11 files changed, 345 insertions, 126 deletions

diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 455d4e6d346d..0b33bfe7dde9 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -227,7 +227,14 @@ as the path relative to the root of the cgroup file system.
 Each cgroup is represented by a directory in the cgroup file system
 containing the following files describing that cgroup:
 
- - tasks: list of tasks (by pid) attached to that cgroup
+ - tasks: list of tasks (by pid) attached to that cgroup.  This list
+   is not guaranteed to be sorted.  Writing a thread id into this file
+   moves the thread into this cgroup.
+ - cgroup.procs: list of tgids in the cgroup.  This list is not
+   guaranteed to be sorted or free of duplicate tgids, and userspace
+   should sort/uniquify the list if this property is required.
+   Writing a tgid into this file moves all threads with that tgid into
+   this cgroup.
  - notify_on_release flag: run the release agent on exit?
  - release_agent: the path to use for release notifications (this file
    exists in the top cgroup only)
@@ -374,7 +381,7 @@ Now you want to do something with this cgroup.
 
 In this directory you can find several files:
 # ls
-notify_on_release tasks
+cgroup.procs notify_on_release tasks
 (plus whatever files added by the attached subsystems)
 
 Now attach your shell to this cgroup:
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 570f9bd9be2b..05d5cf1d743f 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -123,10 +123,18 @@ resuid=n		The user ID which may use the reserved blocks.
 
 sb=n                    Use alternate superblock at this location.
 
-quota
-noquota
-grpquota
-usrquota
+quota                   These options are ignored by the filesystem. They
+noquota                 are used only by quota tools to recognize volumes
+grpquota                where quota should be turned on. See documentation
+usrquota                in the quota-tools package for more details
+                        (http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type>      These options tell filesystem details about quota
+usrjquota=<file>        so that quota information can be properly updated
+grpjquota=<file>        during journal replay. They replace the above
+                        quota options. See documentation in the quota-tools
+                        package for more details
+                        (http://sourceforge.net/projects/linuxquota).
 
 bh              (*)     ext3 associates buffer heads to data pages to
 nobh                    (a) cache disk block mapping information
diff --git a/Documentation/infiniband/user_mad.txt b/Documentation/infiniband/user_mad.txt
index 744687dd195b..8a366959f5cc 100644
--- a/Documentation/infiniband/user_mad.txt
+++ b/Documentation/infiniband/user_mad.txt
@@ -128,8 +128,8 @@ Setting IsSM Capability Bit
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="umad*", NAME="infiniband/%k"
-    KERNEL="issm*", NAME="infiniband/%k"
+    KERNEL=="umad*", NAME="infiniband/%k"
+    KERNEL=="issm*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 
diff --git a/Documentation/infiniband/user_verbs.txt b/Documentation/infiniband/user_verbs.txt
index f847501e50b5..afe3f8da9018 100644
--- a/Documentation/infiniband/user_verbs.txt
+++ b/Documentation/infiniband/user_verbs.txt
@@ -58,7 +58,7 @@ Memory pinning
   To create the appropriate character device files automatically with
   udev, a rule like
 
-    KERNEL="uverbs*", NAME="infiniband/%k"
+    KERNEL=="uverbs*", NAME="infiniband/%k"
 
   can be used.  This will create device nodes named
 
diff --git a/Documentation/isdn/INTERFACE.CAPI b/Documentation/isdn/INTERFACE.CAPI
index 686e107923ec..5fe8de5cc727 100644
--- a/Documentation/isdn/INTERFACE.CAPI
+++ b/Documentation/isdn/INTERFACE.CAPI
@@ -60,10 +60,9 @@ open() operation on regular files or character devices.
 
 After a successful return from register_appl(), CAPI messages from the
 application may be passed to the driver for the device via calls to the
-send_message() callback function. The CAPI message to send is stored in the
-data portion of an skb. Conversely, the driver may call Kernel CAPI's
-capi_ctr_handle_message() function to pass a received CAPI message to Kernel
-CAPI for forwarding to an application, specifying its ApplID.
+send_message() callback function. Conversely, the driver may call Kernel
+CAPI's capi_ctr_handle_message() function to pass a received CAPI message to
+Kernel CAPI for forwarding to an application, specifying its ApplID.
 
