argument. + */ +int pch_gbe_phy_disable_hibernate(struct pch_gbe_hw *hw) +{ + struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw); + u16 mii_reg; + int ret = 0; + + switch (hw->phy.id) { + case PHY_AR803X_ID: + netdev_dbg(adapter->netdev, + "Disabling hibernation for AR803X PHY\n"); + ret = pch_gbe_phy_write_reg_miic(hw, PHY_AR8031_DBG_OFF, + PHY_AR8031_HIBERNATE); + if (ret) + break; + + pch_gbe_phy_read_reg_miic(hw, PHY_AR8031_DBG_DAT, &mii_reg); + mii_reg &= ~PHY_AR8031_PS_HIB_EN; + ret = pch_gbe_phy_write_reg_miic(hw, PHY_AR8031_DBG_DAT, + mii_reg); + break; + default: + netdev_err(adapter->netdev, + "Unknown PHY (%x), could not disable hibernation\n", + hw->phy.id); + return -EINVAL; + } + + if (ret) + netdev_err(adapter->netdev, + "Could not disable PHY hibernation\n"); + return ret; } diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h index 03264dc7b5ec..0cbe69206e04 100644 --- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h +++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h @@ -33,5 +33,6 @@ void pch_gbe_phy_power_up(struct pch_gbe_hw *hw); void pch_gbe_phy_power_down(struct pch_gbe_hw *hw); void pch_gbe_phy_set_rgmii(struct pch_gbe_hw *hw); void pch_gbe_phy_init_setting(struct pch_gbe_hw *hw); +int pch_gbe_phy_disable_hibernate(struct pch_gbe_hw *hw); #endif /* _PCH_GBE_PHY_H_ */ diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.c b/drivers/net/ethernet/pasemi/pasemi_mac.c index a5f0b5da6149..f21ae7b6c766 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.c +++ b/drivers/net/ethernet/pasemi/pasemi_mac.c @@ -191,7 +191,7 @@ static int pasemi_get_mac_addr(struct pasemi_mac *mac) struct device_node *dn = pci_device_to_OF_node(pdev); int len; const u8 *maddr; - u8 addr[6]; + u8 addr[ETH_ALEN]; if (!dn) { dev_dbg(&pdev->dev, @@ -201,8 +201,8 @@ static int pasemi_get_mac_addr(struct pasemi_mac *mac) maddr = of_get_property(dn, "local-mac-address", &len); - if (maddr && len == 6) { - memcpy(mac->mac_addr, maddr, 6); + if (maddr && len == ETH_ALEN) { + memcpy(mac->mac_addr, maddr, ETH_ALEN); return 0; } @@ -219,14 +219,15 @@ static int pasemi_get_mac_addr(struct pasemi_mac *mac) return -ENOENT; } - if (sscanf(maddr, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &addr[0], - &addr[1], &addr[2], &addr[3], &addr[4], &addr[5]) != 6) { + if (sscanf(maddr, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", + &addr[0], &addr[1], &addr[2], &addr[3], &addr[4], &addr[5]) + != ETH_ALEN) { dev_warn(&pdev->dev, "can't parse mac address, not configuring\n"); return -EINVAL; } - memcpy(mac->mac_addr, addr, 6); + memcpy(mac->mac_addr, addr, ETH_ALEN); return 0; } diff --git a/drivers/net/ethernet/pasemi/pasemi_mac.h b/drivers/net/ethernet/pasemi/pasemi_mac.h index e2f4efa8ad46..f2749d46c125 100644 --- a/drivers/net/ethernet/pasemi/pasemi_mac.h +++ b/drivers/net/ethernet/pasemi/pasemi_mac.h @@ -83,7 +83,7 @@ struct pasemi_mac { #define MAC_TYPE_GMAC 1 #define MAC_TYPE_XAUI 2 - u8 mac_addr[6]; + u8 mac_addr[ETH_ALEN]; struct net_lro_mgr lro_mgr; struct net_lro_desc lro_desc[MAX_LRO_DESCRIPTORS]; diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c index 9fbb1cdbfa47..8375cbde9969 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c @@ -536,10 +536,10 @@ static void netxen_p2_nic_set_multi(struct net_device *netdev) { struct netxen_adapter *adapter = netdev_priv(netdev); struct netdev_hw_addr *ha; - u8 null_addr[6]; + u8 null_addr[ETH_ALEN]; int i; - memset(null_addr, 0, 6); + memset(null_addr, 0, ETH_ALEN); if (netdev->flags & IFF_PROMISC) { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 221645e9f182..39351554106d 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -20,7 +20,6 @@ #include <linux/tcp.h> #include <linux/skbuff.h> #include <linux/firmware.h> - #include <linux/ethtool.h> #include <linux/mii.h> #include <linux/timer.h> @@ -38,8 +37,8 @@ #define _QLCNIC_LINUX_MAJOR 5 #define _QLCNIC_LINUX_MINOR 2 -#define _QLCNIC_LINUX_SUBVERSION 44 -#define QLCNIC_LINUX_VERSIONID "5.2.44" +#define _QLCNIC_LINUX_SUBVERSION 45 +#define QLCNIC_LINUX_VERSIONID "5.2.45" #define QLCNIC_DRV_IDC_VER 0x01 #define QLCNIC_DRIVER_VERSION ((_QLCNIC_LINUX_MAJOR << 16) |\ (_QLCNIC_LINUX_MINOR << 8) | (_QLCNIC_LINUX_SUBVERSION)) @@ -467,7 +466,7 @@ struct qlcnic_hardware_context { u32 *ext_reg_tbl; u32 mbox_aen[QLC_83XX_MBX_AEN_CNT]; u32 mbox_reg[4]; - spinlock_t mbx_lock; + struct qlcnic_mailbox *mailbox; }; struct qlcnic_adapter_stats { @@ -950,12 +949,6 @@ struct qlcnic_ipaddr { #define QLCNIC_READD_AGE 20 #define QLCNIC_LB_MAX_FILTERS 64 #define QLCNIC_LB_BUCKET_SIZE 32 - -/* QLCNIC Driver Error Code */ -#define QLCNIC_FW_NOT_RESPOND 51 -#define QLCNIC_TEST_IN_PROGRESS 52 -#define QLCNIC_UNDEFINED_ERROR 53 -#define QLCNIC_LB_CABLE_NOT_CONN 54 #define QLCNIC_ILB_MAX_RCV_LOOP 10 struct qlcnic_filter { @@ -972,6 +965,21 @@ struct qlcnic_filter_hash { u16 fbucket_size; }; +/* Mailbox specific data structures */ +struct qlcnic_mailbox { + struct workqueue_struct *work_q; + struct qlcnic_adapter *adapter; + struct qlcnic_mbx_ops *ops; + struct work_struct work; + struct completion completion; + struct list_head cmd_q; + unsigned long status; + spinlock_t queue_lock; /* Mailbox queue lock */ + spinlock_t aen_lock; /* Mailbox response/AEN lock */ + atomic_t rsp_status; + u32 num_cmds; +}; + struct qlcnic_adapter { struct qlcnic_hardware_context *ahw; struct qlcnic_recv_context *recv_ctx; @@ -1385,9 +1393,20 @@ struct _cdrp_cmd { }; struct qlcnic_cmd_args { - struct _cdrp_cmd req; - struct _cdrp_cmd rsp; - int op_type; + struct completion completion; + struct list_head list; + struct _cdrp_cmd req; + struct _cdrp_cmd rsp; + atomic_t rsp_status; + int pay_size; + u32 rsp_opcode; + u32 total_cmds; + u32 op_type; + u32 type; + u32 cmd_op; + u32 *hdr; /* Back channel message header */ + u32 *pay; /* Back channel message payload */ + u8 func_num; }; int qlcnic_fw_cmd_get_minidump_temp(struct qlcnic_adapter *adapter); @@ -1600,6 +1619,20 @@ struct qlcnic_nic_template { int (*resume)(struct qlcnic_adapter *); }; +struct qlcnic_mbx_ops { + int (*enqueue_cmd) (struct qlcnic_adapter *, + struct qlcnic_cmd_args *, unsigned long *); + void (*dequeue_cmd) (struct qlcnic_adapter *, struct qlcnic_cmd_args *); + void (*decode_resp) (struct qlcnic_adapter *, struct qlcnic_cmd_args *); + void (*encode_cmd) (struct qlcnic_adapter *, struct qlcnic_cmd_args *); + void (*nofity_fw) (struct qlcnic_adapter *, u8); +}; + +int qlcnic_83xx_init_mailbox_work(struct qlcnic_adapter *); +void qlcnic_83xx_detach_mailbox_work(struct qlcnic_adapter *); +void qlcnic_83xx_reinit_mbx_work(struct qlcnic_mailbox *mbx); +void qlcnic_83xx_free_mailbox(struct qlcnic_mailbox *mbx); + /* Adapter hardware abstraction */ struct qlcnic_hardware_ops { void (*read_crb) (struct qlcnic_adapter *, char *, loff_t, size_t); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c index 92da9980a0a0..55a597799cf8 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.c @@ -149,7 +149,7 @@ static struct qlcnic_hardware_ops qlcnic_83xx_hw_ops = { .get_mac_address = qlcnic_83xx_get_mac_address, .setup_intr = qlcnic_83xx_setup_intr, .alloc_mbx_args = qlcnic_83xx_alloc_mbx_args, - .mbx_cmd = qlcnic_83xx_mbx_op, + .mbx_cmd = qlcnic_83xx_issue_cmd, .get_func_no = qlcnic_83xx_get_func_no, .api_lock = qlcnic_83xx_cam_lock, .api_unlock = qlcnic_83xx_cam_unlock, @@ -362,6 +362,10 @@ static inline void qlcnic_83xx_get_mbx_data(struct qlcnic_adapter *adapter, struct qlcnic_cmd_args *cmd) { int i; + + if (cmd->op_type == QLC_83XX_MBX_POST_BC_OP) + return; + for (i = 0; i < cmd->rsp.num; i++) cmd->rsp.arg[i] = readl(QLCNIC_MBX_FW(adapter->ahw, i)); } @@ -398,24 +402,33 @@ irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *adapter) return IRQ_HANDLED; } +static inline void qlcnic_83xx_notify_mbx_response(struct qlcnic_mailbox *mbx) +{ + atomic_set(&mbx->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED); + complete(&mbx->completion); +} + static void qlcnic_83xx_poll_process_aen(struct qlcnic_adapter *adapter) { - u32 resp, event; + u32 resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; unsigned long flags; - spin_lock_irqsave(&adapter->ahw->mbx_lock, flags); - + spin_lock_irqsave(&mbx->aen_lock, flags); resp = QLCRDX(adapter->ahw, QLCNIC_FW_MBX_CTRL); if (!(resp & QLCNIC_SET_OWNER)) goto out; event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); - if (event & QLCNIC_MBX_ASYNC_EVENT) + if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); - + } else { + if (atomic_read(&mbx->rsp_status) != rsp_status) + qlcnic_83xx_notify_mbx_response(mbx); + } out: qlcnic_83xx_enable_legacy_msix_mbx_intr(adapter); - spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); + spin_unlock_irqrestore(&mbx->aen_lock, flags); } irqreturn_t qlcnic_83xx_intr(int irq, void *data) @@ -515,7 +528,7 @@ int qlcnic_83xx_setup_mbx_intr(struct qlcnic_adapter *adapter) } /* Enable mailbox interrupt */ - qlcnic_83xx_enable_mbx_intrpt(adapter); + qlcnic_83xx_enable_mbx_interrupt(adapter); return err; } @@ -628,7 +641,7 @@ void qlcnic_83xx_set_mac_filter_count(struct qlcnic_adapter *adapter) ahw->max_uc_count = count; } -void qlcnic_83xx_enable_mbx_intrpt(struct qlcnic_adapter *adapter) +void qlcnic_83xx_enable_mbx_interrupt(struct qlcnic_adapter *adapter) { u32 val; @@ -687,6 +700,9 @@ static void qlcnic_dump_mbx(struct qlcnic_adapter *adapter, { int i; + if (cmd->op_type == QLC_83XX_MBX_POST_BC_OP) + return; + dev_info(&adapter->pdev->dev, "Host MBX regs(%d)\n", cmd->req.num); for (i = 0; i < cmd->req.num; i++) { @@ -705,120 +721,74 @@ static void qlcnic_dump_mbx(struct qlcnic_adapter *adapter, pr_info("\n"); } -/* Mailbox response for mac rcode */ -u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *adapter) +static inline void +qlcnic_83xx_poll_for_mbx_completion(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) { - u32 fw_data; - u8 mac_cmd_rcode; + struct qlcnic_hardware_context *ahw = adapter->ahw; + int opcode = LSW(cmd->req.arg[0]); + unsigned long max_loops; - fw_data = readl(QLCNIC_MBX_FW(adapter->ahw, 2)); - mac_cmd_rcode = (u8)fw_data; - if (mac_cmd_rcode == QLC_83XX_NO_NIC_RESOURCE || - mac_cmd_rcode == QLC_83XX_MAC_PRESENT || - mac_cmd_rcode == QLC_83XX_MAC_ABSENT) - return QLCNIC_RCODE_SUCCESS; - return 1; -} + max_loops = cmd->total_cmds * QLC_83XX_MBX_CMD_LOOP; -u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *adapter, u32 *wait_time) -{ - u32 data; - struct qlcnic_hardware_context *ahw = adapter->ahw; - /* wait for mailbox completion */ - do { - data = QLCRDX(ahw, QLCNIC_FW_MBX_CTRL); - if (++(*wait_time) > QLCNIC_MBX_TIMEOUT) { - data = QLCNIC_RCODE_TIMEOUT; - break; - } - mdelay(1); - } while (!data); - return data; + for (; max_loops; max_loops--) { + if (atomic_read(&cmd->rsp_status) == + QLC_83XX_MBX_RESPONSE_ARRIVED) + return; + + udelay(1); + } + + dev_err(&adapter->pdev->dev, + "%s: Mailbox command timed out, cmd_op=0x%x, cmd_type=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, opcode, cmd->type, ahw->pci_func, ahw->op_mode); + flush_workqueue(ahw->mailbox->work_q); + return; } -int qlcnic_83xx_mbx_op(struct qlcnic_adapter *adapter, - struct qlcnic_cmd_args *cmd) +int qlcnic_83xx_issue_cmd(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) { - int i; - u16 opcode; - u8 mbx_err_code; - unsigned long flags; + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; struct qlcnic_hardware_context *ahw = adapter->ahw; - u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd, wait_time = 0; + int cmd_type, err, opcode; + unsigned long timeout; opcode = LSW(cmd->req.arg[0]); - if (!test_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status)) { - dev_info(&adapter->pdev->dev, - "Mailbox cmd attempted, 0x%x\n", opcode); - dev_info(&adapter->pdev->dev, "Mailbox detached\n"); - return 0; + cmd_type = cmd->type; + err = mbx->ops->enqueue_cmd(adapter, cmd, &timeout); + if (err) { + dev_err(&adapter->pdev->dev, + "%s: Mailbox not available, cmd_op=0x%x, cmd_context=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, opcode, cmd->type, ahw->pci_func, + ahw->op_mode); + return err; } - spin_lock_irqsave(&adapter->ahw->mbx_lock, flags); - mbx_val = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL); - - if (mbx_val) { - QLCDB(adapter, DRV, - "Mailbox cmd attempted, 0x%x\n", opcode); - QLCDB(adapter, DRV, - "Mailbox not available, 0x%x, collect FW dump\n", - mbx_val); - cmd->rsp.arg[0] = QLCNIC_RCODE_TIMEOUT; - spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); - return cmd->rsp.arg[0]; - } - - /* Fill in mailbox registers */ - mbx_cmd = cmd->req.arg[0]; - writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 0)); - for (i = 1; i < cmd->req.num; i++) - writel(cmd->req.arg[i], QLCNIC_MBX_HOST(ahw, i)); - - /* Signal FW about the impending command */ - QLCWRX(ahw, QLCNIC_HOST_MBX_CTRL, QLCNIC_SET_OWNER); -poll: - rsp = qlcnic_83xx_mbx_poll(adapter, &wait_time); - if (rsp != QLCNIC_RCODE_TIMEOUT) { - /* Get the FW response data */ - fw_data = readl(QLCNIC_MBX_FW(ahw, 0)); - if (fw_data & QLCNIC_MBX_ASYNC_EVENT) { - __qlcnic_83xx_process_aen(adapter); - goto poll; - } - mbx_err_code = QLCNIC_MBX_STATUS(fw_data); - rsp_num = QLCNIC_MBX_NUM_REGS(fw_data); - opcode = QLCNIC_MBX_RSP(fw_data); - qlcnic_83xx_get_mbx_data(adapter, cmd); - - switch (mbx_err_code) { - case QLCNIC_MBX_RSP_OK: - case QLCNIC_MBX_PORT_RSP_OK: - rsp = QLCNIC_RCODE_SUCCESS; - break; - default: - if (opcode == QLCNIC_CMD_CONFIG_MAC_VLAN) { - rsp = qlcnic_83xx_mac_rcode(adapter); - if (!rsp) - goto out; - } + switch (cmd_type) { + case QLC_83XX_MBX_CMD_WAIT: + if (!wait_for_completion_timeout(&cmd->completion, timeout)) { dev_err(&adapter->pdev->dev, - "MBX command 0x%x failed with err:0x%x\n", - opcode, mbx_err_code); - rsp = mbx_err_code; - qlcnic_dump_mbx(adapter, cmd); - break; + "%s: Mailbox command timed out, cmd_op=0x%x, cmd_type=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, opcode, cmd_type, ahw->pci_func, + ahw->op_mode); + flush_workqueue(mbx->work_q); } - goto out; + break; + case QLC_83XX_MBX_CMD_NO_WAIT: + return 0; + case QLC_83XX_MBX_CMD_BUSY_WAIT: + qlcnic_83xx_poll_for_mbx_completion(adapter, cmd); + break; + default: + dev_err(&adapter->pdev->dev, + "%s: Invalid mailbox command, cmd_op=0x%x, cmd_type=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, opcode, cmd_type, ahw->pci_func, + ahw->op_mode); + qlcnic_83xx_detach_mailbox_work(adapter); } - dev_err(&adapter->pdev->dev, "MBX command 0x%x timed out\n", - QLCNIC_MBX_RSP(mbx_cmd)); - rsp = QLCNIC_RCODE_TIMEOUT; -out: - /* clear fw mbx control register */ - QLCWRX(ahw, QLCNIC_FW_MBX_CTRL, QLCNIC_CLR_OWNER); - spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); - return rsp; + return cmd->rsp_opcode; } int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *mbx, @@ -828,6 +798,7 @@ int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *mbx, u32 temp; const struct qlcnic_mailbox_metadata *mbx_tbl; + memset(mbx, 0, sizeof(struct qlcnic_cmd_args)); mbx_tbl = qlcnic_83xx_mbx_tbl; size = ARRAY_SIZE(qlcnic_83xx_mbx_tbl); for (i = 0; i < size; i++) { @@ -850,6 +821,7 @@ int qlcnic_83xx_alloc_mbx_args(struct qlcnic_cmd_args *mbx, memset(mbx->rsp.arg, 0, sizeof(u32) * mbx->rsp.num); temp = adapter->ahw->fw_hal_version << 29; mbx->req.arg[0] = (type | (mbx->req.num << 16) | temp); + mbx->cmd_op = type; return 0; } } @@ -933,20 +905,23 @@ void __qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) static void qlcnic_83xx_process_aen(struct qlcnic_adapter *adapter) { + u32 resp, event, rsp_status = QLC_83XX_MBX_RESPONSE_ARRIVED; struct qlcnic_hardware_context *ahw = adapter->ahw; - u32 resp, event; + struct qlcnic_mailbox *mbx = ahw->mailbox; unsigned long flags; - spin_lock_irqsave(&ahw->mbx_lock, flags); - + spin_lock_irqsave(&mbx->aen_lock, flags); resp = QLCRDX(ahw, QLCNIC_FW_MBX_CTRL); if (resp & QLCNIC_SET_OWNER) { event = readl(QLCNIC_MBX_FW(ahw, 0)); - if (event & QLCNIC_MBX_ASYNC_EVENT) + if (event & QLCNIC_MBX_ASYNC_EVENT) { __qlcnic_83xx_process_aen(adapter); + } else { + if (atomic_read(&mbx->rsp_status) != rsp_status) + qlcnic_83xx_notify_mbx_response(mbx); + } } - - spin_unlock_irqrestore(&ahw->mbx_lock, flags); + spin_unlock_irqrestore(&mbx->aen_lock, flags); } static void qlcnic_83xx_mbx_poll_work(struct work_struct *work) @@ -969,6 +944,7 @@ void qlcnic_83xx_enable_mbx_poll(struct qlcnic_adapter *adapter) return; INIT_DELAYED_WORK(&adapter->mbx_poll_work, qlcnic_83xx_mbx_poll_work); + queue_delayed_work(adapter->qlcnic_wq, &adapter->mbx_poll_work, 0); } void qlcnic_83xx_disable_mbx_poll(struct qlcnic_adapter *adapter) @@ -1355,8 +1331,10 @@ static int qlcnic_83xx_diag_alloc_res(struct net_device *netdev, int test, if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { /* disable and free mailbox interrupt */ - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { + qlcnic_83xx_enable_mbx_poll(adapter); qlcnic_83xx_free_mbx_intr(adapter); + } adapter->ahw->loopback_state = 0; adapter->ahw->hw_ops->setup_link_event(adapter, 1); } @@ -1377,6 +1355,8 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev, for (ring = 0; ring < adapter->max_sds_rings; ring++) { sds_ring = &adapter->recv_ctx->sds_rings[ring]; qlcnic_83xx_disable_intr(adapter, sds_ring); + if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_enable_mbx_poll(adapter); } } @@ -1386,6 +1366,7 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev, if (adapter->ahw->diag_test == QLCNIC_LOOPBACK_TEST) { if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) { err = qlcnic_83xx_setup_mbx_intr(adapter); + qlcnic_83xx_disable_mbx_poll(adapter); if (err) { dev_err(&adapter->pdev->dev, "%s: failed to setup mbx interrupt\n", @@ -1402,6 +1383,10 @@ static void qlcnic_83xx_diag_free_res(struct net_device *netdev, if (netif_running(netdev)) __qlcnic_up(adapter, netdev); + + if (adapter->ahw->diag_test == QLCNIC_INTERRUPT_TEST && + !(adapter->flags & QLCNIC_MSIX_ENABLED)) + qlcnic_83xx_disable_mbx_poll(adapter); out: netif_device_attach(netdev); } @@ -1619,26 +1604,33 @@ static void qlcnic_83xx_set_interface_id_promisc(struct qlcnic_adapter *adapter, int qlcnic_83xx_nic_set_promisc(struct qlcnic_adapter *adapter, u32 mode) { - int err; + struct qlcnic_cmd_args *cmd = NULL; u32 temp = 0; - struct qlcnic_cmd_args cmd; + int err; if (adapter->recv_ctx->state == QLCNIC_HOST_CTX_STATE_FREED) return -EIO; - err = qlcnic_alloc_mbx_args(&cmd, adapter, + cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC); + if (!cmd) + return -ENOMEM; + + err = qlcnic_alloc_mbx_args(cmd, adapter, QLCNIC_CMD_CONFIGURE_MAC_RX_MODE); if (err) - return err; + goto out; + cmd->type = QLC_83XX_MBX_CMD_NO_WAIT; qlcnic_83xx_set_interface_id_promisc(adapter, &temp); - cmd.req.arg[1] = (mode ? 1 : 0) | temp; - err = qlcnic_issue_cmd(adapter, &cmd); - if (err) - dev_info(&adapter->pdev->dev, - "Promiscous mode config failed\n"); + cmd->req.arg[1] = (mode ? 1 : 0) | temp; + err = qlcnic_issue_cmd(adapter, cmd); + if (!err) + return err; - qlcnic_free_mbx_args(&cmd); + qlcnic_free_mbx_args(cmd); + +out: + kfree(cmd); return err; } @@ -1651,7 +1643,7 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode) if (ahw->op_mode == QLCNIC_NON_PRIV_FUNC) { netdev_warn(netdev, "Loopback test not supported in non privileged mode\n"); - return ret; + return -ENOTSUPP; } if (test_bit(__QLCNIC_RESETTING, &adapter->state)) { @@ -1679,19 +1671,17 @@ int qlcnic_83xx_loopback_test(struct net_device *netdev, u8 mode) /* Poll for link up event before running traffic */ do { msleep(QLC_83XX_LB_MSLEEP_COUNT); - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) - qlcnic_83xx_process_aen(adapter); if (test_bit(__QLCNIC_RESETTING, &adapter->state)) { netdev_info(netdev, "Device is resetting, free LB test resources\n"); - ret = -EIO; + ret = -EBUSY; goto free_diag_res; } if (loop++ > QLC_83XX_LB_WAIT_COUNT) { netdev_info(netdev, "Firmware didn't sent link up event to loopback request\n"); - ret = -QLCNIC_FW_NOT_RESPOND; + ret = -ETIMEDOUT; qlcnic_83xx_clear_lb_mode(adapter, mode); goto free_diag_res; } @@ -1728,6 +1718,15 @@ int qlcnic_83xx_set_lb_mode(struct qlcnic_adapter *adapter, u8 mode) return status; config = ahw->port_config; + + /* Check if port is already in loopback mode */ + if ((config & QLC_83XX_CFG_LOOPBACK_HSS) || + (config & QLC_83XX_CFG_LOOPBACK_EXT)) { + netdev_err(netdev, + "Port already in Loopback mode.\n"); + return -EINPROGRESS; + } + set_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); if (mode == QLCNIC_ILB_MODE) @@ -1748,21 +1747,19 @@ int qlcnic_83xx_set_lb_mode(struct qlcnic_adapter *adapter, u8 mode) /* Wait for Link and IDC Completion AEN */ do { msleep(QLC_83XX_LB_MSLEEP_COUNT); - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) - qlcnic_83xx_process_aen(adapter); if (test_bit(__QLCNIC_RESETTING, &adapter->state)) { netdev_info(netdev, "Device is resetting, free LB test resources\n"); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); - return -EIO; + return -EBUSY; } if (loop++ > QLC_83XX_LB_WAIT_COUNT) { netdev_err(netdev, "Did not receive IDC completion AEN\n"); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); qlcnic_83xx_clear_lb_mode(adapter, mode); - return -EIO; + return -ETIMEDOUT; } } while (test_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status)); @@ -1797,21 +1794,19 @@ int qlcnic_83xx_clear_lb_mode(struct qlcnic_adapter *adapter, u8 mode) /* Wait for Link and IDC Completion AEN */ do { msleep(QLC_83XX_LB_MSLEEP_COUNT); - if (!(adapter->flags & QLCNIC_MSIX_ENABLED)) - qlcnic_83xx_process_aen(adapter); if (test_bit(__QLCNIC_RESETTING, &adapter->state)) { netdev_info(netdev, "Device is resetting, free LB test resources\n"); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); - return -EIO; + return -EBUSY; } if (loop++ > QLC_83XX_LB_WAIT_COUNT) { netdev_err(netdev, "Did not receive IDC completion AEN\n"); clear_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status); - return -EIO; + return -ETIMEDOUT; } } while (test_bit(QLC_83XX_IDC_COMP_AEN, &ahw->idc.status)); @@ -1950,25 +1945,31 @@ static void qlcnic_83xx_set_interface_id_macaddr(struct qlcnic_adapter *adapter, int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr, u16 vlan_id, u8 op) { - int err; - u32 *buf, temp = 0; - struct qlcnic_cmd_args cmd; + struct qlcnic_cmd_args *cmd = NULL; struct qlcnic_macvlan_mbx mv; + u32 *buf, temp = 0; + int err; if (adapter->recv_ctx->state == QLCNIC_HOST_CTX_STATE_FREED) return -EIO; - err = qlcnic_alloc_mbx_args(&cmd, adapter, QLCNIC_CMD_CONFIG_MAC_VLAN); + cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC); + if (!cmd) + return -ENOMEM; + + err = qlcnic_alloc_mbx_args(cmd, adapter, QLCNIC_CMD_CONFIG_MAC_VLAN); if (err) - return err; + goto out; + + cmd->type = QLC_83XX_MBX_CMD_NO_WAIT; if (vlan_id) op = (op == QLCNIC_MAC_ADD || op == QLCNIC_MAC_VLAN_ADD) ? QLCNIC_MAC_VLAN_ADD : QLCNIC_MAC_VLAN_DEL; - cmd.req.arg[1] = op | (1 << 8); + cmd->req.arg[1] = op | (1 << 8); qlcnic_83xx_set_interface_id_macaddr(adapter, &temp); - cmd.req.arg[1] |= temp; + cmd->req.arg[1] |= temp; mv.vlan = vlan_id; mv.mac_addr0 = addr[0]; mv.mac_addr1 = addr[1]; @@ -1976,14 +1977,15 @@ int qlcnic_83xx_sre_macaddr_change(struct qlcnic_adapter *adapter, u8 *addr, mv.mac_addr3 = addr[3]; mv.mac_addr4 = addr[4]; mv.mac_addr5 = addr[5]; - buf = &cmd.req.arg[2]; + buf = &cmd->req.arg[2]; memcpy(buf, &mv, sizeof(struct qlcnic_macvlan_mbx)); - err = qlcnic_issue_cmd(adapter, &cmd); - if (err) - dev_err(&adapter->pdev->dev, - "MAC-VLAN %s to CAM failed, err=%d.\n", - ((op == 1) ? "add " : "delete "), err); - qlcnic_free_mbx_args(&cmd); + err = qlcnic_issue_cmd(adapter, cmd); + if (!err) + return err; + + qlcnic_free_mbx_args(cmd); +out: + kfree(cmd); return err; } @@ -2099,10 +2101,12 @@ static void qlcnic_83xx_handle_link_aen(struct qlcnic_adapter *adapter, irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) { struct qlcnic_adapter *adapter = data; - unsigned long flags; + struct qlcnic_mailbox *mbx; u32 mask, resp, event; + unsigned long flags; - spin_lock_irqsave(&adapter->ahw->mbx_lock, flags); + mbx = adapter->ahw->mailbox; + spin_lock_irqsave(&mbx->aen_lock, flags); resp = QLCRDX(adapter->ahw, QLCNIC_FW_MBX_CTRL); if (!(resp & QLCNIC_SET_OWNER)) goto out; @@ -2110,11 +2114,13 @@ irqreturn_t qlcnic_83xx_handle_aen(int irq, void *data) event = readl(QLCNIC_MBX_FW(adapter->ahw, 0)); if (event & QLCNIC_MBX_ASYNC_EVENT) __qlcnic_83xx_process_aen(adapter); + else + qlcnic_83xx_notify_mbx_response(mbx); + out: mask = QLCRDX(adapter->ahw, QLCNIC_DEF_INT_MASK); writel(0, adapter->ahw->pci_base0 + mask); - spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); - + spin_unlock_irqrestore(&mbx->aen_lock, flags); return IRQ_HANDLED; } @@ -3472,3 +3478,300 @@ int qlcnic_83xx_resume(struct qlcnic_adapter *adapter) idc->delay); return err; } + +void qlcnic_83xx_reinit_mbx_work(struct qlcnic_mailbox *mbx) +{ + INIT_COMPLETION(mbx->completion); + set_bit(QLC_83XX_MBX_READY, &mbx->status); +} + +void qlcnic_83xx_free_mailbox(struct qlcnic_mailbox *mbx) +{ + destroy_workqueue(mbx->work_q); + kfree(mbx); +} + +static inline void +qlcnic_83xx_notify_cmd_completion(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) +{ + atomic_set(&cmd->rsp_status, QLC_83XX_MBX_RESPONSE_ARRIVED); + + if (cmd->type == QLC_83XX_MBX_CMD_NO_WAIT) { + qlcnic_free_mbx_args(cmd); + kfree(cmd); + return; + } + complete(&cmd->completion); +} + +static inline void qlcnic_83xx_flush_mbx_queue(struct qlcnic_adapter *adapter) +{ + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; + struct list_head *head = &mbx->cmd_q; + struct qlcnic_cmd_args *cmd = NULL; + + spin_lock(&mbx->queue_lock); + + while (!list_empty(head)) { + cmd = list_entry(head->next, struct qlcnic_cmd_args, list); + list_del(&cmd->list); + mbx->num_cmds--; + qlcnic_83xx_notify_cmd_completion(adapter, cmd); + } + + spin_unlock(&mbx->queue_lock); +} + +static inline int qlcnic_83xx_check_mbx_status(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_mailbox *mbx = ahw->mailbox; + u32 host_mbx_ctrl; + + if (!test_bit(QLC_83XX_MBX_READY, &mbx->status)) + return -EBUSY; + + host_mbx_ctrl = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL); + if (host_mbx_ctrl) { + ahw->idc.collect_dump = 1; + return -EIO; + } + + return 0; +} + +static inline void qlcnic_83xx_signal_mbx_cmd(struct qlcnic_adapter *adapter, + u8 issue_cmd) +{ + if (issue_cmd) + QLCWRX(adapter->ahw, QLCNIC_HOST_MBX_CTRL, QLCNIC_SET_OWNER); + else + QLCWRX(adapter->ahw, QLCNIC_FW_MBX_CTRL, QLCNIC_CLR_OWNER); +} + +static inline void qlcnic_83xx_dequeue_mbx_cmd(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) +{ + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; + + spin_lock(&mbx->queue_lock); + + list_del(&cmd->list); + mbx->num_cmds--; + + spin_unlock(&mbx->queue_lock); + + qlcnic_83xx_notify_cmd_completion(adapter, cmd); +} + +static void qlcnic_83xx_encode_mbx_cmd(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) +{ + u32 mbx_cmd, fw_hal_version, hdr_size, total_size, tmp; + struct qlcnic_hardware_context *ahw = adapter->ahw; + int i, j; + + if (cmd->op_type != QLC_83XX_MBX_POST_BC_OP) { + mbx_cmd = cmd->req.arg[0]; + writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 0)); + for (i = 1; i < cmd->req.num; i++) + writel(cmd->req.arg[i], QLCNIC_MBX_HOST(ahw, i)); + } else { + fw_hal_version = ahw->fw_hal_version; + hdr_size = sizeof(struct qlcnic_bc_hdr) / sizeof(u32); + total_size = cmd->pay_size + hdr_size; + tmp = QLCNIC_CMD_BC_EVENT_SETUP | total_size << 16; + mbx_cmd = tmp | fw_hal_version << 29; + writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 0)); + + /* Back channel specific operations bits */ + mbx_cmd = 0x1 | 1 << 4; + + if (qlcnic_sriov_pf_check(adapter)) + mbx_cmd |= cmd->func_num << 5; + + writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 1)); + + for (i = 2, j = 0; j < hdr_size; i++, j++) + writel(*(cmd->hdr++), QLCNIC_MBX_HOST(ahw, i)); + for (j = 0; j < cmd->pay_size; j++, i++) + writel(*(cmd->pay++), QLCNIC_MBX_HOST(ahw, i)); + } +} + +void qlcnic_83xx_detach_mailbox_work(struct qlcnic_adapter *adapter) +{ + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; + + clear_bit(QLC_83XX_MBX_READY, &mbx->status); + complete(&mbx->completion); + cancel_work_sync(&mbx->work); + flush_workqueue(mbx->work_q); + qlcnic_83xx_flush_mbx_queue(adapter); +} + +static inline int qlcnic_83xx_enqueue_mbx_cmd(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd, + unsigned long *timeout) +{ + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; + + if (test_bit(QLC_83XX_MBX_READY, &mbx->status)) { + atomic_set(&cmd->rsp_status, QLC_83XX_MBX_RESPONSE_WAIT); + init_completion(&cmd->completion); + cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_UNKNOWN; + + spin_lock(&mbx->queue_lock); + + list_add_tail(&cmd->list, &mbx->cmd_q); + mbx->num_cmds++; + cmd->total_cmds = mbx->num_cmds; + *timeout = cmd->total_cmds * QLC_83XX_MBX_TIMEOUT; + queue_work(mbx->work_q, &mbx->work); + + spin_unlock(&mbx->queue_lock); + + return 0; + } + + return -EBUSY; +} + +static inline int qlcnic_83xx_check_mac_rcode(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) +{ + u8 mac_cmd_rcode; + u32 fw_data; + + if (cmd->cmd_op == QLCNIC_CMD_CONFIG_MAC_VLAN) { + fw_data = readl(QLCNIC_MBX_FW(adapter->ahw, 2)); + mac_cmd_rcode = (u8)fw_data; + if (mac_cmd_rcode == QLC_83XX_NO_NIC_RESOURCE || + mac_cmd_rcode == QLC_83XX_MAC_PRESENT || + mac_cmd_rcode == QLC_83XX_MAC_ABSENT) { + cmd->rsp_opcode = QLCNIC_RCODE_SUCCESS; + return QLCNIC_RCODE_SUCCESS; + } + } + + return -EINVAL; +} + +static void qlcnic_83xx_decode_mbx_rsp(struct qlcnic_adapter *adapter, + struct qlcnic_cmd_args *cmd) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct device *dev = &adapter->pdev->dev; + u8 mbx_err_code; + u32 fw_data; + + fw_data = readl(QLCNIC_MBX_FW(ahw, 0)); + mbx_err_code = QLCNIC_MBX_STATUS(fw_data); + qlcnic_83xx_get_mbx_data(adapter, cmd); + + switch (mbx_err_code) { + case QLCNIC_MBX_RSP_OK: + case QLCNIC_MBX_PORT_RSP_OK: + cmd->rsp_opcode = QLCNIC_RCODE_SUCCESS; + break; + default: + if (!qlcnic_83xx_check_mac_rcode(adapter, cmd)) + break; + + dev_err(dev, "%s: Mailbox command failed, opcode=0x%x, cmd_type=0x%x, func=0x%x, op_mode=0x%x, error=0x%x\n", + __func__, cmd->cmd_op, cmd->type, ahw->pci_func, + ahw->op_mode, mbx_err_code); + cmd->rsp_opcode = QLC_83XX_MBX_RESPONSE_FAILED; + qlcnic_dump_mbx(adapter, cmd); + } + + return; +} + +static void qlcnic_83xx_mailbox_worker(struct work_struct *work) +{ + struct qlcnic_mailbox *mbx = container_of(work, struct qlcnic_mailbox, + work); + struct qlcnic_adapter *adapter = mbx->adapter; + struct qlcnic_mbx_ops *mbx_ops = mbx->ops; + struct device *dev = &adapter->pdev->dev; + atomic_t *rsp_status = &mbx->rsp_status; + struct list_head *head = &mbx->cmd_q; + struct qlcnic_hardware_context *ahw; + struct qlcnic_cmd_args *cmd = NULL; + + ahw = adapter->ahw; + + while (true) { + if (qlcnic_83xx_check_mbx_status(adapter)) + return; + + atomic_set(rsp_status, QLC_83XX_MBX_RESPONSE_WAIT); + + spin_lock(&mbx->queue_lock); + + if (list_empty(head)) { + spin_unlock(&mbx->queue_lock); + return; + } + cmd = list_entry(head->next, struct qlcnic_cmd_args, list); + + spin_unlock(&mbx->queue_lock); + + mbx_ops->encode_cmd(adapter, cmd); + mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_REQUEST); + + if (wait_for_completion_timeout(&mbx->completion, + QLC_83XX_MBX_TIMEOUT)) { + mbx_ops->decode_resp(adapter, cmd); + mbx_ops->nofity_fw(adapter, QLC_83XX_MBX_COMPLETION); + } else { + dev_err(dev, "%s: Mailbox command timeout, opcode=0x%x, cmd_type=0x%x, func=0x%x, op_mode=0x%x\n", + __func__, cmd->cmd_op, cmd->type, ahw->pci_func, + ahw->op_mode); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); + qlcnic_83xx_idc_request_reset(adapter, + QLCNIC_FORCE_FW_DUMP_KEY); + cmd->rsp_opcode = QLCNIC_RCODE_TIMEOUT; + } + mbx_ops->dequeue_cmd(adapter, cmd); + } +} + +static struct qlcnic_mbx_ops qlcnic_83xx_mbx_ops = { + .enqueue_cmd = qlcnic_83xx_enqueue_mbx_cmd, + .dequeue_cmd = qlcnic_83xx_dequeue_mbx_cmd, + .decode_resp = qlcnic_83xx_decode_mbx_rsp, + .encode_cmd = qlcnic_83xx_encode_mbx_cmd, + .nofity_fw = qlcnic_83xx_signal_mbx_cmd, +}; + +int qlcnic_83xx_init_mailbox_work(struct qlcnic_adapter *adapter) +{ + struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_mailbox *mbx; + + ahw->mailbox = kzalloc(sizeof(*mbx), GFP_KERNEL); + if (!ahw->mailbox) + return -ENOMEM; + + mbx = ahw->mailbox; + mbx->ops = &qlcnic_83xx_mbx_ops; + mbx->adapter = adapter; + + spin_lock_init(&mbx->queue_lock); + spin_lock_init(&mbx->aen_lock); + INIT_LIST_HEAD(&mbx->cmd_q); + init_completion(&mbx->completion); + + mbx->work_q = create_singlethread_workqueue("qlcnic_mailbox"); + if (mbx->work_q == NULL) { + kfree(mbx); + return -ENOMEM; + } + + INIT_WORK(&mbx->work, qlcnic_83xx_mailbox_worker); + set_bit(QLC_83XX_MBX_READY, &mbx->status); + return 0; +} diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h index 272f56a2e14b..dd22ef3d85e5 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_hw.h @@ -89,6 +89,13 @@ #define QLC_83XX_MAX_RESET_SEQ_ENTRIES 16 +#define QLC_83XX_MBX_POST_BC_OP 0x1 +#define QLC_83XX_MBX_COMPLETION 0x0 +#define QLC_83XX_MBX_REQUEST 0x1 + +#define QLC_83XX_MBX_TIMEOUT (5 * HZ) +#define QLC_83XX_MBX_CMD_LOOP 5000000 + /* status descriptor mailbox data * @phy_addr_{low|high}: physical address of buffer * @sds_ring_size: buffer size @@ -449,6 +456,20 @@ enum qlcnic_83xx_states { #define QLC_83xx_FLASH_MAX_WAIT_USEC 100 #define QLC_83XX_FLASH_LOCK_TIMEOUT 10000 +enum qlc_83xx_mbx_cmd_type { + QLC_83XX_MBX_CMD_WAIT = 0, + QLC_83XX_MBX_CMD_NO_WAIT, + QLC_83XX_MBX_CMD_BUSY_WAIT, +}; + +enum qlc_83xx_mbx_response_states { + QLC_83XX_MBX_RESPONSE_WAIT = 0, + QLC_83XX_MBX_RESPONSE_ARRIVED, +}; + +#define QLC_83XX_MBX_RESPONSE_FAILED 0x2 +#define QLC_83XX_MBX_RESPONSE_UNKNOWN 0x3 + /* Additional registers in 83xx */ enum qlc_83xx_ext_regs { QLCNIC_GLOBAL_RESET = 0, @@ -498,7 +519,7 @@ enum qlc_83xx_ext_regs { /* 83xx funcitons */ int qlcnic_83xx_get_fw_version(struct qlcnic_adapter *); -int qlcnic_83xx_mbx_op(struct qlcnic_adapter *, struct qlcnic_cmd_args *); +int qlcnic_83xx_issue_cmd(struct qlcnic_adapter *, struct qlcnic_cmd_args *); int qlcnic_83xx_setup_intr(struct qlcnic_adapter *, u8); void qlcnic_83xx_get_func_no(struct qlcnic_adapter *); int qlcnic_83xx_cam_lock(struct qlcnic_adapter *); @@ -551,7 +572,7 @@ void qlcnic_set_npar_data(struct qlcnic_adapter *, const struct qlcnic_info *, void qlcnic_83xx_config_intr_coal(struct qlcnic_adapter *); irqreturn_t qlcnic_83xx_handle_aen(int, void *); int qlcnic_83xx_get_port_info(struct qlcnic_adapter *); -void qlcnic_83xx_enable_mbx_intrpt(struct qlcnic_adapter *); +void qlcnic_83xx_enable_mbx_interrupt(struct qlcnic_adapter *); void qlcnic_83xx_disable_mbx_intr(struct qlcnic_adapter *); irqreturn_t qlcnic_83xx_clear_legacy_intr(struct qlcnic_adapter *); irqreturn_t qlcnic_83xx_intr(int, void *); @@ -623,8 +644,6 @@ int qlcnic_83xx_set_led(struct net_device *, enum ethtool_phys_id_state); int qlcnic_83xx_flash_test(struct qlcnic_adapter *); int qlcnic_83xx_enable_flash_write(struct qlcnic_adapter *); int qlcnic_83xx_disable_flash_write(struct qlcnic_adapter *); -u32 qlcnic_83xx_mac_rcode(struct qlcnic_adapter *); -u32 qlcnic_83xx_mbx_poll(struct qlcnic_adapter *, u32 *); void qlcnic_83xx_enable_mbx_poll(struct qlcnic_adapter *); void qlcnic_83xx_disable_mbx_poll(struct qlcnic_adapter *); void qlcnic_83xx_set_mac_filter_count(struct qlcnic_adapter *); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c index 9f4b8d5f0865..cc1e32a7248f 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c @@ -399,6 +399,7 @@ static void qlcnic_83xx_idc_detach_driver(struct qlcnic_adapter *adapter) struct net_device *netdev = adapter->netdev; netif_device_detach(netdev); + qlcnic_83xx_detach_mailbox_work(adapter); /* Disable mailbox interrupt */ qlcnic_83xx_disable_mbx_intr(adapter); @@ -610,6 +611,9 @@ int qlcnic_83xx_idc_reattach_driver(struct qlcnic_adapter *adapter) { int err; + qlcnic_83xx_reinit_mbx_work(adapter->ahw->mailbox); + qlcnic_83xx_enable_mbx_interrupt(adapter); + /* register for NIC IDC AEN Events */ qlcnic_83xx_register_nic_idc_func(adapter, 1); @@ -617,7 +621,7 @@ int qlcnic_83xx_idc_reattach_driver(struct qlcnic_adapter *adapter) if (err) return err; - qlcnic_83xx_enable_mbx_intrpt(adapter); + qlcnic_83xx_enable_mbx_interrupt(adapter); if (qlcnic_83xx_configure_opmode(adapter)) { qlcnic_83xx_idc_enter_failed_state(adapter, 1); @@ -640,7 +644,6 @@ static void qlcnic_83xx_idc_update_idc_params(struct qlcnic_adapter *adapter) struct qlcnic_hardware_context *ahw = adapter->ahw; qlcnic_83xx_idc_update_drv_presence_reg(adapter, 1, 1); - set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status); qlcnic_83xx_idc_update_audit_reg(adapter, 0, 1); set_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status); @@ -810,9 +813,10 @@ static int qlcnic_83xx_idc_init_state(struct qlcnic_adapter *adapter) **/ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) { - u32 val; struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_mailbox *mbx = ahw->mailbox; int ret = 0; + u32 val; /* Perform NIC configuration based ready state entry actions */ if (ahw->idc.state_entry(adapter)) @@ -824,7 +828,7 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) dev_err(&adapter->pdev->dev, "Error: device temperature %d above limits\n", adapter->ahw->temp); - clear_bit(QLC_83XX_MBX_READY, &ahw->idc.status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); set_bit(__QLCNIC_RESETTING, &adapter->state); qlcnic_83xx_idc_detach_driver(adapter); qlcnic_83xx_idc_enter_failed_state(adapter, 1); @@ -837,7 +841,7 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) if (ret) { adapter->flags |= QLCNIC_FW_HANG; if (!