From 22098763a10d9c1340827fcf6edab66f153b27f0 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 13 Sep 2026 12:27:00 -0700 Subject: Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Don't destroy user event fields when removal fails User event fields are destroyed before the event is removed from visibility. But that can fail leaving the still visible event with no fields. Move the destroying of the fields to after the event is successfully removed from visibility. - Initialize function graph state is fork before calling copy_exec_state() For non-CLONE_VM forks, copy_exec_state() allocates a new task_exec_state. If that allocation fails, ftrace_graph_exit_task() will free the tasks ret_stack pointer. Since that pointer is still using the parent's ret_stack, it mistakenly frees the parent's pointer too. Call ftrace_graph_init() on the task first which will NULL out the new tasks's ret_stack and if the copy fails, it will not free anything. - Remove FGRAPH_MAX_INDEX The macro FGRAPH_MAX_INDEX was added but never used. Remove it. - Save ent_size in function graph printing of nested functions The function graph tracer needs to look at the next event to see if the next event is the return of the current function entry. If it is, it prints a single line: ktime_get(); Otherwise it prints it like a nested function: tick_nohz_irq_exit() { ktime_get(); kcpustat_irq_exit(); } In order to look at the next event, it must save the current event so that it has the information to print from it. It saves the event in the iterator descriptor called "ent". What it doesn't save is the ent_size of the event which is now used to know if the function graph arguments are to be printed. The peek doesn't save the size so the size used happens to be that of the size of the last event that was seen. Save the entry event size in the iterator descriptor so that the correct size is used. - Fix several errors with freeing data in the histogram code The histogram code had a lot of leaked or or incorrect accounting when failures happen. Correct them. - Fix histogram regression of .percent and .graph modifiers Up until 6.3 histogram values could have "percent" or "graph" modifiers that changed how they were printed. But a change that added restricting histograms values from being strings, stack traces and other modifiers inadvertently prevented them from using the percent and graph modifiers, which were legal use cases for values. Put back the percent and graph modifiers. - Fix various typos in the comments - Set the trace_clock before initializing a histogram with clock argument The histogram API allows the user to specific which trace clock to use via a "clock=" string. The histogram is set up first before the clock is checked. If the passed in clock is not valid, it exits without fully fixing up the histogram leaving it on the list and a use-after-free can trigger. Update the clock argument first and if it fails then exit gracefully before the histogram trigger is placed on any lists. - Restore :mod: trailer after parsing in ftrace_set_clr_event The function ftrace_set_clr_event() modifies the parse string and needs to put it back to what was passed in. It searches for ":mod:" via a strsep() but fails to put back the first ':' in the string. Add back the ':' in the passed in string. - Take trace_array reference when opening a tracer options file The options files are dynamically created and some tracers add their own options. When a tracer adds their own list of options, the trace_array holding them has an array to hold the list of options for each tracer. This array increases in size via a krealloc(), and the new entry gets a newly allocated array to hold the options of the new tracer being added. The element in each entry of the tracer's option array holds a pointer back to the trace_array, a pointer to the tracer it is associated to, a pointer to the flags of the option. The issue is that these arrays are freed when the trace_array is freed when its instance it represents is removed from the instances directory. There's a race that an open of one of these options files can happen when the instance is being removed. Add a new helper function to be called by the open function of the options file to iterate all existing trace_arrays under a lock and find the one that has the given option element in one of it's tracer arrays. If found, then update the associated trace_array's reference counter to keep it from being freed. If not found, have the open call return -ENODEV. - Disable interrupts when acquiring the lock in rb_wake_up_waiters() The function rb_wake_up_waiters() assumes it will be called in interrupt context and does not disable irqs when taking cpu_buffer->reader_lock, which can be called in hard interrupt context. The issue is in PREEMPT_RT, this function is called in thread context leaving this lock open to a deadlock. Take the lock with interrupts disabled. - Use rcu_assign_pointer() for tmp_ops filter hash The tmp_ops used in update_ftrace_direct_mod() assigns its filter_hash field directly, but that field is annotated as __rcu and sparse complains. Assign it with rcu_assign_pointer() - Fix use-after-free in enable_trigger_private_data_free() The trace_event_call is accessed through the event_trigger_data's trace_event_file pointer to put the trace_event_call on freeing. The issue is that the trace_event_file data may have been freed already causing a use-after-free. Add a field to the event_trigger_data that points directly to the trace_event_call so that it can decrement its reference directly without needing to go through the trace_event_file. - Fix accounting of buffer data remote headers trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount the number of pages is needed for the asked for size as it doesn't take into account the meta data on each page. Add a helper function to do the calculation properly and use that in these functions. - Catch nr_page_va overflow in ring_buffer_desc sizing The number of pages per remote ring buffer is capped by ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to overflow that field would silently allocate a descriptor smaller than what was asked for. - Do not resize the subbuf order if any per_cpu buffer is disabled The mmapping of ring buffers disables resizing the subbuffers, but it is done per-cpu whereas the subbuf size change is done for all the per_cpu buffers under the buffer->mutex. It could change the size of some while the mapping is happening on others. Have the resize of the subbuf order check all the per_cpu buffers under the lock to see if any of them is disabled before starting and causing an inconsistency between buffers that are being mapped. * tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits) ring-buffer: Check resize_disabled before publishing the new subbuf order tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing tracing/remotes: Account for ring buffer page header in size calculation tracing: Don't dereference trace_event_file in deferred trigger free ftrace: Use rcu_assign_pointer() for tmp_ops filter hash ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters() tracing: Take trace_array reference when opening a tracer options file tracing: Fix ring_buffer_read_page_size() kernel-doc tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event() tracing: Fix memory corruption from a "STACKTRACE" histogram key tracing: Fix memory corruption from the histogram stacktrace modifier tracing: Undo the registration when enabling the histogram trigger fails tracing: Take the reference before publishing the named histogram trigger tracing: Set the trace clock before registering the histogram trigger tracing: Fix typo "preceeded" in comment tracing: Fix typo "availabe" in comment tracing: Let histogram values keep the percent and graph modifiers tracing: Keep the entry count when the histogram stats allocation fails tracing: Free histogram the field rejected for a bad modifier tracing: Free histogram the var ref when its initialization fails ... --- net/dcb/Kconfig | 23 + net/dcb/Makefile | 2 + net/dcb/dcbevent.c | 30 + net/dcb/dcbnl.c | 2427 ++++++++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 2482 insertions(+) create mode 100644 net/dcb/Kconfig create mode 100644 net/dcb/Makefile create mode 100644 net/dcb/dcbevent.c create mode 100644 net/dcb/dcbnl.c (limited to 'net/dcb') diff --git a/net/dcb/Kconfig b/net/dcb/Kconfig new file mode 100644 index 000000000..efee8b9fe --- /dev/null +++ b/net/dcb/Kconfig @@ -0,0 +1,23 @@ +# SPDX-License-Identifier: GPL-2.0-only +config DCB + bool "Data Center Bridging support" + default n + help + This enables support for configuring Data Center Bridging (DCB) + features on DCB capable Ethernet adapters via rtnetlink. Say 'Y' + if you have a DCB capable Ethernet adapter which supports this + interface and you are connected to a DCB capable switch. + + DCB is a collection of Ethernet enhancements which allow DCB capable + NICs and switches to support network traffic with differing + requirements (highly reliable, no drops vs. best effort vs. low + latency) to co-exist on Ethernet. + + DCB features include: + Enhanced Transmission Selection (aka Priority Grouping) - provides a + framework for assigning bandwidth guarantees to traffic classes. + Priority-based Flow Control (PFC) - a MAC control pause frame which + works at the granularity of the 802.1p priority instead of the + link (802.3x). + + If unsure, say N. diff --git a/net/dcb/Makefile b/net/dcb/Makefile new file mode 100644 index 000000000..2c0fa16ee --- /dev/null +++ b/net/dcb/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +obj-y += dcbnl.o dcbevent.o diff --git a/net/dcb/dcbevent.c b/net/dcb/dcbevent.c new file mode 100644 index 000000000..8620564c2 --- /dev/null +++ b/net/dcb/dcbevent.c @@ -0,0 +1,30 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2010, Intel Corporation. + * + * Author: John Fastabend + */ + +#include +#include +#include +#include + +static ATOMIC_NOTIFIER_HEAD(dcbevent_notif_chain); + +int register_dcbevent_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_register(&dcbevent_notif_chain, nb); +} +EXPORT_SYMBOL(register_dcbevent_notifier); + +int unregister_dcbevent_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&dcbevent_notif_chain, nb); +} +EXPORT_SYMBOL(unregister_dcbevent_notifier); + +int call_dcbevent_notifiers(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&dcbevent_notif_chain, val, v); +} diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c new file mode 100644 index 000000000..35164bfa5 --- /dev/null +++ b/net/dcb/dcbnl.c @@ -0,0 +1,2427 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2008-2011, Intel Corporation. + * + * Description: Data Center Bridging netlink interface + * Author: Lucy Liu + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Data Center Bridging (DCB) is a collection of Ethernet enhancements + * intended to allow network traffic with differing requirements + * (highly reliable, no drops vs. best effort vs. low latency) to operate + * and co-exist on Ethernet. Current DCB features are: + * + * Enhanced Transmission Selection (aka Priority Grouping [PG]) - provides a + * framework for assigning bandwidth guarantees to traffic classes. + * + * Priority-based Flow Control (PFC) - provides a flow control mechanism which + * can work independently for each 802.1p priority. + * + * Congestion Notification - provides a mechanism for end-to-end congestion + * control for protocols which do not have built-in congestion management. + * + * More information about the emerging standards for these Ethernet features + * can be found at: http://www.ieee802.org/1/pages/dcbridges.html + * + * This file implements an rtnetlink interface to allow configuration of DCB + * features for capable devices. + */ + +/**************** DCB attribute policies *************************************/ + +/* DCB netlink attributes policy */ +static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { + [DCB_ATTR_IFNAME] = {.type = NLA_NUL_STRING, .len = IFNAMSIZ - 1}, + [DCB_ATTR_STATE] = {.type = NLA_U8}, + [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED}, + [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED}, + [DCB_ATTR_SET_ALL] = {.type = NLA_U8}, + [DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG}, + [DCB_ATTR_CAP] = {.type = NLA_NESTED}, + [DCB_ATTR_PFC_STATE] = {.type = NLA_U8}, + [DCB_ATTR_BCN] = {.type = NLA_NESTED}, + [DCB_ATTR_APP] = {.type = NLA_NESTED}, + [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, + [DCB_ATTR_DCBX] = {.type = NLA_U8}, + [DCB_ATTR_FEATCFG] = {.type = NLA_NESTED}, +}; + +/* DCB priority flow control to User Priority nested attributes */ +static const struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { + [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_3] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_4] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_5] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_6] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_7] = {.type = NLA_U8}, + [DCB_PFC_UP_ATTR_ALL] = {.type = NLA_FLAG}, +}; + +/* DCB priority grouping nested attributes */ +static const struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { + [DCB_PG_ATTR_TC_0] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_1] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_2] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_3] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_4] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_5] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_6] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_7] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_TC_ALL] = {.type = NLA_NESTED}, + [DCB_PG_ATTR_BW_ID_0] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_1] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_2] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_3] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_4] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_5] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_6] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_7] = {.type = NLA_U8}, + [DCB_PG_ATTR_BW_ID_ALL] = {.type = NLA_FLAG}, +}; + +/* DCB traffic class nested attributes. */ +static const struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { + [DCB_TC_ATTR_PARAM_PGID] = {.type = NLA_U8}, + [DCB_TC_ATTR_PARAM_UP_MAPPING] = {.type = NLA_U8}, + [DCB_TC_ATTR_PARAM_STRICT_PRIO] = {.type = NLA_U8}, + [DCB_TC_ATTR_PARAM_BW_PCT] = {.type = NLA_U8}, + [DCB_TC_ATTR_PARAM_ALL] = {.type = NLA_FLAG}, +}; + +/* DCB capabilities nested attributes. */ +static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { + [DCB_CAP_ATTR_ALL] = {.type = NLA_FLAG}, + [DCB_CAP_ATTR_PG] = {.type = NLA_U8}, + [DCB_CAP_ATTR_PFC] = {.type = NLA_U8}, + [DCB_CAP_ATTR_UP2TC] = {.type = NLA_U8}, + [DCB_CAP_ATTR_PG_TCS] = {.type = NLA_U8}, + [DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8}, + [DCB_CAP_ATTR_GSP] = {.type = NLA_U8}, + [DCB_CAP_ATTR_BCN] = {.type = NLA_U8}, + [DCB_CAP_ATTR_DCBX] = {.type = NLA_U8}, +}; + +/* DCB capabilities nested attributes. */ +static const struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = { + [DCB_NUMTCS_ATTR_ALL] = {.type = NLA_FLAG}, + [DCB_NUMTCS_ATTR_PG] = {.type = NLA_U8}, + [DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8}, +}; + +/* DCB BCN nested attributes. */ +static const struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { + [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_3] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_4] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_5] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_6] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_7] = {.type = NLA_U8}, + [DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG}, + [DCB_BCN_ATTR_BCNA_0] = {.type = NLA_U32}, + [DCB_BCN_ATTR_BCNA_1] = {.type = NLA_U32}, + [DCB_BCN_ATTR_ALPHA] = {.type = NLA_U32}, + [DCB_BCN_ATTR_BETA] = {.type = NLA_U32}, + [DCB_BCN_ATTR_GD] = {.type = NLA_U32}, + [DCB_BCN_ATTR_GI] = {.type = NLA_U32}, + [DCB_BCN_ATTR_TMAX] = {.type = NLA_U32}, + [DCB_BCN_ATTR_TD] = {.type = NLA_U32}, + [DCB_BCN_ATTR_RMIN] = {.type = NLA_U32}, + [DCB_BCN_ATTR_W] = {.type = NLA_U32}, + [DCB_BCN_ATTR_RD] = {.type = NLA_U32}, + [DCB_BCN_ATTR_RU] = {.type = NLA_U32}, + [DCB_BCN_ATTR_WRTT] = {.type = NLA_U32}, + [DCB_BCN_ATTR_RI] = {.type = NLA_U32}, + [DCB_BCN_ATTR_C] = {.type = NLA_U32}, + [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG}, +}; + +/* DCB APP nested attributes. */ +static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { + [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8}, + [DCB_APP_ATTR_ID] = {.type = NLA_U16}, + [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, +}; + +/* IEEE 802.1Qaz nested attributes. */ +static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { + [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)}, + [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, + [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, + [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, + [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, + [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, + [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, + [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, +}; + +/* DCB number of traffic classes nested attributes. */ +static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { + [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG}, + [DCB_FEATCFG_ATTR_PG] = {.type = NLA_U8}, + [DCB_FEATCFG_ATTR_PFC] = {.type = NLA_U8}, + [DCB_FEATCFG_ATTR_APP] = {.type = NLA_U8}, +}; + +static LIST_HEAD(dcb_app_list); +static LIST_HEAD(dcb_rewr_list); +static DEFINE_SPINLOCK(dcb_lock); + +static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) +{ + switch (selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + case IEEE_8021QAZ_APP_SEL_STREAM: + case IEEE_8021QAZ_APP_SEL_DGRAM: + case IEEE_8021QAZ_APP_SEL_ANY: + case IEEE_8021QAZ_APP_SEL_DSCP: + return DCB_ATTR_IEEE_APP; + case DCB_APP_SEL_PCP: + return DCB_ATTR_DCB_APP; + default: + return DCB_ATTR_IEEE_APP_UNSPEC; + } +} + +static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) +{ + switch (type) { + case DCB_ATTR_IEEE_APP: + case DCB_ATTR_DCB_APP: + return true; + default: + return false; + } +} + +static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) +{ + return dcbnl_app_attr_type_get(selector) == type; +} + +static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, + u32 flags, struct nlmsghdr **nlhp) +{ + struct sk_buff *skb; + struct dcbmsg *dcb; + struct nlmsghdr *nlh; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return NULL; + + nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags); + BUG_ON(!nlh); + + dcb = nlmsg_data(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = cmd; + dcb->dcb_pad = 0; + + if (nlhp) + *nlhp = nlh; + + return skb; +} + +static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + /* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */ + if (!netdev->dcbnl_ops->getstate) + return -EOPNOTSUPP; + + return nla_put_u8(skb, DCB_ATTR_STATE, + netdev->dcbnl_ops->getstate(netdev)); +} + +static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest; + u8 value; + int ret; + int i; + int getall = 0; + + if (!tb[DCB_ATTR_PFC_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getpfccfg) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, + tb[DCB_ATTR_PFC_CFG], + dcbnl_pfc_up_nest, NULL); + if (ret) + return ret; + + nest = nla_nest_start_noflag(skb, DCB_ATTR_PFC_CFG); + if (!nest) + return -EMSGSIZE; + + if (data[DCB_PFC_UP_ATTR_ALL]) + getall = 1; + + for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { + if (!getall && !data[i]) + continue; + + netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, + &value); + ret = nla_put_u8(skb, i, value); + if (ret) { + nla_nest_cancel(skb, nest); + return ret; + } + } + nla_nest_end(skb, nest); + + return 0; +} + +static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + u8 perm_addr[MAX_ADDR_LEN]; + + if (!netdev->dcbnl_ops->getpermhwaddr) + return -EOPNOTSUPP; + + memset(perm_addr, 0, sizeof(perm_addr)); + netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); + + return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); +} + +static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest; + u8 value; + int ret; + int i; + int getall = 0; + + if (!tb[DCB_ATTR_CAP]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getcap) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_CAP_ATTR_MAX, + tb[DCB_ATTR_CAP], dcbnl_cap_nest, + NULL); + if (ret) + return ret; + + nest = nla_nest_start_noflag(skb, DCB_ATTR_CAP); + if (!nest) + return -EMSGSIZE; + + if (data[DCB_CAP_ATTR_ALL]) + getall = 1; + + for (i = DCB_CAP_ATTR_ALL+1; i <= DCB_CAP_ATTR_MAX; i++) { + if (!getall && !data[i]) + continue; + + if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) { + ret = nla_put_u8(skb, i, value); + if (ret) { + nla_nest_cancel(skb, nest); + return ret; + } + } + } + nla_nest_end(skb, nest); + + return 0; +} + +static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest; + u8 value; + int ret; + int i; + int getall = 0; + + if (!tb[DCB_ATTR_NUMTCS]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getnumtcs) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, + tb[DCB_ATTR_NUMTCS], + dcbnl_numtcs_nest, NULL); + if (ret) + return ret; + + nest = nla_nest_start_noflag(skb, DCB_ATTR_NUMTCS); + if (!nest) + return -EMSGSIZE; + + if (data[DCB_NUMTCS_ATTR_ALL]) + getall = 1; + + for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { + if (!getall && !data[i]) + continue; + + ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value); + if (!ret) { + ret = nla_put_u8(skb, i, value); + if (ret) { + nla_nest_cancel(skb, nest); + return ret; + } + } else + return -EINVAL; + } + nla_nest_end(skb, nest); + + return 0; +} + +static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1]; + int ret; + u8 value; + int i; + + if (!tb[DCB_ATTR_NUMTCS]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setnumtcs) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, + tb[DCB_ATTR_NUMTCS], + dcbnl_numtcs_nest, NULL); + if (ret) + return ret; + + for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { + if (data[i] == NULL) + continue; + + value = nla_get_u8(data[i]); + + ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value); + if (ret) + break; + } + + return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret); +} + +static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + if (!netdev->dcbnl_ops->getpfcstate) + return -EOPNOTSUPP; + + return nla_put_u8(skb, DCB_ATTR_PFC_STATE, + netdev->dcbnl_ops->getpfcstate(netdev)); +} + +static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + u8 value; + + if (!tb[DCB_ATTR_PFC_STATE]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpfcstate) + return -EOPNOTSUPP; + + value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]); + + netdev->dcbnl_ops->setpfcstate(netdev, value); + + return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0); +} + +static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *app_nest; + struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; + u16 id; + u8 up, idtype; + int ret; + + if (!tb[DCB_ATTR_APP]) + return -EINVAL; + + ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, + tb[DCB_ATTR_APP], dcbnl_app_nest, + NULL); + if (ret) + return ret; + + /* all must be non-null */ + if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || + (!app_tb[DCB_APP_ATTR_ID])) + return -EINVAL; + + /* either by eth type or by socket number */ + idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); + if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && + (idtype != DCB_APP_IDTYPE_PORTNUM)) + return -EINVAL; + + id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); + + if (netdev->dcbnl_ops->getapp) { + ret = netdev->dcbnl_ops->getapp(netdev, idtype, id); + if (ret < 0) + return ret; + else + up = ret; + } else { + struct dcb_app app = { + .selector = idtype, + .protocol = id, + }; + up = dcb_getapp(netdev, &app); + } + + app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); + if (!app_nest) + return -EMSGSIZE; + + ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype); + if (ret) + goto out_cancel; + + ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id); + if (ret) + goto out_cancel; + + ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up); + if (ret) + goto out_cancel; + + nla_nest_end(skb, app_nest); + + return 0; + +out_cancel: + nla_nest_cancel(skb, app_nest); + return ret; +} + +static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + int ret; + u16 id; + u8 up, idtype; + struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; + + if (!tb[DCB_ATTR_APP]) + return -EINVAL; + + ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, + tb[DCB_ATTR_APP], dcbnl_app_nest, + NULL); + if (ret) + return ret; + + /* all must be non-null */ + if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || + (!app_tb[DCB_APP_ATTR_ID]) || + (!app_tb[DCB_APP_ATTR_PRIORITY])) + return -EINVAL; + + /* either by eth type or by socket number */ + idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); + if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && + (idtype != DCB_APP_IDTYPE_PORTNUM)) + return -EINVAL; + + id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); + up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); + + if (netdev->dcbnl_ops->setapp) { + ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); + if (ret < 0) + return ret; + } else { + struct dcb_app app; + app.selector = idtype; + app.protocol = id; + app.priority = up; + ret = dcb_setapp(netdev, &app); + } + + ret = nla_put_u8(skb, DCB_ATTR_APP, ret); + dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0); + + return ret; +} + +static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + struct nlattr **tb, struct sk_buff *skb, int dir) +{ + struct nlattr *pg_nest, *param_nest, *data; + struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; + struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; + u8 prio, pgid, tc_pct, up_map; + int ret; + int getall = 0; + int i; + + if (!tb[DCB_ATTR_PG_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getpgtccfgtx || + !netdev->dcbnl_ops->getpgtccfgrx || + !netdev->dcbnl_ops->getpgbwgcfgtx || + !netdev->dcbnl_ops->getpgbwgcfgrx) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, + tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, + NULL); + if (ret) + return ret; + + pg_nest = nla_nest_start_noflag(skb, DCB_ATTR_PG_CFG); + if (!pg_nest) + return -EMSGSIZE; + + if (pg_tb[DCB_PG_ATTR_TC_ALL]) + getall = 1; + + for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { + if (!getall && !pg_tb[i]) + continue; + + if (pg_tb[DCB_PG_ATTR_TC_ALL]) + data = pg_tb[DCB_PG_ATTR_TC_ALL]; + else + data = pg_tb[i]; + ret = nla_parse_nested_deprecated(param_tb, + DCB_TC_ATTR_PARAM_MAX, data, + dcbnl_tc_param_nest, NULL); + if (ret) + goto err_pg; + + param_nest = nla_nest_start_noflag(skb, i); + if (!param_nest) + goto err_pg; + + pgid = DCB_ATTR_VALUE_UNDEFINED; + prio = DCB_ATTR_VALUE_UNDEFINED; + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + up_map = DCB_ATTR_VALUE_UNDEFINED; + + if (dir) { + /* Rx */ + netdev->dcbnl_ops->getpgtccfgrx(netdev, + i - DCB_PG_ATTR_TC_0, &prio, + &pgid, &tc_pct, &up_map); + } else { + /* Tx */ + netdev->dcbnl_ops->getpgtccfgtx(netdev, + i - DCB_PG_ATTR_TC_0, &prio, + &pgid, &tc_pct, &up_map); + } + + if (param_tb[DCB_TC_ATTR_PARAM_PGID] || + param_tb[DCB_TC_ATTR_PARAM_ALL]) { + ret = nla_put_u8(skb, + DCB_TC_ATTR_PARAM_PGID, pgid); + if (ret) + goto err_param; + } + if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] || + param_tb[DCB_TC_ATTR_PARAM_ALL]) { + ret = nla_put_u8(skb, + DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); + if (ret) + goto err_param; + } + if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] || + param_tb[DCB_TC_ATTR_PARAM_ALL]) { + ret = nla_put_u8(skb, + DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); + if (ret) + goto err_param; + } + if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] || + param_tb[DCB_TC_ATTR_PARAM_ALL]) { + ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, + tc_pct); + if (ret) + goto err_param; + } + nla_nest_end(skb, param_nest); + } + + if (pg_tb[DCB_PG_ATTR_BW_ID_ALL]) + getall = 1; + else + getall = 0; + + for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { + if (!getall && !pg_tb[i]) + continue; + + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + + if (dir) { + /* Rx */ + netdev->dcbnl_ops->getpgbwgcfgrx(netdev, + i - DCB_PG_ATTR_BW_ID_0, &tc_pct); + } else { + /* Tx */ + netdev->dcbnl_ops->getpgbwgcfgtx(netdev, + i - DCB_PG_ATTR_BW_ID_0, &tc_pct); + } + ret = nla_put_u8(skb, i, tc_pct); + if (ret) + goto err_pg; + } + + nla_nest_end(skb, pg_nest); + + return 0; + +err_param: + nla_nest_cancel(skb, param_nest); +err_pg: + nla_nest_cancel(skb, pg_nest); + + return -EMSGSIZE; +} + +static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0); +} + +static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1); +} + +static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + u8 value; + + if (!tb[DCB_ATTR_STATE]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setstate) + return -EOPNOTSUPP; + + value = nla_get_u8(tb[DCB_ATTR_STATE]); + + return nla_put_u8(skb, DCB_ATTR_STATE, + netdev->dcbnl_ops->setstate(netdev, value)); +} + +static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1]; + int i; + int ret; + u8 value; + + if (!tb[DCB_ATTR_PFC_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpfccfg) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, + tb[DCB_ATTR_PFC_CFG], + dcbnl_pfc_up_nest, NULL); + if (ret) + return ret; + + for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { + if (data[i] == NULL) + continue; + value = nla_get_u8(data[i]); + netdev->dcbnl_ops->setpfccfg(netdev, + data[i]->nla_type - DCB_PFC_UP_ATTR_0, value); + } + + return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0); +} + +static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + int ret; + + if (!tb[DCB_ATTR_SET_ALL]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setall) + return -EOPNOTSUPP; + + ret = nla_put_u8(skb, DCB_ATTR_SET_ALL, + netdev->dcbnl_ops->setall(netdev)); + dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0); + + return ret; +} + +static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb, + int dir) +{ + struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; + struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; + int ret; + int i; + u8 pgid; + u8 up_map; + u8 prio; + u8 tc_pct; + + if (!tb[DCB_ATTR_PG_CFG]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setpgtccfgtx || + !netdev->dcbnl_ops->setpgtccfgrx || + !netdev->dcbnl_ops->setpgbwgcfgtx || + !netdev->dcbnl_ops->setpgbwgcfgrx) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, + tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, + NULL); + if (ret) + return ret; + + for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { + if (!pg_tb[i]) + continue; + + ret = nla_parse_nested_deprecated(param_tb, + DCB_TC_ATTR_PARAM_MAX, + pg_tb[i], + dcbnl_tc_param_nest, NULL); + if (ret) + return ret; + + pgid = DCB_ATTR_VALUE_UNDEFINED; + prio = DCB_ATTR_VALUE_UNDEFINED; + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + up_map = DCB_ATTR_VALUE_UNDEFINED; + + if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]) + prio = + nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]); + + if (param_tb[DCB_TC_ATTR_PARAM_PGID]) + pgid = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_PGID]); + + if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT]) + tc_pct = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_BW_PCT]); + + if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]) + up_map = + nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]); + + /* dir: Tx = 0, Rx = 1 */ + if (dir) { + /* Rx */ + netdev->dcbnl_ops->setpgtccfgrx(netdev, + i - DCB_PG_ATTR_TC_0, + prio, pgid, tc_pct, up_map); + } else { + /* Tx */ + netdev->dcbnl_ops->setpgtccfgtx(netdev, + i - DCB_PG_ATTR_TC_0, + prio, pgid, tc_pct, up_map); + } + } + + for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { + if (!pg_tb[i]) + continue; + + tc_pct = nla_get_u8(pg_tb[i]); + + /* dir: Tx = 0, Rx = 1 */ + if (dir) { + /* Rx */ + netdev->dcbnl_ops->setpgbwgcfgrx(netdev, + i - DCB_PG_ATTR_BW_ID_0, tc_pct); + } else { + /* Tx */ + netdev->dcbnl_ops->setpgbwgcfgtx(netdev, + i - DCB_PG_ATTR_BW_ID_0, tc_pct); + } + } + + return nla_put_u8(skb, DCB_ATTR_PG_CFG, 0); +} + +static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0); +} + +static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1); +} + +static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *bcn_nest; + struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1]; + u8 value_byte; + u32 value_integer; + int ret; + bool getall = false; + int i; + + if (!tb[DCB_ATTR_BCN]) + return -EINVAL; + + if (!netdev->dcbnl_ops->getbcnrp || + !netdev->dcbnl_ops->getbcncfg) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(bcn_tb, DCB_BCN_ATTR_MAX, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, + NULL); + if (ret) + return ret; + + bcn_nest = nla_nest_start_noflag(skb, DCB_ATTR_BCN); + if (!bcn_nest) + return -EMSGSIZE; + + if (bcn_tb[DCB_BCN_ATTR_ALL]) + getall = true; + + for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { + if (!getall && !bcn_tb[i]) + continue; + + netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0, + &value_byte); + ret = nla_put_u8(skb, i, value_byte); + if (ret) + goto err_bcn; + } + + for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { + if (!getall && !bcn_tb[i]) + continue; + + netdev->dcbnl_ops->getbcncfg(netdev, i, + &value_integer); + ret = nla_put_u32(skb, i, value_integer); + if (ret) + goto err_bcn; + } + + nla_nest_end(skb, bcn_nest); + + return 0; + +err_bcn: + nla_nest_cancel(skb, bcn_nest); + return ret; +} + +static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_BCN_ATTR_MAX + 1]; + int i; + int ret; + u8 value_byte; + u32 value_int; + + if (!tb[DCB_ATTR_BCN]) + return -EINVAL; + + if (!netdev->dcbnl_ops->setbcncfg || + !netdev->dcbnl_ops->setbcnrp) + return -EOPNOTSUPP; + + ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, + tb[DCB_ATTR_BCN], dcbnl_bcn_nest, + NULL); + if (ret) + return ret; + + for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { + if (data[i] == NULL) + continue; + value_byte = nla_get_u8(data[i]); + netdev->dcbnl_ops->setbcnrp(netdev, + data[i]->nla_type - DCB_BCN_ATTR_RP_0, value_byte); + } + + for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { + if (data[i] == NULL) + continue; + value_int = nla_get_u32(data[i]); + netdev->dcbnl_ops->setbcncfg(netdev, + i, value_int); + } + + return nla_put_u8(skb, DCB_ATTR_BCN, 0); +} + +static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, + int app_nested_type, int app_info_type, + int app_entry_type) +{ + struct dcb_peer_app_info info; + struct dcb_app *table = NULL; + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + u16 app_count; + int err; + + + /** + * retrieve the peer app configuration form the driver. If the driver + * handlers fail exit without doing anything + */ + err = ops->peer_getappinfo(netdev, &info, &app_count); + if (!err && app_count) { + table = kmalloc_objs(struct dcb_app, app_count); + if (!table) + return -ENOMEM; + + err = ops->peer_getapptable(netdev, table); + } + + if (!err) { + u16 i; + struct nlattr *app; + + /** + * build the message, from here on the only possible failure + * is due to the skb size + */ + err = -EMSGSIZE; + + app = nla_nest_start_noflag(skb, app_nested_type); + if (!app) + goto nla_put_failure; + + if (app_info_type && + nla_put(skb, app_info_type, sizeof(info), &info)) + goto nla_put_failure; + + for (i = 0; i < app_count; i++) { + if (nla_put(skb, app_entry_type, sizeof(struct dcb_app), + &table[i])) + goto nla_put_failure; + } + nla_nest_end(skb, app); + } + err = 0; + +nla_put_failure: + kfree(table); + return err; +} + +static int dcbnl_getapptrust(struct net_device *netdev, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + enum ieee_attrs_app type; + struct nlattr *apptrust; + int nselectors, err, i; + u8 *selectors; + + selectors = kzalloc(IEEE_8021QAZ_APP_SEL_MAX + 1, GFP_KERNEL); + if (!selectors) + return -ENOMEM; + + err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); + if (err) { + err = 0; + goto out; + } + + apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); + if (!apptrust) { + err = -EMSGSIZE; + goto out; + } + + for (i = 0; i < nselectors; i++) { + type = dcbnl_app_attr_type_get(selectors[i]); + err = nla_put_u8(skb, type, selectors[i]); + if (err) { + nla_nest_cancel(skb, apptrust); + goto out; + } + } + nla_nest_end(skb, apptrust); + +out: + kfree(selectors); + return err; +} + +/* Set or delete APP table or rewrite table entries. The APP struct is validated + * and the appropriate callback function is called. + */ +static int dcbnl_app_table_setdel(struct nlattr *attr, + struct net_device *netdev, + int (*setdel)(struct net_device *dev, + struct dcb_app *app)) +{ + struct dcb_app *app_data; + enum ieee_attrs_app type; + struct nlattr *attr_itr; + int rem, err; + + nla_for_each_nested(attr_itr, attr, rem) { + type = nla_type(attr_itr); + + if (!dcbnl_app_attr_type_validate(type)) + continue; + + if (nla_len(attr_itr) < sizeof(struct dcb_app)) + return -ERANGE; + + app_data = nla_data(attr_itr); + + if (!dcbnl_app_selector_validate(type, app_data->selector)) + return -EINVAL; + + err = setdel(netdev, app_data); + if (err) + return err; + } + + return 0; +} + +/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ +static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee, *app, *rewr; + struct dcb_app_type *itr; + int dcbx; + int err; + + if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) + return -EMSGSIZE; + + ieee = nla_nest_start_noflag(skb, DCB_ATTR_IEEE); + if (!ieee) + return -EMSGSIZE; + + if (ops->ieee_getets) { + struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); + err = ops->ieee_getets(netdev, &ets); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) + return -EMSGSIZE; + } + + if (ops->ieee_getmaxrate) { + struct ieee_maxrate maxrate; + memset(&maxrate, 0, sizeof(maxrate)); + err = ops->ieee_getmaxrate(netdev, &maxrate); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, + sizeof(maxrate), &maxrate); + if (err) + return -EMSGSIZE; + } + } + + if (ops->ieee_getqcn) { + struct ieee_qcn qcn; + + memset(&qcn, 0, sizeof(qcn)); + err = ops->ieee_getqcn(netdev, &qcn); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_QCN, + sizeof(qcn), &qcn); + if (err) + return -EMSGSIZE; + } + } + + if (ops->ieee_getqcnstats) { + struct ieee_qcn_stats qcn_stats; + + memset(&qcn_stats, 0, sizeof(qcn_stats)); + err = ops->ieee_getqcnstats(netdev, &qcn_stats); + if (!err) { + err = nla_put(skb, DCB_ATTR_IEEE_QCN_STATS, + sizeof(qcn_stats), &qcn_stats); + if (err) + return -EMSGSIZE; + } + } + + if (ops->ieee_getpfc) { + struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); + err = ops->ieee_getpfc(netdev, &pfc); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) + return -EMSGSIZE; + } + + if (ops->dcbnl_getbuffer) { + struct dcbnl_buffer buffer; + + memset(&buffer, 0, sizeof(buffer)); + err = ops->dcbnl_getbuffer(netdev, &buffer); + if (!err && + nla_put(skb, DCB_ATTR_DCB_BUFFER, sizeof(buffer), &buffer)) + return -EMSGSIZE; + } + + app = nla_nest_start_noflag(skb, DCB_ATTR_IEEE_APP_TABLE); + if (!app) + return -EMSGSIZE; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == netdev->ifindex) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); + if (err) { + spin_unlock_bh(&dcb_lock); + return -EMSGSIZE; + } + } + } + + if (netdev->dcbnl_ops->getdcbx) + dcbx = netdev->dcbnl_ops->getdcbx(netdev); + else + dcbx = -EOPNOTSUPP; + + spin_unlock_bh(&dcb_lock); + nla_nest_end(skb, app); + + rewr = nla_nest_start(skb, DCB_ATTR_DCB_REWR_TABLE); + if (!rewr) + return -EMSGSIZE; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == netdev->ifindex) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); + if (err) { + spin_unlock_bh(&dcb_lock); + nla_nest_cancel(skb, rewr); + return -EMSGSIZE; + } + } + } + + spin_unlock_bh(&dcb_lock); + nla_nest_end(skb, rewr); + + if (ops->dcbnl_getapptrust) { + err = dcbnl_getapptrust(netdev, skb); + if (err) + return err; + } + + /* get peer info if available */ + if (ops->ieee_peer_getets) { + struct ieee_ets ets; + memset(&ets, 0, sizeof(ets)); + err = ops->ieee_peer_getets(netdev, &ets); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) + return -EMSGSIZE; + } + + if (ops->ieee_peer_getpfc) { + struct ieee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); + err = ops->ieee_peer_getpfc(netdev, &pfc); + if (!err && + nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) + return -EMSGSIZE; + } + + if (ops->peer_getappinfo && ops->peer_getapptable) { + err = dcbnl_build_peer_app(netdev, skb, + DCB_ATTR_IEEE_PEER_APP, + DCB_ATTR_IEEE_APP_UNSPEC, + DCB_ATTR_IEEE_APP); + if (err) + return -EMSGSIZE; + } + + nla_nest_end(skb, ieee); + if (dcbx >= 0) { + err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); + if (err) + return -EMSGSIZE; + } + + return 0; +} + +static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, + int dir) +{ + u8 pgid, up_map, prio, tc_pct; + const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; + int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG; + struct nlattr *pg = nla_nest_start_noflag(skb, i); + + if (!pg) + return -EMSGSIZE; + + for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { + struct nlattr *tc_nest = nla_nest_start_noflag(skb, i); + + if (!tc_nest) + return -EMSGSIZE; + + pgid = DCB_ATTR_VALUE_UNDEFINED; + prio = DCB_ATTR_VALUE_UNDEFINED; + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + up_map = DCB_ATTR_VALUE_UNDEFINED; + + if (!dir) + ops->getpgtccfgrx(dev, i - DCB_PG_ATTR_TC_0, + &prio, &pgid, &tc_pct, &up_map); + else + ops->getpgtccfgtx(dev, i - DCB_PG_ATTR_TC_0, + &prio, &pgid, &tc_pct, &up_map); + + if (nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) || + nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct)) + return -EMSGSIZE; + nla_nest_end(skb, tc_nest); + } + + for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + + if (!dir) + ops->getpgbwgcfgrx(dev, i - DCB_PG_ATTR_BW_ID_0, + &tc_pct); + else + ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, + &tc_pct); + if (nla_put_u8(skb, i, tc_pct)) + return -EMSGSIZE; + } + nla_nest_end(skb, pg); + return 0; +} + +static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) +{ + struct nlattr *cee, *app; + struct dcb_app_type *itr; + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + int dcbx, i, err = -EMSGSIZE; + u8 value; + + if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) + goto nla_put_failure; + cee = nla_nest_start_noflag(skb, DCB_ATTR_CEE); + if (!cee) + goto nla_put_failure; + + /* local pg */ + if (ops->getpgtccfgtx && ops->getpgbwgcfgtx) { + err = dcbnl_cee_pg_fill(skb, netdev, 1); + if (err) + goto nla_put_failure; + } + + if (ops->getpgtccfgrx && ops->getpgbwgcfgrx) { + err = dcbnl_cee_pg_fill(skb, netdev, 0); + if (err) + goto nla_put_failure; + } + + /* local pfc */ + if (ops->getpfccfg) { + struct nlattr *pfc_nest = nla_nest_start_noflag(skb, + DCB_ATTR_CEE_PFC); + + if (!pfc_nest) + goto nla_put_failure; + + for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { + ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); + if (nla_put_u8(skb, i, value)) + goto nla_put_failure; + } + nla_nest_end(skb, pfc_nest); + } + + /* local app */ + spin_lock_bh(&dcb_lock); + app = nla_nest_start_noflag(skb, DCB_ATTR_CEE_APP_TABLE); + if (!app) + goto dcb_unlock; + + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == netdev->ifindex) { + struct nlattr *app_nest = nla_nest_start_noflag(skb, + DCB_ATTR_APP); + if (!app_nest) + goto dcb_unlock; + + err = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, + itr->app.selector); + if (err) + goto dcb_unlock; + + err = nla_put_u16(skb, DCB_APP_ATTR_ID, + itr->app.protocol); + if (err) + goto dcb_unlock; + + err = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, + itr->app.priority); + if (err) + goto dcb_unlock; + + nla_nest_end(skb, app_nest); + } + } + nla_nest_end(skb, app); + + if (netdev->dcbnl_ops->getdcbx) + dcbx = netdev->dcbnl_ops->getdcbx(netdev); + else + dcbx = -EOPNOTSUPP; + + spin_unlock_bh(&dcb_lock); + + /* features flags */ + if (ops->getfeatcfg) { + struct nlattr *feat = nla_nest_start_noflag(skb, + DCB_ATTR_CEE_FEAT); + if (!feat) + goto nla_put_failure; + + for (i = DCB_FEATCFG_ATTR_ALL + 1; i <= DCB_FEATCFG_ATTR_MAX; + i++) + if (!ops->getfeatcfg(netdev, i, &value) && + nla_put_u8(skb, i, value)) + goto nla_put_failure; + + nla_nest_end(skb, feat); + } + + /* peer info if available */ + if (ops->cee_peer_getpg) { + struct cee_pg pg; + memset(&pg, 0, sizeof(pg)); + err = ops->cee_peer_getpg(netdev, &pg); + if (!err && + nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) + goto nla_put_failure; + } + + if (ops->cee_peer_getpfc) { + struct cee_pfc pfc; + memset(&pfc, 0, sizeof(pfc)); + err = ops->cee_peer_getpfc(netdev, &pfc); + if (!err && + nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) + goto nla_put_failure; + } + + if (ops->peer_getappinfo && ops->peer_getapptable) { + err = dcbnl_build_peer_app(netdev, skb, + DCB_ATTR_CEE_PEER_APP_TABLE, + DCB_ATTR_CEE_PEER_APP_INFO, + DCB_ATTR_CEE_PEER_APP); + if (err) + goto nla_put_failure; + } + nla_nest_end(skb, cee); + + /* DCBX state */ + if (dcbx >= 0) { + err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); + if (err) + goto nla_put_failure; + } + return 0; + +dcb_unlock: + spin_unlock_bh(&dcb_lock); +nla_put_failure: + err = -EMSGSIZE; + return err; +} + +static int dcbnl_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 portid, int dcbx_ver) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + struct nlmsghdr *nlh; + const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; + int err; + + if (!ops) + return -EOPNOTSUPP; + + skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); + if (!skb) + return -ENOMEM; + + if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) + err = dcbnl_ieee_fill(skb, dev); + else + err = dcbnl_cee_fill(skb, dev); + + if (err < 0) { + /* Report error to broadcast listeners */ + nlmsg_free(skb); + rtnl_set_sk_err(net, RTNLGRP_DCB, err); + } else { + /* End nlmsg and notify broadcast listeners */ + nlmsg_end(skb, nlh); + rtnl_notify(skb, net, 0, RTNLGRP_DCB, NULL, GFP_KERNEL); + } + + return err; +} + +int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 portid) +{ + return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_IEEE); +} +EXPORT_SYMBOL(dcbnl_ieee_notify); + +int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 portid) +{ + return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_CEE); +} +EXPORT_SYMBOL(dcbnl_cee_notify); + +/* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb SET commands. + * If any requested operation can not be completed + * the entire msg is aborted and error value is returned. + * No attempt is made to reconcile the case where only part of the + * cmd can be completed. + */ +static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int prio; + int err; + + if (!ops) + return -EOPNOTSUPP; + + if (!tb[DCB_ATTR_IEEE]) + return -EINVAL; + + err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, + tb[DCB_ATTR_IEEE], + dcbnl_ieee_policy, NULL); + if (err) + return err; + + if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { + struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); + err = ops->ieee_setets(netdev, ets); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_MAXRATE] && ops->ieee_setmaxrate) { + struct ieee_maxrate *maxrate = + nla_data(ieee[DCB_ATTR_IEEE_MAXRATE]); + err = ops->ieee_setmaxrate(netdev, maxrate); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_QCN] && ops->ieee_setqcn) { + struct ieee_qcn *qcn = + nla_data(ieee[DCB_ATTR_IEEE_QCN]); + + err = ops->ieee_setqcn(netdev, qcn); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { + struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); + err = ops->ieee_setpfc(netdev, pfc); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_DCB_BUFFER] && ops->dcbnl_setbuffer) { + struct dcbnl_buffer *buffer = + nla_data(ieee[DCB_ATTR_DCB_BUFFER]); + + for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { + if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { + err = -EINVAL; + goto err; + } + } + + err = ops->dcbnl_setbuffer(netdev, buffer); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_setrewr ?: dcb_setrewr); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], + netdev, ops->ieee_setapp ?: + dcb_ieee_setapp); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + struct nlattr *attr; + int nselectors = 0; + int rem; + + if (!ops->dcbnl_setapptrust) { + err = -EOPNOTSUPP; + goto err; + } + + nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], + rem) { + enum ieee_attrs_app type = nla_type(attr); + u8 selector; + int i; + + if (!dcbnl_app_attr_type_validate(type) || + nla_len(attr) != 1 || + nselectors >= sizeof(selectors)) { + err = -EINVAL; + goto err; + } + + selector = nla_get_u8(attr); + + if (!dcbnl_app_selector_validate(type, selector)) { + err = -EINVAL; + goto err; + } + + /* Duplicate selector ? */ + for (i = 0; i < nselectors; i++) { + if (selectors[i] == selector) { + err = -EINVAL; + goto err; + } + } + + selectors[nselectors++] = selector; + } + + err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); + if (err) + goto err; + } + +err: + err = nla_put_u8(skb, DCB_ATTR_IEEE, err); + dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); + return err; +} + +static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + + if (!ops) + return -EOPNOTSUPP; + + return dcbnl_ieee_fill(skb, netdev); +} + +static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int