From c36ba6603a1154ac617d023bbcc062a12afb258b Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 2 Sep 2015 13:58:36 -0700 Subject: net: Allow user to get table id from route lookup rt_fill_info which is called for 'route get' requests hardcodes the table id as RT_TABLE_MAIN which is not correct when multiple tables are used. Use the newly added table id in the rtable to send back the correct table similar to what is done for IPv6. To maintain current ABI a new request flag, RTM_F_LOOKUP_TABLE, is added to indicate the actual table is wanted versus the hardcoded response. Signed-off-by: David Ahern Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 702024769c74..06625b401422 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -270,6 +270,7 @@ enum rt_scope_t { #define RTM_F_CLONED 0x200 /* This route is cloned */ #define RTM_F_EQUALIZE 0x400 /* Multipath equalizer: NI */ #define RTM_F_PREFIX 0x800 /* Prefix addresses */ +#define RTM_F_LOOKUP_TABLE 0x1000 /* set rtm_table to FIB lookup result */ /* Reserved table identifiers */ -- cgit v1.2.3 From d5566fd72ec1924958fcfd48b65c022c8f7eae64 Mon Sep 17 00:00:00 2001 From: Sowmini Varadhan Date: Fri, 11 Sep 2015 16:48:48 -0400 Subject: rtnetlink: RTEXT_FILTER_SKIP_STATS support to avoid dumping inet/inet6 stats Many commonly used functions like getifaddrs() invoke RTM_GETLINK to dump the interface information, and do not need the the AF_INET6 statististics that are always returned by default from rtnl_fill_ifinfo(). Computing the statistics can be an expensive operation that impacts scaling, so it is desirable to avoid this if the information is not needed. This patch adds a the RTEXT_FILTER_SKIP_STATS extended info flag that can be passed with netlink_request() to avoid statistics computation for the ifinfo path. Signed-off-by: Sowmini Varadhan Signed-off-by: David S. Miller --- include/net/rtnetlink.h | 3 ++- include/uapi/linux/rtnetlink.h | 1 + net/core/rtnetlink.c | 2 +- net/ipv4/devinet.c | 3 ++- net/ipv6/addrconf.c | 13 +++++++++---- 5 files changed, 15 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h index 18fdb98185ab..aff6ceb891a9 100644 --- a/include/net/rtnetlink.h +++ b/include/net/rtnetlink.h @@ -122,7 +122,8 @@ struct rtnl_af_ops { int family; int (*fill_link_af)(struct sk_buff *skb, - const struct net_device *dev); + const struct net_device *dev, + u32 ext_filter_mask); size_t (*get_link_af_size)(const struct net_device *dev); int (*validate_link_af)(const struct net_device *dev, diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 06625b401422..4db0b3ccb497 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -667,6 +667,7 @@ struct tcamsg { #define RTEXT_FILTER_VF (1 << 0) #define RTEXT_FILTER_BRVLAN (1 << 1) #define RTEXT_FILTER_BRVLAN_COMPRESSED (1 << 2) +#define RTEXT_FILTER_SKIP_STATS (1 << 3) /* End of information exported to user level */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a466821d1441..e5452296ec2f 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1272,7 +1272,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (!(af = nla_nest_start(skb, af_ops->family))) goto nla_put_failure; - err = af_ops->fill_link_af(skb, dev); + err = af_ops->fill_link_af(skb, dev, ext_filter_mask); /* * Caller may return ENODATA to indicate that there diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 2d9cb1748f81..735008472844 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1654,7 +1654,8 @@ static size_t inet_get_link_af_size(const struct net_device *dev) return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ } -static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev, + u32 ext_filter_mask) { struct in_device *in_dev = rcu_dereference_rtnl(dev->ip_ptr); struct nlattr *nla; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 030fefdc9aed..75d3dde32c69 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4729,7 +4729,8 @@ static void snmp6_fill_stats(u64 *stats, struct inet6_dev *idev, int attrtype, } } -static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) +static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev, + u32 ext_filter_mask) { struct nlattr *nla; struct ifla_cacheinfo ci; @@ -4749,6 +4750,9 @@ static int inet6_fill_ifla6_attrs(struct sk_buff *skb, struct inet6_dev *idev) /* XXX - MC not implemented */ + if (ext_filter_mask & RTEXT_FILTER_SKIP_STATS) + return 0; + nla = nla_reserve(skb, IFLA_INET6_STATS, IPSTATS_MIB_MAX * sizeof(u64)); if (!nla) goto nla_put_failure; @@ -4784,14 +4788,15 @@ static size_t inet6_get_link_af_size(const struct net_device *dev) return inet6_ifla6_size(); } -static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +static int inet6_fill_link_af(struct sk_buff *skb, const struct net_device *dev, + u32 ext_filter_mask) { struct inet6_dev *idev = __in6_dev_get(dev); if (!idev) return -ENODATA; - if (inet6_fill_ifla6_attrs(skb, idev) < 0) + if (inet6_fill_ifla6_attrs(skb, idev, ext_filter_mask) < 0) return -EMSGSIZE; return 0; @@ -4946,7 +4951,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev, if (!protoinfo) goto nla_put_failure; - if (inet6_fill_ifla6_attrs(skb, idev) < 0) + if (inet6_fill_ifla6_attrs(skb, idev, 0) < 0) goto nla_put_failure; nla_nest_end(skb, protoinfo); -- cgit v1.2.3 From b84ee0d7f375ed7840c7c110d46eac24cf94b2a2 Mon Sep 17 00:00:00 2001 From: Stephen Rothwell Date: Wed, 16 Sep 2015 11:10:16 +1000 Subject: cdc: add header guards Signed-off-by: Stephen Rothwell Signed-off-by: David S. Miller --- include/linux/usb/cdc.h | 4 ++++ include/uapi/linux/usb/cdc.h | 6 +++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h index 959d0c838113..b5706f94ee9e 100644 --- a/include/linux/usb/cdc.h +++ b/include/linux/usb/cdc.h @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public License * version 2 as published by the Free Software Foundation. */ +#ifndef __LINUX_USB_CDC_H +#define __LINUX_USB_CDC_H #include @@ -45,3 +47,5 @@ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, struct usb_interface *intf, u8 *buffer, int buflen); + +#endif /* __LINUX_USB_CDC_H */ diff --git a/include/uapi/linux/usb/cdc.h b/include/uapi/linux/usb/cdc.h index b6a9cdd6e096..e2bc417b243b 100644 --- a/include/uapi/linux/usb/cdc.h +++ b/include/uapi/linux/usb/cdc.h @@ -6,8 +6,8 @@ * firmware based USB peripherals. */ -#ifndef __LINUX_USB_CDC_H -#define __LINUX_USB_CDC_H +#ifndef __UAPI_LINUX_USB_CDC_H +#define __UAPI_LINUX_USB_CDC_H #include @@ -444,4 +444,4 @@ struct usb_cdc_ncm_ndp_input_size { #define USB_CDC_NCM_CRC_NOT_APPENDED 0x00 #define USB_CDC_NCM_CRC_APPENDED 0x01 -#endif /* __LINUX_USB_CDC_H */ +#endif /* __UAPI_LINUX_USB_CDC_H */ -- cgit v1.2.3 From 045efa82ff563cd4e656ca1c2e354fa5bf6bbda4 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Tue, 15 Sep 2015 23:05:42 -0700 Subject: cls_bpf: introduce integrated actions Often cls_bpf classifier is used with single action drop attached. Optimize this use case and let cls_bpf return both classid and action. For backwards compatibility reasons enable this feature under TCA_BPF_FLAG_ACT_DIRECT flag. Then more interesting programs like the following are easier to write: int cls_bpf_prog(struct __sk_buff *skb) { /* classify arp, ip, ipv6 into different traffic classes * and drop all other packets */ switch (skb->protocol) { case htons(ETH_P_ARP): skb->tc_classid = 1; break; case htons(ETH_P_IP): skb->tc_classid = 2; break; case htons(ETH_P_IPV6): skb->tc_classid = 3; break; default: return TC_ACT_SHOT; } return TC_ACT_OK; } Joint work with Daniel Borkmann. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/net/sch_generic.h | 2 +- include/uapi/linux/bpf.h | 1 + include/uapi/linux/pkt_cls.h | 3 +++ net/core/filter.c | 14 +++++++++++ net/sched/cls_bpf.c | 60 ++++++++++++++++++++++++++++++++++++-------- 5 files changed, 68 insertions(+), 12 deletions(-) (limited to 'include/uapi') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 444faa89a55f..da61febb9091 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -251,7 +251,7 @@ struct tcf_proto { struct qdisc_skb_cb { unsigned int pkt_len; u16 slave_dev_queue_mapping; - u16 _pad; + u16 tc_classid; #define QDISC_CB_PRIV_LEN 20 unsigned char data[QDISC_CB_PRIV_LEN]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 92a48e2d5461..2fbd1c71fa3b 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -293,6 +293,7 @@ struct __sk_buff { __u32 tc_index; __u32 cb[5]; __u32 hash; + __u32 tc_classid; }; struct bpf_tunnel_key { diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 4f0d1bc3647d..0a262a83f9d4 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -373,6 +373,8 @@ enum { /* BPF classifier */ +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + enum { TCA_BPF_UNSPEC, TCA_BPF_ACT, @@ -382,6 +384,7 @@ enum { TCA_BPF_OPS, TCA_BPF_FD, TCA_BPF_NAME, + TCA_BPF_FLAGS, __TCA_BPF_MAX, }; diff --git a/net/core/filter.c b/net/core/filter.c index 13079f03902e..971d6ba89758 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1632,6 +1632,9 @@ static bool __is_valid_access(int off, int size, enum bpf_access_type type) static bool sk_filter_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, cb[0]) ... @@ -1648,6 +1651,9 @@ static bool sk_filter_is_valid_access(int off, int size, static bool tc_cls_act_is_valid_access(int off, int size, enum bpf_access_type type) { + if (off == offsetof(struct __sk_buff, tc_classid)) + return type == BPF_WRITE ? true : false; + if (type == BPF_WRITE) { switch (off) { case offsetof(struct __sk_buff, mark): @@ -1760,6 +1766,14 @@ static u32 bpf_net_convert_ctx_access(enum bpf_access_type type, int dst_reg, *insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, ctx_off); break; + case offsetof(struct __sk_buff, tc_classid): + ctx_off -= offsetof(struct __sk_buff, tc_classid); + ctx_off += offsetof(struct sk_buff, cb); + ctx_off += offsetof(struct qdisc_skb_cb, tc_classid); + WARN_ON(type != BPF_WRITE); + *insn++ = BPF_STX_MEM(BPF_H, dst_reg, src_reg, ctx_off); + break; + case offsetof(struct __sk_buff, tc_index): #ifdef CONFIG_NET_SCHED BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tc_index) != 2); diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index e5168f8b9640..77b0ef148256 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -38,6 +38,7 @@ struct cls_bpf_prog { struct bpf_prog *filter; struct list_head link; struct tcf_result res; + bool exts_integrated; struct tcf_exts exts; u32 handle; union { @@ -52,6 +53,7 @@ struct cls_bpf_prog { static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { [TCA_BPF_CLASSID] = { .type = NLA_U32 }, + [TCA_BPF_FLAGS] = { .type = NLA_U32 }, [TCA_BPF_FD] = { .type = NLA_U32 }, [TCA_BPF_NAME] = { .type = NLA_NUL_STRING, .len = CLS_BPF_NAME_LEN }, [TCA_BPF_OPS_LEN] = { .type = NLA_U16 }, @@ -59,6 +61,22 @@ static const struct nla_policy bpf_policy[TCA_BPF_MAX + 1] = { .len = sizeof(struct sock_filter) * BPF_MAXINSNS }, }; +static int cls_bpf_exec_opcode(int code) +{ + switch (code) { + case TC_ACT_OK: + case TC_ACT_RECLASSIFY: + case TC_ACT_SHOT: + case TC_ACT_PIPE: + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + case TC_ACT_UNSPEC: + return code; + default: + return TC_ACT_UNSPEC; + } +} + static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { @@ -79,6 +97,8 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, list_for_each_entry_rcu(prog, &head->plist, link) { int filter_res; + qdisc_skb_cb(skb)->tc_classid = prog->res.classid; + if (at_ingress) { /* It is safe to push/pull even if skb_shared() */ __skb_push(skb, skb->mac_len); @@ -88,6 +108,16 @@ static int cls_bpf_classify(struct sk_buff *skb, const struct tcf_proto *tp, filter_res = BPF_PROG_RUN(prog->filter, skb); } + if (prog->exts_integrated) { + res->class = prog->res.class; + res->classid = qdisc_skb_cb(skb)->tc_classid; + + ret = cls_bpf_exec_opcode(filter_res); + if (ret == TC_ACT_UNSPEC) + continue; + break; + } + if (filter_res == 0) continue; @@ -195,8 +225,7 @@ static unsigned long cls_bpf_get(struct tcf_proto *tp, u32 handle) return ret; } -static int cls_bpf_prog_from_ops(struct nlattr **tb, - struct cls_bpf_prog *prog, u32 classid) +static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) { struct sock_filter *bpf_ops; struct sock_fprog_kern fprog_tmp; @@ -230,15 +259,13 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, prog->bpf_ops = bpf_ops; prog->bpf_num_ops = bpf_num_ops; prog->bpf_name = NULL; - prog->filter = fp; - prog->res.classid = classid; return 0; } -static int cls_bpf_prog_from_efd(struct nlattr **tb, - struct cls_bpf_prog *prog, u32 classid) +static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, + const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -268,9 +295,7 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, prog->bpf_ops = NULL; prog->bpf_fd = bpf_fd; prog->bpf_name = name; - prog->filter = fp; - prog->res.classid = classid; return 0; } @@ -280,8 +305,8 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, unsigned long base, struct nlattr **tb, struct nlattr *est, bool ovr) { + bool is_bpf, is_ebpf, have_exts = false; struct tcf_exts exts; - bool is_bpf, is_ebpf; u32 classid; int ret; @@ -298,9 +323,22 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, return ret; classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + tcf_exts_destroy(&exts); + return -EINVAL; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + + prog->res.classid = classid; + prog->exts_integrated = have_exts; - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog, classid) : - cls_bpf_prog_from_efd(tb, prog, classid); + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog, tp); if (ret < 0) { tcf_exts_destroy(&exts); return ret; -- cgit v1.2.3 From 27b29f63058d26c6c1742f1993338280d5a41dc6 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 15 Sep 2015 23:05:43 -0700 Subject: bpf: add bpf_redirect() helper Existing bpf_clone_redirect() helper clones skb before redirecting it to RX or TX of destination netdev. Introduce bpf_redirect() helper that does that without cloning. Benchmarked with two hosts using 10G ixgbe NICs. One host is doing line rate pktgen. Another host is configured as: $ tc qdisc add dev $dev ingress $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section clone_redirect_xmit drop so it receives the packet on $dev and immediately xmits it on $dev + 1 The section 'clone_redirect_xmit' in tcbpf1_kern.o file has the program that does bpf_clone_redirect() and performance is 2.0 Mpps $ tc filter add dev $dev root pref 10 u32 match u32 0 0 flowid 1:2 \ action bpf run object-file tcbpf1_kern.o section redirect_xmit drop which is using bpf_redirect() - 2.4 Mpps and using cls_bpf with integrated actions as: $ tc filter add dev $dev root pref 10 \ bpf run object-file tcbpf1_kern.o section redirect_xmit integ_act classid 1 performance is 2.5 Mpps To summarize: u32+act_bpf using clone_redirect - 2.0 Mpps u32+act_bpf using redirect - 2.4 Mpps cls_bpf using redirect - 2.5 Mpps For comparison linux bridge in this setup is doing 2.1 Mpps and ixgbe rx + drop in ip_rcv - 7.8 Mpps Signed-off-by: Alexei Starovoitov Acked-by: Daniel Borkmann Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/net/sch_generic.h | 1 + include/uapi/linux/bpf.h | 8 ++++++++ include/uapi/linux/pkt_cls.h | 1 + net/core/dev.c | 8 ++++++++ net/core/filter.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ net/sched/act_bpf.c | 1 + net/sched/cls_bpf.c | 1 + samples/bpf/bpf_helpers.h | 4 ++++ samples/bpf/tcbpf1_kern.c | 24 +++++++++++++++++++++++- 9 files changed, 91 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index da61febb9091..4c79ce8c1f92 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -402,6 +402,7 @@ void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab); bool tcf_destroy(struct tcf_proto *tp, bool force); void tcf_destroy_chain(struct tcf_proto __rcu **fl); +int skb_do_redirect(struct sk_buff *); /* 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) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2fbd1c71fa3b..4ec0b5488294 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -272,6 +272,14 @@ enum bpf_func_id { BPF_FUNC_skb_get_tunnel_key, BPF_FUNC_skb_set_tunnel_key, BPF_FUNC_perf_event_read, /* u64 bpf_perf_event_read(&map, index) */ + /** + * bpf_redirect(ifindex, flags) - redirect to another netdev + * @ifindex: ifindex of the net device + * @flags: bit 0 - if set, redirect to ingress instead of egress + * other bits - reserved + * Return: TC_ACT_REDIRECT + */ + BPF_FUNC_redirect, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 0a262a83f9d4..439873775d49 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -87,6 +87,7 @@ enum { #define TC_ACT_STOLEN 4 #define TC_ACT_QUEUED 5 #define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 #define TC_ACT_JUMP 0x10000000 /* Action type identifiers*/ diff --git a/net/core/dev.c b/net/core/dev.c index 00dccfac8939..ee0d6286f934 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3670,6 +3670,14 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, case TC_ACT_QUEUED: kfree_skb(skb); return NULL; + case TC_ACT_REDIRECT: + /* skb_mac_header check was done by cls/act_bpf, so + * we can safely push the L2 header back before + * redirecting to another netdev + */ + __skb_push(skb, skb->mac_len); + skb_do_redirect(skb); + return NULL; default: break; } diff --git a/net/core/filter.c b/net/core/filter.c index 971d6ba89758..da3f3d94d6e9 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1427,6 +1427,48 @@ const struct bpf_func_proto bpf_clone_redirect_proto = { .arg3_type = ARG_ANYTHING, }; +struct redirect_info { + u32 ifindex; + u32 flags; +}; + +static DEFINE_PER_CPU(struct redirect_info, redirect_info); +static u64 bpf_redirect(u64 ifindex, u64 flags, u64 r3, u64 r4, u64 r5) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + + ri->ifindex = ifindex; + ri->flags = flags; + return TC_ACT_REDIRECT; +} + +int skb_do_redirect(struct sk_buff *skb) +{ + struct redirect_info *ri = this_cpu_ptr(&redirect_info); + struct net_device *dev; + + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); + ri->ifindex = 0; + if (unlikely(!dev)) { + kfree_skb(skb); + return -EINVAL; + } + + if (BPF_IS_REDIRECT_INGRESS(ri->flags)) + return dev_forward_skb(dev, skb); + + skb->dev = dev; + return dev_queue_xmit(skb); +} + +const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + static u64 bpf_get_cgroup_classid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) { return task_get_classid((struct sk_buff *) (unsigned long) r1); @@ -1607,6 +1649,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return &bpf_skb_get_tunnel_key_proto; case BPF_FUNC_skb_set_tunnel_key: return bpf_get_skb_set_tunnel_key_proto(); + case BPF_FUNC_redirect: + return &bpf_redirect_proto; default: return sk_filter_func_proto(func_id); } diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index 559bfa011bda..0bc6f912f870 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -72,6 +72,7 @@ static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act, case TC_ACT_PIPE: case TC_ACT_RECLASSIFY: case TC_ACT_OK: + case TC_ACT_REDIRECT: action = filter_res; break; case TC_ACT_SHOT: diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 77b0ef148256..0590816ab7b0 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -70,6 +70,7 @@ static int cls_bpf_exec_opcode(int code) case TC_ACT_PIPE: case TC_ACT_STOLEN: case TC_ACT_QUEUED: + case TC_ACT_REDIRECT: case TC_ACT_UNSPEC: return code; default: diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h index 3a44d3a272af..21aa1b44c30c 100644 --- a/samples/bpf/bpf_helpers.h +++ b/samples/bpf/bpf_helpers.h @@ -33,6 +33,10 @@ static int (*bpf_get_current_comm)(void *buf, int buf_size) = (void *) BPF_FUNC_get_current_comm; static int (*bpf_perf_event_read)(void *map, int index) = (void *) BPF_FUNC_perf_event_read; +static int (*bpf_clone_redirect)(void *ctx, int ifindex, int flags) = + (void *) BPF_FUNC_clone_redirect; +static int (*bpf_redirect)(int ifindex, int flags) = + (void *) BPF_FUNC_redirect; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c index 9bfb2eb34563..fa051b3d53ee 100644 --- a/samples/bpf/tcbpf1_kern.c +++ b/samples/bpf/tcbpf1_kern.c @@ -5,7 +5,7 @@ #include #include #include - +#include #include "bpf_helpers.h" /* compiler workaround */ @@ -64,4 +64,26 @@ int bpf_prog1(struct __sk_buff *skb) return 0; } +SEC("redirect_xmit") +int _redirect_xmit(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 0); +} +SEC("redirect_recv") +int _redirect_recv(struct __sk_buff *skb) +{ + return bpf_redirect(skb->ifindex + 1, 1); +} +SEC("clone_redirect_xmit") +int _clone_redirect_xmit(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 0); + return TC_ACT_SHOT; +} +SEC("clone_redirect_recv") +int _clone_redirect_recv(struct __sk_buff *skb) +{ + bpf_clone_redirect(skb, skb->ifindex + 1, 1); + return TC_ACT_SHOT; +} char _license[] SEC("license") = "GPL"; -- cgit v1.2.3 From 37587fadff8ce8f40a6952f0383c571a89b29d1d Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 30 Jul 2015 13:22:43 -0700 Subject: arcnet: fix indentation of if_arcnet.h Standardized spacing is easier to read. Signed-off-by: Joe Perches Signed-off-by: Michael Grzeschik --- include/uapi/linux/if_arcnet.h | 55 ++++++++++++++++++++---------------------- 1 file changed, 26 insertions(+), 29 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_arcnet.h b/include/uapi/linux/if_arcnet.h index 46e34bd0e783..cfb642f8e7bd 100644 --- a/include/uapi/linux/if_arcnet.h +++ b/include/uapi/linux/if_arcnet.h @@ -19,7 +19,6 @@ #include #include - /* * These are the defined ARCnet Protocol ID's. */ @@ -57,42 +56,40 @@ * The RFC1201-specific components of an arcnet packet header. */ struct arc_rfc1201 { - __u8 proto; /* protocol ID field - varies */ - __u8 split_flag; /* for use with split packets */ - __be16 sequence; /* sequence number */ - __u8 payload[0]; /* space remaining in packet (504 bytes)*/ + __u8 proto; /* protocol ID field - varies */ + __u8 split_flag; /* for use with split packets */ + __be16 sequence; /* sequence number */ + __u8 payload[0]; /* space remaining in packet (504 bytes)*/ }; #define RFC1201_HDR_SIZE 4 - /* * The RFC1051-specific components. */ struct arc_rfc1051 { - __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ - __u8 payload[0]; /* 507 bytes */ + __u8 proto; /* ARC_P_RFC1051_ARP/RFC1051_IP */ + __u8 payload[0]; /* 507 bytes */ }; #define RFC1051_HDR_SIZE 1 - /* * The ethernet-encap-specific components. We have a real ethernet header * and some data. */ struct arc_eth_encap { - __u8 proto; /* Always ARC_P_ETHER */ - struct ethhdr eth; /* standard ethernet header (yuck!) */ - __u8 payload[0]; /* 493 bytes */ + __u8 proto; /* Always ARC_P_ETHER */ + struct ethhdr eth; /* standard ethernet header (yuck!) */ + __u8 payload[0]; /* 493 bytes */ }; #define ETH_ENCAP_HDR_SIZE 14 - struct arc_cap { __u8 proto; - __u8 cookie[sizeof(int)]; /* Actually NOT sent over the network */ + __u8 cookie[sizeof(int)]; + /* Actually NOT sent over the network */ union { __u8 ack; - __u8 raw[0]; /* 507 bytes */ + __u8 raw[0]; /* 507 bytes */ } mes; }; @@ -105,9 +102,9 @@ struct arc_cap { * driver. */ struct arc_hardware { - __u8 source, /* source ARCnet - filled in automagically */ - dest, /* destination ARCnet - 0 for broadcast */ - offset[2]; /* offset bytes (some weird semantics) */ + __u8 source; /* source ARCnet - filled in automagically */ + __u8 dest; /* destination ARCnet - 0 for broadcast */ + __u8 offset[2]; /* offset bytes (some weird semantics) */ }; #define ARC_HDR_SIZE 4 @@ -116,17 +113,17 @@ struct arc_hardware { * when you do a raw packet capture). */ struct archdr { - /* hardware requirements */ - struct arc_hardware hard; - - /* arcnet encapsulation-specific bits */ - union { - struct arc_rfc1201 rfc1201; - struct arc_rfc1051 rfc1051; - struct arc_eth_encap eth_encap; - struct arc_cap cap; - __u8 raw[0]; /* 508 bytes */ - } soft; + /* hardware requirements */ + struct arc_hardware hard; + + /* arcnet encapsulation-specific bits */ + union { + struct arc_rfc1201 rfc1201; + struct arc_rfc1051 rfc1051; + struct arc_eth_encap eth_encap; + struct arc_cap cap; + __u8 raw[0]; /* 508 bytes */ + } soft; }; #endif /* _LINUX_IF_ARCNET_H */ -- cgit v1.2.3 From 2e5ab5f379f96a6207c45be40c357ebb1beb8ef3 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 17 Aug 2015 10:31:49 +0800 Subject: block: loop: prepare for supporing direct IO This patches provides one interface for enabling direct IO from user space: - userspace(such as losetup) can pass 'file' which is opened/fcntl as O_DIRECT Also __loop_update_dio() is introduced to check if direct I/O can be used on current loop setting. The last big change is to introduce LO_FLAGS_DIRECT_IO flag for userspace to know if direct IO is used to access backing file. Cc: linux-api@vger.kernel.org Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/loop.c | 77 +++++++++++++++++++++++++++++++++++++++++++++++ drivers/block/loop.h | 1 + include/uapi/linux/loop.h | 1 + 3 files changed, 79 insertions(+) (limited to 'include/uapi') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 1875aadb31b0..06cad7edc0d3 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -164,6 +164,62 @@ static loff_t get_loop_size(struct loop_device *lo, struct file *file) return get_size(lo->lo_offset, lo->lo_sizelimit, file); } +static void __loop_update_dio(struct loop_device *lo, bool dio) +{ + struct file *file = lo->lo_backing_file; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + unsigned short sb_bsize = 0; + unsigned dio_align = 0; + bool use_dio; + + if (inode->i_sb->s_bdev) { + sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev); + dio_align = sb_bsize - 1; + } + + /* + * We support direct I/O only if lo_offset is aligned with the + * logical I/O size of backing device, and the logical block + * size of loop is bigger than the backing device's and the loop + * needn't transform transfer. + * + * TODO: the above condition may be loosed in the future, and + * direct I/O may be switched runtime at that time because most + * of requests in sane appplications should be PAGE_SIZE algined + */ + if (dio) { + if (queue_logical_block_size(lo->lo_queue) >= sb_bsize && + !(lo->lo_offset & dio_align) && + mapping->a_ops->direct_IO && + !lo->transfer) + use_dio = true; + else + use_dio = false; + } else { + use_dio = false; + } + + if (lo->use_dio == use_dio) + return; + + /* flush dirty pages before changing direct IO */ + vfs_fsync(file, 0); + + /* + * The flag of LO_FLAGS_DIRECT_IO is handled similarly with + * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup + * will get updated by ioctl(LOOP_GET_STATUS) + */ + blk_mq_freeze_queue(lo->lo_queue); + lo->use_dio = use_dio; + if (use_dio) + lo->lo_flags |= LO_FLAGS_DIRECT_IO; + else + lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; + blk_mq_unfreeze_queue(lo->lo_queue); +} + static int figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit) { @@ -421,6 +477,12 @@ struct switch_request { struct completion wait; }; +static inline void loop_update_dio(struct loop_device *lo) +{ + __loop_update_dio(lo, io_is_direct(lo->lo_backing_file) | + lo->use_dio); +} + /* * Do the actual switch; called from the BIO completion routine */ @@ -441,6 +503,7 @@ static void do_loop_switch(struct loop_device *lo, struct switch_request *p) mapping->host->i_bdev->bd_block_size : PAGE_SIZE; lo->old_gfp_mask = mapping_gfp_mask(mapping); mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS)); + loop_update_dio(lo); } /* @@ -627,11 +690,19 @@ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf) return sprintf(buf, "%s\n", partscan ? "1" : "0"); } +static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf) +{ + int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO); + + return sprintf(buf, "%s\n", dio ? "1" : "0"); +} + LOOP_ATTR_RO(backing_file); LOOP_ATTR_RO(offset); LOOP_ATTR_RO(sizelimit); LOOP_ATTR_RO(autoclear); LOOP_ATTR_RO(partscan); +LOOP_ATTR_RO(dio); static struct attribute *loop_attrs[] = { &loop_attr_backing_file.attr, @@ -639,6 +710,7 @@ static struct attribute *loop_attrs[] = { &loop_attr_sizelimit.attr, &loop_attr_autoclear.attr, &loop_attr_partscan.attr, + &loop_attr_dio.attr, NULL, }; @@ -770,6 +842,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0); + lo->use_dio = false; lo->lo_blocksize = lo_blocksize; lo->lo_device = bdev; lo->lo_flags = lo_flags; @@ -783,6 +856,7 @@ static int loop_set_fd(struct loop_device *lo, fmode_t mode, if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync) blk_queue_flush(lo->lo_queue, REQ_FLUSH); + loop_update_dio(lo); set_capacity(lo->lo_disk, size); bd_set_size(bdev, size << 9); loop_sysfs_init(lo); @@ -1001,6 +1075,9 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) lo->lo_key_owner = uid; } + /* update dio if lo_offset or transfer is changed */ + __loop_update_dio(lo, lo->use_dio); + return 0; } diff --git a/drivers/block/loop.h b/drivers/block/loop.h index b6c7d21a453a..d1de2217c09a 100644 --- a/drivers/block/loop.h +++ b/drivers/block/loop.h @@ -58,6 +58,7 @@ struct loop_device { struct mutex lo_ctl_mutex; struct kthread_worker worker; struct task_struct *worker_task; + bool use_dio; struct request_queue *lo_queue; struct blk_mq_tag_set tag_set; diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index e0cecd2eabdc..949851ce681f 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -21,6 +21,7 @@ enum { LO_FLAGS_READ_ONLY = 1, LO_FLAGS_AUTOCLEAR = 4, LO_FLAGS_PARTSCAN = 8, + LO_FLAGS_DIRECT_IO = 16, }; #include /* for __kernel_old_dev_t */ -- cgit v1.2.3 From ab1cb278bc7027663adbfb0b81404f8398437e11 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 17 Aug 2015 10:31:50 +0800 Subject: block: loop: introduce ioctl command of LOOP_SET_DIRECT_IO If loop block is mounted via 'mount -o loop', it isn't easy to pass file descriptor opened as O_DIRECT, so this patch introduces a new command to support direct IO for this case. Cc: linux-api@vger.kernel.org Signed-off-by: Ming Lei Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/block/loop.c | 19 +++++++++++++++++++ include/uapi/linux/loop.h | 1 + 2 files changed, 20 insertions(+) (limited to 'include/uapi') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 06cad7edc0d3..75db3b98ec2b 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1228,6 +1228,20 @@ static int loop_set_capacity(struct loop_device *lo, struct block_device *bdev) return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit); } +static int loop_set_dio(struct loop_device *lo, unsigned long arg) +{ + int error = -ENXIO; + if (lo->lo_state != Lo_bound) + goto out; + + __loop_update_dio(lo, !!arg); + if (lo->use_dio == !!arg) + return 0; + error = -EINVAL; + out: + return error; +} + static int lo_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { @@ -1271,6 +1285,11 @@ static int lo_ioctl(struct block_device *bdev, fmode_t mode, if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) err = loop_set_capacity(lo, bdev); break; + case LOOP_SET_DIRECT_IO: + err = -EPERM; + if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN)) + err = loop_set_dio(lo, arg); + break; default: err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL; } diff --git a/include/uapi/linux/loop.h b/include/uapi/linux/loop.h index 949851ce681f..c8125ec1f4f2 100644 --- a/include/uapi/linux/loop.h +++ b/include/uapi/linux/loop.h @@ -87,6 +87,7 @@ struct loop_info64 { #define LOOP_GET_STATUS64 0x4C05 #define LOOP_CHANGE_FD 0x4C06 #define LOOP_SET_CAPACITY 0x4C07 +#define LOOP_SET_DIRECT_IO 0x4C08 /* /dev/loop-control interface */ #define LOOP_CTL_ADD 0x4C80 -- cgit v1.2.3 From 8ff6b3bc9493089247e012a9fcba7198e194b4a5 Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Sun, 13 Sep 2015 20:26:11 -0700 Subject: iio: chemical: Add IIO_CONCENTRATION channel type There are air quality sensors that report data back in parts per million of VOC (Volatile Organic Compounds) which are usually indexed from CO2 or another common pollutant. This patchset adds an IIO_CONCENTRATION type that returns a percentage of substance because no other channels types fit this use case. Modifiers for IIO_MOD_CO2 and IIO_MOD_VOC gas types are defined. Signed-off-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 11 +++++++++++ drivers/iio/industrialio-core.c | 3 +++ include/uapi/linux/iio/types.h | 3 +++ 3 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 20312a0e8197..08903b940957 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1460,3 +1460,14 @@ Description: measurements and return the average value as output data. Each value resulted from [_name]_oversampling_ratio measurements is considered as one sample for [_name]_sampling_frequency. + +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_co2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_co2_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentration_voc_raw +What: /sys/bus/iio/devices/iio:deviceX/in_concentrationX_voc_raw +KernelVersion: 4.3 +Contact: linux-iio@vger.kernel.org +Description: + Raw (unscaled no offset etc.) percentage reading of a substance. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index bef690ed0480..ee09a945a2c7 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -75,6 +75,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_ENERGY] = "energy", [IIO_DISTANCE] = "distance", [IIO_VELOCITY] = "velocity", + [IIO_CONCENTRATION] = "concentration", }; static const char * const iio_modifier_names[] = { @@ -111,6 +112,8 @@ static const char * const iio_modifier_names[] = { [IIO_MOD_ROOT_SUM_SQUARED_X_Y_Z] = "sqrt(x^2+y^2+z^2)", [IIO_MOD_I] = "i", [IIO_MOD_Q] = "q", + [IIO_MOD_CO2] = "co2", + [IIO_MOD_VOC] = "voc", }; /* relies on pairs of these shared then separate */ diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 2f8b11722204..1e4c4e346ffb 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -35,6 +35,7 @@ enum iio_chan_type { IIO_ENERGY, IIO_DISTANCE, IIO_VELOCITY, + IIO_CONCENTRATION, }; enum iio_modifier { @@ -72,6 +73,8 @@ enum iio_modifier { IIO_MOD_ROOT_SUM_SQUARED_X_Y_Z, IIO_MOD_I, IIO_MOD_Q, + IIO_MOD_CO2, + IIO_MOD_VOC, }; enum iio_event_type { -- cgit v1.2.3 From d38d54692d454e4dded125677e39f53514dc4277 Mon Sep 17 00:00:00 2001 From: Matt Ranostay Date: Sun, 13 Sep 2015 20:26:12 -0700 Subject: iio: resistance: add IIO_RESISTANCE channel type Signed-off-by: Matt Ranostay Signed-off-by: Jonathan Cameron --- Documentation/ABI/testing/sysfs-bus-iio | 8 ++++++++ drivers/iio/industrialio-core.c | 1 + include/uapi/linux/iio/types.h | 1 + 3 files changed, 10 insertions(+) (limited to 'include/uapi') diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio index 08903b940957..8ce14c85156d 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio +++ b/Documentation/ABI/testing/sysfs-bus-iio @@ -1471,3 +1471,11 @@ KernelVersion: 4.3 Contact: linux-iio@vger.kernel.org Description: Raw (unscaled no offset etc.) percentage reading of a substance. + +What: /sys/bus/iio/devices/iio:deviceX/in_resistance_raw +What: /sys/bus/iio/devices/iio:deviceX/in_resistanceX_raw +KernelVersion: 4.3 +Contact: linux-iio@vger.kernel.org +Description: + Raw (unscaled no offset etc.) resistance reading that can be processed + into an ohm value. diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c index ee09a945a2c7..208358f9e7e3 100644 --- a/drivers/iio/industrialio-core.c +++ b/drivers/iio/industrialio-core.c @@ -76,6 +76,7 @@ static const char * const iio_chan_type_name_spec[] = { [IIO_DISTANCE] = "distance", [IIO_VELOCITY] = "velocity", [IIO_CONCENTRATION] = "concentration", + [IIO_RESISTANCE] = "resistance", }; static const char * const iio_modifier_names[] = { diff --git a/include/uapi/linux/iio/types.h b/include/uapi/linux/iio/types.h index 1e4c4e346ffb..7c63bd67c36e 100644 --- a/include/uapi/linux/iio/types.h +++ b/include/uapi/linux/iio/types.h @@ -36,6 +36,7 @@ enum iio_chan_type { IIO_DISTANCE, IIO_VELOCITY, IIO_CONCENTRATION, + IIO_RESISTANCE, }; enum iio_modifier { -- cgit v1.2.3 From 2594e9064a57634efc146ff4e89a5de562e05011 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Fri, 25 Sep 2015 19:00:11 +0200 Subject: bridge: vlan: add per-vlan struct and move to rhashtables This patch changes the bridge vlan implementation to use rhashtables instead of bitmaps. The main motivation behind this change is that we need extensible per-vlan structures (both per-port and global) so more advanced features can be introduced and the vlan support can be extended. I've tried to break this up but the moment net_port_vlans is changed and the whole API goes away, thus this is a larger patch. A few short goals of this patch are: - Extensible per-vlan structs stored in rhashtables and a sorted list - Keep user-visible behaviour (compressed vlans etc) - Keep fastpath ingress/egress logic the same (optimizations to come later) Here's a brief list of some of the new features we'd like to introduce: - per-vlan counters - vlan ingress/egress mapping - per-vlan igmp configuration - vlan priorities - avoid fdb entries replication (e.g. local fdb scaling issues) The structure is kept single for both global and per-port entries so to avoid code duplication where possible and also because we'll soon introduce "port0 / aka bridge as port" which should simplify things further (thanks to Vlad for the suggestion!). Now we have per-vlan global rhashtable (bridge-wide) and per-vlan port rhashtable, if an entry is added to a port it'll get a pointer to its global context so it can be quickly accessed later. There's also a sorted vlan list which is used for stable walks and some user-visible behaviour such as the vlan ranges, also for error paths. VLANs are stored in a "vlan group" which currently contains the rhashtable, sorted vlan list and the number of "real" vlan entries. A good side-effect of this change is that it resembles how hw keeps per-vlan data. One important note after this change is that if a VLAN is being looked up in the bridge's rhashtable for filtering purposes (or to check if it's an existing usable entry, not just a global context) then the new helper br_vlan_should_use() needs to be used if the vlan is found. In case the lookup is done only with a port's vlan group, then this check can be skipped. Things tested so far: - basic vlan ingress/egress - pvids - untagged vlans - undef CONFIG_BRIDGE_VLAN_FILTERING - adding/deleting vlans in different scenarios (with/without global ctx, while transmitting traffic, in ranges etc) - loading/removing the module while having/adding/deleting vlans - extracting bridge vlan information (user ABI), compressed requests - adding/deleting fdbs on vlans - bridge mac change, promisc mode - default pvid change - kmemleak ON during the whole time Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_device.c | 2 +- net/bridge/br_fdb.c | 76 ++--- net/bridge/br_forward.c | 15 +- net/bridge/br_input.c | 10 +- net/bridge/br_mdb.c | 24 +- net/bridge/br_netlink.c | 174 +++++----- net/bridge/br_private.h | 191 ++++++++--- net/bridge/br_vlan.c | 699 +++++++++++++++++++++++++---------------- 9 files changed, 732 insertions(+), 460 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 3635b7797508..18db14477bdd 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -127,6 +127,7 @@ enum { #define BRIDGE_VLAN_INFO_UNTAGGED (1<<2) /* VLAN egresses untagged */ #define BRIDGE_VLAN_INFO_RANGE_BEGIN (1<<3) /* VLAN is start of vlan range */ #define BRIDGE_VLAN_INFO_RANGE_END (1<<4) /* VLAN is end of vlan range */ +#define BRIDGE_VLAN_INFO_BRENTRY (1<<5) /* Global bridge VLAN entry */ struct bridge_vlan_info { __u16 flags; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 2f81624a8257..c915c5b408ea 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -56,7 +56,7 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (!br_allowed_ingress(br, br_get_vlan_info(br), skb, &vid)) + if (!br_allowed_ingress(br, skb, &vid)) goto out; if (is_broadcast_ether_addr(dest)) diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 6663cc0789a6..41de11e2eb11 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -163,22 +163,27 @@ static void fdb_delete_local(struct net_bridge *br, struct net_bridge_fdb_entry *f) { const unsigned char *addr = f->addr.addr; - u16 vid = f->vlan_id; + struct net_bridge_vlan_group *vg; + const struct net_bridge_vlan *v; struct net_bridge_port *op; + u16 vid = f->vlan_id; /* Maybe another port has same hw addr? */ list_for_each_entry(op, &br->port_list, list) { + vg = nbp_vlan_group(op); if (op != p && ether_addr_equal(op->dev->dev_addr, addr) && - (!vid || nbp_vlan_find(op, vid))) { + (!vid || br_vlan_find(vg, vid))) { f->dst = op; f->added_by_user = 0; return; } } + vg = br_vlan_group(br); + v = br_vlan_find(vg, vid); /* Maybe bridge device has same hw addr? */ if (p && ether_addr_equal(br->dev->dev_addr, addr) && - (!vid || br_vlan_find(br, vid))) { + (!vid || (v && br_vlan_should_use(v)))) { f->dst = NULL; f->added_by_user = 0; return; @@ -203,14 +208,14 @@ void br_fdb_find_delete_local(struct net_bridge *br, void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge *br = p->br; - struct net_port_vlans *pv = nbp_get_vlan_info(p); - bool no_vlan = !pv; + struct net_bridge_vlan *v; int i; - u16 vid; spin_lock_bh(&br->hash_lock); + vg = nbp_vlan_group(p); /* Search all chains since old address/hash is unknown */ for (i = 0; i < BR_HASH_SIZE; i++) { struct hlist_node *h; @@ -226,7 +231,7 @@ void br_fdb_changeaddr(struct net_bridge_port *p, const unsigned char *newaddr) * configured, we can safely be done at * this point. */ - if (no_vlan) + if (!vg || !vg->num_vlans) goto insert; } } @@ -236,15 +241,15 @@ insert: /* insert new address, may fail if invalid address or dup. */ fdb_insert(br, p, newaddr, 0); - if (no_vlan) + if (!vg || !vg->num_vlans) goto done; /* Now add entries for every VLAN configured on the port. * This function runs under RTNL so the bitmap will not change * from under us. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - fdb_insert(br, p, newaddr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) + fdb_insert(br, p, newaddr, v->vid); done: spin_unlock_bh(&br->hash_lock); @@ -252,9 +257,9 @@ done: void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) { + struct net_bridge_vlan_group *vg; struct net_bridge_fdb_entry *f; - struct net_port_vlans *pv; - u16 vid = 0; + struct net_bridge_vlan *v; spin_lock_bh(&br->hash_lock); @@ -264,20 +269,18 @@ void br_fdb_change_mac_address(struct net_bridge *br, const u8 *newaddr) fdb_delete_local(br, NULL, f); fdb_insert(br, NULL, newaddr, 0); - + vg = br_vlan_group(br); + if (!vg || !vg->num_vlans) + goto out; /* Now remove and add entries for every VLAN configured on the * bridge. This function runs under RTNL so the bitmap will not * change from under us. */ - pv = br_get_vlan_info(br); - if (!pv) - goto out; - - for_each_set_bit_from(vid, pv->vlan_bitmap, VLAN_N_VID) { - f = __br_fdb_get(br, br->dev->dev_addr, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + f = __br_fdb_get(br, br->dev->dev_addr, v->vid); if (f && f->is_local && !f->dst) fdb_delete_local(br, NULL, f); - fdb_insert(br, NULL, newaddr, vid); + fdb_insert(br, NULL, newaddr, v->vid); } out: spin_unlock_bh(&br->hash_lock); @@ -844,9 +847,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 nlh_flags) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err = 0; - struct net_port_vlans *pv; if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_NOARP|NUD_REACHABLE))) { pr_info("bridge: RTM_NEWNEIGH with invalid state %#x\n", ndm->ndm_state); @@ -865,9 +869,10 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_NEWNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -877,15 +882,15 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); } else { err = __br_fdb_add(ndm, p, addr, nlh_flags, 0); - if (err || !pv) + if (err || !vg || !vg->num_vlans) goto out; /* We have vlans configured on this port and user didn't * specify a VLAN. To be nice, add/update entry for every * vlan on this port. */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = __br_fdb_add(ndm, p, addr, nlh_flags, vid); + list_for_each_entry(v, &vg->vlan_list, vlist) { + err = __br_fdb_add(ndm, p, addr, nlh_flags, v->vid); if (err) goto out; } @@ -927,9 +932,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid) { + struct net_bridge_vlan_group *vg; struct net_bridge_port *p; + struct net_bridge_vlan *v; int err; - struct net_port_vlans *pv; p = br_port_get_rtnl(dev); if (p == NULL) { @@ -938,9 +944,10 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], return -EINVAL; } - pv = nbp_get_vlan_info(p); + vg = nbp_vlan_group(p); if (vid) { - if (!pv || !test_bit(vid, pv->vlan_bitmap)) { + v = br_vlan_find(vg, vid); + if (!v) { pr_info("bridge: RTM_DELNEIGH with unconfigured " "vlan %d on port %s\n", vid, dev->name); return -EINVAL; @@ -950,16 +957,11 @@ int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], } else { err = -ENOENT; err &= __br_fdb_delete(p, addr, 0); - if (!pv) + if (!vg || !vg->num_vlans) goto out; - /* We have vlans configured on this port and user didn't - * specify a VLAN. To be nice, add/update entry for every - * vlan on this port. - */ - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err &= __br_fdb_delete(p, addr, vid); - } + list_for_each_entry(v, &vg->vlan_list, vlist) + err &= __br_fdb_delete(p, addr, v->vid); } out: return err; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index 48afca729ed7..6d5ed795c3e2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -30,9 +30,11 @@ static int deliver_clone(const struct net_bridge_port *prev, static inline int should_deliver(const struct net_bridge_port *p, const struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(p); return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) && - br_allowed_egress(p->br, nbp_get_vlan_info(p), skb) && - p->state == BR_STATE_FORWARDING; + br_allowed_egress(vg, skb) && p->state == BR_STATE_FORWARDING; } int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb) @@ -76,7 +78,10 @@ EXPORT_SYMBOL_GPL(br_forward_finish); static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) { - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + struct net_bridge_vlan_group *vg; + + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; @@ -99,6 +104,7 @@ static void __br_deliver(const struct net_bridge_port *to, struct sk_buff *skb) static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) { + struct net_bridge_vlan_group *vg; struct net_device *indev; if (skb_warn_if_lro(skb)) { @@ -106,7 +112,8 @@ static void __br_forward(const struct net_bridge_port *to, struct sk_buff *skb) return; } - skb = br_handle_vlan(to->br, nbp_get_vlan_info(to), skb); + vg = nbp_vlan_group(to); + skb = br_handle_vlan(to->br, vg, skb); if (!skb) return; diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 223f4040d9df..e27d0dfd2ee9 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -36,28 +36,28 @@ static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); + struct net_bridge_vlan_group *vg; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); - struct net_port_vlans *pv; u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); + vg = br_vlan_group(br); /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. */ - pv = br_get_vlan_info(br); if (!(brdev->flags & IFF_PROMISC) && - !br_allowed_egress(br, pv, skb)) { + !br_allowed_egress(vg, skb)) { kfree_skb(skb); return NET_RX_DROP; } indev = skb->dev; skb->dev = brdev; - skb = br_handle_vlan(br, pv, skb); + skb = br_handle_vlan(br, vg, skb); if (!skb) return NET_RX_DROP; @@ -140,7 +140,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb if (!p || p->state == BR_STATE_DISABLED) goto drop; - if (!br_allowed_ingress(p->br, nbp_get_vlan_info(p), skb, &vid)) + if (!nbp_allowed_ingress(p, skb, &vid)) goto out; /* insert into forwarding database after filtering to avoid spoofing */ diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index d747275fad18..cd8deea2d074 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -464,11 +464,11 @@ static int __br_mdb_add(struct net *net, struct net_bridge *br, static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -489,10 +489,10 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_add(net, br, entry); if (err) break; @@ -566,11 +566,11 @@ unlock: static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) { struct net *net = sock_net(skb->sk); - unsigned short vid = VLAN_N_VID; + struct net_bridge_vlan_group *vg; struct net_device *dev, *pdev; struct br_mdb_entry *entry; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *v; struct net_bridge *br; int err; @@ -591,10 +591,10 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh) if (!p || p->br != br || p->state == BR_STATE_DISABLED) return -EINVAL; - pv = nbp_get_vlan_info(p); - if (br_vlan_enabled(br) && pv && entry->vid == 0) { - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - entry->vid = vid; + vg = nbp_vlan_group(p); + if (br_vlan_enabled(br) && vg && entry->vid == 0) { + list_for_each_entry(v, &vg->vlan_list, vlist) { + entry->vid = v->vid; err = __br_mdb_del(br, entry); if (!err) __br_mdb_notify(dev, entry, RTM_DELMDB); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ea748c93a07f..bb8bb7b36f04 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -21,36 +21,35 @@ #include "br_private.h" #include "br_private_stp.h" -static int br_get_num_vlan_infos(const struct net_port_vlans *pv, - u32 filter_mask) +static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask, + u16 pvid) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags; int num_vlans = 0; - if (filter_mask & RTEXT_FILTER_BRVLAN) - return pv->num_vlans; - if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - /* Count number of vlan info's - */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + /* Count number of vlan infos */ + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + /* only a context, bridge vlan not activated */ + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) @@ -59,8 +58,8 @@ static int br_get_num_vlan_infos(const struct net_port_vlans *pv, num_vlans += 1; } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -74,28 +73,40 @@ initvars: return num_vlans; } +static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, + u32 filter_mask, u16 pvid) +{ + if (!vg) + return 0; + + if (filter_mask & RTEXT_FILTER_BRVLAN) + return vg->num_vlans; + + return __get_num_vlan_infos(vg, filter_mask, pvid); +} + static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { - struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg = NULL; + struct net_bridge_port *p; + struct net_bridge *br; int num_vlan_infos; + u16 pvid = 0; rcu_read_lock(); - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rcu(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - pv = NULL; - if (pv) - num_vlan_infos = br_get_num_vlan_infos(pv, filter_mask); - else - num_vlan_infos = 0; + if (br_port_exists(dev)) { + p = br_port_get_rcu(dev); + vg = nbp_vlan_group(p); + pvid = nbp_get_pvid(p); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + pvid = br_get_pvid(br); + } + num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask, pvid); rcu_read_unlock(); - if (!num_vlan_infos) - return 0; - /* Each VLAN is returned in bridge_vlan_info along with flags */ return num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); } @@ -185,31 +196,33 @@ nla_put_failure: } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg, + u16 pvid) { - u16 vid_range_start = 0, vid_range_end = 0; - u16 vid_range_flags = 0; - u16 pvid, vid, flags; + struct net_bridge_vlan *v; + u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; + u16 flags; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { + list_for_each_entry(v, &vg->vlan_list, vlist) { flags = 0; - if (vid == pvid) + if (!br_vlan_should_use(v)) + continue; + if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; - } else if ((vid - vid_range_end) == 1 && + } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { - vid_range_end = vid; + vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, @@ -220,8 +233,8 @@ static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, } initvars: - vid_range_start = vid; - vid_range_end = vid; + vid_range_start = v->vid; + vid_range_end = v->vid; vid_range_flags = flags; } @@ -238,19 +251,22 @@ initvars: } static int br_fill_ifvlaninfo(struct sk_buff *skb, - const struct net_port_vlans *pv) + struct net_bridge_vlan_group *vg, + u16 pvid) { struct bridge_vlan_info vinfo; - u16 pvid, vid; + struct net_bridge_vlan *v; - pvid = br_get_pvid(pv); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - vinfo.vid = vid; + list_for_each_entry(v, &vg->vlan_list, vlist) { + if (!br_vlan_should_use(v)) + continue; + + vinfo.vid = v->vid; vinfo.flags = 0; - if (vid == pvid) + if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, @@ -269,11 +285,11 @@ nla_put_failure: * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, - const struct net_bridge_port *port, + struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev) { - const struct net_bridge *br; + struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; @@ -320,16 +336,20 @@ static int br_fill_ifinfo(struct sk_buff *skb, /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - const struct net_port_vlans *pv; + struct net_bridge_vlan_group *vg; struct nlattr *af; + u16 pvid; int err; - if (port) - pv = nbp_get_vlan_info(port); - else - pv = br_get_vlan_info(br); + if (port) { + vg = nbp_vlan_group(port); + pvid = nbp_get_pvid(port); + } else { + vg = br_vlan_group(br); + pvid = br_get_pvid(br); + } - if (!pv || bitmap_empty(pv->vlan_bitmap, VLAN_N_VID)) + if (!vg || !vg->num_vlans) goto done; af = nla_nest_start(skb, IFLA_AF_SPEC); @@ -337,9 +357,9 @@ static int br_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) - err = br_fill_ifvlaninfo_compressed(skb, pv); + err = br_fill_ifvlaninfo_compressed(skb, vg, pvid); else - err = br_fill_ifvlaninfo(skb, pv); + err = br_fill_ifvlaninfo(skb, vg, pvid); if (err) goto nla_put_failure; nla_nest_end(skb, af); @@ -413,14 +433,14 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, switch (cmd) { case RTM_SETLINK: if (p) { + /* if the MASTER flag is set this will act on the global + * per-VLAN entry as well + */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags); if (err) break; - - if (vinfo->flags & BRIDGE_VLAN_INFO_MASTER) - err = br_vlan_add(p->br, vinfo->vid, - vinfo->flags); } else { + vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags); } break; @@ -857,20 +877,22 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) static size_t br_get_link_af_size(const struct net_device *dev) { - struct net_port_vlans *pv; - - if (br_port_exists(dev)) - pv = nbp_get_vlan_info(br_port_get_rtnl(dev)); - else if (dev->priv_flags & IFF_EBRIDGE) - pv = br_get_vlan_info((struct net_bridge *)netdev_priv(dev)); - else - return 0; + struct net_bridge_port *p; + struct net_bridge *br; + int num_vlans = 0; - if (!pv) - return 0; + if (br_port_exists(dev)) { + p = br_port_get_rtnl(dev); + num_vlans = br_get_num_vlan_infos(nbp_vlan_group(p), + RTEXT_FILTER_BRVLAN, 0); + } else if (dev->priv_flags & IFF_EBRIDGE) { + br = netdev_priv(dev); + num_vlans = br_get_num_vlan_infos(br_vlan_group(br), + RTEXT_FILTER_BRVLAN, 0); + } /* Each VLAN is returned in bridge_vlan_info along with flags */ - return pv->num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); + return num_vlans * nla_total_size(sizeof(struct bridge_vlan_info)); } static struct rtnl_af_ops br_af_ops __read_mostly = { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 74e99c75c8e4..cfe945f5ab8b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -20,6 +20,7 @@ #include #include #include +#include #define BR_HASH_BITS 8 #define BR_HASH_SIZE (1 << BR_HASH_BITS) @@ -28,7 +29,6 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<bridge_id, &br->designated_root, 8); } +/* check if a VLAN entry is global */ +static inline bool br_vlan_is_master(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_MASTER; +} + +/* check if a VLAN entry is used by the bridge */ +static inline bool br_vlan_is_brentry(const struct net_bridge_vlan *v) +{ + return v->flags & BRIDGE_VLAN_INFO_BRENTRY; +} + +/* check if we should use the vlan entry is usable */ +static inline bool br_vlan_should_use(const struct net_bridge_vlan *v) +{ + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + return true; + else + return false; + } + + return true; +} + /* br_device.c */ void br_dev_setup(struct net_device *dev); void br_dev_delete(struct net_device *dev, struct list_head *list); @@ -601,18 +670,19 @@ static inline void br_mdb_uninit(void) /* br_vlan.c */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid); -bool br_allowed_egress(struct net_bridge *br, const struct net_port_vlans *v, +bool br_allowed_ingress(struct net_bridge *br, struct sk_buff *skb, u16 *vid); +bool nbp_allowed_ingress(struct net_bridge_port *p, struct sk_buff *skb, + u16 *vid); +bool br_allowed_egress(struct net_bridge_vlan_group *br, const struct sk_buff *skb); bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid); struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb); int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags); int br_vlan_delete(struct net_bridge *br, u16 vid); void br_vlan_flush(struct net_bridge *br); -bool br_vlan_find(struct net_bridge *br, u16 vid); +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid); void br_recalculate_fwd_mask(struct net_bridge *br); int __br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); int br_vlan_filter_toggle(struct net_bridge *br, unsigned long val); @@ -623,19 +693,19 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid); int nbp_vlan_init(struct net_bridge_port *port); +int nbp_get_num_vlan_infos(struct net_bridge_port *p, u32 filter_mask); -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) { - return rcu_dereference_rtnl(br->vlan_info); + return br->vlgrp; } -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) { - return rcu_dereference_rtnl(p->vlan_info); + return p->vlgrp; } /* Since bridge now depends on 8021Q module, but the time bridge sees the @@ -645,9 +715,9 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) { int err = 0; - if (skb_vlan_tag_present(skb)) + if (skb_vlan_tag_present(skb)) { *vid = skb_vlan_tag_get(skb) & VLAN_VID_MASK; - else { + } else { *vid = 0; err = -EINVAL; } @@ -655,13 +725,22 @@ static inline int br_vlan_get_tag(const struct sk_buff *skb, u16 *vid) return err; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) +static inline u16 br_get_pvid(const struct net_bridge *br) { - if (!v) + if (!br) return 0; smp_rmb(); - return v->pvid; + return br->pvid; +} + +static inline u16 nbp_get_pvid(const struct net_bridge_port *p) +{ + if (!p) + return 0; + + smp_rmb(); + return p->pvid; } static inline int br_vlan_enabled(struct net_bridge *br) @@ -670,15 +749,20 @@ static inline int br_vlan_enabled(struct net_bridge *br) } #else static inline bool br_allowed_ingress(struct net_bridge *br, - struct net_port_vlans *v, struct sk_buff *skb, u16 *vid) { return true; } -static inline bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +static inline bool nbp_allowed_ingress(struct net_bridge_port *p, + struct sk_buff *skb, + u16 *vid) +{ + return true; +} + +static inline bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { return true; @@ -691,7 +775,7 @@ static inline bool br_should_learn(struct net_bridge_port *p, } static inline struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *v, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { return skb; @@ -711,11 +795,6 @@ static inline void br_vlan_flush(struct net_bridge *br) { } -static inline bool br_vlan_find(struct net_bridge *br, u16 vid) -{ - return false; -} - static inline void br_recalculate_fwd_mask(struct net_bridge *br) { } @@ -739,32 +818,28 @@ static inline void nbp_vlan_flush(struct net_bridge_port *port) { } -static inline struct net_port_vlans *br_get_vlan_info( - const struct net_bridge *br) -{ - return NULL; -} -static inline struct net_port_vlans *nbp_get_vlan_info( - const struct net_bridge_port *p) +static inline struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, + u16 vid) { return NULL; } -static inline bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) +static inline int nbp_vlan_init(struct net_bridge_port *port) { - return false; + return 0; } -static inline int nbp_vlan_init(struct net_bridge_port *port) +static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) { return 0; } -static inline u16 br_vlan_get_tag(const struct sk_buff *skb, u16 *tag) +static inline u16 br_get_pvid(const struct net_bridge *br) { return 0; } -static inline u16 br_get_pvid(const struct net_port_vlans *v) + +static inline u16 nbp_get_pvid(const struct net_bridge_port *p) { return 0; } @@ -779,6 +854,24 @@ static inline int __br_vlan_filter_toggle(struct net_bridge *br, { return -EOPNOTSUPP; } + +static inline int nbp_get_num_vlan_infos(struct net_bridge_port *p, + u32 filter_mask) +{ + return 0; +} + +static inline struct net_bridge_vlan_group *br_vlan_group( + const struct net_bridge *br) +{ + return NULL; +} + +static inline struct net_bridge_vlan_group *nbp_vlan_group( + const struct net_bridge_port *p) +{ + return NULL; +} #endif struct nf_br_ops { diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 5f5a02b49a99..8b392070051c 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -6,35 +6,65 @@ #include "br_private.h" -static void __vlan_add_pvid(struct net_port_vlans *v, u16 vid) +static inline int br_vlan_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - if (v->pvid == vid) + const struct net_bridge_vlan *vle = ptr; + u16 vid = *(u16 *)arg->key; + + return vle->vid != vid; +} + +static const struct rhashtable_params br_vlan_rht_params = { + .head_offset = offsetof(struct net_bridge_vlan, vnode), + .key_offset = offsetof(struct net_bridge_vlan, vid), + .key_len = sizeof(u16), + .max_size = VLAN_N_VID, + .obj_cmpfn = br_vlan_cmp, + .automatic_shrinking = true, +}; + +static struct net_bridge_vlan *br_vlan_lookup(struct rhashtable *tbl, u16 vid) +{ + return rhashtable_lookup_fast(tbl, &vid, br_vlan_rht_params); +} + +static void __vlan_add_pvid(u16 *pvid, u16 vid) +{ + if (*pvid == vid) return; smp_wmb(); - v->pvid = vid; + *pvid = vid; } -static void __vlan_delete_pvid(struct net_port_vlans *v, u16 vid) +static void __vlan_delete_pvid(u16 *pvid, u16 vid) { - if (v->pvid != vid) + if (*pvid != vid) return; smp_wmb(); - v->pvid = 0; + *pvid = 0; } -static void __vlan_add_flags(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_flags(struct net_bridge_vlan *v, u16 flags) { - if (flags & BRIDGE_VLAN_INFO_PVID) - __vlan_add_pvid(v, vid); - else - __vlan_delete_pvid(v, vid); + if (flags & BRIDGE_VLAN_INFO_PVID) { + if (br_vlan_is_master(v)) + __vlan_add_pvid(&v->br->pvid, v->vid); + else + __vlan_add_pvid(&v->port->pvid, v->vid); + } else { + if (br_vlan_is_master(v)) + __vlan_delete_pvid(&v->br->pvid, v->vid); + else + __vlan_delete_pvid(&v->port->pvid, v->vid); + } if (flags & BRIDGE_VLAN_INFO_UNTAGGED) - set_bit(vid, v->untagged_bitmap); + v->flags |= BRIDGE_VLAN_INFO_UNTAGGED; else - clear_bit(vid, v->untagged_bitmap); + v->flags &= ~BRIDGE_VLAN_INFO_UNTAGGED; } static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, @@ -67,54 +97,26 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_add(struct net_port_vlans *v, u16 vid, u16 flags) +static void __vlan_add_list(struct net_bridge_vlan *v) { - struct net_bridge_port *p = NULL; - struct net_bridge *br; - struct net_device *dev; - int err; - - if (test_bit(vid, v->vlan_bitmap)) { - __vlan_add_flags(v, vid, flags); - return 0; - } - - if (v->port_idx) { - p = v->parent.port; - br = p->br; - dev = p->dev; - } else { - br = v->parent.br; - dev = br->dev; - } - - if (p) { - /* Add VLAN to the device filter if it is supported. - * This ensures tagged traffic enters the bridge when - * promiscuous mode is disabled by br_manage_promisc(). - */ - err = __vlan_vid_add(dev, br, vid, flags); - if (err) - return err; - } + struct list_head *headp, *hpos; + struct net_bridge_vlan *vent; - err = br_fdb_insert(br, p, dev->dev_addr, vid); - if (err) { - br_err(br, "failed insert local address into bridge " - "forwarding table\n"); - goto out_filt; + headp = br_vlan_is_master(v) ? &v->br->vlgrp->vlan_list : + &v->port->vlgrp->vlan_list; + list_for_each_prev(hpos, headp) { + vent = list_entry(hpos, struct net_bridge_vlan, vlist); + if (v->vid < vent->vid) + continue; + else + break; } + list_add(&v->vlist, hpos); +} - set_bit(vid, v->vlan_bitmap); - v->num_vlans++; - __vlan_add_flags(v, vid, flags); - - return 0; - -out_filt: - if (p) - vlan_vid_del(dev, br->vlan_proto, vid); - return err; +static void __vlan_del_list(struct net_bridge_vlan *v) +{ + list_del(&v->vlist); } static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, @@ -146,63 +148,195 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, return err; } -static int __vlan_del(struct net_port_vlans *v, u16 vid) +/* This is the shared VLAN add function which works for both ports and bridge + * devices. There are four possible calls to this function in terms of the + * vlan entry type: + * 1. vlan is being added on a port (no master flags, global entry exists) + * 2. vlan is being added on a bridge (both master and brvlan flags) + * 3. vlan is being added on a port, but a global entry didn't exist which + * is being created right now (master flag set, brvlan flag unset), the + * global entry is used for global per-vlan features, but not for filtering + * 4. same as 3 but with both master and brvlan flags set so the entry + * will be used for filtering in both the port and the bridge + */ +static int __vlan_add(struct net_bridge_vlan *v, u16 flags) { - if (!test_bit(vid, v->vlan_bitmap)) - return -EINVAL; + struct net_bridge_vlan *masterv = NULL; + struct net_bridge_port *p = NULL; + struct rhashtable *tbl; + struct net_device *dev; + struct net_bridge *br; + int err; + + if (br_vlan_is_master(v)) { + br = v->br; + dev = br->dev; + tbl = &br->vlgrp->vlan_hash; + } else { + p = v->port; + br = p->br; + dev = p->dev; + tbl = &p->vlgrp->vlan_hash; + } + + if (p) { + u16 master_flags = flags; + + /* Add VLAN to the device filter if it is supported. + * This ensures tagged traffic enters the bridge when + * promiscuous mode is disabled by br_manage_promisc(). + */ + err = __vlan_vid_add(dev, br, v->vid, flags); + if (err) + goto out; + + /* need to work on the master vlan too */ + if (flags & BRIDGE_VLAN_INFO_MASTER) { + master_flags |= BRIDGE_VLAN_INFO_BRENTRY; + err = br_vlan_add(br, v->vid, master_flags); + if (err) + goto out_filt; + } + + masterv = br_vlan_find(br->vlgrp, v->vid); + if (!masterv) { + /* missing global ctx, create it now */ + err = br_vlan_add(br, v->vid, master_flags); + if (err) + goto out_filt; + masterv = br_vlan_find(br->vlgrp, v->vid); + WARN_ON(!masterv); + } + atomic_inc(&masterv->refcnt); + v->brvlan = masterv; + } + + /* Add the dev mac only if it's a usable vlan */ + if (br_vlan_should_use(v)) { + err = br_fdb_insert(br, p, dev->dev_addr, v->vid); + if (err) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + goto out_filt; + } + } + + err = rhashtable_lookup_insert_fast(tbl, &v->vnode, br_vlan_rht_params); + if (err) + goto out_fdb_insert; - __vlan_delete_pvid(v, vid); - clear_bit(vid, v->untagged_bitmap); + __vlan_add_list(v); + __vlan_add_flags(v, flags); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) + br->vlgrp->num_vlans++; + } else { + p->vlgrp->num_vlans++; + } +out: + return err; + +out_fdb_insert: + br_fdb_find_delete_local(br, p, br->dev->dev_addr, v->vid); + +out_filt: + if (p) { + __vlan_vid_del(dev, br, v->vid); + if (masterv) { + atomic_dec(&masterv->refcnt); + v->brvlan = NULL; + } + } + + goto out; +} + +static int __vlan_del(struct net_bridge_vlan *v) +{ + struct net_bridge_vlan *masterv = v; + struct net_bridge_port *p = NULL; + struct net_bridge *br; + int err = 0; + struct rhashtable *tbl; + u16 *pvid; - if (v->port_idx) { - struct net_bridge_port *p = v->parent.port; - int err; + if (br_vlan_is_master(v)) { + br = v->br; + tbl = &v->br->vlgrp->vlan_hash; + pvid = &v->br->pvid; + } else { + p = v->port; + br = p->br; + tbl = &p->vlgrp->vlan_hash; + masterv = v->brvlan; + pvid = &p->pvid; + } - err = __vlan_vid_del(p->dev, p->br, vid); + __vlan_delete_pvid(pvid, v->vid); + if (p) { + err = __vlan_vid_del(p->dev, p->br, v->vid); if (err) - return err; + goto out; } - clear_bit(vid, v->vlan_bitmap); - v->num_vlans--; - if (bitmap_empty(v->vlan_bitmap, VLAN_N_VID)) { - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); + if (br_vlan_is_master(v)) { + if (br_vlan_is_brentry(v)) { + v->flags &= ~BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans--; + } + } else { + p->vlgrp->num_vlans--; + } + + if (masterv != v) { + rhashtable_remove_fast(tbl, &v->vnode, br_vlan_rht_params); + __vlan_del_list(v); kfree_rcu(v, rcu); } - return 0; + + if (atomic_dec_and_test(&masterv->refcnt)) { + rhashtable_remove_fast(&masterv->br->vlgrp->vlan_hash, + &masterv->vnode, br_vlan_rht_params); + __vlan_del_list(masterv); + kfree_rcu(masterv, rcu); + } +out: + return err; } -static void __vlan_flush(struct net_port_vlans *v) +static void __vlan_flush(struct net_bridge_vlan_group *vlgrp, u16 *pvid) { - smp_wmb(); - v->pvid = 0; - bitmap_zero(v->vlan_bitmap, VLAN_N_VID); - if (v->port_idx) - RCU_INIT_POINTER(v->parent.port->vlan_info, NULL); - else - RCU_INIT_POINTER(v->parent.br->vlan_info, NULL); - kfree_rcu(v, rcu); + struct net_bridge_vlan *vlan, *tmp; + + __vlan_delete_pvid(pvid, *pvid); + list_for_each_entry_safe(vlan, tmp, &vlgrp->vlan_list, vlist) + __vlan_del(vlan); + rhashtable_destroy(&vlgrp->vlan_hash); + kfree(vlgrp); } struct sk_buff *br_handle_vlan(struct net_bridge *br, - const struct net_port_vlans *pv, + struct net_bridge_vlan_group *vg, struct sk_buff *skb) { + struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) goto out; - /* Vlan filter table must be configured at this point. The + /* At this point, we know that the frame was filtered and contains + * a valid vlan id. If the vlan id has untagged flag set, + * send untagged; otherwise, send tagged. + */ + br_vlan_get_tag(skb, &vid); + v = br_vlan_find(vg, vid); + /* Vlan entry must be configured at this point. The * only exception is the bridge is set in promisc mode and the * packet is destined for the bridge device. In this case * pass the packet as is. */ - if (!pv) { + if (!v || !br_vlan_should_use(v)) { if ((br->dev->flags & IFF_PROMISC) && skb->dev == br->dev) { goto out; } else { @@ -210,13 +344,7 @@ struct sk_buff *br_handle_vlan(struct net_bridge *br, return NULL; } } - - /* At this point, we know that the frame was filtered and contains - * a valid vlan id. If the vlan id is set in the untagged bitmap, - * send untagged; otherwise, send tagged. - */ - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, pv->untagged_bitmap)) + if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) skb->vlan_tci = 0; out: @@ -224,29 +352,13 @@ out: } /* Called under RCU */ -bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, - struct sk_buff *skb, u16 *vid) +static bool __allowed_ingress(struct rhashtable *tbl, u16 pvid, __be16 proto, + struct sk_buff *skb, u16 *vid) { + const struct net_bridge_vlan *v; bool tagged; - __be16 proto; - - /* If VLAN filtering is disabled on the bridge, all packets are - * permitted. - */ - if (!br->vlan_enabled) { - BR_INPUT_SKB_CB(skb)->vlan_filtered = false; - return true; - } - - /* If there are no vlan in the permitted list, all packets are - * rejected. - */ - if (!v) - goto drop; BR_INPUT_SKB_CB(skb)->vlan_filtered = true; - proto = br->vlan_proto; - /* If vlan tx offload is disabled on bridge device and frame was * sent from vlan device on the bridge device, it does not have * HW accelerated vlan tag. @@ -281,8 +393,6 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } if (!*vid) { - u16 pvid = br_get_pvid(v); - /* Frame had a tag with VID 0 or did not have a tag. * See if pvid is set on this port. That tells us which * vlan untagged or priority-tagged traffic belongs to. @@ -309,29 +419,59 @@ bool br_allowed_ingress(struct net_bridge *br, struct net_port_vlans *v, } /* Frame had a valid vlan tag. See if vlan is allowed */ - if (test_bit(*vid, v->vlan_bitmap)) + v = br_vlan_lookup(tbl, *vid); + if (v && br_vlan_should_use(v)) return true; drop: kfree_skb(skb); return false; } +bool br_allowed_ingress(struct net_bridge *br, struct sk_buff *skb, u16 *vid) +{ + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; + return true; + } + + return __allowed_ingress(&br->vlgrp->vlan_hash, br->pvid, + br->vlan_proto, skb, vid); +} + +bool nbp_allowed_ingress(struct net_bridge_port *p, struct sk_buff *skb, + u16 *vid) +{ + struct net_bridge *br = p->br; + + /* If VLAN filtering is disabled on the bridge, all packets are + * permitted. + */ + if (!br->vlan_enabled) { + BR_INPUT_SKB_CB(skb)->vlan_filtered = false; + return true; + } + + return __allowed_ingress(&p->vlgrp->vlan_hash, p->pvid, br->vlan_proto, + skb, vid); +} + /* Called under RCU. */ -bool br_allowed_egress(struct net_bridge *br, - const struct net_port_vlans *v, +bool br_allowed_egress(struct net_bridge_vlan_group *vg, const struct sk_buff *skb) { + const struct net_bridge_vlan *v; u16 vid; /* If this packet was not filtered at input, let it pass */ if (!BR_INPUT_SKB_CB(skb)->vlan_filtered) return true; - if (!v) - return false; - br_vlan_get_tag(skb, &vid); - if (test_bit(vid, v->vlan_bitmap)) + v = br_vlan_find(vg, vid); + if (v && br_vlan_should_use(v)) return true; return false; @@ -341,28 +481,26 @@ bool br_allowed_egress(struct net_bridge *br, bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) { struct net_bridge *br = p->br; - struct net_port_vlans *v; /* If filtering was disabled at input, let it pass. */ if (!br->vlan_enabled) return true; - v = rcu_dereference(p->vlan_info); - if (!v) + if (!p->vlgrp->num_vlans) return false; if (!br_vlan_get_tag(skb, vid) && skb->vlan_proto != br->vlan_proto) *vid = 0; if (!*vid) { - *vid = br_get_pvid(v); + *vid = nbp_get_pvid(p); if (!*vid) return false; return true; } - if (test_bit(*vid, v->vlan_bitmap)) + if (br_vlan_find(p->vlgrp, *vid)) return true; return false; @@ -373,31 +511,47 @@ bool br_should_learn(struct net_bridge_port *p, struct sk_buff *skb, u16 *vid) */ int br_vlan_add(struct net_bridge *br, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); + vlan = br_vlan_find(br->vlgrp, vid); + if (vlan) { + if (!br_vlan_is_brentry(vlan)) { + /* Trying to change flags of non-existent bridge vlan */ + if (!(flags & BRIDGE_VLAN_INFO_BRENTRY)) + return -EINVAL; + /* It was only kept for port vlans, now make it real */ + ret = br_fdb_insert(br, NULL, br->dev->dev_addr, + vlan->vid); + if (ret) { + br_err(br, "failed insert local address into bridge forwarding table\n"); + return ret; + } + atomic_inc(&vlan->refcnt); + vlan->flags |= BRIDGE_VLAN_INFO_BRENTRY; + br->vlgrp->num_vlans++; + } + __vlan_add_flags(vlan, flags); + return 0; + } - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) return -ENOMEM; - pv->parent.br = br; - err = __vlan_add(pv, vid, flags); - if (err) - goto out; + vlan->vid = vid; + vlan->flags = flags | BRIDGE_VLAN_INFO_MASTER; + vlan->flags &= ~BRIDGE_VLAN_INFO_PVID; + vlan->br = br; + if (flags & BRIDGE_VLAN_INFO_BRENTRY) + atomic_set(&vlan->refcnt, 1); + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); - rcu_assign_pointer(br->vlan_info, pv); - return 0; -out: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -405,49 +559,32 @@ out: */ int br_vlan_delete(struct net_bridge *br, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return -EINVAL; + v = br_vlan_find(br->vlgrp, vid); + if (!v || !br_vlan_is_brentry(v)) + return -ENOENT; br_fdb_find_delete_local(br, NULL, br->dev->dev_addr, vid); - __vlan_del(pv, vid); - return 0; + return __vlan_del(v); } void br_vlan_flush(struct net_bridge *br) { - struct net_port_vlans *pv; - ASSERT_RTNL(); - pv = rtnl_dereference(br->vlan_info); - if (!pv) - return; - __vlan_flush(pv); + __vlan_flush(br_vlan_group(br), &br->pvid); } -bool br_vlan_find(struct net_bridge *br, u16 vid) +struct net_bridge_vlan *br_vlan_find(struct net_bridge_vlan_group *vg, u16 vid) { - struct net_port_vlans *pv; - bool found = false; + if (!vg) + return NULL; - rcu_read_lock(); - pv = rcu_dereference(br->vlan_info); - - if (!pv) - goto out; - - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; + return br_vlan_lookup(&vg->vlan_hash, vid); } /* Must be protected by RTNL. */ @@ -505,21 +642,16 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) { int err = 0; struct net_bridge_port *p; - struct net_port_vlans *pv; + struct net_bridge_vlan *vlan; __be16 oldproto; - u16 vid, errvid; if (br->vlan_proto == proto) return 0; /* Add VLANs for the new proto to the device filter. */ list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) { - err = vlan_vid_add(p->dev, proto, vid); + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) { + err = vlan_vid_add(p->dev, proto, vlan->vid); if (err) goto err_filt; } @@ -532,30 +664,19 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto) br_recalculate_fwd_mask(br); /* Delete VLANs for the old proto from the device filter. */ - list_for_each_entry(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, oldproto, vid); - } + list_for_each_entry(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, oldproto, vlan->vid); return 0; err_filt: - errvid = vid; - for_each_set_bit(vid, pv->vlan_bitmap, errvid) - vlan_vid_del(p->dev, proto, vid); - - list_for_each_entry_continue_reverse(p, &br->port_list, list) { - pv = rtnl_dereference(p->vlan_info); - if (!pv) - continue; + list_for_each_entry_continue_reverse(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(p->dev, proto, vid); - } + list_for_each_entry_continue_reverse(p, &br->port_list, list) + list_for_each_entry(vlan, &p->vlgrp->vlan_list, vlist) + vlan_vid_del(p->dev, proto, vlan->vid); return err; } @@ -576,9 +697,20 @@ int br_vlan_set_proto(struct net_bridge *br, unsigned long val) return err; } -static bool vlan_default_pvid(struct net_port_vlans *pv, u16 vid) +static bool vlan_default_pvid(struct net_bridge_vlan_group *vg, u16 pvid, + u16 vid) { - return pv && vid == pv->pvid && test_bit(vid, pv->untagged_bitmap); + struct net_bridge_vlan *v; + + if (vid != pvid) + return false; + + v = br_vlan_lookup(&vg->vlan_hash, vid); + if (v && br_vlan_should_use(v) && + (v->flags & BRIDGE_VLAN_INFO_UNTAGGED)) + return true; + + return false; } static void br_vlan_disable_default_pvid(struct net_bridge *br) @@ -589,11 +721,11 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br_get_vlan_info(br), pvid)) + if (vlan_default_pvid(br->vlgrp, br->pvid, pvid)) br_vlan_delete(br, pvid); list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(nbp_get_vlan_info(p), pvid)) + if (vlan_default_pvid(p->vlgrp, p->pvid, pvid)) nbp_vlan_delete(p, pvid); } @@ -602,6 +734,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { + const struct net_bridge_vlan *pvent; struct net_bridge_port *p; u16 old_pvid; int err = 0; @@ -617,11 +750,13 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) /* Update default_pvid config only if we do not conflict with * user configuration. */ - if ((!old_pvid || vlan_default_pvid(br_get_vlan_info(br), old_pvid)) && - !br_vlan_find(br, pvid)) { + pvent = br_vlan_find(br->vlgrp, pvid); + if ((!old_pvid || vlan_default_pvid(br->vlgrp, br->pvid, old_pvid)) && + (!pvent || !br_vlan_should_use(pvent))) { err = br_vlan_add(br, pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); if (err) goto out; br_vlan_delete(br, old_pvid); @@ -633,8 +768,8 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) * user configuration. */ if ((old_pvid && - !vlan_default_pvid(nbp_get_vlan_info(p), old_pvid)) || - nbp_vlan_find(p, pvid)) + !vlan_default_pvid(p->vlgrp, p->pvid, old_pvid)) || + br_vlan_find(p->vlgrp, pvid)) continue; err = nbp_vlan_add(p, pvid, @@ -668,7 +803,8 @@ err_port: if (old_pvid) br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED); + BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); br_vlan_delete(br, pvid); } goto out; @@ -707,10 +843,62 @@ unlock: int br_vlan_init(struct net_bridge *br) { + int ret = -ENOMEM; + + br->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!br->vlgrp) + goto out; + ret = rhashtable_init(&br->vlgrp->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&br->vlgrp->vlan_list); br->vlan_proto = htons(ETH_P_8021Q); br->default_pvid = 1; - return br_vlan_add(br, 1, - BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED); + ret = br_vlan_add(br, 1, + BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | + BRIDGE_VLAN_INFO_BRENTRY); + if (ret) + goto err_vlan_add; + +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&br->vlgrp->vlan_hash); +err_rhtbl: + kfree(br->vlgrp); + + goto out; +} + +int nbp_vlan_init(struct net_bridge_port *p) +{ + int ret = -ENOMEM; + + p->vlgrp = kzalloc(sizeof(struct net_bridge_vlan_group), GFP_KERNEL); + if (!p->vlgrp) + goto out; + + ret = rhashtable_init(&p->vlgrp->vlan_hash, &br_vlan_rht_params); + if (ret) + goto err_rhtbl; + INIT_LIST_HEAD(&p->vlgrp->vlan_list); + if (p->br->default_pvid) { + ret = nbp_vlan_add(p, p->br->default_pvid, + BRIDGE_VLAN_INFO_PVID | + BRIDGE_VLAN_INFO_UNTAGGED); + if (ret) + goto err_vlan_add; + } +out: + return ret; + +err_vlan_add: + rhashtable_destroy(&p->vlgrp->vlan_hash); +err_rhtbl: + kfree(p->vlgrp); + + goto out; } /* Must be protected by RTNL. @@ -718,35 +906,28 @@ int br_vlan_init(struct net_bridge *br) */ int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags) { - struct net_port_vlans *pv = NULL; - int err; + struct net_bridge_vlan *vlan; + int ret; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (pv) - return __vlan_add(pv, vid, flags); - - /* Create port vlan infomration - */ - pv = kzalloc(sizeof(*pv), GFP_KERNEL); - if (!pv) { - err = -ENOMEM; - goto clean_up; + vlan = br_vlan_find(port->vlgrp, vid); + if (vlan) { + __vlan_add_flags(vlan, flags); + return 0; } - pv->port_idx = port->port_no; - pv->parent.port = port; - err = __vlan_add(pv, vid, flags); - if (err) - goto clean_up; + vlan = kzalloc(sizeof(*vlan), GFP_KERNEL); + if (!vlan) + return -ENOMEM; - rcu_assign_pointer(port->vlan_info, pv); - return 0; + vlan->vid = vid; + vlan->port = port; + ret = __vlan_add(vlan, flags); + if (ret) + kfree(vlan); -clean_up: - kfree(pv); - return err; + return ret; } /* Must be protected by RTNL. @@ -754,61 +935,27 @@ clean_up: */ int nbp_vlan_delete(struct net_bridge_port *port, u16 vid) { - struct net_port_vlans *pv; + struct net_bridge_vlan *v; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return -EINVAL; - + v = br_vlan_find(port->vlgrp, vid); + if (!v) + return -ENOENT; br_fdb_find_delete_local(port->br, port, port->dev->dev_addr, vid); br_fdb_delete_by_port(port->br, port, vid, 0); - return __vlan_del(pv, vid); + return __vlan_del(v); } void nbp_vlan_flush(struct net_bridge_port *port) { - struct net_port_vlans *pv; - u16 vid; + struct net_bridge_vlan *vlan; ASSERT_RTNL(); - pv = rtnl_dereference(port->vlan_info); - if (!pv) - return; - - for_each_set_bit(vid, pv->vlan_bitmap, VLAN_N_VID) - vlan_vid_del(port->dev, port->br->vlan_proto, vid); - - __vlan_flush(pv); -} - -bool nbp_vlan_find(struct net_bridge_port *port, u16 vid) -{ - struct net_port_vlans *pv; - bool found = false; - - rcu_read_lock(); - pv = rcu_dereference(port->vlan_info); - - if (!pv) - goto out; + list_for_each_entry(vlan, &port->vlgrp->vlan_list, vlist) + vlan_vid_del(port->dev, port->br->vlan_proto, vlan->vid); - if (test_bit(vid, pv->vlan_bitmap)) - found = true; - -out: - rcu_read_unlock(); - return found; -} - -int nbp_vlan_init(struct net_bridge_port *p) -{ - return p->br->default_pvid ? - nbp_vlan_add(p, p->br->default_pvid, - BRIDGE_VLAN_INFO_PVID | - BRIDGE_VLAN_INFO_UNTAGGED) : - 0; + __vlan_flush(nbp_vlan_group(port), &port->pvid); } -- cgit v1.2.3 From 53bb724f94f57b67213e08a4c155c8c5eb74c644 Mon Sep 17 00:00:00 2001 From: Brian Norris Date: Mon, 21 Sep 2015 13:26:59 -0700 Subject: mtd: provide proper 32/64-bit compat_ioctl() support for BLKPG After a bit of poking around wondering why my 32-bit user-space can't seem to send a proper ioctl(BLKPG) to an MTD on my 64-bit kernel (ARM64), I noticed that struct blkpg_ioctl_arg is actually pretty unsuitable for use in the ioctl() ABI, due to its use of raw pointers, and its lack of alignment/packing restrictions (32-bit arch'es tend to pack the 4 fields into 4 32-bit words, whereas 64-bit arch'es would add padding after the third int, and make this 6 32-bit words). Anyway, this means BLKPG deserves some special compat_ioctl handling. Do the conversion in a small shim for MTD. block/compat_ioctl.c already has compat support for the block subsystem, but it does so by a re-marshalling data to/from user-space (see compat_blkpg_ioctl()). Personally, I think this approach is cleaner. Tested only on MTD, with an ARM32 user space on an ARM64 kernel. Signed-off-by: Brian Norris --- drivers/mtd/mtdchar.c | 42 +++++++++++++++++++++++++++++++++--------- include/linux/blkpg.h | 21 +++++++++++++++++++++ include/uapi/linux/blkpg.h | 6 +++--- 3 files changed, 57 insertions(+), 12 deletions(-) create mode 100644 include/linux/blkpg.h (limited to 'include/uapi') diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c index 55fa27ecf4e1..6d19835b80a9 100644 --- a/drivers/mtd/mtdchar.c +++ b/drivers/mtd/mtdchar.c @@ -498,21 +498,17 @@ static int shrink_ecclayout(const struct nand_ecclayout *from, } static int mtdchar_blkpg_ioctl(struct mtd_info *mtd, - struct blkpg_ioctl_arg __user *arg) + struct blkpg_ioctl_arg *arg) { - struct blkpg_ioctl_arg a; struct blkpg_partition p; if (!capable(CAP_SYS_ADMIN)) return -EPERM; - if (copy_from_user(&a, arg, sizeof(struct blkpg_ioctl_arg))) + if (copy_from_user(&p, arg->data, sizeof(p))) return -EFAULT; - if (copy_from_user(&p, a.data, sizeof(struct blkpg_partition))) - return -EFAULT; - - switch (a.op) { + switch (arg->op) { case BLKPG_ADD_PARTITION: /* Only master mtd device must be used to add partitions */ @@ -966,8 +962,13 @@ static int mtdchar_ioctl(struct file *file, u_int cmd, u_long arg) case BLKPG: { - ret = mtdchar_blkpg_ioctl(mtd, - (struct blkpg_ioctl_arg __user *)arg); + struct blkpg_ioctl_arg __user *blk_arg = argp; + struct blkpg_ioctl_arg a; + + if (copy_from_user(&a, blk_arg, sizeof(a))) + ret = -EFAULT; + else + ret = mtdchar_blkpg_ioctl(mtd, &a); break; } @@ -1046,6 +1047,29 @@ static long mtdchar_compat_ioctl(struct file *file, unsigned int cmd, &buf_user->start); break; } + + case BLKPG: + { + /* Convert from blkpg_compat_ioctl_arg to blkpg_ioctl_arg */ + struct blkpg_compat_ioctl_arg __user *uarg = argp; + struct blkpg_compat_ioctl_arg compat_arg; + struct blkpg_ioctl_arg a; + + if (copy_from_user(&compat_arg, uarg, sizeof(compat_arg))) { + ret = -EFAULT; + break; + } + + memset(&a, 0, sizeof(a)); + a.op = compat_arg.op; + a.flags = compat_arg.flags; + a.datalen = compat_arg.datalen; + a.data = compat_ptr(compat_arg.data); + + ret = mtdchar_blkpg_ioctl(mtd, &a); + break; + } + default: ret = mtdchar_ioctl(file, cmd, (unsigned long)argp); } diff --git a/include/linux/blkpg.h b/include/linux/blkpg.h new file mode 100644 index 000000000000..bef124fde61e --- /dev/null +++ b/include/linux/blkpg.h @@ -0,0 +1,21 @@ +#ifndef _LINUX_BLKPG_H +#define _LINUX_BLKPG_H + +/* + * Partition table and disk geometry handling + */ + +#include +#include + +#ifdef CONFIG_COMPAT +/* For 32-bit/64-bit compatibility of struct blkpg_ioctl_arg */ +struct blkpg_compat_ioctl_arg { + compat_int_t op; + compat_int_t flags; + compat_int_t datalen; + compat_uptr_t data; +}; +#endif + +#endif /* _LINUX_BLKPG_H */ diff --git a/include/uapi/linux/blkpg.h b/include/uapi/linux/blkpg.h index a8519446c111..63739a035085 100644 --- a/include/uapi/linux/blkpg.h +++ b/include/uapi/linux/blkpg.h @@ -1,5 +1,5 @@ -#ifndef _LINUX_BLKPG_H -#define _LINUX_BLKPG_H +#ifndef _UAPI__LINUX_BLKPG_H +#define _UAPI__LINUX_BLKPG_H /* * Partition table and disk geometry handling @@ -56,4 +56,4 @@ struct blkpg_partition { char volname[BLKPG_VOLNAMELTH]; /* volume label */ }; -#endif /* _LINUX_BLKPG_H */ +#endif /* _UAPI__LINUX_BLKPG_H */ -- cgit v1.2.3 From 21fdd092acc7ebda0dfe682008592eb79c382707 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Tue, 29 Sep 2015 09:32:03 -0700 Subject: net: Add support for filtering neigh dump by master device Add support for filtering neighbor dumps by master device by adding the NDA_MASTER attribute to the dump request. A new netlink flag, NLM_F_DUMP_FILTERED, is added to indicate the kernel supports the request and output is filtered as requested. Signed-off-by: David Ahern Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/netlink.h | 1 + net/core/neighbour.c | 32 +++++++++++++++++++++++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 6f3fe16cd22a..f095155d8749 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -54,6 +54,7 @@ struct nlmsghdr { #define NLM_F_ACK 4 /* Reply with ack, with zero or error code */ #define NLM_F_ECHO 8 /* Echo this request */ #define NLM_F_DUMP_INTR 16 /* Dump was inconsistent due to sequence change */ +#define NLM_F_DUMP_FILTERED 32 /* Dump was filtered as requested */ /* Modifiers to GET request */ #define NLM_F_ROOT 0x100 /* specify tree root */ diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2b515ba7e94f..8c57fdf4d68e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2235,14 +2235,42 @@ static void neigh_update_notify(struct neighbour *neigh) __neigh_notify(neigh, RTM_NEWNEIGH, 0); } +static bool neigh_master_filtered(struct net_device *dev, int master_idx) +{ + struct net_device *master; + + if (!master_idx) + return false; + + master = netdev_master_upper_dev_get(dev); + if (!master || master->ifindex != master_idx) + return true; + + return false; +} + static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); + const struct nlmsghdr *nlh = cb->nlh; + struct nlattr *tb[NDA_MAX + 1]; struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; struct neigh_hash_table *nht; + int filter_master_idx = 0; + unsigned int flags = NLM_F_MULTI; + int err; + + err = nlmsg_parse(nlh, sizeof(struct ndmsg), tb, NDA_MAX, NULL); + if (!err) { + if (tb[NDA_MASTER]) + filter_master_idx = nla_get_u32(tb[NDA_MASTER]); + + if (filter_master_idx) + flags |= NLM_F_DUMP_FILTERED; + } rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); @@ -2255,12 +2283,14 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; + if (neigh_master_filtered(n->dev, filter_master_idx)) + continue; if (idx < s_idx) goto next; if (neigh_fill_info(skb, n, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, - NLM_F_MULTI) < 0) { + flags) < 0) { rc = -1; goto out; } -- cgit v1.2.3 From 660dd3d52ead45b8e60dcf966daf304de2121a28 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 30 Sep 2015 09:39:21 +0900 Subject: ALSA: firewire-digi00x: add hwdep interface This commit adds hwdep interface so as the other sound drivers for units on IEEE 1394 bus have. This interface is designed for mixer/control applications. By using this interface, an application can get information about firewire node, can lock/unlock kernel streaming and can get notification at starting/stopping kernel streaming. Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 3 +- include/uapi/sound/firewire.h | 1 + sound/firewire/Kconfig | 1 + sound/firewire/digi00x/Makefile | 2 +- sound/firewire/digi00x/digi00x-hwdep.c | 192 ++++++++++++++++++++++++++++++++ sound/firewire/digi00x/digi00x-pcm.c | 23 +++- sound/firewire/digi00x/digi00x-stream.c | 39 +++++++ sound/firewire/digi00x/digi00x.c | 6 + sound/firewire/digi00x/digi00x.h | 14 +++ 9 files changed, 273 insertions(+), 8 deletions(-) create mode 100644 sound/firewire/digi00x/digi00x-hwdep.c (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index a45be6bdcf5b..aa329132f6c4 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -100,9 +100,10 @@ enum { SNDRV_HWDEP_IFACE_FW_FIREWORKS, /* Echo Audio Fireworks based device */ SNDRV_HWDEP_IFACE_FW_BEBOB, /* BridgeCo BeBoB based device */ SNDRV_HWDEP_IFACE_FW_OXFW, /* Oxford OXFW970/971 based device */ + SNDRV_HWDEP_IFACE_FW_DIGI00X, /* Digidesign Digi 002/003 family */ /* Don't forget to change the following: */ - SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_OXFW + SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_DIGI00X }; struct snd_hwdep_info { diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index 49122df3b56b..f67d228f731b 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -56,6 +56,7 @@ union snd_firewire_event { #define SNDRV_FIREWIRE_TYPE_FIREWORKS 2 #define SNDRV_FIREWIRE_TYPE_BEBOB 3 #define SNDRV_FIREWIRE_TYPE_OXFW 4 +#define SNDRV_FIREWIRE_TYPE_DIGI00X 5 /* RME, MOTU, ... */ struct snd_firewire_get_info { diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig index 74f17a8263db..e61445e2ceaa 100644 --- a/sound/firewire/Kconfig +++ b/sound/firewire/Kconfig @@ -123,6 +123,7 @@ config SND_BEBOB config SND_FIREWIRE_DIGI00X tristate "Digidesign Digi 002/003 family support" select SND_FIREWIRE_LIB + select SND_HWDEP help Say Y here to include support for Digidesign Digi 002/003 family. * Digi 002 Console diff --git a/sound/firewire/digi00x/Makefile b/sound/firewire/digi00x/Makefile index 3c0ff6fff1f0..5bc3c7780a51 100644 --- a/sound/firewire/digi00x/Makefile +++ b/sound/firewire/digi00x/Makefile @@ -1,3 +1,3 @@ snd-firewire-digi00x-objs := amdtp-dot.o digi00x-stream.o digi00x-proc.o \ - digi00x-pcm.o digi00x.o + digi00x-pcm.o digi00x-hwdep.o digi00x.o obj-$(CONFIG_SND_FIREWIRE_DIGI00X) += snd-firewire-digi00x.o diff --git a/sound/firewire/digi00x/digi00x-hwdep.c b/sound/firewire/digi00x/digi00x-hwdep.c new file mode 100644 index 000000000000..d629e415dc8b --- /dev/null +++ b/sound/firewire/digi00x/digi00x-hwdep.c @@ -0,0 +1,192 @@ +/* + * digi00x-hwdep.c - a part of driver for Digidesign Digi 002/003 family + * + * Copyright (c) 2014-2015 Takashi Sakamoto + * + * Licensed under the terms of the GNU General Public License, version 2. + */ + +/* + * This codes give three functionality. + * + * 1.get firewire node information + * 2.get notification about starting/stopping stream + * 3.lock/unlock stream + */ + +#include "digi00x.h" + +static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, + loff_t *offset) +{ + struct snd_dg00x *dg00x = hwdep->private_data; + DEFINE_WAIT(wait); + union snd_firewire_event event; + + spin_lock_irq(&dg00x->lock); + + while (!dg00x->dev_lock_changed) { + prepare_to_wait(&dg00x->hwdep_wait, &wait, TASK_INTERRUPTIBLE); + spin_unlock_irq(&dg00x->lock); + schedule(); + finish_wait(&dg00x->hwdep_wait, &wait); + if (signal_pending(current)) + return -ERESTARTSYS; + spin_lock_irq(&dg00x->lock); + } + + memset(&event, 0, sizeof(event)); + if (dg00x->dev_lock_changed) { + event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS; + event.lock_status.status = (dg00x->dev_lock_count > 0); + dg00x->dev_lock_changed = false; + + count = min_t(long, count, sizeof(event.lock_status)); + } + + spin_unlock_irq(&dg00x->lock); + + if (copy_to_user(buf, &event, count)) + return -EFAULT; + + return count; +} + +static unsigned int hwdep_poll(struct snd_hwdep *hwdep, struct file *file, + poll_table *wait) +{ + struct snd_dg00x *dg00x = hwdep->private_data; + unsigned int events; + + poll_wait(file, &dg00x->hwdep_wait, wait); + + spin_lock_irq(&dg00x->lock); + if (dg00x->dev_lock_changed) + events = POLLIN | POLLRDNORM; + else + events = 0; + spin_unlock_irq(&dg00x->lock); + + return events; +} + +static int hwdep_get_info(struct snd_dg00x *dg00x, void __user *arg) +{ + struct fw_device *dev = fw_parent_device(dg00x->unit); + struct snd_firewire_get_info info; + + memset(&info, 0, sizeof(info)); + info.type = SNDRV_FIREWIRE_TYPE_DIGI00X; + info.card = dev->card->index; + *(__be32 *)&info.guid[0] = cpu_to_be32(dev->config_rom[3]); + *(__be32 *)&info.guid[4] = cpu_to_be32(dev->config_rom[4]); + strlcpy(info.device_name, dev_name(&dev->device), + sizeof(info.device_name)); + + if (copy_to_user(arg, &info, sizeof(info))) + return -EFAULT; + + return 0; +} + +static int hwdep_lock(struct snd_dg00x *dg00x) +{ + int err; + + spin_lock_irq(&dg00x->lock); + + if (dg00x->dev_lock_count == 0) { + dg00x->dev_lock_count = -1; + err = 0; + } else { + err = -EBUSY; + } + + spin_unlock_irq(&dg00x->lock); + + return err; +} + +static int hwdep_unlock(struct snd_dg00x *dg00x) +{ + int err; + + spin_lock_irq(&dg00x->lock); + + if (dg00x->dev_lock_count == -1) { + dg00x->dev_lock_count = 0; + err = 0; + } else { + err = -EBADFD; + } + + spin_unlock_irq(&dg00x->lock); + + return err; +} + +static int hwdep_release(struct snd_hwdep *hwdep, struct file *file) +{ + struct snd_dg00x *dg00x = hwdep->private_data; + + spin_lock_irq(&dg00x->lock); + if (dg00x->dev_lock_count == -1) + dg00x->dev_lock_count = 0; + spin_unlock_irq(&dg00x->lock); + + return 0; +} + +static int hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct snd_dg00x *dg00x = hwdep->private_data; + + switch (cmd) { + case SNDRV_FIREWIRE_IOCTL_GET_INFO: + return hwdep_get_info(dg00x, (void __user *)arg); + case SNDRV_FIREWIRE_IOCTL_LOCK: + return hwdep_lock(dg00x); + case SNDRV_FIREWIRE_IOCTL_UNLOCK: + return hwdep_unlock(dg00x); + default: + return -ENOIOCTLCMD; + } +} + +#ifdef CONFIG_COMPAT +static int hwdep_compat_ioctl(struct snd_hwdep *hwdep, struct file *file, + unsigned int cmd, unsigned long arg) +{ + return hwdep_ioctl(hwdep, file, cmd, + (unsigned long)compat_ptr(arg)); +} +#else +#define hwdep_compat_ioctl NULL +#endif + +static const struct snd_hwdep_ops hwdep_ops = { + .read = hwdep_read, + .release = hwdep_release, + .poll = hwdep_poll, + .ioctl = hwdep_ioctl, + .ioctl_compat = hwdep_compat_ioctl, +}; + +int snd_dg00x_create_hwdep_device(struct snd_dg00x *dg00x) +{ + struct snd_hwdep *hwdep; + int err; + + err = snd_hwdep_new(dg00x->card, "Digi00x", 0, &hwdep); + if (err < 0) + return err; + + strcpy(hwdep->name, "Digi00x"); + hwdep->iface = SNDRV_HWDEP_IFACE_FW_DIGI00X; + hwdep->ops = hwdep_ops; + hwdep->private_data = dg00x; + hwdep->exclusive = true; + + return err; +} diff --git a/sound/firewire/digi00x/digi00x-pcm.c b/sound/firewire/digi00x/digi00x-pcm.c index 87c9aa234890..cac28f70aef7 100644 --- a/sound/firewire/digi00x/digi00x-pcm.c +++ b/sound/firewire/digi00x/digi00x-pcm.c @@ -118,21 +118,25 @@ static int pcm_open(struct snd_pcm_substream *substream) unsigned int rate; int err; + err = snd_dg00x_stream_lock_try(dg00x); + if (err < 0) + goto end; + err = pcm_init_hw_params(dg00x, substream); if (err < 0) - return err; + goto err_locked; /* Check current clock source. */ err = snd_dg00x_stream_get_clock(dg00x, &clock); if (err < 0) - return err; + goto err_locked; if (clock != SND_DG00X_CLOCK_INTERNAL) { err = snd_dg00x_stream_check_external_clock(dg00x, &detect); if (err < 0) - return err; + goto err_locked; if (!detect) { err = -EBUSY; - return err; + goto err_locked; } } @@ -141,18 +145,25 @@ static int pcm_open(struct snd_pcm_substream *substream) amdtp_stream_pcm_running(&dg00x->tx_stream)) { err = snd_dg00x_stream_get_external_rate(dg00x, &rate); if (err < 0) - return err; + goto err_locked; substream->runtime->hw.rate_min = rate; substream->runtime->hw.rate_max = rate; } snd_pcm_set_sync(substream); - +end: + return err; +err_locked: + snd_dg00x_stream_lock_release(dg00x); return err; } static int pcm_close(struct snd_pcm_substream *substream) { + struct snd_dg00x *dg00x = substream->private_data; + + snd_dg00x_stream_lock_release(dg00x); + return 0; } diff --git a/sound/firewire/digi00x/digi00x-stream.c b/sound/firewire/digi00x/digi00x-stream.c index 3278c3e08560..8aac31be3132 100644 --- a/sound/firewire/digi00x/digi00x-stream.c +++ b/sound/firewire/digi00x/digi00x-stream.c @@ -379,3 +379,42 @@ void snd_dg00x_stream_update_duplex(struct snd_dg00x *dg00x) amdtp_stream_update(&dg00x->tx_stream); amdtp_stream_update(&dg00x->rx_stream); } + +void snd_dg00x_stream_lock_changed(struct snd_dg00x *dg00x) +{ + dg00x->dev_lock_changed = true; + wake_up(&dg00x->hwdep_wait); +} + +int snd_dg00x_stream_lock_try(struct snd_dg00x *dg00x) +{ + int err; + + spin_lock_irq(&dg00x->lock); + + /* user land lock this */ + if (dg00x->dev_lock_count < 0) { + err = -EBUSY; + goto end; + } + + /* this is the first time */ + if (dg00x->dev_lock_count++ == 0) + snd_dg00x_stream_lock_changed(dg00x); + err = 0; +end: + spin_unlock_irq(&dg00x->lock); + return err; +} + +void snd_dg00x_stream_lock_release(struct snd_dg00x *dg00x) +{ + spin_lock_irq(&dg00x->lock); + + if (WARN_ON(dg00x->dev_lock_count <= 0)) + goto end; + if (--dg00x->dev_lock_count == 0) + snd_dg00x_stream_lock_changed(dg00x); +end: + spin_unlock_irq(&dg00x->lock); +} diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c index 166c1d43123f..cd93030df1cd 100644 --- a/sound/firewire/digi00x/digi00x.c +++ b/sound/firewire/digi00x/digi00x.c @@ -72,6 +72,8 @@ static int snd_dg00x_probe(struct fw_unit *unit, dg00x->unit = fw_unit_get(unit); mutex_init(&dg00x->mutex); + spin_lock_init(&dg00x->lock); + init_waitqueue_head(&dg00x->hwdep_wait); err = name_card(dg00x); if (err < 0) @@ -87,6 +89,10 @@ static int snd_dg00x_probe(struct fw_unit *unit, if (err < 0) goto error; + err = snd_dg00x_create_hwdep_device(dg00x); + if (err < 0) + goto error; + err = snd_card_register(card); if (err < 0) goto error; diff --git a/sound/firewire/digi00x/digi00x.h b/sound/firewire/digi00x/digi00x.h index 199064504a55..5ba531806262 100644 --- a/sound/firewire/digi00x/digi00x.h +++ b/sound/firewire/digi00x/digi00x.h @@ -22,6 +22,8 @@ #include #include #include +#include +#include #include "../lib.h" #include "../iso-resources.h" @@ -32,6 +34,7 @@ struct snd_dg00x { struct fw_unit *unit; struct mutex mutex; + spinlock_t lock; struct amdtp_stream tx_stream; struct fw_iso_resources tx_resources; @@ -40,6 +43,12 @@ struct snd_dg00x { struct fw_iso_resources rx_resources; unsigned int substreams_counter; + + /* for uapi */ + int dev_lock_count; + bool dev_lock_changed; + wait_queue_head_t hwdep_wait; + }; #define DG00X_ADDR_BASE 0xffffe0000000ull @@ -118,8 +127,13 @@ void snd_dg00x_stream_stop_duplex(struct snd_dg00x *dg00x); void snd_dg00x_stream_update_duplex(struct snd_dg00x *dg00x); void snd_dg00x_stream_destroy_duplex(struct snd_dg00x *dg00x); +void snd_dg00x_stream_lock_changed(struct snd_dg00x *dg00x); +int snd_dg00x_stream_lock_try(struct snd_dg00x *dg00x); +void snd_dg00x_stream_lock_release(struct snd_dg00x *dg00x); + void snd_dg00x_proc_init(struct snd_dg00x *dg00x); int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x); +int snd_dg00x_create_hwdep_device(struct snd_dg00x *dg00x); #endif -- cgit v1.2.3 From 44b7308871ac6fd85fc840bfa3ddb466fe7aff23 Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Wed, 30 Sep 2015 09:39:22 +0900 Subject: ALSA: firewire-digi00x: add support for asynchronous messaging Digi 002/003 family uses asynchronous transaction for messaging. The address to transmit this message is stored on a certain register. This commit allocates a range of address on OHCI 1394 host controller to handle the messaging. As long as I know, the purpose of this message seems to notify lost of synchronization. While, the meaning of content of the message is not clear. Actual examples of this messaging: * When clock source is set as internal: - 0x00007051 - 0x00007052 - 0x00007054 - 0x00007057 - 0x00007058 * When clock source is set as somewhat external: - 0x00009000 - 0x00009010 - 0x00009020 - 0x00009021 - 0x00009022 The lost often occurs when using internal clock source. In this case, users hear sounds with quite short gap every several minutes. In fact, the lost is recovered temporarily. When using with external clock source, the lost seems not to occur. The mechanism is not clear yet. Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- include/uapi/sound/firewire.h | 7 +++ sound/firewire/digi00x/Makefile | 3 +- sound/firewire/digi00x/digi00x-hwdep.c | 12 ++++- sound/firewire/digi00x/digi00x-transaction.c | 81 ++++++++++++++++++++++++++++ sound/firewire/digi00x/digi00x.c | 7 +++ sound/firewire/digi00x/digi00x.h | 7 +++ 6 files changed, 114 insertions(+), 3 deletions(-) create mode 100644 sound/firewire/digi00x/digi00x-transaction.c (limited to 'include/uapi') diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index f67d228f731b..deb041cb9af0 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -9,6 +9,7 @@ #define SNDRV_FIREWIRE_EVENT_LOCK_STATUS 0x000010cc #define SNDRV_FIREWIRE_EVENT_DICE_NOTIFICATION 0xd1ce004e #define SNDRV_FIREWIRE_EVENT_EFW_RESPONSE 0x4e617475 +#define SNDRV_FIREWIRE_EVENT_DIGI00X_MESSAGE 0x746e736c struct snd_firewire_event_common { unsigned int type; /* SNDRV_FIREWIRE_EVENT_xxx */ @@ -40,11 +41,17 @@ struct snd_firewire_event_efw_response { __be32 response[0]; /* some responses */ }; +struct snd_firewire_event_digi00x_message { + unsigned int type; + __u32 message; /* Digi00x-specific message */ +}; + union snd_firewire_event { struct snd_firewire_event_common common; struct snd_firewire_event_lock_status lock_status; struct snd_firewire_event_dice_notification dice_notification; struct snd_firewire_event_efw_response efw_response; + struct snd_firewire_event_digi00x_message digi00x_message; }; diff --git a/sound/firewire/digi00x/Makefile b/sound/firewire/digi00x/Makefile index 5bc3c7780a51..28e3d137ef57 100644 --- a/sound/firewire/digi00x/Makefile +++ b/sound/firewire/digi00x/Makefile @@ -1,3 +1,4 @@ snd-firewire-digi00x-objs := amdtp-dot.o digi00x-stream.o digi00x-proc.o \ - digi00x-pcm.o digi00x-hwdep.o digi00x.o + digi00x-pcm.o digi00x-hwdep.o \ + digi00x-transaction.o digi00x.o obj-$(CONFIG_SND_FIREWIRE_DIGI00X) += snd-firewire-digi00x.o diff --git a/sound/firewire/digi00x/digi00x-hwdep.c b/sound/firewire/digi00x/digi00x-hwdep.c index d629e415dc8b..f188e4758fd2 100644 --- a/sound/firewire/digi00x/digi00x-hwdep.c +++ b/sound/firewire/digi00x/digi00x-hwdep.c @@ -12,6 +12,7 @@ * 1.get firewire node information * 2.get notification about starting/stopping stream * 3.lock/unlock stream + * 4.get asynchronous messaging */ #include "digi00x.h" @@ -25,7 +26,7 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, spin_lock_irq(&dg00x->lock); - while (!dg00x->dev_lock_changed) { + while (!dg00x->dev_lock_changed && dg00x->msg == 0) { prepare_to_wait(&dg00x->hwdep_wait, &wait, TASK_INTERRUPTIBLE); spin_unlock_irq(&dg00x->lock); schedule(); @@ -42,6 +43,13 @@ static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, dg00x->dev_lock_changed = false; count = min_t(long, count, sizeof(event.lock_status)); + } else { + event.digi00x_message.type = + SNDRV_FIREWIRE_EVENT_DIGI00X_MESSAGE; + event.digi00x_message.message = dg00x->msg; + dg00x->msg = 0; + + count = min_t(long, count, sizeof(event.digi00x_message)); } spin_unlock_irq(&dg00x->lock); @@ -61,7 +69,7 @@ static unsigned int hwdep_poll(struct snd_hwdep *hwdep, struct file *file, poll_wait(file, &dg00x->hwdep_wait, wait); spin_lock_irq(&dg00x->lock); - if (dg00x->dev_lock_changed) + if (dg00x->dev_lock_changed || dg00x->msg) events = POLLIN | POLLRDNORM; else events = 0; diff --git a/sound/firewire/digi00x/digi00x-transaction.c b/sound/firewire/digi00x/digi00x-transaction.c new file mode 100644 index 000000000000..49372901a1e1 --- /dev/null +++ b/sound/firewire/digi00x/digi00x-transaction.c @@ -0,0 +1,81 @@ +/* + * digi00x-transaction.c - a part of driver for Digidesign Digi 002/003 family + * + * Copyright (c) 2014-2015 Takashi Sakamoto + * + * Licensed under the terms of the GNU General Public License, version 2. + */ + +#include +#include "digi00x.h" + +static void handle_unknown_message(struct snd_dg00x *dg00x, + unsigned long long offset, __be32 *buf) +{ + unsigned long flags; + + spin_lock_irqsave(&dg00x->lock, flags); + dg00x->msg = be32_to_cpu(*buf); + spin_unlock_irqrestore(&dg00x->lock, flags); + + wake_up(&dg00x->hwdep_wait); +} + +static void handle_message(struct fw_card *card, struct fw_request *request, + int tcode, int destination, int source, + int generation, unsigned long long offset, + void *data, size_t length, void *callback_data) +{ + struct snd_dg00x *dg00x = callback_data; + __be32 *buf = (__be32 *)data; + + if (offset == dg00x->async_handler.offset) + handle_unknown_message(dg00x, offset, buf); + + fw_send_response(card, request, RCODE_COMPLETE); +} + +int snd_dg00x_transaction_reregister(struct snd_dg00x *dg00x) +{ + struct fw_device *device = fw_parent_device(dg00x->unit); + __be32 data[2]; + + /* Unknown. 4bytes. */ + data[0] = cpu_to_be32((device->card->node_id << 16) | + (dg00x->async_handler.offset >> 32)); + data[1] = cpu_to_be32(dg00x->async_handler.offset); + return snd_fw_transaction(dg00x->unit, TCODE_WRITE_BLOCK_REQUEST, + DG00X_ADDR_BASE + DG00X_OFFSET_MESSAGE_ADDR, + &data, sizeof(data), 0); +} + +int snd_dg00x_transaction_register(struct snd_dg00x *dg00x) +{ + static const struct fw_address_region resp_register_region = { + .start = 0xffffe0000000ull, + .end = 0xffffe000ffffull, + }; + int err; + + dg00x->async_handler.length = 4; + dg00x->async_handler.address_callback = handle_message; + dg00x->async_handler.callback_data = dg00x; + + err = fw_core_add_address_handler(&dg00x->async_handler, + &resp_register_region); + if (err < 0) + return err; + + err = snd_dg00x_transaction_reregister(dg00x); + if (err < 0) { + fw_core_remove_address_handler(&dg00x->async_handler); + dg00x->async_handler.address_callback = NULL; + } + + return err; +} + +void snd_dg00x_transaction_unregister(struct snd_dg00x *dg00x) +{ + fw_core_remove_address_handler(&dg00x->async_handler); +} diff --git a/sound/firewire/digi00x/digi00x.c b/sound/firewire/digi00x/digi00x.c index cd93030df1cd..34937a26c198 100644 --- a/sound/firewire/digi00x/digi00x.c +++ b/sound/firewire/digi00x/digi00x.c @@ -46,6 +46,7 @@ static void dg00x_card_free(struct snd_card *card) struct snd_dg00x *dg00x = card->private_data; snd_dg00x_stream_destroy_duplex(dg00x); + snd_dg00x_transaction_unregister(dg00x); fw_unit_put(dg00x->unit); @@ -93,6 +94,10 @@ static int snd_dg00x_probe(struct fw_unit *unit, if (err < 0) goto error; + err = snd_dg00x_transaction_register(dg00x); + if (err < 0) + goto error; + err = snd_card_register(card); if (err < 0) goto error; @@ -109,6 +114,8 @@ static void snd_dg00x_update(struct fw_unit *unit) { struct snd_dg00x *dg00x = dev_get_drvdata(&unit->device); + snd_dg00x_transaction_reregister(dg00x); + mutex_lock(&dg00x->mutex); snd_dg00x_stream_update_duplex(dg00x); mutex_unlock(&dg00x->mutex); diff --git a/sound/firewire/digi00x/digi00x.h b/sound/firewire/digi00x/digi00x.h index 5ba531806262..b960c868b59b 100644 --- a/sound/firewire/digi00x/digi00x.h +++ b/sound/firewire/digi00x/digi00x.h @@ -49,6 +49,9 @@ struct snd_dg00x { bool dev_lock_changed; wait_queue_head_t hwdep_wait; + /* For asynchronous messages. */ + struct fw_address_handler async_handler; + u32 msg; }; #define DG00X_ADDR_BASE 0xffffe0000000ull @@ -110,6 +113,10 @@ int amdtp_dot_add_pcm_hw_constraints(struct amdtp_stream *s, struct snd_pcm_runtime *runtime); void amdtp_dot_set_pcm_format(struct amdtp_stream *s, snd_pcm_format_t format); +int snd_dg00x_transaction_register(struct snd_dg00x *dg00x); +int snd_dg00x_transaction_reregister(struct snd_dg00x *dg00x); +void snd_dg00x_transaction_unregister(struct snd_dg00x *dg00x); + extern const unsigned int snd_dg00x_stream_rates[SND_DG00X_RATE_COUNT]; extern const unsigned int snd_dg00x_stream_pcm_channels[SND_DG00X_RATE_COUNT]; int snd_dg00x_stream_get_external_rate(struct snd_dg00x *dg00x, -- cgit v1.2.3 From 529a7960307012f66faec6426747cf61d320265c Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sun, 13 Sep 2015 13:41:29 -0300 Subject: [media] videodev2.h: add support for the DCI-P3 colorspace This colorspace is used for cinema projectors and is supported by the DisplayPort standard. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 3228fbebcd63..4900e154eca7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -229,6 +229,9 @@ enum v4l2_colorspace { /* Raw colorspace: for RAW unprocessed images */ V4L2_COLORSPACE_RAW = 11, + + /* DCI-P3 colorspace, used by cinema projectors */ + V4L2_COLORSPACE_DCI_P3 = 12, }; /* @@ -256,6 +259,8 @@ enum v4l2_xfer_func { * V4L2_COLORSPACE_SMPTE240M: V4L2_XFER_FUNC_SMPTE240M * * V4L2_COLORSPACE_RAW: V4L2_XFER_FUNC_NONE + * + * V4L2_COLORSPACE_DCI_P3: V4L2_XFER_FUNC_DCI_P3 */ V4L2_XFER_FUNC_DEFAULT = 0, V4L2_XFER_FUNC_709 = 1, @@ -263,6 +268,7 @@ enum v4l2_xfer_func { V4L2_XFER_FUNC_ADOBERGB = 3, V4L2_XFER_FUNC_SMPTE240M = 4, V4L2_XFER_FUNC_NONE = 5, + V4L2_XFER_FUNC_DCI_P3 = 6, }; /* @@ -272,9 +278,10 @@ enum v4l2_xfer_func { #define V4L2_MAP_XFER_FUNC_DEFAULT(colsp) \ ((colsp) == V4L2_COLORSPACE_ADOBERGB ? V4L2_XFER_FUNC_ADOBERGB : \ ((colsp) == V4L2_COLORSPACE_SMPTE240M ? V4L2_XFER_FUNC_SMPTE240M : \ - ((colsp) == V4L2_COLORSPACE_RAW ? V4L2_XFER_FUNC_NONE : \ - ((colsp) == V4L2_COLORSPACE_SRGB || (colsp) == V4L2_COLORSPACE_JPEG ? \ - V4L2_XFER_FUNC_SRGB : V4L2_XFER_FUNC_709)))) + ((colsp) == V4L2_COLORSPACE_DCI_P3 ? V4L2_XFER_FUNC_DCI_P3 : \ + ((colsp) == V4L2_COLORSPACE_RAW ? V4L2_XFER_FUNC_NONE : \ + ((colsp) == V4L2_COLORSPACE_SRGB || (colsp) == V4L2_COLORSPACE_JPEG ? \ + V4L2_XFER_FUNC_SRGB : V4L2_XFER_FUNC_709))))) enum v4l2_ycbcr_encoding { /* @@ -285,7 +292,7 @@ enum v4l2_ycbcr_encoding { * V4L2_COLORSPACE_470_SYSTEM_BG, V4L2_COLORSPACE_ADOBERGB and * V4L2_COLORSPACE_JPEG: V4L2_YCBCR_ENC_601 * - * V4L2_COLORSPACE_REC709: V4L2_YCBCR_ENC_709 + * V4L2_COLORSPACE_REC709 and V4L2_COLORSPACE_DCI_P3: V4L2_YCBCR_ENC_709 * * V4L2_COLORSPACE_SRGB: V4L2_YCBCR_ENC_SYCC * @@ -325,7 +332,8 @@ enum v4l2_ycbcr_encoding { * This depends on the colorspace. */ #define V4L2_MAP_YCBCR_ENC_DEFAULT(colsp) \ - ((colsp) == V4L2_COLORSPACE_REC709 ? V4L2_YCBCR_ENC_709 : \ + (((colsp) == V4L2_COLORSPACE_REC709 || \ + (colsp) == V4L2_COLORSPACE_DCI_P3) ? V4L2_YCBCR_ENC_709 : \ ((colsp) == V4L2_COLORSPACE_BT2020 ? V4L2_YCBCR_ENC_BT2020 : \ ((colsp) == V4L2_COLORSPACE_SMPTE240M ? V4L2_YCBCR_ENC_SMPTE240M : \ V4L2_YCBCR_ENC_601))) -- cgit v1.2.3 From 2bdd28017e0b4747915265dc294ee0165d52c12e Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Sun, 13 Sep 2015 16:15:18 -0300 Subject: [media] videodev2.h: add SMPTE 2084 transfer function define CEA-861.3 adds support for the SMPTE 2084 Electro-Optical Transfer Function as can be used in HDR displays. Add a define for this in videodev2.h. Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 4900e154eca7..80314ad47431 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -269,6 +269,7 @@ enum v4l2_xfer_func { V4L2_XFER_FUNC_SMPTE240M = 4, V4L2_XFER_FUNC_NONE = 5, V4L2_XFER_FUNC_DCI_P3 = 6, + V4L2_XFER_FUNC_SMPTE2084 = 7, }; /* -- cgit v1.2.3 From d9e7d2285a6787b61e8741dddbbf4d6702afa637 Mon Sep 17 00:00:00 2001 From: Ricardo Ribalda Date: Fri, 21 Aug 2015 10:19:20 -0300 Subject: [media] videodev2.h: Fix typo in comment Referenced file has moved Signed-off-by: Ricardo Ribalda Delgado Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 80314ad47431..92d65af41631 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -2280,7 +2280,7 @@ struct v4l2_create_buffers { #define VIDIOC_QUERY_EXT_CTRL _IOWR('V', 103, struct v4l2_query_ext_ctrl) /* Reminder: when adding new ioctls please add support for them to - drivers/media/video/v4l2-compat-ioctl32.c as well! */ + drivers/media/v4l2-core/v4l2-compat-ioctl32.c as well! */ #define BASE_VIDIOC_PRIVATE 192 /* 192-255 are private */ -- cgit v1.2.3 From 49df6397edfc5a8ba8ca813b51fb9729d8e94b40 Mon Sep 17 00:00:00 2001 From: Steve Rutherford Date: Wed, 29 Jul 2015 23:21:40 -0700 Subject: KVM: x86: Split the APIC from the rest of IRQCHIP. First patch in a series which enables the relocation of the PIC/IOAPIC to userspace. Adds capability KVM_CAP_SPLIT_IRQCHIP; KVM_CAP_SPLIT_IRQCHIP enables the construction of LAPICs without the rest of the irqchip. Compile tested for x86. Signed-off-by: Steve Rutherford Suggested-by: Andrew Honig Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 17 +++++++++++++++++ arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/i8254.c | 4 +++- arch/x86/kvm/ioapic.h | 8 ++++++++ arch/x86/kvm/irq.h | 11 ++++++++++- arch/x86/kvm/irq_comm.c | 9 ++++++++- arch/x86/kvm/lapic.c | 6 ++++-- arch/x86/kvm/x86.c | 23 +++++++++++++++++++++-- include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + 10 files changed, 75 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index d9ecceea5a02..43e0816d0de1 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3627,6 +3627,23 @@ struct { KVM handlers should exit to userspace with rc = -EREMOTE. +7.5 KVM_CAP_SPLIT_IRQCHIP + +Architectures: x86 +Parameters: None +Returns: 0 on success, -1 on error + +Create a local apic for each processor in the kernel. This can be used +instead of KVM_CREATE_IRQCHIP if the userspace VMM wishes to emulate the +IOAPIC and PIC (and also the PIT, even though this has to be enabled +separately). + +This supersedes KVM_CREATE_IRQCHIP, creating only local APICs, but no in kernel +IOAPIC or PIC. This also enables in kernel routing of interrupt requests. + +Fails if VCPU has already been created, or if the irqchip is already in the +kernel (i.e. KVM_CREATE_IRQCHIP has already been called). + 8. Other capabilities. ---------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index a0ef289d5a86..befcf555bddc 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -684,6 +684,8 @@ struct kvm_arch { u32 bsp_vcpu_id; u64 disabled_quirks; + + bool irqchip_split; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c index f90952f64e79..08116ff227cc 100644 --- a/arch/x86/kvm/i8254.c +++ b/arch/x86/kvm/i8254.c @@ -35,6 +35,7 @@ #include #include +#include "ioapic.h" #include "irq.h" #include "i8254.h" #include "x86.h" @@ -333,7 +334,8 @@ static void create_pit_timer(struct kvm *kvm, u32 val, int is_period) struct kvm_kpit_state *ps = &kvm->arch.vpit->pit_state; s64 interval; - if (!irqchip_in_kernel(kvm) || ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) + if (!ioapic_in_kernel(kvm) || + ps->flags & KVM_PIT_FLAGS_HPET_LEGACY) return; interval = muldiv64(val, NSEC_PER_SEC, KVM_PIT_FREQ); diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h index bf36d66a1951..a8842c0dee73 100644 --- a/arch/x86/kvm/ioapic.h +++ b/arch/x86/kvm/ioapic.h @@ -97,6 +97,14 @@ static inline struct kvm_ioapic *ioapic_irqchip(struct kvm *kvm) return kvm->arch.vioapic; } +static inline int ioapic_in_kernel(struct kvm *kvm) +{ + int ret; + + ret = (ioapic_irqchip(kvm) != NULL); + return ret; +} + void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu); bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source, int short_hand, unsigned int dest, int dest_mode); diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h index 9e6e7e04de98..2f9703dcd913 100644 --- a/arch/x86/kvm/irq.h +++ b/arch/x86/kvm/irq.h @@ -83,13 +83,22 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm) return kvm->arch.vpic; } +static inline int irqchip_split(struct kvm *kvm) +{ + return kvm->arch.irqchip_split; +} + static inline int irqchip_in_kernel(struct kvm *kvm) { struct kvm_pic *vpic = pic_irqchip(kvm); + bool ret; + + ret = (vpic != NULL); + ret |= irqchip_split(kvm); /* Read vpic before kvm->irq_routing. */ smp_rmb(); - return vpic != NULL; + return ret; } static inline int lapic_in_kernel(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c index 9efff9e5b58c..67f6b62a6814 100644 --- a/arch/x86/kvm/irq_comm.c +++ b/arch/x86/kvm/irq_comm.c @@ -208,7 +208,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id) goto unlock; } clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap); - if (!irqchip_in_kernel(kvm)) + if (!ioapic_in_kernel(kvm)) goto unlock; kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id); @@ -328,3 +328,10 @@ int kvm_setup_default_irq_routing(struct kvm *kvm) return kvm_set_irq_routing(kvm, default_routing, ARRAY_SIZE(default_routing), 0); } + +static const struct kvm_irq_routing_entry empty_routing[] = {}; + +int kvm_setup_empty_irq_routing(struct kvm *kvm) +{ + return kvm_set_irq_routing(kvm, empty_routing, 0, 0); +} diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c4bcc86d6dc4..e05946c36b87 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -209,7 +209,8 @@ out: if (old) kfree_rcu(old, rcu); - kvm_vcpu_request_scan_ioapic(kvm); + if (ioapic_in_kernel(kvm)) + kvm_vcpu_request_scan_ioapic(kvm); } static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val) @@ -1845,7 +1846,8 @@ void kvm_apic_post_state_restore(struct kvm_vcpu *vcpu, kvm_x86_ops->hwapic_isr_update(vcpu->kvm, apic_find_highest_isr(apic)); kvm_make_request(KVM_REQ_EVENT, vcpu); - kvm_rtc_eoi_tracking_restore_one(vcpu); + if (ioapic_in_kernel(vcpu->kvm)) + kvm_rtc_eoi_tracking_restore_one(vcpu); } void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 28c98c8f9d1c..f720774a4797 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2448,6 +2448,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_DISABLE_QUIRKS: case KVM_CAP_SET_BOOT_CPU_ID: + case KVM_CAP_SPLIT_IRQCHIP: #ifdef CONFIG_KVM_DEVICE_ASSIGNMENT case KVM_CAP_ASSIGN_DEV_IRQ: case KVM_CAP_PCI_2_3: @@ -3555,6 +3556,24 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, kvm->arch.disabled_quirks = cap->args[0]; r = 0; break; + case KVM_CAP_SPLIT_IRQCHIP: { + mutex_lock(&kvm->lock); + r = -EEXIST; + if (irqchip_in_kernel(kvm)) + goto split_irqchip_unlock; + if (atomic_read(&kvm->online_vcpus)) + goto split_irqchip_unlock; + r = kvm_setup_empty_irq_routing(kvm); + if (r) + goto split_irqchip_unlock; + /* Pairs with irqchip_in_kernel. */ + smp_wmb(); + kvm->arch.irqchip_split = true; + r = 0; +split_irqchip_unlock: + mutex_unlock(&kvm->lock); + break; + } default: r = -EINVAL; break; @@ -3668,7 +3687,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto get_irqchip_out; r = kvm_vm_ioctl_get_irqchip(kvm, chip); if (r) @@ -3692,7 +3711,7 @@ long kvm_arch_vm_ioctl(struct file *filp, } r = -ENXIO; - if (!irqchip_in_kernel(kvm)) + if (!irqchip_in_kernel(kvm) || irqchip_split(kvm)) goto set_irqchip_out; r = kvm_vm_ioctl_set_irqchip(kvm, chip); if (r) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1bef9e21e725..354f147647ab 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1002,6 +1002,7 @@ static inline int mmu_notifier_retry(struct kvm *kvm, unsigned long mmu_seq) #endif int kvm_setup_default_irq_routing(struct kvm *kvm); +int kvm_setup_empty_irq_routing(struct kvm *kvm); int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *entries, unsigned nr, diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a9256f0331ae..ed00f8fc9ea2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -824,6 +824,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_MULTI_ADDRESS_SPACE 118 #define KVM_CAP_GUEST_DEBUG_HW_BPS 119 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120 +#define KVM_CAP_SPLIT_IRQCHIP 121 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From 7543a635aa09eb138b2cbf60ac3ff19503ae6954 Mon Sep 17 00:00:00 2001 From: Steve Rutherford Date: Wed, 29 Jul 2015 23:21:41 -0700 Subject: KVM: x86: Add KVM exit for IOAPIC EOIs Adds KVM_EXIT_IOAPIC_EOI which allows the kernel to EOI level-triggered IOAPIC interrupts. Uses a per VCPU exit bitmap to decide whether or not the IOAPIC needs to be informed (which is identical to the EOI_EXIT_BITMAP field used by modern x86 processors, but can also be used to elide kvm IOAPIC EOI exits on older processors). [Note: A prototype using ResampleFDs found that decoupling the EOI from the VCPU's thread made it possible for the VCPU to not see a recent EOI after reentering the guest. This does not match real hardware.] Compile tested for Intel x86. Signed-off-by: Steve Rutherford Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 12 ++++++++++++ arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/lapic.c | 24 +++++++++++++++++------- arch/x86/kvm/x86.c | 11 +++++++++++ include/linux/kvm_host.h | 2 +- include/uapi/linux/kvm.h | 5 +++++ 6 files changed, 48 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 43e0816d0de1..0d14bf5db534 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -3309,6 +3309,18 @@ Valid values for 'type' are: to ignore the request, or to gather VM memory core dump and/or reset/shutdown of the VM. + /* KVM_EXIT_IOAPIC_EOI */ + struct { + __u8 vector; + } eoi; + +Indicates that the VCPU's in-kernel local APIC received an EOI for a +level-triggered IOAPIC interrupt. This exit only triggers when the +IOAPIC is implemented in userspace (i.e. KVM_CAP_SPLIT_IRQCHIP is enabled); +the userspace IOAPIC should process the EOI and retrigger the interrupt if +it is still asserted. Vector is the LAPIC interrupt vector for which the +EOI was received. + /* Fix the size of the union. */ char padding[256]; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index befcf555bddc..af09fa1d1be7 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -574,6 +574,8 @@ struct kvm_vcpu_arch { struct { bool pv_unhalted; } pv; + + int pending_ioapic_eoi; }; struct kvm_lpage_info { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index e05946c36b87..ef70f6f3a37a 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -877,15 +877,25 @@ static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector) static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector) { - if (kvm_ioapic_handles_vector(apic, vector)) { - int trigger_mode; - if (apic_test_vector(vector, apic->regs + APIC_TMR)) - trigger_mode = IOAPIC_LEVEL_TRIG; - else - trigger_mode = IOAPIC_EDGE_TRIG; + int trigger_mode; + + /* Eoi the ioapic only if the ioapic doesn't own the vector. */ + if (!kvm_ioapic_handles_vector(apic, vector)) + return; - kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); + /* Request a KVM exit to inform the userspace IOAPIC. */ + if (irqchip_split(apic->vcpu->kvm)) { + apic->vcpu->arch.pending_ioapic_eoi = vector; + kvm_make_request(KVM_REQ_IOAPIC_EOI_EXIT, apic->vcpu); + return; } + + if (apic_test_vector(vector, apic->regs + APIC_TMR)) + trigger_mode = IOAPIC_LEVEL_TRIG; + else + trigger_mode = IOAPIC_EDGE_TRIG; + + kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode); } static int apic_set_eoi(struct kvm_lapic *apic) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f720774a4797..27429daa054e 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6271,6 +6271,17 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu) kvm_pmu_handle_event(vcpu); if (kvm_check_request(KVM_REQ_PMI, vcpu)) kvm_pmu_deliver_pmi(vcpu); + if (kvm_check_request(KVM_REQ_IOAPIC_EOI_EXIT, vcpu)) { + BUG_ON(vcpu->arch.pending_ioapic_eoi > 255); + if (test_bit(vcpu->arch.pending_ioapic_eoi, + (void *) vcpu->arch.eoi_exit_bitmap)) { + vcpu->run->exit_reason = KVM_EXIT_IOAPIC_EOI; + vcpu->run->eoi.vector = + vcpu->arch.pending_ioapic_eoi; + r = 0; + goto out; + } + } if (kvm_check_request(KVM_REQ_SCAN_IOAPIC, vcpu)) vcpu_scan_ioapic(vcpu); if (kvm_check_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu)) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 354f147647ab..3b33215ed447 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -140,6 +140,7 @@ static inline bool is_error_page(struct page *page) #define KVM_REQ_APIC_PAGE_RELOAD 25 #define KVM_REQ_SMI 26 #define KVM_REQ_HV_CRASH 27 +#define KVM_REQ_IOAPIC_EOI_EXIT 28 #define KVM_USERSPACE_IRQ_SOURCE_ID 0 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 @@ -1146,4 +1147,3 @@ static inline void kvm_vcpu_set_dy_eligible(struct kvm_vcpu *vcpu, bool val) } #endif /* CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT */ #endif - diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ed00f8fc9ea2..12e3afbf0f47 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -183,6 +183,7 @@ struct kvm_s390_skeys { #define KVM_EXIT_EPR 23 #define KVM_EXIT_SYSTEM_EVENT 24 #define KVM_EXIT_S390_STSI 25 +#define KVM_EXIT_IOAPIC_EOI 26 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -333,6 +334,10 @@ struct kvm_run { __u8 sel1; __u16 sel2; } s390_stsi; + /* KVM_EXIT_IOAPIC_EOI */ + struct { + __u8 vector; + } eoi; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From e9ea5069d9e569c32ab913c39467df32e056b3a7 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Tue, 15 Sep 2015 14:41:59 +0800 Subject: kvm: add capability for any-length ioeventfds Cc: Gleb Natapov Cc: Paolo Bonzini Signed-off-by: Jason Wang Signed-off-by: Paolo Bonzini --- Documentation/virtual/kvm/api.txt | 6 +++++- include/uapi/linux/kvm.h | 1 + virt/kvm/eventfd.c | 4 +--- virt/kvm/kvm_main.c | 1 + 4 files changed, 8 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index e3e9c41721a2..34cc068e81ea 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -1604,7 +1604,7 @@ provided event instead of triggering an exit. struct kvm_ioeventfd { __u64 datamatch; __u64 addr; /* legal pio/mmio address */ - __u32 len; /* 1, 2, 4, or 8 bytes */ + __u32 len; /* 0, 1, 2, 4, or 8 bytes */ __s32 fd; __u32 flags; __u8 pad[36]; @@ -1627,6 +1627,10 @@ to the registered address is equal to datamatch in struct kvm_ioeventfd. For virtio-ccw devices, addr contains the subchannel id and datamatch the virtqueue index. +With KVM_CAP_IOEVENTFD_ANY_LENGTH, a zero length ioeventfd is allowed, and +the kernel will ignore the length of guest write and may get a faster vmexit. +The speedup may only apply to specific architectures, but the ioeventfd will +work anyway. 4.60 KVM_DIRTY_TLB diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 12e3afbf0f47..03f3618612aa 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -830,6 +830,7 @@ struct kvm_ppc_smmu_info { #define KVM_CAP_GUEST_DEBUG_HW_BPS 119 #define KVM_CAP_GUEST_DEBUG_HW_WPS 120 #define KVM_CAP_SPLIT_IRQCHIP 121 +#define KVM_CAP_IOEVENTFD_ANY_LENGTH 122 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c index 79db45336e3a..ac89299b8699 100644 --- a/virt/kvm/eventfd.c +++ b/virt/kvm/eventfd.c @@ -914,9 +914,7 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args) return -EINVAL; /* ioeventfd with no length can't be combined with DATAMATCH */ - if (!args->len && - args->flags & (KVM_IOEVENTFD_FLAG_PIO | - KVM_IOEVENTFD_FLAG_DATAMATCH)) + if (!args->len && (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH)) return -EINVAL; ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 23116dcb2129..afd7ae6aec65 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2718,6 +2718,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IRQFD: case KVM_CAP_IRQFD_RESAMPLE: #endif + case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: return 1; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING -- cgit v1.2.3 From 9ff42d10c3b3e26d9555878f31b9a2e5c24efa57 Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Thu, 1 Oct 2015 15:36:51 -0700 Subject: userfaultfd: remove kernel header include from uapi header As include/uapi/linux/userfaultfd.h is a user visible header file, it should not include kernel-exclusive header files. So trying to build the userfaultfd test program from the selftests directory fails, since it contains a reference to linux/compiler.h. As it turns out, that header is not really needed there, so we can simply remove it to fix that issue. Signed-off-by: Andre Przywara Cc: Andrea Arcangeli Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/userfaultfd.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h index df0e09bb7dd5..9057d7af3ae1 100644 --- a/include/uapi/linux/userfaultfd.h +++ b/include/uapi/linux/userfaultfd.h @@ -11,8 +11,6 @@ #include -#include - #define UFFD_API ((__u64)0xAA) /* * After implementing the respective features it will become: -- cgit v1.2.3 From 2217d7c68e5caf50ec86b8c75c76bf06eb4b2c45 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Fri, 22 May 2015 14:31:37 +0100 Subject: drivers: firmware: psci: add INVALID_ADDRESS return value PSCI 1.0 introduces the INVALID_ADDRESS return value for functions that take an address as input parameter (eg CPU_SUSPEND). This patch adds INVALID_ADDRESS return value to kernel code and updates the PSCI to linux error conversion to take it into account. The kernel error value associated to INVALID_ADDRESS is set to the error returned when the PSCI error code is INVALID_PARAMETERS to comply with current call sites expected return value, given that the kernel at present has no use for the additional error information reported. Signed-off-by: Lorenzo Pieralisi Acked-by: Sudeep Holla Acked-by: Mark Rutland Tested-by: Jisheng Zhang --- drivers/firmware/psci.c | 1 + include/uapi/linux/psci.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 42700f09a8c5..0821e332c85a 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -78,6 +78,7 @@ static int psci_to_linux_errno(int errno) case PSCI_RET_NOT_SUPPORTED: return -EOPNOTSUPP; case PSCI_RET_INVALID_PARAMS: + case PSCI_RET_INVALID_ADDRESS: return -EINVAL; case PSCI_RET_DENIED: return -EPERM; diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 310d83e0a91b..64469e64688f 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -86,5 +86,6 @@ #define PSCI_RET_INTERNAL_FAILURE -6 #define PSCI_RET_NOT_PRESENT -7 #define PSCI_RET_DISABLED -8 +#define PSCI_RET_INVALID_ADDRESS -9 #endif /* _UAPI_LINUX_PSCI_H */ -- cgit v1.2.3 From 5f004e0c9fb152a080b47d06dc48bdd29765a734 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 26 May 2015 17:06:21 +0100 Subject: drivers: firmware: psci: add PSCI_FEATURES call PSCI v1.0 introduces a PSCI_FEATURES call that allows to probe for features related to a specific function identifier. This patch adds PSCI_FEATURES support to the PSCI firmware layer. Signed-off-by: Lorenzo Pieralisi Tested-by: Jisheng Zhang Cc: Mark Rutland --- drivers/firmware/psci.c | 6 ++++++ include/uapi/linux/psci.h | 2 ++ 2 files changed, 8 insertions(+) (limited to 'include/uapi') diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 3157eb0ef300..cec948b4ccd5 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -197,6 +197,12 @@ static void psci_sys_poweroff(void) invoke_psci_fn(PSCI_0_2_FN_SYSTEM_OFF, 0, 0, 0); } +static int __init psci_features(u32 psci_func_id) +{ + return invoke_psci_fn(PSCI_1_0_FN_PSCI_FEATURES, + psci_func_id, 0, 0); +} + /* * Detect the presence of a resident Trusted OS which may cause CPU_OFF to * return DENIED (which would be fatal). diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 64469e64688f..187b828d77b3 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -46,6 +46,8 @@ #define PSCI_0_2_FN64_MIGRATE PSCI_0_2_FN64(5) #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7) +#define PSCI_1_0_FN_PSCI_FEATURES PSCI_0_2_FN(10) + /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff #define PSCI_0_2_POWER_STATE_ID_SHIFT 0 -- cgit v1.2.3 From a5c00bb28da0bb34f901d090839fc448246aa996 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 26 May 2015 17:10:32 +0100 Subject: drivers: firmware: psci: add extended stateid power_state support PSCI v1.0 augmented the power_state parameter format specification (extended stateid) and introduced a way to probe it through the PSCI_FEATURES interface. This patch implements code that detects the power_state format at run-time through the PSCI_FEATURES interface, so that the power_state argument can be properly detected and validated in the kernel according to the information provided through firmware. Signed-off-by: Lorenzo Pieralisi Tested-by: Jisheng Zhang Cc: Mark Rutland --- drivers/firmware/psci.c | 34 ++++++++++++++++++++++++++++++++-- include/uapi/linux/psci.h | 12 ++++++++++++ 2 files changed, 44 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index cec948b4ccd5..384224320455 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -75,14 +75,34 @@ static u32 psci_function_id[PSCI_FN_MAX]; PSCI_0_2_POWER_STATE_TYPE_MASK | \ PSCI_0_2_POWER_STATE_AFFL_MASK) +#define PSCI_1_0_EXT_POWER_STATE_MASK \ + (PSCI_1_0_EXT_POWER_STATE_ID_MASK | \ + PSCI_1_0_EXT_POWER_STATE_TYPE_MASK) + +static u32 psci_cpu_suspend_feature; + +static inline bool psci_has_ext_power_state(void) +{ + return psci_cpu_suspend_feature & + PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK; +} + bool psci_power_state_loses_context(u32 state) { - return state & PSCI_0_2_POWER_STATE_TYPE_MASK; + const u32 mask = psci_has_ext_power_state() ? + PSCI_1_0_EXT_POWER_STATE_TYPE_MASK : + PSCI_0_2_POWER_STATE_TYPE_MASK; + + return state & mask; } bool psci_power_state_is_valid(u32 state) { - return !(state & ~PSCI_0_2_POWER_STATE_MASK); + const u32 valid_mask = psci_has_ext_power_state() ? + PSCI_1_0_EXT_POWER_STATE_MASK : + PSCI_0_2_POWER_STATE_MASK; + + return !(state & ~valid_mask); } static int psci_to_linux_errno(int errno) @@ -203,6 +223,14 @@ static int __init psci_features(u32 psci_func_id) psci_func_id, 0, 0); } +static void __init psci_init_cpu_suspend(void) +{ + int feature = psci_features(psci_function_id[PSCI_FN_CPU_SUSPEND]); + + if (feature != PSCI_RET_NOT_SUPPORTED) + psci_cpu_suspend_feature = feature; +} + /* * Detect the presence of a resident Trusted OS which may cause CPU_OFF to * return DENIED (which would be fatal). @@ -287,6 +315,8 @@ static int __init psci_probe(void) psci_init_migrate(); + psci_init_cpu_suspend(); + return 0; } diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 187b828d77b3..0a9485f3c6c3 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -58,6 +58,13 @@ #define PSCI_0_2_POWER_STATE_AFFL_MASK \ (0x3 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) +/* PSCI extended power state encoding for CPU_SUSPEND function */ +#define PSCI_1_0_EXT_POWER_STATE_ID_MASK 0xfffffff +#define PSCI_1_0_EXT_POWER_STATE_ID_SHIFT 0 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT 30 +#define PSCI_1_0_EXT_POWER_STATE_TYPE_MASK \ + (0x1 << PSCI_1_0_EXT_POWER_STATE_TYPE_SHIFT) + /* PSCI v0.2 affinity level state returned by AFFINITY_INFO */ #define PSCI_0_2_AFFINITY_LEVEL_ON 0 #define PSCI_0_2_AFFINITY_LEVEL_OFF 1 @@ -78,6 +85,11 @@ #define PSCI_VERSION_MINOR(ver) \ ((ver) & PSCI_VERSION_MINOR_MASK) +/* PSCI features decoding (>=1.0) */ +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT 1 +#define PSCI_1_0_FEATURES_CPU_SUSPEND_PF_MASK \ + (0x1 << PSCI_1_0_FEATURES_CPU_SUSPEND_PF_SHIFT) + /* PSCI return values (inclusive of all PSCI versions) */ #define PSCI_RET_SUCCESS 0 #define PSCI_RET_NOT_SUPPORTED -1 -- cgit v1.2.3 From faf7ec4a92c0231d1079177095077c162eb9b466 Mon Sep 17 00:00:00 2001 From: Sudeep Holla Date: Thu, 18 Jun 2015 15:41:34 +0100 Subject: drivers: firmware: psci: add system suspend support PSCI v1.0 introduces a new API called PSCI_SYSTEM_SUSPEND. This API provides the mechanism by which the calling OS can request entry into the deepest possible system sleep state. It meets all the necessary preconditions for entering suspend to RAM state in Linux. This patch adds support for PSCI_SYSTEM_SUSPEND in psci firmware and registers a psci system suspend operation to implement the suspend-to-RAM(s2r) in a generic way on all the platforms implementing PSCI. Cc: Mark Rutland Cc: Lorenzo Pieralisi Signed-off-by: Sudeep Holla Acked-by: Lorenzo Pieralisi --- drivers/firmware/psci.c | 33 +++++++++++++++++++++++++++++++++ include/uapi/linux/psci.h | 3 +++ 2 files changed, 36 insertions(+) (limited to 'include/uapi') diff --git a/drivers/firmware/psci.c b/drivers/firmware/psci.c index 1fa7284fb21d..492db42c4e08 100644 --- a/drivers/firmware/psci.c +++ b/drivers/firmware/psci.c @@ -20,12 +20,14 @@ #include #include #include +#include #include #include #include #include +#include /* * While a 64-bit OS can make calls with SMC32 calling conventions, for some @@ -223,6 +225,35 @@ static int __init psci_features(u32 psci_func_id) psci_func_id, 0, 0); } +static int psci_system_suspend(unsigned long unused) +{ + return invoke_psci_fn(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND), + virt_to_phys(cpu_resume), 0, 0); +} + +static int psci_system_suspend_enter(suspend_state_t state) +{ + return cpu_suspend(0, psci_system_suspend); +} + +static const struct platform_suspend_ops psci_suspend_ops = { + .valid = suspend_valid_only_mem, + .enter = psci_system_suspend_enter, +}; + +static void __init psci_init_system_suspend(void) +{ + int ret; + + if (!IS_ENABLED(CONFIG_SUSPEND)) + return; + + ret = psci_features(PSCI_FN_NATIVE(1_0, SYSTEM_SUSPEND)); + + if (ret != PSCI_RET_NOT_SUPPORTED) + suspend_set_ops(&psci_suspend_ops); +} + static void __init psci_init_cpu_suspend(void) { int feature = psci_features(psci_function_id[PSCI_FN_CPU_SUSPEND]); @@ -318,6 +349,8 @@ static int __init psci_probe(void) psci_init_cpu_suspend(); + psci_init_system_suspend(); + return 0; } diff --git a/include/uapi/linux/psci.h b/include/uapi/linux/psci.h index 0a9485f3c6c3..3d7a0fc021a7 100644 --- a/include/uapi/linux/psci.h +++ b/include/uapi/linux/psci.h @@ -47,6 +47,9 @@ #define PSCI_0_2_FN64_MIGRATE_INFO_UP_CPU PSCI_0_2_FN64(7) #define PSCI_1_0_FN_PSCI_FEATURES PSCI_0_2_FN(10) +#define PSCI_1_0_FN_SYSTEM_SUSPEND PSCI_0_2_FN(14) + +#define PSCI_1_0_FN64_SYSTEM_SUSPEND PSCI_0_2_FN64(14) /* PSCI v0.2 power state encoding for CPU_SUSPEND function */ #define PSCI_0_2_POWER_STATE_ID_MASK 0xffff -- cgit v1.2.3 From e5e0c3dd257bf34cf001e10422943f90437f0f1b Mon Sep 17 00:00:00 2001 From: Takashi Sakamoto Date: Thu, 1 Oct 2015 22:02:17 +0900 Subject: ALSA: firewire-tascam: add hwdep interface This commit adds hwdep interface so as the other IEEE 1394 sound devices has. This interface is designed for mixer/control applications. By using this interface, an application can get information about firewire node, can lock/unlock kernel streaming and can get notification at starting/stopping kernel streaming. Signed-off-by: Takashi Sakamoto Signed-off-by: Takashi Iwai --- include/uapi/sound/asound.h | 3 +- include/uapi/sound/firewire.h | 1 + sound/firewire/Kconfig | 1 + sound/firewire/tascam/Makefile | 2 +- sound/firewire/tascam/tascam-hwdep.c | 201 ++++++++++++++++++++++++++++++++++ sound/firewire/tascam/tascam-pcm.c | 17 ++- sound/firewire/tascam/tascam-stream.c | 39 +++++++ sound/firewire/tascam/tascam.c | 6 + sound/firewire/tascam/tascam.h | 13 +++ 9 files changed, 278 insertions(+), 5 deletions(-) create mode 100644 sound/firewire/tascam/tascam-hwdep.c (limited to 'include/uapi') diff --git a/include/uapi/sound/asound.h b/include/uapi/sound/asound.h index aa329132f6c4..a82108e5d1c0 100644 --- a/include/uapi/sound/asound.h +++ b/include/uapi/sound/asound.h @@ -101,9 +101,10 @@ enum { SNDRV_HWDEP_IFACE_FW_BEBOB, /* BridgeCo BeBoB based device */ SNDRV_HWDEP_IFACE_FW_OXFW, /* Oxford OXFW970/971 based device */ SNDRV_HWDEP_IFACE_FW_DIGI00X, /* Digidesign Digi 002/003 family */ + SNDRV_HWDEP_IFACE_FW_TASCAM, /* TASCAM FireWire series */ /* Don't forget to change the following: */ - SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_DIGI00X + SNDRV_HWDEP_IFACE_LAST = SNDRV_HWDEP_IFACE_FW_TASCAM }; struct snd_hwdep_info { diff --git a/include/uapi/sound/firewire.h b/include/uapi/sound/firewire.h index deb041cb9af0..db79a12fcc78 100644 --- a/include/uapi/sound/firewire.h +++ b/include/uapi/sound/firewire.h @@ -64,6 +64,7 @@ union snd_firewire_event { #define SNDRV_FIREWIRE_TYPE_BEBOB 3 #define SNDRV_FIREWIRE_TYPE_OXFW 4 #define SNDRV_FIREWIRE_TYPE_DIGI00X 5 +#define SNDRV_FIREWIRE_TYPE_TASCAM 6 /* RME, MOTU, ... */ struct snd_firewire_get_info { diff --git a/sound/firewire/Kconfig b/sound/firewire/Kconfig index bb3f2610c6e9..bee0e5f1a116 100644 --- a/sound/firewire/Kconfig +++ b/sound/firewire/Kconfig @@ -138,6 +138,7 @@ config SND_FIREWIRE_DIGI00X config SND_FIREWIRE_TASCAM tristate "TASCAM FireWire series support" select SND_FIREWIRE_LIB + select SND_HWDEP help Say Y here to include support for TASCAM. * FW-1884 diff --git a/sound/firewire/tascam/Makefile b/sound/firewire/tascam/Makefile index f075b9bb723f..6beefc2ae8b0 100644 --- a/sound/firewire/tascam/Makefile +++ b/sound/firewire/tascam/Makefile @@ -1,3 +1,3 @@ snd-firewire-tascam-objs := tascam-proc.o amdtp-tascam.o tascam-stream.o \ - tascam-pcm.o tascam.o + tascam-pcm.o tascam-hwdep.o tascam.o obj-$(CONFIG_SND_FIREWIRE_TASCAM) += snd-firewire-tascam.o diff --git a/sound/firewire/tascam/tascam-hwdep.c b/sound/firewire/tascam/tascam-hwdep.c new file mode 100644 index 000000000000..131267c3a042 --- /dev/null +++ b/sound/firewire/tascam/tascam-hwdep.c @@ -0,0 +1,201 @@ +/* + * tascam-hwdep.c - a part of driver for TASCAM FireWire series + * + * Copyright (c) 2015 Takashi Sakamoto + * + * Licensed under the terms of the GNU General Public License, version 2. + */ + +/* + * This codes give three functionality. + * + * 1.get firewire node information + * 2.get notification about starting/stopping stream + * 3.lock/unlock stream + */ + +#include "tascam.h" + +static long hwdep_read_locked(struct snd_tscm *tscm, char __user *buf, + long count) +{ + union snd_firewire_event event; + + memset(&event, 0, sizeof(event)); + + event.lock_status.type = SNDRV_FIREWIRE_EVENT_LOCK_STATUS; + event.lock_status.status = (tscm->dev_lock_count > 0); + tscm->dev_lock_changed = false; + + count = min_t(long, count, sizeof(event.lock_status)); + + if (copy_to_user(buf, &event, count)) + return -EFAULT; + + return count; +} + +static long hwdep_read(struct snd_hwdep *hwdep, char __user *buf, long count, + loff_t *offset) +{ + struct snd_tscm *tscm = hwdep->private_data; + DEFINE_WAIT(wait); + union snd_firewire_event event; + + spin_lock_irq(&tscm->lock); + + while (!tscm->dev_lock_changed) { + prepare_to_wait(&tscm->hwdep_wait, &wait, TASK_INTERRUPTIBLE); + spin_unlock_irq(&tscm->lock); + schedule(); + finish_wait(&tscm->hwdep_wait, &wait); + if (signal_pending(current)) + return -ERESTARTSYS; + spin_lock_irq(&tscm->lock); + } + + memset(&event, 0, sizeof(event)); + count = hwdep_read_locked(tscm, buf, count); + spin_unlock_irq(&tscm->lock); + + return count; +} + +static unsigned int hwdep_poll(struct snd_hwdep *hwdep, struct file *file, + poll_table *wait) +{ + struct snd_tscm *tscm = hwdep->private_data; + unsigned int events; + + poll_wait(file, &tscm->hwdep_wait, wait); + + spin_lock_irq(&tscm->lock); + if (tscm->dev_lock_changed) + events = POLLIN | POLLRDNORM; + else + events = 0; + spin_unlock_irq(&tscm->lock); + + return events; +} + +static int hwdep_get_info(struct snd_tscm *tscm, void __user *arg) +{ + struct fw_device *dev = fw_parent_device(tscm->unit); + struct snd_firewire_get_info info; + + memset(&info, 0, sizeof(info)); + info.type = SNDRV_FIREWIRE_TYPE_TASCAM; + info.card = dev->card->index; + *(__be32 *)&info.guid[0] = cpu_to_be32(dev->config_rom[3]); + *(__be32 *)&info.guid[4] = cpu_to_be32(dev->config_rom[4]); + strlcpy(info.device_name, dev_name(&dev->device), + sizeof(info.device_name)); + + if (copy_to_user(arg, &info, sizeof(info))) + return -EFAULT; + + return 0; +} + +static int hwdep_lock(struct snd_tscm *tscm) +{ + int err; + + spin_lock_irq(&tscm->lock); + + if (tscm->dev_lock_count == 0) { + tscm->dev_lock_count = -1; + err = 0; + } else { + err = -EBUSY; + } + + spin_unlock_irq(&tscm->lock); + + return err; +} + +static int hwdep_unlock(struct snd_tscm *tscm) +{ + int err; + + spin_lock_irq(&tscm->lock); + + if (tscm->dev_lock_count == -1) { + tscm->dev_lock_count = 0; + err = 0; + } else { + err = -EBADFD; + } + + spin_unlock_irq(&tscm->lock); + + return err; +} + +static int hwdep_release(struct snd_hwdep *hwdep, struct file *file) +{ + struct snd_tscm *tscm = hwdep->private_data; + + spin_lock_irq(&tscm->lock); + if (tscm->dev_lock_count == -1) + tscm->dev_lock_count = 0; + spin_unlock_irq(&tscm->lock); + + return 0; +} + +static int hwdep_ioctl(struct snd_hwdep *hwdep, struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct snd_tscm *tscm = hwdep->private_data; + + switch (cmd) { + case SNDRV_FIREWIRE_IOCTL_GET_INFO: + return hwdep_get_info(tscm, (void __user *)arg); + case SNDRV_FIREWIRE_IOCTL_LOCK: + return hwdep_lock(tscm); + case SNDRV_FIREWIRE_IOCTL_UNLOCK: + return hwdep_unlock(tscm); + default: + return -ENOIOCTLCMD; + } +} + +#ifdef CONFIG_COMPAT +static int hwdep_compat_ioctl(struct snd_hwdep *hwdep, struct file *file, + unsigned int cmd, unsigned long arg) +{ + return hwdep_ioctl(hwdep, file, cmd, + (unsigned long)compat_ptr(arg)); +} +#else +#define hwdep_compat_ioctl NULL +#endif + +static const struct snd_hwdep_ops hwdep_ops = { + .read = hwdep_read, + .release = hwdep_release, + .poll = hwdep_poll, + .ioctl = hwdep_ioctl, + .ioctl_compat = hwdep_compat_ioctl, +}; + +int snd_tscm_create_hwdep_device(struct snd_tscm *tscm) +{ + struct snd_hwdep *hwdep; + int err; + + err = snd_hwdep_new(tscm->card, "Tascam", 0, &hwdep); + if (err < 0) + return err; + + strcpy(hwdep->name, "Tascam"); + hwdep->iface = SNDRV_HWDEP_IFACE_FW_TASCAM; + hwdep->ops = hwdep_ops; + hwdep->private_data = tscm; + hwdep->exclusive = true; + + return err; +} diff --git a/sound/firewire/tascam/tascam-pcm.c b/sound/firewire/tascam/tascam-pcm.c index 696b371e3c44..380d3db969a5 100644 --- a/sound/firewire/tascam/tascam-pcm.c +++ b/sound/firewire/tascam/tascam-pcm.c @@ -72,9 +72,13 @@ static int pcm_open(struct snd_pcm_substream *substream) unsigned int rate; int err; + err = snd_tscm_stream_lock_try(tscm); + if (err < 0) + goto end; + err = pcm_init_hw_params(tscm, substream); if (err < 0) - return err; + goto err_locked; err = snd_tscm_stream_get_clock(tscm, &clock); if (clock != SND_TSCM_CLOCK_INTERNAL || @@ -82,18 +86,25 @@ static int pcm_open(struct snd_pcm_substream *substream) amdtp_stream_pcm_running(&tscm->tx_stream)) { err = snd_tscm_stream_get_rate(tscm, &rate); if (err < 0) - return err; + goto err_locked; substream->runtime->hw.rate_min = rate; substream->runtime->hw.rate_max = rate; } snd_pcm_set_sync(substream); - +end: + return err; +err_locked: + snd_tscm_stream_lock_release(tscm); return err; } static int pcm_close(struct snd_pcm_substream *substream) { + struct snd_tscm *tscm = substream->private_data; + + snd_tscm_stream_lock_release(tscm); + return 0; } diff --git a/sound/firewire/tascam/tascam-stream.c b/sound/firewire/tascam/tascam-stream.c index 0732f7f0c736..0e6dd5c61f53 100644 --- a/sound/firewire/tascam/tascam-stream.c +++ b/sound/firewire/tascam/tascam-stream.c @@ -455,3 +455,42 @@ void snd_tscm_stream_stop_duplex(struct snd_tscm *tscm) finish_session(tscm); release_resources(tscm); } + +void snd_tscm_stream_lock_changed(struct snd_tscm *tscm) +{ + tscm->dev_lock_changed = true; + wake_up(&tscm->hwdep_wait); +} + +int snd_tscm_stream_lock_try(struct snd_tscm *tscm) +{ + int err; + + spin_lock_irq(&tscm->lock); + + /* user land lock this */ + if (tscm->dev_lock_count < 0) { + err = -EBUSY; + goto end; + } + + /* this is the first time */ + if (tscm->dev_lock_count++ == 0) + snd_tscm_stream_lock_changed(tscm); + err = 0; +end: + spin_unlock_irq(&tscm->lock); + return err; +} + +void snd_tscm_stream_lock_release(struct snd_tscm *tscm) +{ + spin_lock_irq(&tscm->lock); + + if (WARN_ON(tscm->dev_lock_count <= 0)) + goto end; + if (--tscm->dev_lock_count == 0) + snd_tscm_stream_lock_changed(tscm); +end: + spin_unlock_irq(&tscm->lock); +} diff --git a/sound/firewire/tascam/tascam.c b/sound/firewire/tascam/tascam.c index bb4f70656f2f..ee2f498dcce4 100644 --- a/sound/firewire/tascam/tascam.c +++ b/sound/firewire/tascam/tascam.c @@ -110,6 +110,8 @@ static int snd_tscm_probe(struct fw_unit *unit, tscm->spec = (const struct snd_tscm_spec *)entry->driver_data; mutex_init(&tscm->mutex); + spin_lock_init(&tscm->lock); + init_waitqueue_head(&tscm->hwdep_wait); err = check_name(tscm); if (err < 0) @@ -125,6 +127,10 @@ static int snd_tscm_probe(struct fw_unit *unit, if (err < 0) goto error; + err = snd_tscm_create_hwdep_device(tscm); + if (err < 0) + goto error; + err = snd_card_register(card); if (err < 0) goto error; diff --git a/sound/firewire/tascam/tascam.h b/sound/firewire/tascam/tascam.h index 28c875f7808c..75a3b9a81fea 100644 --- a/sound/firewire/tascam/tascam.h +++ b/sound/firewire/tascam/tascam.h @@ -23,6 +23,8 @@ #include #include #include +#include +#include #include "../lib.h" #include "../amdtp-stream.h" @@ -44,6 +46,7 @@ struct snd_tscm { struct fw_unit *unit; struct mutex mutex; + spinlock_t lock; const struct snd_tscm_spec *spec; @@ -52,6 +55,10 @@ struct snd_tscm { struct amdtp_stream tx_stream; struct amdtp_stream rx_stream; unsigned int substreams_counter; + + int dev_lock_count; + bool dev_lock_changed; + wait_queue_head_t hwdep_wait; }; #define TSCM_ADDR_BASE 0xffff00000000ull @@ -97,8 +104,14 @@ void snd_tscm_stream_destroy_duplex(struct snd_tscm *tscm); int snd_tscm_stream_start_duplex(struct snd_tscm *tscm, unsigned int rate); void snd_tscm_stream_stop_duplex(struct snd_tscm *tscm); +void snd_tscm_stream_lock_changed(struct snd_tscm *tscm); +int snd_tscm_stream_lock_try(struct snd_tscm *tscm); +void snd_tscm_stream_lock_release(struct snd_tscm *tscm); + void snd_tscm_proc_init(struct snd_tscm *tscm); int snd_tscm_create_pcm_devices(struct snd_tscm *tscm); +int snd_tscm_create_hwdep_device(struct snd_tscm *tscm); + #endif -- cgit v1.2.3 From 5b2688a59af686f7c0a80edc49d7f190365ac090 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:28:47 +0800 Subject: ASoC: topology: ABI - Add PCM Support and bump ABI version to 4 The struct snd_soc_tplg_pcm_dai is renamed to snd_soc_tplg_pcm. This struct will now be used to handle data related to PCMs (FE DAI & DAI links). It's not for BE, because BE DAI mappings will be provided by ACPI/FDT data. Remove the unused struct snd_soc_tplg_pcm_cfg_caps. We are using snd_soc_tplg_stream and snd_soc_stream_caps instead. Bump ABI version to 4. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 31 +++++++++++++++---------------- sound/soc/soc-topology.c | 4 ++-- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 247c50bd60f0..2aa081ca95c1 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -83,7 +83,7 @@ #define SND_SOC_TPLG_NUM_TEXTS 16 /* ABI version */ -#define SND_SOC_TPLG_ABI_VERSION 0x3 +#define SND_SOC_TPLG_ABI_VERSION 0x4 /* Max size of TLV data */ #define SND_SOC_TPLG_TLV_SIZE 32 @@ -378,30 +378,29 @@ struct snd_soc_tplg_dapm_widget { */ } __attribute__((packed)); -struct snd_soc_tplg_pcm_cfg_caps { - struct snd_soc_tplg_stream_caps caps; - struct snd_soc_tplg_stream_config configs[SND_SOC_TPLG_STREAM_CONFIG_MAX]; - __le32 num_configs; /* number of configs */ -} __attribute__((packed)); /* - * Describes SW/FW specific features of PCM or DAI link. + * Describes SW/FW specific features of PCM (FE DAI & DAI link). * - * File block representation for PCM/DAI-Link :- + * File block representation for PCM :- * +-----------------------------------+-----+ * | struct snd_soc_tplg_hdr | 1 | * +-----------------------------------+-----+ - * | struct snd_soc_tplg_dapm_pcm_dai | N | + * | struct snd_soc_tplg_pcm | N | * +-----------------------------------+-----+ */ -struct snd_soc_tplg_pcm_dai { +struct snd_soc_tplg_pcm { __le32 size; /* in bytes of this structure */ - char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - __le32 id; /* unique ID - used to match */ - __le32 playback; /* supports playback mode */ - __le32 capture; /* supports capture mode */ - __le32 compress; /* 1 = compressed; 0 = PCM */ - struct snd_soc_tplg_pcm_cfg_caps capconf[2]; /* capabilities and configs */ + char pcm_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; + char dai_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; + __le32 pcm_id; /* unique ID - used to match */ + __le32 dai_id; /* unique ID - used to match */ + __le32 playback; /* supports playback mode */ + __le32 capture; /* supports capture mode */ + __le32 compress; /* 1 = compressed; 0 = PCM */ + struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* for DAI link */ + __le32 num_streams; /* number of streams */ + struct snd_soc_tplg_stream_caps caps[2]; /* playback and capture for DAI */ } __attribute__((packed)); #endif diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c index 69d01cd925ce..8d7ec80af51b 100644 --- a/sound/soc/soc-topology.c +++ b/sound/soc/soc-topology.c @@ -1558,7 +1558,7 @@ static int soc_tplg_pcm_dai_elems_load(struct soc_tplg *tplg, pcm_dai = (struct snd_soc_tplg_pcm_dai *)tplg->pos; if (soc_tplg_check_elem_count(tplg, - sizeof(struct snd_soc_tplg_pcm_dai), count, + sizeof(struct snd_soc_tplg_pcm), count, hdr->payload_size, "PCM DAI")) { dev_err(tplg->dev, "ASoC: invalid count %d for PCM DAI elems\n", count); @@ -1566,7 +1566,7 @@ static int soc_tplg_pcm_dai_elems_load(struct soc_tplg *tplg, } dev_dbg(tplg->dev, "ASoC: adding %d PCM DAIs\n", count); - tplg->pos += sizeof(struct snd_soc_tplg_pcm_dai) * count; + tplg->pos += sizeof(struct snd_soc_tplg_pcm) * count; dobj = kzalloc(sizeof(struct snd_soc_dobj), GFP_KERNEL); if (dobj == NULL) -- cgit v1.2.3 From 7654855ef84d78079109bb38195a8db6b188117b Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:29:47 +0800 Subject: ASoC: topology: ABI - Remove unused struct snd_soc_tplg_stream_config The struct snd_soc_tplg_stream_config is no longer used in the ABI. We are using snd_soc_tplg_stream instead. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 2aa081ca95c1..4bef63f5e1ff 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -226,16 +226,6 @@ struct snd_soc_tplg_stream { __le32 dai_fmt; /* SND_SOC_DAIFMT_ */ } __attribute__((packed)); -/* - * Duplex stream configuration supported by SW/FW. - */ -struct snd_soc_tplg_stream_config { - __le32 size; /* in bytes of this structure */ - char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - struct snd_soc_tplg_stream playback; - struct snd_soc_tplg_stream capture; -} __attribute__((packed)); - /* * Manifest. List totals for each payload type. Not used in parsing, but will * be passed to the component driver before any other objects in order for any -- cgit v1.2.3 From e8b3fe8f383bbf055cbd69b776fcbbb5ed3befcd Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:30:05 +0800 Subject: ASoC: topology: ABI - Use __le32 instead of __u32 in snd_soc_tplg_dapm_widget This fixes the endianness of the ABI parameters in the struct. The field 'num_kcontrols' is also extended from 16 bits to 32 bits. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 4bef63f5e1ff..88210a8e450f 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -356,11 +356,11 @@ struct snd_soc_tplg_dapm_widget { __le32 shift; /* bits to shift */ __le32 mask; /* non-shifted mask */ __le32 subseq; /* sort within widget type */ - __u32 invert; /* invert the power bit */ - __u32 ignore_suspend; /* kept enabled over suspend */ - __u16 event_flags; - __u16 event_type; - __u16 num_kcontrols; + __le32 invert; /* invert the power bit */ + __le32 ignore_suspend; /* kept enabled over suspend */ + __le16 event_flags; + __le16 event_type; + __le32 num_kcontrols; struct snd_soc_tplg_private priv; /* * kcontrols that relate to this widget -- cgit v1.2.3 From 731324f5cee3caf230427f754701212961fe0bb1 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:31:34 +0800 Subject: ASoC: topology: ABI - Add name element to snd_soc_tplg_stream For codec-codec links, this struct will be mapped to the DAI links's params, which is struct snd_soc_pcm_stream and it needs a stream name. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 88210a8e450f..218148000187 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -217,6 +217,7 @@ struct snd_soc_tplg_stream_caps { */ struct snd_soc_tplg_stream { __le32 size; /* in bytes of this structure */ + char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; /* Name of the stream */ __le64 format; /* SNDRV_PCM_FMTBIT_* */ __le32 rate; /* SNDRV_PCM_RATE_* */ __le32 period_bytes; /* size of period in bytes */ -- cgit v1.2.3 From 478d0d39719127c42f21ac85b8719a87b8fa7bd7 Mon Sep 17 00:00:00 2001 From: Mengdong Lin Date: Wed, 30 Sep 2015 17:31:44 +0800 Subject: ASoC: topology: ABI - Change stream formats to a bitwise flag The toplogy user space tool will generate this bitwise flag by using SNDRV_PCM_FORMAT_* exposed by asound.h, and the topology core will copy this flag when generating DAI streams. Signed-off-by: Mengdong Lin Acked-by: Liam Girdwood Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 218148000187..eeb74a9cc2f8 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -198,7 +198,7 @@ struct snd_soc_tplg_ctl_hdr { struct snd_soc_tplg_stream_caps { __le32 size; /* in bytes of this structure */ char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN]; - __le64 formats[SND_SOC_TPLG_MAX_FORMATS]; /* supported formats SNDRV_PCM_FMTBIT_* */ + __le64 formats; /* supported formats SNDRV_PCM_FMTBIT_* */ __le32 rates; /* supported rates SNDRV_PCM_RATE_* */ __le32 rate_min; /* min rate */ __le32 rate_max; /* max rate */ -- cgit v1.2.3 From 7c545b327d54cdc3f693093f744459f6e0d8ce58 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:32:04 +0800 Subject: ASoC: topology: ABI - Add the type for BE DAI link Define the topology type for BE DAI link: SND_SOC_TPLG_TYPE_BACKEND_LINK. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index eeb74a9cc2f8..f75fd29bf580 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -103,7 +103,8 @@ #define SND_SOC_TPLG_TYPE_PCM 7 #define SND_SOC_TPLG_TYPE_MANIFEST 8 #define SND_SOC_TPLG_TYPE_CODEC_LINK 9 -#define SND_SOC_TPLG_TYPE_PDATA 10 +#define SND_SOC_TPLG_TYPE_BACKEND_LINK 10 +#define SND_SOC_TPLG_TYPE_PDATA 11 #define SND_SOC_TPLG_TYPE_MAX SND_SOC_TPLG_TYPE_PDATA /* vendor block IDs - please add new vendor types to end */ -- cgit v1.2.3 From e2a9df656f28e42538562d090e2b6f3dec5b41f2 Mon Sep 17 00:00:00 2001 From: Vedang Patel Date: Wed, 30 Sep 2015 17:32:22 +0800 Subject: ASoC: topology: ABI - Add configuration for BE & Codec-Codec DAI Links struct snd_soc_tplg_link_config is defined to configure BE & CC links. Signed-off-by: Vedang Patel Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index f75fd29bf580..538ea1308008 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -395,4 +395,21 @@ struct snd_soc_tplg_pcm { struct snd_soc_tplg_stream_caps caps[2]; /* playback and capture for DAI */ } __attribute__((packed)); + +/* + * Describes the BE or CC link runtime supported configs or params + * + * File block representation for BE/CC link config :- + * +-----------------------------------+-----+ + * | struct snd_soc_tplg_hdr | 1 | + * +-----------------------------------+-----+ + * | struct snd_soc_tplg_link_config | N | + * +-----------------------------------+-----+ + */ +struct snd_soc_tplg_link_config { + __le32 size; /* in bytes of this structure */ + __le32 id; /* unique ID - used to match */ + struct snd_soc_tplg_stream stream[SND_SOC_TPLG_STREAM_CONFIG_MAX]; /* supported configs playback and captrure */ + __le32 num_streams; /* number of streams */ +} __attribute__((packed)); #endif -- cgit v1.2.3 From 76a822a6ae9c0c67309318bb60a4117329252fc4 Mon Sep 17 00:00:00 2001 From: Mengdong Lin Date: Wed, 30 Sep 2015 17:32:40 +0800 Subject: ASoC: topology: ABI - Remove tdm_slot & dai_fmt from snd_soc_tplg_stream These two fields are line parameters for BE/CC links and should not be from toplogy but from ACPI. Signed-off-by: Mengdong Lin Signed-off-by: Mark Brown --- include/uapi/sound/asoc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h index 538ea1308008..26539a7e4880 100644 --- a/include/uapi/sound/asoc.h +++ b/include/uapi/sound/asoc.h @@ -224,8 +224,6 @@ struct snd_soc_tplg_stream { __le32 period_bytes; /* size of period in bytes */ __le32 buffer_bytes; /* size of buffer in bytes */ __le32 channels; /* channels */ - __le32 tdm_slot; /* optional BE bitmask of supported TDM slots */ - __le32 dai_fmt; /* SND_SOC_DAIFMT_ */ } __attribute__((packed)); /* -- cgit v1.2.3 From c46646d0484f5d08e2bede9b45034ba5b8b489cc Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 30 Sep 2015 01:41:51 +0200 Subject: sched, bpf: add helper for retrieving routing realms Using routing realms as part of the classifier is quite useful, it can be viewed as a tag for one or multiple routing entries (think of an analogy to net_cls cgroup for processes), set by user space routing daemons or via iproute2 as an indicator for traffic classifiers and later on processed in the eBPF program. Unlike actions, the classifier can inspect device flags and enable netif_keep_dst() if necessary. tc actions don't have that possibility, but in case people know what they are doing, it can be used from there as well (e.g. via devs that must keep dsts by design anyway). If a realm is set, the handler returns the non-zero realm. User space can set the full 32bit realm for the dst. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/filter.h | 3 ++- include/uapi/linux/bpf.h | 7 +++++++ kernel/bpf/syscall.c | 2 ++ net/core/filter.c | 22 ++++++++++++++++++++++ net/sched/cls_bpf.c | 8 ++++++-- 5 files changed, 39 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/filter.h b/include/linux/filter.h index bad618f316d7..3d5fd24b321b 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -328,7 +328,8 @@ struct bpf_prog { u16 pages; /* Number of allocated pages */ kmemcheck_bitfield_begin(meta); u16 jited:1, /* Is our filter JIT'ed? */ - gpl_compatible:1; /* Is filter GPL compatible? */ + gpl_compatible:1, /* Is filter GPL compatible? */ + dst_needed:1; /* Do we need dst entry? */ kmemcheck_bitfield_end(meta); u32 len; /* Number of filter blocks */ enum bpf_prog_type type; /* Type of BPF program */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4ec0b5488294..564f1f091991 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -280,6 +280,13 @@ enum bpf_func_id { * Return: TC_ACT_REDIRECT */ BPF_FUNC_redirect, + + /** + * bpf_get_route_realm(skb) - retrieve a dst's tclassid + * @skb: pointer to skb + * Return: realm if != 0 + */ + BPF_FUNC_get_route_realm, __BPF_FUNC_MAX_ID, }; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 2190ab14b763..5f35f420c12f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -402,6 +402,8 @@ static void fixup_bpf_calls(struct bpf_prog *prog) */ BUG_ON(!prog->aux->ops->get_func_proto); + if (insn->imm == BPF_FUNC_get_route_realm) + prog->dst_needed = 1; if (insn->imm == BPF_FUNC_tail_call) { /* mark bpf_tail_call as different opcode * to avoid conditional branch in diff --git a/net/core/filter.c b/net/core/filter.c index 04664acb86ce..45c69ce4c847 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -49,6 +49,7 @@ #include #include #include +#include /** * sk_filter - run a packet through a socket filter @@ -1478,6 +1479,25 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; +static u64 bpf_get_route_realm(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ +#ifdef CONFIG_IP_ROUTE_CLASSID + const struct dst_entry *dst; + + dst = skb_dst((struct sk_buff *) (unsigned long) r1); + if (dst) + return dst->tclassid; +#endif + return 0; +} + +static const struct bpf_func_proto bpf_get_route_realm_proto = { + .func = bpf_get_route_realm, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; + static u64 bpf_skb_vlan_push(u64 r1, u64 r2, u64 vlan_tci, u64 r4, u64 r5) { struct sk_buff *skb = (struct sk_buff *) (long) r1; @@ -1648,6 +1668,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id) return bpf_get_skb_set_tunnel_key_proto(); case BPF_FUNC_redirect: return &bpf_redirect_proto; + case BPF_FUNC_get_route_realm: + return &bpf_get_route_realm_proto; default: return sk_filter_func_proto(func_id); } diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 7eeffaf69c75..5faaa5425f7b 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -262,7 +262,8 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog) return 0; } -static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog) +static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, + const struct tcf_proto *tp) { struct bpf_prog *fp; char *name = NULL; @@ -294,6 +295,9 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog) prog->bpf_name = name; prog->filter = fp; + if (fp->dst_needed) + netif_keep_dst(qdisc_dev(tp->q)); + return 0; } @@ -330,7 +334,7 @@ static int cls_bpf_modify_existing(struct net *net, struct tcf_proto *tp, prog->exts_integrated = have_exts; ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog); + cls_bpf_prog_from_efd(tb, prog, tp); if (ret < 0) { tcf_exts_destroy(&exts); return ret; -- cgit v1.2.3 From 90ec9247808ed6b9f072e2c4021868374b0a6d92 Mon Sep 17 00:00:00 2001 From: Mathias Nyman Date: Thu, 1 Oct 2015 18:40:32 +0300 Subject: usb: Add USB 3.1 SuperSpeedPlus device capability descriptor USB 3.1 SuperSpeedPlus device capability descriptor is returned as part of the bos descriptor for devices that support SuperSpeedPlus protocol. The descriptor contains more detailed information about the supported speeds of the device. More details about the descriptor can be found in the USB 3.1 specification section 9.6.2.5 Signed-off-by: Mathias Nyman Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/usb/ch9.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h index f7adc6e01f9e..4338eb7b09b3 100644 --- a/include/uapi/linux/usb/ch9.h +++ b/include/uapi/linux/usb/ch9.h @@ -866,6 +866,35 @@ struct usb_ss_container_id_descriptor { } __attribute__((packed)); #define USB_DT_USB_SS_CONTN_ID_SIZE 20 + +/* + * SuperSpeed Plus USB Capability descriptor: Defines the set of + * SuperSpeed Plus USB specific device level capabilities + */ +#define USB_SSP_CAP_TYPE 0xa +struct usb_ssp_cap_descriptor { + __u8 bLength; + __u8 bDescriptorType; + __u8 bDevCapabilityType; + __u8 bReserved; + __le32 bmAttributes; +#define USB_SSP_SUBLINK_SPEED_ATTRIBS (0x1f << 0) /* sublink speed entries */ +#define USB_SSP_SUBLINK_SPEED_IDS (0xf << 5) /* speed ID entries */ + __u16 wFunctionalitySupport; +#define USB_SSP_MIN_SUBLINK_SPEED_ATTRIBUTE_ID (0xf) +#define USB_SSP_MIN_RX_LANE_COUNT (0xf << 8) +#define USB_SSP_MIN_TX_LANE_COUNT (0xf << 12) + __le16 wReserved; + __le32 bmSublinkSpeedAttr[1]; /* list of sublink speed attrib entries */ +#define USB_SSP_SUBLINK_SPEED_SSID (0xf) /* sublink speed ID */ +#define USB_SSP_SUBLINK_SPEED_LSE (0x3 << 4) /* Lanespeed exponent */ +#define USB_SSP_SUBLINK_SPEED_ST (0x3 << 6) /* Sublink type */ +#define USB_SSP_SUBLINK_SPEED_RSVD (0x3f << 8) /* Reserved */ +#define USB_SSP_SUBLINK_SPEED_LP (0x3 << 14) /* Link protocol */ +#define USB_SSP_SUBLINK_SPEED_LSM (0xff << 16) /* Lanespeed mantissa */ +} __attribute__((packed)); + + /*-------------------------------------------------------------------------*/ /* USB_DT_WIRELESS_ENDPOINT_COMP: companion descriptor associated with -- cgit v1.2.3 From f4a66c20448257fbb8932827e5f766b74d1acbf0 Mon Sep 17 00:00:00 2001 From: Ashutosh Dixit Date: Tue, 29 Sep 2015 18:14:30 -0700 Subject: misc: mic: Update MIC host daemon with COSM changes This patch updates the MIC host daemon to work with corresponding changes in COSM. Other MIC daemon fixes, cleanups and enhancements as are also rolled into this patch. Changes to MIC sysfs ABI which go into effect with this patch are also documented. Reviewed-by: Sudeep Dutt Signed-off-by: Dasaratharaman Chandramouli Signed-off-by: Ashutosh Dixit Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-class-mic.txt | 29 ++- Documentation/mic/mic_overview.txt | 31 ++- Documentation/mic/mpssd/mpss | 4 +- Documentation/mic/mpssd/mpssd.c | 362 ++++++++++++++++---------- Documentation/mic/mpssd/mpssd.h | 1 + drivers/misc/mic/Makefile | 4 + drivers/misc/mic/bus/scif_bus.c | 7 +- drivers/misc/mic/bus/scif_bus.h | 6 +- include/uapi/linux/mic_common.h | 16 +- 9 files changed, 285 insertions(+), 175 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/ABI/testing/sysfs-class-mic.txt b/Documentation/ABI/testing/sysfs-class-mic.txt index 13f48afc534f..d45eed2bf128 100644 --- a/Documentation/ABI/testing/sysfs-class-mic.txt +++ b/Documentation/ABI/testing/sysfs-class-mic.txt @@ -41,18 +41,15 @@ Description: When read, this entry provides the current state of an Intel MIC device in the context of the card OS. Possible values that will be read are: - "offline" - The MIC device is ready to boot the card OS. On + "ready" - The MIC device is ready to boot the card OS. On reading this entry after an OSPM resume, a "boot" has to be written to this entry if the card was previously shutdown during OSPM suspend. - "online" - The MIC device has initiated booting a card OS. + "booting" - The MIC device has initiated booting a card OS. + "online" - The MIC device has completed boot and is online "shutting_down" - The card OS is shutting down. + "resetting" - A reset has been initiated for the MIC device "reset_failed" - The MIC device has failed to reset. - "suspending" - The MIC device is currently being prepared for - suspend. On reading this entry, a "suspend" has to be written - to the state sysfs entry to ensure the card is shutdown during - OSPM suspend. - "suspended" - The MIC device has been suspended. When written, this sysfs entry triggers different state change operations depending upon the current state of the card OS. @@ -62,8 +59,6 @@ Description: sysfs entries. "reset" - Initiates device reset. "shutdown" - Initiates card OS shutdown. - "suspend" - Initiates card OS shutdown and also marks the card - as suspended. What: /sys/class/mic/mic(x)/shutdown_status Date: October 2013 @@ -126,7 +121,7 @@ Description: the card. This sysfs entry can be written with the following valid strings: a) linux - Boot a Linux image. - b) elf - Boot an elf image for flash updates. + b) flash - Boot an image for flash updates. What: /sys/class/mic/mic(x)/log_buf_addr Date: October 2013 @@ -155,3 +150,17 @@ Description: daemon to set the log buffer length address. The correct log buffer length address to be written can be found in the System.map file of the card OS. + +What: /sys/class/mic/mic(x)/heartbeat_enable +Date: March 2015 +KernelVersion: 3.20 +Contact: Ashutosh Dixit +Description: + The MIC drivers detect and inform user space about card crashes + via a heartbeat mechanism (see the description of + shutdown_status above). User space can turn off this + notification by setting heartbeat_enable to 0 and enable it by + setting this entry to 1. If this notification is disabled it is + the responsibility of user space to detect card crashes via + alternative means such as a network ping. This setting is + enabled by default. diff --git a/Documentation/mic/mic_overview.txt b/Documentation/mic/mic_overview.txt index 1a2f2c8ec59e..73f44fc3e715 100644 --- a/Documentation/mic/mic_overview.txt +++ b/Documentation/mic/mic_overview.txt @@ -28,6 +28,10 @@ The Symmetric Communication Interface (SCIF (pronounced as skiff)) is a low level communications API across PCIe currently implemented for MIC. More details are available at scif_overview.txt. +The Coprocessor State Management (COSM) driver on the host allows for +boot, shutdown and reset of Intel MIC devices. It communicates with a COSM +"client" driver on the MIC cards over SCIF to perform these functions. + Here is a block diagram of the various components described above. The virtio backends are situated on the host rather than the card given better single threaded performance for the host compared to MIC, the ability of @@ -51,19 +55,20 @@ the fact that the virtio block storage backend can only be on the host. | | | Virtio over PCIe IOCTLs | | | +--------------------------+ +-----------+ | | | +-----------+ -| MIC DMA | | +----------+ | +-----------+ | | MIC DMA | -| Driver | | | SCIF | | | SCIF | | | Driver | -+-----------+ | +----------+ | +-----------+ | +-----------+ - | | | | | | | -+---------------+ | +-----+-----+ | +-----+-----+ | +---------------+ -|MIC virtual Bus| | |SCIF HW Bus| | |SCIF HW BUS| | |MIC virtual Bus| -+---------------+ | +-----------+ | +-----+-----+ | +---------------+ - | | | | | | | - | +--------------+ | | | +---------------+ | - | |Intel MIC | | | | |Intel MIC | | - +---|Card Driver +----+ | | |Host Driver | | - +--------------+ | +----+---------------+-----+ - | | | +| MIC DMA | | +------+ | +------+ +------+ | | MIC DMA | +| Driver | | | SCIF | | | SCIF | | COSM | | | Driver | ++-----------+ | +------+ | +------+ +--+---+ | +-----------+ + | | | | | | | | ++---------------+ | +------+ | +--+---+ +--+---+ | +----------------+ +|MIC virtual Bus| | |SCIF | | |SCIF | | COSM | | |MIC virtual Bus | ++---------------+ | |HW Bus| | |HW Bus| | Bus | | +----------------+ + | | +------+ | +--+---+ +------+ | | + | | | | | | | | + | +-----------+---+ | | | +---------------+ | + | |Intel MIC | | | | |Intel MIC | | + +---|Card Driver | | | | |Host Driver | | + +------------+--------+ | +----+---------------+-----+ + | | | +-------------------------------------------------------------+ | | | PCIe Bus | diff --git a/Documentation/mic/mpssd/mpss b/Documentation/mic/mpssd/mpss index 582aad4811ae..09ea90931649 100755 --- a/Documentation/mic/mpssd/mpss +++ b/Documentation/mic/mpssd/mpss @@ -119,10 +119,10 @@ stop() # Wait for the cards to go offline for f in $sysfs/* do - while [ "`cat $f/state`" != "offline" ] + while [ "`cat $f/state`" != "ready" ] do sleep 1 - echo -e "Waiting for "`basename $f`" to go offline" + echo -e "Waiting for "`basename $f`" to become ready" done done diff --git a/Documentation/mic/mpssd/mpssd.c b/Documentation/mic/mpssd/mpssd.c index 3c5c379fc29d..aaeafa18d99b 100644 --- a/Documentation/mic/mpssd/mpssd.c +++ b/Documentation/mic/mpssd/mpssd.c @@ -43,7 +43,7 @@ #include #include -static void init_mic(struct mic_info *mic); +static void *init_mic(void *arg); static FILE *logfp; static struct mic_info mic_list; @@ -116,19 +116,18 @@ static struct { .num = htole16(MIC_VRING_ENTRIES), }, #if GSO_ENABLED - .host_features = htole32( + .host_features = htole32( 1 << VIRTIO_NET_F_CSUM | 1 << VIRTIO_NET_F_GSO | 1 << VIRTIO_NET_F_GUEST_TSO4 | 1 << VIRTIO_NET_F_GUEST_TSO6 | - 1 << VIRTIO_NET_F_GUEST_ECN | - 1 << VIRTIO_NET_F_GUEST_UFO), + 1 << VIRTIO_NET_F_GUEST_ECN), #else .host_features = 0, #endif }; -static const char *mic_config_dir = "/etc/sysconfig/mic"; +static const char *mic_config_dir = "/etc/mpss"; static const char *virtblk_backend = "VIRTBLK_BACKEND"; static struct { struct mic_device_desc dd; @@ -192,7 +191,7 @@ tap_configure(struct mic_info *mic, char *dev) return ret; } - snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id); + snprintf(ipaddr, IFNAMSIZ, "172.31.%d.254/24", mic->id + 1); pid = fork(); if (pid == 0) { @@ -255,8 +254,7 @@ static int tun_alloc(struct mic_info *mic, char *dev) return err; } #if GSO_ENABLED - offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO; + offload = TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | TUN_F_TSO_ECN; err = ioctl(fd, TUNSETOFFLOAD, offload); if (err < 0) { @@ -332,7 +330,6 @@ static struct mic_device_desc *get_device_desc(struct mic_info *mic, int type) return d; } mpsslog("%s %s %d not found\n", mic->name, __func__, type); - assert(0); return NULL; } @@ -415,6 +412,13 @@ mic_virtio_copy(struct mic_info *mic, int fd, return ret; } +static inline unsigned _vring_size(unsigned int num, unsigned long align) +{ + return ((sizeof(struct vring_desc) * num + sizeof(__u16) * (3 + num) + + align - 1) & ~(align - 1)) + + sizeof(__u16) * 3 + sizeof(struct vring_used_elem) * num; +} + /* * This initialization routine requires at least one * vring i.e. vr0. vr1 is optional. @@ -426,8 +430,9 @@ init_vr(struct mic_info *mic, int fd, int type, int vr_size; char *va; - vr_size = PAGE_ALIGN(vring_size(MIC_VRING_ENTRIES, - MIC_VIRTIO_RING_ALIGN) + sizeof(struct _mic_vring_info)); + vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES, + MIC_VIRTIO_RING_ALIGN) + + sizeof(struct _mic_vring_info)); va = mmap(NULL, MIC_DEVICE_PAGE_END + vr_size * num_vq, PROT_READ, MAP_SHARED, fd, 0); if (MAP_FAILED == va) { @@ -439,25 +444,25 @@ init_vr(struct mic_info *mic, int fd, int type, set_dp(mic, type, va); vr0->va = (struct mic_vring *)&va[MIC_DEVICE_PAGE_END]; vr0->info = vr0->va + - vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN); + _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN); vring_init(&vr0->vr, MIC_VRING_ENTRIES, vr0->va, MIC_VIRTIO_RING_ALIGN); mpsslog("%s %s vr0 %p vr0->info %p vr_size 0x%x vring 0x%x ", __func__, mic->name, vr0->va, vr0->info, vr_size, - vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); + _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); mpsslog("magic 0x%x expected 0x%x\n", le32toh(vr0->info->magic), MIC_MAGIC + type); assert(le32toh(vr0->info->magic) == MIC_MAGIC + type); if (vr1) { vr1->va = (struct mic_vring *) &va[MIC_DEVICE_PAGE_END + vr_size]; - vr1->info = vr1->va + vring_size(MIC_VRING_ENTRIES, + vr1->info = vr1->va + _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN); vring_init(&vr1->vr, MIC_VRING_ENTRIES, vr1->va, MIC_VIRTIO_RING_ALIGN); mpsslog("%s %s vr1 %p vr1->info %p vr_size 0x%x vring 0x%x ", __func__, mic->name, vr1->va, vr1->info, vr_size, - vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); + _vring_size(MIC_VRING_ENTRIES, MIC_VIRTIO_RING_ALIGN)); mpsslog("magic 0x%x expected 0x%x\n", le32toh(vr1->info->magic), MIC_MAGIC + type + 1); assert(le32toh(vr1->info->magic) == MIC_MAGIC + type + 1); @@ -466,16 +471,21 @@ done: return va; } -static void +static int wait_for_card_driver(struct mic_info *mic, int fd, int type) { struct pollfd pollfd; int err; struct mic_device_desc *desc = get_device_desc(mic, type); + __u8 prev_status; + if (!desc) + return -ENODEV; + prev_status = desc->status; pollfd.fd = fd; mpsslog("%s %s Waiting .... desc-> type %d status 0x%x\n", mic->name, __func__, type, desc->status); + while (1) { pollfd.events = POLLIN; pollfd.revents = 0; @@ -487,8 +497,13 @@ wait_for_card_driver(struct mic_info *mic, int fd, int type) } if (pollfd.revents) { - mpsslog("%s %s Waiting... desc-> type %d status 0x%x\n", - mic->name, __func__, type, desc->status); + if (desc->status != prev_status) { + mpsslog("%s %s Waiting... desc-> type %d " + "status 0x%x\n", + mic->name, __func__, type, + desc->status); + prev_status = desc->status; + } if (desc->status & VIRTIO_CONFIG_S_DRIVER_OK) { mpsslog("%s %s poll.revents %d\n", mic->name, __func__, pollfd.revents); @@ -499,6 +514,7 @@ wait_for_card_driver(struct mic_info *mic, int fd, int type) } } } + return 0; } /* Spin till we have some descriptors */ @@ -575,9 +591,16 @@ virtio_net(void *arg) __func__, strerror(errno)); continue; } - if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) - wait_for_card_driver(mic, mic->mic_net.virtio_net_fd, - VIRTIO_ID_NET); + if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { + err = wait_for_card_driver(mic, + mic->mic_net.virtio_net_fd, + VIRTIO_ID_NET); + if (err) { + mpsslog("%s %s %d Exiting...\n", + mic->name, __func__, __LINE__); + break; + } + } /* * Check if there is data to be read from TUN and write to * virtio net fd if there is. @@ -786,10 +809,16 @@ virtio_console(void *arg) strerror(errno)); continue; } - if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) - wait_for_card_driver(mic, - mic->mic_console.virtio_console_fd, - VIRTIO_ID_CONSOLE); + if (!(desc->status & VIRTIO_CONFIG_S_DRIVER_OK)) { + err = wait_for_card_driver(mic, + mic->mic_console.virtio_console_fd, + VIRTIO_ID_CONSOLE); + if (err) { + mpsslog("%s %s %d Exiting...\n", + mic->name, __func__, __LINE__); + break; + } + } if (console_poll[MONITOR_FD].revents & POLLIN) { copy.iov = iov0; @@ -1048,8 +1077,9 @@ stop_virtblk(struct mic_info *mic) { int vr_size, ret; - vr_size = PAGE_ALIGN(vring_size(MIC_VRING_ENTRIES, - MIC_VIRTIO_RING_ALIGN) + sizeof(struct _mic_vring_info)); + vr_size = PAGE_ALIGN(_vring_size(MIC_VRING_ENTRIES, + MIC_VIRTIO_RING_ALIGN) + + sizeof(struct _mic_vring_info)); ret = munmap(mic->mic_virtblk.block_dp, MIC_DEVICE_PAGE_END + vr_size * virtblk_dev_page.dd.num_vq); if (ret < 0) @@ -1131,6 +1161,10 @@ write_status(int fd, __u8 *status) return ioctl(fd, MIC_VIRTIO_COPY_DESC, ©); } +#ifndef VIRTIO_BLK_T_GET_ID +#define VIRTIO_BLK_T_GET_ID 8 +#endif + static void * virtio_block(void *arg) { @@ -1297,12 +1331,7 @@ reset(struct mic_info *mic) mpsslog("%s: %s %d state %s\n", mic->name, __func__, __LINE__, state); - /* - * If the shutdown was initiated by OSPM, the state stays - * in "suspended" which is also a valid condition for reset. - */ - if ((!strcmp(state, "offline")) || - (!strcmp(state, "suspended"))) { + if (!strcmp(state, "ready")) { free(state); break; } @@ -1331,34 +1360,50 @@ get_mic_shutdown_status(struct mic_info *mic, char *shutdown_status) assert(0); }; -static int get_mic_state(struct mic_info *mic, char *state) +static int get_mic_state(struct mic_info *mic) { - if (!strcmp(state, "offline")) - return MIC_OFFLINE; - if (!strcmp(state, "online")) - return MIC_ONLINE; - if (!strcmp(state, "shutting_down")) - return MIC_SHUTTING_DOWN; - if (!strcmp(state, "reset_failed")) - return MIC_RESET_FAILED; - if (!strcmp(state, "suspending")) - return MIC_SUSPENDING; - if (!strcmp(state, "suspended")) - return MIC_SUSPENDED; - mpsslog("%s: BUG invalid state %s\n", mic->name, state); - /* Invalid state */ - assert(0); + char *state = NULL; + enum mic_states mic_state; + + while (!state) { + state = readsysfs(mic->name, "state"); + sleep(1); + } + mpsslog("%s: %s %d state %s\n", + mic->name, __func__, __LINE__, state); + + if (!strcmp(state, "ready")) { + mic_state = MIC_READY; + } else if (!strcmp(state, "booting")) { + mic_state = MIC_BOOTING; + } else if (!strcmp(state, "online")) { + mic_state = MIC_ONLINE; + } else if (!strcmp(state, "shutting_down")) { + mic_state = MIC_SHUTTING_DOWN; + } else if (!strcmp(state, "reset_failed")) { + mic_state = MIC_RESET_FAILED; + } else if (!strcmp(state, "resetting")) { + mic_state = MIC_RESETTING; + } else { + mpsslog("%s: BUG invalid state %s\n", mic->name, state); + assert(0); + } + + free(state); + return mic_state; }; static void mic_handle_shutdown(struct mic_info *mic) { #define SHUTDOWN_TIMEOUT 60 - int i = SHUTDOWN_TIMEOUT, ret, stat = 0; + int i = SHUTDOWN_TIMEOUT; char *shutdown_status; while (i) { shutdown_status = readsysfs(mic->name, "shutdown_status"); - if (!shutdown_status) + if (!shutdown_status) { + sleep(1); continue; + } mpsslog("%s: %s %d shutdown_status %s\n", mic->name, __func__, __LINE__, shutdown_status); switch (get_mic_shutdown_status(mic, shutdown_status)) { @@ -1377,94 +1422,110 @@ static void mic_handle_shutdown(struct mic_info *mic) i--; } reset: - ret = kill(mic->pid, SIGTERM); - mpsslog("%s: %s %d kill pid %d ret %d\n", - mic->name, __func__, __LINE__, - mic->pid, ret); - if (!ret) { - ret = waitpid(mic->pid, &stat, - WIFSIGNALED(stat)); - mpsslog("%s: %s %d waitpid ret %d pid %d\n", - mic->name, __func__, __LINE__, - ret, mic->pid); - } - if (ret == mic->pid) - reset(mic); + if (!i) + mpsslog("%s: %s %d timing out waiting for shutdown_status %s\n", + mic->name, __func__, __LINE__, shutdown_status); + reset(mic); } -static void * -mic_config(void *arg) +static int open_state_fd(struct mic_info *mic) { - struct mic_info *mic = (struct mic_info *)arg; - char *state = NULL; char pathname[PATH_MAX]; - int fd, ret; - struct pollfd ufds[1]; - char value[4096]; + int fd; snprintf(pathname, PATH_MAX - 1, "%s/%s/%s", MICSYSFSDIR, mic->name, "state"); fd = open(pathname, O_RDONLY); - if (fd < 0) { + if (fd < 0) mpsslog("%s: opening file %s failed %s\n", mic->name, pathname, strerror(errno)); - goto error; + return fd; +} + +static int block_till_state_change(int fd, struct mic_info *mic) +{ + struct pollfd ufds[1]; + char value[PAGE_SIZE]; + int ret; + + ufds[0].fd = fd; + ufds[0].events = POLLERR | POLLPRI; + ret = poll(ufds, 1, -1); + if (ret < 0) { + mpsslog("%s: %s %d poll failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + ret = lseek(fd, 0, SEEK_SET); + if (ret < 0) { + mpsslog("%s: %s %d Failed to seek to 0: %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + ret = read(fd, value, sizeof(value)); + if (ret < 0) { + mpsslog("%s: %s %d Failed to read sysfs entry: %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + return ret; + } + + return 0; +} + +static void * +mic_config(void *arg) +{ + struct mic_info *mic = (struct mic_info *)arg; + int fd, ret, stat = 0; + + fd = open_state_fd(mic); + if (fd < 0) { + mpsslog("%s: %s %d open state fd failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + goto exit; } do { - ret = lseek(fd, 0, SEEK_SET); + ret = block_till_state_change(fd, mic); if (ret < 0) { - mpsslog("%s: Failed to seek to file start '%s': %s\n", - mic->name, pathname, strerror(errno)); - goto close_error1; + mpsslog("%s: %s %d block_till_state_change error %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + goto close_exit; } - ret = read(fd, value, sizeof(value)); - if (ret < 0) { - mpsslog("%s: Failed to read sysfs entry '%s': %s\n", - mic->name, pathname, strerror(errno)); - goto close_error1; - } -retry: - state = readsysfs(mic->name, "state"); - if (!state) - goto retry; - mpsslog("%s: %s %d state %s\n", - mic->name, __func__, __LINE__, state); - switch (get_mic_state(mic, state)) { + + switch (get_mic_state(mic)) { case MIC_SHUTTING_DOWN: mic_handle_shutdown(mic); - goto close_error; - case MIC_SUSPENDING: - mic->boot_on_resume = 1; - setsysfs(mic->name, "state", "suspend"); - mic_handle_shutdown(mic); - goto close_error; - case MIC_OFFLINE: + break; + case MIC_READY: + case MIC_RESET_FAILED: + ret = kill(mic->pid, SIGTERM); + mpsslog("%s: %s %d kill pid %d ret %d\n", + mic->name, __func__, __LINE__, + mic->pid, ret); + if (!ret) { + ret = waitpid(mic->pid, &stat, + WIFSIGNALED(stat)); + mpsslog("%s: %s %d waitpid ret %d pid %d\n", + mic->name, __func__, __LINE__, + ret, mic->pid); + } if (mic->boot_on_resume) { setsysfs(mic->name, "state", "boot"); mic->boot_on_resume = 0; } - break; + goto close_exit; default: break; } - free(state); - - ufds[0].fd = fd; - ufds[0].events = POLLERR | POLLPRI; - ret = poll(ufds, 1, -1); - if (ret < 0) { - mpsslog("%s: poll failed %s\n", - mic->name, strerror(errno)); - goto close_error1; - } } while (1); -close_error: - free(state); -close_error1: + +close_exit: close(fd); -error: +exit: init_mic(mic); pthread_exit(NULL); } @@ -1477,15 +1538,15 @@ set_cmdline(struct mic_info *mic) len = snprintf(buffer, PATH_MAX, "clocksource=tsc highres=off nohz=off "); - len += snprintf(buffer + len, PATH_MAX - len, + len += snprintf(buffer + len, PATH_MAX, "cpufreq_on;corec6_off;pc3_off;pc6_off "); - len += snprintf(buffer + len, PATH_MAX - len, + len += snprintf(buffer + len, PATH_MAX, "ifcfg=static;address,172.31.%d.1;netmask,255.255.255.0", - mic->id); + mic->id + 1); setsysfs(mic->name, "cmdline", buffer); mpsslog("%s: Command line: \"%s\"\n", mic->name, buffer); - snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id); + snprintf(buffer, PATH_MAX, "172.31.%d.1", mic->id + 1); mpsslog("%s: IPADDR: \"%s\"\n", mic->name, buffer); } @@ -1541,8 +1602,6 @@ set_log_buf_info(struct mic_info *mic) close(fd); } -static void init_mic(struct mic_info *mic); - static void change_virtblk_backend(int x, siginfo_t *siginfo, void *p) { @@ -1553,8 +1612,16 @@ change_virtblk_backend(int x, siginfo_t *siginfo, void *p) } static void -init_mic(struct mic_info *mic) +set_mic_boot_params(struct mic_info *mic) +{ + set_log_buf_info(mic); + set_cmdline(mic); +} + +static void * +init_mic(void *arg) { + struct mic_info *mic = (struct mic_info *)arg; struct sigaction ignore = { .sa_flags = 0, .sa_handler = SIG_IGN @@ -1564,7 +1631,7 @@ init_mic(struct mic_info *mic) .sa_sigaction = change_virtblk_backend, }; char buffer[PATH_MAX]; - int err; + int err, fd; /* * Currently, one virtio block device is supported for each MIC card @@ -1577,12 +1644,38 @@ init_mic(struct mic_info *mic) * the MIC daemon. */ sigaction(SIGUSR1, &ignore, NULL); +retry: + fd = open_state_fd(mic); + if (fd < 0) { + mpsslog("%s: %s %d open state fd failed %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + sleep(2); + goto retry; + } + + if (mic->restart) { + snprintf(buffer, PATH_MAX, "boot"); + setsysfs(mic->name, "state", buffer); + mpsslog("%s restarting mic %d\n", + mic->name, mic->restart); + mic->restart = 0; + } + + while (1) { + while (block_till_state_change(fd, mic)) { + mpsslog("%s: %s %d block_till_state_change error %s\n", + mic->name, __func__, __LINE__, strerror(errno)); + sleep(2); + continue; + } + + if (get_mic_state(mic) == MIC_BOOTING) + break; + } mic->pid = fork(); switch (mic->pid) { case 0: - set_log_buf_info(mic); - set_cmdline(mic); add_virtio_device(mic, &virtcons_dev_page.dd); add_virtio_device(mic, &virtnet_dev_page.dd); err = pthread_create(&mic->mic_console.console_thread, NULL, @@ -1612,24 +1705,29 @@ init_mic(struct mic_info *mic) mic->name, mic->id, errno); break; default: - if (mic->restart) { - snprintf(buffer, PATH_MAX, "boot"); - setsysfs(mic->name, "state", buffer); - mpsslog("%s restarting mic %d\n", - mic->name, mic->restart); - mic->restart = 0; - } - pthread_create(&mic->config_thread, NULL, mic_config, mic); + err = pthread_create(&mic->config_thread, NULL, + mic_config, mic); + if (err) + mpsslog("%s mic_config pthread_create failed %s\n", + mic->name, strerror(err)); } + + return NULL; } static void start_daemon(void) { struct mic_info *mic; + int err; - for (mic = mic_list.next; mic != NULL; mic = mic->next) - init_mic(mic); + for (mic = mic_list.next; mic; mic = mic->next) { + set_mic_boot_params(mic); + err = pthread_create(&mic->init_thread, NULL, init_mic, mic); + if (err) + mpsslog("%s init_mic pthread_create failed %s\n", + mic->name, strerror(err)); + } while (1) sleep(60); diff --git a/Documentation/mic/mpssd/mpssd.h b/Documentation/mic/mpssd/mpssd.h index f5f18b15d9a0..8bd64944aacc 100644 --- a/Documentation/mic/mpssd/mpssd.h +++ b/Documentation/mic/mpssd/mpssd.h @@ -86,6 +86,7 @@ struct mic_info { int id; char *name; pthread_t config_thread; + pthread_t init_thread; pid_t pid; struct mic_console_info mic_console; struct mic_net_info mic_net; diff --git a/drivers/misc/mic/Makefile b/drivers/misc/mic/Makefile index a2e75f46fe4e..e288a1106738 100644 --- a/drivers/misc/mic/Makefile +++ b/drivers/misc/mic/Makefile @@ -2,5 +2,9 @@ # Makefile - Intel MIC Linux driver. # Copyright(c) 2013, Intel Corporation. # +obj-$(CONFIG_INTEL_MIC_HOST) += host/ +obj-$(CONFIG_INTEL_MIC_CARD) += card/ obj-y += bus/ obj-$(CONFIG_SCIF) += scif/ +obj-$(CONFIG_MIC_COSM) += cosm/ +obj-$(CONFIG_MIC_COSM) += cosm_client/ diff --git a/drivers/misc/mic/bus/scif_bus.c b/drivers/misc/mic/bus/scif_bus.c index 2da7ceed015d..fd2702143022 100644 --- a/drivers/misc/mic/bus/scif_bus.c +++ b/drivers/misc/mic/bus/scif_bus.c @@ -28,7 +28,6 @@ static ssize_t device_show(struct device *d, return sprintf(buf, "0x%04x\n", dev->id.device); } - static DEVICE_ATTR_RO(device); static ssize_t vendor_show(struct device *d, @@ -38,7 +37,6 @@ static ssize_t vendor_show(struct device *d, return sprintf(buf, "0x%04x\n", dev->id.vendor); } - static DEVICE_ATTR_RO(vendor); static ssize_t modalias_show(struct device *d, @@ -49,7 +47,6 @@ static ssize_t modalias_show(struct device *d, return sprintf(buf, "scif:d%08Xv%08X\n", dev->id.device, dev->id.vendor); } - static DEVICE_ATTR_RO(modalias); static struct attribute *scif_dev_attrs[] = { @@ -144,7 +141,8 @@ struct scif_hw_dev * scif_register_device(struct device *pdev, int id, struct dma_map_ops *dma_ops, struct scif_hw_ops *hw_ops, u8 dnode, u8 snode, struct mic_mw *mmio, struct mic_mw *aper, void *dp, - void __iomem *rdp, struct dma_chan **chan, int num_chan) + void __iomem *rdp, struct dma_chan **chan, int num_chan, + bool card_rel_da) { int ret; struct scif_hw_dev *sdev; @@ -171,6 +169,7 @@ scif_register_device(struct device *pdev, int id, struct dma_map_ops *dma_ops, dma_set_mask(&sdev->dev, DMA_BIT_MASK(64)); sdev->dma_ch = chan; sdev->num_dma_ch = num_chan; + sdev->card_rel_da = card_rel_da; dev_set_name(&sdev->dev, "scif-dev%u", sdev->dnode); /* * device_register() causes the bus infrastructure to look for a diff --git a/drivers/misc/mic/bus/scif_bus.h b/drivers/misc/mic/bus/scif_bus.h index 335a228a8236..94f29ac608b6 100644 --- a/drivers/misc/mic/bus/scif_bus.h +++ b/drivers/misc/mic/bus/scif_bus.h @@ -46,6 +46,8 @@ struct scif_hw_dev_id { * @rdp - Remote device page * @dma_ch - Array of DMA channels * @num_dma_ch - Number of DMA channels available + * @card_rel_da - Set to true if DMA addresses programmed in the DMA engine + * are relative to the card point of view */ struct scif_hw_dev { struct scif_hw_ops *hw_ops; @@ -59,6 +61,7 @@ struct scif_hw_dev { void __iomem *rdp; struct dma_chan **dma_ch; int num_dma_ch; + bool card_rel_da; }; /** @@ -114,7 +117,8 @@ scif_register_device(struct device *pdev, int id, struct scif_hw_ops *hw_ops, u8 dnode, u8 snode, struct mic_mw *mmio, struct mic_mw *aper, void *dp, void __iomem *rdp, - struct dma_chan **chan, int num_chan); + struct dma_chan **chan, int num_chan, + bool card_rel_da); void scif_unregister_device(struct scif_hw_dev *sdev); static inline struct scif_hw_dev *dev_to_scif(struct device *dev) diff --git a/include/uapi/linux/mic_common.h b/include/uapi/linux/mic_common.h index 302a2ced373c..e9686372029d 100644 --- a/include/uapi/linux/mic_common.h +++ b/include/uapi/linux/mic_common.h @@ -75,12 +75,7 @@ struct mic_device_ctrl { * struct mic_bootparam: Virtio device independent information in device page * * @magic: A magic value used by the card to ensure it can see the host - * @c2h_shutdown_db: Card to Host shutdown doorbell set by host - * @h2c_shutdown_db: Host to Card shutdown doorbell set by card * @h2c_config_db: Host to Card Virtio config doorbell set by card - * @shutdown_status: Card shutdown status set by card - * @shutdown_card: Set to 1 by the host when a card shutdown is initiated - * @tot_nodes: Total number of nodes in the SCIF network * @node_id: Unique id of the node * @h2c_scif_db - Host to card SCIF doorbell set by card * @c2h_scif_db - Card to host SCIF doorbell set by host @@ -89,12 +84,7 @@ struct mic_device_ctrl { */ struct mic_bootparam { __le32 magic; - __s8 c2h_shutdown_db; - __s8 h2c_shutdown_db; __s8 h2c_config_db; - __u8 shutdown_status; - __u8 shutdown_card; - __u8 tot_nodes; __u8 node_id; __u8 h2c_scif_db; __u8 c2h_scif_db; @@ -219,12 +209,12 @@ static inline unsigned mic_total_desc_size(struct mic_device_desc *desc) * enum mic_states - MIC states. */ enum mic_states { - MIC_OFFLINE = 0, + MIC_READY = 0, + MIC_BOOTING, MIC_ONLINE, MIC_SHUTTING_DOWN, + MIC_RESETTING, MIC_RESET_FAILED, - MIC_SUSPENDING, - MIC_SUSPENDED, MIC_LAST }; -- cgit v1.2.3 From a44f2630d78bfafc8eb5ab7d8b7b8cd4642ba749 Mon Sep 17 00:00:00 2001 From: Sudeep Dutt Date: Tue, 29 Sep 2015 18:15:03 -0700 Subject: misc: mic: SCIF RMA header file and IOCTL changes This patch updates the SCIF header file and IOCTL interface with the changes required to support RMAs. APIs added include the ability to pin pages and register those pages with SCIF. SCIF kernel clients can also add references to remote registered pages and access them via the CPU. The user space IOCTL interface has been updated to enable SCIF registration, RDMA/CPU copies and fence APIs for RDMA synchronization. Reviewed-by: Nikhil Rao Reviewed-by: Ashutosh Dixit Signed-off-by: Sudeep Dutt Signed-off-by: Greg Kroah-Hartman --- include/linux/scif.h | 234 ++++++++++++++++++++++++++++++++++++++-- include/uapi/linux/scif_ioctl.h | 85 +++++++++++++++ 2 files changed, 309 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/scif.h b/include/linux/scif.h index fd62c051b166..49a35d6edc94 100644 --- a/include/linux/scif.h +++ b/include/linux/scif.h @@ -93,6 +93,27 @@ enum { #define SCIF_PORT_RSVD 1088 typedef struct scif_endpt *scif_epd_t; +typedef struct scif_pinned_pages *scif_pinned_pages_t; + +/** + * struct scif_range - SCIF registered range used in kernel mode + * @cookie: cookie used internally by SCIF + * @nr_pages: number of pages of PAGE_SIZE + * @prot_flags: R/W protection + * @phys_addr: Array of bus addresses + * @va: Array of kernel virtual addresses backed by the pages in the phys_addr + * array. The va is populated only when called on the host for a remote + * SCIF connection on MIC. This is required to support the use case of DMA + * between MIC and another device which is not a SCIF node e.g., an IB or + * ethernet NIC. + */ +struct scif_range { + void *cookie; + int nr_pages; + int prot_flags; + dma_addr_t *phys_addr; + void __iomem **va; +}; /** * struct scif_pollepd - SCIF endpoint to be monitored via scif_poll @@ -389,7 +410,6 @@ int scif_close(scif_epd_t epd); * Errors: * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer - * EFAULT - An invalid address was specified for a parameter * EINVAL - flags is invalid, or len is negative * ENODEV - The remote node is lost or existed, but is not currently in the * network since it may have crashed @@ -442,7 +462,6 @@ int scif_send(scif_epd_t epd, void *msg, int len, int flags); * EAGAIN - The destination node is returning from a low power state * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer - * EFAULT - An invalid address was specified for a parameter * EINVAL - flags is invalid, or len is negative * ENODEV - The remote node is lost or existed, but is not currently in the * network since it may have crashed @@ -505,9 +524,6 @@ int scif_recv(scif_epd_t epd, void *msg, int len, int flags); * SCIF_PROT_READ - allow read operations from the window * SCIF_PROT_WRITE - allow write operations to the window * - * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a - * fixed offset. - * * Return: * Upon successful completion, scif_register() returns the offset at which the * mapping was placed (po); otherwise in user mode SCIF_REGISTER_FAILED (that @@ -520,7 +536,6 @@ int scif_recv(scif_epd_t epd, void *msg, int len, int flags); * EAGAIN - The mapping could not be performed due to lack of resources * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer - * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid * EINVAL - map_flags is invalid, or prot_flags is invalid, or SCIF_MAP_FIXED is * set in flags, and offset is not a multiple of the page size, or addr is not a * multiple of the page size, or len is not a multiple of the page size, or is @@ -803,7 +818,6 @@ int scif_writeto(scif_epd_t epd, off_t loffset, size_t len, off_t * EACCESS - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer - * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid * EINVAL - rma_flags is invalid * ENODEV - The remote node is lost or existed, but is not currently in the * network since it may have crashed @@ -884,7 +898,6 @@ int scif_vreadfrom(scif_epd_t epd, void *addr, size_t len, off_t roffset, * EACCESS - Attempt to write to a read-only range * EBADF, ENOTTY - epd is not a valid endpoint descriptor * ECONNRESET - Connection reset by peer - * EFAULT - Addresses in the range [addr, addr + len - 1] are invalid * EINVAL - rma_flags is invalid * ENODEV - The remote node is lost or existed, but is not currently in the * network since it may have crashed @@ -1028,11 +1041,212 @@ int scif_fence_signal(scif_epd_t epd, off_t loff, u64 lval, off_t roff, * online nodes in the SCIF network including 'self'; otherwise in user mode * -1 is returned and errno is set to indicate the error; in kernel mode no * errors are returned. + */ +int scif_get_node_ids(u16 *nodes, int len, u16 *self); + +/** + * scif_pin_pages() - Pin a set of pages + * @addr: Virtual address of range to pin + * @len: Length of range to pin + * @prot_flags: Page protection flags + * @map_flags: Page classification flags + * @pinned_pages: Handle to pinned pages + * + * scif_pin_pages() pins (locks in physical memory) the physical pages which + * back the range of virtual address pages starting at addr and continuing for + * len bytes. addr and len are constrained to be multiples of the page size. A + * successful scif_pin_pages() call returns a handle to pinned_pages which may + * be used in subsequent calls to scif_register_pinned_pages(). + * + * The pages will remain pinned as long as there is a reference against the + * scif_pinned_pages_t value returned by scif_pin_pages() and until + * scif_unpin_pages() is called, passing the scif_pinned_pages_t value. A + * reference is added to a scif_pinned_pages_t value each time a window is + * created by calling scif_register_pinned_pages() and passing the + * scif_pinned_pages_t value. A reference is removed from a + * scif_pinned_pages_t value each time such a window is deleted. + * + * Subsequent operations which change the memory pages to which virtual + * addresses are mapped (such as mmap(), munmap()) have no effect on the + * scif_pinned_pages_t value or windows created against it. + * + * If the process will fork(), it is recommended that the registered + * virtual address range be marked with MADV_DONTFORK. Doing so will prevent + * problems due to copy-on-write semantics. + * + * The prot_flags argument is formed by OR'ing together one or more of the + * following values. + * SCIF_PROT_READ - allow read operations against the pages + * SCIF_PROT_WRITE - allow write operations against the pages + * The map_flags argument can be set as SCIF_MAP_KERNEL to interpret addr as a + * kernel space address. By default, addr is interpreted as a user space + * address. + * + * Return: + * Upon successful completion, scif_pin_pages() returns 0; otherwise the + * negative of one of the following errors is returned. * * Errors: - * EFAULT - Bad address + * EINVAL - prot_flags is invalid, map_flags is invalid, or offset is negative + * ENOMEM - Not enough space */ -int scif_get_node_ids(u16 *nodes, int len, u16 *self); +int scif_pin_pages(void *addr, size_t len, int prot_flags, int map_flags, + scif_pinned_pages_t *pinned_pages); + +/** + * scif_unpin_pages() - Unpin a set of pages + * @pinned_pages: Handle to pinned pages to be unpinned + * + * scif_unpin_pages() prevents scif_register_pinned_pages() from registering new + * windows against pinned_pages. The physical pages represented by pinned_pages + * will remain pinned until all windows previously registered against + * pinned_pages are deleted (the window is scif_unregister()'d and all + * references to the window are removed (see scif_unregister()). + * + * pinned_pages must have been obtain from a previous call to scif_pin_pages(). + * After calling scif_unpin_pages(), it is an error to pass pinned_pages to + * scif_register_pinned_pages(). + * + * Return: + * Upon successful completion, scif_unpin_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * + * Errors: + * EINVAL - pinned_pages is not valid + */ +int scif_unpin_pages(scif_pinned_pages_t pinned_pages); + +/** + * scif_register_pinned_pages() - Mark a memory region for remote access. + * @epd: endpoint descriptor + * @pinned_pages: Handle to pinned pages + * @offset: Registered address space offset + * @map_flags: Flags which control where pages are mapped + * + * The scif_register_pinned_pages() function opens a window, a range of whole + * pages of the registered address space of the endpoint epd, starting at + * offset po. The value of po, further described below, is a function of the + * parameters offset and pinned_pages, and the value of map_flags. Each page of + * the window represents a corresponding physical memory page of the range + * represented by pinned_pages; the length of the window is the same as the + * length of range represented by pinned_pages. A successful + * scif_register_pinned_pages() call returns po as the return value. + * + * When SCIF_MAP_FIXED is set in the map_flags argument, po will be offset + * exactly, and offset is constrained to be a multiple of the page size. The + * mapping established by scif_register_pinned_pages() will not replace any + * existing registration; an error is returned if any page of the new window + * would intersect an existing window. + * + * When SCIF_MAP_FIXED is not set, the implementation uses offset in an + * implementation-defined manner to arrive at po. The po so chosen will be an + * area of the registered address space that the implementation deems suitable + * for a mapping of the required size. An offset value of 0 is interpreted as + * granting the implementation complete freedom in selecting po, subject to + * constraints described below. A non-zero value of offset is taken to be a + * suggestion of an offset near which the mapping should be placed. When the + * implementation selects a value for po, it does not replace any extant + * window. In all cases, po will be a multiple of the page size. + * + * The physical pages which are so represented by a window are available for + * access in calls to scif_get_pages(), scif_readfrom(), scif_writeto(), + * scif_vreadfrom(), and scif_vwriteto(). While a window is registered, the + * physical pages represented by the window will not be reused by the memory + * subsystem for any other purpose. Note that the same physical page may be + * represented by multiple windows. + * + * Windows created by scif_register_pinned_pages() are unregistered by + * scif_unregister(). + * + * The map_flags argument can be set to SCIF_MAP_FIXED which interprets a + * fixed offset. + * + * Return: + * Upon successful completion, scif_register_pinned_pages() returns the offset + * at which the mapping was placed (po); otherwise the negative of one of the + * following errors is returned. + * + * Errors: + * EADDRINUSE - SCIF_MAP_FIXED is set in map_flags and pages in the new window + * would intersect an existing window + * EAGAIN - The mapping could not be performed due to lack of resources + * ECONNRESET - Connection reset by peer + * EINVAL - map_flags is invalid, or SCIF_MAP_FIXED is set in map_flags, and + * offset is not a multiple of the page size, or offset is negative + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOMEM - Not enough space + * ENOTCONN - The endpoint is not connected + */ +off_t scif_register_pinned_pages(scif_epd_t epd, + scif_pinned_pages_t pinned_pages, + off_t offset, int map_flags); + +/** + * scif_get_pages() - Add references to remote registered pages + * @epd: endpoint descriptor + * @offset: remote registered offset + * @len: length of range of pages + * @pages: returned scif_range structure + * + * scif_get_pages() returns the addresses of the physical pages represented by + * those pages of the registered address space of the peer of epd, starting at + * offset and continuing for len bytes. offset and len are constrained to be + * multiples of the page size. + * + * All of the pages in the specified range [offset, offset + len - 1] must be + * within a single window of the registered address space of the peer of epd. + * + * The addresses are returned as a virtually contiguous array pointed to by the + * phys_addr component of the scif_range structure whose address is returned in + * pages. The nr_pages component of scif_range is the length of the array. The + * prot_flags component of scif_range holds the protection flag value passed + * when the pages were registered. + * + * Each physical page whose address is returned by scif_get_pages() remains + * available and will not be released for reuse until the scif_range structure + * is returned in a call to scif_put_pages(). The scif_range structure returned + * by scif_get_pages() must be unmodified. + * + * It is an error to call scif_close() on an endpoint on which a scif_range + * structure of that endpoint has not been returned to scif_put_pages(). + * + * Return: + * Upon successful completion, scif_get_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * Errors: + * ECONNRESET - Connection reset by peer. + * EINVAL - offset is not a multiple of the page size, or offset is negative, or + * len is not a multiple of the page size + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + * ENXIO - Offsets in the range [offset, offset + len - 1] are invalid + * for the registered address space of the peer epd + */ +int scif_get_pages(scif_epd_t epd, off_t offset, size_t len, + struct scif_range **pages); + +/** + * scif_put_pages() - Remove references from remote registered pages + * @pages: pages to be returned + * + * scif_put_pages() releases a scif_range structure previously obtained by + * calling scif_get_pages(). The physical pages represented by pages may + * be reused when the window which represented those pages is unregistered. + * Therefore, those pages must not be accessed after calling scif_put_pages(). + * + * Return: + * Upon successful completion, scif_put_pages() returns 0; otherwise the + * negative of one of the following errors is returned. + * Errors: + * EINVAL - pages does not point to a valid scif_range structure, or + * the scif_range structure pointed to by pages was already returned + * ENODEV - The remote node is lost or existed, but is not currently in the + * network since it may have crashed + * ENOTCONN - The endpoint is not connected + */ +int scif_put_pages(struct scif_range *pages); /** * scif_poll() - Wait for some event on an endpoint diff --git a/include/uapi/linux/scif_ioctl.h b/include/uapi/linux/scif_ioctl.h index 4a94d917cf99..d9048918be52 100644 --- a/include/uapi/linux/scif_ioctl.h +++ b/include/uapi/linux/scif_ioctl.h @@ -106,6 +106,82 @@ struct scifioctl_msg { __s32 out_len; }; +/** + * struct scifioctl_reg - used for SCIF_REG IOCTL + * @addr: starting virtual address + * @len: length of range + * @offset: offset of window + * @prot: read/write protection + * @flags: flags + * @out_offset: offset returned + */ +struct scifioctl_reg { + __u64 addr; + __u64 len; + __s64 offset; + __s32 prot; + __s32 flags; + __s64 out_offset; +}; + +/** + * struct scifioctl_unreg - used for SCIF_UNREG IOCTL + * @offset: start of range to unregister + * @len: length of range to unregister + */ +struct scifioctl_unreg { + __s64 offset; + __u64 len; +}; + +/** + * struct scifioctl_copy - used for SCIF DMA copy IOCTLs + * + * @loffset: offset in local registered address space to/from + * which to copy + * @len: length of range to copy + * @roffset: offset in remote registered address space to/from + * which to copy + * @addr: user virtual address to/from which to copy + * @flags: flags + * + * This structure is used for SCIF_READFROM, SCIF_WRITETO, SCIF_VREADFROM + * and SCIF_VREADFROM IOCTL's. + */ +struct scifioctl_copy { + __s64 loffset; + __u64 len; + __s64 roffset; + __u64 addr; + __s32 flags; +}; + +/** + * struct scifioctl_fence_mark - used for SCIF_FENCE_MARK IOCTL + * @flags: flags + * @mark: fence handle which is a pointer to a __s32 + */ +struct scifioctl_fence_mark { + __s32 flags; + __u64 mark; +}; + +/** + * struct scifioctl_fence_signal - used for SCIF_FENCE_SIGNAL IOCTL + * @loff: local offset + * @lval: value to write to loffset + * @roff: remote offset + * @rval: value to write to roffset + * @flags: flags + */ +struct scifioctl_fence_signal { + __s64 loff; + __u64 lval; + __s64 roff; + __u64 rval; + __s32 flags; +}; + /** * struct scifioctl_node_ids - used for SCIF_GET_NODEIDS IOCTL * @nodes: pointer to an array of node_ids @@ -125,6 +201,15 @@ struct scifioctl_node_ids { #define SCIF_ACCEPTREG _IOWR('s', 5, __u64) #define SCIF_SEND _IOWR('s', 6, struct scifioctl_msg) #define SCIF_RECV _IOWR('s', 7, struct scifioctl_msg) +#define SCIF_REG _IOWR('s', 8, struct scifioctl_reg) +#define SCIF_UNREG _IOWR('s', 9, struct scifioctl_unreg) +#define SCIF_READFROM _IOWR('s', 10, struct scifioctl_copy) +#define SCIF_WRITETO _IOWR('s', 11, struct scifioctl_copy) +#define SCIF_VREADFROM _IOWR('s', 12, struct scifioctl_copy) +#define SCIF_VWRITETO _IOWR('s', 13, struct scifioctl_copy) #define SCIF_GET_NODEIDS _IOWR('s', 14, struct scifioctl_node_ids) +#define SCIF_FENCE_MARK _IOWR('s', 15, struct scifioctl_fence_mark) +#define SCIF_FENCE_WAIT _IOWR('s', 16, __s32) +#define SCIF_FENCE_SIGNAL _IOWR('s', 17, struct scifioctl_fence_signal) #endif /* SCIF_IOCTL_H */ -- cgit v1.2.3 From 7bd1d4093c2fa37d1ecab05da3c9d48ea2af2264 Mon Sep 17 00:00:00 2001 From: Alexander Shishkin Date: Tue, 22 Sep 2015 15:47:10 +0300 Subject: stm class: Introduce an abstraction for System Trace Module devices A System Trace Module (STM) is a device exporting data in System Trace Protocol (STP) format as defined by MIPI STP standards. Examples of such devices are Intel(R) Trace Hub and Coresight STM. This abstraction provides a unified interface for software trace sources to send their data over an STM device to a debug host. In order to do that, such a trace source needs to be assigned a pair of master/channel identifiers that all the data from this source will be tagged with. The STP decoder on the debug host side will use these master/channel tags to distinguish different trace streams from one another inside one STP stream. This abstraction provides a configfs-based policy management mechanism for dynamic allocation of these master/channel pairs based on trace source-supplied string identifier. It has the flexibility of being defined at runtime and at the same time (provided that the policy definition is aligned with the decoding end) consistency. For userspace trace sources, this abstraction provides write()-based and mmap()-based (if the underlying stm device allows this) output mechanism. For kernel-side trace sources, we provide "stm_source" device class that can be connected to an stm device at run time. Cc: linux-api@vger.kernel.org Reviewed-by: Mathieu Poirier Signed-off-by: Alexander Shishkin Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/configfs-stp-policy | 48 + Documentation/ABI/testing/sysfs-class-stm | 14 + Documentation/ABI/testing/sysfs-class-stm_source | 11 + Documentation/ioctl/ioctl-number.txt | 3 + Documentation/trace/stm.txt | 80 ++ drivers/Kconfig | 2 + drivers/Makefile | 1 + drivers/hwtracing/stm/Kconfig | 8 + drivers/hwtracing/stm/Makefile | 3 + drivers/hwtracing/stm/core.c | 1029 ++++++++++++++++++++++ drivers/hwtracing/stm/policy.c | 529 +++++++++++ drivers/hwtracing/stm/stm.h | 87 ++ include/linux/stm.h | 126 +++ include/uapi/linux/stm.h | 50 ++ 14 files changed, 1991 insertions(+) create mode 100644 Documentation/ABI/testing/configfs-stp-policy create mode 100644 Documentation/ABI/testing/sysfs-class-stm create mode 100644 Documentation/ABI/testing/sysfs-class-stm_source create mode 100644 Documentation/trace/stm.txt create mode 100644 drivers/hwtracing/stm/Kconfig create mode 100644 drivers/hwtracing/stm/Makefile create mode 100644 drivers/hwtracing/stm/core.c create mode 100644 drivers/hwtracing/stm/policy.c create mode 100644 drivers/hwtracing/stm/stm.h create mode 100644 include/linux/stm.h create mode 100644 include/uapi/linux/stm.h (limited to 'include/uapi') diff --git a/Documentation/ABI/testing/configfs-stp-policy b/Documentation/ABI/testing/configfs-stp-policy new file mode 100644 index 000000000000..421ce6825c66 --- /dev/null +++ b/Documentation/ABI/testing/configfs-stp-policy @@ -0,0 +1,48 @@ +What: /config/stp-policy +Date: June 2015 +KernelVersion: 4.3 +Description: + This group contains policies mandating Master/Channel allocation + for software sources wishing to send trace data over an STM + device. + +What: /config/stp-policy/. +Date: June 2015 +KernelVersion: 4.3 +Description: + This group is the root of a policy; its name is a concatenation + of an stm device name to which this policy applies and an + arbitrary string. If part doesn't match an existing + stm device, mkdir will fail with ENODEV; if that device already + has a policy assigned to it, mkdir will fail with EBUSY. + +What: /config/stp-policy/./device +Date: June 2015 +KernelVersion: 4.3 +Description: + STM device to which this policy applies, read only. Same as the + component of its parent directory. + +What: /config/stp-policy/./ +Date: June 2015 +KernelVersion: 4.3 +Description: + Policy node is a string identifier that software clients will + use to request a master/channel to be allocated and assigned to + them. + +What: /config/stp-policy/.