(val & QLC_83XX_IDC_DISABLE_FW_RESET_RECOVERY)) { - clear_bit(QLC_83XX_MBX_READY, &ahw->idc.status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); set_bit(__QLCNIC_RESETTING, &adapter->state); qlcnic_83xx_idc_enter_need_reset_state(adapter, 1); } @@ -845,6 +849,8 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) } if ((val & QLC_83XX_IDC_GRACEFULL_RESET) || ahw->idc.collect_dump) { + clear_bit(QLC_83XX_MBX_READY, &mbx->status); + /* Move to need reset state and prepare for reset */ qlcnic_83xx_idc_enter_need_reset_state(adapter, 1); return ret; @@ -882,12 +888,13 @@ static int qlcnic_83xx_idc_ready_state(struct qlcnic_adapter *adapter) **/ static int qlcnic_83xx_idc_need_reset_state(struct qlcnic_adapter *adapter) { + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; int ret = 0; if (adapter->ahw->idc.prev_state != QLC_83XX_IDC_DEV_NEED_RESET) { qlcnic_83xx_idc_update_audit_reg(adapter, 0, 1); set_bit(__QLCNIC_RESETTING, &adapter->state); - clear_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); if (adapter->ahw->nic_mode == QLC_83XX_VIRTUAL_NIC_MODE) qlcnic_83xx_disable_vnic_mode(adapter, 1); @@ -1079,7 +1086,6 @@ static void qlcnic_83xx_setup_idc_parameters(struct qlcnic_adapter *adapter) adapter->ahw->idc.name = (char **)qlc_83xx_idc_states; clear_bit(__QLCNIC_RESETTING, &adapter->state); - set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status); set_bit(QLC_83XX_MODULE_LOADED, &adapter->ahw->idc.status); /* Check if reset recovery is disabled */ @@ -1190,6 +1196,9 @@ void qlcnic_83xx_idc_request_reset(struct qlcnic_adapter *adapter, u32 key) { u32 val; + if (qlcnic_sriov_vf_check(adapter)) + return; + if (qlcnic_83xx_lock_driver(adapter)) { dev_err(&adapter->pdev->dev, "%s:failed, please retry\n", __func__); @@ -2141,17 +2150,35 @@ static void qlcnic_83xx_clear_function_resources(struct qlcnic_adapter *adapter) int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac) { struct qlcnic_hardware_context *ahw = adapter->ahw; + int err = 0; - if (qlcnic_sriov_vf_check(adapter)) - return qlcnic_sriov_vf_init(adapter, pci_using_dac); + ahw->msix_supported = !!qlcnic_use_msi_x; + err = qlcnic_83xx_init_mailbox_work(adapter); + if (err) + goto exit; - if (qlcnic_83xx_check_hw_status(adapter)) - return -EIO; + if (qlcnic_sriov_vf_check(adapter)) { + err = qlcnic_sriov_vf_init(adapter, pci_using_dac); + if (err) + goto detach_mbx; + else + return err; + } - /* Initilaize 83xx mailbox spinlock */ - spin_lock_init(&ahw->mbx_lock); + err = qlcnic_83xx_check_hw_status(adapter); + if (err) + goto detach_mbx; + + err = qlcnic_setup_intr(adapter, 0); + if (err) { + dev_err(&adapter->pdev->dev, "Failed to setup interrupt\n"); + goto disable_intr; + } + + err = qlcnic_83xx_setup_mbx_intr(adapter); + if (err) + goto disable_mbx_intr; - set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status); qlcnic_83xx_clear_function_resources(adapter); INIT_DELAYED_WORK(&adapter->idc_aen_work, qlcnic_83xx_idc_aen_work); @@ -2162,19 +2189,33 @@ int qlcnic_83xx_init(struct qlcnic_adapter *adapter, int pci_using_dac) if (!qlcnic_83xx_read_flash_descriptor_table(adapter)) qlcnic_83xx_read_flash_mfg_id(adapter); - if (qlcnic_83xx_idc_init(adapter)) - return -EIO; + err = qlcnic_83xx_idc_init(adapter); + if (err) + goto disable_mbx_intr; /* Configure default, SR-IOV or Virtual NIC mode of operation */ - if (qlcnic_83xx_configure_opmode(adapter)) - return -EIO; + err = qlcnic_83xx_configure_opmode(adapter); + if (err) + goto disable_mbx_intr; /* Perform operating mode specific initialization */ - if (adapter->nic_ops->init_driver(adapter)) - return -EIO; + err = adapter->nic_ops->init_driver(adapter); + if (err) + goto disable_mbx_intr; /* Periodically monitor device status */ qlcnic_83xx_idc_poll_dev_state(&adapter->fw_work.work); + return 0; - return adapter->ahw->idc.err_code; +disable_mbx_intr: + qlcnic_83xx_free_mbx_intr(adapter); + +disable_intr: + qlcnic_teardown_intr(adapter); + +detach_mbx: + qlcnic_83xx_detach_mailbox_work(adapter); + qlcnic_83xx_free_mailbox(ahw->mailbox); +exit: + return err; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c index 7aac23ab31d1..79a5855f926c 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c @@ -1006,9 +1006,9 @@ int qlcnic_loopback_test(struct net_device *netdev, u8 mode) msleep(500); qlcnic_process_rcv_ring_diag(sds_ring); if (loop++ > QLCNIC_ILB_MAX_RCV_LOOP) { - netdev_info(netdev, "firmware didnt respond to loopback" - " configure request\n"); - ret = -QLCNIC_FW_NOT_RESPOND; + netdev_info(netdev, + "Firmware didn't sent link up event to loopback request\n"); + ret = -ETIMEDOUT; goto free_res; } else if (adapter->ahw->diag_cnt) { ret = adapter->ahw->diag_cnt; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 6946d354f44f..f807f3b949e2 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -952,17 +952,17 @@ static void qlcnic_handle_fw_message(int desc_cnt, int index, break; case 1: dev_info(dev, "loopback already in progress\n"); - adapter->ahw->diag_cnt = -QLCNIC_TEST_IN_PROGRESS; + adapter->ahw->diag_cnt = -EINPROGRESS; break; case 2: dev_info(dev, "loopback cable is not connected\n"); - adapter->ahw->diag_cnt = -QLCNIC_LB_CABLE_NOT_CONN; + adapter->ahw->diag_cnt = -ENODEV; break; default: dev_info(dev, "loopback configure request failed, err %x\n", ret); - adapter->ahw->diag_cnt = -QLCNIC_UNDEFINED_ERROR; + adapter->ahw->diag_cnt = -EIO; break; } break; diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index ee013fcc3322..b8242bc0293b 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -2145,16 +2145,12 @@ qlcnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) dev_warn(&pdev->dev, "Device does not support MSI interrupts\n"); - err = qlcnic_setup_intr(adapter, 0); - if (err) { - dev_err(&pdev->dev, "Failed to setup interrupt\n"); - goto err_out_disable_msi; - } - - if (qlcnic_83xx_check(adapter)) { - err = qlcnic_83xx_setup_mbx_intr(adapter); - if (err) + if (qlcnic_82xx_check(adapter)) { + err = qlcnic_setup_intr(adapter, 0); + if (err) { + dev_err(&pdev->dev, "Failed to setup interrupt\n"); goto err_out_disable_msi; + } } err = qlcnic_get_act_pci_func(adapter); @@ -2241,9 +2237,11 @@ static void qlcnic_remove(struct pci_dev *pdev) qlcnic_sriov_cleanup(adapter); if (qlcnic_83xx_check(adapter)) { - qlcnic_83xx_free_mbx_intr(adapter); qlcnic_83xx_register_nic_idc_func(adapter, 0); cancel_delayed_work_sync(&adapter->idc_aen_work); + qlcnic_83xx_free_mbx_intr(adapter); + qlcnic_83xx_detach_mailbox_work(adapter); + qlcnic_83xx_free_mailbox(ahw->mailbox); } qlcnic_detach(adapter); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 5d40045b3cea..046286a897ea 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -33,7 +33,7 @@ static int qlcnic_sriov_alloc_bc_mbx_args(struct qlcnic_cmd_args *, u32); static void qlcnic_sriov_vf_poll_dev_state(struct work_struct *); static void qlcnic_sriov_vf_cancel_fw_work(struct qlcnic_adapter *); static void qlcnic_sriov_cleanup_transaction(struct qlcnic_bc_trans *); -static int qlcnic_sriov_vf_mbx_op(struct qlcnic_adapter *, +static int qlcnic_sriov_issue_cmd(struct qlcnic_adapter *, struct qlcnic_cmd_args *); static void qlcnic_sriov_process_bc_cmd(struct work_struct *); @@ -45,7 +45,7 @@ static struct qlcnic_hardware_ops qlcnic_sriov_vf_hw_ops = { .get_mac_address = qlcnic_83xx_get_mac_address, .setup_intr = qlcnic_83xx_setup_intr, .alloc_mbx_args = qlcnic_83xx_alloc_mbx_args, - .mbx_cmd = qlcnic_sriov_vf_mbx_op, + .mbx_cmd = qlcnic_sriov_issue_cmd, .get_func_no = qlcnic_83xx_get_func_no, .api_lock = qlcnic_83xx_cam_lock, .api_unlock = qlcnic_83xx_cam_unlock, @@ -286,96 +286,38 @@ void qlcnic_sriov_cleanup(struct qlcnic_adapter *adapter) static int qlcnic_sriov_post_bc_msg(struct qlcnic_adapter *adapter, u32 *hdr, u32 *pay, u8 pci_func, u8 size) { - u32 rsp, mbx_val, fw_data, rsp_num, mbx_cmd, val, wait_time = 0; struct qlcnic_hardware_context *ahw = adapter->ahw; - unsigned long flags; - u16 opcode; - u8 mbx_err_code; - int i, j; - - opcode = ((struct qlcnic_bc_hdr *)hdr)->cmd_op; - - if (!test_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status)) { - dev_info(&adapter->pdev->dev, - "Mailbox cmd attempted, 0x%x\n", opcode); - dev_info(&adapter->pdev->dev, "Mailbox detached\n"); - return 0; - } - - spin_lock_irqsave(&ahw->mbx_lock, flags); - - mbx_val = QLCRDX(ahw, QLCNIC_HOST_MBX_CTRL); - if (mbx_val) { - QLCDB(adapter, DRV, "Mailbox cmd attempted, 0x%x\n", opcode); - spin_unlock_irqrestore(&ahw->mbx_lock, flags); - return QLCNIC_RCODE_TIMEOUT; - } - /* Fill in mailbox registers */ - val = size + (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); - mbx_cmd = 0x31 | (val << 16) | (adapter->ahw->fw_hal_version << 29); - - writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 0)); - mbx_cmd = 0x1 | (1 << 4); + struct qlcnic_mailbox *mbx = ahw->mailbox; + struct qlcnic_cmd_args cmd; + unsigned long timeout; + int err; - if (qlcnic_sriov_pf_check(adapter)) - mbx_cmd |= (pci_func << 5); + memset(&cmd, 0, sizeof(struct qlcnic_cmd_args)); + cmd.hdr = hdr; + cmd.pay = pay; + cmd.pay_size = size; + cmd.func_num = pci_func; + cmd.op_type = QLC_83XX_MBX_POST_BC_OP; + cmd.cmd_op = ((struct qlcnic_bc_hdr *)hdr)->cmd_op; - writel(mbx_cmd, QLCNIC_MBX_HOST(ahw, 1)); - for (i = 2, j = 0; j < (sizeof(struct qlcnic_bc_hdr) / sizeof(u32)); - i++, j++) { - writel(*(hdr++), QLCNIC_MBX_HOST(ahw, i)); + err = mbx->ops->enqueue_cmd(adapter, &cmd, &timeout); + if (err) { + dev_err(&adapter->pdev->dev, + "%s: Mailbox not available, cmd_op=0x%x, cmd_type=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, cmd.cmd_op, cmd.type, ahw->pci_func, + ahw->op_mode); + return err; } - for (j = 0; j < size; j++, i++) - writel(*(pay++), QLCNIC_MBX_HOST(ahw, i)); - - /* Signal FW about the impending command */ - QLCWRX(ahw, QLCNIC_HOST_MBX_CTRL, QLCNIC_SET_OWNER); - /* Waiting for the mailbox cmd to complete and while waiting here - * some AEN might arrive. If more than 5 seconds expire we can - * assume something is wrong. - */ -poll: - rsp = qlcnic_83xx_mbx_poll(adapter, &wait_time); - if (rsp != QLCNIC_RCODE_TIMEOUT) { - /* Get the FW response data */ - fw_data = readl(QLCNIC_MBX_FW(ahw, 0)); - if (fw_data & QLCNIC_MBX_ASYNC_EVENT) { - __qlcnic_83xx_process_aen(adapter); - goto poll; - } - mbx_err_code = QLCNIC_MBX_STATUS(fw_data); - rsp_num = QLCNIC_MBX_NUM_REGS(fw_data); - opcode = QLCNIC_MBX_RSP(fw_data); - - switch (mbx_err_code) { - case QLCNIC_MBX_RSP_OK: - case QLCNIC_MBX_PORT_RSP_OK: - rsp = QLCNIC_RCODE_SUCCESS; - break; - default: - if (opcode == QLCNIC_CMD_CONFIG_MAC_VLAN) { - rsp = qlcnic_83xx_mac_rcode(adapter); - if (!rsp) - goto out; - } - dev_err(&adapter->pdev->dev, - "MBX command 0x%x failed with err:0x%x\n", - opcode, mbx_err_code); - rsp = mbx_err_code; - break; - } - goto out; + if (!wait_for_completion_timeout(&cmd.completion, timeout)) { + dev_err(&adapter->pdev->dev, + "%s: Mailbox command timed out, cmd_op=0x%x, cmd_type=0x%x, pci_func=0x%x, op_mode=0x%x\n", + __func__, cmd.cmd_op, cmd.type, ahw->pci_func, + ahw->op_mode); + flush_workqueue(mbx->work_q); } - dev_err(&adapter->pdev->dev, "MBX command 0x%x timed out\n", - QLCNIC_MBX_RSP(mbx_cmd)); - rsp = QLCNIC_RCODE_TIMEOUT; -out: - /* clear fw mbx control register */ - QLCWRX(ahw, QLCNIC_FW_MBX_CTRL, QLCNIC_CLR_OWNER); - spin_unlock_irqrestore(&adapter->ahw->mbx_lock, flags); - return rsp; + return cmd.rsp_opcode; } static void qlcnic_sriov_vf_cfg_buff_desc(struct qlcnic_adapter *adapter) @@ -522,8 +464,8 @@ static int qlcnic_sriov_get_vf_acl(struct qlcnic_adapter *adapter) static int qlcnic_sriov_vf_init_driver(struct qlcnic_adapter *adapter) { - struct qlcnic_info nic_info; struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_info nic_info; int err; err = qlcnic_sriov_get_vf_vport_info(adapter, &nic_info, 0); @@ -637,8 +579,6 @@ int qlcnic_sriov_vf_init(struct qlcnic_adapter *adapter, int pci_using_dac) struct qlcnic_hardware_context *ahw = adapter->ahw; int err; - spin_lock_init(&ahw->mbx_lock); - set_bit(QLC_83XX_MBX_READY, &ahw->idc.status); set_bit(QLC_83XX_MODULE_LOADED, &ahw->idc.status); ahw->idc.delay = QLC_83XX_IDC_FW_POLL_DELAY; ahw->reset_context = 0; @@ -1085,6 +1025,7 @@ static void qlcnic_sriov_process_bc_cmd(struct work_struct *work) if (test_bit(QLC_BC_VF_FLR, &vf->state)) return; + memset(&cmd, 0, sizeof(struct qlcnic_cmd_args)); trans = list_first_entry(&vf->rcv_act.wait_list, struct qlcnic_bc_trans, list); adapter = vf->adapter; @@ -1234,6 +1175,7 @@ static void qlcnic_sriov_handle_bc_cmd(struct qlcnic_sriov *sriov, return; } + memset(&cmd, 0, sizeof(struct qlcnic_cmd_args)); cmd_op = hdr->cmd_op; if (qlcnic_sriov_alloc_bc_trans(&trans)) return; @@ -1359,7 +1301,7 @@ int qlcnic_sriov_cfg_bc_intr(struct qlcnic_adapter *adapter, u8 enable) if (enable) cmd.req.arg[1] = (1 << 4) | (1 << 5) | (1 << 6) | (1 << 7); - err = qlcnic_83xx_mbx_op(adapter, &cmd); + err = qlcnic_83xx_issue_cmd(adapter, &cmd); if (err != QLCNIC_RCODE_SUCCESS) { dev_err(&adapter->pdev->dev, @@ -1391,10 +1333,11 @@ static int qlcnic_sriov_retry_bc_cmd(struct qlcnic_adapter *adapter, return -EIO; } -static int qlcnic_sriov_vf_mbx_op(struct qlcnic_adapter *adapter, +static int qlcnic_sriov_issue_cmd(struct qlcnic_adapter *adapter, struct qlcnic_cmd_args *cmd) { struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_mailbox *mbx = ahw->mailbox; struct device *dev = &adapter->pdev->dev; struct qlcnic_bc_trans *trans; int err; @@ -1411,7 +1354,7 @@ static int qlcnic_sriov_vf_mbx_op(struct qlcnic_adapter *adapter, goto cleanup_transaction; retry: - if (!test_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status)) { + if (!test_bit(QLC_83XX_MBX_READY, &mbx->status)) { rsp = -EIO; QLCDB(adapter, DRV, "MBX not Ready!(cmd 0x%x) for VF 0x%x\n", QLCNIC_MBX_RSP(cmd->req.arg[0]), func); @@ -1454,7 +1397,7 @@ err_out: if (rsp == QLCNIC_RCODE_TIMEOUT) { ahw->reset_context = 1; adapter->need_fw_reset = 1; - clear_bit(QLC_83XX_MBX_READY, &ahw->idc.status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); } cleanup_transaction: @@ -1614,7 +1557,7 @@ static int qlcnic_sriov_vf_reinit_driver(struct qlcnic_adapter *adapter) int err; set_bit(QLC_83XX_MBX_READY, &adapter->ahw->idc.status); - qlcnic_83xx_enable_mbx_intrpt(adapter); + qlcnic_83xx_enable_mbx_interrupt(adapter); err = qlcnic_sriov_cfg_bc_intr(adapter, 1); if (err) @@ -1657,8 +1600,10 @@ static void qlcnic_sriov_vf_detach(struct qlcnic_adapter *adapter) struct net_device *netdev = adapter->netdev; u8 i, max_ints = ahw->num_msix - 1; - qlcnic_83xx_disable_mbx_intr(adapter); netif_device_detach(netdev); + qlcnic_83xx_detach_mailbox_work(adapter); + qlcnic_83xx_disable_mbx_intr(adapter); + if (netif_running(netdev)) qlcnic_down(adapter, netdev); @@ -1702,6 +1647,7 @@ static int qlcnic_sriov_vf_handle_dev_ready(struct qlcnic_adapter *adapter) static int qlcnic_sriov_vf_handle_context_reset(struct qlcnic_adapter *adapter) { struct qlcnic_hardware_context *ahw = adapter->ahw; + struct qlcnic_mailbox *mbx = ahw->mailbox; struct device *dev = &adapter->pdev->dev; struct qlc_83xx_idc *idc = &ahw->idc; u8 func = ahw->pci_func; @@ -1712,7 +1658,7 @@ static int qlcnic_sriov_vf_handle_context_reset(struct qlcnic_adapter *adapter) /* Skip the context reset and check if FW is hung */ if (adapter->reset_ctx_cnt < 3) { adapter->need_fw_reset = 1; - clear_bit(QLC_83XX_MBX_READY, &idc->status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); dev_info(dev, "Resetting context, wait here to check if FW is in failed state\n"); return 0; @@ -1737,7 +1683,7 @@ static int qlcnic_sriov_vf_handle_context_reset(struct qlcnic_adapter *adapter) __func__, adapter->reset_ctx_cnt, func); set_bit(__QLCNIC_RESETTING, &adapter->state); adapter->need_fw_reset = 1; - clear_bit(QLC_83XX_MBX_READY, &idc->status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); qlcnic_sriov_vf_detach(adapter); adapter->need_fw_reset = 0; @@ -1787,6 +1733,7 @@ static int qlcnic_sriov_vf_idc_failed_state(struct qlcnic_adapter *adapter) static int qlcnic_sriov_vf_idc_need_quiescent_state(struct qlcnic_adapter *adapter) { + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; struct qlc_83xx_idc *idc = &adapter->ahw->idc; dev_info(&adapter->pdev->dev, "Device is in quiescent state\n"); @@ -1794,7 +1741,7 @@ qlcnic_sriov_vf_idc_need_quiescent_state(struct qlcnic_adapter *adapter) set_bit(__QLCNIC_RESETTING, &adapter->state); adapter->tx_timeo_cnt = 0; adapter->reset_ctx_cnt = 0; - clear_bit(QLC_83XX_MBX_READY, &idc->status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); qlcnic_sriov_vf_detach(adapter); } @@ -1803,6 +1750,7 @@ qlcnic_sriov_vf_idc_need_quiescent_state(struct qlcnic_adapter *adapter) static int qlcnic_sriov_vf_idc_init_reset_state(struct qlcnic_adapter *adapter) { + struct qlcnic_mailbox *mbx = adapter->ahw->mailbox; struct qlc_83xx_idc *idc = &adapter->ahw->idc; u8 func = adapter->ahw->pci_func; @@ -1812,7 +1760,7 @@ static int qlcnic_sriov_vf_idc_init_reset_state(struct qlcnic_adapter *adapter) set_bit(__QLCNIC_RESETTING, &adapter->state); adapter->tx_timeo_cnt = 0; adapter->reset_ctx_cnt = 0; - clear_bit(QLC_83XX_MBX_READY, &idc->status); + clear_bit(QLC_83XX_MBX_READY, &mbx->status); qlcnic_sriov_vf_detach(adapter); } return 0; @@ -1990,7 +1938,7 @@ int qlcnic_sriov_vf_resume(struct qlcnic_adapter *adapter) int err; set_bit(QLC_83XX_MODULE_LOADED, &idc->status); - qlcnic_83xx_enable_mbx_intrpt(adapter); + qlcnic_83xx_enable_mbx_interrupt(adapter); err = qlcnic_sriov_cfg_bc_intr(adapter, 1); if (err) return err; diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h index 7e8d68263963..899433778466 100644 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ b/drivers/net/ethernet/qlogic/qlge/qlge.h @@ -2149,7 +2149,7 @@ struct ql_adapter { struct timer_list timer; atomic_t lb_count; /* Keep local copy of current mac address. */ - char current_mac_addr[6]; + char current_mac_addr[ETH_ALEN]; }; /* diff --git a/drivers/net/ethernet/renesas/Kconfig b/drivers/net/ethernet/renesas/Kconfig index 19a8a045e077..a30c4395b232 100644 --- a/drivers/net/ethernet/renesas/Kconfig +++ b/drivers/net/ethernet/renesas/Kconfig @@ -13,4 +13,4 @@ config SH_ETH Renesas SuperH Ethernet device driver. This driver supporting CPUs are: - SH7619, SH7710, SH7712, SH7724, SH7734, SH7763, SH7757, - R8A7740 and R8A7779. + R8A7740, R8A777x and R8A7790. diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index a753928bab9c..9e2afe8e0c9f 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -189,6 +189,7 @@ static const u16 sh_eth_offset_fast_rcar[SH_ETH_MAX_REGISTER_OFFSET] = { [RMCR] = 0x0258, [TFUCR] = 0x0264, [RFOCR] = 0x0268, + [RMIIMODE] = 0x026c, [FCFTR] = 0x0270, [TRIMD] = 0x027c, }; @@ -392,6 +393,27 @@ static struct sh_eth_cpu_data r8a777x_data = { .hw_swap = 1, }; +/* R8A7790 */ +static struct sh_eth_cpu_data r8a7790_data = { + .set_duplex = sh_eth_set_duplex, + .set_rate = sh_eth_set_rate_r8a777x, + + .ecsr_value = ECSR_PSRTO | ECSR_LCHNG | ECSR_ICD, + .ecsipr_value = ECSIPR_PSRTOIP | ECSIPR_LCHNGIP | ECSIPR_ICDIP, + .eesipr_value = 0x01ff009f, + + .tx_check = EESR_FTC | EESR_CND | EESR_DLC | EESR_CD | EESR_RTO, + .eesr_err_check = EESR_TWB | EESR_TABT | EESR_RABT | EESR_RFE | + EESR_RDE | EESR_RFRMER | EESR_TFE | EESR_TDE | + EESR_ECI, + + .apr = 1, + .mpr = 1, + .tpauser = 1, + .hw_swap = 1, + .rmiimode = 1, +}; + static void sh_eth_set_rate_sh7724(struct net_device *ndev) { struct sh_eth_private *mdp = netdev_priv(ndev); @@ -1124,6 +1146,9 @@ static int sh_eth_dev_init(struct net_device *ndev, bool start) if (ret) goto out; + if (mdp->cd->rmiimode) + sh_eth_write(ndev, 0x1, RMIIMODE); + /* Descriptor format */ sh_eth_ring_format(ndev); if (mdp->cd->rpadir) @@ -2749,6 +2774,7 @@ static struct platform_device_id sh_eth_id_table[] = { { "sh7763-gether", (kernel_ulong_t)&sh7763_data }, { "r8a7740-gether", (kernel_ulong_t)&r8a7740_data }, { "r8a777x-ether", (kernel_ulong_t)&r8a777x_data }, + { "r8a7790-ether", (kernel_ulong_t)&r8a7790_data }, { } }; MODULE_DEVICE_TABLE(platform, sh_eth_id_table); diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h index 99995bf38c40..da93f5cf41f8 100644 --- a/drivers/net/ethernet/renesas/sh_eth.h +++ b/drivers/net/ethernet/renesas/sh_eth.h @@ -60,6 +60,7 @@ enum { EDOCR, TFUCR, RFOCR, + RMIIMODE, FCFTR, RPADIR, TRIMD, @@ -482,6 +483,7 @@ struct sh_eth_cpu_data { unsigned hw_crc:1; /* E-DMAC have CSMR */ unsigned select_mii:1; /* EtherC have RMII_MII (MII select register) */ unsigned shift_rd0:1; /* shift Rx descriptor word 0 right by 16 */ + unsigned rmiimode:1; /* EtherC has RMIIMODE register */ }; struct sh_eth_private { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 03de76c7a177..da8be6e63096 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -109,9 +109,6 @@ static int stmmac_pltfr_probe(struct platform_device *pdev) const char *mac = NULL; res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - addr = devm_ioremap_resource(dev, res); if (IS_ERR(addr)) return PTR_ERR(addr); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 22a7a4336211..db6933ecb543 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -91,6 +91,7 @@ do { \ #define CPSW1_SLAVE_SIZE 0x040 #define CPSW1_CPDMA_OFFSET 0x100 #define CPSW1_STATERAM_OFFSET 0x200 +#define CPSW1_HW_STATS 0x400 #define CPSW1_CPTS_OFFSET 0x500 #define CPSW1_ALE_OFFSET 0x600 #define CPSW1_SLIVER_OFFSET 0x700 @@ -99,6 +100,7 @@ do { \ #define CPSW2_SLAVE_OFFSET 0x200 #define CPSW2_SLAVE_SIZE 0x100 #define CPSW2_CPDMA_OFFSET 0x800 +#define CPSW2_HW_STATS 0x900 #define CPSW2_STATERAM_OFFSET 0xa00 #define CPSW2_CPTS_OFFSET 0xc00 #define CPSW2_ALE_OFFSET 0xd00 @@ -299,6 +301,44 @@ struct cpsw_sliver_regs { u32 rx_pri_map; }; +struct cpsw_hw_stats { + u32 rxgoodframes; + u32 rxbroadcastframes; + u32 rxmulticastframes; + u32 rxpauseframes; + u32 rxcrcerrors; + u32 rxaligncodeerrors; + u32 rxoversizedframes; + u32 rxjabberframes; + u32 rxundersizedframes; + u32 rxfragments; + u32 __pad_0[2]; + u32 rxoctets; + u32 txgoodframes; + u32 txbroadcastframes; + u32 txmulticastframes; + u32 txpauseframes; + u32 txdeferredframes; + u32 txcollisionframes; + u32 txsinglecollframes; + u32 txmultcollframes; + u32 txexcessivecollisions; + u32 txlatecollisions; + u32 txunderrun; + u32 txcarriersenseerrors; + u32 txoctets; + u32 octetframes64; + u32 octetframes65t127; + u32 octetframes128t255; + u32 octetframes256t511; + u32 octetframes512t1023; + u32 octetframes1024tup; + u32 netoctets; + u32 rxsofoverruns; + u32 rxmofoverruns; + u32 rxdmaoverruns; +}; + struct cpsw_slave { void __iomem *regs; struct cpsw_sliver_regs __iomem *sliver; @@ -332,6 +372,7 @@ struct cpsw_priv { struct cpsw_platform_data data; struct cpsw_ss_regs __iomem *regs; struct cpsw_wr_regs __iomem *wr_regs; + u8 __iomem *hw_stats; struct cpsw_host_regs __iomem *host_port_regs; u32 msg_enable; u32 version; @@ -354,6 +395,94 @@ struct cpsw_priv { u32 emac_port; }; +struct cpsw_stats { + char stat_string[ETH_GSTRING_LEN]; + int type; + int sizeof_stat; + int stat_offset; +}; + +enum { + CPSW_STATS, + CPDMA_RX_STATS, + CPDMA_TX_STATS, +}; + +#define CPSW_STAT(m) CPSW_STATS, \ + sizeof(((struct cpsw_hw_stats *)0)->m), \ + offsetof(struct cpsw_hw_stats, m) +#define CPDMA_RX_STAT(m) CPDMA_RX_STATS, \ + sizeof(((struct cpdma_chan_stats *)0)->m), \ + offsetof(struct cpdma_chan_stats, m) +#define CPDMA_TX_STAT(m) CPDMA_TX_STATS, \ + sizeof(((struct cpdma_chan_stats *)0)->m), \ + offsetof(struct cpdma_chan_stats, m) + +static const struct cpsw_stats cpsw_gstrings_stats[] = { + { "Good Rx Frames", CPSW_STAT(rxgoodframes) }, + { "Broadcast Rx Frames", CPSW_STAT(rxbroadcastframes) }, + { "Multicast Rx Frames", CPSW_STAT(rxmulticastframes) }, + { "Pause Rx Frames", CPSW_STAT(rxpauseframes) }, + { "Rx CRC Errors", CPSW_STAT(rxcrcerrors) }, + { "Rx Align/Code Errors", CPSW_STAT(rxaligncodeerrors) }, + { "Oversize Rx Frames", CPSW_STAT(rxoversizedframes) }, + { "Rx Jabbers", CPSW_STAT(rxjabberframes) }, + { "Undersize (Short) Rx Frames", CPSW_STAT(rxundersizedframes) }, + { "Rx Fragments", CPSW_STAT(rxfragments) }, + { "Rx Octets", CPSW_STAT(rxoctets) }, + { "Good Tx Frames", CPSW_STAT(txgoodframes) }, + { "Broadcast Tx Frames", CPSW_STAT(txbroadcastframes) }, + { "Multicast Tx Frames", CPSW_STAT(txmulticastframes) }, + { "Pause Tx Frames", CPSW_STAT(txpauseframes) }, + { "Deferred Tx Frames", CPSW_STAT(txdeferredframes) }, + { "Collisions", CPSW_STAT(txcollisionframes) }, + { "Single Collision Tx Frames", CPSW_STAT(txsinglecollframes) }, + { "Multiple Collision Tx Frames", CPSW_STAT(txmultcollframes) }, + { "Excessive Collisions", CPSW_STAT(txexcessivecollisions) }, + { "Late Collisions", CPSW_STAT(txlatecollisions) }, + { "Tx Underrun", CPSW_STAT(txunderrun) }, + { "Carrier Sense Errors", CPSW_STAT(txcarriersenseerrors) }, + { "Tx Octets", CPSW_STAT(txoctets) }, + { "Rx + Tx 64 Octet Frames", CPSW_STAT(octetframes64) }, + { "Rx + Tx 65-127 Octet Frames", CPSW_STAT(octetframes65t127) }, + { "Rx + Tx 128-255 Octet Frames", CPSW_STAT(octetframes128t255) }, + { "Rx + Tx 256-511 Octet Frames", CPSW_STAT(octetframes256t511) }, + { "Rx + Tx 512-1023 Octet Frames", CPSW_STAT(octetframes512t1023) }, + { "Rx + Tx 1024-Up Octet Frames", CPSW_STAT(octetframes1024tup) }, + { "Net Octets", CPSW_STAT(netoctets) }, + { "Rx Start of Frame Overruns", CPSW_STAT(rxsofoverruns) }, + { "Rx Middle of Frame Overruns", CPSW_STAT(rxmofoverruns) }, + { "Rx DMA Overruns", CPSW_STAT(rxdmaoverruns) }, + { "Rx DMA chan: head_enqueue", CPDMA_RX_STAT(head_enqueue) }, + { "Rx DMA chan: tail_enqueue", CPDMA_RX_STAT(tail_enqueue) }, + { "Rx DMA chan: pad_enqueue", CPDMA_RX_STAT(pad_enqueue) }, + { "Rx DMA chan: misqueued", CPDMA_RX_STAT(misqueued) }, + { "Rx DMA chan: desc_alloc_fail", CPDMA_RX_STAT(desc_alloc_fail) }, + { "Rx DMA chan: pad_alloc_fail", CPDMA_RX_STAT(pad_alloc_fail) }, + { "Rx DMA chan: runt_receive_buf", CPDMA_RX_STAT(runt_receive_buff) }, + { "Rx DMA chan: runt_transmit_buf", CPDMA_RX_STAT(runt_transmit_buff) }, + { "Rx DMA chan: empty_dequeue", CPDMA_RX_STAT(empty_dequeue) }, + { "Rx DMA chan: busy_dequeue", CPDMA_RX_STAT(busy_dequeue) }, + { "Rx DMA chan: good_dequeue", CPDMA_RX_STAT(good_dequeue) }, + { "Rx DMA chan: requeue", CPDMA_RX_STAT(requeue) }, + { "Rx DMA chan: teardown_dequeue", CPDMA_RX_STAT(teardown_dequeue) }, + { "Tx DMA chan: head_enqueue", CPDMA_TX_STAT(head_enqueue) }, + { "Tx DMA chan: tail_enqueue", CPDMA_TX_STAT(tail_enqueue) }, + { "Tx DMA chan: pad_enqueue", CPDMA_TX_STAT(pad_enqueue) }, + { "Tx DMA chan: misqueued", CPDMA_TX_STAT(misqueued) }, + { "Tx DMA chan: desc_alloc_fail", CPDMA_TX_STAT(desc_alloc_fail) }, + { "Tx DMA chan: pad_alloc_fail", CPDMA_TX_STAT(pad_alloc_fail) }, + { "Tx DMA chan: runt_receive_buf", CPDMA_TX_STAT(runt_receive_buff) }, + { "Tx DMA chan: runt_transmit_buf", CPDMA_TX_STAT(runt_transmit_buff) }, + { "Tx DMA chan: empty_dequeue", CPDMA_TX_STAT(empty_dequeue) }, + { "Tx DMA chan: busy_dequeue", CPDMA_TX_STAT(busy_dequeue) }, + { "Tx DMA chan: good_dequeue", CPDMA_TX_STAT(good_dequeue) }, + { "Tx DMA chan: requeue", CPDMA_TX_STAT(requeue) }, + { "Tx DMA chan: teardown_dequeue", CPDMA_TX_STAT(teardown_dequeue) }, +}; + +#define CPSW_STATS_LEN ARRAY_SIZE(cpsw_gstrings_stats) + #define napi_to_priv(napi) container_of(napi, struct cpsw_priv, napi) #define for_each_slave(priv, func, arg...) \ do { \ @@ -723,6 +852,69 @@ static int cpsw_set_coalesce(struct net_device *ndev, return 0; } +static int cpsw_get_sset_count(struct net_device *ndev, int sset) +{ + switch (sset) { + case ETH_SS_STATS: + return CPSW_STATS_LEN; + default: + return -EOPNOTSUPP; + } +} + +static void cpsw_get_strings(struct net_device *ndev, u32 stringset, u8 *data) +{ + u8 *p = data; + int i; + + switch (stringset) { + case ETH_SS_STATS: + for (i = 0; i < CPSW_STATS_LEN; i++) { + memcpy(p, cpsw_gstrings_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + break; + } +} + +static void cpsw_get_ethtool_stats(struct net_device *ndev, + struct ethtool_stats *stats, u64 *data) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + struct cpdma_chan_stats rx_stats; + struct cpdma_chan_stats tx_stats; + u32 val; + u8 *p; + int i; + + /* Collect Davinci CPDMA stats for Rx and Tx Channel */ + cpdma_chan_get_stats(priv->rxch, &rx_stats); + cpdma_chan_get_stats(priv->txch, &tx_stats); + + for (i = 0; i < CPSW_STATS_LEN; i++) { + switch (cpsw_gstrings_stats[i].type) { + case CPSW_STATS: + val = readl(priv->hw_stats + + cpsw_gstrings_stats[i].stat_offset); + data[i] = val; + break; + + case CPDMA_RX_STATS: + p = (u8 *)&rx_stats + + cpsw_gstrings_stats[i].stat_offset; + data[i] = *(u32 *)p; + break; + + case CPDMA_TX_STATS: + p = (u8 *)&tx_stats + + cpsw_gstrings_stats[i].stat_offset; + data[i] = *(u32 *)p; + break; + } + } +} + static inline int __show_stat(char *buf, int maxlen, const char *name, u32 val) { static char *leader = "........................................"; @@ -1232,6 +1424,33 @@ static void cpsw_ndo_tx_timeout(struct net_device *ndev) } +static int cpsw_ndo_set_mac_address(struct net_device *ndev, void *p) +{ + struct cpsw_priv *priv = netdev_priv(ndev); + struct sockaddr *addr = (struct sockaddr *)p; + int flags = 0; + u16 vid = 0; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + if (priv->data.dual_emac) { + vid = priv->slaves[priv->emac_port].port_vlan; + flags = ALE_VLAN; + } + + cpsw_ale_del_ucast(priv->ale, priv->mac_addr, priv->host_port, + flags, vid); + cpsw_ale_add_ucast(priv->ale, addr->sa_data, priv->host_port, + flags, vid); + + memcpy(priv->mac_addr, addr->sa_data, ETH_ALEN); + memcpy(ndev->dev_addr, priv->mac_addr, ETH_ALEN); + for_each_slave(priv, cpsw_set_slave_mac, priv); + + return 0; +} + static struct net_device_stats *cpsw_ndo_get_stats(struct net_device *ndev) { struct cpsw_priv *priv = netdev_priv(ndev); @@ -1326,6 +1545,7 @@ static const struct net_device_ops cpsw_netdev_ops = { .ndo_stop = cpsw_ndo_stop, .ndo_start_xmit = cpsw_ndo_start_xmit, .ndo_change_rx_flags = cpsw_ndo_change_rx_flags, + .ndo_set_mac_address = cpsw_ndo_set_mac_address, .ndo_do_ioctl = cpsw_ndo_ioctl, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = eth_change_mtu, @@ -1426,6 +1646,9 @@ static const struct ethtool_ops cpsw_ethtool_ops = { .set_settings = cpsw_set_settings, .get_coalesce = cpsw_get_coalesce, .set_coalesce = cpsw_set_coalesce, + .get_sset_count = cpsw_get_sset_count, + .get_strings = cpsw_get_strings, + .get_ethtool_stats = cpsw_get_ethtool_stats, }; static void cpsw_slave_init(struct cpsw_slave *slave, struct cpsw_priv *priv, @@ -1623,6 +1846,7 @@ static int cpsw_probe_dual_emac(struct platform_device *pdev, priv_sl2->host_port = priv->host_port; priv_sl2->host_port_regs = priv->host_port_regs; priv_sl2->wr_regs = priv->wr_regs; + priv_sl2->hw_stats = priv->hw_stats; priv_sl2->dma = priv->dma; priv_sl2->txch = priv->txch; priv_sl2->rxch = priv->rxch; @@ -1780,7 +2004,8 @@ static int cpsw_probe(struct platform_device *pdev) switch (priv->version) { case CPSW_VERSION_1: priv->host_port_regs = ss_regs + CPSW1_HOST_PORT_OFFSET; - priv->cpts->reg = ss_regs + CPSW1_CPTS_OFFSET; + priv->cpts->reg = ss_regs + CPSW1_CPTS_OFFSET; + priv->hw_stats = ss_regs + CPSW1_HW_STATS; dma_params.dmaregs = ss_regs + CPSW1_CPDMA_OFFSET; dma_params.txhdp = ss_regs + CPSW1_STATERAM_OFFSET; ale_params.ale_regs = ss_regs + CPSW1_ALE_OFFSET; @@ -1791,7 +2016,8 @@ static int cpsw_probe(struct platform_device *pdev) break; case CPSW_VERSION_2: priv->host_port_regs = ss_regs + CPSW2_HOST_PORT_OFFSET; - priv->cpts->reg = ss_regs + CPSW2_CPTS_OFFSET; + priv->cpts->reg = ss_regs + CPSW2_CPTS_OFFSET; + priv->hw_stats = ss_regs + CPSW2_HW_STATS; dma_params.dmaregs = ss_regs + CPSW2_CPDMA_OFFSET; dma_params.txhdp = ss_regs + CPSW2_STATERAM_OFFSET; ale_params.ale_regs = ss_regs + CPSW2_ALE_OFFSET; diff --git a/drivers/net/ethernet/tile/Kconfig b/drivers/net/ethernet/tile/Kconfig index 098b1c42b393..4083ba8839e1 100644 --- a/drivers/net/ethernet/tile/Kconfig +++ b/drivers/net/ethernet/tile/Kconfig @@ -15,3 +15,14 @@ config TILE_NET To compile this driver as a module, choose M here: the module will be called tile_net. + +config PTP_1588_CLOCK_TILEGX + tristate "Tilera TILE-Gx mPIPE as PTP clock" + select PTP_1588_CLOCK + depends on TILE_NET + depends on TILEGX + ---help--- + This driver adds support for using the mPIPE as a PTP + clock. This clock is only useful if your PTP programs are + getting hardware time stamps on the PTP Ethernet packets + using the SO_TIMESTAMPING API. diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c index f3c2d034b32c..907b5772fd55 100644 --- a/drivers/net/ethernet/tile/tilegx.c +++ b/drivers/net/ethernet/tile/tilegx.c @@ -36,7 +36,10 @@ #include <linux/io.h> #include <linux/ctype.h> #include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/tcp.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> #include <asm/checksum.h> #include <asm/homecache.h> @@ -76,6 +79,9 @@ #define MAX_FRAGS (MAX_SKB_FRAGS + 1) +/* The "kinds" of buffer stacks (small/large/jumbo). */ +#define MAX_KINDS 3 + /* Size of completions data to allocate. * ISSUE: Probably more than needed since we don't use all the channels. */ @@ -130,29 +136,31 @@ struct tile_net_tx_wake { /* Info for a specific cpu. */ struct tile_net_info { - /* The NAPI struct. */ - struct napi_struct napi; - /* Packet queue. */ - gxio_mpipe_iqueue_t iqueue; /* Our cpu. */ int my_cpu; - /* True if iqueue is valid. */ - bool has_iqueue; - /* NAPI flags. */ - bool napi_added; - bool napi_enabled; - /* Number of small sk_buffs which must still be provided. */ - unsigned int num_needed_small_buffers; - /* Number of large sk_buffs which must still be provided. */ - unsigned int num_needed_large_buffers; /* A timer for handling egress completions. */ struct hrtimer egress_timer; /* True if "egress_timer" is scheduled. */ bool egress_timer_scheduled; - /* Comps for each egress channel. */ - struct tile_net_comps *comps_for_echannel[TILE_NET_CHANNELS]; - /* Transmit wake timer for each egress channel. */ - struct tile_net_tx_wake tx_wake[TILE_NET_CHANNELS]; + struct info_mpipe { + /* Packet queue. */ + gxio_mpipe_iqueue_t iqueue; + /* The NAPI struct. */ + struct napi_struct napi; + /* Number of buffers (by kind) which must still be provided. */ + unsigned int num_needed_buffers[MAX_KINDS]; + /* instance id. */ + int instance; + /* True if iqueue is valid. */ + bool has_iqueue; + /* NAPI flags. */ + bool napi_added; + bool napi_enabled; + /* Comps for each egress channel. */ + struct tile_net_comps *comps_for_echannel[TILE_NET_CHANNELS]; + /* Transmit wake timer for each egress channel. */ + struct tile_net_tx_wake tx_wake[TILE_NET_CHANNELS]; + } mpipe[NR_MPIPE_MAX]; }; /* Info for egress on a particular egress channel. */ @@ -177,19 +185,67 @@ struct tile_net_priv { int loopify_channel; /* The egress channel (channel or loopify_channel). */ int echannel; - /* Total stats. */ - struct net_device_stats stats; + /* mPIPE instance, 0 or 1. */ + int instance; +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + /* The timestamp config. */ + struct hwtstamp_config stamp_cfg; +#endif }; -/* Egress info, indexed by "priv->echannel" (lazily created as needed). */ -static struct tile_net_egress egress_for_echannel[TILE_NET_CHANNELS]; +static struct mpipe_data { + /* The ingress irq. */ + int ingress_irq; -/* Devices currently associated with each channel. - * NOTE: The array entry can become NULL after ifconfig down, but - * we do not free the underlying net_device structures, so it is - * safe to use a pointer after reading it from this array. - */ -static struct net_device *tile_net_devs_for_channel[TILE_NET_CHANNELS]; + /* The "context" for all devices. */ + gxio_mpipe_context_t context; + + /* Egress info, indexed by "priv->echannel" + * (lazily created as needed). + */ + struct tile_net_egress + egress_for_echannel[TILE_NET_CHANNELS]; + + /* Devices currently associated with each channel. + * NOTE: The array entry can become NULL after ifconfig down, but + * we do not free the underlying net_device structures, so it is + * safe to use a pointer after reading it from this array. + */ + struct net_device + *tile_net_devs_for_channel[TILE_NET_CHANNELS]; + + /* The actual memory allocated for the buffer stacks. */ + void *buffer_stack_vas[MAX_KINDS]; + + /* The amount of memory allocated for each buffer stack. */ + size_t buffer_stack_bytes[MAX_KINDS]; + + /* The first buffer stack index + * (small = +0, large = +1, jumbo = +2). + */ + int first_buffer_stack; + + /* The buckets. */ + int first_bucket; + int num_buckets; + +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + /* PTP-specific data. */ + struct ptp_clock *ptp_clock; + struct ptp_clock_info caps; + + /* Lock for ptp accessors. */ + struct mutex ptp_lock; +#endif + +} mpipe_data[NR_MPIPE_MAX] = { + [0 ... (NR_MPIPE_MAX - 1)] { + .ingress_irq = -1, + .first_buffer_stack = -1, + .first_bucket = -1, + .num_buckets = 1 + } +}; /* A mutex for "tile_net_devs_for_channel". */ static DEFINE_MUTEX(tile_net_devs_for_channel_mutex); @@ -197,34 +253,17 @@ static DEFINE_MUTEX(tile_net_devs_for_channel_mutex); /* The per-cpu info. */ static DEFINE_PER_CPU(struct tile_net_info, per_cpu_info); -/* The "context" for all devices. */ -static gxio_mpipe_context_t context; -/* Buffer sizes and mpipe enum codes for buffer stacks. +/* The buffer size enums for each buffer stack. * See arch/tile/include/gxio/mpipe.h for the set of possible values. + * We avoid the "10384" size because it can induce "false chaining" + * on "cut-through" jumbo packets. */ -#define BUFFER_SIZE_SMALL_ENUM GXIO_MPIPE_BUFFER_SIZE_128 -#define BUFFER_SIZE_SMALL 128 -#define BUFFER_SIZE_LARGE_ENUM GXIO_MPIPE_BUFFER_SIZE_1664 -#define BUFFER_SIZE_LARGE 1664 - -/* The small/large "buffer stacks". */ -static int small_buffer_stack = -1; -static int large_buffer_stack = -1; - -/* Amount of memory allocated for each buffer stack. */ -static size_t buffer_stack_size; - -/* The actual memory allocated for the buffer stacks. */ -static void *small_buffer_stack_va; -static void *large_buffer_stack_va; - -/* The buckets. */ -static int first_bucket = -1; -static int num_buckets = 1; - -/* The ingress irq. */ -static int ingress_irq = -1; +static gxio_mpipe_buffer_size_enum_t buffer_size_enums[MAX_KINDS] = { + GXIO_MPIPE_BUFFER_SIZE_128, + GXIO_MPIPE_BUFFER_SIZE_1664, + GXIO_MPIPE_BUFFER_SIZE_16384 +}; /* Text value of tile_net.cpus if passed as a module parameter. */ static char *network_cpus_string; @@ -232,11 +271,21 @@ static char *network_cpus_string; /* The actual cpus in "network_cpus". */ static struct cpumask network_cpus_map; -/* If "loopify=LINK" was specified, this is "LINK". */ +/* If "tile_net.loopify=LINK" was specified, this is "LINK". */ static char *loopify_link_name; -/* If "tile_net.custom" was specified, this is non-NULL. */ -static char *custom_str; +/* If "tile_net.custom" was specified, this is true. */ +static bool custom_flag; + +/* If "tile_net.jumbo=NUM" was specified, this is "NUM". */ +static uint jumbo_num; + +/* Obtain mpipe instance from struct tile_net_priv given struct net_device. */ +static inline int mpipe_instance(struct net_device *dev) +{ + struct tile_net_priv *priv = netdev_priv(dev); + return priv->instance; +} /* The "tile_net.cpus" argument specifies the cpus that are dedicated * to handle ingress packets. @@ -289,9 +338,15 @@ MODULE_PARM_DESC(loopify, "name the device to use loop0/1 for ingress/egress"); /* The "tile_net.custom" argument causes us to ignore the "conventional" * classifier metadata, in particular, the "l2_offset". */ -module_param_named(custom, custom_str, charp, 0444); +module_param_named(custom, custom_flag, bool, 0444); MODULE_PARM_DESC(custom, "indicates a (heavily) customized classifier"); +/* The "tile_net.jumbo" argument causes us to support "jumbo" packets, + * and to allocate the given number of "jumbo" buffers. + */ +module_param_named(jumbo, jumbo_num, uint, 0444); +MODULE_PARM_DESC(jumbo, "the number of buffers to support jumbo packets"); + /* Atomically update a statistics field. * Note that on TILE-Gx, this operation is fire-and-forget on the * issuing core (single-cycle dispatch) and takes only a few cycles @@ -305,15 +360,16 @@ static void tile_net_stats_add(unsigned long value, unsigned long *field) } /* Allocate and push a buffer. */ -static bool tile_net_provide_buffer(bool small) +static bool tile_net_provide_buffer(int instance, int kind) { - int stack = small ? small_buffer_stack : large_buffer_stack; + struct mpipe_data *md = &mpipe_data[instance]; + gxio_mpipe_buffer_size_enum_t bse = buffer_size_enums[kind]; + size_t bs = gxio_mpipe_buffer_size_enum_to_buffer_size(bse); const unsigned long buffer_alignment = 128; struct sk_buff *skb; int len; - len = sizeof(struct sk_buff **) + buffer_alignment; - len += (small ? BUFFER_SIZE_SMALL : BUFFER_SIZE_LARGE); + len = sizeof(struct sk_buff **) + buffer_alignment + bs; skb = dev_alloc_skb(len); if (skb == NULL) return false; @@ -328,7 +384,7 @@ static bool tile_net_provide_buffer(bool small) /* Make sure "skb" and the back-pointer have been flushed. */ wmb(); - gxio_mpipe_push_buffer(&context, stack, + gxio_mpipe_push_buffer(&md->context, md->first_buffer_stack + kind, (void *)va_to_tile_io_addr(skb->data)); return true; @@ -354,11 +410,14 @@ static struct sk_buff *mpipe_buf_to_skb(void *va) return skb; } -static void tile_net_pop_all_buffers(int stack) +static void tile_net_pop_all_buffers(int instance, int stack) { + struct mpipe_data *md = &mpipe_data[instance]; + for (;;) { tile_io_addr_t addr = - (tile_io_addr_t)gxio_mpipe_pop_buffer(&context, stack); + (tile_io_addr_t)gxio_mpipe_pop_buffer(&md->context, + stack); if (addr == 0) break; dev_kfree_skb_irq(mpipe_buf_to_skb(tile_io_addr_to_va(addr))); @@ -369,24 +428,111 @@ static void tile_net_pop_all_buffers(int stack) static void tile_net_provide_needed_buffers(void) { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + int instance, kind; + for (instance = 0; instance < NR_MPIPE_MAX && + info->mpipe[instance].has_iqueue; instance++) { + for (kind = 0; kind < MAX_KINDS; kind++) { + while (info->mpipe[instance].num_needed_buffers[kind] + != 0) { + if (!tile_net_provide_buffer(instance, kind)) { + pr_notice("Tile %d still needs" + " some buffers\n", + info->my_cpu); + return; + } + info->mpipe[instance]. + num_needed_buffers[kind]--; + } + } + } +} - while (info->num_needed_small_buffers != 0) { - if (!tile_net_provide_buffer(true)) - goto oops; - info->num_needed_small_buffers--; +/* Get RX timestamp, and store it in the skb. */ +static void tile_rx_timestamp(struct tile_net_priv *priv, struct sk_buff *skb, + gxio_mpipe_idesc_t *idesc) +{ +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + if (unlikely(priv->stamp_cfg.rx_filter != HWTSTAMP_FILTER_NONE)) { + struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(*shhwtstamps)); + shhwtstamps->hwtstamp = ktime_set(idesc->time_stamp_sec, + idesc->time_stamp_ns); } +#endif +} - while (info->num_needed_large_buffers != 0) { - if (!tile_net_provide_buffer(false)) - goto oops; - info->num_needed_large_buffers--; +/* Get TX timestamp, and store it in the skb. */ +static void tile_tx_timestamp(struct sk_buff *skb, int instance) +{ +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + struct skb_shared_info *shtx = skb_shinfo(skb); + if (unlikely((shtx->tx_flags & SKBTX_HW_TSTAMP) != 0)) { + struct mpipe_data *md = &mpipe_data[instance]; + struct skb_shared_hwtstamps shhwtstamps; + struct timespec ts; + + shtx->tx_flags |= SKBTX_IN_PROGRESS; + gxio_mpipe_get_timestamp(&md->context, &ts); + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb, &shhwtstamps); } +#endif +} + +/* Use ioctl() to enable or disable TX or RX timestamping. */ +static int tile_hwtstamp_ioctl(struct net_device *dev, struct ifreq *rq, + int cmd) +{ +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + struct hwtstamp_config config; + struct tile_net_priv *priv = netdev_priv(dev); - return; + if (copy_from_user(&config, rq->ifr_data, sizeof(config))) + return -EFAULT; + + if (config.flags) /* reserved for future extensions */ + return -EINVAL; -oops: - /* Add a description to the page allocation failure dump. */ - pr_notice("Tile %d still needs some buffers\n", info->my_cpu); + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + if (copy_to_user(rq->ifr_data, &config, sizeof(config))) + return -EFAULT; + + priv->stamp_cfg = config; + return 0; +#else + return -EOPNOTSUPP; +#endif } static inline bool filter_packet(struct net_device *dev, void *buf) @@ -409,6 +555,7 @@ static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb, { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); struct tile_net_priv *priv = netdev_priv(dev); + int instance = priv->instance; /* Encode the actual packet length. */ skb_put(skb, len); @@ -419,47 +566,52 @@ static void tile_net_receive_skb(struct net_device *dev, struct sk_buff *skb, if (idesc->cs && idesc->csum_seed_val == 0xFFFF) skb->ip_summed = CHECKSUM_UNNECESSARY; - netif_receive_skb(skb); + /* Get RX timestamp from idesc. */ + tile_rx_timestamp(priv, skb, idesc); + + napi_gro_receive(&info->mpipe[instance].napi, skb); /* Update stats. */ - tile_net_stats_add(1, &priv->stats.rx_packets); - tile_net_stats_add(len, &priv->stats.rx_bytes); + tile_net_stats_add(1, &dev->stats.rx_packets); + tile_net_stats_add(len, &dev->stats.rx_bytes); /* Need a new buffer. */ - if (idesc->size == BUFFER_SIZE_SMALL_ENUM) - info->num_needed_small_buffers++; + if (idesc->size == buffer_size_enums[0]) + info->mpipe[instance].num_needed_buffers[0]++; + else if (idesc->size == buffer_size_enums[1]) + info->mpipe[instance].num_needed_buffers[1]++; else - info->num_needed_large_buffers++; + info->mpipe[instance].num_needed_buffers[2]++; } /* Handle a packet. Return true if "processed", false if "filtered". */ -static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc) +static bool tile_net_handle_packet(int instance, gxio_mpipe_idesc_t *idesc) { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); - struct net_device *dev = tile_net_devs_for_channel[idesc->channel]; + struct mpipe_data *md = &mpipe_data[instance]; + struct net_device *dev = md->tile_net_devs_for_channel[idesc->channel]; uint8_t l2_offset; void *va; void *buf; unsigned long len; bool filter; - /* Drop packets for which no buffer was available. - * NOTE: This happens under heavy load. + /* Drop packets for which no buffer was available (which can + * happen under heavy load), or for which the me/tr/ce flags + * are set (which can happen for jumbo cut-through packets, + * or with a customized classifier). */ - if (idesc->be) { - struct tile_net_priv *priv = netdev_priv(dev); - tile_net_stats_add(1, &priv->stats.rx_dropped); - gxio_mpipe_iqueue_consume(&info->iqueue, idesc); - if (net_ratelimit()) - pr_info("Dropping packet (insufficient buffers).