6 files changed, 89 insertions, 40 deletions

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ba3a7cb1eaa0..9a72cc78e6b8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout;
 #define sysctl_legacy_va_layout 0
 #endif
 
-extern unsigned long mmap_min_addr;
-
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -575,19 +573,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 }
 
 /*
- * If a hint addr is less than mmap_min_addr change hint to be as
- * low as possible but still greater than mmap_min_addr
- */
-static inline unsigned long round_hint_to_min(unsigned long hint)
-{
-        hint &= PAGE_MASK;
-        if (((void *)hint != NULL) &&
-            (hint < mmap_min_addr))
-                return PAGE_ALIGN(mmap_min_addr);
-        return hint;
-}
-
-/*
  * Some inline functions in vmstat.h depend on page_zone()
  */
 #include <linux/vmstat.h>
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index fdffb413b192..f6b90240dd41 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -473,7 +473,6 @@ extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct page *page);
 extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
 extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
-extern void nfs_writedata_release(void *);
 
 /*
  * Try to write back everything synchronously (but check the
@@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_write_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_write_data *wdata);
-extern void nfs_commitdata_release(void *wdata);
 #else
 static inline int
 nfs_commit_inode(struct inode *inode, int how)
@@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode)
  * Allocate nfs_write_data structures
  */
 extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages);
+extern void nfs_writedata_free(struct nfs_write_data *);
 
 /*
  * linux/fs/nfs/read.c
@@ -515,7 +514,6 @@ extern int  nfs_readpage(struct file *, struct page *);
 extern int  nfs_readpages(struct file *, struct address_space *,
                 struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
-extern void nfs_readdata_release(void *data);
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
                                struct page *);
 
@@ -523,6 +521,7 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
  * Allocate nfs_read_data structures
  */
 extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages);
+extern void nfs_readdata_free(struct nfs_read_data *);
 
 /*
  * linux/fs/nfs3proc.c
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index a67dd5c5b6d3..b53f7006cc4e 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -115,28 +115,44 @@ enum perf_counter_sample_format {
         PERF_SAMPLE_TID                         = 1U << 1,
         PERF_SAMPLE_TIME                        = 1U << 2,
         PERF_SAMPLE_ADDR                        = 1U << 3,
-        PERF_SAMPLE_GROUP                       = 1U << 4,
+        PERF_SAMPLE_READ                        = 1U << 4,
         PERF_SAMPLE_CALLCHAIN                   = 1U << 5,
         PERF_SAMPLE_ID                          = 1U << 6,
         PERF_SAMPLE_CPU                         = 1U << 7,
         PERF_SAMPLE_PERIOD                      = 1U << 8,
         PERF_SAMPLE_STREAM_ID                   = 1U << 9,
-        PERF_SAMPLE_TP_RECORD                   = 1U << 10,
+        PERF_SAMPLE_RAW                         = 1U << 10,
 
         PERF_SAMPLE_MAX = 1U << 11,             /* non-ABI */
 };
 
 /*
- * Bits that can be set in attr.read_format to request that
- * reads on the counter should return the indicated quantities,
- * in increasing order of bit value, after the counter value.
+ * The format of the data returned by read() on a perf counter fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *      { u64           value;
+ *        { u64         time_enabled; } && PERF_FORMAT_ENABLED
+ *        { u64         time_running; } && PERF_FORMAT_RUNNING
+ *        { u64         id;           } && PERF_FORMAT_ID
+ *      } && !PERF_FORMAT_GROUP
+ *
+ *      { u64           nr;
+ *        { u64         time_enabled; } && PERF_FORMAT_ENABLED
+ *        { u64         time_running; } && PERF_FORMAT_RUNNING
+ *        { u64         value;
+ *          { u64       id;           } && PERF_FORMAT_ID
+ *        }             cntr[nr];
+ *      } && PERF_FORMAT_GROUP
+ * };
  */
 enum perf_counter_read_format {
         PERF_FORMAT_TOTAL_TIME_ENABLED          = 1U << 0,
         PERF_FORMAT_TOTAL_TIME_RUNNING          = 1U << 1,
         PERF_FORMAT_ID                          = 1U << 2,
+        PERF_FORMAT_GROUP                       = 1U << 3,
 
-        PERF_FORMAT_MAX = 1U << 3,              /* non-ABI */
+        PERF_FORMAT_MAX = 1U << 4,              /* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0     64      /* sizeof first published struct */
@@ -343,10 +359,8 @@ enum perf_event_type {
          * struct {
          *      struct perf_event_header        header;
          *      u32                             pid, tid;
-         *      u64                             value;
-         *      { u64           time_enabled;   } && PERF_FORMAT_ENABLED
-         *      { u64           time_running;   } && PERF_FORMAT_RUNNING
-         *      { u64           parent_id;      } && PERF_FORMAT_ID
+         *
+         *      struct read_format              values;
          * };
          */
         PERF_EVENT_READ                 = 8,
@@ -364,11 +378,24 @@ enum perf_event_type {
          *      { u32                   cpu, res; } && PERF_SAMPLE_CPU
          *      { u64                   period;   } && PERF_SAMPLE_PERIOD
          *
-         *      { u64                   nr;
-         *        { u64 id, val; }      cnt[nr];  } && PERF_SAMPLE_GROUP
+         *      { struct read_format    values;   } && PERF_SAMPLE_READ
          *
          *      { u64                   nr,
          *        u64                   ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+         *
+         *      #
+         *      # The RAW record below is opaque data wrt the ABI
+         *      #
+         *      # That is, the ABI doesn't make any promises wrt to
+         *      # the stability of its content, it may vary depending
+         *      # on event, hardware, kernel version and phase of
+         *      # the moon.
+         *      #
+         *      # In other words, PERF_SAMPLE_RAW contents are not an ABI.
+         *      #
+         *
+         *      { u32                   size;
+         *        char                  data[size];}&& PERF_SAMPLE_RAW
          * };
          */
         PERF_EVENT_SAMPLE               = 9,
@@ -414,9 +441,9 @@ struct perf_callchain_entry {
         __u64                           ip[PERF_MAX_STACK_DEPTH];
 };
 
