Linux userland API discussions
 help / color / mirror / Atom feed

* [RFC PATCH net-next v3 2/4] rtnl: add link netns id to interface messages
From: Nicolas Dichtel @ 2014-10-02 13:48 UTC (permalink / raw)
  To: netdev-u79uwXL29TY76Z2rM5mHXA,
	containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-api-u79uwXL29TY76Z2rM5mHXA
  Cc: cwang-xCSkyg8dI+0RB7SZvlqPiA, Nicolas Dichtel,
	luto-kltTT9wpgjJwATOyAt5JVQ,
	stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ,
	ebiederm-aS9lmoZGLiVWk0Htik3J/w,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
	davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <1412257690-31253-1-git-send-email-nicolas.dichtel-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>

This patch adds a new attribute (IFLA_LINK_NETNSID) which contains the 'link'
netns id when this netns is different from the netns where the interface
stands (for example for x-net interfaces like ip tunnels). When there is no id,
we put NETNSA_NSINDEX_UNKNOWN into this attribute to indicate to userland that
the link netns is different from the interface netns. Hence, userland knows that
some information like IFLA_LINK are not interpretable.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>
---
 include/net/rtnetlink.h      |  2 ++
 include/uapi/linux/if_link.h |  1 +
 net/core/rtnetlink.c         | 13 +++++++++++++
 3 files changed, 16 insertions(+)

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index e21b9f9653c0..6c6d5393fc34 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -46,6 +46,7 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
  *			    to create when creating a new device.
  *	@get_num_rx_queues: Function to determine number of receive queues
  *			    to create when creating a new device.
+ *	@get_link_net: Function to get the i/o netns of the device
  */
 struct rtnl_link_ops {
 	struct list_head	list;
@@ -93,6 +94,7 @@ struct rtnl_link_ops {
 	int			(*fill_slave_info)(struct sk_buff *skb,
 						   const struct net_device *dev,
 						   const struct net_device *slave_dev);
+	struct net		*(*get_link_net)(const struct net_device *dev);
 };
 
 int __rtnl_link_register(struct rtnl_link_ops *ops);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 0bdb77e16875..938c0c02ed2e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -145,6 +145,7 @@ enum {
 	IFLA_CARRIER,
 	IFLA_PHYS_PORT_ID,
 	IFLA_CARRIER_CHANGES,
+	IFLA_LINK_NETNSID,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a6882686ca3a..1b9329512496 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -862,6 +862,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
+	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
 	       + nla_total_size(ext_filter_mask
 			        & RTEXT_FILTER_VF ? 4 : 0) /* IFLA_NUM_VF */
 	       + rtnl_vfinfo_size(dev, ext_filter_mask) /* IFLA_VFINFO_LIST */
@@ -1134,6 +1135,18 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 			goto nla_put_failure;
 	}
 
+	if (dev->rtnl_link_ops &&
+	    dev->rtnl_link_ops->get_link_net) {
+		struct net *link_net = dev->rtnl_link_ops->get_link_net(dev);
+
+		if (!net_eq(dev_net(dev), link_net)) {
+			int id = peernet2id(dev_net(dev), link_net);
+
+			if (nla_put_s32(skb, IFLA_LINK_NETNSID, id))
+				goto nla_put_failure;
+		}
+	}
+
 	if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC)))
 		goto nla_put_failure;
 
-- 
2.1.0

^ permalink raw reply related

* [RFC PATCH net-next v3 1/4] netns: add genl cmd to add and get peer netns ids
From: Nicolas Dichtel @ 2014-10-02 13:48 UTC (permalink / raw)
  To: netdev-u79uwXL29TY76Z2rM5mHXA,
	containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-api-u79uwXL29TY76Z2rM5mHXA
  Cc: davem-fT/PcQaiUtIeIZ0/mPfg9Q, ebiederm-aS9lmoZGLiVWk0Htik3J/w,
	stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
	luto-kltTT9wpgjJwATOyAt5JVQ, cwang-xCSkyg8dI+0RB7SZvlqPiA,
	Nicolas Dichtel
In-Reply-To: <1412257690-31253-1-git-send-email-nicolas.dichtel-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>

With this patch, a user can define an id for a peer netns by providing a FD or a
PID. These ids are local to netns (ie valid only into one netns).

This will be useful for netlink messages when a x-netns interface is dumped.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>
---
 MAINTAINERS                 |   1 +
 include/net/net_namespace.h |   5 ++
 include/uapi/linux/Kbuild   |   1 +
 include/uapi/linux/netns.h  |  31 +++++++
 net/core/net_namespace.c    | 195 ++++++++++++++++++++++++++++++++++++++++++++
 net/netlink/genetlink.c     |   4 +
 6 files changed, 237 insertions(+)
 create mode 100644 include/uapi/linux/netns.h

diff --git a/MAINTAINERS b/MAINTAINERS
index f8db3c3acc67..8e7f5d668e6a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6278,6 +6278,7 @@ F:	include/linux/netdevice.h
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/netns.h
 F:	tools/net/
 F:	tools/testing/selftests/net/
 F:	lib/random32.c
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 361d26077196..d8847d978b59 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -59,6 +59,7 @@ struct net {
 	struct list_head	exit_list;	/* Use only net_mutex */
 
 	struct user_namespace   *user_ns;	/* Owning user namespace */
+	struct idr		netns_ids;
 
 	unsigned int		proc_inum;
 
@@ -289,6 +290,10 @@ static inline struct net *read_pnet(struct net * const *pnet)
 #define __net_initconst	__initconst
 #endif
 
+int peernet2id(struct net *net, struct net *peer);
+struct net *get_net_ns_by_id(struct net *net, int id);
+int netns_genl_register(void);
+
 struct pernet_operations {
 	struct list_head list;
 	int (*init)(struct net *net);
diff --git a/include/uapi/linux/Kbuild b/include/uapi/linux/Kbuild
index 70e150ebc6c9..33a0bbfe4736 100644
--- a/include/uapi/linux/Kbuild
+++ b/include/uapi/linux/Kbuild
@@ -276,6 +276,7 @@ header-y += netfilter_decnet.h
 header-y += netfilter_ipv4.h
 header-y += netfilter_ipv6.h
 header-y += netlink.h
+header-y += netns.h
 header-y += netrom.h
 header-y += nfc.h
 header-y += nfs.h
diff --git a/include/uapi/linux/netns.h b/include/uapi/linux/netns.h
new file mode 100644
index 000000000000..8ebb08885795
--- /dev/null
+++ b/include/uapi/linux/netns.h
@@ -0,0 +1,31 @@
+#ifndef _UAPI_LINUX_NETNS_H_
+#define _UAPI_LINUX_NETNS_H_
+
+/* Generic netlink messages */
+
+#define NETNS_GENL_NAME			"netns"
+#define NETNS_GENL_VERSION		0x1
+
+/* Commands */
+enum {
+	NETNS_CMD_UNSPEC,
+	NETNS_CMD_NEWID,
+	NETNS_CMD_GETID,
+	__NETNS_CMD_MAX,
+};
+
+#define NETNS_CMD_MAX		(__NETNS_CMD_MAX - 1)
+
+/* Attributes */
+enum {
+	NETNSA_NONE,
+#define NETNSA_NSINDEX_UNKNOWN	-1
+	NETNSA_NSID,
+	NETNSA_PID,
+	NETNSA_FD,
+	__NETNSA_MAX,
+};
+
+#define NETNSA_MAX		(__NETNSA_MAX - 1)
+
+#endif /* _UAPI_LINUX_NETNS_H_ */
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 7f155175bba8..4a5680ed42fb 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -15,6 +15,8 @@
 #include <linux/file.h>
 #include <linux/export.h>
 #include <linux/user_namespace.h>
+#include <linux/netns.h>
+#include <net/genetlink.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
@@ -144,6 +146,50 @@ static void ops_free_list(const struct pernet_operations *ops,
 	}
 }
 
+/* This function is used by idr_for_each(). If net is equal to peer, the
+ * function returns the id so that idr_for_each() stops. Because we cannot
+ * returns the id 0 (idr_for_each() will not stop), we return the magic value
+ * -1 for it.
+ */
+static int net_eq_idr(int id, void *net, void *peer)
+{
+	if (net_eq(net, peer))
+		return id ? : -1;
+	return 0;
+}
+
+/* returns NETNSA_NSINDEX_UNKNOWN if not found */
+int peernet2id(struct net *net, struct net *peer)
+{
+	int id = idr_for_each(&net->netns_ids, net_eq_idr, peer);
+
+	ASSERT_RTNL();
+
+	/* Magic value for id 0. */
+	if (id == -1)
+		return 0;
+	if (id == 0)
+		return NETNSA_NSINDEX_UNKNOWN;
+
+	return id;
+}
+
+struct net *get_net_ns_by_id(struct net *net, int id)
+{
+	struct net *peer;
+
+	if (id < 0)
+		return NULL;
+
+	rcu_read_lock();
+	peer = idr_find(&net->netns_ids, id);
+	if (peer)
+		get_net(peer);
+	rcu_read_unlock();
+
+	return peer;
+}
+
 /*
  * setup_net runs the initializers for the network namespace object.
  */
@@ -158,6 +204,7 @@ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
 	atomic_set(&net->passive, 1);
 	net->dev_base_seq = 1;
 	net->user_ns = user_ns;
+	idr_init(&net->netns_ids);
 
 #ifdef NETNS_REFCNT_DEBUG
 	atomic_set(&net->use_count, 0);
@@ -288,6 +335,14 @@ static void cleanup_net(struct work_struct *work)
 	list_for_each_entry(net, &net_kill_list, cleanup_list) {
 		list_del_rcu(&net->list);
 		list_add_tail(&net->exit_list, &net_exit_list);
+		for_each_net(tmp) {
+			int id = peernet2id(tmp, net);
+
+			if (id >= 0)
+				idr_remove(&tmp->netns_ids, id);
+		}
+		idr_destroy(&net->netns_ids);
+
 	}
 	rtnl_unlock();
 
@@ -399,6 +454,146 @@ static struct pernet_operations __net_initdata net_ns_ops = {
 	.exit = net_ns_net_exit,
 };
 
+static struct genl_family netns_genl_family = {
+	.id		= GENL_ID_GENERATE,
+	.name		= NETNS_GENL_NAME,
+	.version	= NETNS_GENL_VERSION,
+	.hdrsize	= 0,
+	.maxattr	= NETNSA_MAX,
+	.netnsok	= true,
+};
+
+static struct nla_policy netns_nl_policy[NETNSA_MAX + 1] = {
+	[NETNSA_NONE]		= { .type = NLA_UNSPEC },
+	[NETNSA_NSID]		= { .type = NLA_S32 },
+	[NETNSA_PID]		= { .type = NLA_U32 },
+	[NETNSA_FD]		= { .type = NLA_U32 },
+};
+
+static int netns_nl_cmd_newid(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct net *peer;
+	int nsid, err;
+
+	if (!info->attrs[NETNSA_NSID])
+		return -EINVAL;
+	nsid = nla_get_s32(info->attrs[NETNSA_NSID]);
+	if (nsid < 0)
+		return -EINVAL;
+
+	if (info->attrs[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(info->attrs[NETNSA_PID]));
+	else if (info->attrs[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(info->attrs[NETNSA_FD]));
+	else
+		return -EINVAL;
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	rtnl_lock();
+	if (peernet2id(net, peer) >= 0) {
+		err = -EEXIST;
+		goto out;
+	}
+
+	err = idr_alloc(&net->netns_ids, peer, nsid, nsid + 1, GFP_KERNEL);
+	if (err >= 0)
+		err = 0;
+out:
+	rtnl_unlock();
+	put_net(peer);
+	return err;
+}
+
+static int netns_nl_get_size(void)
+{
+	return nla_total_size(sizeof(s32)) /* NETNSA_NSID */
+	       ;
+}
+
+static int netns_nl_fill(struct sk_buff *skb, u32 portid, u32 seq, int flags,
+			 int cmd, struct net *net, struct net *peer)
+{
+	void *hdr;
+	int id;
+
+	hdr = genlmsg_put(skb, portid, seq, &netns_genl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	rtnl_lock();
+	id = peernet2id(net, peer);
+	rtnl_unlock();
+	if (nla_put_s32(skb, NETNSA_NSID, id))
+		goto nla_put_failure;
+
+	return genlmsg_end(skb, hdr);
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
+}
+
+static int netns_nl_cmd_getid(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct sk_buff *msg;
+	int err = -ENOBUFS;
+	struct net *peer;
+
+	if (info->attrs[NETNSA_PID])
+		peer = get_net_ns_by_pid(nla_get_u32(info->attrs[NETNSA_PID]));
+	else if (info->attrs[NETNSA_FD])
+		peer = get_net_ns_by_fd(nla_get_u32(info->attrs[NETNSA_FD]));
+	else
+		return -EINVAL;
+
+	if (IS_ERR(peer))
+		return PTR_ERR(peer);
+
+	msg = genlmsg_new(netns_nl_get_size(), GFP_KERNEL);
+	if (!msg) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = netns_nl_fill(msg, info->snd_portid, info->snd_seq,
+			    NLM_F_ACK, NETNS_CMD_GETID, net, peer);
+	if (err < 0)
+		goto err_out;
+
+	err = genlmsg_unicast(net, msg, info->snd_portid);
+	goto out;
+
+err_out:
+	nlmsg_free(msg);
+out:
+	put_net(peer);
+	return err;
+}
+
+static struct genl_ops netns_genl_ops[] = {
+	{
+		.cmd = NETNS_CMD_NEWID,
+		.policy = netns_nl_policy,
+		.doit = netns_nl_cmd_newid,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = NETNS_CMD_GETID,
+		.policy = netns_nl_policy,
+		.doit = netns_nl_cmd_getid,
+		.flags = GENL_ADMIN_PERM,
+	},
+};
+
+int netns_genl_register(void)
+{
+	return genl_register_family_with_ops(&netns_genl_family,
+					     netns_genl_ops);
+}
+
 static int __init net_ns_init(void)
 {
 	struct net_generic *ng;
diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c
index 76393f2f4b22..c6f39e40c9f3 100644
--- a/net/netlink/genetlink.c
+++ b/net/netlink/genetlink.c
@@ -1029,6 +1029,10 @@ static int __init genl_init(void)
 	if (err)
 		goto problem;
 
+	err = netns_genl_register();
+	if (err < 0)
+		goto problem;
+
 	return 0;
 
 problem:
-- 
2.1.0

^ permalink raw reply related

* [RFC PATCH net-next v3 0/4] netns: allow to identify peer netns
From: Nicolas Dichtel @ 2014-10-02 13:48 UTC (permalink / raw)
  To: netdev-u79uwXL29TY76Z2rM5mHXA,
	containers-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-api-u79uwXL29TY76Z2rM5mHXA
  Cc: cwang-xCSkyg8dI+0RB7SZvlqPiA, luto-kltTT9wpgjJwATOyAt5JVQ,
	stephen-OTpzqLSitTUnbdJkjeBofR2eb7JE58TQ,
	ebiederm-aS9lmoZGLiVWk0Htik3J/w,
	akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b,
	davem-fT/PcQaiUtIeIZ0/mPfg9Q
In-Reply-To: <542D5726.8070308-pdR9zngts4EAvxtiuMwx3w@public.gmane.org>

The goal of this serie is to be able to multicast netlink messages with an
attribute that identify a peer netns.
This is needed by the userland to interpret some informations contained in
netlink messages (like IFLA_LINK value, but also some other attributes in case
of x-netns netdevice (see also
http://thread.gmane.org/gmane.linux.network/315933/focus=316064 and
http://thread.gmane.org/gmane.linux.kernel.containers/28301/focus=4239)).