\n"); - return false; + if (idesc->be || idesc->me || idesc->tr || idesc->ce) { + if (dev) + tile_net_stats_add(1, &dev->stats.rx_errors); + goto drop; } /* Get the "l2_offset", if allowed. */ - l2_offset = custom_str ? 0 : gxio_mpipe_idesc_get_l2_offset(idesc); + l2_offset = custom_flag ? 0 : gxio_mpipe_idesc_get_l2_offset(idesc); - /* Get the raw buffer VA (includes "headroom"). */ - va = tile_io_addr_to_va((unsigned long)(long)idesc->va); + /* Get the VA (including NET_IP_ALIGN bytes of "headroom"). */ + va = tile_io_addr_to_va((unsigned long)idesc->va); /* Get the actual packet start/length. */ buf = va + l2_offset; @@ -470,7 +622,10 @@ static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc) filter = filter_packet(dev, buf); if (filter) { - gxio_mpipe_iqueue_drop(&info->iqueue, idesc); + if (dev) + tile_net_stats_add(1, &dev->stats.rx_dropped); +drop: + gxio_mpipe_iqueue_drop(&info->mpipe[instance].iqueue, idesc); } else { struct sk_buff *skb = mpipe_buf_to_skb(va); @@ -480,7 +635,7 @@ static bool tile_net_handle_packet(gxio_mpipe_idesc_t *idesc) tile_net_receive_skb(dev, skb, idesc, len); } - gxio_mpipe_iqueue_consume(&info->iqueue, idesc); + gxio_mpipe_iqueue_consume(&info->mpipe[instance].iqueue, idesc); return !filter; } @@ -501,14 +656,20 @@ static int tile_net_poll(struct napi_struct *napi, int budget) struct tile_net_info *info = &__get_cpu_var(per_cpu_info); unsigned int work = 0; gxio_mpipe_idesc_t *idesc; - int i, n; - - /* Process packets. */ - while ((n = gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc)) > 0) { + int instance, i, n; + struct mpipe_data *md; + struct info_mpipe *info_mpipe = + container_of(napi, struct info_mpipe, napi); + + instance = info_mpipe->instance; + while ((n = gxio_mpipe_iqueue_try_peek( + &info_mpipe->iqueue, + &idesc)) > 0) { for (i = 0; i < n; i++) { if (i == TILE_NET_BATCH) goto done; - if (tile_net_handle_packet(idesc + i)) { + if (tile_net_handle_packet(instance, + idesc + i)) { if (++work >= budget) goto done; } @@ -516,14 +677,16 @@ static int tile_net_poll(struct napi_struct *napi, int budget) } /* There are no packets left. */ - napi_complete(&info->napi); + napi_complete(&info_mpipe->napi); + md = &mpipe_data[instance]; /* Re-enable hypervisor interrupts. */ - gxio_mpipe_enable_notif_ring_interrupt(&context, info->iqueue.ring); + gxio_mpipe_enable_notif_ring_interrupt( + &md->context, info->mpipe[instance].iqueue.ring); /* HACK: Avoid the "rotting packet" problem. */ - if (gxio_mpipe_iqueue_try_peek(&info->iqueue, &idesc) > 0) - napi_schedule(&info->napi); + if (gxio_mpipe_iqueue_try_peek(&info_mpipe->iqueue, &idesc) > 0) + napi_schedule(&info_mpipe->napi); /* ISSUE: Handle completions? */ @@ -533,11 +696,11 @@ done: return work; } -/* Handle an ingress interrupt on the current cpu. */ -static irqreturn_t tile_net_handle_ingress_irq(int irq, void *unused) +/* Handle an ingress interrupt from an instance on the current cpu. */ +static irqreturn_t tile_net_handle_ingress_irq(int irq, void *id) { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); - napi_schedule(&info->napi); + napi_schedule(&info->mpipe[(uint64_t)id].napi); return IRQ_HANDLED; } @@ -579,7 +742,9 @@ static void tile_net_schedule_tx_wake_timer(struct net_device *dev, { struct tile_net_info *info = &per_cpu(per_cpu_info, tx_queue_idx); struct tile_net_priv *priv = netdev_priv(dev); - struct tile_net_tx_wake *tx_wake = &info->tx_wake[priv->echannel]; + int instance = priv->instance; + struct tile_net_tx_wake *tx_wake = + &info->mpipe[instance].tx_wake[priv->echannel]; hrtimer_start(&tx_wake->timer, ktime_set(0, TX_TIMER_DELAY_USEC * 1000UL), @@ -617,7 +782,7 @@ static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t) struct tile_net_info *info = &__get_cpu_var(per_cpu_info); unsigned long irqflags; bool pending = false; - int i; + int i, instance; local_irq_save(irqflags); @@ -625,13 +790,19 @@ static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t) info->egress_timer_scheduled = false; /* Free all possible comps for this tile. */ - for (i = 0; i < TILE_NET_CHANNELS; i++) { - struct tile_net_egress *egress = &egress_for_echannel[i]; - struct tile_net_comps *comps = info->comps_for_echannel[i]; - if (comps->comp_last >= comps->comp_next) - continue; - tile_net_free_comps(egress->equeue, comps, -1, true); - pending = pending || (comps->comp_last < comps->comp_next); + for (instance = 0; instance < NR_MPIPE_MAX && + info->mpipe[instance].has_iqueue; instance++) { + for (i = 0; i < TILE_NET_CHANNELS; i++) { + struct tile_net_egress *egress = + &mpipe_data[instance].egress_for_echannel[i]; + struct tile_net_comps *comps = + info->mpipe[instance].comps_for_echannel[i]; + if (!egress || comps->comp_last >= comps->comp_next) + continue; + tile_net_free_comps(egress->equeue, comps, -1, true); + pending = pending || + (comps->comp_last < comps->comp_next); + } } /* Reschedule timer if needed. */ @@ -643,37 +814,112 @@ static enum hrtimer_restart tile_net_handle_egress_timer(struct hrtimer *t) return HRTIMER_NORESTART; } -/* Helper function for "tile_net_update()". - * "dev" (i.e. arg) is the device being brought up or down, - * or NULL if all devices are now down. - */ -static void tile_net_update_cpu(void *arg) +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + +/* PTP clock operations. */ + +static int ptp_mpipe_adjfreq(struct ptp_clock_info *ptp, s32 ppb) { - struct tile_net_info *info = &__get_cpu_var(per_cpu_info); - struct net_device *dev = arg; + int ret = 0; + struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); + mutex_lock(&md->ptp_lock); + if (gxio_mpipe_adjust_timestamp_freq(&md->context, ppb)) + ret = -EINVAL; + mutex_unlock(&md->ptp_lock); + return ret; +} - if (!info->has_iqueue) - return; +static int ptp_mpipe_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + int ret = 0; + struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); + mutex_lock(&md->ptp_lock); + if (gxio_mpipe_adjust_timestamp(&md->context, delta)) + ret = -EBUSY; + mutex_unlock(&md->ptp_lock); + return ret; +} - if (dev != NULL) { - if (!info->napi_added) { - netif_napi_add(dev, &info->napi, - tile_net_poll, TILE_NET_WEIGHT); - info->napi_added = true; - } - if (!info->napi_enabled) { - napi_enable(&info->napi); - info->napi_enabled = true; - } - enable_percpu_irq(ingress_irq, 0); - } else { - disable_percpu_irq(ingress_irq); - if (info->napi_enabled) { - napi_disable(&info->napi); - info->napi_enabled = false; - } - /* FIXME: Drain the iqueue. */ - } +static int ptp_mpipe_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +{ + int ret = 0; + struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); + mutex_lock(&md->ptp_lock); + if (gxio_mpipe_get_timestamp(&md->context, ts)) + ret = -EBUSY; + mutex_unlock(&md->ptp_lock); + return ret; +} + +static int ptp_mpipe_settime(struct ptp_clock_info *ptp, + const struct timespec *ts) +{ + int ret = 0; + struct mpipe_data *md = container_of(ptp, struct mpipe_data, caps); + mutex_lock(&md->ptp_lock); + if (gxio_mpipe_set_timestamp(&md->context, ts)) + ret = -EBUSY; + mutex_unlock(&md->ptp_lock); + return ret; +} + +static int ptp_mpipe_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *request, int on) +{ + return -EOPNOTSUPP; +} + +static struct ptp_clock_info ptp_mpipe_caps = { + .owner = THIS_MODULE, + .name = "mPIPE clock", + .max_adj = 999999999, + .n_ext_ts = 0, + .pps = 0, + .adjfreq = ptp_mpipe_adjfreq, + .adjtime = ptp_mpipe_adjtime, + .gettime = ptp_mpipe_gettime, + .settime = ptp_mpipe_settime, + .enable = ptp_mpipe_enable, +}; + +#endif /* CONFIG_PTP_1588_CLOCK_TILEGX */ + +/* Sync mPIPE's timestamp up with Linux system time and register PTP clock. */ +static void register_ptp_clock(struct net_device *dev, struct mpipe_data *md) +{ +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + struct timespec ts; + + getnstimeofday(&ts); + gxio_mpipe_set_timestamp(&md->context, &ts); + + mutex_init(&md->ptp_lock); + md->caps = ptp_mpipe_caps; + md->ptp_clock = ptp_clock_register(&md->caps, NULL); + if (IS_ERR(md->ptp_clock)) + netdev_err(dev, "ptp_clock_register failed %ld\n", + PTR_ERR(md->ptp_clock)); +#endif +} + +/* Initialize PTP fields in a new device. */ +static void init_ptp_dev(struct tile_net_priv *priv) +{ +#ifdef CONFIG_PTP_1588_CLOCK_TILEGX + priv->stamp_cfg.rx_filter = HWTSTAMP_FILTER_NONE; + priv->stamp_cfg.tx_type = HWTSTAMP_TX_OFF; +#endif +} + +/* Helper functions for "tile_net_update()". */ +static void enable_ingress_irq(void *irq) +{ + enable_percpu_irq((long)irq, 0); +} + +static void disable_ingress_irq(void *irq) +{ + disable_percpu_irq((long)irq); } /* Helper function for tile_net_open() and tile_net_stop(). @@ -683,19 +929,22 @@ static int tile_net_update(struct net_device *dev) { static gxio_mpipe_rules_t rules; /* too big to fit on the stack */ bool saw_channel = false; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; int channel; int rc; int cpu; - gxio_mpipe_rules_init(&rules, &context); + saw_channel = false; + gxio_mpipe_rules_init(&rules, &md->context); for (channel = 0; channel < TILE_NET_CHANNELS; channel++) { - if (tile_net_devs_for_channel[channel] == NULL) + if (md->tile_net_devs_for_channel[channel] == NULL) continue; if (!saw_channel) { saw_channel = true; - gxio_mpipe_rules_begin(&rules, first_bucket, - num_buckets, NULL); + gxio_mpipe_rules_begin(&rules, md->first_bucket, + md->num_buckets, NULL); gxio_mpipe_rules_set_headroom(&rules, NET_IP_ALIGN); } gxio_mpipe_rules_add_channel(&rules, channel); @@ -706,102 +955,150 @@ static int tile_net_update(struct net_device *dev) */ rc = gxio_mpipe_rules_commit(&rules); if (rc != 0) { - netdev_warn(dev, "gxio_mpipe_rules_commit failed: %d\n", rc); + netdev_warn(dev, "gxio_mpipe_rules_commit: mpipe[%d] %d\n", + instance, rc); return -EIO; } - /* Update all cpus, sequentially (to protect "netif_napi_add()"). */ - for_each_online_cpu(cpu) - smp_call_function_single(cpu, tile_net_update_cpu, - (saw_channel ? dev : NULL), 1); + /* Update all cpus, sequentially (to protect "netif_napi_add()"). + * We use on_each_cpu to handle the IPI mask or unmask. + */ + if (!saw_channel) + on_each_cpu(disable_ingress_irq, + (void *)(long)(md->ingress_irq), 1); + for_each_online_cpu(cpu) { + struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); + + if (!info->mpipe[instance].has_iqueue) + continue; + if (saw_channel) { + if (!info->mpipe[instance].napi_added) { + netif_napi_add(dev, &info->mpipe[instance].napi, + tile_net_poll, TILE_NET_WEIGHT); + info->mpipe[instance].napi_added = true; + } + if (!info->mpipe[instance].napi_enabled) { + napi_enable(&info->mpipe[instance].napi); + info->mpipe[instance].napi_enabled = true; + } + } else { + if (info->mpipe[instance].napi_enabled) { + napi_disable(&info->mpipe[instance].napi); + info->mpipe[instance].napi_enabled = false; + } + /* FIXME: Drain the iqueue. */ + } + } + if (saw_channel) + on_each_cpu(enable_ingress_irq, + (void *)(long)(md->ingress_irq), 1); /* HACK: Allow packets to flow in the simulator. */ if (saw_channel) - sim_enable_mpipe_links(0, -1); + sim_enable_mpipe_links(instance, -1); return 0; } -/* Allocate and initialize mpipe buffer stacks, and register them in - * the mPIPE TLBs, for both small and large packet sizes. - * This routine supports tile_net_init_mpipe(), below. - */ -static int init_buffer_stacks(struct net_device *dev, int num_buffers) +/* Initialize a buffer stack. */ +static int create_buffer_stack(struct net_device *dev, + int kind, size_t num_buffers) { pte_t hash_pte = pte_set_home((pte_t) { 0 }, PAGE_HOME_HASH); - int rc; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; + size_t needed = gxio_mpipe_calc_buffer_stack_bytes(num_buffers); + int stack_idx = md->first_buffer_stack + kind; + void *va; + int i, rc; - /* Compute stack bytes; we round up to 64KB and then use - * alloc_pages() so we get the required 64KB alignment as well. + /* Round up to 64KB and then use alloc_pages() so we get the + * required 64KB alignment. */ - buffer_stack_size = - ALIGN(gxio_mpipe_calc_buffer_stack_bytes(num_buffers), - 64 * 1024); - - /* Allocate two buffer stack indices. */ - rc = gxio_mpipe_alloc_buffer_stacks(&context, 2, 0, 0); - if (rc < 0) { - netdev_err(dev, "gxio_mpipe_alloc_buffer_stacks failed: %d\n", - rc); - return rc; - } - small_buffer_stack = rc; - large_buffer_stack = rc + 1; + md->buffer_stack_bytes[kind] = + ALIGN(needed, 64 * 1024); - /* Allocate the small memory stack. */ - small_buffer_stack_va = - alloc_pages_exact(buffer_stack_size, GFP_KERNEL); - if (small_buffer_stack_va == NULL) { + va = alloc_pages_exact(md->buffer_stack_bytes[kind], GFP_KERNEL); + if (va == NULL) { netdev_err(dev, - "Could not alloc %zd bytes for buffer stacks\n", - buffer_stack_size); + "Could not alloc %zd bytes for buffer stack %d\n", + md->buffer_stack_bytes[kind], kind); return -ENOMEM; } - rc = gxio_mpipe_init_buffer_stack(&context, small_buffer_stack, - BUFFER_SIZE_SMALL_ENUM, - small_buffer_stack_va, - buffer_stack_size, 0); + + /* Initialize the buffer stack. */ + rc = gxio_mpipe_init_buffer_stack(&md->context, stack_idx, + buffer_size_enums[kind], va, + md->buffer_stack_bytes[kind], 0); if (rc != 0) { - netdev_err(dev, "gxio_mpipe_init_buffer_stack: %d\n", rc); + netdev_err(dev, "gxio_mpipe_init_buffer_stack: mpipe[%d] %d\n", + instance, rc); + free_pages_exact(va, md->buffer_stack_bytes[kind]); return rc; } - rc = gxio_mpipe_register_client_memory(&context, small_buffer_stack, + + md->buffer_stack_vas[kind] = va; + + rc = gxio_mpipe_register_client_memory(&md->context, stack_idx, hash_pte, 0); if (rc != 0) { netdev_err(dev, - "gxio_mpipe_register_buffer_memory failed: %d\n", - rc); + "gxio_mpipe_register_client_memory: mpipe[%d] %d\n", + instance, rc); return rc; } - /* Allocate the large buffer stack. */ - large_buffer_stack_va = - alloc_pages_exact(buffer_stack_size, GFP_KERNEL); - if (large_buffer_stack_va == NULL) { - netdev_err(dev, - "Could not alloc %zd bytes for buffer stacks\n", - buffer_stack_size); - return -ENOMEM; - } - rc = gxio_mpipe_init_buffer_stack(&context, large_buffer_stack, - BUFFER_SIZE_LARGE_ENUM, - large_buffer_stack_va, - buffer_stack_size, 0); - if (rc != 0) { - netdev_err(dev, "gxio_mpipe_init_buffer_stack failed: %d\n", - rc); - return rc; + /* Provide initial buffers. */ + for (i = 0; i < num_buffers; i++) { + if (!tile_net_provide_buffer(instance, kind)) { + netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); + return -ENOMEM; + } } - rc = gxio_mpipe_register_client_memory(&context, large_buffer_stack, - hash_pte, 0); - if (rc != 0) { + + return 0; +} + +/* Allocate and initialize mpipe buffer stacks, and register them in + * the mPIPE TLBs, for small, large, and (possibly) jumbo packet sizes. + * This routine supports tile_net_init_mpipe(), below. + */ +static int init_buffer_stacks(struct net_device *dev, + int network_cpus_count) +{ + int num_kinds = MAX_KINDS - (jumbo_num == 0); + size_t num_buffers; + int rc; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; + + /* Allocate the buffer stacks. */ + rc = gxio_mpipe_alloc_buffer_stacks(&md->context, num_kinds, 0, 0); + if (rc < 0) { netdev_err(dev, - "gxio_mpipe_register_buffer_memory failed: %d\n", - rc); + "gxio_mpipe_alloc_buffer_stacks: mpipe[%d] %d\n", + instance, rc); return rc; } + md->first_buffer_stack = rc; - return 0; + /* Enough small/large buffers to (normally) avoid buffer errors. */ + num_buffers = + network_cpus_count * (IQUEUE_ENTRIES + TILE_NET_BATCH); + + /* Allocate the small memory stack. */ + if (rc >= 0) + rc = create_buffer_stack(dev, 0, num_buffers); + + /* Allocate the large buffer stack. */ + if (rc >= 0) + rc = create_buffer_stack(dev, 1, num_buffers); + + /* Allocate the jumbo buffer stack if needed. */ + if (rc >= 0 && jumbo_num != 0) + rc = create_buffer_stack(dev, 2, jumbo_num); + + return rc; } /* Allocate per-cpu resources (memory for completions and idescs). @@ -812,6 +1109,8 @@ static int alloc_percpu_mpipe_resources(struct net_device *dev, { struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); int order, i, rc; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; struct page *page; void *addr; @@ -826,7 +1125,7 @@ static int alloc_percpu_mpipe_resources(struct net_device *dev, addr = pfn_to_kaddr(page_to_pfn(page)); memset(addr, 0, COMPS_SIZE); for (i = 0; i < TILE_NET_CHANNELS; i++) - info->comps_for_echannel[i] = + info->mpipe[instance].comps_for_echannel[i] = addr + i * sizeof(struct tile_net_comps); /* If this is a network cpu, create an iqueue. */ @@ -840,14 +1139,15 @@ static int alloc_percpu_mpipe_resources(struct net_device *dev, return -ENOMEM; } addr = pfn_to_kaddr(page_to_pfn(page)); - rc = gxio_mpipe_iqueue_init(&info->iqueue, &context, ring++, - addr, NOTIF_RING_SIZE, 0); + rc = gxio_mpipe_iqueue_init(&info->mpipe[instance].iqueue, + &md->context, ring++, addr, + NOTIF_RING_SIZE, 0); if (rc < 0) { netdev_err(dev, "gxio_mpipe_iqueue_init failed: %d\n", rc); return rc; } - info->has_iqueue = true; + info->mpipe[instance].has_iqueue = true; } return ring; @@ -860,40 +1160,41 @@ static int init_notif_group_and_buckets(struct net_device *dev, int ring, int network_cpus_count) { int group, rc; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; /* Allocate one NotifGroup. */ - rc = gxio_mpipe_alloc_notif_groups(&context, 1, 0, 0); + rc = gxio_mpipe_alloc_notif_groups(&md->context, 1, 0, 0); if (rc < 0) { - netdev_err(dev, "gxio_mpipe_alloc_notif_groups failed: %d\n", - rc); + netdev_err(dev, "gxio_mpipe_alloc_notif_groups: mpipe[%d] %d\n", + instance, rc); return rc; } group = rc; /* Initialize global num_buckets value. */ if (network_cpus_count > 4) - num_buckets = 256; + md->num_buckets = 256; else if (network_cpus_count > 1) - num_buckets = 16; + md->num_buckets = 16; /* Allocate some buckets, and set global first_bucket value. */ - rc = gxio_mpipe_alloc_buckets(&context, num_buckets, 0, 0); + rc = gxio_mpipe_alloc_buckets(&md->context, md->num_buckets, 0, 0); if (rc < 0) { - netdev_err(dev, "gxio_mpipe_alloc_buckets failed: %d\n", rc); + netdev_err(dev, "gxio_mpipe_alloc_buckets: mpipe[%d] %d\n", + instance, rc); return rc; } - first_bucket = rc; + md->first_bucket = rc; /* Init group and buckets. */ rc = gxio_mpipe_init_notif_group_and_buckets( - &context, group, ring, network_cpus_count, - first_bucket, num_buckets, + &md->context, group, ring, network_cpus_count, + md->first_bucket, md->num_buckets, GXIO_MPIPE_BUCKET_STICKY_FLOW_LOCALITY); if (rc != 0) { - netdev_err( - dev, - "gxio_mpipe_init_notif_group_and_buckets failed: %d\n", - rc); + netdev_err(dev, "gxio_mpipe_init_notif_group_and_buckets: " + "mpipe[%d] %d\n", instance, rc); return rc; } @@ -907,30 +1208,39 @@ static int init_notif_group_and_buckets(struct net_device *dev, */ static int tile_net_setup_interrupts(struct net_device *dev) { - int cpu, rc; + int cpu, rc, irq; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; + + irq = md->ingress_irq; + if (irq < 0) { + irq = create_irq(); + if (irq < 0) { + netdev_err(dev, + "create_irq failed: mpipe[%d] %d\n", + instance, irq); + return irq; + } + tile_irq_activate(irq, TILE_IRQ_PERCPU); - rc = create_irq(); - if (rc < 0) { - netdev_err(dev, "create_irq failed: %d\n", rc); - return rc; - } - ingress_irq = rc; - tile_irq_activate(ingress_irq, TILE_IRQ_PERCPU); - rc = request_irq(ingress_irq, tile_net_handle_ingress_irq, - 0, "tile_net", NULL); - if (rc != 0) { - netdev_err(dev, "request_irq failed: %d\n", rc); - destroy_irq(ingress_irq); - ingress_irq = -1; - return rc; + rc = request_irq(irq, tile_net_handle_ingress_irq, + 0, "tile_net", (void *)((uint64_t)instance)); + + if (rc != 0) { + netdev_err(dev, "request_irq failed: mpipe[%d] %d\n", + instance, rc); + destroy_irq(irq); + return rc; + } + md->ingress_irq = irq; } for_each_online_cpu(cpu) { struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); - if (info->has_iqueue) { - gxio_mpipe_request_notif_ring_interrupt( - &context, cpu_x(cpu), cpu_y(cpu), - KERNEL_PL, ingress_irq, info->iqueue.ring); + if (info->mpipe[instance].has_iqueue) { + gxio_mpipe_request_notif_ring_interrupt(&md->context, + cpu_x(cpu), cpu_y(cpu), KERNEL_PL, irq, + info->mpipe[instance].iqueue.ring); } } @@ -938,39 +1248,45 @@ static int tile_net_setup_interrupts(struct net_device *dev) } /* Undo any state set up partially by a failed call to tile_net_init_mpipe. */ -static void tile_net_init_mpipe_fail(void) +static void tile_net_init_mpipe_fail(int instance) { - int cpu; + int kind, cpu; + struct mpipe_data *md = &mpipe_data[instance]; /* Do cleanups that require the mpipe context first. */ - if (small_buffer_stack >= 0) - tile_net_pop_all_buffers(small_buffer_stack); - if (large_buffer_stack >= 0) - tile_net_pop_all_buffers(large_buffer_stack); + for (kind = 0; kind < MAX_KINDS; kind++) { + if (md->buffer_stack_vas[kind] != NULL) { + tile_net_pop_all_buffers(instance, + md->first_buffer_stack + + kind); + } + } /* Destroy mpipe context so the hardware no longer owns any memory. */ - gxio_mpipe_destroy(&context); + gxio_mpipe_destroy(&md->context); for_each_online_cpu(cpu) { struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); - free_pages((unsigned long)(info->comps_for_echannel[0]), - get_order(COMPS_SIZE)); - info->comps_for_echannel[0] = NULL; - free_pages((unsigned long)(info->iqueue.idescs), + free_pages( + (unsigned long)( + info->mpipe[instance].comps_for_echannel[0]), + get_order(COMPS_SIZE)); + info->mpipe[instance].comps_for_echannel[0] = NULL; + free_pages((unsigned long)(info->mpipe[instance].iqueue.idescs), get_order(NOTIF_RING_SIZE)); - info->iqueue.idescs = NULL; + info->mpipe[instance].iqueue.idescs = NULL; } - if (small_buffer_stack_va) - free_pages_exact(small_buffer_stack_va, buffer_stack_size); - if (large_buffer_stack_va) - free_pages_exact(large_buffer_stack_va, buffer_stack_size); + for (kind = 0; kind < MAX_KINDS; kind++) { + if (md->buffer_stack_vas[kind] != NULL) { + free_pages_exact(md->buffer_stack_vas[kind], + md->buffer_stack_bytes[kind]); + md->buffer_stack_vas[kind] = NULL; + } + } - small_buffer_stack_va = NULL; - large_buffer_stack_va = NULL; - large_buffer_stack = -1; - small_buffer_stack = -1; - first_bucket = -1; + md->first_buffer_stack = -1; + md->first_bucket = -1; } /* The first time any tilegx network device is opened, we initialize @@ -984,9 +1300,11 @@ static void tile_net_init_mpipe_fail(void) */ static int tile_net_init_mpipe(struct net_device *dev) { - int i, num_buffers, rc; + int rc; int cpu; int first_ring, ring; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; int network_cpus_count = cpus_weight(network_cpus_map); if (!hash_default) { @@ -994,36 +1312,21 @@ static int tile_net_init_mpipe(struct net_device *dev) return -EIO; } - rc = gxio_mpipe_init(&context, 0); + rc = gxio_mpipe_init(&md->context, instance); if (rc != 0) { - netdev_err(dev, "gxio_mpipe_init failed: %d\n", rc); + netdev_err(dev, "gxio_mpipe_init: mpipe[%d] %d\n", + instance, rc); return -EIO; } /* Set up the buffer stacks. */ - num_buffers = - network_cpus_count * (IQUEUE_ENTRIES + TILE_NET_BATCH); - rc = init_buffer_stacks(dev, num_buffers); + rc = init_buffer_stacks(dev, network_cpus_count); if (rc != 0) goto fail; - /* Provide initial buffers. */ - rc = -ENOMEM; - for (i = 0; i < num_buffers; i++) { - if (!tile_net_provide_buffer(true)) { - netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); - goto fail; - } - } - for (i = 0; i < num_buffers; i++) { - if (!tile_net_provide_buffer(false)) { - netdev_err(dev, "Cannot allocate initial sk_bufs!\n"); - goto fail; - } - } - /* Allocate one NotifRing for each network cpu. */ - rc = gxio_mpipe_alloc_notif_rings(&context, network_cpus_count, 0, 0); + rc = gxio_mpipe_alloc_notif_rings(&md->context, + network_cpus_count, 0, 0); if (rc < 0) { netdev_err(dev, "gxio_mpipe_alloc_notif_rings failed %d\n", rc); @@ -1050,10 +1353,13 @@ static int tile_net_init_mpipe(struct net_device *dev) if (rc != 0) goto fail; + /* Register PTP clock and set mPIPE timestamp, if configured. */ + register_ptp_clock(dev, md); + return 0; fail: - tile_net_init_mpipe_fail(); + tile_net_init_mpipe_fail(instance); return rc; } @@ -1063,17 +1369,19 @@ fail: */ static int tile_net_init_egress(struct net_device *dev, int echannel) { + static int ering = -1; struct page *headers_page, *edescs_page, *equeue_page; gxio_mpipe_edesc_t *edescs; gxio_mpipe_equeue_t *equeue; unsigned char *headers; int headers_order, edescs_order, equeue_order; size_t edescs_size; - int edma; int rc = -ENOMEM; + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; /* Only initialize once. */ - if (egress_for_echannel[echannel].equeue != NULL) + if (md->egress_for_echannel[echannel].equeue != NULL) return 0; /* Allocate memory for the "headers". */ @@ -1110,28 +1418,41 @@ static int tile_net_init_egress(struct net_device *dev, int echannel) } equeue = pfn_to_kaddr(page_to_pfn(equeue_page)); - /* Allocate an edma ring. Note that in practice this can't - * fail, which is good, because we will leak an edma ring if so. - */ - rc = gxio_mpipe_alloc_edma_rings(&context, 1, 0, 0); - if (rc < 0) { - netdev_warn(dev, "gxio_mpipe_alloc_edma_rings failed: %d\n", - rc); - goto fail_equeue; + /* Allocate an edma ring (using a one entry "free list"). */ + if (ering < 0) { + rc = gxio_mpipe_alloc_edma_rings(&md->context, 1, 0, 0); + if (rc < 0) { + netdev_warn(dev, "gxio_mpipe_alloc_edma_rings: " + "mpipe[%d] %d\n", instance, rc); + goto fail_equeue; + } + ering = rc; } - edma = rc; /* Initialize the equeue. */ - rc = gxio_mpipe_equeue_init(equeue, &context, edma, echannel, + rc = gxio_mpipe_equeue_init(equeue, &md->context, ering, echannel, edescs, edescs_size, 0); if (rc != 0) { - netdev_err(dev, "gxio_mpipe_equeue_init failed: %d\n", rc); + netdev_err(dev, "gxio_mpipe_equeue_init: mpipe[%d] %d\n", + instance, rc); goto fail_equeue; } + /* Don't reuse the ering later. */ + ering = -1; + + if (jumbo_num != 0) { + /* Make sure "jumbo" packets can be egressed safely. */ + if (gxio_mpipe_equeue_set_snf_size(equeue, 10368) < 0) { + /* ISSUE: There is no "gxio_mpipe_equeue_destroy()". */ + netdev_warn(dev, "Jumbo packets may not be egressed" + " properly on channel %d\n", echannel); + } + } + /* Done. */ - egress_for_echannel[echannel].equeue = equeue; - egress_for_echannel[echannel].headers = headers; + md->egress_for_echannel[echannel].equeue = equeue; + md->egress_for_echannel[echannel].headers = headers; return 0; fail_equeue: @@ -1151,11 +1472,25 @@ fail: static int tile_net_link_open(struct net_device *dev, gxio_mpipe_link_t *link, const char *link_name) { - int rc = gxio_mpipe_link_open(link, &context, link_name, 0); + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; + int rc = gxio_mpipe_link_open(link, &md->context, link_name, 0); if (rc < 0) { - netdev_err(dev, "Failed to open '%s'\n", link_name); + netdev_err(dev, "Failed to open '%s', mpipe[%d], %d\n", + link_name, instance, rc); return rc; } + if (jumbo_num != 0) { + u32 attr = GXIO_MPIPE_LINK_RECEIVE_JUMBO; + rc = gxio_mpipe_link_set_attr(link, attr, 1); + if (rc != 0) { + netdev_err(dev, + "Cannot receive jumbo packets on '%s'\n", + link_name); + gxio_mpipe_link_close(link); + return rc; + } + } rc = gxio_mpipe_link_channel(link); if (rc < 0 || rc >= TILE_NET_CHANNELS) { netdev_err(dev, "gxio_mpipe_link_channel bad value: %d\n", rc); @@ -1169,12 +1504,21 @@ static int tile_net_link_open(struct net_device *dev, gxio_mpipe_link_t *link, static int tile_net_open(struct net_device *dev) { struct tile_net_priv *priv = netdev_priv(dev); - int cpu, rc; + int cpu, rc, instance; mutex_lock(&tile_net_devs_for_channel_mutex); - /* Do one-time initialization the first time any device is opened. */ - if (ingress_irq < 0) { + /* Get the instance info. */ + rc = gxio_mpipe_link_instance(dev->name); + if (rc < 0 || rc >= NR_MPIPE_MAX) + return -EIO; + + priv->instance = rc; + instance = rc; + if (!mpipe_data[rc].context.mmio_fast_base) { + /* Do one-time initialization per instance the first time + * any device is opened. + */ rc = tile_net_init_mpipe(dev); if (rc != 0) goto fail; @@ -1205,7 +1549,7 @@ static int tile_net_open(struct net_device *dev) if (rc != 0) goto fail; - tile_net_devs_for_channel[priv->channel] = dev; + mpipe_data[instance].tile_net_devs_for_channel[priv->channel] = dev; rc = tile_net_update(dev); if (rc != 0) @@ -1217,7 +1561,7 @@ static int tile_net_open(struct net_device *dev) for_each_online_cpu(cpu) { struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); struct tile_net_tx_wake *tx_wake = - &info->tx_wake[priv->echannel]; + &info->mpipe[instance].tx_wake[priv->echannel]; hrtimer_init(&tx_wake->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); @@ -1243,7 +1587,7 @@ fail: priv->channel = -1; } priv->echannel = -1; - tile_net_devs_for_channel[priv->channel] = NULL; + mpipe_data[instance].tile_net_devs_for_channel[priv->channel] = NULL; mutex_unlock(&tile_net_devs_for_channel_mutex); /* Don't return raw gxio error codes to generic Linux. */ @@ -1255,18 +1599,20 @@ static int tile_net_stop(struct net_device *dev) { struct tile_net_priv *priv = netdev_priv(dev); int cpu; + int instance = priv->instance; + struct mpipe_data *md = &mpipe_data[instance]; for_each_online_cpu(cpu) { struct tile_net_info *info = &per_cpu(per_cpu_info, cpu); struct tile_net_tx_wake *tx_wake = - &info->tx_wake[priv->echannel]; + &info->mpipe[instance].tx_wake[priv->echannel]; hrtimer_cancel(&tx_wake->timer); netif_stop_subqueue(dev, cpu); } mutex_lock(&tile_net_devs_for_channel_mutex); - tile_net_devs_for_channel[priv->channel] = NULL; + md->tile_net_devs_for_channel[priv->channel] = NULL; (void)tile_net_update(dev); if (priv->loopify_channel >= 0) { if (gxio_mpipe_link_close(&priv->loopify_link) != 0) @@ -1374,20 +1720,20 @@ static int tso_count_edescs(struct sk_buff *skb) return num_edescs; } -/* Prepare modified copies of the skbuff headers. - * FIXME: add support for IPv6. - */ +/* Prepare modified copies of the skbuff headers. */ static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, s64 slot) { struct skb_shared_info *sh = skb_shinfo(skb); struct iphdr *ih; + struct ipv6hdr *ih6; struct tcphdr *th; unsigned int sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb); unsigned int data_len = skb->len - sh_len; unsigned char *data = skb->data; unsigned int ih_off, th_off, p_len; unsigned int isum_seed, tsum_seed, id, seq; + int is_ipv6; long f_id = -1; /* id of the current fragment */ long f_size = skb_headlen(skb) - sh_len; /* current fragment size */ long f_used = 0; /* bytes used from the current fragment */ @@ -1395,18 +1741,24 @@ static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, int segment; /* Locate original headers and compute various lengths. */ - ih = ip_hdr(skb); + is_ipv6 = skb_is_gso_v6(skb); + if (is_ipv6) { + ih6 = ipv6_hdr(skb); + ih_off = skb_network_offset(skb); + } else { + ih = ip_hdr(skb); + ih_off = skb_network_offset(skb); + isum_seed = ((0xFFFF - ih->check) + + (0xFFFF - ih->tot_len) + + (0xFFFF - ih->id)); + id = ntohs(ih->id); + } + th = tcp_hdr(skb); - ih_off = skb_network_offset(skb); th_off = skb_transport_offset(skb); p_len = sh->gso_size; - /* Set up seed values for IP and TCP csum and initialize id and seq. */ - isum_seed = ((0xFFFF - ih->check) + - (0xFFFF - ih->tot_len) + - (0xFFFF - ih->id)); tsum_seed = th->check + (0xFFFF ^ htons(skb->len)); - id = ntohs(ih->id); seq = ntohl(th->seq); /* Prepare all the headers. */ @@ -1420,11 +1772,17 @@ static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, memcpy(buf, data, sh_len); /* Update copied ip header. */ - ih = (struct iphdr *)(buf + ih_off); - ih->tot_len = htons(sh_len + p_len - ih_off); - ih->id = htons(id); - ih->check = csum_long(isum_seed + ih->tot_len + - ih->id) ^ 0xffff; + if (is_ipv6) { + ih6 = (struct ipv6hdr *)(buf + ih_off); + ih6->payload_len = htons(sh_len + p_len - ih_off - + sizeof(*ih6)); + } else { + ih = (struct iphdr *)(buf + ih_off); + ih->tot_len = htons(sh_len + p_len - ih_off); + ih->id = htons(id); + ih->check = csum_long(isum_seed + ih->tot_len + + ih->id) ^ 0xffff; + } /* Update copied tcp header. */ th = (struct tcphdr *)(buf + th_off); @@ -1475,8 +1833,9 @@ static void tso_headers_prepare(struct sk_buff *skb, unsigned char *headers, static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue, struct sk_buff *skb, unsigned char *headers, s64 slot) { - struct tile_net_priv *priv = netdev_priv(dev); struct skb_shared_info *sh = skb_shinfo(skb); + int instance = mpipe_instance(dev); + struct mpipe_data *md = &mpipe_data[instance]; unsigned int sh_len = skb_transport_offset(skb) + tcp_hdrlen(skb); unsigned int data_len = skb->len - sh_len; unsigned int p_len = sh->gso_size; @@ -1499,8 +1858,8 @@ static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue, edesc_head.xfer_size = sh_len; /* This is only used to specify the TLB. */ - edesc_head.stack_idx = large_buffer_stack; - edesc_body.stack_idx = large_buffer_stack; + edesc_head.stack_idx = md->first_buffer_stack; + edesc_body.stack_idx = md->first_buffer_stack; /* Egress all the edescs. */ for (segment = 0; segment < sh->gso_segs; segment++) { @@ -1553,8 +1912,8 @@ static void tso_egress(struct net_device *dev, gxio_mpipe_equeue_t *equeue, } /* Update stats. */ - tile_net_stats_add(tx_packets, &priv->stats.tx_packets); - tile_net_stats_add(tx_bytes, &priv->stats.tx_bytes); + tile_net_stats_add(tx_packets, &dev->stats.tx_packets); + tile_net_stats_add(tx_bytes, &dev->stats.tx_bytes); } /* Do "TSO" handling for egress. @@ -1575,8 +1934,11 @@ static int tile_net_tx_tso(struct sk_buff *skb, struct net_device *dev) struct tile_net_info *info = &__get_cpu_var(per_cpu_info); struct tile_net_priv *priv = netdev_priv(dev); int channel = priv->echannel; - struct tile_net_egress *egress = &egress_for_echannel[channel]; - struct tile_net_comps *comps = info->comps_for_echannel[channel]; + int instance = priv->instance; + struct mpipe_data *md = &mpipe_data[instance]; + struct tile_net_egress *egress = &md->egress_for_echannel[channel]; + struct tile_net_comps *comps = + info->mpipe[instance].comps_for_echannel[channel]; gxio_mpipe_equeue_t *equeue = egress->equeue; unsigned long irqflags; int num_edescs; @@ -1640,10 +2002,13 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); struct tile_net_priv *priv = netdev_priv(dev); - struct tile_net_egress *egress = &egress_for_echannel[priv->echannel]; + int instance = priv->instance; + struct mpipe_data *md = &mpipe_data[instance]; + struct tile_net_egress *egress = + &md->egress_for_echannel[priv->echannel]; gxio_mpipe_equeue_t *equeue = egress->equeue; struct tile_net_comps *comps = - info->comps_for_echannel[priv->echannel]; + info->mpipe[instance].comps_for_echannel[priv->echannel]; unsigned int len = skb->len; unsigned char *data = skb->data; unsigned int num_edescs; @@ -1660,7 +2025,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) num_edescs = tile_net_tx_frags(frags, skb, data, skb_headlen(skb)); /* This is only used to specify the TLB. */ - edesc.stack_idx = large_buffer_stack; + edesc.stack_idx = md->first_buffer_stack; /* Prepare the edescs. */ for (i = 0; i < num_edescs; i++) { @@ -1693,13 +2058,16 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) for (i = 0; i < num_edescs; i++) gxio_mpipe_equeue_put_at(equeue, edescs[i], slot++); + /* Store TX timestamp if needed. */ + tile_tx_timestamp(skb, instance); + /* Add a completion record. */ add_comp(equeue, comps, slot - 1, skb); /* NOTE: Use ETH_ZLEN for short packets (e.g. 42 < 60). */ - tile_net_stats_add(1, &priv->stats.tx_packets); + tile_net_stats_add(1, &dev->stats.tx_packets); tile_net_stats_add(max_t(unsigned int, len, ETH_ZLEN), - &priv->stats.tx_bytes); + &dev->stats.tx_bytes); local_irq_restore(irqflags); @@ -1727,20 +2095,18 @@ static void tile_net_tx_timeout(struct net_device *dev) /* Ioctl commands. */ static int tile_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { - return -EOPNOTSUPP; -} + if (cmd == SIOCSHWTSTAMP) + return tile_hwtstamp_ioctl(dev, rq, cmd); -/* Get system network statistics for device. */ -static struct net_device_stats *tile_net_get_stats(struct net_device *dev) -{ - struct tile_net_priv *priv = netdev_priv(dev); - return &priv->stats; + return -EOPNOTSUPP; } /* Change the MTU. */ static int tile_net_change_mtu(struct net_device *dev, int new_mtu) { - if ((new_mtu < 68) || (new_mtu > 1500)) + if (new_mtu < 68) + return -EINVAL; + if (new_mtu > ((jumbo_num != 0) ? 