err; + + if (!ops) + return -EOPNOTSUPP; + + if (!tb[DCB_ATTR_IEEE]) + return -EINVAL; + + err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, + tb[DCB_ATTR_IEEE], + dcbnl_ieee_policy, NULL); + if (err) + return err; + + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], + netdev, ops->ieee_delapp ?: + dcb_ieee_delapp); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { + err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], + netdev, + ops->dcbnl_delrewr ?: dcb_delrewr); + if (err) + goto err; + } + +err: + err = nla_put_u8(skb, DCB_ATTR_IEEE, err); + dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); + return err; +} + + +/* DCBX configuration */ +static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + if (!netdev->dcbnl_ops->getdcbx) + return -EOPNOTSUPP; + + return nla_put_u8(skb, DCB_ATTR_DCBX, + netdev->dcbnl_ops->getdcbx(netdev)); +} + +static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + u8 value; + + if (!netdev->dcbnl_ops->setdcbx) + return -EOPNOTSUPP; + + if (!tb[DCB_ATTR_DCBX]) + return -EINVAL; + + value = nla_get_u8(tb[DCB_ATTR_DCBX]); + + return nla_put_u8(skb, DCB_ATTR_DCBX, + netdev->dcbnl_ops->setdcbx(netdev, value)); +} + +static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest; + u8 value; + int ret, i; + int getall = 0; + + if (!netdev->dcbnl_ops->getfeatcfg) + return -EOPNOTSUPP; + + if (!tb[DCB_ATTR_FEATCFG]) + return -EINVAL; + + ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, + tb[DCB_ATTR_FEATCFG], + dcbnl_featcfg_nest, NULL); + if (ret) + return ret; + + nest = nla_nest_start_noflag(skb, DCB_ATTR_FEATCFG); + if (!nest) + return -EMSGSIZE; + + if (data[DCB_FEATCFG_ATTR_ALL]) + getall = 1; + + for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { + if (!getall && !data[i]) + continue; + + ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value); + if (!ret) + ret = nla_put_u8(skb, i, value); + + if (ret) { + nla_nest_cancel(skb, nest); + goto nla_put_failure; + } + } + nla_nest_end(skb, nest); + +nla_put_failure: + return ret; +} + +static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1]; + int ret, i; + u8 value; + + if (!netdev->dcbnl_ops->setfeatcfg) + return -ENOTSUPP; + + if (!tb[DCB_ATTR_FEATCFG]) + return -EINVAL; + + ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, + tb[DCB_ATTR_FEATCFG], + dcbnl_featcfg_nest, NULL); + + if (ret) + goto err; + + for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { + if (data[i] == NULL) + continue; + + value = nla_get_u8(data[i]); + + ret = netdev->dcbnl_ops->setfeatcfg(netdev, i, value); + + if (ret) + goto err; + } +err: + ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret); + + return ret; +} + +/* Handle CEE DCBX GET commands. */ +static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh, + u32 seq, struct nlattr **tb, struct sk_buff *skb) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + + if (!ops) + return -EOPNOTSUPP; + + return dcbnl_cee_fill(skb, netdev); +} + +struct reply_func { + /* reply netlink message type */ + int type; + + /* function to fill message contents */ + int (*cb)(struct net_device *, struct nlmsghdr *, u32, + struct nlattr **, struct sk_buff *); +}; + +static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = { + [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate }, + [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate }, + [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg }, + [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg }, + [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr }, + [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap }, + [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs }, + [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs }, + [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate }, + [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate }, + [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp }, + [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp }, + [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg }, + [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg }, + [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg }, + [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg }, + [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall }, + [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg }, + [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg }, + [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get }, + [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set }, + [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del }, + [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx }, + [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx }, + [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg }, + [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg }, + [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get }, +}; + +static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct net_device *netdev; + struct dcbmsg *dcb = nlmsg_data(nlh); + struct nlattr *tb[DCB_ATTR_MAX + 1]; + u32 portid = NETLINK_CB(skb).portid; + int ret = -EINVAL; + struct sk_buff *reply_skb; + struct nlmsghdr *reply_nlh = NULL; + const struct reply_func *fn; + + if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + ret = nlmsg_parse_deprecated(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, + dcbnl_rtnl_policy, extack); + if (ret < 0) + return ret; + + if (dcb->cmd > DCB_CMD_MAX) + return -EINVAL; + + /* check if a reply function has been defined for the command */ + fn = &reply_funcs[dcb->cmd]; + if (!fn->cb) + return -EOPNOTSUPP; + if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN)) + return -EPERM; + + if (!tb[DCB_ATTR_IFNAME]) + return -EINVAL; + + netdev = __dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); + if (!netdev) + return -ENODEV; + + if (!netdev->dcbnl_ops) + return -EOPNOTSUPP; + + reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, + nlh->nlmsg_flags, &reply_nlh); + if (!reply_skb) + return -ENOMEM; + + ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); + if (ret < 0) { + nlmsg_free(reply_skb); + goto out; + } + + nlmsg_end(reply_skb, reply_nlh); + + ret = rtnl_unicast(reply_skb, net, portid); +out: + return ret; +} + +static struct dcb_app_type *dcb_rewr_lookup(const struct dcb_app *app, + int ifindex, int proto) +{ + struct dcb_app_type *itr; + + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->app.selector == app->selector && + itr->app.priority == app->priority && + itr->ifindex == ifindex && + ((proto == -1) || itr->app.protocol == proto)) + return itr; + } + + return NULL; +} + +static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, + int ifindex, int prio) +{ + struct dcb_app_type *itr; + + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == app->selector && + itr->app.protocol == app->protocol && + itr->ifindex == ifindex && + ((prio == -1) || itr->app.priority == prio)) + return itr; + } + + return NULL; +} + +static int dcb_app_add(struct list_head *list, const struct dcb_app *app, + int ifindex) +{ + struct dcb_app_type *entry; + + entry = kmalloc_obj(*entry, GFP_ATOMIC); + if (!entry) + return -ENOMEM; + + memcpy(&entry->app, app, sizeof(*app)); + entry->ifindex = ifindex; + list_add(&entry->list, list); + + return 0; +} + +/** + * dcb_getapp - retrieve the DCBX application user priority + * @dev: network interface + * @app: application to get user priority of + * + * On success returns a non-zero 802.1p user priority bitmap + * otherwise returns 0 as the invalid user priority bitmap to + * indicate an error. + */ +u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u8 prio = 0; + + spin_lock_bh(&dcb_lock); + itr = dcb_app_lookup(app, dev->ifindex, -1); + if (itr) + prio = itr->app.priority; + spin_unlock_bh(&dcb_lock); + + return prio; +} +EXPORT_SYMBOL(dcb_getapp); + +/** + * dcb_setapp - add CEE dcb application data to app list + * @dev: network interface + * @new: application data to add + * + * Priority 0 is an invalid priority in CEE spec. This routine + * removes applications from the app list if the priority is + * set to zero. Priority is expected to be 8-bit 802.1p user priority bitmap + */ +int dcb_setapp(struct net_device *dev, struct dcb_app *new) +{ + struct dcb_app_type *itr; + struct dcb_app_type event; + int err = 