Ids of peer netns are set by userland via a new genl messages. These ids are
stored per netns and are local (ie only valid in the netns where they are set).
To avoid allocating an int for each peer netns, I use idr_for_each() to retrieve
the id of a peer netns.

Patch 1/4 introduces the netlink API mechanism to set and get these ids.
Patch 2/4 and 3/4 shows an example of how to use these ids in rtnetlink
messages. And patch 4/4 shows that the netlink messages can be symetric between
a GET and a SET.

iproute2 patches are available, I can send them on demand.

Here is a small screenshot to show how it can be used by userland:
$ ip netns add foo
$ ip netns del foo
$ ip netns
$ touch /var/run/netns/init_net
$ mount --bind /proc/1/ns/net /var/run/netns/init_net
$ ip netns add foo
$ ip netns exec foo ip netns set init_net 0
$ ip netns
foo
init_net
$ ip netns exec foo ip netns
foo
init_net (id: 0)
$ ip netns exec foo ip link add ipip1 link-netnsid 0 type ipip remote 10.16.0.121 local 10.16.0.249
$ ip netns exec foo ip l ls ipip1
6: ipip1@NONE: <POINTOPOINT,NOARP> mtu 1480 qdisc noop state DOWN mode DEFAULT group default 
    link/ipip 10.16.0.249 peer 10.16.0.121 link-netnsid 0

The parameter link-netnsid shows us where the interface sends and receives
packets (and thus we know where encapsulated addresses are set).

RFCv2 -> RFCv3:
  ids are now defined by userland (via netlink). Ids are stored in each netns
  (and they are local to this netns).
  add get_link_net support for ip6 tunnels
  netnsid is now a s32 instead of a u32

RFCv1 -> RFCv2:
  remove useless ()
  ids are now stored in the user ns. It's possible to get an id for a peer netns
  only if the current netns and the peer netns have the same user ns parent.

 MAINTAINERS                  |   1 +
 include/net/ip6_tunnel.h     |   1 +
 include/net/ip_tunnels.h     |   1 +
 include/net/net_namespace.h  |   5 ++
 include/net/rtnetlink.h      |   2 +
 include/uapi/linux/Kbuild    |   1 +
 include/uapi/linux/if_link.h |   1 +
 include/uapi/linux/netns.h   |  31 +++++++
 net/core/net_namespace.c     | 195 +++++++++++++++++++++++++++++++++++++++++++
 net/core/rtnetlink.c         |  38 ++++++++-
 net/ipv4/ip_gre.c            |   2 +
 net/ipv4/ip_tunnel.c         |   8 ++
 net/ipv4/ip_vti.c            |   1 +
 net/ipv4/ipip.c              |   1 +
 net/ipv6/ip6_gre.c           |   1 +
 net/ipv6/ip6_tunnel.c        |   9 ++
 net/ipv6/ip6_vti.c           |   1 +
 net/ipv6/sit.c               |   1 +
 net/netlink/genetlink.c      |   4 +
 19 files changed, 301 insertions(+), 3 deletions(-)

Comments are welcome.

Regards,
Nicolas

^ permalink raw reply

* Re: [RFC PATCH net-next v2 0/5] netns: allow to identify peer netns
From: Nicolas Dichtel @ 2014-10-02 13:46 UTC (permalink / raw)
  To: Eric W. Biederman
  Cc: Network Development, Linux Containers,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	Andy Lutomirski, Stephen Hemminger, Cong Wang, Linux API,
	Andrew Morton, David S. Miller
In-Reply-To: <87y4t2gtd0.fsf-JOvCrm2gF+uungPnsOpG7nhyD016LWXt@public.gmane.org>

Le 29/09/2014 20:43, Eric W. Biederman a écrit :
> Nicolas Dichtel <nicolas.dichtel@6wind.com> writes:
>
>> Le 26/09/2014 20:57, Eric W. Biederman a écrit :
>>> Andy Lutomirski <luto@amacapital.net> writes:
>>>
>>>> On Fri, Sep 26, 2014 at 11:10 AM, Eric W. Biederman
>>>> <ebiederm@xmission.com> wrote:
>>>>> Nicolas Dichtel <nicolas.dichtel@6wind.com> writes:
>>>>>
>>>>>> The goal of this serie is to be able to multicast netlink messages with an
>>>>>> attribute that identify a peer netns.
>>>>>> This is needed by the userland to interpret some informations contained in
>>>>>> netlink messages (like IFLA_LINK value, but also some other attributes in case
>>>>>> of x-netns netdevice (see also
>>>>>> http://thread.gmane.org/gmane.linux.network/315933/focus=316064 and
>>>>>> http://thread.gmane.org/gmane.linux.kernel.containers/28301/focus=4239)).
>>>>>
>>>>> I want say that the problem addressed by patch 3/5 of this series is a
>>>>> fundamentally valid problem.  We have network objects spanning network
>>>>> namespaces and it would be very nice to be able to talk about them in
>>>>> netlink, and file descriptors are too local and argubably too heavy
>>>>> weight for netlink quires and especially for netlink broadcast messages.
>>>>>
>>>>> Furthermore the concept of ineternal concept of peernet2id seems valid.
>>>>>
>>>>> However what you do not address is a way for CRIU (aka process
>>>>> migration) to be able to restore these ids after process migration.
>>>>> Going farther it looks like you are actively breaking process migration
>>>>> at this time, making this set of patches a no-go.
>> Ok, I will look more deeply into CRIU.
>>
>>>>>
>>>>> When adding a new form of namespace id CRIU patches are just about
>>>>> as necessary as iproute patches.
>> Noted.
>
>
>
>>>>> That does not describe what you have actually implemented in the
>>>>> patches.
>>>>>
>>>>> I see two ways to go with this.
>>>>>
>>>>> - A per network namespace table to that you can store ids for ``peer''
>>>>>     network namespaces.  The table would need to be populated manually by
>>>>>     the likes of ip netns add.
>>>>>
>>>>>     That flips the order of assignment and makes this idea solid.
>> I have a preference for this solution, because it allows to have a full
>> broadcast messages. When you have a lot of network interfaces (> 10k),
>> it saves a lot of time to avoid another request to get all informations.
>
> My practical question is how often does it happen that we care?
In fact, I don't think that scenarii with a lot of netns have a full mesh of
x-netns interfaces. It will be more one "link" netns with the physical
interface and all other with one interface with the link part in this "link"
netns. Hence, only one nsid is needing in each netns.

>
>>>>>     Unfortunately in the case of a fully referencing mesh of N network
>>>>>     namespaces such a mesh winds up taking O(N^2) space, which seems
>>>>>     undesirable.
>> Memory consumption vs performances ;-)
>> In fact, when you have a lot of netns, you already should have some memory
>> available (at least N lo interfaces + N interfaces (veth or a x-netns
>> interface)). I'm not convinced that this is really an obstacle.
>
> I would have to see how it all fits together. O(N^2) grows a lot faster
> that N.  So after a point it isn't in the same ballpark of memory
> consumption.
>
>>> broadcast message business, and only care about the remote namespace for
>>> unicast messages.  Putting the work in an infrequently used slow path
>>> instead of a comparitively common path gives us much more freedom in
>>> the implementation.
>> I think it's better to have a full netlink messages, instead a partial one.
>> There is already a lot of attributes added for each rtnl interface messages to
>> be sure to describe all parameters of these interfaces.
>> And if the user don't care about ids (user has not set any id with iproute2),
>> we can just add the same attribute with id 0 (let's say it's a reserved id) to
>> indicate that the link part of this interface is in another netns.
>
> I imagine an id like that is something we would want ip netns add to
> set, and probably set in all existing network namespaces as well.
>
>> The great benefit of your first proposal is that the ids are set by the
>> userspace and thus it allows a high flexibility.
>>
>> Would you accept a patch that implements this first solution?
>
> I would not fundamentally reject it.  I would really like to make
> certain we think through how it will be used and what the practical
> benefits are.  Depending on how it is used the data structure could
> be a killer or it could be a case where we see how to manage it and
> simply don't care.
I will send a v3, so we can talk about it.


Thank you,
Nicolas
_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/containers

^ permalink raw reply

* [PATCH 7/7] ARM: multi_v7_defconfig: Enable Maxim 77693 charger
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Enable the max77693 charger driver used on Trats2 board. This allows
querying the charging status through power supply interface.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
---
 arch/arm/configs/multi_v7_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index a25549d015e8..54367775aade 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -248,6 +248,7 @@ CONFIG_GPIO_TPS6586X=y
 CONFIG_GPIO_TPS65910=y
 CONFIG_BATTERY_SBS=y
 CONFIG_CHARGER_TPS65090=y
+CONFIG_CHARGER_MAX77693=y
 CONFIG_POWER_RESET_AS3722=y
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_SUN6I=y
-- 
1.9.1

^ permalink raw reply related

* [PATCH 6/7] ARM: exynos_defconfig: Enable Maxim 77693 charger
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-pm-u79uwXL29TY76Z2rM5mHXA, Rob Herring, Pawel Moll,
	Mark Rutland, Ian Campbell, Kumar Gala,
	devicetree-u79uwXL29TY76Z2rM5mHXA,
	linux-api-u79uwXL29TY76Z2rM5mHXA
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r,
	linux-samsung-soc-u79uwXL29TY76Z2rM5mHXA, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>

Enable the max77693 charger driver used on Trats2 board. This allows
querying the charging status through power supply interface.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
---
 arch/arm/configs/exynos_defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/configs/exynos_defconfig b/arch/arm/configs/exynos_defconfig
index b14d8c3f7e12..78a963de612a 100644
--- a/arch/arm/configs/exynos_defconfig
+++ b/arch/arm/configs/exynos_defconfig
@@ -79,6 +79,7 @@ CONFIG_DEBUG_GPIO=y
 CONFIG_POWER_SUPPLY=y
 CONFIG_BATTERY_SBS=y
 CONFIG_CHARGER_TPS65090=y
+CONFIG_CHARGER_MAX77693=y
 # CONFIG_HWMON is not set
 CONFIG_THERMAL=y
 CONFIG_EXYNOS_THERMAL=y
-- 
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe devicetree" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

^ permalink raw reply related

* [PATCH 5/7] ARM: dts: exynos4412-trats: Add max77693 charger node
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Add to Trats2 DTS new node for configuring the max77693 charger driver.
Only the maxim,constant-microvolt differs from default value but set all
of the optional properties anyway.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
---
 arch/arm/boot/dts/exynos4412-trats2.dts | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm/boot/dts/exynos4412-trats2.dts b/arch/arm/boot/dts/exynos4412-trats2.dts
index dd9ac66770f7..952aeba473f1 100644
--- a/arch/arm/boot/dts/exynos4412-trats2.dts
+++ b/arch/arm/boot/dts/exynos4412-trats2.dts
@@ -543,6 +543,16 @@
 					regulator-max-microamp = <2580000>;
 				};
 			};
+
+			charger {
+				compatible = "maxim,max77693-charger";
+
+				maxim,constant-microvolt = <4350000>;
+				maxim,min-system-microvolt = <3600000>;
+				maxim,thermal-regulation-celsius = <100>;
+				maxim,battery-overcurrent-microamp = <3500000>;
+				maxim,charge-input-threshold-microvolt = <4300000>;
+			};
 		};
 	};
 
-- 
1.9.1

^ permalink raw reply related

* [PATCH 4/7] Documentation: charger: max77693: Document exported sysfs entry
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Document the settings exported by max77693 charger driver through sysfs
entries:
 - fast_charge_timer
 - top_off_threshold_current
 - top_off_timer

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
---
 Documentation/ABI/testing/sysfs-class-power | 42 +++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index 909e7602c717..369d2a2d7d3e 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -32,3 +32,45 @@ Description:
 		Valid values:
 		- 5, 6 or 7 (hours),
 		- 0: disabled.
+
+What:		/sys/class/power_supply/max77693-charger/device/fast_charge_timer
+Date:		January 2015
+KernelVersion:	3.19.0
+Contact:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
+Description:
+		This entry shows and sets the maximum time the max77693
+		charger operates in fast-charge mode. When the timer expires
+		the device will terminate fast-charge mode (charging current
+		will drop to 0 A) and will trigger interrupt.
+
+		Valid values:
+		- 4 - 16 (hours), step by 2 (rounded down)
+		- 0: disabled.
+
+What:		/sys/class/power_supply/max77693-charger/device/top_off_threshold_current
+Date:		January 2015
+KernelVersion:	3.19.0
+Contact:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
+Description:
+		This entry shows and sets the charging current threshold for
+		entering top-off charging mode. When charging current in fast
+		charge mode drops below this value, the charger will trigger
+		interrupt and start top-off charging mode.
+
+		Valid values:
+		- 100000 - 200000 (microamps), step by 25000 (rounded down)
+		- 200000 - 350000 (microamps), step by 50000 (rounded down)
+		- 0: disabled.
+
+What:		/sys/class/power_supply/max77693-charger/device/top_off_timer
+Date:		January 2015
+KernelVersion:	3.19.0
+Contact:	Krzysztof Kozlowski <k.kozlowski@samsung.com>
+Description:
+		This entry shows and sets the maximum time the max77693
+		charger operates in top-off charge mode. When the timer expires
+		the device will terminate top-off charge mode (charging current
+		will drop to 0 A) and will trigger interrupt.
+
+		Valid values:
+		- 0 - 70 (minutes), step by 10 (rounded down)
-- 
1.9.1

^ permalink raw reply related

* [PATCH 3/7] devicetree: mfd: max77693: Document new bindings for charger
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Document new device tree bindings for for Maxim 77693 charger driver.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Cc: devicetree@vger.kernel.org
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Pawel Moll <pawel.moll@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ian Campbell <ijc+devicetree@hellion.org.uk>
Cc: Kumar Gala <galak@codeaurora.org>
---
 Documentation/devicetree/bindings/mfd/max77693.txt | 46 ++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/Documentation/devicetree/bindings/mfd/max77693.txt b/Documentation/devicetree/bindings/mfd/max77693.txt
index 11921cc417bf..d0c3d787df12 100644
--- a/Documentation/devicetree/bindings/mfd/max77693.txt
+++ b/Documentation/devicetree/bindings/mfd/max77693.txt
@@ -27,6 +27,42 @@ Optional properties:
 
 	[*] refer Documentation/devicetree/bindings/regulator/regulator.txt
 
+- charger : Node configuring the charger driver.
+  If present, required properties:
+  - compatible : Must be "maxim,max77693-charger".
+
+  Optional properties (if not set, defaults will be used):
+  - maxim,constant-microvolt : Battery constant voltage in uV. The charger
+    will operate in fast charge constant current mode till battery voltage
+    reaches this level. Then the charger will switch to fast charge constant
+    voltage mode. Also vsys (system voltage) will be set to this value when
+    DC power is supplied but charger is not enabled.
+    Valid values: 3650000 - 4400000, step by 25000 (rounded down)
+    Default: 4200000
+
+  - maxim,min-system-microvolt : Minimal system voltage in uV.
+    Valid values: 3000000 - 3700000, step by 100000 (rounded down)
+    Default: 3600000
+
+  - maxim,thermal-regulation-celsius : Temperature in Celsius for entering
+    high temperature charging mode. If die temperature exceeds this value
+    the charging current will be reduced by 105 mA/Celsius.
+    Valid values: 70, 85, 100, 115
+    Default: 100
+
+  - maxim,battery-overcurrent-microamp : Overcurrent protection threshold
+    in uA (current from battery to system).
+    Valid values: 2000000 - 3500000, step by 250000 (rounded down)
+    Default: 3500000
+
+  - maxim,charge-input-threshold-microvolt : Threshold voltage in uV for
+    triggering input voltage regulation loop. If input voltage decreases
+    below this value, the input current will be reduced to reach the
+    threshold voltage.
+    Valid values: 4300000, 4700000, 4800000, 4900000
+    Default: 4300000
+
+
 Example:
 	max77693@66 {
 		compatible = "maxim,max77693";
@@ -52,4 +88,14 @@ Example:
 					regulator-boot-on;
 			};
 		};
+
+		charger {
+			compatible = "maxim,max77693-charger";
+
+			maxim,constant-microvolt = <4200000>;
+			maxim,min-system-microvolt = <3600000>;
+			maxim,thermal-regulation-celsius = <75>;
+			maxim,battery-overcurrent-microamp = <3000000>;
+			maxim,charge-input-threshold-microvolt = <4300000>;
+		};
 	};
-- 
1.9.1

^ permalink raw reply related

* [PATCH 2/7] power: max77693: Add charger driver for Maxim 77693
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Krzysztof Kozlowski, linux-samsung-soc, Russell King,
	Bartlomiej Zolnierkiewicz, Tomasz Figa, Kyungmin Park, Kukjin Kim,
	Ben Dooks, Javier Martinez Canillas, linux-arm-kernel,
	Marek Szyprowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Add new driver for Maxim 77693 switch-mode charger (part of max77693
MFD driver) providing power supply class information to userspace.

