Merge tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Don't destroy user event fields when removal fails

   User event fields are destroyed before the event is removed from
   visibility. But that can fail leaving the still visible event with no
   fields. Move the destroying of the fields to after the event is
   successfully removed from visibility.

 - Initialize function graph state is fork before calling
   copy_exec_state()

   For non-CLONE_VM forks, copy_exec_state() allocates a new
   task_exec_state. If that allocation fails, ftrace_graph_exit_task()
   will free the tasks ret_stack pointer. Since that pointer is still
   using the parent's ret_stack, it mistakenly frees the parent's
   pointer too.

   Call ftrace_graph_init() on the task first which will NULL out the
   new tasks's ret_stack and if the copy fails, it will not free
   anything.

 - Remove FGRAPH_MAX_INDEX

   The macro FGRAPH_MAX_INDEX was added but never used. Remove it.

 - Save ent_size in function graph printing of nested functions

   The function graph tracer needs to look at the next event to see if
   the next event is the return of the current function entry. If it is,
   it prints a single line:

	ktime_get();

   Otherwise it prints it like a nested function:

	tick_nohz_irq_exit() {
	    ktime_get();
	    kcpustat_irq_exit();
	}

   In order to look at the next event, it must save the current event so
   that it has the information to print from it. It saves the event in
   the iterator descriptor called "ent". What it doesn't save is the
   ent_size of the event which is now used to know if the function graph
   arguments are to be printed. The peek doesn't save the size so the
   size used happens to be that of the size of the last event that was
   seen.

   Save the entry event size in the iterator descriptor so that the
   correct size is used.

 - Fix several errors with freeing data in the histogram code

   The histogram code had a lot of leaked or or incorrect accounting
   when failures happen. Correct them.

 - Fix histogram regression of .percent and .graph modifiers

   Up until 6.3 histogram values could have "percent" or "graph"
   modifiers that changed how they were printed. But a change that added
   restricting histograms values from being strings, stack traces and
   other modifiers inadvertently prevented them from using the percent
   and graph modifiers, which were legal use cases for values.

   Put back the percent and graph modifiers.

 - Fix various typos in the comments

 - Set the trace_clock before initializing a histogram with clock
   argument

   The histogram API allows the user to specific which trace clock to
   use via a "clock=" string. The histogram is set up first before the
   clock is checked. If the passed in clock is not valid, it exits
   without fully fixing up the histogram leaving it on the list and a
   use-after-free can trigger.

   Update the clock argument first and if it fails then exit gracefully
   before the histogram trigger is placed on any lists.

 - Restore :mod: trailer after parsing in ftrace_set_clr_event

   The function ftrace_set_clr_event() modifies the parse string and
   needs to put it back to what was passed in. It searches for ":mod:"
   via a strsep() but fails to put back the first ':' in the string.

   Add back the ':' in the passed in string.

 - Take trace_array reference when opening a tracer options file

   The options files are dynamically created and some tracers add their
   own options. When a tracer adds their own list of options, the
   trace_array holding them has an array to hold the list of options for
   each tracer. This array increases in size via a krealloc(), and the
   new entry gets a newly allocated array to hold the options of the new
   tracer being added.

   The element in each entry of the tracer's option array holds a
   pointer back to the trace_array, a pointer to the tracer it is
   associated to, a pointer to the flags of the option.

   The issue is that these arrays are freed when the trace_array is
   freed when its instance it represents is removed from the instances
   directory. There's a race that an open of one of these options files
   can happen when the instance is being removed.

   Add a new helper function to be called by the open function of the
   options file to iterate all existing trace_arrays under a lock and
   find the one that has the given option element in one of it's tracer
   arrays. If found, then update the associated trace_array's reference
   counter to keep it from being freed. If not found, have the open call
   return -ENODEV.

 - Disable interrupts when acquiring the lock in rb_wake_up_waiters()

   The function rb_wake_up_waiters() assumes it will be called in
   interrupt context and does not disable irqs when taking
   cpu_buffer->reader_lock, which can be called in hard interrupt
   context. The issue is in PREEMPT_RT, this function is called in
   thread context leaving this lock open to a deadlock.

   Take the lock with interrupts disabled.

 - Use rcu_assign_pointer() for tmp_ops filter hash

   The tmp_ops used in update_ftrace_direct_mod() assigns its
   filter_hash field directly, but that field is annotated as __rcu and
   sparse complains. Assign it with rcu_assign_pointer()

 - Fix use-after-free in enable_trigger_private_data_free()

   The trace_event_call is accessed through the event_trigger_data's
   trace_event_file pointer to put the trace_event_call on freeing. The
   issue is that the trace_event_file data may have been freed already
   causing a use-after-free. Add a field to the event_trigger_data that
   points directly to the trace_event_call so that it can decrement its
   reference directly without needing to go through the
   trace_event_file.

