This is the mail archive of the gdb-patches@sourceware.org mailing list for the GDB project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

[PATCH 1/2] Implement support for checking /proc/PID/coredump_filter


This is the core patch.  It implements the support for honoring the
/proc/PID/coredump_filter file.

Changes from v3:

  - Removed the new 'enum memory_mapping_state'; now
    linux_find_memory_regions_full is either calling
    gcore_create_callback when the mapping should be dumped (with
    'modified = 1'), or not calling the function at all.

  - Reviewed comments.  Added new variable 'should_dump_p', and
    removed 'modified' from linux_find_memory_regions_full.

gdb/ChangeLog:
2015-03-19  Sergio Durigan Junior  <sergiodj@redhat.com>
	    Jan Kratochvil  <jan.kratochvil@redhat.com>
	    Oleg Nesterov  <oleg@redhat.com>

	PR corefiles/16092
	* linux-tdep.c: Include 'gdbcmd.h' and 'gdb_regex.h'.
	New enum identifying the various options of the coredump_filter
	file.
	(struct smaps_vmflags): New struct.
	(use_coredump_filter): New variable.
	(decode_vmflags): New function.
	(mapping_is_anonymous_p): Likewise.
	(dump_mapping_p): Likewise.
	(linux_find_memory_regions_full): New variables
	'coredumpfilter_name', 'coredumpfilterdata', 'pid', 'filterflags',
	'should_dump_p'.  Removed variable 'modified'.  Read
	/proc/<PID>/smaps file; improve parsing of its information.
	Implement memory mapping filtering based on its contents.
	(show_use_coredump_filter): New function.
	(_initialize_linux_tdep): New command 'set use-coredump-filter'.
---
 gdb/linux-tdep.c | 408 +++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 380 insertions(+), 28 deletions(-)

diff --git a/gdb/linux-tdep.c b/gdb/linux-tdep.c
index ea0d4cd..3831580 100644
--- a/gdb/linux-tdep.c
+++ b/gdb/linux-tdep.c
@@ -35,9 +35,61 @@
 #include "observer.h"
 #include "objfiles.h"
 #include "infcall.h"
+#include "gdbcmd.h"
+#include "gdb_regex.h"
 
 #include <ctype.h>
 
+/* This enum represents the values that the user can choose when
+   informing the Linux kernel about which memory mappings will be
+   dumped in a corefile.  They are described in the file
+   Documentation/filesystems/proc.txt, inside the Linux kernel
+   tree.  */
+
+enum
+  {
+    COREFILTER_ANON_PRIVATE = 1 << 0,
+    COREFILTER_ANON_SHARED = 1 << 1,
+    COREFILTER_MAPPED_PRIVATE = 1 << 2,
+    COREFILTER_MAPPED_SHARED = 1 << 3,
+    COREFILTER_ELF_HEADERS = 1 << 4,
+    COREFILTER_HUGETLB_PRIVATE = 1 << 5,
+    COREFILTER_HUGETLB_SHARED = 1 << 6,
+  };
+
+/* This struct is used to map flags found in the "VmFlags:" field (in
+   the /proc/<PID>/smaps file).  */
+
+struct smaps_vmflags
+  {
+    /* Zero if this structure has not been initialized yet.  It
+       probably means that the Linux kernel being used does not emit
+       the "VmFlags:" field on "/proc/PID/smaps".  */
+
+    unsigned int initialized_p : 1;
+
+    /* Memory mapped I/O area (VM_IO, "io").  */
+
+    unsigned int io_page : 1;
+
+    /* Area uses huge TLB pages (VM_HUGETLB, "ht").  */
+
+    unsigned int uses_huge_tlb : 1;
+
+    /* Do not include this memory region on the coredump (VM_DONTDUMP, "dd").  */
+
+    unsigned int exclude_coredump : 1;
+
+    /* Is this a MAP_SHARED mapping (VM_SHARED, "sh").  */
+
+    unsigned int shared_mapping : 1;
+  };
+
+/* Whether to take the /proc/PID/coredump_filter into account when
+   generating a corefile.  */
+
+static int use_coredump_filter = 1;
+
 /* This enum represents the signals' numbers on a generic architecture
    running the Linux kernel.  The definition of "generic" comes from
    the file <include/uapi/asm-generic/signal.h>, from the Linux kernel
@@ -381,6 +433,220 @@ read_mapping (const char *line,
   *filename = p;
 }
 