The charger has +20V tolerant input. Current input can be set from 0 to
2.58 A. The charger can deliver up to 2.1 A to the battery or 3.5 A to
the system (when supplying additional current from battery to system).

The driver is configured through DTS (battery and system related
settings) and sysfs entries (timers and top-off charging threshold).

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
---
 drivers/power/Kconfig            |   6 +
 drivers/power/Makefile           |   1 +
 drivers/power/max77693_charger.c | 763 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 770 insertions(+)
 create mode 100644 drivers/power/max77693_charger.c

diff --git a/drivers/power/Kconfig b/drivers/power/Kconfig
index 0108c2af005b..77e6cd7bb801 100644
--- a/drivers/power/Kconfig
+++ b/drivers/power/Kconfig
@@ -332,6 +332,12 @@ config CHARGER_MAX14577
 	  Say Y to enable support for the battery charger control sysfs and
 	  platform data of MAX14577/77836 MUICs.
 
+config CHARGER_MAX77693
+	tristate "Maxim MAX77693 battery charger driver"
+	depends on MFD_MAX77693
+	help
+	  Say Y to enable support for the Maxim MAX77693 battery charger.
+
 config CHARGER_MAX8997
 	tristate "Maxim MAX8997/MAX8966 PMIC battery charger driver"
 	depends on MFD_MAX8997 && REGULATOR_MAX8997
diff --git a/drivers/power/Makefile b/drivers/power/Makefile
index dfa894273926..2d7ad66cc7d6 100644
--- a/drivers/power/Makefile
+++ b/drivers/power/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_CHARGER_LP8788)	+= lp8788-charger.o
 obj-$(CONFIG_CHARGER_GPIO)	+= gpio-charger.o
 obj-$(CONFIG_CHARGER_MANAGER)	+= charger-manager.o
 obj-$(CONFIG_CHARGER_MAX14577)	+= max14577_charger.o
+obj-$(CONFIG_CHARGER_MAX77693)	+= max77693_charger.o
 obj-$(CONFIG_CHARGER_MAX8997)	+= max8997_charger.o
 obj-$(CONFIG_CHARGER_MAX8998)	+= max8998_charger.o
 obj-$(CONFIG_CHARGER_BQ2415X)	+= bq2415x_charger.o
diff --git a/drivers/power/max77693_charger.c b/drivers/power/max77693_charger.c
new file mode 100644
index 000000000000..dfdbcc2f0795
--- /dev/null
+++ b/drivers/power/max77693_charger.c
@@ -0,0 +1,763 @@
+/*
+ * max77693_charger.c - Battery charger driver for the Maxim 77693
+ *
+ * Copyright (C) 2014 Samsung Electronics
+ * Krzysztof Kozlowski <k.kozlowski@samsung.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * 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 General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/power_supply.h>
+#include <linux/regmap.h>
+#include <linux/mfd/max77693.h>
+#include <linux/mfd/max77693-private.h>
+
+static const char *max77693_charger_name		= "max77693-charger";
+static const char *max77693_charger_model		= "MAX77693";
+static const char *max77693_charger_manufacturer	= "Maxim Integrated";
+
+struct max77693_charger {
+	struct device		*dev;
+	struct max77693_dev	*max77693;
+	struct power_supply	charger;
+
+	struct max77693_charger_platform_data	*pdata;
+};
+
+static int max77693_get_charger_state(struct regmap *regmap)
+{
+	int state;
+	unsigned int data;
+
+	if (regmap_read(regmap, MAX77693_CHG_REG_CHG_DETAILS_01, &data) < 0)
+		return POWER_SUPPLY_STATUS_UNKNOWN;
+
+	data &= CHG_DETAILS_01_CHG_MASK;
+	data >>= CHG_DETAILS_01_CHG_SHIFT;
+
+	switch (data) {
+	case MAX77693_CHARGING_PREQUALIFICATION:
+	case MAX77693_CHARGING_FAST_CONST_CURRENT:
+	case MAX77693_CHARGING_FAST_CONST_VOLTAGE:
+	case MAX77693_CHARGING_TOP_OFF:
+	/* In high temp the charging current is reduced, but still charging */
+	case MAX77693_CHARGING_HIGH_TEMP:
+		state = POWER_SUPPLY_STATUS_CHARGING;
+		break;
+	case MAX77693_CHARGING_DONE:
+		state = POWER_SUPPLY_STATUS_FULL;
+		break;
+	case MAX77693_CHARGING_TIMER_EXPIRED:
+	case MAX77693_CHARGING_THERMISTOR_SUSPEND:
+		state = POWER_SUPPLY_STATUS_NOT_CHARGING;
+		break;
+	case MAX77693_CHARGING_OFF:
+	case MAX77693_CHARGING_OVER_TEMP:
+	case MAX77693_CHARGING_WATCHDOG_EXPIRED:
+		state = POWER_SUPPLY_STATUS_DISCHARGING;
+		break;
+	case MAX77693_CHARGING_RESERVED:
+	default:
+		state = POWER_SUPPLY_STATUS_UNKNOWN;
+	}
+
+	return state;
+}
+
+static int max77693_get_charge_type(struct regmap *regmap)
+{
+	int state;
+	unsigned int data;
+
+	if (regmap_read(regmap, MAX77693_CHG_REG_CHG_DETAILS_01, &data) < 0)
+		return POWER_SUPPLY_CHARGE_TYPE_UNKNOWN;
+
+	data &= CHG_DETAILS_01_CHG_MASK;
+	data >>= CHG_DETAILS_01_CHG_SHIFT;
+
+	switch (data) {
+	case MAX77693_CHARGING_PREQUALIFICATION:
+	/*
+	 * Top-off: trickle or fast? In top-off the current varies between
+	 * 100 and 250 mA. It is higher than prequalification current.
+	 */
+	case MAX77693_CHARGING_TOP_OFF:
+		state = POWER_SUPPLY_CHARGE_TYPE_TRICKLE;
+		break;
+	case MAX77693_CHARGING_FAST_CONST_CURRENT:
+	case MAX77693_CHARGING_FAST_CONST_VOLTAGE:
+	/* In high temp the charging current is reduced, but still charging */
+	case MAX77693_CHARGING_HIGH_TEMP:
+		state = POWER_SUPPLY_CHARGE_TYPE_FAST;
+		break;
+	case MAX77693_CHARGING_DONE:
+	case MAX77693_CHARGING_TIMER_EXPIRED:
+	case MAX77693_CHARGING_THERMISTOR_SUSPEND:
+	case MAX77693_CHARGING_OFF:
+	case MAX77693_CHARGING_OVER_TEMP:
+	case MAX77693_CHARGING_WATCHDOG_EXPIRED:
+		state = POWER_SUPPLY_CHARGE_TYPE_NONE;
+		break;
+	case MAX77693_CHARGING_RESERVED:
+	default:
+		state = POWER_SUPPLY_CHARGE_TYPE_UNKNOWN;
+	}
+
+	return state;
+}
+
+/*
+ * Supported health statuses:
+ *  - POWER_SUPPLY_HEALTH_DEAD
+ *  - POWER_SUPPLY_HEALTH_GOOD
+ *  - POWER_SUPPLY_HEALTH_OVERVOLTAGE
+ *  - POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE
+ *  - POWER_SUPPLY_HEALTH_UNKNOWN
+ *  - POWER_SUPPLY_HEALTH_UNSPEC_FAILURE
+ */
+static int max77693_get_battery_health(struct regmap *regmap)
+{
+	int state;
+	unsigned int data;
+
+	if (regmap_read(regmap, MAX77693_CHG_REG_CHG_DETAILS_01, &data) < 0)
+		return POWER_SUPPLY_HEALTH_UNKNOWN;
+
+	data &= CHG_DETAILS_01_BAT_MASK;
+	data >>= CHG_DETAILS_01_BAT_SHIFT;
+
+	switch (data) {
+	case MAX77693_BATTERY_NOBAT:
+		state = POWER_SUPPLY_HEALTH_DEAD;
+		break;
+	case MAX77693_BATTERY_PREQUALIFICATION:
+	case MAX77693_BATTERY_GOOD:
+	case MAX77693_BATTERY_LOWVOLTAGE:
+		state = POWER_SUPPLY_HEALTH_GOOD;
+		break;
+	case MAX77693_BATTERY_TIMER_EXPIRED:
+		/*
+		 * Took longer to charge than expected, charging suspended.
+		 * Damaged battery?
+		 */
+		state = POWER_SUPPLY_HEALTH_SAFETY_TIMER_EXPIRE;
+		break;
+	case MAX77693_BATTERY_OVERVOLTAGE:
+		state = POWER_SUPPLY_HEALTH_OVERVOLTAGE;
+		break;
+	case MAX77693_BATTERY_OVERCURRENT:
+		state = POWER_SUPPLY_HEALTH_UNSPEC_FAILURE;
+		break;
+	case MAX77693_BATTERY_RESERVED:
+	default:
+		state = POWER_SUPPLY_HEALTH_UNKNOWN;
+		break;
+	}
+
+	return state;
+}
+
+static int max77693_get_present(struct regmap *regmap)
+{
+	unsigned int data;
+
+	/*
+	 * Read CHG_INT_OK register. High DETBAT bit here should be
+	 * equal to value 0x0 in CHG_DETAILS_01/BAT field.
+	 */
+	regmap_read(regmap, MAX77693_CHG_REG_CHG_INT_OK, &data);
+	if (data & CHG_INT_OK_DETBAT_MASK)
+		return 0;
+	return 1;
+}
+
+static int max77693_get_online(struct regmap *regmap)
+{
+	unsigned int data;
+
+	regmap_read(regmap, MAX77693_CHG_REG_CHG_INT_OK, &data);
+	if (data & CHG_INT_OK_CHGIN_MASK)
+		return 1;
+	return 0;
+}
+
+static enum power_supply_property max77693_charger_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_CHARGE_TYPE,
+	POWER_SUPPLY_PROP_HEALTH,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_ONLINE,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+};
+
+static int max77693_charger_get_property(struct power_supply *psy,
+			    enum power_supply_property psp,
+			    union power_supply_propval *val)
+{
+	struct max77693_charger *chg = container_of(psy,
+						  struct max77693_charger,
+						  charger);
+	struct regmap *regmap = chg->max77693->regmap;
+	int ret = 0;
+
+	switch (psp) {
+	case POWER_SUPPLY_PROP_STATUS:
+		val->intval = max77693_get_charger_state(regmap);
+		break;
+	case POWER_SUPPLY_PROP_CHARGE_TYPE:
+		val->intval = max77693_get_charge_type(regmap);
+		break;
+	case POWER_SUPPLY_PROP_HEALTH:
+		val->intval = max77693_get_battery_health(regmap);
+		break;
+	case POWER_SUPPLY_PROP_PRESENT:
+		val->intval = max77693_get_present(regmap);
+		break;
+	case POWER_SUPPLY_PROP_ONLINE:
+		val->intval = max77693_get_online(regmap);
+		break;
+	case POWER_SUPPLY_PROP_MODEL_NAME:
+		val->strval = max77693_charger_model;
+		break;
+	case POWER_SUPPLY_PROP_MANUFACTURER:
+		val->strval = max77693_charger_manufacturer;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static ssize_t device_attr_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count,
+		int (*fn)(struct max77693_charger *, unsigned long))
+{
+	struct max77693_charger *chg = dev_get_drvdata(dev);
+	unsigned long val;
+	int ret;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret)
+		return ret;
+
+	ret = fn(chg, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t fast_charge_timer_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct max77693_charger *chg = dev_get_drvdata(dev);
+	unsigned int data, val;
+	int ret;
+
+	ret = regmap_read(chg->max77693->regmap, MAX77693_CHG_REG_CHG_CNFG_01,
+			&data);
+	if (ret < 0)
+		return ret;
+
+	data &= CHG_CNFG_01_FCHGTIME_MASK;
+	data >>= CHG_CNFG_01_FCHGTIME_SHIFT;
+	switch (data) {
+	case 0x1 ... 0x7:
+		/* Starting from 4 hours, step by 2 hours */
+		val = 4 + (data - 1) * 2;
+		break;
+	case 0x0:
+	default:
+		val = 0;
+		break;
+	}
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static int max77693_set_fast_charge_timer(struct max77693_charger *chg,
+		unsigned long hours)
+{
+	unsigned int data;
+
+	/*
+	 * 0x00 - disable
+	 * 0x01 - 4h
+	 * 0x02 - 6h
+	 * ...
+	 * 0x07 - 16h
+	 * Round down odd values.
+	 */
+	switch (hours) {
+	case 4 ... 16:
+		data = (hours - 4) / 2 + 1;
+		break;
+	case 0:
+		/* Disable */
+		data = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	data <<= CHG_CNFG_01_FCHGTIME_SHIFT;
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_01,
+			CHG_CNFG_01_FCHGTIME_MASK, data);
+}
+
+static ssize_t fast_charge_timer_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return device_attr_store(dev, attr, buf, count,
+			max77693_set_fast_charge_timer);
+}
+
+static ssize_t top_off_threshold_current_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct max77693_charger *chg = dev_get_drvdata(dev);
+	unsigned int data, val;
+	int ret;
+
+	ret = regmap_read(chg->max77693->regmap, MAX77693_CHG_REG_CHG_CNFG_03,
+			&data);
+	if (ret < 0)
+		return ret;
+
+	data &= CHG_CNFG_03_TOITH_MASK;
+	data >>= CHG_CNFG_03_TOITH_SHIFT;
+
+	if (data <= 0x04)
+		val = 100000 + data * 25000;
+	else
+		val = data * 50000;
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static int max77693_set_top_off_threshold_current(struct max77693_charger *chg,
+		unsigned long uamp)
+{
+	unsigned int data;
+
+	if (uamp < 100000 || uamp > 350000)
+		return -EINVAL;
+
+	if (uamp <= 200000)
+		data = (uamp - 100000) / 25000;
+	else
+		/* (200000, 350000> */
+		data = uamp / 50000;
+
+	data <<= CHG_CNFG_03_TOITH_SHIFT;
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_03,
+			CHG_CNFG_03_TOITH_MASK, data);
+}
+
+static ssize_t top_off_threshold_current_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return device_attr_store(dev, attr, buf, count,
+			max77693_set_top_off_threshold_current);
+}
+
+static ssize_t top_off_timer_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct max77693_charger *chg = dev_get_drvdata(dev);
+	unsigned int data, val;
+	int ret;
+
+	ret = regmap_read(chg->max77693->regmap, MAX77693_CHG_REG_CHG_CNFG_03,
+			&data);
+	if (ret < 0)
+		return ret;
+
+	data &= CHG_CNFG_03_TOTIME_MASK;
+	data >>= CHG_CNFG_03_TOTIME_SHIFT;
+
+	val = data * 10;
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n", val);
+}
+
+static int max77693_set_top_off_timer(struct max77693_charger *chg,
+		unsigned long minutes)
+{
+	unsigned int data;
+
+	if (minutes > 70)
+		return -EINVAL;
+
+	data = minutes / 10;
+	data <<= CHG_CNFG_03_TOTIME_SHIFT;
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_03,
+			CHG_CNFG_03_TOTIME_MASK, data);
+}
+
+static ssize_t top_off_timer_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	return device_attr_store(dev, attr, buf, count,
+			max77693_set_top_off_timer);
+}
+
+static DEVICE_ATTR_RW(fast_charge_timer);
+static DEVICE_ATTR_RW(top_off_threshold_current);
+static DEVICE_ATTR_RW(top_off_timer);
+
+static int max77693_set_constant_volt(struct max77693_charger *chg,
+		unsigned int uvolt)
+{
+	unsigned int data;
+
+	/*
+	 * 0x00 - 3.650 V
+	 * 0x01 - 3.675 V
+	 * ...
+	 * 0x1b - 4.325 V
+	 * 0x1c - 4.340 V
+	 * 0x1d - 4.350 V
+	 * 0x1e - 4.375 V
+	 * 0x1f - 4.400 V
+	 */
+	if (uvolt >= 3650000 && uvolt < 4340000)
+		data = (uvolt - 3650000) / 25000;
+	else if (uvolt >= 4340000 && uvolt < 4350000)
+		data = 0x1c;
+	else if (uvolt >= 4350000 && uvolt <= 4400000)
+		data = 0x1d + (uvolt - 4350000) / 25000;
+	else {
+		dev_err(chg->dev, "Wrong value for charging constant voltage\n");
+		return -EINVAL;
+	}
+
+	data <<= CHG_CNFG_04_CHGCVPRM_SHIFT;
+
+	dev_dbg(chg->dev, "Charging constant voltage: %u (0x%x)\n", uvolt,
+			data);
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_04,
+			CHG_CNFG_04_CHGCVPRM_MASK, data);
+}
+
+static int max77693_set_min_system_volt(struct max77693_charger *chg,
+		unsigned int uvolt)
+{
+	unsigned int data;
+
+	if (uvolt < 3000000 || uvolt > 3700000) {
+		dev_err(chg->dev, "Wrong value for minimum system regulation voltage\n");
+		return -EINVAL;
+	}
+
+	data = (uvolt - 3000000) / 100000;
+
+	data <<= CHG_CNFG_04_MINVSYS_SHIFT;
+
+	dev_dbg(chg->dev, "Minimum system regulation voltage: %u (0x%x)\n",
+			uvolt, data);
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_04,
+			CHG_CNFG_04_MINVSYS_MASK, data);
+}
+
+static int max77693_set_thermal_regulation_temp(struct max77693_charger *chg,
+		unsigned int cels)
+{
+	unsigned int data;
+
+	switch (cels) {
+	case 70:
+	case 85:
+	case 100:
+	case 115:
+		data = (cels - 70) / 15;
+		break;
+	default:
+		dev_err(chg->dev, "Wrong value for thermal regulation loop temperature\n");
+		return -EINVAL;
+	}
+
+	data <<= CHG_CNFG_07_REGTEMP_SHIFT;
+
+	dev_dbg(chg->dev, "Thermal regulation loop temperature: %u (0x%x)\n",
+			cels, data);
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_07,
+			CHG_CNFG_07_REGTEMP_MASK, data);
+}
+
+static int max77693_set_batttery_overcurrent(struct max77693_charger *chg,
+		unsigned int uamp)
+{
+	unsigned int data;
+
+	if (uamp && (uamp < 2000000 || uamp > 3500000)) {
+		dev_err(chg->dev, "Wrong value for battery overcurrent\n");
+		return -EINVAL;
+	}
+
+	if (uamp)
+		data = ((uamp - 2000000) / 250000) + 1;
+	else
+		data = 0; /* disable */
+
+	data <<= CHG_CNFG_12_B2SOVRC_SHIFT;
+
+	dev_dbg(chg->dev, "Battery overcurrent: %u (0x%x)\n", uamp, data);
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_12,
+			CHG_CNFG_12_B2SOVRC_MASK, data);
+}
+
+static int max77693_set_charge_input_threshold_volt(struct max77693_charger *chg,
+		unsigned int uvolt)
+{
+	unsigned int data;
+
+	switch (uvolt) {
+	case 4300000:
+		data = 0x0;
+		break;
+	case 4700000:
+	case 4800000:
+	case 4900000:
+		data = (uvolt - 4700000) / 100000;
+	default:
+		dev_err(chg->dev, "Wrong value for charge input voltage regulation threshold\n");
+		return -EINVAL;
+	}
+
+	data <<= CHG_CNFG_12_VCHGINREG_SHIFT;
+
+	dev_dbg(chg->dev, "Charge input voltage regulation threshold: %u (0x%x)\n",
+			uvolt, data);
+
+	return regmap_update_bits(chg->max77693->regmap,
+			MAX77693_CHG_REG_CHG_CNFG_12,
+			CHG_CNFG_12_VCHGINREG_MASK, data);
+}
+
+/*
+ * Sets charger registers to proper and safe default values.
+ */
+static int max77693_reg_init(struct max77693_charger *chg)
+{
+	int ret;
+	unsigned int data;
+
+	/* Unlock charger register protection */
+	data = (0x3 << CHG_CNFG_06_CHGPROT_SHIFT);
+	ret = regmap_update_bits(chg->max77693->regmap,
+				MAX77693_CHG_REG_CHG_CNFG_06,
+				CHG_CNFG_06_CHGPROT_MASK, data);
+	if (ret) {
+		dev_err(chg->dev, "Error unlocking registers: %d\n", ret);
+		return ret;
+	}
+
+	ret = max77693_set_fast_charge_timer(chg, DEFAULT_FAST_CHARGE_TIMER);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_top_off_threshold_current(chg,
+			DEFAULT_TOP_OFF_THRESHOLD_CURRENT);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_top_off_timer(chg, DEFAULT_TOP_OFF_TIMER);
+	if (ret)
+		return ret;
+
+	if (!chg->pdata)
+		return 0;
+
+	ret = max77693_set_constant_volt(chg,
+			chg->pdata->constant_volt);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_min_system_volt(chg,
+			chg->pdata->min_system_volt);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_thermal_regulation_temp(chg,
+			chg->pdata->thermal_regulation_temp);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_batttery_overcurrent(chg,
+			chg->pdata->batttery_overcurrent);
+	if (ret)
+		return ret;
+
+	ret = max77693_set_charge_input_threshold_volt(chg,
+			chg->pdata->charge_input_threshold_volt);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+#ifdef CONFIG_OF
+static struct max77693_charger_platform_data *max77693_dt_init(
+		struct device *dev)
+{
+	struct max77693_charger_platform_data *pdata;
+	struct device_node *np = dev->of_node;
+
+	if (!np)
+		return NULL;
+
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
+	if (!pdata)
+		return NULL;
+
+	if (of_property_read_u32(np, "maxim,constant-microvolt",
+			&pdata->constant_volt))
+		pdata->constant_volt = DEFAULT_CONSTANT_VOLT;
+
+	if (of_property_read_u32(np, "maxim,min-system-microvolt",
+			&pdata->min_system_volt))
+		pdata->min_system_volt = DEFAULT_MIN_SYSTEM_VOLT;
+
+	if (of_property_read_u32(np, "maxim,thermal-regulation-celsius",
+			&pdata->thermal_regulation_temp))
+		pdata->thermal_regulation_temp = DEFAULT_THERMAL_REGULATION_TEMP;
+
+	if (of_property_read_u32(np, "maxim,battery-overcurrent-microamp",
+			&pdata->batttery_overcurrent))
+		pdata->batttery_overcurrent = DEFAULT_BATTERY_OVERCURRENT;
+
+	if (of_property_read_u32(np, "maxim,charge-input-threshold-microvolt",
+			&pdata->charge_input_threshold_volt))
+		pdata->charge_input_threshold_volt =
+			DEFAULT_CHARGER_INPUT_THRESHOLD_VOLT;
+
+	return pdata;
+}
+#else /* CONFIG_OF */
+static struct max77693_charger_platform_data *max77693_dt_init(
+		struct device *dev)
+{
+	return NULL;
+}
+#endif /* CONFIG_OF */
+
+static int max77693_charger_probe(struct platform_device *pdev)
+{
+	struct max77693_charger *chg;
+	struct max77693_dev *max77693 = dev_get_drvdata(pdev->dev.parent);
+	int ret;
+
+	chg = devm_kzalloc(&pdev->dev, sizeof(*chg), GFP_KERNEL);
+	if (!chg)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, chg);
+	chg->dev = &pdev->dev;
+	chg->max77693 = max77693;
+
+	chg->pdata = max77693_dt_init(&pdev->dev);
+
+	ret = max77693_reg_init(chg);
+	if (ret)
+		return ret;
+
+	chg->charger.name = max77693_charger_name;
+	chg->charger.type = POWER_SUPPLY_TYPE_BATTERY;
+	chg->charger.properties = max77693_charger_props;
+	chg->charger.num_properties = ARRAY_SIZE(max77693_charger_props);
+	chg->charger.get_property = max77693_charger_get_property;
+
+	ret = device_create_file(&pdev->dev, &dev_attr_fast_charge_timer);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: create fast charge timer sysfs entry\n");
+		goto err;
+	}
+
+	ret = device_create_file(&pdev->dev,
+			&dev_attr_top_off_threshold_current);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: create top off current sysfs entry\n");
+		goto err;
+	}
+
+	ret = device_create_file(&pdev->dev, &dev_attr_top_off_timer);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: create top off timer sysfs entry\n");
+		goto err;
+	}
+
+	ret = power_supply_register(&pdev->dev, &chg->charger);
+	if (ret) {
+		dev_err(&pdev->dev, "failed: power supply register\n");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	device_remove_file(&pdev->dev, &dev_attr_top_off_timer);
+	device_remove_file(&pdev->dev, &dev_attr_top_off_threshold_current);
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
+
+	return ret;
+}
+
+static int max77693_charger_remove(struct platform_device *pdev)
+{
+	struct max77693_charger *chg = platform_get_drvdata(pdev);
+
+	device_remove_file(&pdev->dev, &dev_attr_top_off_timer);
+	device_remove_file(&pdev->dev, &dev_attr_top_off_threshold_current);
+	device_remove_file(&pdev->dev, &dev_attr_fast_charge_timer);
+
+	power_supply_unregister(&chg->charger);
+
+	return 0;
+}
+
+static const struct platform_device_id max77693_charger_id[] = {
+	{ "max77693-charger", 0, },
+	{ }
+};
+MODULE_DEVICE_TABLE(platform, max77693_charger_id);
+
+static struct platform_driver max77693_charger_driver = {
+	.driver = {
+		.owner	= THIS_MODULE,
+		.name	= "max77693-charger",
+	},
+	.probe		= max77693_charger_probe,
+	.remove		= max77693_charger_remove,
+	.id_table	= max77693_charger_id,
+};
+module_platform_driver(max77693_charger_driver);
+
+MODULE_AUTHOR("Krzysztof Kozlowski <k.kozlowski@samsung.com>");
+MODULE_DESCRIPTION("Maxim 77693 charger driver");
+MODULE_LICENSE("GPL");
-- 
1.9.1

