[PATCH 10/19] libctf: ELF file opening
Nick Alcock
nick.alcock@oracle.com
Tue Apr 30 22:57:00 GMT 2019
These functions let you open an ELF file with a customarily-named CTF
section in it, automatically opening the CTF file and associating the
symbol and string tables in the ELF file with the CTF container, so that
you can look up the types of symbols in the ELF file via
ctf_lookup_by_symbol(), and so that strings can be shared between the
ELF file and CTF container, to save space.
These functions are both quite rusty (unused since 2009, though nothing
has changed that should have broken them) and likely to change in the
near future, since the naming of CTF sections in this implementation has
not been nailed down yet -- it is likely there will be many of them, one
per translation unit, plus one shared across many TUs, so ctf_open() and
ctf_fdopen() will probably grow a parameter indicating which of the many
possible CTF containers is wanted, as well as a variant returning an
array or a hash allowing you to open all of them at once.
I am amenable to dropping these functions for now, until things are more
nailed down, but introducing them here helps answer people's questions
about what the function with the obvious name of ctf_open() does. :)
libctf/
* ctf-lib.c (_PAGESIZE): New.
(_PAGEMASK): Likewise.
(_libctf_init): Populate them.
(ehdr_to_gelf): New.
(shdr_to_gelf): Likewise.
(ctf_sect_mmap): Likewise.
(ctf_sect_munmap): Likewise.
(ctf_fdopen): Likewise.
(ctf_open): Likewise.
* ctf-impl.h: New definitions.
include/
* ctf-api.h (ctf_fdopen): New.
(ctf_open): Likewise.
---
include/ctf-api.h | 2 +
libctf/ctf-impl.h | 3 +
libctf/ctf-lib.c | 346 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 351 insertions(+)
diff --git a/include/ctf-api.h b/include/ctf-api.h
index 4329c6b2f7..f1a786f451 100644
--- a/include/ctf-api.h
+++ b/include/ctf-api.h
@@ -202,6 +202,8 @@ extern ctf_file_t *ctf_simple_open (const char *, size_t, const char *, size_t,
size_t, const char *, size_t, int *);
extern ctf_file_t *ctf_bufopen (const ctf_sect_t *, const ctf_sect_t *,
const ctf_sect_t *, int *);
+extern ctf_file_t *ctf_fdopen (int, int *);
+extern ctf_file_t *ctf_open (const char *, int *);
extern ctf_file_t *ctf_create (int *);
extern void ctf_close (ctf_file_t *);
extern ctf_sect_t ctf_getdatasect (const ctf_file_t *);
diff --git a/libctf/ctf-impl.h b/libctf/ctf-impl.h
index 0d33cdb01e..2f8caed228 100644
--- a/libctf/ctf-impl.h
+++ b/libctf/ctf-impl.h
@@ -314,6 +314,9 @@ extern const char *ctf_strptr (ctf_file_t *, uint32_t);
extern ctf_file_t *ctf_set_open_errno (int *, int);
extern long ctf_set_errno (ctf_file_t *, int);
+extern const void *ctf_sect_mmap (ctf_sect_t *, int);
+extern void ctf_sect_munmap (const ctf_sect_t *);
+
extern void *ctf_data_alloc (size_t);
extern void ctf_data_free (void *, size_t);
extern void ctf_data_protect (void *, size_t);
diff --git a/libctf/ctf-lib.c b/libctf/ctf-lib.c
index afe9cbefa6..e60d2c985b 100644
--- a/libctf/ctf-lib.c
+++ b/libctf/ctf-lib.c
@@ -25,12 +25,358 @@
#include <string.h>
#include <fcntl.h>
#include <errno.h>
+#include <dlfcn.h>
+#include <endian.h>
+#include <gelf.h>
#include <zlib.h>
+static size_t _PAGESIZE;