 Deregistration requests (CAPI operation CAPI_RELEASE) from applications are
 forwarded as calls to the release_appl() callback function, passing the same
@@ -142,6 +141,7 @@ u16  (*send_message)(struct capi_ctr *ctrlr, struct sk_buff *skb)
         to accepting or queueing the message. Errors occurring during the
         actual processing of the message should be signaled with an
         appropriate reply message.
+        May be called in process or interrupt context.
         Calls to this function are not serialized by Kernel CAPI, ie. it must
         be prepared to be re-entered.
 
@@ -154,7 +154,8 @@ read_proc_t *ctr_read_proc
         system entry, /proc/capi/controllers/<n>; will be called with a
         pointer to the device's capi_ctr structure as the last (data) argument
 
-Note: Callback functions are never called in interrupt context.
+Note: Callback functions except send_message() are never called in interrupt
+context.
 
 - to be filled in before calling capi_ctr_ready():
 
@@ -171,14 +172,40 @@ u8 serial[CAPI_SERIAL_LEN]
         value to return for CAPI_GET_SERIAL
 
 
-4.3 The _cmsg Structure
+4.3 SKBs
+
+CAPI messages are passed between Kernel CAPI and the driver via send_message()
+and capi_ctr_handle_message(), stored in the data portion of a socket buffer
+(skb).  Each skb contains a single CAPI message coded according to the CAPI 2.0
+standard.
+
+For the data transfer messages, DATA_B3_REQ and DATA_B3_IND, the actual
+payload data immediately follows the CAPI message itself within the same skb.
+The Data and Data64 parameters are not used for processing. The Data64
+parameter may be omitted by setting the length field of the CAPI message to 22
+instead of 30.
+
+
+4.4 The _cmsg Structure
 
 (declared in <linux/isdn/capiutil.h>)
 
 The _cmsg structure stores the contents of a CAPI 2.0 message in an easily
-accessible form. It contains members for all possible CAPI 2.0 parameters, of
-which only those appearing in the message type currently being processed are
-actually used. Unused members should be set to zero.
+accessible form. It contains members for all possible CAPI 2.0 parameters,
+including subparameters of the Additional Info and B Protocol structured
+parameters, with the following exceptions:
+
+* second Calling party number (CONNECT_IND)
+
+* Data64 (DATA_B3_REQ and DATA_B3_IND)
+
+* Sending complete (subparameter of Additional Info, CONNECT_REQ and INFO_REQ)
+
+* Global Configuration (subparameter of B Protocol, CONNECT_REQ, CONNECT_RESP
+  and SELECT_B_PROTOCOL_REQ)
+
+Only those parameters appearing in the message type currently being processed
+are actually used. Unused members should be set to zero.
 
 Members are named after the CAPI 2.0 standard names of the parameters they
 represent. See <linux/isdn/capiutil.h> for the exact spelling. Member data
@@ -190,18 +217,19 @@ u16         for CAPI parameters of type 'word'
 
 u32         for CAPI parameters of type 'dword'
 
-_cstruct    for CAPI parameters of type 'struct' not containing any
-            variably-sized (struct) subparameters (eg. 'Called Party Number')
+_cstruct    for CAPI parameters of type 'struct'
             The member is a pointer to a buffer containing the parameter in
             CAPI encoding (length + content). It may also be NULL, which will
             be taken to represent an empty (zero length) parameter.
+            Subparameters are stored in encoded form within the content part.
 
-_cmstruct   for CAPI parameters of type 'struct' containing 'struct'
-            subparameters ('Additional Info' and 'B Protocol')
+_cmstruct   alternative representation for CAPI parameters of type 'struct'
+            (used only for the 'Additional Info' and 'B Protocol' parameters)
             The representation is a single byte containing one of the values:
-            CAPI_DEFAULT: the parameter is empty
-            CAPI_COMPOSE: the values of the subparameters are stored
-            individually in the corresponding _cmsg structure members
+            CAPI_DEFAULT: The parameter is empty/absent.
+            CAPI_COMPOSE: The parameter is present.
+            Subparameter values are stored individually in the corresponding
+            _cmsg structure members.
 