+/* Helper function to decode the "VmFlags" field in /proc/PID/smaps.
+
+   This function was based on the documentation found on
+   <Documentation/filesystems/proc.txt>, on the Linux kernel.
+
+   Linux kernels before commit
+   834f82e2aa9a8ede94b17b656329f850c1471514 do not have this field on
+   smaps.  */
+
+static void
+decode_vmflags (char *p, struct smaps_vmflags *v)
+{
+  char *saveptr;
+  const char *s;
+
+  v->initialized_p = 1;
+  p = skip_to_space (p);
+  p = skip_spaces (p);
+
+  for (s = strtok_r (p, " ", &saveptr);
+       s != NULL;
+       s = strtok_r (NULL, " ", &saveptr))
+    {
+      if (strcmp (s, "io") == 0)
+	v->io_page = 1;
+      else if (strcmp (s, "ht") == 0)
+	v->uses_huge_tlb = 1;
+      else if (strcmp (s, "dd") == 0)
+	v->exclude_coredump = 1;
+      else if (strcmp (s, "sh") == 0)
+	v->shared_mapping = 1;
+    }
+}
+
+/* Return 1 if the memory mapping is anonymous, 0 otherwise.
+
+   FILENAME is the name of the file present in the first line of the
+   memory mapping, in the "/proc/PID/smaps" output.  For example, if
+   the first line is:
+
+   7fd0ca877000-7fd0d0da0000 r--p 00000000 fd:02 2100770   /path/to/file
+
+   Then FILENAME will be "/path/to/file".  */
+
+static int
+mapping_is_anonymous_p (const char *filename)
+{
+  static regex_t dev_zero_regex, shmem_file_regex, file_deleted_regex;
+  static int init_regex_p = 0;
+
+  if (!init_regex_p)
+    {
+      struct cleanup *c = make_cleanup (null_cleanup, NULL);
+
+      /* Let's be pessimistic and assume there will be an error while
+	 compiling the regex'es.  */
+      init_regex_p = -1;
+
+      /* DEV_ZERO_REGEX matches "/dev/zero" filenames (with or
+	 without the "(deleted)" string in the end).  We know for
+	 sure, based on the Linux kernel code, that memory mappings
+	 whose associated filename is "/dev/zero" are guaranteed to be
+	 MAP_ANONYMOUS.  */
+      compile_rx_or_error (&dev_zero_regex, "^/dev/zero\\( (deleted)\\)\\?$",
+			   _("Could not compile regex to match /dev/zero "
+			     "filename"));
+      /* SHMEM_FILE_REGEX matches "/SYSV%08x" filenames (with or
+	 without the "(deleted)" string in the end).  These filenames
+	 refer to shared memory (shmem), and memory mappings
+	 associated with them are MAP_ANONYMOUS as well.  */
+      compile_rx_or_error (&shmem_file_regex,
+			   "^/\\?SYSV[0-9a-fA-F]\\{8\\}\\( (deleted)\\)\\?$",
+			   _("Could not compile regex to match shmem "
+			     "filenames"));
+      /* FILE_DELETED_REGEX is a heuristic we use to try to mimic the
+	 Linux kernel's 'n_link == 0' code, which is responsible to
+	 decide if it is dealing with a 'MAP_SHARED | MAP_ANONYMOUS'
+	 mapping.  In other words, if FILE_DELETED_REGEX matches, it
+	 does not necessarily mean that we are dealing with an
+	 anonymous shared mapping.  However, there is no easy way to
+	 detect this currently, so this is the best approximation we
+	 have.
+
+	 As a result, GDB will dump readonly pages of deleted
+	 executables when using the default value of coredump_filter
+	 (0x33), while the Linux kernel will not dump those pages.
+	 But we can live with that.  */
+      compile_rx_or_error (&file_deleted_regex, " (deleted)$",
+			   _("Could not compile regex to match "
+			     "'<file> (deleted)'"));
+      /* We will never release these regexes, so just discard the
+	 cleanups.  */
+      discard_cleanups (c);
+
+      /* If we reached this point, then everything succeeded.  */
+      init_regex_p = 1;
+    }
+
+  if (init_regex_p == -1)
+    {
+      /* There was an error while compiling the regex'es above.  In
+	 order to try to give some reliable information to the caller,
+	 we just try to find the string "(deleted)" in the filename.
+	 If we managed to find it, then we assume the mapping is
+	 anonymous.  */
+      return strstr (filename, "(deleted)") != NULL;
+    }
+
+  if (*filename == '\0'
+      || regexec (&dev_zero_regex, filename, 0, NULL, 0) == 0
+      || regexec (&shmem_file_regex, filename, 0, NULL, 0) == 0