+static size_t _PAGEMASK;
+
_libctf_constructor_(_libctf_init)
static void _libctf_init (void)
{
_libctf_debug = getenv ("LIBCTF_DEBUG") != NULL;
+
+ _PAGESIZE = getpagesize ();
+ _PAGEMASK = ~(_PAGESIZE - 1);
+}
+
+/* Convert a 32-bit ELF file header into GElf. */
+
+static void
+ehdr_to_gelf (const Elf32_Ehdr *src, GElf_Ehdr *dst)
+{
+ memcpy (dst->e_ident, src->e_ident, EI_NIDENT);
+ dst->e_type = src->e_type;
+ dst->e_machine = src->e_machine;
+ dst->e_version = src->e_version;
+ dst->e_entry = (Elf64_Addr) src->e_entry;
+ dst->e_phoff = (Elf64_Off) src->e_phoff;
+ dst->e_shoff = (Elf64_Off) src->e_shoff;
+ dst->e_flags = src->e_flags;
+ dst->e_ehsize = src->e_ehsize;
+ dst->e_phentsize = src->e_phentsize;
+ dst->e_phnum = src->e_phnum;
+ dst->e_shentsize = src->e_shentsize;
+ dst->e_shnum = src->e_shnum;
+ dst->e_shstrndx = src->e_shstrndx;
+}
+
+/* Convert a 32-bit ELF section header into GElf. */
+
+static void
+shdr_to_gelf (const Elf32_Shdr *src, GElf_Shdr *dst)
+{
+ dst->sh_name = src->sh_name;
+ dst->sh_type = src->sh_type;
+ dst->sh_flags = src->sh_flags;
+ dst->sh_addr = src->sh_addr;
+ dst->sh_offset = src->sh_offset;
+ dst->sh_size = src->sh_size;
+ dst->sh_link = src->sh_link;
+ dst->sh_info = src->sh_info;
+ dst->sh_addralign = src->sh_addralign;
+ dst->sh_entsize = src->sh_entsize;
+}
+
+/* In order to mmap a section from the ELF file, we must round down sh_offset
+ to the previous page boundary, and mmap the surrounding page. We store
+ the pointer to the start of the actual section data back into sp->cts_data. */
+
+const void *
+ctf_sect_mmap (ctf_sect_t *sp, int fd)
+{
+ size_t pageoff = sp->cts_offset & ~_PAGEMASK;
+
+ caddr_t base = mmap (NULL, sp->cts_size + pageoff, PROT_READ,
+ MAP_PRIVATE, fd, sp->cts_offset & _PAGEMASK);
+
+ if (base != MAP_FAILED)
+ sp->cts_data = base + pageoff;
+
+ return base;
+}
+
+/* Since sp->cts_data has the adjusted offset, we have to again round down
+ to get the actual mmap address and round up to get the size. */
+
+void
+ctf_sect_munmap (const ctf_sect_t *sp)
+{
+ uintptr_t addr = (uintptr_t) sp->cts_data;
+ uintptr_t pageoff = addr & ~_PAGEMASK;
+
+ (void) munmap ((void *) (addr - pageoff), sp->cts_size + pageoff);
+}
+
+/* Open the specified file descriptor and return a pointer to a CTF container.
+ The file can be either an ELF file or raw CTF file. The caller is
+ responsible for closing the file descriptor when it is no longer needed. */
+
+ctf_file_t *
+ctf_fdopen (int fd, int *errp)
+{
+ ctf_sect_t ctfsect, symsect, strsect;
+ ctf_file_t *fp = NULL;
+
+ struct stat st;
+ ssize_t nbytes;
+
+ union
+ {
+ ctf_preamble_t ctf;
+ Elf32_Ehdr e32;
+ GElf_Ehdr e64;
+ } hdr;
+
+ memset (&ctfsect, 0, sizeof (ctf_sect_t));
+ memset (&symsect, 0, sizeof (ctf_sect_t));
+ memset (&strsect, 0, sizeof (ctf_sect_t));
+ memset (&hdr.ctf, 0, sizeof (hdr));
+
+ if (fstat (fd, &st) == -1)
+ return (ctf_set_open_errno (errp, errno));
+
+ if ((nbytes = pread (fd, &hdr.ctf, sizeof (hdr), 0)) <= 0)
+ return (ctf_set_open_errno (errp, nbytes < 0 ? errno : ECTF_FMT));
+
+ /*
+ * If we have read enough bytes to form a CTF header and the magic
+ * string matches, attempt to interpret the file as raw CTF.