 Functions capi_cmsg2message() and capi_message2cmsg() are provided to convert
 messages between their transport encoding described in the CAPI 2.0 standard
@@ -297,3 +325,26 @@ char *capi_cmd2str(u8 Command, u8 Subcommand)
         be NULL if the command/subcommand is not one of those defined in the
         CAPI 2.0 standard.
 
+
+7. Debugging
+
+The module kernelcapi has a module parameter showcapimsgs controlling some
+debugging output produced by the module. It can only be set when the module is
+loaded, via a parameter "showcapimsgs=<n>" to the modprobe command, either on
+the command line or in the configuration file.
+
+If the lowest bit of showcapimsgs is set, kernelcapi logs controller and
+application up and down events.
+
+In addition, every registered CAPI controller has an associated traceflag
+parameter controlling how CAPI messages sent from and to tha controller are
+logged. The traceflag parameter is initialized with the value of the
+showcapimsgs parameter when the controller is registered, but can later be
+changed via the MANUFACTURER_REQ command KCAPI_CMD_TRACE.
+
+If the value of traceflag is non-zero, CAPI messages are logged.
+DATA_B3 messages are only logged if the value of traceflag is > 2.
+
+If the lowest bit of traceflag is set, only the command/subcommand and message
+length are logged. Otherwise, kernelcapi logs a readable representation of
+the entire message.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 6fa7292947e5..9107b387e91f 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -671,6 +671,7 @@ and is between 256 and 4096 characters. It is defined in the file
         earlyprintk=    [X86,SH,BLACKFIN]
                         earlyprintk=vga
                         earlyprintk=serial[,ttySn[,baudrate]]
+                        earlyprintk=ttySn[,baudrate]
                         earlyprintk=dbgp[debugController#]
 
                         Append ",keep" to not disable it when the real console
diff --git a/Documentation/networking/pktgen.txt b/Documentation/networking/pktgen.txt
index c6cf4a3c16e0..61bb645d50e0 100644
--- a/Documentation/networking/pktgen.txt
+++ b/Documentation/networking/pktgen.txt
@@ -90,6 +90,11 @@ Examples:
  pgset "dstmac 00:00:00:00:00:00"    sets MAC destination address
  pgset "srcmac 00:00:00:00:00:00"    sets MAC source address
 
+ pgset "queue_map_min 0" Sets the min value of tx queue interval
+ pgset "queue_map_max 7" Sets the max value of tx queue interval, for multiqueue devices
+                         To select queue 1 of a given device,
+                         use queue_map_min=1 and queue_map_max=1
+
  pgset "src_mac_count 1" Sets the number of MACs we'll range through.  
                          The 'minimum' MAC is what you set with srcmac.
 
@@ -101,6 +106,9 @@ Examples:
                               IPDST_RND, UDPSRC_RND,
                               UDPDST_RND, MACSRC_RND, MACDST_RND 
                               MPLS_RND, VID_RND, SVID_RND
+                              QUEUE_MAP_RND # queue map random
+                              QUEUE_MAP_CPU # queue map mirrors smp_processor_id()
+
 
  pgset "udp_src_min 9"   set UDP source port min, If < udp_src_max, then
                          cycle through the port range.
diff --git a/Documentation/scsi/hptiop.txt b/Documentation/scsi/hptiop.txt
index a6eb4add1be6..9605179711f4 100644
--- a/Documentation/scsi/hptiop.txt
+++ b/Documentation/scsi/hptiop.txt
@@ -3,6 +3,25 @@ HIGHPOINT ROCKETRAID 3xxx/4xxx ADAPTER DRIVER (hptiop)
 Controller Register Map
 -------------------------
 