//masters +Date: June 2015 +KernelVersion: 4.3 +Description: + Range of masters from which to allocate for users of this node. + Write two numbers: the first master and the last master number. + +What: /config/stp-policy/.//channels +Date: June 2015 +KernelVersion: 4.3 +Description: + Range of channels from which to allocate for users of this node. + Write two numbers: the first channel and the last channel + number. + diff --git a/Documentation/ABI/testing/sysfs-class-stm b/Documentation/ABI/testing/sysfs-class-stm new file mode 100644 index 000000000000..c9aa4f3fc9a7 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-stm @@ -0,0 +1,14 @@ +What: /sys/class/stm//masters +Date: June 2015 +KernelVersion: 4.3 +Contact: Alexander Shishkin +Description: + Shows first and last available to software master numbers on + this STM device. + +What: /sys/class/stm//channels +Date: June 2015 +KernelVersion: 4.3 +Contact: Alexander Shishkin +Description: + Shows the number of channels per master on this STM device. diff --git a/Documentation/ABI/testing/sysfs-class-stm_source b/Documentation/ABI/testing/sysfs-class-stm_source new file mode 100644 index 000000000000..57b8dd39bbf7 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-stm_source @@ -0,0 +1,11 @@ +What: /sys/class/stm_source//stm_source_link +Date: June 2015 +KernelVersion: 4.3 +Contact: Alexander Shishkin +Description: + stm_source device linkage to stm device, where its tracing data + is directed. Reads return an existing connection or "" if + this stm_source is not connected to any stm device yet. + Write an existing (registered) stm device's name here to + connect that device. If a device is already connected to this + stm_source, it will first be disconnected. diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index df1b25eb8382..3785b7e131f8 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -81,6 +81,9 @@ Code Seq#(hex) Include File Comments 0x22 all scsi/sg.h '#' 00-3F IEEE 1394 Subsystem Block for the entire subsystem '$' 00-0F linux/perf_counter.h, linux/perf_event.h +'%' 00-0F include/uapi/linux/stm.h + System Trace Module subsystem + '&' 00-07 drivers/firewire/nosy-user.h '1' 00-1F PPS kit from Ulrich Windl diff --git a/Documentation/trace/stm.txt b/Documentation/trace/stm.txt new file mode 100644 index 000000000000..ea035f9dbfd7 --- /dev/null +++ b/Documentation/trace/stm.txt @@ -0,0 +1,80 @@ +System Trace Module +=================== + +System Trace Module (STM) is a device described in MIPI STP specs as +STP trace stream generator. STP (System Trace Protocol) is a trace +protocol multiplexing data from multiple trace sources, each one of +which is assigned a unique pair of master and channel. While some of +these masters and channels are statically allocated to certain +hardware trace sources, others are available to software. Software +trace sources are usually free to pick for themselves any +master/channel combination from this pool. + +On the receiving end of this STP stream (the decoder side), trace +sources can only be identified by master/channel combination, so in +order for the decoder to be able to make sense of the trace that +involves multiple trace sources, it needs to be able to map those +master/channel pairs to the trace sources that it understands. + +For instance, it is helpful to know that syslog messages come on +master 7 channel 15, while arbitrary user applications can use masters +48 to 63 and channels 0 to 127. + +To solve this mapping problem, stm class provides a policy management +mechanism via configfs, that allows defining rules that map string +identifiers to ranges of masters and channels. If these rules (policy) +are consistent with what decoder expects, it will be able to properly +process the trace data. + +This policy is a tree structure containing rules (policy_node) that +have a name (string identifier) and a range of masters and channels +associated with it, located in "stp-policy" subsystem directory in +configfs. The topmost directory's name (the policy) is formatted as +the STM device name to which this policy applies and and arbitrary +string identifier separated by a stop. From the examle above, a rule +may look like this: + +$ ls /config/stp-policy/dummy_stm.my-policy/user +channels masters +$ cat /config/stp-policy/dummy_stm.my-policy/user/masters +48 63 +$ cat /config/stp-policy/dummy_stm.my-policy/user/channels +0 127 + +which means that the master allocation pool for this rule consists of +masters 48 through 63 and channel allocation pool has channels 0 +through 127 in it. Now, any producer (trace source) identifying itself +with "user" identification string will be allocated a master and +channel from within these ranges. + +These rules can be nested, for example, one can define a rule "dummy" +under "user" directory from the example above and this new rule will +be used for trace sources with the id string of "user/dummy". + +Trace sources have to open the stm class device's node and write their +trace data into its file descriptor. In order to identify themselves +to the policy, they need to do a STP_POLICY_ID_SET ioctl on this file +descriptor providing their id string. Otherwise, they will be +automatically allocated a master/channel pair upon first write to this +file descriptor according to the "default" rule of the policy, if such +exists. + +Some STM devices may allow direct mapping of the channel mmio regions +to userspace for zero-copy writing. One mappable page (in terms of +mmu) will usually contain multiple channels' mmios, so the user will +need to allocate that many channels to themselves (via the +aforementioned ioctl() call) to be able to do this. That is, if your +stm device's channel mmio region is 64 bytes and hardware page size is +4096 bytes, after a successful STP_POLICY_ID_SET ioctl() call with +width==64, you should be able to mmap() one page on this file +descriptor and obtain direct access to an mmio region for 64 channels. + +For kernel-based trace sources, there is "stm_source" device +class. Devices of this class can be connected and disconnected to/from +stm devices at runtime via a sysfs attribute. + +Examples of STM devices are Intel(R) Trace Hub [1] and Coresight STM +[2]. + +[1] https://software.intel.com/sites/default/files/managed/d3/3c/intel-th-developer-manual.pdf +[2] http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ddi0444b/index.html diff --git a/drivers/Kconfig b/drivers/Kconfig index 46b4a8e0f859..b6e1cea63f81 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -188,4 +188,6 @@ source "drivers/nvdimm/Kconfig" source "drivers/nvmem/Kconfig" +source "drivers/hwtracing/stm/Kconfig" + endmenu diff --git a/drivers/Makefile b/drivers/Makefile index b250b36b54f2..e71b5e2a2c71 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -165,5 +165,6 @@ obj-$(CONFIG_PERF_EVENTS) += perf/ obj-$(CONFIG_RAS) += ras/ obj-$(CONFIG_THUNDERBOLT) += thunderbolt/ obj-$(CONFIG_CORESIGHT) += hwtracing/coresight/ +obj-$(CONFIG_STM) += hwtracing/stm/ obj-$(CONFIG_ANDROID) += android/ obj-$(CONFIG_NVMEM) += nvmem/ diff --git a/drivers/hwtracing/stm/Kconfig b/drivers/hwtracing/stm/Kconfig new file mode 100644 index 000000000000..e101cb4f8e43 --- /dev/null +++ b/drivers/hwtracing/stm/Kconfig @@ -0,0 +1,8 @@ +config STM + tristate "System Trace Module devices" + help + A System Trace Module (STM) is a device exporting data in System + Trace Protocol (STP) format as defined by MIPI STP standards. + Examples of such devices are Intel(R) Trace Hub and Coresight STM. + + Say Y here to enable System Trace Module device support. diff --git a/drivers/hwtracing/stm/Makefile b/drivers/hwtracing/stm/Makefile new file mode 100644 index 000000000000..adec7016499f --- /dev/null +++ b/drivers/hwtracing/stm/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_STM) += stm_core.o + +stm_core-y := core.o policy.o diff --git a/drivers/hwtracing/stm/core.c b/drivers/hwtracing/stm/core.c new file mode 100644 index 000000000000..b79c42c62557 --- /dev/null +++ b/drivers/hwtracing/stm/core.c @@ -0,0 +1,1029 @@ +/* + * System Trace Module (STM) infrastructure + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * STM class implements generic infrastructure for System Trace Module devices + * as defined in MIPI STPv2 specification. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "stm.h" + +#include + +static unsigned int stm_core_up; + +/* + * The SRCU here makes sure that STM device doesn't disappear from under a + * stm_source_write() caller, which may want to have as little overhead as + * possible. + */ +static struct srcu_struct stm_source_srcu; + +static ssize_t masters_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct stm_device *stm = to_stm_device(dev); + int ret; + + ret = sprintf(buf, "%u %u\n", stm->data->sw_start, stm->data->sw_end); + + return ret; +} + +static DEVICE_ATTR_RO(masters); + +static ssize_t channels_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct stm_device *stm = to_stm_device(dev); + int ret; + + ret = sprintf(buf, "%u\n", stm->data->sw_nchannels); + + return ret; +} + +static DEVICE_ATTR_RO(channels); + +static struct attribute *stm_attrs[] = { + &dev_attr_masters.attr, + &dev_attr_channels.attr, + NULL, +}; + +ATTRIBUTE_GROUPS(stm); + +static struct class stm_class = { + .name = "stm", + .dev_groups = stm_groups, +}; + +static int stm_dev_match(struct device *dev, const void *data) +{ + const char *name = data; + + return sysfs_streq(name, dev_name(dev)); +} + +/** + * stm_find_device() - find stm device by name + * @buf: character buffer containing the name + * + * This is called when either policy gets assigned to an stm device or an + * stm_source device gets linked to an stm device. + * + * This grabs device's reference (get_device()) and module reference, both + * of which the calling path needs to make sure to drop with stm_put_device(). + * + * Return: stm device pointer or null if lookup failed. + */ +struct stm_device *stm_find_device(const char *buf) +{ + struct stm_device *stm; + struct device *dev; + + if (!stm_core_up) + return NULL; + + dev = class_find_device(&stm_class, NULL, buf, stm_dev_match); + if (!dev) + return NULL; + + stm = to_stm_device(dev); + if (!try_module_get(stm->owner)) { + put_device(dev); + return NULL; + } + + return stm; +} + +/** + * stm_put_device() - drop references on the stm device + * @stm: stm device, previously acquired by stm_find_device() + * + * This drops the module reference and device reference taken by + * stm_find_device(). + */ +void stm_put_device(struct stm_device *stm) +{ + module_put(stm->owner); + put_device(&stm->dev); +} + +/* + * Internally we only care about software-writable masters here, that is the + * ones in the range [stm_data->sw_start..stm_data..sw_end], however we need + * original master numbers to be visible externally, since they are the ones + * that will appear in the STP stream. Thus, the internal bookkeeping uses + * $master - stm_data->sw_start to reference master descriptors and such. + */ + +#define __stm_master(_s, _m) \ + ((_s)->masters[(_m) - (_s)->data->sw_start]) + +static inline struct stp_master * +stm_master(struct stm_device *stm, unsigned int idx) +{ + if (idx < stm->data->sw_start || idx > stm->data->sw_end) + return NULL; + + return __stm_master(stm, idx); +} + +static int stp_master_alloc(struct stm_device *stm, unsigned int idx) +{ + struct stp_master *master; + size_t size; + + size = ALIGN(stm->data->sw_nchannels, 8) / 8; + size += sizeof(struct stp_master); + master = kzalloc(size, GFP_ATOMIC); + if (!master) + return -ENOMEM; + + master->nr_free = stm->data->sw_nchannels; + __stm_master(stm, idx) = master; + + return 0; +} + +static void stp_master_free(struct stm_device *stm, unsigned int idx) +{ + struct stp_master *master = stm_master(stm, idx); + + if (!master) + return; + + __stm_master(stm, idx) = NULL; + kfree(master); +} + +static void stm_output_claim(struct stm_device *stm, struct stm_output *output) +{ + struct stp_master *master = stm_master(stm, output->master); + + if (WARN_ON_ONCE(master->nr_free < output->nr_chans)) + return; + + bitmap_allocate_region(&master->chan_map[0], output->channel, + ilog2(output->nr_chans)); + + master->nr_free -= output->nr_chans; +} + +static void +stm_output_disclaim(struct stm_device *stm, struct stm_output *output) +{ + struct stp_master *master = stm_master(stm, output->master); + + bitmap_release_region(&master->chan_map[0], output->channel, + ilog2(output->nr_chans)); + + output->nr_chans = 0; + master->nr_free += output->nr_chans; +} + +/* + * This is like bitmap_find_free_region(), except it can ignore @start bits + * at the beginning. + */ +static int find_free_channels(unsigned long *bitmap, unsigned int start, + unsigned int end, unsigned int width) +{ + unsigned int pos; + int i; + + for (pos = start; pos < end + 1; pos = ALIGN(pos, width)) { + pos = find_next_zero_bit(bitmap, end + 1, pos); + if (pos + width > end + 1) + break; + + if (pos & (width - 1)) + continue; + + for (i = 1; i < width && !test_bit(pos + i, bitmap); i++) + ; + if (i == width) + return pos; + } + + return -1; +} + +static unsigned int +stm_find_master_chan(struct stm_device *stm, unsigned int width, + unsigned int *mstart, unsigned int mend, + unsigned int *cstart, unsigned int cend) +{ + struct stp_master *master; + unsigned int midx; + int pos, err; + + for (midx = *mstart; midx <= mend; midx++) { + if (!stm_master(stm, midx)) { + err = stp_master_alloc(stm, midx); + if (err) + return err; + } + + master = stm_master(stm, midx); + + if (!master->nr_free) + continue; + + pos = find_free_channels(master->chan_map, *cstart, cend, + width); + if (pos < 0) + continue; + + *mstart = midx; + *cstart = pos; + return 0; + } + + return -ENOSPC; +} + +static int stm_output_assign(struct stm_device *stm, unsigned int width, + struct stp_policy_node *policy_node, + struct stm_output *output) +{ + unsigned int midx, cidx, mend, cend; + int ret = -EINVAL; + + if (width > stm->data->sw_nchannels) + return -EINVAL; + + if (policy_node) { + stp_policy_node_get_ranges(policy_node, + &midx, &mend, &cidx, &cend); + } else { + midx = stm->data->sw_start; + cidx = 0; + mend = stm->data->sw_end; + cend = stm->data->sw_nchannels - 1; + } + + spin_lock(&stm->mc_lock); + /* output is already assigned -- shouldn't happen */ + if (WARN_ON_ONCE(output->nr_chans)) + goto unlock; + + ret = stm_find_master_chan(stm, width, &midx, mend, &cidx, cend); + if (ret) + goto unlock; + + output->master = midx; + output->channel = cidx; + output->nr_chans = width; + stm_output_claim(stm, output); + dev_dbg(&stm->dev, "assigned %u:%u (+%u)\n", midx, cidx, width); + + ret = 0; +unlock: + spin_unlock(&stm->mc_lock); + + return ret; +} + +static void stm_output_free(struct stm_device *stm, struct stm_output *output) +{ + spin_lock(&stm->mc_lock); + if (output->nr_chans) + stm_output_disclaim(stm, output); + spin_unlock(&stm->mc_lock); +} + +static int major_match(struct device *dev, const void *data) +{ + unsigned int major = *(unsigned int *)data; + + return MAJOR(dev->devt) == major; +} + +static int stm_char_open(struct inode *inode, struct file *file) +{ + struct stm_file *stmf; + struct device *dev; + unsigned int major = imajor(inode); + int err = -ENODEV; + + dev = class_find_device(&stm_class, NULL, &major, major_match); + if (!dev) + return -ENODEV; + + stmf = kzalloc(sizeof(*stmf), GFP_KERNEL); + if (!stmf) + return -ENOMEM; + + stmf->stm = to_stm_device(dev); + + if (!try_module_get(stmf->stm->owner)) + goto err_free; + + file->private_data = stmf; + + return nonseekable_open(inode, file); + +err_free: + kfree(stmf); + + return err; +} + +static int stm_char_release(struct inode *inode, struct file *file) +{ + struct stm_file *stmf = file->private_data; + + stm_output_free(stmf->stm, &stmf->output); + stm_put_device(stmf->stm); + kfree(stmf); + + return 0; +} + +static int stm_file_assign(struct stm_file *stmf, char *id, unsigned int width) +{ + struct stm_device *stm = stmf->stm; + int ret; + + stmf->policy_node = stp_policy_node_lookup(stm, id); + + ret = stm_output_assign(stm, width, stmf->policy_node, &stmf->output); + + if (stmf->policy_node) + stp_policy_node_put(stmf->policy_node); + + return ret; +} + +static void stm_write(struct stm_data *data, unsigned int master, + unsigned int channel, const char *buf, size_t count) +{ + unsigned int flags = STP_PACKET_TIMESTAMPED; + const unsigned char *p = buf, nil = 0; + size_t pos; + ssize_t sz; + + for (pos = 0, p = buf; count > pos; pos += sz, p += sz) { + sz = min_t(unsigned int, count - pos, 8); + sz = data->packet(data, master, channel, STP_PACKET_DATA, flags, + sz, p); + flags = 0; + } + + data->packet(data, master, channel, STP_PACKET_FLAG, 0, 0, &nil); +} + +static ssize_t stm_char_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct stm_file *stmf = file->private_data; + struct stm_device *stm = stmf->stm; + char *kbuf; + int err; + + /* + * if no m/c have been assigned to this writer up to this + * point, use "default" policy entry + */ + if (!stmf->output.nr_chans) { + err = stm_file_assign(stmf, "default", 1); + /* + * EBUSY means that somebody else just assigned this + * output, which is just fine for write() + */ + if (err && err != -EBUSY) + return err; + } + + kbuf = kmalloc(count + 1, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + err = copy_from_user(kbuf, buf, count); + if (err) { + kfree(kbuf); + return -EFAULT; + } + + stm_write(stm->data, stmf->output.master, stmf->output.channel, kbuf, + count); + + kfree(kbuf); + + return count; +} + +static int stm_char_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct stm_file *stmf = file->private_data; + struct stm_device *stm = stmf->stm; + unsigned long size, phys; + + if (!stm->data->mmio_addr) + return -EOPNOTSUPP; + + if (vma->vm_pgoff) + return -EINVAL; + + size = vma->vm_end - vma->vm_start; + + if (stmf->output.nr_chans * stm->data->sw_mmiosz != size) + return -EINVAL; + + phys = stm->data->mmio_addr(stm->data, stmf->output.master, + stmf->output.channel, + stmf->output.nr_chans); + + if (!phys) + return -EINVAL; + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP; + vm_iomap_memory(vma, phys, size); + + return 0; +} + +static int stm_char_policy_set_ioctl(struct stm_file *stmf, void __user *arg) +{ + struct stm_device *stm = stmf->stm; + struct stp_policy_id *id; + int ret = -EINVAL; + u32 size; + + if (stmf->output.nr_chans) + return -EBUSY; + + if (copy_from_user(&size, arg, sizeof(size))) + return -EFAULT; + + if (size >= PATH_MAX + sizeof(*id)) + return -EINVAL; + + /* + * size + 1 to make sure the .id string at the bottom is terminated, + * which is also why memdup_user() is not useful here + */ + id = kzalloc(size + 1, GFP_KERNEL); + if (!id) + return -ENOMEM; + + if (copy_from_user(id, arg, size)) { + ret = -EFAULT; + goto err_free; + } + + if (id->__reserved_0 || id->__reserved_1) + goto err_free; + + if (id->width < 1 || + id->width > PAGE_SIZE / stm->data->sw_mmiosz) + goto err_free; + + ret = stm_file_assign(stmf, id->id, id->width); + if (ret) + goto err_free; + + ret = 0; + + if (stm->data->link) + ret = stm->data->link(stm->data, stmf->output.master, + stmf->output.channel); + + if (ret) { + stm_output_free(stmf->stm, &stmf->output); + stm_put_device(stmf->stm); + } + +err_free: + kfree(id); + + return ret; +} + +static int stm_char_policy_get_ioctl(struct stm_file *stmf, void __user *arg) +{ + struct stp_policy_id id = { + .size = sizeof(id), + .master = stmf->output.master, + .channel = stmf->output.channel, + .width = stmf->output.nr_chans, + .__reserved_0 = 0, + .__reserved_1 = 0, + }; + + return copy_to_user(arg, &id, id.size) ? -EFAULT : 0; +} + +static long +stm_char_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct stm_file *stmf = file->private_data; + struct stm_data *stm_data = stmf->stm->data; + int err = -ENOTTY; + u64 options; + + switch (cmd) { + case STP_POLICY_ID_SET: + err = stm_char_policy_set_ioctl(stmf, (void __user *)arg); + if (err) + return err; + + return stm_char_policy_get_ioctl(stmf, (void __user *)arg); + + case STP_POLICY_ID_GET: + return stm_char_policy_get_ioctl(stmf, (void __user *)arg); + + case STP_SET_OPTIONS: + if (copy_from_user(&options, (u64 __user *)arg, sizeof(u64))) + return -EFAULT; + + if (stm_data->set_options) + err = stm_data->set_options(stm_data, + stmf->output.master, + stmf->output.channel, + stmf->output.nr_chans, + options); + + break; + default: + break; + } + + return err; +} + +#ifdef CONFIG_COMPAT +static long +stm_char_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + return stm_char_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); +} +#else +#define stm_char_compat_ioctl NULL +#endif + +static const struct file_operations stm_fops = { + .open = stm_char_open, + .release = stm_char_release, + .write = stm_char_write, + .mmap = stm_char_mmap, + .unlocked_ioctl = stm_char_ioctl, + .compat_ioctl = stm_char_compat_ioctl, + .llseek = no_llseek, +}; + +static void stm_device_release(struct device *dev) +{ + struct stm_device *stm = to_stm_device(dev); + + kfree(stm); +} + +int stm_register_device(struct device *parent, struct stm_data *stm_data, + struct module *owner) +{ + struct stm_device *stm; + unsigned int nmasters; + int err = -ENOMEM; + + if (!stm_core_up) + return -EPROBE_DEFER; + + if (!stm_data->packet || !stm_data->sw_nchannels) + return -EINVAL; + + nmasters = stm_data->sw_end - stm_data->sw_start; + stm = kzalloc(sizeof(*stm) + nmasters * sizeof(void *), GFP_KERNEL); + if (!stm) + return -ENOMEM; + + stm->major = register_chrdev(0, stm_data->name, &stm_fops); + if (stm->major < 0) + goto err_free; + + device_initialize(&stm->dev); + stm->dev.devt = MKDEV(stm->major, 0); + stm->dev.class = &stm_class; + stm->dev.parent = parent; + stm->dev.release = stm_device_release; + + err = kobject_set_name(&stm->dev.kobj, "%s", stm_data->name); + if (err) + goto err_device; + + err = device_add(&stm->dev); + if (err) + goto err_device; + + spin_lock_init(&stm->link_lock); + INIT_LIST_HEAD(&stm->link_list); + + spin_lock_init(&stm->mc_lock); + mutex_init(&stm->policy_mutex); + stm->sw_nmasters = nmasters; + stm->owner = owner; + stm->data = stm_data; + stm_data->stm = stm; + + return 0; + +err_device: + put_device(&stm->dev); +err_free: + kfree(stm); + + return err; +} +EXPORT_SYMBOL_GPL(stm_register_device); + +static void __stm_source_link_drop(struct stm_source_device *src, + struct stm_device *stm); + +void stm_unregister_device(struct stm_data *stm_data) +{ + struct stm_device *stm = stm_data->stm; + struct stm_source_device *src, *iter; + int i; + + spin_lock(&stm->link_lock); + list_for_each_entry_safe(src, iter, &stm->link_list, link_entry) { + __stm_source_link_drop(src, stm); + } + spin_unlock(&stm->link_lock); + + synchronize_srcu(&stm_source_srcu); + + unregister_chrdev(stm->major, stm_data->name); + + mutex_lock(&stm->policy_mutex); + if (stm->policy) + stp_policy_unbind(stm->policy); + mutex_unlock(&stm->policy_mutex); + + for (i = 0; i < stm->sw_nmasters; i++) + stp_master_free(stm, i); + + device_unregister(&stm->dev); + stm_data->stm = NULL; +} +EXPORT_SYMBOL_GPL(stm_unregister_device); + +/** + * stm_source_link_add() - connect an stm_source device to an stm device + * @src: stm_source device + * @stm: stm device + * + * This function establishes a link from stm_source to an stm device so that + * the former can send out trace data to the latter. + * + * Return: 0 on success, -errno otherwise. + */ +static int stm_source_link_add(struct stm_source_device *src, + struct stm_device *stm) +{ + char *id; + int err; + + spin_lock(&stm->link_lock); + spin_lock(&src->link_lock); + + /* src->link is dereferenced under stm_source_srcu but not the list */ + rcu_assign_pointer(src->link, stm); + list_add_tail(&src->link_entry, &stm->link_list); + + spin_unlock(&src->link_lock); + spin_unlock(&stm->link_lock); + + id = kstrdup(src->data->name, GFP_KERNEL); + if (id) { + src->policy_node = + stp_policy_node_lookup(stm, id); + + kfree(id); + } + + err = stm_output_assign(stm, src->data->nr_chans, + src->policy_node, &src->output); + + if (src->policy_node) + stp_policy_node_put(src->policy_node); + + if (err) + goto fail_detach; + + /* this is to notify the STM device that a new link has been made */ + if (stm->data->link) + err = stm->data->link(stm->data, src->output.master, + src->output.channel); + + if (err) + goto fail_free_output; + + /* this is to let the source carry out all necessary preparations */ + if (src->data->link) + src->data->link(src->data); + + return 0; + +fail_free_output: + stm_output_free(stm, &src->output); + stm_put_device(stm); + +fail_detach: + spin_lock(&stm->link_lock); + spin_lock(&src->link_lock); + + rcu_assign_pointer(src->link, NULL); + list_del_init(&src->link_entry); + + spin_unlock(&src->link_lock); + spin_unlock(&stm->link_lock); + + return err; +} + +/** + * __stm_source_link_drop() - detach stm_source from an stm device + * @src: stm_source device + * @stm: stm device + * + * If @stm is @src::link, disconnect them from one another and put the + * reference on the @stm device. + * + * Caller must hold stm::link_lock. + */ +static void __stm_source_link_drop(struct stm_source_device *src, + struct stm_device *stm) +{ + spin_lock(&src->link_lock); + if (WARN_ON_ONCE(src->link != stm)) { + spin_unlock(&src->link_lock); + return; + } + + stm_output_free(src->link, &src->output); + /* caller must hold stm::link_lock */ + list_del_init(&src->link_entry); + /* matches stm_find_device() from stm_source_link_store() */ + stm_put_device(src->link); + rcu_assign_pointer(src->link, NULL); + + spin_unlock(&src->link_lock); +} + +/** + * stm_source_link_drop() - detach stm_source from its stm device + * @src: stm_source device + * + * Unlinking means disconnecting from source's STM device; after this + * writes will be unsuccessful until it is linked to a new STM device. + * + * This will happen on "stm_source_link" sysfs attribute write to undo + * the existing link (if any), or on linked STM device's de-registration. + */ +static void stm_source_link_drop(struct stm_source_device *src) +{ + struct stm_device *stm; + int idx; + + idx = srcu_read_lock(&stm_source_srcu); + stm = srcu_dereference(src->link, &stm_source_srcu); + + if (stm) { + if (src->data->unlink) + src->data->unlink(src->data); + + spin_lock(&stm->link_lock); + __stm_source_link_drop(src, stm); + spin_unlock(&stm->link_lock); + } + + srcu_read_unlock(&stm_source_srcu, idx); +} + +static ssize_t stm_source_link_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct stm_source_device *src = to_stm_source_device(dev); + struct stm_device *stm; + int idx, ret; + + idx = srcu_read_lock(&stm_source_srcu); + stm = srcu_dereference(src->link, &stm_source_srcu); + ret = sprintf(buf, "%s\n", + stm ? dev_name(&stm->dev) : ""); + srcu_read_unlock(&stm_source_srcu, idx); + + return ret; +} + +static ssize_t stm_source_link_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct stm_source_device *src = to_stm_source_device(dev); + struct stm_device *link; + int err; + + stm_source_link_drop(src); + + link = stm_find_device(buf); + if (!link) + return -EINVAL; + + err = stm_source_link_add(src, link); + if (err) + stm_put_device(link); + + return err ? : count; +} + +static DEVICE_ATTR_RW(stm_source_link); + +static struct attribute *stm_source_attrs[] = { + &dev_attr_stm_source_link.attr, + NULL, +}; + +ATTRIBUTE_GROUPS(stm_source); + +static struct class stm_source_class = { + .name = "stm_source", + .dev_groups = stm_source_groups, +}; + +static void stm_source_device_release(struct device *dev) +{ + struct stm_source_device *src = to_stm_source_device(dev); + + kfree(src); +} + +/** + * stm_source_register_device() - register an stm_source device + * @parent: parent device + * @data: device description structure + * + * This will create a device of stm_source class that can write + * data to an stm device once linked. + * + * Return: 0 on success, -errno otherwise. + */ +int stm_source_register_device(struct device *parent, + struct stm_source_data *data) +{ + struct stm_source_device *src; + int err; + + if (!stm_core_up) + return -EPROBE_DEFER; + + src = kzalloc(sizeof(*src), GFP_KERNEL); + if (!src) + return -ENOMEM; + + device_initialize(&src->dev); + src->dev.class = &stm_source_class; + src->dev.parent = parent; + src->dev.release = stm_source_device_release; + + err = kobject_set_name(&src->dev.kobj, "%s", data->name); + if (err) + goto err; + + err = device_add(&src->dev); + if (err) + goto err; + + spin_lock_init(&src->link_lock); + INIT_LIST_HEAD(&src->link_entry); + src->data = data; + data->src = src; + + return 0; + +err: + put_device(&src->dev); + kfree(src); + + return err; +} +EXPORT_SYMBOL_GPL(stm_source_register_device); + +/** + * stm_source_unregister_device() - unregister an stm_source device + * @data: device description that was used to register the device + * + * This will remove a previously created stm_source device from the system. + */ +void stm_source_unregister_device(struct stm_source_data *data) +{ + struct stm_source_device *src = data->src; + + stm_source_link_drop(src); + + device_destroy(&stm_source_class, src->dev.devt); +} +EXPORT_SYMBOL_GPL(stm_source_unregister_device); + +int stm_source_write(struct stm_source_data *data, unsigned int chan, + const char *buf, size_t count) +{ + struct stm_source_device *src = data->src; + struct stm_device *stm; + int idx; + + if (!src->output.nr_chans) + return -ENODEV; + + if (chan >= src->output.nr_chans) + return -EINVAL; + + idx = srcu_read_lock(&stm_source_srcu); + + stm = srcu_dereference(src->link, &stm_source_srcu); + if (stm) + stm_write(stm->data, src->output.master, + src->output.channel + chan, + buf, count); + else + count = -ENODEV; + + srcu_read_unlock(&stm_source_srcu, idx); + + return count; +} +EXPORT_SYMBOL_GPL(stm_source_write); + +static int __init stm_core_init(void) +{ + int err; + + err = class_register(&stm_class); + if (err) + return err; + + err = class_register(&stm_source_class); + if (err) + goto err_stm; + + err = stp_configfs_init(); + if (err) + goto err_src; + + init_srcu_struct(&stm_source_srcu); + + stm_core_up++; + + return 0; + +err_src: + class_unregister(&stm_source_class); +err_stm: + class_unregister(&stm_class); + + return err; +} + +module_init(stm_core_init); + +static void __exit stm_core_exit(void) +{ + cleanup_srcu_struct(&stm_source_srcu); + class_unregister(&stm_source_class); + class_unregister(&stm_class); + stp_configfs_exit(); +} + +module_exit(stm_core_exit); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("System Trace Module device class"); +MODULE_AUTHOR("Alexander Shishkin "); diff --git a/drivers/hwtracing/stm/policy.c b/drivers/hwtracing/stm/policy.c new file mode 100644 index 000000000000..6498a9dbb7bd --- /dev/null +++ b/drivers/hwtracing/stm/policy.c @@ -0,0 +1,529 @@ +/* + * System Trace Module (STM) master/channel allocation policy management + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * A master/channel allocation policy allows mapping string identifiers to + * master and channel ranges, where allocation can be done. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include +#include +#include +#include +#include +#include +#include "stm.h" + +/* + * STP Master/Channel allocation policy configfs layout. + */ + +struct stp_policy { + struct config_group group; + struct stm_device *stm; +}; + +struct stp_policy_node { + struct config_group group; + struct stp_policy *policy; + unsigned int first_master; + unsigned int last_master; + unsigned int first_channel; + unsigned int last_channel; +}; + +static struct configfs_subsystem stp_policy_subsys; + +void stp_policy_node_get_ranges(struct stp_policy_node *policy_node, + unsigned int *mstart, unsigned int *mend, + unsigned int *cstart, unsigned int *cend) +{ + *mstart = policy_node->first_master; + *mend = policy_node->last_master; + *cstart = policy_node->first_channel; + *cend = policy_node->last_channel; +} + +static inline char *stp_policy_node_name(struct stp_policy_node *policy_node) +{ + return policy_node->group.cg_item.ci_name ? : ""; +} + +static inline struct stp_policy *to_stp_policy(struct config_item *item) +{ + return item ? + container_of(to_config_group(item), struct stp_policy, group) : + NULL; +} + +static inline struct stp_policy_node * +to_stp_policy_node(struct config_item *item) +{ + return item ? + container_of(to_config_group(item), struct stp_policy_node, + group) : + NULL; +} + +static ssize_t stp_policy_node_masters_show(struct stp_policy_node *policy_node, + char *page) +{ + ssize_t count; + + count = sprintf(page, "%u %u\n", policy_node->first_master, + policy_node->last_master); + + return count; +} + +static ssize_t +stp_policy_node_masters_store(struct stp_policy_node *policy_node, + const char *page, size_t count) +{ + unsigned int first, last; + struct stm_device *stm; + char *p = (char *)page; + ssize_t ret = -ENODEV; + + if (sscanf(p, "%u %u", &first, &last) != 2) + return -EINVAL; + + mutex_lock(&stp_policy_subsys.su_mutex); + stm = policy_node->policy->stm; + if (!stm) + goto unlock; + + /* must be within [sw_start..sw_end], which is an inclusive range */ + if (first > INT_MAX || last > INT_MAX || first > last || + first < stm->data->sw_start || + last > stm->data->sw_end) { + ret = -ERANGE; + goto unlock; + } + + ret = count; + policy_node->first_master = first; + policy_node->last_master = last; + +unlock: + mutex_unlock(&stp_policy_subsys.su_mutex); + + return ret; +} + +static ssize_t +stp_policy_node_channels_show(struct stp_policy_node *policy_node, char *page) +{ + ssize_t count; + + count = sprintf(page, "%u %u\n", policy_node->first_channel, + policy_node->last_channel); + + return count; +} + +static ssize_t +stp_policy_node_channels_store(struct stp_policy_node *policy_node, + const char *page, size_t count) +{ + unsigned int first, last; + struct stm_device *stm; + char *p = (char *)page; + ssize_t ret = -ENODEV; + + if (sscanf(p, "%u %u", &first, &last) != 2) + return -EINVAL; + + mutex_lock(&stp_policy_subsys.su_mutex); + stm = policy_node->policy->stm; + if (!stm) + goto unlock; + + if (first > INT_MAX || last > INT_MAX || first > last || + last >= stm->data->sw_nchannels) { + ret = -ERANGE; + goto unlock; + } + + ret = count; + policy_node->first_channel = first; + policy_node->last_channel = last; + +unlock: + mutex_unlock(&stp_policy_subsys.su_mutex); + + return ret; +} + +static void stp_policy_node_release(struct config_item *item) +{ + kfree(to_stp_policy_node(item)); +} + +struct stp_policy_node_attribute { + struct configfs_attribute attr; + ssize_t (*show)(struct stp_policy_node *, char *); + ssize_t (*store)(struct stp_policy_node *, const char *, size_t); +}; + +static ssize_t stp_policy_node_attr_show(struct config_item *item, + struct configfs_attribute *attr, + char *page) +{ + struct stp_policy_node *policy_node = to_stp_policy_node(item); + struct stp_policy_node_attribute *pn_attr = + container_of(attr, struct stp_policy_node_attribute, attr); + ssize_t count = 0; + + if (pn_attr->show) + count = pn_attr->show(policy_node, page); + + return count; +} + +static ssize_t stp_policy_node_attr_store(struct config_item *item, + struct configfs_attribute *attr, + const char *page, size_t len) +{ + struct stp_policy_node *policy_node = to_stp_policy_node(item); + struct stp_policy_node_attribute *pn_attr = + container_of(attr, struct stp_policy_node_attribute, attr); + ssize_t count = -EINVAL; + + if (pn_attr->store) + count = pn_attr->store(policy_node, page, len); + + return count; +} + +static struct configfs_item_operations stp_policy_node_item_ops = { + .release = stp_policy_node_release, + .show_attribute = stp_policy_node_attr_show, + .store_attribute = stp_policy_node_attr_store, +}; + +static struct stp_policy_node_attribute stp_policy_node_attr_range = { + .attr = { + .ca_owner = THIS_MODULE, + .ca_name = "masters", + .ca_mode = S_IRUGO | S_IWUSR, + }, + .show = stp_policy_node_masters_show, + .store = stp_policy_node_masters_store, +}; + +static struct stp_policy_node_attribute stp_policy_node_attr_channels = { + .attr = { + .ca_owner = THIS_MODULE, + .ca_name = "channels", + .ca_mode = S_IRUGO | S_IWUSR, + }, + .show = stp_policy_node_channels_show, + .store = stp_policy_node_channels_store, +}; + +static struct configfs_attribute *stp_policy_node_attrs[] = { + &stp_policy_node_attr_range.attr, + &stp_policy_node_attr_channels.attr, + NULL, +}; + +static struct config_item_type stp_policy_type; +static struct config_item_type stp_policy_node_type; + +static struct config_group * +stp_policy_node_make(struct config_group *group, const char *name) +{ + struct stp_policy_node *policy_node, *parent_node; + struct stp_policy *policy; + + if (group->cg_item.ci_type == &stp_policy_type) { + policy = container_of(group, struct stp_policy, group); + } else { + parent_node = container_of(group, struct stp_policy_node, + group); + policy = parent_node->policy; + } + + if (!policy->stm) + return ERR_PTR(-ENODEV); + + policy_node = kzalloc(sizeof(struct stp_policy_node), GFP_KERNEL); + if (!policy_node) + return ERR_PTR(-ENOMEM); + + config_group_init_type_name(&policy_node->group, name, + &stp_policy_node_type); + + policy_node->policy = policy; + + /* default values for the attributes */ + policy_node->first_master = policy->stm->data->sw_start; + policy_node->last_master = policy->stm->data->sw_end; + policy_node->first_channel = 0; + policy_node->last_channel = policy->stm->data->sw_nchannels - 1; + + return &policy_node->group; +} + +static void +stp_policy_node_drop(struct config_group *group, struct config_item *item) +{ + config_item_put(item); +} + +static struct configfs_group_operations stp_policy_node_group_ops = { + .make_group = stp_policy_node_make, + .drop_item = stp_policy_node_drop, +}; + +static struct config_item_type stp_policy_node_type = { + .ct_item_ops = &stp_policy_node_item_ops, + .ct_group_ops = &stp_policy_node_group_ops, + .ct_attrs = stp_policy_node_attrs, + .ct_owner = THIS_MODULE, +}; + +/* + * Root group: policies. + */ +static struct configfs_attribute stp_policy_attr_device = { + .ca_owner = THIS_MODULE, + .ca_name = "device", + .ca_mode = S_IRUGO, +}; + +static struct configfs_attribute *stp_policy_attrs[] = { + &stp_policy_attr_device, + NULL, +}; + +static ssize_t stp_policy_attr_show(struct config_item *item, + struct configfs_attribute *attr, + char *page) +{ + struct stp_policy *policy = to_stp_policy(item); + ssize_t count; + + count = sprintf(page, "%s\n", + (policy && policy->stm) ? + policy->stm->data->name : + ""); + + return count; +} + +void stp_policy_unbind(struct stp_policy *policy) +{ + struct stm_device *stm = policy->stm; + + if (WARN_ON_ONCE(!policy->stm)) + return; + + mutex_lock(&stm->policy_mutex); + stm->policy = NULL; + mutex_unlock(&stm->policy_mutex); + + policy->stm = NULL; + + stm_put_device(stm); +} + +static void stp_policy_release(struct config_item *item) +{ + struct stp_policy *policy = to_stp_policy(item); + + stp_policy_unbind(policy); + kfree(policy); +} + +static struct configfs_item_operations stp_policy_item_ops = { + .release = stp_policy_release, + .show_attribute = stp_policy_attr_show, +}; + +static struct configfs_group_operations stp_policy_group_ops = { + .make_group = stp_policy_node_make, +}; + +static struct config_item_type stp_policy_type = { + .ct_item_ops = &stp_policy_item_ops, + .ct_group_ops = &stp_policy_group_ops, + .ct_attrs = stp_policy_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct config_group * +stp_policies_make(struct config_group *group, const char *name) +{ + struct config_group *ret; + struct stm_device *stm; + char *devname, *p; + + devname = kasprintf(GFP_KERNEL, "%s", name); + if (!devname) + return ERR_PTR(-ENOMEM); + + /* + * node must look like ., where + * is the name of an existing stm device and + * is an arbitrary string + */ + p = strchr(devname, '.'); + if (!p) { + kfree(devname); + return ERR_PTR(-EINVAL); + } + + *p++ = '\0'; + + stm = stm_find_device(devname); + kfree(devname); + + if (!stm) + return ERR_PTR(-ENODEV); + + mutex_lock(&stm->policy_mutex); + if (stm->policy) { + ret = ERR_PTR(-EBUSY); + goto unlock_policy; + } + + stm->policy = kzalloc(sizeof(*stm->policy), GFP_KERNEL); + if (!stm->policy) { + ret = ERR_PTR(-ENOMEM); + goto unlock_policy; + } + + config_group_init_type_name(&stm->policy->group, name, + &stp_policy_type); + stm->policy->stm = stm; + + ret = &stm->policy->group; + +unlock_policy: + mutex_unlock(&stm->policy_mutex); + + if (IS_ERR(ret)) + stm_put_device(stm); + + return ret; +} + +static struct configfs_group_operations stp_policies_group_ops = { + .make_group = stp_policies_make, +}; + +static struct config_item_type stp_policies_type = { + .ct_group_ops = &stp_policies_group_ops, + .ct_owner = THIS_MODULE, +}; + +static struct configfs_subsystem stp_policy_subsys = { + .su_group = { + .cg_item = { + .ci_namebuf = "stp-policy", + .ci_type = &stp_policies_type, + }, + }, +}; + +/* + * Lock the policy mutex from the outside + */ +static struct stp_policy_node * +__stp_policy_node_lookup(struct stp_policy *policy, char *s) +{ + struct stp_policy_node *policy_node, *ret; + struct list_head *head = &policy->group.cg_children; + struct config_item *item; + char *start, *end = s; + + if (list_empty(head)) + return NULL; + + /* return the first entry if everything else fails */ + item = list_entry(head->next, struct config_item, ci_entry); + ret = to_stp_policy_node(item); + +next: + for (;;) { + start = strsep(&end, "/"); + if (!start) + break; + + if (!*start) + continue; + + list_for_each_entry(item, head, ci_entry) { + policy_node = to_stp_policy_node(item); + + if (!strcmp(start, + policy_node->group.cg_item.ci_name)) { + ret = policy_node; + + if (!end) + goto out; + + head = &policy_node->group.cg_children; + goto next; + } + } + break; + } + +out: + return ret; +} + + +struct stp_policy_node * +stp_policy_node_lookup(struct stm_device *stm, char *s) +{ + struct stp_policy_node *policy_node = NULL; + + mutex_lock(&stp_policy_subsys.su_mutex); + + mutex_lock(&stm->policy_mutex); + if (stm->policy) + policy_node = __stp_policy_node_lookup(stm->policy, s); + mutex_unlock(&stm->policy_mutex); + + if (policy_node) + config_item_get(&policy_node->group.cg_item); + mutex_unlock(&stp_policy_subsys.su_mutex); + + return policy_node; +} + +void stp_policy_node_put(struct stp_policy_node *policy_node) +{ + config_item_put(&policy_node->group.cg_item); +} + +int __init stp_configfs_init(void) +{ + int err; + + config_group_init(&stp_policy_subsys.su_group); + mutex_init(&stp_policy_subsys.su_mutex); + err = configfs_register_subsystem(&stp_policy_subsys); + + return err; +} + +void __exit stp_configfs_exit(void) +{ + configfs_unregister_subsystem(&stp_policy_subsys); +} diff --git a/drivers/hwtracing/stm/stm.h b/drivers/hwtracing/stm/stm.h new file mode 100644 index 000000000000..cf33bf976abe --- /dev/null +++ b/drivers/hwtracing/stm/stm.h @@ -0,0 +1,87 @@ +/* + * System Trace Module (STM) infrastructure + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * STM class implements generic infrastructure for System Trace Module devices + * as defined in MIPI STPv2 specification. + */ + +#ifndef _STM_STM_H_ +#define _STM_STM_H_ + +struct stp_policy; +struct stp_policy_node; + +struct stp_policy_node * +stp_policy_node_lookup(struct stm_device *stm, char *s); +void stp_policy_node_put(struct stp_policy_node *policy_node); +void stp_policy_unbind(struct stp_policy *policy); + +void stp_policy_node_get_ranges(struct stp_policy_node *policy_node, + unsigned int *mstart, unsigned int *mend, + unsigned int *cstart, unsigned int *cend); +int stp_configfs_init(void); +void stp_configfs_exit(void); + +struct stp_master { + unsigned int nr_free; + unsigned long chan_map[0]; +}; + +struct stm_device { + struct device dev; + struct module *owner; + struct stp_policy *policy; + struct mutex policy_mutex; + int major; + unsigned int sw_nmasters; + struct stm_data *data; + spinlock_t link_lock; + struct list_head link_list; + /* master allocation */ + spinlock_t mc_lock; + struct stp_master *masters[0]; +}; + +#define to_stm_device(_d) \ + container_of((_d), struct stm_device, dev) + +struct stm_output { + unsigned int master; + unsigned int channel; + unsigned int nr_chans; +}; + +struct stm_file { + struct stm_device *stm; + struct stp_policy_node *policy_node; + struct stm_output output; +}; + +struct stm_device *stm_find_device(const char *name); +void stm_put_device(struct stm_device *stm); + +struct stm_source_device { + struct device dev; + struct stm_source_data *data; + spinlock_t link_lock; + struct stm_device *link; + struct list_head link_entry; + /* one output per stm_source device */ + struct stp_policy_node *policy_node; + struct stm_output output; +}; + +#define to_stm_source_device(_d) \ + container_of((_d), struct stm_source_device, dev) + +#endif /* _STM_STM_H_ */ diff --git a/include/linux/stm.h b/include/linux/stm.h new file mode 100644 index 000000000000..9d0083d364e6 --- /dev/null +++ b/include/linux/stm.h @@ -0,0 +1,126 @@ +/* + * System Trace Module (STM) infrastructure apis + * Copyright (C) 2014 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _STM_H_ +#define _STM_H_ + +#include + +/** + * enum stp_packet_type - STP packets that an STM driver sends + */ +enum stp_packet_type { + STP_PACKET_DATA = 0, + STP_PACKET_FLAG, + STP_PACKET_USER, + STP_PACKET_MERR, + STP_PACKET_GERR, + STP_PACKET_TRIG, + STP_PACKET_XSYNC, +}; + +/** + * enum stp_packet_flags - STP packet modifiers + */ +enum stp_packet_flags { + STP_PACKET_MARKED = 0x1, + STP_PACKET_TIMESTAMPED = 0x2, +}; + +struct stp_policy; + +struct stm_device; + +/** + * struct stm_data - STM device description and callbacks + * @name: device name + * @stm: internal structure, only used by stm class code + * @sw_start: first STP master available to software + * @sw_end: last STP master available to software + * @sw_nchannels: number of STP channels per master + * @sw_mmiosz: size of one channel's IO space, for mmap, optional + * @packet: callback that sends an STP packet + * @mmio_addr: mmap callback, optional + * @link: called when a new stm_source gets linked to us, optional + * @unlink: likewise for unlinking, again optional + * @set_options: set device-specific options on a channel + * + * Fill out this structure before calling stm_register_device() to create + * an STM device and stm_unregister_device() to destroy it. It will also be + * passed back to @packet(), @mmio_addr(), @link(), @unlink() and @set_options() + * callbacks. + * + * Normally, an STM device will have a range of masters available to software + * and the rest being statically assigned to various hardware trace sources. + * The former is defined by the the range [@sw_start..@sw_end] of the device + * description. That is, the lowest master that can be allocated to software + * writers is @sw_start and data from this writer will appear is @sw_start + * master in the STP stream. + */ +struct stm_data { + const char *name; + struct stm_device *stm; + unsigned int sw_start; + unsigned int sw_end; + unsigned int sw_nchannels; + unsigned int sw_mmiosz; + ssize_t (*packet)(struct stm_data *, unsigned int, + unsigned int, unsigned int, + unsigned int, unsigned int, + const unsigned char *); + phys_addr_t (*mmio_addr)(struct stm_data *, unsigned int, + unsigned int, unsigned int); + int (*link)(struct stm_data *, unsigned int, + unsigned int); + void (*unlink)(struct stm_data *, unsigned int, + unsigned int); + long (*set_options)(struct stm_data *, unsigned int, + unsigned int, unsigned int, + unsigned long); +}; + +int stm_register_device(struct device *parent, struct stm_data *stm_data, + struct module *owner); +void stm_unregister_device(struct stm_data *stm_data); + +struct stm_source_device; + +/** + * struct stm_source_data - STM source device description and callbacks + * @name: device name, will be used for policy lookup + * @src: internal structure, only used by stm class code + * @nr_chans: number of channels to allocate + * @link: called when this source gets linked to an STM device + * @unlink: called when this source is about to get unlinked from its STM + * + * Fill in this structure before calling stm_source_register_device() to + * register a source device. Also pass it to unregister and write calls. + */ +struct stm_source_data { + const char *name; + struct stm_source_device *src; + unsigned int percpu; + unsigned int nr_chans; + int (*link)(struct stm_source_data *data); + void (*unlink)(struct stm_source_data *data); +}; + +int stm_source_register_device(struct device *parent, + struct stm_source_data *data); +void stm_source_unregister_device(struct stm_source_data *data); + +int stm_source_write(struct stm_source_data *data, unsigned int chan, + const char *buf, size_t count); + +#endif /* _STM_H_ */ diff --git a/include/uapi/linux/stm.h b/include/uapi/linux/stm.h new file mode 100644 index 000000000000..626a8d3f63b5 --- /dev/null +++ b/include/uapi/linux/stm.h @@ -0,0 +1,50 @@ +/* + * System Trace Module (STM) userspace interfaces + * Copyright (c) 2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * STM class implements generic infrastructure for System Trace Module devices + * as defined in MIPI STPv2 specification. + */ + +#ifndef _UAPI_LINUX_STM_H +#define _UAPI_LINUX_STM_H + +#include + +/** + * struct stp_policy_id - identification for the STP policy + * @size: size of the structure including real id[] length + * @master: assigned master + * @channel: first assigned channel + * @width: number of requested channels + * @id: identification string + * + * User must calculate the total size of the structure and put it into + * @size field, fill out the @id and desired @width. In return, kernel + * fills out @master, @channel and @width. + */ +struct stp_policy_id { + __u32 size; + __u16 master; + __u16 channel; + __u16 width; + /* padding */ + __u16 __reserved_0; + __u32 __reserved_1; + char id[0]; +}; + +#define STP_POLICY_ID_SET _IOWR('%', 0, struct stp_policy_id) +#define STP_POLICY_ID_GET _IOR('%', 1, struct stp_policy_id) +#define STP_SET_OPTIONS _IOW('%', 2, __u64) + +#endif /* _UAPI_LINUX_STM_H */ -- cgit v1.2.3 From 7910228b6bb35f3c8e0bc72a8d84c29616cb1b90 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:28 +0200 Subject: bridge: netlink: add group_fwd_mask support Add IFLA_BR_GROUP_FWD_MASK attribute to allow setting and retrieving the group_fwd_mask via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 14 +++++++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 3a5f263cfc2f..f7f480613555 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -232,6 +232,7 @@ enum { IFLA_BR_PRIORITY, IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, + IFLA_BR_GROUP_FWD_MASK, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c3186198d46d..39b201a2bc12 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -764,6 +764,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, + [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -829,6 +830,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], } #endif + if (data[IFLA_BR_GROUP_FWD_MASK]) { + u16 fwd_mask = nla_get_u16(data[IFLA_BR_GROUP_FWD_MASK]); + + if (fwd_mask & BR_GROUPFWD_RESTRICTED) + return -EINVAL; + br->group_fwd_mask = fwd_mask; + } + return 0; } @@ -844,6 +853,7 @@ static size_t br_get_size(const struct net_device *brdev) #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ #endif + nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ 0; } @@ -856,6 +866,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u32 ageing_time = jiffies_to_clock_t(br->ageing_time); u32 stp_enabled = br->stp_enabled; u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; + u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || @@ -864,7 +875,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_AGEING_TIME, ageing_time) || nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || - nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled)) + nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || + nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 5127c81f84de0dd643d5840a2c7de571bc6aceb3 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:29 +0200 Subject: bridge: netlink: export root id Add IFLA_BR_ROOT_ID and export br->designated_root via netlink. For this purpose add struct ifla_bridge_id that would represent struct bridge_id. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++++ net/bridge/br_netlink.c | 9 ++++++++- 2 files changed, 14 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index f7f480613555..03814371df44 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -233,11 +233,17 @@ enum { IFLA_BR_VLAN_FILTERING, IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, + IFLA_BR_ROOT_ID, __IFLA_BR_MAX, }; #define IFLA_BR_MAX (__IFLA_BR_MAX - 1) +struct ifla_bridge_id { + __u8 prio[2]; + __u8 addr[6]; /* ETH_ALEN */ +}; + enum { BRIDGE_MODE_UNSPEC, BRIDGE_MODE_HAIRPIN, diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 39b201a2bc12..7a3692469db6 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -854,6 +854,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ + nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ 0; } @@ -868,6 +869,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); + struct ifla_bridge_id root_id; + + memset(&root_id, 0, sizeof(root_id)); + memcpy(root_id.prio, br->designated_root.prio, sizeof(root_id.prio)); + memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -876,7 +882,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_STP_STATE, stp_enabled) || nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || - nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask)) + nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || + nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 7599a2201fc71cdca16a92d350f14cce8730e03f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:30 +0200 Subject: bridge: netlink: export bridge id Add IFLA_BR_BRIDGE_ID and export br->bridge_id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 03814371df44..748495438a8b 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -234,6 +234,7 @@ enum { IFLA_BR_VLAN_PROTOCOL, IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, + IFLA_BR_BRIDGE_ID, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 7a3692469db6..a63f944a7f12 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -855,6 +855,7 @@ static size_t br_get_size(const struct net_device *brdev) #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ 0; } @@ -869,11 +870,14 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) u16 priority = (br->bridge_id.prio[0] << 8) | br->bridge_id.prio[1]; u16 group_fwd_mask = br->group_fwd_mask; u8 vlan_enabled = br_vlan_enabled(br); - struct ifla_bridge_id root_id; + struct ifla_bridge_id root_id, bridge_id; + memset(&bridge_id, 0, sizeof(bridge_id)); memset(&root_id, 0, sizeof(root_id)); memcpy(root_id.prio, br->designated_root.prio, sizeof(root_id.prio)); memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); + memcpy(bridge_id.prio, br->bridge_id.prio, sizeof(bridge_id.prio)); + memcpy(bridge_id.addr, br->bridge_id.addr, sizeof(bridge_id.addr)); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -883,7 +887,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u16(skb, IFLA_BR_PRIORITY, priority) || nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || - nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id)) + nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || + nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 8762ba680fe8d41b444fc92f90ce7194b2b8303b Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:31 +0200 Subject: bridge: netlink: export root port Add IFLA_BR_ROOT_PORT and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 748495438a8b..172268a5767d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -235,6 +235,7 @@ enum { IFLA_BR_GROUP_FWD_MASK, IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, + IFLA_BR_ROOT_PORT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a63f944a7f12..652db1ca0acc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -856,6 +856,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ 0; } @@ -888,7 +889,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_VLAN_FILTERING, vlan_enabled) || nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || - nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id)) + nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || + nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 684dd248bee8c73eadb90706123bf1494d3218b8 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:32 +0200 Subject: bridge: netlink: export root path cost Add IFLA_BR_ROOT_PATH_COST and export it via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 4 +++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 172268a5767d..7d7236d143fb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -236,6 +236,7 @@ enum { IFLA_BR_ROOT_ID, IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, + IFLA_BR_ROOT_PATH_COST, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 652db1ca0acc..cd0488b689d4 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -857,6 +857,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ 0; } @@ -890,7 +891,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u16(skb, IFLA_BR_GROUP_FWD_MASK, group_fwd_mask) || nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || - nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port)) + nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || + nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From ed4163098e3090bb7b51421bde977e355275a554 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:33 +0200 Subject: bridge: netlink: export topology_change and topology_change_detected Add IFLA_BR_TOPOLOGY_CHANGE and IFLA_BR_TOPOLOGY_CHANGE_DETECTED and export them via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7d7236d143fb..b00286ca1bfe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -237,6 +237,8 @@ enum { IFLA_BR_BRIDGE_ID, IFLA_BR_ROOT_PORT, IFLA_BR_ROOT_PATH_COST, + IFLA_BR_TOPOLOGY_CHANGE, + IFLA_BR_TOPOLOGY_CHANGE_DETECTED, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cd0488b689d4..8bcaa5171f35 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -858,6 +858,8 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ 0; } @@ -892,7 +894,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put(skb, IFLA_BR_ROOT_ID, sizeof(root_id), &root_id) || nla_put(skb, IFLA_BR_BRIDGE_ID, sizeof(bridge_id), &bridge_id) || nla_put_u16(skb, IFLA_BR_ROOT_PORT, br->root_port) || - nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost)) + nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || + nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || + nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + br->topology_change_detected)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From d76bd14e0f759040efc8ce142dd6d1f9eca33d39 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:34 +0200 Subject: bridge: netlink: export all timers Export the following bridge timers (also exported via sysfs): IFLA_BR_HELLO_TIMER, IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 4 ++++ net/bridge/br_netlink.c | 16 +++++++++++++++- 2 files changed, 19 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b00286ca1bfe..a1e33282ab9d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -239,6 +239,10 @@ enum { IFLA_BR_ROOT_PATH_COST, IFLA_BR_TOPOLOGY_CHANGE, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, + IFLA_BR_HELLO_TIMER, + IFLA_BR_TCN_TIMER, + IFLA_BR_TOPOLOGY_CHANGE_TIMER, + IFLA_BR_GC_TIMER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 8bcaa5171f35..755bfe0ab404 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -860,12 +860,17 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ 0; } static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); + u64 hello_timer, tcn_timer, topology_change_timer, gc_timer; u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); @@ -882,6 +887,10 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) memcpy(root_id.addr, br->designated_root.addr, sizeof(root_id.addr)); memcpy(bridge_id.prio, br->bridge_id.prio, sizeof(bridge_id.prio)); memcpy(bridge_id.addr, br->bridge_id.addr, sizeof(bridge_id.addr)); + hello_timer = br_timer_value(&br->hello_timer); + tcn_timer = br_timer_value(&br->tcn_timer); + topology_change_timer = br_timer_value(&br->topology_change_timer); + gc_timer = br_timer_value(&br->gc_timer); if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -897,7 +906,12 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_ROOT_PATH_COST, br->root_path_cost) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE, br->topology_change) || nla_put_u8(skb, IFLA_BR_TOPOLOGY_CHANGE_DETECTED, - br->topology_change_detected)) + br->topology_change_detected) || + nla_put_u64(skb, IFLA_BR_HELLO_TIMER, hello_timer) || + nla_put_u64(skb, IFLA_BR_TCN_TIMER, tcn_timer) || + nla_put_u64(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, + topology_change_timer) || + nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 111189abc5c3f0ea6f516a6c3e8d8c3a2cf391d9 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:35 +0200 Subject: bridge: netlink: add group_addr support Add IFLA_BR_GROUP_ADDR attribute to allow setting and retrieving the group_addr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 25 ++++++++++++++++++++++++- 2 files changed, 25 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a1e33282ab9d..eaeaac17dfdd 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -243,6 +243,7 @@ enum { IFLA_BR_TCN_TIMER, IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, + IFLA_BR_GROUP_ADDR, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 755bfe0ab404..a05a4306d42d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -765,6 +765,8 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, + [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, + .len = ETH_ALEN }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -838,6 +840,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->group_fwd_mask = fwd_mask; } + if (data[IFLA_BR_GROUP_ADDR]) { + u8 new_addr[ETH_ALEN]; + + if (nla_len(data[IFLA_BR_GROUP_ADDR]) != ETH_ALEN) + return -EINVAL; + memcpy(new_addr, nla_data(data[IFLA_BR_GROUP_ADDR]), ETH_ALEN); + if (!is_link_local_ether_addr(new_addr)) + return -EINVAL; + if (new_addr[5] == 1 || /* 802.3x Pause address */ + new_addr[5] == 2 || /* 802.3ad Slow protocols */ + new_addr[5] == 3) /* 802.1X PAE address */ + return -EINVAL; + spin_lock_bh(&br->lock); + memcpy(br->group_addr, new_addr, sizeof(br->group_addr)); + spin_unlock_bh(&br->lock); + br->group_addr_set = true; + br_recalculate_fwd_mask(br); + } + return 0; } @@ -864,6 +885,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ + nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ 0; } @@ -911,7 +933,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u64(skb, IFLA_BR_TCN_TIMER, tcn_timer) || nla_put_u64(skb, IFLA_BR_TOPOLOGY_CHANGE_TIMER, topology_change_timer) || - nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer)) + nla_put_u64(skb, IFLA_BR_GC_TIMER, gc_timer) || + nla_put(skb, IFLA_BR_GROUP_ADDR, ETH_ALEN, br->group_addr)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING -- cgit v1.2.3 From 150217c688217e549ef8a36ea4f6718977373765 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:36 +0200 Subject: bridge: netlink: add fdb flush Simple attribute that flushes the bridge's fdb. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eaeaac17dfdd..9ca9bf8bfe04 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -244,6 +244,7 @@ enum { IFLA_BR_TOPOLOGY_CHANGE_TIMER, IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, + IFLA_BR_FDB_FLUSH, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index a05a4306d42d..5853c5737006 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -859,6 +859,9 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br_recalculate_fwd_mask(br); } + if (data[IFLA_BR_FDB_FLUSH]) + br_fdb_flush(br); + return 0; } -- cgit v1.2.3 From a9a6bc70f5f70b3835b081e401b469b88c7c8a3a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:37 +0200 Subject: bridge: netlink: add support for multicast_router Add IFLA_BR_MCAST_ROUTER to allow setting and retrieving br->multicast_router when igmp snooping is enabled. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9ca9bf8bfe04..5d2c92973afe 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -245,6 +245,7 @@ enum { IFLA_BR_GC_TIMER, IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, + IFLA_BR_MCAST_ROUTER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 5853c5737006..f4df609c1ad9 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -767,6 +767,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -862,6 +863,16 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_FDB_FLUSH]) br_fdb_flush(br); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (data[IFLA_BR_MCAST_ROUTER]) { + u8 multicast_router = nla_get_u8(data[IFLA_BR_MCAST_ROUTER]); + + err = br_multicast_set_router(br, multicast_router); + if (err) + return err; + } +#endif + return 0; } @@ -889,6 +900,9 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_GC_TIMER */ nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ +#endif 0; } @@ -945,6 +959,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return -EMSGSIZE; #endif +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router)) + return -EMSGSIZE; +#endif + return 0; } -- cgit v1.2.3 From 89126327f921bd278c72284d38428443bbef344f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:38 +0200 Subject: bridge: netlink: add support for multicast_snooping Add IFLA_BR_MCAST_SNOOPING to allow enabling/disabling multicast snooping via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5d2c92973afe..22cb395a713d 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -246,6 +246,7 @@ enum { IFLA_BR_GROUP_ADDR, IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, + IFLA_BR_MCAST_SNOOPING, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index f4df609c1ad9..25e1c66d70f1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -768,6 +768,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -871,6 +872,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_SNOOPING]) { + u8 mcast_snooping = nla_get_u8(data[IFLA_BR_MCAST_SNOOPING]); + + err = br_multicast_toggle(br, mcast_snooping); + if (err) + return err; + } #endif return 0; @@ -902,6 +911,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(ETH_ALEN) + /* IFLA_BR_GROUP_ADDR */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ #endif 0; } @@ -960,7 +970,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING - if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router)) + if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || + nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 295141d9049bdf4fa316b325d2e2501b210dbe06 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:39 +0200 Subject: bridge: netlink: add support for multicast_query_use_ifaddr Add IFLA_BR_MCAST_QUERY_USE_IFADDR to allow setting/getting br->multicast_query_use_ifaddr via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 22cb395a713d..7090b3977eac 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -247,6 +247,7 @@ enum { IFLA_BR_FDB_FLUSH, IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, + IFLA_BR_MCAST_QUERY_USE_IFADDR, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 25e1c66d70f1..12ef844273a7 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -769,6 +769,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -880,6 +881,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_QUERY_USE_IFADDR]) { + u8 val; + + val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); + br->multicast_query_use_ifaddr = !!val; + } #endif return 0; @@ -912,6 +920,7 @@ static size_t br_get_size(const struct net_device *brdev) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ #endif 0; } @@ -971,7 +980,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || - nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled)) + nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || + nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, + br->multicast_query_use_ifaddr)) return -EMSGSIZE; #endif -- cgit v1.2.3 From ba062d7cc6a09a8194eba975d5ee635378a55bfc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:40 +0200 Subject: bridge: netlink: add support for multicast_querier Add IFLA_BR_MCAST_QUERIER to allow setting/getting br->multicast_querier via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 7090b3977eac..fe5fac5c2a7f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -248,6 +248,7 @@ enum { IFLA_BR_MCAST_ROUTER, IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, + IFLA_BR_MCAST_QUERIER, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 12ef844273a7..e21296dacf42 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -770,6 +770,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -888,6 +889,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], val = nla_get_u8(data[IFLA_BR_MCAST_QUERY_USE_IFADDR]); br->multicast_query_use_ifaddr = !!val; } + + if (data[IFLA_BR_MCAST_QUERIER]) { + u8 mcast_querier = nla_get_u8(data[IFLA_BR_MCAST_QUERIER]); + + err = br_multicast_set_querier(br, mcast_querier); + if (err) + return err; + } #endif return 0; @@ -921,6 +930,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_ROUTER */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ #endif 0; } @@ -982,7 +992,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, - br->multicast_query_use_ifaddr)) + br->multicast_query_use_ifaddr) || + nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 431db3c050af0be72b3b01fa7484982f35cb268f Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:41 +0200 Subject: bridge: netlink: add support for igmp's hash_elasticity Add IFLA_BR_MCAST_HASH_ELASTICITY to allow setting/getting br->hash_elasticity via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fe5fac5c2a7f..ca7ca766d8af 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -249,6 +249,7 @@ enum { IFLA_BR_MCAST_SNOOPING, IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, + IFLA_BR_MCAST_HASH_ELASTICITY, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e21296dacf42..b210a639e8d1 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -771,6 +771,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, + [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -897,6 +898,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_HASH_ELASTICITY]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_HASH_ELASTICITY]); + + br->hash_elasticity = val; + } #endif return 0; @@ -931,6 +938,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ #endif 0; } @@ -993,7 +1001,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || nla_put_u8(skb, IFLA_BR_MCAST_QUERY_USE_IFADDR, br->multicast_query_use_ifaddr) || - nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier)) + nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || + nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, + br->hash_elasticity)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 858079fdae16421d4908722140346cfdddedf343 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:42 +0200 Subject: bridge: netlink: add support for igmp's hash_max Add IFLA_BR_MCAST_HASH_MAX to allow setting/getting br->hash_max via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- 2 files changed, 13 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index ca7ca766d8af..10a44a735512 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -250,6 +250,7 @@ enum { IFLA_BR_MCAST_QUERY_USE_IFADDR, IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, + IFLA_BR_MCAST_HASH_MAX, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index b210a639e8d1..d6b61b0eeada 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -772,6 +772,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -904,6 +905,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->hash_elasticity = val; } + + if (data[IFLA_BR_MCAST_HASH_MAX]) { + u32 hash_max = nla_get_u32(data[IFLA_BR_MCAST_HASH_MAX]); + + err = br_multicast_set_hash_max(br, hash_max); + if (err) + return err; + } #endif return 0; @@ -939,6 +948,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ #endif 0; } @@ -1003,7 +1013,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) br->multicast_query_use_ifaddr) || nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, - br->hash_elasticity)) + br->hash_elasticity) || + nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 79b859f573d6afa64e328cc7f50ad7a209e0c92d Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:43 +0200 Subject: bridge: netlink: add support for multicast_last_member_count Add IFLA_BR_MCAST_LAST_MEMBER_CNT to allow setting/getting br->multicast_last_member_count via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 12 +++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 10a44a735512..5409a461e47e 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -251,6 +251,7 @@ enum { IFLA_BR_MCAST_QUERIER, IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, + IFLA_BR_MCAST_LAST_MEMBER_CNT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d6b61b0eeada..cf6ccaea8180 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -773,6 +773,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -913,6 +914,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_MCAST_LAST_MEMBER_CNT]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_LAST_MEMBER_CNT]); + + br->multicast_last_member_count = val; + } #endif return 0; @@ -949,6 +956,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ #endif 0; } @@ -1014,7 +1022,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u8(skb, IFLA_BR_MCAST_QUERIER, br->multicast_querier) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_ELASTICITY, br->hash_elasticity) || - nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max)) + nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || + nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, + br->multicast_last_member_count)) return -EMSGSIZE; #endif -- cgit v1.2.3 From b89e6babad4b7ca7298ad863c6c83dc76b0abdef Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:44 +0200 Subject: bridge: netlink: add support for multicast_startup_query_count Add IFLA_BR_MCAST_STARTUP_QUERY_CNT to allow setting/getting br->multicast_startup_query_count via netlink. Also align the ifla comments. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 22 ++++++++++++++++------ 2 files changed, 17 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5409a461e47e..fd841b5269c1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -252,6 +252,7 @@ enum { IFLA_BR_MCAST_HASH_ELASTICITY, IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, + IFLA_BR_MCAST_STARTUP_QUERY_CNT, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cf6ccaea8180..6744e30120af 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -774,6 +774,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -920,6 +921,12 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_last_member_count = val; } + + if (data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]) { + u32 val = nla_get_u32(data[IFLA_BR_MCAST_STARTUP_QUERY_CNT]); + + br->multicast_startup_query_count = val; + } #endif return 0; @@ -942,8 +949,8 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_BRIDGE_ID */ nla_total_size(sizeof(u16)) + /* IFLA_BR_ROOT_PORT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_ROOT_PATH_COST */ - nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ - nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_TOPOLOGY_CHANGE_DETECTED */ nla_total_size(sizeof(u64)) + /* IFLA_BR_HELLO_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TCN_TIMER */ nla_total_size(sizeof(u64)) + /* IFLA_BR_TOPOLOGY_CHANGE_TIMER */ @@ -954,9 +961,10 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_SNOOPING */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERY_USE_IFADDR */ nla_total_size(sizeof(u8)) + /* IFLA_BR_MCAST_QUERIER */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ - nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_ELASTICITY */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ + nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ #endif 0; } @@ -1024,7 +1032,9 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) br->hash_elasticity) || nla_put_u32(skb, IFLA_BR_MCAST_HASH_MAX, br->hash_max) || nla_put_u32(skb, IFLA_BR_MCAST_LAST_MEMBER_CNT, - br->multicast_last_member_count)) + br->multicast_last_member_count) || + nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, + br->multicast_startup_query_count)) return -EMSGSIZE; #endif -- cgit v1.2.3 From 7e4df51eb35deedd3ba8d4db92a6c36fb7eff90a Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:45 +0200 Subject: bridge: netlink: add support for igmp's intervals Add support to set/get all of the igmp's configurable intervals via netlink. These currently are: IFLA_BR_MCAST_LAST_MEMBER_INTVL IFLA_BR_MCAST_MEMBERSHIP_INTVL IFLA_BR_MCAST_QUERIER_INTVL IFLA_BR_MCAST_QUERY_INTVL IFLA_BR_MCAST_QUERY_RESPONSE_INTVL IFLA_BR_MCAST_STARTUP_QUERY_INTVL Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 6 ++++ net/bridge/br_netlink.c | 70 +++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 75 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fd841b5269c1..b8c88aa19fef 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -253,6 +253,12 @@ enum { IFLA_BR_MCAST_HASH_MAX, IFLA_BR_MCAST_LAST_MEMBER_CNT, IFLA_BR_MCAST_STARTUP_QUERY_CNT, + IFLA_BR_MCAST_LAST_MEMBER_INTVL, + IFLA_BR_MCAST_MEMBERSHIP_INTVL, + IFLA_BR_MCAST_QUERIER_INTVL, + IFLA_BR_MCAST_QUERY_INTVL, + IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, + IFLA_BR_MCAST_STARTUP_QUERY_INTVL, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6744e30120af..30def4fb5901 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -775,6 +775,12 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, + [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -927,6 +933,42 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_startup_query_count = val; } + + if (data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_LAST_MEMBER_INTVL]); + + br->multicast_last_member_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_MEMBERSHIP_INTVL]); + + br->multicast_membership_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERIER_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERIER_INTVL]); + + br->multicast_querier_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERY_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_INTVL]); + + br->multicast_query_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_QUERY_RESPONSE_INTVL]); + + br->multicast_query_response_interval = clock_t_to_jiffies(val); + } + + if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { + u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); + + br->multicast_startup_query_interval = clock_t_to_jiffies(val); + } #endif return 0; @@ -965,6 +1007,12 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_HASH_MAX */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_LAST_MEMBER_CNT */ nla_total_size(sizeof(u32)) + /* IFLA_BR_MCAST_STARTUP_QUERY_CNT */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_LAST_MEMBER_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_MEMBERSHIP_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERIER_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ + nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ #endif 0; } @@ -972,7 +1020,7 @@ static size_t br_get_size(const struct net_device *brdev) static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) { struct net_bridge *br = netdev_priv(brdev); - u64 hello_timer, tcn_timer, topology_change_timer, gc_timer; + u64 hello_timer, tcn_timer, topology_change_timer, gc_timer, clockval; u32 forward_delay = jiffies_to_clock_t(br->forward_delay); u32 hello_time = jiffies_to_clock_t(br->hello_time); u32 age_time = jiffies_to_clock_t(br->max_age); @@ -993,6 +1041,7 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) tcn_timer = br_timer_value(&br->tcn_timer); topology_change_timer = br_timer_value(&br->topology_change_timer); gc_timer = br_timer_value(&br->gc_timer); + clockval = 0; if (nla_put_u32(skb, IFLA_BR_FORWARD_DELAY, forward_delay) || nla_put_u32(skb, IFLA_BR_HELLO_TIME, hello_time) || @@ -1036,6 +1085,25 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) nla_put_u32(skb, IFLA_BR_MCAST_STARTUP_QUERY_CNT, br->multicast_startup_query_count)) return -EMSGSIZE; + + clockval = jiffies_to_clock_t(br->multicast_last_member_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_membership_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_MEMBERSHIP_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_querier_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERIER_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_query_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_query_response_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, clockval)) + return -EMSGSIZE; + clockval = jiffies_to_clock_t(br->multicast_startup_query_interval); + if (nla_put_u64(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval)) + return -EMSGSIZE; #endif return 0; -- cgit v1.2.3 From 93870cc02a0af4392401713d14235accafc752bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:46 +0200 Subject: bridge: netlink: add support for netfilter tables config Add support to allow getting/setting netfilter tables settings. Currently these are IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES and IFLA_BR_NF_CALL_ARPTABLES. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ net/bridge/br_netlink.c | 37 ++++++++++++++++++++++++++++++++++++- 2 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index b8c88aa19fef..0200bed6e5d6 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -259,6 +259,9 @@ enum { IFLA_BR_MCAST_QUERY_INTVL, IFLA_BR_MCAST_QUERY_RESPONSE_INTVL, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, + IFLA_BR_NF_CALL_IPTABLES, + IFLA_BR_NF_CALL_IP6TABLES, + IFLA_BR_NF_CALL_ARPTABLES, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 30def4fb5901..fd37caf02b51 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -781,6 +781,9 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, + [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, + [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, + [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -970,6 +973,25 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], br->multicast_startup_query_interval = clock_t_to_jiffies(val); } #endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (data[IFLA_BR_NF_CALL_IPTABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IPTABLES]); + + br->nf_call_iptables = val ? true : false; + } + + if (data[IFLA_BR_NF_CALL_IP6TABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_IP6TABLES]); + + br->nf_call_ip6tables = val ? true : false; + } + + if (data[IFLA_BR_NF_CALL_ARPTABLES]) { + u8 val = nla_get_u8(data[IFLA_BR_NF_CALL_ARPTABLES]); + + br->nf_call_arptables = val ? true : false; + } +#endif return 0; } @@ -1013,6 +1035,11 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_INTVL */ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_QUERY_RESPONSE_INTVL */ nla_total_size(sizeof(u64)) + /* IFLA_BR_MCAST_STARTUP_QUERY_INTVL */ +#endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IPTABLES */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_IP6TABLES */ + nla_total_size(sizeof(u8)) + /* IFLA_BR_NF_CALL_ARPTABLES */ #endif 0; } @@ -1070,7 +1097,6 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto)) return -EMSGSIZE; #endif - #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BR_MCAST_ROUTER, br->multicast_router) || nla_put_u8(skb, IFLA_BR_MCAST_SNOOPING, !br->multicast_disabled) || @@ -1105,6 +1131,15 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) if (nla_put_u64(skb, IFLA_BR_MCAST_STARTUP_QUERY_INTVL, clockval)) return -EMSGSIZE; #endif +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + if (nla_put_u8(skb, IFLA_BR_NF_CALL_IPTABLES, + br->nf_call_iptables ? 1 : 0) || + nla_put_u8(skb, IFLA_BR_NF_CALL_IP6TABLES, + br->nf_call_ip6tables ? 1 : 0) || + nla_put_u8(skb, IFLA_BR_NF_CALL_ARPTABLES, + br->nf_call_arptables ? 1 : 0)) + return -EMSGSIZE; +#endif return 0; } -- cgit v1.2.3 From 0f963b7592ef9e054974b6672b86ec1edd84b4bc Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 4 Oct 2015 14:23:47 +0200 Subject: bridge: netlink: add support for default_pvid Add IFLA_BR_VLAN_DEFAULT_PVID to allow setting/getting bridge's default_pvid via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 13 ++++++++++++- net/bridge/br_private.h | 1 + net/bridge/br_vlan.c | 14 +++++++------- 4 files changed, 21 insertions(+), 8 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 0200bed6e5d6..c5b15bfeabe2 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -262,6 +262,7 @@ enum { IFLA_BR_NF_CALL_IPTABLES, IFLA_BR_NF_CALL_IP6TABLES, IFLA_BR_NF_CALL_ARPTABLES, + IFLA_BR_VLAN_DEFAULT_PVID, __IFLA_BR_MAX, }; diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index fd37caf02b51..70efe2edde2b 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -784,6 +784,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, + [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], @@ -847,6 +848,14 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (err) return err; } + + if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { + __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); + + err = __br_vlan_set_default_pvid(br, defpvid); + if (err) + return err; + } #endif if (data[IFLA_BR_GROUP_FWD_MASK]) { @@ -1007,6 +1016,7 @@ static size_t br_get_size(const struct net_device *brdev) nla_total_size(sizeof(u8)) + /* IFLA_BR_VLAN_FILTERING */ #ifdef CONFIG_BRIDGE_VLAN_FILTERING nla_total_size(sizeof(__be16)) + /* IFLA_BR_VLAN_PROTOCOL */ + nla_total_size(sizeof(u16)) + /* IFLA_BR_VLAN_DEFAULT_PVID */ #endif nla_total_size(sizeof(u16)) + /* IFLA_BR_GROUP_FWD_MASK */ nla_total_size(sizeof(struct ifla_bridge_id)) + /* IFLA_BR_ROOT_ID */ @@ -1094,7 +1104,8 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_VLAN_FILTERING - if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto)) + if (nla_put_be16(skb, IFLA_BR_VLAN_PROTOCOL, br->vlan_proto) || + nla_put_u16(skb, IFLA_BR_VLAN_DEFAULT_PVID, br->default_pvid)) return -EMSGSIZE; #endif #ifdef CONFIG_BRIDGE_IGMP_SNOOPING diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1ff6a0faef3f..09d3ecbcb4f0 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -690,6 +690,7 @@ int __br_vlan_set_proto(struct net_bridge *br, __be16 proto); int br_vlan_set_proto(struct net_bridge *br, unsigned long val); int br_vlan_init(struct net_bridge *br); int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val); +int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid); int nbp_vlan_add(struct net_bridge_port *port, u16 vid, u16 flags); int nbp_vlan_delete(struct net_bridge_port *port, u16 vid); void nbp_vlan_flush(struct net_bridge_port *port); diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index b879111582f0..eae07ee9bfe0 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -727,7 +727,7 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) br->default_pvid = 0; } -static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) +int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) { const struct net_bridge_vlan *pvent; struct net_bridge_port *p; @@ -735,6 +735,11 @@ static int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid) int err = 0; unsigned long *changed; + if (!pvid) { + br_vlan_disable_default_pvid(br); + return 0; + } + changed = kcalloc(BITS_TO_LONGS(BR_MAX_PORTS), sizeof(unsigned long), GFP_KERNEL); if (!changed) @@ -825,12 +830,7 @@ int br_vlan_set_default_pvid(struct net_bridge *br, unsigned long val) err = -EPERM; goto unlock; } - - if (!pvid) - br_vlan_disable_default_pvid(br); - else - err = __br_vlan_set_default_pvid(br, pvid); - + err = __br_vlan_set_default_pvid(br, pvid); unlock: rtnl_unlock(); return err; -- cgit v1.2.3 From 70ba07b675b53782ad366ebc4d3a00eab9a06bc9 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 30 Sep 2015 17:32:01 +0200 Subject: atm: remove 'struct zatm_t_hist' The zatm_t_hist structure is not used anywhere in the kernel, but is exported to user space. As we are trying to eliminate uses of time_t in the kernel for y2038 compatibility, the current definition triggers checking tools because it contains 'struct timeval'. As pointed out by Chas Williams, the only user of this structure was the ZATM_GETHIST ioctl command that has been removed a long time ago, and we can remove the structure as well without breaking any user space. Signed-off-by: Arnd Bergmann Cc: Chas Williams <3chas3@gmail.com> Cc: linux-atm-general@lists.sourceforge.net Signed-off-by: David S. Miller --- include/uapi/linux/atm_zatm.