+      || regexec (&file_deleted_regex, filename, 0, NULL, 0) == 0)
+    return 1;
+
+  return 0;
+}
+
+/* Return 0 if the memory mapping (which is related to FILTERFLAGS, V,
+   MAYBE_PRIVATE_P, and MAPPING_ANONYMOUS_P) should not be dumped, or
+   greater than 0 if it should.
+
+   In a nutshell, this is the logic that we follow in order to decide
+   if a mapping should be dumped or not.
+
+   - If the mapping is associated to a file whose name ends with "
+     (deleted)", or if the file is "/dev/zero", or if it is
+     "/SYSV%08x" (shared memory), or if there is no file associated
+     with it, or if the AnonHugePages: or the Anonymous: fields in the
+     /proc/PID/smaps have contents, then GDB considers this mapping to
+     be anonymous.  Otherwise, GDB considers this mapping to be a
+     file-backed mapping (because there will be a file associated with
+     it).
+ 
+     It is worth mentioning that, from all those checks described
+     above, the most fragile is the one to see if the file name ends
+     with " (deleted)".  This does not necessarily mean that the
+     mapping is anonymous, because the deleted file associated with
+     the mapping may have been a hard link to another file, for
+     example.  The Linux kernel checks to see if "i_nlink == 0", but
+     GDB cannot easily do this check.  Therefore, we made a compromise
+     here, and we assume that if the file name ends with " (deleted)",
+     then the mapping is indeed anonymous.  FWIW, this is something
+     the Linux kernel could do better: expose this information in a
+     more direct way.
+ 
+   - If we see the flag "sh" in the "VmFlags:" field (in
+     /proc/PID/smaps), then certainly the memory mapping is shared
+     (VM_SHARED).  If we have access to the VmFlags, and we don't see
+     the "sh" there, then certainly the mapping is private.  However,
+     Linux kernels before commit
+     834f82e2aa9a8ede94b17b656329f850c1471514 do not have the
+     "VmFlags:" field; in that case, we use another heuristic: if we
+     see 'p' in the permission flags, then we assume that the mapping
+     is private, even though the presence of the 's' flag there would
+     mean VM_MAYSHARE, which means the mapping could still be private.
+     This should work OK enough, however.  */
+
+static int
+dump_mapping_p (unsigned int filterflags, const struct smaps_vmflags *v,
+		int maybe_private_p, int mapping_anon_p, const char *filename)
+{
+  /* Initially, we trust in what we received from outside.  This value
+     may not be very precise (i.e., it was probably gathered from the
+     permission line in the /proc/PID/smaps list, which actually
+     refers to VM_MAYSHARE, and not VM_SHARED), but it is what we have
+     for now.  */
+  int private_p = maybe_private_p;
+
+  /* We always dump vDSO and vsyscall mappings.  */
+  if (strcmp ("[vdso]", filename) == 0
+      || strcmp ("[vsyscall]", filename) == 0)
+    return 1;
+
+  if (v->initialized_p)
+    {
+      /* We never dump I/O mappings.  */
+      if (v->io_page)
+	return 0;
+
+      /* Check if we should exclude this mapping.  */
+      if (v->exclude_coredump)
+	return 0;
+
+      /* Update our notion of whether this mapping is shared or
+	 private based on a trustworthy value.  */
+      private_p = !v->shared_mapping;
+
+      /* HugeTLB checking.  */
+      if (v->uses_huge_tlb)
+	{
+	  if ((private_p && (filterflags & COREFILTER_HUGETLB_PRIVATE))
+	      || (!private_p && (filterflags & COREFILTER_HUGETLB_SHARED)))
+	    return 1;
+
+	  return 0;
+	}
+    }
+
+  if (private_p)
+    {
+      if (mapping_anon_p)
+	return (filterflags & COREFILTER_ANON_PRIVATE) != 0;
+      else
+	return (filterflags & COREFILTER_MAPPED_PRIVATE) != 0;
+    }
+  else
+    {
+      if (mapping_anon_p)
+	return (filterflags & COREFILTER_ANON_SHARED) != 0;
+      else
+	return (filterflags & COREFILTER_MAPPED_SHARED) != 0;
+    }
+}
+
 /* Implement the "info proc" command.  */
 