+For RR44xx Intel IOP based adapters, the controller IOP is accessed via PCI BAR0 and BAR2:
+
+     BAR0 offset    Register
+            0x11C5C Link Interface IRQ Set
+            0x11C60 Link Interface IRQ Clear
+
+     BAR2 offset    Register
+            0x10    Inbound Message Register 0
+            0x14    Inbound Message Register 1
+            0x18    Outbound Message Register 0
+            0x1C    Outbound Message Register 1
+            0x20    Inbound Doorbell Register
+            0x24    Inbound Interrupt Status Register
+            0x28    Inbound Interrupt Mask Register
+            0x30    Outbound Interrupt Status Register
+            0x34    Outbound Interrupt Mask Register
+            0x40    Inbound Queue Port
+            0x44    Outbound Queue Port
+
 For Intel IOP based adapters, the controller IOP is accessed via PCI BAR0:
 
      BAR0 offset    Register
@@ -93,7 +112,7 @@ The driver exposes following sysfs attributes:
 
 
 -----------------------------------------------------------------------------
-Copyright (C) 2006-2007 HighPoint Technologies, Inc. All Rights Reserved.
+Copyright (C) 2006-2009 HighPoint Technologies, Inc. All Rights Reserved.
 
   This file is distributed in the hope that it will be useful,
   but WITHOUT ANY WARRANTY; without even the implied warranty of
diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
index 72a22f65960e..262d8e6793a3 100644
--- a/Documentation/vm/ksm.txt
+++ b/Documentation/vm/ksm.txt
@@ -52,15 +52,15 @@ The KSM daemon is controlled by sysfs files in /sys/kernel/mm/ksm/,
 readable by all but writable only by root:
 
 max_kernel_pages - set to maximum number of kernel pages that KSM may use
-                   e.g. "echo 2000 > /sys/kernel/mm/ksm/max_kernel_pages"
+                   e.g. "echo 100000 > /sys/kernel/mm/ksm/max_kernel_pages"
                    Value 0 imposes no limit on the kernel pages KSM may use;
                    but note that any process using MADV_MERGEABLE can cause
                    KSM to allocate these pages, unswappable until it exits.
-                   Default: 2000 (chosen for demonstration purposes)
+                   Default: quarter of memory (chosen to not pin too much)
 
 pages_to_scan    - how many present pages to scan before ksmd goes to sleep
-                   e.g. "echo 200 > /sys/kernel/mm/ksm/pages_to_scan"
-                   Default: 200 (chosen for demonstration purposes)
+                   e.g. "echo 100 > /sys/kernel/mm/ksm/pages_to_scan"
+                   Default: 100 (chosen for demonstration purposes)
 
 sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                    e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
@@ -70,7 +70,8 @@ run              - set 0 to stop ksmd from running but keep merged pages,
                    set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                    set 2 to stop ksmd and unmerge all pages currently merged,
                          but leave mergeable areas registered for next run
-                   Default: 1 (for immediate use by apps which register)
+                   Default: 0 (must be changed to 1 to activate KSM,
+                               except if CONFIG_SYSFS is disabled)
 
 The effectiveness of KSM and MADV_MERGEABLE is shown in /sys/kernel/mm/ksm/:
 
@@ -86,4 +87,4 @@ pages_volatile embraces several different kinds of activity, but a high
 proportion there would also indicate poor use of madvise MADV_MERGEABLE.
 
 Izik Eidus,
-Hugh Dickins, 30 July 2009
+Hugh Dickins, 24 Sept 2009
diff --git a/Documentation/vm/page-types.c b/Documentation/vm/page-types.c
index fa1a30d9e9d5..3ec4f2a22585 100644
--- a/Documentation/vm/page-types.c
+++ b/Documentation/vm/page-types.c
@@ -2,7 +2,10 @@
  * page-types: Tool for querying page flags
  *
  * Copyright (C) 2009 Intel corporation
- * Copyright (C) 2009 Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Authors: Wu Fengguang <fengguang.wu@intel.com>
+ *
+ * Released under the General Public License (GPL).
  */
 
 #define _LARGEFILE64_SOURCE
@@ -69,7 +72,9 @@
 #define KPF_COMPOUND_TAIL       16
 #define KPF_HUGE                17
 #define KPF_UNEVICTABLE         18
+#define KPF_HWPOISON            19
 #define KPF_NOPAGE              20
+#define KPF_KSM                 21
 