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/atm_zatm.h b/include/uapi/linux/atm_zatm.h index 10f0fa29454f..9c9c6ad55f14 100644 --- a/include/uapi/linux/atm_zatm.h +++ b/include/uapi/linux/atm_zatm.h @@ -35,12 +35,6 @@ struct zatm_pool_req { struct zatm_pool_info info; /* actual information */ }; -struct zatm_t_hist { - struct timeval real; /* real (wall-clock) time */ - struct timeval expected; /* expected real time */ -}; - - #define ZATM_OAM_POOL 0 /* free buffer pool for OAM cells */ #define ZATM_AAL0_POOL 1 /* free buffer pool for AAL0 cells */ #define ZATM_AAL5_POOL_BASE 2 /* first AAL5 free buffer pool */ -- cgit v1.2.3 From 33db4125ec745426c3483d6817d8f7ea5324cd05 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Thu, 1 Oct 2015 15:00:37 -0700 Subject: openvswitch: Rename LABEL->LABELS Conntrack LABELS (plural) are exposed by conntrack; rename the OVS name for these to be consistent with conntrack. Fixes: c2ac667 "openvswitch: Allow matching on conntrack label" Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 12 +++---- net/openvswitch/actions.c | 2 +- net/openvswitch/conntrack.c | 74 ++++++++++++++++++++-------------------- net/openvswitch/conntrack.h | 2 +- net/openvswitch/flow.h | 2 +- net/openvswitch/flow_netlink.c | 18 +++++----- 6 files changed, 55 insertions(+), 55 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 32e07d8cbaf4..c736344afed4 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -326,7 +326,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ - OVS_KEY_ATTR_CT_LABEL, /* 16-octet connection tracking label */ + OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ #ifdef __KERNEL__ OVS_KEY_ATTR_TUNNEL_INFO, /* struct ip_tunnel_info */ @@ -439,9 +439,9 @@ struct ovs_key_nd { __u8 nd_tll[ETH_ALEN]; }; -#define OVS_CT_LABEL_LEN 16 -struct ovs_key_ct_label { - __u8 ct_label[OVS_CT_LABEL_LEN]; +#define OVS_CT_LABELS_LEN 16 +struct ovs_key_ct_labels { + __u8 ct_labels[OVS_CT_LABELS_LEN]; }; /* OVS_KEY_ATTR_CT_STATE flags */ @@ -623,7 +623,7 @@ struct ovs_action_hash { * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection * tracking mark field in the connection. - * @OVS_CT_ATTR_LABEL: %OVS_CT_LABEL_LEN value followed by %OVS_CT_LABEL_LEN + * @OVS_CT_ATTR_LABEL: %OVS_CT_LABELS_LEN value followed by %OVS_CT_LABELS_LEN * mask. For each bit set in the mask, the corresponding bit in the value is * copied to the connection tracking label field in the connection. * @OVS_CT_ATTR_HELPER: variable length string defining conntrack ALG. @@ -633,7 +633,7 @@ enum ovs_ct_attr { OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */ OVS_CT_ATTR_ZONE, /* u16 zone id. */ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */ - OVS_CT_ATTR_LABEL, /* label to associate with this connection. */ + OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */ OVS_CT_ATTR_HELPER, /* netlink helper to assist detection of related connections. */ __OVS_CT_ATTR_MAX diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index 315f5330b6e5..e23a61cc3d5c 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -968,7 +968,7 @@ static int execute_masked_set_action(struct sk_buff *skb, case OVS_KEY_ATTR_CT_STATE: case OVS_KEY_ATTR_CT_ZONE: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: err = -EINVAL; break; } diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 002a755fa07e..7d80acfb80d0 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -37,9 +37,9 @@ struct md_mark { }; /* Metadata label for masked write to conntrack label. */ -struct md_label { - struct ovs_key_ct_label value; - struct ovs_key_ct_label mask; +struct md_labels { + struct ovs_key_ct_labels value; + struct ovs_key_ct_labels mask; }; /* Conntrack action context for execution. */ @@ -50,7 +50,7 @@ struct ovs_conntrack_info { u32 flags; u16 family; struct md_mark mark; - struct md_label label; + struct md_labels labels; }; static u16 key_to_nfproto(const struct sw_flow_key *key) @@ -109,21 +109,21 @@ static u32 ovs_ct_get_mark(const struct nf_conn *ct) #endif } -static void ovs_ct_get_label(const struct nf_conn *ct, - struct ovs_key_ct_label *label) +static void ovs_ct_get_labels(const struct nf_conn *ct, + struct ovs_key_ct_labels *labels) { struct nf_conn_labels *cl = ct ? nf_ct_labels_find(ct) : NULL; if (cl) { size_t len = cl->words * sizeof(long); - if (len > OVS_CT_LABEL_LEN) - len = OVS_CT_LABEL_LEN; - else if (len < OVS_CT_LABEL_LEN) - memset(label, 0, OVS_CT_LABEL_LEN); - memcpy(label, cl->bits, len); + if (len > OVS_CT_LABELS_LEN) + len = OVS_CT_LABELS_LEN; + else if (len < OVS_CT_LABELS_LEN) + memset(labels, 0, OVS_CT_LABELS_LEN); + memcpy(labels, cl->bits, len); } else { - memset(label, 0, OVS_CT_LABEL_LEN); + memset(labels, 0, OVS_CT_LABELS_LEN); } } @@ -134,7 +134,7 @@ static void __ovs_ct_update_key(struct sw_flow_key *key, u8 state, key->ct.state = state; key->ct.zone = zone->id; key->ct.mark = ovs_ct_get_mark(ct); - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); } /* Update 'key' based on skb->nfct. If 'post_ct' is true, then OVS has @@ -179,8 +179,8 @@ int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_KEY_ATTR_CT_LABEL, sizeof(key->ct.label), - &key->ct.label)) + nla_put(skb, OVS_KEY_ATTR_CT_LABELS, sizeof(key->ct.labels), + &key->ct.labels)) return -EMSGSIZE; return 0; @@ -213,9 +213,9 @@ static int ovs_ct_set_mark(struct sk_buff *skb, struct sw_flow_key *key, #endif } -static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, - const struct ovs_key_ct_label *label, - const struct ovs_key_ct_label *mask) +static int ovs_ct_set_labels(struct sk_buff *skb, struct sw_flow_key *key, + const struct ovs_key_ct_labels *labels, + const struct ovs_key_ct_labels *mask) { enum ip_conntrack_info ctinfo; struct nf_conn_labels *cl; @@ -235,15 +235,15 @@ static int ovs_ct_set_label(struct sk_buff *skb, struct sw_flow_key *key, nf_ct_labels_ext_add(ct); cl = nf_ct_labels_find(ct); } - if (!cl || cl->words * sizeof(long) < OVS_CT_LABEL_LEN) + if (!cl || cl->words * sizeof(long) < OVS_CT_LABELS_LEN) return -ENOSPC; - err = nf_connlabels_replace(ct, (u32 *)label, (u32 *)mask, - OVS_CT_LABEL_LEN / sizeof(u32)); + err = nf_connlabels_replace(ct, (u32 *)labels, (u32 *)mask, + OVS_CT_LABELS_LEN / sizeof(u32)); if (err) return err; - ovs_ct_get_label(ct, &key->ct.label); + ovs_ct_get_labels(ct, &key->ct.labels); return 0; } @@ -465,12 +465,12 @@ static int ovs_ct_commit(struct net *net, struct sw_flow_key *key, return 0; } -static bool label_nonzero(const struct ovs_key_ct_label *label) +static bool labels_nonzero(const struct ovs_key_ct_labels *labels) { size_t i; - for (i = 0; i < sizeof(*label); i++) - if (label->ct_label[i]) + for (i = 0; i < sizeof(*labels); i++) + if (labels->ct_labels[i]) return true; return false; @@ -506,9 +506,9 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, if (err) goto err; } - if (label_nonzero(&info->label.mask)) - err = ovs_ct_set_label(skb, key, &info->label.value, - &info->label.mask); + if (labels_nonzero(&info->labels.mask)) + err = ovs_ct_set_labels(skb, key, &info->labels.value, + &info->labels.mask); err: skb_push(skb, nh_ofs); return err; @@ -545,8 +545,8 @@ static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), .maxlen = sizeof(struct md_mark) }, - [OVS_CT_ATTR_LABEL] = { .minlen = sizeof(struct md_label), - .maxlen = sizeof(struct md_label) }, + [OVS_CT_ATTR_LABELS] = { .minlen = sizeof(struct md_labels), + .maxlen = sizeof(struct md_labels) }, [OVS_CT_ATTR_HELPER] = { .minlen = 1, .maxlen = NF_CT_HELPER_NAME_LEN } }; @@ -593,10 +593,10 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } #endif #ifdef CONFIG_NF_CONNTRACK_LABELS - case OVS_CT_ATTR_LABEL: { - struct md_label *label = nla_data(a); + case OVS_CT_ATTR_LABELS: { + struct md_labels *labels = nla_data(a); - info->label = *label; + info->labels = *labels; break; } #endif @@ -633,7 +633,7 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr) attr == OVS_KEY_ATTR_CT_MARK) return true; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - attr == OVS_KEY_ATTR_CT_LABEL) { + attr == OVS_KEY_ATTR_CT_LABELS) { struct ovs_net *ovs_net = net_generic(net, ovs_net_id); return ovs_net->xt_label; @@ -711,8 +711,8 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, &ct_info->mark)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) && - nla_put(skb, OVS_CT_ATTR_LABEL, sizeof(ct_info->label), - &ct_info->label)) + nla_put(skb, OVS_CT_ATTR_LABELS, sizeof(ct_info->labels), + &ct_info->labels)) return -EMSGSIZE; if (ct_info->helper) { if (nla_put_string(skb, OVS_CT_ATTR_HELPER, @@ -737,7 +737,7 @@ void ovs_ct_free_action(const struct nlattr *a) void ovs_ct_init(struct net *net) { - unsigned int n_bits = sizeof(struct ovs_key_ct_label) * BITS_PER_BYTE; + unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE; struct ovs_net *ovs_net = net_generic(net, ovs_net_id); if (nf_connlabels_get(net, n_bits)) { diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index 43f5dd7a5577..6bd603c6a031 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -72,7 +72,7 @@ static inline void ovs_ct_fill_key(const struct sk_buff *skb, key->ct.state = 0; key->ct.zone = 0; key->ct.mark = 0; - memset(&key->ct.label, 0, sizeof(key->ct.label)); + memset(&key->ct.labels, 0, sizeof(key->ct.labels)); } static inline int ovs_ct_put_key(const struct sw_flow_key *key, diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index fe527d2dd4b7..8cfa15a08668 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -116,7 +116,7 @@ struct sw_flow_key { u16 zone; u32 mark; u8 state; - struct ovs_key_ct_label label; + struct ovs_key_ct_labels labels; } ct; } __aligned(BITS_PER_LONG/8); /* Ensure that we can do comparisons as longs. */ diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 5c030a4d7338..a60e3b7684bc 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -294,7 +294,7 @@ size_t ovs_key_attr_size(void) + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ - + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABEL */ + + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ + nla_total_size(12) /* OVS_KEY_ATTR_ETHERNET */ + nla_total_size(2) /* OVS_KEY_ATTR_ETHERTYPE */ + nla_total_size(4) /* OVS_KEY_ATTR_VLAN */ @@ -352,7 +352,7 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, - [OVS_KEY_ATTR_CT_LABEL] = { .len = sizeof(struct ovs_key_ct_label) }, + [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, }; static bool check_attr_len(unsigned int attr_len, unsigned int expected_len) @@ -833,14 +833,14 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, SW_FLOW_KEY_PUT(match, ct.mark, mark, is_mask); *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_MARK); } - if (*attrs & (1 << OVS_KEY_ATTR_CT_LABEL) && - ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABEL)) { - const struct ovs_key_ct_label *cl; + if (*attrs & (1 << OVS_KEY_ATTR_CT_LABELS) && + ovs_ct_verify(net, OVS_KEY_ATTR_CT_LABELS)) { + const struct ovs_key_ct_labels *cl; - cl = nla_data(a[OVS_KEY_ATTR_CT_LABEL]); - SW_FLOW_KEY_MEMCPY(match, ct.label, cl->ct_label, + cl = nla_data(a[OVS_KEY_ATTR_CT_LABELS]); + SW_FLOW_KEY_MEMCPY(match, ct.labels, cl->ct_labels, sizeof(*cl), is_mask); - *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABEL); + *attrs &= ~(1ULL << OVS_KEY_ATTR_CT_LABELS); } return 0; } @@ -1973,7 +1973,7 @@ static int validate_set(const struct nlattr *a, case OVS_KEY_ATTR_PRIORITY: case OVS_KEY_ATTR_SKB_MARK: case OVS_KEY_ATTR_CT_MARK: - case OVS_KEY_ATTR_CT_LABEL: + case OVS_KEY_ATTR_CT_LABELS: case OVS_KEY_ATTR_ETHERNET: break; -- cgit v1.2.3 From a29a9a585b2840a205f085a34dfd65c75e86f7c3 Mon Sep 17 00:00:00 2001 From: Ken-ichirou MATSUZAWA Date: Mon, 5 Oct 2015 11:50:46 +0900 Subject: netfilter: nfnetlink_log: allow to attach conntrack This patch enables to include the conntrack information together with the packet that is sent to user-space via NFLOG, then a user-space program can acquire NATed information by this NFULA_CT attribute. Including the conntrack information is optional, you can set it via NFULNL_CFG_F_CONNTRACK flag with the NFULA_CFG_FLAGS attribute like NFQUEUE. Signed-off-by: Ken-ichirou MATSUZAWA Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nfnetlink_log.h | 3 +++ net/netfilter/Kconfig | 9 ++++--- net/netfilter/nfnetlink_log.c | 37 ++++++++++++++++++++++++---- 3 files changed, 40 insertions(+), 9 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/netfilter/nfnetlink_log.h b/include/uapi/linux/netfilter/nfnetlink_log.h index 90c2c9575bac..fb21f0c717a1 100644 --- a/include/uapi/linux/netfilter/nfnetlink_log.h +++ b/include/uapi/linux/netfilter/nfnetlink_log.h @@ -51,6 +51,8 @@ enum nfulnl_attr_type { NFULA_HWTYPE, /* hardware type */ NFULA_HWHEADER, /* hardware header */ NFULA_HWLEN, /* hardware header length */ + NFULA_CT, /* nf_conntrack_netlink.h */ + NFULA_CT_INFO, /* enum ip_conntrack_info */ __NFULA_MAX }; @@ -93,5 +95,6 @@ enum nfulnl_attr_config { #define NFULNL_CFG_F_SEQ 0x0001 #define NFULNL_CFG_F_SEQ_GLOBAL 0x0002 +#define NFULNL_CFG_F_CONNTRACK 0x0004 #endif /* _NFNETLINK_LOG_H */ diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index d287818fe965..e22349ea7256 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -363,12 +363,13 @@ config NF_CT_NETLINK_HELPER If unsure, say `N'. config NETFILTER_NETLINK_GLUE_CT - bool "NFQUEUE integration with Connection Tracking" + bool "NFQUEUE and NFLOG integration with Connection Tracking" default n - depends on NETFILTER_NETLINK_QUEUE && NF_CT_NETLINK + depends on (NETFILTER_NETLINK_QUEUE || NETFILTER_NETLINK_LOG) && NF_CT_NETLINK help - If this option is enabled, NFQUEUE can include Connection Tracking - information together with the packet is the enqueued via NFNETLINK. + If this option is enabled, NFQUEUE and NFLOG can include + Connection Tracking information together with the packet is + the enqueued via NFNETLINK. config NF_NAT tristate diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 4670821b569d..e1d1187f6646 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -401,7 +402,9 @@ __build_packet_message(struct nfnl_log_net *log, unsigned int hooknum, const struct net_device *indev, const struct net_device *outdev, - const char *prefix, unsigned int plen) + const char *prefix, unsigned int plen, + const struct nfnl_ct_hook *nfnl_ct, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; @@ -575,6 +578,10 @@ __build_packet_message(struct nfnl_log_net *log, htonl(atomic_inc_return(&log->global_seq)))) goto nla_put_failure; + if (ct && nfnl_ct->build(inst->skb, ct, ctinfo, + NFULA_CT, NFULA_CT_INFO) < 0) + goto nla_put_failure; + if (data_len) { struct nlattr *nla; int size = nla_attr_size(data_len); @@ -620,12 +627,16 @@ nfulnl_log_packet(struct net *net, const struct nf_loginfo *li_user, const char *prefix) { - unsigned int size, data_len; + size_t size; + unsigned int data_len; struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; unsigned int plen; struct nfnl_log_net *log = nfnl_log_pernet(net); + const struct nfnl_ct_hook *nfnl_ct = NULL; + struct nf_conn *ct = NULL; + enum ip_conntrack_info uninitialized_var(ctinfo); if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; @@ -671,6 +682,14 @@ nfulnl_log_packet(struct net *net, size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); + if (inst->flags & NFULNL_CFG_F_CONNTRACK) { + nfnl_ct = rcu_dereference(nfnl_ct_hook); + if (nfnl_ct != NULL) { + ct = nfnl_ct->get_ct(skb, &ctinfo); + if (ct != NULL) + size += nfnl_ct->build_size(ct); + } + } qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ @@ -715,7 +734,8 @@ nfulnl_log_packet(struct net *net, inst->qlen++; __build_packet_message(log, inst, skb, data_len, pf, - hooknum, in, out, prefix, plen); + hooknum, in, out, prefix, plen, + nfnl_ct, ct, ctinfo); if (inst->qlen >= qthreshold) __nfulnl_flush(inst); @@ -899,13 +919,20 @@ nfulnl_recv_config(struct sock *ctnl, struct sk_buff *skb, } if (nfula[NFULA_CFG_FLAGS]) { - __be16 flags = nla_get_be16(nfula[NFULA_CFG_FLAGS]); + u16 flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS])); if (!inst) { ret = -ENODEV; goto out; } - nfulnl_set_flags(inst, ntohs(flags)); + + if (flags & NFULNL_CFG_F_CONNTRACK && + rcu_access_pointer(nfnl_ct_hook) == NULL) { + ret = -EOPNOTSUPP; + goto out; + } + + nfulnl_set_flags(inst, flags); } out_put: -- cgit v1.2.3 From 6b26ba3a7d952e611dcde1f3f77ce63bcc70540a Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Mon, 5 Oct 2015 13:09:47 +0200 Subject: openvswitch: netlink attributes for IPv6 tunneling Add netlink attributes for IPv6 tunnel addresses. This enables IPv6 support for tunnels. Signed-off-by: Jiri Benc Acked-by: Pravin B Shelar Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 2 + net/openvswitch/flow_netlink.c | 121 +++++++++++++++++++++++++++------------ 2 files changed, 86 insertions(+), 37 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 32e07d8cbaf4..4036e1b1980f 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -349,6 +349,8 @@ enum ovs_tunnel_key_attr { OVS_TUNNEL_KEY_ATTR_TP_SRC, /* be16 src Transport Port. */ OVS_TUNNEL_KEY_ATTR_TP_DST, /* be16 dst Transport Port. */ OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS, /* Nested OVS_VXLAN_EXT_* */ + OVS_TUNNEL_KEY_ATTR_IPV6_SRC, /* struct in6_addr src IPv6 address. */ + OVS_TUNNEL_KEY_ATTR_IPV6_DST, /* struct in6_addr dst IPv6 address. */ __OVS_TUNNEL_KEY_ATTR_MAX }; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 6be701f6b31b..77850f177a47 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -262,8 +262,8 @@ size_t ovs_tun_key_attr_size(void) * updating this function. */ return nla_total_size(8) /* OVS_TUNNEL_KEY_ATTR_ID */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_SRC */ - + nla_total_size(4) /* OVS_TUNNEL_KEY_ATTR_IPV4_DST */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_SRC */ + + nla_total_size(16) /* OVS_TUNNEL_KEY_ATTR_IPV[46]_DST */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TOS */ + nla_total_size(1) /* OVS_TUNNEL_KEY_ATTR_TTL */ + nla_total_size(0) /* OVS_TUNNEL_KEY_ATTR_DONT_FRAGMENT */ @@ -323,6 +323,8 @@ static const struct ovs_len_tbl ovs_tunnel_key_lens[OVS_TUNNEL_KEY_ATTR_MAX + 1] [OVS_TUNNEL_KEY_ATTR_GENEVE_OPTS] = { .len = OVS_ATTR_VARIABLE }, [OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS] = { .len = OVS_ATTR_NESTED, .next = ovs_vxlan_ext_key_lens }, + [OVS_TUNNEL_KEY_ATTR_IPV6_SRC] = { .len = sizeof(struct in6_addr) }, + [OVS_TUNNEL_KEY_ATTR_IPV6_DST] = { .len = sizeof(struct in6_addr) }, }; /* The size of the argument for each %OVS_KEY_ATTR_* Netlink attribute. */ @@ -542,14 +544,14 @@ static int vxlan_tun_opt_from_nlattr(const struct nlattr *attr, return 0; } -static int ipv4_tun_from_nlattr(const struct nlattr *attr, - struct sw_flow_match *match, bool is_mask, - bool log) +static int ip_tun_from_nlattr(const struct nlattr *attr, + struct sw_flow_match *match, bool is_mask, + bool log) { struct nlattr *a; int rem; bool ttl = false; - __be16 tun_flags = 0; + __be16 tun_flags = 0, ipv4 = false, ipv6 = false; int opts_type = 0; nla_for_each_nested(a, attr, rem) { @@ -578,10 +580,22 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, case OVS_TUNNEL_KEY_ATTR_IPV4_SRC: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.src, nla_get_in_addr(a), is_mask); + ipv4 = true; break; case OVS_TUNNEL_KEY_ATTR_IPV4_DST: SW_FLOW_KEY_PUT(match, tun_key.u.ipv4.dst, nla_get_in_addr(a), is_mask); + ipv4 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_SRC: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; + break; + case OVS_TUNNEL_KEY_ATTR_IPV6_DST: + SW_FLOW_KEY_PUT(match, tun_key.u.ipv6.dst, + nla_get_in6_addr(a), is_mask); + ipv6 = true; break; case OVS_TUNNEL_KEY_ATTR_TOS: SW_FLOW_KEY_PUT(match, tun_key.tos, @@ -636,7 +650,7 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, opts_type = type; break; default: - OVS_NLERR(log, "Unknown IPv4 tunnel attribute %d", + OVS_NLERR(log, "Unknown IP tunnel attribute %d", type); return -EINVAL; } @@ -646,22 +660,36 @@ static int ipv4_tun_from_nlattr(const struct nlattr *attr, if (is_mask) SW_FLOW_KEY_MEMSET_FIELD(match, tun_proto, 0xff, true); else - SW_FLOW_KEY_PUT(match, tun_proto, AF_INET, false); + SW_FLOW_KEY_PUT(match, tun_proto, ipv6 ? AF_INET6 : AF_INET, + false); if (rem > 0) { - OVS_NLERR(log, "IPv4 tunnel attribute has %d unknown bytes.", + OVS_NLERR(log, "IP tunnel attribute has %d unknown bytes.", rem); return -EINVAL; } + if (ipv4 && ipv6) { + OVS_NLERR(log, "Mixed IPv4 and IPv6 tunnel attributes"); + return -EINVAL; + } + if (!is_mask) { - if (!match->key->tun_key.u.ipv4.dst) { + if (!ipv4 && !ipv6) { + OVS_NLERR(log, "IP tunnel dst address not specified"); + return -EINVAL; + } + if (ipv4 && !match->key->tun_key.u.ipv4.dst) { OVS_NLERR(log, "IPv4 tunnel dst address is zero"); return -EINVAL; } + if (ipv6 && ipv6_addr_any(&match->key->tun_key.u.ipv6.dst)) { + OVS_NLERR(log, "IPv6 tunnel dst address is zero"); + return -EINVAL; + } if (!ttl) { - OVS_NLERR(log, "IPv4 tunnel TTL not specified."); + OVS_NLERR(log, "IP tunnel TTL not specified."); return -EINVAL; } } @@ -686,21 +714,36 @@ static int vxlan_opt_to_nlattr(struct sk_buff *skb, return 0; } -static int __ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int __ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { if (output->tun_flags & TUNNEL_KEY && nla_put_be64(skb, OVS_TUNNEL_KEY_ATTR_ID, output->tun_id)) return -EMSGSIZE; - if (output->u.ipv4.src && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, - output->u.ipv4.src)) - return -EMSGSIZE; - if (output->u.ipv4.dst && - nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, - output->u.ipv4.dst)) - return -EMSGSIZE; + switch (tun_proto) { + case AF_INET: + if (output->u.ipv4.src && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_SRC, + output->u.ipv4.src)) + return -EMSGSIZE; + if (output->u.ipv4.dst && + nla_put_in_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV4_DST, + output->u.ipv4.dst)) + return -EMSGSIZE; + break; + case AF_INET6: + if (!ipv6_addr_any(&output->u.ipv6.src) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_SRC, + &output->u.ipv6.src)) + return -EMSGSIZE; + if (!ipv6_addr_any(&output->u.ipv6.dst) && + nla_put_in6_addr(skb, OVS_TUNNEL_KEY_ATTR_IPV6_DST, + &output->u.ipv6.dst)) + return -EMSGSIZE; + break; + } if (output->tos && nla_put_u8(skb, OVS_TUNNEL_KEY_ATTR_TOS, output->tos)) return -EMSGSIZE; @@ -734,9 +777,10 @@ static int __ipv4_tun_to_nlattr(struct sk_buff *skb, return 0; } -static int ipv4_tun_to_nlattr(struct sk_buff *skb, - const struct ip_tunnel_key *output, - const void *tun_opts, int swkey_tun_opts_len) +static int ip_tun_to_nlattr(struct sk_buff *skb, + const struct ip_tunnel_key *output, + const void *tun_opts, int swkey_tun_opts_len, + unsigned short tun_proto) { struct nlattr *nla; int err; @@ -745,7 +789,8 @@ static int ipv4_tun_to_nlattr(struct sk_buff *skb, if (!nla) return -EMSGSIZE; - err = __ipv4_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len); + err = __ip_tun_to_nlattr(skb, output, tun_opts, swkey_tun_opts_len, + tun_proto); if (err) return err; @@ -757,9 +802,10 @@ int ovs_nla_put_egress_tunnel_key(struct sk_buff *skb, const struct ip_tunnel_info *egress_tun_info, const void *egress_tun_opts) { - return __ipv4_tun_to_nlattr(skb, &egress_tun_info->key, - egress_tun_opts, - egress_tun_info->options_len); + return __ip_tun_to_nlattr(skb, &egress_tun_info->key, + egress_tun_opts, + egress_tun_info->options_len, + ip_tunnel_info_af(egress_tun_info)); } static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, @@ -810,8 +856,8 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, *attrs &= ~(1 << OVS_KEY_ATTR_SKB_MARK); } if (*attrs & (1 << OVS_KEY_ATTR_TUNNEL)) { - if (ipv4_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, - is_mask, log) < 0) + if (ip_tun_from_nlattr(a[OVS_KEY_ATTR_TUNNEL], match, + is_mask, log) < 0) return -EINVAL; *attrs &= ~(1 << OVS_KEY_ATTR_TUNNEL); } @@ -1377,8 +1423,8 @@ static int __ovs_nla_put_key(const struct sw_flow_key *swkey, if (output->tun_key.tun_flags & TUNNEL_OPTIONS_PRESENT) opts = TUN_METADATA_OPTS(output, swkey->tun_opts_len); - if (ipv4_tun_to_nlattr(skb, &output->tun_key, opts, - swkey->tun_opts_len)) + if (ip_tun_to_nlattr(skb, &output->tun_key, opts, + swkey->tun_opts_len, swkey->tun_proto)) goto nla_put_failure; } @@ -1881,7 +1927,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr, int err = 0, start, opts_type; ovs_match_init(&match, &key, NULL); - opts_type = ipv4_tun_from_nlattr(nla_data(attr), &match, false, log); + opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log); if (opts_type < 0) return opts_type; @@ -2380,10 +2426,11 @@ static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb) if (!start) return -EMSGSIZE; - err = ipv4_tun_to_nlattr(skb, &tun_info->key, - tun_info->options_len ? + err = ip_tun_to_nlattr(skb, &tun_info->key, + tun_info->options_len ? ip_tunnel_info_opts(tun_info) : NULL, - tun_info->options_len); + tun_info->options_len, + ip_tunnel_info_af(tun_info)); if (err) return err; nla_nest_end(skb, start); -- cgit v1.2.3 From 4ebc7660ab4559cad10b6595e05f70562bb26dc5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:55 +0200 Subject: bridge: netlink: export port's root id Add IFLA_BRPORT_ROOT_ID to allow getting the designated root id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c5b15bfeabe2..c45c1d7894e7 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -292,6 +292,7 @@ enum { IFLA_BRPORT_PROXYARP, /* proxy ARP */ IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ + IFLA_BRPORT_ROOT_ID, /* designated root */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 330abf4b033a..cad4050310ee 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -127,6 +127,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + 0; } @@ -160,7 +161,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, - !!(p->flags & BR_PROXYARP_WIFI))) + !!(p->flags & BR_PROXYARP_WIFI)) || + nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), + &p->designated_root)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 80df9a2692edf7afffda9282e716e7b1df198e07 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:56 +0200 Subject: bridge: netlink: export port's bridge id Add IFLA_BRPORT_BRIDGE_ID to allow getting the designated bridge id via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index c45c1d7894e7..e891c32c9993 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -293,6 +293,7 @@ enum { IFLA_BRPORT_LEARNING_SYNC, /* mac learning sync from device */ IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ + IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index cad4050310ee..c3e0b73d660d 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -128,6 +128,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + 0; } @@ -163,7 +164,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), - &p->designated_root)) + &p->designated_root) || + nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), + &p->designated_bridge)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 96f94e7f4a216282a24819968184c881e6343692 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:57 +0200 Subject: bridge: netlink: export port's designated cost and port Add IFLA_BRPORT_DESIGNATED_(COST|PORT) to allow getting the port's designated cost and port respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e891c32c9993..837caf940135 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -294,6 +294,8 @@ enum { IFLA_BRPORT_PROXYARP_WIFI, /* proxy ARP for Wi-Fi */ IFLA_BRPORT_ROOT_ID, /* designated root */ IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ + IFLA_BRPORT_DESIGNATED_PORT, + IFLA_BRPORT_DESIGNATED_COST, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c3e0b73d660d..678d22747044 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -129,6 +129,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + 0; } @@ -166,7 +168,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), - &p->designated_bridge)) + &p->designated_bridge) || + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 42d452c4b5e7bf0e3024fa9512ec462f70545ae5 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:58 +0200 Subject: bridge: netlink: export port's id and number Add IFLA_BRPORT_(ID|NO) to allow getting port's port_id and port_no respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 6 +++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 837caf940135..6857563eb27c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -296,6 +296,8 @@ enum { IFLA_BRPORT_BRIDGE_ID, /* designated bridge */ IFLA_BRPORT_DESIGNATED_PORT, IFLA_BRPORT_DESIGNATED_COST, + IFLA_BRPORT_ID, + IFLA_BRPORT_NO, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 678d22747044..e51332792c3c 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -131,6 +131,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + 0; } @@ -170,7 +172,9 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || - nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost)) + nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || + nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || + nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From e08e838ac5707cb1f1294e0d53b31997a0367b99 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:11:59 +0200 Subject: bridge: netlink: export port's topology_change_ack and config_pending Add IFLA_BRPORT_TOPOLOGY_CHANGE_ACK and IFLA_BRPORT_CONFIG_PENDING to allow getting port's topology_change_ack and config_pending respectively via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 2 ++ net/bridge/br_netlink.c | 7 ++++++- 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 6857563eb27c..1d6aeb1bbe95 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -298,6 +298,8 @@ enum { IFLA_BRPORT_DESIGNATED_COST, IFLA_BRPORT_ID, IFLA_BRPORT_NO, + IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + IFLA_BRPORT_CONFIG_PENDING, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index e51332792c3c..433d632ad7d0 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -133,6 +133,8 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + 0; } @@ -174,7 +176,10 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || - nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no)) + nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || + nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, + p->topology_change_ack) || + nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending)) return -EMSGSIZE; return 0; -- cgit v1.2.3 From 61c0a9a83e0b12c712cd686172446aba8ea48685 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:00 +0200 Subject: bridge: netlink: export port's timer values Add the following attributes in order to export port's timer values: IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER and IFLA_BRPORT_HOLD_TIMER. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 3 +++ net/bridge/br_netlink.c | 14 ++++++++++++++ 2 files changed, 17 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 1d6aeb1bbe95..9c17f605e013 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -300,6 +300,9 @@ enum { IFLA_BRPORT_NO, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, IFLA_BRPORT_CONFIG_PENDING, + IFLA_BRPORT_MESSAGE_AGE_TIMER, + IFLA_BRPORT_FORWARD_DELAY_TIMER, + IFLA_BRPORT_HOLD_TIMER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 433d632ad7d0..04b0e5072686 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -135,6 +135,9 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ + 0; } @@ -156,6 +159,7 @@ static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); + u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || @@ -182,6 +186,16 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending)) return -EMSGSIZE; + timerval = br_timer_value(&p->message_age_timer); + if (nla_put_u64(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval)) + return -EMSGSIZE; + timerval = br_timer_value(&p->forward_delay_timer); + if (nla_put_u64(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval)) + return -EMSGSIZE; + timerval = br_timer_value(&p->hold_timer); + if (nla_put_u64(skb, IFLA_BRPORT_HOLD_TIMER, timerval)) + return -EMSGSIZE; + return 0; } -- cgit v1.2.3 From 9b0c6e4deb3df91bf0aea8158ea77dc58c9d90b6 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:01 +0200 Subject: bridge: netlink: allow to flush port's fdb Add IFLA_BRPORT_FLUSH to allow flushing port's fdb similar to sysfs's flush. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 3 +++ 2 files changed, 4 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9c17f605e013..fcea39a56095 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -303,6 +303,7 @@ enum { IFLA_BRPORT_MESSAGE_AGE_TIMER, IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, + IFLA_BRPORT_FLUSH, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 04b0e5072686..6468166d6bdc 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -631,6 +631,9 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) return err; } + if (tb[IFLA_BRPORT_FLUSH]) + br_fdb_delete_by_port(p->br, p, 0, 0); + br_port_flags_change(p, old_flags ^ p->flags); return 0; } -- cgit v1.2.3 From 5d6ae479ab7ddf77bb22bdf739268581453ff886 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Tue, 6 Oct 2015 14:12:02 +0200 Subject: bridge: netlink: add support for port's multicast_router attribute Add IFLA_BRPORT_MULTICAST_ROUTER to allow setting/getting port's multicast_router via netlink. Signed-off-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/uapi/linux/if_link.h | 1 + net/bridge/br_netlink.c | 19 +++++++++++++++++++ 2 files changed, 20 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index fcea39a56095..e3b6217f34f1 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -304,6 +304,7 @@ enum { IFLA_BRPORT_FORWARD_DELAY_TIMER, IFLA_BRPORT_HOLD_TIMER, IFLA_BRPORT_FLUSH, + IFLA_BRPORT_MULTICAST_ROUTER, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 6468166d6bdc..d78b4429505a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -138,6 +138,9 @@ static inline size_t br_port_info_size(void) + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ +#endif + 0; } @@ -196,6 +199,12 @@ static int br_port_fill_attrs(struct sk_buff *skb, if (nla_put_u64(skb, IFLA_BRPORT_HOLD_TIMER, timerval)) return -EMSGSIZE; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, + p->multicast_router)) + return -EMSGSIZE; +#endif + return 0; } @@ -560,6 +569,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, + [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, }; /* Change the state of the port and notify spanning tree */ @@ -634,6 +644,15 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { + u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); + + err = br_multicast_set_port_router(p, mcast_router); + if (err) + return err; + } +#endif br_port_flags_change(p, old_flags ^ p->flags); return 0; } -- cgit v1.2.3 From 0a7cc172a01e4a203667fb601cd80131db8d0c9a Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 6 Oct 2015 10:59:56 -0700 Subject: openvswitch: Fix typos in CT headers These comments hadn't caught up to their implementations, fix them. Fixes: 7f8a436eaa2c "openvswitch: Add conntrack action" Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index c736344afed4..a9a4a59912e9 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -630,7 +630,7 @@ struct ovs_action_hash { */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, - OVS_CT_ATTR_FLAGS, /* u8 bitmask of OVS_CT_F_*. */ + OVS_CT_ATTR_FLAGS, /* u32 bitmask of OVS_CT_F_*. */ OVS_CT_ATTR_ZONE, /* u16 zone id. */ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */ OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */ @@ -705,7 +705,7 @@ enum ovs_action_attr { * data immediately followed by a mask. * The data must be zero for the unmasked * bits. */ - OVS_ACTION_ATTR_CT, /* One nested OVS_CT_ATTR_* . */ + OVS_ACTION_ATTR_CT, /* Nested OVS_CT_ATTR_* . */ __OVS_ACTION_ATTR_MAX, /* Nothing past this will be accepted * from userspace. */ -- cgit v1.2.3 From fbccce5965a58d56aaed9e9acd1bec75d8a66e87 Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 6 Oct 2015 11:00:00 -0700 Subject: openvswitch: Extend ct_state match field to 32 bits The ct_state field was initially added as an 8-bit field, however six of the bits are already being used and use cases are already starting to appear that may push the limits of this field. This patch extends the field to 32 bits while retaining the internal representation of 8 bits. This should cover forward compatibility of the ABI for the foreseeable future. This patch also reorders the OVS_CS_F_* bits to be sequential. Suggested-by: Jarno Rajahalme Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 8 ++++---- net/openvswitch/conntrack.c | 2 +- net/openvswitch/conntrack.h | 4 ++-- net/openvswitch/flow_netlink.c | 8 ++++---- 4 files changed, 11 insertions(+), 11 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index a9a4a59912e9..c861a4cf5fec 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -323,7 +323,7 @@ enum ovs_key_attr { OVS_KEY_ATTR_MPLS, /* array of struct ovs_key_mpls. * The implementation may restrict * the accepted length of the array. */ - OVS_KEY_ATTR_CT_STATE, /* u8 bitmask of OVS_CS_F_* */ + OVS_KEY_ATTR_CT_STATE, /* u32 bitmask of OVS_CS_F_* */ OVS_KEY_ATTR_CT_ZONE, /* u16 connection tracking zone. */ OVS_KEY_ATTR_CT_MARK, /* u32 connection tracking mark */ OVS_KEY_ATTR_CT_LABELS, /* 16-octet connection tracking label */ @@ -449,9 +449,9 @@ struct ovs_key_ct_labels { #define OVS_CS_F_ESTABLISHED 0x02 /* Part of an existing connection. */ #define OVS_CS_F_RELATED 0x04 /* Related to an established * connection. */ -#define OVS_CS_F_INVALID 0x20 /* Could not track connection. */ -#define OVS_CS_F_REPLY_DIR 0x40 /* Flow is in the reply direction. */ -#define OVS_CS_F_TRACKED 0x80 /* Conntrack has occurred. */ +#define OVS_CS_F_REPLY_DIR 0x08 /* Flow is in the reply direction. */ +#define OVS_CS_F_INVALID 0x10 /* Could not track connection. */ +#define OVS_CS_F_TRACKED 0x20 /* Conntrack has occurred. */ /** * enum ovs_flow_attr - attributes for %OVS_FLOW_* commands. diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 7d80acfb80d0..466d5576fe3f 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -167,7 +167,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb) { - if (nla_put_u8(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) + if (nla_put_u32(skb, OVS_KEY_ATTR_CT_STATE, key->ct.state)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && diff --git a/net/openvswitch/conntrack.h b/net/openvswitch/conntrack.h index d6eca8394254..da8714942c95 100644 --- a/net/openvswitch/conntrack.h +++ b/net/openvswitch/conntrack.h @@ -35,7 +35,7 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key); int ovs_ct_put_key(const struct sw_flow_key *key, struct sk_buff *skb); void ovs_ct_free_action(const struct nlattr *a); -static inline bool ovs_ct_state_supported(u8 state) +static inline bool ovs_ct_state_supported(u32 state) { return !(state & ~(OVS_CS_F_NEW | OVS_CS_F_ESTABLISHED | OVS_CS_F_RELATED | OVS_CS_F_REPLY_DIR | @@ -53,7 +53,7 @@ static inline bool ovs_ct_verify(struct net *net, int attr) return false; } -static inline bool ovs_ct_state_supported(u8 state) +static inline bool ovs_ct_state_supported(u32 state) { return false; } diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index d47b5c5c640e..171a691f1c32 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -291,7 +291,7 @@ size_t ovs_key_attr_size(void) + nla_total_size(4) /* OVS_KEY_ATTR_SKB_MARK */ + nla_total_size(4) /* OVS_KEY_ATTR_DP_HASH */ + nla_total_size(4) /* OVS_KEY_ATTR_RECIRC_ID */ - + nla_total_size(1) /* OVS_KEY_ATTR_CT_STATE */ + + nla_total_size(4) /* OVS_KEY_ATTR_CT_STATE */ + nla_total_size(2) /* OVS_KEY_ATTR_CT_ZONE */ + nla_total_size(4) /* OVS_KEY_ATTR_CT_MARK */ + nla_total_size(16) /* OVS_KEY_ATTR_CT_LABELS */ @@ -349,7 +349,7 @@ static const struct ovs_len_tbl ovs_key_lens[OVS_KEY_ATTR_MAX + 1] = { [OVS_KEY_ATTR_TUNNEL] = { .len = OVS_ATTR_NESTED, .next = ovs_tunnel_key_lens, }, [OVS_KEY_ATTR_MPLS] = { .len = sizeof(struct ovs_key_mpls) }, - [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u8) }, + [OVS_KEY_ATTR_CT_STATE] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_ZONE] = { .len = sizeof(u16) }, [OVS_KEY_ATTR_CT_MARK] = { .len = sizeof(u32) }, [OVS_KEY_ATTR_CT_LABELS] = { .len = sizeof(struct ovs_key_ct_labels) }, @@ -814,10 +814,10 @@ static int metadata_from_nlattrs(struct net *net, struct sw_flow_match *match, if (*attrs & (1 << OVS_KEY_ATTR_CT_STATE) && ovs_ct_verify(net, OVS_KEY_ATTR_CT_STATE)) { - u8 ct_state = nla_get_u8(a[OVS_KEY_ATTR_CT_STATE]); + u32 ct_state = nla_get_u32(a[OVS_KEY_ATTR_CT_STATE]); if (!is_mask && !ovs_ct_state_supported(ct_state)) { - OVS_NLERR(log, "ct_state flags %02x unsupported", + OVS_NLERR(log, "ct_state flags %08x unsupported", ct_state); return -EINVAL; } -- cgit v1.2.3 From ab38a7b5a4493a3658d891a8e91f9ffcb3d2defb Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Tue, 6 Oct 2015 11:00:01 -0700 Subject: openvswitch: Change CT_ATTR_FLAGS to CT_ATTR_COMMIT Previously, the CT_ATTR_FLAGS attribute, when nested under the OVS_ACTION_ATTR_CT, encoded a 32-bit bitmask of flags that modify the semantics of the ct action. It's more extensible to just represent each flag as a nested attribute, and this requires no additional error checking to reject flags that aren't currently supported. Suggested-by: Ben Pfaff Signed-off-by: Joe Stringer Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 14 ++++---------- net/openvswitch/conntrack.c | 13 ++++++------- 2 files changed, 10 insertions(+), 17 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index c861a4cf5fec..036f73bc54cd 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -618,7 +618,9 @@ struct ovs_action_hash { /** * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action. - * @OVS_CT_ATTR_FLAGS: u32 connection tracking flags. + * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack + * table. This allows future packets for the same connection to be identified + * as 'established' or 'related'. * @OVS_CT_ATTR_ZONE: u16 connection tracking zone. * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection @@ -630,7 +632,7 @@ struct ovs_action_hash { */ enum ovs_ct_attr { OVS_CT_ATTR_UNSPEC, - OVS_CT_ATTR_FLAGS, /* u32 bitmask of OVS_CT_F_*. */ + OVS_CT_ATTR_COMMIT, /* No argument, commits connection. */ OVS_CT_ATTR_ZONE, /* u16 zone id. */ OVS_CT_ATTR_MARK, /* mark to associate with this connection. */ OVS_CT_ATTR_LABELS, /* labels to associate with this connection. */ @@ -641,14 +643,6 @@ enum ovs_ct_attr { #define OVS_CT_ATTR_MAX (__OVS_CT_ATTR_MAX - 1) -/* - * OVS_CT_ATTR_FLAGS flags - bitmask of %OVS_CT_F_* - * @OVS_CT_F_COMMIT: Commits the flow to the conntrack table. This allows - * future packets for the same connection to be identified as 'established' - * or 'related'. - */ -#define OVS_CT_F_COMMIT 0x01 - /** * enum ovs_action_attr - Action types. * diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 466d5576fe3f..80bf702715bb 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -47,7 +47,7 @@ struct ovs_conntrack_info { struct nf_conntrack_helper *helper; struct nf_conntrack_zone zone; struct nf_conn *ct; - u32 flags; + u8 commit : 1; u16 family; struct md_mark mark; struct md_labels labels; @@ -493,7 +493,7 @@ int ovs_ct_execute(struct net *net, struct sk_buff *skb, return err; } - if (info->flags & OVS_CT_F_COMMIT) + if (info->commit) err = ovs_ct_commit(net, key, info, skb); else err = ovs_ct_lookup(net, key, info, skb); @@ -539,8 +539,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name, } static const struct ovs_ct_len_tbl ovs_ct_attr_lens[OVS_CT_ATTR_MAX + 1] = { - [OVS_CT_ATTR_FLAGS] = { .minlen = sizeof(u32), - .maxlen = sizeof(u32) }, + [OVS_CT_ATTR_COMMIT] = { .minlen = 0, .maxlen = 0 }, [OVS_CT_ATTR_ZONE] = { .minlen = sizeof(u16), .maxlen = sizeof(u16) }, [OVS_CT_ATTR_MARK] = { .minlen = sizeof(struct md_mark), @@ -576,8 +575,8 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, } switch (type) { - case OVS_CT_ATTR_FLAGS: - info->flags = nla_get_u32(a); + case OVS_CT_ATTR_COMMIT: + info->commit = true; break; #ifdef CONFIG_NF_CONNTRACK_ZONES case OVS_CT_ATTR_ZONE: @@ -701,7 +700,7 @@ int ovs_ct_action_to_attr(const struct ovs_conntrack_info *ct_info, if (!start) return -EMSGSIZE; - if (nla_put_u32(skb, OVS_CT_ATTR_FLAGS, ct_info->flags)) + if (ct_info->commit && nla_put_flag(skb, OVS_CT_ATTR_COMMIT)) return -EMSGSIZE; if (IS_ENABLED(CONFIG_NF_CONNTRACK_ZONES) && nla_put_u16(skb, OVS_CT_ATTR_ZONE, ct_info->zone.id)) -- cgit v1.2.3 From 9d99a8dda154f38307d43d9c9aa504bd3703d596 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 2 Oct 2015 15:25:49 +0200 Subject: nvme: move hardware structures out of the uapi version of nvme.h Currently all NVMe command and completion structures are exposed to userspace through the uapi version of nvme.h. They are not an ABI between the kernel and userspace, and will change in C-incompatible way for future versions of the spec. Move them to the kernel version of the file and rename the uapi header to nvme_ioctl.h so that userspace can easily detect the presence of the new clean header. Nvme-cli already carries a local copy of the header, so it won't be affected by this move. Signed-off-by: Christoph Hellwig Acked-by: Keith Busch Signed-off-by: Jens Axboe --- drivers/block/nvme-core.c | 1 + include/linux/nvme.h | 526 ++++++++++++++++++++++++++++++++++- include/uapi/linux/nvme.h | 589 ---------------------------------------- include/uapi/linux/nvme_ioctl.h | 65 +++++ 4 files changed, 590 insertions(+), 591 deletions(-) delete mode 100644 include/uapi/linux/nvme.h create mode 100644 include/uapi/linux/nvme_ioctl.h (limited to 'include/uapi') diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c index a20f66a44b96..a526696d684d 100644 --- a/drivers/block/nvme-core.c +++ b/drivers/block/nvme-core.c @@ -42,6 +42,7 @@ #include #include +#include #include "nvme.h" #define NVME_MINORS (1U << MINORBITS) diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 364cb9adbbbc..91a805437876 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -15,8 +15,6 @@ #ifndef _LINUX_NVME_H #define _LINUX_NVME_H -#include - struct nvme_bar { __u64 cap; /* Controller Capabilities */ __u32 vs; /* Version */ @@ -73,4 +71,528 @@ enum { NVME_CSTS_SHST_MASK = 3 << 2, }; +struct nvme_id_power_state { + __le16 max_power; /* centiwatts */ + __u8 rsvd2; + __u8 flags; + __le32 entry_lat; /* microseconds */ + __le32 exit_lat; /* microseconds */ + __u8 read_tput; + __u8 read_lat; + __u8 write_tput; + __u8 write_lat; + __le16 idle_power; + __u8 idle_scale; + __u8 rsvd19; + __le16 active_power; + __u8 active_work_scale; + __u8 rsvd23[9]; +}; + +enum { + NVME_PS_FLAGS_MAX_POWER_SCALE = 1 << 0, + NVME_PS_FLAGS_NON_OP_STATE = 1 << 1, +}; + +struct nvme_id_ctrl { + __le16 vid; + __le16 ssvid; + char sn[20]; + char mn[40]; + char fr[8]; + __u8 rab; + __u8 ieee[3]; + __u8 mic; + __u8 mdts; + __u16 cntlid; + __u32 ver; + __u8 rsvd84[172]; + __le16 oacs; + __u8 acl; + __u8 aerl; + __u8 frmw; + __u8 lpa; + __u8 elpe; + __u8 npss; + __u8 avscc; + __u8 apsta; + __le16 wctemp; + __le16 cctemp; + __u8 rsvd270[242]; + __u8 sqes; + __u8 cqes; + __u8 rsvd514[2]; + __le32 nn; + __le16 oncs; + __le16 fuses; + __u8 fna; + __u8 vwc; + __le16 awun; + __le16 awupf; + __u8 nvscc; + __u8 rsvd531; + __le16 acwu; + __u8 rsvd534[2]; + __le32 sgls; + __u8 rsvd540[1508]; + struct nvme_id_power_state psd[32]; + __u8 vs[1024]; +}; + +enum { + NVME_CTRL_ONCS_COMPARE = 1 << 0, + NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, + NVME_CTRL_ONCS_DSM = 1 << 2, + NVME_CTRL_VWC_PRESENT = 1 << 0, +}; + +struct nvme_lbaf { + __le16 ms; + __u8 ds; + __u8 rp; +}; + +struct nvme_id_ns { + __le64 nsze; + __le64 ncap; + __le64 nuse; + __u8 nsfeat; + __u8 nlbaf; + __u8 flbas; + __u8 mc; + __u8 dpc; + __u8 dps; + __u8 nmic; + __u8 rescap; + __u8 fpi; + __u8 rsvd33; + __le16 nawun; + __le16 nawupf; + __le16 nacwu; + __le16 nabsn; + __le16 nabo; + __le16 nabspf; + __u16 rsvd46; + __le64 nvmcap[2]; + __u8 rsvd64[40]; + __u8 nguid[16]; + __u8 eui64[8]; + struct nvme_lbaf lbaf[16]; + __u8 rsvd192[192]; + __u8 vs[3712]; +}; + +enum { + NVME_NS_FEAT_THIN = 1 << 0, + NVME_NS_FLBAS_LBA_MASK = 0xf, + NVME_NS_FLBAS_META_EXT = 0x10, + NVME_LBAF_RP_BEST = 0, + NVME_LBAF_RP_BETTER = 1, + NVME_LBAF_RP_GOOD = 2, + NVME_LBAF_RP_DEGRADED = 3, + NVME_NS_DPC_PI_LAST = 1 << 4, + NVME_NS_DPC_PI_FIRST = 1 << 3, + NVME_NS_DPC_PI_TYPE3 = 1 << 2, + NVME_NS_DPC_PI_TYPE2 = 1 << 1, + NVME_NS_DPC_PI_TYPE1 = 1 << 0, + NVME_NS_DPS_PI_FIRST = 1 << 3, + NVME_NS_DPS_PI_MASK = 0x7, + NVME_NS_DPS_PI_TYPE1 = 1, + NVME_NS_DPS_PI_TYPE2 = 2, + NVME_NS_DPS_PI_TYPE3 = 3, +}; + +struct nvme_smart_log { + __u8 critical_warning; + __u8 temperature[2]; + __u8 avail_spare; + __u8 spare_thresh; + __u8 percent_used; + __u8 rsvd6[26]; + __u8 data_units_read[16]; + __u8 data_units_written[16]; + __u8 host_reads[16]; + __u8 host_writes[16]; + __u8 ctrl_busy_time[16]; + __u8 power_cycles[16]; + __u8 power_on_hours[16]; + __u8 unsafe_shutdowns[16]; + __u8 media_errors[16]; + __u8 num_err_log_entries[16]; + __le32 warning_temp_time; + __le32 critical_comp_time; + __le16 temp_sensor[8]; + __u8 rsvd216[296]; +}; + +enum { + NVME_SMART_CRIT_SPARE = 1 << 0, + NVME_SMART_CRIT_TEMPERATURE = 1 << 1, + NVME_SMART_CRIT_RELIABILITY = 1 << 2, + NVME_SMART_CRIT_MEDIA = 1 << 3, + NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, +}; + +enum { + NVME_AER_NOTICE_NS_CHANGED = 0x0002, +}; + +struct nvme_lba_range_type { + __u8 type; + __u8 attributes; + __u8 rsvd2[14]; + __u64 slba; + __u64 nlb; + __u8 guid[16]; + __u8 rsvd48[16]; +}; + +enum { + NVME_LBART_TYPE_FS = 0x01, + NVME_LBART_TYPE_RAID = 0x02, + NVME_LBART_TYPE_CACHE = 0x03, + NVME_LBART_TYPE_SWAP = 0x04, + + NVME_LBART_ATTRIB_TEMP = 1 << 0, + NVME_LBART_ATTRIB_HIDE = 1 << 1, +}; + +struct nvme_reservation_status { + __le32 gen; + __u8 rtype; + __u8 regctl[2]; + __u8 resv5[2]; + __u8 ptpls; + __u8 resv10[13]; + struct { + __le16 cntlid; + __u8 rcsts; + __u8 resv3[5]; + __le64 hostid; + __le64 rkey; + } regctl_ds[]; +}; + +/* I/O commands */ + +enum nvme_opcode { + nvme_cmd_flush = 0x00, + nvme_cmd_write = 0x01, + nvme_cmd_read = 0x02, + nvme_cmd_write_uncor = 0x04, + nvme_cmd_compare = 0x05, + nvme_cmd_write_zeroes = 0x08, + nvme_cmd_dsm = 0x09, + nvme_cmd_resv_register = 0x0d, + nvme_cmd_resv_report = 0x0e, + nvme_cmd_resv_acquire = 0x11, + nvme_cmd_resv_release = 0x15, +}; + +struct nvme_common_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __le32 cdw2[2]; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le32 cdw10[6]; +}; + +struct nvme_rw_command { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2; + __le64 metadata; + __le64 prp1; + __le64 prp2; + __le64 slba; + __le16 length; + __le16 control; + __le32 dsmgmt; + __le32 reftag; + __le16 apptag; + __le16 appmask; +}; + +enum { + NVME_RW_LR = 1 << 15, + NVME_RW_FUA = 1 << 14, + NVME_RW_DSM_FREQ_UNSPEC = 0, + NVME_RW_DSM_FREQ_TYPICAL = 1, + NVME_RW_DSM_FREQ_RARE = 2, + NVME_RW_DSM_FREQ_READS = 3, + NVME_RW_DSM_FREQ_WRITES = 4, + NVME_RW_DSM_FREQ_RW = 5, + NVME_RW_DSM_FREQ_ONCE = 6, + NVME_RW_DSM_FREQ_PREFETCH = 7, + NVME_RW_DSM_FREQ_TEMP = 8, + NVME_RW_DSM_LATENCY_NONE = 0 << 4, + NVME_RW_DSM_LATENCY_IDLE = 1 << 4, + NVME_RW_DSM_LATENCY_NORM = 2 << 4, + NVME_RW_DSM_LATENCY_LOW = 3 << 4, + NVME_RW_DSM_SEQ_REQ = 1 << 6, + NVME_RW_DSM_COMPRESSED = 1 << 7, + NVME_RW_PRINFO_PRCHK_REF = 1 << 10, + NVME_RW_PRINFO_PRCHK_APP = 1 << 11, + NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, + NVME_RW_PRINFO_PRACT = 1 << 13, +}; + +struct nvme_dsm_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 nr; + __le32 attributes; + __u32 rsvd12[4]; +}; + +enum { + NVME_DSMGMT_IDR = 1 << 0, + NVME_DSMGMT_IDW = 1 << 1, + NVME_DSMGMT_AD = 1 << 2, +}; + +struct nvme_dsm_range { + __le32 cattr; + __le32 nlb; + __le64 slba; +}; + +/* Admin commands */ + +enum nvme_admin_opcode { + nvme_admin_delete_sq = 0x00, + nvme_admin_create_sq = 0x01, + nvme_admin_get_log_page = 0x02, + nvme_admin_delete_cq = 0x04, + nvme_admin_create_cq = 0x05, + nvme_admin_identify = 0x06, + nvme_admin_abort_cmd = 0x08, + nvme_admin_set_features = 0x09, + nvme_admin_get_features = 0x0a, + nvme_admin_async_event = 0x0c, + nvme_admin_activate_fw = 0x10, + nvme_admin_download_fw = 0x11, + nvme_admin_format_nvm = 0x80, + nvme_admin_security_send = 0x81, + nvme_admin_security_recv = 0x82, +}; + +enum { + NVME_QUEUE_PHYS_CONTIG = (1 << 0), + NVME_CQ_IRQ_ENABLED = (1 << 1), + NVME_SQ_PRIO_URGENT = (0 << 1), + NVME_SQ_PRIO_HIGH = (1 << 1), + NVME_SQ_PRIO_MEDIUM = (2 << 1), + NVME_SQ_PRIO_LOW = (3 << 1), + NVME_FEAT_ARBITRATION = 0x01, + NVME_FEAT_POWER_MGMT = 0x02, + NVME_FEAT_LBA_RANGE = 0x03, + NVME_FEAT_TEMP_THRESH = 0x04, + NVME_FEAT_ERR_RECOVERY = 0x05, + NVME_FEAT_VOLATILE_WC = 0x06, + NVME_FEAT_NUM_QUEUES = 0x07, + NVME_FEAT_IRQ_COALESCE = 0x08, + NVME_FEAT_IRQ_CONFIG = 0x09, + NVME_FEAT_WRITE_ATOMIC = 0x0a, + NVME_FEAT_ASYNC_EVENT = 0x0b, + NVME_FEAT_AUTO_PST = 0x0c, + NVME_FEAT_SW_PROGRESS = 0x80, + NVME_FEAT_HOST_ID = 0x81, + NVME_FEAT_RESV_MASK = 0x82, + NVME_FEAT_RESV_PERSIST = 0x83, + NVME_LOG_ERROR = 0x01, + NVME_LOG_SMART = 0x02, + NVME_LOG_FW_SLOT = 0x03, + NVME_LOG_RESERVATION = 0x80, + NVME_FWACT_REPL = (0 << 3), + NVME_FWACT_REPL_ACTV = (1 << 3), + NVME_FWACT_ACTV = (2 << 3), +}; + +struct nvme_identify { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 cns; + __u32 rsvd11[5]; +}; + +struct nvme_features { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[2]; + __le64 prp1; + __le64 prp2; + __le32 fid; + __le32 dword11; + __u32 rsvd12[4]; +}; + +struct nvme_create_cq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 cqid; + __le16 qsize; + __le16 cq_flags; + __le16 irq_vector; + __u32 rsvd12[4]; +}; + +struct nvme_create_sq { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __u64 rsvd8; + __le16 sqid; + __le16 qsize; + __le16 sq_flags; + __le16 cqid; + __u32 rsvd12[4]; +}; + +struct nvme_delete_queue { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 qid; + __u16 rsvd10; + __u32 rsvd11[5]; +}; + +struct nvme_abort_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[9]; + __le16 sqid; + __u16 cid; + __u32 rsvd11[5]; +}; + +struct nvme_download_firmware { + __u8 opcode; + __u8 flags; + __u16 command_id; + __u32 rsvd1[5]; + __le64 prp1; + __le64 prp2; + __le32 numd; + __le32 offset; + __u32 rsvd12[4]; +}; + +struct nvme_format_cmd { + __u8 opcode; + __u8 flags; + __u16 command_id; + __le32 nsid; + __u64 rsvd2[4]; + __le32 cdw10; + __u32 rsvd11[5]; +}; + +struct nvme_command { + union { + struct nvme_common_command common; + struct nvme_rw_command rw; + struct nvme_identify identify; + struct nvme_features features; + struct nvme_create_cq create_cq; + struct nvme_create_sq create_sq; + struct nvme_delete_queue delete_queue; + struct nvme_download_firmware dlfw; + struct nvme_format_cmd format; + struct nvme_dsm_cmd dsm; + struct nvme_abort_cmd abort; + }; +}; + +enum { + NVME_SC_SUCCESS = 0x0, + NVME_SC_INVALID_OPCODE = 0x1, + NVME_SC_INVALID_FIELD = 0x2, + NVME_SC_CMDID_CONFLICT = 0x3, + NVME_SC_DATA_XFER_ERROR = 0x4, + NVME_SC_POWER_LOSS = 0x5, + NVME_SC_INTERNAL = 0x6, + NVME_SC_ABORT_REQ = 0x7, + NVME_SC_ABORT_QUEUE = 0x8, + NVME_SC_FUSED_FAIL = 0x9, + NVME_SC_FUSED_MISSING = 0xa, + NVME_SC_INVALID_NS = 0xb, + NVME_SC_CMD_SEQ_ERROR = 0xc, + NVME_SC_SGL_INVALID_LAST = 0xd, + NVME_SC_SGL_INVALID_COUNT = 0xe, + NVME_SC_SGL_INVALID_DATA = 0xf, + NVME_SC_SGL_INVALID_METADATA = 0x10, + NVME_SC_SGL_INVALID_TYPE = 0x11, + NVME_SC_LBA_RANGE = 0x80, + NVME_SC_CAP_EXCEEDED = 0x81, + NVME_SC_NS_NOT_READY = 0x82, + NVME_SC_RESERVATION_CONFLICT = 0x83, + NVME_SC_CQ_INVALID = 0x100, + NVME_SC_QID_INVALID = 0x101, + NVME_SC_QUEUE_SIZE = 0x102, + NVME_SC_ABORT_LIMIT = 0x103, + NVME_SC_ABORT_MISSING = 0x104, + NVME_SC_ASYNC_LIMIT = 0x105, + NVME_SC_FIRMWARE_SLOT = 0x106, + NVME_SC_FIRMWARE_IMAGE = 0x107, + NVME_SC_INVALID_VECTOR = 0x108, + NVME_SC_INVALID_LOG_PAGE = 0x109, + NVME_SC_INVALID_FORMAT = 0x10a, + NVME_SC_FIRMWARE_NEEDS_RESET = 0x10b, + NVME_SC_INVALID_QUEUE = 0x10c, + NVME_SC_FEATURE_NOT_SAVEABLE = 0x10d, + NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, + NVME_SC_FEATURE_NOT_PER_NS = 0x10f, + NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, + NVME_SC_BAD_ATTRIBUTES = 0x180, + NVME_SC_INVALID_PI = 0x181, + NVME_SC_READ_ONLY = 0x182, + NVME_SC_WRITE_FAULT = 0x280, + NVME_SC_READ_ERROR = 0x281, + NVME_SC_GUARD_CHECK = 0x282, + NVME_SC_APPTAG_CHECK = 0x283, + NVME_SC_REFTAG_CHECK = 0x284, + NVME_SC_COMPARE_FAILED = 0x285, + NVME_SC_ACCESS_DENIED = 0x286, + NVME_SC_DNR = 0x4000, +}; + +struct nvme_completion { + __le32 result; /* Used by admin commands to return data */ + __u32 rsvd; + __le16 sq_head; /* how much of this queue may be reclaimed */ + __le16 sq_id; /* submission queue that generated this entry */ + __u16 command_id; /* of the command which completed */ + __le16 status; /* did the command fail, and if so, why? */ +}; + +#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8)) + #endif /* _LINUX_NVME_H */ diff --git a/include/uapi/linux/nvme.h b/include/uapi/linux/nvme.h deleted file mode 100644 index 8864194a4151..000000000000 --- a/include/uapi/linux/nvme.h +++ /dev/null @@ -1,589 +0,0 @@ -/* - * Definitions for the NVM Express interface - * Copyright (c) 2011-2014, Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - */ - -#ifndef _UAPI_LINUX_NVME_H -#define _UAPI_LINUX_NVME_H - -#include - -struct nvme_id_power_state { - __le16 max_power; /* centiwatts */ - __u8 rsvd2; - __u8 flags; - __le32 entry_lat; /* microseconds */ - __le32 exit_lat; /* microseconds */ - __u8 read_tput; - __u8 read_lat; - __u8 write_tput; - __u8 write_lat; - __le16 idle_power; - __u8 idle_scale; - __u8 rsvd19; - __le16 active_power; - __u8 active_work_scale; - __u8 rsvd23[9]; -}; - -enum { - NVME_PS_FLAGS_MAX_POWER_SCALE = 1 << 0, - NVME_PS_FLAGS_NON_OP_STATE = 1 << 1, -}; - -struct nvme_id_ctrl { - __le16 vid; - __le16 ssvid; - char sn[20]; - char mn[40]; - char fr[8]; - __u8 rab; - __u8 ieee[3]; - __u8 mic; - __u8 mdts; - __u16 cntlid; - __u32 ver; - __u8 rsvd84[172]; - __le16 oacs; - __u8 acl; - __u8 aerl; - __u8 frmw; - __u8 lpa; - __u8 elpe; - __u8 npss; - __u8 avscc; - __u8 apsta; - __le16 wctemp; - __le16 cctemp; - __u8 rsvd270[242]; - __u8 sqes; - __u8 cqes; - __u8 rsvd514[2]; - __le32 nn; - __le16 oncs; - __le16 fuses; - __u8 fna; - __u8 vwc; - __le16 awun; - __le16 awupf; - __u8 nvscc; - __u8 rsvd531; - __le16 acwu; - __u8 rsvd534[2]; - __le32 sgls; - __u8 rsvd540[1508]; - struct nvme_id_power_state psd[32]; - __u8 vs[1024]; -}; - -enum { - NVME_CTRL_ONCS_COMPARE = 1 << 0, - NVME_CTRL_ONCS_WRITE_UNCORRECTABLE = 1 << 1, - NVME_CTRL_ONCS_DSM = 1 << 2, - NVME_CTRL_VWC_PRESENT = 1 << 0, -}; - -struct nvme_lbaf { - __le16 ms; - __u8 ds; - __u8 rp; -}; - -struct nvme_id_ns { - __le64 nsze; - __le64 ncap; - __le64 nuse; - __u8 nsfeat; - __u8 nlbaf; - __u8 flbas; - __u8 mc; - __u8 dpc; - __u8 dps; - __u8 nmic; - __u8 rescap; - __u8 fpi; - __u8 rsvd33; - __le16 nawun; - __le16 nawupf; - __le16 nacwu; - __le16 nabsn; - __le16 nabo; - __le16 nabspf; - __u16 rsvd46; - __le64 nvmcap[2]; - __u8 rsvd64[40]; - __u8 nguid[16]; - __u8 eui64[8]; - struct nvme_lbaf lbaf[16]; - __u8 rsvd192[192]; - __u8 vs[3712]; -}; - -enum { - NVME_NS_FEAT_THIN = 1 << 0, - NVME_NS_FLBAS_LBA_MASK = 0xf, - NVME_NS_FLBAS_META_EXT = 0x10, - NVME_LBAF_RP_BEST = 0, - NVME_LBAF_RP_BETTER = 1, - NVME_LBAF_RP_GOOD = 2, - NVME_LBAF_RP_DEGRADED = 3, - NVME_NS_DPC_PI_LAST = 1 << 4, - NVME_NS_DPC_PI_FIRST = 1 << 3, - NVME_NS_DPC_PI_TYPE3 = 1 << 2, - NVME_NS_DPC_PI_TYPE2 = 1 << 1, - NVME_NS_DPC_PI_TYPE1 = 1 << 0, - NVME_NS_DPS_PI_FIRST = 1 << 3, - NVME_NS_DPS_PI_MASK = 0x7, - NVME_NS_DPS_PI_TYPE1 = 1, - NVME_NS_DPS_PI_TYPE2 = 2, - NVME_NS_DPS_PI_TYPE3 = 3, -}; - -struct nvme_smart_log { - __u8 critical_warning; - __u8 temperature[2]; - __u8 avail_spare; - __u8 spare_thresh; - __u8 percent_used; - __u8 rsvd6[26]; - __u8 data_units_read[16]; - __u8 data_units_written[16]; - __u8 host_reads[16]; - __u8 host_writes[16]; - __u8 ctrl_busy_time[16]; - __u8 power_cycles[16]; - __u8 power_on_hours[16]; - __u8 unsafe_shutdowns[16]; - __u8 media_errors[16]; - __u8 num_err_log_entries[16]; - __le32 warning_temp_time; - __le32 critical_comp_time; - __le16 temp_sensor[8]; - __u8 rsvd216[296]; -}; - -enum { - NVME_SMART_CRIT_SPARE = 1 << 0, - NVME_SMART_CRIT_TEMPERATURE = 1 << 1, - NVME_SMART_CRIT_RELIABILITY = 1 << 2, - NVME_SMART_CRIT_MEDIA = 1 << 3, - NVME_SMART_CRIT_VOLATILE_MEMORY = 1 << 4, -}; - -enum { - NVME_AER_NOTICE_NS_CHANGED = 0x0002, -}; - -struct nvme_lba_range_type { - __u8 type; - __u8 attributes; - __u8 rsvd2[14]; - __u64 slba; - __u64 nlb; - __u8 guid[16]; - __u8 rsvd48[16]; -}; - -enum { - NVME_LBART_TYPE_FS = 0x01, - NVME_LBART_TYPE_RAID = 0x02, - NVME_LBART_TYPE_CACHE = 0x03, - NVME_LBART_TYPE_SWAP = 0x04, - - NVME_LBART_ATTRIB_TEMP = 1 << 0, - NVME_LBART_ATTRIB_HIDE = 1 << 1, -}; - -struct nvme_reservation_status { - __le32 gen; - __u8 rtype; - __u8 regctl[2]; - __u8 resv5[2]; - __u8 ptpls; - __u8 resv10[13]; - struct { - __le16 cntlid; - __u8 rcsts; - __u8 resv3[5]; - __le64 hostid; - __le64 rkey; - } regctl_ds[]; -}; - -/* I/O commands */ - -enum nvme_opcode { - nvme_cmd_flush = 0x00, - nvme_cmd_write = 0x01, - nvme_cmd_read = 0x02, - nvme_cmd_write_uncor = 0x04, - nvme_cmd_compare = 0x05, - nvme_cmd_write_zeroes = 0x08, - nvme_cmd_dsm = 0x09, - nvme_cmd_resv_register = 0x0d, - nvme_cmd_resv_report = 0x0e, - nvme_cmd_resv_acquire = 0x11, - nvme_cmd_resv_release = 0x15, -}; - -struct nvme_common_command { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __le32 cdw2[2]; - __le64 metadata; - __le64 prp1; - __le64 prp2; - __le32 cdw10[6]; -}; - -struct nvme_rw_command { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2; - __le64 metadata; - __le64 prp1; - __le64 prp2; - __le64 slba; - __le16 length; - __le16 control; - __le32 dsmgmt; - __le32 reftag; - __le16 apptag; - __le16 appmask; -}; - -enum { - NVME_RW_LR = 1 << 15, - NVME_RW_FUA = 1 << 14, - NVME_RW_DSM_FREQ_UNSPEC = 0, - NVME_RW_DSM_FREQ_TYPICAL = 1, - NVME_RW_DSM_FREQ_RARE = 2, - NVME_RW_DSM_FREQ_READS = 3, - NVME_RW_DSM_FREQ_WRITES = 4, - NVME_RW_DSM_FREQ_RW = 5, - NVME_RW_DSM_FREQ_ONCE = 6, - NVME_RW_DSM_FREQ_PREFETCH = 7, - NVME_RW_DSM_FREQ_TEMP = 8, - NVME_RW_DSM_LATENCY_NONE = 0 << 4, - NVME_RW_DSM_LATENCY_IDLE = 1 << 4, - NVME_RW_DSM_LATENCY_NORM = 2 << 4, - NVME_RW_DSM_LATENCY_LOW = 3 << 4, - NVME_RW_DSM_SEQ_REQ = 1 << 6, - NVME_RW_DSM_COMPRESSED = 1 << 7, - NVME_RW_PRINFO_PRCHK_REF = 1 << 10, - NVME_RW_PRINFO_PRCHK_APP = 1 << 11, - NVME_RW_PRINFO_PRCHK_GUARD = 1 << 12, - NVME_RW_PRINFO_PRACT = 1 << 13, -}; - -struct nvme_dsm_cmd { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 nr; - __le32 attributes; - __u32 rsvd12[4]; -}; - -enum { - NVME_DSMGMT_IDR = 1 << 0, - NVME_DSMGMT_IDW = 1 << 1, - NVME_DSMGMT_AD = 1 << 2, -}; - -struct nvme_dsm_range { - __le32 cattr; - __le32 nlb; - __le64 slba; -}; - -/* Admin commands */ - -enum nvme_admin_opcode { - nvme_admin_delete_sq = 0x00, - nvme_admin_create_sq = 0x01, - nvme_admin_get_log_page = 0x02, - nvme_admin_delete_cq = 0x04, - nvme_admin_create_cq = 0x05, - nvme_admin_identify = 0x06, - nvme_admin_abort_cmd = 0x08, - nvme_admin_set_features = 0x09, - nvme_admin_get_features = 0x0a, - nvme_admin_async_event = 0x0c, - nvme_admin_activate_fw = 0x10, - nvme_admin_download_fw = 0x11, - nvme_admin_format_nvm = 0x80, - nvme_admin_security_send = 0x81, - nvme_admin_security_recv = 0x82, -}; - -enum { - NVME_QUEUE_PHYS_CONTIG = (1 << 0), - NVME_CQ_IRQ_ENABLED = (1 << 1), - NVME_SQ_PRIO_URGENT = (0 << 1), - NVME_SQ_PRIO_HIGH = (1 << 1), - NVME_SQ_PRIO_MEDIUM = (2 << 1), - NVME_SQ_PRIO_LOW = (3 << 1), - NVME_FEAT_ARBITRATION = 0x01, - NVME_FEAT_POWER_MGMT = 0x02, - NVME_FEAT_LBA_RANGE = 0x03, - NVME_FEAT_TEMP_THRESH = 0x04, - NVME_FEAT_ERR_RECOVERY = 0x05, - NVME_FEAT_VOLATILE_WC = 0x06, - NVME_FEAT_NUM_QUEUES = 0x07, - NVME_FEAT_IRQ_COALESCE = 0x08, - NVME_FEAT_IRQ_CONFIG = 0x09, - NVME_FEAT_WRITE_ATOMIC = 0x0a, - NVME_FEAT_ASYNC_EVENT = 0x0b, - NVME_FEAT_AUTO_PST = 0x0c, - NVME_FEAT_SW_PROGRESS = 0x80, - NVME_FEAT_HOST_ID = 0x81, - NVME_FEAT_RESV_MASK = 0x82, - NVME_FEAT_RESV_PERSIST = 0x83, - NVME_LOG_ERROR = 0x01, - NVME_LOG_SMART = 0x02, - NVME_LOG_FW_SLOT = 0x03, - NVME_LOG_RESERVATION = 0x80, - NVME_FWACT_REPL = (0 << 3), - NVME_FWACT_REPL_ACTV = (1 << 3), - NVME_FWACT_ACTV = (2 << 3), -}; - -struct nvme_identify { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 cns; - __u32 rsvd11[5]; -}; - -struct nvme_features { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[2]; - __le64 prp1; - __le64 prp2; - __le32 fid; - __le32 dword11; - __u32 rsvd12[4]; -}; - -struct nvme_create_cq { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __u64 rsvd8; - __le16 cqid; - __le16 qsize; - __le16 cq_flags; - __le16 irq_vector; - __u32 rsvd12[4]; -}; - -struct nvme_create_sq { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __u64 rsvd8; - __le16 sqid; - __le16 qsize; - __le16 sq_flags; - __le16 cqid; - __u32 rsvd12[4]; -}; - -struct nvme_delete_queue { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[9]; - __le16 qid; - __u16 rsvd10; - __u32 rsvd11[5]; -}; - -struct nvme_abort_cmd { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[9]; - __le16 sqid; - __u16 cid; - __u32 rsvd11[5]; -}; - -struct nvme_download_firmware { - __u8 opcode; - __u8 flags; - __u16 command_id; - __u32 rsvd1[5]; - __le64 prp1; - __le64 prp2; - __le32 numd; - __le32 offset; - __u32 rsvd12[4]; -}; - -struct nvme_format_cmd { - __u8 opcode; - __u8 flags; - __u16 command_id; - __le32 nsid; - __u64 rsvd2[4]; - __le32 cdw10; - __u32 rsvd11[5]; -}; - -struct nvme_command { - union { - struct nvme_common_command common; - struct nvme_rw_command rw; - struct nvme_identify identify; - struct nvme_features features; - struct nvme_create_cq create_cq; - struct nvme_create_sq create_sq; - struct nvme_delete_queue delete_queue; - struct nvme_download_firmware dlfw; - struct nvme_format_cmd format; - struct nvme_dsm_cmd dsm; - struct nvme_abort_cmd abort; - }; -}; - -enum { - NVME_SC_SUCCESS = 0x0, - NVME_SC_INVALID_OPCODE = 0x1, - NVME_SC_INVALID_FIELD = 0x2, - NVME_SC_CMDID_CONFLICT = 0x3, - NVME_SC_DATA_XFER_ERROR = 0x4, - NVME_SC_POWER_LOSS = 0x5, - NVME_SC_INTERNAL = 0x6, - NVME_SC_ABORT_REQ = 0x7, - NVME_SC_ABORT_QUEUE = 0x8, - NVME_SC_FUSED_FAIL = 0x9, - NVME_SC_FUSED_MISSING = 0xa, - NVME_SC_INVALID_NS = 0xb, - NVME_SC_CMD_SEQ_ERROR = 0xc, - NVME_SC_SGL_INVALID_LAST = 0xd, - NVME_SC_SGL_INVALID_COUNT = 0xe, - NVME_SC_SGL_INVALID_DATA = 0xf, - NVME_SC_SGL_INVALID_METADATA = 0x10, - NVME_SC_SGL_INVALID_TYPE = 0x11, - NVME_SC_LBA_RANGE = 0x80, - NVME_SC_CAP_EXCEEDED = 0x81, - NVME_SC_NS_NOT_READY = 0x82, - NVME_SC_RESERVATION_CONFLICT = 0x83, - NVME_SC_CQ_INVALID = 0x100, - NVME_SC_QID_INVALID = 0x101, - NVME_SC_QUEUE_SIZE = 0x102, - NVME_SC_ABORT_LIMIT = 0x103, - NVME_SC_ABORT_MISSING = 0x104, - NVME_SC_ASYNC_LIMIT = 0x105, - NVME_SC_FIRMWARE_SLOT = 0x106, - NVME_SC_FIRMWARE_IMAGE = 0x107, - NVME_SC_INVALID_VECTOR = 0x108, - NVME_SC_INVALID_LOG_PAGE = 0x109, - NVME_SC_INVALID_FORMAT = 0x10a, - NVME_SC_FIRMWARE_NEEDS_RESET = 0x10b, - NVME_SC_INVALID_QUEUE = 0x10c, - NVME_SC_FEATURE_NOT_SAVEABLE = 0x10d, - NVME_SC_FEATURE_NOT_CHANGEABLE = 0x10e, - NVME_SC_FEATURE_NOT_PER_NS = 0x10f, - NVME_SC_FW_NEEDS_RESET_SUBSYS = 0x110, - NVME_SC_BAD_ATTRIBUTES = 0x180, - NVME_SC_INVALID_PI = 0x181, - NVME_SC_READ_ONLY = 0x182, - NVME_SC_WRITE_FAULT = 0x280, - NVME_SC_READ_ERROR = 0x281, - NVME_SC_GUARD_CHECK = 0x282, - NVME_SC_APPTAG_CHECK = 0x283, - NVME_SC_REFTAG_CHECK = 0x284, - NVME_SC_COMPARE_FAILED = 0x285, - NVME_SC_ACCESS_DENIED = 0x286, - NVME_SC_DNR = 0x4000, -}; - -struct nvme_completion { - __le32 result; /* Used by admin commands to return data */ - __u32 rsvd; - __le16 sq_head; /* how much of this queue may be reclaimed */ - __le16 sq_id; /* submission queue that generated this entry */ - __u16 command_id; /* of the command which completed */ - __le16 status; /* did the command fail, and if so, why? */ -}; - -struct nvme_user_io { - __u8 opcode; - __u8 flags; - __u16 control; - __u16 nblocks; - __u16 rsvd; - __u64 metadata; - __u64 addr; - __u64 slba; - __u32 dsmgmt; - __u32 reftag; - __u16 apptag; - __u16 appmask; -}; - -struct nvme_passthru_cmd { - __u8 opcode; - __u8 flags; - __u16 rsvd1; - __u32 nsid; - __u32 cdw2; - __u32 cdw3; - __u64 metadata; - __u64 addr; - __u32 metadata_len; - __u32 data_len; - __u32 cdw10; - __u32 cdw11; - __u32 cdw12; - __u32 cdw13; - __u32 cdw14; - __u32 cdw15; - __u32 timeout_ms; - __u32 result; -}; - -#define NVME_VS(major, minor) (((major) << 16) | ((minor) << 8)) - -#define nvme_admin_cmd nvme_passthru_cmd - -#define NVME_IOCTL_ID _IO('N', 0x40) -#define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) -#define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) -#define NVME_IOCTL_IO_CMD _IOWR('N', 0x43, struct nvme_passthru_cmd) -#define NVME_IOCTL_RESET _IO('N', 0x44) -#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45) - -#endif /* _UAPI_LINUX_NVME_H */ diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h new file mode 100644 index 000000000000..c4b2a3f90829 --- /dev/null +++ b/include/uapi/linux/nvme_ioctl.h @@ -0,0 +1,65 @@ +/* + * Definitions for the NVM Express ioctl interface + * Copyright (c) 2011-2014, Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _UAPI_LINUX_NVME_IOCTL_H +#define _UAPI_LINUX_NVME_IOCTL_H + +#include + +struct nvme_user_io { + __u8 opcode; + __u8 flags; + __u16 control; + __u16 nblocks; + __u16 rsvd; + __u64 metadata; + __u64 addr; + __u64 slba; + __u32 dsmgmt; + __u32 reftag; + __u16 apptag; + __u16 appmask; +}; + +struct nvme_passthru_cmd { + __u8 opcode; + __u8 flags; + __u16 rsvd1; + __u32 nsid; + __u32 cdw2; + __u32 cdw3; + __u64 metadata; + __u64 addr; + __u32 metadata_len; + __u32 data_len; + __u32 cdw10; + __u32 cdw11; + __u32 cdw12; + __u32 cdw13; + __u32 cdw14; + __u32 cdw15; + __u32 timeout_ms; + __u32 result; +}; + +#define nvme_admin_cmd nvme_passthru_cmd + +#define NVME_IOCTL_ID _IO('N', 0x40) +#define NVME_IOCTL_ADMIN_CMD _IOWR('N', 0x41, struct nvme_admin_cmd) +#define NVME_IOCTL_SUBMIT_IO _IOW('N', 0x42, struct nvme_user_io) +#define NVME_IOCTL_IO_CMD _IOWR('N', 0x43, struct nvme_passthru_cmd) +#define NVME_IOCTL_RESET _IO('N', 0x44) +#define NVME_IOCTL_SUBSYS_RESET _IO('N', 0x45) + +#endif /* _UAPI_LINUX_NVME_IOCTL_H */ -- cgit v1.2.3 From 3c462c880b52aae2cfbbb8db8b401eef118cc128 Mon Sep 17 00:00:00 2001 From: Goldwyn Rodrigues Date: Wed, 19 Aug 2015 07:35:54 +1000 Subject: md: Increment version for clustered bitmaps Add BITMAP_MAJOR_CLUSTERED as 5, in order to prevent older kernels to assemble a clustered device. In order to maximize compatibility, the major version is set to BITMAP_MAJOR_CLUSTERED *only* if the bitmap is clustered. Added MD_FEATURE_CLUSTERED in order to return error for older kernels which would assemble MD even if the bitmap is corrupted. Signed-off-by: Goldwyn Rodrigues Signed-off-by: NeilBrown --- drivers/md/bitmap.c | 10 ++++------ drivers/md/bitmap.h | 2 ++ drivers/md/md.c | 3 +++ include/uapi/linux/raid/md_p.h | 2 ++ 4 files changed, 11 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c index 48b5890c28e3..e9d3ee703e6d 100644 --- a/drivers/md/bitmap.c +++ b/drivers/md/bitmap.c @@ -613,12 +613,10 @@ re_read: daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ; write_behind = le32_to_cpu(sb->write_behind); sectors_reserved = le32_to_cpu(sb->sectors_reserved); - /* XXX: This is a hack to ensure that we don't use clustering - * in case: - * - dm-raid is in use and - * - the nodes written in bitmap_sb is erroneous. + /* Setup nodes/clustername only if bitmap version is + * cluster-compatible */ - if (!bitmap->mddev->sync_super) { + if (sb->version == cpu_to_le32(BITMAP_MAJOR_CLUSTERED)) { nodes = le32_to_cpu(sb->nodes); strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64); @@ -628,7 +626,7 @@ re_read: if (sb->magic != cpu_to_le32(BITMAP_MAGIC)) reason = "bad magic"; else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO || - le32_to_cpu(sb->version) > BITMAP_MAJOR_HI) + le32_to_cpu(sb->version) > BITMAP_MAJOR_CLUSTERED) reason = "unrecognized superblock version"; else if (chunksize < 512) reason = "bitmap chunksize too small"; diff --git a/drivers/md/bitmap.h b/drivers/md/bitmap.h index f1f4dd01090d..8731fa06855f 100644 --- a/drivers/md/bitmap.h +++ b/drivers/md/bitmap.h @@ -9,8 +9,10 @@ #define BITMAP_MAJOR_LO 3 /* version 4 insists the bitmap is in little-endian order * with version 3, it is host-endian which is non-portable + * Version 5 is currently set only for clustered devices */ #define BITMAP_MAJOR_HI 4 +#define BITMAP_MAJOR_CLUSTERED 5 #define BITMAP_MAJOR_HOSTENDIAN 3 /* diff --git a/drivers/md/md.c b/drivers/md/md.c index c702de18207a..1e1bdd86f40c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1735,6 +1735,9 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) } } + if (mddev_is_clustered(mddev)) + sb->feature_map |= cpu_to_le32(MD_FEATURE_CLUSTERED); + if (rdev->badblocks.count == 0) /* Nothing to do for bad blocks*/ ; else if (sb->bblog_offset == 0) diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 2ae6131e69a5..867ee874fa80 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -302,6 +302,7 @@ struct mdp_superblock_1 { #define MD_FEATURE_RECOVERY_BITMAP 128 /* recovery that is happening * is guided by bitmap. */ +#define MD_FEATURE_CLUSTERED 256 /* clustered MD */ #define MD_FEATURE_ALL (MD_FEATURE_BITMAP_OFFSET \ |MD_FEATURE_RECOVERY_OFFSET \ |MD_FEATURE_RESHAPE_ACTIVE \ @@ -310,6 +311,7 @@ struct mdp_superblock_1 { |MD_FEATURE_RESHAPE_BACKWARDS \ |MD_FEATURE_NEW_OFFSET \ |MD_FEATURE_RECOVERY_BITMAP \ + |MD_FEATURE_CLUSTERED \ ) #endif -- cgit v1.2.3 From ae2ee627dc87a70910de91b791b3cd0e9c6facdd Mon Sep 17 00:00:00 2001 From: Matt Fleming Date: Tue, 25 Aug 2015 16:32:55 +0100 Subject: efifb: Add support for 64-bit frame buffer addresses The EFI Graphics Output Protocol uses 64-bit frame buffer addresses but these get truncated to 32-bit by the EFI boot stub when storing the address in the 'lfb_base' field of 'struct screen_info'. Add a 'ext_lfb_base' field for the upper 32-bits of the frame buffer address and set VIDEO_TYPE_CAPABILITY_64BIT_BASE when the field is useable. It turns out that the reason no one has required this support so far is that there's actually code in tianocore to "downgrade" PCI resources that have option ROMs and 64-bit BARS from 64-bit to 32-bit to cope with legacy option ROMs that can't handle 64-bit addresses. The upshot is that basically all GOP devices in the wild use a 32-bit frame buffer address. Still, it is possible to build firmware that uses a full 64-bit GOP frame buffer address. Chad did, which led to him reporting this issue. Add support in anticipation of GOP devices using 64-bit addresses more widely, and so that efifb works out of the box when that happens. Reported-by: Chad Page Cc: Pete Hawkins Acked-by: Peter Jones Cc: Matthew Garrett Cc: Geert Uytterhoeven Signed-off-by: Matt Fleming --- arch/x86/boot/compressed/eboot.c | 24 ++++++++++++++++++++---- drivers/video/fbdev/efifb.c | 24 +++++++++++++++++++++++- include/uapi/linux/screen_info.h | 5 +++-- 3 files changed, 46 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c index 7d69afd8b6fa..43473bb86ac0 100644 --- a/arch/x86/boot/compressed/eboot.c +++ b/arch/x86/boot/compressed/eboot.c @@ -624,7 +624,7 @@ setup_pixel_info(struct screen_info *si, u32 pixels_per_scan_line, static efi_status_t __gop_query32(struct efi_graphics_output_protocol_32 *gop32, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_32 *mode; efi_status_t status; @@ -650,7 +650,8 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -713,6 +714,13 @@ setup_gop32(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); @@ -727,7 +735,7 @@ out: static efi_status_t __gop_query64(struct efi_graphics_output_protocol_64 *gop64, struct efi_graphics_output_mode_info **info, - unsigned long *size, u32 *fb_base) + unsigned long *size, u64 *fb_base) { struct efi_graphics_output_protocol_mode_64 *mode; efi_status_t status; @@ -753,7 +761,8 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, unsigned long nr_gops; u16 width, height; u32 pixels_per_scan_line; - u32 fb_base; + u32 ext_lfb_base; + u64 fb_base; struct efi_pixel_bitmask pixel_info; int pixel_format; efi_status_t status; @@ -816,6 +825,13 @@ setup_gop64(struct screen_info *si, efi_guid_t *proto, si->lfb_width = width; si->lfb_height = height; si->lfb_base = fb_base; + + ext_lfb_base = (u64)(unsigned long)fb_base >> 32; + if (ext_lfb_base) { + si->capabilities |= VIDEO_CAPABILITY_64BIT_BASE; + si->ext_lfb_base = ext_lfb_base; + } + si->pages = 1; setup_pixel_info(si, pixels_per_scan_line, pixel_info, pixel_format); diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c index 4bfff349b1fb..95d293b7445a 100644 --- a/drivers/video/fbdev/efifb.c +++ b/drivers/video/fbdev/efifb.c @@ -114,6 +114,20 @@ static int efifb_setup(char *options) return 0; } +static inline bool fb_base_is_valid(void) +{ + if (screen_info.lfb_base) + return true; + + if (!(screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)) + return false; + + if (screen_info.ext_lfb_base) + return true; + + return false; +} + static int efifb_probe(struct platform_device *dev) { struct fb_info *info; @@ -141,7 +155,7 @@ static int efifb_probe(struct platform_device *dev) screen_info.lfb_depth = 32; if (!screen_info.pages) screen_info.pages = 1; - if (!screen_info.lfb_base) { + if (!fb_base_is_valid()) { printk(KERN_DEBUG "efifb: invalid framebuffer address\n"); return -ENODEV; } @@ -160,6 +174,14 @@ static int efifb_probe(struct platform_device *dev) } efifb_fix.smem_start = screen_info.lfb_base; + + if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) { + u64 ext_lfb_base; + + ext_lfb_base = (u64)(unsigned long)screen_info.ext_lfb_base << 32; + efifb_fix.smem_start |= ext_lfb_base; + } + efifb_defined.bits_per_pixel = screen_info.lfb_depth; efifb_defined.xres = screen_info.lfb_width; efifb_defined.yres = screen_info.lfb_height; diff --git a/include/uapi/linux/screen_info.h b/include/uapi/linux/screen_info.h index 7530e7447620..8b8d39dfb67f 100644 --- a/include/uapi/linux/screen_info.h +++ b/include/uapi/linux/screen_info.h @@ -43,7 +43,8 @@ struct screen_info { __u16 pages; /* 0x32 */ __u16 vesa_attributes; /* 0x34 */ __u32 capabilities; /* 0x36 */ - __u8 _reserved[6]; /* 0x3a */ + __u32 ext_lfb_base; /* 0x3a */ + __u8 _reserved[2]; /* 0x3e */ } __attribute__((packed)); #define VIDEO_TYPE_MDA 0x10 /* Monochrome Text Display */ @@ -69,6 +70,6 @@ struct screen_info { #define VIDEO_FLAGS_NOCURSOR (1 << 0) /* The video mode has no cursor set */ #define VIDEO_CAPABILITY_SKIP_QUIRKS (1 << 0) - +#define VIDEO_CAPABILITY_64BIT_BASE (1 << 1) /* Frame buffer base is 64-bit */ #endif /* _UAPI_SCREEN_INFO_H */ -- cgit v1.2.3 From c9692657c0321fec7bcb3ca8c6db56c08c640ace Mon Sep 17 00:00:00 2001 From: Manjeet Pawar Date: Fri, 9 Oct 2015 15:59:40 +0530 Subject: arm64: Fix MINSIGSTKSZ and SIGSTKSZ MINSIGSTKSZ and SIGSTKSZ for ARM64 are not correctly set in latest kernel. This patch fixes this issue. This issue is reported in LTP (testcase: sigaltstack02.c). Testcase failed when sigaltstack() called with stack size "MINSIGSTKSZ - 1" Since in Glibc-2.22, MINSIGSTKSZ is set to 5120 but in kernel it is set to 2048 so testcase gets failed. Testcase Output: sigaltstack02 1 TPASS : stgaltstack() fails, Invalid Flag value,errno:22 sigaltstack02 2 TFAIL : sigaltstack() returned 0, expected -1,errno:12 Reported Issue in Glibc Bugzilla: Bugfix in Glibc-2.22: [Bug 16850] https://sourceware.org/bugzilla/show_bug.cgi?id=16850 Acked-by: Arnd Bergmann Signed-off-by: Akhilesh Kumar Signed-off-by: Manjeet Pawar Signed-off-by: Rohit Thapliyal Signed-off-by: Will Deacon --- arch/arm64/include/uapi/asm/signal.h | 3 +++ include/uapi/asm-generic/signal.h | 2 ++ 2 files changed, 5 insertions(+) (limited to 'include/uapi') diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 8d1e7236431b..991bf5db2ca1 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -19,6 +19,9 @@ /* Required for AArch32 compatibility. */ #define SA_RESTORER 0x04000000 +#define MINSIGSTKSZ 5120 +#define SIGSTKSZ 16384 + #include #endif diff --git a/include/uapi/asm-generic/signal.h b/include/uapi/asm-generic/signal.h index 9df61f1edb0f..3094618d382f 100644 --- a/include/uapi/asm-generic/signal.h +++ b/include/uapi/asm-generic/signal.h @@ -80,8 +80,10 @@ * SA_RESTORER 0x04000000 */ +#if !defined MINSIGSTKSZ || !defined SIGSTKSZ #define MINSIGSTKSZ 2048 #define SIGSTKSZ 8192 +#endif #ifndef __ASSEMBLY__ typedef struct { -- cgit v1.2.3 From e844463743095bc8b230f507de066d047c87476b Mon Sep 17 00:00:00 2001 From: "Arad, Ronen" Date: Fri, 9 Oct 2015 10:35:47 -0700 Subject: rtnetlink: fix gcc -Wconversion warning RTA_ALIGNTO is currently define as 4. It has to be 4U to prevent warning for RTA_ALIGN and RTA_DATA expansions when -Wconversion gcc option is enabled. This follows NLMSG_ALIGNTO definition in . Signed-off-by: Ronen Arad Signed-off-by: David S. Miller --- include/uapi/linux/rtnetlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 702024769c74..9d8f5d10c1e5 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -160,7 +160,7 @@ struct rtattr { /* Macros to handle rtattributes */ -#define RTA_ALIGNTO 4 +#define RTA_ALIGNTO 4U #define RTA_ALIGN(len) ( ((len)+RTA_ALIGNTO-1) & ~(RTA_ALIGNTO-1) ) #define RTA_OK(rta,len) ((len) >= (int)sizeof(struct rtattr) && \ (rta)->rta_len >= sizeof(struct rtattr) && \ -- cgit v1.2.3 From 6e19bc4b7091ffd26586100eee78232b44427ec7 Mon Sep 17 00:00:00 2001 From: Dmitry Shmidt Date: Wed, 7 Oct 2015 11:32:53 +0200 Subject: nl80211: allow BSS data to include CLOCK_BOOTTIME timestamp For location and connectivity services, userspace would often like to know the time when the BSS was last seen. The current "last seen" value is calculated in a way that makes it less useful, especially if the system suspended in the meantime. Add the ability for the driver to report a real CLOCK_BOOTTIME stamp that can then be reported to userspace (if present). Drivers wishing to use this must be converted to the new API to call cfg80211_inform_bss_data() or cfg80211_inform_bss_frame_data(). They need to ensure the reported value is accurate enough even when the frame might have been buffered in the device (e.g. firmware.) Signed-off-by: Dmitry Shmidt [modified to use struct, inlines] Signed-off-by: Johannes Berg --- Documentation/DocBook/80211.tmpl | 5 ++- include/net/cfg80211.h | 95 ++++++++++++++++++++++++++++++++-------- include/uapi/linux/nl80211.h | 4 ++ net/wireless/core.h | 1 + net/wireless/nl80211.c | 5 +++ net/wireless/scan.c | 58 ++++++++++++------------ net/wireless/trace.h | 22 +++++----- 7 files changed, 130 insertions(+), 60 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index aac9357d4866..f9b9ad7894f5 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -154,8 +154,9 @@ !Finclude/net/cfg80211.h cfg80211_scan_request !Finclude/net/cfg80211.h cfg80211_scan_done !Finclude/net/cfg80211.h cfg80211_bss -!Finclude/net/cfg80211.h cfg80211_inform_bss_width_frame -!Finclude/net/cfg80211.h cfg80211_inform_bss_width +!Finclude/net/cfg80211.h cfg80211_inform_bss +!Finclude/net/cfg80211.h cfg80211_inform_bss_frame_data +!Finclude/net/cfg80211.h cfg80211_inform_bss_data !Finclude/net/cfg80211.h cfg80211_unlink_bss !Finclude/net/cfg80211.h cfg80211_find_ie !Finclude/net/cfg80211.h ieee80211_bss_get_ie diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 90332a1838cc..7f1e9ee844e2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1575,6 +1575,26 @@ enum cfg80211_signal_type { CFG80211_SIGNAL_TYPE_UNSPEC, }; +/** + * struct cfg80211_inform_bss - BSS inform data + * @chan: channel the frame was received on + * @scan_width: scan width that was used + * @signal: signal strength value, according to the wiphy's + * signal type + * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was + * received; should match the time when the frame was actually + * received by the device (not just by the host, in case it was + * buffered on the device) and be accurate to about 10ms. + * If the frame isn't buffered, just passing the return value of + * ktime_get_boot_ns() is likely appropriate. + */ +struct cfg80211_inform_bss { + struct ieee80211_channel *chan; + enum nl80211_bss_scan_width scan_width; + s32 signal; + u64 boottime_ns; +}; + /** * struct cfg80211_bss_ie_data - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs @@ -3958,14 +3978,11 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy); void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); /** - * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame - * + * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @mgmt: the management frame (probe response or beacon) * @len: length of the management frame - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -3975,11 +3992,26 @@ void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, @@ -3987,9 +4019,13 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width_frame(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, - mgmt, len, signal, gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); } /** @@ -4006,11 +4042,10 @@ enum cfg80211_bss_frame_type { }; /** - * cfg80211_inform_bss_width - inform cfg80211 of a new BSS + * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) @@ -4018,7 +4053,6 @@ enum cfg80211_bss_frame_type { * @beacon_interval: the beacon interval announced by the peer * @ie: additional IEs sent by the peer * @ielen: length of the additional IEs - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -4028,13 +4062,32 @@ enum cfg80211_bss_frame_type { * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, @@ -4044,11 +4097,15 @@ cfg80211_inform_bss(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, ftype, - bssid, tsf, capability, - beacon_interval, ie, ielen, signal, - gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); } struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c0ab6b0a3919..5dadb844fe18 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3364,6 +3364,9 @@ enum nl80211_bss_scan_width { * (not present if no beacon frame has been received yet) * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and * @NL80211_BSS_TSF is known to be from a probe response (flag attribute) + * @NL80211_BSS_LAST_SEEN_BOOTTIME: CLOCK_BOOTTIME timestamp when this entry + * was last updated by a received frame. The value is expected to be + * accurate to about 10ms. (u64, nanoseconds) * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -3383,6 +3386,7 @@ enum nl80211_bss { NL80211_BSS_CHAN_WIDTH, NL80211_BSS_BEACON_TSF, NL80211_BSS_PRESP_DATA, + NL80211_BSS_LAST_SEEN_BOOTTIME, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/core.h b/net/wireless/core.h index b9d5bc8c148d..a618b4b86fa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -137,6 +137,7 @@ struct cfg80211_internal_bss { struct list_head list; struct list_head hidden_list; struct rb_node rbn; + u64 ts_boottime; unsigned long ts; unsigned long refcount; atomic_t hold; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f05ba8b7af61..fb0712b3d9cb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6605,6 +6605,11 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, jiffies_to_msecs(jiffies - intbss->ts))) goto nla_put_failure; + if (intbss->ts_boottime && + nla_put_u64(msg, NL80211_BSS_LAST_SEEN_BOOTTIME, + intbss->ts_boottime)) + goto nla_put_failure; + switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3a50aa2553bf..3feaa03aa046 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -839,6 +839,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, found->pub.signal = tmp->pub.signal; found->pub.capability = tmp->pub.capability; found->ts = tmp->ts; + found->ts_boottime = tmp->ts_boottime; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -938,14 +939,13 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } /* Returned bss is reference counted and must be cleaned up appropriately. */ -struct cfg80211_bss* -cfg80211_inform_bss_width(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - enum cfg80211_bss_frame_type ftype, - const u8 *bssid, u64 tsf, u16 capability, - u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp) +struct cfg80211_bss * +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp) { struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; @@ -957,19 +957,21 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, rx_channel); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); if (!channel) return NULL; memcpy(tmp.pub.bssid, bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = beacon_interval; tmp.pub.capability = capability; + tmp.ts_boottime = data->boottime_ns; + /* * If we do not know here whether the IEs are from a Beacon or Probe * Response frame, we need to pick one of the options and only use it @@ -999,7 +1001,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1019,15 +1021,15 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width); +EXPORT_SYMBOL(cfg80211_inform_bss_data); -/* Returned bss is reference counted and must be cleaned up appropriately. */ +/* cfg80211_inform_bss_width_frame helper */ struct cfg80211_bss * -cfg80211_inform_bss_width_frame(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp) +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp) + { struct cfg80211_internal_bss tmp = {}, *res; struct cfg80211_bss_ies *ies; @@ -1040,8 +1042,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != offsetof(struct ieee80211_mgmt, u.beacon.variable)); - trace_cfg80211_inform_bss_width_frame(wiphy, rx_channel, scan_width, mgmt, - len, signal); + trace_cfg80211_inform_bss_frame(wiphy, data, mgmt, len); if (WARN_ON(!mgmt)) return NULL; @@ -1050,14 +1051,14 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, rx_channel); + ielen, data->chan); if (!channel) return NULL; @@ -1077,12 +1078,13 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + tmp.ts_boottime = data->boottime_ns; - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1102,7 +1104,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width_frame); +EXPORT_SYMBOL(cfg80211_inform_bss_frame_data); void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a808279a432a..0c392d36781b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2670,30 +2670,30 @@ TRACE_EVENT(cfg80211_get_bss, __entry->privacy) ); -TRACE_EVENT(cfg80211_inform_bss_width_frame, - TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal), - TP_ARGS(wiphy, channel, scan_width, mgmt, len, signal), +TRACE_EVENT(cfg80211_inform_bss_frame, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len), + TP_ARGS(wiphy, data, mgmt, len), TP_STRUCT__entry( WIPHY_ENTRY CHAN_ENTRY __field(enum nl80211_bss_scan_width, scan_width) __dynamic_array(u8, mgmt, len) __field(s32, signal) + __field(u64, ts_boottime) ), TP_fast_assign( WIPHY_ASSIGN; - CHAN_ASSIGN(channel); - __entry->scan_width = scan_width; + CHAN_ASSIGN(data->chan); + __entry->scan_width = data->scan_width; if (mgmt) memcpy(__get_dynamic_array(mgmt), mgmt, len); - __entry->signal = signal; + __entry->signal = data->signal; + __entry->ts_boottime = data->boottime_ns; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d", + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d, tsb:%llu", WIPHY_PR_ARG, CHAN_PR_ARG, __entry->scan_width, - __entry->signal) + __entry->signal, (unsigned long long)__entry->ts_boottime) ); DECLARE_EVENT_CLASS(cfg80211_bss_evt, -- cgit v1.2.3 From 3b06d277957c7af705a9c0cdda4b371759efb717 Mon Sep 17 00:00:00 2001 From: Avraham Stern Date: Mon, 12 Oct 2015 09:51:34 +0300 Subject: cfg80211: Add multiple scan plans for scheduled scan Add the option to configure multiple 'scan plans' for scheduled scan. Each 'scan plan' defines the number of scan cycles and the interval between scans. The scan plans are executed in the order they were configured. The last scan plan will always run infinitely and thus defines only the interval between scans. The maximum number of scan plans supported by the device and the maximum number of iterations in a single scan plan are advertised to userspace so it can configure the scan plans appropriately. When scheduled scan results are received there is no way to know which scan plan is being currently executed, so there is no way to know when the next scan iteration will start. This is not a problem, however. The scan start timestamp is only used for flushing old scan results, and there is no difference between flushing all results received until the end of the previous iteration or the start of the current one, since no results will be received in between. Signed-off-by: Avraham Stern Signed-off-by: Luca Coelho Signed-off-by: Johannes Berg --- drivers/net/wireless/ath/ath6kl/cfg80211.c | 2 +- drivers/net/wireless/iwlwifi/mvm/ops.c | 1 + drivers/net/wireless/iwlwifi/mvm/scan.c | 4 +- drivers/net/wireless/ti/wl12xx/scan.c | 3 +- drivers/net/wireless/ti/wl18xx/scan.c | 8 +- include/net/cfg80211.h | 31 ++++- include/uapi/linux/nl80211.h | 53 ++++++++- net/wireless/core.c | 3 + net/wireless/nl80211.c | 179 ++++++++++++++++++++++++++--- net/wireless/scan.c | 3 +- 10 files changed, 262 insertions(+), 25 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c index a511ef3614b9..3fda750db2a9 100644 --- a/drivers/net/wireless/ath/ath6kl/cfg80211.c +++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c @@ -3312,7 +3312,7 @@ static int ath6kl_cfg80211_sscan_start(struct wiphy *wiphy, } /* fw uses seconds, also make sure that it's >0 */ - interval = max_t(u16, 1, request->interval / 1000); + interval = max_t(u16, 1, request->scan_plans[0].interval); ath6kl_wmi_scanparams_cmd(ar->wmi, vif->fw_vif_idx, interval, interval, diff --git a/drivers/net/wireless/iwlwifi/mvm/ops.c b/drivers/net/wireless/iwlwifi/mvm/ops.c index 064c100e45fe..f0728b784edb 100644 --- a/drivers/net/wireless/iwlwifi/mvm/ops.c +++ b/drivers/net/wireless/iwlwifi/mvm/ops.c @@ -629,6 +629,7 @@ static void iwl_op_mode_mvm_stop(struct iwl_op_mode *op_mode) kfree(mvm->d3_resume_sram); if (mvm->nd_config) { kfree(mvm->nd_config->match_sets); + kfree(mvm->nd_config->scan_plans); kfree(mvm->nd_config); mvm->nd_config = NULL; } diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c index 4a1f9af63bf0..cee4f267ca66 100644 --- a/drivers/net/wireless/iwlwifi/mvm/scan.c +++ b/drivers/net/wireless/iwlwifi/mvm/scan.c @@ -1271,12 +1271,12 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm, params.type = iwl_mvm_get_scan_type(mvm, vif, ¶ms); - if (req->interval > U16_MAX) { + if (req->scan_plans[0].interval > U16_MAX) { IWL_DEBUG_SCAN(mvm, "interval value is > 16-bits, set to max possible\n"); params.interval = U16_MAX; } else { - params.interval = req->interval / MSEC_PER_SEC; + params.interval = req->scan_plans[0].interval; } /* In theory, LMAC scans can handle a 32-bit delay, but since diff --git a/drivers/net/wireless/ti/wl12xx/scan.c b/drivers/net/wireless/ti/wl12xx/scan.c index 7c355fff2c5e..ebed13af9852 100644 --- a/drivers/net/wireless/ti/wl12xx/scan.c +++ b/drivers/net/wireless/ti/wl12xx/scan.c @@ -350,7 +350,8 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl, cfg->bss_type = SCAN_BSS_TYPE_ANY; /* currently NL80211 supports only a single interval */ for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++) - cfg->intervals[i] = cpu_to_le32(req->interval); + cfg->intervals[i] = cpu_to_le32(req->scan_plans[0].interval * + MSEC_PER_SEC); cfg->ssid_len = 0; ret = wlcore_scan_sched_scan_ssid_list(wl, wlvif, req); diff --git a/drivers/net/wireless/ti/wl18xx/scan.c b/drivers/net/wireless/ti/wl18xx/scan.c index c938c494c785..bc15aa2c3efa 100644 --- a/drivers/net/wireless/ti/wl18xx/scan.c +++ b/drivers/net/wireless/ti/wl18xx/scan.c @@ -228,13 +228,15 @@ int wl18xx_scan_sched_scan_config(struct wl1271 *wl, wl18xx_adjust_channels(cmd, cmd_channels); if (c->num_short_intervals && c->long_interval && - c->long_interval > req->interval) { - cmd->short_cycles_msec = cpu_to_le16(req->interval); + c->long_interval > req->scan_plans[0].interval * MSEC_PER_SEC) { + cmd->short_cycles_msec = + cpu_to_le16(req->scan_plans[0].interval * MSEC_PER_SEC); cmd->long_cycles_msec = cpu_to_le16(c->long_interval); cmd->short_cycles_count = c->num_short_intervals; } else { cmd->short_cycles_msec = 0; - cmd->long_cycles_msec = cpu_to_le16(req->interval); + cmd->long_cycles_msec = + cpu_to_le16(req->scan_plans[0].interval * MSEC_PER_SEC); cmd->short_cycles_count = 0; } wl1271_debug(DEBUG_SCAN, "short_interval: %d, long_interval: %d, num_short: %d", diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 7f1e9ee844e2..48155be5db7f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5,6 +5,7 @@ * * Copyright 2006-2010 Johannes Berg * Copyright 2013-2014 Intel Mobile Communications GmbH + * Copyright 2015 Intel Deutschland GmbH * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -1500,6 +1501,20 @@ struct cfg80211_match_set { s32 rssi_thold; }; +/** + * struct cfg80211_sched_scan_plan - scan plan for scheduled scan + * + * @interval: interval between scheduled scan iterations. In seconds. + * @iterations: number of scan iterations in this scan plan. Zero means + * infinite loop. + * The last scan plan will always have this parameter set to zero, + * all other scan plans will have a finite number of iterations. + */ +struct cfg80211_sched_scan_plan { + u32 interval; + u32 iterations; +}; + /** * struct cfg80211_sched_scan_request - scheduled scan request description * @@ -1507,7 +1522,6 @@ struct cfg80211_match_set { * @n_ssids: number of SSIDs * @n_channels: total number of channels to scan * @scan_width: channel width for scanning - * @interval: interval between each scheduled scan cycle * @ie: optional information element(s) to add into Probe Request or %NULL * @ie_len: length of ie in octets * @flags: bit field of flags controlling operation @@ -1526,6 +1540,9 @@ struct cfg80211_match_set { * @mac_addr_mask: MAC address mask used with randomisation, bits that * are 0 in the mask should be randomised, bits that are 1 should * be taken from the @mac_addr + * @scan_plans: scan plans to be executed in this scheduled scan. Lowest + * index must be executed first. + * @n_scan_plans: number of scan plans, at least 1. * @rcu_head: RCU callback used to free the struct * @owner_nlportid: netlink portid of owner (if this should is a request * owned by a particular socket) @@ -1539,7 +1556,6 @@ struct cfg80211_sched_scan_request { int n_ssids; u32 n_channels; enum nl80211_bss_scan_width scan_width; - u32 interval; const u8 *ie; size_t ie_len; u32 flags; @@ -1547,6 +1563,8 @@ struct cfg80211_sched_scan_request { int n_match_sets; s32 min_rssi_thold; u32 delay; + struct cfg80211_sched_scan_plan *scan_plans; + int n_scan_plans; u8 mac_addr[ETH_ALEN] __aligned(2); u8 mac_addr_mask[ETH_ALEN] __aligned(2); @@ -3076,6 +3094,12 @@ struct wiphy_vendor_command { * include fixed IEs like supported rates * @max_sched_scan_ie_len: same as max_scan_ie_len, but for scheduled * scans + * @max_sched_scan_plans: maximum number of scan plans (scan interval and number + * of iterations) for scheduled scan supported by the device. + * @max_sched_scan_plan_interval: maximum interval (in seconds) for a + * single scan plan supported by the device. + * @max_sched_scan_plan_iterations: maximum number of iterations for a single + * scan plan supported by the device. * @coverage_class: current coverage class * @fw_version: firmware version for ethtool reporting * @hw_version: hardware version for ethtool reporting @@ -3183,6 +3207,9 @@ struct wiphy { u8 max_match_sets; u16 max_scan_ie_len; u16 max_sched_scan_ie_len; + u32 max_sched_scan_plans; + u32 max_sched_scan_plan_interval; + u32 max_sched_scan_plan_iterations; int n_cipher_suites; const u32 *cipher_suites; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 5dadb844fe18..1f0b4cf5dd03 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -10,6 +10,7 @@ * Copyright 2008, 2009 Luis R. Rodriguez * Copyright 2008 Jouni Malinen * Copyright 2008 Colin McCabe + * Copyright 2015 Intel Deutschland GmbH * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above @@ -328,7 +329,15 @@ * partial scan results may be available * * @NL80211_CMD_START_SCHED_SCAN: start a scheduled scan at certain - * intervals, as specified by %NL80211_ATTR_SCHED_SCAN_INTERVAL. + * intervals and certain number of cycles, as specified by + * %NL80211_ATTR_SCHED_SCAN_PLANS. If %NL80211_ATTR_SCHED_SCAN_PLANS is + * not specified and only %NL80211_ATTR_SCHED_SCAN_INTERVAL is specified, + * scheduled scan will run in an infinite loop with the specified interval. + * These attributes are mutually exculsive, + * i.e. NL80211_ATTR_SCHED_SCAN_INTERVAL must not be passed if + * NL80211_ATTR_SCHED_SCAN_PLANS is defined. + * If for some reason scheduled scan is aborted by the driver, all scan + * plans are canceled (including scan plans that did not start yet). * Like with normal scans, if SSIDs (%NL80211_ATTR_SCAN_SSIDS) * are passed, they are used in the probe requests. For * broadcast, a broadcast SSID must be passed (ie. an empty @@ -1761,6 +1770,19 @@ enum nl80211_commands { * @NL80211_ATTR_REG_INDOOR: flag attribute, if set indicates that the device * is operating in an indoor environment. * + * @NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS: maximum number of scan plans for + * scheduled scan supported by the device (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL: maximum interval (in seconds) for + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS: maximum number of iterations in + * a scan plan (u32), a wiphy attribute. + * @NL80211_ATTR_SCHED_SCAN_PLANS: a list of scan plans for scheduled scan. + * Each scan plan defines the number of scan iterations and the interval + * between scans. The last scan plan will always run infinitely, + * thus it must not specify the number of iterations, only the interval + * between scans. The scan plans are executed sequentially. + * Each scan plan is a nested attribute of &enum nl80211_sched_scan_plan. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -2130,6 +2152,11 @@ enum nl80211_attrs { NL80211_ATTR_REG_INDOOR, + NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + NL80211_ATTR_SCHED_SCAN_PLANS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -4593,4 +4620,28 @@ enum nl80211_tdls_peer_capability { NL80211_TDLS_PEER_WMM = 1<<2, }; +/** + * enum nl80211_sched_scan_plan - scanning plan for scheduled scan + * @__NL80211_SCHED_SCAN_PLAN_INVALID: attribute number 0 is reserved + * @NL80211_SCHED_SCAN_PLAN_INTERVAL: interval between scan iterations. In + * seconds (u32). + * @NL80211_SCHED_SCAN_PLAN_ITERATIONS: number of scan iterations in this + * scan plan (u32). The last scan plan must not specify this attribute + * because it will run infinitely. A value of zero is invalid as it will + * make the scan plan meaningless. + * @NL80211_SCHED_SCAN_PLAN_MAX: highest scheduled scan plan attribute number + * currently defined + * @__NL80211_SCHED_SCAN_PLAN_AFTER_LAST: internal use + */ +enum nl80211_sched_scan_plan { + __NL80211_SCHED_SCAN_PLAN_INVALID, + NL80211_SCHED_SCAN_PLAN_INTERVAL, + NL80211_SCHED_SCAN_PLAN_ITERATIONS, + + /* keep last */ + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST, + NL80211_SCHED_SCAN_PLAN_MAX = + __NL80211_SCHED_SCAN_PLAN_AFTER_LAST - 1 +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/core.c b/net/wireless/core.c index f223026ddb03..a83037da21b6 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -461,6 +461,9 @@ use_default_name: rdev->wiphy.max_num_csa_counters = 1; + rdev->wiphy.max_sched_scan_plans = 1; + rdev->wiphy.max_sched_scan_plan_interval = U32_MAX; + return &rdev->wiphy; } EXPORT_SYMBOL(wiphy_new_nm); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index fb0712b3d9cb..28c29e7da749 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -479,6 +479,12 @@ nl80211_match_policy[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1] = { [NL80211_SCHED_SCAN_MATCH_ATTR_RSSI] = { .type = NLA_U32 }, }; +static const struct nla_policy +nl80211_plan_policy[NL80211_SCHED_SCAN_PLAN_MAX + 1] = { + [NL80211_SCHED_SCAN_PLAN_INTERVAL] = { .type = NLA_U32 }, + [NL80211_SCHED_SCAN_PLAN_ITERATIONS] = { .type = NLA_U32 }, +}; + static int nl80211_prepare_wdev_dump(struct sk_buff *skb, struct netlink_callback *cb, struct cfg80211_registered_device **rdev, @@ -1304,7 +1310,13 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, nla_put_u16(msg, NL80211_ATTR_MAX_SCHED_SCAN_IE_LEN, rdev->wiphy.max_sched_scan_ie_len) || nla_put_u8(msg, NL80211_ATTR_MAX_MATCH_SETS, - rdev->wiphy.max_match_sets)) + rdev->wiphy.max_match_sets) || + nla_put_u32(msg, NL80211_ATTR_MAX_NUM_SCHED_SCAN_PLANS, + rdev->wiphy.max_sched_scan_plans) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_INTERVAL, + rdev->wiphy.max_sched_scan_plan_interval) || + nla_put_u32(msg, NL80211_ATTR_MAX_SCAN_PLAN_ITERATIONS, + rdev->wiphy.max_sched_scan_plan_iterations)) goto nla_put_failure; if ((rdev->wiphy.flags & WIPHY_FLAG_IBSS_RSN) && @@ -5974,14 +5986,100 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) return err; } +static int +nl80211_parse_sched_scan_plans(struct wiphy *wiphy, int n_plans, + struct cfg80211_sched_scan_request *request, + struct nlattr **attrs) +{ + int tmp, err, i = 0; + struct nlattr *attr; + + if (!attrs[NL80211_ATTR_SCHED_SCAN_PLANS]) { + u32 interval; + + /* + * If scan plans are not specified, + * %NL80211_ATTR_SCHED_SCAN_INTERVAL must be specified. In this + * case one scan plan will be set with the specified scan + * interval and infinite number of iterations. + */ + if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return -EINVAL; + + interval = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]); + if (!interval) + return -EINVAL; + + request->scan_plans[0].interval = + DIV_ROUND_UP(interval, MSEC_PER_SEC); + if (!request->scan_plans[0].interval) + return -EINVAL; + + if (request->scan_plans[0].interval > + wiphy->max_sched_scan_plan_interval) + request->scan_plans[0].interval = + wiphy->max_sched_scan_plan_interval; + + return 0; + } + + nla_for_each_nested(attr, attrs[NL80211_ATTR_SCHED_SCAN_PLANS], tmp) { + struct nlattr *plan[NL80211_SCHED_SCAN_PLAN_MAX + 1]; + + if (WARN_ON(i >= n_plans)) + return -EINVAL; + + err = nla_parse(plan, NL80211_SCHED_SCAN_PLAN_MAX, + nla_data(attr), nla_len(attr), + nl80211_plan_policy); + if (err) + return err; + + if (!plan[NL80211_SCHED_SCAN_PLAN_INTERVAL]) + return -EINVAL; + + request->scan_plans[i].interval = + nla_get_u32(plan[NL80211_SCHED_SCAN_PLAN_INTERVAL]); + if (!request->scan_plans[i].interval || + request->scan_plans[i].interval > + wiphy->max_sched_scan_plan_interval) + return -EINVAL; + + if (plan[NL80211_SCHED_SCAN_PLAN_ITERATIONS]) { + request->scan_plans[i].iterations = + nla_get_u32(plan[NL80211_SCHED_SCAN_PLAN_ITERATIONS]); + if (!request->scan_plans[i].iterations || + (request->scan_plans[i].iterations > + wiphy->max_sched_scan_plan_iterations)) + return -EINVAL; + } else if (i < n_plans - 1) { + /* + * All scan plans but the last one must specify + * a finite number of iterations + */ + return -EINVAL; + } + + i++; + } + + /* + * The last scan plan must not specify the number of + * iterations, it is supposed to run infinitely + */ + if (request->scan_plans[n_plans - 1].iterations) + return -EINVAL; + + return 0; +} + static struct cfg80211_sched_scan_request * nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, struct nlattr **attrs) { struct cfg80211_sched_scan_request *request; struct nlattr *attr; - int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i; - u32 interval; + int err, tmp, n_ssids = 0, n_match_sets = 0, n_channels, i, n_plans = 0; enum ieee80211_band band; size_t ie_len; struct nlattr *tb[NL80211_SCHED_SCAN_MATCH_ATTR_MAX + 1]; @@ -5990,13 +6088,6 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (!is_valid_ie_attr(attrs[NL80211_ATTR_IE])) return ERR_PTR(-EINVAL); - if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) - return ERR_PTR(-EINVAL); - - interval = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]); - if (interval == 0) - return ERR_PTR(-EINVAL); - if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { n_channels = validate_scan_freqs( attrs[NL80211_ATTR_SCAN_FREQUENCIES]); @@ -6060,9 +6151,37 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, if (ie_len > wiphy->max_sched_scan_ie_len) return ERR_PTR(-EINVAL); + if (attrs[NL80211_ATTR_SCHED_SCAN_PLANS]) { + /* + * NL80211_ATTR_SCHED_SCAN_INTERVAL must not be specified since + * each scan plan already specifies its own interval + */ + if (attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(attr, + attrs[NL80211_ATTR_SCHED_SCAN_PLANS], tmp) + n_plans++; + } else { + /* + * The scan interval attribute is kept for backward + * compatibility. If no scan plans are specified and sched scan + * interval is specified, one scan plan will be set with this + * scan interval and infinite number of iterations. + */ + if (!attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) + return ERR_PTR(-EINVAL); + + n_plans = 1; + } + + if (!n_plans || n_plans > wiphy->max_sched_scan_plans) + return ERR_PTR(-EINVAL); + request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->match_sets) * n_match_sets + + sizeof(*request->scan_plans) * n_plans + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); if (!request) @@ -6090,6 +6209,18 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, } request->n_match_sets = n_match_sets; + if (n_match_sets) + request->scan_plans = (void *)(request->match_sets + + n_match_sets); + else if (request->ie) + request->scan_plans = (void *)(request->ie + ie_len); + else if (n_ssids) + request->scan_plans = (void *)(request->ssids + n_ssids); + else + request->scan_plans = (void *)(request->channels + n_channels); + + request->n_scan_plans = n_plans; + i = 0; if (attrs[NL80211_ATTR_SCAN_FREQUENCIES]) { /* user specified, bail out if channel not found */ @@ -6252,7 +6383,10 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev, request->delay = nla_get_u32(attrs[NL80211_ATTR_SCHED_SCAN_DELAY]); - request->interval = interval; + err = nl80211_parse_sched_scan_plans(wiphy, n_plans, request, attrs); + if (err) + goto out_free; + request->scan_start = jiffies; return request; @@ -8850,7 +8984,7 @@ static int nl80211_send_wowlan_tcp(struct sk_buff *msg, static int nl80211_send_wowlan_nd(struct sk_buff *msg, struct cfg80211_sched_scan_request *req) { - struct nlattr *nd, *freqs, *matches, *match; + struct nlattr *nd, *freqs, *matches, *match, *scan_plans, *scan_plan; int i; if (!req) @@ -8860,7 +8994,9 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, if (!nd) return -ENOBUFS; - if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, req->interval)) + if (req->n_scan_plans == 1 && + nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_INTERVAL, + req->scan_plans[0].interval * 1000)) return -ENOBUFS; if (nla_put_u32(msg, NL80211_ATTR_SCHED_SCAN_DELAY, req->delay)) @@ -8887,6 +9023,23 @@ static int nl80211_send_wowlan_nd(struct sk_buff *msg, nla_nest_end(msg, matches); } + scan_plans = nla_nest_start(msg, NL80211_ATTR_SCHED_SCAN_PLANS); + if (!scan_plans) + return -ENOBUFS; + + for (i = 0; i < req->n_scan_plans; i++) { + scan_plan = nla_nest_start(msg, i + 1); + if (!scan_plan || + nla_put_u32(msg, NL80211_SCHED_SCAN_PLAN_INTERVAL, + req->scan_plans[i].interval) || + (req->scan_plans[i].iterations && + nla_put_u32(msg, NL80211_SCHED_SCAN_PLAN_ITERATIONS, + req->scan_plans[i].iterations))) + return -ENOBUFS; + nla_nest_end(msg, scan_plan); + } + nla_nest_end(msg, scan_plans); + nla_nest_end(msg, nd); return 0; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3feaa03aa046..14d5369eb778 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -266,8 +266,7 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) spin_lock_bh(&rdev->bss_lock); __cfg80211_bss_expire(rdev, request->scan_start); spin_unlock_bh(&rdev->bss_lock); - request->scan_start = - jiffies + msecs_to_jiffies(request->interval); + request->scan_start = jiffies; } nl80211_send_sched_scan_results(rdev, request->dev); } -- cgit v1.2.3 From ba61a8d9d780980e8284355a0be750897e7af212 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Wed, 30 Sep 2015 13:26:42 +0200 Subject: can: avoid using timeval for uapi The can subsystem communicates with user space using a bcm_msg_head header, which contains two timestamps. This is problematic for multiple reasons: a) The structure layout is currently incompatible between 64-bit user space and 32-bit user space, and cannot work in compat mode (other than x32). b) The timeval structure layout will change in 32-bit user space when we fix the y2038 overflow problem by redefining time_t to 64-bit, making new 32-bit user space incompatible with the current kernel interface. Cars last a long time and often use old kernels, so the actual users of this code are the most likely ones to migrate to y2038 safe user space. This tries to work around part of the problem by changing the publicly visible user interface in the header, but not the binary interface. Fortunately, the values passed around in the structure are relative times and do not actually suffer from the y2038 overflow, so 32-bit is enough here. We replace the use of 'struct timeval' with a newly defined 'struct bcm_timeval' that uses the exact same binary layout as before and that still suffers from problem a) but not problem b). The downside of this approach is that any user space program that currently assigns a timeval structure to these members rather than writing the tv_sec/tv_usec portions individually will suffer a compile-time error when built with an updated kernel header. Fixing this error makes it work fine with old and new headers though. We could address problem a) by using '__u32' or 'int' members rather than 'long', but that would have a more significant downside in also breaking support for all existing 64-bit user binaries that might be using this interface, which is likely not acceptable. Signed-off-by: Arnd Bergmann Acked-by: Oliver Hartkopp Cc: linux-can@vger.kernel.org Cc: linux-api@vger.kernel.org Signed-off-by: Marc Kleine-Budde --- include/uapi/linux/can/bcm.h | 7 ++++++- net/can/bcm.c | 15 ++++++++++----- 2 files changed, 16 insertions(+), 6 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/can/bcm.h b/include/uapi/linux/can/bcm.h index 89ddb9dc9bdf..7a291dc1ff15 100644 --- a/include/uapi/linux/can/bcm.h +++ b/include/uapi/linux/can/bcm.h @@ -47,6 +47,11 @@ #include #include +struct bcm_timeval { + long tv_sec; + long tv_usec; +}; + /** * struct bcm_msg_head - head of messages to/from the broadcast manager * @opcode: opcode, see enum below. @@ -62,7 +67,7 @@ struct bcm_msg_head { __u32 opcode; __u32 flags; __u32 count; - struct timeval ival1, ival2; + struct bcm_timeval ival1, ival2; canid_t can_id; __u32 nframes; struct can_frame frames[0]; diff --git a/net/can/bcm.c b/net/can/bcm.c index a1ba6875c2a2..6863310d6973 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -96,7 +96,7 @@ struct bcm_op { canid_t can_id; u32 flags; unsigned long frames_abs, frames_filtered; - struct timeval ival1, ival2; + struct bcm_timeval ival1, ival2; struct hrtimer timer, thrtimer; struct tasklet_struct tsklet, thrtsklet; ktime_t rx_stamp, kt_ival1, kt_ival2, kt_lastmsg; @@ -131,6 +131,11 @@ static inline struct bcm_sock *bcm_sk(const struct sock *sk) return (struct bcm_sock *)sk; } +static inline ktime_t bcm_timeval_to_ktime(struct bcm_timeval tv) +{ + return ktime_set(tv.tv_sec, tv.tv_usec * NSEC_PER_USEC); +} + #define CFSIZ sizeof(struct can_frame) #define OPSIZ sizeof(struct bcm_op) #define MHSIZ sizeof(struct bcm_msg_head) @@ -953,8 +958,8 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, op->count = msg_head->count; op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; - op->kt_ival1 = timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = timeval_to_ktime(msg_head->ival2); + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero values? */ if (!op->kt_ival1.tv64 && !op->kt_ival2.tv64) @@ -1134,8 +1139,8 @@ static int bcm_rx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, /* set timer value */ op->ival1 = msg_head->ival1; op->ival2 = msg_head->ival2; - op->kt_ival1 = timeval_to_ktime(msg_head->ival1); - op->kt_ival2 = timeval_to_ktime(msg_head->ival2); + op->kt_ival1 = bcm_timeval_to_ktime(msg_head->ival1); + op->kt_ival2 = bcm_timeval_to_ktime(msg_head->ival2); /* disable an active timer due to zero value? */ if (!op->kt_ival1.tv64) -- cgit v1.2.3 From a82d24f83de2c63199acead488259fcdf947e90e Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:55 +0200 Subject: ALSA: emu10k1: added EMU10K1 version of DECLARE_BITMAP macro for UAPI MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compilation error: error: expected specifier-qualifier-list before ‘DECLARE_BITMAP’ DECLARE_BITMAP(gpr_valid, 0x200); /* bitmask of valid initializers */ DECLARE_BITMAP macro is not meant for userspace headers and thus added here as private copy for emu10k.h. Fix was suggested by Arnd Bergmann in message <2168807.4Yxh5gl11Q@wuerfel> and Takashi Iwai in message on lkml. Signed-off-by: Mikko Rapeli Signed-off-by: Takashi Iwai --- include/uapi/sound/emu10k1.h | 14 +++++++++++--- 1 file changed, 11 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/emu10k1.h b/include/uapi/sound/emu10k1.h index ec1535bb6aed..5175e166987d 100644 --- a/include/uapi/sound/emu10k1.h +++ b/include/uapi/sound/emu10k1.h @@ -34,6 +34,14 @@ #define EMU10K1_FX8010_PCM_COUNT 8 +/* + * Following definition is copied from linux/types.h to support compiling + * this header file in userspace since they are not generally available for + * uapi headers. + */ +#define __EMU10K1_DECLARE_BITMAP(name,bits) \ + unsigned long name[(bits) / (sizeof(unsigned long) * 8)] + /* instruction set */ #define iMAC0 0x00 /* R = A + (X * Y >> 31) ; saturation */ #define iMAC1 0x01 /* R = A + (-X * Y >> 31) ; saturation */ @@ -300,7 +308,7 @@ struct snd_emu10k1_fx8010_control_old_gpr { struct snd_emu10k1_fx8010_code { char name[128]; - DECLARE_BITMAP(gpr_valid, 0x200); /* bitmask of valid initializers */ + __EMU10K1_DECLARE_BITMAP(gpr_valid, 0x200); /* bitmask of valid initializers */ __u32 __user *gpr_map; /* initializers */ unsigned int gpr_add_control_count; /* count of GPR controls to add/replace */ @@ -313,11 +321,11 @@ struct snd_emu10k1_fx8010_code { unsigned int gpr_list_control_total; /* total count of GPR controls */ struct snd_emu10k1_fx8010_control_gpr __user *gpr_list_controls; /* listed GPR controls */ - DECLARE_BITMAP(tram_valid, 0x100); /* bitmask of valid initializers */ + __EMU10K1_DECLARE_BITMAP(tram_valid, 0x100); /* bitmask of valid initializers */ __u32 __user *tram_data_map; /* data initializers */ __u32 __user *tram_addr_map; /* map initializers */ - DECLARE_BITMAP(code_valid, 1024); /* bitmask of valid instructions */ + __EMU10K1_DECLARE_BITMAP(code_valid, 1024); /* bitmask of valid instructions */ __u32 __user *code; /* one instruction - 64 bits */ }; -- cgit v1.2.3 From ffc287c89169705d9a01d48e05453ab0eda631e4 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:56:06 +0200 Subject: ALSA: hdspm: use __u8, __u32 and __u64 from linux/types.h instead of stdint.h Kernel headers should use linux/types.h based definitions. Signed-off-by: Mikko Rapeli Signed-off-by: Takashi Iwai --- include/uapi/sound/hdspm.h | 40 ++++++++++++++++++---------------------- 1 file changed, 18 insertions(+), 22 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/sound/hdspm.h b/include/uapi/sound/hdspm.h index 5737332d38f2..c4db6f5b306e 100644 --- a/include/uapi/sound/hdspm.h +++ b/include/uapi/sound/hdspm.h @@ -20,11 +20,7 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#ifdef __KERNEL__ #include -#else -#include -#endif /* Maximum channels is 64 even on 56Mode you have 64playbacks to matrix */ #define HDSPM_MAX_CHANNELS 64 @@ -46,15 +42,15 @@ enum hdspm_speed { /* -------------------- IOCTL Peak/RMS Meters -------------------- */ struct hdspm_peak_rms { - uint32_t input_peaks[64]; - uint32_t playback_peaks[64]; - uint32_t output_peaks[64]; + __u32 input_peaks[64]; + __u32 playback_peaks[64]; + __u32 output_peaks[64]; - uint64_t input_rms[64]; - uint64_t playback_rms[64]; - uint64_t output_rms[64]; + __u64 input_rms[64]; + __u64 playback_rms[64]; + __u64 output_rms[64]; - uint8_t speed; /* enum {ss, ds, qs} */ + __u8 speed; /* enum {ss, ds, qs} */ int status2; }; @@ -155,21 +151,21 @@ enum hdspm_syncsource { }; struct hdspm_status { - uint8_t card_type; /* enum hdspm_io_type */ + __u8 card_type; /* enum hdspm_io_type */ enum hdspm_syncsource autosync_source; - uint64_t card_clock; - uint32_t master_period; + __u64 card_clock; + __u32 master_period; union { struct { - uint8_t sync_wc; /* enum hdspm_sync */ - uint8_t sync_madi; /* enum hdspm_sync */ - uint8_t sync_tco; /* enum hdspm_sync */ - uint8_t sync_in; /* enum hdspm_sync */ - uint8_t madi_input; /* enum hdspm_madi_input */ - uint8_t channel_format; /* enum hdspm_madi_channel_format */ - uint8_t frame_format; /* enum hdspm_madi_frame_format */ + __u8 sync_wc; /* enum hdspm_sync */ + __u8 sync_madi; /* enum hdspm_sync */ + __u8 sync_tco; /* enum hdspm_sync */ + __u8 sync_in; /* enum hdspm_sync */ + __u8 madi_input; /* enum hdspm_madi_input */ + __u8 channel_format; /* enum hdspm_madi_channel_format */ + __u8 frame_format; /* enum hdspm_madi_frame_format */ } madi; } card_specific; }; @@ -184,7 +180,7 @@ struct hdspm_status { #define HDSPM_ADDON_TCO 1 struct hdspm_version { - uint8_t card_type; /* enum hdspm_io_type */ + __u8 card_type; /* enum hdspm_io_type */ char cardname[20]; unsigned int serial; unsigned short firmware_rev; -- cgit v1.2.3 From bea51b30b281039f0f43fb4f42028ddf33fb601f Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 26 Sep 2015 02:24:36 +0800 Subject: nfs42: add NFS_IOC_CLONE ioctl It can be called by user space to CLONE two files. Follow btrfs lead and define NFS_IOC_CLONE same as BTRFS_IOC_CLONE. Thus we don't mess up userspace with too many ioctls. Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/nfs4file.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/nfs.h | 4 ++ 2 files changed, 106 insertions(+) (limited to 'include/uapi') diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index b0dbe0abed53..fc68ba5f030c 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -4,6 +4,7 @@ * Copyright (C) 1992 Rick Sladkey */ #include +#include #include #include #include "delegation.h" @@ -192,8 +193,104 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_deallocate(filep, offset, len); return nfs42_proc_allocate(filep, offset, len); } + +static noinline long +nfs42_ioctl_clone(struct file *dst_file, unsigned long srcfd, + u64 src_off, u64 dst_off, u64 count) +{ + struct inode *dst_inode = file_inode(dst_file); + struct fd src_file; + struct inode *src_inode; + int ret; + + /* dst file must be opened for writing */ + if (!(dst_file->f_mode & FMODE_WRITE)) + return -EINVAL; + + ret = mnt_want_write_file(dst_file); + if (ret) + return ret; + + src_file = fdget(srcfd); + if (!src_file.file) { + ret = -EBADF; + goto out_drop_write; + } + + src_inode = file_inode(src_file.file); + + /* src and dst must be different files */ + ret = -EINVAL; + if (src_inode == dst_inode) + goto out_fput; + + /* src file must be opened for reading */ + if (!(src_file.file->f_mode & FMODE_READ)) + goto out_fput; + + /* src and dst must be regular files */ + ret = -EISDIR; + if (!S_ISREG(src_inode->i_mode) || !S_ISREG(dst_inode->i_mode)) + goto out_fput; + + ret = -EXDEV; + if (src_file.file->f_path.mnt != dst_file->f_path.mnt || + src_inode->i_sb != dst_inode->i_sb) + goto out_fput; + + /* XXX: do we lock at all? what if server needs CB_RECALL_LAYOUT? */ + if (dst_inode < src_inode) { + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_CHILD); + } else { + mutex_lock_nested(&src_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&dst_inode->i_mutex, I_MUTEX_CHILD); + } + + /* flush all pending writes on both src and dst so that server + * has the latest data */ + ret = nfs_sync_inode(src_inode); + if (ret) + goto out_unlock; + ret = nfs_sync_inode(dst_inode); + if (ret) + goto out_unlock; + + ret = nfs42_proc_clone(src_file.file, dst_file, src_off, dst_off, count); + + /* truncate inode page cache of the dst range so that future reads can fetch + * new data from server */ + if (!ret) + truncate_inode_pages_range(&dst_inode->i_data, dst_off, dst_off + count - 1); + +out_unlock: + if (dst_inode < src_inode) { + mutex_unlock(&src_inode->i_mutex); + mutex_unlock(&dst_inode->i_mutex); + } else { + mutex_unlock(&dst_inode->i_mutex); + mutex_unlock(&src_inode->i_mutex); + } +out_fput: + fdput(src_file); +out_drop_write: + mnt_drop_write_file(dst_file); + return ret; +} #endif /* CONFIG_NFS_V4_2 */ +long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + switch (cmd) { +#ifdef CONFIG_NFS_V4_2 + case NFS_IOC_CLONE: + return nfs42_ioctl_clone(file, arg, 0, 0, 0); +#endif + } + + return -ENOTTY; +} + const struct file_operations nfs4_file_operations = { #ifdef CONFIG_NFS_V4_2 .llseek = nfs4_file_llseek, @@ -216,4 +313,9 @@ const struct file_operations nfs4_file_operations = { #endif /* CONFIG_NFS_V4_2 */ .check_flags = nfs_check_flags, .setlease = simple_nosetlease, +#ifdef CONFIG_COMPAT + .unlocked_ioctl = nfs4_ioctl, +#else + .compat_ioctl = nfs4_ioctl, +#endif /* CONFIG_COMPAT */ }; diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index 5199a36dd574..d85748d3564d 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -31,6 +31,10 @@ #define NFS_PIPE_DIRNAME "nfs" +/* NFS ioctls */ +/* Let's follow btrfs lead on CLONE to avoid messing userspace */ +#define NFS_IOC_CLONE _IOW(0x94, 9, int) + /* * NFS stats. The good thing with these values is that NFSv3 errors are * a superset of NFSv2 errors (with the exception of NFSERR_WFLUSH which -- cgit v1.2.3 From a340abcf4173461f688292a6879b4d5bc781c2b1 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Sat, 26 Sep 2015 02:24:39 +0800 Subject: nfs42: add NFS_IOC_CLONE_RANGE ioctl It follows btrfs BTRFS_IOC_CLONE_RANGE lead on ioctl number and arguments. Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- fs/nfs/nfs4file.c | 14 ++++++++++++++ include/uapi/linux/nfs.h | 9 ++++++++- 2 files changed, 22 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 4f463dd8bae3..4384a1d00ceb 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -288,14 +288,28 @@ out_drop_write: mnt_drop_write_file(dst_file); return ret; } + +static long nfs42_ioctl_clone_range(struct file *dst_file, void __user *argp) +{ + struct nfs_ioctl_clone_range_args args; + + if (copy_from_user(&args, argp, sizeof(args))) + return -EFAULT; + + return nfs42_ioctl_clone(dst_file, args.src_fd, args.src_off, args.dst_off, args.count); +} #endif /* CONFIG_NFS_V4_2 */ long nfs4_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + void __user *argp = (void __user *)arg; + switch (cmd) { #ifdef CONFIG_NFS_V4_2 case NFS_IOC_CLONE: return nfs42_ioctl_clone(file, arg, 0, 0, 0); + case NFS_IOC_CLONE_RANGE: + return nfs42_ioctl_clone_range(file, argp); #endif } diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index d85748d3564d..c6b86cc404f8 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -33,7 +33,14 @@ /* NFS ioctls */ /* Let's follow btrfs lead on CLONE to avoid messing userspace */ -#define NFS_IOC_CLONE _IOW(0x94, 9, int) +#define NFS_IOC_CLONE _IOW(0x94, 9, int) +#define NFS_IOC_CLONE_RANGE _IOW(0x94, 13, int) + +struct nfs_ioctl_clone_range_args { + __s64 src_fd; + __u64 src_off, count; + __u64 dst_off; +}; /* * NFS stats. The good thing with these values is that NFSv3 errors are -- cgit v1.2.3 From 7a6007c309c9b0e573dc17ac9d81e8b5f173847d Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:50 +0200 Subject: include/uapi/drm/sis_drm.h: move sis_file_private to drivers/gpu/drm/sis/sis_drv.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Fixes userspace compile error: drm/sis_drm.h:68:19: error: field ‘obj_list’ has incomplete type struct list_head obj_list; Suggested by Emil Velikov at https://lkml.org/lkml/2015/6/3/792 Signed-off-by: Mikko Rapeli Signed-off-by: Dave Airlie --- drivers/gpu/drm/sis/sis_drv.h | 4 ++++ include/uapi/drm/sis_drm.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/sis/sis_drv.h b/drivers/gpu/drm/sis/sis_drv.h index 16f972b2a76a..328f8a750976 100644 --- a/drivers/gpu/drm/sis/sis_drv.h +++ b/drivers/gpu/drm/sis/sis_drv.h @@ -67,6 +67,10 @@ typedef struct drm_sis_private { struct idr object_idr; } drm_sis_private_t; +struct sis_file_private { + struct list_head obj_list; +}; + extern int sis_idle(struct drm_device *dev); extern void sis_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv); diff --git a/include/uapi/drm/sis_drm.h b/include/uapi/drm/sis_drm.h index df3763222d73..374858cdcdaa 100644 --- a/include/uapi/drm/sis_drm.h +++ b/include/uapi/drm/sis_drm.h @@ -64,8 +64,4 @@ typedef struct { unsigned long offset, size; } drm_sis_fb_t; -struct sis_file_private { - struct list_head obj_list; -}; - #endif /* __SIS_DRM_H__ */ -- cgit v1.2.3 From c76af02d90ee9e9d2ef478fc6f874ad2abcf3ec9 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:48 +0200 Subject: via_drm.h: move struct via_file_private definition to drivers/gpu/drm/via/via_drv.h Fixes userspace compile error since list_head is not exported to userspace headers. Suggested by Emil Velikov at https://lkml.org/lkml/2015/6/3/792 Signed-off-by: Mikko Rapeli Signed-off-by: Dave Airlie --- drivers/gpu/drm/via/via_drv.h | 4 ++++ include/uapi/drm/via_drm.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h index 644093f5046c..286a785fab4f 100644 --- a/drivers/gpu/drm/via/via_drv.h +++ b/drivers/gpu/drm/via/via_drv.h @@ -102,6 +102,10 @@ typedef struct drm_via_private { uint32_t dma_diff; } drm_via_private_t; +struct via_file_private { + struct list_head obj_list; +}; + enum via_family { VIA_OTHER = 0, /* Baseline */ VIA_PRO_GROUP_A, /* Another video engine and DMA commands */ diff --git a/include/uapi/drm/via_drm.h b/include/uapi/drm/via_drm.h index 8b0533ccbd5a..45bc80c3714b 100644 --- a/include/uapi/drm/via_drm.h +++ b/include/uapi/drm/via_drm.h @@ -274,8 +274,4 @@ typedef struct drm_via_dmablit { drm_via_blitsync_t sync; } drm_via_dmablit_t; -struct via_file_private { - struct list_head obj_list; -}; - #endif /* _VIA_DRM_H_ */ -- cgit v1.2.3 From 62fb7a5e10962ac6ae2a2d2dbd3aedcb2a3e3257 Mon Sep 17 00:00:00 2001 From: Gerd Hoffmann Date: Tue, 28 Oct 2014 12:48:00 +0100 Subject: virtio-gpu: add 3d/virgl support Add the bits needed for opengl rendering support: query capabilities, new virtio commands, drm ioctls. Signed-off-by: Dave Airlie Signed-off-by: Gerd Hoffmann --- drivers/gpu/drm/virtio/Makefile | 3 +- drivers/gpu/drm/virtio/virtgpu_drv.c | 15 + drivers/gpu/drm/virtio/virtgpu_drv.h | 60 ++++ drivers/gpu/drm/virtio/virtgpu_gem.c | 41 +++ drivers/gpu/drm/virtio/virtgpu_ioctl.c | 573 +++++++++++++++++++++++++++++++++ drivers/gpu/drm/virtio/virtgpu_kms.c | 133 +++++++- drivers/gpu/drm/virtio/virtgpu_ttm.c | 1 + drivers/gpu/drm/virtio/virtgpu_vq.c | 265 +++++++++++++++ include/uapi/drm/Kbuild | 1 + include/uapi/drm/virtgpu_drm.h | 167 ++++++++++ include/uapi/linux/virtio_gpu.h | 112 ++++++- 11 files changed, 1368 insertions(+), 3 deletions(-) create mode 100644 drivers/gpu/drm/virtio/virtgpu_ioctl.c create mode 100644 include/uapi/drm/virtgpu_drm.h (limited to 'include/uapi') diff --git a/drivers/gpu/drm/virtio/Makefile b/drivers/gpu/drm/virtio/Makefile index 2ee1602d77d4..da7bf192e462 100644 --- a/drivers/gpu/drm/virtio/Makefile +++ b/drivers/gpu/drm/virtio/Makefile @@ -6,6 +6,7 @@ ccflags-y := -Iinclude/drm virtio-gpu-y := virtgpu_drv.o virtgpu_kms.o virtgpu_drm_bus.o virtgpu_gem.o \ virtgpu_fb.o virtgpu_display.o virtgpu_vq.o virtgpu_ttm.o \ - virtgpu_fence.o virtgpu_object.o virtgpu_debugfs.o virtgpu_plane.o + virtgpu_fence.o virtgpu_object.o virtgpu_debugfs.o virtgpu_plane.o \ + virtgpu_ioctl.o obj-$(CONFIG_DRM_VIRTIO_GPU) += virtio-gpu.o diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.c b/drivers/gpu/drm/virtio/virtgpu_drv.c index 7d9610aaeff9..c27d3a30df0a 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.c +++ b/drivers/gpu/drm/virtio/virtgpu_drv.c @@ -73,6 +73,14 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { +#ifdef __LITTLE_ENDIAN + /* + * Gallium command stream send by virgl is native endian. + * Because of that we only support little endian guests on + * little endian hosts. + */ + VIRTIO_GPU_F_VIRGL, +#endif }; static struct virtio_driver virtio_gpu_driver = { .feature_table = features, @@ -114,6 +122,8 @@ static struct drm_driver driver = { .set_busid = drm_virtio_set_busid, .load = virtio_gpu_driver_load, .unload = virtio_gpu_driver_unload, + .open = virtio_gpu_driver_open, + .postclose = virtio_gpu_driver_postclose, .dumb_create = virtio_gpu_mode_dumb_create, .dumb_map_offset = virtio_gpu_mode_dumb_mmap, @@ -125,8 +135,13 @@ static struct drm_driver driver = { #endif .gem_free_object = virtio_gpu_gem_free_object, + .gem_open_object = virtio_gpu_gem_object_open, + .gem_close_object = virtio_gpu_gem_object_close, .fops = &virtio_gpu_driver_fops, + .ioctls = virtio_gpu_ioctls, + .num_ioctls = DRM_VIRTIO_NUM_IOCTLS, + .name = DRIVER_NAME, .desc = DRIVER_DESC, .date = DRIVER_DATE, diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h index 6d4db2dba90b..27191088a701 100644 --- a/drivers/gpu/drm/virtio/virtgpu_drv.h +++ b/drivers/gpu/drm/virtio/virtgpu_drv.h @@ -146,6 +146,21 @@ struct virtio_gpu_queue { struct work_struct dequeue_work; }; +struct virtio_gpu_drv_capset { + uint32_t id; + uint32_t max_version; + uint32_t max_size; +}; + +struct virtio_gpu_drv_cap_cache { + struct list_head head; + void *caps_cache; + uint32_t id; + uint32_t version; + uint32_t size; + atomic_t is_valid; +}; + struct virtio_gpu_device { struct device *dev; struct drm_device *ddev; @@ -179,7 +194,13 @@ struct virtio_gpu_device { struct idr ctx_id_idr; spinlock_t ctx_id_idr_lock; + bool has_virgl_3d; + struct work_struct config_changed_work; + + struct virtio_gpu_drv_capset *capsets; + uint32_t num_capsets; + struct list_head cap_cache; }; struct virtio_gpu_fpriv { @@ -193,6 +214,8 @@ extern struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS]; /* virtio_kms.c */ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags); int virtio_gpu_driver_unload(struct drm_device *dev); +int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file); +void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file); /* virtio_gem.c */ void virtio_gpu_gem_free_object(struct drm_gem_object *gem_obj); @@ -203,6 +226,10 @@ int virtio_gpu_gem_create(struct drm_file *file, uint64_t size, struct drm_gem_object **obj_p, uint32_t *handle_p); +int virtio_gpu_gem_object_open(struct drm_gem_object *obj, + struct drm_file *file); +void virtio_gpu_gem_object_close(struct drm_gem_object *obj, + struct drm_file *file); struct virtio_gpu_object *virtio_gpu_alloc_object(struct drm_device *dev, size_t size, bool kernel, bool pinned); @@ -260,10 +287,43 @@ void virtio_gpu_cursor_ping(struct virtio_gpu_device *vgdev, int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev); void virtio_gpu_cmd_resource_inval_backing(struct virtio_gpu_device *vgdev, uint32_t resource_id); +int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx); +int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev, + int idx, int version, + struct virtio_gpu_drv_cap_cache **cache_p); +void virtio_gpu_cmd_context_create(struct virtio_gpu_device *vgdev, uint32_t id, + uint32_t nlen, const char *name); +void virtio_gpu_cmd_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t id); +void virtio_gpu_cmd_context_attach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id); +void virtio_gpu_cmd_context_detach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id); +void virtio_gpu_cmd_submit(struct virtio_gpu_device *vgdev, + void *data, uint32_t data_size, + uint32_t ctx_id, struct virtio_gpu_fence **fence); +void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence); +void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence); +void +virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev, + struct virtio_gpu_resource_create_3d *rc_3d, + struct virtio_gpu_fence **fence); void virtio_gpu_ctrl_ack(struct virtqueue *vq); void virtio_gpu_cursor_ack(struct virtqueue *vq); +void virtio_gpu_fence_ack(struct virtqueue *vq); void virtio_gpu_dequeue_ctrl_func(struct work_struct *work); void virtio_gpu_dequeue_cursor_func(struct work_struct *work); +void virtio_gpu_dequeue_fence_func(struct work_struct *work); /* virtio_gpu_display.c */ int virtio_gpu_framebuffer_init(struct drm_device *dev, diff --git a/drivers/gpu/drm/virtio/virtgpu_gem.c b/drivers/gpu/drm/virtio/virtgpu_gem.c index cfa0d27150bd..1feb7cee3f0d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_gem.c +++ b/drivers/gpu/drm/virtio/virtgpu_gem.c @@ -138,3 +138,44 @@ int virtio_gpu_mode_dumb_mmap(struct drm_file *file_priv, drm_gem_object_unreference_unlocked(gobj); return 0; } + +int virtio_gpu_gem_object_open(struct drm_gem_object *obj, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct virtio_gpu_object *qobj = gem_to_virtio_gpu_obj(obj); + int r; + + if (!vgdev->has_virgl_3d) + return 0; + + r = virtio_gpu_object_reserve(qobj, false); + if (r) + return r; + + virtio_gpu_cmd_context_attach_resource(vgdev, vfpriv->ctx_id, + qobj->hw_res_handle); + virtio_gpu_object_unreserve(qobj); + return 0; +} + +void virtio_gpu_gem_object_close(struct drm_gem_object *obj, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = obj->dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct virtio_gpu_object *qobj = gem_to_virtio_gpu_obj(obj); + int r; + + if (!vgdev->has_virgl_3d) + return; + + r = virtio_gpu_object_reserve(qobj, false); + if (r) + return; + + virtio_gpu_cmd_context_detach_resource(vgdev, vfpriv->ctx_id, + qobj->hw_res_handle); + virtio_gpu_object_unreserve(qobj); +} diff --git a/drivers/gpu/drm/virtio/virtgpu_ioctl.c b/drivers/gpu/drm/virtio/virtgpu_ioctl.c new file mode 100644 index 000000000000..4ef672b314c6 --- /dev/null +++ b/drivers/gpu/drm/virtio/virtgpu_ioctl.c @@ -0,0 +1,573 @@ +/* + * Copyright (C) 2015 Red Hat, Inc. + * All Rights Reserved. + * + * Authors: + * Dave Airlie + * Alon Levy + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * 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 COPYRIGHT HOLDER(S) OR AUTHOR(S) 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 +#include "virtgpu_drv.h" +#include +#include "ttm/ttm_execbuf_util.h" + +static void convert_to_hw_box(struct virtio_gpu_box *dst, + const struct drm_virtgpu_3d_box *src) +{ + dst->x = cpu_to_le32(src->x); + dst->y = cpu_to_le32(src->y); + dst->z = cpu_to_le32(src->z); + dst->w = cpu_to_le32(src->w); + dst->h = cpu_to_le32(src->h); + dst->d = cpu_to_le32(src->d); +} + +static int virtio_gpu_map_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_map *virtio_gpu_map = data; + + return virtio_gpu_mode_dumb_mmap(file_priv, vgdev->ddev, + virtio_gpu_map->handle, + &virtio_gpu_map->offset); +} + +static int virtio_gpu_object_list_validate(struct ww_acquire_ctx *ticket, + struct list_head *head) +{ + struct ttm_validate_buffer *buf; + struct ttm_buffer_object *bo; + struct virtio_gpu_object *qobj; + int ret; + + ret = ttm_eu_reserve_buffers(ticket, head, true, NULL); + if (ret != 0) + return ret; + + list_for_each_entry(buf, head, head) { + bo = buf->bo; + qobj = container_of(bo, struct virtio_gpu_object, tbo); + ret = ttm_bo_validate(bo, &qobj->placement, false, false); + if (ret) { + ttm_eu_backoff_reservation(ticket, head); + return ret; + } + } + return 0; +} + +static void virtio_gpu_unref_list(struct list_head *head) +{ + struct ttm_validate_buffer *buf; + struct ttm_buffer_object *bo; + struct virtio_gpu_object *qobj; + list_for_each_entry(buf, head, head) { + bo = buf->bo; + qobj = container_of(bo, struct virtio_gpu_object, tbo); + + drm_gem_object_unreference_unlocked(&qobj->gem_base); + } +} + +static int virtio_gpu_execbuffer(struct drm_device *dev, + struct drm_virtgpu_execbuffer *exbuf, + struct drm_file *drm_file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = drm_file->driver_priv; + struct drm_gem_object *gobj; + struct virtio_gpu_fence *fence; + struct virtio_gpu_object *qobj; + int ret; + uint32_t *bo_handles = NULL; + void __user *user_bo_handles = NULL; + struct list_head validate_list; + struct ttm_validate_buffer *buflist = NULL; + int i; + struct ww_acquire_ctx ticket; + void *buf; + + if (vgdev->has_virgl_3d == false) + return -ENOSYS; + + INIT_LIST_HEAD(&validate_list); + if (exbuf->num_bo_handles) { + + bo_handles = drm_malloc_ab(exbuf->num_bo_handles, + sizeof(uint32_t)); + buflist = drm_calloc_large(exbuf->num_bo_handles, + sizeof(struct ttm_validate_buffer)); + if (!bo_handles || !buflist) { + drm_free_large(bo_handles); + drm_free_large(buflist); + return -ENOMEM; + } + + user_bo_handles = (void __user *)(uintptr_t)exbuf->bo_handles; + if (copy_from_user(bo_handles, user_bo_handles, + exbuf->num_bo_handles * sizeof(uint32_t))) { + ret = -EFAULT; + drm_free_large(bo_handles); + drm_free_large(buflist); + return ret; + } + + for (i = 0; i < exbuf->num_bo_handles; i++) { + gobj = drm_gem_object_lookup(dev, + drm_file, bo_handles[i]); + if (!gobj) { + drm_free_large(bo_handles); + drm_free_large(buflist); + return -ENOENT; + } + + qobj = gem_to_virtio_gpu_obj(gobj); + buflist[i].bo = &qobj->tbo; + + list_add(&buflist[i].head, &validate_list); + } + drm_free_large(bo_handles); + } + + ret = virtio_gpu_object_list_validate(&ticket, &validate_list); + if (ret) + goto out_free; + + buf = kmalloc(exbuf->size, GFP_KERNEL); + if (!buf) { + ret = -ENOMEM; + goto out_unresv; + } + if (copy_from_user(buf, (void __user *)(uintptr_t)exbuf->command, + exbuf->size)) { + kfree(buf); + ret = -EFAULT; + goto out_unresv; + } + virtio_gpu_cmd_submit(vgdev, buf, exbuf->size, + vfpriv->ctx_id, &fence); + + ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f); + + /* fence the command bo */ + virtio_gpu_unref_list(&validate_list); + drm_free_large(buflist); + fence_put(&fence->f); + return 0; + +out_unresv: + ttm_eu_backoff_reservation(&ticket, &validate_list); +out_free: + virtio_gpu_unref_list(&validate_list); + drm_free_large(buflist); + return ret; +} + +/* + * Usage of execbuffer: + * Relocations need to take into account the full VIRTIO_GPUDrawable size. + * However, the command as passed from user space must *not* contain the initial + * VIRTIO_GPUReleaseInfo struct (first XXX bytes) + */ +static int virtio_gpu_execbuffer_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_virtgpu_execbuffer *execbuffer = data; + return virtio_gpu_execbuffer(dev, execbuffer, file_priv); +} + + +static int virtio_gpu_getparam_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_getparam *param = data; + int value; + + switch (param->param) { + case VIRTGPU_PARAM_3D_FEATURES: + value = vgdev->has_virgl_3d == true ? 1 : 0; + break; + default: + return -EINVAL; + } + if (copy_to_user((void __user *)(unsigned long)param->value, + &value, sizeof(int))) { + return -EFAULT; + } + return 0; +} + +static int virtio_gpu_resource_create_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_resource_create *rc = data; + int ret; + uint32_t res_id; + struct virtio_gpu_object *qobj; + struct drm_gem_object *obj; + uint32_t handle = 0; + uint32_t size; + struct list_head validate_list; + struct ttm_validate_buffer mainbuf; + struct virtio_gpu_fence *fence = NULL; + struct ww_acquire_ctx ticket; + struct virtio_gpu_resource_create_3d rc_3d; + + if (vgdev->has_virgl_3d == false) { + if (rc->depth > 1) + return -EINVAL; + if (rc->nr_samples > 1) + return -EINVAL; + if (rc->last_level > 1) + return -EINVAL; + if (rc->target != 2) + return -EINVAL; + if (rc->array_size > 1) + return -EINVAL; + } + + INIT_LIST_HEAD(&validate_list); + memset(&mainbuf, 0, sizeof(struct ttm_validate_buffer)); + + virtio_gpu_resource_id_get(vgdev, &res_id); + + size = rc->size; + + /* allocate a single page size object */ + if (size == 0) + size = PAGE_SIZE; + + qobj = virtio_gpu_alloc_object(dev, size, false, false); + if (IS_ERR(qobj)) { + ret = PTR_ERR(qobj); + goto fail_id; + } + obj = &qobj->gem_base; + + if (!vgdev->has_virgl_3d) { + virtio_gpu_cmd_create_resource(vgdev, res_id, rc->format, + rc->width, rc->height); + + ret = virtio_gpu_object_attach(vgdev, qobj, res_id, NULL); + } else { + /* use a gem reference since unref list undoes them */ + drm_gem_object_reference(&qobj->gem_base); + mainbuf.bo = &qobj->tbo; + list_add(&mainbuf.head, &validate_list); + + ret = virtio_gpu_object_list_validate(&ticket, &validate_list); + if (ret) { + DRM_DEBUG("failed to validate\n"); + goto fail_unref; + } + + rc_3d.resource_id = cpu_to_le32(res_id); + rc_3d.target = cpu_to_le32(rc->target); + rc_3d.format = cpu_to_le32(rc->format); + rc_3d.bind = cpu_to_le32(rc->bind); + rc_3d.width = cpu_to_le32(rc->width); + rc_3d.height = cpu_to_le32(rc->height); + rc_3d.depth = cpu_to_le32(rc->depth); + rc_3d.array_size = cpu_to_le32(rc->array_size); + rc_3d.last_level = cpu_to_le32(rc->last_level); + rc_3d.nr_samples = cpu_to_le32(rc->nr_samples); + rc_3d.flags = cpu_to_le32(rc->flags); + + virtio_gpu_cmd_resource_create_3d(vgdev, &rc_3d, NULL); + ret = virtio_gpu_object_attach(vgdev, qobj, res_id, &fence); + if (ret) { + ttm_eu_backoff_reservation(&ticket, &validate_list); + goto fail_unref; + } + ttm_eu_fence_buffer_objects(&ticket, &validate_list, &fence->f); + } + + qobj->hw_res_handle = res_id; + + ret = drm_gem_handle_create(file_priv, obj, &handle); + if (ret) { + + drm_gem_object_release(obj); + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } + return ret; + } + drm_gem_object_unreference_unlocked(obj); + + rc->res_handle = res_id; /* similiar to a VM address */ + rc->bo_handle = handle; + + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } + return 0; +fail_unref: + if (vgdev->has_virgl_3d) { + virtio_gpu_unref_list(&validate_list); + fence_put(&fence->f); + } +//fail_obj: +// drm_gem_object_handle_unreference_unlocked(obj); +fail_id: + virtio_gpu_resource_id_put(vgdev, res_id); + return ret; +} + +static int virtio_gpu_resource_info_ioctl(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + struct drm_virtgpu_resource_info *ri = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + + gobj = drm_gem_object_lookup(dev, file_priv, ri->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ri->size = qobj->gem_base.size; + ri->res_handle = qobj->hw_res_handle; + drm_gem_object_unreference_unlocked(gobj); + return 0; +} + +static int virtio_gpu_transfer_from_host_ioctl(struct drm_device *dev, + void *data, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct drm_virtgpu_3d_transfer_from_host *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + struct virtio_gpu_fence *fence; + int ret; + u32 offset = args->offset; + struct virtio_gpu_box box; + + if (vgdev->has_virgl_3d == false) + return -ENOSYS; + + gobj = drm_gem_object_lookup(dev, file, args->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ret = virtio_gpu_object_reserve(qobj, false); + if (ret) + goto out; + + ret = ttm_bo_validate(&qobj->tbo, &qobj->placement, + true, false); + if (unlikely(ret)) + goto out_unres; + + convert_to_hw_box(&box, &args->box); + virtio_gpu_cmd_transfer_from_host_3d + (vgdev, qobj->hw_res_handle, + vfpriv->ctx_id, offset, args->level, + &box, &fence); + reservation_object_add_excl_fence(qobj->tbo.resv, + &fence->f); + + fence_put(&fence->f); +out_unres: + virtio_gpu_object_unreserve(qobj); +out: + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_transfer_to_host_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + struct drm_virtgpu_3d_transfer_to_host *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + struct virtio_gpu_fence *fence; + struct virtio_gpu_box box; + int ret; + u32 offset = args->offset; + + gobj = drm_gem_object_lookup(dev, file, args->bo_handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + ret = virtio_gpu_object_reserve(qobj, false); + if (ret) + goto out; + + ret = ttm_bo_validate(&qobj->tbo, &qobj->placement, + true, false); + if (unlikely(ret)) + goto out_unres; + + convert_to_hw_box(&box, &args->box); + if (!vgdev->has_virgl_3d) { + virtio_gpu_cmd_transfer_to_host_2d + (vgdev, qobj->hw_res_handle, offset, + box.w, box.h, box.x, box.y, NULL); + } else { + virtio_gpu_cmd_transfer_to_host_3d + (vgdev, qobj->hw_res_handle, + vfpriv ? vfpriv->ctx_id : 0, offset, + args->level, &box, &fence); + reservation_object_add_excl_fence(qobj->tbo.resv, + &fence->f); + fence_put(&fence->f); + } + +out_unres: + virtio_gpu_object_unreserve(qobj); +out: + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_wait_ioctl(struct drm_device *dev, void *data, + struct drm_file *file) +{ + struct drm_virtgpu_3d_wait *args = data; + struct drm_gem_object *gobj = NULL; + struct virtio_gpu_object *qobj = NULL; + int ret; + bool nowait = false; + + gobj = drm_gem_object_lookup(dev, file, args->handle); + if (gobj == NULL) + return -ENOENT; + + qobj = gem_to_virtio_gpu_obj(gobj); + + if (args->flags & VIRTGPU_WAIT_NOWAIT) + nowait = true; + ret = virtio_gpu_object_wait(qobj, nowait); + + drm_gem_object_unreference_unlocked(gobj); + return ret; +} + +static int virtio_gpu_get_caps_ioctl(struct drm_device *dev, + void *data, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct drm_virtgpu_get_caps *args = data; + int size; + int i; + int found_valid = -1; + int ret; + struct virtio_gpu_drv_cap_cache *cache_ent; + void *ptr; + if (vgdev->num_capsets == 0) + return -ENOSYS; + + spin_lock(&vgdev->display_info_lock); + for (i = 0; i < vgdev->num_capsets; i++) { + if (vgdev->capsets[i].id == args->cap_set_id) { + if (vgdev->capsets[i].max_version >= args->cap_set_ver) { + found_valid = i; + break; + } + } + } + + if (found_valid == -1) { + spin_unlock(&vgdev->display_info_lock); + return -EINVAL; + } + + size = vgdev->capsets[found_valid].max_size; + if (args->size > size) { + spin_unlock(&vgdev->display_info_lock); + return -EINVAL; + } + + list_for_each_entry(cache_ent, &vgdev->cap_cache, head) { + if (cache_ent->id == args->cap_set_id && + cache_ent->version == args->cap_set_ver) { + ptr = cache_ent->caps_cache; + spin_unlock(&vgdev->display_info_lock); + goto copy_exit; + } + } + spin_unlock(&vgdev->display_info_lock); + + /* not in cache - need to talk to hw */ + virtio_gpu_cmd_get_capset(vgdev, found_valid, args->cap_set_ver, + &cache_ent); + + ret = wait_event_timeout(vgdev->resp_wq, + atomic_read(&cache_ent->is_valid), 5 * HZ); + + ptr = cache_ent->caps_cache; + +copy_exit: + if (copy_to_user((void __user *)(unsigned long)args->addr, ptr, size)) + return -EFAULT; + + return 0; +} + +struct drm_ioctl_desc virtio_gpu_ioctls[DRM_VIRTIO_NUM_IOCTLS] = { + DRM_IOCTL_DEF_DRV(VIRTGPU_MAP, virtio_gpu_map_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_EXECBUFFER, virtio_gpu_execbuffer_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_GETPARAM, virtio_gpu_getparam_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_CREATE, + virtio_gpu_resource_create_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_RESOURCE_INFO, virtio_gpu_resource_info_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + /* make transfer async to the main ring? - no sure, can we + thread these in the underlying GL */ + DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_FROM_HOST, + virtio_gpu_transfer_from_host_ioctl, + DRM_AUTH|DRM_UNLOCKED), + DRM_IOCTL_DEF_DRV(VIRTGPU_TRANSFER_TO_HOST, + virtio_gpu_transfer_to_host_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_WAIT, virtio_gpu_wait_ioctl, + DRM_AUTH|DRM_UNLOCKED), + + DRM_IOCTL_DEF_DRV(VIRTGPU_GET_CAPS, virtio_gpu_get_caps_ioctl, + DRM_AUTH|DRM_UNLOCKED), +}; diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c index 782766c00d70..06496a128162 100644 --- a/drivers/gpu/drm/virtio/virtgpu_kms.c +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -52,6 +52,41 @@ static void virtio_gpu_config_changed_work_func(struct work_struct *work) events_clear, &events_clear); } +static void virtio_gpu_ctx_id_get(struct virtio_gpu_device *vgdev, + uint32_t *resid) +{ + int handle; + + idr_preload(GFP_KERNEL); + spin_lock(&vgdev->ctx_id_idr_lock); + handle = idr_alloc(&vgdev->ctx_id_idr, NULL, 1, 0, 0); + spin_unlock(&vgdev->ctx_id_idr_lock); + idr_preload_end(); + *resid = handle; +} + +static void virtio_gpu_ctx_id_put(struct virtio_gpu_device *vgdev, uint32_t id) +{ + spin_lock(&vgdev->ctx_id_idr_lock); + idr_remove(&vgdev->ctx_id_idr, id); + spin_unlock(&vgdev->ctx_id_idr_lock); +} + +static void virtio_gpu_context_create(struct virtio_gpu_device *vgdev, + uint32_t nlen, const char *name, + uint32_t *ctx_id) +{ + virtio_gpu_ctx_id_get(vgdev, ctx_id); + virtio_gpu_cmd_context_create(vgdev, *ctx_id, nlen, name); +} + +static void virtio_gpu_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t ctx_id) +{ + virtio_gpu_cmd_context_destroy(vgdev, ctx_id); + virtio_gpu_ctx_id_put(vgdev, ctx_id); +} + static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, void (*work_func)(struct work_struct *work)) { @@ -60,6 +95,36 @@ static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, INIT_WORK(&vgvq->dequeue_work, work_func); } +static void virtio_gpu_get_capsets(struct virtio_gpu_device *vgdev, + int num_capsets) +{ + int i, ret; + + vgdev->capsets = kcalloc(num_capsets, + sizeof(struct virtio_gpu_drv_capset), + GFP_KERNEL); + if (!vgdev->capsets) { + DRM_ERROR("failed to allocate cap sets\n"); + return; + } + for (i = 0; i < num_capsets; i++) { + virtio_gpu_cmd_get_capset_info(vgdev, i); + ret = wait_event_timeout(vgdev->resp_wq, + vgdev->capsets[i].id > 0, 5 * HZ); + if (ret == 0) { + DRM_ERROR("timed out waiting for cap set %d\n", i); + kfree(vgdev->capsets); + vgdev->capsets = NULL; + return; + } + DRM_INFO("cap set %d: id %d, max-version %d, max-size %d\n", + i, vgdev->capsets[i].id, + vgdev->capsets[i].max_version, + vgdev->capsets[i].max_size); + } + vgdev->num_capsets = num_capsets; +} + int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) { static vq_callback_t *callbacks[] = { @@ -70,7 +135,7 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) struct virtio_gpu_device *vgdev; /* this will expand later */ struct virtqueue *vqs[2]; - u32 num_scanouts; + u32 num_scanouts, num_capsets; int ret; if (!virtio_has_feature(dev->virtdev, VIRTIO_F_VERSION_1)) @@ -96,9 +161,15 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) spin_lock_init(&vgdev->fence_drv.lock); INIT_LIST_HEAD(&vgdev->fence_drv.fences); + INIT_LIST_HEAD(&vgdev->cap_cache); INIT_WORK(&vgdev->config_changed_work, virtio_gpu_config_changed_work_func); + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_VIRGL)) + vgdev->has_virgl_3d = true; + DRM_INFO("virgl 3d acceleration %s\n", + vgdev->has_virgl_3d ? "enabled" : "not available"); + ret = vgdev->vdev->config->find_vqs(vgdev->vdev, 2, vqs, callbacks, names); if (ret) { @@ -129,6 +200,11 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) ret = -EINVAL; goto err_scanouts; } + DRM_INFO("number of scanouts: %d\n", num_scanouts); + + virtio_cread(vgdev->vdev, struct virtio_gpu_config, + num_capsets, &num_capsets); + DRM_INFO("number of cap sets: %d\n", num_capsets); ret = virtio_gpu_modeset_init(vgdev); if (ret) @@ -137,6 +213,8 @@ int virtio_gpu_driver_load(struct drm_device *dev, unsigned long flags) virtio_device_ready(vgdev->vdev); vgdev->vqs_ready = true; + if (num_capsets) + virtio_gpu_get_capsets(vgdev, num_capsets); virtio_gpu_cmd_get_display_info(vgdev); wait_event_timeout(vgdev->resp_wq, !vgdev->display_info_pending, 5 * HZ); @@ -157,6 +235,16 @@ err_vqs: return ret; } +static void virtio_gpu_cleanup_cap_cache(struct virtio_gpu_device *vgdev) +{ + struct virtio_gpu_drv_cap_cache *cache_ent, *tmp; + + list_for_each_entry_safe(cache_ent, tmp, &vgdev->cap_cache, head) { + kfree(cache_ent->caps_cache); + kfree(cache_ent); + } +} + int virtio_gpu_driver_unload(struct drm_device *dev) { struct virtio_gpu_device *vgdev = dev->dev_private; @@ -170,6 +258,49 @@ int virtio_gpu_driver_unload(struct drm_device *dev) virtio_gpu_modeset_fini(vgdev); virtio_gpu_ttm_fini(vgdev); virtio_gpu_free_vbufs(vgdev); + virtio_gpu_cleanup_cap_cache(vgdev); + kfree(vgdev->capsets); kfree(vgdev); return 0; } + +int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv; + uint32_t id; + char dbgname[64], tmpname[TASK_COMM_LEN]; + + /* can't create contexts without 3d renderer */ + if (!vgdev->has_virgl_3d) + return 0; + + get_task_comm(tmpname, current); + snprintf(dbgname, sizeof(dbgname), "%s", tmpname); + dbgname[63] = 0; + /* allocate a virt GPU context for this opener */ + vfpriv = kzalloc(sizeof(*vfpriv), GFP_KERNEL); + if (!vfpriv) + return -ENOMEM; + + virtio_gpu_context_create(vgdev, strlen(dbgname), dbgname, &id); + + vfpriv->ctx_id = id; + file->driver_priv = vfpriv; + return 0; +} + +void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv; + + if (!vgdev->has_virgl_3d) + return; + + vfpriv = file->driver_priv; + + virtio_gpu_context_destroy(vgdev, vfpriv->ctx_id); + kfree(vfpriv); + file->driver_priv = NULL; +} diff --git a/drivers/gpu/drm/virtio/virtgpu_ttm.c b/drivers/gpu/drm/virtio/virtgpu_ttm.c index b092d7b9a292..9fd924cd2b7f 100644 --- a/drivers/gpu/drm/virtio/virtgpu_ttm.c +++ b/drivers/gpu/drm/virtio/virtgpu_ttm.c @@ -32,6 +32,7 @@ #include #include #include +#include #include "virtgpu_drv.h" #include diff --git a/drivers/gpu/drm/virtio/virtgpu_vq.c b/drivers/gpu/drm/virtio/virtgpu_vq.c index ee25e9a4ae03..5a0f8a745b9d 100644 --- a/drivers/gpu/drm/virtio/virtgpu_vq.c +++ b/drivers/gpu/drm/virtio/virtgpu_vq.c @@ -586,6 +586,47 @@ static void virtio_gpu_cmd_get_display_info_cb(struct virtio_gpu_device *vgdev, drm_kms_helper_hotplug_event(vgdev->ddev); } +static void virtio_gpu_cmd_get_capset_info_cb(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) +{ + struct virtio_gpu_get_capset_info *cmd = + (struct virtio_gpu_get_capset_info *)vbuf->buf; + struct virtio_gpu_resp_capset_info *resp = + (struct virtio_gpu_resp_capset_info *)vbuf->resp_buf; + int i = le32_to_cpu(cmd->capset_index); + + spin_lock(&vgdev->display_info_lock); + vgdev->capsets[i].id = le32_to_cpu(resp->capset_id); + vgdev->capsets[i].max_version = le32_to_cpu(resp->capset_max_version); + vgdev->capsets[i].max_size = le32_to_cpu(resp->capset_max_size); + spin_unlock(&vgdev->display_info_lock); + wake_up(&vgdev->resp_wq); +} + +static void virtio_gpu_cmd_capset_cb(struct virtio_gpu_device *vgdev, + struct virtio_gpu_vbuffer *vbuf) +{ + struct virtio_gpu_get_capset *cmd = + (struct virtio_gpu_get_capset *)vbuf->buf; + struct virtio_gpu_resp_capset *resp = + (struct virtio_gpu_resp_capset *)vbuf->resp_buf; + struct virtio_gpu_drv_cap_cache *cache_ent; + + spin_lock(&vgdev->display_info_lock); + list_for_each_entry(cache_ent, &vgdev->cap_cache, head) { + if (cache_ent->version == le32_to_cpu(cmd->capset_version) && + cache_ent->id == le32_to_cpu(cmd->capset_id)) { + memcpy(cache_ent->caps_cache, resp->capset_data, + cache_ent->size); + atomic_set(&cache_ent->is_valid, 1); + break; + } + } + spin_unlock(&vgdev->display_info_lock); + wake_up(&vgdev->resp_wq); +} + + int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev) { struct virtio_gpu_ctrl_hdr *cmd_p; @@ -609,6 +650,230 @@ int virtio_gpu_cmd_get_display_info(struct virtio_gpu_device *vgdev) return 0; } +int virtio_gpu_cmd_get_capset_info(struct virtio_gpu_device *vgdev, int idx) +{ + struct virtio_gpu_get_capset_info *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + void *resp_buf; + + resp_buf = kzalloc(sizeof(struct virtio_gpu_resp_capset_info), + GFP_KERNEL); + if (!resp_buf) + return -ENOMEM; + + cmd_p = virtio_gpu_alloc_cmd_resp + (vgdev, &virtio_gpu_cmd_get_capset_info_cb, &vbuf, + sizeof(*cmd_p), sizeof(struct virtio_gpu_resp_capset_info), + resp_buf); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_GET_CAPSET_INFO); + cmd_p->capset_index = cpu_to_le32(idx); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + return 0; +} + +int virtio_gpu_cmd_get_capset(struct virtio_gpu_device *vgdev, + int idx, int version, + struct virtio_gpu_drv_cap_cache **cache_p) +{ + struct virtio_gpu_get_capset *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + int max_size = vgdev->capsets[idx].max_size; + struct virtio_gpu_drv_cap_cache *cache_ent; + void *resp_buf; + + if (idx > vgdev->num_capsets) + return -EINVAL; + + if (version > vgdev->capsets[idx].max_version) + return -EINVAL; + + cache_ent = kzalloc(sizeof(*cache_ent), GFP_KERNEL); + if (!cache_ent) + return -ENOMEM; + + cache_ent->caps_cache = kmalloc(max_size, GFP_KERNEL); + if (!cache_ent->caps_cache) { + kfree(cache_ent); + return -ENOMEM; + } + + resp_buf = kzalloc(sizeof(struct virtio_gpu_resp_capset) + max_size, + GFP_KERNEL); + if (!resp_buf) { + kfree(cache_ent->caps_cache); + kfree(cache_ent); + return -ENOMEM; + } + + cache_ent->version = version; + cache_ent->id = vgdev->capsets[idx].id; + atomic_set(&cache_ent->is_valid, 0); + cache_ent->size = max_size; + spin_lock(&vgdev->display_info_lock); + list_add_tail(&cache_ent->head, &vgdev->cap_cache); + spin_unlock(&vgdev->display_info_lock); + + cmd_p = virtio_gpu_alloc_cmd_resp + (vgdev, &virtio_gpu_cmd_capset_cb, &vbuf, sizeof(*cmd_p), + sizeof(struct virtio_gpu_resp_capset) + max_size, + resp_buf); + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_GET_CAPSET); + cmd_p->capset_id = cpu_to_le32(vgdev->capsets[idx].id); + cmd_p->capset_version = cpu_to_le32(version); + *cache_p = cache_ent; + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + + return 0; +} + +void virtio_gpu_cmd_context_create(struct virtio_gpu_device *vgdev, uint32_t id, + uint32_t nlen, const char *name) +{ + struct virtio_gpu_ctx_create *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_CREATE); + cmd_p->hdr.ctx_id = cpu_to_le32(id); + cmd_p->nlen = cpu_to_le32(nlen); + strncpy(cmd_p->debug_name, name, sizeof(cmd_p->debug_name)-1); + cmd_p->debug_name[sizeof(cmd_p->debug_name)-1] = 0; + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void virtio_gpu_cmd_context_destroy(struct virtio_gpu_device *vgdev, + uint32_t id) +{ + struct virtio_gpu_ctx_destroy *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_DESTROY); + cmd_p->hdr.ctx_id = cpu_to_le32(id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void virtio_gpu_cmd_context_attach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id) +{ + struct virtio_gpu_ctx_resource *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_ATTACH_RESOURCE); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); + +} + +void virtio_gpu_cmd_context_detach_resource(struct virtio_gpu_device *vgdev, + uint32_t ctx_id, + uint32_t resource_id) +{ + struct virtio_gpu_ctx_resource *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_CTX_DETACH_RESOURCE); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + virtio_gpu_queue_ctrl_buffer(vgdev, vbuf); +} + +void +virtio_gpu_cmd_resource_create_3d(struct virtio_gpu_device *vgdev, + struct virtio_gpu_resource_create_3d *rc_3d, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_resource_create_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + *cmd_p = *rc_3d; + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_RESOURCE_CREATE_3D); + cmd_p->hdr.flags = 0; + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_transfer_to_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_transfer_host_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + cmd_p->box = *box; + cmd_p->offset = cpu_to_le64(offset); + cmd_p->level = cpu_to_le32(level); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_transfer_from_host_3d(struct virtio_gpu_device *vgdev, + uint32_t resource_id, uint32_t ctx_id, + uint64_t offset, uint32_t level, + struct virtio_gpu_box *box, + struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_transfer_host_3d *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->resource_id = cpu_to_le32(resource_id); + cmd_p->box = *box; + cmd_p->offset = cpu_to_le64(offset); + cmd_p->level = cpu_to_le32(level); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + +void virtio_gpu_cmd_submit(struct virtio_gpu_device *vgdev, + void *data, uint32_t data_size, + uint32_t ctx_id, struct virtio_gpu_fence **fence) +{ + struct virtio_gpu_cmd_submit *cmd_p; + struct virtio_gpu_vbuffer *vbuf; + + cmd_p = virtio_gpu_alloc_cmd(vgdev, &vbuf, sizeof(*cmd_p)); + memset(cmd_p, 0, sizeof(*cmd_p)); + + vbuf->data_buf = data; + vbuf->data_size = data_size; + + cmd_p->hdr.type = cpu_to_le32(VIRTIO_GPU_CMD_SUBMIT_3D); + cmd_p->hdr.ctx_id = cpu_to_le32(ctx_id); + cmd_p->size = cpu_to_le32(data_size); + + virtio_gpu_queue_fenced_ctrl_buffer(vgdev, vbuf, &cmd_p->hdr, fence); +} + int virtio_gpu_object_attach(struct virtio_gpu_device *vgdev, struct virtio_gpu_object *obj, uint32_t resource_id, diff --git a/include/uapi/drm/Kbuild b/include/uapi/drm/Kbuild index 2d9a25daab05..38d437096c35 100644 --- a/include/uapi/drm/Kbuild +++ b/include/uapi/drm/Kbuild @@ -17,3 +17,4 @@ header-y += tegra_drm.h header-y += via_drm.h header-y += vmwgfx_drm.h header-y += msm_drm.h +header-y += virtgpu_drm.h diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h new file mode 100644 index 000000000000..fc9e2d6e5e2f --- /dev/null +++ b/include/uapi/drm/virtgpu_drm.h @@ -0,0 +1,167 @@ +/* + * Copyright 2013 Red Hat + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * 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 AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ +#ifndef VIRTGPU_DRM_H +#define VIRTGPU_DRM_H + +#include +#include "drm/drm.h" + +/* Please note that modifications to all structs defined here are + * subject to backwards-compatibility constraints. + * + * Do not use pointers, use uint64_t instead for 32 bit / 64 bit user/kernel + * compatibility Keep fields aligned to their size + */ + +#define DRM_VIRTGPU_MAP 0x01 +#define DRM_VIRTGPU_EXECBUFFER 0x02 +#define DRM_VIRTGPU_GETPARAM 0x03 +#define DRM_VIRTGPU_RESOURCE_CREATE 0x04 +#define DRM_VIRTGPU_RESOURCE_INFO 0x05 +#define DRM_VIRTGPU_TRANSFER_FROM_HOST 0x06 +#define DRM_VIRTGPU_TRANSFER_TO_HOST 0x07 +#define DRM_VIRTGPU_WAIT 0x08 +#define DRM_VIRTGPU_GET_CAPS 0x09 + +struct drm_virtgpu_map { + uint64_t offset; /* use for mmap system call */ + uint32_t handle; + uint32_t pad; +}; + +struct drm_virtgpu_execbuffer { + uint32_t flags; /* for future use */ + uint32_t size; + uint64_t command; /* void* */ + uint64_t bo_handles; + uint32_t num_bo_handles; + uint32_t pad; +}; + +#define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */ + +struct drm_virtgpu_getparam { + uint64_t param; + uint64_t value; +}; + +/* NO_BO flags? NO resource flag? */ +/* resource flag for y_0_top */ +struct drm_virtgpu_resource_create { + uint32_t target; + uint32_t format; + uint32_t bind; + uint32_t width; + uint32_t height; + uint32_t depth; + uint32_t array_size; + uint32_t last_level; + uint32_t nr_samples; + uint32_t flags; + uint32_t bo_handle; /* if this is set - recreate a new resource attached to this bo ? */ + uint32_t res_handle; /* returned by kernel */ + uint32_t size; /* validate transfer in the host */ + uint32_t stride; /* validate transfer in the host */ +}; + +struct drm_virtgpu_resource_info { + uint32_t bo_handle; + uint32_t res_handle; + uint32_t size; + uint32_t stride; +}; + +struct drm_virtgpu_3d_box { + uint32_t x; + uint32_t y; + uint32_t z; + uint32_t w; + uint32_t h; + uint32_t d; +}; + +struct drm_virtgpu_3d_transfer_to_host { + uint32_t bo_handle; + struct drm_virtgpu_3d_box box; + uint32_t level; + uint32_t offset; +}; + +struct drm_virtgpu_3d_transfer_from_host { + uint32_t bo_handle; + struct drm_virtgpu_3d_box box; + uint32_t level; + uint32_t offset; +}; + +#define VIRTGPU_WAIT_NOWAIT 1 /* like it */ +struct drm_virtgpu_3d_wait { + uint32_t handle; /* 0 is an invalid handle */ + uint32_t flags; +}; + +struct drm_virtgpu_get_caps { + uint32_t cap_set_id; + uint32_t cap_set_ver; + uint64_t addr; + uint32_t size; + uint32_t pad; +}; + +#define DRM_IOCTL_VIRTGPU_MAP \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map) + +#define DRM_IOCTL_VIRTGPU_EXECBUFFER \ + DRM_IOW(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\ + struct drm_virtgpu_execbuffer) + +#define DRM_IOCTL_VIRTGPU_GETPARAM \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_GETPARAM,\ + struct drm_virtgpu_getparam) + +#define DRM_IOCTL_VIRTGPU_RESOURCE_CREATE \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE, \ + struct drm_virtgpu_resource_create) + +#define DRM_IOCTL_VIRTGPU_RESOURCE_INFO \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_INFO, \ + struct drm_virtgpu_resource_info) + +#define DRM_IOCTL_VIRTGPU_TRANSFER_FROM_HOST \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_TRANSFER_FROM_HOST, \ + struct drm_virtgpu_3d_transfer_from_host) + +#define DRM_IOCTL_VIRTGPU_TRANSFER_TO_HOST \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_TRANSFER_TO_HOST, \ + struct drm_virtgpu_3d_transfer_to_host) + +#define DRM_IOCTL_VIRTGPU_WAIT \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_WAIT, \ + struct drm_virtgpu_3d_wait) + +#define DRM_IOCTL_VIRTGPU_GET_CAPS \ + DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_GET_CAPS, \ + struct drm_virtgpu_get_caps) + +#endif diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index 478be5270e26..7a63faa9065c 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -40,6 +40,8 @@ #include +#define VIRTIO_GPU_F_VIRGL 0 + enum virtio_gpu_ctrl_type { VIRTIO_GPU_UNDEFINED = 0, @@ -52,6 +54,18 @@ enum virtio_gpu_ctrl_type { VIRTIO_GPU_CMD_TRANSFER_TO_HOST_2D, VIRTIO_GPU_CMD_RESOURCE_ATTACH_BACKING, VIRTIO_GPU_CMD_RESOURCE_DETACH_BACKING, + VIRTIO_GPU_CMD_GET_CAPSET_INFO, + VIRTIO_GPU_CMD_GET_CAPSET, + + /* 3d commands */ + VIRTIO_GPU_CMD_CTX_CREATE = 0x0200, + VIRTIO_GPU_CMD_CTX_DESTROY, + VIRTIO_GPU_CMD_CTX_ATTACH_RESOURCE, + VIRTIO_GPU_CMD_CTX_DETACH_RESOURCE, + VIRTIO_GPU_CMD_RESOURCE_CREATE_3D, + VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D, + VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D, + VIRTIO_GPU_CMD_SUBMIT_3D, /* cursor commands */ VIRTIO_GPU_CMD_UPDATE_CURSOR = 0x0300, @@ -60,6 +74,8 @@ enum virtio_gpu_ctrl_type { /* success responses */ VIRTIO_GPU_RESP_OK_NODATA = 0x1100, VIRTIO_GPU_RESP_OK_DISPLAY_INFO, + VIRTIO_GPU_RESP_OK_CAPSET_INFO, + VIRTIO_GPU_RESP_OK_CAPSET, /* error responses */ VIRTIO_GPU_RESP_ERR_UNSPEC = 0x1200, @@ -180,13 +196,107 @@ struct virtio_gpu_resp_display_info { } pmodes[VIRTIO_GPU_MAX_SCANOUTS]; }; +/* data passed in the control vq, 3d related */ + +struct virtio_gpu_box { + __le32 x, y, z; + __le32 w, h, d; +}; + +/* VIRTIO_GPU_CMD_TRANSFER_TO_HOST_3D, VIRTIO_GPU_CMD_TRANSFER_FROM_HOST_3D */ +struct virtio_gpu_transfer_host_3d { + struct virtio_gpu_ctrl_hdr hdr; + struct virtio_gpu_box box; + __le64 offset; + __le32 resource_id; + __le32 level; + __le32 stride; + __le32 layer_stride; +}; + +/* VIRTIO_GPU_CMD_RESOURCE_CREATE_3D */ +#define VIRTIO_GPU_RESOURCE_FLAG_Y_0_TOP (1 << 0) +struct virtio_gpu_resource_create_3d { + struct virtio_gpu_ctrl_hdr hdr; + __le32 resource_id; + __le32 target; + __le32 format; + __le32 bind; + __le32 width; + __le32 height; + __le32 depth; + __le32 array_size; + __le32 last_level; + __le32 nr_samples; + __le32 flags; + __le32 padding; +}; + +/* VIRTIO_GPU_CMD_CTX_CREATE */ +struct virtio_gpu_ctx_create { + struct virtio_gpu_ctrl_hdr hdr; + __le32 nlen; + __le32 padding; + char debug_name[64]; +}; + +/* VIRTIO_GPU_CMD_CTX_DESTROY */ +struct virtio_gpu_ctx_destroy { + struct virtio_gpu_ctrl_hdr hdr; +}; + +/* VIRTIO_GPU_CMD_CTX_ATTACH_RESOURCE, VIRTIO_GPU_CMD_CTX_DETACH_RESOURCE */ +struct virtio_gpu_ctx_resource { + struct virtio_gpu_ctrl_hdr hdr; + __le32 resource_id; + __le32 padding; +}; + +/* VIRTIO_GPU_CMD_SUBMIT_3D */ +struct virtio_gpu_cmd_submit { + struct virtio_gpu_ctrl_hdr hdr; + __le32 size; + __le32 padding; +}; + +#define VIRTIO_GPU_CAPSET_VIRGL 1 + +/* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ +struct virtio_gpu_get_capset_info { + struct virtio_gpu_ctrl_hdr hdr; + __le32 capset_index; + __le32 padding; +}; + +/* VIRTIO_GPU_RESP_OK_CAPSET_INFO */ +struct virtio_gpu_resp_capset_info { + struct virtio_gpu_ctrl_hdr hdr; + __le32 capset_id; + __le32 capset_max_version; + __le32 capset_max_size; + __le32 padding; +}; + +/* VIRTIO_GPU_CMD_GET_CAPSET */ +struct virtio_gpu_get_capset { + struct virtio_gpu_ctrl_hdr hdr; + __le32 capset_id; + __le32 capset_version; +}; + +/* VIRTIO_GPU_RESP_OK_CAPSET */ +struct virtio_gpu_resp_capset { + struct virtio_gpu_ctrl_hdr hdr; + uint8_t capset_data[]; +}; + #define VIRTIO_GPU_EVENT_DISPLAY (1 << 0) struct virtio_gpu_config { __u32 events_read; __u32 events_clear; __u32 num_scanouts; - __u32 reserved; + __u32 num_capsets; }; /* simple formats for fbcon/X use */ -- cgit v1.2.3 From 22375f3e79b5b9e1dcbac998fd8473484d391d93 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:49 +0200 Subject: savage_drm.h: include Fixes compiler error: drm/savage_drm.h:50:24: error: array type has incomplete element type struct drm_tex_region texList[SAVAGE_NR_TEX_HEAPS][SAVAGE_NR_TEX_REGIONS + Signed-off-by: Mikko Rapeli Signed-off-by: Daniel Vetter --- include/uapi/drm/savage_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/savage_drm.h b/include/uapi/drm/savage_drm.h index 818d49be2e6e..9dc9dc1a7753 100644 --- a/include/uapi/drm/savage_drm.h +++ b/include/uapi/drm/savage_drm.h @@ -26,6 +26,8 @@ #ifndef __SAVAGE_DRM_H__ #define __SAVAGE_DRM_H__ +#include + #ifndef __SAVAGE_SAREA_DEFINES__ #define __SAVAGE_SAREA_DEFINES__ -- cgit v1.2.3 From 0aa4a4b8200c9e47021e8bd2d54b3d20ca407640 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:46 +0200 Subject: r128_drm.h: include drm/drm.h Fixes compile error: drm/r128_drm.h:156:23: error: array type has incomplete element type struct drm_clip_rect boxes[R128_NR_SAREA_CLIPRECTS]; Signed-off-by: Mikko Rapeli Signed-off-by: Daniel Vetter --- include/uapi/drm/r128_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/r128_drm.h b/include/uapi/drm/r128_drm.h index 8d8878b55f55..76b0aa3e8210 100644 --- a/include/uapi/drm/r128_drm.h +++ b/include/uapi/drm/r128_drm.h @@ -33,6 +33,8 @@ #ifndef __R128_DRM_H__ #define __R128_DRM_H__ +#include + /* WARNING: If you change any of these defines, make sure to change the * defines in the X server file (r128_sarea.h) */ -- cgit v1.2.3 From 70d994704e2c93a3d6be1de0c9f103fc7c186022 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:55:51 +0200 Subject: drm/i810_drm.h: include drm/drm.h Fixes userspace compilation error: error: array type has incomplete element type struct drm_clip_rect boxes[I810_NR_SAREA_CLIPRECTS]; Signed-off-by: Mikko Rapeli Signed-off-by: Daniel Vetter --- include/uapi/drm/i810_drm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/drm/i810_drm.h b/include/uapi/drm/i810_drm.h index 7a10bb6f2c0f..34736efd5824 100644 --- a/include/uapi/drm/i810_drm.h +++ b/include/uapi/drm/i810_drm.h @@ -1,6 +1,8 @@ #ifndef _I810_DRM_H_ #define _I810_DRM_H_ +#include + /* WARNING: These defines must be the same as what the Xserver uses. * if you change them, you must change the defines in the Xserver. */ -- cgit v1.2.3 From f902dd893427eade90f7eaf858e5ff8b150a5a12 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Wed, 14 Oct 2015 17:03:35 -0700 Subject: Input: add input-event-codes header file Add input-event-codes header file and move all type and axis defines there. The purpose of this new header file is to have a single canonical source for event-codes which can be used outside of C-code too. One example of such usage is the use of event-codes in devicetree source files. Signed-off-by: Hans de Goede Acked-by: Rob Herring Signed-off-by: Dmitry Torokhov --- include/uapi/linux/Kbuild | 1 + include/uapi/linux/input-event-codes.h | 805 +++++++++++++++++++++++++++++++++ include/uapi/linux/input.h | 788 +------------------------------- 3 files changed, 807 insertions(+), 787 deletions(-) create mode 100644 include/uapi/linux/input-event-codes.h (limited to 'include/uapi') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f7b2db44eb4b..0f263093cef9 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -191,6 +191,7 @@ header-y += inet_diag.h header-y += in.h header-y += inotify.h header-y += input.h +header-y += input-event-codes.h header-y += in_route.h header-y += ioctl.h header-y += ip6_tunnel.h diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h new file mode 100644 index 000000000000..87cf351bab03 --- /dev/null +++ b/include/uapi/linux/input-event-codes.h @@ -0,0 +1,805 @@ +/* + * Input event codes + * + * *** IMPORTANT *** + * This file is not only included from C-code but also from devicetree source + * files. As such this file MUST only contain comments and defines. + * + * Copyright (c) 1999-2002 Vojtech Pavlik + * Copyright (c) 2015 Hans de Goede + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ +#ifndef _UAPI_INPUT_EVENT_CODES_H +#define _UAPI_INPUT_EVENT_CODES_H + +/* + * Device properties and quirks + */ + +#define INPUT_PROP_POINTER 0x00 /* needs a pointer */ +#define INPUT_PROP_DIRECT 0x01 /* direct input devices */ +#define INPUT_PROP_BUTTONPAD 0x02 /* has button(s) under pad */ +#define INPUT_PROP_SEMI_MT 0x03 /* touch rectangle only */ +#define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ +#define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ +#define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ + +#define INPUT_PROP_MAX 0x1f +#define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) + +/* + * Event types + */ + +#define EV_SYN 0x00 +#define EV_KEY 0x01 +#define EV_REL 0x02 +#define EV_ABS 0x03 +#define EV_MSC 0x04 +#define EV_SW 0x05 +#define EV_LED 0x11 +#define EV_SND 0x12 +#define EV_REP 0x14 +#define EV_FF 0x15 +#define EV_PWR 0x16 +#define EV_FF_STATUS 0x17 +#define EV_MAX 0x1f +#define EV_CNT (EV_MAX+1) + +/* + * Synchronization events. + */ + +#define SYN_REPORT 0 +#define SYN_CONFIG 1 +#define SYN_MT_REPORT 2 +#define SYN_DROPPED 3 +#define SYN_MAX 0xf +#define SYN_CNT (SYN_MAX+1) + +/* + * Keys and buttons + * + * Most of the keys/buttons are modeled after USB HUT 1.12 + * (see http://www.usb.org/developers/hidpage). + * Abbreviations in the comments: + * AC - Application Control + * AL - Application Launch Button + * SC - System Control + */ + +#define KEY_RESERVED 0 +#define KEY_ESC 1 +#define KEY_1 2 +#define KEY_2 3 +#define KEY_3 4 +#define KEY_4 5 +#define KEY_5 6 +#define KEY_6 7 +#define KEY_7 8 +#define KEY_8 9 +#define KEY_9 10 +#define KEY_0 11 +#define KEY_MINUS 12 +#define KEY_EQUAL 13 +#define KEY_BACKSPACE 14 +#define KEY_TAB 15 +#define KEY_Q 16 +#define KEY_W 17 +#define KEY_E 18 +#define KEY_R 19 +#define KEY_T 20 +#define KEY_Y 21 +#define KEY_U 22 +#define KEY_I 23 +#define KEY_O 24 +#define KEY_P 25 +#define KEY_LEFTBRACE 26 +#define KEY_RIGHTBRACE 27 +#define KEY_ENTER 28 +#define KEY_LEFTCTRL 29 +#define KEY_A 30 +#define KEY_S 31 +#define KEY_D 32 +#define KEY_F 33 +#define KEY_G 34 +#define KEY_H 35 +#define KEY_J 36 +#define KEY_K 37 +#define KEY_L 38 +#define KEY_SEMICOLON 39 +#define KEY_APOSTROPHE 40 +#define KEY_GRAVE 41 +#define KEY_LEFTSHIFT 42 +#define KEY_BACKSLASH 43 +#define KEY_Z 44 +#define KEY_X 45 +#define KEY_C 46 +#define KEY_V 47 +#define KEY_B 48 +#define KEY_N 49 +#define KEY_M 50 +#define KEY_COMMA 51 +#define KEY_DOT 52 +#define KEY_SLASH 53 +#define KEY_RIGHTSHIFT 54 +#define KEY_KPASTERISK 55 +#define KEY_LEFTALT 56 +#define KEY_SPACE 57 +#define KEY_CAPSLOCK 58 +#define KEY_F1 59 +#define KEY_F2 60 +#define KEY_F3 61 +#define KEY_F4 62 +#define KEY_F5 63 +#define KEY_F6 64 +#define KEY_F7 65 +#define KEY_F8 66 +#define KEY_F9 67 +#define KEY_F10 68 +#define KEY_NUMLOCK 69 +#define KEY_SCROLLLOCK 70 +#define KEY_KP7 71 +#define KEY_KP8 72 +#define KEY_KP9 73 +#define KEY_KPMINUS 74 +#define KEY_KP4 75 +#define KEY_KP5 76 +#define KEY_KP6 77 +#define KEY_KPPLUS 78 +#define KEY_KP1 79 +#define KEY_KP2 80 +#define KEY_KP3 81 +#define KEY_KP0 82 +#define KEY_KPDOT 83 + +#define KEY_ZENKAKUHANKAKU 85 +#define KEY_102ND 86 +#define KEY_F11 87 +#define KEY_F12 88 +#define KEY_RO 89 +#define KEY_KATAKANA 90 +#define KEY_HIRAGANA 91 +#define KEY_HENKAN 92 +#define KEY_KATAKANAHIRAGANA 93 +#define KEY_MUHENKAN 94 +#define KEY_KPJPCOMMA 95 +#define KEY_KPENTER 96 +#define KEY_RIGHTCTRL 97 +#define KEY_KPSLASH 98 +#define KEY_SYSRQ 99 +#define KEY_RIGHTALT 100 +#define KEY_LINEFEED 101 +#define KEY_HOME 102 +#define KEY_UP 103 +#define KEY_PAGEUP 104 +#define KEY_LEFT 105 +#define KEY_RIGHT 106 +#define KEY_END 107 +#define KEY_DOWN 108 +#define KEY_PAGEDOWN 109 +#define KEY_INSERT 110 +#define KEY_DELETE 111 +#define KEY_MACRO 112 +#define KEY_MUTE 113 +#define KEY_VOLUMEDOWN 114 +#define KEY_VOLUMEUP 115 +#define KEY_POWER 116 /* SC System Power Down */ +#define KEY_KPEQUAL 117 +#define KEY_KPPLUSMINUS 118 +#define KEY_PAUSE 119 +#define KEY_SCALE 120 /* AL Compiz Scale (Expose) */ + +#define KEY_KPCOMMA 121 +#define KEY_HANGEUL 122 +#define KEY_HANGUEL KEY_HANGEUL +#define KEY_HANJA 123 +#define KEY_YEN 124 +#define KEY_LEFTMETA 125 +#define KEY_RIGHTMETA 126 +#define KEY_COMPOSE 127 + +#define KEY_STOP 128 /* AC Stop */ +#define KEY_AGAIN 129 +#define KEY_PROPS 130 /* AC Properties */ +#define KEY_UNDO 131 /* AC Undo */ +#define KEY_FRONT 132 +#define KEY_COPY 133 /* AC Copy */ +#define KEY_OPEN 134 /* AC Open */ +#define KEY_PASTE 135 /* AC Paste */ +#define KEY_FIND 136 /* AC Search */ +#define KEY_CUT 137 /* AC Cut */ +#define KEY_HELP 138 /* AL Integrated Help Center */ +#define KEY_MENU 139 /* Menu (show menu) */ +#define KEY_CALC 140 /* AL Calculator */ +#define KEY_SETUP 141 +#define KEY_SLEEP 142 /* SC System Sleep */ +#define KEY_WAKEUP 143 /* System Wake Up */ +#define KEY_FILE 144 /* AL Local Machine Browser */ +#define KEY_SENDFILE 145 +#define KEY_DELETEFILE 146 +#define KEY_XFER 147 +#define KEY_PROG1 148 +#define KEY_PROG2 149 +#define KEY_WWW 150 /* AL Internet Browser */ +#define KEY_MSDOS 151 +#define KEY_COFFEE 152 /* AL Terminal Lock/Screensaver */ +#define KEY_SCREENLOCK KEY_COFFEE +#define KEY_ROTATE_DISPLAY 153 /* Display orientation for e.g. tablets */ +#define KEY_DIRECTION KEY_ROTATE_DISPLAY +#define KEY_CYCLEWINDOWS 154 +#define KEY_MAIL 155 +#define KEY_BOOKMARKS 156 /* AC Bookmarks */ +#define KEY_COMPUTER 157 +#define KEY_BACK 158 /* AC Back */ +#define KEY_FORWARD 159 /* AC Forward */ +#define KEY_CLOSECD 160 +#define KEY_EJECTCD 161 +#define KEY_EJECTCLOSECD 162 +#define KEY_NEXTSONG 163 +#define KEY_PLAYPAUSE 164 +#define KEY_PREVIOUSSONG 165 +#define KEY_STOPCD 166 +#define KEY_RECORD 167 +#define KEY_REWIND 168 +#define KEY_PHONE 169 /* Media Select Telephone */ +#define KEY_ISO 170 +#define KEY_CONFIG 171 /* AL Consumer Control Configuration */ +#define KEY_HOMEPAGE 172 /* AC Home */ +#define KEY_REFRESH 173 /* AC Refresh */ +#define KEY_EXIT 174 /* AC Exit */ +#define KEY_MOVE 175 +#define KEY_EDIT 176 +#define KEY_SCROLLUP 177 +#define KEY_SCROLLDOWN 178 +#define KEY_KPLEFTPAREN 179 +#define KEY_KPRIGHTPAREN 180 +#define KEY_NEW 181 /* AC New */ +#define KEY_REDO 182 /* AC Redo/Repeat */ + +#define KEY_F13 183 +#define KEY_F14 184 +#define KEY_F15 185 +#define KEY_F16 186 +#define KEY_F17 187 +#define KEY_F18 188 +#define KEY_F19 189 +#define KEY_F20 190 +#define KEY_F21 191 +#define KEY_F22 192 +#define KEY_F23 193 +#define KEY_F24 194 + +#define KEY_PLAYCD 200 +#define KEY_PAUSECD 201 +#define KEY_PROG3 202 +#define KEY_PROG4 203 +#define KEY_DASHBOARD 204 /* AL Dashboard */ +#define KEY_SUSPEND 205 +#define KEY_CLOSE 206 /* AC Close */ +#define KEY_PLAY 207 +#define KEY_FASTFORWARD 208 +#define KEY_BASSBOOST 209 +#define KEY_PRINT 210 /* AC Print */ +#define KEY_HP 211 +#define KEY_CAMERA 212 +#define KEY_SOUND 213 +#define KEY_QUESTION 214 +#define KEY_EMAIL 215 +#define KEY_CHAT 216 +#define KEY_SEARCH 217 +#define KEY_CONNECT 218 +#define KEY_FINANCE 219 /* AL Checkbook/Finance */ +#define KEY_SPORT 220 +#define KEY_SHOP 221 +#define KEY_ALTERASE 222 +#define KEY_CANCEL 223 /* AC Cancel */ +#define KEY_BRIGHTNESSDOWN 224 +#define KEY_BRIGHTNESSUP 225 +#define KEY_MEDIA 226 + +#define KEY_SWITCHVIDEOMODE 227 /* Cycle between available video + outputs (Monitor/LCD/TV-out/etc) */ +#define KEY_KBDILLUMTOGGLE 228 +#define KEY_KBDILLUMDOWN 229 +#define KEY_KBDILLUMUP 230 + +#define KEY_SEND 231 /* AC Send */ +#define KEY_REPLY 232 /* AC Reply */ +#define KEY_FORWARDMAIL 233 /* AC Forward Msg */ +#define KEY_SAVE 234 /* AC Save */ +#define KEY_DOCUMENTS 235 + +#define KEY_BATTERY 236 + +#define KEY_BLUETOOTH 237 +#define KEY_WLAN 238 +#define KEY_UWB 239 + +#define KEY_UNKNOWN 240 + +#define KEY_VIDEO_NEXT 241 /* drive next video source */ +#define KEY_VIDEO_PREV 242 /* drive previous video source */ +#define KEY_BRIGHTNESS_CYCLE 243 /* brightness up, after max is min */ +#define KEY_BRIGHTNESS_AUTO 244 /* Set Auto Brightness: manual + brightness control is off, + rely on ambient */ +#define KEY_BRIGHTNESS_ZERO KEY_BRIGHTNESS_AUTO +#define KEY_DISPLAY_OFF 245 /* display device to off state */ + +#define KEY_WWAN 246 /* Wireless WAN (LTE, UMTS, GSM, etc.) */ +#define KEY_WIMAX KEY_WWAN +#define KEY_RFKILL 247 /* Key that controls all radios */ + +#define KEY_MICMUTE 248 /* Mute / unmute the microphone */ + +/* Code 255 is reserved for special needs of AT keyboard driver */ + +#define BTN_MISC 0x100 +#define BTN_0 0x100 +#define BTN_1 0x101 +#define BTN_2 0x102 +#define BTN_3 0x103 +#define BTN_4 0x104 +#define BTN_5 0x105 +#define BTN_6 0x106 +#define BTN_7 0x107 +#define BTN_8 0x108 +#define BTN_9 0x109 + +#define BTN_MOUSE 0x110 +#define BTN_LEFT 0x110 +#define BTN_RIGHT 0x111 +#define BTN_MIDDLE 0x112 +#define BTN_SIDE 0x113 +#define BTN_EXTRA 0x114 +#define BTN_FORWARD 0x115 +#define BTN_BACK 0x116 +#define BTN_TASK 0x117 + +#define BTN_JOYSTICK 0x120 +#define BTN_TRIGGER 0x120 +#define BTN_THUMB 0x121 +#define BTN_THUMB2 0x122 +#define BTN_TOP 0x123 +#define BTN_TOP2 0x124 +#define BTN_PINKIE 0x125 +#define BTN_BASE 0x126 +#define BTN_BASE2 0x127 +#define BTN_BASE3 0x128 +#define BTN_BASE4 0x129 +#define BTN_BASE5 0x12a +#define BTN_BASE6 0x12b +#define BTN_DEAD 0x12f + +#define BTN_GAMEPAD 0x130 +#define BTN_SOUTH 0x130 +#define BTN_A BTN_SOUTH +#define BTN_EAST 0x131 +#define BTN_B BTN_EAST +#define BTN_C 0x132 +#define BTN_NORTH 0x133 +#define BTN_X BTN_NORTH +#define BTN_WEST 0x134 +#define BTN_Y BTN_WEST +#define BTN_Z 0x135 +#define BTN_TL 0x136 +#define BTN_TR 0x137 +#define BTN_TL2 0x138 +#define BTN_TR2 0x139 +#define BTN_SELECT 0x13a +#define BTN_START 0x13b +#define BTN_MODE 0x13c +#define BTN_THUMBL 0x13d +#define BTN_THUMBR 0x13e + +#define BTN_DIGI 0x140 +#define BTN_TOOL_PEN 0x140 +#define BTN_TOOL_RUBBER 0x141 +#define BTN_TOOL_BRUSH 0x142 +#define BTN_TOOL_PENCIL 0x143 +#define BTN_TOOL_AIRBRUSH 0x144 +#define BTN_TOOL_FINGER 0x145 +#define BTN_TOOL_MOUSE 0x146 +#define BTN_TOOL_LENS 0x147 +#define BTN_TOOL_QUINTTAP 0x148 /* Five fingers on trackpad */ +#define BTN_TOUCH 0x14a +#define BTN_STYLUS 0x14b +#define BTN_STYLUS2 0x14c +#define BTN_TOOL_DOUBLETAP 0x14d +#define BTN_TOOL_TRIPLETAP 0x14e +#define BTN_TOOL_QUADTAP 0x14f /* Four fingers on trackpad */ + +#define BTN_WHEEL 0x150 +#define BTN_GEAR_DOWN 0x150 +#define BTN_GEAR_UP 0x151 + +#define KEY_OK 0x160 +#define KEY_SELECT 0x161 +#define KEY_GOTO 0x162 +#define KEY_CLEAR 0x163 +#define KEY_POWER2 0x164 +#define KEY_OPTION 0x165 +#define KEY_INFO 0x166 /* AL OEM Features/Tips/Tutorial */ +#define KEY_TIME 0x167 +#define KEY_VENDOR 0x168 +#define KEY_ARCHIVE 0x169 +#define KEY_PROGRAM 0x16a /* Media Select Program Guide */ +#define KEY_CHANNEL 0x16b +#define KEY_FAVORITES 0x16c +#define KEY_EPG 0x16d +#define KEY_PVR 0x16e /* Media Select Home */ +#define KEY_MHP 0x16f +#define KEY_LANGUAGE 0x170 +#define KEY_TITLE 0x171 +#define KEY_SUBTITLE 0x172 +#define KEY_ANGLE 0x173 +#define KEY_ZOOM 0x174 +#define KEY_MODE 0x175 +#define KEY_KEYBOARD 0x176 +#define KEY_SCREEN 0x177 +#define KEY_PC 0x178 /* Media Select Computer */ +#define KEY_TV 0x179 /* Media Select TV */ +#define KEY_TV2 0x17a /* Media Select Cable */ +#define KEY_VCR 0x17b /* Media Select VCR */ +#define KEY_VCR2 0x17c /* VCR Plus */ +#define KEY_SAT 0x17d /* Media Select Satellite */ +#define KEY_SAT2 0x17e +#define KEY_CD 0x17f /* Media Select CD */ +#define KEY_TAPE 0x180 /* Media Select Tape */ +#define KEY_RADIO 0x181 +#define KEY_TUNER 0x182 /* Media Select Tuner */ +#define KEY_PLAYER 0x183 +#define KEY_TEXT 0x184 +#define KEY_DVD 0x185 /* Media Select DVD */ +#define KEY_AUX 0x186 +#define KEY_MP3 0x187 +#define KEY_AUDIO 0x188 /* AL Audio Browser */ +#define KEY_VIDEO 0x189 /* AL Movie Browser */ +#define KEY_DIRECTORY 0x18a +#define KEY_LIST 0x18b +#define KEY_MEMO 0x18c /* Media Select Messages */ +#define KEY_CALENDAR 0x18d +#define KEY_RED 0x18e +#define KEY_GREEN 0x18f +#define KEY_YELLOW 0x190 +#define KEY_BLUE 0x191 +#define KEY_CHANNELUP 0x192 /* Channel Increment */ +#define KEY_CHANNELDOWN 0x193 /* Channel Decrement */ +#define KEY_FIRST 0x194 +#define KEY_LAST 0x195 /* Recall Last */ +#define KEY_AB 0x196 +#define KEY_NEXT 0x197 +#define KEY_RESTART 0x198 +#define KEY_SLOW 0x199 +#define KEY_SHUFFLE 0x19a +#define KEY_BREAK 0x19b +#define KEY_PREVIOUS 0x19c +#define KEY_DIGITS 0x19d +#define KEY_TEEN 0x19e +#define KEY_TWEN 0x19f +#define KEY_VIDEOPHONE 0x1a0 /* Media Select Video Phone */ +#define KEY_GAMES 0x1a1 /* Media Select Games */ +#define KEY_ZOOMIN 0x1a2 /* AC Zoom In */ +#define KEY_ZOOMOUT 0x1a3 /* AC Zoom Out */ +#define KEY_ZOOMRESET 0x1a4 /* AC Zoom */ +#define KEY_WORDPROCESSOR 0x1a5 /* AL Word Processor */ +#define KEY_EDITOR 0x1a6 /* AL Text Editor */ +#define KEY_SPREADSHEET 0x1a7 /* AL Spreadsheet */ +#define KEY_GRAPHICSEDITOR 0x1a8 /* AL Graphics Editor */ +#define KEY_PRESENTATION 0x1a9 /* AL Presentation App */ +#define KEY_DATABASE 0x1aa /* AL Database App */ +#define KEY_NEWS 0x1ab /* AL Newsreader */ +#define KEY_VOICEMAIL 0x1ac /* AL Voicemail */ +#define KEY_ADDRESSBOOK 0x1ad /* AL Contacts/Address Book */ +#define KEY_MESSENGER 0x1ae /* AL Instant Messaging */ +#define KEY_DISPLAYTOGGLE 0x1af /* Turn display (LCD) on and off */ +#define KEY_BRIGHTNESS_TOGGLE KEY_DISPLAYTOGGLE +#define KEY_SPELLCHECK 0x1b0 /* AL Spell Check */ +#define KEY_LOGOFF 0x1b1 /* AL Logoff */ + +#define KEY_DOLLAR 0x1b2 +#define KEY_EURO 0x1b3 + +#define KEY_FRAMEBACK 0x1b4 /* Consumer - transport controls */ +#define KEY_FRAMEFORWARD 0x1b5 +#define KEY_CONTEXT_MENU 0x1b6 /* GenDesc - system context menu */ +#define KEY_MEDIA_REPEAT 0x1b7 /* Consumer - transport control */ +#define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ +#define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ +#define KEY_IMAGES 0x1ba /* AL Image Browser */ + +#define KEY_DEL_EOL 0x1c0 +#define KEY_DEL_EOS 0x1c1 +#define KEY_INS_LINE 0x1c2 +#define KEY_DEL_LINE 0x1c3 + +#define KEY_FN 0x1d0 +#define KEY_FN_ESC 0x1d1 +#define KEY_FN_F1 0x1d2 +#define KEY_FN_F2 0x1d3 +#define KEY_FN_F3 0x1d4 +#define KEY_FN_F4 0x1d5 +#define KEY_FN_F5 0x1d6 +#define KEY_FN_F6 0x1d7 +#define KEY_FN_F7 0x1d8 +#define KEY_FN_F8 0x1d9 +#define KEY_FN_F9 0x1da +#define KEY_FN_F10 0x1db +#define KEY_FN_F11 0x1dc +#define KEY_FN_F12 0x1dd +#define KEY_FN_1 0x1de +#define KEY_FN_2 0x1df +#define KEY_FN_D 0x1e0 +#define KEY_FN_E 0x1e1 +#define KEY_FN_F 0x1e2 +#define KEY_FN_S 0x1e3 +#define KEY_FN_B 0x1e4 + +#define KEY_BRL_DOT1 0x1f1 +#define KEY_BRL_DOT2 0x1f2 +#define KEY_BRL_DOT3 0x1f3 +#define KEY_BRL_DOT4 0x1f4 +#define KEY_BRL_DOT5 0x1f5 +#define KEY_BRL_DOT6 0x1f6 +#define KEY_BRL_DOT7 0x1f7 +#define KEY_BRL_DOT8 0x1f8 +#define KEY_BRL_DOT9 0x1f9 +#define KEY_BRL_DOT10 0x1fa + +#define KEY_NUMERIC_0 0x200 /* used by phones, remote controls, */ +#define KEY_NUMERIC_1 0x201 /* and other keypads */ +#define KEY_NUMERIC_2 0x202 +#define KEY_NUMERIC_3 0x203 +#define KEY_NUMERIC_4 0x204 +#define KEY_NUMERIC_5 0x205 +#define KEY_NUMERIC_6 0x206 +#define KEY_NUMERIC_7 0x207 +#define KEY_NUMERIC_8 0x208 +#define KEY_NUMERIC_9 0x209 +#define KEY_NUMERIC_STAR 0x20a +#define KEY_NUMERIC_POUND 0x20b +#define KEY_NUMERIC_A 0x20c /* Phone key A - HUT Telephony 0xb9 */ +#define KEY_NUMERIC_B 0x20d +#define KEY_NUMERIC_C 0x20e +#define KEY_NUMERIC_D 0x20f + +#define KEY_CAMERA_FOCUS 0x210 +#define KEY_WPS_BUTTON 0x211 /* WiFi Protected Setup key */ + +#define KEY_TOUCHPAD_TOGGLE 0x212 /* Request switch touchpad on or off */ +#define KEY_TOUCHPAD_ON 0x213 +#define KEY_TOUCHPAD_OFF 0x214 + +#define KEY_CAMERA_ZOOMIN 0x215 +#define KEY_CAMERA_ZOOMOUT 0x216 +#define KEY_CAMERA_UP 0x217 +#define KEY_CAMERA_DOWN 0x218 +#define KEY_CAMERA_LEFT 0x219 +#define KEY_CAMERA_RIGHT 0x21a + +#define KEY_ATTENDANT_ON 0x21b +#define KEY_ATTENDANT_OFF 0x21c +#define KEY_ATTENDANT_TOGGLE 0x21d /* Attendant call on or off */ +#define KEY_LIGHTS_TOGGLE 0x21e /* Reading light on or off */ + +#define BTN_DPAD_UP 0x220 +#define BTN_DPAD_DOWN 0x221 +#define BTN_DPAD_LEFT 0x222 +#define BTN_DPAD_RIGHT 0x223 + +#define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ + +#define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ +#define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ +#define KEY_JOURNAL 0x242 /* AL Log/Journal/Timecard */ +#define KEY_CONTROLPANEL 0x243 /* AL Control Panel */ +#define KEY_APPSELECT 0x244 /* AL Select Task/Application */ +#define KEY_SCREENSAVER 0x245 /* AL Screen Saver */ +#define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */ + +#define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ +#define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ + +#define KEY_KBDINPUTASSIST_PREV 0x260 +#define KEY_KBDINPUTASSIST_NEXT 0x261 +#define KEY_KBDINPUTASSIST_PREVGROUP 0x262 +#define KEY_KBDINPUTASSIST_NEXTGROUP 0x263 +#define KEY_KBDINPUTASSIST_ACCEPT 0x264 +#define KEY_KBDINPUTASSIST_CANCEL 0x265 + +#define BTN_TRIGGER_HAPPY 0x2c0 +#define BTN_TRIGGER_HAPPY1 0x2c0 +#define BTN_TRIGGER_HAPPY2 0x2c1 +#define BTN_TRIGGER_HAPPY3 0x2c2 +#define BTN_TRIGGER_HAPPY4 0x2c3 +#define BTN_TRIGGER_HAPPY5 0x2c4 +#define BTN_TRIGGER_HAPPY6 0x2c5 +#define BTN_TRIGGER_HAPPY7 0x2c6 +#define BTN_TRIGGER_HAPPY8 0x2c7 +#define BTN_TRIGGER_HAPPY9 0x2c8 +#define BTN_TRIGGER_HAPPY10 0x2c9 +#define BTN_TRIGGER_HAPPY11 0x2ca +#define BTN_TRIGGER_HAPPY12 0x2cb +#define BTN_TRIGGER_HAPPY13 0x2cc +#define BTN_TRIGGER_HAPPY14 0x2cd +#define BTN_TRIGGER_HAPPY15 0x2ce +#define BTN_TRIGGER_HAPPY16 0x2cf +#define BTN_TRIGGER_HAPPY17 0x2d0 +#define BTN_TRIGGER_HAPPY18 0x2d1 +#define BTN_TRIGGER_HAPPY19 0x2d2 +#define BTN_TRIGGER_HAPPY20 0x2d3 +#define BTN_TRIGGER_HAPPY21 0x2d4 +#define BTN_TRIGGER_HAPPY22 0x2d5 +#define BTN_TRIGGER_HAPPY23 0x2d6 +#define BTN_TRIGGER_HAPPY24 0x2d7 +#define BTN_TRIGGER_HAPPY25 0x2d8 +#define BTN_TRIGGER_HAPPY26 0x2d9 +#define BTN_TRIGGER_HAPPY27 0x2da +#define BTN_TRIGGER_HAPPY28 0x2db +#define BTN_TRIGGER_HAPPY29 0x2dc +#define BTN_TRIGGER_HAPPY30 0x2dd +#define BTN_TRIGGER_HAPPY31 0x2de +#define BTN_TRIGGER_HAPPY32 0x2df +#define BTN_TRIGGER_HAPPY33 0x2e0 +#define BTN_TRIGGER_HAPPY34 0x2e1 +#define BTN_TRIGGER_HAPPY35 0x2e2 +#define BTN_TRIGGER_HAPPY36 0x2e3 +#define BTN_TRIGGER_HAPPY37 0x2e4 +#define BTN_TRIGGER_HAPPY38 0x2e5 +#define BTN_TRIGGER_HAPPY39 0x2e6 +#define BTN_TRIGGER_HAPPY40 0x2e7 + +/* We avoid low common keys in module aliases so they don't get huge. */ +#define KEY_MIN_INTERESTING KEY_MUTE +#define KEY_MAX 0x2ff +#define KEY_CNT (KEY_MAX+1) + +/* + * Relative axes + */ + +#define REL_X 0x00 +#define REL_Y 0x01 +#define REL_Z 0x02 +#define REL_RX 0x03 +#define REL_RY 0x04 +#define REL_RZ 0x05 +#define REL_HWHEEL 0x06 +#define REL_DIAL 0x07 +#define REL_WHEEL 0x08 +#define REL_MISC 0x09 +#define REL_MAX 0x0f +#define REL_CNT (REL_MAX+1) + +/* + * Absolute axes + */ + +#define ABS_X 0x00 +#define ABS_Y 0x01 +#define ABS_Z 0x02 +#define ABS_RX 0x03 +#define ABS_RY 0x04 +#define ABS_RZ 0x05 +#define ABS_THROTTLE 0x06 +#define ABS_RUDDER 0x07 +#define ABS_WHEEL 0x08 +#define ABS_GAS 0x09 +#define ABS_BRAKE 0x0a +#define ABS_HAT0X 0x10 +#define ABS_HAT0Y 0x11 +#define ABS_HAT1X 0x12 +#define ABS_HAT1Y 0x13 +#define ABS_HAT2X 0x14 +#define ABS_HAT2Y 0x15 +#define ABS_HAT3X 0x16 +#define ABS_HAT3Y 0x17 +#define ABS_PRESSURE 0x18 +#define ABS_DISTANCE 0x19 +#define ABS_TILT_X 0x1a +#define ABS_TILT_Y 0x1b +#define ABS_TOOL_WIDTH 0x1c + +#define ABS_VOLUME 0x20 + +#define ABS_MISC 0x28 + +#define ABS_MT_SLOT 0x2f /* MT slot being modified */ +#define ABS_MT_TOUCH_MAJOR 0x30 /* Major axis of touching ellipse */ +#define ABS_MT_TOUCH_MINOR 0x31 /* Minor axis (omit if circular) */ +#define ABS_MT_WIDTH_MAJOR 0x32 /* Major axis of approaching ellipse */ +#define ABS_MT_WIDTH_MINOR 0x33 /* Minor axis (omit if circular) */ +#define ABS_MT_ORIENTATION 0x34 /* Ellipse orientation */ +#define ABS_MT_POSITION_X 0x35 /* Center X touch position */ +#define ABS_MT_POSITION_Y 0x36 /* Center Y touch position */ +#define ABS_MT_TOOL_TYPE 0x37 /* Type of touching device */ +#define ABS_MT_BLOB_ID 0x38 /* Group a set of packets as a blob */ +#define ABS_MT_TRACKING_ID 0x39 /* Unique ID of initiated contact */ +#define ABS_MT_PRESSURE 0x3a /* Pressure on contact area */ +#define ABS_MT_DISTANCE 0x3b /* Contact hover distance */ +#define ABS_MT_TOOL_X 0x3c /* Center X tool position */ +#define ABS_MT_TOOL_Y 0x3d /* Center Y tool position */ + + +#define ABS_MAX 0x3f +#define ABS_CNT (ABS_MAX+1) + +/* + * Switch events + */ + +#define SW_LID 0x00 /* set = lid shut */ +#define SW_TABLET_MODE 0x01 /* set = tablet mode */ +#define SW_HEADPHONE_INSERT 0x02 /* set = inserted */ +#define SW_RFKILL_ALL 0x03 /* rfkill master switch, type "any" + set = radio enabled */ +#define SW_RADIO SW_RFKILL_ALL /* deprecated */ +#define SW_MICROPHONE_INSERT 0x04 /* set = inserted */ +#define SW_DOCK 0x05 /* set = plugged into dock */ +#define SW_LINEOUT_INSERT 0x06 /* set = inserted */ +#define SW_JACK_PHYSICAL_INSERT 0x07 /* set = mechanical switch set */ +#define SW_VIDEOOUT_INSERT 0x08 /* set = inserted */ +#define SW_CAMERA_LENS_COVER 0x09 /* set = lens covered */ +#define SW_KEYPAD_SLIDE 0x0a /* set = keypad slide out */ +#define SW_FRONT_PROXIMITY 0x0b /* set = front proximity sensor active */ +#define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ +#define SW_LINEIN_INSERT 0x0d /* set = inserted */ +#define SW_MUTE_DEVICE 0x0e /* set = device disabled */ +#define SW_MAX 0x0f +#define SW_CNT (SW_MAX+1) + +/* + * Misc events + */ + +#define MSC_SERIAL 0x00 +#define MSC_PULSELED 0x01 +#define MSC_GESTURE 0x02 +#define MSC_RAW 0x03 +#define MSC_SCAN 0x04 +#define MSC_TIMESTAMP 0x05 +#define MSC_MAX 0x07 +#define MSC_CNT (MSC_MAX+1) + +/* + * LEDs + */ + +#define LED_NUML 0x00 +#define LED_CAPSL 0x01 +#define LED_SCROLLL 0x02 +#define LED_COMPOSE 0x03 +#define LED_KANA 0x04 +#define LED_SLEEP 0x05 +#define LED_SUSPEND 0x06 +#define LED_MUTE 0x07 +#define LED_MISC 0x08 +#define LED_MAIL 0x09 +#define LED_CHARGING 0x0a +#define LED_MAX 0x0f +#define LED_CNT (LED_MAX+1) + +/* + * Autorepeat values + */ + +#define REP_DELAY 0x00 +#define REP_PERIOD 0x01 +#define REP_MAX 0x01 +#define REP_CNT (REP_MAX+1) + +/* + * Sounds + */ + +#define SND_CLICK 0x00 +#define SND_BELL 0x01 +#define SND_TONE 0x02 +#define SND_MAX 0x07 +#define SND_CNT (SND_MAX+1) + +#endif diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 731417c025f6..f24043a12777 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -16,6 +16,7 @@ #include #endif +#include "input-event-codes.h" /* * The event structure itself @@ -156,793 +157,6 @@ struct input_keymap_entry { #define EVIOCSCLOCKID _IOW('E', 0xa0, int) /* Set clockid to be used for timestamps */ -/* - * Device properties and quirks - */ - -#define INPUT_PROP_POINTER 0x00 /* needs a pointer */ -#define INPUT_PROP_DIRECT 0x01 /* direct input devices */ -#define INPUT_PROP_BUTTONPAD 0x02 /* has button(s) under pad */ -#define INPUT_PROP_SEMI_MT 0x03 /* touch rectangle only */ -#define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ -#define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ -#define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ - -#define INPUT_PROP_MAX 0x1f -#define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) - -/* - * Event types - */ - -#define EV_SYN 0x00 -#define EV_KEY 0x01 -#define EV_REL 0x02 -#define EV_ABS 0x03 -#define EV_MSC 0x04 -#define EV_SW 0x05 -#define EV_LED 0x11 -#define EV_SND 0x12 -#define EV_REP 0x14 -#define EV_FF 0x15 -#define EV_PWR 0x16 -#define EV_FF_STATUS 0x17 -#define EV_MAX 0x1f -#define EV_CNT (EV_MAX+1) - -/* - * Synchronization events. - */ - -#define SYN_REPORT 0 -#define SYN_CONFIG 1 -#define SYN_MT_REPORT 2 -#define SYN_DROPPED 3 -#define SYN_MAX 0xf -#define SYN_CNT (SYN_MAX+1) - -/* - * Keys and buttons - * - * Most of the keys/buttons are modeled after USB HUT 1.12 - * (see http://www.usb.org/developers/hidpage). - * Abbreviations in the comments: - * AC - Application Control - * AL - Application Launch Button - * SC - System Control - */ - -#define KEY_RESERVED 0 -#define KEY_ESC 1 -#define KEY_1 2 -#define KEY_2 3 -#define KEY_3 4 -#define KEY_4 5 -#define KEY_5 6 -#define KEY_6 7 -#define KEY_7 8 -#define KEY_8 9 -#define KEY_9 10 -#define KEY_0 11 -#define KEY_MINUS 12 -#define KEY_EQUAL 13 -#define KEY_BACKSPACE 14 -#define KEY_TAB 15 -#define KEY_Q 16 -#define KEY_W 17 -#define KEY_E 18 -#define KEY_R 19 -#define KEY_T 20 -#define KEY_Y 21 -#define KEY_U 22 -#define KEY_I 23 -#define KEY_O 24 -#define KEY_P 25 -#define KEY_LEFTBRACE 26 -#define KEY_RIGHTBRACE 27 -#define KEY_ENTER 28 -#define KEY_LEFTCTRL 29 -#define KEY_A 30 -#define KEY_S 31 -#define KEY_D 32 -#define KEY_F 33 -#define KEY_G 34 -#define KEY_H 35 -#define KEY_J 36 -#define KEY_K 37 -#define KEY_L 38 -#define KEY_SEMICOLON 39 -#define KEY_APOSTROPHE 40 -#define KEY_GRAVE 41 -#define KEY_LEFTSHIFT 42 -#define KEY_BACKSLASH 43 -#define KEY_Z 44 -#define KEY_X 45 -#define KEY_C 46 -#define KEY_V 47 -#define KEY_B 48 -#define KEY_N 49 -#define KEY_M 50 -#define KEY_COMMA 51 -#define KEY_DOT 52 -#define KEY_SLASH 53 -#define KEY_RIGHTSHIFT 54 -#define KEY_KPASTERISK 55 -#define KEY_LEFTALT 56 -#define KEY_SPACE 57 -#define KEY_CAPSLOCK 58 -#define KEY_F1 59 -#define KEY_F2 60 -#define KEY_F3 61 -#define KEY_F4 62 -#define KEY_F5 63 -#define KEY_F6 64 -#define KEY_F7 65 -#define KEY_F8 66 -#define KEY_F9 67 -#define KEY_F10 68 -#define KEY_NUMLOCK 69 -#define KEY_SCROLLLOCK 70 -#define KEY_KP7 71 -#define KEY_KP8 72 -#define KEY_KP9 73 -#define KEY_KPMINUS 74 -#define KEY_KP4 75 -#define KEY_KP5 76 -#define KEY_KP6 77 -#define KEY_KPPLUS 78 -#define KEY_KP1 79 -#define KEY_KP2 80 -#define KEY_KP3 81 -#define KEY_KP0 82 -#define KEY_KPDOT 83 - -#define KEY_ZENKAKUHANKAKU 85 -#define KEY_102ND 86 -#define KEY_F11 87 -#define KEY_F12 88 -#define KEY_RO 89 -#define KEY_KATAKANA 90 -#define KEY_HIRAGANA 91 -#define KEY_HENKAN 92 -#define KEY_KATAKANAHIRAGANA 93 -#define KEY_MUHENKAN 94 -#define KEY_KPJPCOMMA 95 -#define KEY_KPENTER 96 -#define KEY_RIGHTCTRL 97 -#define KEY_KPSLASH 98 -#define KEY_SYSRQ 99 -#define KEY_RIGHTALT 100 -#define KEY_LINEFEED 101 -#define KEY_HOME 102 -#define KEY_UP 103 -#define KEY_PAGEUP 104 -#define KEY_LEFT 105 -#define KEY_RIGHT 106 -#define KEY_END 107 -#define KEY_DOWN 108 -#define KEY_PAGEDOWN 109 -#define KEY_INSERT 110 -#define KEY_DELETE 111 -#define KEY_MACRO 112 -#define KEY_MUTE 113 -#define KEY_VOLUMEDOWN 114 -#define KEY_VOLUMEUP 115 -#define KEY_POWER 116 /* SC System Power Down */ -#define KEY_KPEQUAL 117 -#define KEY_KPPLUSMINUS 118 -#define KEY_PAUSE 119 -#define KEY_SCALE 120 /* AL Compiz Scale (Expose) */ - -#define KEY_KPCOMMA 121 -#define KEY_HANGEUL 122 -#define KEY_HANGUEL KEY_HANGEUL -#define KEY_HANJA 123 -#define KEY_YEN 124 -#define KEY_LEFTMETA 125 -#define KEY_RIGHTMETA 126 -#define KEY_COMPOSE 127 - -#define KEY_STOP 128 /* AC Stop */ -#define KEY_AGAIN 129 -#define KEY_PROPS 130 /* AC Properties */ -#define KEY_UNDO 131 /* AC Undo */ -#define KEY_FRONT 132 -#define KEY_COPY 133 /* AC Copy */ -#define KEY_OPEN 134 /* AC Open */ -#define KEY_PASTE 135 /* AC Paste */ -#define KEY_FIND 136 /* AC Search */ -#define KEY_CUT 137 /* AC Cut */ -#define KEY_HELP 138 /* AL Integrated Help Center */ -#define KEY_MENU 139 /* Menu (show menu) */ -#define KEY_CALC 140 /* AL Calculator */ -#define KEY_SETUP 141 -#define KEY_SLEEP 142 /* SC System Sleep */ -#define KEY_WAKEUP 143 /* System Wake Up */ -#define KEY_FILE 144 /* AL Local Machine Browser */ -#define KEY_SENDFILE 145 -#define KEY_DELETEFILE 146 -#define KEY_XFER 147 -#define KEY_PROG1 148 -#define KEY_PROG2 149 -#define KEY_WWW 150 /* AL Internet Browser */ -#define KEY_MSDOS 151 -#define KEY_COFFEE 152 /* AL Terminal Lock/Screensaver */ -#define KEY_SCREENLOCK KEY_COFFEE -#define KEY_ROTATE_DISPLAY 153 /* Display orientation for e.g. tablets */ -#define KEY_DIRECTION KEY_ROTATE_DISPLAY -#define KEY_CYCLEWINDOWS 154 -#define KEY_MAIL 155 -#define KEY_BOOKMARKS 156 /* AC Bookmarks */ -#define KEY_COMPUTER 157 -#define KEY_BACK 158 /* AC Back */ -#define KEY_FORWARD 159 /* AC Forward */ -#define KEY_CLOSECD 160 -#define KEY_EJECTCD 161 -#define KEY_EJECTCLOSECD 162 -#define KEY_NEXTSONG 163 -#define KEY_PLAYPAUSE 164 -#define KEY_PREVIOUSSONG 165 -#define KEY_STOPCD 166 -#define KEY_RECORD 167 -#define KEY_REWIND 168 -#define KEY_PHONE 169 /* Media Select Telephone */ -#define KEY_ISO 170 -#define KEY_CONFIG 171 /* AL Consumer Control Configuration */ -#define KEY_HOMEPAGE 172 /* AC Home */ -#define KEY_REFRESH 173 /* AC Refresh */ -#define KEY_EXIT 174 /* AC Exit */ -#define KEY_MOVE 175 -#define KEY_EDIT 176 -#define KEY_SCROLLUP 177 -#define KEY_SCROLLDOWN 178 -#define KEY_KPLEFTPAREN 179 -#define KEY_KPRIGHTPAREN 180 -#define KEY_NEW 181 /* AC New */ -#define KEY_REDO 182 /* AC Redo/Repeat */ - -#define KEY_F13 183 -#define KEY_F14 184 -#define KEY_F15 185 -#define KEY_F16 186 -#define KEY_F17 187 -#define KEY_F18 188 -#define KEY_F19 189 -#define KEY_F20 190 -#define KEY_F21 191 -#define KEY_F22 192 -#define KEY_F23 193 -#define KEY_F24 194 - -#define KEY_PLAYCD 200 -#define KEY_PAUSECD 201 -#define KEY_PROG3 202 -#define KEY_PROG4 203 -#define KEY_DASHBOARD 204 /* AL Dashboard */ -#define KEY_SUSPEND 205 -#define KEY_CLOSE 206 /* AC Close */ -#define KEY_PLAY 207 -#define KEY_FASTFORWARD 208 -#define KEY_BASSBOOST 209 -#define KEY_PRINT 210 /* AC Print */ -#define KEY_HP 211 -#define KEY_CAMERA 212 -#define KEY_SOUND 213 -#define KEY_QUESTION 214 -#define KEY_EMAIL 215 -#define KEY_CHAT 216 -#define KEY_SEARCH 217 -#define KEY_CONNECT 218 -#define KEY_FINANCE 219 /* AL Checkbook/Finance */ -#define KEY_SPORT 220 -#define KEY_SHOP 221 -#define KEY_ALTERASE 222 -#define KEY_CANCEL 223 /* AC Cancel */ -#define KEY_BRIGHTNESSDOWN 224 -#define KEY_BRIGHTNESSUP 225 -#define KEY_MEDIA 226 - -#define KEY_SWITCHVIDEOMODE 227 /* Cycle between available video - outputs (Monitor/LCD/TV-out/etc) */ -#define KEY_KBDILLUMTOGGLE 228 -#define KEY_KBDILLUMDOWN 229 -#define KEY_KBDILLUMUP 230 - -#define KEY_SEND 231 /* AC Send */ -#define KEY_REPLY 232 /* AC Reply */ -#define KEY_FORWARDMAIL 233 /* AC Forward Msg */ -#define KEY_SAVE 234 /* AC Save */ -#define KEY_DOCUMENTS 235 - -#define KEY_BATTERY 236 - -#define KEY_BLUETOOTH 237 -#define KEY_WLAN 238 -#define KEY_UWB 239 - -#define KEY_UNKNOWN 240 - -#define KEY_VIDEO_NEXT 241 /* drive next video source */ -#define KEY_VIDEO_PREV 242 /* drive previous video source */ -#define KEY_BRIGHTNESS_CYCLE 243 /* brightness up, after max is min */ -#define KEY_BRIGHTNESS_AUTO 244 /* Set Auto Brightness: manual - brightness control is off, - rely on ambient */ -#define KEY_BRIGHTNESS_ZERO KEY_BRIGHTNESS_AUTO -#define KEY_DISPLAY_OFF 245 /* display device to off state */ - -#define KEY_WWAN 246 /* Wireless WAN (LTE, UMTS, GSM, etc.) */ -#define KEY_WIMAX KEY_WWAN -#define KEY_RFKILL 247 /* Key that controls all radios */ - -#define KEY_MICMUTE 248 /* Mute / unmute the microphone */ - -/* Code 255 is reserved for special needs of AT keyboard driver */ - -#define BTN_MISC 0x100 -#define BTN_0 0x100 -#define BTN_1 0x101 -#define BTN_2 0x102 -#define BTN_3 0x103 -#define BTN_4 0x104 -#define BTN_5 0x105 -#define BTN_6 0x106 -#define BTN_7 0x107 -#define BTN_8 0x108 -#define BTN_9 0x109 - -#define BTN_MOUSE 0x110 -#define BTN_LEFT 0x110 -#define BTN_RIGHT 0x111 -#define BTN_MIDDLE 0x112 -#define BTN_SIDE 0x113 -#define BTN_EXTRA 0x114 -#define BTN_FORWARD 0x115 -#define BTN_BACK 0x116 -#define BTN_TASK 0x117 - -#define BTN_JOYSTICK 0x120 -#define BTN_TRIGGER 0x120 -#define BTN_THUMB 0x121 -#define BTN_THUMB2 0x122 -#define BTN_TOP 0x123 -#define BTN_TOP2 0x124 -#define BTN_PINKIE 0x125 -#define BTN_BASE 0x126 -#define BTN_BASE2 0x127 -#define BTN_BASE3 0x128 -#define BTN_BASE4 0x129 -#define BTN_BASE5 0x12a -#define BTN_BASE6 0x12b -#define BTN_DEAD 0x12f - -#define BTN_GAMEPAD 0x130 -#define BTN_SOUTH 0x130 -#define BTN_A BTN_SOUTH -#define BTN_EAST 0x131 -#define BTN_B BTN_EAST -#define BTN_C 0x132 -#define BTN_NORTH 0x133 -#define BTN_X BTN_NORTH -#define BTN_WEST 0x134 -#define BTN_Y BTN_WEST -#define BTN_Z 0x135 -#define BTN_TL 0x136 -#define BTN_TR 0x137 -#define BTN_TL2 0x138 -#define BTN_TR2 0x139 -#define BTN_SELECT 0x13a -#define BTN_START 0x13b -#define BTN_MODE 0x13c -#define BTN_THUMBL 0x13d -#define BTN_THUMBR 0x13e - -#define BTN_DIGI 0x140 -#define BTN_TOOL_PEN 0x140 -#define BTN_TOOL_RUBBER 0x141 -#define BTN_TOOL_BRUSH 0x142 -#define BTN_TOOL_PENCIL 0x143 -#define BTN_TOOL_AIRBRUSH 0x144 -#define BTN_TOOL_FINGER 0x145 -#define BTN_TOOL_MOUSE 0x146 -#define BTN_TOOL_LENS 0x147 -#define BTN_TOOL_QUINTTAP 0x148 /* Five fingers on trackpad */ -#define BTN_TOUCH 0x14a -#define BTN_STYLUS 0x14b -#define BTN_STYLUS2 0x14c -#define BTN_TOOL_DOUBLETAP 0x14d -#define BTN_TOOL_TRIPLETAP 0x14e -#define BTN_TOOL_QUADTAP 0x14f /* Four fingers on trackpad */ - -#define BTN_WHEEL 0x150 -#define BTN_GEAR_DOWN 0x150 -#define BTN_GEAR_UP 0x151 - -#define KEY_OK 0x160 -#define KEY_SELECT 0x161 -#define KEY_GOTO 0x162 -#define KEY_CLEAR 0x163 -#define KEY_POWER2 0x164 -#define KEY_OPTION 0x165 -#define KEY_INFO 0x166 /* AL OEM Features/Tips/Tutorial */ -#define KEY_TIME 0x167 -#define KEY_VENDOR 0x168 -#define KEY_ARCHIVE 0x169 -#define KEY_PROGRAM 0x16a /* Media Select Program Guide */ -#define KEY_CHANNEL 0x16b -#define KEY_FAVORITES 0x16c -#define KEY_EPG 0x16d -#define KEY_PVR 0x16e /* Media Select Home */ -#define KEY_MHP 0x16f -#define KEY_LANGUAGE 0x170 -#define KEY_TITLE 0x171 -#define KEY_SUBTITLE 0x172 -#define KEY_ANGLE 0x173 -#define KEY_ZOOM 0x174 -#define KEY_MODE 0x175 -#define KEY_KEYBOARD 0x176 -#define KEY_SCREEN 0x177 -#define KEY_PC 0x178 /* Media Select Computer */ -#define KEY_TV 0x179 /* Media Select TV */ -#define KEY_TV2 0x17a /* Media Select Cable */ -#define KEY_VCR 0x17b /* Media Select VCR */ -#define KEY_VCR2 0x17c /* VCR Plus */ -#define KEY_SAT 0x17d /* Media Select Satellite */ -#define KEY_SAT2 0x17e -#define KEY_CD 0x17f /* Media Select CD */ -#define KEY_TAPE 0x180 /* Media Select Tape */ -#define KEY_RADIO 0x181 -#define KEY_TUNER 0x182 /* Media Select Tuner */ -#define KEY_PLAYER 0x183 -#define KEY_TEXT 0x184 -#define KEY_DVD 0x185 /* Media Select DVD */ -#define KEY_AUX 0x186 -#define KEY_MP3 0x187 -#define KEY_AUDIO 0x188 /* AL Audio Browser */ -#define KEY_VIDEO 0x189 /* AL Movie Browser */ -#define KEY_DIRECTORY 0x18a -#define KEY_LIST 0x18b -#define KEY_MEMO 0x18c /* Media Select Messages */ -#define KEY_CALENDAR 0x18d -#define KEY_RED 0x18e -#define KEY_GREEN 0x18f -#define KEY_YELLOW 0x190 -#define KEY_BLUE 0x191 -#define KEY_CHANNELUP 0x192 /* Channel Increment */ -#define KEY_CHANNELDOWN 0x193 /* Channel Decrement */ -#define KEY_FIRST 0x194 -#define KEY_LAST 0x195 /* Recall Last */ -#define KEY_AB 0x196 -#define KEY_NEXT 0x197 -#define KEY_RESTART 0x198 -#define KEY_SLOW 0x199 -#define KEY_SHUFFLE 0x19a -#define KEY_BREAK 0x19b -#define KEY_PREVIOUS 0x19c -#define KEY_DIGITS 0x19d -#define KEY_TEEN 0x19e -#define KEY_TWEN 0x19f -#define KEY_VIDEOPHONE 0x1a0 /* Media Select Video Phone */ -#define KEY_GAMES 0x1a1 /* Media Select Games */ -#define KEY_ZOOMIN 0x1a2 /* AC Zoom In */ -#define KEY_ZOOMOUT 0x1a3 /* AC Zoom Out */ -#define KEY_ZOOMRESET 0x1a4 /* AC Zoom */ -#define KEY_WORDPROCESSOR 0x1a5 /* AL Word Processor */ -#define KEY_EDITOR 0x1a6 /* AL Text Editor */ -#define KEY_SPREADSHEET 0x1a7 /* AL Spreadsheet */ -#define KEY_GRAPHICSEDITOR 0x1a8 /* AL Graphics Editor */ -#define KEY_PRESENTATION 0x1a9 /* AL Presentation App */ -#define KEY_DATABASE 0x1aa /* AL Database App */ -#define KEY_NEWS 0x1ab /* AL Newsreader */ -#define KEY_VOICEMAIL 0x1ac /* AL Voicemail */ -#define KEY_ADDRESSBOOK 0x1ad /* AL Contacts/Address Book */ -#define KEY_MESSENGER 0x1ae /* AL Instant Messaging */ -#define KEY_DISPLAYTOGGLE 0x1af /* Turn display (LCD) on and off */ -#define KEY_BRIGHTNESS_TOGGLE KEY_DISPLAYTOGGLE -#define KEY_SPELLCHECK 0x1b0 /* AL Spell Check */ -#define KEY_LOGOFF 0x1b1 /* AL Logoff */ - -#define KEY_DOLLAR 0x1b2 -#define KEY_EURO 0x1b3 - -#define KEY_FRAMEBACK 0x1b4 /* Consumer - transport controls */ -#define KEY_FRAMEFORWARD 0x1b5 -#define KEY_CONTEXT_MENU 0x1b6 /* GenDesc - system context menu */ -#define KEY_MEDIA_REPEAT 0x1b7 /* Consumer - transport control */ -#define KEY_10CHANNELSUP 0x1b8 /* 10 channels up (10+) */ -#define KEY_10CHANNELSDOWN 0x1b9 /* 10 channels down (10-) */ -#define KEY_IMAGES 0x1ba /* AL Image Browser */ - -#define KEY_DEL_EOL 0x1c0 -#define KEY_DEL_EOS 0x1c1 -#define KEY_INS_LINE 0x1c2 -#define KEY_DEL_LINE 0x1c3 - -#define KEY_FN 0x1d0 -#define KEY_FN_ESC 0x1d1 -#define KEY_FN_F1 0x1d2 -#define KEY_FN_F2 0x1d3 -#define KEY_FN_F3 0x1d4 -#define KEY_FN_F4 0x1d5 -#define KEY_FN_F5 0x1d6 -#define KEY_FN_F6 0x1d7 -#define KEY_FN_F7 0x1d8 -#define KEY_FN_F8 0x1d9 -#define KEY_FN_F9 0x1da -#define KEY_FN_F10 0x1db -#define KEY_FN_F11 0x1dc -#define KEY_FN_F12 0x1dd -#define KEY_FN_1 0x1de -#define KEY_FN_2 0x1df -#define KEY_FN_D 0x1e0 -#define KEY_FN_E 0x1e1 -#define KEY_FN_F 0x1e2 -#define KEY_FN_S 0x1e3 -#define KEY_FN_B 0x1e4 - -#define KEY_BRL_DOT1 0x1f1 -#define KEY_BRL_DOT2 0x1f2 -#define KEY_BRL_DOT3 0x1f3 -#define KEY_BRL_DOT4 0x1f4 -#define KEY_BRL_DOT5 0x1f5 -#define KEY_BRL_DOT6 0x1f6 -#define KEY_BRL_DOT7 0x1f7 -#define KEY_BRL_DOT8 0x1f8 -#define KEY_BRL_DOT9 0x1f9 -#define KEY_BRL_DOT10 0x1fa - -#define KEY_NUMERIC_0 0x200 /* used by phones, remote controls, */ -#define KEY_NUMERIC_1 0x201 /* and other keypads */ -#define KEY_NUMERIC_2 0x202 -#define KEY_NUMERIC_3 0x203 -#define KEY_NUMERIC_4 0x204 -#define KEY_NUMERIC_5 0x205 -#define KEY_NUMERIC_6 0x206 -#define KEY_NUMERIC_7 0x207 -#define KEY_NUMERIC_8 0x208 -#define KEY_NUMERIC_9 0x209 -#define KEY_NUMERIC_STAR 0x20a -#define KEY_NUMERIC_POUND 0x20b -#define KEY_NUMERIC_A 0x20c /* Phone key A - HUT Telephony 0xb9 */ -#define KEY_NUMERIC_B 0x20d -#define KEY_NUMERIC_C 0x20e -#define KEY_NUMERIC_D 0x20f - -#define KEY_CAMERA_FOCUS 0x210 -#define KEY_WPS_BUTTON 0x211 /* WiFi Protected Setup key */ - -#define KEY_TOUCHPAD_TOGGLE 0x212 /* Request switch touchpad on or off */ -#define KEY_TOUCHPAD_ON 0x213 -#define KEY_TOUCHPAD_OFF 0x214 - -#define KEY_CAMERA_ZOOMIN 0x215 -#define KEY_CAMERA_ZOOMOUT 0x216 -#define KEY_CAMERA_UP 0x217 -#define KEY_CAMERA_DOWN 0x218 -#define KEY_CAMERA_LEFT 0x219 -#define KEY_CAMERA_RIGHT 0x21a - -#define KEY_ATTENDANT_ON 0x21b -#define KEY_ATTENDANT_OFF 0x21c -#define KEY_ATTENDANT_TOGGLE 0x21d /* Attendant call on or off */ -#define KEY_LIGHTS_TOGGLE 0x21e /* Reading light on or off */ - -#define BTN_DPAD_UP 0x220 -#define BTN_DPAD_DOWN 0x221 -#define BTN_DPAD_LEFT 0x222 -#define BTN_DPAD_RIGHT 0x223 - -#define KEY_ALS_TOGGLE 0x230 /* Ambient light sensor */ - -#define KEY_BUTTONCONFIG 0x240 /* AL Button Configuration */ -#define KEY_TASKMANAGER 0x241 /* AL Task/Project Manager */ -#define KEY_JOURNAL 0x242 /* AL Log/Journal/Timecard */ -#define KEY_CONTROLPANEL 0x243 /* AL Control Panel */ -#define KEY_APPSELECT 0x244 /* AL Select Task/Application */ -#define KEY_SCREENSAVER 0x245 /* AL Screen Saver */ -#define KEY_VOICECOMMAND 0x246 /* Listening Voice Command */ - -#define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ -#define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ - -#define KEY_KBDINPUTASSIST_PREV 0x260 -#define KEY_KBDINPUTASSIST_NEXT 0x261 -#define KEY_KBDINPUTASSIST_PREVGROUP 0x262 -#define KEY_KBDINPUTASSIST_NEXTGROUP 0x263 -#define KEY_KBDINPUTASSIST_ACCEPT 0x264 -#define KEY_KBDINPUTASSIST_CANCEL 0x265 - -#define BTN_TRIGGER_HAPPY 0x2c0 -#define BTN_TRIGGER_HAPPY1 0x2c0 -#define BTN_TRIGGER_HAPPY2 0x2c1 -#define BTN_TRIGGER_HAPPY3 0x2c2 -#define BTN_TRIGGER_HAPPY4 0x2c3 -#define BTN_TRIGGER_HAPPY5 0x2c4 -#define BTN_TRIGGER_HAPPY6 0x2c5 -#define BTN_TRIGGER_HAPPY7 0x2c6 -#define BTN_TRIGGER_HAPPY8 0x2c7 -#define BTN_TRIGGER_HAPPY9 0x2c8 -#define BTN_TRIGGER_HAPPY10 0x2c9 -#define BTN_TRIGGER_HAPPY11 0x2ca -#define BTN_TRIGGER_HAPPY12 0x2cb -#define BTN_TRIGGER_HAPPY13 0x2cc -#define BTN_TRIGGER_HAPPY14 0x2cd -#define BTN_TRIGGER_HAPPY15 0x2ce -#define BTN_TRIGGER_HAPPY16 0x2cf -#define BTN_TRIGGER_HAPPY17 0x2d0 -#define BTN_TRIGGER_HAPPY18 0x2d1 -#define BTN_TRIGGER_HAPPY19 0x2d2 -#define BTN_TRIGGER_HAPPY20 0x2d3 -#define BTN_TRIGGER_HAPPY21 0x2d4 -#define BTN_TRIGGER_HAPPY22 0x2d5 -#define BTN_TRIGGER_HAPPY23 0x2d6 -#define BTN_TRIGGER_HAPPY24 0x2d7 -#define BTN_TRIGGER_HAPPY25 0x2d8 -#define BTN_TRIGGER_HAPPY26 0x2d9 -#define BTN_TRIGGER_HAPPY27 0x2da -#define BTN_TRIGGER_HAPPY28 0x2db -#define BTN_TRIGGER_HAPPY29 0x2dc -#define BTN_TRIGGER_HAPPY30 0x2dd -#define BTN_TRIGGER_HAPPY31 0x2de -#define BTN_TRIGGER_HAPPY32 0x2df -#define BTN_TRIGGER_HAPPY33 0x2e0 -#define BTN_TRIGGER_HAPPY34 0x2e1 -#define BTN_TRIGGER_HAPPY35 0x2e2 -#define BTN_TRIGGER_HAPPY36 0x2e3 -#define BTN_TRIGGER_HAPPY37 0x2e4 -#define BTN_TRIGGER_HAPPY38 0x2e5 -#define BTN_TRIGGER_HAPPY39 0x2e6 -#define BTN_TRIGGER_HAPPY40 0x2e7 - -/* We avoid low common keys in module aliases so they don't get huge. */ -#define KEY_MIN_INTERESTING KEY_MUTE -#define KEY_MAX 0x2ff -#define KEY_CNT (KEY_MAX+1) - -/* - * Relative axes - */ - -#define REL_X 0x00 -#define REL_Y 0x01 -#define REL_Z 0x02 -#define REL_RX 0x03 -#define REL_RY 0x04 -#define REL_RZ 0x05 -#define REL_HWHEEL 0x06 -#define REL_DIAL 0x07 -#define REL_WHEEL 0x08 -#define REL_MISC 0x09 -#define REL_MAX 0x0f -#define REL_CNT (REL_MAX+1) - -/* - * Absolute axes - */ - -#define ABS_X 0x00 -#define ABS_Y 0x01 -#define ABS_Z 0x02 -#define ABS_RX 0x03 -#define ABS_RY 0x04 -#define ABS_RZ 0x05 -#define ABS_THROTTLE 0x06 -#define ABS_RUDDER 0x07 -#define ABS_WHEEL 0x08 -#define ABS_GAS 0x09 -#define ABS_BRAKE 0x0a -#define ABS_HAT0X 0x10 -#define ABS_HAT0Y 0x11 -#define ABS_HAT1X 0x12 -#define ABS_HAT1Y 0x13 -#define ABS_HAT2X 0x14 -#define ABS_HAT2Y 0x15 -#define ABS_HAT3X 0x16 -#define ABS_HAT3Y 0x17 -#define ABS_PRESSURE 0x18 -#define ABS_DISTANCE 0x19 -#define ABS_TILT_X 0x1a -#define ABS_TILT_Y 0x1b -#define ABS_TOOL_WIDTH 0x1c - -#define ABS_VOLUME 0x20 - -#define ABS_MISC 0x28 - -#define ABS_MT_SLOT 0x2f /* MT slot being modified */ -#define ABS_MT_TOUCH_MAJOR 0x30 /* Major axis of touching ellipse */ -#define ABS_MT_TOUCH_MINOR 0x31 /* Minor axis (omit if circular) */ -#define ABS_MT_WIDTH_MAJOR 0x32 /* Major axis of approaching ellipse */ -#define ABS_MT_WIDTH_MINOR 0x33 /* Minor axis (omit if circular) */ -#define ABS_MT_ORIENTATION 0x34 /* Ellipse orientation */ -#define ABS_MT_POSITION_X 0x35 /* Center X touch position */ -#define ABS_MT_POSITION_Y 0x36 /* Center Y touch position */ -#define ABS_MT_TOOL_TYPE 0x37 /* Type of touching device */ -#define ABS_MT_BLOB_ID 0x38 /* Group a set of packets as a blob */ -#define ABS_MT_TRACKING_ID 0x39 /* Unique ID of initiated contact */ -#define ABS_MT_PRESSURE 0x3a /* Pressure on contact area */ -#define ABS_MT_DISTANCE 0x3b /* Contact hover distance */ -#define ABS_MT_TOOL_X 0x3c /* Center X tool position */ -#define ABS_MT_TOOL_Y 0x3d /* Center Y tool position */ - - -#define ABS_MAX 0x3f -#define ABS_CNT (ABS_MAX+1) - -/* - * Switch events - */ - -#define SW_LID 0x00 /* set = lid shut */ -#define SW_TABLET_MODE 0x01 /* set = tablet mode */ -#define SW_HEADPHONE_INSERT 0x02 /* set = inserted */ -#define SW_RFKILL_ALL 0x03 /* rfkill master switch, type "any" - set = radio enabled */ -#define SW_RADIO SW_RFKILL_ALL /* deprecated */ -#define SW_MICROPHONE_INSERT 0x04 /* set = inserted */ -#define SW_DOCK 0x05 /* set = plugged into dock */ -#define SW_LINEOUT_INSERT 0x06 /* set = inserted */ -#define SW_JACK_PHYSICAL_INSERT 0x07 /* set = mechanical switch set */ -#define SW_VIDEOOUT_INSERT 0x08 /* set = inserted */ -#define SW_CAMERA_LENS_COVER 0x09 /* set = lens covered */ -#define SW_KEYPAD_SLIDE 0x0a /* set = keypad slide out */ -#define SW_FRONT_PROXIMITY 0x0b /* set = front proximity sensor active */ -#define SW_ROTATE_LOCK 0x0c /* set = rotate locked/disabled */ -#define SW_LINEIN_INSERT 0x0d /* set = inserted */ -#define SW_MUTE_DEVICE 0x0e /* set = device disabled */ -#define SW_MAX 0x0f -#define SW_CNT (SW_MAX+1) - -/* - * Misc events - */ - -#define MSC_SERIAL 0x00 -#define MSC_PULSELED 0x01 -#define MSC_GESTURE 0x02 -#define MSC_RAW 0x03 -#define MSC_SCAN 0x04 -#define MSC_TIMESTAMP 0x05 -#define MSC_MAX 0x07 -#define MSC_CNT (MSC_MAX+1) - -/* - * LEDs - */ - -#define LED_NUML 0x00 -#define LED_CAPSL 0x01 -#define LED_SCROLLL 0x02 -#define LED_COMPOSE 0x03 -#define LED_KANA 0x04 -#define LED_SLEEP 0x05 -#define LED_SUSPEND 0x06 -#define LED_MUTE 0x07 -#define LED_MISC 0x08 -#define LED_MAIL 0x09 -#define LED_CHARGING 0x0a -#define LED_MAX 0x0f -#define LED_CNT (LED_MAX+1) - -/* - * Autorepeat values - */ - -#define REP_DELAY 0x00 -#define REP_PERIOD 0x01 -#define REP_MAX 0x01 -#define REP_CNT (REP_MAX+1) - -/* - * Sounds - */ - -#define SND_CLICK 0x00 -#define SND_BELL 0x01 -#define SND_TONE 0x02 -#define SND_MAX 0x07 -#define SND_CNT (SND_MAX+1) - /* * IDs. */ -- cgit v1.2.3 From 52a9266788324edbbfd45f02cf23440c01ee0432 Mon Sep 17 00:00:00 2001 From: Elias Vanderstuyft Date: Mon, 21 Sep 2015 15:59:11 -0700 Subject: Input: fix EVIOCSFF macro inconsistency by using _IOW() Just like the EVIOCSABS(abs) macro, use the more compact _IOW(..., type) instead of _IOC(_IOC_WRITE, ..., sizeof(type)) for the EVIOCSFF macro. Signed-off-by: Elias Vanderstuyft Signed-off-by: Dmitry Torokhov --- include/uapi/linux/input.