+ */
+ if ((size_t) nbytes >= sizeof (ctf_preamble_t) &&
+ hdr.ctf.ctp_magic == CTF_MAGIC)
+ {
+ void *data;
+
+ if (hdr.ctf.ctp_version > CTF_VERSION)
+ return (ctf_set_open_errno (errp, ECTF_CTFVERS));
+
+ data = mmap (NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+
+ if (data == MAP_FAILED)
+ return (ctf_set_open_errno (errp, errno));
+
+ ctfsect.cts_name = _CTF_SECTION;
+ ctfsect.cts_type = SHT_PROGBITS;
+ ctfsect.cts_flags = SHF_ALLOC;
+ ctfsect.cts_size = (size_t) st.st_size;
+ ctfsect.cts_entsize = 1;
+ ctfsect.cts_offset = 0;
+
+ if ((fp = ctf_simple_open (data, (size_t) st.st_size, NULL, 0, 0,
+ NULL, 0, errp)) == NULL)
+ ctf_sect_munmap (&ctfsect);
+
+ return fp;
+ }
+
+ /* If we have read enough bytes to form an ELF header and the magic
+ string matches, attempt to interpret the file as an ELF file. We
+ do our own largefile ELF processing, and convert everything to
+ GElf structures so that clients can operate on any data model. */
+
+ if ((size_t) nbytes >= sizeof (Elf32_Ehdr)
+ && memcmp (&hdr.e32.e_ident[EI_MAG0], ELFMAG, SELFMAG) == 0)
+ {
+#if __BYTE_ORDER == __BIG_ENDIAN
+ unsigned char order = ELFDATA2MSB;
+#elif __BYTE_ORDER == __LITTLE_ENDIAN
+ unsigned char order = ELFDATA2LSB;
+#else
+#error Unknown endianness
+#endif
+ GElf_Half i, n;
+ GElf_Shdr *sp;
+
+ void *strs_map;
+ size_t strs_mapsz;
+ const char *strs;
+
+ if (hdr.e32.e_ident[EI_DATA] != order)
+ return (ctf_set_open_errno (errp, ECTF_ENDIAN));
+ if (hdr.e32.e_version != EV_CURRENT)
+ return (ctf_set_open_errno (errp, ECTF_ELFVERS));
+
+ if (hdr.e32.e_ident[EI_CLASS] == ELFCLASS64)
+ {
+ if ((size_t) nbytes < sizeof (GElf_Ehdr))
+ return (ctf_set_open_errno (errp, ECTF_FMT));
+ }
+ else
+ {
+ Elf32_Ehdr e32 = hdr.e32;
+ ehdr_to_gelf (&e32, &hdr.e64);
+ }
+
+ if (hdr.e64.e_shstrndx >= hdr.e64.e_shnum)
+ return (ctf_set_open_errno (errp, ECTF_CORRUPT));
+
+ n = hdr.e64.e_shnum;
+ nbytes = sizeof (GElf_Shdr) * n;
+
+ if ((sp = malloc (nbytes)) == NULL)
+ return (ctf_set_open_errno (errp, errno));
+
+ /* Read in and convert to GElf the array of Shdr structures
+ from e_shoff so we can locate sections of interest. */
+
+ if (hdr.e32.e_ident[EI_CLASS] == ELFCLASS32)
+ {
+ Elf32_Shdr *sp32;
+
+ nbytes = sizeof (Elf32_Shdr) * n;
+
+ if ((sp32 = malloc (nbytes)) == NULL || pread (fd, sp32, nbytes,
+ hdr.e64.e_shoff) !=
+ nbytes)
+ {
+ free (sp);
+ return (ctf_set_open_errno (errp, errno));
+ }
+
+ for (i = 0; i < n; i++)
+ shdr_to_gelf (&sp32[i], &sp[i]);
+
+ free (sp32);
+
+ }
+ else if (pread (fd, sp, nbytes, hdr.e64.e_shoff) != nbytes)
+ {
+ free (sp);
+ return (ctf_set_open_errno (errp, errno));
+ }
+
+ /* Now mmap the section header strings section so that we can
+ perform string comparison on the section names. */
+
+ strs_mapsz = sp[hdr.e64.e_shstrndx].sh_size +
+ (sp[hdr.e64.e_shstrndx].sh_offset & ~_PAGEMASK);
+
+ strs_map = mmap (NULL, strs_mapsz, PROT_READ, MAP_PRIVATE,
+ fd, sp[hdr.e64.e_shstrndx].sh_offset & _PAGEMASK);
+
+ strs = (const char *) strs_map
+ + (sp[hdr.e64.e_shstrndx].sh_offset & ~_PAGEMASK);
+
+ if (strs_map == MAP_FAILED)
+ {
+ free (sp);