9000 : 1500)) return -EINVAL; dev->mtu = new_mtu; return 0; @@ -1772,9 +2138,13 @@ static int tile_net_set_mac_address(struct net_device *dev, void *p) */ static void tile_net_netpoll(struct net_device *dev) { - disable_percpu_irq(ingress_irq); - tile_net_handle_ingress_irq(ingress_irq, NULL); - enable_percpu_irq(ingress_irq, 0); + int instance = mpipe_instance(dev); + struct tile_net_info *info = &__get_cpu_var(per_cpu_info); + struct mpipe_data *md = &mpipe_data[instance]; + + disable_percpu_irq(md->ingress_irq); + napi_schedule(&info->mpipe[instance].napi); + enable_percpu_irq(md->ingress_irq, 0); } #endif @@ -1784,7 +2154,6 @@ static const struct net_device_ops tile_net_ops = { .ndo_start_xmit = tile_net_tx, .ndo_select_queue = tile_net_select_queue, .ndo_do_ioctl = tile_net_ioctl, - .ndo_get_stats = tile_net_get_stats, .ndo_change_mtu = tile_net_change_mtu, .ndo_tx_timeout = tile_net_tx_timeout, .ndo_set_mac_address = tile_net_set_mac_address, @@ -1800,14 +2169,21 @@ static const struct net_device_ops tile_net_ops = { */ static void tile_net_setup(struct net_device *dev) { + netdev_features_t features = 0; + ether_setup(dev); dev->netdev_ops = &tile_net_ops; dev->watchdog_timeo = TILE_NET_TIMEOUT; - dev->features |= NETIF_F_LLTX; - dev->features |= NETIF_F_HW_CSUM; - dev->features |= NETIF_F_SG; - dev->features |= NETIF_F_TSO; dev->mtu = 1500; + + features |= NETIF_F_HW_CSUM; + features |= NETIF_F_SG; + features |= NETIF_F_TSO; + features |= NETIF_F_TSO6; + + dev->hw_features |= features; + dev->vlan_features |= features; + dev->features |= features; } /* Allocate the device structure, register the device, and obtain the @@ -1842,6 +2218,7 @@ static void tile_net_dev_init(const char *name, const uint8_t *mac) priv->channel = -1; priv->loopify_channel = -1; priv->echannel = -1; + init_ptp_dev(priv); /* Get the MAC address and set it in the device struct; this must * be done before the device is opened. If the MAC is all zeroes, @@ -1871,9 +2248,12 @@ static void tile_net_init_module_percpu(void *unused) { struct tile_net_info *info = &__get_cpu_var(per_cpu_info); int my_cpu = smp_processor_id(); + int instance; - info->has_iqueue = false; - + for (instance = 0; instance < NR_MPIPE_MAX; instance++) { + info->mpipe[instance].has_iqueue = false; + info->mpipe[instance].instance = instance; + } info->my_cpu = my_cpu; /* Initialize the egress timer. */ @@ -1890,6 +2270,8 @@ static int __init tile_net_init_module(void) pr_info("Tilera Network Driver\n"); + BUILD_BUG_ON(NR_MPIPE_MAX != 2); + mutex_init(&tile_net_devs_for_channel_mutex); /* Initialize each CPU. */ diff --git a/drivers/net/ethernet/tile/tilepro.c b/drivers/net/ethernet/tile/tilepro.c index 36435499814b..106be47716e7 100644 --- a/drivers/net/ethernet/tile/tilepro.c +++ b/drivers/net/ethernet/tile/tilepro.c @@ -31,6 +31,7 @@ #include <linux/in6.h> #include <linux/timer.h> #include <linux/io.h> +#include <linux/u64_stats_sync.h> #include <asm/checksum.h> #include <asm/homecache.h> @@ -88,13 +89,6 @@ /* ISSUE: This has not been thoroughly tested (except at 1500). */ #define TILE_NET_MTU 1500 -/* HACK: Define to support GSO. */ -/* ISSUE: This may actually hurt performance of the TCP blaster. */ -/* #define TILE_NET_GSO */ - -/* Define this to collapse "duplicate" acks. */ -/* #define IGNORE_DUP_ACKS */ - /* HACK: Define this to verify incoming packets. */ /* #define TILE_NET_VERIFY_INGRESS */ @@ -156,10 +150,13 @@ struct tile_netio_queue { * Statistics counters for a specific cpu and device. */ struct tile_net_stats_t { - u32 rx_packets; - u32 rx_bytes; - u32 tx_packets; - u32 tx_bytes; + struct u64_stats_sync syncp; + u64 rx_packets; /* total packets received */ + u64 tx_packets; /* total packets transmitted */ + u64 rx_bytes; /* total bytes received */ + u64 tx_bytes; /* total bytes transmitted */ + u64 rx_errors; /* packets truncated or marked bad by hw */ + u64 rx_dropped; /* packets not for us or intf not up */ }; @@ -218,8 +215,6 @@ struct tile_net_priv { int network_cpus_count; /* Credits per network cpu. */ int network_cpus_credits; - /* Network stats. */ - struct net_device_stats stats; /* For NetIO bringup retries. */ struct delayed_work retry_work; /* Quick access to per cpu data. */ @@ -627,79 +622,6 @@ static void tile_net_handle_egress_timer(unsigned long arg) } -#ifdef IGNORE_DUP_ACKS - -/* - * Help detect "duplicate" ACKs. These are sequential packets (for a - * given flow) which are exactly 66 bytes long, sharing everything but - * ID=2@0x12, Hsum=2@0x18, Ack=4@0x2a, WinSize=2@0x30, Csum=2@0x32, - * Tstamps=10@0x38. The ID's are +1, the Hsum's are -1, the Ack's are - * +N, and the Tstamps are usually identical. - * - * NOTE: Apparently truly duplicate acks (with identical "ack" values), - * should not be collapsed, as they are used for some kind of flow control. - */ -static bool is_dup_ack(char *s1, char *s2, unsigned int len) -{ - int i; - - unsigned long long ignorable = 0; - - /* Identification. */ - ignorable |= (1ULL << 0x12); - ignorable |= (1ULL << 0x13); - - /* Header checksum. */ - ignorable |= (1ULL << 0x18); - ignorable |= (1ULL << 0x19); - - /* ACK. */ - ignorable |= (1ULL << 0x2a); - ignorable |= (1ULL << 0x2b); - ignorable |= (1ULL << 0x2c); - ignorable |= (1ULL << 0x2d); - - /* WinSize. */ - ignorable |= (1ULL << 0x30); - ignorable |= (1ULL << 0x31); - - /* Checksum. */ - ignorable |= (1ULL << 0x32); - ignorable |= (1ULL << 0x33); - - for (i = 0; i < len; i++, ignorable >>= 1) { - - if ((ignorable & 1) || (s1[i] == s2[i])) - continue; - -#ifdef TILE_NET_DEBUG - /* HACK: Mention non-timestamp diffs. */ - if (i < 0x38 && i != 0x2f && - net_ratelimit()) - pr_info("Diff at 0x%x\n", i); -#endif - - return false; - } - -#ifdef TILE_NET_NO_SUPPRESS_DUP_ACKS - /* HACK: Do not suppress truly duplicate ACKs. */ - /* ISSUE: Is this actually necessary or helpful? */ - if (s1[0x2a] == s2[0x2a] && - s1[0x2b] == s2[0x2b] && - s1[0x2c] == s2[0x2c] && - s1[0x2d] == s2[0x2d]) { - return false; - } -#endif - - return true; -} - -#endif - - - static void tile_net_discard_aux(struct tile_net_cpu *info, int index) { struct tile_netio_queue *queue = &info->queue; @@ -774,6 +696,7 @@ static bool tile_net_poll_aux(struct tile_net_cpu *info, int index) netio_pkt_t *pkt = (netio_pkt_t *)((unsigned long) &qsp[1] + index); netio_pkt_metadata_t *metadata = NETIO_PKT_METADATA(pkt); + netio_pkt_status_t pkt_status = NETIO_PKT_STATUS_M(metadata, pkt); /* Extract the packet size. FIXME: Shouldn't the second line */ /* get subtracted? Mostly moot, since it should be "zero". */ @@ -806,40 +729,25 @@ static bool tile_net_poll_aux(struct tile_net_cpu *info, int index) #endif /* TILE_NET_DUMP_PACKETS */ #ifdef TILE_NET_VERIFY_INGRESS - if (!NETIO_PKT_L4_CSUM_CORRECT_M(metadata, pkt) && - NETIO_PKT_L4_CSUM_CALCULATED_M(metadata, pkt)) { - /* Bug 6624: Includes UDP packets with a "zero" checksum. */ - pr_warning("Bad L4 checksum on %d byte packet.\n", len); - } - if (!NETIO_PKT_L3_CSUM_CORRECT_M(metadata, pkt) && - NETIO_PKT_L3_CSUM_CALCULATED_M(metadata, pkt)) { + if (pkt_status == NETIO_PKT_STATUS_OVERSIZE && len >= 64) { dump_packet(buf, len, "rx"); - panic("Bad L3 checksum."); - } - switch (NETIO_PKT_STATUS_M(metadata, pkt)) { - case NETIO_PKT_STATUS_OVERSIZE: - if (len >= 64) { - dump_packet(buf, len, "rx"); - panic("Unexpected OVERSIZE."); - } - break; - case NETIO_PKT_STATUS_BAD: - pr_warning("Unexpected BAD %ld byte packet.\n", len); + panic("Unexpected OVERSIZE."); } #endif filter = 0; - /* ISSUE: Filter TCP packets with "bad" checksums? */ - - if (!(dev->flags & IFF_UP)) { + if (pkt_status == NETIO_PKT_STATUS_BAD) { + /* Handle CRC error and hardware truncation. */ + filter = 2; + } else if (!(dev->flags & IFF_UP)) { /* Filter packets received before we're up. */ filter = 1; - } else if (NETIO_PKT_STATUS_M(metadata, pkt) == NETIO_PKT_STATUS_BAD) { + } else if (NETIO_PKT_ETHERTYPE_RECOGNIZED_M(metadata, pkt) && + pkt_status == NETIO_PKT_STATUS_UNDERSIZE) { /* Filter "truncated" packets. */ - filter = 1; + filter = 2; } else if (!(dev->flags & IFF_PROMISC)) { - /* FIXME: Implement HW multicast filter. */ if (!is_multicast_ether_addr(buf)) { /* Filter packets not for our address. */ const u8 *mine = dev->dev_addr; @@ -847,9 +755,14 @@ static bool tile_net_poll_aux(struct tile_net_cpu *info, int index) } } - if (filter) { + u64_stats_update_begin(&stats->syncp); - /* ISSUE: Update "drop" statistics? */ + if (filter != 0) { + + if (filter == 1) + stats->rx_dropped++; + else + stats->rx_errors++; tile_net_provide_linux_buffer(info, va, small); @@ -881,6 +794,8 @@ static bool tile_net_poll_aux(struct tile_net_cpu *info, int index) stats->rx_bytes += len; } + u64_stats_update_end(&stats->syncp); + /* ISSUE: It would be nice to defer this until the packet has */ /* actually been processed. */ tile_net_return_credit(info); @@ -1907,8 +1822,10 @@ busy: kfree_skb(olds[i]); /* Update stats. */ + u64_stats_update_begin(&stats->syncp); stats->tx_packets += num_segs; stats->tx_bytes += (num_segs * sh_len) + d_len; + u64_stats_update_end(&stats->syncp); /* Make sure the egress timer is scheduled. */ tile_net_schedule_egress_timer(info); @@ -1936,7 +1853,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) unsigned int csum_start = skb_checksum_start_offset(skb); - lepp_frag_t frags[LEPP_MAX_FRAGS]; + lepp_frag_t frags[1 + MAX_SKB_FRAGS]; unsigned int num_frags; @@ -1951,7 +1868,7 @@ static int tile_net_tx(struct sk_buff *skb, struct net_device *dev) unsigned int cmd_head, cmd_tail, cmd_next; unsigned int comp_tail; - lepp_cmd_t cmds[LEPP_MAX_FRAGS]; + lepp_cmd_t cmds[1 + MAX_SKB_FRAGS]; /* @@ -2089,8 +2006,10 @@ busy: kfree_skb(olds[i]); /* HACK: Track "expanded" size for short packets (e.g. 42 < 60). */ + u64_stats_update_begin(&stats->syncp); stats->tx_packets++; stats->tx_bytes += ((len >= ETH_ZLEN) ? len : ETH_ZLEN); + u64_stats_update_end(&stats->syncp); /* Make sure the egress timer is scheduled. */ tile_net_schedule_egress_timer(info); @@ -2127,30 +2046,51 @@ static int tile_net_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) * * Returns the address of the device statistics structure. */ -static struct net_device_stats *tile_net_get_stats(struct net_device *dev) +static struct rtnl_link_stats64 *tile_net_get_stats64(struct net_device *dev, + struct rtnl_link_stats64 *stats) { struct tile_net_priv *priv = netdev_priv(dev); - u32 rx_packets = 0; - u32 tx_packets = 0; - u32 rx_bytes = 0; - u32 tx_bytes = 0; + u64 rx_packets = 0, tx_packets = 0; + u64 rx_bytes = 0, tx_bytes = 0; + u64 rx_errors = 0, rx_dropped = 0; int i; for_each_online_cpu(i) { - if (priv->cpu[i]) { - rx_packets += priv->cpu[i]->stats.rx_packets; - rx_bytes += priv->cpu[i]->stats.rx_bytes; - tx_packets += priv->cpu[i]->stats.tx_packets; - tx_bytes += priv->cpu[i]->stats.tx_bytes; - } + struct tile_net_stats_t *cpu_stats; + u64 trx_packets, ttx_packets, trx_bytes, ttx_bytes; + u64 trx_errors, trx_dropped; + unsigned int start; + + if (priv->cpu[i] == NULL) + continue; + cpu_stats = &priv->cpu[i]->stats; + + do { + start = u64_stats_fetch_begin_bh(&cpu_stats->syncp); + trx_packets = cpu_stats->rx_packets; + ttx_packets = cpu_stats->tx_packets; + trx_bytes = cpu_stats->rx_bytes; + ttx_bytes = cpu_stats->tx_bytes; + trx_errors = cpu_stats->rx_errors; + trx_dropped = cpu_stats->rx_dropped; + } while (u64_stats_fetch_retry_bh(&cpu_stats->syncp, start)); + + rx_packets += trx_packets; + tx_packets += ttx_packets; + rx_bytes += trx_bytes; + tx_bytes += ttx_bytes; + rx_errors += trx_errors; + rx_dropped += trx_dropped; } - priv->stats.rx_packets = rx_packets; - priv->stats.rx_bytes = rx_bytes; - priv->stats.tx_packets = tx_packets; - priv->stats.tx_bytes = tx_bytes; + stats->rx_packets = rx_packets; + stats->tx_packets = tx_packets; + stats->rx_bytes = rx_bytes; + stats->tx_bytes = tx_bytes; + stats->rx_errors = rx_errors; + stats->rx_dropped = rx_dropped; - return &priv->stats; + return stats; } @@ -2287,7 +2227,7 @@ static const struct net_device_ops tile_net_ops = { .ndo_stop = tile_net_stop, .ndo_start_xmit = tile_net_tx, .ndo_do_ioctl = tile_net_ioctl, - .ndo_get_stats = tile_net_get_stats, + .ndo_get_stats64 = tile_net_get_stats64, .ndo_change_mtu = tile_net_change_mtu, .ndo_tx_timeout = tile_net_tx_timeout, .ndo_set_mac_address = tile_net_set_mac_address, @@ -2305,39 +2245,30 @@ static const struct net_device_ops tile_net_ops = { */ static void tile_net_setup(struct net_device *dev) { - PDEBUG("tile_net_setup()\n"); + netdev_features_t features = 0; ether_setup(dev); - dev->netdev_ops = &tile_net_ops; - dev->watchdog_timeo = TILE_NET_TIMEOUT; + dev->tx_queue_len = TILE_NET_TX_QUEUE_LEN; + dev->mtu = TILE_NET_MTU; - /* We want lockless xmit. */ - dev->features |= NETIF_F_LLTX; - - /* We support hardware tx checksums. */ - dev->features |= NETIF_F_HW_CSUM; - - /* We support scatter/gather. */ - dev->features |= NETIF_F_SG; - - /* We support TSO. */ - dev->features |= NETIF_F_TSO; + features |= NETIF_F_HW_CSUM; + features |= NETIF_F_SG; -#ifdef TILE_NET_GSO - /* We support GSO. */ - dev->features |= NETIF_F_GSO; -#endif + /* We support TSO iff the HV supports sufficient frags. */ + if (LEPP_MAX_FRAGS >= 1 + MAX_SKB_FRAGS) + features |= NETIF_F_TSO; + /* We can't support HIGHDMA without hash_default, since we need + * to be able to finv() with a VA if we don't have hash_default. + */ if (hash_default) - dev->features |= NETIF_F_HIGHDMA; - - /* ISSUE: We should support NETIF_F_UFO. */ + features |= NETIF_F_HIGHDMA; - dev->tx_queue_len = TILE_NET_TX_QUEUE_LEN; - - dev->mtu = TILE_NET_MTU; + dev->hw_features |= features; + dev->vlan_features |= features; + dev->features |= features; } diff --git a/drivers/net/ethernet/via/via-velocity.c b/drivers/net/ethernet/via/via-velocity.c index 1d6dc41f755d..ef776310fab1 100644 --- a/drivers/net/ethernet/via/via-velocity.c +++ b/drivers/net/ethernet/via/via-velocity.c @@ -2376,6 +2376,23 @@ out_0: return ret; } +#ifdef CONFIG_NET_POLL_CONTROLLER +/** + * velocity_poll_controller - Velocity Poll controller function + * @dev: network device + * + * + * Used by NETCONSOLE and other diagnostic tools to allow network I/P + * with interrupts disabled. + */ +static void velocity_poll_controller(struct net_device *dev) +{ + disable_irq(dev->irq); + velocity_intr(dev->irq, dev); + enable_irq(dev->irq); +} +#endif + /** * velocity_mii_ioctl - MII ioctl handler * @dev: network device @@ -2641,6 +2658,9 @@ static const struct net_device_ops velocity_netdev_ops = { .ndo_do_ioctl = velocity_ioctl, .ndo_vlan_rx_add_vid = velocity_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = velocity_vlan_rx_kill_vid, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = velocity_poll_controller, +#endif }; /** diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index d0f9c2fd1d4f..a822207b8241 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -600,6 +600,9 @@ static int macvlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], if (!vlan->port->passthru) return -EOPNOTSUPP; + if (flags & NLM_F_REPLACE) + return -EOPNOTSUPP; + if (is_unicast_ether_addr(addr)) err = dev_uc_add_excl(dev, addr); else if (is_multicast_ether_addr(addr)) diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index bff7e0b0b4e7..9ccccd40c410 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -622,6 +622,86 @@ static int team_change_mode(struct team *team, const char *kind) } +/********************* + * Peers notification + *********************/ + +static void team_notify_peers_work(struct work_struct *work) +{ + struct team *team; + + team = container_of(work, struct team, notify_peers.dw.work); + + if (!rtnl_trylock()) { + schedule_delayed_work(&team->notify_peers.dw, 0); + return; + } + call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, team->dev); + rtnl_unlock(); + if (!atomic_dec_and_test(&team->notify_peers.count_pending)) + schedule_delayed_work(&team->notify_peers.dw, + msecs_to_jiffies(team->notify_peers.interval)); +} + +static void team_notify_peers(struct team *team) +{ + if (!team->notify_peers.count || !netif_running(team->dev)) + return; + atomic_set(&team->notify_peers.count_pending, team->notify_peers.count); + schedule_delayed_work(&team->notify_peers.dw, 0); +} + +static void team_notify_peers_init(struct team *team) +{ + INIT_DELAYED_WORK(&team->notify_peers.dw, team_notify_peers_work); +} + +static void team_notify_peers_fini(struct team *team) +{ + cancel_delayed_work_sync(&team->notify_peers.dw); +} + + +/******************************* + * Send multicast group rejoins + *******************************/ + +static void team_mcast_rejoin_work(struct work_struct *work) +{ + struct team *team; + + team = container_of(work, struct team, mcast_rejoin.dw.work); + + if (!rtnl_trylock()) { + schedule_delayed_work(&team->mcast_rejoin.dw, 0); + return; + } + call_netdevice_notifiers(NETDEV_RESEND_IGMP, team->dev); + rtnl_unlock(); + if (!atomic_dec_and_test(&team->mcast_rejoin.count_pending)) + schedule_delayed_work(&team->mcast_rejoin.dw, + msecs_to_jiffies(team->mcast_rejoin.interval)); +} + +static void team_mcast_rejoin(struct team *team) +{ + if (!team->mcast_rejoin.count || !netif_running(team->dev)) + return; + atomic_set(&team->mcast_rejoin.count_pending, team->mcast_rejoin.count); + schedule_delayed_work(&team->mcast_rejoin.dw, 0); +} + +static void team_mcast_rejoin_init(struct team *team) +{ + INIT_DELAYED_WORK(&team->mcast_rejoin.dw, team_mcast_rejoin_work); +} + +static void team_mcast_rejoin_fini(struct team *team) +{ + cancel_delayed_work_sync(&team->mcast_rejoin.dw); +} + + /************************ * Rx path frame handler ************************/ @@ -846,6 +926,8 @@ static void team_port_enable(struct team *team, team_queue_override_port_add(team, port); if (team->ops.port_enabled) team->ops.port_enabled(team, port); + team_notify_peers(team); + team_mcast_rejoin(team); } static void __reconstruct_port_hlist(struct team *team, int rm_index) @@ -875,6 +957,8 @@ static void team_port_disable(struct team *team, team->en_port_count--; team_queue_override_port_del(team, port); team_adjust_ops(team); + team_notify_peers(team); + team_mcast_rejoin(team); } #define TEAM_VLAN_FEATURES (NETIF_F_ALL_CSUM | NETIF_F_SG | \ @@ -953,6 +1037,9 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port, struct netpoll *np; int err; + if (!team->dev->npinfo) + return 0; + np = kzalloc(sizeof(*np), gfp); if (!np) return -ENOMEM; @@ -979,12 +1066,6 @@ static void team_port_disable_netpoll(struct team_port *port) __netpoll_cleanup(np); kfree(np); } - -static struct netpoll_info *team_netpoll_info(struct team *team) -{ - return team->dev->npinfo; -} - #else static int team_port_enable_netpoll(struct team *team, struct team_port *port, gfp_t gfp) @@ -994,10 +1075,6 @@ static int team_port_enable_netpoll(struct team *team, struct team_port *port, static void team_port_disable_netpoll(struct team_port *port) { } -static struct netpoll_info *team_netpoll_info(struct team *team) -{ - return NULL; -} #endif static void __team_port_change_port_added(struct team_port *port, bool linkup); @@ -1079,13 +1156,11 @@ static int team_port_add(struct team *team, struct net_device *port_dev) goto err_vids_add; } - if (team_netpoll_info(team)) { - err = team_port_enable_netpoll(team, port, GFP_KERNEL); - if (err) { - netdev_err(dev, "Failed to enable netpoll on device %s\n", - portname); - goto err_enable_netpoll; - } + err = team_port_enable_netpoll(team, port, GFP_KERNEL); + if (err) { + netdev_err(dev, "Failed to enable netpoll on device %s\n", + portname); + goto err_enable_netpoll; } err = netdev_master_upper_dev_link(port_dev, dev); @@ -1205,6 +1280,62 @@ static int team_mode_option_set(struct team *team, struct team_gsetter_ctx *ctx) return team_change_mode(team, ctx->data.str_val); } +static int team_notify_peers_count_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + ctx->data.u32_val = team->notify_peers.count; + return 0; +} + +static int team_notify_peers_count_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + team->notify_peers.count = ctx->data.u32_val; + return 0; +} + +static int team_notify_peers_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + ctx->data.u32_val = team->notify_peers.interval; + return 0; +} + +static int team_notify_peers_interval_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + team->notify_peers.interval = ctx->data.u32_val; + return 0; +} + +static int team_mcast_rejoin_count_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + ctx->data.u32_val = team->mcast_rejoin.count; + return 0; +} + +static int team_mcast_rejoin_count_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + team->mcast_rejoin.count = ctx->data.u32_val; + return 0; +} + +static int team_mcast_rejoin_interval_get(struct team *team, + struct team_gsetter_ctx *ctx) +{ + ctx->data.u32_val = team->mcast_rejoin.interval; + return 0; +} + +static int team_mcast_rejoin_interval_set(struct team *team, + struct team_gsetter_ctx *ctx) +{ + team->mcast_rejoin.interval = ctx->data.u32_val; + return 0; +} + static int team_port_en_option_get(struct team *team, struct team_gsetter_ctx *ctx) { @@ -1317,6 +1448,30 @@ static const struct team_option team_options[] = { .setter = team_mode_option_set, }, { + .name = "notify_peers_count", + .type = TEAM_OPTION_TYPE_U32, + .getter = team_notify_peers_count_get, + .setter = team_notify_peers_count_set, + }, + { + .name = "notify_peers_interval", + .type = TEAM_OPTION_TYPE_U32, + .getter = team_notify_peers_interval_get, + .setter = team_notify_peers_interval_set, + }, + { + .name = "mcast_rejoin_count", + .type = TEAM_OPTION_TYPE_U32, + .getter = team_mcast_rejoin_count_get, + .setter = team_mcast_rejoin_count_set, + }, + { + .name = "mcast_rejoin_interval", + .type = TEAM_OPTION_TYPE_U32, + .getter = team_mcast_rejoin_interval_get, + .setter = team_mcast_rejoin_interval_set, + }, + { .name = "enabled", .type = TEAM_OPTION_TYPE_BOOL, .per_port = true, @@ -1396,6 +1551,10 @@ static int team_init(struct net_device *dev) INIT_LIST_HEAD(&team->option_list); INIT_LIST_HEAD(&team->option_inst_list); + + team_notify_peers_init(team); + team_mcast_rejoin_init(team); + err = team_options_register(team, team_options, ARRAY_SIZE(team_options)); if (err) goto err_options_register; @@ -1406,6 +1565,8 @@ static int team_init(struct net_device *dev) return 0; err_options_register: + team_mcast_rejoin_fini(team); + team_notify_peers_fini(team); team_queue_override_fini(team); err_team_queue_override_init: free_percpu(team->pcpu_stats); @@ -1425,6 +1586,8 @@ static void team_uninit(struct net_device *dev) __team_change_mode(team, NULL); /* cleanup */ __team_options_unregister(team, team_options, ARRAY_SIZE(team_options)); + team_mcast_rejoin_fini(team); + team_notify_peers_fini(team); team_queue_override_fini(team); mutex_unlock(&team->lock); } @@ -2698,6 +2861,10 @@ static int team_device_event(struct notifier_block *unused, case NETDEV_PRE_TYPE_CHANGE: /* Forbid to change type of underlaying device */ return NOTIFY_BAD; + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, port->team->dev); + break; } return NOTIFY_DONE; } diff --git a/drivers/net/tun.c b/drivers/net/tun.c index db690a372260..5dce262f538e 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -60,6 +60,7 @@ #include <linux/if_arp.h> #include <linux/if_ether.h> #include <linux/if_tun.h> +#include <linux/if_vlan.h> #include <linux/crc32.h> #include <linux/nsproxy.h> #include <linux/virtio_net.h> @@ -739,6 +740,11 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) >= dev->tx_queue_len / tun->numqueues) goto drop; + if (skb->sk) { + sock_tx_timestamp(skb->sk, &skb_shinfo(skb)->tx_flags); + sw_tx_timestamp(skb); + } + /* Orphan the skb - required as we might hang on to it * for indefinite time. */ if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) @@ -1260,6 +1266,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, { struct tun_pi pi = { 0, skb->protocol }; ssize_t total = 0; + int vlan_offset = 0; if (!(tun->flags & TUN_NO_PI)) { if ((len -= sizeof(pi)) < 0) @@ -1323,11 +1330,40 @@ static ssize_t tun_put_user(struct tun_struct *tun, total += tun->vnet_hdr_sz; } - len = min_t(int, skb->len, len); + if (!vlan_tx_tag_present(skb)) { + len = min_t(int, skb->len, len); + } else { + int copy, ret; + struct { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; + } veth; + + veth.h_vlan_proto = skb->vlan_proto; + veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb)); + + vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto); + len = min_t(int, skb->len + VLAN_HLEN, len); + + copy = min_t(int, vlan_offset, len); + ret = skb_copy_datagram_const_iovec(skb, 0, iv, total, copy); + len -= copy; + total += copy; + if (ret || !len) + goto done; - skb_copy_datagram_const_iovec(skb, 0, iv, total, len); - total += skb->len; + copy = min_t(int, sizeof(veth), len); + ret = memcpy_toiovecend(iv, (void *)&veth, total, copy); + len -= copy; + total += copy; + if (ret || !len) + goto done; + } + skb_copy_datagram_const_iovec(skb, vlan_offset, iv, total, len); + total += len; + +done: tun->dev->stats.tx_packets++; tun->dev->stats.tx_bytes += len; @@ -1476,7 +1512,6 @@ static int tun_sendmsg(struct kiocb *iocb, struct socket *sock, return ret; } - static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t total_len, int flags) @@ -1488,10 +1523,15 @@ static int tun_recvmsg(struct kiocb *iocb, struct socket *sock, if (!tun) return -EBADFD; - if (flags & ~(MSG_DONTWAIT|MSG_TRUNC)) { + if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) { ret = -EINVAL; goto out; } + if (flags & MSG_ERRQUEUE) { + ret = sock_recv_errqueue(sock->sk, m, total_len, + SOL_PACKET, TUN_TX_TIMESTAMP); + goto out; + } ret = tun_do_read(tun, tfile, iocb, m->msg_iov, total_len, flags & MSG_DONTWAIT); if (ret > total_len) { @@ -1682,7 +1722,8 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) tun_flow_init(tun); dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | - TUN_USER_FEATURES; + TUN_USER_FEATURES | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_STAG_TX; dev->features = dev->hw_features; dev->vlan_features = dev->features; @@ -2274,6 +2315,7 @@ static const struct ethtool_ops tun_ethtool_ops = { .get_msglevel = tun_get_msglevel, .set_msglevel = tun_set_msglevel, .get_link = ethtool_op_get_link, + .get_ts_info = ethtool_op_get_ts_info, }; diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index ad5d1e4384db..b96ad4f15b8a 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -778,6 +778,9 @@ static int ax88178_change_mtu(struct net_device *net, int new_mtu) dev->hard_mtu = net->mtu + net->hard_header_len; ax88178_set_mfb(dev); + /* max qlen depend on hard_mtu and rx_urb_size */ + usbnet_update_max_qlen(dev); + return 0; } diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index 2bc87e3a8141..5a468f317ca5 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -688,6 +688,9 @@ static int ax88179_change_mtu(struct net_device *net, int new_mtu) 2, 2, &tmp16); } + /* max qlen depend on hard_mtu and rx_urb_size */ + usbnet_update_max_qlen(dev); + return 0; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 06ee82f557d4..e4811d7b5af1 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -59,15 +59,13 @@ * For high speed, each frame comfortably fits almost 36 max size * Ethernet packets (so queues should be bigger). * - * REVISIT qlens should be members of 'struct usbnet'; the goal is to - * let the USB host controller be busy for 5msec or more before an irq - * is required, under load. Jumbograms change the equation. + * The goal is to let the USB host controller be busy for 5msec or + * more before an irq is required, under load. Jumbograms change + * the equation. */ -#define RX_MAX_QUEUE_MEMORY (60 * 1518) -#define RX_QLEN(dev) (((dev)->udev->speed == USB_SPEED_HIGH) ? \ - (RX_MAX_QUEUE_MEMORY/(dev)->rx_urb_size) : 4) -#define TX_QLEN(dev) (((dev)->udev->speed == USB_SPEED_HIGH) ? \ - (RX_MAX_QUEUE_MEMORY/(dev)->hard_mtu) : 4) +#define MAX_QUEUE_MEMORY (60 * 1518) +#define RX_QLEN(dev) ((dev)->rx_qlen) +#define TX_QLEN(dev) ((dev)->tx_qlen) // reawaken network queue this soon after stopping; else watchdog barks #define TX_TIMEOUT_JIFFIES (5*HZ) @@ -347,6 +345,31 @@ void usbnet_skb_return (struct usbnet *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(usbnet_skb_return); +/* must be called if hard_mtu or rx_urb_size changed */ +void usbnet_update_max_qlen(struct usbnet *dev) +{ + enum usb_device_speed speed = dev->udev->speed; + + switch (speed) { + case USB_SPEED_HIGH: + dev->rx_qlen = MAX_QUEUE_MEMORY / dev->rx_urb_size; + dev->tx_qlen = MAX_QUEUE_MEMORY / dev->hard_mtu; + break; + case USB_SPEED_SUPER: + /* + * Not take default 5ms qlen for super speed HC to + * save memory, and iperf tests show 2.5ms qlen can + * work well + */ + dev->rx_qlen = 5 * MAX_QUEUE_MEMORY / dev->rx_urb_size; + dev->tx_qlen = 5 * MAX_QUEUE_MEMORY / dev->hard_mtu; + break; + default: + dev->rx_qlen = dev->tx_qlen = 4; + } +} +EXPORT_SYMBOL_GPL(usbnet_update_max_qlen); + /*------------------------------------------------------------------------- * @@ -375,6 +398,9 @@ int usbnet_change_mtu (struct net_device *net, int new_mtu) usbnet_unlink_rx_urbs(dev); } + /* max qlen depend on hard_mtu and rx_urb_size */ + usbnet_update_max_qlen(dev); + return 0; } EXPORT_SYMBOL_GPL(usbnet_change_mtu); @@ -843,6 +869,9 @@ int usbnet_open (struct net_device *net) goto done; } + /* hard_mtu or rx_urb_size may change in reset() */ + usbnet_update_max_qlen(dev); + // insist peer be connected if (info->check_connect && (retval = info->check_connect (dev)) < 0) { netif_dbg(dev, ifup, dev->net, "can't open; %d\n", retval); @@ -927,6 +956,9 @@ int usbnet_set_settings (struct net_device *net, struct ethtool_cmd *cmd) if (dev->driver_info->link_reset) dev->driver_info->link_reset(dev); + /* hard_mtu or rx_urb_size may change in link_reset() */ + usbnet_update_max_qlen(dev); + return retval; } @@ -1020,6 +1052,9 @@ static void __handle_link_change(struct usbnet *dev) tasklet_schedule(&dev->bh); } + /* hard_mtu or rx_urb_size may change during link change */ + usbnet_update_max_qlen(dev); + clear_bit(EVENT_LINK_CHANGE, &dev->flags); } @@ -1599,6 +1634,9 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) if ((dev->driver_info->flags & FLAG_WWAN) != 0) SET_NETDEV_DEVTYPE(net, &wwan_type); + /* initialize max rx_qlen and tx_qlen */ + usbnet_update_max_qlen(dev); + status = register_netdev (net); if (status) goto out4; diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 3d2a90a62649..f21600277583 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -106,6 +106,9 @@ struct virtnet_info { /* Has control virtqueue */ bool has_cvq; + /* Host can handle any s/g split between our header and packet data */ + bool any_header_sg; + /* enable config space updates */ bool config_enable; @@ -669,12 +672,28 @@ static void free_old_xmit_skbs(struct send_queue *sq) static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) { - struct skb_vnet_hdr *hdr = skb_vnet_hdr(skb); + struct skb_vnet_hdr *hdr; const unsigned char *dest = ((struct ethhdr *)skb->data)->h_dest; struct virtnet_info *vi = sq->vq->vdev->priv; unsigned num_sg; + unsigned hdr_len; + bool can_push; pr_debug("%s: xmit %p %pM\n", vi->dev->name, skb, dest); + if (vi->mergeable_rx_bufs) + hdr_len = sizeof hdr->mhdr; + else + hdr_len = sizeof hdr->hdr; + + can_push = vi->any_header_sg && + !((unsigned long)skb->data & (__alignof__(*hdr) - 1)) && + !skb_header_cloned(skb) && skb_headroom(skb) >= hdr_len; + /* Even if we can, don't push here yet as this would skew + * csum_start offset below. */ + if (can_push) + hdr = (struct skb_vnet_hdr *)(skb->data - hdr_len); + else + hdr = skb_vnet_hdr(skb); if (skb->ip_summed == CHECKSUM_PARTIAL) { hdr->hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; @@ -703,15 +722,18 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr->hdr.gso_size = hdr->hdr.hdr_len = 0; } - hdr->mhdr.num_buffers = 0; - - /* Encode metadata header at front. */ if (vi->mergeable_rx_bufs) - sg_set_buf(sq->sg, &hdr->mhdr, sizeof hdr->mhdr); - else - sg_set_buf(sq->sg, &hdr->hdr, sizeof hdr->hdr); + hdr->mhdr.num_buffers = 0; - num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1; + if (can_push) { + __skb_push(skb, hdr_len); + num_sg = skb_to_sgvec(skb, sq->sg, 0, skb->len); + /* Pull header back to avoid skew in tx bytes calculations. */ + __skb_pull(skb, hdr_len); + } else { + sg_set_buf(sq->sg, hdr, hdr_len); + num_sg = skb_to_sgvec(skb, sq->sg + 1, 0, skb->len) + 1; + } return virtqueue_add_outbuf(sq->vq, sq->sg, num_sg, skb, GFP_ATOMIC); } @@ -1552,6 +1574,9 @@ static int virtnet_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) vi->mergeable_rx_bufs = true; + if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT)) + vi->any_header_sg = true; + if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ)) vi->has_cvq = true; @@ -1727,6 +1752,7 @@ static unsigned int features[] = { VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, VIRTIO_NET_F_CTRL_MAC_ADDR, + VIRTIO_F_ANY_LAYOUT, }; static struct virtio_driver virtio_net_driver = { diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index f4c6db419ddb..c3dd6e496327 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -408,6 +408,26 @@ static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f, return NULL; } +/* Replace destination of unicast mac */ +static int vxlan_fdb_replace(struct vxlan_fdb *f, + __be32 ip, __be16 port, __u32 vni, __u32 ifindex) +{ + struct vxlan_rdst *rd; + + rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex); + if (rd) + return 0; + + rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list); + if (!rd) + return 0; + rd->remote_ip = ip; + rd->remote_port = port; + rd->remote_vni = vni; + rd->remote_ifindex = ifindex; + return 1; +} + /* Add/update destinations for multicast */ static int vxlan_fdb_append(struct vxlan_fdb *f, __be32 ip, __be16 port, __u32 vni, __u32 ifindex) @@ -458,6 +478,19 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, f->updated = jiffies; notify = 1; } + if ((flags & NLM_F_REPLACE)) { + /* Only change unicasts */ + if (!(is_multicast_ether_addr(f->eth_addr) || + is_zero_ether_addr(f->eth_addr))) { + int rc = vxlan_fdb_replace(f, ip, port, vni, + ifindex); + + if (rc < 0) + return rc; + notify |= rc; + } else + return -EOPNOTSUPP; + } if ((flags & NLM_F_APPEND) && (is_multicast_ether_addr(f->eth_addr) || is_zero_ether_addr(f->eth_addr))) { @@ -474,6 +507,11 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan, if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax) return -ENOSPC; + /* Disallow replace to add a multicast entry */ + if ((flags & NLM_F_REPLACE) && + (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac))) + return -EOPNOTSUPP; + netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip); f = kmalloc(sizeof(*f), GFP_ATOMIC); if (!f) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index e37fea6e178d..c71e78c46705 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3579,6 +3579,49 @@ int pcie_set_mps(struct pci_dev *dev, int mps) } /** + * pcie_get_minimum_link - determine minimum link settings of a PCI device + * @dev: PCI device to query + * @speed: storage for minimum speed + * @width: storage for minimum width + * + * This function will walk up the PCI device chain and determine the minimum + * link width and speed of the device. + */ +int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, + enum pcie_link_width *width) +{ + int ret; + + *speed = PCI_SPEED_UNKNOWN; + *width = PCIE_LNK_WIDTH_UNKNOWN; + + while (dev) { + u16 lnksta; + enum pci_bus_speed next_speed; + enum pcie_link_width next_width; + + ret = pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); + if (ret) + return ret; + + next_speed = pcie_link_speed[lnksta & PCI_EXP_LNKSTA_CLS]; + next_width = (lnksta & PCI_EXP_LNKSTA_NLW) >> + PCI_EXP_LNKSTA_NLW_SHIFT; + + if (next_speed < *speed) + *speed = next_speed; + + if (next_width < *width) + *width = next_width; + + dev = dev->bus->self; + } + + return 0; +} +EXPORT_SYMBOL(pcie_get_minimum_link); + +/** * pci_select_bars - Make BAR mask from the type of resource * @dev: the PCI device for which BAR mask is made * @flags: resource type mask to be selected diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index d1182c4a754e..948d1a033a22 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -6,6 +6,9 @@ #define PCI_CFG_SPACE_SIZE 256 #define PCI_CFG_SPACE_EXP_SIZE 4096 +extern const unsigned char pcix_bus_speed[]; +extern const unsigned char pcie_link_speed[]; + /* Functions internal to the PCI core code */ int pci_create_sysfs_dev_files(struct pci_dev *pdev); diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 46ada5c098eb..496c5b082d42 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -513,7 +513,7 @@ static struct pci_host_bridge *pci_alloc_host_bridge(struct pci_bus *b) return bridge; } -static unsigned char pcix_bus_speed[] = { +const unsigned char pcix_bus_speed[] = { PCI_SPEED_UNKNOWN, /* 0 */ PCI_SPEED_66MHz_PCIX, /* 1 */ PCI_SPEED_100MHz_PCIX, /* 2 */ @@ -532,7 +532,7 @@ static unsigned char pcix_bus_speed[] = { PCI_SPEED_133MHz_PCIX_533 /* F */ }; -static unsigned char pcie_link_speed[] = { +const unsigned char pcie_link_speed[] = { PCI_SPEED_UNKNOWN, /* 0 */ PCIE_SPEED_2_5GT, /* 1 */ PCIE_SPEED_5_0GT, /* 2 */ diff --git a/drivers/scsi/bnx2i/57xx_iscsi_hsi.h b/drivers/scsi/bnx2i/57xx_iscsi_hsi.h index f2db5fe7bdc2..62f00da09ad1 100644 --- a/drivers/scsi/bnx2i/57xx_iscsi_hsi.h +++ b/drivers/scsi/bnx2i/57xx_iscsi_hsi.h @@ -581,8 +581,10 @@ struct iscsi_kwqe_init1 { #define ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE_SHIFT 4 #define ISCSI_KWQE_INIT1_KEEP_ALIVE_ENABLE (0x1<<5) #define ISCSI_KWQE_INIT1_KEEP_ALIVE_ENABLE_SHIFT 5 -#define ISCSI_KWQE_INIT1_RESERVED1 (0x3<<6) -#define ISCSI_KWQE_INIT1_RESERVED1_SHIFT 6 +#define ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE (0x1<<6) +#define ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE_SHIFT 6 +#define ISCSI_KWQE_INIT1_RESERVED1 (0x1<<7) +#define ISCSI_KWQE_INIT1_RESERVED1_SHIFT 7 u16 cq_num_wqes; #elif defined(__LITTLE_ENDIAN) u16 cq_num_wqes; @@ -593,8 +595,10 @@ struct iscsi_kwqe_init1 { #define ISCSI_KWQE_INIT1_DELAYED_ACK_ENABLE_SHIFT 4 #define ISCSI_KWQE_INIT1_KEEP_ALIVE_ENABLE (0x1<<5) #define ISCSI_KWQE_INIT1_KEEP_ALIVE_ENABLE_SHIFT 5 -#define ISCSI_KWQE_INIT1_RESERVED1 (0x3<<6) -#define ISCSI_KWQE_INIT1_RESERVED1_SHIFT 6 +#define ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE (0x1<<6) +#define ISCSI_KWQE_INIT1_TIME_STAMPS_ENABLE_SHIFT 6 +#define ISCSI_KWQE_INIT1_RESERVED1 (0x1<<7) +#define ISCSI_KWQE_INIT1_RESERVED1_SHIFT 7 u8 cq_log_wqes_per_page; #endif #if defined(__BIG_ENDIAN) diff --git a/drivers/scsi/bnx2i/bnx2i_init.c b/drivers/scsi/bnx2i/bnx2i_init.c index 50fef6963a81..3104202902ed 100644 --- a/drivers/scsi/bnx2i/bnx2i_init.c +++ b/drivers/scsi/bnx2i/bnx2i_init.c @@ -172,16 +172,14 @@ void bnx2i_start(void *handle) struct bnx2i_hba *hba = handle; int i = HZ; - /* - * We should never register devices that don't support iSCSI - * (see bnx2i_init_one), so something is wrong if we try to - * start a iSCSI adapter on hardware with 0 supported iSCSI - * connections + /* On some bnx2x devices, it is possible that iSCSI is no + * longer supported after firmware is downloaded. In that + * case, the iscsi_init_msg will return failure. */ - BUG_ON(!hba->cnic->max_iscsi_conn); bnx2i_send_fw_iscsi_init_msg(hba); - while (!test_bit(ADAPTER_STATE_UP, &hba->adapter_state) && i--) + while (!test_bit(ADAPTER_STATE_UP, &hba->adapter_state) && + !test_bit(ADAPTER_STATE_INIT_FAILED, &hba->adapter_state) && i--) msleep(BNX2I_INIT_POLL_TIME); } diff --git a/include/linux/dm9000.h b/include/linux/dm9000.h index 96e87693d933..841925fbfe8a 100644 --- a/include/linux/dm9000.h +++ b/include/linux/dm9000.h @@ -14,6 +14,8 @@ #ifndef __DM9000_PLATFORM_DATA #define __DM9000_PLATFORM_DATA __FILE__ +#include <linux/if_ether.h> + /* IO control flags */ #define DM9000_PLATF_8BITONLY (0x0001) @@ -27,7 +29,7 @@ struct dm9000_plat_data { unsigned int flags; - unsigned char dev_addr[6]; + unsigned char dev_addr[ETH_ALEN]; /* allow replacement IO routines */ diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h index 51b793466ff3..343d82a54468 100644 --- a/include/linux/fs_enet_pd.h +++ b/include/linux/fs_enet_pd.h @@ -18,6 +18,7 @@ #include <linux/string.h> #include <linux/of_mdio.h> +#include <linux/if_ether.h> #include <asm/types.h> #define FS_ENET_NAME "fs_enet" @@ -135,7 +136,7 @@ struct fs_platform_info { const struct fs_mii_bus_info *bus_info; int rx_ring, tx_ring; /* number of buffers on rx */ - __u8 macaddr[6]; /* mac address */ + __u8 macaddr[ETH_ALEN]; /* mac address */ int rx_copybreak; /* limit we copy small frames */ int use_napi; /* use NAPI */ int napi_weight; /* NAPI weight */ diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index b0dc87a2a376..4e101af9c1ff 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -16,6 +16,7 @@ #define LINUX_IEEE80211_H #include <linux/types.h> +#include <linux/if_ether.h> #include <asm/byteorder.h> /* @@ -209,28 +210,28 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; - u8 addr4[6]; + u8 addr4[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_hdr_3addr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; } __packed __aligned(2); struct ieee80211_qos_hdr { __le16 frame_control; __le16 duration_id; - u8 addr1[6]; - u8 addr2[6]; - u8 addr3[6]; + u8 addr1[ETH_ALEN]; + u8 addr2[ETH_ALEN]; + u8 addr3[ETH_ALEN]; __le16 seq_ctrl; __le16 qos_ctrl; } __packed __aligned(2); @@ -608,8 +609,8 @@ struct ieee80211s_hdr { u8 flags; u8 ttl; __le32 seqnum; - u8 eaddr1[6]; - u8 eaddr2[6]; + u8 eaddr1[ETH_ALEN]; + u8 eaddr2[ETH_ALEN]; } __packed __aligned(2); /* Mesh flags */ @@ -758,7 +759,7 @@ struct ieee80211_rann_ie { u8 rann_flags; u8 rann_hopcount; u8 rann_ttl; - u8 rann_addr[6]; + u8 rann_addr[ETH_ALEN]; __le32 rann_seq; __le32 rann_interval; __le32 rann_metric; @@ -802,9 +803,9 @@ enum ieee80211_vht_opmode_bits { struct ieee80211_mgmt { __le16 frame_control; __le16 duration; - u8 da[6]; - u8 sa[6]; - u8 bssid[6]; + u8 da[ETH_ALEN]; + u8 sa[ETH_ALEN]; + u8 bssid[ETH_ALEN]; __le16 seq_ctrl; union { struct { @@ -833,7 +834,7 @@ struct ieee80211_mgmt { struct { __le16 capab_info; __le16 listen_interval; - u8 current_ap[6]; + u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ u8 variable[0]; } __packed reassoc_req; @@ -966,21 +967,21 @@ struct ieee80211_vendor_ie { struct ieee80211_rts { __le16 frame_control; __le16 duration; - u8 ra[6]; - u8 ta[6]; + u8 ra[ETH_ALEN]; + u8 ta[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_cts { __le16 frame_control; __le16 duration; - u8 ra[6]; + u8 ra[ETH_ALEN]; } __packed __aligned(2); struct ieee80211_pspoll { __le16 frame_control; __le16 aid; - u8 bssid[6]; - u8 ta[6]; + u8 bssid[ETH_ALEN]; + u8 ta[ETH_ALEN]; } __packed __aligned(2); /* TDLS */ @@ -989,14 +990,14 @@ struct ieee80211_pspoll { struct ieee80211_tdls_lnkie { u8 ie_type; /* Link Identifier IE */ u8 ie_len; - u8 bssid[6]; - u8 init_sta[6]; - u8 resp_sta[6]; + u8 bssid[ETH_ALEN]; + u8 init_sta[ETH_ALEN]; + u8 resp_sta[ETH_ALEN]; } __packed; struct ieee80211_tdls_data { - u8 da[6]; - u8 sa[6]; + u8 da[ETH_ALEN]; + u8 sa[ETH_ALEN]; __be16 ether_type; u8 payload_type; u8 category; @@ -1090,8 +1091,8 @@ struct ieee80211_p2p_noa_attr { struct ieee80211_bar { __le16 frame_control; __le16 duration; - __u8 ra[6]; - __u8 ta[6]; + __u8 ra[ETH_ALEN]; + __u8 ta[ETH_ALEN]; __le16 control; __le16 start_seq_num; } __packed; diff --git a/include/linux/if_team.h b/include/linux/if_team.h index f6156f91eb1c..a899dc24be15 100644 --- a/include/linux/if_team.h +++ b/include/linux/if_team.h @@ -10,9 +10,9 @@ #ifndef _LINUX_IF_TEAM_H_ #define _LINUX_IF_TEAM_H_ - #include <linux/netpoll.h> #include <net/sch_generic.h> +#include <linux/types.h> #include <uapi/linux/if_team.h> struct team_pcpu_stats { @@ -194,6 +194,18 @@ struct team { bool user_carrier_enabled; bool queue_override_enabled; struct list_head *qom_lists; /* array of queue override mapping lists */ + struct { + unsigned int count; + unsigned int interval; /* in ms */ + atomic_t count_pending; + struct delayed_work dw; + } notify_peers; + struct { + unsigned int count; + unsigned int interval; /* in ms */ + atomic_t count_pending; + struct delayed_work dw; + } mcast_rejoin; long mode_priv[TEAM_MODE_PRIV_LONGS]; }; diff --git a/include/linux/igmp.h b/include/linux/igmp.h index e3362b5f13e8..f47550d75f85 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -129,6 +129,5 @@ extern void ip_mc_unmap(struct in_device *); extern void ip_mc_remap(struct in_device *); extern void ip_mc_dec_group(struct in_device *in_dev, __be32 addr); extern void ip_mc_inc_group(struct in_device *in_dev, __be32 addr); -extern void ip_mc_rejoin_groups(struct in_device *in_dev); #endif diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h index bb1c8096a7eb..cd1fdf75103b 100644 --- a/include/linux/mlx4/cmd.h +++ b/include/linux/mlx4/cmd.h @@ -69,6 +69,7 @@ enum { MLX4_CMD_SET_ICM_SIZE = 0xffd, /*master notify fw on finish for slave's flr*/ MLX4_CMD_INFORM_FLR_DONE = 0x5b, + MLX4_CMD_GET_OP_REQ = 0x59, /* TPT commands */ MLX4_CMD_SW2HW_MPT = 0xd, diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 52c23a892bab..09ef2f448a00 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -33,6 +33,7 @@ #ifndef MLX4_DEVICE_H #define MLX4_DEVICE_H +#include <linux/if_ether.h> #include <linux/pci.h> #include <linux/completion.h> #include <linux/radix-tree.h> @@ -207,6 +208,7 @@ enum mlx4_event { MLX4_EVENT_TYPE_CMD = 0x0a, MLX4_EVENT_TYPE_VEP_UPDATE = 0x19, MLX4_EVENT_TYPE_COMM_CHANNEL = 0x18, + MLX4_EVENT_TYPE_OP_REQUIRED = 0x1a, MLX4_EVENT_TYPE_FATAL_WARNING = 0x1b, MLX4_EVENT_TYPE_FLR_EVENT = 0x1c, MLX4_EVENT_TYPE_PORT_MNG_CHG_EVENT = 0x1d, @@ -619,7 +621,7 @@ struct mlx4_eth_av { u8 dgid[16]; u32 reserved4[2]; __be16 vlan; - u8 mac[6]; + u8 mac[ETH_ALEN]; }; union mlx4_ext_av { @@ -913,10 +915,10 @@ enum mlx4_net_trans_promisc_mode { }; struct mlx4_spec_eth { - u8 dst_mac[6]; - u8 dst_mac_msk[6]; - u8 src_mac[6]; - u8 src_mac_msk[6]; + u8 dst_mac[ETH_ALEN]; + u8 dst_mac_msk[ETH_ALEN]; + u8 src_mac[ETH_ALEN]; + u8 src_mac_msk[ETH_ALEN]; u8 ether_type_enable; __be16 ether_type; __be16 vlan_id_msk; diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index 262deac02c9e..6d351473c292 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -34,6 +34,7 @@ #define MLX4_QP_H #include <linux/types.h> +#include <linux/if_ether.h> #include <linux/mlx4/device.h> @@ -143,7 +144,7 @@ struct mlx4_qp_path { u8 feup; u8 fvl_rx; u8 reserved4[2]; - u8 dmac[6]; + u8 dmac[ETH_ALEN]; }; enum { /* fl */ @@ -318,7 +319,7 @@ struct mlx4_wqe_datagram_seg { __be32 dqpn; __be32 qkey; __be16 vlan; - u8 mac[6]; + u8 mac[ETH_ALEN]; }; struct mlx4_wqe_lso_seg { diff --git a/include/linux/mv643xx_eth.h b/include/linux/mv643xx_eth.h index 6e8215b15998..61a0da38d0cb 100644 --- a/include/linux/mv643xx_eth.h +++ b/include/linux/mv643xx_eth.h @@ -6,6 +6,7 @@ #define __LINUX_MV643XX_ETH_H #include <linux/mbus.h> +#include <linux/if_ether.h> #define MV643XX_ETH_SHARED_NAME "mv643xx_eth" #define MV643XX_ETH_NAME "mv643xx_eth_port" @@ -48,7 +49,7 @@ struct mv643xx_eth_platform_data { * Use this MAC address if it is valid, overriding the * address that is already in the hardware. */ - u8 mac_addr[6]; + u8 mac_addr[ETH_ALEN]; /* * If speed is 0, autonegotiation is enabled. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 9a4156845e93..077363dcd860 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -728,6 +728,16 @@ struct netdev_fcoe_hbainfo { }; #endif +#define MAX_PHYS_PORT_ID_LEN 32 + +/* This structure holds a unique identifier to identify the + * physical port used by a netdevice. + */ +struct netdev_phys_port_id { + unsigned char id[MAX_PHYS_PORT_ID_LEN]; + unsigned char id_len; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -932,6 +942,12 @@ struct netdev_fcoe_hbainfo { * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. + * + * int (*ndo_get_phys_port_id)(struct net_device *dev, + * struct netdev_phys_port_id *ppid); + * Called to get ID of physical port of this device. If driver does + * not implement this, it is assumed that the hw is not able to have + * multiple net devices on single physical port. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); @@ -1060,6 +1076,8 @@ struct net_device_ops { struct nlmsghdr *nlh); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); + int (*ndo_get_phys_port_id)(struct net_device *dev, + struct netdev_phys_port_id *ppid); }; /* @@ -1633,6 +1651,7 @@ struct packet_offload { #define NETDEV_NOTIFY_PEERS 0x0013 #define NETDEV_JOIN 0x0014 #define NETDEV_CHANGEUPPER 0x0015 +#define NETDEV_RESEND_IGMP 0x0016 extern int register_netdevice_notifier(struct notifier_block *nb); extern int unregister_netdevice_notifier(struct notifier_block *nb); @@ -1665,9 +1684,6 @@ extern int call_netdevice_notifiers(unsigned long val, struct net_device *dev); extern rwlock_t dev_base_lock; /* Device list lock */ -extern seqcount_t devnet_rename_seq; /* Device rename seq */ - - #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ @@ -2317,6 +2333,8 @@ extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_change_carrier(struct net_device *, bool new_carrier); +extern int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid); extern int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq); diff --git a/include/linux/pci.h b/include/linux/pci.h index 0fd1f1582fa1..2edbee64aeba 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -183,6 +183,19 @@ enum pci_bus_flags { PCI_BUS_FLAGS_NO_MMRBC = (__force pci_bus_flags_t) 2, }; +/* These values come from the PCI Express Spec */ +enum pcie_link_width { + PCIE_LNK_WIDTH_RESRV = 0x00, + PCIE_LNK_X1 = 0x01, + PCIE_LNK_X2 = 0x02, + PCIE_LNK_X4 = 0x04, + PCIE_LNK_X8 = 0x08, + PCIE_LNK_X12 = 0x0C, + PCIE_LNK_X16 = 0x10, + PCIE_LNK_X32 = 0x20, + PCIE_LNK_WIDTH_UNKNOWN = 0xFF, +}; + /* Based on the PCI Hotplug Spec, but some values are made up by us */ enum pci_bus_speed { PCI_SPEED_33MHz = 0x00, @@ -921,6 +934,8 @@ int pcie_get_readrq(struct pci_dev *dev); int pcie_set_readrq(struct pci_dev *dev, int rq); int pcie_get_mps(struct pci_dev *dev); int pcie_set_mps(struct pci_dev *dev, int mps); +int pcie_get_minimum_link(struct pci_dev *dev, enum pci_bus_speed *speed, + enum pcie_link_width *width); int __pci_reset_function(struct pci_dev *dev); int __pci_reset_function_locked(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h index 8db71dcd6337..64e61e05d9a0 100644 --- a/include/linux/pci_hotplug.h +++ b/include/linux/pci_hotplug.h @@ -28,19 +28,6 @@ #ifndef _PCI_HOTPLUG_H #define _PCI_HOTPLUG_H -/* These values come from the PCI Express Spec */ -enum pcie_link_width { - PCIE_LNK_WIDTH_RESRV = 0x00, - PCIE_LNK_X1 = 0x01, - PCIE_LNK_X2 = 0x02, - PCIE_LNK_X4 = 0x04, - PCIE_LNK_X8 = 0x08, - PCIE_LNK_X12 = 0x0C, - PCIE_LNK_X16 = 0x10, - PCIE_LNK_X32 = 0x20, - PCIE_LNK_WIDTH_UNKNOWN = 0xFF, -}; - /** * struct hotplug_slot_ops -the callbacks that the hotplug pci core can use * @owner: The module owner of this structure diff --git a/include/linux/sh_eth.h b/include/linux/sh_eth.h index fc305713fc6d..6205eeba392b 100644 --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@ -2,6 +2,7 @@ #define __ASM_SH_ETH_H__ #include <linux/phy.h> +#include <linux/if_ether.h> enum {EDMAC_LITTLE_ENDIAN, EDMAC_BIG_ENDIAN}; enum { @@ -18,7 +19,7 @@ struct sh_eth_plat_data { phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr); - unsigned char mac_addr[6]; + unsigned char mac_addr[ETH_ALEN]; unsigned no_ether_link:1; unsigned ether_link_active_low:1; unsigned needs_init:1; diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 3b71a4e83642..ae46475d4568 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1805,10 +1805,13 @@ static inline void pskb_trim_unique(struct sk_buff *skb, unsigned int len) */ static inline void skb_orphan(struct sk_buff *skb) { - if (skb->destructor) + if (skb->destructor) { skb->destructor(skb); - skb->destructor = NULL; - skb->sk = NULL; + skb->destructor = NULL; + skb->sk = NULL; + } else { + BUG_ON(skb->sk); + } } /** diff --git a/include/linux/smsc911x.h b/include/linux/smsc911x.h index 4dde70e74822..eec3efd19beb 100644 --- a/include/linux/smsc911x.h +++ b/include/linux/smsc911x.h @@ -22,6 +22,7 @@ #define __LINUX_SMSC911X_H__ #include <linux/phy.h> +#include <linux/if_ether.h> /* platform_device configuration data, should be assigned to * the platform_device's dev.platform_data */ @@ -31,7 +32,7 @@ struct smsc911x_platform_config { unsigned int flags; unsigned int shift; phy_interface_t phy_interface; - unsigned char mac[6]; + unsigned char mac[ETH_ALEN]; }; /* Constants for platform_device irq polarity configuration */ diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 472120b4fac5..d68633452d9b 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -107,7 +107,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt) * only four options will fit in a standard TCP header */ #define TCP_NUM_SACKS 4 -struct tcp_cookie_values; struct tcp_request_sock_ops; struct tcp_request_sock { @@ -238,6 +237,7 @@ struct tcp_sock { u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ + u32 notsent_lowat; /* TCP_NOTSENT_LOWAT */ u32 pushed_seq; /* Last pushed seq, required to talk to windows */ u32 lost_out; /* Lost packets */ u32 sacked_out; /* SACK'd packets */ diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h index f18d64129f99..8fbc008e183e 100644 --- a/include/linux/usb/usbnet.h +++ b/include/linux/usb/usbnet.h @@ -34,6 +34,7 @@ struct usbnet { struct mutex phy_mutex; unsigned char suspend_count; unsigned char pkt_cnt, pkt_err; + unsigned short rx_qlen, tx_qlen; /* i/o info: pipes etc */ unsigned in, out; @@ -253,4 +254,6 @@ extern void usbnet_link_change(struct usbnet *, bool, bool); extern int usbnet_status_start(struct usbnet *dev, gfp_t mem_flags); extern void usbnet_status_stop(struct usbnet *dev); +extern void usbnet_update_max_qlen(struct usbnet *dev); + #endif /* __LINUX_USB_USBNET_H */ diff --git a/include/linux/uwb/spec.h b/include/linux/uwb/spec.h index b52e44f1bd33..0df24bfcdb38 100644 --- a/include/linux/uwb/spec.h +++ b/include/linux/uwb/spec.h @@ -32,6 +32,7 @@ #include <linux/types.h> #include <linux/bitmap.h> +#include <linux/if_ether.h> #define i1480_FW 0x00000303 /* #define i1480_FW 0x00000302 */ @@ -130,7 +131,7 @@ enum { UWB_DRP_BACKOFF_WIN_MAX = 16 }; * it is also used to define headers sent down and up the wire/radio). */ struct uwb_mac_addr { - u8 data[6]; + u8 data[ETH_ALEN]; } __attribute__((packed)); @@ -568,7 +569,7 @@ struct uwb_rc_evt_confirm { /* Device Address Management event. [WHCI] section 3.1.3.2. */ struct uwb_rc_evt_dev_addr_mgmt { struct uwb_rceb rceb; - u8 baAddr[6]; + u8 baAddr[ETH_ALEN]; u8 bResultCode; } __attribute__((packed)); diff --git a/include/media/tveeprom.h b/include/media/tveeprom.h index 4a1191abd936..f7119ee3977b 100644 --- a/include/media/tveeprom.h +++ b/include/media/tveeprom.h @@ -12,6 +12,8 @@ enum tveeprom_audio_processor { TVEEPROM_AUDPROC_OTHER, }; +#include <linux/if_ether.h> + struct tveeprom { u32 has_radio; /* If has_ir == 0, then it is unknown what the IR capabilities are, @@ -40,7 +42,7 @@ struct tveeprom { u32 revision; u32 serial_number; char rev_str[5]; - u8 MAC_address[6]; + u8 MAC_address[ETH_ALEN]; }; void tveeprom_hauppauge_analog(struct i2c_client *c, struct tveeprom *tvee, diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h index d9fa68f26c41..9a36d9297114 100644 --- a/include/net/9p/transport.h +++ b/include/net/9p/transport.h @@ -40,8 +40,6 @@ * @close: member function to discard a connection on this transport * @request: member function to issue a request to the transport * @cancel: member function to cancel a request (if it hasn't been sent) - * @cancelled: member function to notify that a cancelled request will not - * not receive a reply * * This is the basic API for a transport module which is registered by the * transport module with the 9P core network module and used by the client @@ -60,7 +58,6 @@ struct p9_trans_module { void (*close) (struct p9_client *); int (*request) (struct p9_client *, struct p9_req_t *req); int (*cancel) (struct p9_client *, struct p9_req_t *req); - int (*cancelled)(struct p9_client *, struct p9_req_t *req); int (*zc_request)(struct p9_client *, struct p9_req_t *, char *, char *, int , int, int, int); }; diff --git a/include/net/act_api.h b/include/net/act_api.h index b8ffac7b6bab..9e90fdff470d 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -82,36 +82,36 @@ struct tc_action_ops { int (*walk)(struct sk_buff *, struct netlink_callback *, int, struct tc_action *); }; -extern struct tcf_common *tcf_hash_lookup(u32 index, - struct tcf_hashinfo *hinfo); -extern void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo); -extern int tcf_hash_release(struct tcf_common *p, int bind, - struct tcf_hashinfo *hinfo); -extern int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, - int type, struct tc_action *a); -extern u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo); -extern int tcf_hash_search(struct tc_action *a, u32 index); -extern struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, - int bind, struct tcf_hashinfo *hinfo); -extern struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, - struct tc_action *a, int size, - int bind, u32 *idx_gen, - struct tcf_hashinfo *hinfo); -extern void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo); +struct tcf_common *tcf_hash_lookup(u32 index, struct tcf_hashinfo *hinfo); +void tcf_hash_destroy(struct tcf_common *p, struct tcf_hashinfo *hinfo); +int tcf_hash_release(struct tcf_common *p, int bind, + struct tcf_hashinfo *hinfo); +int tcf_generic_walker(struct sk_buff *skb, struct netlink_callback *cb, + int type, struct tc_action *a); +u32 tcf_hash_new_index(u32 *idx_gen, struct tcf_hashinfo *hinfo); +int tcf_hash_search(struct tc_action *a, u32 index); +struct tcf_common *tcf_hash_check(u32 index, struct tc_action *a, + int bind, struct tcf_hashinfo *hinfo); +struct tcf_common *tcf_hash_create(u32 index, struct nlattr *est, + struct tc_action *a, int size, + int bind, u32 *idx_gen, + struct tcf_hashinfo *hinfo); +void tcf_hash_insert(struct tcf_common *p, struct tcf_hashinfo *hinfo); -extern int tcf_register_action(struct tc_action_ops *a); -extern int tcf_unregister_action(struct tc_action_ops *a); -extern void tcf_action_destroy(struct tc_action *a, int bind); -extern int tcf_action_exec(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res); -extern struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind); -extern struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, - struct nlattr *est, char *n, int ovr, - int bind); -extern int tcf_action_dump(struct sk_buff *skb, struct tc_action *a, int, int); -extern int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); -extern int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); -extern int tcf_action_copy_stats (struct sk_buff *,struct tc_action *, int); +int tcf_register_action(struct tc_action_ops *a); +int tcf_unregister_action(struct tc_action_ops *a); +void tcf_action_destroy(struct tc_action *a, int bind); +int tcf_action_exec(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res); +struct tc_action *tcf_action_init(struct net *net, struct nlattr *nla, + struct nlattr *est, char *n, int ovr, + int bind); +struct tc_action *tcf_action_init_1(struct net *net, struct nlattr *nla, + struct nlattr *est, char *n, int ovr, + int bind); +int tcf_action_dump(struct sk_buff *skb, struct tc_action *a, int, int); +int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int); +int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int); +int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); #endif /* CONFIG_NET_CLS_ACT */ #endif diff --git a/include/net/addrconf.h b/include/net/addrconf.h index c7b181cb47a6..43fa31a610b8 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -53,51 +53,36 @@ struct prefix_info { #define IN6_ADDR_HSIZE_SHIFT 4 #define IN6_ADDR_HSIZE (1 << IN6_ADDR_HSIZE_SHIFT) -extern int addrconf_init(void); -extern void addrconf_cleanup(void); +int addrconf_init(void); +void addrconf_cleanup(void); -extern int addrconf_add_ifaddr(struct net *net, - void __user *arg); -extern int addrconf_del_ifaddr(struct net *net, - void __user *arg); -extern int addrconf_set_dstaddr(struct net *net, - void __user *arg); +int addrconf_add_ifaddr(struct net *net, void __user *arg); +int addrconf_del_ifaddr(struct net *net, void __user *arg); +int addrconf_set_dstaddr(struct net *net, void __user *arg); -extern int ipv6_chk_addr(struct net *net, - const struct in6_addr *addr, - const struct net_device *dev, - int strict); +int ipv6_chk_addr(struct net *net, const struct in6_addr *addr, + const struct net_device *dev, int strict); #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) -extern int ipv6_chk_home_addr(struct net *net, - const struct in6_addr *addr); +int ipv6_chk_home_addr(struct net *net, const struct in6_addr *addr); #endif -extern int ipv6_chk_prefix(const struct in6_addr *addr, - struct net_device *dev); - -extern struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, - const struct in6_addr *addr, - struct net_device *dev, - int strict); - -extern int ipv6_dev_get_saddr(struct net *net, - const struct net_device *dev, - const struct in6_addr *daddr, - unsigned int srcprefs, - struct in6_addr *saddr); -extern int __ipv6_get_lladdr(struct inet6_dev *idev, - struct in6_addr *addr, - unsigned char banned_flags); -extern int ipv6_get_lladdr(struct net_device *dev, - struct in6_addr *addr, - unsigned char banned_flags); -extern int ipv6_rcv_saddr_equal(const struct sock *sk, - const struct sock *sk2); -extern void addrconf_join_solict(struct net_device *dev, - const struct in6_addr *addr); -extern void addrconf_leave_solict(struct inet6_dev *idev, - const struct in6_addr *addr); +int ipv6_chk_prefix(const struct in6_addr *addr, struct net_device *dev); + +struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, + const struct in6_addr *addr, + struct net_device *dev, int strict); + +int ipv6_dev_get_saddr(struct net *net, const struct net_device *dev, + const struct in6_addr *daddr, unsigned int srcprefs, + struct in6_addr *saddr); +int __ipv6_get_lladdr(struct inet6_dev *idev, struct in6_addr *addr, + unsigned char banned_flags); +int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr, + unsigned char banned_flags); +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2); +void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr); +void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr); static inline unsigned long addrconf_timeout_fixup(u32 timeout, unsigned int unit) @@ -124,41 +109,38 @@ static inline int addrconf_finite_timeout(unsigned long timeout) /* * IPv6 Address Label subsystem (addrlabel.c) */ -extern int ipv6_addr_label_init(void); -extern void ipv6_addr_label_cleanup(void); -extern void ipv6_addr_label_rtnl_register(void); -extern u32 ipv6_addr_label(struct net *net, - const struct in6_addr *addr, - int type, int ifindex); +int ipv6_addr_label_init(void); +void ipv6_addr_label_cleanup(void); +void ipv6_addr_label_rtnl_register(void); +u32 ipv6_addr_label(struct net *net, const struct in6_addr *addr, + int type, int ifindex); /* * multicast prototypes (mcast.c) */ -extern int ipv6_sock_mc_join(struct sock *sk, int ifindex, - const struct in6_addr *addr); -extern int ipv6_sock_mc_drop(struct sock *sk, int ifindex, - const struct in6_addr *addr); -extern void ipv6_sock_mc_close(struct sock *sk); -extern bool inet6_mc_check(struct sock *sk, - const struct in6_addr *mc_addr, - const struct in6_addr *src_addr); - -extern int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr); -extern int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr); -extern int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr); -extern void ipv6_mc_up(struct inet6_dev *idev); -extern void ipv6_mc_down(struct inet6_dev *idev); -extern void ipv6_mc_unmap(struct inet6_dev *idev); -extern void ipv6_mc_remap(struct inet6_dev *idev); -extern void ipv6_mc_init_dev(struct inet6_dev *idev); -extern void ipv6_mc_destroy_dev(struct inet6_dev *idev); -extern void addrconf_dad_failure(struct inet6_ifaddr *ifp); - -extern bool ipv6_chk_mcast_addr(struct net_device *dev, - const struct in6_addr *group, - const struct in6_addr *src_addr); - -extern void ipv6_mc_dad_complete(struct inet6_dev *idev); +int ipv6_sock_mc_join(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int ipv6_sock_mc_drop(struct sock *sk, int ifindex, + const struct in6_addr *addr); +void ipv6_sock_mc_close(struct sock *sk); +bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr, + const struct in6_addr *src_addr); + +int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr); +int __ipv6_dev_mc_dec(struct inet6_dev *idev, const struct in6_addr *addr); +int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr); +void ipv6_mc_up(struct inet6_dev *idev); +void ipv6_mc_down(struct inet6_dev *idev); +void ipv6_mc_unmap(struct inet6_dev *idev); +void ipv6_mc_remap(struct inet6_dev *idev); +void ipv6_mc_init_dev(struct inet6_dev *idev); +void ipv6_mc_destroy_dev(struct inet6_dev *idev); +void addrconf_dad_failure(struct inet6_ifaddr *ifp); + +bool ipv6_chk_mcast_addr(struct net_device *dev, const struct in6_addr *group, + const struct in6_addr *src_addr); + +void ipv6_mc_dad_complete(struct inet6_dev *idev); /* * identify MLD packets for MLD filter exceptions */ @@ -184,29 +166,31 @@ static inline bool ipv6_is_mld(struct sk_buff *skb, int nexthdr, int offset) return false; } -extern void addrconf_prefix_rcv(struct net_device *dev, - u8 *opt, int len, bool sllao); +void addrconf_prefix_rcv(struct net_device *dev, + u8 *opt, int len, bool sllao); /* * anycast prototypes (anycast.c) */ -extern int ipv6_sock_ac_join(struct sock *sk,int ifindex, const struct in6_addr *addr); -extern int ipv6_sock_ac_drop(struct sock *sk,int ifindex, const struct in6_addr *addr); -extern void ipv6_sock_ac_close(struct sock *sk); - -extern int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr); -extern int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); -extern bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, +int ipv6_sock_ac_join(struct sock *sk, int ifindex, + const struct in6_addr *addr); +int ipv6_sock_ac_drop(struct sock *sk, int ifindex, + const struct in6_addr *addr); +void ipv6_sock_ac_close(struct sock *sk); + +int ipv6_dev_ac_inc(struct net_device *dev, const struct in6_addr *addr); +int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr); +bool ipv6_chk_acast_addr(struct net *net, struct net_device *dev, const struct in6_addr *addr); /* Device notifier */ -extern int register_inet6addr_notifier(struct notifier_block *nb); -extern int unregister_inet6addr_notifier(struct notifier_block *nb); -extern int inet6addr_notifier_call_chain(unsigned long val, void *v); +int register_inet6addr_notifier(struct notifier_block *nb); +int unregister_inet6addr_notifier(struct notifier_block *nb); +int inet6addr_notifier_call_chain(unsigned long val, void *v); -extern void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, - struct ipv6_devconf *devconf); +void inet6_netconf_notify_devconf(struct net *net, int type, int ifindex, + struct ipv6_devconf *devconf); /** * __in6_dev_get - get inet6_dev pointer from netdevice @@ -240,7 +224,7 @@ static inline struct inet6_dev *in6_dev_get(const struct net_device *dev) return idev; } -extern void in6_dev_finish_destroy(struct inet6_dev *idev); +void in6_dev_finish_destroy(struct inet6_dev *idev); static inline void in6_dev_put(struct inet6_dev *idev) { @@ -258,7 +242,7 @@ static inline void in6_dev_hold(struct inet6_dev *idev) atomic_inc(&idev->refcnt); } -extern void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); +void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp); static inline void in6_ifa_put(struct inet6_ifaddr *ifp) { @@ -340,8 +324,8 @@ static inline bool ipv6_addr_is_solict_mult(const struct in6_addr *addr) } #ifdef CONFIG_PROC_FS -extern int if6_proc_init(void); -extern void if6_proc_exit(void); +int if6_proc_init(void); +void if6_proc_exit(void); #endif #endif diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h index 03e6e9453623..e797d45a5ae6 100644 --- a/include/net/af_rxrpc.h +++ b/include/net/af_rxrpc.h @@ -31,24 +31,21 @@ enum { typedef void (*rxrpc_interceptor_t)(struct sock *, unsigned long, struct sk_buff *); -extern void rxrpc_kernel_intercept_rx_messages(struct socket *, - rxrpc_interceptor_t); -extern struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, - struct sockaddr_rxrpc *, - struct key *, - unsigned long, - gfp_t); -extern int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, - size_t); -extern void rxrpc_kernel_abort_call(struct rxrpc_call *, u32); -extern void rxrpc_kernel_end_call(struct rxrpc_call *); -extern bool rxrpc_kernel_is_data_last(struct sk_buff *); -extern u32 rxrpc_kernel_get_abort_code(struct sk_buff *); -extern int rxrpc_kernel_get_error_number(struct sk_buff *); -extern void rxrpc_kernel_data_delivered(struct sk_buff *); -extern void rxrpc_kernel_free_skb(struct sk_buff *); -extern struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, - unsigned long); -extern int rxrpc_kernel_reject_call(struct socket *); +void rxrpc_kernel_intercept_rx_messages(struct socket *, rxrpc_interceptor_t); +struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *, + struct sockaddr_rxrpc *, + struct key *, + unsigned long, + gfp_t); +int rxrpc_kernel_send_data(struct rxrpc_call *, struct msghdr *, size_t); +void rxrpc_kernel_abort_call(struct rxrpc_call *, u32); +void rxrpc_kernel_end_call(struct rxrpc_call *); +bool rxrpc_kernel_is_data_last(struct sk_buff *); +u32 rxrpc_kernel_get_abort_code(struct sk_buff *); +int rxrpc_kernel_get_error_number(struct sk_buff *); +void rxrpc_kernel_data_delivered(struct sk_buff *); +void rxrpc_kernel_free_skb(struct sk_buff *); +struct rxrpc_call *rxrpc_kernel_accept_call(struct socket *, unsigned long); +int rxrpc_kernel_reject_call(struct socket *); #endif /* _NET_RXRPC_H */ diff --git a/include/net/af_unix.h b/include/net/af_unix.h index dbdfd2b0f3b3..05442df4ca89 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -6,12 +6,12 @@ #include <linux/mutex.h> #include <net/sock.h> -extern void unix_inflight(struct file *fp); -extern void unix_notinflight(struct file *fp); -extern void unix_gc(void); -extern void wait_for_unix_gc(void); -extern struct sock *unix_get_socket(struct file *filp); -extern struct sock *unix_peer_get(struct sock *); +void unix_inflight(struct file *fp); +void unix_notinflight(struct file *fp); +void unix_gc(void); +void wait_for_unix_gc(void); +struct sock *unix_get_socket(struct file *filp); +struct sock *unix_peer_get(struct sock *); #define UNIX_HASH_SIZE 256 #define UNIX_HASH_BITS 8 @@ -71,8 +71,8 @@ long unix_inq_len(struct sock *sk); long unix_outq_len(struct sock *sk); #ifdef CONFIG_SYSCTL -extern int unix_sysctl_register(struct net *net); -extern void unix_sysctl_unregister(struct net *net); +int unix_sysctl_register(struct net *net); +void unix_sysctl_unregister(struct net *net); #else static inline int unix_sysctl_register(struct net *net) { return 0; } static inline void unix_sysctl_unregister(struct net *net) {} diff --git a/net/vmw_vsock/af_vsock.h b/include/net/af_vsock.h index 7d64d3609ec9..7d64d3609ec9 100644 --- a/net/vmw_vsock/af_vsock.h +++ b/include/net/af_vsock.h diff --git a/include/net/arp.h b/include/net/arp.h index b630dae03411..7509d9da4e36 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -46,22 +46,22 @@ static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 return n; } -extern void arp_init(void); -extern int arp_find(unsigned char *haddr, struct sk_buff *skb); -extern int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); -extern void arp_send(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, - const unsigned char *src_hw, const unsigned char *th); -extern int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); -extern void arp_ifdown(struct net_device *dev); +void arp_init(void); +int arp_find(unsigned char *haddr, struct sk_buff *skb); +int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, const unsigned char *th); +int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); +void arp_ifdown(struct net_device *dev); -extern struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, - const unsigned char *src_hw, - const unsigned char *target_hw); -extern void arp_xmit(struct sk_buff *skb); +struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw); +void arp_xmit(struct sk_buff *skb); int arp_invalidate(struct net_device *dev, __be32 ip); #endif /* _ARP_H */ diff --git a/include/net/ax25.h b/include/net/ax25.h index 89ed9ac5701f..bf0396e9a5d3 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -195,7 +195,7 @@ static inline void ax25_hold_route(ax25_route *ax25_rt) atomic_inc(&ax25_rt->refcount); } -extern void __ax25_put_route(ax25_route *ax25_rt); +void __ax25_put_route(ax25_route *ax25_rt); static inline void ax25_put_route(ax25_route *ax25_rt) { @@ -272,30 +272,31 @@ static inline __be16 ax25_type_trans(struct sk_buff *skb, struct net_device *dev /* af_ax25.c */ extern struct hlist_head ax25_list; extern spinlock_t ax25_list_lock; -extern void ax25_cb_add(ax25_cb *); +void ax25_cb_add(ax25_cb *); struct sock *ax25_find_listener(ax25_address *, int, struct net_device *, int); struct sock *ax25_get_socket(ax25_address *, ax25_address *, int); -extern ax25_cb *ax25_find_cb(ax25_address *, ax25_address *, ax25_digi *, struct net_device *); -extern void ax25_send_to_raw(ax25_address *, struct sk_buff *, int); -extern void ax25_destroy_socket(ax25_cb *); -extern ax25_cb * __must_check ax25_create_cb(void); -extern void ax25_fillin_cb(ax25_cb *, ax25_dev *); -extern struct sock *ax25_make_new(struct sock *, struct ax25_dev *); +ax25_cb *ax25_find_cb(ax25_address *, ax25_address *, ax25_digi *, + struct net_device *); +void ax25_send_to_raw(ax25_address *, struct sk_buff *, int); +void ax25_destroy_socket(ax25_cb *); +ax25_cb * __must_check ax25_create_cb(void); +void ax25_fillin_cb(ax25_cb *, ax25_dev *); +struct sock *ax25_make_new(struct sock *, struct ax25_dev *); /* ax25_addr.c */ extern const ax25_address ax25_bcast; extern const ax25_address ax25_defaddr; extern const ax25_address null_ax25_address; -extern char *ax2asc(char *buf, const ax25_address *); -extern void asc2ax(ax25_address *addr, const char *callsign); -extern int ax25cmp(const ax25_address *, const ax25_address *); -extern int ax25digicmp(const ax25_digi *, const ax25_digi *); -extern const unsigned char *ax25_addr_parse(const unsigned char *, int, +char *ax2asc(char *buf, const ax25_address *); +void asc2ax(ax25_address *addr, const char *callsign); +int ax25cmp(const ax25_address *, const ax25_address *); +int ax25digicmp(const ax25_digi *, const ax25_digi *); +const unsigned char *ax25_addr_parse(const unsigned char *, int, ax25_address *, ax25_address *, ax25_digi *, int *, int *); -extern int ax25_addr_build(unsigned char *, const ax25_address *, - const ax25_address *, const ax25_digi *, int, int); -extern int ax25_addr_size(const ax25_digi *); -extern void ax25_digi_invert(const ax25_digi *, ax25_digi *); +int ax25_addr_build(unsigned char *, const ax25_address *, + const ax25_address *, const ax25_digi *, int, int); +int ax25_addr_size(const ax25_digi *); +void ax25_digi_invert(const ax25_digi *, ax25_digi *); /* ax25_dev.c */ extern ax25_dev *ax25_dev_list; @@ -306,33 +307,33 @@ static inline ax25_dev *ax25_dev_ax25dev(struct net_device *dev) return dev->ax25_ptr; } -extern ax25_dev *ax25_addr_ax25dev(ax25_address *); -extern void ax25_dev_device_up(struct net_device *); -extern void ax25_dev_device_down(struct net_device *); -extern int ax25_fwd_ioctl(unsigned int, struct ax25_fwd_struct *); -extern struct net_device *ax25_fwd_dev(struct net_device *); -extern void ax25_dev_free(void); +ax25_dev *ax25_addr_ax25dev(ax25_address *); +void ax25_dev_device_up(struct net_device *); +void ax25_dev_device_down(struct net_device *); +int ax25_fwd_ioctl(unsigned int, struct ax25_fwd_struct *); +struct net_device *ax25_fwd_dev(struct net_device *); +void ax25_dev_free(void); /* ax25_ds_in.c */ -extern int ax25_ds_frame_in(ax25_cb *, struct sk_buff *, int); +int ax25_ds_frame_in(ax25_cb *, struct sk_buff *, int); /* ax25_ds_subr.c */ -extern void ax25_ds_nr_error_recovery(ax25_cb *); -extern void ax25_ds_enquiry_response(ax25_cb *); -extern void ax25_ds_establish_data_link(ax25_cb *); -extern void ax25_dev_dama_off(ax25_dev *); -extern void ax25_dama_on(ax25_cb *); -extern void ax25_dama_off(ax25_cb *); +void ax25_ds_nr_error_recovery(ax25_cb *); +void ax25_ds_enquiry_response(ax25_cb *); +void ax25_ds_establish_data_link(ax25_cb *); +void ax25_dev_dama_off(ax25_dev *); +void ax25_dama_on(ax25_cb *); +void ax25_dama_off(ax25_cb *); /* ax25_ds_timer.c */ -extern void ax25_ds_setup_timer(ax25_dev *); -extern void ax25_ds_set_timer(ax25_dev *); -extern void ax25_ds_del_timer(ax25_dev *); -extern void ax25_ds_timer(ax25_cb *); -extern void ax25_ds_t1_timeout(ax25_cb *); -extern void ax25_ds_heartbeat_expiry(ax25_cb *); -extern void ax25_ds_t3timer_expiry(ax25_cb *); -extern void ax25_ds_idletimer_expiry(ax25_cb *); +void ax25_ds_setup_timer(ax25_dev *); +void ax25_ds_set_timer(ax25_dev *); +void ax25_ds_del_timer(ax25_dev *); +void ax25_ds_timer(ax25_cb *); +void ax25_ds_t1_timeout(ax25_cb *); +void ax25_ds_heartbeat_expiry(ax25_cb *); +void ax25_ds_t3timer_expiry(ax25_cb *); +void ax25_ds_idletimer_expiry(ax25_cb *); /* ax25_iface.c */ @@ -342,107 +343,109 @@ struct ax25_protocol { int (*func)(struct sk_buff *, ax25_cb *); }; -extern void ax25_register_pid(struct ax25_protocol *ap); -extern void ax25_protocol_release(unsigned int); +void ax25_register_pid(struct ax25_protocol *ap); +void ax25_protocol_release(unsigned int); struct ax25_linkfail { struct hlist_node lf_node; void (*func)(ax25_cb *, int); }; -extern void ax25_linkfail_register(struct ax25_linkfail *lf); -extern void ax25_linkfail_release(struct ax25_linkfail *lf); -extern int __must_check ax25_listen_register(ax25_address *, - struct net_device *); -extern void ax25_listen_release(ax25_address *, struct net_device *); -extern int (*ax25_protocol_function(unsigned int))(struct sk_buff *, ax25_cb *); -extern int ax25_listen_mine(ax25_address *, struct net_device *); -extern void ax25_link_failed(ax25_cb *, int); -extern int ax25_protocol_is_registered(unsigned int); +void ax25_linkfail_register(struct ax25_linkfail *lf); +void ax25_linkfail_release(struct ax25_linkfail *lf); +int __must_check ax25_listen_register(ax25_address *, struct net_device *); +void ax25_listen_release(ax25_address *, struct net_device *); +int(*ax25_protocol_function(unsigned int))(struct sk_buff *, ax25_cb *); +int ax25_listen_mine(ax25_address *, struct net_device *); +void ax25_link_failed(ax25_cb *, int); +int ax25_protocol_is_registered(unsigned int); /* ax25_in.c */ -extern int ax25_rx_iframe(ax25_cb *, struct sk_buff *); -extern int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); +int ax25_rx_iframe(ax25_cb *, struct sk_buff *); +int ax25_kiss_rcv(struct sk_buff *, struct net_device *, struct packet_type *, + struct net_device *); /* ax25_ip.c */ -extern int ax25_hard_header(struct sk_buff *, struct net_device *, - unsigned short, const void *, - const void *, unsigned int); -extern int ax25_rebuild_header(struct sk_buff *); +int ax25_hard_header(struct sk_buff *, struct net_device *, unsigned short, + const void *, const void *, unsigned int); +int ax25_rebuild_header(struct sk_buff *); extern const struct header_ops ax25_header_ops; /* ax25_out.c */ -extern ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, ax25_digi *, struct net_device *); -extern void ax25_output(ax25_cb *, int, struct sk_buff *); -extern void ax25_kick(ax25_cb *); -extern void ax25_transmit_buffer(ax25_cb *, struct sk_buff *, int); -extern void ax25_queue_xmit(struct sk_buff *skb, struct net_device *dev); -extern int ax25_check_iframes_acked(ax25_cb *, unsigned short); +ax25_cb *ax25_send_frame(struct sk_buff *, int, ax25_address *, ax25_address *, + ax25_digi *, struct net_device *); +void ax25_output(ax25_cb *, int, struct sk_buff *); +void ax25_kick(ax25_cb *); +void ax25_transmit_buffer(ax25_cb *, struct sk_buff *, int); +void ax25_queue_xmit(struct sk_buff *skb, struct net_device *dev); +int ax25_check_iframes_acked(ax25_cb *, unsigned short); /* ax25_route.c */ -extern void ax25_rt_device_down(struct net_device *); -extern int ax25_rt_ioctl(unsigned int, void __user *); +void ax25_rt_device_down(struct net_device *); +int ax25_rt_ioctl(unsigned int, void __user *); extern const struct file_operations ax25_route_fops; -extern ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev); -extern int ax25_rt_autobind(ax25_cb *, ax25_address *); -extern struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *, ax25_address *, ax25_digi *); -extern void ax25_rt_free(void); +ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev); +int ax25_rt_autobind(ax25_cb *, ax25_address *); +struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *, + ax25_address *, ax25_digi *); +void ax25_rt_free(void); /* ax25_std_in.c */ -extern int ax25_std_frame_in(ax25_cb *, struct sk_buff *, int); +int ax25_std_frame_in(ax25_cb *, struct sk_buff *, int); /* ax25_std_subr.c */ -extern void ax25_std_nr_error_recovery(ax25_cb *); -extern void ax25_std_establish_data_link(ax25_cb *); -extern void ax25_std_transmit_enquiry(ax25_cb *); -extern void ax25_std_enquiry_response(ax25_cb *); -extern void ax25_std_timeout_response(ax25_cb *); +void ax25_std_nr_error_recovery(ax25_cb *); +void ax25_std_establish_data_link(ax25_cb *); +void ax25_std_transmit_enquiry(ax25_cb *); +void ax25_std_enquiry_response(ax25_cb *); +void ax25_std_timeout_response(ax25_cb *); /* ax25_std_timer.c */ -extern void ax25_std_heartbeat_expiry(ax25_cb *); -extern void ax25_std_t1timer_expiry(ax25_cb *); -extern void ax25_std_t2timer_expiry(ax25_cb *); -extern void ax25_std_t3timer_expiry(ax25_cb *); -extern void ax25_std_idletimer_expiry(ax25_cb *); +void ax25_std_heartbeat_expiry(ax25_cb *); +void ax25_std_t1timer_expiry(ax25_cb *); +void ax25_std_t2timer_expiry(ax25_cb *); +void ax25_std_t3timer_expiry(ax25_cb *); +void ax25_std_idletimer_expiry(ax25_cb *); /* ax25_subr.c */ -extern void ax25_clear_queues(ax25_cb *); -extern void ax25_frames_acked(ax25_cb *, unsigned short); -extern void ax25_requeue_frames(ax25_cb *); -extern int ax25_validate_nr(ax25_cb *, unsigned short); -extern int ax25_decode(ax25_cb *, struct sk_buff *, int *, int *, int *); -extern void ax25_send_control(ax25_cb *, int, int, int); -extern void ax25_return_dm(struct net_device *, ax25_address *, ax25_address *, ax25_digi *); -extern void ax25_calculate_t1(ax25_cb *); -extern void ax25_calculate_rtt(ax25_cb *); -extern void ax25_disconnect(ax25_cb *, int); +void ax25_clear_queues(ax25_cb *); +void ax25_frames_acked(ax25_cb *, unsigned short); +void ax25_requeue_frames(ax25_cb *); +int ax25_validate_nr(ax25_cb *, unsigned short); +int ax25_decode(ax25_cb *, struct sk_buff *, int *, int *, int *); +void ax25_send_control(ax25_cb *, int, int, int); +void ax25_return_dm(struct net_device *, ax25_address *, ax25_address *, + ax25_digi *); +void ax25_calculate_t1(ax25_cb *); +void ax25_calculate_rtt(ax25_cb *); +void ax25_disconnect(ax25_cb *, int); /* ax25_timer.c */ -extern void ax25_setup_timers(ax25_cb *); -extern void ax25_start_heartbeat(ax25_cb *); -extern void ax25_start_t1timer(ax25_cb *); -extern void ax25_start_t2timer(ax25_cb *); -extern void ax25_start_t3timer(ax25_cb *); -extern void ax25_start_idletimer(ax25_cb *); -extern void ax25_stop_heartbeat(ax25_cb *); -extern void ax25_stop_t1timer(ax25_cb *); -extern void ax25_stop_t2timer(ax25_cb *); -extern void ax25_stop_t3timer(ax25_cb *); -extern void ax25_stop_idletimer(ax25_cb *); -extern int ax25_t1timer_running(ax25_cb *); -extern unsigned long ax25_display_timer(struct timer_list *); +void ax25_setup_timers(ax25_cb *); +void ax25_start_heartbeat(ax25_cb *); +void ax25_start_t1timer(ax25_cb *); +void ax25_start_t2timer(ax25_cb *); +void ax25_start_t3timer(ax25_cb *); +void ax25_start_idletimer(ax25_cb *); +void ax25_stop_heartbeat(ax25_cb *); +void ax25_stop_t1timer(ax25_cb *); +void ax25_stop_t2timer(ax25_cb *); +void ax25_stop_t3timer(ax25_cb *); +void ax25_stop_idletimer(ax25_cb *); +int ax25_t1timer_running(ax25_cb *); +unsigned long ax25_display_timer(struct timer_list *); /* ax25_uid.c */ extern int ax25_uid_policy; -extern ax25_uid_assoc *ax25_findbyuid(kuid_t); -extern int __must_check ax25_uid_ioctl(int, struct sockaddr_ax25 *); +ax25_uid_assoc *ax25_findbyuid(kuid_t); +int __must_check ax25_uid_ioctl(int, struct sockaddr_ax25 *); extern const struct file_operations ax25_uid_fops; -extern void ax25_uid_free(void); +void ax25_uid_free(void); /* sysctl_net_ax25.c */ #ifdef CONFIG_SYSCTL -extern int ax25_register_dev_sysctl(ax25_dev *ax25_dev); -extern void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev); +int ax25_register_dev_sysctl(ax25_dev *ax25_dev); +void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev); #else static inline int ax25_register_dev_sysctl(ax25_dev *ax25_dev) { return 0; } static inline void ax25_unregister_dev_sysctl(ax25_dev *ax25_dev) {} diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7b0730aeb892..f49de283f50e 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -2841,7 +2841,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv); * * Return: A non-negative wiphy index or a negative error code. */ -extern int wiphy_register(struct wiphy *wiphy); +int wiphy_register(struct wiphy *wiphy); /** * wiphy_unregister - deregister a wiphy from cfg80211 @@ -2852,14 +2852,14 @@ extern int wiphy_register(struct wiphy *wiphy); * pointer, but the call may sleep to wait for an outstanding * request that is being handled. */ -extern void wiphy_unregister(struct wiphy *wiphy); +void wiphy_unregister(struct wiphy *wiphy); /** * wiphy_free - free wiphy * * @wiphy: The wiphy to free */ -extern void wiphy_free(struct wiphy *wiphy); +void wiphy_free(struct wiphy *wiphy); /* internal structs */ struct cfg80211_conn; @@ -3014,14 +3014,14 @@ static inline void *wdev_priv(struct wireless_dev *wdev) * @band: band, necessary due to channel number overlap * Return: The corresponding frequency (in MHz), or 0 if the conversion failed. */ -extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); +int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number * @freq: center frequency * Return: The corresponding channel, or 0 if the conversion failed. */ -extern int ieee80211_frequency_to_channel(int freq); +int ieee80211_frequency_to_channel(int freq); /* * Name indirection necessary because the ieee80211 code also has @@ -3030,8 +3030,8 @@ extern int ieee80211_frequency_to_channel(int freq); * to include both header files you'll (rightfully!) get a symbol * clash. */ -extern struct ieee80211_channel *__ieee80211_get_channel(struct wiphy *wiphy, - int freq); +struct ieee80211_channel *__ieee80211_get_channel(struct wiphy *wiphy, + int freq); /** * ieee80211_get_channel - get channel struct from wiphy for specified frequency * @wiphy: the struct wiphy to get the channel for @@ -3141,13 +3141,14 @@ struct ieee80211_radiotap_iterator { int _reset_on_ext; }; -extern int ieee80211_radiotap_iterator_init( - struct ieee80211_radiotap_iterator *iterator, - struct ieee80211_radiotap_header *radiotap_header, - int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns); +int +ieee80211_radiotap_iterator_init(struct ieee80211_radiotap_iterator *iterator, + struct ieee80211_radiotap_header *radiotap_header, + int max_length, + const struct ieee80211_radiotap_vendor_namespaces *vns); -extern int ieee80211_radiotap_iterator_next( - struct ieee80211_radiotap_iterator *iterator); +int +ieee80211_radiotap_iterator_next(struct ieee80211_radiotap_iterator *iterator); extern const unsigned char rfc1042_header[6]; @@ -3307,7 +3308,7 @@ const u8 *cfg80211_find_vendor_ie(unsigned int oui, u8 oui_type, * * Return: 0 on success. -ENOMEM. */ -extern int regulatory_hint(struct wiphy *wiphy, const char *alpha2); +int regulatory_hint(struct wiphy *wiphy, const char *alpha2); /** * wiphy_apply_custom_regulatory - apply a custom driver regulatory domain @@ -3321,9 +3322,8 @@ extern int regulatory_hint(struct wiphy *wiphy, const char *alpha2); * default channel settings will be disregarded. If no rule is found for a * channel on the regulatory domain the channel will be disabled. */ -extern void wiphy_apply_custom_regulatory( - struct wiphy *wiphy, - const struct ieee80211_regdomain *regd); +void wiphy_apply_custom_regulatory(struct wiphy *wiphy, + const struct ieee80211_regdomain *regd); /** * freq_reg_info - get regulatory information for the given frequency diff --git a/include/net/checksum.h b/include/net/checksum.h index 600d1d705bb8..8f59ca50477c 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -107,11 +107,11 @@ static inline void csum_replace2(__sum16 *sum, __be16 from, __be16 to) } struct sk_buff; -extern void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, - __be32 from, __be32 to, int pseudohdr); -extern void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, - const __be32 *from, const __be32 *to, - int pseudohdr); +void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, + __be32 from, __be32 to, int pseudohdr); +void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, + const __be32 *from, const __be32 *to, + int pseudohdr); static inline void inet_proto_csum_replace2(__sum16 *sum, struct sk_buff *skb, __be16 from, __be16 to, diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 0fee0617fb7d..f55c14510bd6 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -24,7 +24,7 @@ struct cgroup_cls_state u32 classid; }; -extern void sock_update_classid(struct sock *sk); +void sock_update_classid(struct sock *sk); #if IS_BUILTIN(CONFIG_NET_CLS_CGROUP) static inline u32 task_cls_classid(struct task_struct *p) diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index e361f4882426..4b2b557fb0e8 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -10,21 +10,25 @@ struct fib_rule { struct list_head list; - atomic_t refcnt; int iifindex; int oifindex; u32 mark; u32 mark_mask; - u32 pref; u32 flags; u32 table; u8 action; + /* 3 bytes hole, try to use */ u32 target; struct fib_rule __rcu *ctarget; + struct net *fr_net; + + atomic_t refcnt; + u32 pref; + int suppress_ifgroup; + int suppress_prefixlen; char iifname[IFNAMSIZ]; char oifname[IFNAMSIZ]; struct rcu_head rcu; - struct net * fr_net; }; struct fib_lookup_arg { @@ -46,6 +50,8 @@ struct fib_rules_ops { int (*action)(struct fib_rule *, struct flowi *, int, struct fib_lookup_arg *); + bool (*suppress)(struct fib_rule *, + struct fib_lookup_arg *); int (*match)(struct fib_rule *, struct flowi *, int); int (*configure)(struct fib_rule *, @@ -80,6 +86,8 @@ struct fib_rules_ops { [FRA_FWMARK] = { .type = NLA_U32 }, \ [FRA_FWMASK] = { .type = NLA_U32 }, \ [FRA_TABLE] = { .type = NLA_U32 }, \ + [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ + [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ [FRA_GOTO] = { .type = NLA_U32 } static inline void fib_rule_get(struct fib_rule *rule) diff --git a/include/net/irda/irlan_common.h b/include/net/irda/irlan_common.h index 0af8b8dfbc22..550c2d6ec7ff 100644 --- a/include/net/irda/irlan_common.h +++ b/include/net/irda/irlan_common.h @@ -32,6 +32,7 @@ #include <linux/types.h> #include <linux/skbuff.h> #include <linux/netdevice.h> +#include <linux/if_ether.h> #include <net/irda/irttp.h> @@ -161,7 +162,7 @@ struct irlan_provider_cb { int access_type; /* Access type */ __u16 send_arb_val; - __u8 mac_address[6]; /* Generated MAC address for peer device */ + __u8 mac_address[ETH_ALEN]; /* Generated MAC address for peer device */ }; /* diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 5b7a3dadadde..e5f02909f1ad 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -2877,14 +2877,14 @@ enum ieee80211_tpt_led_trigger_flags { }; #ifdef CONFIG_MAC80211_LEDS -extern char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); -extern char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); -extern char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); -extern char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); -extern char *__ieee80211_create_tpt_led_trigger( - struct ieee80211_hw *hw, unsigned int flags, - const struct ieee80211_tpt_blink *blink_table, - unsigned int blink_table_len); +char *__ieee80211_get_tx_led_name(struct ieee80211_hw *hw); +char *__ieee80211_get_rx_led_name(struct ieee80211_hw *hw); +char *__ieee80211_get_assoc_led_name(struct ieee80211_hw *hw); +char *__ieee80211_get_radio_led_name(struct ieee80211_hw *hw); +char *__ieee80211_create_tpt_led_trigger(struct ieee80211_hw *hw, + unsigned int flags, + const struct ieee80211_tpt_blink *blink_table, + unsigned int blink_table_len); #endif /** * ieee80211_get_tx_led_name - get name of TX LED diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 7e748ad8b50c..536501a3e58d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -195,68 +195,67 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 -extern void neigh_table_init(struct neigh_table *tbl); -extern int neigh_table_clear(struct neigh_table *tbl); -extern struct neighbour * neigh_lookup(struct neigh_table *tbl, - const void *pkey, - struct net_device *dev); -extern struct neighbour * neigh_lookup_nodev(struct neigh_table *tbl, - struct net *net, - const void *pkey); -extern struct neighbour * __neigh_create(struct neigh_table *tbl, - const void *pkey, - struct net_device *dev, - bool want_ref); +void neigh_table_init(struct neigh_table *tbl); +int neigh_table_clear(struct neigh_table *tbl); +struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, + struct net_device *dev); +struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, + const void *pkey); +struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, bool want_ref); static inline struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev) { return __neigh_create(tbl, pkey, dev, true); } -extern void neigh_destroy(struct neighbour *neigh); -extern int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); -extern int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, - u32 flags); -extern void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); -extern int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); -extern int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); -extern int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); -extern int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb); -extern int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); -extern struct neighbour *neigh_event_ns(struct neigh_table *tbl, +void neigh_destroy(struct neighbour *neigh); +int __neigh_event_send(struct neighbour *neigh, struct sk_buff *skb); +int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags); +void neigh_changeaddr(struct neigh_table *tbl, struct net_device *dev); +int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev); +int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb); +int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb); +int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb); +int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb); +struct neighbour *neigh_event_ns(struct neigh_table *tbl, u8 *lladdr, void *saddr, struct net_device *dev); -extern struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct neigh_table *tbl); -extern void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); +struct neigh_parms *neigh_parms_alloc(struct net_device *dev, + struct neigh_table *tbl); +void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms); static inline -struct net *neigh_parms_net(const struct neigh_parms *parms) +struct net *neigh_parms_net(const struct neigh_parms *parms) { return read_pnet(&parms->net); } -extern unsigned long neigh_rand_reach_time(unsigned long base); +unsigned long neigh_rand_reach_time(unsigned long base); -extern void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, - struct sk_buff *skb); -extern struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev, int creat); -extern struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, - struct net *net, - const void *key, - struct net_device *dev); -extern int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, struct net_device *dev); +void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, + struct sk_buff *skb); +struct pneigh_entry *pneigh_lookup(struct neigh_table *tbl, struct net *net, + const void *key, struct net_device *dev, + int creat); +struct pneigh_entry *__pneigh_lookup(struct neigh_table *tbl, struct net *net, + const void *key, struct net_device *dev); +int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *key, + struct net_device *dev); -static inline -struct net *pneigh_net(const struct pneigh_entry *pneigh) +static inline struct net *pneigh_net(const struct pneigh_entry *pneigh) { return read_pnet(&pneigh->net); } -extern void neigh_app_ns(struct neighbour *n); -extern void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie); -extern void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)); -extern void pneigh_for_each(struct neigh_table *tbl, void (*cb)(struct pneigh_entry *)); +void neigh_app_ns(struct neighbour *n); +void neigh_for_each(struct neigh_table *tbl, + void (*cb)(struct neighbour *, void *), void *cookie); +void __neigh_for_each_release(struct neigh_table *tbl, + int (*cb)(struct neighbour *)); +void pneigh_for_each(struct neigh_table *tbl, + void (*cb)(struct pneigh_entry *)); struct neigh_seq_state { struct seq_net_private p; @@ -270,15 +269,14 @@ struct neigh_seq_state { #define NEIGH_SEQ_IS_PNEIGH 0x00000002 #define NEIGH_SEQ_SKIP_NOARP 0x00000004 }; -extern void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, unsigned int); -extern void *neigh_seq_next(struct seq_file *, void *, loff_t *); -extern void neigh_seq_stop(struct seq_file *, void *); - -extern int neigh_sysctl_register(struct net_device *dev, - struct neigh_parms *p, - char *p_name, - proc_handler *proc_handler); -extern void neigh_sysctl_unregister(struct neigh_parms *p); +void *neigh_seq_start(struct seq_file *, loff_t *, struct neigh_table *, + unsigned int); +void *neigh_seq_next(struct seq_file *, void *, loff_t *); +void neigh_seq_stop(struct seq_file *, void *); + +int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, + char *p_name, proc_handler *proc_handler); +void neigh_sysctl_unregister(struct neigh_parms *p); static inline void __neigh_parms_put(struct neigh_parms *parms) { diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 84e37b1ca9e1..1313456a0994 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -119,7 +119,6 @@ struct net { struct netns_ipvs *ipvs; #endif struct sock *diag_nlsk; - atomic_t rt_genid; atomic_t fnhe_genid; }; @@ -333,14 +332,42 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header) } #endif -static inline int rt_genid(struct net *net) +static inline int rt_genid_ipv4(struct net *net) { - return atomic_read(&net->rt_genid); + return atomic_read(&net->ipv4.rt_genid); } -static inline void rt_genid_bump(struct net *net) +static inline void rt_genid_bump_ipv4(struct net *net) { - atomic_inc(&net->rt_genid); + atomic_inc(&net->ipv4.rt_genid); +} + +#if IS_ENABLED(CONFIG_IPV6) +static inline int rt_genid_ipv6(struct net *net) +{ + return atomic_read(&net->ipv6.rt_genid); +} + +static inline void rt_genid_bump_ipv6(struct net *net) +{ + atomic_inc(&net->ipv6.rt_genid); +} +#else +static inline int rt_genid_ipv6(struct net *net) +{ + return 0; +} + +static inline void rt_genid_bump_ipv6(struct net *net) +{ +} +#endif + +/* For callers who don't really care about whether it's IPv4 or IPv6 */ +static inline void rt_genid_bump_all(struct net *net) +{ + rt_genid_bump_ipv4(net); + rt_genid_bump_ipv6(net); } static inline int fnhe_genid(struct net *net) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 2ba9de89e8ec..bf2ec2202c56 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -77,5 +77,6 @@ struct netns_ipv4 { struct fib_rules_ops *mr_rules_ops; #endif #endif + atomic_t rt_genid; }; #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 005e2c2e39a9..0fb2401197c5 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -72,6 +72,7 @@ struct netns_ipv6 { #endif #endif atomic_t dev_addr_genid; + atomic_t rt_genid; }; #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) diff --git a/include/net/netprio_cgroup.h b/include/net/netprio_cgroup.h index 50ab8c26ab59..379dd5db0f2f 100644 --- a/include/net/netprio_cgroup.h +++ b/include/net/netprio_cgroup.h @@ -29,7 +29,7 @@ struct cgroup_netprio_state { struct cgroup_subsys_state css; }; -extern void sock_update_netprioidx(struct sock *sk); +void sock_update_netprioidx(struct sock *sk); #if IS_BUILTIN(CONFIG_NETPRIO_CGROUP) diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 13174509cdfd..2ebef77a2f9a 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -14,8 +14,8 @@ struct tcf_walker { int (*fn)(struct tcf_proto *, unsigned long node, struct tcf_walker *); }; -extern int register_tcf_proto_ops(struct tcf_proto_ops *ops); -extern int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); +int register_tcf_proto_ops(struct tcf_proto_ops *ops); +int unregister_tcf_proto_ops(struct tcf_proto_ops *ops); static inline unsigned long __cls_set_class(unsigned long *clp, unsigned long cl) @@ -126,17 +126,17 @@ tcf_exts_exec(struct sk_buff *skb, struct tcf_exts *exts, return 0; } -extern int tcf_exts_validate(struct net *net, struct tcf_proto *tp, - struct nlattr **tb, struct nlattr *rate_tlv, - struct tcf_exts *exts, - const struct tcf_ext_map *map); -extern void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts); -extern void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, - struct tcf_exts *src); -extern int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts, - const struct tcf_ext_map *map); -extern int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, - const struct tcf_ext_map *map); +int tcf_exts_validate(struct net *net, struct tcf_proto *tp, + struct nlattr **tb, struct nlattr *rate_tlv, + struct tcf_exts *exts, + const struct tcf_ext_map *map); +void tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts); +void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, + struct tcf_exts *src); +int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts, + const struct tcf_ext_map *map); +int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, + const struct tcf_ext_map *map); /** * struct tcf_pkt_info - packet information @@ -239,14 +239,14 @@ struct tcf_ematch_ops { struct list_head link; }; -extern int tcf_em_register(struct tcf_ematch_ops *); -extern void tcf_em_unregister(struct tcf_ematch_ops *); -extern int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *, - struct tcf_ematch_tree *); -extern void tcf_em_tree_destroy(struct tcf_proto *, struct tcf_ematch_tree *); -extern int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int); -extern int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, - struct tcf_pkt_info *); +int tcf_em_register(struct tcf_ematch_ops *); +void tcf_em_unregister(struct tcf_ematch_ops *); +int tcf_em_tree_validate(struct tcf_proto *, struct nlattr *, + struct tcf_ematch_tree *); +void tcf_em_tree_destroy(struct tcf_proto *, struct tcf_ematch_tree *); +int tcf_em_tree_dump(struct sk_buff *, struct tcf_ematch_tree *, int); +int __tcf_em_tree_match(struct sk_buff *, struct tcf_ematch_tree *, + struct tcf_pkt_info *); /** * tcf_em_tree_change - replace ematch tree of a running classifier diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 388bf8b6d060..f7c24f8fbdc5 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -64,8 +64,8 @@ struct qdisc_watchdog { struct Qdisc *qdisc; }; -extern void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); -extern void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires); +void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc); +void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires); static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) @@ -73,31 +73,31 @@ static inline void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, qdisc_watchdog_schedule_ns(wd, PSCHED_TICKS2NS(expires)); } -extern void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); +void qdisc_watchdog_cancel(struct qdisc_watchdog *wd); extern struct Qdisc_ops pfifo_qdisc_ops; extern struct Qdisc_ops bfifo_qdisc_ops; extern struct Qdisc_ops pfifo_head_drop_qdisc_ops; -extern int fifo_set_limit(struct Qdisc *q, unsigned int limit); -extern struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, - unsigned int limit); - -extern int register_qdisc(struct Qdisc_ops *qops); -extern int unregister_qdisc(struct Qdisc_ops *qops); -extern void qdisc_list_del(struct Qdisc *q); -extern struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); -extern struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); -extern struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, - struct nlattr *tab); -extern void qdisc_put_rtab(struct qdisc_rate_table *tab); -extern void qdisc_put_stab(struct qdisc_size_table *tab); -extern void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc); -extern int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, - struct net_device *dev, struct netdev_queue *txq, - spinlock_t *root_lock); - -extern void __qdisc_run(struct Qdisc *q); +int fifo_set_limit(struct Qdisc *q, unsigned int limit); +struct Qdisc *fifo_create_dflt(struct Qdisc *sch, struct Qdisc_ops *ops, + unsigned int limit); + +int register_qdisc(struct Qdisc_ops *qops); +int unregister_qdisc(struct Qdisc_ops *qops); +void qdisc_list_del(struct Qdisc *q); +struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle); +struct Qdisc *qdisc_lookup_class(struct net_device *dev, u32 handle); +struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, + struct nlattr *tab); +void qdisc_put_rtab(struct qdisc_rate_table *tab); +void qdisc_put_stab(struct qdisc_size_table *tab); +void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc); +int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, struct netdev_queue *txq, + spinlock_t *root_lock); + +void __qdisc_run(struct Qdisc *q); static inline void qdisc_run(struct Qdisc *q) { @@ -105,10 +105,10 @@ static inline void qdisc_run(struct Qdisc *q) __qdisc_run(q); } -extern int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res); -extern int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, +int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res); +int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, + struct tcf_result *res); /* Calculate maximal size of packet seen by hard_start_xmit routine of this device. diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 6eab63363e59..ffc9d883b163 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -350,30 +350,32 @@ qdisc_class_find(const struct Qdisc_class_hash *hash, u32 id) return NULL; } -extern int qdisc_class_hash_init(struct Qdisc_class_hash *); -extern void qdisc_class_hash_insert(struct Qdisc_class_hash *, struct Qdisc_class_common *); -extern void qdisc_class_hash_remove(struct Qdisc_class_hash *, struct Qdisc_class_common *); -extern void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); -extern void qdisc_class_hash_destroy(struct Qdisc_class_hash *); - -extern void dev_init_scheduler(struct net_device *dev); -extern void dev_shutdown(struct net_device *dev); -extern void dev_activate(struct net_device *dev); -extern void dev_deactivate(struct net_device *dev); -extern void dev_deactivate_many(struct list_head *head); -extern struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, - struct Qdisc *qdisc); -extern void qdisc_reset(struct Qdisc *qdisc); -extern void qdisc_destroy(struct Qdisc *qdisc); -extern void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n); -extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, - struct Qdisc_ops *ops); -extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, - struct Qdisc_ops *ops, u32 parentid); -extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, - const struct qdisc_size_table *stab); -extern void tcf_destroy(struct tcf_proto *tp); -extern void tcf_destroy_chain(struct tcf_proto **fl); +int qdisc_class_hash_init(struct Qdisc_class_hash *); +void qdisc_class_hash_insert(struct Qdisc_class_hash *, + struct Qdisc_class_common *); +void qdisc_class_hash_remove(struct Qdisc_class_hash *, + struct Qdisc_class_common *); +void qdisc_class_hash_grow(struct Qdisc *, struct Qdisc_class_hash *); +void qdisc_class_hash_destroy(struct Qdisc_class_hash *); + +void dev_init_scheduler(struct net_device *dev); +void dev_shutdown(struct net_device *dev); +void dev_activate(struct net_device *dev); +void dev_deactivate(struct net_device *dev); +void dev_deactivate_many(struct list_head *head); +struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, + struct Qdisc *qdisc); +void qdisc_reset(struct Qdisc *qdisc); +void qdisc_destroy(struct Qdisc *qdisc); +void qdisc_tree_decrease_qlen(struct Qdisc *qdisc, unsigned int n); +struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, + struct Qdisc_ops *ops); +struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, + struct Qdisc_ops *ops, u32 parentid); +void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); +void tcf_destroy(struct tcf_proto *tp); +void tcf_destroy_chain(struct tcf_proto **fl); /* Reset all TX qdiscs greater then index of a device. */ static inline void qdisc_reset_all_tx_gt(struct net_device *dev, unsigned int i) @@ -692,7 +694,8 @@ static inline u64 psched_l2t_ns(const struct psched_ratecfg *r, return ((u64)(len + r->overhead) * r->mult) >> r->shift; } -extern void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf); +void psched_ratecfg_precompute(struct psched_ratecfg *r, + const struct tc_ratespec *conf); static inline void psched_ratecfg_getrate(struct tc_ratespec *res, const struct psched_ratecfg *r) diff --git a/include/net/sctp/auth.h b/include/net/sctp/auth.h index 49bc9577c61e..754c511f4cf9 100644 --- a/include/net/sctp/auth.h +++ b/include/net/sctp/auth.h @@ -22,7 +22,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sctp/checksum.h b/include/net/sctp/checksum.h index 0cb08e6fb6df..483e6303458d 100644 --- a/include/net/sctp/checksum.h +++ b/include/net/sctp/checksum.h @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -85,4 +85,19 @@ static inline __le32 sctp_end_cksum(__u32 crc32) return cpu_to_le32(~crc32); } +/* Calculate the CRC32C checksum of an SCTP packet. */ +static inline __le32 sctp_compute_cksum(const struct sk_buff *skb, + unsigned int offset) +{ + const struct sk_buff *iter; + + __u32 crc32 = sctp_start_cksum(skb->data + offset, + skb_headlen(skb) - offset); + skb_walk_frags(skb, iter) + crc32 = sctp_update_cksum((__u8 *) iter->data, + skb_headlen(iter), crc32); + + return sctp_end_cksum(crc32); +} + #endif /* __sctp_checksum_h__ */ diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index ca50e0751e47..a1e7aa5c8bbf 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index d8e37ecea691..cb28df9c2781 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -613,7 +613,7 @@ static inline void sctp_v4_map_v6(union sctp_addr *addr) */ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport *t) { - if (t->dst && !dst_check(t->dst, 0)) { + if (t->dst && !dst_check(t->dst, t->dst_cookie)) { dst_release(t->dst); t->dst = NULL; } diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2a82d1384706..2aa66dda4a5a 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email addresses: - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index e745c92a1532..c0f4e29eedd5 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email addresses: - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -946,6 +946,7 @@ struct sctp_transport { __u64 hb_nonce; struct rcu_head rcu; + u32 dst_cookie; }; struct sctp_transport *sctp_transport_new(struct net *, const union sctp_addr *, diff --git a/include/net/sctp/tsnmap.h b/include/net/sctp/tsnmap.h index 2c5d2b4d5d1e..c361d6f7e0cb 100644 --- a/include/net/sctp/tsnmap.h +++ b/include/net/sctp/tsnmap.h @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sctp/ulpevent.h b/include/net/sctp/ulpevent.h index ca4693b4e09e..34f0d34d22ce 100644 --- a/include/net/sctp/ulpevent.h +++ b/include/net/sctp/ulpevent.h @@ -31,7 +31,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sctp/ulpqueue.h b/include/net/sctp/ulpqueue.h index 00e50ba3f24b..add3237a9fdb 100644 --- a/include/net/sctp/ulpqueue.h +++ b/include/net/sctp/ulpqueue.h @@ -30,7 +30,7 @@ * * Please send any bug reports or fixes you make to the * email addresses: - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/net/sock.h b/include/net/sock.h index 31d5cfbb51ec..ab6a8b75207e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -746,11 +746,6 @@ static inline int sk_stream_wspace(const struct sock *sk) extern void sk_stream_write_space(struct sock *sk); -static inline bool sk_stream_memory_free(const struct sock *sk) -{ - return sk->sk_wmem_queued < sk->sk_sndbuf; -} - /* OOB backlog add */ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) { @@ -950,6 +945,7 @@ struct proto { unsigned int inuse_idx; #endif + bool (*stream_memory_free)(const struct sock *sk); /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); atomic_long_t *memory_allocated; /* Current allocated memory. */ @@ -1088,6 +1084,21 @@ static inline struct cg_proto *parent_cg_proto(struct proto *proto, } #endif +static inline bool sk_stream_memory_free(const struct sock *sk) +{ + if (sk->sk_wmem_queued >= sk->sk_sndbuf) + return false; + + return sk->sk_prot->stream_memory_free ? + sk->sk_prot->stream_memory_free(sk) : true; +} + +static inline bool sk_stream_is_writeable(const struct sock *sk) +{ + return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && + sk_stream_memory_free(sk); +} + static inline bool sk_has_memory_pressure(const struct sock *sk) { @@ -1509,6 +1520,7 @@ extern struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority); extern void sock_wfree(struct sk_buff *skb); +extern void skb_orphan_partial(struct sk_buff *skb); extern void sock_rfree(struct sk_buff *skb); extern void sock_edemux(struct sk_buff *skb); @@ -2249,6 +2261,8 @@ static inline struct sock *skb_steal_sock(struct sk_buff *skb) extern void sock_enable_timestamp(struct sock *sk, int flag); extern int sock_get_timestamp(struct sock *, struct timeval __user *); extern int sock_get_timestampns(struct sock *, struct timespec __user *); +extern int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type); /* * Enable debug/info messages diff --git a/include/net/tcp.h b/include/net/tcp.h index d1980054ec75..27b652f379ef 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -192,10 +192,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define TCPOLEN_TIMESTAMP 10 #define TCPOLEN_MD5SIG 18 #define TCPOLEN_EXP_FASTOPEN_BASE 4 -#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */ -#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */ -#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN) -#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX) /* But this is what stacks really send out. */ #define TCPOLEN_TSTAMP_ALIGNED 12 @@ -284,6 +280,7 @@ extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; +extern unsigned int sysctl_tcp_notsent_lowat; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -591,7 +588,6 @@ extern void tcp_initialize_rcv_mss(struct sock *sk); extern int tcp_mtu_to_mss(struct sock *sk, int pmtu); extern int tcp_mss_to_mtu(struct sock *sk, int mss); extern void tcp_mtup_init(struct sock *sk); -extern void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt); extern void tcp_init_buffer_space(struct sock *sk); static inline void tcp_bound_rto(const struct sock *sk) @@ -1094,15 +1090,6 @@ static inline void tcp_openreq_init(struct request_sock *req, ireq->loc_port = tcp_hdr(skb)->dest; } -/* Compute time elapsed between SYNACK and the ACK completing 3WHS */ -static inline void tcp_synack_rtt_meas(struct sock *sk, - struct request_sock *req) -{ - if (tcp_rsk(req)->snt_synack) - tcp_valid_rtt_meas(sk, - tcp_time_stamp - tcp_rsk(req)->snt_synack); -} - extern void tcp_enter_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) @@ -1549,6 +1536,19 @@ extern int tcp_gro_complete(struct sk_buff *skb); extern void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); +static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) +{ + return tp->notsent_lowat ?: sysctl_tcp_notsent_lowat; +} + +static inline bool tcp_stream_memory_free(const struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 notsent_bytes = tp->write_seq - tp->snd_nxt; + + return notsent_bytes < tcp_notsent_lowat(tp); +} + #ifdef CONFIG_PROC_FS extern int tcp4_proc_init(void); extern void tcp4_proc_exit(void); diff --git a/include/net/udp.h b/include/net/udp.h index 74c10ec5e74f..ef2e0b7843a0 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -183,6 +183,7 @@ extern int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len); extern int udp_push_pending_frames(struct sock *sk); extern void udp_flush_pending_frames(struct sock *sk); +extern void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); extern int udp_rcv(struct sk_buff *skb); extern int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int udp_disconnect(struct sock *sk, int flags); diff --git a/net/vmw_vsock/vsock_addr.h b/include/net/vsock_addr.h index 9ccd5316eac0..9ccd5316eac0 100644 --- a/net/vmw_vsock/vsock_addr.h +++ b/include/net/vsock_addr.h diff --git a/include/uapi/linux/dn.h b/include/uapi/linux/dn.h index 9c50445462d9..5fbdd3d49eba 100644 --- a/include/uapi/linux/dn.h +++ b/include/uapi/linux/dn.h @@ -2,6 +2,7 @@ #define _LINUX_DN_H #include <linux/types.h> +#include <linux/if_ether.h> /* @@ -120,7 +121,7 @@ struct linkinfo_dn { * Ethernet address format (for DECnet) */ union etheraddress { - __u8 dne_addr[6]; /* Full ethernet address */ + __u8 dne_addr[ETH_ALEN]; /* Full ethernet address */ struct { __u8 dne_hiord[4]; /* DECnet HIORD prefix */ __u8 dne_nodeaddr[2]; /* DECnet node address */ diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h index 51da65b68b85..2b82d7e30974 100644 --- a/include/uapi/linux/fib_rules.h +++ b/include/uapi/linux/fib_rules.h @@ -44,8 +44,8 @@ enum { FRA_FWMARK, /* mark */ FRA_FLOW, /* flow/class id */ FRA_UNUSED6, - FRA_UNUSED7, - FRA_UNUSED8, + FRA_SUPPRESS_IFGROUP, + FRA_SUPPRESS_PREFIXLEN, FRA_TABLE, /* Extended table id */ FRA_FWMASK, /* mask for netfilter mark */ FRA_OIFNAME, diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 2d70d79ce2fd..39f621a9fe82 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -14,6 +14,7 @@ #define _UAPI_LINUX_IF_BRIDGE_H #include <linux/types.h> +#include <linux/if_ether.h> #define SYSFS_BRIDGE_ATTR "bridge" #define SYSFS_BRIDGE_FDB "brforward" @@ -88,7 +89,7 @@ struct __port_info { }; struct __fdb_entry { - __u8 mac_addr[6]; + __u8 mac_addr[ETH_ALEN]; __u8 port_no; __u8 is_local; __u32 ageing_timer_value; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 03f6170ab337..04c0e7a5d484 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -143,6 +143,7 @@ enum { IFLA_NUM_TX_QUEUES, IFLA_NUM_RX_QUEUES, IFLA_CARRIER, + IFLA_PHYS_PORT_ID, __IFLA_MAX }; diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index 82334f88967e..1870ee29bb37 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -71,6 +71,9 @@ /* read-only flag */ #define IFF_PERSIST 0x0800 +/* Socket options */ +#define TUN_TX_TIMESTAMP 1 + /* Features for GSO (TUNSETOFFLOAD). */ #define TUN_F_CSUM 0x01 /* You can hand me unchecksummed packets. */ #define TUN_F_TSO4 0x02 /* I can handle TSO for IPv4 packets */ diff --git a/include/uapi/linux/netfilter_bridge/ebt_802_3.h b/include/uapi/linux/netfilter_bridge/ebt_802_3.h index 5bf84912a082..f37522aade24 100644 --- a/include/uapi/linux/netfilter_bridge/ebt_802_3.h +++ b/include/uapi/linux/netfilter_bridge/ebt_802_3.h @@ -2,6 +2,7 @@ #define _UAPI__LINUX_BRIDGE_EBT_802_3_H #include <linux/types.h> +#include <linux/if_ether.h> #define EBT_802_3_SAP 0x01 #define EBT_802_3_TYPE 0x02 @@ -42,8 +43,8 @@ struct hdr_ni { }; struct ebt_802_3_hdr { - __u8 daddr[6]; - __u8 saddr[6]; + __u8 daddr[ETH_ALEN]; + __u8 saddr[ETH_ALEN]; __be16 len; union { struct hdr_ui ui; diff --git a/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h index c6a204c97047..eac0f6548f47 100644 --- a/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/uapi/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -2,6 +2,7 @@ #define _IPT_CLUSTERIP_H_target #include <linux/types.h> +#include <linux/if_ether.h> enum clusterip_hashmode { CLUSTERIP_HASHMODE_SIP = 0, @@ -22,7 +23,7 @@ struct ipt_clusterip_tgt_info { __u32 flags; /* only relevant for new ones */ - __u8 clustermac[6]; + __u8 clustermac[ETH_ALEN]; __u16 num_total_nodes; __u16 num_local_nodes; __u16 local_nodes[CLUSTERIP_MAX_NODES]; diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h index 66b466e4ca08..ca451e99b28b 100644 --- a/include/uapi/linux/sctp.h +++ b/include/uapi/linux/sctp.h @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8d776ebc4829..377f1e59411d 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -111,6 +111,7 @@ enum { #define TCP_REPAIR_OPTIONS 22 #define TCP_FASTOPEN 23 /* Enable FastOpen on listeners */ #define TCP_TIMESTAMP 24 +#define TCP_NOTSENT_LOWAT 25 /* limit number of unsent bytes in write queue */ struct tcp_repair_opt { __u32 opt_code; diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index c520203fac2f..172a7f00780c 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -60,7 +60,7 @@ struct virtio_net_config { /* The config defining mac address (if VIRTIO_NET_F_MAC) */ - __u8 mac[6]; + __u8 mac[ETH_ALEN]; /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */ __u16 status; /* Maximum number of each of transmit and receive queues; @@ -70,7 +70,9 @@ struct virtio_net_config { __u16 max_virtqueue_pairs; } __attribute__((packed)); -/* This is the first element of the scatter-gather list. If you don't +/* This header comes first in the scatter-gather list. + * If VIRTIO_F_ANY_LAYOUT is not negotiated, it must + * be the first element of the scatter-gather list. If you don't * specify GSO or CSUM features, you can simply ignore the header. */ struct virtio_net_hdr { #define VIRTIO_NET_HDR_F_NEEDS_CSUM 1 // Use csum_start, csum_offset diff --git a/include/uapi/linux/wimax/i2400m.h b/include/uapi/linux/wimax/i2400m.h index 62d356153565..fd198bc24a3c 100644 --- a/include/uapi/linux/wimax/i2400m.h +++ b/include/uapi/linux/wimax/i2400m.h @@ -122,7 +122,7 @@ #define __LINUX__WIMAX__I2400M_H__ #include <linux/types.h> - +#include <linux/if_ether.h> /* * Host Device Interface (HDI) common to all busses @@ -487,7 +487,7 @@ struct i2400m_tlv_l4_message_versions { struct i2400m_tlv_detailed_device_info { struct i2400m_tlv_hdr hdr; __u8 reserved1[400]; - __u8 mac_address[6]; + __u8 mac_address[ETH_ALEN]; __u8 reserved2[2]; } __attribute__((packed)); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 2fb2d88e8c2e..61fc573f1142 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -210,6 +210,7 @@ out_vid_del: static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) { struct net_device *new_dev; + struct vlan_dev_priv *vlan; struct net *net = dev_net(real_dev); struct vlan_net *vn = net_generic(net, vlan_net_id); char name[IFNAMSIZ]; @@ -260,11 +261,12 @@ static int register_vlan_device(struct net_device *real_dev, u16 vlan_id) new_dev->mtu = real_dev->mtu; new_dev->priv_flags |= (real_dev->priv_flags & IFF_UNICAST_FLT); - vlan_dev_priv(new_dev)->vlan_proto = htons(ETH_P_8021Q); - vlan_dev_priv(new_dev)->vlan_id = vlan_id; - vlan_dev_priv(new_dev)->real_dev = real_dev; - vlan_dev_priv(new_dev)->dent = NULL; - vlan_dev_priv(new_dev)->flags = VLAN_FLAG_REORDER_HDR; + vlan = vlan_dev_priv(new_dev); + vlan->vlan_proto = htons(ETH_P_8021Q); + vlan->vlan_id = vlan_id; + vlan->real_dev = real_dev; + vlan->dent = NULL; + vlan->flags = VLAN_FLAG_REORDER_HDR; new_dev->rtnl_link_ops = &vlan_link_ops; err = register_vlan_dev(new_dev); @@ -459,6 +461,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_NOTIFY_PEERS: case NETDEV_BONDING_FAILOVER: + case NETDEV_RESEND_IGMP: /* Propagate to vlan devices */ vlan_group_for_each_dev(grp, i, vlandev) call_netdevice_notifiers(event, vlandev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 1cd3d2a406f5..9ab8a7ed99c0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -107,10 +107,10 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, u16 vlan_tci = 0; int rc; - if (!(vlan_dev_priv(dev)->flags & VLAN_FLAG_REORDER_HDR)) { + if (!