^ permalink raw reply related

* [PATCH 1/7] mfd: max77693: Add defines for MAX77693 charger driver
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski
In-Reply-To: <1412252528-30148-1-git-send-email-k.kozlowski@samsung.com>

Prepare for adding support for Maxim 77693 charger by adding necessary
new defines and structure for device tree parsed data.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
---
 include/linux/mfd/max77693-private.h | 108 +++++++++++++++++++++++++++++++++++
 include/linux/mfd/max77693.h         |   8 +++
 2 files changed, 116 insertions(+)

diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index fc17d56581b2..e1b2b61285b9 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -144,10 +144,118 @@ enum max77693_pmic_reg {
 #define FLASH_INT_FLED1_SHORT	BIT(3)
 #define FLASH_INT_OVER_CURRENT	BIT(4)
 
+/* Fast charge timer in in hours */
+#define DEFAULT_FAST_CHARGE_TIMER		4
+/* microamps */
+#define DEFAULT_TOP_OFF_THRESHOLD_CURRENT	150000
+/* minutes */
+#define DEFAULT_TOP_OFF_TIMER			30
+/* microvolts */
+#define DEFAULT_CONSTANT_VOLT			4200000
+/* microvolts */
+#define DEFAULT_MIN_SYSTEM_VOLT			3600000
+/* celsius */
+#define DEFAULT_THERMAL_REGULATION_TEMP		100
+/* microamps */
+#define DEFAULT_BATTERY_OVERCURRENT		3500000
+/* microvolts */
+#define DEFAULT_CHARGER_INPUT_THRESHOLD_VOLT	4300000
+
+/* MAX77693_CHG_REG_CHG_INT_OK register */
+#define CHG_INT_OK_BYP_SHIFT		0
+#define CHG_INT_OK_BAT_SHIFT		3
+#define CHG_INT_OK_CHG_SHIFT		4
+#define CHG_INT_OK_CHGIN_SHIFT		6
+#define CHG_INT_OK_DETBAT_SHIFT		7
+#define CHG_INT_OK_BYP_MASK		BIT(CHG_INT_OK_BYP_SHIFT)
+#define CHG_INT_OK_BAT_MASK		BIT(CHG_INT_OK_BAT_SHIFT)
+#define CHG_INT_OK_CHG_MASK		BIT(CHG_INT_OK_CHG_SHIFT)
+#define CHG_INT_OK_CHGIN_MASK		BIT(CHG_INT_OK_CHGIN_SHIFT)
+#define CHG_INT_OK_DETBAT_MASK		BIT(CHG_INT_OK_DETBAT_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_00 register */
+#define CHG_DETAILS_00_CHGIN_SHIFT	5
+#define CHG_DETAILS_00_CHGIN_MASK	(0x3 << CHG_DETAILS_00_CHGIN_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01 register */
+#define CHG_DETAILS_01_CHG_SHIFT	0
+#define CHG_DETAILS_01_BAT_SHIFT	4
+#define CHG_DETAILS_01_TREG_SHIFT	7
+#define CHG_DETAILS_01_CHG_MASK		(0xf << CHG_DETAILS_01_CHG_SHIFT)
+#define CHG_DETAILS_01_BAT_MASK		(0x7 << CHG_DETAILS_01_BAT_SHIFT)
+#define CHG_DETAILS_01_TREG_MASK	BIT(7)
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01/CHG field */
+enum max77693_charger_charging_state {
+	MAX77693_CHARGING_PREQUALIFICATION	= 0x0,
+	MAX77693_CHARGING_FAST_CONST_CURRENT,
+	MAX77693_CHARGING_FAST_CONST_VOLTAGE,
+	MAX77693_CHARGING_TOP_OFF,
+	MAX77693_CHARGING_DONE,
+	MAX77693_CHARGING_HIGH_TEMP,
+	MAX77693_CHARGING_TIMER_EXPIRED,
+	MAX77693_CHARGING_THERMISTOR_SUSPEND,
+	MAX77693_CHARGING_OFF,
+	MAX77693_CHARGING_RESERVED,
+	MAX77693_CHARGING_OVER_TEMP,
+	MAX77693_CHARGING_WATCHDOG_EXPIRED,
+};
+
+/* MAX77693_CHG_REG_CHG_DETAILS_01/BAT field */
+enum max77693_charger_battery_state {
+	MAX77693_BATTERY_NOBAT			= 0x0,
+	/* Dead-battery or low-battery prequalification */
+	MAX77693_BATTERY_PREQUALIFICATION,
+	MAX77693_BATTERY_TIMER_EXPIRED,
+	MAX77693_BATTERY_GOOD,
+	MAX77693_BATTERY_LOWVOLTAGE,
+	MAX77693_BATTERY_OVERVOLTAGE,
+	MAX77693_BATTERY_OVERCURRENT,
+	MAX77693_BATTERY_RESERVED,
+};
+
+/* MAX77693_CHG_REG_CHG_DETAILS_02 register */
+#define CHG_DETAILS_02_BYP_SHIFT	0
+#define CHG_DETAILS_02_BYP_MASK		(0xf << CHG_DETAILS_02_BYP_SHIFT)
+
 /* MAX77693 CHG_CNFG_00 register */
 #define CHG_CNFG_00_CHG_MASK		0x1
 #define CHG_CNFG_00_BUCK_MASK		0x4
 