 - Fix accounting of buffer data remote headers

   trace_buffer_desc_size() and trace_remote_alloc_buffer() undercount
   the number of pages is needed for the asked for size as it doesn't
   take into account the meta data on each page. Add a helper function
   to do the calculation properly and use that in these functions.

 - Catch nr_page_va overflow in ring_buffer_desc sizing

   The number of pages per remote ring buffer is capped by
   ring_buffer_desc::nr_page_va (32 bits). A buffer_size large enough to
   overflow that field would silently allocate a descriptor smaller than
   what was asked for.

 - Do not resize the subbuf order if any per_cpu buffer is disabled

   The mmapping of ring buffers disables resizing the subbuffers, but it
   is done per-cpu whereas the subbuf size change is done for all the
   per_cpu buffers under the buffer->mutex. It could change the size of
   some while the mapping is happening on others. Have the resize of the
   subbuf order check all the per_cpu buffers under the lock to see if
   any of them is disabled before starting and causing an inconsistency
   between buffers that are being mapped.

* tag 'trace-v7.3-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (25 commits)
  ring-buffer: Check resize_disabled before publishing the new subbuf order
  tracing/remotes: Catch nr_page_va overflow in ring_buffer_desc sizing
  tracing/remotes: Account for ring buffer page header in size calculation
  tracing: Don't dereference trace_event_file in deferred trigger free
  ftrace: Use rcu_assign_pointer() for tmp_ops filter hash
  ring-buffer: Acquire the lock with irqsave in rb_wake_up_waiters()
  tracing: Take trace_array reference when opening a tracer options file
  tracing: Fix ring_buffer_read_page_size() kernel-doc
  tracing: Restore :mod: trailer after parsing in ftrace_set_clr_event()
  tracing: Fix memory corruption from a "STACKTRACE" histogram key
  tracing: Fix memory corruption from the histogram stacktrace modifier
  tracing: Undo the registration when enabling the histogram trigger fails
  tracing: Take the reference before publishing the named histogram trigger
  tracing: Set the trace clock before registering the histogram trigger
  tracing: Fix typo "preceeded" in comment
  tracing: Fix typo "availabe" in comment
  tracing: Let histogram values keep the percent and graph modifiers
  tracing: Keep the entry count when the histogram stats allocation fails
  tracing: Free histogram the field rejected for a bad modifier
  tracing: Free histogram the var ref when its initialization fails
  ...