0; + + event.ifindex = dev->ifindex; + memcpy(&event.app, new, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); + + spin_lock_bh(&dcb_lock); + /* Search for existing match and replace */ + itr = dcb_app_lookup(new, dev->ifindex, -1); + if (itr) { + if (new->priority) + itr->app.priority = new->priority; + else { + list_del(&itr->list); + kfree(itr); + } + goto out; + } + /* App type does not exist add new application type */ + if (new->priority) + err = dcb_app_add(&dcb_app_list, new, dev->ifindex); +out: + spin_unlock_bh(&dcb_lock); + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; +} +EXPORT_SYMBOL(dcb_setapp); + +/** + * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority + * @dev: network interface + * @app: where to store the retrieve application data + * + * Helper routine which on success returns a non-zero 802.1Qaz user + * priority bitmap otherwise returns 0 to indicate the dcb_app was + * not found in APP list. + */ +u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u8 prio = 0; + + spin_lock_bh(&dcb_lock); + itr = dcb_app_lookup(app, dev->ifindex, -1); + if (itr) + prio |= 1 << itr->app.priority; + spin_unlock_bh(&dcb_lock); + + return prio; +} +EXPORT_SYMBOL(dcb_ieee_getapp_mask); + +/* Get protocol value from rewrite entry. */ +u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u16 proto = 0; + + spin_lock_bh(&dcb_lock); + itr = dcb_rewr_lookup(app, dev->ifindex, -1); + if (itr) + proto = itr->app.protocol; + spin_unlock_bh(&dcb_lock); + + return proto; +} +EXPORT_SYMBOL(dcb_getrewr); + + /* Add rewrite entry to the rewrite list. */ +int dcb_setrewr(struct net_device *dev, struct dcb_app *new) +{ + int err; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and abort if found. */ + if (dcb_rewr_lookup(new, dev->ifindex, new->protocol)) { + err = -EEXIST; + goto out; + } + + err = dcb_app_add(&dcb_rewr_list, new, dev->ifindex); +out: + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_setrewr); + +/* Delete rewrite entry from the rewrite list. */ +int dcb_delrewr(struct net_device *dev, struct dcb_app *del) +{ + struct dcb_app_type *itr; + int err = -ENOENT; + + spin_lock_bh(&dcb_lock); + /* Search for existing match and remove it. */ + itr = dcb_rewr_lookup(del, dev->ifindex, del->protocol); + if (itr) { + list_del(&itr->list); + kfree(itr); + err = 0; + } + + spin_unlock_bh(&dcb_lock); + + return err; +} +EXPORT_SYMBOL(dcb_delrewr); + +/** + * dcb_ieee_setapp - add IEEE dcb application data to app list + * @dev: network interface + * @new: application data to add + * + * This adds Application data to the list. Multiple application + * entries may exists for the same selector and protocol as long + * as the priorities are different. Priority is expected to be a + * 3-bit unsigned integer + */ +int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) +{ + struct dcb_app_type event; + int err = 0; + + event.ifindex = dev->ifindex; + memcpy(&event.app, new, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); + + spin_lock_bh(&dcb_lock); + /* Search for existing match and abort if found */ + if (dcb_app_lookup(new, dev->ifindex, new->priority)) { + err = -EEXIST; + goto out; + } + + err = dcb_app_add(&dcb_app_list, new, dev->ifindex); +out: + spin_unlock_bh(&dcb_lock); + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; +} +EXPORT_SYMBOL(dcb_ieee_setapp); + +/** + * dcb_ieee_delapp - delete IEEE dcb application data from list + * @dev: network interface + * @del: application data to delete + * + * This removes a matching APP data from the APP list + */ +int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) +{ + struct dcb_app_type *itr; + struct dcb_app_type event; + int err = -ENOENT; + + event.ifindex = dev->ifindex; + memcpy(&event.app, del, sizeof(event.app)); + if (dev->dcbnl_ops->getdcbx) + event.dcbx = dev->dcbnl_ops->getdcbx(dev); + + spin_lock_bh(&dcb_lock); + /* Search for existing match and remove it. */ + if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) { + list_del(&itr->list); + kfree(itr); + err = 0; + } + + spin_unlock_bh(&dcb_lock); + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; +} +EXPORT_SYMBOL(dcb_ieee_delapp); + +/* dcb_getrewr_prio_pcp_mask_map - For a given device, find mapping from + * priorities to the PCP and DEI values assigned to that priority. + */ +void dcb_getrewr_prio_pcp_mask_map(const struct net_device *dev, + struct dcb_rewr_prio_pcp_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == DCB_APP_SEL_PCP && + itr->app.protocol < 16 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1 << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_getrewr_prio_pcp_mask_map); + +/* dcb_getrewr_prio_dscp_mask_map - For a given device, find mapping from + * priorities to the DSCP values assigned to that priority. + */ +void dcb_getrewr_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_rewr_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1ULL << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_getrewr_prio_dscp_mask_map); + +/* + * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from + * priorities to the DSCP values assigned to that priority. Initialize p_map + * such that each map element holds a bit mask of DSCP values configured for + * that priority by APP entries. + */ +void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, + struct dcb_ieee_app_prio_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 prio; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) { + prio = itr->app.priority; + p_map->map[prio] |= 1ULL << itr->app.protocol; + } + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map); + +/* + * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from + * DSCP values to the priorities assigned to that DSCP value. Initialize p_map + * such that each map element holds a bit mask of priorities configured for a + * given DSCP value by APP entries. + */ +void +dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, + struct dcb_ieee_app_dscp_map *p_map) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + + memset(p_map->map, 0, sizeof(p_map->map)); + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && + itr->app.protocol < 64 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) + p_map->map[itr->app.protocol] |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); +} +EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); + +/* + * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet + * type, with valid PID values >= 1536. A special meaning is then assigned to + * protocol value of 0: "default priority. For use when priority is not + * otherwise specified". + * + * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries + * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default + * priorities set by these entries. + */ +u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) +{ + int ifindex = dev->ifindex; + struct dcb_app_type *itr; + u8 mask = 0; + + spin_lock_bh(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->ifindex == ifindex && + itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + itr->app.protocol == 0 && + itr->app.priority < IEEE_8021QAZ_MAX_TCS) + mask |= 1 << itr->app.priority; + } + spin_unlock_bh(&dcb_lock); + + return mask; +} +EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); + +static void dcbnl_flush_dev(struct net_device *dev) +{ + struct dcb_app_type *itr, *tmp; + + spin_lock_bh(&dcb_lock); + + list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) { + if (itr->ifindex == dev->ifindex) { + list_del(&itr->list); + kfree(itr); + } + } + + spin_unlock_bh(&dcb_lock); +} + +static int dcbnl_netdevice_event(struct notifier_block *nb, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + switch (event) { + case NETDEV_UNREGISTER: + if (!dev->dcbnl_ops) + return NOTIFY_DONE; + + dcbnl_flush_dev(dev); + + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static struct notifier_block dcbnl_nb __read_mostly = { + .notifier_call = dcbnl_netdevice_event, +}; + +static const struct rtnl_msg_handler dcbnl_rtnl_msg_handlers[] __initconst = { + {.msgtype = RTM_GETDCB, .doit = dcb_doit}, + {.msgtype = RTM_SETDCB, .doit = dcb_doit}, +}; + +static int __init dcbnl_init(void) +{ + int err; + + err = register_netdevice_notifier(&dcbnl_nb); + if (err) + return err; + + rtnl_register_many(dcbnl_rtnl_msg_handlers); + + return 0; +} +device_initcall(dcbnl_init); -- cgit v1.3.1