(vlan->flags & VLAN_FLAG_REORDER_HDR)) { vhdr = (struct vlan_hdr *) skb_push(skb, VLAN_HLEN); - vlan_tci = vlan_dev_priv(dev)->vlan_id; + vlan_tci = vlan->vlan_id; vlan_tci |= vlan_dev_get_egress_qos_mask(dev, skb); vhdr->h_vlan_TCI = htons(vlan_tci); @@ -133,7 +133,7 @@ static int vlan_dev_hard_header(struct sk_buff *skb, struct net_device *dev, saddr = dev->dev_addr; /* Now make the underlying real hard header */ - dev = vlan_dev_priv(dev)->real_dev; + dev = vlan->real_dev; rc = dev_hard_header(skb, dev, type, daddr, saddr, len + vhdrlen); if (rc > 0) rc += vhdrlen; diff --git a/net/9p/client.c b/net/9p/client.c index 8b93cae2d11d..ba93bdab2701 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -658,17 +658,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq) /* * if we haven't received a response for oldreq, - * remove it from the list, and notify the transport - * layer that the reply will never arrive. + * remove it from the list */ - spin_lock(&c->lock); if (oldreq->status == REQ_STATUS_FLSH) { + spin_lock(&c->lock); list_del(&oldreq->req_list); spin_unlock(&c->lock); - if (c->trans_mod->cancelled) - c->trans_mod->cancelled(c, req); - } else { - spin_unlock(&c->lock); } p9_free_req(c, req); diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 928f2bb9bf8d..8f68df5d2973 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -588,17 +588,6 @@ static int rdma_cancel(struct p9_client *client, struct p9_req_t *req) return 1; } -/* A request has been fully flushed without a reply. - * That means we have posted one buffer in excess. - */ -static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req) -{ - struct p9_trans_rdma *rdma = client->trans; - - atomic_inc(&rdma->excess_rc); - return 0; -} - /** * trans_create_rdma - Transport method for creating atransport instance * @client: client instance diff --git a/net/Kconfig b/net/Kconfig index 2b406608a1a4..ee0213667272 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -281,7 +281,7 @@ menu "Network testing" config NET_PKTGEN tristate "Packet Generator (USE WITH CAUTION)" - depends on PROC_FS + depends on INET && PROC_FS ---help--- This module will inject preconfigured packets, at a configurable rate, out of a given interface. It is used for network interface diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 69363bd37f64..0feaaa0d37d1 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -245,22 +245,22 @@ fail: int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp) { struct netpoll *np; - int err = 0; + int err; + + if (!p->br->dev->npinfo) + return 0; np = kzalloc(sizeof(*p->np), gfp); - err = -ENOMEM; if (!np) - goto out; + return -ENOMEM; err = __netpoll_setup(np, p->dev, gfp); if (err) { kfree(np); - goto out; + return err; } p->np = np; - -out: return err; } diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 5623be6b9ecd..aa6c9a8ba32a 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -363,7 +363,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (err) goto err2; - if (br_netpoll_info(br) && ((err = br_netpoll_enable(p, GFP_KERNEL)))) + err = br_netpoll_enable(p, GFP_KERNEL); + if (err) goto err3; err = netdev_master_upper_dev_link(dev, br->dev); diff --git a/net/bridge/br_notify.c b/net/bridge/br_notify.c index 3a3f371b2841..2998dd1769a0 100644 --- a/net/bridge/br_notify.c +++ b/net/bridge/br_notify.c @@ -102,6 +102,11 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_PRE_TYPE_CHANGE: /* Forbid underlaying device to change its type. */ return NOTIFY_BAD; + + case NETDEV_RESEND_IGMP: + /* Propagate to master device */ + call_netdevice_notifiers(event, br->dev); + break; } /* Events that may cause spanning tree to refresh */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 2f7da41851bf..1514c9f4f102 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -334,11 +334,6 @@ extern void br_dev_delete(struct net_device *dev, struct list_head *list); extern netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev); #ifdef CONFIG_NET_POLL_CONTROLLER -static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) -{ - return br->dev->npinfo; -} - static inline void br_netpoll_send_skb(const struct net_bridge_port *p, struct sk_buff *skb) { @@ -351,11 +346,6 @@ static inline void br_netpoll_send_skb(const struct net_bridge_port *p, extern int br_netpoll_enable(struct net_bridge_port *p, gfp_t gfp); extern void br_netpoll_disable(struct net_bridge_port *p); #else -static inline struct netpoll_info *br_netpoll_info(struct net_bridge *br) -{ - return NULL; -} - static inline void br_netpoll_send_skb(const struct net_bridge_port *p, struct sk_buff *skb) { diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index eb0a46a49bd4..3be308e14302 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -409,7 +409,7 @@ static void ceph_sock_write_space(struct sock *sk) * and net/core/stream.c:sk_stream_write_space(). */ if (con_flag_test(con, CON_FLAG_WRITE_PENDING)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { dout("%s %p queueing write work\n", __func__, con); clear_bit(SOCK_NOSPACE, &sk->sk_socket->flags); queue_con(con); diff --git a/net/core/dev.c b/net/core/dev.c index 26755dd40daa..58eb802584b9 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -174,7 +174,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id; static DEFINE_HASHTABLE(napi_hash, 8); -seqcount_t devnet_rename_seq; +static seqcount_t devnet_rename_seq; static inline void dev_base_seq_inc(struct net *net) { @@ -4989,6 +4989,24 @@ int dev_change_carrier(struct net_device *dev, bool new_carrier) EXPORT_SYMBOL(dev_change_carrier); /** + * dev_get_phys_port_id - Get device physical port ID + * @dev: device + * @ppid: port ID + * + * Get device physical port ID + */ +int dev_get_phys_port_id(struct net_device *dev, + struct netdev_phys_port_id *ppid) +{ + const struct net_device_ops *ops = dev->netdev_ops; + + if (!ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + return ops->ndo_get_phys_port_id(dev, ppid); +} +EXPORT_SYMBOL(dev_get_phys_port_id); + +/** * dev_new_index - allocate an ifindex * @net: the applicable net namespace * diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 21735440c44a..2e654138433c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -33,6 +33,9 @@ int fib_default_rule_add(struct fib_rules_ops *ops, r->flags = flags; r->fr_net = hold_net(ops->fro_net); + r->suppress_prefixlen = -1; + r->suppress_ifgroup = -1; + /* The lock is not required here, the list in unreacheable * at the moment this function is called */ list_add_tail(&r->list, &ops->rules_list); @@ -226,6 +229,9 @@ jumped: else err = ops->action(rule, fl, flags, arg); + if (!err && ops->suppress && ops->suppress(rule, arg)) + continue; + if (err != -EAGAIN) { if ((arg->flags & FIB_LOOKUP_NOREF) || likely(atomic_inc_not_zero(&rule->refcnt))) { @@ -337,6 +343,15 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh) rule->action = frh->action; rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); + if (tb[FRA_SUPPRESS_PREFIXLEN]) + rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + else + rule->suppress_prefixlen = -1; + + if (tb[FRA_SUPPRESS_IFGROUP]) + rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + else + rule->suppress_ifgroup = -1; if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); @@ -523,6 +538,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */ + + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */ + nla_total_size(4) /* FRA_FWMARK */ + nla_total_size(4); /* FRA_FWMASK */ @@ -548,6 +565,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->table = rule->table; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; + if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) + goto nla_put_failure; frh->res1 = 0; frh->res2 = 0; frh->action = rule->action; @@ -580,6 +599,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, (rule->target && nla_put_u32(skb, FRA_GOTO, rule->target))) goto nla_put_failure; + + if (rule->suppress_ifgroup != -1) { + if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup)) + goto nla_put_failure; + } + if (ops->fill(rule, skb, frh) < 0) goto nla_put_failure; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 00ee068efc1c..ade9ff1c1980 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -139,7 +139,11 @@ ipv6: break; } case IPPROTO_IPIP: - goto again; + proto = htons(ETH_P_IP); + goto ip; + case IPPROTO_IPV6: + proto = htons(ETH_P_IPV6); + goto ipv6; default: break; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9232c68941ab..60533db8b72d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1441,16 +1441,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 981fed397d1d..8826b0d1e0cc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -334,6 +334,27 @@ static ssize_t store_group(struct device *dev, struct device_attribute *attr, return netdev_store(dev, attr, buf, len, change_group); } +static ssize_t show_phys_port_id(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + ssize_t ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (dev_isalive(netdev)) { + struct netdev_phys_port_id ppid; + + ret = dev_get_phys_port_id(netdev, &ppid); + if (!ret) + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); + } + rtnl_unlock(); + + return ret; +} + static struct device_attribute net_class_attributes[] = { __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), @@ -355,6 +376,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len), __ATTR(netdev_group, S_IRUGO | S_IWUSR, show_group, store_group), + __ATTR(phys_port_id, S_IRUGO, show_phys_port_id, NULL), {} }; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 9640972ec50e..261357a66300 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -160,6 +160,8 @@ #include <net/net_namespace.h> #include <net/checksum.h> #include <net/ipv6.h> +#include <net/udp.h> +#include <net/ip6_checksum.h> #include <net/addrconf.h> #ifdef CONFIG_XFRM #include <net/xfrm.h> @@ -198,6 +200,7 @@ #define F_QUEUE_MAP_RND (1<<13) /* queue map Random */ #define F_QUEUE_MAP_CPU (1<<14) /* queue map mirrors smp_processor_id() */ #define F_NODE (1<<15) /* Node memory alloc*/ +#define F_UDPCSUM (1<<16) /* Include UDP checksum */ /* Thread control flag bits */ #define T_STOP (1<<0) /* Stop run */ @@ -631,6 +634,9 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_UDPDST_RND) seq_printf(seq, "UDPDST_RND "); + if (pkt_dev->flags & F_UDPCSUM) + seq_printf(seq, "UDPCSUM "); + if (pkt_dev->flags & F_MPLS_RND) seq_printf(seq, "MPLS_RND "); @@ -1228,6 +1234,12 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!NODE_ALLOC") == 0) pkt_dev->flags &= ~F_NODE; + else if (strcmp(f, "UDPCSUM") == 0) + pkt_dev->flags |= F_UDPCSUM; + + else if (strcmp(f, "!UDPCSUM") == 0) + pkt_dev->flags &= ~F_UDPCSUM; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", @@ -2733,7 +2745,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); udph->len = htons(datalen + 8); /* DATA + udphdr */ - udph->check = 0; /* No checksum */ + udph->check = 0; iph->ihl = 5; iph->version = 4; @@ -2747,11 +2759,28 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->frag_off = 0; iplen = 20 + 8 + datalen; iph->tot_len = htons(iplen); - iph->check = 0; - iph->check = ip_fast_csum((void *)iph, iph->ihl); + ip_send_check(iph); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; + + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum = 0; + udp4_hwcsum(skb, udph->source, udph->dest); + } else { + __wsum csum = udp_csum(skb); + + /* add protocol-dependent pseudo-header */ + udph->check = csum_tcpudp_magic(udph->source, udph->dest, + datalen + 8, IPPROTO_UDP, csum); + + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + } + pktgen_finalize_skb(pkt_dev, skb, datalen); #ifdef CONFIG_XFRM @@ -2768,7 +2797,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct sk_buff *skb = NULL; __u8 *eth; struct udphdr *udph; - int datalen; + int datalen, udplen; struct ipv6hdr *iph; __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; @@ -2844,10 +2873,11 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, net_info_ratelimited("increased datalen to %d\n", datalen); } + udplen = datalen + sizeof(struct udphdr); udph->source = htons(pkt_dev->cur_udp_src); udph->dest = htons(pkt_dev->cur_udp_dst); - udph->len = htons(datalen + sizeof(struct udphdr)); - udph->check = 0; /* No checksum */ + udph->len = htons(udplen); + udph->check = 0; *(__be32 *) iph = htonl(0x60000000); /* Version + flow */ @@ -2858,7 +2888,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, iph->hop_limit = 32; - iph->payload_len = htons(sizeof(struct udphdr) + datalen); + iph->payload_len = htons(udplen); iph->nexthdr = IPPROTO_UDP; iph->daddr = pkt_dev->cur_in6_daddr; @@ -2868,6 +2898,23 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; + if (!(pkt_dev->flags & F_UDPCSUM)) { + skb->ip_summed = CHECKSUM_NONE; + } else if (odev->features & NETIF_F_V6_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + udph->check = ~csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, 0); + } else { + __wsum csum = udp_csum(skb); + + /* add protocol-dependent pseudo-header */ + udph->check = csum_ipv6_magic(&iph->saddr, &iph->daddr, udplen, IPPROTO_UDP, csum); + + if (udph->check == 0) + udph->check = CSUM_MANGLED_0; + } + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3de740834d1f..0b2972c59b97 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -767,7 +767,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ - + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ + + rtnl_link_get_af_size(dev) /* IFLA_AF_SPEC */ + + nla_total_size(MAX_PHYS_PORT_ID_LEN); /* IFLA_PHYS_PORT_ID */ } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -846,6 +847,24 @@ static int rtnl_port_fill(struct sk_buff *skb, struct net_device *dev) return 0; } +static int rtnl_phys_port_id_fill(struct sk_buff *skb, struct net_device *dev) +{ + int err; + struct netdev_phys_port_id ppid; + + err = dev_get_phys_port_id(dev, &ppid); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + if (nla_put(skb, IFLA_PHYS_PORT_ID, ppid.id_len, ppid.id)) + return -EMSGSIZE; + + return 0; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask) @@ -913,6 +932,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } + if (rtnl_phys_port_id_fill(skb, dev)) + goto nla_put_failure; + attr = nla_reserve(skb, IFLA_STATS, sizeof(struct rtnl_link_stats)); if (attr == NULL) @@ -1113,6 +1135,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_PROMISCUITY] = { .type = NLA_U32 }, [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, + [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_PORT_ID_LEN }, }; EXPORT_SYMBOL(ifla_policy); diff --git a/net/core/sock.c b/net/core/sock.c index 2c097c5a35dd..83667de45ec9 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -93,6 +93,7 @@ #include <linux/capability.h> #include <linux/errno.h> +#include <linux/errqueue.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/in.h> @@ -1575,6 +1576,25 @@ void sock_wfree(struct sk_buff *skb) } EXPORT_SYMBOL(sock_wfree); +void skb_orphan_partial(struct sk_buff *skb) +{ + /* TCP stack sets skb->ooo_okay based on sk_wmem_alloc, + * so we do not completely orphan skb, but transfert all + * accounted bytes but one, to avoid unexpected reorders. + */ + if (skb->destructor == sock_wfree +#ifdef CONFIG_INET + || skb->destructor == tcp_wfree +#endif + ) { + atomic_sub(skb->truesize - 1, &skb->sk->sk_wmem_alloc); + skb->truesize = 1; + } else { + skb_orphan(skb); + } +} +EXPORT_SYMBOL(skb_orphan_partial); + /* * Read buffer destructor automatically called from kfree_skb. */ @@ -2425,6 +2445,52 @@ void sock_enable_timestamp(struct sock *sk, int flag) } } +int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, + int level, int type) +{ + struct sock_exterr_skb *serr; + struct sk_buff *skb, *skb2; + int copied, err; + + err = -EAGAIN; + skb = skb_dequeue(&sk->sk_error_queue); + if (skb == NULL) + goto out; + + copied = skb->len; + if (copied > len) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + if (err) + goto out_free_skb; + + sock_recv_timestamp(msg, sk, skb); + + serr = SKB_EXT_ERR(skb); + put_cmsg(msg, level, type, sizeof(serr->ee), &serr->ee); + + msg->msg_flags |= MSG_ERRQUEUE; + err = copied; + + /* Reset and regenerate socket error */ + spin_lock_bh(&sk->sk_error_queue.lock); + sk->sk_err = 0; + if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { + sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; + spin_unlock_bh(&sk->sk_error_queue.lock); + sk->sk_error_report(sk); + } else + spin_unlock_bh(&sk->sk_error_queue.lock); + +out_free_skb: + kfree_skb(skb); +out: + return err; +} +EXPORT_SYMBOL(sock_recv_errqueue); + /* * Get a socket option on an socket. * diff --git a/net/core/stream.c b/net/core/stream.c index f5df85dcd20b..512f0a24269b 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -30,7 +30,7 @@ void sk_stream_write_space(struct sock *sk) struct socket *sock = sk->sk_socket; struct socket_wq *wq; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) { + if (sk_stream_is_writeable(sk) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 6c7c78b83940..ba64750f0387 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -336,7 +336,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -347,7 +347,7 @@ unsigned int dccp_poll(struct file *file, struct socket *sock, * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 34ca6d5a3a4b..43923dc77440 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1126,10 +1126,7 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len) if (len < (int) sizeof(ifr)) break; memset(&ifr, 0, sizeof(struct ifreq)); - if (ifa->ifa_label) - strcpy(ifr.ifr_name, ifa->ifa_label); - else - strcpy(ifr.ifr_name, dev->name); + strcpy(ifr.ifr_name, ifa->ifa_label); (*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET; (*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr = diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 26aa65d1fce4..523be38e37de 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -101,6 +101,30 @@ errout: return err; } +static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +{ + struct fib_result *result = (struct fib_result *) arg->result; + struct net_device *dev = result->fi->fib_dev; + + /* do not accept result if the route does + * not meet the required prefix length + */ + if (result->prefixlen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + if (!(arg->flags & FIB_LOOKUP_NOREF)) + fib_info_put(result->fi); + return true; +} static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { @@ -267,6 +291,7 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = { .rule_size = sizeof(struct fib4_rule), .addr_size = sizeof(u32), .action = fib4_rule_action, + .suppress = fib4_rule_suppress, .match = fib4_rule_match, .configure = fib4_rule_configure, .delete = fib4_rule_delete, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cd71190d2962..ef7618630f36 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -88,6 +88,7 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> +#include <linux/pkt_sched.h> #include <net/net_namespace.h> #include <net/arp.h> @@ -315,6 +316,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) if (size < 256) return NULL; } + skb->priority = TC_PRIO_CONTROL; igmp_skb_size(skb) = size; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, @@ -670,6 +672,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ip_rt_put(rt); return -1; } + skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); @@ -1323,16 +1326,17 @@ out: EXPORT_SYMBOL(ip_mc_inc_group); /* - * Resend IGMP JOIN report; used for bonding. - * Called with rcu_read_lock() + * Resend IGMP JOIN report; used by netdev notifier. */ -void ip_mc_rejoin_groups(struct in_device *in_dev) +static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; - for_each_pmc_rcu(in_dev, im) { + ASSERT_RTNL(); + + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; @@ -1349,7 +1353,6 @@ void ip_mc_rejoin_groups(struct in_device *in_dev) } #endif } -EXPORT_SYMBOL(ip_mc_rejoin_groups); /* * A socket has left a multicast group on device dev @@ -2735,8 +2738,42 @@ static struct pernet_operations igmp_net_ops = { .exit = igmp_net_exit, }; +static int igmp_netdev_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct in_device *in_dev; + + switch (event) { + case NETDEV_RESEND_IGMP: + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) + ip_mc_rejoin_groups(in_dev); + break; + default: + break; + } + return NOTIFY_DONE; +} + +static struct notifier_block igmp_notifier = { + .notifier_call = igmp_netdev_event, +}; + int __init igmp_mc_proc_init(void) { - return register_pernet_subsys(&igmp_net_ops); + int err; + + err = register_pernet_subsys(&igmp_net_ops); + if (err) + return err; + err = register_netdevice_notifier(&igmp_notifier); + if (err) + goto reg_notif_fail; + return 0; + +reg_notif_fail: + unregister_pernet_subsys(&igmp_net_ops); + return err; } #endif diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index 17cc0ffa8c0d..79b263da4168 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -44,176 +44,10 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> -#define HASH_SIZE 16 -#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&(HASH_SIZE-1)) - static struct rtnl_link_ops vti_link_ops __read_mostly; static int vti_net_id __read_mostly; -struct vti_net { - struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; - struct ip_tunnel __rcu *tunnels_wc[1]; - struct ip_tunnel __rcu **tunnels[4]; - - struct net_device *fb_tunnel_dev; -}; - -static int vti_fb_tunnel_init(struct net_device *dev); static int vti_tunnel_init(struct net_device *dev); -static void vti_tunnel_setup(struct net_device *dev); -static void vti_dev_free(struct net_device *dev); -static int vti_tunnel_bind_dev(struct net_device *dev); - -#define VTI_XMIT(stats1, stats2) do { \ - int err; \ - int pkt_len = skb->len; \ - err = dst_output(skb); \ - if (net_xmit_eval(err) == 0) { \ - u64_stats_update_begin(&(stats1)->syncp); \ - (stats1)->tx_bytes += pkt_len; \ - (stats1)->tx_packets++; \ - u64_stats_update_end(&(stats1)->syncp); \ - } else { \ - (stats2)->tx_errors++; \ - (stats2)->tx_aborted_errors++; \ - } \ -} while (0) - - -static struct ip_tunnel *vti_tunnel_lookup(struct net *net, - __be32 remote, __be32 local) -{ - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); - struct ip_tunnel *t; - struct vti_net *ipn = net_generic(net, vti_net_id); - - for_each_ip_tunnel_rcu(t, ipn->tunnels_r_l[h0 ^ h1]) - if (local == t->parms.iph.saddr && - remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) - return t; - for_each_ip_tunnel_rcu(t, ipn->tunnels_r[h0]) - if (remote == t->parms.iph.daddr && (t->dev->flags&IFF_UP)) - return t; - - for_each_ip_tunnel_rcu(t, ipn->tunnels_l[h1]) - if (local == t->parms.iph.saddr && (t->dev->flags&IFF_UP)) - return t; - - for_each_ip_tunnel_rcu(t, ipn->tunnels_wc[0]) - if (t && (t->dev->flags&IFF_UP)) - return t; - return NULL; -} - -static struct ip_tunnel __rcu **__vti_bucket(struct vti_net *ipn, - struct ip_tunnel_parm *parms) -{ - __be32 remote = parms->iph.daddr; - __be32 local = parms->iph.saddr; - unsigned h = 0; - int prio = 0; - - if (remote) { - prio |= 2; - h ^= HASH(remote); - } - if (local) { - prio |= 1; - h ^= HASH(local); - } - return &ipn->tunnels[prio][h]; -} - -static inline struct ip_tunnel __rcu **vti_bucket(struct vti_net *ipn, - struct ip_tunnel *t) -{ - return __vti_bucket(ipn, &t->parms); -} - -static void vti_tunnel_unlink(struct vti_net *ipn, struct ip_tunnel *t) -{ - struct ip_tunnel __rcu **tp; - struct ip_tunnel *iter; - - for (tp = vti_bucket(ipn, t); - (iter = rtnl_dereference(*tp)) != NULL; - tp = &iter->next) { - if (t == iter) { - rcu_assign_pointer(*tp, t->next); - break; - } - } -} - -static void vti_tunnel_link(struct vti_net *ipn, struct ip_tunnel *t) -{ - struct ip_tunnel __rcu **tp = vti_bucket(ipn, t); - - rcu_assign_pointer(t->next, rtnl_dereference(*tp)); - rcu_assign_pointer(*tp, t); -} - -static struct ip_tunnel *vti_tunnel_locate(struct net *net, - struct ip_tunnel_parm *parms, - int create) -{ - __be32 remote = parms->iph.daddr; - __be32 local = parms->iph.saddr; - struct ip_tunnel *t, *nt; - struct ip_tunnel __rcu **tp; - struct net_device *dev; - char name[IFNAMSIZ]; - struct vti_net *ipn = net_generic(net, vti_net_id); - - for (tp = __vti_bucket(ipn, parms); - (t = rtnl_dereference(*tp)) != NULL; - tp = &t->next) { - if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) - return t; - } - if (!create) - return NULL; - - if (parms->name[0]) - strlcpy(name, parms->name, IFNAMSIZ); - else - strcpy(name, "vti%d"); - - dev = alloc_netdev(sizeof(*t), name, vti_tunnel_setup); - if (dev == NULL) - return NULL; - - dev_net_set(dev, net); - - nt = netdev_priv(dev); - nt->parms = *parms; - dev->rtnl_link_ops = &vti_link_ops; - - vti_tunnel_bind_dev(dev); - - if (register_netdevice(dev) < 0) - goto failed_free; - - dev_hold(dev); - vti_tunnel_link(ipn, nt); - return nt; - -failed_free: - free_netdev(dev); - return NULL; -} - -static void vti_tunnel_uninit(struct net_device *dev) -{ - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - - vti_tunnel_unlink(ipn, netdev_priv(dev)); - dev_put(dev); -} static int vti_err(struct sk_buff *skb, u32 info) { @@ -222,6 +56,8 @@ static int vti_err(struct sk_buff *skb, u32 info) * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. */ + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; @@ -252,7 +88,8 @@ static int vti_err(struct sk_buff *skb, u32 info) err = -ENOENT; - t = vti_tunnel_lookup(dev_net(skb->dev), iph->daddr, iph->saddr); + t = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->daddr, iph->saddr, 0); if (t == NULL) goto out; @@ -281,8 +118,11 @@ static int vti_rcv(struct sk_buff *skb) { struct ip_tunnel *tunnel; const struct iphdr *iph = ip_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); - tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); if (tunnel != NULL) { struct pcpu_tstats *tstats; @@ -311,7 +151,6 @@ static int vti_rcv(struct sk_buff *skb) static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; u8 tos; struct rtable *rt; /* Route to the other host */ @@ -319,6 +158,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct iphdr *old_iph = ip_hdr(skb); __be32 dst = tiph->daddr; struct flowi4 fl4; + int err; if (skb->protocol != htons(ETH_P_IP)) goto tx_error; @@ -367,8 +207,10 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) nf_reset(skb); skb->dev = skb_dst(skb)->dev; - tstats = this_cpu_ptr(dev->tstats); - VTI_XMIT(tstats, &dev->stats); + err = dst_output(skb); + if (net_xmit_eval(err) == 0) + err = skb->len; + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); return NETDEV_TX_OK; tx_error_icmp: @@ -379,198 +221,57 @@ tx_error: return NETDEV_TX_OK; } -static int vti_tunnel_bind_dev(struct net_device *dev) -{ - struct net_device *tdev = NULL; - struct ip_tunnel *tunnel; - struct iphdr *iph; - - tunnel = netdev_priv(dev); - iph = &tunnel->parms.iph; - - if (iph->daddr) { - struct rtable *rt; - struct flowi4 fl4; - memset(&fl4, 0, sizeof(fl4)); - flowi4_init_output(&fl4, tunnel->parms.link, - be32_to_cpu(tunnel->parms.i_key), - RT_TOS(iph->tos), RT_SCOPE_UNIVERSE, - IPPROTO_IPIP, 0, - iph->daddr, iph->saddr, 0, 0); - rt = ip_route_output_key(dev_net(dev), &fl4); - if (!IS_ERR(rt)) { - tdev = rt->dst.dev; - ip_rt_put(rt); - } - dev->flags |= IFF_POINTOPOINT; - } - - if (!tdev && tunnel->parms.link) - tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link); - - if (tdev) { - dev->hard_header_len = tdev->hard_header_len + - sizeof(struct iphdr); - dev->mtu = tdev->mtu; - } - dev->iflink = tunnel->parms.link; - return dev->mtu; -} - static int vti_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip_tunnel_parm p; - struct ip_tunnel *t; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - - switch (cmd) { - case SIOCGETTUNNEL: - t = NULL; - if (dev == ipn->fb_tunnel_dev) { - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, - sizeof(p))) { - err = -EFAULT; - break; - } - t = vti_tunnel_locate(net, &p, 0); - } - if (t == NULL) - t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof(p)); - p.i_flags |= GRE_KEY | VTI_ISVTI; - p.o_flags |= GRE_KEY; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; - break; - - case SIOCADDTUNNEL: - case SIOCCHGTUNNEL: - err = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - goto done; - err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) - goto done; + if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) + return -EFAULT; - err = -EINVAL; + if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPIP || p.iph.ihl != 5) - goto done; - - t = vti_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL); - - if (dev != ipn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) { - if (t != NULL) { - if (t->dev != dev) { - err = -EEXIST; - break; - } - } else { - if (((dev->flags&IFF_POINTOPOINT) && - !p.iph.daddr) || - (!(dev->flags&IFF_POINTOPOINT) && - p.iph.daddr)) { - err = -EINVAL; - break; - } - t = netdev_priv(dev); - vti_tunnel_unlink(ipn, t); - synchronize_net(); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - t->parms.iph.protocol = IPPROTO_IPIP; - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - vti_tunnel_link(ipn, t); - netdev_state_change(dev); - } - } - - if (t) { - err = 0; - if (cmd == SIOCCHGTUNNEL) { - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - if (t->parms.link != p.link) { - t->parms.link = p.link; - vti_tunnel_bind_dev(dev); - netdev_state_change(dev); - } - } - p.i_flags |= GRE_KEY | VTI_ISVTI; - p.o_flags |= GRE_KEY; - if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, - sizeof(p))) - err = -EFAULT; - } else - err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); - break; + return -EINVAL; + } - case SIOCDELTUNNEL: - err = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - goto done; - - if (dev == ipn->fb_tunnel_dev) { - err = -EFAULT; - if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, - sizeof(p))) - goto done; - err = -ENOENT; - - t = vti_tunnel_locate(net, &p, 0); - if (t == NULL) - goto done; - err = -EPERM; - if (t->dev == ipn->fb_tunnel_dev) - goto done; - dev = t->dev; - } - unregister_netdevice(dev); - err = 0; - break; + err = ip_tunnel_ioctl(dev, &p, cmd); + if (err) + return err; - default: - err = -EINVAL; + if (cmd != SIOCDELTUNNEL) { + p.i_flags |= GRE_KEY | VTI_ISVTI; + p.o_flags |= GRE_KEY; } -done: - return err; -} - -static int vti_tunnel_change_mtu(struct net_device *dev, int new_mtu) -{ - if (new_mtu < 68 || new_mtu > 0xFFF8) - return -EINVAL; - dev->mtu = new_mtu; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) + return -EFAULT; return 0; } static const struct net_device_ops vti_netdev_ops = { .ndo_init = vti_tunnel_init, - .ndo_uninit = vti_tunnel_uninit, + .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = vti_tunnel_xmit, .ndo_do_ioctl = vti_tunnel_ioctl, - .ndo_change_mtu = vti_tunnel_change_mtu, + .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, }; -static void vti_dev_free(struct net_device *dev) +static void vti_tunnel_setup(struct net_device *dev) { - free_percpu(dev->tstats); - free_netdev(dev); + dev->netdev_ops = &vti_netdev_ops; + ip_tunnel_setup(dev, vti_net_id); } -static void vti_tunnel_setup(struct net_device *dev) +static int vti_tunnel_init(struct net_device *dev) { - dev->netdev_ops = &vti_netdev_ops; - dev->destructor = vti_dev_free; + struct ip_tunnel *tunnel = netdev_priv(dev); + struct iphdr *iph = &tunnel->parms.iph; + + memcpy(dev->dev_addr, &iph->saddr, 4); + memcpy(dev->broadcast, &iph->daddr, 4); dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -581,38 +282,18 @@ static void vti_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; -} -static int vti_tunnel_init(struct net_device *dev) -{ - struct ip_tunnel *tunnel = netdev_priv(dev); - - tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); - - memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); - memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); - - dev->tstats = alloc_percpu(struct pcpu_tstats); - if (!dev->tstats) - return -ENOMEM; - - return 0; + return ip_tunnel_init(dev); } -static int __net_init vti_fb_tunnel_init(struct net_device *dev) +static void __net_init vti_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; - struct vti_net *ipn = net_generic(dev_net(dev), vti_net_id); iph->version = 4; iph->protocol = IPPROTO_IPIP; iph->ihl = 5; - - dev_hold(dev); - rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); - return 0; } static struct xfrm_tunnel vti_handler __read_mostly = { @@ -621,76 +302,30 @@ static struct xfrm_tunnel vti_handler __read_mostly = { .priority = 1, }; -static void vti_destroy_tunnels(struct vti_net *ipn, struct list_head *head) -{ - int prio; - - for (prio = 1; prio < 4; prio++) { - int h; - for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - - t = rtnl_dereference(ipn->tunnels[prio][h]); - while (t != NULL) { - unregister_netdevice_queue(t->dev, head); - t = rtnl_dereference(t->next); - } - } - } -} - static int __net_init vti_init_net(struct net *net) { int err; - struct vti_net *ipn = net_generic(net, vti_net_id); - - ipn->tunnels[0] = ipn->tunnels_wc; - ipn->tunnels[1] = ipn->tunnels_l; - ipn->tunnels[2] = ipn->tunnels_r; - ipn->tunnels[3] = ipn->tunnels_r_l; - - ipn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), - "ip_vti0", - vti_tunnel_setup); - if (!ipn->fb_tunnel_dev) { - err = -ENOMEM; - goto err_alloc_dev; - } - dev_net_set(ipn->fb_tunnel_dev, net); - - err = vti_fb_tunnel_init(ipn->fb_tunnel_dev); - if (err) - goto err_reg_dev; - ipn->fb_tunnel_dev->rtnl_link_ops = &vti_link_ops; + struct ip_tunnel_net *itn; - err = register_netdev(ipn->fb_tunnel_dev); + err = ip_tunnel_init_net(net, vti_net_id, &vti_link_ops, "ip_vti0"); if (err) - goto err_reg_dev; + return err; + itn = net_generic(net, vti_net_id); + vti_fb_tunnel_init(itn->fb_tunnel_dev); return 0; - -err_reg_dev: - vti_dev_free(ipn->fb_tunnel_dev); -err_alloc_dev: - /* nothing */ - return err; } static void __net_exit vti_exit_net(struct net *net) { - struct vti_net *ipn = net_generic(net, vti_net_id); - LIST_HEAD(list); - - rtnl_lock(); - vti_destroy_tunnels(ipn, &list); - unregister_netdevice_many(&list); - rtnl_unlock(); + struct ip_tunnel_net *itn = net_generic(net, vti_net_id); + ip_tunnel_delete_net(itn); } static struct pernet_operations vti_net_ops = { .init = vti_init_net, .exit = vti_exit_net, .id = &vti_net_id, - .size = sizeof(struct vti_net), + .size = sizeof(struct ip_tunnel_net), }; static int vti_tunnel_validate(struct nlattr *tb[], struct nlattr *data[]) @@ -728,78 +363,19 @@ static void vti_netlink_parms(struct nlattr *data[], static int vti_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip_tunnel *nt; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); - int mtu; - int err; - - nt = netdev_priv(dev); - vti_netlink_parms(data, &nt->parms); - - if (vti_tunnel_locate(net, &nt->parms, 0)) - return -EEXIST; + struct ip_tunnel_parm parms; - mtu = vti_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) - dev->mtu = mtu; - - err = register_netdevice(dev); - if (err) - goto out; - - dev_hold(dev); - vti_tunnel_link(ipn, nt); - -out: - return err; + vti_netlink_parms(data, &parms); + return ip_tunnel_newlink(dev, tb, &parms); } static int vti_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[]) { - struct ip_tunnel *t, *nt; - struct net *net = dev_net(dev); - struct vti_net *ipn = net_generic(net, vti_net_id); struct ip_tunnel_parm p; - int mtu; - - if (dev == ipn->fb_tunnel_dev) - return -EINVAL; - nt = netdev_priv(dev); vti_netlink_parms(data, &p); - - t = vti_tunnel_locate(net, &p, 0); - - if (t) { - if (t->dev != dev) - return -EEXIST; - } else { - t = nt; - - vti_tunnel_unlink(ipn, t); - t->parms.iph.saddr = p.iph.saddr; - t->parms.iph.daddr = p.iph.daddr; - t->parms.i_key = p.i_key; - t->parms.o_key = p.o_key; - if (dev->type != ARPHRD_ETHER) { - memcpy(dev->dev_addr, &p.iph.saddr, 4); - memcpy(dev->broadcast, &p.iph.daddr, 4); - } - vti_tunnel_link(ipn, t); - netdev_state_change(dev); - } - - if (t->parms.link != p.link) { - t->parms.link = p.link; - mtu = vti_tunnel_bind_dev(dev); - if (!tb[IFLA_MTU]) - dev->mtu = mtu; - netdev_state_change(dev); - } - - return 0; + return ip_tunnel_changelink(dev, tb, &p); } static size_t vti_get_size(const struct net_device *dev) @@ -865,7 +441,7 @@ static int __init vti_init(void) err = xfrm4_mode_tunnel_input_register(&vti_handler); if (err < 0) { unregister_pernet_device(&vti_net_ops); - pr_info(KERN_INFO "vti init: can't register tunnel\n"); + pr_info("vti init: can't register tunnel\n"); } err = rtnl_link_register(&vti_link_ops); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 132a09664704..bacc0bcf48ce 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -127,9 +127,9 @@ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr_table *ipmr_new_table(struct net *net, u32 id); static void ipmr_free_table(struct mr_table *mrt); -static int ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local); +static void ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local); static int ipmr_cache_report(struct mr_table *mrt, struct sk_buff *pkt, vifi_t vifi, int assert); static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb, @@ -1795,9 +1795,9 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev) /* "local" means that we should preserve one skb (for local delivery) */ -static int ip_mr_forward(struct net *net, struct mr_table *mrt, - struct sk_buff *skb, struct mfc_cache *cache, - int local) +static void ip_mr_forward(struct net *net, struct mr_table *mrt, + struct sk_buff *skb, struct mfc_cache *cache, + int local) { int psend = -1; int vif, ct; @@ -1903,14 +1903,13 @@ last_forward: ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { ipmr_queue_xmit(net, mrt, skb, cache, psend); - return 0; + return; } } dont_forward: if (!local) kfree_skb(skb); - return 0; } static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb) diff --git a/net/ipv4/route.c b/net/ipv4/route.c index a9a54a236832..e805481eff72 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -435,12 +435,12 @@ static inline int ip_rt_proc_init(void) static inline bool rt_is_expired(const struct rtable *rth) { - return rth->rt_genid != rt_genid(dev_net(rth->dst.dev)); + return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev)); } void rt_cache_flush(struct net *net) { - rt_genid_bump(net); + rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, @@ -1458,7 +1458,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, #endif rth->dst.output = ip_rt_bug; - rth->rt_genid = rt_genid(dev_net(dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev)); rth->rt_flags = RTCF_MULTICAST; rth->rt_type = RTN_MULTICAST; rth->rt_is_input= 1; @@ -1589,7 +1589,7 @@ static int __mkroute_input(struct sk_buff *skb, goto cleanup; } - rth->rt_genid = rt_genid(dev_net(rth->dst.dev)); + rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); rth->rt_flags = flags; rth->rt_type = res->type; rth->rt_is_input = 1; @@ -1760,7 +1760,7 @@ local_input: rth->dst.tclassid = itag; #endif - rth->rt_genid = rt_genid(net); + rth->rt_genid = rt_genid_ipv4(net); rth->rt_flags = flags|RTCF_LOCAL; rth->rt_type = res.type; rth->rt_is_input = 1; @@ -1945,7 +1945,7 @@ add: rth->dst.output = ip_output; - rth->rt_genid = rt_genid(dev_net(dev_out)); + rth->rt_genid = rt_genid_ipv4(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; rth->rt_is_input = 0; @@ -2227,7 +2227,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; - rt->rt_genid = rt_genid(net); + rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_gateway = ort->rt_gateway; @@ -2665,7 +2665,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = { static __net_init int rt_genid_init(struct net *net) { - atomic_set(&net->rt_genid, 0); + atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); get_random_bytes(&net->ipv4.dev_addr_genid, sizeof(net->ipv4.dev_addr_genid)); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 610e324348d1..8ed7c32ae28e 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -559,6 +559,13 @@ static struct ctl_table ipv4_table[] = { .extra1 = &one, }, { + .procname = "tcp_notsent_lowat", + .data = &sysctl_tcp_notsent_lowat, + .maxlen = sizeof(sysctl_tcp_notsent_lowat), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "tcp_rmem", .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5423223e93c2..ab64eea042fa 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -410,10 +410,6 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - /* Presumed zeroed, in order of appearance: - * cookie_in_always, cookie_out_never, - * s_data_constant, s_data_in, s_data_out - */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -499,7 +495,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= POLLIN | POLLRDNORM; if (!