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index f24043a12777..a8e74b45dbe2 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -148,7 +148,7 @@ struct input_keymap_entry { #define EVIOCGABS(abs) _IOR('E', 0x40 + (abs), struct input_absinfo) /* get abs value/limits */ #define EVIOCSABS(abs) _IOW('E', 0xc0 + (abs), struct input_absinfo) /* set abs value/limits */ -#define EVIOCSFF _IOC(_IOC_WRITE, 'E', 0x80, sizeof(struct ff_effect)) /* send a force effect to a force feedback device */ +#define EVIOCSFF _IOW('E', 0x80, struct ff_effect) /* send a force effect to a force feedback device */ #define EVIOCRMFF _IOW('E', 0x81, int) /* Erase a force effect */ #define EVIOCGEFFECTS _IOR('E', 0x84, int) /* Report number of effects playable at the same time */ -- cgit v1.2.3 From 33b96d934902f96e901b72ac18bbc47afad1ac20 Mon Sep 17 00:00:00 2001 From: Elias Vanderstuyft Date: Wed, 14 Oct 2015 17:29:37 -0700 Subject: Input: document and check on implicitly defined FF_MAX_EFFECTS There is an undocumented upper bound for the total number of ff effects: FF_GAIN (= 96). This can be found as follows: - user: write(EV_FF, effect_id, iterations) calls kernel: ff->playback(effect_id, ...): starts effect "effect_id" - user: write(EV_FF, FF_GAIN, gain) calls kernel: ff->set_gain(gain, ...): sets gain A collision occurs when effect_id equals FF_GAIN. According to input_ff_event(), FF_GAIN is the smallest value where a collision occurs. Therefore the greatest safe value for effect_id is FF_GAIN - 1, and thus the total number of effects should never exceed FF_GAIN. Define FF_MAX_EFFECTS as FF_GAIN and check on this limit in ff-core. Signed-off-by: Elias Vanderstuyft Signed-off-by: Dmitry Torokhov --- drivers/input/ff-core.c | 5 +++++ include/uapi/linux/input.h | 8 ++++++++ 2 files changed, 13 insertions(+) (limited to 'include/uapi') diff --git a/drivers/input/ff-core.c b/drivers/input/ff-core.c index eab56c0aacd5..8f2042432c85 100644 --- a/drivers/input/ff-core.c +++ b/drivers/input/ff-core.c @@ -318,6 +318,11 @@ int input_ff_create(struct input_dev *dev, unsigned int max_effects) return -EINVAL; } + if (max_effects > FF_MAX_EFFECTS) { + dev_err(&dev->dev, "cannot allocate more than FF_MAX_EFFECTS effects\n"); + return -EINVAL; + } + ff_dev_size = sizeof(struct ff_device) + max_effects * sizeof(struct file *); if (ff_dev_size < max_effects) /* overflow */ diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index a8e74b45dbe2..4f9f2a0f5573 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -414,6 +414,14 @@ struct ff_effect { #define FF_GAIN 0x60 #define FF_AUTOCENTER 0x61 +/* + * ff->playback(effect_id = FF_GAIN) is the first effect_id to + * cause a collision with another ff method, in this case ff->set_gain(). + * Therefore the greatest safe value for effect_id is FF_GAIN - 1, + * and thus the total number of effects should never exceed FF_GAIN. + */ +#define FF_MAX_EFFECTS FF_GAIN + #define FF_MAX 0x7f #define FF_CNT (FF_MAX+1) -- cgit v1.2.3 From 8b4953e13f4c5d9a3c869f5fca7d51e1700e7db0 Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Sat, 17 Oct 2015 16:15:18 -0400 Subject: ext4: reserve code points for the project quota feature Signed-off-by: Theodore Ts'o --- fs/ext4/ext4.h | 8 +++++++- include/uapi/linux/fs.h | 1 + 2 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 3f248c9f899f..320f10ef4a23 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -374,6 +374,7 @@ struct flex_groups { #define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */ #define EXT4_EOFBLOCKS_FL 0x00400000 /* Blocks allocated beyond EOF */ #define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */ +#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */ #define EXT4_FL_USER_VISIBLE 0x004BDFFF /* User visible flags */ @@ -431,6 +432,7 @@ enum { EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */ EXT4_INODE_EOFBLOCKS = 22, /* Blocks allocated beyond EOF */ EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */ + EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */ EXT4_INODE_RESERVED = 31, /* reserved for ext4 lib */ }; @@ -475,6 +477,7 @@ static inline void ext4_check_flag_values(void) CHECK_FLAG_VALUE(EA_INODE); CHECK_FLAG_VALUE(EOFBLOCKS); CHECK_FLAG_VALUE(INLINE_DATA); + CHECK_FLAG_VALUE(PROJINHERIT); CHECK_FLAG_VALUE(RESERVED); } @@ -692,6 +695,7 @@ struct ext4_inode { __le32 i_crtime; /* File Creation time */ __le32 i_crtime_extra; /* extra FileCreationtime (nsec << 2 | epoch) */ __le32 i_version_hi; /* high 32 bits for 64-bit version */ + __le32 i_projid; /* Project ID */ }; struct move_extent { @@ -1179,7 +1183,8 @@ struct ext4_super_block { __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */ __le32 s_lpf_ino; /* Location of the lost+found inode */ - __le32 s_reserved[100]; /* Padding to the end of the block */ + __le32 s_prj_quota_inum; /* inode for tracking project quota */ + __le32 s_reserved[99]; /* Padding to the end of the block */ __le32 s_checksum; /* crc32c(superblock) */ }; @@ -1566,6 +1571,7 @@ static inline int ext4_encrypted_inode(struct inode *inode) */ #define EXT4_FEATURE_RO_COMPAT_METADATA_CSUM 0x0400 #define EXT4_FEATURE_RO_COMPAT_READONLY 0x1000 +#define EXT4_FEATURE_RO_COMPAT_PROJECT 0x2000 #define EXT4_FEATURE_INCOMPAT_COMPRESSION 0x0001 #define EXT4_FEATURE_INCOMPAT_FILETYPE 0x0002 diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h index 9b964a5920af..f15d980249b5 100644 --- a/include/uapi/linux/fs.h +++ b/include/uapi/linux/fs.h @@ -197,6 +197,7 @@ struct inodes_stat_t { #define FS_EXTENT_FL 0x00080000 /* Extents */ #define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ +#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ -- cgit v1.2.3 From b3958b9e18140457b5600b03619e4c2e530761fe Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Fri, 16 Oct 2015 16:12:34 -0700 Subject: uapi: add mpls_iptunnel.h Add missing rule to export mpls iptunnel header needed by iproute2 Signed-off-by: Stephen Hemminger Acked-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/uapi/linux/Kbuild | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild index f7b2db44eb4b..70d89230b641 100644 --- a/include/uapi/linux/Kbuild +++ b/include/uapi/linux/Kbuild @@ -263,6 +263,7 @@ header-y += minix_fs.h header-y += mman.h header-y += mmtimer.h header-y += mpls.h +header-y += mpls_iptunnel.h header-y += mqueue.h header-y += mroute6.h header-y += mroute.h -- cgit v1.2.3 From 137d36af4a53858b8db7ca83c8480247118b8bdf Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:56:48 +0200 Subject: mtd: mtd-user: remove stdint.h include Kernel headers should use linux/types.h instead. Signed-off-by: Mikko Rapeli Signed-off-by: Brian Norris --- include/uapi/mtd/mtd-user.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/mtd/mtd-user.h b/include/uapi/mtd/mtd-user.h index 83327c808c86..e71d5558cc23 100644 --- a/include/uapi/mtd/mtd-user.h +++ b/include/uapi/mtd/mtd-user.h @@ -20,8 +20,6 @@ #ifndef __MTD_USER_H__ #define __MTD_USER_H__ -#include - /* This file is blessed for inclusion by userspace */ #include -- cgit v1.2.3 From b9511cd761faafca7a1acc059e792c1399f9d7c6 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Fri, 16 Oct 2015 16:24:05 +0300 Subject: perf/x86: Fix time_shift in perf_event_mmap_page Commit: b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock") allowed the time_shift value in perf_event_mmap_page to be as much as 32. Unfortunately the documented algorithms for using time_shift have it shifting an integer, whereas to work correctly with the value 32, the type must be u64. In the case of perf tools, Intel PT decodes correctly but the timestamps that are output (for example by perf script) have lost 32-bits of granularity so they look like they are not changing at all. Fix by limiting the shift to 31 and adjusting the multiplier accordingly. Also update the documentation of perf_event_mmap_page so that new code based on it will be more future-proof. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Cc: Andy Lutomirski Cc: Arnaldo Carvalho de Melo Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Thomas Gleixner Cc: Vince Weaver Fixes: b20112edeadf ("perf/x86: Improve accuracy of perf/sched clock") Link: http://lkml.kernel.org/r/1445001845-13688-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Ingo Molnar --- arch/x86/kernel/tsc.c | 11 +++++++++++ include/uapi/linux/perf_event.h | 4 ++-- 2 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 69b84a26ea17..c7c4d9c51e99 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -259,6 +259,17 @@ static void set_cyc2ns_scale(unsigned long cpu_khz, int cpu) clocks_calc_mult_shift(&data->cyc2ns_mul, &data->cyc2ns_shift, cpu_khz, NSEC_PER_MSEC, 0); + /* + * cyc2ns_shift is exported via arch_perf_update_userpage() where it is + * not expected to be greater than 31 due to the original published + * conversion algorithm shifting a 32-bit value (now specifies a 64-bit + * value) - refer perf_event_mmap_page documentation in perf_event.h. + */ + if (data->cyc2ns_shift == 32) { + data->cyc2ns_shift = 31; + data->cyc2ns_mul >>= 1; + } + data->cyc2ns_offset = ns_now - mul_u64_u32_shr(tsc_now, data->cyc2ns_mul, data->cyc2ns_shift); diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 2881145cda86..6c72e72e975c 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -476,7 +476,7 @@ struct perf_event_mmap_page { * u64 delta; * * quot = (cyc >> time_shift); - * rem = cyc & ((1 << time_shift) - 1); + * rem = cyc & (((u64)1 << time_shift) - 1); * delta = time_offset + quot * time_mult + * ((rem * time_mult) >> time_shift); * @@ -507,7 +507,7 @@ struct perf_event_mmap_page { * And vice versa: * * quot = cyc >> time_shift; - * rem = cyc & ((1 << time_shift) - 1); + * rem = cyc & (((u64)1 << time_shift) - 1); * timestamp = time_zero + quot * time_mult + * ((rem * time_mult) >> time_shift); */ -- cgit v1.2.3 From c229bf9dc179d2023e185c0f705bdf68484c1e73 Mon Sep 17 00:00:00 2001 From: Stephane Eranian Date: Tue, 13 Oct 2015 09:09:08 +0200 Subject: perf: Add PERF_SAMPLE_BRANCH_CALL Add a new branch sample type to cover only call branches (function calls). The current ANY_CALL included direct, indirect calls and far jumps. We want to be able to differentiate indirect from direct calls. Therefore we introduce PERF_SAMPLE_BRANCH_CALL. The implementation is up to each architecture. Signed-off-by: Stephane Eranian Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: David Ahern Cc: Jiri Olsa Cc: Linus Torvalds Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vince Weaver Cc: khandual@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1444720151-10275-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar --- include/uapi/linux/perf_event.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 6c72e72e975c..651221334f49 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -168,6 +168,7 @@ enum perf_branch_sample_type_shift { PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ + PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ PERF_SAMPLE_BRANCH_MAX_SHIFT /* non-ABI */ }; @@ -188,6 +189,7 @@ enum perf_branch_sample_type { PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; -- cgit v1.2.3 From f3c3ecec97c24cf0e53bb61ee85698acc00bcd68 Mon Sep 17 00:00:00 2001 From: Antti Palosaari Date: Sat, 10 Oct 2015 13:50:57 -0300 Subject: [media] v4l2: rename V4L2_TUNER_ADC to V4L2_TUNER_SDR SDR receiver has ADC (Analog-to-Digital Converter) and SDR transmitter has DAC (Digital-to-Analog Converter). Originally I though it could be good idea to have own type for receiver and transmitter, but now I feel one common type for SDR is enough. So lets rename it. Signed-off-by: Antti Palosaari Acked-by: Mauro Carvalho Chehab Signed-off-by: Hans Verkuil [hans.verkuil@cisco.com: this was added in 4.4, so update 4.2 to 4.4] Signed-off-by: Mauro Carvalho Chehab --- Documentation/DocBook/media/v4l/compat.xml | 12 ++++++++++++ Documentation/DocBook/media/v4l/dev-sdr.xml | 6 +++--- Documentation/DocBook/media/v4l/v4l2.xml | 7 +++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 6 +++--- include/uapi/linux/videodev2.h | 5 ++++- 5 files changed, 29 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/Documentation/DocBook/media/v4l/compat.xml b/Documentation/DocBook/media/v4l/compat.xml index a0aef85d33c1..08f4efcab4e9 100644 --- a/Documentation/DocBook/media/v4l/compat.xml +++ b/Documentation/DocBook/media/v4l/compat.xml @@ -2591,6 +2591,18 @@ and &v4l2-mbus-framefmt;. +
+ V4L2 in Linux 4.4 + + + Renamed V4L2_TUNER_ADC to +V4L2_TUNER_SDR. The use of +V4L2_TUNER_ADC is deprecated now. + + + +
+
Relation of V4L2 to other Linux multimedia APIs diff --git a/Documentation/DocBook/media/v4l/dev-sdr.xml b/Documentation/DocBook/media/v4l/dev-sdr.xml index f8903568a243..3344921354e8 100644 --- a/Documentation/DocBook/media/v4l/dev-sdr.xml +++ b/Documentation/DocBook/media/v4l/dev-sdr.xml @@ -44,10 +44,10 @@ frequency. -The V4L2_TUNER_ADC tuner type is used for ADC tuners, and +The V4L2_TUNER_SDR tuner type is used for SDR tuners, and the V4L2_TUNER_RF tuner type is used for RF tuners. The -tuner index of the RF tuner (if any) must always follow the ADC tuner index. -Normally the ADC tuner is #0 and the RF tuner is #1. +tuner index of the RF tuner (if any) must always follow the SDR tuner index. +Normally the SDR tuner is #0 and the RF tuner is #1. diff --git a/Documentation/DocBook/media/v4l/v4l2.xml b/Documentation/DocBook/media/v4l/v4l2.xml index e98caa1c39bd..01a24df92e1d 100644 --- a/Documentation/DocBook/media/v4l/v4l2.xml +++ b/Documentation/DocBook/media/v4l/v4l2.xml @@ -151,6 +151,13 @@ Rubli, Andy Walls, Muralidharan Karicheri, Mauro Carvalho Chehab, structs, ioctls) must be noted in more detail in the history chapter (compat.xml), along with the possible impact on existing drivers and applications. --> + + 4.4 + 2015-05-26 + ap + Renamed V4L2_TUNER_ADC to V4L2_TUNER_SDR. + + 3.21 diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 5dc69086cf84..056a5ade5870 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1637,7 +1637,7 @@ static int v4l_g_frequency(const struct v4l2_ioctl_ops *ops, struct v4l2_frequency *p = arg; if (vfd->vfl_type == VFL_TYPE_SDR) - p->type = V4L2_TUNER_ADC; + p->type = V4L2_TUNER_SDR; else p->type = (vfd->vfl_type == VFL_TYPE_RADIO) ? V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV; @@ -1652,7 +1652,7 @@ static int v4l_s_frequency(const struct v4l2_ioctl_ops *ops, enum v4l2_tuner_type type; if (vfd->vfl_type == VFL_TYPE_SDR) { - if (p->type != V4L2_TUNER_ADC && p->type != V4L2_TUNER_RF) + if (p->type != V4L2_TUNER_SDR && p->type != V4L2_TUNER_RF) return -EINVAL; } else { type = (vfd->vfl_type == VFL_TYPE_RADIO) ? @@ -2277,7 +2277,7 @@ static int v4l_enum_freq_bands(const struct v4l2_ioctl_ops *ops, int err; if (vfd->vfl_type == VFL_TYPE_SDR) { - if (p->type != V4L2_TUNER_ADC && p->type != V4L2_TUNER_RF) + if (p->type != V4L2_TUNER_SDR && p->type != V4L2_TUNER_RF) return -EINVAL; type = p->type; } else { diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 92d65af41631..fa8bf2d07a52 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -165,10 +165,13 @@ enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, V4L2_TUNER_ANALOG_TV = 2, V4L2_TUNER_DIGITAL_TV = 3, - V4L2_TUNER_ADC = 4, + V4L2_TUNER_SDR = 4, V4L2_TUNER_RF = 5, }; +/* Deprecated, do not use */ +#define V4L2_TUNER_ADC V4L2_TUNER_SDR + enum v4l2_memory { V4L2_MEMORY_MMAP = 1, V4L2_MEMORY_USERPTR = 2, -- cgit v1.2.3 From 41018cb84a9ed440db1508d67d9dd4084d5460eb Mon Sep 17 00:00:00 2001 From: Antti Palosaari Date: Sat, 10 Oct 2015 13:50:58 -0300 Subject: [media] v4l2: add RF gain control Add new RF tuner gain control named RF Gain. That is aimed for first amplifier chip right after antenna connector. There is existing LNA Gain control, which is quite same, but it is aimed for cases amplifier is integrated to tuner chip. Some designs have both, as almost all recent tuner silicons has integrated LNA/RF amplifier in any case. Signed-off-by: Antti Palosaari Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls.c | 2 ++ include/uapi/linux/v4l2-controls.h | 1 + 2 files changed, 3 insertions(+) (limited to 'include/uapi') diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 44521a9da66d..a89b94601b90 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -888,6 +888,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_TUNE_DEEMPHASIS: return "De-Emphasis"; case V4L2_CID_RDS_RECEPTION: return "RDS Reception"; case V4L2_CID_RF_TUNER_CLASS: return "RF Tuner Controls"; + case V4L2_CID_RF_TUNER_RF_GAIN: return "RF Gain"; case V4L2_CID_RF_TUNER_LNA_GAIN_AUTO: return "LNA Gain, Auto"; case V4L2_CID_RF_TUNER_LNA_GAIN: return "LNA Gain"; case V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO: return "Mixer Gain, Auto"; @@ -1161,6 +1162,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_PILOT_TONE_FREQUENCY: case V4L2_CID_TUNE_POWER_LEVEL: case V4L2_CID_TUNE_ANTENNA_CAPACITOR: + case V4L2_CID_RF_TUNER_RF_GAIN: case V4L2_CID_RF_TUNER_LNA_GAIN: case V4L2_CID_RF_TUNER_MIXER_GAIN: case V4L2_CID_RF_TUNER_IF_GAIN: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index d448c536b49d..1bdce501ad6b 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -936,6 +936,7 @@ enum v4l2_deemphasis { #define V4L2_CID_RF_TUNER_BANDWIDTH_AUTO (V4L2_CID_RF_TUNER_CLASS_BASE + 11) #define V4L2_CID_RF_TUNER_BANDWIDTH (V4L2_CID_RF_TUNER_CLASS_BASE + 12) +#define V4L2_CID_RF_TUNER_RF_GAIN (V4L2_CID_RF_TUNER_CLASS_BASE + 32) #define V4L2_CID_RF_TUNER_LNA_GAIN_AUTO (V4L2_CID_RF_TUNER_CLASS_BASE + 41) #define V4L2_CID_RF_TUNER_LNA_GAIN (V4L2_CID_RF_TUNER_CLASS_BASE + 42) #define V4L2_CID_RF_TUNER_MIXER_GAIN_AUTO (V4L2_CID_RF_TUNER_CLASS_BASE + 51) -- cgit v1.2.3 From 9effc72fd71b6e8fd2676bcb57fac3f05ab93043 Mon Sep 17 00:00:00 2001 From: Antti Palosaari Date: Sat, 10 Oct 2015 13:51:00 -0300 Subject: [media] v4l2: add support for SDR transmitter New IOCTL ops: vidioc_enum_fmt_sdr_out vidioc_g_fmt_sdr_out vidioc_s_fmt_sdr_out vidioc_try_fmt_sdr_out New vb2 buffertype: V4L2_BUF_TYPE_SDR_OUTPUT New v4l2 capability: V4L2_CAP_SDR_OUTPUT Signed-off-by: Antti Palosaari Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 2 ++ drivers/media/v4l2-core/v4l2-dev.c | 14 ++++++++++++-- drivers/media/v4l2-core/v4l2-ioctl.c | 25 +++++++++++++++++++++++++ drivers/media/v4l2-core/videobuf-core.c | 4 +++- include/media/v4l2-ioctl.h | 8 ++++++++ include/trace/events/v4l2.h | 1 + include/uapi/linux/videodev2.h | 5 ++++- 7 files changed, 55 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index d032e9a2b212..327e83ac2469 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -214,6 +214,7 @@ static int __get_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: return get_v4l2_sliced_vbi_format(&kp->fmt.sliced, &up->fmt.sliced); case V4L2_BUF_TYPE_SDR_CAPTURE: + case V4L2_BUF_TYPE_SDR_OUTPUT: return get_v4l2_sdr_format(&kp->fmt.sdr, &up->fmt.sdr); default: pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n", @@ -260,6 +261,7 @@ static int __put_v4l2_format32(struct v4l2_format *kp, struct v4l2_format32 __us case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: return put_v4l2_sliced_vbi_format(&kp->fmt.sliced, &up->fmt.sliced); case V4L2_BUF_TYPE_SDR_CAPTURE: + case V4L2_BUF_TYPE_SDR_OUTPUT: return put_v4l2_sdr_format(&kp->fmt.sdr, &up->fmt.sdr); default: pr_info("compat_ioctl32: unexpected VIDIOC_FMT type %d\n", diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c index 71a1b93b0790..6b1eaeddbdb3 100644 --- a/drivers/media/v4l2-core/v4l2-dev.c +++ b/drivers/media/v4l2-core/v4l2-dev.c @@ -637,8 +637,8 @@ static void determine_valid_ioctls(struct video_device *vdev) ops->vidioc_try_fmt_sliced_vbi_out))) set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls); SET_VALID_IOCTL(ops, VIDIOC_G_SLICED_VBI_CAP, vidioc_g_sliced_vbi_cap); - } else if (is_sdr) { - /* SDR specific ioctls */ + } else if (is_sdr && is_rx) { + /* SDR receiver specific ioctls */ if (ops->vidioc_enum_fmt_sdr_cap) set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls); if (ops->vidioc_g_fmt_sdr_cap) @@ -647,6 +647,16 @@ static void determine_valid_ioctls(struct video_device *vdev) set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls); if (ops->vidioc_try_fmt_sdr_cap) set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls); + } else if (is_sdr && is_tx) { + /* SDR transmitter specific ioctls */ + if (ops->vidioc_enum_fmt_sdr_out) + set_bit(_IOC_NR(VIDIOC_ENUM_FMT), valid_ioctls); + if (ops->vidioc_g_fmt_sdr_out) + set_bit(_IOC_NR(VIDIOC_G_FMT), valid_ioctls); + if (ops->vidioc_s_fmt_sdr_out) + set_bit(_IOC_NR(VIDIOC_S_FMT), valid_ioctls); + if (ops->vidioc_try_fmt_sdr_out) + set_bit(_IOC_NR(VIDIOC_TRY_FMT), valid_ioctls); } if (is_vid || is_vbi || is_sdr) { diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 056a5ade5870..073ab36b880a 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -153,6 +153,7 @@ const char *v4l2_type_names[] = { [V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE] = "vid-cap-mplane", [V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE] = "vid-out-mplane", [V4L2_BUF_TYPE_SDR_CAPTURE] = "sdr-cap", + [V4L2_BUF_TYPE_SDR_OUTPUT] = "sdr-out", }; EXPORT_SYMBOL(v4l2_type_names); @@ -326,6 +327,7 @@ static void v4l_print_format(const void *arg, bool write_only) sliced->service_lines[1][i]); break; case V4L2_BUF_TYPE_SDR_CAPTURE: + case V4L2_BUF_TYPE_SDR_OUTPUT: sdr = &p->fmt.sdr; pr_cont(", pixelformat=%c%c%c%c\n", (sdr->pixelformat >> 0) & 0xff, @@ -974,6 +976,10 @@ static int check_fmt(struct file *file, enum v4l2_buf_type type) if (is_sdr && is_rx && ops->vidioc_g_fmt_sdr_cap) return 0; break; + case V4L2_BUF_TYPE_SDR_OUTPUT: + if (is_sdr && is_tx && ops->vidioc_g_fmt_sdr_out) + return 0; + break; default: break; } @@ -1324,6 +1330,11 @@ static int v4l_enum_fmt(const struct v4l2_ioctl_ops *ops, break; ret = ops->vidioc_enum_fmt_sdr_cap(file, fh, arg); break; + case V4L2_BUF_TYPE_SDR_OUTPUT: + if (unlikely(!is_tx || !is_sdr || !ops->vidioc_enum_fmt_sdr_out)) + break; + ret = ops->vidioc_enum_fmt_sdr_out(file, fh, arg); + break; } if (ret == 0) v4l_fill_fmtdesc(p); @@ -1418,6 +1429,10 @@ static int v4l_g_fmt(const struct v4l2_ioctl_ops *ops, if (unlikely(!is_rx || !is_sdr || !ops->vidioc_g_fmt_sdr_cap)) break; return ops->vidioc_g_fmt_sdr_cap(file, fh, arg); + case V4L2_BUF_TYPE_SDR_OUTPUT: + if (unlikely(!is_tx || !is_sdr || !ops->vidioc_g_fmt_sdr_out)) + break; + return ops->vidioc_g_fmt_sdr_out(file, fh, arg); } return -EINVAL; } @@ -1497,6 +1512,11 @@ static int v4l_s_fmt(const struct v4l2_ioctl_ops *ops, break; CLEAR_AFTER_FIELD(p, fmt.sdr); return ops->vidioc_s_fmt_sdr_cap(file, fh, arg); + case V4L2_BUF_TYPE_SDR_OUTPUT: + if (unlikely(!is_tx || !is_sdr || !ops->vidioc_s_fmt_sdr_out)) + break; + CLEAR_AFTER_FIELD(p, fmt.sdr); + return ops->vidioc_s_fmt_sdr_out(file, fh, arg); } return -EINVAL; } @@ -1576,6 +1596,11 @@ static int v4l_try_fmt(const struct v4l2_ioctl_ops *ops, break; CLEAR_AFTER_FIELD(p, fmt.sdr); return ops->vidioc_try_fmt_sdr_cap(file, fh, arg); + case V4L2_BUF_TYPE_SDR_OUTPUT: + if (unlikely(!is_tx || !is_sdr || !ops->vidioc_try_fmt_sdr_out)) + break; + CLEAR_AFTER_FIELD(p, fmt.sdr); + return ops->vidioc_try_fmt_sdr_out(file, fh, arg); } return -EINVAL; } diff --git a/drivers/media/v4l2-core/videobuf-core.c b/drivers/media/v4l2-core/videobuf-core.c index 926836d1813a..6c02989ee33f 100644 --- a/drivers/media/v4l2-core/videobuf-core.c +++ b/drivers/media/v4l2-core/videobuf-core.c @@ -576,7 +576,8 @@ int videobuf_qbuf(struct videobuf_queue *q, struct v4l2_buffer *b) } if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT || q->type == V4L2_BUF_TYPE_VBI_OUTPUT - || q->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT) { + || q->type == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT + || q->type == V4L2_BUF_TYPE_SDR_OUTPUT) { buf->size = b->bytesused; buf->field = b->field; buf->ts = b->timestamp; @@ -1154,6 +1155,7 @@ unsigned int videobuf_poll_stream(struct file *file, case V4L2_BUF_TYPE_VIDEO_OUTPUT: case V4L2_BUF_TYPE_VBI_OUTPUT: case V4L2_BUF_TYPE_SLICED_VBI_OUTPUT: + case V4L2_BUF_TYPE_SDR_OUTPUT: rc = POLLOUT | POLLWRNORM; break; default: diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h index 8fbbd76d78e8..017ffb2220c7 100644 --- a/include/media/v4l2-ioctl.h +++ b/include/media/v4l2-ioctl.h @@ -36,6 +36,8 @@ struct v4l2_ioctl_ops { struct v4l2_fmtdesc *f); int (*vidioc_enum_fmt_sdr_cap) (struct file *file, void *fh, struct v4l2_fmtdesc *f); + int (*vidioc_enum_fmt_sdr_out) (struct file *file, void *fh, + struct v4l2_fmtdesc *f); /* VIDIOC_G_FMT handlers */ int (*vidioc_g_fmt_vid_cap) (struct file *file, void *fh, @@ -60,6 +62,8 @@ struct v4l2_ioctl_ops { struct v4l2_format *f); int (*vidioc_g_fmt_sdr_cap) (struct file *file, void *fh, struct v4l2_format *f); + int (*vidioc_g_fmt_sdr_out) (struct file *file, void *fh, + struct v4l2_format *f); /* VIDIOC_S_FMT handlers */ int (*vidioc_s_fmt_vid_cap) (struct file *file, void *fh, @@ -84,6 +88,8 @@ struct v4l2_ioctl_ops { struct v4l2_format *f); int (*vidioc_s_fmt_sdr_cap) (struct file *file, void *fh, struct v4l2_format *f); + int (*vidioc_s_fmt_sdr_out) (struct file *file, void *fh, + struct v4l2_format *f); /* VIDIOC_TRY_FMT handlers */ int (*vidioc_try_fmt_vid_cap) (struct file *file, void *fh, @@ -108,6 +114,8 @@ struct v4l2_ioctl_ops { struct v4l2_format *f); int (*vidioc_try_fmt_sdr_cap) (struct file *file, void *fh, struct v4l2_format *f); + int (*vidioc_try_fmt_sdr_out) (struct file *file, void *fh, + struct v4l2_format *f); /* Buffer handlers */ int (*vidioc_reqbufs) (struct file *file, void *fh, struct v4l2_requestbuffers *b); diff --git a/include/trace/events/v4l2.h b/include/trace/events/v4l2.h index 04ef89b15ae2..22afa26e34b2 100644 --- a/include/trace/events/v4l2.h +++ b/include/trace/events/v4l2.h @@ -28,6 +28,7 @@ EM( V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE, "VIDEO_CAPTURE_MPLANE" ) \ EM( V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE, "VIDEO_OUTPUT_MPLANE" ) \ EM( V4L2_BUF_TYPE_SDR_CAPTURE, "SDR_CAPTURE" ) \ + EM( V4L2_BUF_TYPE_SDR_OUTPUT, "SDR_OUTPUT" ) \ EMe(V4L2_BUF_TYPE_PRIVATE, "PRIVATE" ) SHOW_TYPE diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index fa8bf2d07a52..f95e1ef0e7e6 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -145,6 +145,7 @@ enum v4l2_buf_type { V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE = 9, V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE = 10, V4L2_BUF_TYPE_SDR_CAPTURE = 11, + V4L2_BUF_TYPE_SDR_OUTPUT = 12, /* Deprecated, do not use */ V4L2_BUF_TYPE_PRIVATE = 0x80, }; @@ -159,7 +160,8 @@ enum v4l2_buf_type { || (type) == V4L2_BUF_TYPE_VIDEO_OVERLAY \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY \ || (type) == V4L2_BUF_TYPE_VBI_OUTPUT \ - || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT) + || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT \ + || (type) == V4L2_BUF_TYPE_SDR_OUTPUT) enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, @@ -435,6 +437,7 @@ struct v4l2_capability { #define V4L2_CAP_SDR_CAPTURE 0x00100000 /* Is a SDR capture device */ #define V4L2_CAP_EXT_PIX_FORMAT 0x00200000 /* Supports the extended pixel format */ +#define V4L2_CAP_SDR_OUTPUT 0x00400000 /* Is a SDR output device */ #define V4L2_CAP_READWRITE 0x01000000 /* read/write systemcalls */ #define V4L2_CAP_ASYNCIO 0x02000000 /* async I/O */ -- cgit v1.2.3 From 4124a3c4abcf3c37d2445ff9a936a2d08988e01a Mon Sep 17 00:00:00 2001 From: Antti Palosaari Date: Sat, 10 Oct 2015 13:51:02 -0300 Subject: [media] v4l: add type field to v4l2_modulator struct Add type field to that struct like it counterpart v4l2_tuner already has. We need type field to distinguish different tuner types from each others for transmitter too. Signed-off-by: Antti Palosaari Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ioctl.c | 18 +++++++++++++++++- include/uapi/linux/videodev2.h | 3 ++- 2 files changed, 19 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 073ab36b880a..7486af2c8ae4 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1646,15 +1646,31 @@ static int v4l_s_tuner(const struct v4l2_ioctl_ops *ops, static int v4l_g_modulator(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { + struct video_device *vfd = video_devdata(file); struct v4l2_modulator *p = arg; int err; + if (vfd->vfl_type == VFL_TYPE_RADIO) + p->type = V4L2_TUNER_RADIO; + err = ops->vidioc_g_modulator(file, fh, p); if (!err) p->capability |= V4L2_TUNER_CAP_FREQ_BANDS; return err; } +static int v4l_s_modulator(const struct v4l2_ioctl_ops *ops, + struct file *file, void *fh, void *arg) +{ + struct video_device *vfd = video_devdata(file); + struct v4l2_modulator *p = arg; + + if (vfd->vfl_type == VFL_TYPE_RADIO) + p->type = V4L2_TUNER_RADIO; + + return ops->vidioc_s_modulator(file, fh, p); +} + static int v4l_g_frequency(const struct v4l2_ioctl_ops *ops, struct file *file, void *fh, void *arg) { @@ -2441,7 +2457,7 @@ static struct v4l2_ioctl_info v4l2_ioctls[] = { IOCTL_INFO_STD(VIDIOC_G_AUDOUT, vidioc_g_audout, v4l_print_audioout, 0), IOCTL_INFO_STD(VIDIOC_S_AUDOUT, vidioc_s_audout, v4l_print_audioout, INFO_FL_PRIO), IOCTL_INFO_FNC(VIDIOC_G_MODULATOR, v4l_g_modulator, v4l_print_modulator, INFO_FL_CLEAR(v4l2_modulator, index)), - IOCTL_INFO_STD(VIDIOC_S_MODULATOR, vidioc_s_modulator, v4l_print_modulator, INFO_FL_PRIO), + IOCTL_INFO_FNC(VIDIOC_S_MODULATOR, v4l_s_modulator, v4l_print_modulator, INFO_FL_PRIO), IOCTL_INFO_FNC(VIDIOC_G_FREQUENCY, v4l_g_frequency, v4l_print_frequency, INFO_FL_CLEAR(v4l2_frequency, tuner)), IOCTL_INFO_FNC(VIDIOC_S_FREQUENCY, v4l_s_frequency, v4l_print_frequency, INFO_FL_PRIO), IOCTL_INFO_FNC(VIDIOC_CROPCAP, v4l_cropcap, v4l_print_cropcap, INFO_FL_CLEAR(v4l2_cropcap, type)), diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index f95e1ef0e7e6..a0e87d16b726 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1593,7 +1593,8 @@ struct v4l2_modulator { __u32 rangelow; __u32 rangehigh; __u32 txsubchans; - __u32 reserved[4]; + __u32 type; /* enum v4l2_tuner_type */ + __u32 reserved[3]; }; /* Flags for the 'capability' field */ -- cgit v1.2.3 From 39bb0c92829ad9d7525fa809aa89fc411c85a2c2 Mon Sep 17 00:00:00 2001 From: Samuel Li Date: Thu, 8 Oct 2015 16:31:43 -0400 Subject: drm/amdgpu: update the core VI support for Stoney Add core VI enablement for Stoney. Signed-off-by: Samuel Li Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 ++- drivers/gpu/drm/amd/amdgpu/vi.c | 36 +++++++++++++++++++++++++----- include/uapi/drm/amdgpu_drm.h | 2 +- 3 files changed, 34 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 645690bcb4b3..d5b421330145 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1166,7 +1166,8 @@ static int amdgpu_early_init(struct amdgpu_device *adev) case CHIP_TONGA: case CHIP_FIJI: case CHIP_CARRIZO: - if (adev->asic_type == CHIP_CARRIZO) + case CHIP_STONEY: + if (adev->asic_type == CHIP_CARRIZO || adev->asic_type == CHIP_STONEY) adev->family = AMDGPU_FAMILY_CZ; else adev->family = AMDGPU_FAMILY_VI; diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c index b55ceb14fdcd..9904761c9c37 100644 --- a/drivers/gpu/drm/amd/amdgpu/vi.c +++ b/drivers/gpu/drm/amd/amdgpu/vi.c @@ -232,6 +232,13 @@ static const u32 cz_mgcg_cgcg_init[] = mmHDP_XDP_CGTT_BLK_CTRL, 0xc0000fff, 0x00000104, }; +static const u32 stoney_mgcg_cgcg_init[] = +{ + mmCGTT_DRM_CLK_CTRL0, 0xffffffff, 0x00000100, + mmHDP_XDP_CGTT_BLK_CTRL, 0xffffffff, 0x00000104, + mmHDP_HOST_PATH_CNTL, 0xffffffff, 0x0f000027, +}; + static void vi_init_golden_registers(struct amdgpu_device *adev) { /* Some of the registers might be dependent on GRBM_GFX_INDEX */ @@ -258,6 +265,11 @@ static void vi_init_golden_registers(struct amdgpu_device *adev) cz_mgcg_cgcg_init, (const u32)ARRAY_SIZE(cz_mgcg_cgcg_init)); break; + case CHIP_STONEY: + amdgpu_program_register_sequence(adev, + stoney_mgcg_cgcg_init, + (const u32)ARRAY_SIZE(stoney_mgcg_cgcg_init)); + break; default: break; } @@ -488,6 +500,7 @@ static int vi_read_register(struct amdgpu_device *adev, u32 se_num, case CHIP_FIJI: case CHIP_TONGA: case CHIP_CARRIZO: + case CHIP_STONEY: asic_register_table = cz_allowed_read_registers; size = ARRAY_SIZE(cz_allowed_read_registers); break; @@ -543,8 +556,10 @@ static void vi_print_gpu_status_regs(struct amdgpu_device *adev) RREG32(mmSRBM_STATUS2)); dev_info(adev->dev, " SDMA0_STATUS_REG = 0x%08X\n", RREG32(mmSDMA0_STATUS_REG + SDMA0_REGISTER_OFFSET)); - dev_info(adev->dev, " SDMA1_STATUS_REG = 0x%08X\n", - RREG32(mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET)); + if (adev->sdma.num_instances > 1) { + dev_info(adev->dev, " SDMA1_STATUS_REG = 0x%08X\n", + RREG32(mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET)); + } dev_info(adev->dev, " CP_STAT = 0x%08x\n", RREG32(mmCP_STAT)); dev_info(adev->dev, " CP_STALLED_STAT1 = 0x%08x\n", RREG32(mmCP_STALLED_STAT1)); @@ -639,9 +654,11 @@ u32 vi_gpu_check_soft_reset(struct amdgpu_device *adev) reset_mask |= AMDGPU_RESET_DMA; /* SDMA1_STATUS_REG */ - tmp = RREG32(mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET); - if (!(tmp & SDMA0_STATUS_REG__IDLE_MASK)) - reset_mask |= AMDGPU_RESET_DMA1; + if (adev->sdma.num_instances > 1) { + tmp = RREG32(mmSDMA0_STATUS_REG + SDMA1_REGISTER_OFFSET); + if (!(tmp & SDMA0_STATUS_REG__IDLE_MASK)) + reset_mask |= AMDGPU_RESET_DMA1; + } #if 0 /* VCE_STATUS */ if (adev->asic_type != CHIP_TOPAZ) { @@ -1316,6 +1333,7 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) adev->num_ip_blocks = ARRAY_SIZE(tonga_ip_blocks); break; case CHIP_CARRIZO: + case CHIP_STONEY: adev->ip_blocks = cz_ip_blocks; adev->num_ip_blocks = ARRAY_SIZE(cz_ip_blocks); break; @@ -1327,11 +1345,18 @@ int vi_set_ip_blocks(struct amdgpu_device *adev) return 0; } +#define ATI_REV_ID_FUSE_MACRO__ADDRESS 0xC0014044 +#define ATI_REV_ID_FUSE_MACRO__SHIFT 9 +#define ATI_REV_ID_FUSE_MACRO__MASK 0x00001E00 + static uint32_t vi_get_rev_id(struct amdgpu_device *adev) { if (adev->asic_type == CHIP_TOPAZ) return (RREG32(mmPCIE_EFUSE4) & PCIE_EFUSE4__STRAP_BIF_ATI_REV_ID_MASK) >> PCIE_EFUSE4__STRAP_BIF_ATI_REV_ID__SHIFT; + else if (adev->flags & AMD_IS_APU) + return (RREG32_SMC(ATI_REV_ID_FUSE_MACRO__ADDRESS) & ATI_REV_ID_FUSE_MACRO__MASK) + >> ATI_REV_ID_FUSE_MACRO__SHIFT; else return (RREG32(mmCC_DRM_ID_STRAPS) & CC_DRM_ID_STRAPS__ATI_REV_ID_MASK) >> CC_DRM_ID_STRAPS__ATI_REV_ID__SHIFT; @@ -1398,6 +1423,7 @@ static int vi_common_early_init(void *handle) adev->firmware.smu_load = true; break; case CHIP_CARRIZO: + case CHIP_STONEY: adev->has_uvd = true; adev->cg_flags = 0; /* Disable UVD pg */ diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index fbdd11851725..e52933a73580 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -640,6 +640,6 @@ struct drm_amdgpu_info_hw_ip { #define AMDGPU_FAMILY_CI 120 /* Bonaire, Hawaii */ #define AMDGPU_FAMILY_KV 125 /* Kaveri, Kabini, Mullins */ #define AMDGPU_FAMILY_VI 130 /* Iceland, Tonga */ -#define AMDGPU_FAMILY_CZ 135 /* Carrizo */ +#define AMDGPU_FAMILY_CZ 135 /* Carrizo, Stoney */ #endif -- cgit v1.2.3 From b9788a446828703cf126dfb9d3843d240af44122 Mon Sep 17 00:00:00 2001 From: Peng Tao Date: Wed, 21 Oct 2015 03:18:16 +0800 Subject: nfs: add missing linux/types.h After merging the nfs tree, today's linux-next build (powerpc allyesconfig produced this warning: ./usr/include/linux/nfs.h:40: found __[us]{8,16,32,64} type without #include Reported-by: Stephen Rothwell Signed-off-by: Peng Tao Signed-off-by: Trond Myklebust --- include/uapi/linux/nfs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfs.h b/include/uapi/linux/nfs.h index c6b86cc404f8..654bae3f1a38 100644 --- a/include/uapi/linux/nfs.h +++ b/include/uapi/linux/nfs.h @@ -7,6 +7,8 @@ #ifndef _UAPI_LINUX_NFS_H #define _UAPI_LINUX_NFS_H +#include + #define NFS_PROGRAM 100003 #define NFS_PORT 2049 #define NFS_MAXDATA 8192 -- cgit v1.2.3 From bbd3e064362e5057cc4799ba2e4d68c7593e490b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Oct 2015 14:10:48 +0200 Subject: block: add an API for Persistent Reservations This commits adds a driver API and ioctls for controlling Persistent Reservations s/genericly/generically/ at the block layer. Persistent Reservations are supported by SCSI and NVMe and allow controlling who gets access to a device in a shared storage setup. Note that we add a pr_ops structure to struct block_device_operations instead of adding the members directly to avoid bloating all instances of devices that will never support Persistent Reservations. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- Documentation/block/pr.txt | 119 +++++++++++++++++++++++++++++++++++++++++++++ block/ioctl.c | 103 +++++++++++++++++++++++++++++++++++++++ include/linux/blkdev.h | 2 + include/linux/pr.h | 18 +++++++ include/uapi/linux/pr.h | 48 ++++++++++++++++++ 5 files changed, 290 insertions(+) create mode 100644 Documentation/block/pr.txt create mode 100644 include/linux/pr.h create mode 100644 include/uapi/linux/pr.h (limited to 'include/uapi') diff --git a/Documentation/block/pr.txt b/Documentation/block/pr.txt new file mode 100644 index 000000000000..d3eb1ca65051 --- /dev/null +++ b/Documentation/block/pr.txt @@ -0,0 +1,119 @@ + +Block layer support for Persistent Reservations +=============================================== + +The Linux kernel supports a user space interface for simplified +Persistent Reservations which map to block devices that support +these (like SCSI). Persistent Reservations allow restricting +access to block devices to specific initiators in a shared storage +setup. + +This document gives a general overview of the support ioctl commands. +For a more detailed reference please refer the the SCSI Primary +Commands standard, specifically the section on Reservations and the +"PERSISTENT RESERVE IN" and "PERSISTENT RESERVE OUT" commands. + +All implementations are expected to ensure the reservations survive +a power loss and cover all connections in a multi path environment. +These behaviors are optional in SPC but will be automatically applied +by Linux. + + +The following types of reservations are supported: +-------------------------------------------------- + + - PR_WRITE_EXCLUSIVE + + Only the initiator that owns the reservation can write to the + device. Any initiator can read from the device. + + - PR_EXCLUSIVE_ACCESS + + Only the initiator that owns the reservation can access the + device. + + - PR_WRITE_EXCLUSIVE_REG_ONLY + + Only initiators with a registered key can write to the device, + Any initiator can read from the device. + + - PR_EXCLUSIVE_ACCESS_REG_ONLY + + Only initiators with a registered key can access the device. + + - PR_WRITE_EXCLUSIVE_ALL_REGS + + Only initiators with a registered key can write to the device, + Any initiator can read from the device. + All initiators with a registered key are considered reservation + holders. + Please reference the SPC spec on the meaning of a reservation + holder if you want to use this type. + + - PR_EXCLUSIVE_ACCESS_ALL_REGS + + Only initiators with a registered key can access the device. + All initiators with a registered key are considered reservation + holders. + Please reference the SPC spec on the meaning of a reservation + holder if you want to use this type. + + +The following ioctl are supported: +---------------------------------- + +1. IOC_PR_REGISTER + +This ioctl command registers a new reservation if the new_key argument +is non-null. If no existing reservation exists old_key must be zero, +if an existing reservation should be replaced old_key must contain +the old reservation key. + +If the new_key argument is 0 it unregisters the existing reservation passed +in old_key. + + +2. IOC_PR_RESERVE + +This ioctl command reserves the device and thus restricts access for other +devices based on the type argument. The key argument must be the existing +reservation key for the device as acquired by the IOC_PR_REGISTER, +IOC_PR_REGISTER_IGNORE, IOC_PR_PREEMPT or IOC_PR_PREEMPT_ABORT commands. + + +3. IOC_PR_RELEASE + +This ioctl command releases the reservation specified by key and flags +and thus removes any access restriction implied by it. + + +4. IOC_PR_PREEMPT + +This ioctl command releases the existing reservation referred to by +old_key and replaces it with a a new reservation of type for the +reservation key new_key. + + +5. IOC_PR_PREEMPT_ABORT + +This ioctl command works like IOC_PR_PREEMPT except that it also aborts +any outstanding command sent over a connection identified by old_key. + +6. IOC_PR_CLEAR + +This ioctl command unregisters both key and any other reservation key +registered with the device and drops any existing reservation. + + +Flags +----- + +All the ioctls have a flag field. Currently only one flag is supported: + + - PR_FL_IGNORE_KEY + + Ignore the existing reservation key. This is commonly supported for + IOC_PR_REGISTER, and some implementation may support the flag for + IOC_PR_RESERVE. + +For all unknown flags the kernel will return -EOPNOTSUPP. diff --git a/block/ioctl.c b/block/ioctl.c index df62b47d2379..0918aed2d847 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -7,6 +7,7 @@ #include #include #include +#include #include static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg) @@ -295,6 +296,96 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode, */ EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl); +static int blkdev_pr_register(struct block_device *bdev, + struct pr_registration __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_registration reg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_register) + return -EOPNOTSUPP; + if (copy_from_user(®, arg, sizeof(reg))) + return -EFAULT; + + if (reg.flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags); +} + +static int blkdev_pr_reserve(struct block_device *bdev, + struct pr_reservation __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_reservation rsv; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_reserve) + return -EOPNOTSUPP; + if (copy_from_user(&rsv, arg, sizeof(rsv))) + return -EFAULT; + + if (rsv.flags & ~PR_FL_IGNORE_KEY) + return -EOPNOTSUPP; + return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags); +} + +static int blkdev_pr_release(struct block_device *bdev, + struct pr_reservation __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_reservation rsv; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_release) + return -EOPNOTSUPP; + if (copy_from_user(&rsv, arg, sizeof(rsv))) + return -EFAULT; + + if (rsv.flags) + return -EOPNOTSUPP; + return ops->pr_release(bdev, rsv.key, rsv.type); +} + +static int blkdev_pr_preempt(struct block_device *bdev, + struct pr_preempt __user *arg, bool abort) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_preempt p; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_preempt) + return -EOPNOTSUPP; + if (copy_from_user(&p, arg, sizeof(p))) + return -EFAULT; + + if (p.flags) + return -EOPNOTSUPP; + return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort); +} + +static int blkdev_pr_clear(struct block_device *bdev, + struct pr_clear __user *arg) +{ + const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; + struct pr_clear c; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + if (!ops || !ops->pr_clear) + return -EOPNOTSUPP; + if (copy_from_user(&c, arg, sizeof(c))) + return -EFAULT; + + if (c.flags) + return -EOPNOTSUPP; + return ops->pr_clear(bdev, c.key); +} + /* * Is it an unrecognized ioctl? The correct returns are either * ENOTTY (final) or ENOIOCTLCMD ("I don't know this one, try a @@ -477,6 +568,18 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd, case BLKTRACESETUP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); + case IOC_PR_REGISTER: + return blkdev_pr_register(bdev, argp); + case IOC_PR_RESERVE: + return blkdev_pr_reserve(bdev, argp); + case IOC_PR_RELEASE: + return blkdev_pr_release(bdev, argp); + case IOC_PR_PREEMPT: + return blkdev_pr_preempt(bdev, argp, false); + case IOC_PR_PREEMPT_ABORT: + return blkdev_pr_preempt(bdev, argp, true); + case IOC_PR_CLEAR: + return blkdev_pr_clear(bdev, argp); default: return __blkdev_driver_ioctl(bdev, mode, cmd, arg); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 19c2e947d4d1..fe25da05e823 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -35,6 +35,7 @@ struct sg_io_hdr; struct bsg_job; struct blkcg_gq; struct blk_flush_queue; +struct pr_ops; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -1633,6 +1634,7 @@ struct block_device_operations { /* this callback is with swap_lock and sometimes page table lock held */ void (*swap_slot_free_notify) (struct block_device *, unsigned long); struct module *owner; + const struct pr_ops *pr_ops; }; extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, diff --git a/include/linux/pr.h b/include/linux/pr.h new file mode 100644 index 000000000000..65c01c10b335 --- /dev/null +++ b/include/linux/pr.h @@ -0,0 +1,18 @@ +#ifndef LINUX_PR_H +#define LINUX_PR_H + +#include + +struct pr_ops { + int (*pr_register)(struct block_device *bdev, u64 old_key, u64 new_key, + u32 flags); + int (*pr_reserve)(struct block_device *bdev, u64 key, + enum pr_type type, u32 flags); + int (*pr_release)(struct block_device *bdev, u64 key, + enum pr_type type); + int (*pr_preempt)(struct block_device *bdev, u64 old_key, u64 new_key, + enum pr_type type, bool abort); + int (*pr_clear)(struct block_device *bdev, u64 key); +}; + +#endif /* LINUX_PR_H */ diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h new file mode 100644 index 000000000000..57d7c0f916b6 --- /dev/null +++ b/include/uapi/linux/pr.h @@ -0,0 +1,48 @@ +#ifndef _UAPI_PR_H +#define _UAPI_PR_H + +enum pr_type { + PR_WRITE_EXCLUSIVE = 1, + PR_EXCLUSIVE_ACCESS = 2, + PR_WRITE_EXCLUSIVE_REG_ONLY = 3, + PR_EXCLUSIVE_ACCESS_REG_ONLY = 4, + PR_WRITE_EXCLUSIVE_ALL_REGS = 5, + PR_EXCLUSIVE_ACCESS_ALL_REGS = 6, +}; + +struct pr_reservation { + __u64 key; + __u32 type; + __u32 flags; +}; + +struct pr_registration { + __u64 old_key; + __u64 new_key; + __u32 flags; + __u32 __pad; +}; + +struct pr_preempt { + __u64 old_key; + __u64 new_key; + __u32 type; + __u32 flags; +}; + +struct pr_clear { + __u64 key; + __u32 flags; + __u32 __pad; +}; + +#define PR_FL_IGNORE_KEY (1 << 0) /* ignore existing key */ + +#define IOC_PR_REGISTER _IOW('p', 200, struct pr_registration) +#define IOC_PR_RESERVE _IOW('p', 201, struct pr_reservation) +#define IOC_PR_RELEASE _IOW('p', 202, struct pr_reservation) +#define IOC_PR_PREEMPT _IOW('p', 203, struct pr_preempt) +#define IOC_PR_PREEMPT_ABORT _IOW('p', 204, struct pr_preempt) +#define IOC_PR_CLEAR _IOW('p', 205, struct pr_clear) + +#endif /* _UAPI_PR_H */ -- cgit v1.2.3 From 1d008a1df927846788b9dc02e770f65951f98ddc Mon Sep 17 00:00:00 2001 From: Joe Stringer Date: Mon, 19 Oct 2015 19:18:58 -0700 Subject: openvswitch: Clarify conntrack COMMIT behaviour The presence of this attribute does not modify the ct_state for the current packet, only future packets. Make this more clear in the header definition. Signed-off-by: Joe Stringer Acked-by: Thomas Graf Acked-by: Pravin B Shelar Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 036f73bc54cd..e663627a8ef3 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -620,7 +620,8 @@ struct ovs_action_hash { * enum ovs_ct_attr - Attributes for %OVS_ACTION_ATTR_CT action. * @OVS_CT_ATTR_COMMIT: If present, commits the connection to the conntrack * table. This allows future packets for the same connection to be identified - * as 'established' or 'related'. + * as 'established' or 'related'. The flow key for the current packet will + * retain the pre-commit connection state. * @OVS_CT_ATTR_ZONE: u16 connection tracking zone. * @OVS_CT_ATTR_MARK: u32 value followed by u32 mask. For each bit set in the * mask, the corresponding bit in the value is copied to the connection -- cgit v1.2.3 From 6d8a74972b7115b41d4d17a4444c026755ca24be Mon Sep 17 00:00:00 2001 From: Eran Ben Elisha Date: Wed, 21 Oct 2015 17:00:42 +0300 Subject: IB/core: Extend ib_uverbs_create_qp ib_uverbs_ex_create_qp follows the extension verbs mechanism. New features (for example, QP creation flags field which is added in a downstream patch) could used via user-space libraries without breaking the ABI. Signed-off-by: Eran Ben Elisha Reviewed-by: Haggai Eran Signed-off-by: Doug Ledford --- drivers/infiniband/core/uverbs.h | 1 + drivers/infiniband/core/uverbs_cmd.c | 254 +++++++++++++++++++++++++--------- drivers/infiniband/core/uverbs_main.c | 1 + include/uapi/rdma/ib_user_verbs.h | 26 ++++ 4 files changed, 217 insertions(+), 65 deletions(-) (limited to 'include/uapi') diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index 3863d33c243d..94bbd8c155fc 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -272,5 +272,6 @@ IB_UVERBS_DECLARE_EX_CMD(create_flow); IB_UVERBS_DECLARE_EX_CMD(destroy_flow); IB_UVERBS_DECLARE_EX_CMD(query_device); IB_UVERBS_DECLARE_EX_CMD(create_cq); +IB_UVERBS_DECLARE_EX_CMD(create_qp); #endif /* UVERBS_H */ diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 88b3b78340f2..b2a37d545e0b 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -1741,66 +1741,65 @@ ssize_t ib_uverbs_destroy_cq(struct ib_uverbs_file *file, return in_len; } -ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, - struct ib_device *ib_dev, - const char __user *buf, int in_len, - int out_len) -{ - struct ib_uverbs_create_qp cmd; - struct ib_uverbs_create_qp_resp resp; - struct ib_udata udata; - struct ib_uqp_object *obj; - struct ib_device *device; - struct ib_pd *pd = NULL; - struct ib_xrcd *xrcd = NULL; - struct ib_uobject *uninitialized_var(xrcd_uobj); - struct ib_cq *scq = NULL, *rcq = NULL; - struct ib_srq *srq = NULL; - struct ib_qp *qp; - struct ib_qp_init_attr attr; - int ret; - - if (out_len < sizeof resp) - return -ENOSPC; - - if (copy_from_user(&cmd, buf, sizeof cmd)) - return -EFAULT; +static int create_qp(struct ib_uverbs_file *file, + struct ib_udata *ucore, + struct ib_udata *uhw, + struct ib_uverbs_ex_create_qp *cmd, + size_t cmd_sz, + int (*cb)(struct ib_uverbs_file *file, + struct ib_uverbs_ex_create_qp_resp *resp, + struct ib_udata *udata), + void *context) +{ + struct ib_uqp_object *obj; + struct ib_device *device; + struct ib_pd *pd = NULL; + struct ib_xrcd *xrcd = NULL; + struct ib_uobject *uninitialized_var(xrcd_uobj); + struct ib_cq *scq = NULL, *rcq = NULL; + struct ib_srq *srq = NULL; + struct ib_qp *qp; + char *buf; + struct ib_qp_init_attr attr; + struct ib_uverbs_ex_create_qp_resp resp; + int ret; - if (cmd.qp_type == IB_QPT_RAW_PACKET && !capable(CAP_NET_RAW)) + if (cmd->qp_type == IB_QPT_RAW_PACKET && !capable(CAP_NET_RAW)) return -EPERM; - INIT_UDATA(&udata, buf + sizeof cmd, - (unsigned long) cmd.response + sizeof resp, - in_len - sizeof cmd, out_len - sizeof resp); - obj = kzalloc(sizeof *obj, GFP_KERNEL); if (!obj) return -ENOMEM; - init_uobj(&obj->uevent.uobject, cmd.user_handle, file->ucontext, &qp_lock_class); + init_uobj(&obj->uevent.uobject, cmd->user_handle, file->ucontext, + &qp_lock_class); down_write(&obj->uevent.uobject.mutex); - if (cmd.qp_type == IB_QPT_XRC_TGT) { - xrcd = idr_read_xrcd(cmd.pd_handle, file->ucontext, &xrcd_uobj); + if (cmd->qp_type == IB_QPT_XRC_TGT) { + xrcd = idr_read_xrcd(cmd->pd_handle, file->ucontext, + &xrcd_uobj); if (!xrcd) { ret = -EINVAL; goto err_put; } device = xrcd->device; } else { - if (cmd.qp_type == IB_QPT_XRC_INI) { - cmd.max_recv_wr = cmd.max_recv_sge = 0; + if (cmd->qp_type == IB_QPT_XRC_INI) { + cmd->max_recv_wr = 0; + cmd->max_recv_sge = 0; } else { - if (cmd.is_srq) { - srq = idr_read_srq(cmd.srq_handle, file->ucontext); + if (cmd->is_srq) { + srq = idr_read_srq(cmd->srq_handle, + file->ucontext); if (!srq || srq->srq_type != IB_SRQT_BASIC) { ret = -EINVAL; goto err_put; } } - if (cmd.recv_cq_handle != cmd.send_cq_handle) { - rcq = idr_read_cq(cmd.recv_cq_handle, file->ucontext, 0); + if (cmd->recv_cq_handle != cmd->send_cq_handle) { + rcq = idr_read_cq(cmd->recv_cq_handle, + file->ucontext, 0); if (!rcq) { ret = -EINVAL; goto err_put; @@ -1808,9 +1807,9 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, } } - scq = idr_read_cq(cmd.send_cq_handle, file->ucontext, !!rcq); + scq = idr_read_cq(cmd->send_cq_handle, file->ucontext, !!rcq); rcq = rcq ?: scq; - pd = idr_read_pd(cmd.pd_handle, file->ucontext); + pd = idr_read_pd(cmd->pd_handle, file->ucontext); if (!pd || !scq) { ret = -EINVAL; goto err_put; @@ -1825,31 +1824,49 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, attr.recv_cq = rcq; attr.srq = srq; attr.xrcd = xrcd; - attr.sq_sig_type = cmd.sq_sig_all ? IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR; - attr.qp_type = cmd.qp_type; + attr.sq_sig_type = cmd->sq_sig_all ? IB_SIGNAL_ALL_WR : + IB_SIGNAL_REQ_WR; + attr.qp_type = cmd->qp_type; attr.create_flags = 0; - attr.cap.max_send_wr = cmd.max_send_wr; - attr.cap.max_recv_wr = cmd.max_recv_wr; - attr.cap.max_send_sge = cmd.max_send_sge; - attr.cap.max_recv_sge = cmd.max_recv_sge; - attr.cap.max_inline_data = cmd.max_inline_data; + attr.cap.max_send_wr = cmd->max_send_wr; + attr.cap.max_recv_wr = cmd->max_recv_wr; + attr.cap.max_send_sge = cmd->max_send_sge; + attr.cap.max_recv_sge = cmd->max_recv_sge; + attr.cap.max_inline_data = cmd->max_inline_data; obj->uevent.events_reported = 0; INIT_LIST_HEAD(&obj->uevent.event_list); INIT_LIST_HEAD(&obj->mcast_list); - if (cmd.qp_type == IB_QPT_XRC_TGT) + if (cmd_sz >= offsetof(typeof(*cmd), create_flags) + + sizeof(cmd->create_flags)) + attr.create_flags = cmd->create_flags; + + if (attr.create_flags) { + ret = -EINVAL; + goto err_put; + } + + buf = (void *)cmd + sizeof(*cmd); + if (cmd_sz > sizeof(*cmd)) + if (!(buf[0] == 0 && !memcmp(buf, buf + 1, + cmd_sz - sizeof(*cmd) - 1))) { + ret = -EINVAL; + goto err_put; + } + + if (cmd->qp_type == IB_QPT_XRC_TGT) qp = ib_create_qp(pd, &attr); else - qp = device->create_qp(pd, &attr, &udata); + qp = device->create_qp(pd, &attr, uhw); if (IS_ERR(qp)) { ret = PTR_ERR(qp); goto err_put; } - if (cmd.qp_type != IB_QPT_XRC_TGT) { + if (cmd->qp_type != IB_QPT_XRC_TGT) { qp->real_qp = qp; qp->device = device; qp->pd = pd; @@ -1875,19 +1892,20 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, goto err_destroy; memset(&resp, 0, sizeof resp); - resp.qpn = qp->qp_num; - resp.qp_handle = obj->uevent.uobject.id; - resp.max_recv_sge = attr.cap.max_recv_sge; - resp.max_send_sge = attr.cap.max_send_sge; - resp.max_recv_wr = attr.cap.max_recv_wr; - resp.max_send_wr = attr.cap.max_send_wr; - resp.max_inline_data = attr.cap.max_inline_data; + resp.base.qpn = qp->qp_num; + resp.base.qp_handle = obj->uevent.uobject.id; + resp.base.max_recv_sge = attr.cap.max_recv_sge; + resp.base.max_send_sge = attr.cap.max_send_sge; + resp.base.max_recv_wr = attr.cap.max_recv_wr; + resp.base.max_send_wr = attr.cap.max_send_wr; + resp.base.max_inline_data = attr.cap.max_inline_data; - if (copy_to_user((void __user *) (unsigned long) cmd.response, - &resp, sizeof resp)) { - ret = -EFAULT; - goto err_copy; - } + resp.response_length = offsetof(typeof(resp), response_length) + + sizeof(resp.response_length); + + ret = cb(file, &resp, ucore); + if (ret) + goto err_cb; if (xrcd) { obj->uxrcd = container_of(xrcd_uobj, struct ib_uxrcd_object, @@ -1913,9 +1931,8 @@ ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, up_write(&obj->uevent.uobject.mutex); - return in_len; - -err_copy: + return 0; +err_cb: idr_remove_uobj(&ib_uverbs_qp_idr, &obj->uevent.uobject); err_destroy: @@ -1937,6 +1954,113 @@ err_put: return ret; } +static int ib_uverbs_create_qp_cb(struct ib_uverbs_file *file, + struct ib_uverbs_ex_create_qp_resp *resp, + struct ib_udata *ucore) +{ + if (ib_copy_to_udata(ucore, &resp->base, sizeof(resp->base))) + return -EFAULT; + + return 0; +} + +ssize_t ib_uverbs_create_qp(struct ib_uverbs_file *file, + struct ib_device *ib_dev, + const char __user *buf, int in_len, + int out_len) +{ + struct ib_uverbs_create_qp cmd; + struct ib_uverbs_ex_create_qp cmd_ex; + struct ib_udata ucore; + struct ib_udata uhw; + ssize_t resp_size = sizeof(struct ib_uverbs_create_qp_resp); + int err; + + if (out_len < resp_size) + return -ENOSPC; + + if (copy_from_user(&cmd, buf, sizeof(cmd))) + return -EFAULT; + + INIT_UDATA(&ucore, buf, (unsigned long)cmd.response, sizeof(cmd), + resp_size); + INIT_UDATA(&uhw, buf + sizeof(cmd), + (unsigned long)cmd.response + resp_size, + in_len - sizeof(cmd), out_len - resp_size); + + memset(&cmd_ex, 0, sizeof(cmd_ex)); + cmd_ex.user_handle = cmd.user_handle; + cmd_ex.pd_handle = cmd.pd_handle; + cmd_ex.send_cq_handle = cmd.send_cq_handle; + cmd_ex.recv_cq_handle = cmd.recv_cq_handle; + cmd_ex.srq_handle = cmd.srq_handle; + cmd_ex.max_send_wr = cmd.max_send_wr; + cmd_ex.max_recv_wr = cmd.max_recv_wr; + cmd_ex.max_send_sge = cmd.max_send_sge; + cmd_ex.max_recv_sge = cmd.max_recv_sge; + cmd_ex.max_inline_data = cmd.max_inline_data; + cmd_ex.sq_sig_all = cmd.sq_sig_all; + cmd_ex.qp_type = cmd.qp_type; + cmd_ex.is_srq = cmd.is_srq; + + err = create_qp(file, &ucore, &uhw, &cmd_ex, + offsetof(typeof(cmd_ex), is_srq) + + sizeof(cmd.is_srq), ib_uverbs_create_qp_cb, + NULL); + + if (err) + return err; + + return in_len; +} + +static int ib_uverbs_ex_create_qp_cb(struct ib_uverbs_file *file, + struct ib_uverbs_ex_create_qp_resp *resp, + struct ib_udata *ucore) +{ + if (ib_copy_to_udata(ucore, resp, resp->response_length)) + return -EFAULT; + + return 0; +} + +int ib_uverbs_ex_create_qp(struct ib_uverbs_file *file, + struct ib_device *ib_dev, + struct ib_udata *ucore, + struct ib_udata *uhw) +{ + struct ib_uverbs_ex_create_qp_resp resp; + struct ib_uverbs_ex_create_qp cmd = {0}; + int err; + + if (ucore->inlen < (offsetof(typeof(cmd), comp_mask) + + sizeof(cmd.comp_mask))) + return -EINVAL; + + err = ib_copy_from_udata(&cmd, ucore, min(sizeof(cmd), ucore->inlen)); + if (err) + return err; + + if (cmd.comp_mask) + return -EINVAL; + + if (cmd.reserved) + return -EINVAL; + + if (ucore->outlen < (offsetof(typeof(resp), response_length) + + sizeof(resp.response_length))) + return -ENOSPC; + + err = create_qp(file, ucore, uhw, &cmd, + min(ucore->inlen, sizeof(cmd)), + ib_uverbs_ex_create_qp_cb, NULL); + + if (err) + return err; + + return 0; +} + ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file, struct ib_device *ib_dev, const char __user *buf, int in_len, int out_len) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index c29a660c72fe..e3ef28861be6 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -127,6 +127,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file, [IB_USER_VERBS_EX_CMD_DESTROY_FLOW] = ib_uverbs_ex_destroy_flow, [IB_USER_VERBS_EX_CMD_QUERY_DEVICE] = ib_uverbs_ex_query_device, [IB_USER_VERBS_EX_CMD_CREATE_CQ] = ib_uverbs_ex_create_cq, + [IB_USER_VERBS_EX_CMD_CREATE_QP] = ib_uverbs_ex_create_qp, }; static void ib_uverbs_add_one(struct ib_device *device); diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h index 978841eeaff1..8126c143a519 100644 --- a/include/uapi/rdma/ib_user_verbs.h +++ b/include/uapi/rdma/ib_user_verbs.h @@ -92,6 +92,7 @@ enum { enum { IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE, IB_USER_VERBS_EX_CMD_CREATE_CQ = IB_USER_VERBS_CMD_CREATE_CQ, + IB_USER_VERBS_EX_CMD_CREATE_QP = IB_USER_VERBS_CMD_CREATE_QP, IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD, IB_USER_VERBS_EX_CMD_DESTROY_FLOW, }; @@ -516,6 +517,25 @@ struct ib_uverbs_create_qp { __u64 driver_data[0]; }; +struct ib_uverbs_ex_create_qp { + __u64 user_handle; + __u32 pd_handle; + __u32 send_cq_handle; + __u32 recv_cq_handle; + __u32 srq_handle; + __u32 max_send_wr; + __u32 max_recv_wr; + __u32 max_send_sge; + __u32 max_recv_sge; + __u32 max_inline_data; + __u8 sq_sig_all; + __u8 qp_type; + __u8 is_srq; + __u8 reserved; + __u32 comp_mask; + __u32 create_flags; +}; + struct ib_uverbs_open_qp { __u64 response; __u64 user_handle; @@ -538,6 +558,12 @@ struct ib_uverbs_create_qp_resp { __u32 reserved; }; +struct ib_uverbs_ex_create_qp_resp { + struct ib_uverbs_create_qp_resp base; + __u32 comp_mask; + __u32 response_length; +}; + /* * This struct needs to remain a multiple of 8 bytes to keep the * alignment of the modify QP parameters. -- cgit v1.2.3 From a43eec304259a6c637f4014a6d4767159b6a3aa3 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Tue, 20 Oct 2015 20:02:34 -0700 Subject: bpf: introduce bpf_perf_event_output() helper This helper is used to send raw data from eBPF program into special PERF_TYPE_SOFTWARE/PERF_COUNT_SW_BPF_OUTPUT perf_event. User space needs to perf_event_open() it (either for one or all cpus) and store FD into perf_event_array (similar to bpf_perf_event_read() helper) before eBPF program can send data into it. Today the programs triggered by kprobe collect the data and either store it into the maps or print it via bpf_trace_printk() where latter is the debug facility and not suitable to stream the data. This new helper replaces such bpf_trace_printk() usage and allows programs to have dedicated channel into user space for post-processing of the raw data collected. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/uapi/linux/bpf.h | 11 ++++++++++ include/uapi/linux/perf_event.h | 1 + kernel/bpf/arraymap.c | 2 ++ kernel/bpf/verifier.c | 3 ++- kernel/trace/bpf_trace.c | 46 +++++++++++++++++++++++++++++++++++++++++ 5 files changed, 62 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 564f1f091991..2e032426cfb7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -287,6 +287,17 @@ enum bpf_func_id { * Return: realm if != 0 */ BPF_FUNC_get_route_realm, + + /** + * bpf_perf_event_output(ctx, map, index, data, size) - output perf raw sample + * @ctx: struct pt_regs* + * @map: pointer to perf_event_array map + * @index: index of event in the map + * @data: data on stack to be output as raw data + * @size: size of data + * Return: 0 on success + */ + BPF_FUNC_perf_event_output, __BPF_FUNC_MAX_ID, }; diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 2881145cda86..d3c417615361 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -110,6 +110,7 @@ enum perf_sw_ids { PERF_COUNT_SW_ALIGNMENT_FAULTS = 7, PERF_COUNT_SW_EMULATION_FAULTS = 8, PERF_COUNT_SW_DUMMY = 9, + PERF_COUNT_SW_BPF_OUTPUT = 10, PERF_COUNT_SW_MAX, /* non-ABI */ }; diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index f2d9e698c753..e3cfe46b074f 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -295,6 +295,8 @@ static void *perf_event_fd_array_get_ptr(struct bpf_map *map, int fd) return (void *)attr; if (attr->type != PERF_TYPE_RAW && + !(attr->type == PERF_TYPE_SOFTWARE && + attr->config == PERF_COUNT_SW_BPF_OUTPUT) && attr->type != PERF_TYPE_HARDWARE) { perf_event_release_kernel(event); return ERR_PTR(-EINVAL); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1d6b97be79e1..b56cf51f8d42 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -245,6 +245,7 @@ static const struct { } func_limit[] = { {BPF_MAP_TYPE_PROG_ARRAY, BPF_FUNC_tail_call}, {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_read}, + {BPF_MAP_TYPE_PERF_EVENT_ARRAY, BPF_FUNC_perf_event_output}, }; static void print_verifier_state(struct verifier_env *env) @@ -910,7 +911,7 @@ static int check_map_func_compatibility(struct bpf_map *map, int func_id) * don't allow any other map type to be passed into * the special func; */ - if (bool_map != bool_func) + if (bool_func && bool_map != bool_func) return -EINVAL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 0fe96c7c8803..47febbe7998e 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -215,6 +215,50 @@ const struct bpf_func_proto bpf_perf_event_read_proto = { .arg2_type = ARG_ANYTHING, }; +static u64 bpf_perf_event_output(u64 r1, u64 r2, u64 index, u64 r4, u64 size) +{ + struct pt_regs *regs = (struct pt_regs *) (long) r1; + struct bpf_map *map = (struct bpf_map *) (long) r2; + struct bpf_array *array = container_of(map, struct bpf_array, map); + void *data = (void *) (long) r4; + struct perf_sample_data sample_data; + struct perf_event *event; + struct perf_raw_record raw = { + .size = size, + .data = data, + }; + + if (unlikely(index >= array->map.max_entries)) + return -E2BIG; + + event = (struct perf_event *)array->ptrs[index]; + if (unlikely(!event)) + return -ENOENT; + + if (unlikely(event->attr.type != PERF_TYPE_SOFTWARE || + event->attr.config != PERF_COUNT_SW_BPF_OUTPUT)) + return -EINVAL; + + if (unlikely(event->oncpu != smp_processor_id())) + return -EOPNOTSUPP; + + perf_sample_data_init(&sample_data, 0, 0); + sample_data.raw = &raw; + perf_event_output(event, &sample_data, regs); + return 0; +} + +static const struct bpf_func_proto bpf_perf_event_output_proto = { + .func = bpf_perf_event_output, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_STACK, + .arg5_type = ARG_CONST_STACK_SIZE, +}; + static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func_id) { switch (func_id) { @@ -242,6 +286,8 @@ static const struct bpf_func_proto *kprobe_prog_func_proto(enum bpf_func_id func return &bpf_get_smp_processor_id_proto; case BPF_FUNC_perf_event_read: return &bpf_perf_event_read_proto; + case BPF_FUNC_perf_event_output: + return &bpf_perf_event_output_proto; default: return NULL; } -- cgit v1.2.3 From dd461d6aa894761fe67c30ddf81eec0d08be216b Mon Sep 17 00:00:00 2001 From: Hiroshi Shimamoto Date: Fri, 28 Aug 2015 06:57:55 +0000 Subject: if_link: Add control trust VF Add netlink directives and ndo entry to trust VF user. This controls the special permission of VF user. The administrator will dedicatedly trust VF user to use some features which impacts security and/or performance. The administrator never turn it on unless VF user is fully trusted. CC: Sy Jong Choi Signed-off-by: Hiroshi Shimamoto Acked-by: Greg Rose Tested-by: Krishneil Singh Signed-off-by: Jeff Kirsher --- include/linux/if_link.h | 1 + include/linux/netdevice.h | 3 +++ include/uapi/linux/if_link.h | 6 ++++++ net/core/rtnetlink.c | 24 +++++++++++++++++++++--- 4 files changed, 31 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/include/linux/if_link.h b/include/linux/if_link.h index ae5d0d22955d..f923d15b432c 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -24,5 +24,6 @@ struct ifla_vf_info { __u32 min_tx_rate; __u32 max_tx_rate; __u32 rss_query_en; + __u32 trusted; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 69fdd427c8cb..773383859bd9 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -881,6 +881,7 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); @@ -1109,6 +1110,8 @@ struct net_device_ops { int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); + int (*ndo_set_vf_trust)(struct net_device *dev, + int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index e3b6217f34f1..a7aea8418abb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -550,6 +550,7 @@ enum { * on/off switch */ IFLA_VF_STATS, /* network device statistics */ + IFLA_VF_TRUST, /* Trust VF */ __IFLA_VF_MAX, }; @@ -611,6 +612,11 @@ enum { #define IFLA_VF_STATS_MAX (__IFLA_VF_STATS_MAX - 1) +struct ifla_vf_trust { + __u32 vf; + __u32 setting; +}; + /* VF ports management section * * Nested layout of set/get msg is: diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 7c78b5aca944..504bd17b7456 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -838,7 +838,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, /* IFLA_VF_STATS_BROADCAST */ nla_total_size(sizeof(__u64)) + /* IFLA_VF_STATS_MULTICAST */ - nla_total_size(sizeof(__u64))); + nla_total_size(sizeof(__u64)) + + nla_total_size(sizeof(struct ifla_vf_trust))); return size; } else return 0; @@ -1161,6 +1162,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_link_state vf_linkstate; struct ifla_vf_rss_query_en vf_rss_query_en; struct ifla_vf_stats vf_stats; + struct ifla_vf_trust vf_trust; /* * Not all SR-IOV capable drivers support the @@ -1170,6 +1172,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, */ ivi.spoofchk = -1; ivi.rss_query_en = -1; + ivi.trusted = -1; memset(ivi.mac, 0, sizeof(ivi.mac)); /* The default value for VF link state is "auto" * IFLA_VF_LINK_STATE_AUTO which equals zero @@ -1183,7 +1186,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_tx_rate.vf = vf_spoofchk.vf = vf_linkstate.vf = - vf_rss_query_en.vf = ivi.vf; + vf_rss_query_en.vf = + vf_trust.vf = ivi.vf; memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; @@ -1194,6 +1198,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; vf_rss_query_en.setting = ivi.rss_query_en; + vf_trust.setting = ivi.trusted; vf = nla_nest_start(skb, IFLA_VF_INFO); if (!vf) { nla_nest_cancel(skb, vfinfo); @@ -1211,7 +1216,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, &vf_linkstate) || nla_put(skb, IFLA_VF_RSS_QUERY_EN, sizeof(vf_rss_query_en), - &vf_rss_query_en)) + &vf_rss_query_en) || + nla_put(skb, IFLA_VF_TRUST, + sizeof(vf_trust), &vf_trust)) goto nla_put_failure; memset(&vf_stats, 0, sizeof(vf_stats)); if (dev->netdev_ops->ndo_get_vf_stats) @@ -1348,6 +1355,7 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { [IFLA_VF_LINK_STATE] = { .len = sizeof(struct ifla_vf_link_state) }, [IFLA_VF_RSS_QUERY_EN] = { .len = sizeof(struct ifla_vf_rss_query_en) }, [IFLA_VF_STATS] = { .type = NLA_NESTED }, + [IFLA_VF_TRUST] = { .len = sizeof(struct ifla_vf_trust) }, }; static const struct nla_policy ifla_vf_stats_policy[IFLA_VF_STATS_MAX + 1] = { @@ -1587,6 +1595,16 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) return err; } + if (tb[IFLA_VF_TRUST]) { + struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_trust) + err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); + if (err < 0) + return err; + } + return err; } -- cgit v1.2.3 From 91afb7c373e881d5038a78e1206a0f6469440ec3 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:56:07 +0200 Subject: xen/gntalloc: use types from linux/types.h in userspace headers __u32, __u64 etc. are preferred for userspace API headers. Signed-off-by: Mikko Rapeli Signed-off-by: David Vrabel --- include/uapi/xen/gntalloc.h | 22 ++++++++++++---------- 1 file changed, 12 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/xen/gntalloc.h b/include/uapi/xen/gntalloc.h index 76bd58065f4f..48d2790ef928 100644 --- a/include/uapi/xen/gntalloc.h +++ b/include/uapi/xen/gntalloc.h @@ -11,6 +11,8 @@ #ifndef __LINUX_PUBLIC_GNTALLOC_H__ #define __LINUX_PUBLIC_GNTALLOC_H__ +#include + /* * Allocates a new page and creates a new grant reference. */ @@ -19,17 +21,17 @@ _IOC(_IOC_NONE, 'G', 5, sizeof(struct ioctl_gntalloc_alloc_gref)) struct ioctl_gntalloc_alloc_gref { /* IN parameters */ /* The ID of the domain to be given access to the grants. */ - uint16_t domid; + __u16 domid; /* Flags for this mapping */ - uint16_t flags; + __u16 flags; /* Number of pages to map */ - uint32_t count; + __u32 count; /* OUT parameters */ /* The offset to be used on a subsequent call to mmap(). */ - uint64_t index; + __u64 index; /* The grant references of the newly created grant, one per page */ /* Variable size, depending on count */ - uint32_t gref_ids[1]; + __u32 gref_ids[1]; }; #define GNTALLOC_FLAG_WRITABLE 1 @@ -43,9 +45,9 @@ _IOC(_IOC_NONE, 'G', 6, sizeof(struct ioctl_gntalloc_dealloc_gref)) struct ioctl_gntalloc_dealloc_gref { /* IN parameters */ /* The offset returned in the map operation */ - uint64_t index; + __u64 index; /* Number of references to unmap */ - uint32_t count; + __u32 count; }; /* @@ -67,11 +69,11 @@ struct ioctl_gntalloc_unmap_notify { * be cleared. Otherwise, it can be any byte in the page whose * notification we are adjusting. */ - uint64_t index; + __u64 index; /* Action(s) to take on unmap */ - uint32_t action; + __u32 action; /* Event channel to notify */ - uint32_t event_channel_port; + __u32 event_channel_port; }; /* Clear (set to zero) the byte specified by index */ -- cgit v1.2.3 From a36012be64e65760d208c23ea68dc12a895001d8 Mon Sep 17 00:00:00 2001 From: Mikko Rapeli Date: Thu, 15 Oct 2015 07:56:08 +0200 Subject: xen/gntdev: use types from linux/types.h in userspace headers __u32, __u64 etc. are preferred for userspace API headers. Signed-off-by: Mikko Rapeli Signed-off-by: David Vrabel --- include/uapi/xen/gntdev.h | 34 ++++++++++++++++++---------------- 1 file changed, 18 insertions(+), 16 deletions(-) (limited to 'include/uapi') diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h index 5304bd3c84c5..aa7610a9b867 100644 --- a/include/uapi/xen/gntdev.h +++ b/include/uapi/xen/gntdev.h @@ -33,11 +33,13 @@ #ifndef __LINUX_PUBLIC_GNTDEV_H__ #define __LINUX_PUBLIC_GNTDEV_H__ +#include + struct ioctl_gntdev_grant_ref { /* The domain ID of the grant to be mapped. */ - uint32_t domid; + __u32 domid; /* The grant reference of the grant to be mapped. */ - uint32_t ref; + __u32 ref; }; /* @@ -50,11 +52,11 @@ _IOC(_IOC_NONE, 'G', 0, sizeof(struct ioctl_gntdev_map_grant_ref)) struct ioctl_gntdev_map_grant_ref { /* IN parameters */ /* The number of grants to be mapped. */ - uint32_t count; - uint32_t pad; + __u32 count; + __u32 pad; /* OUT parameters */ /* The offset to be used on a subsequent call to mmap(). */ - uint64_t index; + __u64 index; /* Variable IN parameter. */ /* Array of grant references, of size @count. */ struct ioctl_gntdev_grant_ref refs[1]; @@ -70,10 +72,10 @@ _IOC(_IOC_NONE, 'G', 1, sizeof(struct ioctl_gntdev_unmap_grant_ref)) struct ioctl_gntdev_unmap_grant_ref { /* IN parameters */ /* The offset was returned by the corresponding map operation. */ - uint64_t index; + __u64 index; /* The number of pages to be unmapped. */ - uint32_t count; - uint32_t pad; + __u32 count; + __u32 pad; }; /* @@ -93,13 +95,13 @@ _IOC(_IOC_NONE, 'G', 2, sizeof(struct ioctl_gntdev_get_offset_for_vaddr)) struct ioctl_gntdev_get_offset_for_vaddr { /* IN parameters */ /* The virtual address of the first mapped page in a range. */ - uint64_t vaddr; + __u64 vaddr; /* OUT parameters */ /* The offset that was used in the initial mmap() operation. */ - uint64_t offset; + __u64 offset; /* The number of pages mapped in the VM area that begins at @vaddr. */ - uint32_t count; - uint32_t pad; + __u32 count; + __u32 pad; }; /* @@ -113,7 +115,7 @@ _IOC(_IOC_NONE, 'G', 3, sizeof(struct ioctl_gntdev_set_max_grants)) struct ioctl_gntdev_set_max_grants { /* IN parameter */ /* The maximum number of grants that may be mapped at once. */ - uint32_t count; + __u32 count; }; /* @@ -135,11 +137,11 @@ struct ioctl_gntdev_unmap_notify { * be cleared. Otherwise, it can be any byte in the page whose * notification we are adjusting. */ - uint64_t index; + __u64 index; /* Action(s) to take on unmap */ - uint32_t action; + __u32 action; /* Event channel to notify */ - uint32_t event_channel_port; + __u32 event_channel_port; }; /* Clear (set to zero) the byte specified by index */ -- cgit v1.2.3 From c57d3e7a9391c03ae7ee5572be850284393f5bef Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Tue, 8 Sep 2015 11:05:49 +0200 Subject: i2c-dev: Fix typo in ioctl name reference The ioctl is named I2C_RDWR for "I2C read/write". But references to it were misspelled "rdrw". Fix them. Signed-off-by: Jean Delvare Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-dev.c | 6 +++--- fs/compat_ioctl.c | 2 +- include/uapi/linux/i2c-dev.h | 4 +++- 3 files changed, 7 insertions(+), 5 deletions(-) (limited to 'include/uapi') diff --git a/drivers/i2c/i2c-dev.c b/drivers/i2c/i2c-dev.c index 71c7a3975b62..38538971f481 100644 --- a/drivers/i2c/i2c-dev.c +++ b/drivers/i2c/i2c-dev.c @@ -235,7 +235,7 @@ static int i2cdev_check_addr(struct i2c_adapter *adapter, unsigned int addr) return result; } -static noinline int i2cdev_ioctl_rdrw(struct i2c_client *client, +static noinline int i2cdev_ioctl_rdwr(struct i2c_client *client, unsigned long arg) { struct i2c_rdwr_ioctl_data rdwr_arg; @@ -250,7 +250,7 @@ static noinline int i2cdev_ioctl_rdrw(struct i2c_client *client, /* Put an arbitrary limit on the number of messages that can * be sent at once */ - if (rdwr_arg.nmsgs > I2C_RDRW_IOCTL_MAX_MSGS) + if (rdwr_arg.nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; rdwr_pa = memdup_user(rdwr_arg.msgs, @@ -456,7 +456,7 @@ static long i2cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg) return put_user(funcs, (unsigned long __user *)arg); case I2C_RDWR: - return i2cdev_ioctl_rdrw(client, arg); + return i2cdev_ioctl_rdwr(client, arg); case I2C_SMBUS: return i2cdev_ioctl_smbus(client, arg); diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c index 48851f6ea6ec..dcf26537c935 100644 --- a/fs/compat_ioctl.c +++ b/fs/compat_ioctl.c @@ -686,7 +686,7 @@ static int do_i2c_rdwr_ioctl(unsigned int fd, unsigned int cmd, if (get_user(nmsgs, &udata->nmsgs)) return -EFAULT; - if (nmsgs > I2C_RDRW_IOCTL_MAX_MSGS) + if (nmsgs > I2C_RDWR_IOCTL_MAX_MSGS) return -EINVAL; if (get_user(datap, &udata->msgs)) diff --git a/include/uapi/linux/i2c-dev.h b/include/uapi/linux/i2c-dev.h index 3f311551795d..2f05e66de01e 100644 --- a/include/uapi/linux/i2c-dev.h +++ b/include/uapi/linux/i2c-dev.h @@ -66,7 +66,9 @@ struct i2c_rdwr_ioctl_data { __u32 nmsgs; /* number of i2c_msgs */ }; -#define I2C_RDRW_IOCTL_MAX_MSGS 42 +#define I2C_RDWR_IOCTL_MAX_MSGS 42 +/* Originally defined with a typo, keep it for compatibility */ +#define I2C_RDRW_IOCTL_MAX_MSGS I2C_RDWR_IOCTL_MAX_MSGS #endif /* _UAPI_LINUX_I2C_DEV_H */ -- cgit v1.2.3 From c4d4c91b44d8309082127893221a1971a27c50ca Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 13 Aug 2015 14:31:54 -0700 Subject: MD: replace special disk roles with macros Add the following two macros for special roles: spare and faulty MD_DISK_ROLE_SPARE 0xffff MD_DISK_ROLE_FAULTY 0xfffe Add MD_DISK_ROLE_MAX 0xff00 as the maximal possible regular role, and minimal value of special role. Signed-off-by: Song Liu Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- drivers/md/md.c | 14 +++++++------- include/uapi/linux/raid/md_p.h | 4 ++++ 2 files changed, 11 insertions(+), 7 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/md.c b/drivers/md/md.c index 44d034246723..cfe5c8704a26 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1608,7 +1608,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) ++ev1; if (rdev->desc_nr >= 0 && rdev->desc_nr < le32_to_cpu(sb->max_dev) && - le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < 0xfffe) + le16_to_cpu(sb->dev_roles[rdev->desc_nr]) < MD_DISK_ROLE_MAX) if (ev1 < mddev->events) return -EINVAL; } else if (mddev->bitmap) { @@ -1628,14 +1628,14 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) int role; if (rdev->desc_nr < 0 || rdev->desc_nr >= le32_to_cpu(sb->max_dev)) { - role = 0xffff; + role = MD_DISK_ROLE_SPARE; rdev->desc_nr = -1; } else role = le16_to_cpu(sb->dev_roles[rdev->desc_nr]); switch(role) { - case 0xffff: /* spare */ + case MD_DISK_ROLE_SPARE: /* spare */ break; - case 0xfffe: /* faulty */ + case MD_DISK_ROLE_FAULTY: /* faulty */ set_bit(Faulty, &rdev->flags); break; default: @@ -1788,18 +1788,18 @@ retry: max_dev = le32_to_cpu(sb->max_dev); for (i=0; idev_roles[i] = cpu_to_le16(0xfffe); + sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY); rdev_for_each(rdev2, mddev) { i = rdev2->desc_nr; if (test_bit(Faulty, &rdev2->flags)) - sb->dev_roles[i] = cpu_to_le16(0xfffe); + sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY); else if (test_bit(In_sync, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); else if (rdev2->raid_disk >= 0) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); else - sb->dev_roles[i] = cpu_to_le16(0xffff); + sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE); } sb->sb_csum = calc_sb_1_csum(sb); diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 867ee874fa80..d1fc8a637368 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -90,6 +90,10 @@ * dire need */ +#define MD_DISK_ROLE_SPARE 0xffff +#define MD_DISK_ROLE_FAULTY 0xfffe +#define MD_DISK_ROLE_MAX 0xff00 /* max value of regular disk role */ + typedef struct mdp_device_descriptor_s { __u32 number; /* 0 Device number in the entire set */ __u32 major; /* 1 Device major number */ -- cgit v1.2.3 From bac624f3f86a8c7db395c7f85ccad6a504b9c4b4 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Thu, 13 Aug 2015 14:31:55 -0700 Subject: MD: add a new disk role to present write journal device Next patches will use a disk as raid5/6 journaling. We need a new disk role to present the journal device and add MD_FEATURE_JOURNAL to feature_map for backward compability. Signed-off-by: Song Liu Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- drivers/md/md.c | 23 +++++++++++++++++++++-- drivers/md/md.h | 5 +++++ include/uapi/linux/raid/md_p.h | 3 +++ 3 files changed, 29 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/md.c b/drivers/md/md.c index cfe5c8704a26..391341a772c7 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1638,6 +1638,15 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) case MD_DISK_ROLE_FAULTY: /* faulty */ set_bit(Faulty, &rdev->flags); break; + case MD_DISK_ROLE_JOURNAL: /* journal device */ + if (!(le32_to_cpu(sb->feature_map) & MD_FEATURE_JOURNAL)) { + /* journal device without journal feature */ + printk(KERN_WARNING + "md: journal device provided without journal feature, ignoring the device\n"); + return -EINVAL; + } + set_bit(Journal, &rdev->flags); + break; default: rdev->saved_raid_disk = role; if ((le32_to_cpu(sb->feature_map) & @@ -1796,7 +1805,10 @@ retry: sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_FAULTY); else if (test_bit(In_sync, &rdev2->flags)) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); - else if (rdev2->raid_disk >= 0) + else if (test_bit(Journal, &rdev2->flags)) { + sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_JOURNAL); + sb->feature_map |= cpu_to_le32(MD_FEATURE_JOURNAL); + } else if (rdev2->raid_disk >= 0) sb->dev_roles[i] = cpu_to_le16(rdev2->raid_disk); else sb->dev_roles[i] = cpu_to_le16(MD_DISK_ROLE_SPARE); @@ -5840,7 +5852,8 @@ static int get_disk_info(struct mddev *mddev, void __user * arg) else if (test_bit(In_sync, &rdev->flags)) { info.state |= (1<flags)) + info.state |= (1<flags)) info.state |= (1<flags); + if (info->state & (1<flags); /* * check whether the device shows up in other nodes */ @@ -7330,6 +7345,10 @@ static int md_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "(F)"); continue; } + if (test_bit(Journal, &rdev->flags)) { + seq_printf(seq, "(J)"); + continue; + } if (rdev->raid_disk < 0) seq_printf(seq, "(S)"); /* spare */ if (test_bit(Replacement, &rdev->flags)) diff --git a/drivers/md/md.h b/drivers/md/md.h index 2ea00356bb23..88dc6312f5d5 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -172,6 +172,11 @@ enum flag_bits { * This device is seen locally but not * by the whole cluster */ + Journal, /* This device is used as journal for + * raid-5/6. + * Usually, this device should be faster + * than other devices in the array + */ }; #define BB_LEN_MASK (0x00000000000001FFULL) diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index d1fc8a637368..eaaab52077a3 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -89,9 +89,11 @@ * read requests will only be sent here in * dire need */ +#define MD_DISK_JOURNAL 18 /* disk is used as the write journal in RAID-5/6 */ #define MD_DISK_ROLE_SPARE 0xffff #define MD_DISK_ROLE_FAULTY 0xfffe +#define MD_DISK_ROLE_JOURNAL 0xfffd #define MD_DISK_ROLE_MAX 0xff00 /* max value of regular disk role */ typedef struct mdp_device_descriptor_s { @@ -307,6 +309,7 @@ struct mdp_superblock_1 { * is guided by bitmap. */ #define MD_FEATURE_CLUSTERED 256 /* clustered MD */ +#define MD_FEATURE_JOURNAL 512 /* support write cache */ #define MD_FEATURE_ALL (MD_FEATURE_BITMAP_OFFSET \ |MD_FEATURE_RECOVERY_OFFSET \ |MD_FEATURE_RESHAPE_ACTIVE \ -- cgit v1.2.3 From 3069aa8def32b0c2b83cd27d1c37ed30b47ce879 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 13 Aug 2015 14:31:56 -0700 Subject: md: override md superblock recovery_offset for journal device Journal device stores data in a log structure. We need record the log start. Here we override md superblock recovery_offset for this purpose. This field of a journal device is meaningless otherwise. Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- drivers/md/md.c | 6 ++++++ drivers/md/md.h | 8 +++++++- include/uapi/linux/raid/md_p.h | 5 ++++- 3 files changed, 17 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/md.c b/drivers/md/md.c index 391341a772c7..3592beb6931e 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -1646,6 +1646,7 @@ static int super_1_validate(struct mddev *mddev, struct md_rdev *rdev) return -EINVAL; } set_bit(Journal, &rdev->flags); + rdev->journal_tail = le64_to_cpu(sb->journal_tail); break; default: rdev->saved_raid_disk = role; @@ -1721,6 +1722,9 @@ static void super_1_sync(struct mddev *mddev, struct md_rdev *rdev) sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_BITMAP); } + /* Note: recovery_offset and journal_tail share space */ + if (test_bit(Journal, &rdev->flags)) + sb->journal_tail = cpu_to_le64(rdev->journal_tail); if (test_bit(Replacement, &rdev->flags)) sb->feature_map |= cpu_to_le32(MD_FEATURE_REPLACEMENT); @@ -8097,6 +8101,8 @@ static int remove_and_add_spares(struct mddev *mddev, continue; if (test_bit(Faulty, &rdev->flags)) continue; + if (test_bit(Journal, &rdev->flags)) + continue; if (mddev->ro && ! (rdev->saved_raid_disk >= 0 && !test_bit(Bitmap_sync, &rdev->flags))) diff --git a/drivers/md/md.h b/drivers/md/md.h index 88dc6312f5d5..2b0f62fb6146 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -87,10 +87,16 @@ struct md_rdev { * array and could again if we did a partial * resync from the bitmap */ - sector_t recovery_offset;/* If this device has been partially + union { + sector_t recovery_offset;/* If this device has been partially * recovered, this is where we were * up to. */ + sector_t journal_tail; /* If this device is a journal device, + * this is the journal tail (journal + * recovery start point) + */ + }; atomic_t nr_pending; /* number of pending requests. * only maintained for arrays that diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index eaaab52077a3..a5f54ff26c20 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -258,7 +258,10 @@ struct mdp_superblock_1 { __le64 data_offset; /* sector start of data, often 0 */ __le64 data_size; /* sectors in this device that can be used for data */ __le64 super_offset; /* sector start of this superblock */ - __le64 recovery_offset;/* sectors before this offset (from data_offset) have been recovered */ + union { + __le64 recovery_offset;/* sectors before this offset (from data_offset) have been recovered */ + __le64 journal_tail;/* journal tail of journal device (from data_offset) */ + }; __le32 dev_number; /* permanent identifier of this device - not role in raid */ __le32 cnt_corrected_read; /* number of read errors that were corrected by re-writing */ __u8 device_uuid[16]; /* user-space setable, ignored by kernel */ -- cgit v1.2.3 From f6bed0ef0a808164f51197de062e0450ce6c1f96 Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 13 Aug 2015 14:31:59 -0700 Subject: raid5: add basic stripe log This introduces a simple log for raid5. Data/parity writing to raid array first writes to the log, then write to raid array disks. If crash happens, we can recovery data from the log. This can speed up raid resync and fix write hole issue. The log structure is pretty simple. Data/meta data is stored in block unit, which is 4k generally. It has only one type of meta data block. The meta data block can track 3 types of data, stripe data, stripe parity and flush block. MD superblock will point to the last valid meta data block. Each meta data block has checksum/seq number, so recovery can scan the log correctly. We store a checksum of stripe data/parity to the metadata block, so meta data and stripe data/parity can be written to log disk together. otherwise, meta data write must wait till stripe data/parity is finished. For stripe data, meta data block will record stripe data sector and size. Currently the size is always 4k. This meta data record can be made simpler if we just fix write hole (eg, we can record data of a stripe's different disks together), but this format can be extended to support caching in the future, which must record data address/size. For stripe parity, meta data block will record stripe sector. It's size should be 4k (for raid5) or 8k (for raid6). We always store p parity first. This format should work for caching too. flush block indicates a stripe is in raid array disks. Fixing write hole doesn't need this type of meta data, it's for caching extension. Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- drivers/md/Makefile | 2 +- drivers/md/raid5-cache.c | 608 +++++++++++++++++++++++++++++++++++++++++ drivers/md/raid5.c | 4 + drivers/md/raid5.h | 9 + include/uapi/linux/raid/md_p.h | 58 ++++ 5 files changed, 680 insertions(+), 1 deletion(-) create mode 100644 drivers/md/raid5-cache.c (limited to 'include/uapi') diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 462f443a4f85..f34979cd141a 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -17,7 +17,7 @@ dm-cache-smq-y += dm-cache-policy-smq.o dm-cache-cleaner-y += dm-cache-policy-cleaner.o dm-era-y += dm-era-target.o md-mod-y += md.o bitmap.o -raid456-y += raid5.o +raid456-y += raid5.o raid5-cache.o # Note: link order is important. All raid personalities # and must come before md.o, as they each initialise diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c new file mode 100644 index 000000000000..d18a7700bcb9 --- /dev/null +++ b/drivers/md/raid5-cache.c @@ -0,0 +1,608 @@ +/* + * Copyright (C) 2015 Shaohua Li + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + */ +#include +#include +#include +#include +#include +#include +#include +#include "md.h" +#include "raid5.h" + +/* + * metadata/data stored in disk with 4k size unit (a block) regardless + * underneath hardware sector size. only works with PAGE_SIZE == 4096 + */ +#define BLOCK_SECTORS (8) + +struct r5l_log { + struct md_rdev *rdev; + + u32 uuid_checksum; + + sector_t device_size; /* log device size, round to + * BLOCK_SECTORS */ + + sector_t last_checkpoint; /* log tail. where recovery scan + * starts from */ + u64 last_cp_seq; /* log tail sequence */ + + sector_t log_start; /* log head. where new data appends */ + u64 seq; /* log head sequence */ + + struct mutex io_mutex; + struct r5l_io_unit *current_io; /* current io_unit accepting new data */ + + spinlock_t io_list_lock; + struct list_head running_ios; /* io_units which are still running, + * and have not yet been completely + * written to the log */ + struct list_head io_end_ios; /* io_units which have been completely + * written to the log but not yet written + * to the RAID */ + + struct kmem_cache *io_kc; + + struct list_head no_space_stripes; /* pending stripes, log has no space */ + spinlock_t no_space_stripes_lock; +}; + +/* + * an IO range starts from a meta data block and end at the next meta data + * block. The io unit's the meta data block tracks data/parity followed it. io + * unit is written to log disk with normal write, as we always flush log disk + * first and then start move data to raid disks, there is no requirement to + * write io unit with FLUSH/FUA + */ +struct r5l_io_unit { + struct r5l_log *log; + + struct page *meta_page; /* store meta block */ + int meta_offset; /* current offset in meta_page */ + + struct bio_list bios; + atomic_t pending_io; /* pending bios not written to log yet */ + struct bio *current_bio;/* current_bio accepting new data */ + + atomic_t pending_stripe;/* how many stripes not flushed to raid */ + u64 seq; /* seq number of the metablock */ + sector_t log_start; /* where the io_unit starts */ + sector_t log_end; /* where the io_unit ends */ + struct list_head log_sibling; /* log->running_ios */ + struct list_head stripe_list; /* stripes added to the io_unit */ + + int state; + wait_queue_head_t wait_state; +}; + +/* r5l_io_unit state */ +enum r5l_io_unit_state { + IO_UNIT_RUNNING = 0, /* accepting new IO */ + IO_UNIT_IO_START = 1, /* io_unit bio start writing to log, + * don't accepting new bio */ + IO_UNIT_IO_END = 2, /* io_unit bio finish writing to log */ + IO_UNIT_STRIPE_START = 3, /* stripes of io_unit are flushing to raid */ + IO_UNIT_STRIPE_END = 4, /* stripes data finished writing to raid */ +}; + +static sector_t r5l_ring_add(struct r5l_log *log, sector_t start, sector_t inc) +{ + start += inc; + if (start >= log->device_size) + start = start - log->device_size; + return start; +} + +static sector_t r5l_ring_distance(struct r5l_log *log, sector_t start, + sector_t end) +{ + if (end >= start) + return end - start; + else + return end + log->device_size - start; +} + +static bool r5l_has_free_space(struct r5l_log *log, sector_t size) +{ + sector_t used_size; + + used_size = r5l_ring_distance(log, log->last_checkpoint, + log->log_start); + + return log->device_size > used_size + size; +} + +static struct r5l_io_unit *r5l_alloc_io_unit(struct r5l_log *log) +{ + struct r5l_io_unit *io; + /* We can't handle memory allocate failure so far */ + gfp_t gfp = GFP_NOIO | __GFP_NOFAIL; + + io = kmem_cache_zalloc(log->io_kc, gfp); + io->log = log; + io->meta_page = alloc_page(gfp | __GFP_ZERO); + + bio_list_init(&io->bios); + INIT_LIST_HEAD(&io->log_sibling); + INIT_LIST_HEAD(&io->stripe_list); + io->state = IO_UNIT_RUNNING; + init_waitqueue_head(&io->wait_state); + return io; +} + +static void r5l_free_io_unit(struct r5l_log *log, struct r5l_io_unit *io) +{ + __free_page(io->meta_page); + kmem_cache_free(log->io_kc, io); +} + +static void r5l_move_io_unit_list(struct list_head *from, struct list_head *to, + enum r5l_io_unit_state state) +{ + struct r5l_io_unit *io; + + while (!list_empty(from)) { + io = list_first_entry(from, struct r5l_io_unit, log_sibling); + /* don't change list order */ + if (io->state >= state) + list_move_tail(&io->log_sibling, to); + else + break; + } +} + +static void r5l_wake_reclaim(struct r5l_log *log, sector_t space); +static void __r5l_set_io_unit_state(struct r5l_io_unit *io, + enum r5l_io_unit_state state) +{ + struct r5l_log *log = io->log; + + if (WARN_ON(io->state >= state)) + return; + io->state = state; + if (state == IO_UNIT_IO_END) + r5l_move_io_unit_list(&log->running_ios, &log->io_end_ios, + IO_UNIT_IO_END); + wake_up(&io->wait_state); +} + +static void r5l_set_io_unit_state(struct r5l_io_unit *io, + enum r5l_io_unit_state state) +{ + struct r5l_log *log = io->log; + unsigned long flags; + + spin_lock_irqsave(&log->io_list_lock, flags); + __r5l_set_io_unit_state(io, state); + spin_unlock_irqrestore(&log->io_list_lock, flags); +} + +/* XXX: totally ignores I/O errors */ +static void r5l_log_endio(struct bio *bio) +{ + struct r5l_io_unit *io = bio->bi_private; + struct r5l_log *log = io->log; + + bio_put(bio); + + if (!atomic_dec_and_test(&io->pending_io)) + return; + + r5l_set_io_unit_state(io, IO_UNIT_IO_END); + md_wakeup_thread(log->rdev->mddev->thread); +} + +static void r5l_submit_current_io(struct r5l_log *log) +{ + struct r5l_io_unit *io = log->current_io; + struct r5l_meta_block *block; + struct bio *bio; + u32 crc; + + if (!io) + return; + + block = page_address(io->meta_page); + block->meta_size = cpu_to_le32(io->meta_offset); + crc = crc32_le(log->uuid_checksum, (void *)block, PAGE_SIZE); + block->checksum = cpu_to_le32(crc); + + log->current_io = NULL; + r5l_set_io_unit_state(io, IO_UNIT_IO_START); + + while ((bio = bio_list_pop(&io->bios))) { + /* all IO must start from rdev->data_offset */ + bio->bi_iter.bi_sector += log->rdev->data_offset; + submit_bio(WRITE, bio); + } +} + +static struct r5l_io_unit *r5l_new_meta(struct r5l_log *log) +{ + struct r5l_io_unit *io; + struct r5l_meta_block *block; + struct bio *bio; + + io = r5l_alloc_io_unit(log); + + block = page_address(io->meta_page); + block->magic = cpu_to_le32(R5LOG_MAGIC); + block->version = R5LOG_VERSION; + block->seq = cpu_to_le64(log->seq); + block->position = cpu_to_le64(log->log_start); + + io->log_start = log->log_start; + io->meta_offset = sizeof(struct r5l_meta_block); + io->seq = log->seq; + + bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL, BIO_MAX_PAGES); + io->current_bio = bio; + bio->bi_rw = WRITE; + bio->bi_bdev = log->rdev->bdev; + bio->bi_iter.bi_sector = log->log_start; + bio_add_page(bio, io->meta_page, PAGE_SIZE, 0); + bio->bi_end_io = r5l_log_endio; + bio->bi_private = io; + + bio_list_add(&io->bios, bio); + atomic_inc(&io->pending_io); + + log->seq++; + log->log_start = r5l_ring_add(log, log->log_start, BLOCK_SECTORS); + io->log_end = log->log_start; + /* current bio hit disk end */ + if (log->log_start == 0) + io->current_bio = NULL; + + spin_lock_irq(&log->io_list_lock); + list_add_tail(&io->log_sibling, &log->running_ios); + spin_unlock_irq(&log->io_list_lock); + + return io; +} + +static int r5l_get_meta(struct r5l_log *log, unsigned int payload_size) +{ + struct r5l_io_unit *io; + + io = log->current_io; + if (io && io->meta_offset + payload_size > PAGE_SIZE) + r5l_submit_current_io(log); + io = log->current_io; + if (io) + return 0; + + log->current_io = r5l_new_meta(log); + return 0; +} + +static void r5l_append_payload_meta(struct r5l_log *log, u16 type, + sector_t location, + u32 checksum1, u32 checksum2, + bool checksum2_valid) +{ + struct r5l_io_unit *io = log->current_io; + struct r5l_payload_data_parity *payload; + + payload = page_address(io->meta_page) + io->meta_offset; + payload->header.type = cpu_to_le16(type); + payload->header.flags = cpu_to_le16(0); + payload->size = cpu_to_le32((1 + !!checksum2_valid) << + (PAGE_SHIFT - 9)); + payload->location = cpu_to_le64(location); + payload->checksum[0] = cpu_to_le32(checksum1); + if (checksum2_valid) + payload->checksum[1] = cpu_to_le32(checksum2); + + io->meta_offset += sizeof(struct r5l_payload_data_parity) + + sizeof(__le32) * (1 + !!checksum2_valid); +} + +static void r5l_append_payload_page(struct r5l_log *log, struct page *page) +{ + struct r5l_io_unit *io = log->current_io; + +alloc_bio: + if (!io->current_bio) { + struct bio *bio; + + bio = bio_kmalloc(GFP_NOIO | __GFP_NOFAIL, BIO_MAX_PAGES); + bio->bi_rw = WRITE; + bio->bi_bdev = log->rdev->bdev; + bio->bi_iter.bi_sector = log->log_start; + bio->bi_end_io = r5l_log_endio; + bio->bi_private = io; + bio_list_add(&io->bios, bio); + atomic_inc(&io->pending_io); + io->current_bio = bio; + } + if (!bio_add_page(io->current_bio, page, PAGE_SIZE, 0)) { + io->current_bio = NULL; + goto alloc_bio; + } + log->log_start = r5l_ring_add(log, log->log_start, + BLOCK_SECTORS); + /* current bio hit disk end */ + if (log->log_start == 0) + io->current_bio = NULL; + + io->log_end = log->log_start; +} + +static void r5l_log_stripe(struct r5l_log *log, struct stripe_head *sh, + int data_pages, int parity_pages) +{ + int i; + int meta_size; + struct r5l_io_unit *io; + + meta_size = + ((sizeof(struct r5l_payload_data_parity) + sizeof(__le32)) + * data_pages) + + sizeof(struct r5l_payload_data_parity) + + sizeof(__le32) * parity_pages; + + r5l_get_meta(log, meta_size); + io = log->current_io; + + for (i = 0; i < sh->disks; i++) { + if (!test_bit(R5_Wantwrite, &sh->dev[i].flags)) + continue; + if (i == sh->pd_idx || i == sh->qd_idx) + continue; + r5l_append_payload_meta(log, R5LOG_PAYLOAD_DATA, + raid5_compute_blocknr(sh, i, 0), + sh->dev[i].log_checksum, 0, false); + r5l_append_payload_page(log, sh->dev[i].page); + } + + if (sh->qd_idx >= 0) { + r5l_append_payload_meta(log, R5LOG_PAYLOAD_PARITY, + sh->sector, sh->dev[sh->pd_idx].log_checksum, + sh->dev[sh->qd_idx].log_checksum, true); + r5l_append_payload_page(log, sh->dev[sh->pd_idx].page); + r5l_append_payload_page(log, sh->dev[sh->qd_idx].page); + } else { + r5l_append_payload_meta(log, R5LOG_PAYLOAD_PARITY, + sh->sector, sh->dev[sh->pd_idx].log_checksum, + 0, false); + r5l_append_payload_page(log, sh->dev[sh->pd_idx].page); + } + + list_add_tail(&sh->log_list, &io->stripe_list); + atomic_inc(&io->pending_stripe); + sh->log_io = io; +} + +/* + * running in raid5d, where reclaim could wait for raid5d too (when it flushes + * data from log to raid disks), so we shouldn't wait for reclaim here + */ +int r5l_write_stripe(struct r5l_log *log, struct stripe_head *sh) +{ + int write_disks = 0; + int data_pages, parity_pages; + int meta_size; + int reserve; + int i; + + if (!log) + return -EAGAIN; + /* Don't support stripe batch */ + if (sh->log_io || !test_bit(R5_Wantwrite, &sh->dev[sh->pd_idx].flags) || + test_bit(STRIPE_SYNCING, &sh->state)) { + /* the stripe is written to log, we start writing it to raid */ + clear_bit(STRIPE_LOG_TRAPPED, &sh->state); + return -EAGAIN; + } + + for (i = 0; i < sh->disks; i++) { + void *addr; + + if (!test_bit(R5_Wantwrite, &sh->dev[i].flags)) + continue; + write_disks++; + /* checksum is already calculated in last run */ + if (test_bit(STRIPE_LOG_TRAPPED, &sh->state)) + continue; + addr = kmap_atomic(sh->dev[i].page); + sh->dev[i].log_checksum = crc32_le(log->uuid_checksum, + addr, PAGE_SIZE); + kunmap_atomic(addr); + } + parity_pages = 1 + !!(sh->qd_idx >= 0); + data_pages = write_disks - parity_pages; + + meta_size = + ((sizeof(struct r5l_payload_data_parity) + sizeof(__le32)) + * data_pages) + + sizeof(struct r5l_payload_data_parity) + + sizeof(__le32) * parity_pages; + /* Doesn't work with very big raid array */ + if (meta_size + sizeof(struct r5l_meta_block) > PAGE_SIZE) + return -EINVAL; + + set_bit(STRIPE_LOG_TRAPPED, &sh->state); + atomic_inc(&sh->count); + + mutex_lock(&log->io_mutex); + /* meta + data */ + reserve = (1 + write_disks) << (PAGE_SHIFT - 9); + if (r5l_has_free_space(log, reserve)) + r5l_log_stripe(log, sh, data_pages, parity_pages); + else { + spin_lock(&log->no_space_stripes_lock); + list_add_tail(&sh->log_list, &log->no_space_stripes); + spin_unlock(&log->no_space_stripes_lock); + + r5l_wake_reclaim(log, reserve); + } + mutex_unlock(&log->io_mutex); + + return 0; +} + +void r5l_write_stripe_run(struct r5l_log *log) +{ + if (!log) + return; + mutex_lock(&log->io_mutex); + r5l_submit_current_io(log); + mutex_unlock(&log->io_mutex); +} + +/* This will run after log space is reclaimed */ +static void r5l_run_no_space_stripes(struct r5l_log *log) +{ + struct stripe_head *sh; + + spin_lock(&log->no_space_stripes_lock); + while (!list_empty(&log->no_space_stripes)) { + sh = list_first_entry(&log->no_space_stripes, + struct stripe_head, log_list); + list_del_init(&sh->log_list); + set_bit(STRIPE_HANDLE, &sh->state); + raid5_release_stripe(sh); + } + spin_unlock(&log->no_space_stripes_lock); +} + +static void r5l_wake_reclaim(struct r5l_log *log, sector_t space) +{ + /* will implement later */ +} + +static int r5l_recovery_log(struct r5l_log *log) +{ + /* fake recovery */ + log->seq = log->last_cp_seq + 1; + log->log_start = r5l_ring_add(log, log->last_checkpoint, BLOCK_SECTORS); + return 0; +} + +static void r5l_write_super(struct r5l_log *log, sector_t cp) +{ + struct mddev *mddev = log->rdev->mddev; + + log->rdev->journal_tail = cp; + set_bit(MD_CHANGE_DEVS, &mddev->flags); +} + +static int r5l_load_log(struct r5l_log *log) +{ + struct md_rdev *rdev = log->rdev; + struct page *page; + struct r5l_meta_block *mb; + sector_t cp = log->rdev->journal_tail; + u32 stored_crc, expected_crc; + bool create_super = false; + int ret; + + /* Make sure it's valid */ + if (cp >= rdev->sectors || round_down(cp, BLOCK_SECTORS) != cp) + cp = 0; + page = alloc_page(GFP_KERNEL); + if (!page) + return -ENOMEM; + + if (!sync_page_io(rdev, cp, PAGE_SIZE, page, READ, false)) { + ret = -EIO; + goto ioerr; + } + mb = page_address(page); + + if (le32_to_cpu(mb->magic) != R5LOG_MAGIC || + mb->version != R5LOG_VERSION) { + create_super = true; + goto create; + } + stored_crc = le32_to_cpu(mb->checksum); + mb->checksum = 0; + expected_crc = crc32_le(log->uuid_checksum, (void *)mb, PAGE_SIZE); + if (stored_crc != expected_crc) { + create_super = true; + goto create; + } + if (le64_to_cpu(mb->position) != cp) { + create_super = true; + goto create; + } +create: + if (create_super) { + log->last_cp_seq = prandom_u32(); + cp = 0; + /* + * Make sure super points to correct address. Log might have + * data very soon. If super hasn't correct log tail address, + * recovery can't find the log + */ + r5l_write_super(log, cp); + } else + log->last_cp_seq = le64_to_cpu(mb->seq); + + log->device_size = round_down(rdev->sectors, BLOCK_SECTORS); + log->last_checkpoint = cp; + + __free_page(page); + + return r5l_recovery_log(log); +ioerr: + __free_page(page); + return ret; +} + +int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev) +{ + struct r5l_log *log; + + if (PAGE_SIZE != 4096) + return -EINVAL; + log = kzalloc(sizeof(*log), GFP_KERNEL); + if (!log) + return -ENOMEM; + log->rdev = rdev; + + log->uuid_checksum = crc32_le(~0, (void *)rdev->mddev->uuid, + sizeof(rdev->mddev->uuid)); + + mutex_init(&log->io_mutex); + + spin_lock_init(&log->io_list_lock); + INIT_LIST_HEAD(&log->running_ios); + + log->io_kc = KMEM_CACHE(r5l_io_unit, 0); + if (!log->io_kc) + goto io_kc; + + INIT_LIST_HEAD(&log->no_space_stripes); + spin_lock_init(&log->no_space_stripes_lock); + + if (r5l_load_log(log)) + goto error; + + conf->log = log; + return 0; +error: + kmem_cache_destroy(log->io_kc); +io_kc: + kfree(log); + return -EINVAL; +} + +void r5l_exit_log(struct r5l_log *log) +{ + kmem_cache_destroy(log->io_kc); + kfree(log); +} diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 4b789f1f4550..64a256538ff7 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -895,6 +895,8 @@ static void ops_run_io(struct stripe_head *sh, struct stripe_head_state *s) might_sleep(); + if (r5l_write_stripe(conf->log, sh) == 0) + return; for (i = disks; i--; ) { int rw; int replace_only = 0; @@ -3495,6 +3497,7 @@ returnbi: WARN_ON(test_bit(R5_SkipCopy, &dev->flags)); WARN_ON(dev->page != dev->orig_page); } + if (!discard_pending && test_bit(R5_Discard, &sh->dev[sh->pd_idx].flags)) { clear_bit(R5_Discard, &sh->dev[sh->pd_idx].flags); @@ -5745,6 +5748,7 @@ static int handle_active_stripes(struct r5conf *conf, int group, for (i = 0; i < batch_size; i++) handle_stripe(batch[i]); + r5l_write_stripe_run(conf->log); cond_resched(); diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h index a42c123d15d2..87fae2b50d87 100644 --- a/drivers/md/raid5.h +++ b/drivers/md/raid5.h @@ -223,6 +223,9 @@ struct stripe_head { struct stripe_head *batch_head; /* protected by stripe lock */ spinlock_t batch_lock; /* only header's lock is useful */ struct list_head batch_list; /* protected by head's batch lock*/ + + struct r5l_io_unit *log_io; + struct list_head log_list; /** * struct stripe_operations * @target - STRIPE_OP_COMPUTE_BLK target @@ -244,6 +247,7 @@ struct stripe_head { struct bio *toread, *read, *towrite, *written; sector_t sector; /* sector of this page */ unsigned long flags; + u32 log_checksum; } dev[1]; /* allocated with extra space depending of RAID geometry */ }; @@ -544,6 +548,7 @@ struct r5conf { struct r5worker_group *worker_groups; int group_cnt; int worker_cnt_per_group; + struct r5l_log *log; }; @@ -618,4 +623,8 @@ extern sector_t raid5_compute_sector(struct r5conf *conf, sector_t r_sector, extern struct stripe_head * raid5_get_active_stripe(struct r5conf *conf, sector_t sector, int previous, int noblock, int noquiesce); +extern int r5l_init_log(struct r5conf *conf, struct md_rdev *rdev); +extern void r5l_exit_log(struct r5l_log *log); +extern int r5l_write_stripe(struct r5l_log *log, struct stripe_head *head_sh); +extern void r5l_write_stripe_run(struct r5l_log *log); #endif diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index a5f54ff26c20..96e4196f9c79 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -324,4 +324,62 @@ struct mdp_superblock_1 { |MD_FEATURE_CLUSTERED \ ) +struct r5l_payload_header { + __le16 type; + __le16 flags; +} __attribute__ ((__packed__)); + +enum r5l_payload_type { + R5LOG_PAYLOAD_DATA = 0, + R5LOG_PAYLOAD_PARITY = 1, + R5LOG_PAYLOAD_FLUSH = 2, +}; + +struct r5l_payload_data_parity { + struct r5l_payload_header header; + __le32 size; /* sector. data/parity size. each 4k + * has a checksum */ + __le64 location; /* sector. For data, it's raid sector. For + * parity, it's stripe sector */ + __le32 checksum[]; +} __attribute__ ((__packed__)); + +enum r5l_payload_data_parity_flag { + R5LOG_PAYLOAD_FLAG_DISCARD = 1, /* payload is discard */ + /* + * RESHAPED/RESHAPING is only set when there is reshape activity. Note, + * both data/parity of a stripe should have the same flag set + * + * RESHAPED: reshape is running, and this stripe finished reshape + * RESHAPING: reshape is running, and this stripe isn't reshaped + */ + R5LOG_PAYLOAD_FLAG_RESHAPED = 2, + R5LOG_PAYLOAD_FLAG_RESHAPING = 3, +}; + +struct r5l_payload_flush { + struct r5l_payload_header header; + __le32 size; /* flush_stripes size, bytes */ + __le64 flush_stripes[]; +} __attribute__ ((__packed__)); + +enum r5l_payload_flush_flag { + R5LOG_PAYLOAD_FLAG_FLUSH_STRIPE = 1, /* data represents whole stripe */ +}; + +struct r5l_meta_block { + __le32 magic; + __le32 checksum; + __u8 version; + __u8 __zero_pading_1; + __le16 __zero_pading_2; + __le32 meta_size; /* whole size of the block */ + + __le64 seq; + __le64 position; /* sector, start from rdev->data_offset, current position */ + struct r5l_payload_header payloads[]; +} __attribute__ ((__packed__)); + +#define R5LOG_VERSION 0x1 +#define R5LOG_MAGIC 0x6433c509 #endif -- cgit v1.2.3 From a5f5774c55a2e3ed75f4d6c5556b7bfcb726e6f0 Mon Sep 17 00:00:00 2001 From: Jon Hunter Date: Tue, 22 Sep 2015 10:27:53 +0100 Subject: mmc: block: Add new ioctl to send multi commands Certain eMMC devices allow vendor specific device information to be read via a sequence of vendor commands. These vendor commands must be issued in sequence and an atomic fashion. One way to support this would be to add an ioctl function for sending a sequence of commands to the device atomically as proposed here. These multi commands are simple array of the existing mmc_ioc_cmd structure. The structure passed via the ioctl uses a __u64 type to specify the number of commands (so that the structure is aligned on a 64-bit boundary) and a zero length array as a header for list of commands to be issued. The maximum number of commands that can be sent is determined by MMC_IOC_MAX_CMDS (which defaults to 255 and should be more than sufficient). This based upon work by Seshagiri Holi . Signed-off-by: Seshagiri Holi Signed-off-by: Jon Hunter Signed-off-by: Ulf Hansson --- drivers/mmc/card/block.c | 206 ++++++++++++++++++++++++++++++----------- include/uapi/linux/mmc/ioctl.h | 19 +++- 2 files changed, 169 insertions(+), 56 deletions(-) (limited to 'include/uapi') diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index c742cfd7674e..f6acf0f6c410 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -387,6 +387,24 @@ out: return ERR_PTR(err); } +static int mmc_blk_ioctl_copy_to_user(struct mmc_ioc_cmd __user *ic_ptr, + struct mmc_blk_ioc_data *idata) +{ + struct mmc_ioc_cmd *ic = &idata->ic; + + if (copy_to_user(&(ic_ptr->response), ic->response, + sizeof(ic->response))) + return -EFAULT; + + if (!idata->ic.write_flag) { + if (copy_to_user((void __user *)(unsigned long)ic->data_ptr, + idata->buf, idata->buf_bytes)) + return -EFAULT; + } + + return 0; +} + static int ioctl_rpmb_card_status_poll(struct mmc_card *card, u32 *status, u32 retries_max) { @@ -447,12 +465,9 @@ out: return err; } -static int mmc_blk_ioctl_cmd(struct block_device *bdev, - struct mmc_ioc_cmd __user *ic_ptr) +static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, + struct mmc_blk_ioc_data *idata) { - struct mmc_blk_ioc_data *idata; - struct mmc_blk_data *md; - struct mmc_card *card; struct mmc_command cmd = {0}; struct mmc_data data = {0}; struct mmc_request mrq = {NULL}; @@ -461,33 +476,12 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, int is_rpmb = false; u32 status = 0; - /* - * The caller must have CAP_SYS_RAWIO, and must be calling this on the - * whole block device, not on a partition. This prevents overspray - * between sibling partitions. - */ - if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains)) - return -EPERM; - - idata = mmc_blk_ioctl_copy_from_user(ic_ptr); - if (IS_ERR(idata)) - return PTR_ERR(idata); - - md = mmc_blk_get(bdev->bd_disk); - if (!md) { - err = -EINVAL; - goto cmd_err; - } + if (!card || !md || !idata) + return -EINVAL; if (md->area_type & MMC_BLK_DATA_AREA_RPMB) is_rpmb = true; - card = md->queue.card; - if (IS_ERR(card)) { - err = PTR_ERR(card); - goto cmd_done; - } - cmd.opcode = idata->ic.opcode; cmd.arg = idata->ic.arg; cmd.flags = idata->ic.flags; @@ -530,23 +524,21 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, mrq.cmd = &cmd; - mmc_get_card(card); - err = mmc_blk_part_switch(card, md); if (err) - goto cmd_rel_host; + return err; if (idata->ic.is_acmd) { err = mmc_app_cmd(card->host, card); if (err) - goto cmd_rel_host; + return err; } if (is_rpmb) { err = mmc_set_blockcount(card, data.blocks, idata->ic.write_flag & (1 << 31)); if (err) - goto cmd_rel_host; + return err; } if ((MMC_EXTRACT_INDEX_FROM_ARG(cmd.arg) == EXT_CSD_SANITIZE_START) && @@ -557,7 +549,7 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, pr_err("%s: ioctl_do_sanitize() failed. err = %d", __func__, err); - goto cmd_rel_host; + return err; } mmc_wait_for_req(card->host, &mrq); @@ -565,14 +557,12 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, if (cmd.error) { dev_err(mmc_dev(card->host), "%s: cmd error %d\n", __func__, cmd.error); - err = cmd.error; - goto cmd_rel_host; + return cmd.error; } if (data.error) { dev_err(mmc_dev(card->host), "%s: data error %d\n", __func__, data.error); - err = data.error; - goto cmd_rel_host; + return data.error; } /* @@ -582,18 +572,7 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, if (idata->ic.postsleep_min_us) usleep_range(idata->ic.postsleep_min_us, idata->ic.postsleep_max_us); - if (copy_to_user(&(ic_ptr->response), cmd.resp, sizeof(cmd.resp))) { - err = -EFAULT; - goto cmd_rel_host; - } - - if (!idata->ic.write_flag) { - if (copy_to_user((void __user *)(unsigned long) idata->ic.data_ptr, - idata->buf, idata->buf_bytes)) { - err = -EFAULT; - goto cmd_rel_host; - } - } + memcpy(&(idata->ic.response), cmd.resp, sizeof(cmd.resp)); if (is_rpmb) { /* @@ -607,9 +586,42 @@ static int mmc_blk_ioctl_cmd(struct block_device *bdev, __func__, status, err); } -cmd_rel_host: + return err; +} + +static int mmc_blk_ioctl_cmd(struct block_device *bdev, + struct mmc_ioc_cmd __user *ic_ptr) +{ + struct mmc_blk_ioc_data *idata; + struct mmc_blk_data *md; + struct mmc_card *card; + int err; + + idata = mmc_blk_ioctl_copy_from_user(ic_ptr); + if (IS_ERR(idata)) + return PTR_ERR(idata); + + md = mmc_blk_get(bdev->bd_disk); + if (!md) { + err = -EINVAL; + goto cmd_err; + } + + card = md->queue.card; + if (IS_ERR(card)) { + err = PTR_ERR(card); + goto cmd_done; + } + + mmc_get_card(card); + + err = __mmc_blk_ioctl_cmd(card, md, idata); + mmc_put_card(card); + if (!err) + err = mmc_blk_ioctl_copy_to_user(ic_ptr, idata); + cmd_done: mmc_blk_put(md); cmd_err: @@ -618,13 +630,97 @@ cmd_err: return err; } +static int mmc_blk_ioctl_multi_cmd(struct block_device *bdev, + struct mmc_ioc_multi_cmd __user *user) +{ + struct mmc_blk_ioc_data **idata = NULL; + struct mmc_ioc_cmd __user *cmds = user->cmds; + struct mmc_card *card; + struct mmc_blk_data *md; + int i, err = -EFAULT; + __u64 num_of_cmds; + + if (copy_from_user(&num_of_cmds, &user->num_of_cmds, + sizeof(num_of_cmds))) + return -EFAULT; + + if (num_of_cmds > MMC_IOC_MAX_CMDS) + return -EINVAL; + + idata = kcalloc(num_of_cmds, sizeof(*idata), GFP_KERNEL); + if (!idata) + return -ENOMEM; + + for (i = 0; i < num_of_cmds; i++) { + idata[i] = mmc_blk_ioctl_copy_from_user(&cmds[i]); + if (IS_ERR(idata[i])) { + err = PTR_ERR(idata[i]); + num_of_cmds = i; + goto cmd_err; + } + } + + md = mmc_blk_get(bdev->bd_disk); + if (!md) + goto cmd_err; + + card = md->queue.card; + if (IS_ERR(card)) { + err = PTR_ERR(card); + goto cmd_done; + } + + mmc_get_card(card); + + for (i = 0; i < num_of_cmds; i++) { + err = __mmc_blk_ioctl_cmd(card, md, idata[i]); + if (err) { + mmc_put_card(card); + goto cmd_done; + } + } + + mmc_put_card(card); + + /* copy to user if data and response */ + for (i = 0; i < num_of_cmds; i++) { + err = mmc_blk_ioctl_copy_to_user(&cmds[i], idata[i]); + if (err) + break; + } + +cmd_done: + mmc_blk_put(md); +cmd_err: + for (i = 0; i < num_of_cmds; i++) { + kfree(idata[i]->buf); + kfree(idata[i]); + } + kfree(idata); + return err; +} + static int mmc_blk_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { - int ret = -EINVAL; - if (cmd == MMC_IOC_CMD) - ret = mmc_blk_ioctl_cmd(bdev, (struct mmc_ioc_cmd __user *)arg); - return ret; + /* + * The caller must have CAP_SYS_RAWIO, and must be calling this on the + * whole block device, not on a partition. This prevents overspray + * between sibling partitions. + */ + if ((!capable(CAP_SYS_RAWIO)) || (bdev != bdev->bd_contains)) + return -EPERM; + + switch (cmd) { + case MMC_IOC_CMD: + return mmc_blk_ioctl_cmd(bdev, + (struct mmc_ioc_cmd __user *)arg); + case MMC_IOC_MULTI_CMD: + return mmc_blk_ioctl_multi_cmd(bdev, + (struct mmc_ioc_multi_cmd __user *)arg); + default: + return -EINVAL; + } } #ifdef CONFIG_COMPAT diff --git a/include/uapi/linux/mmc/ioctl.h b/include/uapi/linux/mmc/ioctl.h index 1f5e68923929..7e385b83b9d8 100644 --- a/include/uapi/linux/mmc/ioctl.h +++ b/include/uapi/linux/mmc/ioctl.h @@ -45,8 +45,24 @@ struct mmc_ioc_cmd { }; #define mmc_ioc_cmd_set_data(ic, ptr) ic.data_ptr = (__u64)(unsigned long) ptr -#define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) +/** + * struct mmc_ioc_multi_cmd - multi command information + * @num_of_cmds: Number of commands to send. Must be equal to or less than + * MMC_IOC_MAX_CMDS. + * @cmds: Array of commands with length equal to 'num_of_cmds' + */ +struct mmc_ioc_multi_cmd { + __u64 num_of_cmds; + struct mmc_ioc_cmd cmds[0]; +}; +#define MMC_IOC_CMD _IOWR(MMC_BLOCK_MAJOR, 0, struct mmc_ioc_cmd) +/* + * MMC_IOC_MULTI_CMD: Used to send an array of MMC commands described by + * the structure mmc_ioc_multi_cmd. The MMC driver will issue all + * commands in array in sequence to card. + */ +#define MMC_IOC_MULTI_CMD _IOWR(MMC_BLOCK_MAJOR, 1, struct mmc_ioc_multi_cmd) /* * Since this ioctl is only meant to enhance (and not replace) normal access * to the mmc bus device, an upper data transfer limit of MMC_IOC_MAX_BYTES @@ -54,4 +70,5 @@ struct mmc_ioc_cmd { * block device operations. */ #define MMC_IOC_MAX_BYTES (512L * 256) +#define MMC_IOC_MAX_CMDS 255 #endif /* LINUX_MMC_IOCTL_H */ -- cgit v1.2.3 From 06a16293f71927f756dcf37558a79c0b05a91641 Mon Sep 17 00:00:00 2001 From: David Herrmann Date: Sat, 24 Oct 2015 16:20:18 -0700 Subject: Input: evdev - add event-mask API Hardware manufacturers group keys in the weirdest way possible. This may cause a power-key to be grouped together with normal keyboard keys and thus be reported on the same kernel interface. However, user-space is often only interested in specific sets of events. For instance, daemons dealing with system-reboot (like systemd-logind) listen for KEY_POWER, but are not interested in any main keyboard keys. Usually, power keys are reported via separate interfaces, however, some i8042 boards report it in the AT matrix. To avoid waking up those system daemons on each key-press, we had two ideas: - split off KEY_POWER into a separate interface unconditionally - allow filtering a specific set of events on evdev FDs Splitting of KEY_POWER is a rather weird way to deal with this and may break backwards-compatibility. It is also specific to KEY_POWER and might be required for other stuff, too. Moreover, we might end up with a huge set of input-devices just to have them properly split. Hence, this patchset implements the second idea: An event-mask to specify which events you're interested in. Two ioctls allow setting this mask for each event-type. If not set, all events are reported. The type==0 entry is used same as in EVIOCGBIT to set the actual EV_* mask of filtered events. This way, you have a two-level filter. We are heavily forward-compatible to new event-types and event-codes. So new user-space will be able to run on an old kernel which doesn't know the given event-codes or event-types. Signed-off-by: David Herrmann Signed-off-by: Dmitry Torokhov --- drivers/input/evdev.c | 234 ++++++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/input.h | 60 ++++++++++++ 2 files changed, 292 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index 08d496411f75..6b10f5b29218 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -58,10 +58,55 @@ struct evdev_client { struct list_head node; int clk_type; bool revoked; + unsigned long *evmasks[EV_CNT]; unsigned int bufsize; struct input_event buffer[]; }; +static size_t evdev_get_mask_cnt(unsigned int type) +{ + static const size_t counts[EV_CNT] = { + /* EV_SYN==0 is EV_CNT, _not_ SYN_CNT, see EVIOCGBIT */ + [EV_SYN] = EV_CNT, + [EV_KEY] = KEY_CNT, + [EV_REL] = REL_CNT, + [EV_ABS] = ABS_CNT, + [EV_MSC] = MSC_CNT, + [EV_SW] = SW_CNT, + [EV_LED] = LED_CNT, + [EV_SND] = SND_CNT, + [EV_FF] = FF_CNT, + }; + + return (type < EV_CNT) ? counts[type] : 0; +} + +/* requires the buffer lock to be held */ +static bool __evdev_is_filtered(struct evdev_client *client, + unsigned int type, + unsigned int code) +{ + unsigned long *mask; + size_t cnt; + + /* EV_SYN and unknown codes are never filtered */ + if (type == EV_SYN || type >= EV_CNT) + return false; + + /* first test whether the type is filtered */ + mask = client->evmasks[0]; + if (mask && !test_bit(type, mask)) + return true; + + /* unknown values are never filtered */ + cnt = evdev_get_mask_cnt(type); + if (!cnt || code >= cnt) + return false; + + mask = client->evmasks[type]; + return mask && !test_bit(code, mask); +} + /* flush queued events of type @type, caller must hold client->buffer_lock */ static void __evdev_flush_queue(struct evdev_client *client, unsigned int type) { @@ -226,12 +271,21 @@ static void evdev_pass_values(struct evdev_client *client, spin_lock(&client->buffer_lock); for (v = vals; v != vals + count; v++) { + if (__evdev_is_filtered(client, v->type, v->code)) + continue; + + if (v->type == EV_SYN && v->code == SYN_REPORT) { + /* drop empty SYN_REPORT */ + if (client->packet_head == client->head) + continue; + + wakeup = true; + } + event.type = v->type; event.code = v->code; event.value = v->value; __pass_event(client, &event); - if (v->type == EV_SYN && v->code == SYN_REPORT) - wakeup = true; } spin_unlock(&client->buffer_lock); @@ -410,6 +464,7 @@ static int evdev_release(struct inode *inode, struct file *file) { struct evdev_client *client = file->private_data; struct evdev *evdev = client->evdev; + unsigned int i; mutex_lock(&evdev->mutex); evdev_ungrab(evdev, client); @@ -417,6 +472,9 @@ static int evdev_release(struct inode *inode, struct file *file) evdev_detach_client(evdev, client); + for (i = 0; i < EV_CNT; ++i) + kfree(client->evmasks[i]); + kvfree(client); evdev_close_device(evdev); @@ -627,7 +685,46 @@ static int bits_to_user(unsigned long *bits, unsigned int maxbit, return len; } + +static int bits_from_user(unsigned long *bits, unsigned int maxbit, + unsigned int maxlen, const void __user *p, int compat) +{ + int len, i; + + if (compat) { + if (maxlen % sizeof(compat_long_t)) + return -EINVAL; + + len = BITS_TO_LONGS_COMPAT(maxbit) * sizeof(compat_long_t); + if (len > maxlen) + len = maxlen; + + for (i = 0; i < len / sizeof(compat_long_t); i++) + if (copy_from_user((compat_long_t *) bits + + i + 1 - ((i % 2) << 1), + (compat_long_t __user *) p + i, + sizeof(compat_long_t))) + return -EFAULT; + if (i % 2) + *((compat_long_t *) bits + i - 1) = 0; + + } else { + if (maxlen % sizeof(long)) + return -EINVAL; + + len = BITS_TO_LONGS(maxbit) * sizeof(long); + if (len > maxlen) + len = maxlen; + + if (copy_from_user(bits, p, len)) + return -EFAULT; + } + + return len; +} + #else + static int bits_to_user(unsigned long *bits, unsigned int maxbit, unsigned int maxlen, void __user *p, int compat) { @@ -640,6 +737,24 @@ static int bits_to_user(unsigned long *bits, unsigned int maxbit, return copy_to_user(p, bits, len) ? -EFAULT : len; } + +static int bits_from_user(unsigned long *bits, unsigned int maxbit, + unsigned int maxlen, const void __user *p, int compat) +{ + size_t chunk_size = compat ? sizeof(compat_long_t) : sizeof(long); + int len; + + if (maxlen % chunk_size) + return -EINVAL; + + len = compat ? BITS_TO_LONGS_COMPAT(maxbit) : BITS_TO_LONGS(maxbit); + len *= chunk_size; + if (len > maxlen) + len = maxlen; + + return copy_from_user(bits, p, len) ? -EFAULT : len; +} + #endif /* __BIG_ENDIAN */ #else @@ -655,6 +770,21 @@ static int bits_to_user(unsigned long *bits, unsigned int maxbit, return copy_to_user(p, bits, len) ? -EFAULT : len; } +static int bits_from_user(unsigned long *bits, unsigned int maxbit, + unsigned int maxlen, const void __user *p, int compat) +{ + int len; + + if (maxlen % sizeof(long)) + return -EINVAL; + + len = BITS_TO_LONGS(maxbit) * sizeof(long); + if (len > maxlen) + len = maxlen; + + return copy_from_user(bits, p, len) ? -EFAULT : len; +} + #endif /* CONFIG_COMPAT */ static int str_to_user(const char *str, unsigned int maxlen, void __user *p) @@ -849,6 +979,81 @@ static int evdev_revoke(struct evdev *evdev, struct evdev_client *client, return 0; } +/* must be called with evdev-mutex held */ +static int evdev_set_mask(struct evdev_client *client, + unsigned int type, + const void __user *codes, + u32 codes_size, + int compat) +{ + unsigned long flags, *mask, *oldmask; + size_t cnt; + int error; + + /* we allow unknown types and 'codes_size > size' for forward-compat */ + cnt = evdev_get_mask_cnt(type); + if (!cnt) + return 0; + + mask = kcalloc(sizeof(unsigned long), BITS_TO_LONGS(cnt), GFP_KERNEL); + if (!mask) + return -ENOMEM; + + error = bits_from_user(mask, cnt - 1, codes_size, codes, compat); + if (error < 0) { + kfree(mask); + return error; + } + + spin_lock_irqsave(&client->buffer_lock, flags); + oldmask = client->evmasks[type]; + client->evmasks[type] = mask; + spin_unlock_irqrestore(&client->buffer_lock, flags); + + kfree(oldmask); + + return 0; +} + +/* must be called with evdev-mutex held */ +static int evdev_get_mask(struct evdev_client *client, + unsigned int type, + void __user *codes, + u32 codes_size, + int compat) +{ + unsigned long *mask; + size_t cnt, size, xfer_size; + int i; + int error; + + /* we allow unknown types and 'codes_size > size' for forward-compat */ + cnt = evdev_get_mask_cnt(type); + size = sizeof(unsigned long) * BITS_TO_LONGS(cnt); + xfer_size = min_t(size_t, codes_size, size); + + if (cnt > 0) { + mask = client->evmasks[type]; + if (mask) { + error = bits_to_user(mask, cnt - 1, + xfer_size, codes, compat); + if (error < 0) + return error; + } else { + /* fake mask with all bits set */ + for (i = 0; i < xfer_size; i++) + if (put_user(0xffU, (u8 __user *)codes + i)) + return -EFAULT; + } + } + + if (xfer_size < codes_size) + if (clear_user(codes + xfer_size, codes_size - xfer_size)) + return -EFAULT; + + return 0; +} + static long evdev_do_ioctl(struct file *file, unsigned int cmd, void __user *p, int compat_mode) { @@ -856,6 +1061,7 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd, struct evdev *evdev = client->evdev; struct input_dev *dev = evdev->handle.dev; struct input_absinfo abs; + struct input_mask mask; struct ff_effect effect; int __user *ip = (int __user *)p; unsigned int i, t, u, v; @@ -917,6 +1123,30 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd, else return evdev_revoke(evdev, client, file); + case EVIOCGMASK: { + void __user *codes_ptr; + + if (copy_from_user(&mask, p, sizeof(mask))) + return -EFAULT; + + codes_ptr = (void __user *)(unsigned long)mask.codes_ptr; + return evdev_get_mask(client, + mask.type, codes_ptr, mask.codes_size, + compat_mode); + } + + case EVIOCSMASK: { + const void __user *codes_ptr; + + if (copy_from_user(&mask, p, sizeof(mask))) + return -EFAULT; + + codes_ptr = (const void __user *)(unsigned long)mask.codes_ptr; + return evdev_set_mask(client, + mask.type, codes_ptr, mask.codes_size, + compat_mode); + } + case EVIOCSCLOCKID: if (copy_from_user(&i, p, sizeof(unsigned int))) return -EFAULT; diff --git a/include/uapi/linux/input.h b/include/uapi/linux/input.h index 4f9f2a0f5573..2758687300b4 100644 --- a/include/uapi/linux/input.h +++ b/include/uapi/linux/input.h @@ -98,6 +98,12 @@ struct input_keymap_entry { __u8 scancode[32]; }; +struct input_mask { + __u32 type; + __u32 codes_size; + __u64 codes_ptr; +}; + #define EVIOCGVERSION _IOR('E', 0x01, int) /* get driver version */ #define EVIOCGID _IOR('E', 0x02, struct input_id) /* get device ID */ #define EVIOCGREP _IOR('E', 0x03, unsigned int[2]) /* get repeat settings */ @@ -155,6 +161,60 @@ struct input_keymap_entry { #define EVIOCGRAB _IOW('E', 0x90, int) /* Grab/Release device */ #define EVIOCREVOKE _IOW('E', 0x91, int) /* Revoke device access */ +/** + * EVIOCGMASK - Retrieve current event mask + * + * This ioctl allows user to retrieve the current event mask for specific + * event type. The argument must be of type "struct input_mask" and + * specifies the event type to query, the address of the receive buffer and + * the size of the receive buffer. + * + * The event mask is a per-client mask that specifies which events are + * forwarded to the client. Each event code is represented by a single bit + * in the event mask. If the bit is set, the event is passed to the client + * normally. Otherwise, the event is filtered and will never be queued on + * the client's receive buffer. + * + * Event masks do not affect global state of the input device. They only + * affect the file descriptor they are applied to. + * + * The default event mask for a client has all bits set, i.e. all events + * are forwarded to the client. If the kernel is queried for an unknown + * event type or if the receive buffer is larger than the number of + * event codes known to the kernel, the kernel returns all zeroes for those + * codes. + * + * At maximum, codes_size bytes are copied. + * + * This ioctl may fail with ENODEV in case the file is revoked, EFAULT + * if the receive-buffer points to invalid memory, or EINVAL if the kernel + * does not implement the ioctl. + */ +#define EVIOCGMASK _IOR('E', 0x92, struct input_mask) /* Get event-masks */ + +/** + * EVIOCSMASK - Set event mask + * + * This ioctl is the counterpart to EVIOCGMASK. Instead of receiving the + * current event mask, this changes the client's event mask for a specific + * type. See EVIOCGMASK for a description of event-masks and the + * argument-type. + * + * This ioctl provides full forward compatibility. If the passed event type + * is unknown to the kernel, or if the number of event codes specified in + * the mask is bigger than what is known to the kernel, the ioctl is still + * accepted and applied. However, any unknown codes are left untouched and + * stay cleared. That means, the kernel always filters unknown codes + * regardless of what the client requests. If the new mask doesn't cover + * all known event-codes, all remaining codes are automatically cleared and + * thus filtered. + * + * This ioctl may fail with ENODEV in case the file is revoked. EFAULT is + * returned if the receive-buffer points to invalid memory. EINVAL is returned + * if the kernel does not implement the ioctl. + */ +#define EVIOCSMASK _IOW('E', 0x93, struct input_mask) /* Set event-masks */ + #define EVIOCSCLOCKID _IOW('E', 0xa0, int) /* Set clockid to be used for timestamps */ /* -- cgit v1.2.3 From 12907fc79818a62a2478f84f7795afa774bf7f9c Mon Sep 17 00:00:00 2001 From: David Sterba Date: Sat, 10 Oct 2015 17:16:50 +0200 Subject: btrfs: extend balance filter limit to take minimum and maximum The 'limit' filter is underdesigned, it should have been a range for [min,max], with some relaxed semantics when one of the bounds is missing. Besides that, using a full u64 for a single value is a waste of bytes. Let's fix both by extending the use of the u64 bytes for the [min,max] range. This can be done in a backward compatible way, the range will be interpreted only if the appropriate flag is set (BTRFS_BALANCE_ARGS_LIMIT_RANGE). Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 14 ++++++++++++-- fs/btrfs/volumes.c | 42 ++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/volumes.h | 1 + include/uapi/linux/btrfs.h | 13 ++++++++++++- 4 files changed, 67 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 3fa3c3b7bb66..460cd69b405e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -846,8 +846,18 @@ struct btrfs_disk_balance_args { /* BTRFS_BALANCE_ARGS_* */ __le64 flags; - /* BTRFS_BALANCE_ARGS_LIMIT value */ - __le64 limit; + /* + * BTRFS_BALANCE_ARGS_LIMIT with value 'limit' + * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum + * and maximum + */ + union { + __le64 limit; + struct { + __le32 limit_min; + __le32 limit_max; + }; + }; __le64 unused[7]; } __attribute__ ((__packed__)); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index f86d83805b44..e2fdd2e01104 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3300,6 +3300,16 @@ static int should_balance_chunk(struct btrfs_root *root, return 0; else bargs->limit--; + } else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) { + /* + * Same logic as the 'limit' filter; the minimum cannot be + * determined here because we do not have the global informatoin + * about the count of all chunks that satisfy the filters. + */ + if (bargs->limit_max == 0) + return 0; + else + bargs->limit_max--; } return 1; @@ -3314,6 +3324,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) struct btrfs_device *device; u64 old_size; u64 size_to_free; + u64 chunk_type; struct btrfs_chunk *chunk; struct btrfs_path *path; struct btrfs_key key; @@ -3324,9 +3335,13 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) int ret; int enospc_errors = 0; bool counting = true; + /* The single value limit and min/max limits use the same bytes in the */ u64 limit_data = bctl->data.limit; u64 limit_meta = bctl->meta.limit; u64 limit_sys = bctl->sys.limit; + u32 count_data = 0; + u32 count_meta = 0; + u32 count_sys = 0; /* step one make some room on all the devices */ devices = &fs_info->fs_devices->devices; @@ -3367,6 +3382,10 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info) spin_unlock(&fs_info->balance_lock); again: if (!counting) { + /* + * The single value limit and min/max limits use the same bytes + * in the + */ bctl->data.limit = limit_data; bctl->meta.limit = limit_meta; bctl->sys.limit = limit_sys; @@ -3414,6 +3433,7 @@ again: } chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk); + chunk_type = btrfs_chunk_type(leaf, chunk); if (!counting) { spin_lock(&fs_info->balance_lock); @@ -3434,6 +3454,28 @@ again: spin_lock(&fs_info->balance_lock); bctl->stat.expected++; spin_unlock(&fs_info->balance_lock); + + if (chunk_type & BTRFS_BLOCK_GROUP_DATA) + count_data++; + else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) + count_sys++; + else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA) + count_meta++; + + goto loop; + } + + /* + * Apply limit_min filter, no need to check if the LIMITS + * filter is used, limit_min is 0 by default + */ + if (((chunk_type & BTRFS_BLOCK_GROUP_DATA) && + count_data < bctl->data.limit_min) + || ((chunk_type & BTRFS_BLOCK_GROUP_METADATA) && + count_meta < bctl->meta.limit_min) + || ((chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) && + count_sys < bctl->sys.limit_min)) { + mutex_unlock(&fs_info->delete_unused_bgs_mutex); goto loop; } diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index b8e64ea984f1..628d4e17019d 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -380,6 +380,7 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_DRANGE (1ULL << 3) #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) +#define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) #define BTRFS_BALANCE_ARGS_MASK \ (BTRFS_BALANCE_ARGS_PROFILES | \ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index b6dec05c7196..11f13108b78b 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -217,7 +217,18 @@ struct btrfs_balance_args { __u64 flags; - __u64 limit; /* limit number of processed chunks */ + /* + * BTRFS_BALANCE_ARGS_LIMIT with value 'limit' + * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum + * and maximum + */ + union { + __u64 limit; /* limit number of processed chunks */ + struct { + __u32 limit_min; + __u32 limit_max; + }; + }; __u64 unused[7]; } __attribute__ ((__packed__)); -- cgit v1.2.3 From dee32d0ac3719ef8d640efaf0884111df444730f Mon Sep 17 00:00:00 2001 From: Gabríel Arthúr Pétursson Date: Mon, 28 Sep 2015 22:32:41 +0000 Subject: btrfs: add balance filter for stripes MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Balance block groups which have the given number of stripes, defined by a range min..max. This is useful to selectively rebalance only chunks that do not span enough devices, applies to RAID0/10/5/6. Signed-off-by: Gabríel Arthúr Pétursson [ renamed bargs members, added to the UAPI, wrote the changelog ] Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 9 ++++++++- fs/btrfs/volumes.c | 19 +++++++++++++++++++ fs/btrfs/volumes.h | 1 + include/uapi/linux/btrfs.h | 10 +++++++++- 4 files changed, 37 insertions(+), 2 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 460cd69b405e..8ccbf4317a4a 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -859,7 +859,14 @@ struct btrfs_disk_balance_args { }; }; - __le64 unused[7]; + /* + * Process chunks that cross stripes_min..stripes_max devices, + * BTRFS_BALANCE_ARGS_STRIPES_RANGE + */ + __le32 stripes_min; + __le32 stripes_max; + + __le64 unused[6]; } __attribute__ ((__packed__)); /* diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index e2fdd2e01104..9f5d16739880 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3220,6 +3220,19 @@ static int chunk_vrange_filter(struct extent_buffer *leaf, return 1; } +static int chunk_stripes_range_filter(struct extent_buffer *leaf, + struct btrfs_chunk *chunk, + struct btrfs_balance_args *bargs) +{ + int num_stripes = btrfs_chunk_num_stripes(leaf, chunk); + + if (bargs->stripes_min <= num_stripes + && num_stripes <= bargs->stripes_max) + return 0; + + return 1; +} + static int chunk_soft_convert_filter(u64 chunk_type, struct btrfs_balance_args *bargs) { @@ -3286,6 +3299,12 @@ static int should_balance_chunk(struct btrfs_root *root, return 0; } + /* stripes filter */ + if ((bargs->flags & BTRFS_BALANCE_ARGS_STRIPES_RANGE) && + chunk_stripes_range_filter(leaf, chunk, bargs)) { + return 0; + } + /* soft profile changing mode */ if ((bargs->flags & BTRFS_BALANCE_ARGS_SOFT) && chunk_soft_convert_filter(chunk_type, bargs)) { diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 628d4e17019d..a5bf224d3c65 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -381,6 +381,7 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_VRANGE (1ULL << 4) #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) #define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) +#define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) #define BTRFS_BALANCE_ARGS_MASK \ (BTRFS_BALANCE_ARGS_PROFILES | \ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 11f13108b78b..17a94704b183 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -229,7 +229,15 @@ struct btrfs_balance_args { __u32 limit_max; }; }; - __u64 unused[7]; + + /* + * Process chunks that cross stripes_min..stripes_max devices, + * BTRFS_BALANCE_ARGS_STRIPES_RANGE + */ + __le32 stripes_min; + __le32 stripes_max; + + __u64 unused[6]; } __attribute__ ((__packed__)); /* report balance progress to userspace */ -- cgit v1.2.3 From bc3094673f22d00794a8606200788e411b4ec80d Mon Sep 17 00:00:00 2001 From: David Sterba Date: Tue, 20 Oct 2015 18:22:13 +0200 Subject: btrfs: extend balance filter usage to take minimum and maximum Similar to the 'limit' filter, we can enhance the 'usage' filter to accept a range. The change is backward compatible, the range is applied only in connection with the BTRFS_BALANCE_ARGS_USAGE_RANGE flag. We don't have a usecase yet, the current syntax has been sufficient. The enhancement should provide parity with other range-like filters. Signed-off-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 14 ++++++++++++-- fs/btrfs/volumes.c | 41 ++++++++++++++++++++++++++++++++++++++++- fs/btrfs/volumes.h | 1 + include/uapi/linux/btrfs.h | 8 +++++++- 4 files changed, 60 insertions(+), 4 deletions(-) (limited to 'include/uapi') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 8ccbf4317a4a..4001585ec434 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -823,8 +823,18 @@ struct btrfs_disk_balance_args { */ __le64 profiles; - /* usage filter */ - __le64 usage; + /* + * usage filter + * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' + * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max + */ + union { + __le64 usage; + struct { + __le32 usage_min; + __le32 usage_max; + }; + }; /* devid filter */ __le64 devid; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 9f5d16739880..17ed76d18eb6 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3059,16 +3059,19 @@ static void update_balance_args(struct btrfs_balance_control *bctl) * (albeit full) chunks. */ if (!(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->data.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->data.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->data.usage = 90; } if (!(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->sys.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->sys.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->sys.usage = 90; } if (!(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE) && + !(bctl->meta.flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && !(bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT)) { bctl->meta.flags |= BTRFS_BALANCE_ARGS_USAGE; bctl->meta.usage = 90; @@ -3122,6 +3125,39 @@ static int chunk_profiles_filter(u64 chunk_type, static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, struct btrfs_balance_args *bargs) +{ + struct btrfs_block_group_cache *cache; + u64 chunk_used; + u64 user_thresh_min; + u64 user_thresh_max; + int ret = 1; + + cache = btrfs_lookup_block_group(fs_info, chunk_offset); + chunk_used = btrfs_block_group_used(&cache->item); + + if (bargs->usage_min == 0) + user_thresh_min = 0; + else + user_thresh_min = div_factor_fine(cache->key.offset, + bargs->usage_min); + + if (bargs->usage_max == 0) + user_thresh_max = 1; + else if (bargs->usage_max > 100) + user_thresh_max = cache->key.offset; + else + user_thresh_max = div_factor_fine(cache->key.offset, + bargs->usage_max); + + if (user_thresh_min <= chunk_used && chunk_used < user_thresh_max) + ret = 0; + + btrfs_put_block_group(cache); + return ret; +} + +static int chunk_usage_range_filter(struct btrfs_fs_info *fs_info, + u64 chunk_offset, struct btrfs_balance_args *bargs) { struct btrfs_block_group_cache *cache; u64 chunk_used, user_thresh; @@ -3130,7 +3166,7 @@ static int chunk_usage_filter(struct btrfs_fs_info *fs_info, u64 chunk_offset, cache = btrfs_lookup_block_group(fs_info, chunk_offset); chunk_used = btrfs_block_group_used(&cache->item); - if (bargs->usage == 0) + if (bargs->usage_min == 0) user_thresh = 1; else if (bargs->usage > 100) user_thresh = cache->key.offset; @@ -3279,6 +3315,9 @@ static int should_balance_chunk(struct btrfs_root *root, if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE) && chunk_usage_filter(bctl->fs_info, chunk_offset, bargs)) { return 0; + } else if ((bargs->flags & BTRFS_BALANCE_ARGS_USAGE_RANGE) && + chunk_usage_range_filter(bctl->fs_info, chunk_offset, bargs)) { + return 0; } /* devid filter */ diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index a5bf224d3c65..2a396cbb14a5 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -382,6 +382,7 @@ struct map_lookup { #define BTRFS_BALANCE_ARGS_LIMIT (1ULL << 5) #define BTRFS_BALANCE_ARGS_LIMIT_RANGE (1ULL << 6) #define BTRFS_BALANCE_ARGS_STRIPES_RANGE (1ULL << 7) +#define BTRFS_BALANCE_ARGS_USAGE_RANGE (1ULL << 8) #define BTRFS_BALANCE_ARGS_MASK \ (BTRFS_BALANCE_ARGS_PROFILES | \ diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 17a94704b183..dea893199257 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -206,7 +206,13 @@ struct btrfs_ioctl_feature_flags { */ struct btrfs_balance_args { __u64 profiles; - __u64 usage; + union { + __le64 usage; + struct { + __le32 usage_min; + __le32 usage_max; + }; + }; __u64 devid; __u64 pstart; __u64 pend; -- cgit v1.2.3 From be73c2cbc857a4a3424c0e3cdd70002d5a27a756 Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:38 +0100 Subject: NFC: netlink: Add missing NFC_ATTR comments NFC_CMD_ACTIVATE_TARGET and NFC_ATTR_SE_PARAMS comments are missing. Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- include/uapi/linux/nfc.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi') diff --git a/include/uapi/linux/nfc.h b/include/uapi/linux/nfc.h index dd3f75389076..399f39ff8048 100644 --- a/include/uapi/linux/nfc.h +++ b/include/uapi/linux/nfc.h @@ -86,6 +86,7 @@ * for this event is the application ID (AID). * @NFC_CMD_GET_SE: Dump all discovered secure elements from an NFC controller. * @NFC_CMD_SE_IO: Send/Receive APDUs to/from the selected secure element. + * @NFC_CMD_ACTIVATE_TARGET: Request NFC controller to reactivate target. * @NFC_CMD_VENDOR: Vendor specific command, to be implemented directly * from the driver in order to support hardware specific operations. */ @@ -156,6 +157,7 @@ enum nfc_commands { * @NFC_ATTR_APDU: Secure element APDU * @NFC_ATTR_TARGET_ISO15693_DSFID: ISO 15693 Data Storage Format Identifier * @NFC_ATTR_TARGET_ISO15693_UID: ISO 15693 Unique Identifier + * @NFC_ATTR_SE_PARAMS: Parameters data from an evt_transaction * @NFC_ATTR_VENDOR_ID: NFC manufacturer unique ID, typically an OUI * @NFC_ATTR_VENDOR_SUBCMD: Vendor specific sub command * @NFC_ATTR_VENDOR_DATA: Vendor specific data, to be optionally passed -- cgit v1.2.3 From 3c2f85b8ce8acee0502d61fb53015eabd7d4c8fb Mon Sep 17 00:00:00 2001 From: Easwar Hariharan Date: Mon, 26 Oct 2015 10:28:31 -0400 Subject: staging/rdma/hfi1: Remove QSFP_ENABLED from HFI capability mask The QSFP interface code has been running without issues and the flag is never set to off. This patch removes the QSFP_ENABLED bit from HFI1_CAP. Reviewed-by: Mike Marciniszyn Signed-off-by: Easwar Hariharan Signed-off-by: Ira Weiny Signed-off-by: Greg Kroah-Hartman --- drivers/staging/rdma/hfi1/chip.c | 3 +-- drivers/staging/rdma/hfi1/common.h | 2 -- drivers/staging/rdma/hfi1/qsfp.c | 13 ++++--------- include/uapi/rdma/hfi/hfi1_user.h | 4 ++-- 4 files changed, 7 insertions(+), 15 deletions(-) (limited to 'include/uapi') diff --git a/drivers/staging/rdma/hfi1/chip.c b/drivers/staging/rdma/hfi1/chip.c index 1747ab6410a9..a898d3eed888 100644 --- a/drivers/staging/rdma/hfi1/chip.c +++ b/drivers/staging/rdma/hfi1/chip.c @@ -5714,8 +5714,7 @@ void init_qsfp(struct hfi1_pportdata *ppd) u64 qsfp_mask; if (loopback == LOOPBACK_SERDES || loopback == LOOPBACK_LCB || - ppd->dd->icode == ICODE_FUNCTIONAL_SIMULATOR || - !HFI1_CAP_IS_KSET(QSFP_ENABLED)) { + ppd->dd->icode == ICODE_FUNCTIONAL_SIMULATOR) { ppd->driver_link_ready = 1; return; } diff --git a/drivers/staging/rdma/hfi1/common.h b/drivers/staging/rdma/hfi1/common.h index 5f2293729cf9..de62cbe2224c 100644 --- a/drivers/staging/rdma/hfi1/common.h +++ b/drivers/staging/rdma/hfi1/common.h @@ -147,7 +147,6 @@ HFI1_CAP_USE_SDMA_HEAD | \ HFI1_CAP_EXTENDED_PSN | \ HFI1_CAP_PRINT_UNIMPL | \ - HFI1_CAP_QSFP_ENABLED | \ HFI1_CAP_NO_INTEGRITY | \ HFI1_CAP_PKEY_CHECK) << \ HFI1_CAP_USER_SHIFT) @@ -163,7 +162,6 @@ HFI1_CAP_SDMA | \ HFI1_CAP_PRINT_UNIMPL | \ HFI1_CAP_STATIC_RATE_CTRL | \ - HFI1_CAP_QSFP_ENABLED | \ HFI1_CAP_PKEY_CHECK | \ HFI1_CAP_MULTI_PKT_EGR | \ HFI1_CAP_EXTENDED_PSN | \ diff --git a/drivers/staging/rdma/hfi1/qsfp.c b/drivers/staging/rdma/hfi1/qsfp.c index 3138936157db..ffdb1d787a80 100644 --- a/drivers/staging/rdma/hfi1/qsfp.c +++ b/drivers/staging/rdma/hfi1/qsfp.c @@ -403,16 +403,11 @@ static const char *pwr_codes = "1.5W2.0W2.5W3.5W"; int qsfp_mod_present(struct hfi1_pportdata *ppd) { - if (HFI1_CAP_IS_KSET(QSFP_ENABLED)) { - struct hfi1_devdata *dd = ppd->dd; - u64 reg; + struct hfi1_devdata *dd = ppd->dd; + u64 reg; - reg = read_csr(dd, - dd->hfi1_id ? ASIC_QSFP2_IN : ASIC_QSFP1_IN); - return !(reg & QSFP_HFI0_MODPRST_N); - } - /* always return cable present */ - return 1; + reg = read_csr(dd, dd->hfi1_id ? ASIC_QSFP2_IN : ASIC_QSFP1_IN); + return !(reg & QSFP_HFI0_MODPRST_N); } /* diff --git a/include/uapi/rdma/hfi/hfi1_user.h b/include/uapi/rdma/hfi/hfi1_user.h index 78c442fbf263..599562fe5d57 100644 --- a/include/uapi/rdma/hfi/hfi1_user.h +++ b/include/uapi/rdma/hfi/hfi1_user.h @@ -88,7 +88,7 @@ #define HFI1_CAP_SDMA_AHG (1UL << 2) /* Enable SDMA AHG support */ #define HFI1_CAP_EXTENDED_PSN (1UL << 3) /* Enable Extended PSN support */ #define HFI1_CAP_HDRSUPP (1UL << 4) /* Enable Header Suppression */ -/* 1UL << 5 reserved */ +/* 1UL << 5 unused */ #define HFI1_CAP_USE_SDMA_HEAD (1UL << 6) /* DMA Hdr Q tail vs. use CSR */ #define HFI1_CAP_MULTI_PKT_EGR (1UL << 7) /* Enable multi-packet Egr buffs*/ #define HFI1_CAP_NODROP_RHQ_FULL (1UL << 8) /* Don't drop on Hdr Q full */ @@ -99,7 +99,7 @@ #define HFI1_CAP_NO_INTEGRITY (1UL << 13) /* Enable ctxt integrity checks */ #define HFI1_CAP_PKEY_CHECK (1UL << 14) /* Enable ctxt PKey checking */ #define HFI1_CAP_STATIC_RATE_CTRL (1UL << 15) /* Allow PBC.StaticRateControl */ -#define HFI1_CAP_QSFP_ENABLED (1UL << 16) /* Enable QSFP check during LNI */ +/* 1UL << 16 unused */ #define HFI1_CAP_SDMA_HEAD_CHECK (1UL << 17) /* SDMA head checking */ #define HFI1_CAP_EARLY_CREDIT_RETURN (1UL << 18) /* early credit return */ -- cgit v1.2.3 From 5523662edd4fe937267053c2018b75be2ac17860 Mon Sep 17 00:00:00 2001 From: Stephen Chandler Paul Date: Sat, 24 Oct 2015 13:10:29 -0700 Subject: Input: add userio module Debugging input devices, specifically laptop touchpads, can be tricky without having the physical device handy. Here we try to remedy that with userio. This module allows an application to connect to a character device provided by the kernel, and emulate any serio device. In combination with userspace programs that can record PS/2 devices and replay them through the /dev/userio device, this allows developers to debug driver issues on the PS/2 level with devices simply by requesting a recording from the user experiencing the issue without having to have the physical hardware in front of them. Signed-off-by: Stephen Chandler Paul Reviewed-by: David Herrmann Signed-off-by: Dmitry Torokhov --- Documentation/input/userio.txt | 70 ++++++++++ MAINTAINERS | 6 + drivers/input/serio/Kconfig | 14 ++ drivers/input/serio/Makefile | 1 + drivers/input/serio/userio.c | 285 +++++++++++++++++++++++++++++++++++++++++ include/linux/miscdevice.h | 1 + include/uapi/linux/userio.h | 44 +++++++ 7 files changed, 421 insertions(+) create mode 100644 Documentation/input/userio.txt create mode 100644 drivers/input/serio/userio.c create mode 100644 include/uapi/linux/userio.h (limited to 'include/uapi') diff --git a/Documentation/input/userio.txt b/Documentation/input/userio.txt new file mode 100644 index 000000000000..0880c0f447a6 --- /dev/null +++ b/Documentation/input/userio.txt @@ -0,0 +1,70 @@ + The userio Protocol + (c) 2015 Stephen Chandler Paul + Sponsored by Red Hat +-------------------------------------------------------------------------------- + +1. Introduction +~~~~~~~~~~~~~~~ + This module is intended to try to make the lives of input driver developers +easier by allowing them to test various serio devices (mainly the various +touchpads found on laptops) without having to have the physical device in front +of them. userio accomplishes this by allowing any privileged userspace program +to directly interact with the kernel's serio driver and control a virtual serio +port from there. + +2. Usage overview +~~~~~~~~~~~~~~~~~ + In order to interact with the userio kernel module, one simply opens the +/dev/userio character device in their applications. Commands are sent to the +kernel module by writing to the device, and any data received from the serio +driver is read as-is from the /dev/userio device. All of the structures and +macros you need to interact with the device are defined in and +. + +3. Command Structure +~~~~~~~~~~~~~~~~~~~~ + The struct used for sending commands to /dev/userio is as follows: + + struct userio_cmd { + __u8 type; + __u8 data; + }; + + "type" describes the type of command that is being sent. This can be any one +of the USERIO_CMD macros defined in . "data" is the argument +that goes along with the command. In the event that the command doesn't have an +argument, this field can be left untouched and will be ignored by the kernel. +Each command should be sent by writing the struct directly to the character +device. In the event that the command you send is invalid, an error will be +returned by the character device and a more descriptive error will be printed +to the kernel log. Only one command can be sent at a time, any additional data +written to the character device after the initial command will be ignored. + To close the virtual serio port, just close /dev/userio. + +4. Commands +~~~~~~~~~~~ + +4.1 USERIO_CMD_REGISTER +~~~~~~~~~~~~~~~~~~~~~~~ + Registers the port with the serio driver and begins transmitting data back and +forth. Registration can only be performed once a port type is set with +USERIO_CMD_SET_PORT_TYPE. Has no argument. + +4.2 USERIO_CMD_SET_PORT_TYPE +~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Sets the type of port we're emulating, where "data" is the port type being +set. Can be any of the macros from . For example: SERIO_8042 +would set the port type to be a normal PS/2 port. + +4.3 USERIO_CMD_SEND_INTERRUPT +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + Sends an interrupt through the virtual serio port to the serio driver, where +"data" is the interrupt data being sent. + +5. Userspace tools +~~~~~~~~~~~~~~~~~~ + The userio userspace tools are able to record PS/2 devices using some of the +debugging information from i8042, and play back the devices on /dev/userio. The +latest version of these tools can be found at: + + https://github.com/Lyude/ps2emu diff --git a/MAINTAINERS b/MAINTAINERS index 797236befd27..ba59bd7b3557 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -11100,6 +11100,12 @@ S: Maintained F: drivers/media/v4l2-core/videobuf2-* F: include/media/videobuf2-* +VIRTUAL SERIO DEVICE DRIVER +M: Stephen Chandler Paul +S: Maintained +F: drivers/input/serio/userio.c +F: include/uapi/linux/userio.h + VIRTIO CONSOLE DRIVER M: Amit Shah L: virtualization@lists.linux-foundation.org diff --git a/drivers/input/serio/Kconfig b/drivers/input/serio/Kconfig index 200841b77edb..c3d05b4d3118 100644 --- a/drivers/input/serio/Kconfig +++ b/drivers/input/serio/Kconfig @@ -292,4 +292,18 @@ config SERIO_SUN4I_PS2 To compile this driver as a module, choose M here: the module will be called sun4i-ps2. +config USERIO + tristate "User space serio port driver support" + help + Say Y here if you want to support user level drivers for serio + subsystem accessible under char device 10:240 - /dev/userio. Using + this facility userspace programs can implement serio ports that + will be used by the standard in-kernel serio consumer drivers, + such as psmouse and atkbd. + + To compile this driver as a module, choose M here: the module will be + called userio. + + If you are unsure, say N. + endif diff --git a/drivers/input/serio/Makefile b/drivers/input/serio/Makefile index c600089b7a34..2374ef9b33d7 100644 --- a/drivers/input/serio/Makefile +++ b/drivers/input/serio/Makefile @@ -30,3 +30,4 @@ obj-$(CONFIG_SERIO_APBPS2) += apbps2.o obj-$(CONFIG_SERIO_OLPC_APSP) += olpc_apsp.o obj-$(CONFIG_HYPERV_KEYBOARD) += hyperv-keyboard.o obj-$(CONFIG_SERIO_SUN4I_PS2) += sun4i-ps2.o +obj-$(CONFIG_USERIO) += userio.o diff --git a/drivers/input/serio/userio.c b/drivers/input/serio/userio.c new file mode 100644 index 000000000000..df1fd41860ac --- /dev/null +++ b/drivers/input/serio/userio.c @@ -0,0 +1,285 @@ +/* + * userio kernel serio device emulation module + * Copyright (C) 2015 Red Hat + * Copyright (C) 2015 Stephen Chandler Paul + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as published by + * the Free Software Foundation; either version 2 of the License, or (at + * your option) any later version. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser + * General Public License for more details. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define USERIO_NAME "userio" +#define USERIO_BUFSIZE 16 + +static struct miscdevice userio_misc; + +struct userio_device { + struct serio *serio; + struct mutex mutex; + + bool running; + + u8 head; + u8 tail; + + spinlock_t buf_lock; + unsigned char buf[USERIO_BUFSIZE]; + + wait_queue_head_t waitq; +}; + +/** + * userio_device_write - Write data from serio to a userio device in userspace + * @id: The serio port for the userio device + * @val: The data to write to the device + */ +static int userio_device_write(struct serio *id, unsigned char val) +{ + struct userio_device *userio = id->port_data; + unsigned long flags; + + spin_lock_irqsave(&userio->buf_lock, flags); + + userio->buf[userio->head] = val; + userio->head = (userio->head + 1) % USERIO_BUFSIZE; + + if (userio->head == userio->tail) + dev_warn(userio_misc.this_device, + "Buffer overflowed, userio client isn't keeping up"); + + spin_unlock_irqrestore(&userio->buf_lock, flags); + + wake_up_interruptible(&userio->waitq); + + return 0; +} + +static int userio_char_open(struct inode *inode, struct file *file) +{ + struct userio_device *userio; + + userio = kzalloc(sizeof(struct userio_device), GFP_KERNEL); + if (!userio) + return -ENOMEM; + + mutex_init(&userio->mutex); + spin_lock_init(&userio->buf_lock); + init_waitqueue_head(&userio->waitq); + + userio->serio = kzalloc(sizeof(struct serio), GFP_KERNEL); + if (!userio->serio) { + kfree(userio); + return -ENOMEM; + } + + userio->serio->write = userio_device_write; + userio->serio->port_data = userio; + + file->private_data = userio; + + return 0; +} + +static int userio_char_release(struct inode *inode, struct file *file) +{ + struct userio_device *userio = file->private_data; + + if (userio->running) { + /* + * Don't free the serio port here, serio_unregister_port() + * does it for us. + */ + serio_unregister_port(userio->serio); + } else { + kfree(userio->serio); + } + + kfree(userio); + + return 0; +} + +static ssize_t userio_char_read(struct file *file, char __user *user_buffer, + size_t count, loff_t *ppos) +{ + struct userio_device *userio = file->private_data; + int error; + size_t nonwrap_len, copylen; + unsigned char buf[USERIO_BUFSIZE]; + unsigned long flags; + + /* + * By the time we get here, the data that was waiting might have + * been taken by another thread. Grab the buffer lock and check if + * there's still any data waiting, otherwise repeat this process + * until we have data (unless the file descriptor is non-blocking + * of course). + */ + for (;;) { + spin_lock_irqsave(&userio->buf_lock, flags); + + nonwrap_len = CIRC_CNT_TO_END(userio->head, + userio->tail, + USERIO_BUFSIZE); + copylen = min(nonwrap_len, count); + if (copylen) { + memcpy(buf, &userio->buf[userio->tail], copylen); + userio->tail = (userio->tail + copylen) % + USERIO_BUFSIZE; + } + + spin_unlock_irqrestore(&userio->buf_lock, flags); + + if (nonwrap_len) + break; + + /* buffer was/is empty */ + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + + /* + * count == 0 is special - no IO is done but we check + * for error conditions (see above). + */ + if (count == 0) + return 0; + + error = wait_event_interruptible(userio->waitq, + userio->head != userio->tail); + if (error) + return error; + } + + if (copylen) + if (copy_to_user(user_buffer, buf, copylen)) + return -EFAULT; + + return copylen; +} + +static ssize_t userio_char_write(struct file *file, const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct userio_device *userio = file->private_data; + struct userio_cmd cmd; + int error; + + if (count != sizeof(cmd)) { + dev_warn(userio_misc.this_device, "Invalid payload size\n"); + return -EINVAL; + } + + if (copy_from_user(&cmd, buffer, sizeof(cmd))) + return -EFAULT; + + error = mutex_lock_interruptible(&userio->mutex); + if (error) + return error; + + switch (cmd.type) { + case USERIO_CMD_REGISTER: + if (!userio->serio->id.type) { + dev_warn(userio_misc.this_device, + "No port type given on /dev/userio\n"); + + error = -EINVAL; + goto out; + } + + if (userio->running) { + dev_warn(userio_misc.this_device, + "Begin command sent, but we're already running\n"); + error = -EBUSY; + goto out; + } + + userio->running = true; + serio_register_port(userio->serio); + break; + + case USERIO_CMD_SET_PORT_TYPE: + if (userio->running) { + dev_warn(userio_misc.this_device, + "Can't change port type on an already running userio instance\n"); + error = -EBUSY; + goto out; + } + + userio->serio->id.type = cmd.data; + break; + + case USERIO_CMD_SEND_INTERRUPT: + if (!userio->running) { + dev_warn(userio_misc.this_device, + "The device must be registered before sending interrupts\n"); + error = -ENODEV; + goto out; + } + + serio_interrupt(userio->serio, cmd.data, 0); + break; + + default: + error = -EOPNOTSUPP; + goto out; + } + +out: + mutex_unlock(&userio->mutex); + return error ?: count; +} + +static unsigned int userio_char_poll(struct file *file, poll_table *wait) +{ + struct userio_device *userio = file->private_data; + + poll_wait(file, &userio->waitq, wait); + + if (userio->head != userio->tail) + return POLLIN | POLLRDNORM; + + return 0; +} + +static const struct file_operations userio_fops = { + .owner = THIS_MODULE, + .open = userio_char_open, + .release = userio_char_release, + .read = userio_char_read, + .write = userio_char_write, + .poll = userio_char_poll, + .llseek = no_llseek, +}; + +static struct miscdevice userio_misc = { + .fops = &userio_fops, + .minor = USERIO_MINOR, + .name = USERIO_NAME, +}; +module_driver(userio_misc, misc_register, misc_deregister); + +MODULE_ALIAS_MISCDEV(USERIO_MINOR); +MODULE_ALIAS("devname:" USERIO_NAME); + +MODULE_AUTHOR("Stephen Chandler Paul "); +MODULE_DESCRIPTION("Virtual Serio Device Support"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 81f6e427ba6b..543037465973 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -49,6 +49,7 @@ #define LOOP_CTRL_MINOR 237 #define VHOST_NET_MINOR 238 #define UHID_MINOR 239 +#define USERIO_MINOR 240 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/uapi/linux/userio.h b/include/uapi/linux/userio.h new file mode 100644 index 000000000000..37d147f0a13a --- /dev/null +++ b/include/uapi/linux/userio.h @@ -0,0 +1,44 @@ +/* + * userio: virtual serio device support + * Copyright (C) 2015 Red Hat + * Copyright (C) 2015 Lyude (Stephen Chandler Paul) + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU Lesser General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS + * FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public License for more + * details. + * + * This is the public header used for user-space communication with the userio + * driver. __attribute__((__packed__)) is used for all structs to keep ABI + * compatibility between all architectures. + */ + +#ifndef _USERIO_H +#define _USERIO_H + +#include + +enum userio_cmd_type { + USERIO_CMD_REGISTER = 0, + USERIO_CMD_SET_PORT_TYPE = 1, + USERIO_CMD_SEND_INTERRUPT = 2 +}; + +/* + * userio Commands + * All commands sent to /dev/userio are encoded using this structure. The type + * field should contain a USERIO_CMD* value that indicates what kind of command + * is being sent to userio. The data field should contain the accompanying + * argument for the command, if there is one. + */ +struct userio_cmd { + __u8 type; + __u8 data; +} __attribute__((__packed__)); + +#endif /* !_USERIO_H */ -- cgit v1.2.3 From f8e529ed941ba2bbcbf310b575d968159ce7e895 Mon Sep 17 00:00:00 2001 From: Tycho Andersen Date: Tue, 27 Oct 2015 09:23:59 +0900 Subject: seccomp, ptrace: add support for dumping seccomp filters This patch adds support for dumping a process' (classic BPF) seccomp filters via ptrace. PTRACE_SECCOMP_GET_FILTER allows the tracer to dump the user's classic BPF seccomp filters. addr should be an integer which represents the ith seccomp filter (0 is the most recently installed filter). data should be a struct sock_filter * with enough room for the ith filter, or NULL, in which case the filter is not saved. The return value for this command is the number of BPF instructions the program represents, or negative in the case of errors. Command specific errors are ENOENT: which indicates that there is no ith filter in this seccomp tree, and EMEDIUMTYPE, which indicates that the ith filter was not installed as a classic BPF filter. A caveat with this approach is that there is no way to get explicitly at the heirarchy of seccomp filters, and users need to memcmp() filters to decide which are inherited. This means that a task which installs two of the same filter can potentially confuse users of this interface. v2: * make save_orig const * check that the orig_prog exists (not necessary right now, but when grows eBPF support it will be) * s/n/filter_off and make it an unsigned long to match ptrace * count "down" the tree instead of "up" when passing a filter offset v3: * don't take the current task's lock for inspecting its seccomp mode * use a 0x42** constant for the ptrace command value v4: * don't copy to userspace while holding spinlocks v5: * add another condition to WARN_ON v6: * rebase on net-next Signed-off-by: Tycho Andersen Acked-by: Kees Cook CC: Will Drewry Reviewed-by: Oleg Nesterov CC: Andy Lutomirski CC: Pavel Emelyanov CC: Serge E. Hallyn CC: Alexei Starovoitov CC: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/seccomp.h | 11 +++++++ include/uapi/linux/ptrace.h | 2 ++ kernel/ptrace.c | 5 +++ kernel/seccomp.c | 76 ++++++++++++++++++++++++++++++++++++++++++++- 4 files changed, 93 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h index f4265039a94c..2296e6b2f690 100644 --- a/include/linux/seccomp.h +++ b/include/linux/seccomp.h @@ -95,4 +95,15 @@ static inline void get_seccomp_filter(struct task_struct *tsk) return; } #endif /* CONFIG_SECCOMP_FILTER */ + +#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) +extern long seccomp_get_filter(struct task_struct *task, + unsigned long filter_off, void __user *data); +#else +static inline long seccomp_get_filter(struct task_struct *task, + unsigned long n, void __user *data) +{ + return -EINVAL; +} +#endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */ #endif /* _LINUX_SECCOMP_H */ diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h index a7a697986614..fb8106509000 100644 --- a/include/uapi/linux/ptrace.h +++ b/include/uapi/linux/ptrace.h @@ -64,6 +64,8 @@ struct ptrace_peeksiginfo_args { #define PTRACE_GETSIGMASK 0x420a #define PTRACE_SETSIGMASK 0x420b +#define PTRACE_SECCOMP_GET_FILTER 0x420c + /* Read signals from a shared (process wide) queue */ #define PTRACE_PEEKSIGINFO_SHARED (1 << 0) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 787320de68e0..b760bae64cf1 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -1016,6 +1016,11 @@ int ptrace_request(struct task_struct *child, long request, break; } #endif + + case PTRACE_SECCOMP_GET_FILTER: + ret = seccomp_get_filter(child, addr, datavp); + break; + default: break; } diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 06858a74bb9c..580ac2d4024f 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -347,6 +347,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) { struct seccomp_filter *sfilter; int ret; + const bool save_orig = config_enabled(CONFIG_CHECKPOINT_RESTORE); if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return ERR_PTR(-EINVAL); @@ -370,7 +371,7 @@ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) return ERR_PTR(-ENOMEM); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, - seccomp_check_filter, false); + seccomp_check_filter, save_orig); if (ret < 0) { kfree(sfilter); return ERR_PTR(ret); @@ -867,3 +868,76 @@ long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter) /* prctl interface doesn't have flags, so they are always zero. */ return do_seccomp(op, 0, uargs); } + +#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE) +long seccomp_get_filter(struct task_struct *task, unsigned long filter_off, + void __user *data) +{ + struct seccomp_filter *filter; + struct sock_fprog_kern *fprog; + long ret; + unsigned long count = 0; + + if (!capable(CAP_SYS_ADMIN) || + current->seccomp.mode != SECCOMP_MODE_DISABLED) { + return -EACCES; + } + + spin_lock_irq(&task->sighand->siglock); + if (task->seccomp.mode != SECCOMP_MODE_FILTER) { + ret = -EINVAL; + goto out; + } + + filter = task->seccomp.filter; + while (filter) { + filter = filter->prev; + count++; + } + + if (filter_off >= count) { + ret = -ENOENT; + goto out; + } + count -= filter_off; + + filter = task->seccomp.filter; + while (filter && count > 1) { + filter = filter->prev; + count--; + } + + if (WARN_ON(count != 1 || !filter)) { + /* The filter tree shouldn't shrink while we're using it. */ + ret = -ENOENT; + goto out; + } + + fprog = filter->prog->orig_prog; + if (!fprog) { + /* This must be a new non-cBPF filter, since we save every + * every cBPF filter's orig_prog above when + * CONFIG_CHECKPOINT_RESTORE is enabled. + */ + ret = -EMEDIUMTYPE; + goto out; + } + + ret = fprog->len; + if (!data) + goto out; + + get_seccomp_filter(task); + spin_unlock_irq(&task->sighand->siglock); + + if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog))) + ret = -EFAULT; + + put_seccomp_filter(task); + return ret; + +out: + spin_unlock_irq(&task->sighand->siglock); + return ret; +} +#endif -- cgit v1.2.3 From cd9e9808d18fe7107c306f6e71c8be7230ee42b4 Mon Sep 17 00:00:00 2001 From: Matias Bjørling Date: Wed, 28 Oct 2015 19:54:55 +0100 Subject: lightnvm: Support for Open-Channel SSDs MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Open-channel SSDs are devices that share responsibilities with the host in order to implement and maintain features that typical SSDs keep strictly in firmware. These include (i) the Flash Translation Layer (FTL), (ii) bad block management, and (iii) hardware units such as the flash controller, the interface controller, and large amounts of flash chips. In this way, Open-channels SSDs exposes direct access to their physical flash storage, while keeping a subset of the internal features of SSDs. LightNVM is a specification that gives support to Open-channel SSDs LightNVM allows the host to manage data placement, garbage collection, and parallelism. Device specific responsibilities such as bad block management, FTL extensions to support atomic IOs, or metadata persistence are still handled by the device. The implementation of LightNVM consists of two parts: core and (multiple) targets. The core implements functionality shared across targets. This is initialization, teardown and statistics. The targets implement the interface that exposes physical flash to user-space applications. Examples of such targets include key-value store, object-store, as well as traditional block devices, which can be application-specific. Contributions in this patch from: Javier Gonzalez Dongsheng Yang Jesper Madsen Signed-off-by: Matias Bjørling Signed-off-by: Jens Axboe --- Documentation/ioctl/ioctl-number.txt | 1 + MAINTAINERS | 8 + drivers/Kconfig | 2 + drivers/Makefile | 1 + drivers/lightnvm/Kconfig | 28 ++ drivers/lightnvm/Makefile | 5 + drivers/lightnvm/core.c | 826 +++++++++++++++++++++++++++++++++++ include/linux/lightnvm.h | 522 ++++++++++++++++++++++ include/uapi/linux/lightnvm.h | 130 ++++++ 9 files changed, 1523 insertions(+) create mode 100644 drivers/lightnvm/Kconfig create mode 100644 drivers/lightnvm/Makefile create mode 100644 drivers/lightnvm/core.c create mode 100644 include/linux/lightnvm.h create mode 100644 include/uapi/linux/lightnvm.h (limited to 'include/uapi') diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index df1b25eb8382..8a44d44cf901 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -149,6 +149,7 @@ Code Seq#(hex) Include File Comments 'K' all linux/kd.h 'L' 00-1F linux/loop.h conflict! 'L' 10-1F drivers/scsi/mpt2sas/mpt2sas_ctl.h conflict! +'L' 20-2F linux/lightnvm.h 'L' E0-FF linux/ppdd.h encrypted disk device driver 'M' all linux/soundcard.h conflict! diff --git a/MAINTAINERS b/MAINTAINERS index f1d5a59432fc..d8be12c57f84 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6243,6 +6243,14 @@ F: drivers/nvdimm/pmem.c F: include/linux/pmem.h F: arch/*/include/asm/pmem.h +LIGHTNVM PLATFORM SUPPORT +M: Matias Bjorling +W: http://github/OpenChannelSSD +S: Maintained +F: drivers/lightnvm/ +F: include/linux/lightnvm.h +F: include/uapi/linux/lightnvm.h + LINUX FOR IBM pSERIES (RS/6000) M: Paul Mackerras W: http://www.ibm.com/linux/ltc/projects/ppc diff --git a/drivers/Kconfig b/drivers/Kconfig index e69ec82ac80a..3a5ab4d5873d 100644 --- a/drivers/Kconfig +++ b/drivers/Kconfig @@ -44,6 +44,8 @@ source "drivers/net/Kconfig" source "drivers/isdn/Kconfig" +source "drivers/lightnvm/Kconfig" + # input before char - char/joystick depends on it. As does USB. source "drivers/input/Kconfig" diff --git a/drivers/Makefile b/drivers/Makefile index 42f9dd5f07c8..7f1b7c5a1cfd 100644 --- a/drivers/Makefile +++ b/drivers/Makefile @@ -70,6 +70,7 @@ obj-$(CONFIG_NUBUS) += nubus/ obj-y += macintosh/ obj-$(CONFIG_IDE) += ide/ obj-$(CONFIG_SCSI) += scsi/ +obj-$(CONFIG_NVM) += lightnvm/ obj-y += nvme/ obj-$(CONFIG_ATA) += ata/ obj-$(CONFIG_TARGET_CORE) += target/ diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig new file mode 100644 index 000000000000..d4f309f127cd --- /dev/null +++ b/drivers/lightnvm/Kconfig @@ -0,0 +1,28 @@ +# +# Open-Channel SSD NVM configuration +# + +menuconfig NVM + bool "Open-Channel SSD target support" + depends on BLOCK + help + Say Y here to get to enable Open-channel SSDs. + + Open-Channel SSDs implement a set of extension to SSDs, that + exposes direct access to the underlying non-volatile memory. + + If you say N, all options in this submenu will be skipped and disabled + only do this if you know what you are doing. + +if NVM + +config NVM_DEBUG + bool "Open-Channel SSD debugging support" + ---help--- + Exposes a debug management interface to create/remove targets at: + + /sys/module/lnvm/parameters/configure_debug + + It is required to create/remove targets without IOCTLs. + +endif # NVM diff --git a/drivers/lightnvm/Makefile b/drivers/lightnvm/Makefile new file mode 100644 index 000000000000..38185e990d5d --- /dev/null +++ b/drivers/lightnvm/Makefile @@ -0,0 +1,5 @@ +# +# Makefile for Open-Channel SSDs. +# + +obj-$(CONFIG_NVM) := core.o diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c new file mode 100644 index 000000000000..f659e605a406 --- /dev/null +++ b/drivers/lightnvm/core.c @@ -0,0 +1,826 @@ +/* + * Copyright (C) 2015 IT University of Copenhagen. All rights reserved. + * Initial release: Matias Bjorling + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, + * USA. + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static LIST_HEAD(nvm_targets); +static LIST_HEAD(nvm_mgrs); +static LIST_HEAD(nvm_devices); +static DECLARE_RWSEM(nvm_lock); + +static struct nvm_tgt_type *nvm_find_target_type(const char *name) +{ + struct nvm_tgt_type *tt; + + list_for_each_entry(tt, &nvm_targets, list) + if (!strcmp(name, tt->name)) + return tt; + + return NULL; +} + +int nvm_register_target(struct nvm_tgt_type *tt) +{ + int ret = 0; + + down_write(&nvm_lock); + if (nvm_find_target_type(tt->name)) + ret = -EEXIST; + else + list_add(&tt->list, &nvm_targets); + up_write(&nvm_lock); + + return ret; +} +EXPORT_SYMBOL(nvm_register_target); + +void nvm_unregister_target(struct nvm_tgt_type *tt) +{ + if (!tt) + return; + + down_write(&nvm_lock); + list_del(&tt->list); + up_write(&nvm_lock); +} +EXPORT_SYMBOL(nvm_unregister_target); + +void *nvm_dev_dma_alloc(struct nvm_dev *dev, gfp_t mem_flags, + dma_addr_t *dma_handler) +{ + return dev->ops->dev_dma_alloc(dev->q, dev->ppalist_pool, mem_flags, + dma_handler); +} +EXPORT_SYMBOL(nvm_dev_dma_alloc); + +void nvm_dev_dma_free(struct nvm_dev *dev, void *ppa_list, + dma_addr_t dma_handler) +{ + dev->ops->dev_dma_free(dev->ppalist_pool, ppa_list, dma_handler); +} +EXPORT_SYMBOL(nvm_dev_dma_free); + +static struct nvmm_type *nvm_find_mgr_type(const char *name) +{ + struct nvmm_type *mt; + + list_for_each_entry(mt, &nvm_mgrs, list) + if (!strcmp(name, mt->name)) + return mt; + + return NULL; +} + +int nvm_register_mgr(struct nvmm_type *mt) +{ + int ret = 0; + + down_write(&nvm_lock); + if (nvm_find_mgr_type(mt->name)) + ret = -EEXIST; + else + list_add(&mt->list, &nvm_mgrs); + up_write(&nvm_lock); + + return ret; +} +EXPORT_SYMBOL(nvm_register_mgr); + +void nvm_unregister_mgr(struct nvmm_type *mt) +{ + if (!mt) + return; + + down_write(&nvm_lock); + list_del(&mt->list); + up_write(&nvm_lock); +} +EXPORT_SYMBOL(nvm_unregister_mgr); + +static struct nvm_dev *nvm_find_nvm_dev(const char *name) +{ + struct nvm_dev *dev; + + list_for_each_entry(dev, &nvm_devices, devices) + if (!strcmp(name, dev->name)) + return dev; + + return NULL; +} + +struct nvm_block *nvm_get_blk(struct nvm_dev *dev, struct nvm_lun *lun, + unsigned long flags) +{ + return dev->mt->get_blk(dev, lun, flags); +} +EXPORT_SYMBOL(nvm_get_blk); + +/* Assumes that all valid pages have already been moved on release to bm */ +void nvm_put_blk(struct nvm_dev *dev, struct nvm_block *blk) +{ + return dev->mt->put_blk(dev, blk); +} +EXPORT_SYMBOL(nvm_put_blk); + +int nvm_submit_io(struct nvm_dev *dev, struct nvm_rq *rqd) +{ + return dev->mt->submit_io(dev, rqd); +} +EXPORT_SYMBOL(nvm_submit_io); + +int nvm_erase_blk(struct nvm_dev *dev, struct nvm_block *blk) +{ + return dev->mt->erase_blk(dev, blk, 0); +} +EXPORT_SYMBOL(nvm_erase_blk); + +static void nvm_core_free(struct nvm_dev *dev) +{ + kfree(dev); +} + +static int nvm_core_init(struct nvm_dev *dev) +{ + struct nvm_id *id = &dev->identity; + struct nvm_id_group *grp = &id->groups[0]; + + /* device values */ + dev->nr_chnls = grp->num_ch; + dev->luns_per_chnl = grp->num_lun; + dev->pgs_per_blk = grp->num_pg; + dev->blks_per_lun = grp->num_blk; + dev->nr_planes = grp->num_pln; + dev->sec_size = grp->csecs; + dev->oob_size = grp->sos; + dev->sec_per_pg = grp->fpg_sz / grp->csecs; + dev->addr_mode = id->ppat; + dev->addr_format = id->ppaf; + + dev->plane_mode = NVM_PLANE_SINGLE; + dev->max_rq_size = dev->ops->max_phys_sect * dev->sec_size; + + if (grp->mpos & 0x020202) + dev->plane_mode = NVM_PLANE_DOUBLE; + if (grp->mpos & 0x040404) + dev->plane_mode = NVM_PLANE_QUAD; + + /* calculated values */ + dev->sec_per_pl = dev->sec_per_pg * dev->nr_planes; + dev->sec_per_blk = dev->sec_per_pl * dev->pgs_per_blk; + dev->sec_per_lun = dev->sec_per_blk * dev->blks_per_lun; + dev->nr_luns = dev->luns_per_chnl * dev->nr_chnls; + + dev->total_blocks = dev->nr_planes * + dev->blks_per_lun * + dev->luns_per_chnl * + dev->nr_chnls; + dev->total_pages = dev->total_blocks * dev->pgs_per_blk; + INIT_LIST_HEAD(&dev->online_targets); + + return 0; +} + +static void nvm_free(struct nvm_dev *dev) +{ + if (!dev) + return; + + if (dev->mt) + dev->mt->unregister_mgr(dev); + + nvm_core_free(dev); +} + +static int nvm_init(struct nvm_dev *dev) +{ + struct nvmm_type *mt; + int ret = 0; + + if (!dev->q || !dev->ops) + return -EINVAL; + + if (dev->ops->identity(dev->q, &dev->identity)) { + pr_err("nvm: device could not be identified\n"); + ret = -EINVAL; + goto err; + } + + pr_debug("nvm: ver:%x nvm_vendor:%x groups:%u\n", + dev->identity.ver_id, dev->identity.vmnt, + dev->identity.cgrps); + + if (dev->identity.ver_id != 1) { + pr_err("nvm: device not supported by kernel."); + goto err; + } + + if (dev->identity.cgrps != 1) { + pr_err("nvm: only one group configuration supported."); + goto err; + } + + ret = nvm_core_init(dev); + if (ret) { + pr_err("nvm: could not initialize core structures.\n"); + goto err; + } + + /* register with device with a supported manager */ + list_for_each_entry(mt, &nvm_mgrs, list) { + ret = mt->register_mgr(dev); + if (ret < 0) + goto err; /* initialization failed */ + if (ret > 0) { + dev->mt = mt; + break; /* successfully initialized */ + } + } + + if (!ret) { + pr_info("nvm: no compatible manager found.\n"); + return 0; + } + + pr_info("nvm: registered %s [%u/%u/%u/%u/%u/%u]\n", + dev->name, dev->sec_per_pg, dev->nr_planes, + dev->pgs_per_blk, dev->blks_per_lun, dev->nr_luns, + dev->nr_chnls); + return 0; +err: + nvm_free(dev); + pr_err("nvm: failed to initialize nvm\n"); + return ret; +} + +static void nvm_exit(struct nvm_dev *dev) +{ + if (dev->ppalist_pool) + dev->ops->destroy_dma_pool(dev->ppalist_pool); + nvm_free(dev); + + pr_info("nvm: successfully unloaded\n"); +} + +int nvm_register(struct request_queue *q, char *disk_name, + struct nvm_dev_ops *ops) +{ + struct nvm_dev *dev; + int ret; + + if (!ops->identity) + return -EINVAL; + + dev = kzalloc(sizeof(struct nvm_dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + dev->q = q; + dev->ops = ops; + strncpy(dev->name, disk_name, DISK_NAME_LEN); + + ret = nvm_init(dev); + if (ret) + goto err_init; + + down_write(&nvm_lock); + list_add(&dev->devices, &nvm_devices); + up_write(&nvm_lock); + + if (dev->ops->max_phys_sect > 1) { + dev->ppalist_pool = dev->ops->create_dma_pool(dev->q, + "ppalist"); + if (!dev->ppalist_pool) { + pr_err("nvm: could not create ppa pool\n"); + return -ENOMEM; + } + } else if (dev->ops->max_phys_sect > 256) { + pr_info("nvm: max sectors supported is 256.\n"); + return -EINVAL; + } + + return 0; +err_init: + kfree(dev); + return ret; +} +EXPORT_SYMBOL(nvm_register); + +void nvm_unregister(char *disk_name) +{ + struct nvm_dev *dev = nvm_find_nvm_dev(disk_name); + + if (!dev) { + pr_err("nvm: could not find device %s to unregister\n", + disk_name); + return; + } + + nvm_exit(dev); + + down_write(&nvm_lock); + list_del(&dev->devices); + up_write(&nvm_lock); +} +EXPORT_SYMBOL(nvm_unregister); + +static const struct block_device_operations nvm_fops = { + .owner = THIS_MODULE, +}; + +static int nvm_create_target(struct nvm_dev *dev, + struct nvm_ioctl_create *create) +{ + struct nvm_ioctl_create_simple *s = &create->conf.s; + struct request_queue *tqueue; + struct nvmm_type *mt; + struct gendisk *tdisk; + struct nvm_tgt_type *tt; + struct nvm_target *t; + void *targetdata; + int ret = 0; + + if (!dev->mt) { + /* register with device with a supported NVM manager */ + list_for_each_entry(mt, &nvm_mgrs, list) { + ret = mt->register_mgr(dev); + if (ret < 0) + return ret; /* initialization failed */ + if (ret > 0) { + dev->mt = mt; + break; /* successfully initialized */ + } + } + + if (!ret) { + pr_info("nvm: no compatible nvm manager found.\n"); + return -ENODEV; + } + } + + tt = nvm_find_target_type(create->tgttype); + if (!tt) { + pr_err("nvm: target type %s not found\n", create->tgttype); + return -EINVAL; + } + + down_write(&nvm_lock); + list_for_each_entry(t, &dev->online_targets, list) { + if (!strcmp(create->tgtname, t->disk->disk_name)) { + pr_err("nvm: target name already exists.\n"); + up_write(&nvm_lock); + return -EINVAL; + } + } + up_write(&nvm_lock); + + t = kmalloc(sizeof(struct nvm_target), GFP_KERNEL); + if (!t) + return -ENOMEM; + + tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node); + if (!tqueue) + goto err_t; + blk_queue_make_request(tqueue, tt->make_rq); + + tdisk = alloc_disk(0); + if (!tdisk) + goto err_queue; + + sprintf(tdisk->disk_name, "%s", create->tgtname); + tdisk->flags = GENHD_FL_EXT_DEVT; + tdisk->major = 0; + tdisk->first_minor = 0; + tdisk->fops = &nvm_fops; + tdisk->queue = tqueue; + + targetdata = tt->init(dev, tdisk, s->lun_begin, s->lun_end); + if (IS_ERR(targetdata)) + goto err_init; + + tdisk->private_data = targetdata; + tqueue->queuedata = targetdata; + + blk_queue_max_hw_sectors(tqueue, 8 * dev->ops->max_phys_sect); + + set_capacity(tdisk, tt->capacity(targetdata)); + add_disk(tdisk); + + t->type = tt; + t->disk = tdisk; + + down_write(&nvm_lock); + list_add_tail(&t->list, &dev->online_targets); + up_write(&nvm_lock); + + return 0; +err_init: + put_disk(tdisk); +err_queue: + blk_cleanup_queue(tqueue); +err_t: + kfree(t); + return -ENOMEM; +} + +static void nvm_remove_target(struct nvm_target *t) +{ + struct nvm_tgt_type *tt = t->type; + struct gendisk *tdisk = t->disk; + struct request_queue *q = tdisk->queue; + + lockdep_assert_held(&nvm_lock); + + del_gendisk(tdisk); + if (tt->exit) + tt->exit(tdisk->private_data); + + blk_cleanup_queue(q); + + put_disk(tdisk); + + list_del(&t->list); + kfree(t); +} + +static int __nvm_configure_create(struct nvm_ioctl_create *create) +{ + struct nvm_dev *dev; + struct nvm_ioctl_create_simple *s; + + dev = nvm_find_nvm_dev(create->dev); + if (!dev) { + pr_err("nvm: device not found\n"); + return -EINVAL; + } + + if (create->conf.type != NVM_CONFIG_TYPE_SIMPLE) { + pr_err("nvm: config type not valid\n"); + return -EINVAL; + } + s = &create->conf.s; + + if (s->lun_begin > s->lun_end || s->lun_end > dev->nr_luns) { + pr_err("nvm: lun out of bound (%u:%u > %u)\n", + s->lun_begin, s->lun_end, dev->nr_luns); + return -EINVAL; + } + + return nvm_create_target(dev, create); +} + +static int __nvm_configure_remove(struct nvm_ioctl_remove *remove) +{ + struct nvm_target *t = NULL; + struct nvm_dev *dev; + int ret = -1; + + down_write(&nvm_lock); + list_for_each_entry(dev, &nvm_devices, devices) + list_for_each_entry(t, &dev->online_targets, list) { + if (!strcmp(remove->tgtname, t->disk->disk_name)) { + nvm_remove_target(t); + ret = 0; + break; + } + } + up_write(&nvm_lock); + + if (ret) { + pr_err("nvm: target \"%s\" doesn't exist.\n", remove->tgtname); + return -EINVAL; + } + + return 0; +} + +#ifdef CONFIG_NVM_DEBUG +static int nvm_configure_show(const char *val) +{ + struct nvm_dev *dev; + char opcode, devname[DISK_NAME_LEN]; + int ret; + + ret = sscanf(val, "%c %32s", &opcode, devname); + if (ret != 2) { + pr_err("nvm: invalid command. Use \"opcode devicename\".\n"); + return -EINVAL; + } + + dev = nvm_find_nvm_dev(devname); + if (!dev) { + pr_err("nvm: device not found\n"); + return -EINVAL; + } + + if (!dev->mt) + return 0; + + dev->mt->free_blocks_print(dev); + + return 0; +} + +static int nvm_configure_remove(const char *val) +{ + struct nvm_ioctl_remove remove; + char opcode; + int ret; + + ret = sscanf(val, "%c %256s", &opcode, remove.tgtname); + if (ret != 2) { + pr_err("nvm: invalid command. Use \"d targetname\".\n"); + return -EINVAL; + } + + remove.flags = 0; + + return __nvm_configure_remove(&remove); +} + +static int nvm_configure_create(const char *val) +{ + struct nvm_ioctl_create create; + char opcode; + int lun_begin, lun_end, ret; + + ret = sscanf(val, "%c %256s %256s %48s %u:%u", &opcode, create.dev, + create.tgtname, create.tgttype, + &lun_begin, &lun_end); + if (ret != 6) { + pr_err("nvm: invalid command. Use \"opcode device name tgttype lun_begin:lun_end\".\n"); + return -EINVAL; + } + + create.flags = 0; + create.conf.type = NVM_CONFIG_TYPE_SIMPLE; + create.conf.s.lun_begin = lun_begin; + create.conf.s.lun_end = lun_end; + + return __nvm_configure_create(&create); +} + + +/* Exposes administrative interface through /sys/module/lnvm/configure_by_str */ +static int nvm_configure_by_str_event(const char *val, + const struct kernel_param *kp) +{ + char opcode; + int ret; + + ret = sscanf(val, "%c", &opcode); + if (ret != 1) { + pr_err("nvm: string must have the format of \"cmd ...\"\n"); + return -EINVAL; + } + + switch (opcode) { + case 'a': + return nvm_configure_create(val); + case 'd': + return nvm_configure_remove(val); + case 's': + return nvm_configure_show(val); + default: + pr_err("nvm: invalid command\n"); + return -EINVAL; + } + + return 0; +} + +static int nvm_configure_get(char *buf, const struct kernel_param *kp) +{ + int sz = 0; + char *buf_start = buf; + struct nvm_dev *dev; + + buf += sprintf(buf, "available devices:\n"); + down_write(&nvm_lock); + list_for_each_entry(dev, &nvm_devices, devices) { + if (sz > 4095 - DISK_NAME_LEN) + break; + buf += sprintf(buf, " %32s\n", dev->name); + } + up_write(&nvm_lock); + + return buf - buf_start - 1; +} + +static const struct kernel_param_ops nvm_configure_by_str_event_param_ops = { + .set = nvm_configure_by_str_event, + .get = nvm_configure_get, +}; + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "lnvm." + +module_param_cb(configure_debug, &nvm_configure_by_str_event_param_ops, NULL, + 0644); + +#endif /* CONFIG_NVM_DEBUG */ + +static long nvm_ioctl_info(struct file *file, void __user *arg) +{ + struct nvm_ioctl_info *info; + struct nvm_tgt_type *tt; + int tgt_iter = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + info = memdup_user(arg, sizeof(struct nvm_ioctl_info)); + if (IS_ERR(info)) + return -EFAULT; + + info->version[0] = NVM_VERSION_MAJOR; + info->version[1] = NVM_VERSION_MINOR; + info->version[2] = NVM_VERSION_PATCH; + + down_write(&nvm_lock); + list_for_each_entry(tt, &nvm_targets, list) { + struct nvm_ioctl_info_tgt *tgt = &info->tgts[tgt_iter]; + + tgt->version[0] = tt->version[0]; + tgt->version[1] = tt->version[1]; + tgt->version[2] = tt->version[2]; + strncpy(tgt->tgtname, tt->name, NVM_TTYPE_NAME_MAX); + + tgt_iter++; + } + + info->tgtsize = tgt_iter; + up_write(&nvm_lock); + + if (copy_to_user(arg, info, sizeof(struct nvm_ioctl_info))) + return -EFAULT; + + kfree(info); + return 0; +} + +static long nvm_ioctl_get_devices(struct file *file, void __user *arg) +{ + struct nvm_ioctl_get_devices *devices; + struct nvm_dev *dev; + int i = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + devices = kzalloc(sizeof(struct nvm_ioctl_get_devices), GFP_KERNEL); + if (!devices) + return -ENOMEM; + + down_write(&nvm_lock); + list_for_each_entry(dev, &nvm_devices, devices) { + struct nvm_ioctl_device_info *info = &devices->info[i]; + + sprintf(info->devname, "%s", dev->name); + if (dev->mt) { + info->bmversion[0] = dev->mt->version[0]; + info->bmversion[1] = dev->mt->version[1]; + info->bmversion[2] = dev->mt->version[2]; + sprintf(info->bmname, "%s", dev->mt->name); + } else { + sprintf(info->bmname, "none"); + } + + i++; + if (i > 31) { + pr_err("nvm: max 31 devices can be reported.