 static void
@@ -819,48 +1085,86 @@ linux_find_memory_regions_full (struct gdbarch *gdbarch,
 				void *obfd)
 {
   char mapsfilename[100];
-  char *data;
+  char coredumpfilter_name[100];
+  char *data, *coredumpfilterdata;
+  pid_t pid;
+  /* Default dump behavior of coredump_filter (0x33), according to
+     Documentation/filesystems/proc.txt from the Linux kernel
+     tree.  */
+  unsigned int filterflags = (COREFILTER_ANON_PRIVATE
+			      | COREFILTER_ANON_SHARED
+			      | COREFILTER_ELF_HEADERS
+			      | COREFILTER_HUGETLB_PRIVATE);
 
   /* We need to know the real target PID to access /proc.  */
   if (current_inferior ()->fake_pid_p)
     return 1;
 
-  xsnprintf (mapsfilename, sizeof mapsfilename,
-	     "/proc/%d/smaps", current_inferior ()->pid);
+  pid = current_inferior ()->pid;
+
+  if (use_coredump_filter)
+    {
+      xsnprintf (coredumpfilter_name, sizeof (coredumpfilter_name),
+		 "/proc/%d/coredump_filter", pid);
+      coredumpfilterdata = target_fileio_read_stralloc (coredumpfilter_name);
+      if (coredumpfilterdata != NULL)
+	{
+	  sscanf (coredumpfilterdata, "%x", &filterflags);
+	  xfree (coredumpfilterdata);
+	}
+    }
+
+  xsnprintf (mapsfilename, sizeof mapsfilename, "/proc/%d/smaps", pid);
   data = target_fileio_read_stralloc (mapsfilename);
   if (data == NULL)
     {
       /* Older Linux kernels did not support /proc/PID/smaps.  */
-      xsnprintf (mapsfilename, sizeof mapsfilename,
-		 "/proc/%d/maps", current_inferior ()->pid);
+      xsnprintf (mapsfilename, sizeof mapsfilename, "/proc/%d/maps", pid);
       data = target_fileio_read_stralloc (mapsfilename);
     }
-  if (data)
+
+  if (data != NULL)
     {
       struct cleanup *cleanup = make_cleanup (xfree, data);
-      char *line;
+      char *line, *t;
 
-      line = strtok (data, "\n");
-      while (line)
+      line = strtok_r (data, "\n", &t);
+      while (line != NULL)
 	{
 	  ULONGEST addr, endaddr, offset, inode;
 	  const char *permissions, *device, *filename;
+	  struct smaps_vmflags v;
 	  size_t permissions_len, device_len;
-	  int read, write, exec;
-	  int modified = 0, has_anonymous = 0;
+	  int read, write, exec, private;
+	  int has_anonymous = 0;
+	  int should_dump_p = 0;
+	  int mapping_anon_p;
 
+	  memset (&v, 0, sizeof (v));
 	  read_mapping (line, &addr, &endaddr, &permissions, &permissions_len,
 			&offset, &device, &device_len, &inode, &filename);
+	  mapping_anon_p = mapping_is_anonymous_p (filename);
 
 	  /* Decode permissions.  */
 	  read = (memchr (permissions, 'r', permissions_len) != 0);
 	  write = (memchr (permissions, 'w', permissions_len) != 0);
 	  exec = (memchr (permissions, 'x', permissions_len) != 0);
-
-	  /* Try to detect if region was modified by parsing smaps counters.  */
-	  for (line = strtok (NULL, "\n");
-	       line && line[0] >= 'A' && line[0] <= 'Z';
-	       line = strtok (NULL, "\n"))
+	  /* 'private' here actually means VM_MAYSHARE, and not
+	     VM_SHARED.  In order to know if a mapping is really
+	     private or not, we must check the flag "sh" in the
+	     VmFlags field.  This is done by decode_vmflags.  However,
+	     if we are using a Linux kernel released before the commit
+	     834f82e2aa9a8ede94b17b656329f850c1471514, we will not
+	     have the VmFlags there.  In this case, there is really no
+	     way to know if we are dealing with VM_SHARED, so we just
+	     assume that VM_MAYSHARE is enough.  */
+	  private = memchr (permissions, 'p', permissions_len) != 0;
+
+	  /* Try to detect if region should be dumped by parsing smaps
+	     counters.  */
+	  for (line = strtok_r (NULL, "\n", &t);
+	       line != NULL && line[0] >= 'A' && line[0] <= 'Z';
+	       line = strtok_r (NULL, "\n", &t))
 	    {
 	      char keyword[64 + 1];
 