 /* [32-] kernel hacking assistances */
 #define KPF_RESERVED            32
@@ -116,7 +121,9 @@ static char *page_flag_names[] = {
         [KPF_COMPOUND_TAIL]     = "T:compound_tail",
         [KPF_HUGE]              = "G:huge",
         [KPF_UNEVICTABLE]       = "u:unevictable",
+        [KPF_HWPOISON]          = "X:hwpoison",
         [KPF_NOPAGE]            = "n:nopage",
+        [KPF_KSM]               = "x:ksm",
 
         [KPF_RESERVED]          = "r:reserved",
         [KPF_MLOCKED]           = "m:mlocked",
@@ -152,9 +159,6 @@ static unsigned long	opt_size[MAX_ADDR_RANGES];
 static int              nr_vmas;
 static unsigned long    pg_start[MAX_VMAS];
 static unsigned long    pg_end[MAX_VMAS];
-static unsigned long    voffset;
-
-static int              pagemap_fd;
 
 #define MAX_BIT_FILTERS 64
 static int              nr_bit_filters;
@@ -163,9 +167,16 @@ static uint64_t		opt_bits[MAX_BIT_FILTERS];
 
 static int              page_size;
 
-#define PAGES_BATCH     (64 << 10)      /* 64k pages */
+static int              pagemap_fd;
 static int              kpageflags_fd;
 
+static int              opt_hwpoison;
+static int              opt_unpoison;
+
+static char             *hwpoison_debug_fs = "/debug/hwpoison";
+static int              hwpoison_inject_fd;
+static int              hwpoison_forget_fd;
+
 #define HASH_SHIFT      13
 #define HASH_SIZE       (1 << HASH_SHIFT)
 #define HASH_MASK       (HASH_SIZE - 1)
@@ -207,6 +218,74 @@ static void fatal(const char *x, ...)
         exit(EXIT_FAILURE);
 }
 
+int checked_open(const char *pathname, int flags)
+{
+        int fd = open(pathname, flags);
+
+        if (fd < 0) {
+                perror(pathname);
+                exit(EXIT_FAILURE);
+        }
+
+        return fd;
+}
+
+/*
+ * pagemap/kpageflags routines
+ */
+
+static unsigned long do_u64_read(int fd, char *name,
+                                 uint64_t *buf,
+                                 unsigned long index,
+                                 unsigned long count)
+{
+        long bytes;
+
+        if (index > ULONG_MAX / 8)
+                fatal("index overflow: %lu\n", index);
+
+        if (lseek(fd, index * 8, SEEK_SET) < 0) {
+                perror(name);
+                exit(EXIT_FAILURE);
+        }
+
+        bytes = read(fd, buf, count * 8);
+        if (bytes < 0) {
+                perror(name);
+                exit(EXIT_FAILURE);
+        }
+        if (bytes % 8)
+                fatal("partial read: %lu bytes\n", bytes);
+
+        return bytes / 8;
+}
+
+static unsigned long kpageflags_read(uint64_t *buf,
+                                     unsigned long index,
+                                     unsigned long pages)
+{
+        return do_u64_read(kpageflags_fd, PROC_KPAGEFLAGS, buf, index, pages);
+}
+
+static unsigned long pagemap_read(uint64_t *buf,
+                                  unsigned long index,
+                                  unsigned long pages)
+{
+        return do_u64_read(pagemap_fd, "/proc/pid/pagemap", buf, index, pages);
+}
+
+static unsigned long pagemap_pfn(uint64_t val)
+{
+        unsigned long pfn;
+
+        if (val & PM_PRESENT)
+                pfn = PM_PFRAME(val);
+        else
+                pfn = 0;
+
+        return pfn;
+}
+
 
 /*
  * page flag names
@@ -255,7 +334,8 @@ static char *page_flag_longname(uint64_t flags)
  * page list and summary
  */
 