\n"); + break; + } + } + up_write(&nvm_lock); + + devices->nr_devices = i; + + if (copy_to_user(arg, devices, sizeof(struct nvm_ioctl_get_devices))) + return -EFAULT; + + kfree(devices); + return 0; +} + +static long nvm_ioctl_dev_create(struct file *file, void __user *arg) +{ + struct nvm_ioctl_create create; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&create, arg, sizeof(struct nvm_ioctl_create))) + return -EFAULT; + + create.dev[DISK_NAME_LEN - 1] = '\0'; + create.tgttype[NVM_TTYPE_NAME_MAX - 1] = '\0'; + create.tgtname[DISK_NAME_LEN - 1] = '\0'; + + if (create.flags != 0) { + pr_err("nvm: no flags supported\n"); + return -EINVAL; + } + + return __nvm_configure_create(&create); +} + +static long nvm_ioctl_dev_remove(struct file *file, void __user *arg) +{ + struct nvm_ioctl_remove remove; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + if (copy_from_user(&remove, arg, sizeof(struct nvm_ioctl_remove))) + return -EFAULT; + + remove.tgtname[DISK_NAME_LEN - 1] = '\0'; + + if (remove.flags != 0) { + pr_err("nvm: no flags supported\n"); + return -EINVAL; + } + + return __nvm_configure_remove(&remove); +} + +static long nvm_ctl_ioctl(struct file *file, uint cmd, unsigned long arg) +{ + void __user *argp = (void __user *)arg; + + switch (cmd) { + case NVM_INFO: + return nvm_ioctl_info(file, argp); + case NVM_GET_DEVICES: + return nvm_ioctl_get_devices(file, argp); + case NVM_DEV_CREATE: + return nvm_ioctl_dev_create(file, argp); + case NVM_DEV_REMOVE: + return nvm_ioctl_dev_remove(file, argp); + } + return 0; +} + +static const struct file_operations _ctl_fops = { + .open = nonseekable_open, + .unlocked_ioctl = nvm_ctl_ioctl, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice _nvm_misc = { + .minor = MISC_DYNAMIC_MINOR, + .name = "lightnvm", + .nodename = "lightnvm/control", + .fops = &_ctl_fops, +}; + +MODULE_ALIAS_MISCDEV(MISC_DYNAMIC_MINOR); + +static int __init nvm_mod_init(void) +{ + int ret; + + ret = misc_register(&_nvm_misc); + if (ret) + pr_err("nvm: misc_register failed for control device"); + + return ret; +} + +static void __exit nvm_mod_exit(void) +{ + misc_deregister(&_nvm_misc); +} + +MODULE_AUTHOR("Matias Bjorling "); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION("0.1"); +module_init(nvm_mod_init); +module_exit(nvm_mod_exit); diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h new file mode 100644 index 000000000000..122b176600fa --- /dev/null +++ b/include/linux/lightnvm.h @@ -0,0 +1,522 @@ +#ifndef NVM_H +#define NVM_H + +enum { + NVM_IO_OK = 0, + NVM_IO_REQUEUE = 1, + NVM_IO_DONE = 2, + NVM_IO_ERR = 3, + + NVM_IOTYPE_NONE = 0, + NVM_IOTYPE_GC = 1, +}; + +#ifdef CONFIG_NVM + +#include +#include +#include +#include + +enum { + /* HW Responsibilities */ + NVM_RSP_L2P = 1 << 0, + NVM_RSP_ECC = 1 << 1, + + /* Physical Adressing Mode */ + NVM_ADDRMODE_LINEAR = 0, + NVM_ADDRMODE_CHANNEL = 1, + + /* Plane programming mode for LUN */ + NVM_PLANE_SINGLE = 0, + NVM_PLANE_DOUBLE = 1, + NVM_PLANE_QUAD = 2, + + /* Status codes */ + NVM_RSP_SUCCESS = 0x0, + NVM_RSP_NOT_CHANGEABLE = 0x1, + NVM_RSP_ERR_FAILWRITE = 0x40ff, + NVM_RSP_ERR_EMPTYPAGE = 0x42ff, + + /* Device opcodes */ + NVM_OP_HBREAD = 0x02, + NVM_OP_HBWRITE = 0x81, + NVM_OP_PWRITE = 0x91, + NVM_OP_PREAD = 0x92, + NVM_OP_ERASE = 0x90, + + /* PPA Command Flags */ + NVM_IO_SNGL_ACCESS = 0x0, + NVM_IO_DUAL_ACCESS = 0x1, + NVM_IO_QUAD_ACCESS = 0x2, + + NVM_IO_SUSPEND = 0x80, + NVM_IO_SLC_MODE = 0x100, + NVM_IO_SCRAMBLE_DISABLE = 0x200, +}; + +struct nvm_id_group { + u8 mtype; + u8 fmtype; + u16 res16; + u8 num_ch; + u8 num_lun; + u8 num_pln; + u16 num_blk; + u16 num_pg; + u16 fpg_sz; + u16 csecs; + u16 sos; + u32 trdt; + u32 trdm; + u32 tprt; + u32 tprm; + u32 tbet; + u32 tbem; + u32 mpos; + u16 cpar; + u8 res[913]; +} __packed; + +struct nvm_addr_format { + u8 ch_offset; + u8 ch_len; + u8 lun_offset; + u8 lun_len; + u8 pln_offset; + u8 pln_len; + u8 blk_offset; + u8 blk_len; + u8 pg_offset; + u8 pg_len; + u8 sect_offset; + u8 sect_len; + u8 res[4]; +}; + +struct nvm_id { + u8 ver_id; + u8 vmnt; + u8 cgrps; + u8 res[5]; + u32 cap; + u32 dom; + struct nvm_addr_format ppaf; + u8 ppat; + u8 resv[224]; + struct nvm_id_group groups[4]; +} __packed; + +struct nvm_target { + struct list_head list; + struct nvm_tgt_type *type; + struct gendisk *disk; +}; + +struct nvm_tgt_instance { + struct nvm_tgt_type *tt; +}; + +#define ADDR_EMPTY (~0ULL) + +#define NVM_VERSION_MAJOR 1 +#define NVM_VERSION_MINOR 0 +#define NVM_VERSION_PATCH 0 + +#define NVM_SEC_BITS (8) +#define NVM_PL_BITS (6) +#define NVM_PG_BITS (16) +#define NVM_BLK_BITS (16) +#define NVM_LUN_BITS (10) +#define NVM_CH_BITS (8) + +struct ppa_addr { + union { + /* Channel-based PPA format in nand 4x2x2x2x8x10 */ + struct { + sector_t ch : 4; + sector_t sec : 2; /* 4 sectors per page */ + sector_t pl : 2; /* 4 planes per LUN */ + sector_t lun : 2; /* 4 LUNs per channel */ + sector_t pg : 8; /* 256 pages per block */ + sector_t blk : 10;/* 1024 blocks per plane */ + sector_t resved : 36; + } chnl; + + /* Generic structure for all addresses */ + struct { + sector_t sec : NVM_SEC_BITS; + sector_t pl : NVM_PL_BITS; + sector_t pg : NVM_PG_BITS; + sector_t blk : NVM_BLK_BITS; + sector_t lun : NVM_LUN_BITS; + sector_t ch : NVM_CH_BITS; + } g; + + sector_t ppa; + }; +} __packed; + +struct nvm_rq { + struct nvm_tgt_instance *ins; + struct nvm_dev *dev; + + struct bio *bio; + + union { + struct ppa_addr ppa_addr; + dma_addr_t dma_ppa_list; + }; + + struct ppa_addr *ppa_list; + + void *metadata; + dma_addr_t dma_metadata; + + uint8_t opcode; + uint16_t nr_pages; + uint16_t flags; +}; + +static inline struct nvm_rq *nvm_rq_from_pdu(void *pdu) +{ + return pdu - sizeof(struct nvm_rq); +} + +static inline void *nvm_rq_to_pdu(struct nvm_rq *rqdata) +{ + return rqdata + 1; +} + +struct nvm_block; + +typedef int (nvm_l2p_update_fn)(u64, u32, __le64 *, void *); +typedef int (nvm_bb_update_fn)(u32, void *, unsigned int, void *); +typedef int (nvm_id_fn)(struct request_queue *, struct nvm_id *); +typedef int (nvm_get_l2p_tbl_fn)(struct request_queue *, u64, u32, + nvm_l2p_update_fn *, void *); +typedef int (nvm_op_bb_tbl_fn)(struct request_queue *, int, unsigned int, + nvm_bb_update_fn *, void *); +typedef int (nvm_op_set_bb_fn)(struct request_queue *, struct nvm_rq *, int); +typedef int (nvm_submit_io_fn)(struct request_queue *, struct nvm_rq *); +typedef int (nvm_erase_blk_fn)(struct request_queue *, struct nvm_rq *); +typedef void *(nvm_create_dma_pool_fn)(struct request_queue *, char *); +typedef void (nvm_destroy_dma_pool_fn)(void *); +typedef void *(nvm_dev_dma_alloc_fn)(struct request_queue *, void *, gfp_t, + dma_addr_t *); +typedef void (nvm_dev_dma_free_fn)(void *, void*, dma_addr_t); + +struct nvm_dev_ops { + nvm_id_fn *identity; + nvm_get_l2p_tbl_fn *get_l2p_tbl; + nvm_op_bb_tbl_fn *get_bb_tbl; + nvm_op_set_bb_fn *set_bb; + + nvm_submit_io_fn *submit_io; + nvm_erase_blk_fn *erase_block; + + nvm_create_dma_pool_fn *create_dma_pool; + nvm_destroy_dma_pool_fn *destroy_dma_pool; + nvm_dev_dma_alloc_fn *dev_dma_alloc; + nvm_dev_dma_free_fn *dev_dma_free; + + uint8_t max_phys_sect; +}; + +struct nvm_lun { + int id; + + int lun_id; + int chnl_id; + + unsigned int nr_free_blocks; /* Number of unused blocks */ + struct nvm_block *blocks; + + spinlock_t lock; +}; + +struct nvm_block { + struct list_head list; + struct nvm_lun *lun; + unsigned long id; + + void *priv; + int type; +}; + +struct nvm_dev { + struct nvm_dev_ops *ops; + + struct list_head devices; + struct list_head online_targets; + + /* Media manager */ + struct nvmm_type *mt; + void *mp; + + /* Device information */ + int nr_chnls; + int nr_planes; + int luns_per_chnl; + int sec_per_pg; /* only sectors for a single page */ + int pgs_per_blk; + int blks_per_lun; + int sec_size; + int oob_size; + int addr_mode; + struct nvm_addr_format addr_format; + + /* Calculated/Cached values. These do not reflect the actual usable + * blocks at run-time. + */ + int max_rq_size; + int plane_mode; /* drive device in single, double or quad mode */ + + int sec_per_pl; /* all sectors across planes */ + int sec_per_blk; + int sec_per_lun; + + unsigned long total_pages; + unsigned long total_blocks; + int nr_luns; + unsigned max_pages_per_blk; + + void *ppalist_pool; + + struct nvm_id identity; + + /* Backend device */ + struct request_queue *q; + char name[DISK_NAME_LEN]; +}; + +/* fallback conversion */ +static struct ppa_addr __generic_to_linear_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + + l.ppa = r.g.sec + + r.g.pg * dev->sec_per_pg + + r.g.blk * (dev->pgs_per_blk * + dev->sec_per_pg) + + r.g.lun * (dev->blks_per_lun * + dev->pgs_per_blk * + dev->sec_per_pg) + + r.g.ch * (dev->blks_per_lun * + dev->pgs_per_blk * + dev->luns_per_chnl * + dev->sec_per_pg); + + return l; +} + +/* fallback conversion */ +static struct ppa_addr __linear_to_generic_addr(struct nvm_dev *dev, + struct ppa_addr r) +{ + struct ppa_addr l; + int secs, pgs, blks, luns; + sector_t ppa = r.ppa; + + l.ppa = 0; + + div_u64_rem(ppa, dev->sec_per_pg, &secs); + l.g.sec = secs; + + sector_div(ppa, dev->sec_per_pg); + div_u64_rem(ppa, dev->sec_per_blk, &pgs); + l.g.pg = pgs; + + sector_div(ppa, dev->pgs_per_blk); + div_u64_rem(ppa, dev->blks_per_lun, &blks); + l.g.blk = blks; + + sector_div(ppa, dev->blks_per_lun); + div_u64_rem(ppa, dev->luns_per_chnl, &luns); + l.g.lun = luns; + + sector_div(ppa, dev->luns_per_chnl); + l.g.ch = ppa; + + return l; +} + +static struct ppa_addr __generic_to_chnl_addr(struct ppa_addr r) +{ + struct ppa_addr l; + + l.ppa = 0; + + l.chnl.sec = r.g.sec; + l.chnl.pl = r.g.pl; + l.chnl.pg = r.g.pg; + l.chnl.blk = r.g.blk; + l.chnl.lun = r.g.lun; + l.chnl.ch = r.g.ch; + + return l; +} + +static struct ppa_addr __chnl_to_generic_addr(struct ppa_addr r) +{ + struct ppa_addr l; + + l.ppa = 0; + + l.g.sec = r.chnl.sec; + l.g.pl = r.chnl.pl; + l.g.pg = r.chnl.pg; + l.g.blk = r.chnl.blk; + l.g.lun = r.chnl.lun; + l.g.ch = r.chnl.ch; + + return l; +} + +static inline struct ppa_addr addr_to_generic_mode(struct nvm_dev *dev, + struct ppa_addr gppa) +{ + switch (dev->addr_mode) { + case NVM_ADDRMODE_LINEAR: + return __linear_to_generic_addr(dev, gppa); + case NVM_ADDRMODE_CHANNEL: + return __chnl_to_generic_addr(gppa); + default: + BUG(); + } + return gppa; +} + +static inline struct ppa_addr generic_to_addr_mode(struct nvm_dev *dev, + struct ppa_addr gppa) +{ + switch (dev->addr_mode) { + case NVM_ADDRMODE_LINEAR: + return __generic_to_linear_addr(dev, gppa); + case NVM_ADDRMODE_CHANNEL: + return __generic_to_chnl_addr(gppa); + default: + BUG(); + } + return gppa; +} + +static inline int ppa_empty(struct ppa_addr ppa_addr) +{ + return (ppa_addr.ppa == ADDR_EMPTY); +} + +static inline void ppa_set_empty(struct ppa_addr *ppa_addr) +{ + ppa_addr->ppa = ADDR_EMPTY; +} + +static inline struct ppa_addr block_to_ppa(struct nvm_dev *dev, + struct nvm_block *blk) +{ + struct ppa_addr ppa; + struct nvm_lun *lun = blk->lun; + + ppa.ppa = 0; + ppa.g.blk = blk->id % dev->blks_per_lun; + ppa.g.lun = lun->lun_id; + ppa.g.ch = lun->chnl_id; + + return ppa; +} + +typedef void (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); +typedef sector_t (nvm_tgt_capacity_fn)(void *); +typedef int (nvm_tgt_end_io_fn)(struct nvm_rq *, int); +typedef void *(nvm_tgt_init_fn)(struct nvm_dev *, struct gendisk *, int, int); +typedef void (nvm_tgt_exit_fn)(void *); + +struct nvm_tgt_type { + const char *name; + unsigned int version[3]; + + /* target entry points */ + nvm_tgt_make_rq_fn *make_rq; + nvm_tgt_capacity_fn *capacity; + nvm_tgt_end_io_fn *end_io; + + /* module-specific init/teardown */ + nvm_tgt_init_fn *init; + nvm_tgt_exit_fn *exit; + + /* For internal use */ + struct list_head list; +}; + +extern int nvm_register_target(struct nvm_tgt_type *); +extern void nvm_unregister_target(struct nvm_tgt_type *); + +extern void *nvm_dev_dma_alloc(struct nvm_dev *, gfp_t, dma_addr_t *); +extern void nvm_dev_dma_free(struct nvm_dev *, void *, dma_addr_t); + +typedef int (nvmm_register_fn)(struct nvm_dev *); +typedef void (nvmm_unregister_fn)(struct nvm_dev *); +typedef struct nvm_block *(nvmm_get_blk_fn)(struct nvm_dev *, + struct nvm_lun *, unsigned long); +typedef void (nvmm_put_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_open_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_close_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef void (nvmm_flush_blk_fn)(struct nvm_dev *, struct nvm_block *); +typedef int (nvmm_submit_io_fn)(struct nvm_dev *, struct nvm_rq *); +typedef int (nvmm_end_io_fn)(struct nvm_rq *, int); +typedef int (nvmm_erase_blk_fn)(struct nvm_dev *, struct nvm_block *, + unsigned long); +typedef struct nvm_lun *(nvmm_get_lun_fn)(struct nvm_dev *, int); +typedef void (nvmm_free_blocks_print_fn)(struct nvm_dev *); + +struct nvmm_type { + const char *name; + unsigned int version[3]; + + nvmm_register_fn *register_mgr; + nvmm_unregister_fn *unregister_mgr; + + /* Block administration callbacks */ + nvmm_get_blk_fn *get_blk; + nvmm_put_blk_fn *put_blk; + nvmm_open_blk_fn *open_blk; + nvmm_close_blk_fn *close_blk; + nvmm_flush_blk_fn *flush_blk; + + nvmm_submit_io_fn *submit_io; + nvmm_end_io_fn *end_io; + nvmm_erase_blk_fn *erase_blk; + + /* Configuration management */ + nvmm_get_lun_fn *get_lun; + + /* Statistics */ + nvmm_free_blocks_print_fn *free_blocks_print; + struct list_head list; +}; + +extern int nvm_register_mgr(struct nvmm_type *); +extern void nvm_unregister_mgr(struct nvmm_type *); + +extern struct nvm_block *nvm_get_blk(struct nvm_dev *, struct nvm_lun *, + unsigned long); +extern void nvm_put_blk(struct nvm_dev *, struct nvm_block *); + +extern int nvm_register(struct request_queue *, char *, + struct nvm_dev_ops *); +extern void nvm_unregister(char *); + +extern int nvm_submit_io(struct nvm_dev *, struct nvm_rq *); +extern int nvm_erase_blk(struct nvm_dev *, struct nvm_block *); +#else /* CONFIG_NVM */ +struct nvm_dev_ops; + +static inline int nvm_register(struct request_queue *q, char *disk_name, + struct nvm_dev_ops *ops) +{ + return -EINVAL; +} +static inline void nvm_unregister(char *disk_name) {} +#endif /* CONFIG_NVM */ +#endif /* LIGHTNVM.H */ diff --git a/include/uapi/linux/lightnvm.h b/include/uapi/linux/lightnvm.h new file mode 100644 index 000000000000..928f98997d8a --- /dev/null +++ b/include/uapi/linux/lightnvm.h @@ -0,0 +1,130 @@ +/* + * Copyright (C) 2015 CNEX Labs. All rights reserved. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License version + * 2 as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; see the file COPYING. If not, write to + * the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, + * USA. + */ + +#ifndef _UAPI_LINUX_LIGHTNVM_H +#define _UAPI_LINUX_LIGHTNVM_H + +#ifdef __KERNEL__ +#include +#include +#else /* __KERNEL__ */ +#include +#include +#define DISK_NAME_LEN 32 +#endif /* __KERNEL__ */ + +#include +#include + +#define NVM_TTYPE_NAME_MAX 48 +#define NVM_TTYPE_MAX 63 + +#define NVM_CTRL_FILE "/dev/lightnvm/control" + +struct nvm_ioctl_info_tgt { + __u32 version[3]; + __u32 reserved; + char tgtname[NVM_TTYPE_NAME_MAX]; +}; + +struct nvm_ioctl_info { + __u32 version[3]; /* in/out - major, minor, patch */ + __u16 tgtsize; /* number of targets */ + __u16 reserved16; /* pad to 4K page */ + __u32 reserved[12]; + struct nvm_ioctl_info_tgt tgts[NVM_TTYPE_MAX]; +}; + +enum { + NVM_DEVICE_ACTIVE = 1 << 0, +}; + +struct nvm_ioctl_device_info { + char devname[DISK_NAME_LEN]; + char bmname[NVM_TTYPE_NAME_MAX]; + __u32 bmversion[3]; + __u32 flags; + __u32 reserved[8]; +}; + +struct nvm_ioctl_get_devices { + __u32 nr_devices; + __u32 reserved[31]; + struct nvm_ioctl_device_info info[31]; +}; + +struct nvm_ioctl_create_simple { + __u32 lun_begin; + __u32 lun_end; +}; + +enum { + NVM_CONFIG_TYPE_SIMPLE = 0, +}; + +struct nvm_ioctl_create_conf { + __u32 type; + union { + struct nvm_ioctl_create_simple s; + }; +}; + +struct nvm_ioctl_create { + char dev[DISK_NAME_LEN]; /* open-channel SSD device */ + char tgttype[NVM_TTYPE_NAME_MAX]; /* target type name */ + char tgtname[DISK_NAME_LEN]; /* dev to expose target as */ + + __u32 flags; + + struct nvm_ioctl_create_conf conf; +}; + +struct nvm_ioctl_remove { + char tgtname[DISK_NAME_LEN]; + + __u32 flags; +}; + + +/* The ioctl type, 'L', 0x20 - 0x2F documented in ioctl-number.txt */ +enum { + /* top level cmds */ + NVM_INFO_CMD = 0x20, + NVM_GET_DEVICES_CMD, + + /* device level cmds */ + NVM_DEV_CREATE_CMD, + NVM_DEV_REMOVE_CMD, +}; + +#define NVM_IOCTL 'L' /* 0x4c */ + +#define NVM_INFO _IOWR(NVM_IOCTL, NVM_INFO_CMD, \ + struct nvm_ioctl_info) +#define NVM_GET_DEVICES _IOR(NVM_IOCTL, NVM_GET_DEVICES_CMD, \ + struct nvm_ioctl_get_devices) +#define NVM_DEV_CREATE _IOW(NVM_IOCTL, NVM_DEV_CREATE_CMD, \ + struct nvm_ioctl_create) +#define NVM_DEV_REMOVE _IOW(NVM_IOCTL, NVM_DEV_REMOVE_CMD, \ + struct nvm_ioctl_remove) + +#define NVM_VERSION_MAJOR 1 +#define NVM_VERSION_MINOR 0 +#define NVM_VERSION_PATCHLEVEL 0 + +#endif -- cgit v1.2.3 From f80b0ba959641f13524507d60eae4d01ea65c991 Mon Sep 17 00:00:00 2001 From: "Sean O. Stalley" Date: Thu, 29 Oct 2015 17:35:39 -0500 Subject: PCI: Add Enhanced Allocation register entries Add registers defined in PCI-SIG's Enhanced allocation ECN. [bhelgaas: s/WRITEABLE/WRITABLE] Signed-off-by: Sean O. Stalley [david.daney@cavium.com: Added more definitions for PCI_EA_BEI_*] Signed-off-by: Signed-off-by: David Daney Signed-off-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 43 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 42 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 413417f3707b..f890876aa070 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -216,7 +216,8 @@ #define PCI_CAP_ID_MSIX 0x11 /* MSI-X */ #define PCI_CAP_ID_SATA 0x12 /* SATA Data/Index Conf. */ #define PCI_CAP_ID_AF 0x13 /* PCI Advanced Features */ -#define PCI_CAP_ID_MAX PCI_CAP_ID_AF +#define PCI_CAP_ID_EA 0x14 /* PCI Enhanced Allocation */ +#define PCI_CAP_ID_MAX PCI_CAP_ID_EA #define PCI_CAP_LIST_NEXT 1 /* Next capability in the list */ #define PCI_CAP_FLAGS 2 /* Capability defined flags (16 bits) */ #define PCI_CAP_SIZEOF 4 @@ -353,6 +354,46 @@ #define PCI_AF_STATUS_TP 0x01 #define PCI_CAP_AF_SIZEOF 6 /* size of AF registers */ +/* PCI Enhanced Allocation registers */ + +#define PCI_EA_NUM_ENT 2 /* Number of Capability Entries */ +#define PCI_EA_NUM_ENT_MASK 0x3f /* Num Entries Mask */ +#define PCI_EA_FIRST_ENT 4 /* First EA Entry in List */ +#define PCI_EA_FIRST_ENT_BRIDGE 8 /* First EA Entry for Bridges */ +#define PCI_EA_ES 0x00000007 /* Entry Size */ +#define PCI_EA_BEI(x) (((x) >> 4) & 0xf) /* BAR Equivalent Indicator */ +/* 0-5 map to BARs 0-5 respectively */ +#define PCI_EA_BEI_BAR0 0 +#define PCI_EA_BEI_BAR5 5 +#define PCI_EA_BEI_BRIDGE 6 /* Resource behind bridge */ +#define PCI_EA_BEI_ENI 7 /* Equivalent Not Indicated */ +#define PCI_EA_BEI_ROM 8 /* Expansion ROM */ +/* 9-14 map to VF BARs 0-5 respectively */ +#define PCI_EA_BEI_VF_BAR0 9 +#define PCI_EA_BEI_VF_BAR5 14 +#define PCI_EA_BEI_RESERVED 15 /* Reserved - Treat like ENI */ +#define PCI_EA_PP(x) (((x) >> 8) & 0xff) /* Primary Properties */ +#define PCI_EA_SP(x) (((x) >> 16) & 0xff) /* Secondary Properties */ +#define PCI_EA_P_MEM 0x00 /* Non-Prefetch Memory */ +#define PCI_EA_P_MEM_PREFETCH 0x01 /* Prefetchable Memory */ +#define PCI_EA_P_IO 0x02 /* I/O Space */ +#define PCI_EA_P_VF_MEM_PREFETCH 0x03 /* VF Prefetchable Memory */ +#define PCI_EA_P_VF_MEM 0x04 /* VF Non-Prefetch Memory */ +#define PCI_EA_P_BRIDGE_MEM 0x05 /* Bridge Non-Prefetch Memory */ +#define PCI_EA_P_BRIDGE_MEM_PREFETCH 0x06 /* Bridge Prefetchable Memory */ +#define PCI_EA_P_BRIDGE_IO 0x07 /* Bridge I/O Space */ +/* 0x08-0xfc reserved */ +#define PCI_EA_P_MEM_RESERVED 0xfd /* Reserved Memory */ +#define PCI_EA_P_IO_RESERVED 0xfe /* Reserved I/O Space */ +#define PCI_EA_P_UNAVAILABLE 0xff /* Entry Unavailable */ +#define PCI_EA_WRITABLE 0x40000000 /* Writable: 1 = RW, 0 = HwInit */ +#define PCI_EA_ENABLE 0x80000000 /* Enable for this entry */ +#define PCI_EA_BASE 4 /* Base Address Offset */ +#define PCI_EA_MAX_OFFSET 8 /* MaxOffset (resource length) */ +/* bit 0 is reserved */ +#define PCI_EA_IS_64 0x00000002 /* 64-bit field flag */ +#define PCI_EA_FIELD_MASK 0xfffffffc /* For Base & Max Offset */ + /* PCI-X registers (Type 0 (non-bridge) devices) */ #define PCI_X_CMD 2 /* Modes & Features */ -- cgit v1.2.3 From 26635112d4d057c9ea38f6284423a30a41a09240 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Thu, 29 Oct 2015 17:35:40 -0500 Subject: PCI: Make Enhanced Allocation bitmasks more obvious Expand bitmask #defines completely. This puts the shift in the code instead of in the #define, but it makes it more obvious in the header file how fields in the register are laid out. No functional change. Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 15 ++++++++------- include/uapi/linux/pci_regs.h | 6 +++--- 2 files changed, 11 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 364f98b30130..e8330b68cecd 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2195,7 +2195,7 @@ static int pci_ea_read(struct pci_dev *dev, int offset) int ent_size, ent_offset = offset; resource_size_t start, end; unsigned long flags; - u32 dw0, base, max_offset; + u32 dw0, bei, base, max_offset; u8 prop; bool support_64 = (sizeof(resource_size_t) >= 8); @@ -2208,20 +2208,21 @@ static int pci_ea_read(struct pci_dev *dev, int offset) if (!(dw0 & PCI_EA_ENABLE)) /* Entry not enabled */ goto out; - prop = PCI_EA_PP(dw0); + bei = (dw0 & PCI_EA_BEI) >> 4; + prop = (dw0 & PCI_EA_PP) >> 8; + /* * If the Property is in the reserved range, try the Secondary * Property instead. */ if (prop > PCI_EA_P_BRIDGE_IO && prop < PCI_EA_P_MEM_RESERVED) - prop = PCI_EA_SP(dw0); + prop = (dw0 & PCI_EA_SP) >> 16; if (prop > PCI_EA_P_BRIDGE_IO) goto out; - res = pci_ea_get_resource(dev, PCI_EA_BEI(dw0), prop); + res = pci_ea_get_resource(dev, bei, prop); if (!res) { - dev_err(&dev->dev, "Unsupported EA entry BEI: %u\n", - PCI_EA_BEI(dw0)); + dev_err(&dev->dev, "Unsupported EA entry BEI: %u\n", bei); goto out; } @@ -2293,7 +2294,7 @@ static int pci_ea_read(struct pci_dev *dev, int offset) res->end = end; res->flags = flags; dev_printk(KERN_DEBUG, &dev->dev, "EA - BEI %2u, Prop 0x%02x: %pR\n", - PCI_EA_BEI(dw0), prop, res); + bei, prop, res); out: return offset + ent_size; } diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index f890876aa070..1becea86c73c 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -361,7 +361,7 @@ #define PCI_EA_FIRST_ENT 4 /* First EA Entry in List */ #define PCI_EA_FIRST_ENT_BRIDGE 8 /* First EA Entry for Bridges */ #define PCI_EA_ES 0x00000007 /* Entry Size */ -#define PCI_EA_BEI(x) (((x) >> 4) & 0xf) /* BAR Equivalent Indicator */ +#define PCI_EA_BEI 0x000000f0 /* BAR Equivalent Indicator */ /* 0-5 map to BARs 0-5 respectively */ #define PCI_EA_BEI_BAR0 0 #define PCI_EA_BEI_BAR5 5 @@ -372,8 +372,8 @@ #define PCI_EA_BEI_VF_BAR0 9 #define PCI_EA_BEI_VF_BAR5 14 #define PCI_EA_BEI_RESERVED 15 /* Reserved - Treat like ENI */ -#define PCI_EA_PP(x) (((x) >> 8) & 0xff) /* Primary Properties */ -#define PCI_EA_SP(x) (((x) >> 16) & 0xff) /* Secondary Properties */ +#define PCI_EA_PP 0x0000ff00 /* Primary Properties */ +#define PCI_EA_SP 0x00ff0000 /* Secondary Properties */ #define PCI_EA_P_MEM 0x00 /* Non-Prefetch Memory */ #define PCI_EA_P_MEM_PREFETCH 0x01 /* Prefetchable Memory */ #define PCI_EA_P_IO 0x02 /* I/O Space */ -- cgit v1.2.3 From 8ed66f0e8235118a31720acdab3bbbe9debd0f6a Mon Sep 17 00:00:00 2001 From: "John W. Linville" Date: Mon, 26 Oct 2015 17:01:44 -0400 Subject: geneve: implement support for IPv6-based tunnels NOTE: Link-local IPv6 addresses for remote endpoints are not supported, since the driver currently has no capacity for binding a geneve interface to a specific link. Signed-off-by: John W. Linville Reviewed-by: Jesse Gross Signed-off-by: David S. Miller --- drivers/net/geneve.c | 473 +++++++++++++++++++++++++++++++++++-------- include/uapi/linux/if_link.h | 1 + 2 files changed, 395 insertions(+), 79 deletions(-) (limited to 'include/uapi') diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index 445071c163cb..393b0bddf7cf 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -46,16 +46,27 @@ struct geneve_net { static int geneve_net_id; +union geneve_addr { + struct sockaddr_in sin; + struct sockaddr_in6 sin6; + struct sockaddr sa; +}; + +static union geneve_addr geneve_remote_unspec = { .sa.sa_family = AF_UNSPEC, }; + /* Pseudo network device */ struct geneve_dev { struct hlist_node hlist; /* vni hash table */ struct net *net; /* netns for packet i/o */ struct net_device *dev; /* netdev for geneve tunnel */ - struct geneve_sock *sock; /* socket used for geneve tunnel */ + struct geneve_sock *sock4; /* IPv4 socket used for geneve tunnel */ +#if IS_ENABLED(CONFIG_IPV6) + struct geneve_sock *sock6; /* IPv6 socket used for geneve tunnel */ +#endif u8 vni[3]; /* virtual network ID for tunnel */ u8 ttl; /* TTL override */ u8 tos; /* TOS override */ - struct sockaddr_in remote; /* IPv4 address for link partner */ + union geneve_addr remote; /* IP address for link partner */ struct list_head next; /* geneve's per namespace list */ __be16 dst_port; bool collect_md; @@ -103,11 +114,31 @@ static struct geneve_dev *geneve_lookup(struct geneve_sock *gs, vni_list_head = &gs->vni_list[hash]; hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) { if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && - addr == geneve->remote.sin_addr.s_addr) + addr == geneve->remote.sin.sin_addr.s_addr) + return geneve; + } + return NULL; +} + +#if IS_ENABLED(CONFIG_IPV6) +static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs, + struct in6_addr addr6, u8 vni[]) +{ + struct hlist_head *vni_list_head; + struct geneve_dev *geneve; + __u32 hash; + + /* Find the device for this VNI */ + hash = geneve_net_vni_hash(vni); + vni_list_head = &gs->vni_list[hash]; + hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) { + if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && + ipv6_addr_equal(&addr6, &geneve->remote.sin6.sin6_addr)) return geneve; } return NULL; } +#endif static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb) { @@ -121,24 +152,49 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) struct metadata_dst *tun_dst = NULL; struct geneve_dev *geneve = NULL; struct pcpu_sw_netstats *stats; - struct iphdr *iph; - u8 *vni; + struct iphdr *iph = NULL; __be32 addr; - int err; + static u8 zero_vni[3]; + u8 *vni; + int err = 0; + sa_family_t sa_family; +#if IS_ENABLED(CONFIG_IPV6) + struct ipv6hdr *ip6h = NULL; + struct in6_addr addr6; + static struct in6_addr zero_addr6; +#endif - iph = ip_hdr(skb); /* outer IP header... */ + sa_family = gs->sock->sk->sk_family; - if (gs->collect_md) { - static u8 zero_vni[3]; + if (sa_family == AF_INET) { + iph = ip_hdr(skb); /* outer IP header... */ - vni = zero_vni; - addr = 0; - } else { - vni = gnvh->vni; - addr = iph->saddr; - } + if (gs->collect_md) { + vni = zero_vni; + addr = 0; + } else { + vni = gnvh->vni; + + addr = iph->saddr; + } + + geneve = geneve_lookup(gs, addr, vni); +#if IS_ENABLED(CONFIG_IPV6) + } else if (sa_family == AF_INET6) { + ip6h = ipv6_hdr(skb); /* outer IPv6 header... */ - geneve = geneve_lookup(gs, addr, vni); + if (gs->collect_md) { + vni = zero_vni; + addr6 = zero_addr6; + } else { + vni = gnvh->vni; + + addr6 = ip6h->saddr; + } + + geneve = geneve6_lookup(gs, addr6, vni); +#endif + } if (!geneve) goto drop; @@ -149,7 +205,7 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) (gnvh->oam ? TUNNEL_OAM : 0) | (gnvh->critical ? TUNNEL_CRIT_OPT : 0); - tun_dst = udp_tun_rx_dst(skb, AF_INET, flags, + tun_dst = udp_tun_rx_dst(skb, sa_family, flags, vni_to_tunnel_id(gnvh->vni), gnvh->opt_len * 4); if (!tun_dst) @@ -179,12 +235,25 @@ static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb) skb_reset_network_header(skb); - err = IP_ECN_decapsulate(iph, skb); + if (iph) + err = IP_ECN_decapsulate(iph, skb); +#if IS_ENABLED(CONFIG_IPV6) + if (ip6h) + err = IP6_ECN_decapsulate(ip6h, skb); +#endif if (unlikely(err)) { - if (log_ecn_error) - net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n", - &iph->saddr, iph->tos); + if (log_ecn_error) { + if (iph) + net_info_ratelimited("non-ECT from %pI4 " + "with TOS=%#x\n", + &iph->saddr, iph->tos); +#if IS_ENABLED(CONFIG_IPV6) + if (ip6h) + net_info_ratelimited("non-ECT from %pI6\n", + &ip6h->saddr); +#endif + } if (err > 1) { ++geneve->dev->stats.rx_frame_errors; ++geneve->dev->stats.rx_errors; @@ -284,6 +353,7 @@ static struct socket *geneve_create_sock(struct net *net, bool ipv6, if (ipv6) { udp_conf.family = AF_INET6; + udp_conf.ipv6_v6only = 1; } else { udp_conf.family = AF_INET; udp_conf.local_ip.s_addr = htonl(INADDR_ANY); @@ -458,9 +528,9 @@ static void geneve_notify_del_rx_port(struct geneve_sock *gs) udp_del_offload(&gs->udp_offloads); } -static void geneve_sock_release(struct geneve_sock *gs) +static void __geneve_sock_release(struct geneve_sock *gs) { - if (--gs->refcnt) + if (!gs || --gs->refcnt) return; list_del(&gs->list); @@ -469,66 +539,117 @@ static void geneve_sock_release(struct geneve_sock *gs) kfree_rcu(gs, rcu); } +static void geneve_sock_release(struct geneve_dev *geneve) +{ + __geneve_sock_release(geneve->sock4); +#if IS_ENABLED(CONFIG_IPV6) + __geneve_sock_release(geneve->sock6); +#endif +} + static struct geneve_sock *geneve_find_sock(struct geneve_net *gn, + sa_family_t family, __be16 dst_port) { struct geneve_sock *gs; list_for_each_entry(gs, &gn->sock_list, list) { if (inet_sk(gs->sock->sk)->inet_sport == dst_port && - inet_sk(gs->sock->sk)->sk.sk_family == AF_INET) { + inet_sk(gs->sock->sk)->sk.sk_family == family) { return gs; } } return NULL; } -static int geneve_open(struct net_device *dev) +static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6) { - struct geneve_dev *geneve = netdev_priv(dev); struct net *net = geneve->net; struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_sock *gs; __u32 hash; - gs = geneve_find_sock(gn, geneve->dst_port); + gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->dst_port); if (gs) { gs->refcnt++; goto out; } - gs = geneve_socket_create(net, geneve->dst_port, false); + gs = geneve_socket_create(net, geneve->dst_port, ipv6); if (IS_ERR(gs)) return PTR_ERR(gs); out: gs->collect_md = geneve->collect_md; - geneve->sock = gs; +#if IS_ENABLED(CONFIG_IPV6) + if (ipv6) + geneve->sock6 = gs; + else +#endif + geneve->sock4 = gs; hash = geneve_net_vni_hash(geneve->vni); hlist_add_head_rcu(&geneve->hlist, &gs->vni_list[hash]); return 0; } +static int geneve_open(struct net_device *dev) +{ + struct geneve_dev *geneve = netdev_priv(dev); + bool ipv6 = geneve->remote.sa.sa_family == AF_INET6; + bool metadata = geneve->collect_md; + int ret = 0; + + geneve->sock4 = NULL; +#if IS_ENABLED(CONFIG_IPV6) + geneve->sock6 = NULL; + if (ipv6 || metadata) + ret = geneve_sock_add(geneve, true); +#endif + if (!ret && (!ipv6 || metadata)) + ret = geneve_sock_add(geneve, false); + if (ret < 0) + geneve_sock_release(geneve); + + return ret; +} + static int geneve_stop(struct net_device *dev) { struct geneve_dev *geneve = netdev_priv(dev); - struct geneve_sock *gs = geneve->sock; if (!hlist_unhashed(&geneve->hlist)) hlist_del_rcu(&geneve->hlist); - geneve_sock_release(gs); + geneve_sock_release(geneve); return 0; } +static void geneve_build_header(struct genevehdr *geneveh, + __be16 tun_flags, u8 vni[3], + u8 options_len, u8 *options) +{ + geneveh->ver = GENEVE_VER; + geneveh->opt_len = options_len / 4; + geneveh->oam = !!(tun_flags & TUNNEL_OAM); + geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); + geneveh->rsvd1 = 0; + memcpy(geneveh->vni, vni, 3); + geneveh->proto_type = htons(ETH_P_TEB); + geneveh->rsvd2 = 0; + + memcpy(geneveh->options, options, options_len); +} + static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb, __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum) + bool csum, bool xnet) { struct genevehdr *gnvh; int min_headroom; int err; + skb_scrub_packet(skb, xnet); + min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr); err = skb_cow_head(skb, min_headroom); @@ -544,15 +665,7 @@ static int geneve_build_skb(struct rtable *rt, struct sk_buff *skb, } gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - gnvh->ver = GENEVE_VER; - gnvh->opt_len = opt_len / 4; - gnvh->oam = !!(tun_flags & TUNNEL_OAM); - gnvh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); - gnvh->rsvd1 = 0; - memcpy(gnvh->vni, vni, 3); - gnvh->proto_type = htons(ETH_P_TEB); - gnvh->rsvd2 = 0; - memcpy(gnvh->options, opt, opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); skb_set_inner_protocol(skb, htons(ETH_P_TEB)); return 0; @@ -562,10 +675,47 @@ free_rt: return err; } -static struct rtable *geneve_get_rt(struct sk_buff *skb, - struct net_device *dev, - struct flowi4 *fl4, - struct ip_tunnel_info *info) +#if IS_ENABLED(CONFIG_IPV6) +static int geneve6_build_skb(struct dst_entry *dst, struct sk_buff *skb, + __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, + bool csum, bool xnet) +{ + struct genevehdr *gnvh; + int min_headroom; + int err; + + skb_scrub_packet(skb, xnet); + + min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len + + GENEVE_BASE_HLEN + opt_len + sizeof(struct ipv6hdr); + err = skb_cow_head(skb, min_headroom); + if (unlikely(err)) { + kfree_skb(skb); + goto free_dst; + } + + skb = udp_tunnel_handle_offloads(skb, csum); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + goto free_dst; + } + + gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); + geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); + + skb_set_inner_protocol(skb, htons(ETH_P_TEB)); + return 0; + +free_dst: + dst_release(dst); + return err; +} +#endif + +static struct rtable *geneve_get_v4_rt(struct sk_buff *skb, + struct net_device *dev, + struct flowi4 *fl4, + struct ip_tunnel_info *info) { struct geneve_dev *geneve = netdev_priv(dev); struct rtable *rt = NULL; @@ -588,7 +738,7 @@ static struct rtable *geneve_get_rt(struct sk_buff *skb, } fl4->flowi4_tos = RT_TOS(tos); - fl4->daddr = geneve->remote.sin_addr.s_addr; + fl4->daddr = geneve->remote.sin.sin_addr.s_addr; } rt = ip_route_output_key(geneve->net, fl4); @@ -604,6 +754,41 @@ static struct rtable *geneve_get_rt(struct sk_buff *skb, return rt; } +#if IS_ENABLED(CONFIG_IPV6) +static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb, + struct net_device *dev, + struct flowi6 *fl6, + struct ip_tunnel_info *info) +{ + struct geneve_dev *geneve = netdev_priv(dev); + struct geneve_sock *gs6 = geneve->sock6; + struct dst_entry *dst = NULL; + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_mark = skb->mark; + fl6->flowi6_proto = IPPROTO_UDP; + + if (info) { + fl6->daddr = info->key.u.ipv6.dst; + fl6->saddr = info->key.u.ipv6.src; + } else { + fl6->daddr = geneve->remote.sin6.sin6_addr; + } + + if (ipv6_stub->ipv6_dst_lookup(geneve->net, gs6->sock->sk, &dst, fl6)) { + netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr); + return ERR_PTR(-ENETUNREACH); + } + if (dst->dev == dev) { /* is this necessary? */ + netdev_dbg(dev, "circular route to %pI6\n", &fl6->daddr); + dst_release(dst); + return ERR_PTR(-ELOOP); + } + + return dst; +} +#endif + /* Convert 64 bit tunnel ID to 24 bit VNI. */ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) { @@ -618,11 +803,11 @@ static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni) #endif } -static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct ip_tunnel_info *info) { struct geneve_dev *geneve = netdev_priv(dev); - struct geneve_sock *gs = geneve->sock; - struct ip_tunnel_info *info = NULL; + struct geneve_sock *gs4 = geneve->sock4; struct rtable *rt = NULL; const struct iphdr *iip; /* interior IP header */ int err = -EINVAL; @@ -631,10 +816,10 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) __be16 sport; bool udp_csum; __be16 df; + bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); if (geneve->collect_md) { - info = skb_tunnel_info(skb); - if (unlikely(info && !(info->mode & IP_TUNNEL_INFO_TX))) { + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { netdev_dbg(dev, "no tunnel metadata\n"); goto tx_error; } @@ -642,9 +827,8 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) goto tx_error; } - rt = geneve_get_rt(skb, dev, &fl4, info); + rt = geneve_get_v4_rt(skb, dev, &fl4, info); if (IS_ERR(rt)) { - netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr); err = PTR_ERR(rt); goto tx_error; } @@ -665,7 +849,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) udp_csum = !!(key->tun_flags & TUNNEL_CSUM); err = geneve_build_skb(rt, skb, key->tun_flags, vni, - info->options_len, opts, udp_csum); + info->options_len, opts, udp_csum, xnet); if (unlikely(err)) goto err; @@ -675,7 +859,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) } else { udp_csum = false; err = geneve_build_skb(rt, skb, 0, geneve->vni, - 0, NULL, udp_csum); + 0, NULL, udp_csum, xnet); if (unlikely(err)) goto err; @@ -686,7 +870,7 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) ttl = ttl ? : ip4_dst_hoplimit(&rt->dst); df = 0; } - err = udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, fl4.saddr, fl4.daddr, + err = udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, fl4.saddr, fl4.daddr, tos, ttl, df, sport, geneve->dst_port, !net_eq(geneve->net, dev_net(geneve->dev)), !udp_csum); @@ -706,6 +890,101 @@ err: return NETDEV_TX_OK; } +#if IS_ENABLED(CONFIG_IPV6) +static netdev_tx_t geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, + struct ip_tunnel_info *info) +{ + struct geneve_dev *geneve = netdev_priv(dev); + struct geneve_sock *gs6 = geneve->sock6; + struct dst_entry *dst = NULL; + int err = -EINVAL; + struct flowi6 fl6; + __u8 ttl; + __be16 sport; + bool udp_csum; + bool xnet = !net_eq(geneve->net, dev_net(geneve->dev)); + + if (geneve->collect_md) { + if (unlikely(!info || !(info->mode & IP_TUNNEL_INFO_TX))) { + netdev_dbg(dev, "no tunnel metadata\n"); + goto tx_error; + } + } + + dst = geneve_get_v6_dst(skb, dev, &fl6, info); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto tx_error; + } + + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); + skb_reset_mac_header(skb); + + if (info) { + const struct ip_tunnel_key *key = &info->key; + u8 *opts = NULL; + u8 vni[3]; + + tunnel_id_to_vni(key->tun_id, vni); + if (key->tun_flags & TUNNEL_GENEVE_OPT) + opts = ip_tunnel_info_opts(info); + + udp_csum = !!(key->tun_flags & TUNNEL_CSUM); + err = geneve6_build_skb(dst, skb, key->tun_flags, vni, + info->options_len, opts, + udp_csum, xnet); + if (unlikely(err)) + goto err; + + ttl = key->ttl; + } else { + udp_csum = false; + err = geneve6_build_skb(dst, skb, 0, geneve->vni, + 0, NULL, udp_csum, xnet); + if (unlikely(err)) + goto err; + + ttl = geneve->ttl; + if (!ttl && ipv6_addr_is_multicast(&fl6.daddr)) + ttl = 1; + ttl = ttl ? : ip6_dst_hoplimit(dst); + } + err = udp_tunnel6_xmit_skb(dst, gs6->sock->sk, skb, dev, + &fl6.saddr, &fl6.daddr, 0, ttl, + sport, geneve->dst_port, !udp_csum); + + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + return NETDEV_TX_OK; + +tx_error: + dev_kfree_skb(skb); +err: + if (err == -ELOOP) + dev->stats.collisions++; + else if (err == -ENETUNREACH) + dev->stats.tx_carrier_errors++; + else + dev->stats.tx_errors++; + return NETDEV_TX_OK; +} +#endif + +static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct geneve_dev *geneve = netdev_priv(dev); + struct ip_tunnel_info *info = NULL; + + if (geneve->collect_md) + info = skb_tunnel_info(skb); + +#if IS_ENABLED(CONFIG_IPV6) + if ((info && ip_tunnel_info_af(info) == AF_INET6) || + (!info && geneve->remote.sa.sa_family == AF_INET6)) + return geneve6_xmit_skb(skb, dev, info); +#endif + return geneve_xmit_skb(skb, dev, info); +} + static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); @@ -716,7 +995,7 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; - rt = geneve_get_rt(skb, dev, &fl4, info); + rt = geneve_get_v4_rt(skb, dev, &fl4, info); if (IS_ERR(rt)) return PTR_ERR(rt); @@ -785,6 +1064,7 @@ static void geneve_setup(struct net_device *dev) static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = { [IFLA_GENEVE_ID] = { .type = NLA_U32 }, [IFLA_GENEVE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GENEVE_REMOTE6] = { .len = sizeof(struct in6_addr) }, [IFLA_GENEVE_TTL] = { .type = NLA_U8 }, [IFLA_GENEVE_TOS] = { .type = NLA_U8 }, [IFLA_GENEVE_PORT] = { .type = NLA_U16 }, @@ -816,7 +1096,7 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[]) static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, __be16 dst_port, - __be32 rem_addr, + union geneve_addr *remote, u8 vni[], bool *tun_on_same_port, bool *tun_collect_md) @@ -832,7 +1112,7 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, *tun_on_same_port = true; } if (!memcmp(vni, geneve->vni, sizeof(geneve->vni)) && - rem_addr == geneve->remote.sin_addr.s_addr && + !memcmp(remote, &geneve->remote, sizeof(geneve->remote)) && dst_port == geneve->dst_port) t = geneve; } @@ -840,18 +1120,20 @@ static struct geneve_dev *geneve_find_dev(struct geneve_net *gn, } static int geneve_configure(struct net *net, struct net_device *dev, - __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos, - __be16 dst_port, bool metadata) + union geneve_addr *remote, + __u32 vni, __u8 ttl, __u8 tos, __be16 dst_port, + bool metadata) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *t, *geneve = netdev_priv(dev); bool tun_collect_md, tun_on_same_port; int err; - if (metadata) { - if (rem_addr || vni || tos || ttl) - return -EINVAL; - } + if (!remote) + return -EINVAL; + if (metadata && + (remote->sa.sa_family != AF_UNSPEC || vni || tos || ttl)) + return -EINVAL; geneve->net = net; geneve->dev = dev; @@ -860,16 +1142,19 @@ static int geneve_configure(struct net *net, struct net_device *dev, geneve->vni[1] = (vni & 0x0000ff00) >> 8; geneve->vni[2] = vni & 0x000000ff; - geneve->remote.sin_addr.s_addr = rem_addr; - if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr))) + if ((remote->sa.sa_family == AF_INET && + IN_MULTICAST(ntohl(remote->sin.sin_addr.s_addr))) || + (remote->sa.sa_family == AF_INET6 && + ipv6_addr_is_multicast(&remote->sin6.sin6_addr))) return -EINVAL; + geneve->remote = *remote; geneve->ttl = ttl; geneve->tos = tos; geneve->dst_port = dst_port; geneve->collect_md = metadata; - t = geneve_find_dev(gn, dst_port, rem_addr, geneve->vni, + t = geneve_find_dev(gn, dst_port, remote, geneve->vni, &tun_on_same_port, &tun_collect_md); if (t) return -EBUSY; @@ -896,15 +1181,36 @@ static int geneve_newlink(struct net *net, struct net_device *dev, __be16 dst_port = htons(GENEVE_UDP_PORT); __u8 ttl = 0, tos = 0; bool metadata = false; - __be32 rem_addr = 0; + union geneve_addr remote = geneve_remote_unspec; __u32 vni = 0; + if (data[IFLA_GENEVE_REMOTE] && data[IFLA_GENEVE_REMOTE6]) + return -EINVAL; + + if (data[IFLA_GENEVE_REMOTE]) { + remote.sa.sa_family = AF_INET; + remote.sin.sin_addr.s_addr = + nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); + } + + if (data[IFLA_GENEVE_REMOTE6]) { + if (!IS_ENABLED(CONFIG_IPV6)) + return -EPFNOSUPPORT; + + remote.sa.sa_family = AF_INET6; + remote.sin6.sin6_addr = + nla_get_in6_addr(data[IFLA_GENEVE_REMOTE6]); + + if (ipv6_addr_type(&remote.sin6.sin6_addr) & + IPV6_ADDR_LINKLOCAL) { + netdev_dbg(dev, "link-local remote is unsupported\n"); + return -EINVAL; + } + } + if (data[IFLA_GENEVE_ID]) vni = nla_get_u32(data[IFLA_GENEVE_ID]); - if (data[IFLA_GENEVE_REMOTE]) - rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]); - if (data[IFLA_GENEVE_TTL]) ttl = nla_get_u8(data[IFLA_GENEVE_TTL]); @@ -917,8 +1223,8 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (data[IFLA_GENEVE_COLLECT_METADATA]) metadata = true; - return geneve_configure(net, dev, rem_addr, vni, - ttl, tos, dst_port, metadata); + return geneve_configure(net, dev, &remote, vni, ttl, tos, dst_port, + metadata); } static void geneve_dellink(struct net_device *dev, struct list_head *head) @@ -932,7 +1238,7 @@ static void geneve_dellink(struct net_device *dev, struct list_head *head) static size_t geneve_get_size(const struct net_device *dev) { return nla_total_size(sizeof(__u32)) + /* IFLA_GENEVE_ID */ - nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */ + nla_total_size(sizeof(struct in6_addr)) + /* IFLA_GENEVE_REMOTE{6} */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL */ nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TOS */ nla_total_size(sizeof(__be16)) + /* IFLA_GENEVE_PORT */ @@ -949,9 +1255,17 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev) if (nla_put_u32(skb, IFLA_GENEVE_ID, vni)) goto nla_put_failure; - if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, - geneve->remote.sin_addr.s_addr)) - goto nla_put_failure; + if (geneve->remote.sa.sa_family == AF_INET) { + if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE, + geneve->remote.sin.sin_addr.s_addr)) + goto nla_put_failure; +#if IS_ENABLED(CONFIG_IPV6) + } else { + if (nla_put_in6_addr(skb, IFLA_GENEVE_REMOTE6, + &geneve->remote.sin6.sin6_addr)) + goto nla_put_failure; +#endif + } if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) || nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos)) @@ -997,7 +1311,8 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name, if (IS_ERR(dev)) return dev; - err = geneve_configure(net, dev, 0, 0, 0, 0, htons(dst_port), true); + err = geneve_configure(net, dev, &geneve_remote_unspec, + 0, 0, 0, htons(dst_port), true); if (err) { free_netdev(dev); return ERR_PTR(err); diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index a7aea8418abb..5ad57375a99f 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -461,6 +461,7 @@ enum { IFLA_GENEVE_TOS, IFLA_GENEVE_PORT, /* destination port */ IFLA_GENEVE_COLLECT_METADATA, + IFLA_GENEVE_REMOTE6, __IFLA_GENEVE_MAX }; #define IFLA_GENEVE_MAX (__IFLA_GENEVE_MAX - 1) -- cgit v1.2.3 From 71cdb6978a80f9f6c51bef0622388c1414c2fe32 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Oct 2015 14:10:51 +0200 Subject: dm: add support for passing through persistent reservations This adds support to pass through persistent reservation requests similar to the existing ioctl handling, and with the same limitations, e.g. devices may only have a single target attached. This is mostly intended for multipathing. Signed-off-by: Christoph Hellwig Signed-off-by: Mike Snitzer --- drivers/md/dm-mpath.c | 2 +- drivers/md/dm.c | 123 ++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/dm-ioctl.h | 4 +- 3 files changed, 126 insertions(+), 3 deletions(-) (limited to 'include/uapi') diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c index 77066a199984..aaa6caa46a9f 100644 --- a/drivers/md/dm-mpath.c +++ b/drivers/md/dm-mpath.c @@ -1682,7 +1682,7 @@ out: *---------------------------------------------------------------*/ static struct target_type multipath_target = { .name = "multipath", - .version = {1, 9, 0}, + .version = {1, 10, 0}, .module = THIS_MODULE, .ctr = multipath_ctr, .dtr = multipath_dtr, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 9b3fe5be0cee..c31ca8bc6af5 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -24,6 +24,7 @@ #include #include /* for rq_end_sector() */ #include +#include #include @@ -3553,11 +3554,133 @@ void dm_free_md_mempools(struct dm_md_mempools *pools) kfree(pools); } +static int dm_pr_register(struct block_device *bdev, u64 old_key, u64 new_key, + u32 flags) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_register) + r = ops->pr_register(bdev, old_key, new_key, flags); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_reserve(struct block_device *bdev, u64 key, enum pr_type type, + u32 flags) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_reserve) + r = ops->pr_reserve(bdev, key, type, flags); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_release(struct block_device *bdev, u64 key, enum pr_type type) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_release) + r = ops->pr_release(bdev, key, type); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_preempt(struct block_device *bdev, u64 old_key, u64 new_key, + enum pr_type type, bool abort) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_preempt) + r = ops->pr_preempt(bdev, old_key, new_key, type, abort); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static int dm_pr_clear(struct block_device *bdev, u64 key) +{ + struct mapped_device *md = bdev->bd_disk->private_data; + const struct pr_ops *ops; + struct dm_target *tgt; + fmode_t mode; + int srcu_idx, r; + + r = dm_get_live_table_for_ioctl(md, &tgt, &bdev, &mode, &srcu_idx); + if (r < 0) + return r; + + ops = bdev->bd_disk->fops->pr_ops; + if (ops && ops->pr_clear) + r = ops->pr_clear(bdev, key); + else + r = -EOPNOTSUPP; + + dm_put_live_table(md, srcu_idx); + return r; +} + +static const struct pr_ops dm_pr_ops = { + .pr_register = dm_pr_register, + .pr_reserve = dm_pr_reserve, + .pr_release = dm_pr_release, + .pr_preempt = dm_pr_preempt, + .pr_clear = dm_pr_clear, +}; + static const struct block_device_operations dm_blk_dops = { .open = dm_blk_open, .release = dm_blk_close, .ioctl = dm_blk_ioctl, .getgeo = dm_blk_getgeo, + .pr_ops = &dm_pr_ops, .owner = THIS_MODULE }; diff --git a/include/uapi/linux/dm-ioctl.h b/include/uapi/linux/dm-ioctl.h index d34611e35a30..30afd0a23c4b 100644 --- a/include/uapi/linux/dm-ioctl.h +++ b/include/uapi/linux/dm-ioctl.h @@ -267,9 +267,9 @@ enum { #define DM_DEV_SET_GEOMETRY _IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl) #define DM_VERSION_MAJOR 4 -#define DM_VERSION_MINOR 33 +#define DM_VERSION_MINOR 34 #define DM_VERSION_PATCHLEVEL 0 -#define DM_VERSION_EXTRA "-ioctl (2015-8-18)" +#define DM_VERSION_EXTRA "-ioctl (2015-10-28)" /* Status bits */ #define DM_READONLY_FLAG (1 << 0) /* In/Out */ -- cgit v1.2.3 From 5c7e81c3de9eb3db01e16190a1da0899efee645b Mon Sep 17 00:00:00 2001 From: Shaohua Li Date: Thu, 13 Aug 2015 14:32:04 -0700 Subject: raid5: enable log for raid array with cache disk Now log is safe to enable for raid array with cache disk Signed-off-by: Shaohua Li Signed-off-by: NeilBrown --- drivers/md/raid5.c | 11 +++++++++++ include/uapi/linux/raid/md_p.h | 1 + 2 files changed, 12 insertions(+) (limited to 'include/uapi') diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 122702d957a6..b0bf81d084fd 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -6329,8 +6329,11 @@ static void raid5_free_percpu(struct r5conf *conf) static void free_conf(struct r5conf *conf) { + if (conf->log) + r5l_exit_log(conf->log); if (conf->shrinker.seeks) unregister_shrinker(&conf->shrinker); + free_thread_groups(conf); shrink_stripes(conf); raid5_free_percpu(conf); @@ -6996,6 +6999,14 @@ static int run(struct mddev *mddev) mddev->queue); } + if (journal_dev) { + char b[BDEVNAME_SIZE]; + + printk(KERN_INFO"md/raid:%s: using device %s as journal\n", + mdname(mddev), bdevname(journal_dev->bdev, b)); + r5l_init_log(conf, journal_dev); + } + return 0; abort: md_unregister_thread(&mddev->thread); diff --git a/include/uapi/linux/raid/md_p.h b/include/uapi/linux/raid/md_p.h index 96e4196f9c79..c3e654c6d518 100644 --- a/include/uapi/linux/raid/md_p.h +++ b/include/uapi/linux/raid/md_p.h @@ -322,6 +322,7 @@ struct mdp_superblock_1 { |MD_FEATURE_NEW_OFFSET \ |MD_FEATURE_RECOVERY_BITMAP \ |MD_FEATURE_CLUSTERED \ + |MD_FEATURE_JOURNAL \ ) struct r5l_payload_header { -- cgit v1.2.3 From b2197755b2633e164a439682fb05a9b5ea48f706 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 29 Oct 2015 14:58:09 +0100 Subject: bpf: add support for persistent maps/progs This work adds support for "persistent" eBPF maps/programs. The term "persistent" is to be understood that maps/programs have a facility that lets them survive process termination. This is desired by various eBPF subsystem users. Just to name one example: tc classifier/action. Whenever tc parses the ELF object, extracts and loads maps/progs into the kernel, these file descriptors will be out of reach after the tc instance exits. So a subsequent tc invocation won't be able to access/relocate on this resource, and therefore maps cannot easily be shared, f.e. between the ingress and egress networking data path. The current workaround is that Unix domain sockets (UDS) need to be instrumented in order to pass the created eBPF map/program file descriptors to a third party management daemon through UDS' socket passing facility. This makes it a bit complicated to deploy shared eBPF maps or programs (programs f.e. for tail calls) among various processes. We've been brainstorming on how we could tackle this issue and various approches have been tried out so far, which can be read up further in the below reference. The architecture we eventually ended up with is a minimal file system that can hold map/prog objects. The file system is a per mount namespace singleton, and the default mount point is /sys/fs/bpf/. Any subsequent mounts within a given namespace will point to the same instance. The file system allows for creating a user-defined directory structure. The objects for maps/progs are created/fetched through bpf(2) with two new commands (BPF_OBJ_PIN/BPF_OBJ_GET). I.e. a bpf file descriptor along with a pathname is being passed to bpf(2) that in turn creates (we call it eBPF object pinning) the file system nodes. Only the pathname is being passed to bpf(2) for getting a new BPF file descriptor to an existing node. The user can use that to access maps and progs later on, through bpf(2). Removal of file system nodes is being managed through normal VFS functions such as unlink(2), etc. The file system code is kept to a very minimum and can be further extended later on. The next step I'm working on is to add dump eBPF map/prog commands to bpf(2), so that a specification from a given file descriptor can be retrieved. This can be used by things like CRIU but also applications can inspect the meta data after calling BPF_OBJ_GET. Big thanks also to Alexei and Hannes who significantly contributed in the design discussion that eventually let us end up with this architecture here. Reference: https://lkml.org/lkml/2015/10/15/925 Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- include/linux/bpf.h | 7 + include/uapi/linux/bpf.h | 45 +----- include/uapi/linux/magic.h | 1 + kernel/bpf/Makefile | 4 +- kernel/bpf/inode.c | 387 +++++++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 30 +++- 6 files changed, 433 insertions(+), 41 deletions(-) create mode 100644 kernel/bpf/inode.c (limited to 'include/uapi') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 0b5fb6acef64..de464e6683b6 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -167,11 +167,18 @@ struct bpf_prog *bpf_prog_get(u32 ufd); void bpf_prog_put(struct bpf_prog *prog); void bpf_prog_put_rcu(struct bpf_prog *prog); +struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); void bpf_map_put(struct bpf_map *map); extern int sysctl_unprivileged_bpf_disabled; +int bpf_map_new_fd(struct bpf_map *map); +int bpf_prog_new_fd(struct bpf_prog *prog); + +int bpf_obj_pin_user(u32 ufd, const char __user *pathname); +int bpf_obj_get_user(const char __user *pathname); + /* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); #else diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 2e032426cfb7..9ea2d22fa2cb 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -63,50 +63,16 @@ struct bpf_insn { __s32 imm; /* signed immediate constant */ }; -/* BPF syscall commands */ +/* BPF syscall commands, see bpf(2) man-page for details. */ enum bpf_cmd { - /* create a map with given type and attributes - * fd = bpf(BPF_MAP_CREATE, union bpf_attr *, u32 size) - * returns fd or negative error - * map is deleted when fd is closed - */ BPF_MAP_CREATE, - - /* lookup key in a given map - * err = bpf(BPF_MAP_LOOKUP_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->value - * returns zero and stores found elem into value - * or negative error - */ BPF_MAP_LOOKUP_ELEM, - - /* create or update key/value pair in a given map - * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->value, attr->flags - * returns zero or negative error - */ BPF_MAP_UPDATE_ELEM, - - /* find and delete elem by key in a given map - * err = bpf(BPF_MAP_DELETE_ELEM, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key - * returns zero or negative error - */ BPF_MAP_DELETE_ELEM, - - /* lookup key in a given map and return next key - * err = bpf(BPF_MAP_GET_NEXT_KEY, union bpf_attr *attr, u32 size) - * Using attr->map_fd, attr->key, attr->next_key - * returns zero and stores next key or negative error - */ BPF_MAP_GET_NEXT_KEY, - - /* verify and load eBPF program - * prog_fd = bpf(BPF_PROG_LOAD, union bpf_attr *attr, u32 size) - * Using attr->prog_type, attr->insns, attr->license - * returns fd or negative error - */ BPF_PROG_LOAD, + BPF_OBJ_PIN, + BPF_OBJ_GET, }; enum bpf_map_type { @@ -160,6 +126,11 @@ union bpf_attr { __aligned_u64 log_buf; /* user supplied buffer */ __u32 kern_version; /* checked when prog_type=kprobe */ }; + + struct { /* anonymous struct used by BPF_OBJ_* commands */ + __aligned_u64 pathname; + __u32 bpf_fd; + }; } __attribute__((aligned(8))); /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 7b1425a6b370..accb036bbc9c 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -75,5 +75,6 @@ #define ANON_INODE_FS_MAGIC 0x09041934 #define BTRFS_TEST_MAGIC 0x73727279 #define NSFS_MAGIC 0x6e736673 +#define BPF_FS_MAGIC 0xcafe4a11 #endif /* __LINUX_MAGIC_H__ */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index e6983be12bd3..13272582eee0 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,2 +1,4 @@ obj-y := core.o -obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o + +obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c new file mode 100644 index 000000000000..be6d726e31c9 --- /dev/null +++ b/kernel/bpf/inode.c @@ -0,0 +1,387 @@ +/* + * Minimal file system backend for holding eBPF maps and programs, + * used by bpf(2) object pinning. + * + * Authors: + * + * Daniel Borkmann + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +enum bpf_type { + BPF_TYPE_UNSPEC = 0, + BPF_TYPE_PROG, + BPF_TYPE_MAP, +}; + +static void *bpf_any_get(void *raw, enum bpf_type type) +{ + switch (type) { + case BPF_TYPE_PROG: + atomic_inc(&((struct bpf_prog *)raw)->aux->refcnt); + break; + case BPF_TYPE_MAP: + atomic_inc(&((struct bpf_map *)raw)->refcnt); + break; + default: + WARN_ON_ONCE(1); + break; + } + + return raw; +} + +static void bpf_any_put(void *raw, enum bpf_type type) +{ + switch (type) { + case BPF_TYPE_PROG: + bpf_prog_put(raw); + break; + case BPF_TYPE_MAP: + bpf_map_put(raw); + break; + default: + WARN_ON_ONCE(1); + break; + } +} + +static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) +{ + void *raw; + + *type = BPF_TYPE_MAP; + raw = bpf_map_get(ufd); + if (IS_ERR(raw)) { + *type = BPF_TYPE_PROG; + raw = bpf_prog_get(ufd); + } + + return raw; +} + +static const struct inode_operations bpf_dir_iops; + +static const struct inode_operations bpf_prog_iops = { }; +static const struct inode_operations bpf_map_iops = { }; + +static struct inode *bpf_get_inode(struct super_block *sb, + const struct inode *dir, + umode_t mode) +{ + struct inode *inode; + + switch (mode & S_IFMT) { + case S_IFDIR: + case S_IFREG: + break; + default: + return ERR_PTR(-EINVAL); + } + + inode = new_inode(sb); + if (!inode) + return ERR_PTR(-ENOSPC); + + inode->i_ino = get_next_ino(); + inode->i_atime = CURRENT_TIME; + inode->i_mtime = inode->i_atime; + inode->i_ctime = inode->i_atime; + + inode_init_owner(inode, dir, mode); + + return inode; +} + +static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) +{ + *type = BPF_TYPE_UNSPEC; + if (inode->i_op == &bpf_prog_iops) + *type = BPF_TYPE_PROG; + else if (inode->i_op == &bpf_map_iops) + *type = BPF_TYPE_MAP; + else + return -EACCES; + + return 0; +} + +static bool bpf_dname_reserved(const struct dentry *dentry) +{ + return strchr(dentry->d_name.name, '.'); +} + +static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + + if (bpf_dname_reserved(dentry)) + return -EPERM; + + inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = &bpf_dir_iops; + inode->i_fop = &simple_dir_operations; + + inc_nlink(inode); + inc_nlink(dir); + + d_instantiate(dentry, inode); + dget(dentry); + + return 0; +} + +static int bpf_mkobj_ops(struct inode *dir, struct dentry *dentry, + umode_t mode, const struct inode_operations *iops) +{ + struct inode *inode; + + if (bpf_dname_reserved(dentry)) + return -EPERM; + + inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFREG); + if (IS_ERR(inode)) + return PTR_ERR(inode); + + inode->i_op = iops; + inode->i_private = dentry->d_fsdata; + + d_instantiate(dentry, inode); + dget(dentry); + + return 0; +} + +static int bpf_mkobj(struct inode *dir, struct dentry *dentry, umode_t mode, + dev_t devt) +{ + enum bpf_type type = MINOR(devt); + + if (MAJOR(devt) != UNNAMED_MAJOR || !S_ISREG(mode) || + dentry->d_fsdata == NULL) + return -EPERM; + + switch (type) { + case BPF_TYPE_PROG: + return bpf_mkobj_ops(dir, dentry, mode, &bpf_prog_iops); + case BPF_TYPE_MAP: + return bpf_mkobj_ops(dir, dentry, mode, &bpf_map_iops); + default: + return -EPERM; + } +} + +static const struct inode_operations bpf_dir_iops = { + .lookup = simple_lookup, + .mknod = bpf_mkobj, + .mkdir = bpf_mkdir, + .rmdir = simple_rmdir, + .unlink = simple_unlink, +}; + +static int bpf_obj_do_pin(const struct filename *pathname, void *raw, + enum bpf_type type) +{ + struct dentry *dentry; + struct inode *dir; + struct path path; + umode_t mode; + dev_t devt; + int ret; + + dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0); + if (IS_ERR(dentry)) + return PTR_ERR(dentry); + + mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); + devt = MKDEV(UNNAMED_MAJOR, type); + + ret = security_path_mknod(&path, dentry, mode, devt); + if (ret) + goto out; + + dir = d_inode(path.dentry); + if (dir->i_op != &bpf_dir_iops) { + ret = -EPERM; + goto out; + } + + dentry->d_fsdata = raw; + ret = vfs_mknod(dir, dentry, mode, devt); + dentry->d_fsdata = NULL; +out: + done_path_create(&path, dentry); + return ret; +} + +int bpf_obj_pin_user(u32 ufd, const char __user *pathname) +{ + struct filename *pname; + enum bpf_type type; + void *raw; + int ret; + + pname = getname(pathname); + if (IS_ERR(pname)) + return PTR_ERR(pname); + + raw = bpf_fd_probe_obj(ufd, &type); + if (IS_ERR(raw)) { + ret = PTR_ERR(raw); + goto out; + } + + ret = bpf_obj_do_pin(pname, raw, type); + if (ret != 0) + bpf_any_put(raw, type); +out: + putname(pname); + return ret; +} + +static void *bpf_obj_do_get(const struct filename *pathname, + enum bpf_type *type) +{ + struct inode *inode; + struct path path; + void *raw; + int ret; + + ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path); + if (ret) + return ERR_PTR(ret); + + inode = d_backing_inode(path.dentry); + ret = inode_permission(inode, MAY_WRITE); + if (ret) + goto out; + + ret = bpf_inode_type(inode, type); + if (ret) + goto out; + + raw = bpf_any_get(inode->i_private, *type); + touch_atime(&path); + + path_put(&path); + return raw; +out: + path_put(&path); + return ERR_PTR(ret); +} + +int bpf_obj_get_user(const char __user *pathname) +{ + enum bpf_type type = BPF_TYPE_UNSPEC; + struct filename *pname; + int ret = -ENOENT; + void *raw; + + pname = getname(pathname); + if (IS_ERR(pname)) + return PTR_ERR(pname); + + raw = bpf_obj_do_get(pname, &type); + if (IS_ERR(raw)) { + ret = PTR_ERR(raw); + goto out; + } + + if (type == BPF_TYPE_PROG) + ret = bpf_prog_new_fd(raw); + else if (type == BPF_TYPE_MAP) + ret = bpf_map_new_fd(raw); + else + goto out; + + if (ret < 0) + bpf_any_put(raw, type); +out: + putname(pname); + return ret; +} + +static void bpf_evict_inode(struct inode *inode) +{ + enum bpf_type type; + + truncate_inode_pages_final(&inode->i_data); + clear_inode(inode); + + if (!bpf_inode_type(inode, &type)) + bpf_any_put(inode->i_private, type); +} + +static const struct super_operations bpf_super_ops = { + .statfs = simple_statfs, + .drop_inode = generic_delete_inode, + .evict_inode = bpf_evict_inode, +}; + +static int bpf_fill_super(struct super_block *sb, void *data, int silent) +{ + static struct tree_descr bpf_rfiles[] = { { "" } }; + struct inode *inode; + int ret; + + ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); + if (ret) + return ret; + + sb->s_op = &bpf_super_ops; + + inode = sb->s_root->d_inode; + inode->i_op = &bpf_dir_iops; + inode->i_mode &= ~S_IALLUGO; + inode->i_mode |= S_ISVTX | S_IRWXUGO; + + return 0; +} + +static struct dentry *bpf_mount(struct file_system_type *type, int flags, + const char *dev_name, void *data) +{ + return mount_ns(type, flags, current->nsproxy->mnt_ns, bpf_fill_super); +} + +static struct file_system_type bpf_fs_type = { + .owner = THIS_MODULE, + .name = "bpf", + .mount = bpf_mount, + .kill_sb = kill_litter_super, + .fs_flags = FS_USERNS_MOUNT, +}; + +MODULE_ALIAS_FS("bpf"); + +static int __init bpf_init(void) +{ + int ret; + + ret = sysfs_create_mount_point(fs_kobj, "bpf"); + if (ret) + return ret; + + ret = register_filesystem(&bpf_fs_type); + if (ret) + sysfs_remove_mount_point(fs_kobj, "bpf"); + + return ret; +} +fs_initcall(bpf_init); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index d7783cb04d86..0d3313d02a7e 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -111,7 +111,7 @@ static const struct file_operations bpf_map_fops = { .release = bpf_map_release, }; -static int bpf_map_new_fd(struct bpf_map *map) +int bpf_map_new_fd(struct bpf_map *map) { return anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC); @@ -174,7 +174,7 @@ struct bpf_map *__bpf_map_get(struct fd f) return f.file->private_data; } -static struct bpf_map *bpf_map_get(u32 ufd) +struct bpf_map *bpf_map_get(u32 ufd) { struct fd f = fdget(ufd); struct bpf_map *map; @@ -548,7 +548,7 @@ static const struct file_operations bpf_prog_fops = { .release = bpf_prog_release, }; -static int bpf_prog_new_fd(struct bpf_prog *prog) +int bpf_prog_new_fd(struct bpf_prog *prog) { return anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); @@ -674,6 +674,24 @@ free_prog_nouncharge: return err; } +#define BPF_OBJ_LAST_FIELD bpf_fd + +static int bpf_obj_pin(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_OBJ)) + return -EINVAL; + + return bpf_obj_pin_user(attr->bpf_fd, u64_to_ptr(attr->pathname)); +} + +static int bpf_obj_get(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_OBJ) || attr->bpf_fd != 0) + return -EINVAL; + + return bpf_obj_get_user(u64_to_ptr(attr->pathname)); +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -734,6 +752,12 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_PROG_LOAD: err = bpf_prog_load(&attr); break; + case BPF_OBJ_PIN: + err = bpf_obj_pin(&attr); + break; + case BPF_OBJ_GET: + err = bpf_obj_get(&attr); + break; default: err = -EINVAL; break; -- cgit v1.2.3 From fcf3f91c34105c3551741febbfc1066aaa7f1db7 Mon Sep 17 00:00:00 2001 From: Ben Skeggs Date: Fri, 4 Sep 2015 14:40:32 +1000 Subject: drm/nouveau: remove unnecessary usage of object handles No longer required in a lot of cases, as objects are identified over NVIF via an alternate mechanism since the rework. Signed-off-by: Ben Skeggs --- drivers/gpu/drm/nouveau/nouveau_abi16.c | 17 +++++------------ drivers/gpu/drm/nouveau/nouveau_chan.c | 30 +++++++++++++----------------- drivers/gpu/drm/nouveau/nouveau_chan.h | 3 +-- drivers/gpu/drm/nouveau/nouveau_display.c | 5 ++--- drivers/gpu/drm/nouveau/nouveau_drm.c | 10 ++++------ drivers/gpu/drm/nouveau/nouveau_drm.h | 5 ----- drivers/gpu/drm/nouveau/nouveau_gem.c | 2 +- drivers/gpu/drm/nouveau/nouveau_sysfs.c | 5 ++--- drivers/gpu/drm/nouveau/nv50_display.c | 7 +++---- include/uapi/drm/nouveau_drm.h | 8 -------- 10 files changed, 31 insertions(+), 61 deletions(-) (limited to 'include/uapi') diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index d336c2247d6a..0b3c8abd6843 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -51,8 +51,7 @@ nouveau_abi16_get(struct drm_file *file_priv, struct drm_device *dev) * device (ie. the one that belongs to the fd it * opened) */ - if (nvif_device_init(&cli->base.object, - NOUVEAU_ABI16_DEVICE, NV_DEVICE, + if (nvif_device_init(&cli->base.object, 0, NV_DEVICE, &args, sizeof(args), &abi16->device) == 0) return cli->abi16; @@ -133,7 +132,6 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16, /* destroy channel object, all children will be killed too */ if (chan->chan) { - abi16->handles &= ~(1ULL << (chan->chan->user.handle & 0xffff)); nouveau_channel_idle(chan->chan); nouveau_channel_del(&chan->chan); } @@ -268,26 +266,21 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) return nouveau_abi16_put(abi16, -EINVAL); /* allocate "abi16 channel" data and make up a handle for it */ - init->channel = __ffs64(~abi16->handles); - if (~abi16->handles == 0) - return nouveau_abi16_put(abi16, -ENOSPC); - chan = kzalloc(sizeof(*chan), GFP_KERNEL); if (!chan) return nouveau_abi16_put(abi16, -ENOMEM); INIT_LIST_HEAD(&chan->notifiers); list_add(&chan->head, &abi16->channels); - abi16->handles |= (1ULL << init->channel); /* create channel object and initialise dma and fence management */ - ret = nouveau_channel_new(drm, device, - NOUVEAU_ABI16_CHAN(init->channel), - init->fb_ctxdma_handle, + ret = nouveau_channel_new(drm, device, init->fb_ctxdma_handle, init->tt_ctxdma_handle, &chan->chan); if (ret) goto done; + init->channel = chan->chan->chid; + if (device->info.family >= NV_DEVICE_INFO_V0_TESLA) init->pushbuf_domains = NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART; @@ -338,7 +331,7 @@ nouveau_abi16_chan(struct nouveau_abi16 *abi16, int channel) struct nouveau_abi16_chan *chan; list_for_each_entry(chan, &abi16->channels, head) { - if (chan->chan->user.handle == NOUVEAU_ABI16_CHAN(channel)) + if (chan->chan->chid == channel) return chan; } diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index ff5e59db49db..1860f389f21f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -55,10 +55,8 @@ nouveau_channel_idle(struct nouveau_channel *chan) } if (ret) { - NV_PRINTK(err, cli, "failed to idle channel " - "0x%08x [%s]\n", - chan->user.handle, - nvxx_client(&cli->base)->name); + NV_PRINTK(err, cli, "failed to idle channel %d [%s]\n", + chan->chid, nvxx_client(&cli->base)->name); return ret; } } @@ -89,7 +87,7 @@ nouveau_channel_del(struct nouveau_channel **pchan) static int nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, - u32 handle, u32 size, struct nouveau_channel **pchan) + u32 size, struct nouveau_channel **pchan) { struct nouveau_cli *cli = (void *)device->object.client; struct nvkm_mmu *mmu = nvxx_mmu(device); @@ -174,8 +172,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, } } - ret = nvif_object_init(&device->object, NVDRM_PUSH | - (handle & 0xffff), NV_DMA_FROM_MEMORY, + ret = nvif_object_init(&device->object, 0, NV_DMA_FROM_MEMORY, &args, sizeof(args), &chan->push.ctxdma); if (ret) { nouveau_channel_del(pchan); @@ -187,7 +184,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, static int nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device, - u32 handle, u32 engine, struct nouveau_channel **pchan) + u32 engine, struct nouveau_channel **pchan) { static const u16 oclasses[] = { MAXWELL_CHANNEL_GPFIFO_A, KEPLER_CHANNEL_GPFIFO_A, @@ -206,7 +203,7 @@ nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device, int ret; /* allocate dma push buffer */ - ret = nouveau_channel_prep(drm, device, handle, 0x12000, &chan); + ret = nouveau_channel_prep(drm, device, 0x12000, &chan); *pchan = chan; if (ret) return ret; @@ -236,7 +233,7 @@ nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device, size = sizeof(args.nv50); } - ret = nvif_object_init(&device->object, handle, *oclass++, + ret = nvif_object_init(&device->object, 0, *oclass++, &args, size, &chan->user); if (ret == 0) { if (chan->user.oclass >= KEPLER_CHANNEL_GPFIFO_A) @@ -256,7 +253,7 @@ nouveau_channel_ind(struct nouveau_drm *drm, struct nvif_device *device, static int nouveau_channel_dma(struct nouveau_drm *drm, struct nvif_device *device, - u32 handle, struct nouveau_channel **pchan) + struct nouveau_channel **pchan) { static const u16 oclasses[] = { NV40_CHANNEL_DMA, NV17_CHANNEL_DMA, @@ -269,7 +266,7 @@ nouveau_channel_dma(struct nouveau_drm *drm, struct nvif_device *device, int ret; /* allocate dma push buffer */ - ret = nouveau_channel_prep(drm, device, handle, 0x10000, &chan); + ret = nouveau_channel_prep(drm, device, 0x10000, &chan); *pchan = chan; if (ret) return ret; @@ -280,7 +277,7 @@ nouveau_channel_dma(struct nouveau_drm *drm, struct nvif_device *device, args.offset = chan->push.vma.offset; do { - ret = nvif_object_init(&device->object, handle, *oclass++, + ret = nvif_object_init(&device->object, 0, *oclass++, &args, sizeof(args), &chan->user); if (ret == 0) { chan->chid = args.chid; @@ -401,8 +398,7 @@ nouveau_channel_init(struct nouveau_channel *chan, u32 vram, u32 gart) int nouveau_channel_new(struct nouveau_drm *drm, struct nvif_device *device, - u32 handle, u32 arg0, u32 arg1, - struct nouveau_channel **pchan) + u32 arg0, u32 arg1, struct nouveau_channel **pchan) { struct nouveau_cli *cli = (void *)device->object.client; bool super; @@ -412,10 +408,10 @@ nouveau_channel_new(struct nouveau_drm *drm, struct nvif_device *device, super = cli->base.super; cli->base.super = true; - ret = nouveau_channel_ind(drm, device, handle, arg0, pchan); + ret = nouveau_channel_ind(drm, device, arg0, pchan); if (ret) { NV_PRINTK(dbg, cli, "ib channel create, %d\n", ret); - ret = nouveau_channel_dma(drm, device, handle, pchan); + ret = nouveau_channel_dma(drm, device, pchan); if (ret) { NV_PRINTK(dbg, cli, "dma channel create, %d\n", ret); goto done; diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h index 2ed32414cb69..48062c94f36d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.h +++ b/drivers/gpu/drm/nouveau/nouveau_chan.h @@ -42,8 +42,7 @@ struct nouveau_channel { int nouveau_channel_new(struct nouveau_drm *, struct nvif_device *, - u32 handle, u32 arg0, u32 arg1, - struct nouveau_channel **); + u32 arg0, u32 arg1, struct nouveau_channel **); void nouveau_channel_del(struct nouveau_channel **); int nouveau_channel_idle(struct nouveau_channel *); diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 614b32e6381c..db6bc6760545 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -509,9 +509,8 @@ nouveau_display_create(struct drm_device *dev) int i; for (i = 0, ret = -ENODEV; ret && i < ARRAY_SIZE(oclass); i++) { - ret = nvif_object_init(&drm->device.object, - NVDRM_DISPLAY, oclass[i], - NULL, 0, &disp->disp); + ret = nvif_object_init(&drm->device.object, 0, + oclass[i], NULL, 0, &disp->disp); } if (ret == 0) { diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 45ba67819199..f93266582f27 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -208,7 +208,7 @@ nouveau_accel_init(struct nouveau_drm *drm) } if (device->info.family >= NV_DEVICE_INFO_V0_KEPLER) { - ret = nouveau_channel_new(drm, &drm->device, NVDRM_CHAN + 1, + ret = nouveau_channel_new(drm, &drm->device, KEPLER_CHANNEL_GPFIFO_A_V0_ENGINE_CE0| KEPLER_CHANNEL_GPFIFO_A_V0_ENGINE_CE1, 0, &drm->cechan); @@ -221,7 +221,7 @@ nouveau_accel_init(struct nouveau_drm *drm) if (device->info.chipset >= 0xa3 && device->info.chipset != 0xaa && device->info.chipset != 0xac) { - ret = nouveau_channel_new(drm, &drm->device, NVDRM_CHAN + 1, + ret = nouveau_channel_new(drm, &drm->device, NvDmaFB, NvDmaTT, &drm->cechan); if (ret) NV_ERROR(drm, "failed to create ce channel, %d\n", ret); @@ -233,8 +233,7 @@ nouveau_accel_init(struct nouveau_drm *drm) arg1 = NvDmaTT; } - ret = nouveau_channel_new(drm, &drm->device, NVDRM_CHAN, arg0, arg1, - &drm->channel); + ret = nouveau_channel_new(drm, &drm->device, arg0, arg1, &drm->channel); if (ret) { NV_ERROR(drm, "failed to create kernel channel, %d\n", ret); nouveau_accel_fini(drm); @@ -403,8 +402,7 @@ nouveau_drm_load(struct drm_device *dev, unsigned long flags) nouveau_get_hdmi_dev(drm); - ret = nvif_device_init(&drm->client.base.object, - NVDRM_DEVICE, NV_DEVICE, + ret = nvif_device_init(&drm->client.base.object, 0, NV_DEVICE, &(struct nv_device_v0) { .device = ~0, }, sizeof(struct nv_device_v0), diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.h b/drivers/gpu/drm/nouveau/nouveau_drm.h index 3c902c24a8dd..acfa03bd50de 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.h +++ b/drivers/gpu/drm/nouveau/nouveau_drm.h @@ -74,11 +74,6 @@ enum nouveau_drm_notify_route { }; enum nouveau_drm_handle { - NVDRM_CLIENT = 0xffffffff, - NVDRM_DEVICE = 0xdddddddd, - NVDRM_CONTROL = 0xdddddddc, - NVDRM_DISPLAY = 0xd1500000, - NVDRM_PUSH = 0xbbbb0000, /* |= client chid */ NVDRM_CHAN = 0xcccc0000, /* |= client chid */ NVDRM_NVSW = 0x55550000, }; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 41be584147b9..6bf1a7895708 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -682,7 +682,7 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, return -ENOMEM; list_for_each_entry(temp, &abi16->channels, head) { - if (temp->chan->user.handle == (NVDRM_CHAN | req->channel)) { + if (temp->chan->chid == req->channel) { chan = temp->chan; break; } diff --git a/drivers/gpu/drm/nouveau/nouveau_sysfs.c b/drivers/gpu/drm/nouveau/nouveau_sysfs.c index d12a5faee047..5dac3546c1b8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_sysfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_sysfs.c @@ -188,9 +188,8 @@ nouveau_sysfs_init(struct drm_device *dev) if (!sysfs) return -ENOMEM; - ret = nvif_object_init(&device->object, NVDRM_CONTROL, - NVIF_IOCTL_NEW_V0_CONTROL, NULL, 0, - &sysfs->ctrl); + ret = nvif_object_init(&device->object, 0, NVIF_IOCTL_NEW_V0_CONTROL, + NULL, 0, &sysfs->ctrl); if (ret == 0) device_create_file(nvxx_device(device)->dev, &dev_attr_pstate); diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c index 4ae87aed4505..c053c50b346a 100644 --- a/drivers/gpu/drm/nouveau/nv50_display.c +++ b/drivers/gpu/drm/nouveau/nv50_display.c @@ -68,7 +68,6 @@ nv50_chan_create(struct nvif_device *device, struct nvif_object *disp, const s32 *oclass, u8 head, void *data, u32 size, struct nv50_chan *chan) { - const u32 handle = (oclass[0] << 16) | head; struct nvif_sclass *sclass; int ret, i, n; @@ -81,7 +80,7 @@ nv50_chan_create(struct nvif_device *device, struct nvif_object *disp, while (oclass[0]) { for (i = 0; i < n; i++) { if (sclass[i].oclass == oclass[0]) { - ret = nvif_object_init(disp, handle, oclass[0], + ret = nvif_object_init(disp, 0, oclass[0], data, size, &chan->user); if (ret == 0) nvif_object_map(&chan->user); @@ -231,8 +230,8 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, if (!dmac->ptr) return -ENOMEM; - ret = nvif_object_init(&device->object, 0xd0000000, - NV_DMA_FROM_MEMORY, &(struct nv_dma_v0) { + ret = nvif_object_init(&device->object, 0, NV_DMA_FROM_MEMORY, + &(struct nv_dma_v0) { .target = NV_DMA_V0_TARGET_PCI_US, .access = NV_DMA_V0_ACCESS_RD, .start = dmac->handle + 0x0000, diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 5507eead5863..fd594cc73cc0 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -27,14 +27,6 @@ #define DRM_NOUVEAU_EVENT_NVIF 0x80000000 -/* reserved object handles when using deprecated object APIs - these - * are here so that libdrm can allow interoperability with the new - * object APIs - */ -#define NOUVEAU_ABI16_CLIENT 0xffffffff -#define NOUVEAU_ABI16_DEVICE 0xdddddddd -#define NOUVEAU_ABI16_CHAN(n) (0xcccc0000 | (n)) - #define NOUVEAU_GEM_DOMAIN_CPU (1 << 0) #define NOUVEAU_GEM_DOMAIN_VRAM (1 << 1) #define NOUVEAU_GEM_DOMAIN_GART (1 << 2) -- cgit v1.2.3 From 033291eccbdb1b70ffc02641edae19ac825dc75d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 15 Oct 2015 15:08:48 -0600 Subject: vfio: Include No-IOMMU mode There is really no way to safely give a user full access to a DMA capable device without an IOMMU to protect the host system. There is also no way to provide DMA translation, for use cases such as device assignment to virtual machines. However, there are still those users that want userspace drivers even under those conditions. The UIO driver exists for this use case, but does not provide the degree of device access and programming that VFIO has. In an effort to avoid code duplication, this introduces a No-IOMMU mode for VFIO. This mode requires building VFIO with CONFIG_VFIO_NOIOMMU and enabling the "enable_unsafe_noiommu_mode" option on the vfio driver. This should make it very clear that this mode is not safe. Additionally, CAP_SYS_RAWIO privileges are necessary to work with groups and containers using this mode. Groups making use of this support are named /dev/vfio/noiommu-$GROUP and can only make use of the special VFIO_NOIOMMU_IOMMU for the container. Use of this mode, specifically binding a device without a native IOMMU group to a VFIO bus driver will taint the kernel and should therefore not be considered supported. This patch includes no-iommu support for the vfio-pci bus driver only. Signed-off-by: Alex Williamson Acked-by: Michael S. Tsirkin --- drivers/vfio/Kconfig | 15 ++++ drivers/vfio/pci/vfio_pci.c | 8 +- drivers/vfio/vfio.c | 186 ++++++++++++++++++++++++++++++++++++++++++-- include/linux/vfio.h | 3 + include/uapi/linux/vfio.h | 7 ++ 5 files changed, 209 insertions(+), 10 deletions(-) (limited to 'include/uapi') diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 454017928ed0..b6d3cdc2791b 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -31,5 +31,20 @@ menuconfig VFIO If you don't know what to do here, say N. +menuconfig VFIO_NOIOMMU + bool "VFIO No-IOMMU support" + depends on VFIO + help + VFIO is built on the ability to isolate devices using the IOMMU. + Only with an IOMMU can userspace access to DMA capable devices be + considered secure. VFIO No-IOMMU mode enables IOMMU groups for + devices without IOMMU backing for the purpose of re-using the VFIO + infrastructure in a non-secure mode. Use of this mode will result + in an unsupportable kernel and will therefore taint the kernel. + Device assignment to virtual machines is also not possible with + this mode since there is no IOMMU to provide DMA translation. + + If you don't know what to do here, say N. + source "drivers/vfio/pci/Kconfig" source "drivers/vfio/platform/Kconfig" diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c index 964ad572aaee..32b88bd2c82c 100644 --- a/drivers/vfio/pci/vfio_pci.c +++ b/drivers/vfio/pci/vfio_pci.c @@ -940,13 +940,13 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL) return -EINVAL; - group = iommu_group_get(&pdev->dev); + group = vfio_iommu_group_get(&pdev->dev); if (!group) return -EINVAL; vdev = kzalloc(sizeof(*vdev), GFP_KERNEL); if (!vdev) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); return -ENOMEM; } @@ -957,7 +957,7 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev); if (ret) { - iommu_group_put(group); + vfio_iommu_group_put(group, &pdev->dev); kfree(vdev); return ret; } @@ -993,7 +993,7 @@ static void vfio_pci_remove(struct pci_dev *pdev) if (!vdev) return; - iommu_group_put(pdev->dev.iommu_group); + vfio_iommu_group_put(pdev->dev.iommu_group, &pdev->dev); kfree(vdev); if (vfio_pci_is_vga(pdev)) { diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index ab056f7af54d..de632da2e22f 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -62,6 +62,7 @@ struct vfio_container { struct rw_semaphore group_lock; struct vfio_iommu_driver *iommu_driver; void *iommu_data; + bool noiommu; }; struct vfio_unbound_dev { @@ -84,6 +85,7 @@ struct vfio_group { struct list_head unbound_list; struct mutex unbound_lock; atomic_t opened; + bool noiommu; }; struct vfio_device { @@ -95,6 +97,147 @@ struct vfio_device { void *device_data; }; +#ifdef CONFIG_VFIO_NOIOMMU +static bool noiommu __read_mostly; +module_param_named(enable_unsafe_noiommu_support, + noiommu, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(enable_unsafe_noiommu_mode, "Enable UNSAFE, no-IOMMU mode. This mode provides no device isolation, no DMA translation, no host kernel protection, cannot be used for device assignment to virtual machines, requires RAWIO permissions, and will taint the kernel. If you do not know what this is for, step away. (default: false)"); +#endif + +/* + * vfio_iommu_group_{get,put} are only intended for VFIO bus driver probe + * and remove functions, any use cases other than acquiring the first + * reference for the purpose of calling vfio_add_group_dev() or removing + * that symmetric reference after vfio_del_group_dev() should use the raw + * iommu_group_{get,put} functions. In particular, vfio_iommu_group_put() + * removes the device from the dummy group and cannot be nested. + */ +struct iommu_group *vfio_iommu_group_get(struct device *dev) +{ + struct iommu_group *group; + int __maybe_unused ret; + + group = iommu_group_get(dev); + +#ifdef CONFIG_VFIO_NOIOMMU + /* + * With noiommu enabled, an IOMMU group will be created for a device + * that doesn't already have one and doesn't have an iommu_ops on their + * bus. We use iommu_present() again in the main code to detect these + * fake groups. + */ + if (group || !noiommu || iommu_present(dev->bus)) + return group; + + group = iommu_group_alloc(); + if (IS_ERR(group)) + return NULL; + + iommu_group_set_name(group, "vfio-noiommu"); + ret = iommu_group_add_device(group, dev); + iommu_group_put(group); + if (ret) + return NULL; + + /* + * Where to taint? At this point we've added an IOMMU group for a + * device that is not backed by iommu_ops, therefore any iommu_ + * callback using iommu_ops can legitimately Oops. So, while we may + * be about to give a DMA capable device to a user without IOMMU + * protection, which is clearly taint-worthy, let's go ahead and do + * it here. + */ + add_taint(TAINT_USER, LOCKDEP_STILL_OK); + dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n"); +#endif + + return group; +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_get); + +void vfio_iommu_group_put(struct iommu_group *group, struct device *dev) +{ +#ifdef CONFIG_VFIO_NOIOMMU + if (!iommu_present(dev->bus)) + iommu_group_remove_device(dev); +#endif + + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(vfio_iommu_group_put); + +#ifdef CONFIG_VFIO_NOIOMMU +static void *vfio_noiommu_open(unsigned long arg) +{ + if (arg != VFIO_NOIOMMU_IOMMU) + return ERR_PTR(-EINVAL); + if (!capable(CAP_SYS_RAWIO)) + return ERR_PTR(-EPERM); + + return NULL; +} + +static void vfio_noiommu_release(void *iommu_data) +{ +} + +static long vfio_noiommu_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + if (cmd == VFIO_CHECK_EXTENSION) + return arg == VFIO_NOIOMMU_IOMMU ? 1 : 0; + + return -ENOTTY; +} + +static int vfio_iommu_present(struct device *dev, void *unused) +{ + return iommu_present(dev->bus) ? 1 : 0; +} + +static int vfio_noiommu_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + return iommu_group_for_each_dev(iommu_group, NULL, + vfio_iommu_present) ? -EINVAL : 0; +} + +static void vfio_noiommu_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ +} + +static struct vfio_iommu_driver_ops vfio_noiommu_ops = { + .name = "vfio-noiommu", + .owner = THIS_MODULE, + .open = vfio_noiommu_open, + .release = vfio_noiommu_release, + .ioctl = vfio_noiommu_ioctl, + .attach_group = vfio_noiommu_attach_group, + .detach_group = vfio_noiommu_detach_group, +}; + +static struct vfio_iommu_driver vfio_noiommu_driver = { + .ops = &vfio_noiommu_ops, +}; + +/* + * Wrap IOMMU drivers, the noiommu driver is the one and only driver for + * noiommu groups (and thus containers) and not available for normal groups. + */ +#define vfio_for_each_iommu_driver(con, pos) \ + for (pos = con->noiommu ? &vfio_noiommu_driver : \ + list_first_entry(&vfio.iommu_drivers_list, \ + struct vfio_iommu_driver, vfio_next); \ + (con->noiommu ? pos != NULL : \ + &pos->vfio_next != &vfio.iommu_drivers_list); \ + pos = con->noiommu ? NULL : list_next_entry(pos, vfio_next)) +#else +#define vfio_for_each_iommu_driver(con, pos) \ + list_for_each_entry(pos, &vfio.iommu_drivers_list, vfio_next) +#endif + + /** * IOMMU driver registration */ @@ -199,7 +342,8 @@ static void vfio_group_unlock_and_free(struct vfio_group *group) /** * Group objects - create, release, get, put, search */ -static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) +static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group, + bool noiommu) { struct vfio_group *group, *tmp; struct device *dev; @@ -217,6 +361,7 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) atomic_set(&group->container_users, 0); atomic_set(&group->opened, 0); group->iommu_group = iommu_group; + group->noiommu = noiommu; group->nb.notifier_call = vfio_iommu_group_notifier; @@ -252,7 +397,8 @@ static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group) dev = device_create(vfio.class, NULL, MKDEV(MAJOR(vfio.group_devt), minor), - group, "%d", iommu_group_id(iommu_group)); + group, "%s%d", noiommu ? "noiommu-" : "", + iommu_group_id(iommu_group)); if (IS_ERR(dev)) { vfio_free_group_minor(minor); vfio_group_unlock_and_free(group); @@ -640,7 +786,8 @@ int vfio_add_group_dev(struct device *dev, group = vfio_group_get_from_iommu(iommu_group); if (!group) { - group = vfio_create_group(iommu_group); + group = vfio_create_group(iommu_group, + !iommu_present(dev->bus)); if (IS_ERR(group)) { iommu_group_put(iommu_group); return PTR_ERR(group); @@ -852,8 +999,7 @@ static long vfio_ioctl_check_extension(struct vfio_container *container, */ if (!driver) { mutex_lock(&vfio.iommu_drivers_lock); - list_for_each_entry(driver, &vfio.iommu_drivers_list, - vfio_next) { + vfio_for_each_iommu_driver(container, driver) { if (!try_module_get(driver->ops->owner)) continue; @@ -922,7 +1068,7 @@ static long vfio_ioctl_set_iommu(struct vfio_container *container, } mutex_lock(&vfio.iommu_drivers_lock); - list_for_each_entry(driver, &vfio.iommu_drivers_list, vfio_next) { + vfio_for_each_iommu_driver(container, driver) { void *data; if (!try_module_get(driver->ops->owner)) @@ -1187,6 +1333,9 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) if (atomic_read(&group->container_users)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + f = fdget(container_fd); if (!f.file) return -EBADF; @@ -1202,6 +1351,13 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) down_write(&container->group_lock); + /* Real groups and fake groups cannot mix */ + if (!list_empty(&container->group_list) && + container->noiommu != group->noiommu) { + ret = -EPERM; + goto unlock_out; + } + driver = container->iommu_driver; if (driver) { ret = driver->ops->attach_group(container->iommu_data, @@ -1211,6 +1367,7 @@ static int vfio_group_set_container(struct vfio_group *group, int container_fd) } group->container = container; + container->noiommu = group->noiommu; list_add(&group->container_next, &container->group_list); /* Get a reference on the container and mark a user within the group */ @@ -1241,6 +1398,9 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) !group->container->iommu_driver || !vfio_group_viable(group)) return -EINVAL; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) + return -EPERM; + device = vfio_device_get_from_name(group, buf); if (!device) return -ENODEV; @@ -1283,6 +1443,10 @@ static int vfio_group_get_device_fd(struct vfio_group *group, char *buf) fd_install(ret, filep); + if (group->noiommu) + dev_warn(device->dev, "vfio-noiommu device opened by user " + "(%s:%d)\n", current->comm, task_pid_nr(current)); + return ret; } @@ -1371,6 +1535,11 @@ static int vfio_group_fops_open(struct inode *inode, struct file *filep) if (!group) return -ENODEV; + if (group->noiommu && !capable(CAP_SYS_RAWIO)) { + vfio_group_put(group); + return -EPERM; + } + /* Do we need multiple instances of the group open? Seems not. */ opened = atomic_cmpxchg(&group->opened, 0, 1); if (opened) { @@ -1533,6 +1702,11 @@ struct vfio_group *vfio_group_get_external_user(struct file *filep) if (!atomic_inc_not_zero(&group->container_users)) return ERR_PTR(-EINVAL); + if (group->noiommu) { + atomic_dec(&group->container_users); + return ERR_PTR(-EPERM); + } + if (!group->container->iommu_driver || !vfio_group_viable(group)) { atomic_dec(&group->container_users); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index ddb440975382..610a86a892b8 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -44,6 +44,9 @@ struct vfio_device_ops { void (*request)(void *device_data, unsigned int count); }; +extern struct iommu_group *vfio_iommu_group_get(struct device *dev); +extern void vfio_iommu_group_put(struct iommu_group *group, struct device *dev); + extern int vfio_add_group_dev(struct device *dev, const struct vfio_device_ops *ops, void *device_data); diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 9fd7b5d8df2f..751b69f858c8 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -38,6 +38,13 @@ #define VFIO_SPAPR_TCE_v2_IOMMU 7 +/* + * The No-IOMMU IOMMU offers no translation or isolation for devices and + * supports no ioctls outside of VFIO_CHECK_EXTENSION. Use of VFIO's No-IOMMU + * code will taint the host kernel and should be used with extreme caution. + */ +#define VFIO_NOIOMMU_IOMMU 8 + /* * The IOCTL interface is designed for extensibility by embedding the * structure length (argsz) and flags into structures passed between -- cgit v1.2.3 From 6172180c6b37ea164bf8a9bad70bb348d0a16563 Mon Sep 17 00:00:00 2001 From: Tvrtko Ursulin Date: Wed, 23 Sep 2015 10:10:31 +0100 Subject: drm: Use userspace compatible type in fourcc_mod_code macro MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit __u64 should be used instead of u64. Feature originally added in: commit e3eb3250d84ef97b766312345774367b6a310db8 Author: Rob Clark Date: Thu Feb 5 14:41:52 2015 +0000 drm: add support for tiled/compressed/etc modifier in addfb2 Signed-off-by: Tvrtko Ursulin Cc: Rob Clark Cc: Daniel Stone Cc: Daniel Vetter Cc: dri-devel@lists.freedesktop.org Cc: stable@vger.kernel.org # v4.1+ Fixes: e3eb3250d84e ("drm: add support for tiled/compressed/etc modifier in addfb2") Reviewed-by: Ville Syrjälä Link: http://patchwork.freedesktop.org/patch/msgid/1442999431-28568-1-git-send-email-tvrtko.ursulin@linux.intel.com Signed-off-by: Jani Nikula --- include/uapi/drm/drm_fourcc.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index 8c5e8b91a3cb..0b69a7753558 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -158,7 +158,7 @@ /* add more to the end as needed */ #define fourcc_mod_code(vendor, val) \ - ((((u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL)) + ((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | (val & 0x00ffffffffffffffULL)) /* * Format Modifier tokens: -- cgit v1.2.3 From a8ca5d0ecbdde5cc3d7accacbd69968b0c98764e Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Thu, 5 Nov 2015 18:51:33 -0800 Subject: mm: mlock: add new mlock system call With the refactored mlock code, introduce a new system call for mlock. The new call will allow the user to specify what lock states are being added. mlock2 is trivial at the moment, but a follow on patch will add a new mlock state making it useful. Signed-off-by: Eric B Munson Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Heiko Carstens Cc: Geert Uytterhoeven Cc: Catalin Marinas Cc: Stephen Rothwell Cc: Guenter Roeck Cc: Jonathan Corbet Cc: Kirill A. Shutemov Cc: Michael Kerrisk Cc: Ralf Baechle Cc: Shuah Khan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + include/linux/syscalls.h | 2 ++ include/uapi/asm-generic/unistd.h | 4 +++- kernel/sys_ni.c | 1 + mm/mlock.c | 8 ++++++++ 6 files changed, 16 insertions(+), 1 deletion(-) (limited to 'include/uapi') diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index caa2c712d1e7..f17705e1332c 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -382,3 +382,4 @@ 373 i386 shutdown sys_shutdown 374 i386 userfaultfd sys_userfaultfd 375 i386 membarrier sys_membarrier +376 i386 mlock2 sys_mlock2 diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index 278842fdf1f6..314a90bfc09c 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -331,6 +331,7 @@ 322 64 execveat stub_execveat 323 common userfaultfd sys_userfaultfd 324 common membarrier sys_membarrier +325 common mlock2 sys_mlock2 # # x32-specific system call numbers start at 512 to avoid cache impact diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index a460e2ef2843..a156b82dd14c 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -887,4 +887,6 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); + #endif diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index ee124009e12a..1324b0292ec2 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -713,9 +713,11 @@ __SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat) __SYSCALL(__NR_userfaultfd, sys_userfaultfd) #define __NR_membarrier 283 __SYSCALL(__NR_membarrier, sys_membarrier) +#define __NR_mlock2 284 +__SYSCALL(__NR_mlock2, sys_mlock2) #undef __NR_syscalls -#define __NR_syscalls 284 +#define __NR_syscalls 285 /* * All syscalls below here should go away really, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index a02decf15583..0623787ec67a 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -194,6 +194,7 @@ cond_syscall(sys_mlock); cond_syscall(sys_munlock); cond_syscall(sys_mlockall); cond_syscall(sys_munlockall); +cond_syscall(sys_mlock2); cond_syscall(sys_mincore); cond_syscall(sys_madvise); cond_syscall(sys_mremap); diff --git a/mm/mlock.c b/mm/mlock.c index fbd8c03f7b37..35dcf8fa7195 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -644,6 +644,14 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) return do_mlock(start, len, VM_LOCKED); } +SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) +{ + if (flags) + return -EINVAL; + + return do_mlock(start, len, VM_LOCKED); +} + SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) { int ret; -- cgit v1.2.3 From b0f205c2a3082dd9081f9a94e50658c5fa906ff1 Mon Sep 17 00:00:00 2001 From: Eric B Munson Date: Thu, 5 Nov 2015 18:51:39 -0800 Subject: mm: mlock: add mlock flags to enable VM_LOCKONFAULT usage The previous patch introduced a flag that specified pages in a VMA should be placed on the unevictable LRU, but they should not be made present when the area is created. This patch adds the ability to set this state via the new mlock system calls. We add MLOCK_ONFAULT for mlock2 and MCL_ONFAULT for mlockall. MLOCK_ONFAULT will set the VM_LOCKONFAULT modifier for VM_LOCKED. MCL_ONFAULT should be used as a modifier to the two other mlockall flags. When used with MCL_CURRENT, all current mappings will be marked with VM_LOCKED | VM_LOCKONFAULT. When used with MCL_FUTURE, the mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. When used with both MCL_CURRENT and MCL_FUTURE, all current mappings and mm->def_flags will be marked with VM_LOCKED | VM_LOCKONFAULT. Prior to this patch, mlockall() will unconditionally clear the mm->def_flags any time it is called without MCL_FUTURE. This behavior is maintained after adding MCL_ONFAULT. If a call to mlockall(MCL_FUTURE) is followed by mlockall(MCL_CURRENT), the mm->def_flags will be cleared and new VMAs will be unlocked. This remains true with or without MCL_ONFAULT in either mlockall() invocation. munlock() will unconditionally clear both vma flags. munlockall() unconditionally clears for VMA flags on all VMAs and in the mm->def_flags field. Signed-off-by: Eric B Munson Acked-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Jonathan Corbet Cc: Catalin Marinas Cc: Geert Uytterhoeven Cc: Guenter Roeck Cc: Heiko Carstens Cc: Kirill A. Shutemov Cc: Michael Kerrisk Cc: Ralf Baechle Cc: Shuah Khan Cc: Stephen Rothwell Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/include/uapi/asm/mman.h | 3 ++ arch/mips/include/uapi/asm/mman.h | 6 ++++ arch/parisc/include/uapi/asm/mman.h | 3 ++ arch/powerpc/include/uapi/asm/mman.h | 1 + arch/sparc/include/uapi/asm/mman.h | 1 + arch/tile/include/uapi/asm/mman.h | 1 + arch/xtensa/include/uapi/asm/mman.h | 6 ++++ include/uapi/asm-generic/mman-common.h | 5 ++++ include/uapi/asm-generic/mman.h | 1 + mm/mlock.c | 51 +++++++++++++++++++++++++--------- 10 files changed, 65 insertions(+), 13 deletions(-) (limited to 'include/uapi') diff --git a/arch/alpha/include/uapi/asm/mman.h b/arch/alpha/include/uapi/asm/mman.h index 0086b472bc2b..f2f949671798 100644 --- a/arch/alpha/include/uapi/asm/mman.h +++ b/arch/alpha/include/uapi/asm/mman.h @@ -37,6 +37,9 @@ #define MCL_CURRENT 8192 /* lock all currently mapped pages */ #define MCL_FUTURE 16384 /* lock all additions to address space */ +#define MCL_ONFAULT 32768 /* lock all pages that are faulted in */ + +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ #define MADV_NORMAL 0 /* no further special treatment */ #define MADV_RANDOM 1 /* expect random page references */ diff --git a/arch/mips/include/uapi/asm/mman.h b/arch/mips/include/uapi/asm/mman.h index cfcb876cae6b..97c03f468924 100644 --- a/arch/mips/include/uapi/asm/mman.h +++ b/arch/mips/include/uapi/asm/mman.h @@ -61,6 +61,12 @@ */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ + +/* + * Flags for mlock + */ +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ #define MADV_NORMAL 0 /* no further special treatment */ #define MADV_RANDOM 1 /* expect random page references */ diff --git a/arch/parisc/include/uapi/asm/mman.h b/arch/parisc/include/uapi/asm/mman.h index 294d251ca7b2..ecc3ae1ca28e 100644 --- a/arch/parisc/include/uapi/asm/mman.h +++ b/arch/parisc/include/uapi/asm/mman.h @@ -31,6 +31,9 @@ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ + +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ #define MADV_NORMAL 0 /* no further special treatment */ #define MADV_RANDOM 1 /* expect random page references */ diff --git a/arch/powerpc/include/uapi/asm/mman.h b/arch/powerpc/include/uapi/asm/mman.h index 6ea26df0a73c..03c06ba7464f 100644 --- a/arch/powerpc/include/uapi/asm/mman.h +++ b/arch/powerpc/include/uapi/asm/mman.h @@ -22,6 +22,7 @@ #define MCL_CURRENT 0x2000 /* lock all currently mapped pages */ #define MCL_FUTURE 0x4000 /* lock all additions to address space */ +#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */ #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ diff --git a/arch/sparc/include/uapi/asm/mman.h b/arch/sparc/include/uapi/asm/mman.h index 0b14df33cffa..9765896ecb2c 100644 --- a/arch/sparc/include/uapi/asm/mman.h +++ b/arch/sparc/include/uapi/asm/mman.h @@ -17,6 +17,7 @@ #define MCL_CURRENT 0x2000 /* lock all currently mapped pages */ #define MCL_FUTURE 0x4000 /* lock all additions to address space */ +#define MCL_ONFAULT 0x8000 /* lock all pages that are faulted in */ #define MAP_POPULATE 0x8000 /* populate (prefault) pagetables */ #define MAP_NONBLOCK 0x10000 /* do not block on IO */ diff --git a/arch/tile/include/uapi/asm/mman.h b/arch/tile/include/uapi/asm/mman.h index 81b8fc348d63..63ee13faf17d 100644 --- a/arch/tile/include/uapi/asm/mman.h +++ b/arch/tile/include/uapi/asm/mman.h @@ -36,6 +36,7 @@ */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ #endif /* _ASM_TILE_MMAN_H */ diff --git a/arch/xtensa/include/uapi/asm/mman.h b/arch/xtensa/include/uapi/asm/mman.h index 201aec0e0446..360944e1da52 100644 --- a/arch/xtensa/include/uapi/asm/mman.h +++ b/arch/xtensa/include/uapi/asm/mman.h @@ -74,6 +74,12 @@ */ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ + +/* + * Flags for mlock + */ +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ #define MADV_NORMAL 0 /* no further special treatment */ #define MADV_RANDOM 1 /* expect random page references */ diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h index ddc3b36f1046..a74dd84bbb6d 100644 --- a/include/uapi/asm-generic/mman-common.h +++ b/include/uapi/asm-generic/mman-common.h @@ -25,6 +25,11 @@ # define MAP_UNINITIALIZED 0x0 /* Don't support this flag */ #endif +/* + * Flags for mlock + */ +#define MLOCK_ONFAULT 0x01 /* Lock pages in range after they are faulted in, do not prefault */ + #define MS_ASYNC 1 /* sync memory asynchronously */ #define MS_INVALIDATE 2 /* invalidate the caches */ #define MS_SYNC 4 /* synchronous memory sync */ diff --git a/include/uapi/asm-generic/mman.h b/include/uapi/asm-generic/mman.h index e9fe6fd2a074..7162cd4cca73 100644 --- a/include/uapi/asm-generic/mman.h +++ b/include/uapi/asm-generic/mman.h @@ -17,5 +17,6 @@ #define MCL_CURRENT 1 /* lock all current mappings */ #define MCL_FUTURE 2 /* lock all future mappings */ +#define MCL_ONFAULT 4 /* lock all pages that are faulted in */ #endif /* __ASM_GENERIC_MMAN_H */ diff --git a/mm/mlock.c b/mm/mlock.c index ca3894113b97..339d9e0949b6 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -506,7 +506,8 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) || is_vm_hugetlb_page(vma) || vma == get_gate_vma(current->mm)) - goto out; /* don't set VM_LOCKED, don't count */ + /* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */ + goto out; pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, @@ -577,7 +578,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, prev = vma; for (nstart = start ; ; ) { - vm_flags_t newflags = vma->vm_flags & ~VM_LOCKED; + vm_flags_t newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; newflags |= flags; @@ -646,10 +647,15 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len) SYSCALL_DEFINE3(mlock2, unsigned long, start, size_t, len, int, flags) { - if (flags) + vm_flags_t vm_flags = VM_LOCKED; + + if (flags & ~MLOCK_ONFAULT) return -EINVAL; - return do_mlock(start, len, VM_LOCKED); + if (flags & MLOCK_ONFAULT) + vm_flags |= VM_LOCKONFAULT; + + return do_mlock(start, len, vm_flags); } SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) @@ -666,24 +672,43 @@ SYSCALL_DEFINE2(munlock, unsigned long, start, size_t, len) return ret; } +/* + * Take the MCL_* flags passed into mlockall (or 0 if called from munlockall) + * and translate into the appropriate modifications to mm->def_flags and/or the + * flags for all current VMAs. + * + * There are a couple of subtleties with this. If mlockall() is called multiple + * times with different flags, the values do not necessarily stack. If mlockall + * is called once including the MCL_FUTURE flag and then a second time without + * it, VM_LOCKED and VM_LOCKONFAULT will be cleared from mm->def_flags. + */ static int apply_mlockall_flags(int flags) { struct vm_area_struct * vma, * prev = NULL; + vm_flags_t to_add = 0; - if (flags & MCL_FUTURE) + current->mm->def_flags &= VM_LOCKED_CLEAR_MASK; + if (flags & MCL_FUTURE) { current->mm->def_flags |= VM_LOCKED; - else - current->mm->def_flags &= ~VM_LOCKED; - if (flags == MCL_FUTURE) - goto out; + if (flags & MCL_ONFAULT) + current->mm->def_flags |= VM_LOCKONFAULT; + + if (!(flags & MCL_CURRENT)) + goto out; + } + + if (flags & MCL_CURRENT) { + to_add |= VM_LOCKED; + if (flags & MCL_ONFAULT) + to_add |= VM_LOCKONFAULT; + } for (vma = current->mm->mmap; vma ; vma = prev->vm_next) { vm_flags_t newflags; - newflags = vma->vm_flags & ~VM_LOCKED; - if (flags & MCL_CURRENT) - newflags |= VM_LOCKED; + newflags = vma->vm_flags & VM_LOCKED_CLEAR_MASK; + newflags |= to_add; /* Ignore errors */ mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags); @@ -698,7 +723,7 @@ SYSCALL_DEFINE1(mlockall, int, flags) unsigned long lock_limit; int ret; - if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE))) + if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT))) return -EINVAL; if (!can_do_mlock()) -- cgit v1.2.3