+/* MAX77693_CHG_REG_CHG_CNFG_01 register */
+#define CHG_CNFG_01_FCHGTIME_SHIFT	0
+#define CHG_CNFG_01_CHGRSTRT_SHIFT	4
+#define CHG_CNFG_01_PQEN_SHIFT		7
+#define CHG_CNFG_01_FCHGTIME_MASK	(0x7 << CHG_CNFG_01_FCHGTIME_SHIFT)
+#define CHG_CNFG_01_CHGRSTRT_MASK	(0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT)
+#define CHG_CNFG_01_PQEN_MAKS		BIT(CHG_CNFG_01_PQEN_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_03 register */
+#define CHG_CNFG_03_TOITH_SHIFT		0
+#define CHG_CNFG_03_TOTIME_SHIFT	3
+#define CHG_CNFG_03_TOITH_MASK		(0x7 << CHG_CNFG_03_TOITH_SHIFT)
+#define CHG_CNFG_03_TOTIME_MASK		(0x7 << CHG_CNFG_03_TOTIME_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_04 register */
+#define CHG_CNFG_04_CHGCVPRM_SHIFT	0
+#define CHG_CNFG_04_MINVSYS_SHIFT	5
+#define CHG_CNFG_04_CHGCVPRM_MASK	(0x1f << CHG_CNFG_04_CHGCVPRM_SHIFT)
+#define CHG_CNFG_04_MINVSYS_MASK	(0x7 << CHG_CNFG_04_MINVSYS_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_06 register */
+#define CHG_CNFG_06_CHGPROT_SHIFT	2
+#define CHG_CNFG_06_CHGPROT_MASK	(0x3 << CHG_CNFG_06_CHGPROT_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_07 register */
+#define CHG_CNFG_07_REGTEMP_SHIFT	5
+#define CHG_CNFG_07_REGTEMP_MASK	(0x3 << CHG_CNFG_07_REGTEMP_SHIFT)
+
+/* MAX77693_CHG_REG_CHG_CNFG_12 register */
+#define CHG_CNFG_12_B2SOVRC_SHIFT	0
+#define CHG_CNFG_12_VCHGINREG_SHIFT	3
+#define CHG_CNFG_12_B2SOVRC_MASK	(0x7 << CHG_CNFG_12_B2SOVRC_SHIFT)
+#define CHG_CNFG_12_VCHGINREG_MASK	(0x3 << CHG_CNFG_12_VCHGINREG_SHIFT)
+
 /* MAX77693 CHG_CNFG_09 Register */
 #define CHG_CNFG_09_CHGIN_ILIM_MASK	0x7F
 
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index f0b6585cd874..88ef24b28294 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -63,6 +63,14 @@ struct max77693_muic_platform_data {
 	int path_uart;
 };
 
+struct max77693_charger_platform_data {
+	u32 constant_volt;
+	u32 min_system_volt;
+	u32 thermal_regulation_temp;
+	u32 batttery_overcurrent;
+	u32 charge_input_threshold_volt;
+};
+
 /* MAX77693 led flash */
 
 /* triggers */
-- 
1.9.1

^ permalink raw reply related

* [PATCH 0/7] power/mfd: Add max77693 charger driver
From: Krzysztof Kozlowski @ 2014-10-02 12:22 UTC (permalink / raw)
  To: Sebastian Reichel, Dmitry Eremin-Solenikov, David Woodhouse,
	Samuel Ortiz, Lee Jones, linux-kernel, linux-pm, Rob Herring,
	Pawel Moll, Mark Rutland, Ian Campbell, Kumar Gala, devicetree,
	linux-api
  Cc: Ben Dooks, Kukjin Kim, Russell King, Javier Martinez Canillas,
	linux-arm-kernel, linux-samsung-soc, Kyungmin Park,
	Marek Szyprowski, Bartlomiej Zolnierkiewicz, Tomasz Figa,
	Krzysztof Kozlowski

Hi,


The patchset adds max77693 charger driver present on Trats2 board
(and Galaxy S III). The driver configures battery charger and exposes
power supply interface.

Driver is necessary to provide full charging stack on Trats2 device
(extcon, charger-manager etc.).

The first 2 patches depend on each other but the rest (documentation,
DTS, defconfigs) can be pulled independently.

Everything rebased on next-20140926.


P.S. Unfortunately the pathset touches defconfigs, dts and documentation
(new bindings) so the recipients list is huge. Sorry for that.


Best regards,
Krzysztof

Krzysztof Kozlowski (7):
  mfd: max77693: Add defines for MAX77693 charger driver
  power: max77693: Add charger driver for Maxim 77693
  devicetree: mfd: max77693: Document new bindings for charger
  Documentation: charger: max77693: Document exported sysfs entry
  ARM: dts: exynos4412-trats: Add max77693 charger node
  ARM: exynos_defconfig: Enable Maxim 77693 charger
  ARM: multi_v7_defconfig: Enable Maxim 77693 charger

 Documentation/ABI/testing/sysfs-class-power        |  42 ++
 Documentation/devicetree/bindings/mfd/max77693.txt |  46 ++
 arch/arm/boot/dts/exynos4412-trats2.dts            |  10 +
 arch/arm/configs/exynos_defconfig                  |   1 +
 arch/arm/configs/multi_v7_defconfig                |   1 +
 drivers/power/Kconfig                              |   6 +
 drivers/power/Makefile                             |   1 +
 drivers/power/max77693_charger.c                   | 763 +++++++++++++++++++++
 include/linux/mfd/max77693-private.h               | 108 +++
 include/linux/mfd/max77693.h                       |   8 +
 10 files changed, 986 insertions(+)
 create mode 100644 drivers/power/max77693_charger.c

-- 
1.9.1


^ permalink raw reply

* [PATCH] Documentation: charger: max14577: Update the date of introducing ABI
From: Krzysztof Kozlowski @ 2014-10-02 12:12 UTC (permalink / raw)
  To: Sebastian Reichel, linux-api-u79uwXL29TY76Z2rM5mHXA,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA
  Cc: Lee Jones, Krzysztof Kozlowski

Update the date of introducing max14577 charger's ABI (fast_charge_timer
sysfs entry) to approximate date of kernel release which actually
introduces this.

The old date came from previous driver submissions.

Signed-off-by: Krzysztof Kozlowski <k.kozlowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
---
 Documentation/ABI/testing/sysfs-class-power | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/ABI/testing/sysfs-class-power b/Documentation/ABI/testing/sysfs-class-power
index ad4fb90ab23d..909e7602c717 100644
--- a/Documentation/ABI/testing/sysfs-class-power
+++ b/Documentation/ABI/testing/sysfs-class-power
@@ -20,7 +20,7 @@ Description:
 		amended over time.
 
 What:		/sys/class/power_supply/max14577-charger/device/fast_charge_timer
-Date:		July 2014
+Date:		October 2014
 KernelVersion:	3.18.0
 Contact:	Krzysztof Kozlowski <k.kozlowski-Sze3O3UU22JBDgjK7y7TUQ@public.gmane.org>
 Description:
-- 
1.9.1

^ permalink raw reply related

* Re: [PATCH] fanotify: add a flag to allow setting O_CLOEXEC on event fd
From: Michael Kerrisk (man-pages) @ 2014-10-02 11:55 UTC (permalink / raw)
  To: Pádraig Brady
  Cc: Yann Droneaud, Andrew Morton, Heinrich Schuchardt, Eric Paris,
	Richard Guy Briggs, Al Viro, lkml, linux-fsdevel@vger.kernel.org,
	stable, Linux API, Jan Kara, Lino Sanfilippo, Valdis Kletnieks
In-Reply-To: <542D1726.3040801@draigBrady.com>

On Thu, Oct 2, 2014 at 11:13 AM, Pádraig Brady <P@draigbrady.com> wrote:
> On 10/02/2014 08:52 AM, Yann Droneaud wrote:
>> In order to not potentially break applications which were
>> requesting O_CLOEXEC on event file descriptors but which
>> actually need it to be not effective as the kernel currently
>> ignore the flag, so the file descriptor is inherited accross
>> exec regardless of O_CLOEXEC (please forgive me for the
>> wording), this patch introduces FAN_FD_CLOEXEC flag to
>> fanotify_init() so that application can request O_CLOEXEC
>> to be effective.
>> Newer application would use FAN_FD_CLOEXEC flag along
>> O_CLOEXEC to enable close on exec on newly created
>> file descriptor:
>>
>>   fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK|FAN_FD_CLOEXEC,
>>                      O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);
>
> Ugh really?
> IMHO there should be widespread or at least known breakage with
> O_CLOEXEC before adding messiness like this.
> It seems surprising to me that apps that would depend on
> O_CLOEXEC being ineffective.
>
> please reconsider this one.

Agreed. The number of applications for which there are silent (not
*yet* observed) breakages because O_CLOEXEC is not working as expected
is likely rather larger than the set of applications that randomly
specify O_CLOEXEC and then somehow get broken as a result.

Cheers,

Michael


-- 
Michael Kerrisk
Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/
Linux/UNIX System Programming Training: http://man7.org/training/

^ permalink raw reply

* Re: [PATCHv8.1] fanotify: enable close-on-exec on events' fd when requested in fanotify_init()
From: Jan Kara @ 2014-10-02 10:44 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Yann Droneaud, Heinrich Schuchardt, Eric Paris,
	Richard Guy Briggs, Al Viro, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	stable-u79uwXL29TY76Z2rM5mHXA, linux-api-u79uwXL29TY76Z2rM5mHXA,
	Jan Kara, Lino Sanfilippo, Valdis Kletnieks,
	Michael Kerrisk-manpages
In-Reply-To: <20141001153621.65e9258e65a6167bf2e4cb50-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>

On Wed 01-10-14 15:36:21, Andrew Morton wrote:
> On Mon, 29 Sep 2014 10:49:15 +0200 Yann Droneaud <ydroneaud-RlY5vtjFyJ3QT0dZR+AlfA@public.gmane.org> wrote:
> 
> > According to commit 80af258867648 ('fanotify: groups can specify
> > their f_flags for new fd'), file descriptors created as part of
> > file access notification events inherit flags from the
> > event_f_flags argument passed to syscall fanotify_init(2).
> > 
> > So while it is legal for userspace to call fanotify_init() with
> > O_CLOEXEC as part of its second argument, O_CLOEXEC is currently
> > silently ignored.
> > 
> > Indeed event_f_flags are only given to dentry_open(), which only
> > seems to care about O_ACCMODE and O_PATH in do_dentry_open(),
> > O_DIRECT in open_check_o_direct() and O_LARGEFILE in
> > generic_file_open().
> > 
> > But it seems logical to set close-on-exec flag on the file
> > descriptor if userspace is allowed to request it with O_CLOEXEC.
> > 
> > In fact, according to some lookup on http://codesearch.debian.net/
> > and various search engine, there's already some userspace code
> > requesting it:
> > 
> > - in systemd's readahead[2]:
> > 
> >     fanotify_fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK, O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);
> > 
> > - in clsync[3]:
> > 
> >     #define FANOTIFY_EVFLAGS (O_LARGEFILE|O_RDONLY|O_CLOEXEC)
> > 
> >     int fanotify_d = fanotify_init(FANOTIFY_FLAGS, FANOTIFY_EVFLAGS);
> > 
> > - in examples [4] from "Filesystem monitoring in the Linux
> >   kernel" article[5] by Aleksander Morgado:
> > 
> >     if ((fanotify_fd = fanotify_init (FAN_CLOEXEC,
> >                                       O_RDONLY | O_CLOEXEC | O_LARGEFILE)) < 0)
> 
> So we have a number of apps which are setting O_CLOEXEC, but it doesn't
> actually work.  With this change it *will* work, so the behaviour of
> those apps might change, possibly breaking them?
  Possibly. OTOH I'd dare to say that most of the apps specifying O_CLOEXEC
want that behavior and their security may be weakened by the fact that
O_CLOEXEC is ignored. So we are weighting possible security issues for apps
doing things right (and Mihai mentioned in this thread that at least he has
an application which needs O_CLOEXEC working) against possible breakage for
apps which just randomly set O_CLOEXEC without wanting. So I'm really for
fixing O_CLOEXEC behavior.

								Honza
-- 
Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
SUSE Labs, CR

^ permalink raw reply

* Re: [PATCH] fanotify: add a flag to allow setting O_CLOEXEC on event fd
From: Pádraig Brady @ 2014-10-02  9:13 UTC (permalink / raw)
  To: Yann Droneaud
  Cc: Andrew Morton, Heinrich Schuchardt, Eric Paris,
	Richard Guy Briggs, Al Viro, linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	stable-u79uwXL29TY76Z2rM5mHXA, linux-api-u79uwXL29TY76Z2rM5mHXA,
	Jan Kara, Lino Sanfilippo, Valdis Kletnieks,
	Michael Kerrisk-manpages
In-Reply-To: <1412236349-30035-1-git-send-email-ydroneaud-RlY5vtjFyJ3QT0dZR+AlfA@public.gmane.org>

On 10/02/2014 08:52 AM, Yann Droneaud wrote:
> In order to not potentially break applications which were
> requesting O_CLOEXEC on event file descriptors but which
> actually need it to be not effective as the kernel currently
> ignore the flag, so the file descriptor is inherited accross
> exec regardless of O_CLOEXEC (please forgive me for the
> wording), this patch introduces FAN_FD_CLOEXEC flag to
> fanotify_init() so that application can request O_CLOEXEC
> to be effective.
> Newer application would use FAN_FD_CLOEXEC flag along
> O_CLOEXEC to enable close on exec on newly created
> file descriptor:
> 
>   fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK|FAN_FD_CLOEXEC,
>                      O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);

Ugh really?
IMHO there should be widespread or at least known breakage with
O_CLOEXEC before adding messiness like this.
It seems surprising to me that apps that would depend on
O_CLOEXEC being ineffective.

please reconsider this one.

thanks,
Pádraig.