-static void show_page_range(unsigned long offset, uint64_t flags)
+static void show_page_range(unsigned long voffset,
+                            unsigned long offset, uint64_t flags)
 {
         static uint64_t      flags0;
         static unsigned long voff;
@@ -281,7 +361,8 @@ static void show_page_range(unsigned long offset, uint64_t flags)
         count  = 1;
 }
 
-static void show_page(unsigned long offset, uint64_t flags)
+static void show_page(unsigned long voffset,
+                      unsigned long offset, uint64_t flags)
 {
         if (opt_pid)
                 printf("%lx\t", voffset);
@@ -362,6 +443,62 @@ static uint64_t well_known_flags(uint64_t flags)
         return flags;
 }
 
+static uint64_t kpageflags_flags(uint64_t flags)
+{
+        flags = expand_overloaded_flags(flags);
+
+        if (!opt_raw)
+                flags = well_known_flags(flags);
+
+        return flags;
+}
+
+/*
+ * page actions
+ */
+
+static void prepare_hwpoison_fd(void)
+{
+        char buf[100];
+
+        if (opt_hwpoison && !hwpoison_inject_fd) {
+                sprintf(buf, "%s/corrupt-pfn", hwpoison_debug_fs);
+                hwpoison_inject_fd = checked_open(buf, O_WRONLY);
+        }
+
+        if (opt_unpoison && !hwpoison_forget_fd) {
+                sprintf(buf, "%s/renew-pfn", hwpoison_debug_fs);
+                hwpoison_forget_fd = checked_open(buf, O_WRONLY);
+        }
+}
+
+static int hwpoison_page(unsigned long offset)
+{
+        char buf[100];
+        int len;
+
+        len = sprintf(buf, "0x%lx\n", offset);
+        len = write(hwpoison_inject_fd, buf, len);
+        if (len < 0) {
+                perror("hwpoison inject");
+                return len;
+        }
+        return 0;
+}
+
+static int unpoison_page(unsigned long offset)
+{
+        char buf[100];
+        int len;
+
+        len = sprintf(buf, "0x%lx\n", offset);
+        len = write(hwpoison_forget_fd, buf, len);
+        if (len < 0) {
+                perror("hwpoison forget");
+                return len;
+        }
+        return 0;
+}
 
 /*
  * page frame walker
@@ -394,104 +531,83 @@ static int hash_slot(uint64_t flags)
         exit(EXIT_FAILURE);
 }
 
-static void add_page(unsigned long offset, uint64_t flags)
+static void add_page(unsigned long voffset,
+                     unsigned long offset, uint64_t flags)
 {
-        flags = expand_overloaded_flags(flags);
-
-        if (!opt_raw)
-                flags = well_known_flags(flags);
+        flags = kpageflags_flags(flags);
 
         if (!bit_mask_ok(flags))
                 return;
 
+        if (opt_hwpoison)
+                hwpoison_page(offset);
+        if (opt_unpoison)
+                unpoison_page(offset);
+
         if (opt_list == 1)
-                show_page_range(offset, flags);
+                show_page_range(voffset, offset, flags);
         else if (opt_list == 2)
-                show_page(offset, flags);
+                show_page(voffset, offset, flags);
 
         nr_pages[hash_slot(flags)]++;
         total_pages++;
 }
 
-static void walk_pfn(unsigned long index, unsigned long count)
+#define KPAGEFLAGS_BATCH        (64 << 10)      /* 64k pages */
+static void walk_pfn(unsigned long voffset,
+                     unsigned long index,
+                     unsigned long count)
 {
+        uint64_t buf[KPAGEFLAGS_BATCH];
         unsigned long batch;
-        unsigned long n;
+        unsigned long pages;
         unsigned long i;
 
-        if (index > ULONG_MAX / KPF_BYTES)
-                fatal("index overflow: %lu\n", index);
-
-        lseek(kpageflags_fd, index * KPF_BYTES, SEEK_SET);
-
         while (count) {
-                uint64_t kpageflags_buf[KPF_BYTES * PAGES_BATCH];
-
-                batch = min_t(unsigned long, count, PAGES_BATCH);
-                n = read(kpageflags_fd, kpageflags_buf, batch * KPF_BYTES);
-                if (n == 0)
+                batch = min_t(unsigned long, count, KPAGEFLAGS_BATCH);
+                pages = kpageflags_read(buf, index, batch);
+                if (pages == 0)
                         break;
-                if (n < 0) {
-                        perror(PROC_KPAGEFLAGS);
-                        exit(EXIT_FAILURE);
-                }
 