+ return (ctf_set_open_errno (errp, ECTF_MMAP));
+ }
+
+ /* Iterate over the section header array looking for the CTF
+ section and symbol table. The strtab is linked to symtab. */
+
+ for (i = 0; i < n; i++)
+ {
+ const GElf_Shdr *shp = &sp[i];
+ const GElf_Shdr *lhp = &sp[shp->sh_link];
+
+ if (shp->sh_link >= hdr.e64.e_shnum)
+ continue; /* Corrupt sh_link field. */
+
+ if (shp->sh_name >= sp[hdr.e64.e_shstrndx].sh_size ||
+ lhp->sh_name >= sp[hdr.e64.e_shstrndx].sh_size)
+ continue; /* Corrupt sh_name field. */
+
+ if (shp->sh_type == SHT_PROGBITS
+ && strcmp (strs + shp->sh_name, _CTF_SECTION) == 0)
+ {
+ ctfsect.cts_name = strs + shp->sh_name;
+ ctfsect.cts_type = shp->sh_type;
+ ctfsect.cts_flags = shp->sh_flags;
+ ctfsect.cts_size = shp->sh_size;
+ ctfsect.cts_entsize = shp->sh_entsize;
+ ctfsect.cts_offset = (off64_t) shp->sh_offset;
+
+ }
+ else if (shp->sh_type == SHT_SYMTAB)
+ {
+ symsect.cts_name = strs + shp->sh_name;
+ symsect.cts_type = shp->sh_type;
+ symsect.cts_flags = shp->sh_flags;
+ symsect.cts_size = shp->sh_size;
+ symsect.cts_entsize = shp->sh_entsize;
+ symsect.cts_offset = (off64_t) shp->sh_offset;
+
+ strsect.cts_name = strs + lhp->sh_name;
+ strsect.cts_type = lhp->sh_type;
+ strsect.cts_flags = lhp->sh_flags;
+ strsect.cts_size = lhp->sh_size;
+ strsect.cts_entsize = lhp->sh_entsize;
+ strsect.cts_offset = (off64_t) lhp->sh_offset;
+ }
+ }
+
+ free (sp); /* Free section header array. */
+
+ if (ctfsect.cts_type == SHT_NULL)
+ {
+ (void) munmap (strs_map, strs_mapsz);
+ return (ctf_set_open_errno (errp, ECTF_NOCTFDATA));
+ }
+
+ /* Now mmap the CTF data, symtab, and strtab sections and
+ call ctf_bufopen() to do the rest of the work. */
+
+ if (ctf_sect_mmap (&ctfsect, fd) == MAP_FAILED)
+ {
+ (void) munmap (strs_map, strs_mapsz);
+ return (ctf_set_open_errno (errp, ECTF_MMAP));
+ }
+
+ if (symsect.cts_type != SHT_NULL && strsect.cts_type != SHT_NULL)
+ {
+ if (ctf_sect_mmap (&symsect, fd) == MAP_FAILED ||
+ ctf_sect_mmap (&strsect, fd) == MAP_FAILED)
+ {
+ (void) ctf_set_open_errno (errp, ECTF_MMAP);
+ goto bad;
+ }
+ fp = ctf_bufopen (&ctfsect, &symsect, &strsect, errp);
+ }
+ else
+ fp = ctf_bufopen (&ctfsect, NULL, NULL, errp);
+
+ bad:
+ /* Unmap all and abort. */
+ if (fp == NULL)
+ {
+ ctf_sect_munmap (&ctfsect);
+ ctf_sect_munmap (&symsect);
+ ctf_sect_munmap (&strsect);
+ }
+ else
+ fp->ctf_flags |= LCTF_MMAP;
+
+ (void) munmap (strs_map, strs_mapsz);
+ return fp;
+ }
+
+ return (ctf_set_open_errno (errp, ECTF_FMT));
+}
+
+/* Open the specified file and return a pointer to a CTF container. The file
+ can be either an ELF file or raw CTF file. This is just a convenient
+ wrapper around ctf_fdopen() for callers. */
+ctf_file_t *
+ctf_open (const char *filename, int *errp)
+{
+ ctf_file_t *fp;
+ int fd;
+
+ if ((fd = open (filename, O_RDONLY)) == -1)
+ {
+ if (errp != NULL)
+ *errp = errno;
+ return NULL;
+ }
+
+ fp = ctf_fdopen (fd, errp);
+ (void) close (fd);
+ return fp;
}
/* Write the compressed CTF data stream to the specified gzFile descriptor.
--
2.21.0.237.gd0cfaa883d
More information about the Binutils
mailing list