^ permalink raw reply

* [PATCH] fanotify: add a flag to allow setting O_CLOEXEC on event fd
From: Yann Droneaud @ 2014-10-02  7:52 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Yann Droneaud, Heinrich Schuchardt, Eric Paris,
	Richard Guy Briggs, Al Viro, linux-kernel, linux-fsdevel, stable,
	linux-api, Jan Kara, Lino Sanfilippo, Valdis Kletnieks,
	Michael Kerrisk-manpages
In-Reply-To: <1412230855.28184.5.camel@localhost.localdomain>

In order to not potentially break applications which were
requesting O_CLOEXEC on event file descriptors but which
actually need it to be not effective as the kernel currently
ignore the flag, so the file descriptor is inherited accross
exec regardless of O_CLOEXEC (please forgive me for the
wording), this patch introduces FAN_FD_CLOEXEC flag to
fanotify_init() so that application can request O_CLOEXEC
to be effective.
Newer application would use FAN_FD_CLOEXEC flag along
O_CLOEXEC to enable close on exec on newly created
file descriptor:

  fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK|FAN_FD_CLOEXEC,
                     O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);

Signed-off-by: Yann Droneaud <ydroneaud@opteya.com>
---

Hi Andrew,

While I believe fanotify_init() must enable close-on-exec
when requested by userspace to prevent unwelcomed security
issue, I understand your concerns regarding the possible
breakage on userspace application requesting O_CLOEXEC
but relying on it not being enable on file descriptor
created for the events.

So with a new flag to fanotify_init(), we could allow
newer applications to really enable O_CLOEXEC.

But I feel bad to have to force application to specify
twice they want close on exec:
  - are you sure ?
  - are you really sure ?
  - is this your final answer ?
  ...

Regards.

Yann Droneaud
OPTEYA


 fs/notify/fanotify/fanotify_user.c | 6 +++++-
 include/uapi/linux/fanotify.h      | 5 ++++-
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index c991616acca9..3c1fb1412f37 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -78,7 +78,7 @@ static int create_fd(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags);
+	client_fd = get_unused_fd_flags(group->fanotify_data.f_flags & O_CLOEXEC);
 	if (client_fd < 0)
 		return client_fd;
 
@@ -706,6 +706,10 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 		return -EINVAL;
 	}
 
+	if ((event_f_flags & O_CLOEXEC) &&
+	    !(flags & FAN_FD_CLOEXEC))
+		event_f_flags ^= O_CLOEXEC;
+
 	user = get_current_user();
 	if (atomic_read(&user->fanotify_listeners) > FANOTIFY_DEFAULT_MAX_LISTENERS) {
 		free_uid(user);
diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h
index 030508d195d3..f2d517be3152 100644
--- a/include/uapi/linux/fanotify.h
+++ b/include/uapi/linux/fanotify.h
@@ -36,7 +36,10 @@
 #define FAN_UNLIMITED_QUEUE	0x00000010
 #define FAN_UNLIMITED_MARKS	0x00000020
 
-#define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | \
+/* flags used for fanotify_init() too */
+#define FAN_FD_CLOEXEC		0x00000100
+
+#define FAN_ALL_INIT_FLAGS	(FAN_CLOEXEC | FAN_NONBLOCK | FAN_FD_CLOEXEC | \
 				 FAN_ALL_CLASS_BITS | FAN_UNLIMITED_QUEUE |\
 				 FAN_UNLIMITED_MARKS)
 
-- 
1.9.3

^ permalink raw reply related

* Re: [PATCHv8.1] fanotify: enable close-on-exec on events' fd when requested in fanotify_init()
From: Mihai Donțu @ 2014-10-02  6:50 UTC (permalink / raw)
  To: Yann Droneaud
  Cc: Andrew Morton, Heinrich Schuchardt, Eric Paris,
	Richard Guy Briggs, Al Viro, linux-kernel, linux-fsdevel, stable,
	linux-api, Jan Kara, Lino Sanfilippo, Valdis Kletnieks,
	Michael Kerrisk-manpages
In-Reply-To: <1412230855.28184.5.camel@localhost.localdomain>

On Thu, 02 Oct 2014 08:20:55 +0200 Yann Droneaud wrote:
> Hi,
> 
> Le mercredi 01 octobre 2014 à 15:36 -0700, Andrew Morton a écrit :
> > On Mon, 29 Sep 2014 10:49:15 +0200 Yann Droneaud <ydroneaud@opteya.com> wrote:
> > 
> > > According to commit 80af258867648 ('fanotify: groups can specify
> > > their f_flags for new fd'), file descriptors created as part of
> > > file access notification events inherit flags from the
> > > event_f_flags argument passed to syscall fanotify_init(2).
> > > 
> > > So while it is legal for userspace to call fanotify_init() with
> > > O_CLOEXEC as part of its second argument, O_CLOEXEC is currently
> > > silently ignored.
> > > 
> > > Indeed event_f_flags are only given to dentry_open(), which only
> > > seems to care about O_ACCMODE and O_PATH in do_dentry_open(),
> > > O_DIRECT in open_check_o_direct() and O_LARGEFILE in
> > > generic_file_open().
> > > 
> > > But it seems logical to set close-on-exec flag on the file
> > > descriptor if userspace is allowed to request it with O_CLOEXEC.
> > > 
> > > In fact, according to some lookup on http://codesearch.debian.net/
> > > and various search engine, there's already some userspace code
> > > requesting it:
> > > 
> > > - in systemd's readahead[2]:
> > > 
> > >     fanotify_fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK, O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);
> > > 
> > > - in clsync[3]:
> > > 
> > >     #define FANOTIFY_EVFLAGS (O_LARGEFILE|O_RDONLY|O_CLOEXEC)
> > > 
> > >     int fanotify_d = fanotify_init(FANOTIFY_FLAGS, FANOTIFY_EVFLAGS);
> > > 
> > > - in examples [4] from "Filesystem monitoring in the Linux
> > >   kernel" article[5] by Aleksander Morgado:
> > > 
> > >     if ((fanotify_fd = fanotify_init (FAN_CLOEXEC,
> > >                                       O_RDONLY | O_CLOEXEC | O_LARGEFILE)) < 0)
> > 
> > So we have a number of apps which are setting O_CLOEXEC, but it doesn't
> > actually work.  With this change it *will* work, so the behaviour of
> > those apps might change, possibly breaking them?
> > 
> 
> In the other hand, not enabling close-on-exec might expose unwanted file
> descriptor to childs, creating security issues. YMMV.
> 

As someone who uses fanotify for content introspection, I can say that
I am _explicitly_ marking the fd obtained via read() as O_CLOEXEC,
because I have encountered a situation where a child managed to create
a deadlock because it kept the fd open after the main application
responded with FAN_ALLOW.

-- 
Mihai Donțu

^ permalink raw reply

* Re: [PATCHv8.1] fanotify: enable close-on-exec on events' fd when requested in fanotify_init()
From: Yann Droneaud @ 2014-10-02  6:20 UTC (permalink / raw)
  To: Andrew Morton
  Cc: Heinrich Schuchardt, Eric Paris, Richard Guy Briggs, Al Viro,
	linux-kernel, linux-fsdevel, stable, linux-api, Jan Kara,
	Lino Sanfilippo, Valdis Kletnieks, Michael Kerrisk-manpages,
	Yann Droneaud
In-Reply-To: <20141001153621.65e9258e65a6167bf2e4cb50@linux-foundation.org>

Hi,

Le mercredi 01 octobre 2014 à 15:36 -0700, Andrew Morton a écrit :
> On Mon, 29 Sep 2014 10:49:15 +0200 Yann Droneaud <ydroneaud@opteya.com> wrote:
> 
> > According to commit 80af258867648 ('fanotify: groups can specify
> > their f_flags for new fd'), file descriptors created as part of
> > file access notification events inherit flags from the
> > event_f_flags argument passed to syscall fanotify_init(2).
> > 
> > So while it is legal for userspace to call fanotify_init() with
> > O_CLOEXEC as part of its second argument, O_CLOEXEC is currently
> > silently ignored.
> > 
> > Indeed event_f_flags are only given to dentry_open(), which only
> > seems to care about O_ACCMODE and O_PATH in do_dentry_open(),
> > O_DIRECT in open_check_o_direct() and O_LARGEFILE in
> > generic_file_open().
> > 
> > But it seems logical to set close-on-exec flag on the file
> > descriptor if userspace is allowed to request it with O_CLOEXEC.
> > 
> > In fact, according to some lookup on http://codesearch.debian.net/
> > and various search engine, there's already some userspace code
> > requesting it:
> > 
> > - in systemd's readahead[2]:
> > 
> >     fanotify_fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK, O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);
> > 
> > - in clsync[3]:
> > 
> >     #define FANOTIFY_EVFLAGS (O_LARGEFILE|O_RDONLY|O_CLOEXEC)
> > 
> >     int fanotify_d = fanotify_init(FANOTIFY_FLAGS, FANOTIFY_EVFLAGS);
> > 
> > - in examples [4] from "Filesystem monitoring in the Linux
> >   kernel" article[5] by Aleksander Morgado:
> > 
> >     if ((fanotify_fd = fanotify_init (FAN_CLOEXEC,
> >                                       O_RDONLY | O_CLOEXEC | O_LARGEFILE)) < 0)
> 
> So we have a number of apps which are setting O_CLOEXEC, but it doesn't
> actually work.  With this change it *will* work, so the behaviour of
> those apps might change, possibly breaking them?
> 

In the other hand, not enabling close-on-exec might expose unwanted file
descriptor to childs, creating security issues. YMMV.

-- 
Yann Droneaud
OPTEYA

^ permalink raw reply

* Re: [PATCHv8.1] fanotify: enable close-on-exec on events' fd when requested in fanotify_init()
From: Andrew Morton @ 2014-10-01 22:36 UTC (permalink / raw)
  To: Yann Droneaud
  Cc: Heinrich Schuchardt, Eric Paris, Richard Guy Briggs, Al Viro,
	linux-kernel-u79uwXL29TY76Z2rM5mHXA,
	linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	stable-u79uwXL29TY76Z2rM5mHXA, linux-api-u79uwXL29TY76Z2rM5mHXA,
	Jan Kara, Lino Sanfilippo, Valdis Kletnieks,
	Michael Kerrisk-manpages
In-Reply-To: <1411980555-10818-1-git-send-email-ydroneaud-RlY5vtjFyJ3QT0dZR+AlfA@public.gmane.org>

On Mon, 29 Sep 2014 10:49:15 +0200 Yann Droneaud <ydroneaud-RlY5vtjFyJ3QT0dZR+AlfA@public.gmane.org> wrote:

> According to commit 80af258867648 ('fanotify: groups can specify
> their f_flags for new fd'), file descriptors created as part of
> file access notification events inherit flags from the
> event_f_flags argument passed to syscall fanotify_init(2).
> 
> So while it is legal for userspace to call fanotify_init() with
> O_CLOEXEC as part of its second argument, O_CLOEXEC is currently
> silently ignored.
> 
> Indeed event_f_flags are only given to dentry_open(), which only
> seems to care about O_ACCMODE and O_PATH in do_dentry_open(),
> O_DIRECT in open_check_o_direct() and O_LARGEFILE in
> generic_file_open().
> 
> But it seems logical to set close-on-exec flag on the file
> descriptor if userspace is allowed to request it with O_CLOEXEC.
> 
> In fact, according to some lookup on http://codesearch.debian.net/
> and various search engine, there's already some userspace code
> requesting it:
> 
> - in systemd's readahead[2]:
> 
>     fanotify_fd = fanotify_init(FAN_CLOEXEC|FAN_NONBLOCK, O_RDONLY|O_LARGEFILE|O_CLOEXEC|O_NOATIME);
> 
> - in clsync[3]:
> 
>     #define FANOTIFY_EVFLAGS (O_LARGEFILE|O_RDONLY|O_CLOEXEC)
> 
>     int fanotify_d = fanotify_init(FANOTIFY_FLAGS, FANOTIFY_EVFLAGS);
> 
> - in examples [4] from "Filesystem monitoring in the Linux
>   kernel" article[5] by Aleksander Morgado:
> 
>     if ((fanotify_fd = fanotify_init (FAN_CLOEXEC,
>                                       O_RDONLY | O_CLOEXEC | O_LARGEFILE)) < 0)

So we have a number of apps which are setting O_CLOEXEC, but it doesn't
actually work.  With this change it *will* work, so the behaviour of
those apps might change, possibly breaking them?

^ permalink raw reply

* Re: [PATCH v3] mm: add mremap flag for preserving the old mapping
From: Daniel Micay @ 2014-10-01  2:32 UTC (permalink / raw)
  To: Andy Lutomirski
  Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton,
	Jason Evans, Linux API
In-Reply-To: <CALCETrVHgvhAN3neoOpJEk94uM7QKm2izZpp+=1UA6qieaQiTQ@mail.gmail.com>

On 30/09/14 01:49 PM, Andy Lutomirski wrote:
> 
> I think it might pay to add an explicit vm_op to authorize
> duplication, especially for non-cow mappings.  IOW this kind of
> extension seems quite magical for anything that doesn't have the
> normal COW semantics, including for plain old read-only mappings.

This sounds like the best way forwards.

Setting up the op for private, anonymous mappings and having it check
vm_flags & VM_WRITE dynamically seems like it would be enough for the
intended use case in general purpose allocators. It can be extended to
other mapping types later if there's a compelling use case.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply

* Re: [PATCH 1/4] Adds general codes to enforces project quota limits
From: Jan Kara @ 2014-09-30 20:07 UTC (permalink / raw)
  To: Li Xi
  Cc: linux-fsdevel-u79uwXL29TY76Z2rM5mHXA,
	linux-ext4-u79uwXL29TY76Z2rM5mHXA,
	linux-api-u79uwXL29TY76Z2rM5mHXA, tytso-3s7WtUTddSA,
	adilger-m1MBpc4rdrD3fQ9qLvQP4Q, jack-AlSwsSmVLrQ,
	viro-RmSDqhL/yNMiFSDQTTA3OLVCufUGDwFn, hch-wEGCiKHe2LqWVfeAwA7xHQ,
	dmonakhov-GEFAQzZX7r8dnm+yROfE0A
In-Reply-To: <1411567470-31799-2-git-send-email-lixi-LfVdkaOWEx8@public.gmane.org>

On Wed 24-09-14 22:04:27, Li Xi wrote:
> @@ -1413,6 +1416,15 @@ static void __dquot_initialize(struct inode *inode, int type)
>  		case GRPQUOTA:
>  			qid = make_kqid_gid(inode->i_gid);
>  			break;
> +		case PRJQUOTA:
> +			/* Project ID is not supported */
> +			if (!inode->i_sb->dq_op->get_projid)
> +				continue;
> +			rc = inode->i_sb->dq_op->get_projid(inode, &projid);
> +			if (rc)
> +				continue;
> +			qid = make_kqid_projid(projid);
> +			break;
  I realized one more thing: We don't want to check ->get_projid() here.
Rather we should check ->get_projid() when turning quota on in
quota_quotaon() and return -EINVAL when ->get_projid() isn't set - that way
user is early notified the fs doesn't support project quotas. Then here
in __dquot_initialize() we can just check sb_has_quota_active(sb, PRJQUOTA).