-                if (n % KPF_BYTES != 0)
-                        fatal("partial read: %lu bytes\n", n);
-                n = n / KPF_BYTES;
+                for (i = 0; i < pages; i++)
+                        add_page(voffset + i, index + i, buf[i]);
 
-                for (i = 0; i < n; i++)
-                        add_page(index + i, kpageflags_buf[i]);
-
-                index += batch;
-                count -= batch;
+                index += pages;
+                count -= pages;
         }
 }
 
-
-#define PAGEMAP_BATCH   4096
-static unsigned long task_pfn(unsigned long pgoff)
+#define PAGEMAP_BATCH   (64 << 10)
+static void walk_vma(unsigned long index, unsigned long count)
 {
-        static uint64_t buf[PAGEMAP_BATCH];
-        static unsigned long start;
-        static long count;
-        uint64_t pfn;
+        uint64_t buf[PAGEMAP_BATCH];
+        unsigned long batch;
+        unsigned long pages;
+        unsigned long pfn;
+        unsigned long i;
 
-        if (pgoff < start || pgoff >= start + count) {
-                if (lseek64(pagemap_fd,
-                            (uint64_t)pgoff * PM_ENTRY_BYTES,
-                            SEEK_SET) < 0) {
-                        perror("pagemap seek");
-                        exit(EXIT_FAILURE);
-                }
-                count = read(pagemap_fd, buf, sizeof(buf));
-                if (count == 0)
-                        return 0;
-                if (count < 0) {
-                        perror("pagemap read");
-                        exit(EXIT_FAILURE);
-                }
-                if (count % PM_ENTRY_BYTES) {
-                        fatal("pagemap read not aligned.\n");
-                        exit(EXIT_FAILURE);
-                }
-                count /= PM_ENTRY_BYTES;
-                start = pgoff;
-        }
+        while (count) {
+                batch = min_t(unsigned long, count, PAGEMAP_BATCH);
+                pages = pagemap_read(buf, index, batch);
+                if (pages == 0)
+                        break;
 
-        pfn = buf[pgoff - start];
-        if (pfn & PM_PRESENT)
-                pfn = PM_PFRAME(pfn);
-        else
-                pfn = 0;
+                for (i = 0; i < pages; i++) {
+                        pfn = pagemap_pfn(buf[i]);
+                        if (pfn)
+                                walk_pfn(index + i, pfn, 1);
+                }
 
-        return pfn;
+                index += pages;
+                count -= pages;
+        }
 }
 
 static void walk_task(unsigned long index, unsigned long count)
 {
-        int i = 0;
         const unsigned long end = index + count;
+        unsigned long start;
+        int i = 0;
 
         while (index < end) {
 
@@ -501,15 +617,11 @@ static void walk_task(unsigned long index, unsigned long count)
                 if (pg_start[i] >= end)
                         return;
 
-                voffset = max_t(unsigned long, pg_start[i], index);
-                index   = min_t(unsigned long, pg_end[i], end);
+                start = max_t(unsigned long, pg_start[i], index);
+                index = min_t(unsigned long, pg_end[i], end);
 
-                assert(voffset < index);
-                for (; voffset < index; voffset++) {
-                        unsigned long pfn = task_pfn(voffset);
-                        if (pfn)
-                                walk_pfn(pfn, 1);
-                }
+                assert(start < index);
+                walk_vma(start, index - start);
         }
 }
 
@@ -527,18 +639,14 @@ static void walk_addr_ranges(void)
 {
         int i;
 