@@ -869,11 +1173,17 @@ linux_find_memory_regions_full (struct gdbarch *gdbarch,
 		  warning (_("Error parsing {s,}maps file '%s'"), mapsfilename);
 		  break;
 		}
+
 	      if (strcmp (keyword, "Anonymous:") == 0)
-		has_anonymous = 1;
-	      if (strcmp (keyword, "Shared_Dirty:") == 0
-		  || strcmp (keyword, "Private_Dirty:") == 0
-		  || strcmp (keyword, "Swap:") == 0
+		{
+		  /* Older Linux kernels did not support the
+		     "Anonymous:" counter.  Check it here.  */
+		  has_anonymous = 1;
+		}
+	      else if (strcmp (keyword, "VmFlags:") == 0)
+		decode_vmflags (line, &v);
+
+	      if (strcmp (keyword, "AnonHugePages:") == 0
 		  || strcmp (keyword, "Anonymous:") == 0)
 		{
 		  unsigned long number;
@@ -884,19 +1194,38 @@ linux_find_memory_regions_full (struct gdbarch *gdbarch,
 			       mapsfilename);
 		      break;
 		    }
-		  if (number != 0)
-		    modified = 1;
+		  if (number > 0)
+		    {
+		      /* Even if we are dealing with a file-backed
+			 mapping, if it contains anonymous pages we
+			 consider it to be an anonymous mapping,
+			 because this is what the Linux kernel does:
+
+			 // Dump segments that have been written to.
+			 if (vma->anon_vma && FILTER(ANON_PRIVATE))
+			 	goto whole;
+		      */
+		      mapping_anon_p = 1;
+		    }
 		}
 	    }
 
-	  /* Older Linux kernels did not support the "Anonymous:" counter.
-	     If it is missing, we can't be sure - dump all the pages.  */
-	  if (!has_anonymous)
-	    modified = 1;
+	  if (has_anonymous)
+	    should_dump_p = dump_mapping_p (filterflags, &v, private,
+					    mapping_anon_p, filename);
+	  else
+	    {
+	      /* Older Linux kernels did not support the "Anonymous:" counter.
+		 If it is missing, we can't be sure - dump all the pages.  */
+	      should_dump_p = 1;
+	    }
 
 	  /* Invoke the callback function to create the corefile segment.  */
-	  func (addr, endaddr - addr, offset, inode,
-		read, write, exec, modified, filename, obfd);
+	  if (should_dump_p)
+	    func (addr, endaddr - addr, offset, inode,
+		  read, write, exec, 1, /* MODIFIED is true because we
+					   want to dump the mapping.  */
+		  filename, obfd);
 	}
 
       do_cleanups (cleanup);
@@ -1972,6 +2301,17 @@ linux_infcall_mmap (CORE_ADDR size, unsigned prot)
   return retval;
 }
 
+/* Display whether the gcore command is using the
+   /proc/PID/coredump_filter file.  */
+
+static void
+show_use_coredump_filter (struct ui_file *file, int from_tty,
+			  struct cmd_list_element *c, const char *value)
+{
+  fprintf_filtered (file, _("Use of /proc/PID/coredump_filter file to generate"
+			    " corefiles is %s.\n"), value);
+}
+
 /* To be called from the various GDB_OSABI_LINUX handlers for the
    various GNU/Linux architectures and machine types.  */
 
@@ -2008,4 +2348,16 @@ _initialize_linux_tdep (void)
   /* Observers used to invalidate the cache when needed.  */
   observer_attach_inferior_exit (invalidate_linux_cache_inf);
   observer_attach_inferior_appeared (invalidate_linux_cache_inf);
+
+  add_setshow_boolean_cmd ("use-coredump-filter", class_files,
+			   &use_coredump_filter, _("\
+Set whether gcore should consider /proc/PID/coredump_filter."),
+			   _("\
+Show whether gcore should consider /proc/PID/coredump_filter."),
+			   _("\
+Use this command to set whether gcore should consider the contents\n\
+of /proc/PID/coredump_filter when generating the corefile.  For more information\n\
+about this file, refer to the manpage of core(5)."),
+			   NULL, show_use_coredump_filter,
+			   &setlist, &showlist);
 }
-- 
1.9.3


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]