1 files changed, 330 insertions, 0 deletions

diff --git a/include/net/6lowpan.h b/include/net/6lowpan.h
new file mode 100644
index 000000000..c80539be1
--- /dev/null
+++ b/include/net/6lowpan.h
@@ -0,0 +1,330 @@
+/*
+ * Copyright 2011, Siemens AG
+ * written by Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+/*
+ * Based on patches from Jon Smirl <jonsmirl@gmail.com>
+ * Copyright (c) 2011 Jon Smirl <jonsmirl@gmail.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 in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License along
+ * with this program; if not, write to the Free Software Foundation, Inc.,
+ * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+/* Jon's code is based on 6lowpan implementation for Contiki which is:
+ * Copyright (c) 2008, Swedish Institute of Computer Science.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the Institute nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE INSTITUTE AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE INSTITUTE OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+#ifndef __6LOWPAN_H__
+#define __6LOWPAN_H__
+
+#include <linux/debugfs.h>
+
+#include <net/ipv6.h>
+#include <net/net_namespace.h>
+
+/* special link-layer handling */
+#include <net/mac802154.h>
+
+#define EUI64_ADDR_LEN		8
+
+#define LOWPAN_NHC_MAX_ID_LEN	1
+/* Maximum next header compression length which we currently support inclusive
+ * possible inline data.
+ */
+#define LOWPAN_NHC_MAX_HDR_LEN	(sizeof(struct udphdr))
+/* Max IPHC Header len without IPv6 hdr specific inline data.
+ * Useful for getting the "extra" bytes we need at worst case compression.
+ *
+ * LOWPAN_IPHC + CID + LOWPAN_NHC_MAX_ID_LEN
+ */
+#define LOWPAN_IPHC_MAX_HEADER_LEN	(2 + 1 + LOWPAN_NHC_MAX_ID_LEN)
+/* Maximum worst case IPHC header buffer size */
+#define LOWPAN_IPHC_MAX_HC_BUF_LEN	(sizeof(struct ipv6hdr) +	\
+					 LOWPAN_IPHC_MAX_HEADER_LEN +	\
+					 LOWPAN_NHC_MAX_HDR_LEN)
+/* SCI/DCI is 4 bit width, so we have maximum 16 entries */
+#define LOWPAN_IPHC_CTX_TABLE_SIZE	(1 << 4)
+
+#define LOWPAN_DISPATCH_IPV6		0x41 /* 01000001 = 65 */
+#define LOWPAN_DISPATCH_IPHC		0x60 /* 011xxxxx = ... */
+#define LOWPAN_DISPATCH_IPHC_MASK	0xe0
+
+static inline bool lowpan_is_ipv6(u8 dispatch)
+{
+	return dispatch == LOWPAN_DISPATCH_IPV6;
+}
+
+static inline bool lowpan_is_iphc(u8 dispatch)
+{
+	return (dispatch & LOWPAN_DISPATCH_IPHC_MASK) == LOWPAN_DISPATCH_IPHC;
+}
+
+#define LOWPAN_PRIV_SIZE(llpriv_size)	\
+	(sizeof(struct lowpan_dev) + llpriv_size)
+
+enum lowpan_lltypes {
+	LOWPAN_LLTYPE_BTLE,
+	LOWPAN_LLTYPE_IEEE802154,
+};
+
+enum lowpan_iphc_ctx_flags {
+	LOWPAN_IPHC_CTX_FLAG_ACTIVE,
+	LOWPAN_IPHC_CTX_FLAG_COMPRESSION,
+};
+
+struct lowpan_iphc_ctx {
+	u8 id;
+	struct in6_addr pfx;
+	u8 plen;
+	unsigned long flags;
+};
+
+struct lowpan_iphc_ctx_table {
+	spinlock_t lock;
+	const struct lowpan_iphc_ctx_ops *ops;
+	struct lowpan_iphc_ctx table[LOWPAN_IPHC_CTX_TABLE_SIZE];
+};
+
+static inline bool lowpan_iphc_ctx_is_active(const struct lowpan_iphc_ctx *ctx)
+{
+	return test_bit(LOWPAN_IPHC_CTX_FLAG_ACTIVE, &ctx->flags);
+}
+
+static inline bool
+lowpan_iphc_ctx_is_compression(const struct lowpan_iphc_ctx *ctx)
+{
+	return test_bit(LOWPAN_IPHC_CTX_FLAG_COMPRESSION, &ctx->flags);
+}
+
+struct lowpan_dev {
+	enum lowpan_lltypes lltype;
+	struct dentry *iface_debugfs;
+	struct lowpan_iphc_ctx_table ctx;
+
+	/* must be last */
+	u8 priv[] __aligned(sizeof(void *));
+};
+
+struct lowpan_802154_neigh {
+	__le16 short_addr;
+};
+
+static inline
+struct lowpan_802154_neigh *lowpan_802154_neigh(void *neigh_priv)
+{
+	return neigh_priv;
+}
+
+static inline
+struct lowpan_dev *lowpan_dev(const struct net_device *dev)
+{
+	return netdev_priv(dev);
+}
+
+/* private device info */
+struct lowpan_802154_dev {
+	struct net_device	*wdev; /* wpan device ptr */
+	u16			fragment_tag;
+};
+
+static inline struct
+lowpan_802154_dev *lowpan_802154_dev(const struct net_device *dev)
+{
+	return (struct lowpan_802154_dev *)lowpan_dev(dev)->priv;
+}
+
+struct lowpan_802154_cb {
+	u16 d_tag;
+	unsigned int d_size;
+	u8 d_offset;
+};
+
+static inline
+struct lowpan_802154_cb *lowpan_802154_cb(const struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct lowpan_802154_cb) > sizeof(skb->cb));
+	return (struct lowpan_802154_cb *)skb->cb;
+}
+
+static inline void lowpan_iphc_uncompress_eui64_lladdr(struct in6_addr *ipaddr,
+						       const void *lladdr)
+{
+	/* fe:80::XXXX:XXXX:XXXX:XXXX
+	 *        \_________________/
+	 *              hwaddr
+	 */