								Honza
-- 
Jan Kara <jack-AlSwsSmVLrQ@public.gmane.org>
SUSE Labs, CR

^ permalink raw reply

* Re: [PATCH v3] mm: add mremap flag for preserving the old mapping
From: Andy Lutomirski @ 2014-09-30 17:49 UTC (permalink / raw)
  To: Daniel Micay
  Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Andrew Morton,
	Jason Evans, Linux API
In-Reply-To: <542A79AF.8060602@gmail.com>

On Sep 30, 2014 2:36 AM, "Daniel Micay" <danielmicay@gmail.com> wrote:
>
> On 30/09/14 01:53 AM, Andy Lutomirski wrote:
> > On Mon, Sep 29, 2014 at 9:55 PM, Daniel Micay <danielmicay@gmail.com> wrote:
> >> This introduces the MREMAP_RETAIN flag for preserving the source mapping
> >> when MREMAP_MAYMOVE moves the pages to a new destination. Accesses to
> >> the source location will fault and cause fresh pages to be mapped in.
> >>
> >> For consistency, the old_len >= new_len case could decommit the pages
> >> instead of unmapping. However, userspace can accomplish the same thing
> >> via madvise and a coherent definition of the flag is possible without
> >> the extra complexity.
> >
> > IMO this needs very clear documentation of exactly what it does.
>
> Agreed, and thanks for the review. I'll post a slightly modified version
> of the patch soon (mostly more commit message changes).
>
> > Does it preserve the contents of the source pages?  (If so, why?
> > Aren't you wasting a bunch of time on page faults and possibly
> > unnecessary COWs?)
>
> The source will act as if it was just created. For an anonymous memory
> mapping, it will fault on any accesses and bring in new zeroed pages.
>
> In jemalloc, it replaces an enormous memset(dst, src, size) followed by
> madvise(src, size, MADV_DONTNEED) with mremap. Using mremap also ends up
> eliding page faults from writes at the destination.
>
> TCMalloc has nearly the same page allocation design, although it tries
> to throttle the purging so it won't always gain as much.
>
> > Does it work on file mappings?  Can it extend file mappings while it moves them?
>
> It works on file mappings. If a move occurs, there will be the usual
> extended destination mapping but with the source mapping left intact.
>
> It wouldn't be useful with existing allocators, but in theory a general
> purpose allocator could expose an MMIO API in order to reuse the same
> address space via MAP_FIXED/MREMAP_FIXED to reduce VM fragmentation.
>
> > If you MREMAP_RETAIN a partially COWed private mapping, what happens?
>
> The original mapping is zeroed in the following test, as it would be
> without fork:
>
> #define _GNU_SOURCE
>
> #include <string.h>
> #include <stdlib.h>
> #include <sys/mman.h>
> #include <unistd.h>
> #include <sys/wait.h>
>
> int main(void) {
>   size_t size = 1024 * 1024;
>   char *orig = mmap(NULL, size, PROT_READ|PROT_WRITE,
>                     MAP_PRIVATE|MAP_ANONYMOUS, -1, 0);
>   memset(orig, 5, size);
>   int pid = fork();
>   if (pid == -1)
>     return 1;
>   if (pid == 0) {
>     memset(orig, 5, 1024);
>     char *new = mremap(orig, size, size * 128, MREMAP_MAYMOVE|4);
>     if (new == orig) return 1;
>     for (size_t i = 0; i < size; i++)
>       if (new[i] != 5)
>         return 1;
>     for (size_t i = 0; i < size; i++)
>       if (orig[i] != 0)
>         return 1;
>     return 0;
>   }
>   int status;
>   if (wait(&status) < -1) return 1;
>   if (WIFEXITED(status))
>     return WEXITSTATUS(status);
>   return 1;
> }
>
> Hopefully this is the case you're referring to. :)

What about private file mappings?

>
> > Does it work on special mappings?  If so, please prevent it from doing
> > so.  mremapping x86's vdso is a thing, and duplicating x86's vdso
> > should not become a thing, because x86_32 in particular will become
> > extremely confused.
>
> I'll add a check for arch_vma_name(vma) == NULL.

Careful!  That function is deprecated in favor of vm_ops->name.

I think it might pay to add an explicit vm_op to authorize
duplication, especially for non-cow mappings.  IOW this kind of
extension seems quite magical for anything that doesn't have the
normal COW semantics, including for plain old read-only mappings.

>
> There's an existing check for VM_DONTEXPAND | VM_PFNMAP when expanding
> allocations (the only case this flag impacts). Are there other kinds of
> special mappings that you're referring to?

I was referring to special mappings in the install_special_mapping
sense.  Those may or may not have VM_PFNMAP set.

If VM_DONTEXPAND blocks this new feature entirely, that's probably good.

--Andy

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

^ permalink raw reply

* Re: [PATCH v4 04/11] drivers: base: support cpu cache information interface to userspace via sysfs
From: Sudeep Holla @ 2014-09-30 13:53 UTC (permalink / raw)
  To: Greg Kroah-Hartman
  Cc: Sudeep Holla, LKML, Heiko Carstens, Lorenzo Pieralisi,
	Stephen Boyd, linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linux390-tA70FqPdS9bQT0dZR+AlfA@public.gmane.org,
	linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org,
	linux-ia64-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	linuxppc-dev-uLR06cmDAlY/bJ5BZ2RsiQ@public.gmane.org,
	linux-s390-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
	x86-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org
In-Reply-To: <20140924063511.GA12929-U8xfFu+wG4EAvxtiuMwx3w@public.gmane.org>

Hi Greg,

On 24/09/14 07:35, Greg Kroah-Hartman wrote:
> On Wed, Sep 17, 2014 at 12:00:48PM -0700, Greg Kroah-Hartman wrote:
>> On Wed, Sep 17, 2014 at 06:25:10PM +0100, Sudeep Holla wrote:
>>> Hi Greg,
>>>
>>> On 03/09/14 18:00, Sudeep Holla wrote:

[...]
>>>
>>> Can you review the first 4 patches in this series please ?
>>
>> It's in my todo queue, which is really long at the moment due to me
>> going to conferences (at one right now...)  Will be working on this
>> soon, thanks for your patience.
>
> Based on the review comments, I think you are going to change at least
> the first patch, right?  Please resend the latest version of this
> series, with all of the accumulated tested-by and acked lines and
> resend.
>

I have posted the new version as you suggested. I was holding off
assuming the merge window would open this week and hence the delay.

Regards,
Sudeep

^ permalink raw reply

* [PATCH v5 04/11] drivers: base: support cpu cache information interface to userspace via sysfs
From: Sudeep Holla @ 2014-09-30 13:48 UTC (permalink / raw)
  To: LKML
  Cc: linux-s390, Lorenzo Pieralisi, linux-ia64, Greg Kroah-Hartman,
	Sudeep Holla, Heiko Carstens, x86, linux-api, linux390,
	linuxppc-dev, linux-arm-kernel
In-Reply-To: <1412084912-2767-1-git-send-email-sudeep.holla@arm.com>

This patch adds initial support for providing processor cache information
to userspace through sysfs interface. This is based on already existing
implementations(x86, ia64, s390 and powerpc) and hence the interface is
intended to be fully compatible.

The main purpose of this generic support is to avoid further code
duplication to support new architectures and also to unify all the existing
different implementations.

This implementation maintains the hierarchy of cache objects which reflects
the system's cache topology. Cache devices are instantiated as needed as
CPUs come online. The cache information is replicated per-cpu even if they are
shared. A per-cpu array of cache information maintained is used mainly for
sysfs-related book keeping.

It also implements the shared_cpu_map attribute, which is essential for
enabling both kernel and user-space to discover the system's overall cache
topology.

This patch also add the missing ABI documentation for the cacheinfo sysfs
interface already, which is well defined and widely used.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Reviewed-by: Stephen Boyd <sboyd@codeaurora.org>
Tested-by: Stephen Boyd <sboyd@codeaurora.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-api@vger.kernel.org
Cc: linux390@de.ibm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: linux-s390@vger.kernel.org
Cc: x86@kernel.org
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |  47 ++
 drivers/base/Makefile                              |   2 +-
 drivers/base/cacheinfo.c                           | 541 +++++++++++++++++++++
 include/linux/cacheinfo.h                          | 100 ++++
 4 files changed, 689 insertions(+), 1 deletion(-)
 create mode 100644 drivers/base/cacheinfo.c
 create mode 100644 include/linux/cacheinfo.h

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index acb9bfc89b48..99983e67c13c 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -224,3 +224,50 @@ Description:	Parameters for the Intel P-state driver
 		frequency range.
 