-struct perf_tracepoint_record {
-        int                             size;
-        char                            *record;
+struct perf_raw_record {
+        u32                             size;
+        void                            *data;
 };
 
 struct task_struct;
@@ -687,11 +714,13 @@ struct perf_sample_data {
         struct pt_regs                  *regs;
         u64                             addr;
         u64                             period;
-        void                            *private;
+        struct perf_raw_record          *raw;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
                                  struct perf_sample_data *data);
+extern void perf_counter_output(struct perf_counter *counter, int nmi,
+                                struct perf_sample_data *data);
 
 /*
  * Return 1 for a software counter, 0 for a hardware counter
diff --git a/include/linux/security.h b/include/linux/security.h
index 5eff459b3833..1f16eea2017b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -28,6 +28,7 @@
 #include <linux/resource.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
+#include <linux/mm.h> /* PAGE_ALIGN */
 #include <linux/msg.h>
 #include <linux/sched.h>
 #include <linux/key.h>
@@ -66,6 +67,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
 extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
+extern int cap_file_mmap(struct file *file, unsigned long reqprot,
+                         unsigned long prot, unsigned long flags,
+                         unsigned long addr, unsigned long addr_only);
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
                           unsigned long arg4, unsigned long arg5);
@@ -92,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb);
 extern int cap_netlink_recv(struct sk_buff *skb, int cap);
 
 extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
 /*
  * Values used in the task_security_ops calls
  */
@@ -116,6 +121,21 @@ struct request_sock;
 #define LSM_UNSAFE_PTRACE       2
 #define LSM_UNSAFE_PTRACE_CAP   4
 
+/*
+ * If a hint addr is less than mmap_min_addr change hint to be as
+ * low as possible but still greater than mmap_min_addr
+ */
+static inline unsigned long round_hint_to_min(unsigned long hint)
+{
+        hint &= PAGE_MASK;
+        if (((void *)hint != NULL) &&
+            (hint < mmap_min_addr))
+                return PAGE_ALIGN(mmap_min_addr);
+        return hint;
+}
+extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp,
+                                 void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #ifdef CONFIG_SECURITY
 
 struct security_mnt_opts {
@@ -2197,9 +2217,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot,
                                      unsigned long addr,
                                      unsigned long addr_only)
 {
-        if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
-                return -EACCES;
-        return 0;
+        return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
 }
 
 static inline int security_file_mprotect(struct vm_area_struct *vma,
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6788e1a4d4ca..cf3c2f5dba51 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -77,7 +77,14 @@ struct task_struct;
 #define __WAIT_BIT_KEY_INITIALIZER(word, bit)                           \
         { .flags = word, .bit_nr = bit, }
 
-extern void init_waitqueue_head(wait_queue_head_t *q);
+extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *);
+
+#define init_waitqueue_head(q)                          \
+        do {                                            \
+                static struct lock_class_key __key;     \
+                                                        \
+                __init_waitqueue_head((q), &__key);     \
+        } while (0)
 
 #ifdef CONFIG_LOCKDEP
 # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 7fb16d90e7b1..f64fbaae781a 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -637,12 +637,20 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *      pc = preempt_count();
  *
  *      __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
- *      __entry_size = __data_size + sizeof(*entry);
+ *
+ *      // Below we want to get the aligned size by taking into account
+ *      // the u32 field that will later store the buffer size
+ *      __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *                           sizeof(u64));
+ *      __entry_size -= sizeof(u32);
  *
  *      do {
  *              char raw_data[__entry_size]; <- allocate our sample in the stack
  *              struct trace_entry *ent;
  *
+ *              zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *              *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
  *              entry = (struct ftrace_raw_<call> *)raw_data;
  *              ent = &entry->ent;
  *              tracing_generic_entry_update(ent, irq_flags, pc);
@@ -685,12 +693,15 @@ static void ftrace_profile_##call(proto)				\
         pc = preempt_count();                                           \
                                                                         \
         __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
-        __entry_size = ALIGN(__data_size + sizeof(*entry), sizeof(u64));\
+        __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+                             sizeof(u64));                              \
+        __entry_size -= sizeof(u32);                                    \
                                                                         \
         do {                                                            \
                 char raw_data[__entry_size];                            \
                 struct trace_entry *ent;                                \
                                                                         \
+                *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \
                 entry = (struct ftrace_raw_##call *)raw_data;           \
                 ent = &entry->ent;                                      \
                 tracing_generic_entry_update(ent, irq_flags, pc);       \