+	ipaddr->s6_addr[0] = 0xFE;
+	ipaddr->s6_addr[1] = 0x80;
+	memcpy(&ipaddr->s6_addr[8], lladdr, EUI64_ADDR_LEN);
+	/* second bit-flip (Universe/Local)
+	 * is done according RFC2464
+	 */
+	ipaddr->s6_addr[8] ^= 0x02;
+}
+
+static inline void lowpan_iphc_uncompress_eui48_lladdr(struct in6_addr *ipaddr,
+						       const void *lladdr)
+{
+	/* fe:80::XXXX:XXff:feXX:XXXX
+	 *        \_________________/
+	 *              hwaddr
+	 */
+	ipaddr->s6_addr[0] = 0xFE;
+	ipaddr->s6_addr[1] = 0x80;
+	memcpy(&ipaddr->s6_addr[8], lladdr, 3);
+	ipaddr->s6_addr[11] = 0xFF;
+	ipaddr->s6_addr[12] = 0xFE;
+	memcpy(&ipaddr->s6_addr[13], lladdr + 3, 3);
+}
+
+#ifdef DEBUG
+/* print data in line */
+static inline void raw_dump_inline(const char *caller, char *msg,
+				   const unsigned char *buf, int len)
+{
+	if (msg)
+		pr_debug("%s():%s: ", caller, msg);
+
+	print_hex_dump_debug("", DUMP_PREFIX_NONE, 16, 1, buf, len, false);
+}
+
+/* print data in a table format:
+ *
+ * addr: xx xx xx xx xx xx
+ * addr: xx xx xx xx xx xx
+ * ...
+ */
+static inline void raw_dump_table(const char *caller, char *msg,
+				  const unsigned char *buf, int len)
+{
+	if (msg)
+		pr_debug("%s():%s:\n", caller, msg);
+
+	print_hex_dump_debug("\t", DUMP_PREFIX_OFFSET, 16, 1, buf, len, false);
+}
+#else
+static inline void raw_dump_table(const char *caller, char *msg,
+				  const unsigned char *buf, int len) { }
+static inline void raw_dump_inline(const char *caller, char *msg,
+				   const unsigned char *buf, int len) { }
+#endif
+
+/**
+ * lowpan_fetch_skb - getting inline data from 6LoWPAN header
+ *
+ * This function will pull data from sk buffer and put it into data to
+ * remove the 6LoWPAN inline data. This function returns true if the
+ * sk buffer is too small to pull the amount of data which is specified
+ * by len.
+ *
+ * @skb: the buffer where the inline data should be pulled from.
+ * @data: destination buffer for the inline data.
+ * @len: amount of data which should be pulled in bytes.
+ */
+static inline bool lowpan_fetch_skb(struct sk_buff *skb, void *data,
+				    unsigned int len)
+{
+	if (unlikely(!pskb_may_pull(skb, len)))
+		return true;
+
+	skb_copy_from_linear_data(skb, data, len);
+	skb_pull(skb, len);
+
+	return false;
+}
+
+static inline bool lowpan_802154_is_valid_src_short_addr(__le16 addr)
+{
+	/* First bit of addr is multicast, reserved or 802.15.4 specific */
+	return !(addr & cpu_to_le16(0x8000));
+}
+
+static inline void lowpan_push_hc_data(u8 **hc_ptr, const void *data,
+				       const size_t len)
+{
+	memcpy(*hc_ptr, data, len);
+	*hc_ptr += len;
+}
+
+int lowpan_register_netdevice(struct net_device *dev,
+			      enum lowpan_lltypes lltype);
+int lowpan_register_netdev(struct net_device *dev,
+			   enum lowpan_lltypes lltype);
+void lowpan_unregister_netdevice(struct net_device *dev);
+void lowpan_unregister_netdev(struct net_device *dev);
+
+/**
+ * lowpan_header_decompress - replace 6LoWPAN header with IPv6 header
+ *
+ * This function replaces the IPHC 6LoWPAN header which should be pointed at
+ * skb->data and skb_network_header, with the IPv6 header.
+ * It would be nice that the caller have the necessary headroom of IPv6 header
+ * and greatest Transport layer header, this would reduce the overhead for
+ * reallocate headroom.
+ *
+ * @skb: the buffer which should be manipulate.
+ * @dev: the lowpan net device pointer.
+ * @daddr: destination lladdr of mac header which is used for compression
+ *	methods.
+ * @saddr: source lladdr of mac header which is used for compression
+ *	methods.
+ */
+int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
+			     const void *daddr, const void *saddr);
+
+/**
+ * lowpan_header_compress - replace IPv6 header with 6LoWPAN header
+ *
+ * This function replaces the IPv6 header which should be pointed at
+ * skb->data and skb_network_header, with the IPHC 6LoWPAN header.
+ * The caller need to be sure that the sk buffer is not shared and at have
+ * at least a headroom which is smaller or equal LOWPAN_IPHC_MAX_HEADER_LEN,
+ * which is the IPHC "more bytes than IPv6 header" at worst case.
+ *
+ * @skb: the buffer which should be manipulate.
+ * @dev: the lowpan net device pointer.
+ * @daddr: destination lladdr of mac header which is used for compression
+ *	methods.
+ * @saddr: source lladdr of mac header which is used for compression
+ *	methods.
+ */
+int lowpan_header_compress(struct sk_buff *skb, const struct net_device *dev,
+			   const void *daddr, const void *saddr);
+
+#endif /* __6LOWPAN_H__ */