-        kpageflags_fd = open(PROC_KPAGEFLAGS, O_RDONLY);
-        if (kpageflags_fd < 0) {
-                perror(PROC_KPAGEFLAGS);
-                exit(EXIT_FAILURE);
-        }
+        kpageflags_fd = checked_open(PROC_KPAGEFLAGS, O_RDONLY);
 
         if (!nr_addr_ranges)
                 add_addr_range(0, ULONG_MAX);
 
         for (i = 0; i < nr_addr_ranges; i++)
                 if (!opt_pid)
-                        walk_pfn(opt_offset[i], opt_size[i]);
+                        walk_pfn(0, opt_offset[i], opt_size[i]);
                 else
                         walk_task(opt_offset[i], opt_size[i]);
 
@@ -575,6 +683,8 @@ static void usage(void)
 "            -l|--list                 Show page details in ranges\n"
 "            -L|--list-each            Show page details one by one\n"
 "            -N|--no-summary           Don't show summay info\n"
+"            -X|--hwpoison             hwpoison pages\n"
+"            -x|--unpoison             unpoison pages\n"
 "            -h|--help                 Show this usage message\n"
 "addr-spec:\n"
 "            N                         one page at offset N (unit: pages)\n"
@@ -624,11 +734,7 @@ static void parse_pid(const char *str)
         opt_pid = parse_number(str);
 
         sprintf(buf, "/proc/%d/pagemap", opt_pid);
-        pagemap_fd = open(buf, O_RDONLY);
-        if (pagemap_fd < 0) {
-                perror(buf);
-                exit(EXIT_FAILURE);
-        }
+        pagemap_fd = checked_open(buf, O_RDONLY);
 
         sprintf(buf, "/proc/%d/maps", opt_pid);
         file = fopen(buf, "r");
@@ -788,6 +894,8 @@ static struct option opts[] = {
         { "list"      , 0, NULL, 'l' },
         { "list-each" , 0, NULL, 'L' },
         { "no-summary", 0, NULL, 'N' },
+        { "hwpoison"  , 0, NULL, 'X' },
+        { "unpoison"  , 0, NULL, 'x' },
         { "help"      , 0, NULL, 'h' },
         { NULL        , 0, NULL, 0 }
 };
@@ -799,7 +907,7 @@ int main(int argc, char *argv[])
         page_size = getpagesize();
 
         while ((c = getopt_long(argc, argv,
-                                "rp:f:a:b:lLNh", opts, NULL)) != -1) {
+                                "rp:f:a:b:lLNXxh", opts, NULL)) != -1) {
                 switch (c) {
                 case 'r':
                         opt_raw = 1;
@@ -825,6 +933,14 @@ int main(int argc, char *argv[])
                 case 'N':
                         opt_no_summary = 1;
                         break;
+                case 'X':
+                        opt_hwpoison = 1;
+                        prepare_hwpoison_fd();
+                        break;
+                case 'x':
+                        opt_unpoison = 1;
+                        prepare_hwpoison_fd();
+                        break;
                 case 'h':
                         usage();
                         exit(0);
@@ -844,7 +960,7 @@ int main(int argc, char *argv[])
         walk_addr_ranges();
 
         if (opt_list == 1)
-                show_page_range(0, 0);  /* drain the buffer */
+                show_page_range(0, 0, 0);  /* drain the buffer */
 
         if (opt_no_summary)
                 return 0;
diff --git a/Documentation/vm/pagemap.txt b/Documentation/vm/pagemap.txt
index 600a304a828c..df09b9650a81 100644
--- a/Documentation/vm/pagemap.txt
+++ b/Documentation/vm/pagemap.txt
@@ -57,7 +57,9 @@ There are three components to pagemap:
     16. COMPOUND_TAIL
     16. HUGE
     18. UNEVICTABLE
+    19. HWPOISON
     20. NOPAGE
+    21. KSM
 
 Short descriptions to the page flags:
 
@@ -86,9 +88,15 @@ Short descriptions to the page flags:
 17. HUGE
     this is an integral part of a HugeTLB page
 
+19. HWPOISON
+    hardware detected memory corruption on this page: don't touch the data!
+
 20. NOPAGE
     no page frame exists at the requested address
 
+21. KSM
+    identical memory pages dynamically shared between one or more processes
+
     [IO related page flags]
  1. ERROR     IO error occurred
  3. UPTODATE  page has up-to-date data