(sk->sk_shutdown & SEND_SHUTDOWN)) { - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) { + if (sk_stream_is_writeable(sk)) { mask |= POLLOUT | POLLWRNORM; } else { /* send SIGIO later */ set_bit(SOCK_ASYNC_NOSPACE, @@ -510,7 +506,7 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) * wspace test but before the flags are set, * IO signal will be lost. */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) mask |= POLLOUT | POLLWRNORM; } } else @@ -2631,6 +2627,10 @@ static int do_tcp_setsockopt(struct sock *sk, int level, else tp->tsoffset = val - tcp_time_stamp; break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: err = -ENOPROTOOPT; break; @@ -2847,6 +2847,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_TIMESTAMP: val = tcp_time_stamp + tp->tsoffset; break; + case TCP_NOTSENT_LOWAT: + val = tp->notsent_lowat; + break; default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 28af45abe062..b61274b666f6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1048,6 +1048,7 @@ struct tcp_sacktag_state { int reord; int fack_count; int flag; + s32 rtt; /* RTT measured by SACKing never-retransmitted data */ }; /* Check if skb is fully within the SACK block. In presence of GSO skbs, @@ -1108,7 +1109,7 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, static u8 tcp_sacktag_one(struct sock *sk, struct tcp_sacktag_state *state, u8 sacked, u32 start_seq, u32 end_seq, - bool dup_sack, int pcount) + int dup_sack, int pcount, u32 xmit_time) { struct tcp_sock *tp = tcp_sk(sk); int fack_count = state->fack_count; @@ -1148,6 +1149,9 @@ static u8 tcp_sacktag_one(struct sock *sk, state->reord); if (!after(end_seq, tp->high_seq)) state->flag |= FLAG_ORIG_SACK_ACKED; + /* Pick the earliest sequence sacked for RTT */ + if (state->rtt < 0) + state->rtt = tcp_time_stamp - xmit_time; } if (sacked & TCPCB_LOST) { @@ -1205,7 +1209,8 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, * tcp_highest_sack_seq() when skb is highest_sack. */ tcp_sacktag_one(sk, state, TCP_SKB_CB(skb)->sacked, - start_seq, end_seq, dup_sack, pcount); + start_seq, end_seq, dup_sack, pcount, + TCP_SKB_CB(skb)->when); if (skb == tp->lost_skb_hint) tp->lost_cnt_hint += pcount; @@ -1479,7 +1484,8 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq, dup_sack, - tcp_skb_pcount(skb)); + tcp_skb_pcount(skb), + TCP_SKB_CB(skb)->when); if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) @@ -1536,7 +1542,7 @@ static int tcp_sack_cache_ok(const struct tcp_sock *tp, const struct tcp_sack_bl static int tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, - u32 prior_snd_una) + u32 prior_snd_una, s32 *sack_rtt) { struct tcp_sock *tp = tcp_sk(sk); const unsigned char *ptr = (skb_transport_header(ack_skb) + @@ -1554,6 +1560,7 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, state.flag = 0; state.reord = tp->packets_out; + state.rtt = -1; if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) @@ -1737,6 +1744,7 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif + *sack_rtt = state.rtt; return state.flag; } @@ -2792,65 +2800,51 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, tcp_xmit_retransmit_queue(sk); } -void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) +static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, + s32 seq_rtt, s32 sack_rtt) { - tcp_rtt_estimator(sk, seq_rtt); - tcp_set_rto(sk); - inet_csk(sk)->icsk_backoff = 0; -} -EXPORT_SYMBOL(tcp_valid_rtt_meas); + const struct tcp_sock *tp = tcp_sk(sk); + + /* Prefer RTT measured from ACK's timing to TS-ECR. This is because + * broken middle-boxes or peers may corrupt TS-ECR fields. But + * Karn's algorithm forbids taking RTT if some retransmitted data + * is acked (RFC6298). + */ + if (flag & FLAG_RETRANS_DATA_ACKED) + seq_rtt = -1; + + if (seq_rtt < 0) + seq_rtt = sack_rtt; -/* Read draft-ietf-tcplw-high-performance before mucking - * with this code. (Supersedes RFC1323) - */ -static void tcp_ack_saw_tstamp(struct sock *sk, int flag) -{ /* RTTM Rule: A TSecr value received in a segment is used to * update the averaged RTT measurement only if the segment * acknowledges some new data, i.e., only if it advances the * left edge of the send window. - * * See draft-ietf-tcplw-high-performance-00, section 3.3. - * 1998/04/10 Andrey V. Savochkin <saw@msu.ru> - * - * Changed: reset backoff as soon as we see the first valid sample. - * If we do not, we get strongly overestimated rto. With timestamps - * samples are accepted even from very old segments: f.e., when rtt=1 - * increases to 8, we retransmit 5 times and after 8 seconds delayed - * answer arrives rto becomes 120 seconds! If at least one of segments - * in window is lost... Voila. --ANK (010210) */ - struct tcp_sock *tp = tcp_sk(sk); - - tcp_valid_rtt_meas(sk, tcp_time_stamp - tp->rx_opt.rcv_tsecr); -} + if (seq_rtt < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) + seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; -static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag) -{ - /* We don't have a timestamp. Can only use - * packets that are not retransmitted to determine - * rtt estimates. Also, we must not reset the - * backoff for rto until we get a non-retransmitted - * packet. This allows us to deal with a situation - * where the network delay has increased suddenly. - * I.e. Karn's algorithm. (SIGCOMM '87, p5.) - */ + if (seq_rtt < 0) + return false; - if (flag & FLAG_RETRANS_DATA_ACKED) - return; + tcp_rtt_estimator(sk, seq_rtt); + tcp_set_rto(sk); - tcp_valid_rtt_meas(sk, seq_rtt); + /* RFC6298: only reset backoff on valid RTT measurement. */ + inet_csk(sk)->icsk_backoff = 0; + return true; } -static inline void tcp_ack_update_rtt(struct sock *sk, const int flag, - const s32 seq_rtt) +/* Compute time elapsed between (last) SYNACK and the ACK completing 3WHS. */ +static void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) { - const struct tcp_sock *tp = tcp_sk(sk); - /* Note that peer MAY send zero echo. In this case it is ignored. (rfc1323) */ - if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr) - tcp_ack_saw_tstamp(sk, flag); - else if (seq_rtt >= 0) - tcp_ack_no_tstamp(sk, seq_rtt, flag); + struct tcp_sock *tp = tcp_sk(sk); + s32 seq_rtt = -1; + + if (tp->lsndtime && !tp->total_retrans) + seq_rtt = tcp_time_stamp - tp->lsndtime; + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, seq_rtt, -1); } static void tcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) @@ -2939,7 +2933,7 @@ static u32 tcp_tso_acked(struct sock *sk, struct sk_buff *skb) * arrived at the other end. */ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, - u32 prior_snd_una) + u32 prior_snd_una, s32 sack_rtt) { struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); @@ -2978,8 +2972,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (sacked & TCPCB_SACKED_RETRANS) tp->retrans_out -= acked_pcount; flag |= FLAG_RETRANS_DATA_ACKED; - ca_seq_rtt = -1; - seq_rtt = -1; } else { ca_seq_rtt = now - scb->when; last_ackt = skb->tstamp; @@ -3031,6 +3023,10 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, if (skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) flag |= FLAG_SACK_RENEGING; + if (tcp_ack_update_rtt(sk, flag, seq_rtt, sack_rtt) || + (flag & FLAG_ACKED)) + tcp_rearm_rto(sk); + if (flag & FLAG_ACKED) { const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops; @@ -3040,9 +3036,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, tcp_mtup_probe_success(sk); } - tcp_ack_update_rtt(sk, flag, seq_rtt); - tcp_rearm_rto(sk); - if (tcp_is_reno(tp)) { tcp_remove_reno_sacks(sk, pkts_acked); } else { @@ -3274,6 +3267,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) int prior_packets = tp->packets_out; const int prior_unsacked = tp->packets_out - tp->sacked_out; int acked = 0; /* Number of packets newly acked */ + s32 sack_rtt = -1; /* If the ack is older than previous acks * then we can probably ignore it. @@ -3330,7 +3324,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) flag |= tcp_ack_update_window(sk, skb, ack, ack_seq); if (TCP_SKB_CB(skb)->sacked) - flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, + &sack_rtt); if (TCP_ECN_rcv_ecn_echo(tp, tcp_hdr(skb))) flag |= FLAG_ECE; @@ -3349,7 +3344,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ acked = tp->packets_out; - flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una, sack_rtt); acked -= tp->packets_out; if (tcp_ack_is_dubious(sk, flag)) { @@ -3402,7 +3397,8 @@ old_ack: * If data was DSACKed, see if we can undo a cwnd reduction. */ if (TCP_SKB_CB(skb)->sacked) { - flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una, + &sack_rtt); tcp_fastretrans_alert(sk, acked, prior_unsacked, is_dupack, flag); } @@ -5624,9 +5620,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * so release it. */ if (req) { - tcp_synack_rtt_meas(sk, req); tp->total_retrans = req->num_retrans; - reqsk_fastopen_remove(sk, req, false); } else { /* Make sure socket is routed, for correct metrics. */ @@ -5651,6 +5645,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->snd_una = TCP_SKB_CB(skb)->ack_seq; tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); + tcp_synack_rtt_meas(sk, req); if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index b299da5ff499..280efe5f19c1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -890,7 +890,7 @@ bool tcp_syn_flood_action(struct sock *sk, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); lopt = inet_csk(sk)->icsk_accept_queue.listen_opt; - if (!lopt->synflood_warned) { + if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) { lopt->synflood_warned = 1; pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, ntohs(tcp_hdr(skb)->dest), msg); @@ -1462,7 +1462,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * limitations, they conserve resources and peer is * evidently real one. */ - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, "TCP"); if (!want_cookie) goto drop; @@ -1671,8 +1672,6 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -2802,6 +2801,7 @@ struct proto tcp_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index ab1c08658528..58a3e69aef64 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -411,6 +411,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tcp_enable_early_retrans(newtp); newtp->tlp_high_seq = 0; + newtp->lsndtime = treq->snt_synack; + newtp->total_retrans = req->num_retrans; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control @@ -666,12 +668,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; - /* Got ACK for our SYNACK, so update baseline for SYNACK RTT sample. */ - if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) - tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; - else if (req->num_retrans) /* don't take RTT sample if retrans && ~TS */ - tcp_rsk(req)->snt_synack = 0; - /* For Fast Open no more processing is needed (sk is the * child socket). */ diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 92fde8d1aa82..884efff5b531 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -65,6 +65,9 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; +unsigned int sysctl_tcp_notsent_lowat __read_mostly = UINT_MAX; +EXPORT_SYMBOL(sysctl_tcp_notsent_lowat); + static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, int push_one, gfp_t gfp); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 766e6bab9113..9e88af0e8ab0 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -704,7 +704,7 @@ EXPORT_SYMBOL(udp_flush_pending_frames); * @src: source IP address * @dst: destination IP address */ -static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) +void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); struct sk_buff *frags = skb_shinfo(skb)->frag_list; @@ -740,6 +740,7 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) uh->check = CSUM_MANGLED_0; } } +EXPORT_SYMBOL_GPL(udp4_hwcsum); static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) { diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index da4241c8c7da..7fd8572bac80 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4654,6 +4654,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) break; } atomic_inc(&net->ipv6.dev_addr_genid); + rt_genid_bump_ipv6(net); } static void ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index a5ac969aeefe..0d1a9b153fbb 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -766,6 +766,7 @@ static int __net_init inet6_net_init(struct net *net) net->ipv6.sysctl.bindv6only = 0; net->ipv6.sysctl.icmpv6_time = 1*HZ; + atomic_set(&net->ipv6.rt_genid, 0); err = ipv6_init_mibs(net); if (err) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2e1a432867c0..a6c58ce43d34 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -55,26 +55,33 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, struct fib6_table *table; struct net *net = rule->fr_net; pol_lookup_t lookup = arg->lookup_ptr; + int err = 0; switch (rule->action) { case FR_ACT_TO_TBL: break; case FR_ACT_UNREACHABLE: + err = -ENETUNREACH; rt = net->ipv6.ip6_null_entry; goto discard_pkt; default: case FR_ACT_BLACKHOLE: + err = -EINVAL; rt = net->ipv6.ip6_blk_hole_entry; goto discard_pkt; case FR_ACT_PROHIBIT: + err = -EACCES; rt = net->ipv6.ip6_prohibit_entry; goto discard_pkt; } table = fib6_get_table(net, rule->table); - if (table) - rt = lookup(net, table, flp6, flags); + if (!table) { + err = -EAGAIN; + goto out; + } + rt = lookup(net, table, flp6, flags); if (rt != net->ipv6.ip6_null_entry) { struct fib6_rule *r = (struct fib6_rule *)rule; @@ -101,6 +108,7 @@ static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, } again: ip6_rt_put(rt); + err = -EAGAIN; rt = NULL; goto out; @@ -108,9 +116,31 @@ discard_pkt: dst_hold(&rt->dst); out: arg->result = rt; - return rt == NULL ? -EAGAIN : 0; + return err; } +static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg) +{ + struct rt6_info *rt = (struct rt6_info *) arg->result; + struct net_device *dev = rt->rt6i_idev->dev; + /* do not accept result if the route does + * not meet the required prefix length + */ + if (rt->rt6i_dst.plen <= rule->suppress_prefixlen) + goto suppress_route; + + /* do not accept result if the route uses a device + * belonging to a forbidden interface group + */ + if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup) + goto suppress_route; + + return false; + +suppress_route: + ip6_rt_put(rt); + return true; +} static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) { @@ -244,6 +274,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .addr_size = sizeof(struct in6_addr), .action = fib6_rule_action, .match = fib6_rule_match, + .suppress = fib6_rule_suppress, .configure = fib6_rule_configure, .compare = fib6_rule_compare, .fill = fib6_rule_fill, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index bff3d821c7eb..ed828d6f37b2 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -425,8 +425,8 @@ out: * node. */ -static struct fib6_node * fib6_add_1(struct fib6_node *root, void *addr, - int addrlen, int plen, +static struct fib6_node *fib6_add_1(struct fib6_node *root, + struct in6_addr *addr, int plen, int offset, int allow_create, int replace_required) { @@ -543,7 +543,7 @@ insert_above: but if it is >= plen, the value is ignored in any case. */ - bit = __ipv6_addr_diff(addr, &key->addr, addrlen); + bit = __ipv6_addr_diff(addr, &key->addr, sizeof(*addr)); /* * (intermediate)[in] @@ -822,9 +822,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) if (!allow_create && !replace_required) pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); - fn = fib6_add_1(root, &rt->rt6i_dst.addr, sizeof(struct in6_addr), - rt->rt6i_dst.plen, offsetof(struct rt6_info, rt6i_dst), - allow_create, replace_required); + fn = fib6_add_1(root, &rt->rt6i_dst.addr, rt->rt6i_dst.plen, + offsetof(struct rt6_info, rt6i_dst), allow_create, + replace_required); if (IS_ERR(fn)) { err = PTR_ERR(fn); @@ -863,7 +863,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) /* Now add the first leaf node to new subtree */ sn = fib6_add_1(sfn, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); @@ -882,7 +882,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) fn->subtree = sfn; } else { sn = fib6_add_1(fn->subtree, &rt->rt6i_src.addr, - sizeof(struct in6_addr), rt->rt6i_src.plen, + rt->rt6i_src.plen, offsetof(struct rt6_info, rt6i_src), allow_create, replace_required); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 03986d31fa41..a60a84ef04f7 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -110,8 +110,8 @@ static struct kmem_cache *mrt_cachep __read_mostly; static struct mr6_table *ip6mr_new_table(struct net *net, u32 id); static void ip6mr_free_table(struct mr6_table *mrt); -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache); +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache); static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt, mifi_t mifi, int assert); static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb, @@ -2074,8 +2074,8 @@ static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev) return ct; } -static int ip6_mr_forward(struct net *net, struct mr6_table *mrt, - struct sk_buff *skb, struct mfc6_cache *cache) +static void ip6_mr_forward(struct net *net, struct mr6_table *mrt, + struct sk_buff *skb, struct mfc6_cache *cache) { int psend = -1; int vif, ct; @@ -2156,12 +2156,11 @@ forward: last_forward: if (psend != -1) { ip6mr_forward2(net, mrt, skb, cache, psend); - return 0; + return; } dont_forward: kfree_skb(skb); - return 0; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 99cd65c715cd..db25b8eb62bd 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -44,6 +44,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> +#include <linux/pkt_sched.h> #include <net/mld.h> #include <linux/netfilter.h> @@ -1376,6 +1377,7 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, int size) if (!skb) return NULL; + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { @@ -1769,7 +1771,7 @@ static void igmp6_send(struct in6_addr *addr, struct net_device *dev, int type) rcu_read_unlock(); return; } - + skb->priority = TC_PRIO_CONTROL; skb_reserve(skb, hlen); if (ipv6_get_lladdr(dev, &addr_buf, IFA_F_TENTATIVE)) { diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c45f7a5c36e9..c1e533498203 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -63,6 +63,8 @@ #include <linux/seq_file.h> #include <linux/export.h> +#define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ + static struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; @@ -108,11 +110,14 @@ found: */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { - struct icmp6hdr *_hdr; + struct icmp6hdr _hdr; const struct icmp6hdr *hdr; + /* We require only the four bytes of the ICMPv6 header, not any + * additional bytes of message body in "struct icmp6hdr". + */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), - sizeof(_hdr), &_hdr); + ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b70f8979003b..e22c4db8d07a 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -283,9 +283,8 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net, memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers); - rt->rt6i_genid = rt_genid(net); + rt->rt6i_genid = rt_genid_ipv6(net); INIT_LIST_HEAD(&rt->rt6i_siblings); - rt->rt6i_nsiblings = 0; } return rt; } @@ -1062,7 +1061,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev))) + if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev))) return NULL; if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6e1649d58533..38c196ca6011 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -963,7 +963,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) if (!ipv6_unicast_destination(skb)) goto drop; - if (inet_csk_reqsk_queue_is_full(sk) && !isn) { + if ((sysctl_tcp_syncookies == 2 || + inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, skb, "TCPv6"); if (!want_cookie) goto drop; @@ -1237,8 +1238,6 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); - tcp_synack_rtt_meas(newsk, req); - newtp->total_retrans = req->num_retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; @@ -1926,6 +1925,7 @@ struct proto tcpv6_prot = { .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, + .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, diff --git a/net/irda/irttp.c b/net/irda/irttp.c index ae43c62f9045..85372cfa7b9f 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -75,7 +75,7 @@ static pi_minor_info_t pi_minor_call_table[] = { { NULL, 0 }, /* 0x00 */ { irttp_param_max_sdu_size, PV_INTEGER | PV_BIG_ENDIAN } /* 0x01 */ }; -static pi_major_info_t pi_major_call_table[] = {{ pi_minor_call_table, 2 }}; +static pi_major_info_t pi_major_call_table[] = { { pi_minor_call_table, 2 } }; static pi_param_info_t param_info = { pi_major_call_table, 1, 0x0f, 4 }; /************************ GLOBAL PROCEDURES ************************/ @@ -205,7 +205,7 @@ static void irttp_todo_expired(unsigned long data) */ static void irttp_flush_queues(struct tsap_cb *self) { - struct sk_buff* skb; + struct sk_buff *skb; IRDA_DEBUG(4, "%s()\n", __func__); @@ -400,7 +400,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify) /* The IrLMP spec (IrLMP 1.1 p10) says that we have the right to * use only 0x01-0x6F. Of course, we can use LSAP_ANY as well. * JeanII */ - if((stsap_sel != LSAP_ANY) && + if ((stsap_sel != LSAP_ANY) && ((stsap_sel < 0x01) || (stsap_sel >= 0x70))) { IRDA_DEBUG(0, "%s(), invalid tsap!\n", __func__); return NULL; @@ -427,7 +427,7 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify) ttp_notify.data_indication = irttp_data_indication; ttp_notify.udata_indication = irttp_udata_indication; ttp_notify.flow_indication = irttp_flow_indication; - if(notify->status_indication != NULL) + if (notify->status_indication != NULL) ttp_notify.status_indication = irttp_status_indication; ttp_notify.instance = self; strncpy(ttp_notify.name, notify->name, NOTIFY_MAX_NAME); @@ -639,8 +639,7 @@ int irttp_data_request(struct tsap_cb *self, struct sk_buff *skb) */ if ((self->tx_max_sdu_size != 0) && (self->tx_max_sdu_size != TTP_SAR_UNBOUND) && - (skb->len > self->tx_max_sdu_size)) - { + (skb->len > self->tx_max_sdu_size)) { IRDA_ERROR("%s: SAR enabled, but data is larger than TxMaxSduSize!\n", __func__); ret = -EMSGSIZE; @@ -733,8 +732,7 @@ static void irttp_run_tx_queue(struct tsap_cb *self) * poll us through irttp_flow_indication() - Jean II */ while ((self->send_credit > 0) && (!irlmp_lap_tx_queue_full(self->lsap)) && - (skb = skb_dequeue(&self->tx_queue))) - { + (skb = skb_dequeue(&self->tx_queue))) { /* * Since we can transmit and receive frames concurrently, * the code below is a critical region and we must assure that @@ -798,8 +796,7 @@ static void irttp_run_tx_queue(struct tsap_cb *self) * where we can spend a bit of time doing stuff. - Jean II */ if ((self->tx_sdu_busy) && (skb_queue_len(&self->tx_queue) < TTP_TX_LOW_THRESHOLD) && - (!self->close_pend)) - { + (!self->close_pend)) { if (self->notify.flow_indication) self->notify.flow_indication(self->notify.instance, self, FLOW_START); @@ -892,7 +889,7 @@ static int irttp_udata_indication(void *instance, void *sap, /* Just pass data to layer above */ if (self->notify.udata_indication) { err = self->notify.udata_indication(self->notify.instance, - self,skb); + self, skb); /* Same comment as in irttp_do_data_indication() */ if (!err) return 0; @@ -1057,7 +1054,7 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow) * to do that. Jean II */ /* If we need to send disconnect. try to do it now */ - if(self->disconnect_pend) + if (self->disconnect_pend) irttp_start_todo_timer(self, 0); } @@ -1116,7 +1113,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -EBADR;); if (self->connected) { - if(userdata) + if (userdata) dev_kfree_skb(userdata); return -EISCONN; } @@ -1137,7 +1134,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, * headers */ IRDA_ASSERT(skb_headroom(userdata) >= TTP_MAX_HEADER, - { dev_kfree_skb(userdata); return -1; } ); + { dev_kfree_skb(userdata); return -1; }); } /* Initialize connection parameters */ @@ -1157,7 +1154,7 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, * Give away max 127 credits for now */ if (n > 127) { - self->avail_credit=n-127; + self->avail_credit = n - 127; n = 127; } @@ -1166,10 +1163,10 @@ int irttp_connect_request(struct tsap_cb *self, __u8 dtsap_sel, /* SAR enabled? */ if (max_sdu_size > 0) { IRDA_ASSERT(skb_headroom(tx_skb) >= (TTP_MAX_HEADER + TTP_SAR_HEADER), - { dev_kfree_skb(tx_skb); return -1; } ); + { dev_kfree_skb(tx_skb); return -1; }); /* Insert SAR parameters */ - frame = skb_push(tx_skb, TTP_HEADER+TTP_SAR_HEADER); + frame = skb_push(tx_skb, TTP_HEADER + TTP_SAR_HEADER); frame[0] = TTP_PARAMETERS | n; frame[1] = 0x04; /* Length */ @@ -1386,7 +1383,7 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size, * headers */ IRDA_ASSERT(skb_headroom(userdata) >= TTP_MAX_HEADER, - { dev_kfree_skb(userdata); return -1; } ); + { dev_kfree_skb(userdata); return -1; }); } self->avail_credit = 0; @@ -1409,10 +1406,10 @@ int irttp_connect_response(struct tsap_cb *self, __u32 max_sdu_size, /* SAR enabled? */ if (max_sdu_size > 0) { IRDA_ASSERT(skb_headroom(tx_skb) >= (TTP_MAX_HEADER + TTP_SAR_HEADER), - { dev_kfree_skb(tx_skb); return -1; } ); + { dev_kfree_skb(tx_skb); return -1; }); /* Insert TTP header with SAR parameters */ - frame = skb_push(tx_skb, TTP_HEADER+TTP_SAR_HEADER); + frame = skb_push(tx_skb, TTP_HEADER + TTP_SAR_HEADER); frame[0] = TTP_PARAMETERS | n; frame[1] = 0x04; /* Length */ @@ -1522,7 +1519,7 @@ int irttp_disconnect_request(struct tsap_cb *self, struct sk_buff *userdata, * function may be called from various context, like user, timer * for following a disconnect_indication() (i.e. net_bh). * Jean II */ - if(test_and_set_bit(0, &self->disconnect_pend)) { + if (test_and_set_bit(0, &self->disconnect_pend)) { IRDA_DEBUG(0, "%s(), disconnect already pending\n", __func__); if (userdata) @@ -1627,7 +1624,7 @@ static void irttp_disconnect_indication(void *instance, void *sap, * Jean II */ /* No need to notify the client if has already tried to disconnect */ - if(self->notify.disconnect_indication) + if (self->notify.disconnect_indication) self->notify.disconnect_indication(self->notify.instance, self, reason, skb); else @@ -1738,8 +1735,7 @@ static void irttp_run_rx_queue(struct tsap_cb *self) * This is the last fragment, so time to reassemble! */ if ((self->rx_sdu_size <= self->rx_max_sdu_size) || - (self->rx_max_sdu_size == TTP_SAR_UNBOUND)) - { + (self->rx_max_sdu_size == TTP_SAR_UNBOUND)) { /* * A little optimizing. Only queue the fragment if * there are other fragments. Since if this is the @@ -1860,7 +1856,7 @@ static int irttp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "dtsap_sel: %02x\n", self->dtsap_sel); seq_printf(seq, " connected: %s, ", - self->connected? "TRUE":"FALSE"); + self->connected ? "TRUE" : "FALSE"); seq_printf(seq, "avail credit: %d, ", self->avail_credit); seq_printf(seq, "remote credit: %d, ", @@ -1876,9 +1872,9 @@ static int irttp_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "rx_queue len: %u\n", skb_queue_len(&self->rx_queue)); seq_printf(seq, " tx_sdu_busy: %s, ", - self->tx_sdu_busy? "TRUE":"FALSE"); + self->tx_sdu_busy ? "TRUE" : "FALSE"); seq_printf(seq, "rx_sdu_busy: %s\n", - self->rx_sdu_busy? "TRUE":"FALSE"); + self->rx_sdu_busy ? "TRUE" : "FALSE"); seq_printf(seq, " max_seg_size: %u, ", self->max_seg_size); seq_printf(seq, "tx_max_sdu_size: %u, ", diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 3c0da8728036..23e596e438b3 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -66,15 +66,7 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, static void sctp_nat_csum(struct sk_buff *skb, sctp_sctphdr_t *sctph, unsigned int sctphoff) { - __u32 crc32; - struct sk_buff *iter; - - crc32 = sctp_start_cksum((__u8 *)sctph, skb_headlen(skb) - sctphoff); - skb_walk_frags(skb, iter) - crc32 = sctp_update_cksum((u8 *) iter->data, - skb_headlen(iter), crc32); - sctph->checksum = sctp_end_cksum(crc32); - + sctph->checksum = sctp_compute_cksum(skb, sctphoff); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -151,10 +143,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) { unsigned int sctphoff; struct sctphdr *sh, _sctph; - struct sk_buff *iter; - __le32 cmp; - __le32 val; - __u32 tmp; + __le32 cmp, val; #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) @@ -168,13 +157,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 0; cmp = sh->checksum; - - tmp = sctp_start_cksum((__u8 *) sh, skb_headlen(skb)); - skb_walk_frags(skb, iter) - tmp = sctp_update_cksum((__u8 *) iter->data, - skb_headlen(iter), tmp); - - val = sctp_end_cksum(tmp); + val = sctp_compute_cksum(skb, sctphoff); if (val != cmp) { /* CRC failure, dump it. */ diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index 396e55d46f90..754536f2c674 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -34,9 +34,7 @@ sctp_manip_pkt(struct sk_buff *skb, const struct nf_conntrack_tuple *tuple, enum nf_nat_manip_type maniptype) { - struct sk_buff *frag; sctp_sctphdr_t *hdr; - __u32 crc32; if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) return false; @@ -51,11 +49,7 @@ sctp_manip_pkt(struct sk_buff *skb, hdr->dest = tuple->dst.u.sctp.port; } - crc32 = sctp_start_cksum((u8 *)hdr, skb_headlen(skb) - hdroff); - skb_walk_frags(skb, frag) - crc32 = sctp_update_cksum((u8 *)frag->data, skb_headlen(frag), - crc32); - hdr->checksum = sctp_end_cksum(crc32); + hdr->checksum = sctp_compute_cksum(skb, hdroff); return true; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 0c61b59175dc..6273772aa30c 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -294,14 +294,14 @@ static void **alloc_pg_vec(struct netlink_sock *nlk, { unsigned int block_nr = req->nm_block_nr; unsigned int i; - void **pg_vec, *ptr; + void **pg_vec; pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL); if (pg_vec == NULL) return NULL; for (i = 0; i < block_nr; i++) { - pg_vec[i] = ptr = alloc_one_pg_vec_page(order); + pg_vec[i] = alloc_one_pg_vec_page(order); if (pg_vec[i] == NULL) goto err1; } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 4b66c752eae5..0c0f6c9a90e7 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -88,6 +88,7 @@ #include <linux/virtio_net.h> #include <linux/errqueue.h> #include <linux/net_tstamp.h> +#include <linux/if_arp.h> #ifdef CONFIG_INET #include <net/inet_common.h> @@ -1923,7 +1924,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, __be16 proto, unsigned char *addr, int hlen) { union tpacket_uhdr ph; - int to_write, offset, len, tp_len, nr_frags, len_max; + int to_write, offset, len, tp_len, nr_frags, len_max, max_frame_len; struct socket *sock = po->sk.sk_socket; struct page *page; void *data; @@ -1946,10 +1947,6 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, tp_len = ph.h1->tp_len; break; } - if (unlikely(tp_len > size_max)) { - pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); - return -EMSGSIZE; - } skb_reserve(skb, hlen); skb_reset_network_header(skb); @@ -2005,10 +2002,25 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, if (unlikely(err)) return err; + if (dev->type == ARPHRD_ETHER) + skb->protocol = eth_type_trans(skb, dev); + data += dev->hard_header_len; to_write -= dev->hard_header_len; } + max_frame_len = dev->mtu + dev->hard_header_len; + if (skb->protocol == htons(ETH_P_8021Q)) + max_frame_len += VLAN_HLEN; + + if (size_max > max_frame_len) + size_max = max_frame_len; + + if (unlikely(tp_len > size_max)) { + pr_err("packet size is too long (%d > %d)\n", tp_len, size_max); + return -EMSGSIZE; + } + offset = offset_in_page(data); len_max = PAGE_SIZE - offset; len = ((to_write > len_max) ? len_max : to_write); @@ -2047,7 +2059,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct net_device *dev; __be16 proto; bool need_rls_dev = false; - int err, reserve = 0; + int err; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; int tp_len, size_max; @@ -2080,8 +2092,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) if (unlikely(dev == NULL)) goto out; - reserve = dev->hard_header_len; - err = -ENETDOWN; if (unlikely(!(dev->flags & IFF_UP))) goto out_put; @@ -2089,9 +2099,6 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) size_max = po->tx_ring.frame_size - (po->tp_hdrlen - sizeof(struct sockaddr_ll)); - if (size_max > dev->mtu + reserve) - size_max = dev->mtu + reserve; - do { ph = packet_current_frame(po, &po->tx_ring, TP_STATUS_SEND_REQUEST); @@ -2324,22 +2331,20 @@ static int packet_snd(struct socket *sock, sock_tx_timestamp(sk, &skb_shinfo(skb)->tx_flags); + if (dev->type == ARPHRD_ETHER) { + skb->protocol = eth_type_trans(skb, dev); + if (skb->protocol == htons(ETH_P_8021Q)) + reserve += VLAN_HLEN; + } else { + skb->protocol = proto; + skb->dev = dev; + } + if (!gso_type && (len > dev->mtu + reserve + extra_len)) { - /* Earlier code assumed this would be a VLAN pkt, - * double-check this now that we have the actual - * packet in hand. - */ - struct ethhdr *ehdr; - skb_reset_mac_header(skb); - ehdr = eth_hdr(skb); - if (ehdr->h_proto != htons(ETH_P_8021Q)) { - err = -EMSGSIZE; - goto out_free; - } + err = -EMSGSIZE; + goto out_free; } - skb->protocol = proto; - skb->dev = dev; skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; @@ -2638,51 +2643,6 @@ out: return err; } -static int packet_recv_error(struct sock *sk, struct msghdr *msg, int len) -{ - struct sock_exterr_skb *serr; - struct sk_buff *skb, *skb2; - int copied, err; - - err = -EAGAIN; - skb = skb_dequeue(&sk->sk_error_queue); - if (skb == NULL) - goto out; - - copied = skb->len; - if (copied > len) { - msg->msg_flags |= MSG_TRUNC; - copied = len; - } - err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); - if (err) - goto out_free_skb; - - sock_recv_timestamp(msg, sk, skb); - - serr = SKB_EXT_ERR(skb); - put_cmsg(msg, SOL_PACKET, PACKET_TX_TIMESTAMP, - sizeof(serr->ee), &serr->ee); - - msg->msg_flags |= MSG_ERRQUEUE; - err = copied; - - /* Reset and regenerate socket error */ - spin_lock_bh(&sk->sk_error_queue.lock); - sk->sk_err = 0; - if ((skb2 = skb_peek(&sk->sk_error_queue)) != NULL) { - sk->sk_err = SKB_EXT_ERR(skb2)->ee.ee_errno; - spin_unlock_bh(&sk->sk_error_queue.lock); - sk->sk_error_report(sk); - } else - spin_unlock_bh(&sk->sk_error_queue.lock); - -out_free_skb: - kfree_skb(skb); -out: - return err; -} - /* * Pull a packet from our receive queue and hand it to the user. * If necessary we block. @@ -2708,7 +2668,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, #endif if (flags & MSG_ERRQUEUE) { - err = packet_recv_error(sk, msg, len); + err = sock_recv_errqueue(sk, msg, len, + SOL_PACKET, PACKET_TX_TIMESTAMP); goto out; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 82f6016d89ab..a6d788d45216 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -412,12 +412,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) /* If a delay is expected, orphan the skb. (orphaning usually takes * place at TX completion time, so _before_ the link transit delay) - * Ideally, this orphaning should be done after the rate limiting - * module, because this breaks TCP Small Queue, and other mechanisms - * based on socket sk_wmem_alloc. */ if (q->latency || q->jitter) - skb_orphan(skb); + skb_orphan_partial(skb); /* * If we need to duplicate packet, then re-insert at top of the diff --git a/net/sctp/associola.c b/net/sctp/associola.c index bce5b79662a6..e425ba0bd79e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/auth.c b/net/sctp/auth.c index ba1dfc3f8def..3aab967081be 100644 --- a/net/sctp/auth.c +++ b/net/sctp/auth.c @@ -22,7 +22,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 64977ea0f9c5..f34ce8bc1395 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index 5780565f5b7d..b50b90c16a86 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -24,7 +24,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/command.c b/net/sctp/command.c index c0044019db9e..f4bebdadf007 100644 --- a/net/sctp/command.c +++ b/net/sctp/command.c @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/debug.c b/net/sctp/debug.c index f4998780d6df..44aa4e7543a9 100644 --- a/net/sctp/debug.c +++ b/net/sctp/debug.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 9e3d257de0e0..825b7543a436 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/input.c b/net/sctp/input.c index 3fa4d858c35a..fa91aff02388 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -87,15 +87,7 @@ static inline int sctp_rcv_checksum(struct net *net, struct sk_buff *skb) { struct sctphdr *sh = sctp_hdr(skb); __le32 cmp = sh->checksum; - struct sk_buff *list; - __le32 val; - __u32 tmp = sctp_start_cksum((__u8 *)sh, skb_headlen(skb)); - - skb_walk_frags(skb, list) - tmp = sctp_update_cksum((__u8 *)list->data, skb_headlen(list), - tmp); - - val = sctp_end_cksum(tmp); + __le32 val = sctp_compute_cksum(skb, 0); if (val != cmp) { /* CRC failure, dump it. */ diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index cb25f040fed0..e70f60ae92ef 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -30,7 +30,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 09ffcc912d23..5a9402e3c0cf 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -351,7 +351,7 @@ out: rt = (struct rt6_info *)dst; t->dst = dst; - + t->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; pr_debug("rt6_dst:%pI6 rt6_src:%pI6\n", &rt->rt6i_dst.addr, &fl6->saddr); } else { diff --git a/net/sctp/objcnt.c b/net/sctp/objcnt.c index fe012c44f8df..aec346cbed67 100644 --- a/net/sctp/objcnt.c +++ b/net/sctp/objcnt.c @@ -26,7 +26,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/output.c b/net/sctp/output.c index a46d1eb41762..5a55c55d71ad 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -26,7 +26,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index ef9e2bbc0f2f..51313233e635 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/primitive.c b/net/sctp/primitive.c index 794bb14decde..31fa437da117 100644 --- a/net/sctp/primitive.c +++ b/net/sctp/primitive.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/proc.c b/net/sctp/proc.c index 62526c477050..aff0cac45b64 100644 --- a/net/sctp/proc.c +++ b/net/sctp/proc.c @@ -22,7 +22,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 4a17494d736c..b52ec2510101 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp @@ -1547,7 +1547,7 @@ module_exit(sctp_exit); */ MODULE_ALIAS("net-pf-" __stringify(PF_INET) "-proto-132"); MODULE_ALIAS("net-pf-" __stringify(PF_INET6) "-proto-132"); -MODULE_AUTHOR("Linux Kernel SCTP developers <lksctp-developers@lists.sourceforge.net>"); +MODULE_AUTHOR("Linux Kernel SCTP developers <linux-sctp@vger.kernel.org>"); MODULE_DESCRIPTION("Support for the SCTP protocol (RFC2960)"); module_param_named(no_checksums, sctp_checksum_disable, bool, 0644); MODULE_PARM_DESC(no_checksums, "Disable checksums computing and verification"); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 362ae6e2fd93..780a2d4b98a2 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -29,7 +29,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 9da68852ee94..f1f3aac3f3bb 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index f6b7109195a6..93271f0966c6 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 84d98d8a5a74..64ea5fd87eb2 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/socket.c b/net/sctp/socket.c index c6670d2e3f8d..02457123bdee 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -34,7 +34,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ssnmap.c b/net/sctp/ssnmap.c index da8603523808..72b5939101bb 100644 --- a/net/sctp/ssnmap.c +++ b/net/sctp/ssnmap.c @@ -24,7 +24,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 9a5c4c9eddaf..190674702b20 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -25,7 +25,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/transport.c b/net/sctp/transport.c index bdbbc3fd7c14..9602c52aa617 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -30,7 +30,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/tsnmap.c b/net/sctp/tsnmap.c index b46019568a86..0eff8667d4c7 100644 --- a/net/sctp/tsnmap.c +++ b/net/sctp/tsnmap.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 44a45dbee4df..c07624fca7e5 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -28,7 +28,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 04e3d470f877..2cdb3010f50f 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -27,7 +27,7 @@ * * Please send any bug reports or fixes you make to the * email address(es): - * lksctp developers <lksctp-developers@lists.sourceforge.net> + * lksctp developers <linux-sctp@vger.kernel.org> * * Or submit a bug report through the following website: * http://www.sf.net/projects/lksctp diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 7762b9f8a8b7..9c9caaa5e0d3 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -442,7 +442,7 @@ static void svc_tcp_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) && sock) + if (sk_stream_is_writeable(sk) && sock) clear_bit(SOCK_NOSPACE, &sock->flags); svc_write_space(sk); } diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ddf0602603bd..d6656d7768f4 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -1602,7 +1602,7 @@ static void xs_tcp_write_space(struct sock *sk) read_lock_bh(&sk->sk_callback_lock); /* from net/core/stream.c:sk_stream_write_space */ - if (sk_stream_wspace(sk) >= sk_stream_min_wspace(sk)) + if (sk_stream_is_writeable(sk)) xs_write_space(sk); read_unlock_bh(&sk->sk_callback_lock); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 593071dabd1c..57896eee1c25 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -96,8 +96,7 @@ #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> - -#include "af_vsock.h" +#include <net/af_vsock.h> static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr); static void vsock_sk_destruct(struct sock *sk); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index ffc11df02af2..9d6986634e0b 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -34,8 +34,8 @@ #include <linux/wait.h> #include <linux/workqueue.h> #include <net/sock.h> +#include <net/af_vsock.h> -#include "af_vsock.h" #include "vmci_transport_notify.h" static int vmci_transport_recv_dgram_cb(void *data, struct vmci_datagram *dg); diff --git a/net/vmw_vsock/vmci_transport.h b/net/vmw_vsock/vmci_transport.h index fd88ea8924e4..ce6c9623d5f0 100644 --- a/net/vmw_vsock/vmci_transport.h +++ b/net/vmw_vsock/vmci_transport.h @@ -19,8 +19,8 @@ #include <linux/vmw_vmci_defs.h> #include <linux/vmw_vmci_api.h> -#include "vsock_addr.h" -#include "af_vsock.h" +#include <net/vsock_addr.h> +#include <net/af_vsock.h> /* If the packet format changes in a release then this should change too. */ #define VMCI_TRANSPORT_PACKET_VERSION 1 diff --git a/net/vmw_vsock/vsock_addr.c b/net/vmw_vsock/vsock_addr.c index ec2611b4ea0e..82486ee55eac 100644 --- a/net/vmw_vsock/vsock_addr.c +++ b/net/vmw_vsock/vsock_addr.c @@ -17,8 +17,7 @@ #include <linux/socket.h> #include <linux/stddef.h> #include <net/sock.h> - -#include "vsock_addr.h" +#include <net/vsock_addr.h> void vsock_addr_init(struct sockaddr_vm *addr, u32 cid, u32 port) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index e52cab3591dd..d8da6b8c6ba8 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -660,7 +660,13 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) xfrm_pol_hold(policy); net->xfrm.policy_count[dir]++; atomic_inc(&flow_cache_genid); - rt_genid_bump(net); + + /* After previous checking, family can either be AF_INET or AF_INET6 */ + if (policy->family == AF_INET) + rt_genid_bump_ipv4(net); + else + rt_genid_bump_ipv6(net); + if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 65f67cb0aefb..6713f04e30ba 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -50,8 +50,13 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall); static inline void selinux_xfrm_notify_policyload(void) { + struct net *net; + atomic_inc(&flow_cache_genid); - rt_genid_bump(&init_net); + rtnl_lock(); + for_each_net(net) + rt_genid_bump_all(net); + rtnl_unlock(); } #else static inline int selinux_xfrm_enabled(void) |