 		More details can be found in Documentation/cpu-freq/intel-pstate.txt
+
+What:		/sys/devices/system/cpu/cpu*/cache/index*/<set_of_attributes_mentioned_below>
+Date:		July 2014(documented, existed before August 2008)
+Contact:	Sudeep Holla <sudeep.holla@arm.com>
+		Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Parameters for the CPU cache attributes
+
+		allocation_policy:
+			- WriteAllocate: allocate a memory location to a cache line
+					 on a cache miss because of a write
+			- ReadAllocate: allocate a memory location to a cache line
+					on a cache miss because of a read
+			- ReadWriteAllocate: both writeallocate and readallocate
+
+		attributes: LEGACY used only on IA64 and is same as write_policy
+
+		coherency_line_size: the minimum amount of data in bytes that gets
+				     transferred from memory to cache
+
+		level: the cache hierarcy in the multi-level cache configuration
+
+		number_of_sets: total number of sets in the cache, a set is a
+				collection of cache lines with the same cache index
+
+		physical_line_partition: number of physical cache line per cache tag
+
+		shared_cpu_list: the list of logical cpus sharing the cache
+
+		shared_cpu_map: logical cpu mask containing the list of cpus sharing
+				the cache
+
+		size: the total cache size in kB
+
+		type:
+			- Instruction: cache that only holds instructions
+			- Data: cache that only caches data
+			- Unified: cache that holds both data and instructions
+
+		ways_of_associativity: degree of freedom in placing a particular block
+					of memory in the cache
+
+		write_policy:
+			- WriteThrough: data is written to both the cache line
+					and to the block in the lower-level memory
+			- WriteBack: data is written only to the cache line and
+				     the modified cache line is written to main
+				     memory only when it is replaced
diff --git a/drivers/base/Makefile b/drivers/base/Makefile
index 4aab26ec0292..f901bc1cffc8 100644
--- a/drivers/base/Makefile
+++ b/drivers/base/Makefile
@@ -4,7 +4,7 @@ obj-y			:= component.o core.o bus.o dd.o syscore.o \
 			   driver.o class.o platform.o \
 			   cpu.o firmware.o init.o map.o devres.o \
 			   attribute_container.o transport_class.o \
-			   topology.o container.o
+			   topology.o container.o cacheinfo.o
 obj-$(CONFIG_DEVTMPFS)	+= devtmpfs.o
 obj-$(CONFIG_DMA_CMA) += dma-contiguous.o
 obj-y			+= power/
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
new file mode 100644
index 000000000000..8ed4ea1f3716
--- /dev/null
+++ b/drivers/base/cacheinfo.c
@@ -0,0 +1,541 @@
+/*
+ * cacheinfo support - processor cache information via sysfs
+ *
+ * Based on arch/x86/kernel/cpu/intel_cacheinfo.c
+ * Author: Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * 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 "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; 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.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#include <linux/bitops.h>
+#include <linux/cacheinfo.h>
+#include <linux/compiler.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/of.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/sysfs.h>
+
+/* pointer to per cpu cacheinfo */
+static DEFINE_PER_CPU(struct cpu_cacheinfo, ci_cpu_cacheinfo);
+#define ci_cacheinfo(cpu)	(&per_cpu(ci_cpu_cacheinfo, cpu))
+#define cache_leaves(cpu)	(ci_cacheinfo(cpu)->num_leaves)
+#define per_cpu_cacheinfo(cpu)	(ci_cacheinfo(cpu)->info_list)
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu)
+{
+	return ci_cacheinfo(cpu);
+}
+
+#ifdef CONFIG_OF
+static int cache_setup_of_node(unsigned int cpu)
+{
+	struct device_node *np;
+	struct cacheinfo *this_leaf;
+	struct device *cpu_dev = get_cpu_device(cpu);
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	unsigned int index = 0;
+
+	/* skip if of_node is already populated */
+	if (this_cpu_ci->info_list->of_node)
+		return 0;
+
+	if (!cpu_dev) {
+		pr_err("No cpu device for CPU %d\n", cpu);
+		return -ENODEV;
+	}
+	np = cpu_dev->of_node;
+	if (!np) {
+		pr_err("Failed to find cpu%d device node\n", cpu);
+		return -ENOENT;
+	}
+
+	while (np && index < cache_leaves(cpu)) {
+		this_leaf = this_cpu_ci->info_list + index;
+		if (this_leaf->level != 1)
+			np = of_find_next_cache_node(np);
+		else
+			np = of_node_get(np);/* cpu node itself */
+		this_leaf->of_node = np;
+		index++;
+	}
+	return 0;
+}
+
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	return sib_leaf->of_node == this_leaf->of_node;
+}
+#else
+static inline int cache_setup_of_node(unsigned int cpu) { return 0; }
+static inline bool cache_leaves_are_shared(struct cacheinfo *this_leaf,
+					   struct cacheinfo *sib_leaf)
+{
+	/*
+	 * For non-DT systems, assume unique level 1 cache, system-wide
+	 * shared caches for all other levels. This will be used only if
+	 * arch specific code has not populated shared_cpu_map
+	 */
+	return !(this_leaf->level == 1);
+}
+#endif
+
+static int cache_shared_cpu_map_setup(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int index;
+	int ret;
+
+	ret = cache_setup_of_node(cpu);
+	if (ret)
+		return ret;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		unsigned int i;
+
+		this_leaf = this_cpu_ci->info_list + index;
+		/* skip if shared_cpu_map is already populated */
+		if (!cpumask_empty(&this_leaf->shared_cpu_map))
+			continue;
+
+		cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+		for_each_online_cpu(i) {
+			struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
+
+			if (i == cpu || !sib_cpu_ci->info_list)
+				continue;/* skip if itself or no cacheinfo */
+			sib_leaf = sib_cpu_ci->info_list + index;
+			if (cache_leaves_are_shared(this_leaf, sib_leaf)) {
+				cpumask_set_cpu(cpu, &sib_leaf->shared_cpu_map);
+				cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static void cache_shared_cpu_map_remove(unsigned int cpu)
+{
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	struct cacheinfo *this_leaf, *sib_leaf;
+	unsigned int sibling, index;
+
+	for (index = 0; index < cache_leaves(cpu); index++) {
+		this_leaf = this_cpu_ci->info_list + index;
+		for_each_cpu(sibling, &this_leaf->shared_cpu_map) {
+			struct cpu_cacheinfo *sib_cpu_ci;
+
+			if (sibling == cpu) /* skip itself */
+				continue;
+			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			sib_leaf = sib_cpu_ci->info_list + index;
+			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
+			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
+		}
+		of_node_put(this_leaf->of_node);
+	}
+}
+
+static void free_cache_attributes(unsigned int cpu)
+{
+	cache_shared_cpu_map_remove(cpu);
+
+	kfree(per_cpu_cacheinfo(cpu));
+	per_cpu_cacheinfo(cpu) = NULL;
+}
+
+int __weak init_cache_level(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+int __weak populate_cache_leaves(unsigned int cpu)
+{
+	return -ENOENT;
+}
+
+static int detect_cache_attributes(unsigned int cpu)
+{
+	int ret;
+
+	if (init_cache_level(cpu))
+		return -ENOENT;
+
+	per_cpu_cacheinfo(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct cacheinfo), GFP_KERNEL);
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOMEM;
+
+	ret = populate_cache_leaves(cpu);
+	if (ret)
+		goto free_ci;
+	/*
+	 * For systems using DT for cache hierarcy, of_node and shared_cpu_map
+	 * will be set up here only if they are not populated already
+	 */
+	ret = cache_shared_cpu_map_setup(cpu);
+	if (ret)
+		goto free_ci;
+	return 0;
+
+free_ci:
+	free_cache_attributes(cpu);
+	return ret;
+}
+
+/* pointer to cpuX/cache device */
+static DEFINE_PER_CPU(struct device *, ci_cache_dev);
+#define per_cpu_cache_dev(cpu)	(per_cpu(ci_cache_dev, cpu))
+
+static cpumask_t cache_dev_map;
+
+/* pointer to array of devices for cpuX/cache/indexY */
+static DEFINE_PER_CPU(struct device **, ci_index_dev);
+#define per_cpu_index_dev(cpu)	(per_cpu(ci_index_dev, cpu))
+#define per_cache_index_dev(cpu, idx)	((per_cpu_index_dev(cpu))[idx])
+
+#define show_one(file_name, object)				\
+static ssize_t file_name##_show(struct device *dev,		\
+		struct device_attribute *attr, char *buf)	\
+{								\
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);	\
+	return sprintf(buf, "%u\n", this_leaf->object);		\
+}
+
+show_one(level, level);
+show_one(coherency_line_size, coherency_line_size);
+show_one(number_of_sets, number_of_sets);
+show_one(physical_line_partition, physical_line_partition);
+show_one(ways_of_associativity, ways_of_associativity);
+
+static ssize_t size_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%uK\n", this_leaf->size >> 10);
+}
+
+static ssize_t shared_cpumap_show_func(struct device *dev, bool list, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+
+	return cpumap_print_to_pagebuf(list, buf, mask);
+}
+
+static ssize_t shared_cpu_map_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, false, buf);
+}
+
+static ssize_t shared_cpu_list_show(struct device *dev,
+				    struct device_attribute *attr, char *buf)
+{
+	return shared_cpumap_show_func(dev, true, buf);
+}
+
+static ssize_t type_show(struct device *dev,
+			 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+
+	switch (this_leaf->type) {
+	case CACHE_TYPE_DATA:
+		return sprintf(buf, "Data\n");
+	case CACHE_TYPE_INST:
+		return sprintf(buf, "Instruction\n");
+	case CACHE_TYPE_UNIFIED:
+		return sprintf(buf, "Unified\n");
+	default:
+		return -EINVAL;
+	}
+}
+
+static ssize_t allocation_policy_show(struct device *dev,
+				      struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if ((ci_attr & CACHE_READ_ALLOCATE) && (ci_attr & CACHE_WRITE_ALLOCATE))
+		n = sprintf(buf, "ReadWriteAllocate\n");
+	else if (ci_attr & CACHE_READ_ALLOCATE)
+		n = sprintf(buf, "ReadAllocate\n");
+	else if (ci_attr & CACHE_WRITE_ALLOCATE)
+		n = sprintf(buf, "WriteAllocate\n");
+	return n;
+}
+
+static ssize_t write_policy_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	unsigned int ci_attr = this_leaf->attributes;
+	int n = 0;
+
+	if (ci_attr & CACHE_WRITE_THROUGH)
+		n = sprintf(buf, "WriteThrough\n");
+	else if (ci_attr & CACHE_WRITE_BACK)
+		n = sprintf(buf, "WriteBack\n");
+	return n;
+}
+
+static DEVICE_ATTR_RO(level);
+static DEVICE_ATTR_RO(type);
+static DEVICE_ATTR_RO(coherency_line_size);
+static DEVICE_ATTR_RO(ways_of_associativity);
+static DEVICE_ATTR_RO(number_of_sets);
+static DEVICE_ATTR_RO(size);
+static DEVICE_ATTR_RO(allocation_policy);
+static DEVICE_ATTR_RO(write_policy);
+static DEVICE_ATTR_RO(shared_cpu_map);
+static DEVICE_ATTR_RO(shared_cpu_list);
+static DEVICE_ATTR_RO(physical_line_partition);
+
+static struct attribute *cache_default_attrs[] = {
+	&dev_attr_type.attr,
+	&dev_attr_level.attr,
+	&dev_attr_shared_cpu_map.attr,
+	&dev_attr_shared_cpu_list.attr,
+	&dev_attr_coherency_line_size.attr,
+	&dev_attr_ways_of_associativity.attr,
+	&dev_attr_number_of_sets.attr,
+	&dev_attr_size.attr,
+	&dev_attr_allocation_policy.attr,
+	&dev_attr_write_policy.attr,
+	&dev_attr_physical_line_partition.attr,
+	NULL
+};
+
+static umode_t
+cache_default_attrs_is_visible(struct kobject *kobj,
+			       struct attribute *attr, int unused)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct cacheinfo *this_leaf = dev_get_drvdata(dev);
+	const struct cpumask *mask = &this_leaf->shared_cpu_map;
+	umode_t mode = attr->mode;
+
+	if ((attr == &dev_attr_type.attr) && this_leaf->type)
+		return mode;
+	if ((attr == &dev_attr_level.attr) && this_leaf->level)
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_map.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_shared_cpu_list.attr) && !cpumask_empty(mask))
+		return mode;
+	if ((attr == &dev_attr_coherency_line_size.attr) &&
+	    this_leaf->coherency_line_size)
+		return mode;
+	if ((attr == &dev_attr_ways_of_associativity.attr) &&
+	    this_leaf->size) /* allow 0 = full associativity */
+		return mode;
+	if ((attr == &dev_attr_number_of_sets.attr) &&
+	    this_leaf->number_of_sets)
+		return mode;
+	if ((attr == &dev_attr_size.attr) && this_leaf->size)
+		return mode;
+	if ((attr == &dev_attr_write_policy.attr) &&
+	    (this_leaf->attributes & CACHE_WRITE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_allocation_policy.attr) &&
+	    (this_leaf->attributes & CACHE_ALLOCATE_POLICY_MASK))
+		return mode;
+	if ((attr == &dev_attr_physical_line_partition.attr) &&
+	    this_leaf->physical_line_partition)
+		return mode;
+
+	return 0;
+}
+
+static const struct attribute_group cache_default_group = {
+	.attrs = cache_default_attrs,
+	.is_visible = cache_default_attrs_is_visible,
+};
+
+static const struct attribute_group *cache_default_groups[] = {
+	&cache_default_group,
+	NULL,
+};
+
+static const struct attribute_group *cache_private_groups[] = {
+	&cache_default_group,
+	NULL, /* Place holder for private group */
+	NULL,
+};
+
+const struct attribute_group *
+__weak cache_get_priv_group(struct cacheinfo *this_leaf)
+{
+	return NULL;
+}
+
+static const struct attribute_group **
+cache_get_attribute_groups(struct cacheinfo *this_leaf)
+{
+	const struct attribute_group *priv_group =
+			cache_get_priv_group(this_leaf);
+
+	if (!priv_group)
+		return cache_default_groups;
+
+	if (!cache_private_groups[1])
+		cache_private_groups[1] = priv_group;
+
+	return cache_private_groups;
+}
+
+/* Add/Remove cache interface for CPU device */
+static void cpu_cache_sysfs_exit(unsigned int cpu)
+{
+	int i;
+	struct device *ci_dev;
+
+	if (per_cpu_index_dev(cpu)) {
+		for (i = 0; i < cache_leaves(cpu); i++) {
+			ci_dev = per_cache_index_dev(cpu, i);
+			if (!ci_dev)
+				continue;
+			device_unregister(ci_dev);
+		}
+		kfree(per_cpu_index_dev(cpu));
+		per_cpu_index_dev(cpu) = NULL;
+	}
+	device_unregister(per_cpu_cache_dev(cpu));
+	per_cpu_cache_dev(cpu) = NULL;
+}
+
+static int cpu_cache_sysfs_init(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	if (per_cpu_cacheinfo(cpu) == NULL)
+		return -ENOENT;
+
+	per_cpu_cache_dev(cpu) = cpu_device_create(dev, NULL, NULL, "cache");
+	if (IS_ERR(per_cpu_cache_dev(cpu)))
+		return PTR_ERR(per_cpu_cache_dev(cpu));
+
+	/* Allocate all required memory */
+	per_cpu_index_dev(cpu) = kcalloc(cache_leaves(cpu),
+					 sizeof(struct device *), GFP_KERNEL);
+	if (unlikely(per_cpu_index_dev(cpu) == NULL))
+		goto err_out;
+
+	return 0;
+
+err_out:
+	cpu_cache_sysfs_exit(cpu);
+	return -ENOMEM;
+}
+
+static int cache_add_dev(unsigned int cpu)
+{
+	unsigned int i;
+	int rc;
+	struct device *ci_dev, *parent;
+	struct cacheinfo *this_leaf;
+	struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
+	const struct attribute_group **cache_groups;
+
+	rc = cpu_cache_sysfs_init(cpu);
+	if (unlikely(rc < 0))
+		return rc;
+
+	parent = per_cpu_cache_dev(cpu);
+	for (i = 0; i < cache_leaves(cpu); i++) {
+		this_leaf = this_cpu_ci->info_list + i;
+		if (this_leaf->disable_sysfs)
+			continue;
+		cache_groups = cache_get_attribute_groups(this_leaf);
+		ci_dev = cpu_device_create(parent, this_leaf, cache_groups,
+					   "index%1u", i);
+		if (IS_ERR(ci_dev)) {
+			rc = PTR_ERR(ci_dev);
+			goto err;
+		}
+		per_cache_index_dev(cpu, i) = ci_dev;
+	}
+	cpumask_set_cpu(cpu, &cache_dev_map);
+
+	return 0;
+err:
+	cpu_cache_sysfs_exit(cpu);
+	return rc;
+}
+
+static void cache_remove_dev(unsigned int cpu)
+{
+	if (!cpumask_test_cpu(cpu, &cache_dev_map))
+		return;
+	cpumask_clear_cpu(cpu, &cache_dev_map);
+
+	cpu_cache_sysfs_exit(cpu);
+}
+
+static int cacheinfo_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+	int rc = 0;
+
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		rc = detect_cache_attributes(cpu);
+		if (!rc)
+			rc = cache_add_dev(cpu);
+		break;
+	case CPU_DEAD:
+		cache_remove_dev(cpu);
+		if (per_cpu_cacheinfo(cpu))
+			free_cache_attributes(cpu);
+		break;
+	}
+	return notifier_from_errno(rc);
+}
+
+static int __init cacheinfo_sysfs_init(void)
+{
+	int cpu, rc = 0;
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu) {
+		rc = detect_cache_attributes(cpu);
+		if (rc) {
+			pr_err("error detecting cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+		rc = cache_add_dev(cpu);
+		if (rc) {
+			free_cache_attributes(cpu);
+			pr_err("error populating cacheinfo..cpu%d\n", cpu);
+			goto out;
+		}
+	}
+	__hotcpu_notifier(cacheinfo_cpu_callback, 0);
+
+out:
+	cpu_notifier_register_done();
+	return rc;
+}
+
+device_initcall(cacheinfo_sysfs_init);
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
new file mode 100644
index 000000000000..3daf5ed392c9
--- /dev/null
+++ b/include/linux/cacheinfo.h
@@ -0,0 +1,100 @@
+#ifndef _LINUX_CACHEINFO_H
+#define _LINUX_CACHEINFO_H
+
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+
+struct device_node;
+struct attribute;
+
+enum cache_type {
+	CACHE_TYPE_NOCACHE = 0,
+	CACHE_TYPE_INST = BIT(0),
+	CACHE_TYPE_DATA = BIT(1),
+	CACHE_TYPE_SEPARATE = CACHE_TYPE_INST | CACHE_TYPE_DATA,
+	CACHE_TYPE_UNIFIED = BIT(2),
+};
+
+/**
+ * struct cacheinfo - represent a cache leaf node
+ * @type: type of the cache - data, inst or unified
+ * @level: represents the hierarcy in the multi-level cache
+ * @coherency_line_size: size of each cache line usually representing
+ *	the minimum amount of data that gets transferred from memory
+ * @number_of_sets: total number of sets, a set is a collection of cache
+ *	lines sharing the same index
+ * @ways_of_associativity: number of ways in which a particular memory
+ *	block can be placed in the cache
+ * @physical_line_partition: number of physical cache lines sharing the
+ *	same cachetag
+ * @size: Total size of the cache
+ * @shared_cpu_map: logical cpumask representing all the cpus sharing
+ *	this cache node
+ * @attributes: bitfield representing various cache attributes
+ * @of_node: if devicetree is used, this represents either the cpu node in
+ *	case there's no explicit cache node or the cache node itself in the
+ *	device tree
+ * @disable_sysfs: indicates whether this node is visible to the user via
+ *	sysfs or not
+ * @priv: pointer to any private data structure specific to particular
+ *	cache design
+ *
+ * While @of_node, @disable_sysfs and @priv are used for internal book
+ * keeping, the remaining members form the core properties of the cache
+ */
+struct cacheinfo {
+	enum cache_type type;
+	unsigned int level;
+	unsigned int coherency_line_size;
+	unsigned int number_of_sets;
+	unsigned int ways_of_associativity;
+	unsigned int physical_line_partition;
+	unsigned int size;
+	cpumask_t shared_cpu_map;
+	unsigned int attributes;
+#define CACHE_WRITE_THROUGH	BIT(0)
+#define CACHE_WRITE_BACK	BIT(1)
+#define CACHE_WRITE_POLICY_MASK		\
+	(CACHE_WRITE_THROUGH | CACHE_WRITE_BACK)
+#define CACHE_READ_ALLOCATE	BIT(2)
+#define CACHE_WRITE_ALLOCATE	BIT(3)
+#define CACHE_ALLOCATE_POLICY_MASK	\
+	(CACHE_READ_ALLOCATE | CACHE_WRITE_ALLOCATE)
+
+	struct device_node *of_node;
+	bool disable_sysfs;
+	void *priv;
+};
+
+struct cpu_cacheinfo {
+	struct cacheinfo *info_list;
+	unsigned int num_levels;
+	unsigned int num_leaves;
+};
+
+/*
+ * Helpers to make sure "func" is executed on the cpu whose cache
+ * attributes are being detected
+ */
+#define DEFINE_SMP_CALL_CACHE_FUNCTION(func)			\
+static inline void _##func(void *ret)				\
+{								\
+	int cpu = smp_processor_id();				\
+	*(int *)ret = __##func(cpu);				\
+}								\
+								\
+int func(unsigned int cpu)					\
+{								\
+	int ret;						\
+	smp_call_function_single(cpu, _##func, &ret, true);	\
+	return ret;						\
+}
+
+struct cpu_cacheinfo *get_cpu_cacheinfo(unsigned int cpu);
+int init_cache_level(unsigned int cpu);
+int populate_cache_leaves(unsigned int cpu);
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
+
+#endif /* _LINUX_CACHEINFO_H */
-- 
1.9.1

^ permalink raw reply related

page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox