Bug 24431 - ELF reader fails to determine __ksymtab format

This is a fallout from this commit:

 ad8c253 Bug 24431 - ELF reader can't interpret ksymtab with Kernel 4.19+

The problem is that the method used to determine if the format of the
__ksymtab section is pre or post v4.19.  In that commit, we assumed
that a kernel without relocations for the __ksymtab section implies a
v4.19 format, because in that format, we don't need relocations for
that section.  But then it can happen that the entire kernel be built
without relocations, in the case a non relocatable kernels.  So just
looking a the presence of relocations is not a good enough
discriminant to determine the format of the __ksymtab section.

This patch rather tries to read the first entry of the __ksymtab
section assuming a pre v4.19 format, comes up with an address, and
then looks the .symtab section up with that address.  If the lookup
succeeds and we find a symbol, then we can reasonably assume that the
__ksymtab section is in the v4.19 format.  Otherwise, we do the same
assuming a v4.19 format, etc.

Tested on v4.9, v4.16 and v4.16 kernels in 32 and 64 bits.

	* src/abg-dwarf-reader.cc
	(read_context::{try_reading_first_ksymtab_entry_using_pre_v4_19_format,
	try_reading_first_ksymtab_entry_using_v4_19_format}): Define new
	member functions.
	(read_context::maybe_adjust_sym_address_from_v4_19_ksymtab): Make
	member function this const.
	(read_context::get_ksymtab_format): Implement the new heuristic
	here, using try_reading_first_ksymtab_entry_using_pre_v4_19_format
	and try_reading_first_ksymtab_entry_using_v4_19_format, rather
	than assuming that if we have no relocations, then we are in the
	v4.19 format.
	(maybe_adjust_sym_address_from_v4_19_ksymtab): When on a 64 bits
	architecture, ensure the 32 bits address read from the v4.19
	format __ksymtab section is converted into a 64 bits address.

Signed-off-by: Dodji Seketeli <dodji@redhat.com>

diff --git a/src/abg-dwarf-reader.cc b/src/abg-dwarf-reader.cc
index 93f10e7d17a09127079ce24ebbf92f5bfc3c1d61..7bde0f3c8738906c72c2d3fd91859728ab9a4a0c 100644 (file)
--- a/src/abg-dwarf-reader.cc
+++ b/src/abg-dwarf-reader.cc
@@ -7130,6 +7130,81 @@ public:
     return true;
   }
 
+  /// Try reading the first __ksymtab section entry as if it is in the
+  /// v4_19 format and lookup a symbol from the .symbol section to see
+  /// if that succeeds.  If it does, then we can assume the __ksymtab
+  /// section is in the v4_19 format.
+  ///
+  /// @return the symbol resulting from the lookup of the symbol
+  /// address we got from reading the first entry of the ksymtab
+  /// section assuming the v4.19 format.  If nil, it means the
+  /// __ksymtab section is not in the v4.19 format.
+  elf_symbol_sptr
+  try_reading_first_ksymtab_entry_using_pre_v4_19_format() const
+  {
+    Elf_Scn *section = find_ksymtab_section();
+    Elf_Data *elf_data = elf_rawdata(section, 0);
+    uint8_t *bytes = reinterpret_cast<uint8_t*>(elf_data->d_buf);
+    bool is_big_endian = elf_architecture_is_big_endian();
+    elf_symbol_sptr symbol;
+    unsigned char symbol_value_size = architecture_word_size();
+
+    GElf_Addr symbol_address = 0, adjusted_symbol_address = 0;
+    ABG_ASSERT(read_int_from_array_of_bytes(bytes,
+                                           symbol_value_size,
+                                           is_big_endian,
+                                           symbol_address));
+    adjusted_symbol_address = maybe_adjust_fn_sym_address(symbol_address);
+    symbol = lookup_elf_symbol_from_address(adjusted_symbol_address);
+    return symbol;
+  }
+
+  /// Try reading the first __ksymtab section entry as if it is in the
+  /// pre-v4_19 format and lookup a symbol from the .symbol section to
+  /// see if that succeeds.  If it does, then we can assume the
+  /// __ksymtab section is in the pre-v4_19 format.
+  ///
+  /// @return the symbol resulting from the lookup of the symbol
+  /// address we got from reading the first entry of the ksymtab
+  /// section assuming the pre-v4.19 format.  If nil, it means the
+  /// __ksymtab section is not in the pre-v4.19 format.
+  elf_symbol_sptr
+  try_reading_first_ksymtab_entry_using_v4_19_format() const
+  {
+    Elf_Scn *section = find_ksymtab_section();
+    Elf_Data *elf_data = elf_rawdata(section, 0);
+    uint8_t *bytes = reinterpret_cast<uint8_t*>(elf_data->d_buf);
+    bool is_big_endian = elf_architecture_is_big_endian();
+    elf_symbol_sptr symbol;
+    unsigned char symbol_value_size = 4;
+    unsigned char arch_word_size = architecture_word_size();
+
+    GElf_Addr symbol_address = 0, adjusted_symbol_address = 0;
+    ABG_ASSERT(read_int_from_array_of_bytes(bytes,
+                                           symbol_value_size,
+                                           is_big_endian,
+                                           symbol_address));
+    GElf_Shdr mem;
+    GElf_Shdr *section_header = gelf_getshdr(section, &mem);
+    if (arch_word_size == 4)
+      symbol_address = (uint32_t)(symbol_address + section_header->sh_addr);
+    else if (arch_word_size == 8)
+      {
+       symbol_address = symbol_address + section_header->sh_addr;
+       if (symbol_address < ((uint64_t)1 << 32))
+         // The symbol address is expressed in 32 bits.  So let's
+         // convert it to a 64 bits address with the 4 most
+         // significant bytes set to ff each.
+         symbol_address = ((uint64_t)0xffffffff << 32) | symbol_address;
+      }
+    else
+      ABG_ASSERT_NOT_REACHED;
+
+    adjusted_symbol_address = maybe_adjust_fn_sym_address(symbol_address);
+    symbol = lookup_elf_symbol_from_address(adjusted_symbol_address);
+    return symbol;
+  }
+
   /// Determine the format of the __ksymtab and __ksymtab_gpl
   /// sections.
   ///
@@ -7146,18 +7221,22 @@ public:
       {
        if (ksymtab_format_ == UNDEFINED_KSYMTAB_FORMAT)
          {
-           // Only kernels prior to v4.19 systematically had a
-           // .rela__ksymtab section.  And not having a
-           // .rela__ksymtab means that there are no relocations for
-           // the __ksymtab section.  And that is a hint that
-           // __ksymtab entries are "place-relative" addresses in
-           // that case, thus, not needing relocations.  So we use
-           // the presence of the .rela__ksymtab as a property of pre
-           // v4.19 "classical" ksymtab kernels.
-           if (find_section(elf_handle(), ".rela__ksymtab", SHT_RELA))
+           // OK this is a dirty little heuristic to determine the
+           // format of the ksymtab section.
+           //
+           // We try to read the first ksymtab entry assuming a
+           // pre-v4.19 format.  If that succeeds then we are in the
+           // pr-v4.19 format.  Otherwise, try reading it assuming a
+           // v4.19 format.  For now, we just support
+           // PRE_V4_19_KSYMTAB_FORMAT and V4_19_KSYMTAB_FORMAT.
+           if (try_reading_first_ksymtab_entry_using_pre_v4_19_format())
              ksymtab_format_ = PRE_V4_19_KSYMTAB_FORMAT;
-           else
+           else if (try_reading_first_ksymtab_entry_using_v4_19_format())
              ksymtab_format_ = V4_19_KSYMTAB_FORMAT;
+           else
+             // If a new format emerges, then we need to add its
+             // support above.
+             ABG_ASSERT_NOT_REACHED;
          }
       }
     return ksymtab_format_;
@@ -7540,7 +7619,7 @@ public:
   GElf_Addr
   maybe_adjust_sym_address_from_v4_19_ksymtab(GElf_Addr addr,
                                              size_t addr_offset,
-                                             Elf_Scn *ksymtab_section)
+                                             Elf_Scn *ksymtab_section) const
   {
     GElf_Addr result = addr;
 
@@ -7550,9 +7629,20 @@ public:
        GElf_Shdr *section_header = gelf_getshdr(ksymtab_section, &mem);
        if (architecture_word_size() == 4)
          result = (uint32_t)(addr + section_header->sh_addr + addr_offset);
+       else if (architecture_word_size() == 8)
+         {
+           result = addr + section_header->sh_addr + addr_offset;
+           if (result < ((uint64_t)1 << 32))
+             // The symbol address is expressed in 32 bits.  So let's
+             // convert it to a 64 bits address with the 4 most
+             // significant bytes set to ff each.  This is how 64
+             // bits addresses of symbols are in the .symbol section,
+             // so we need this address to be consistent with that
+             // format.
+             result = ((uint64_t)0xffffffff << 32) | result;
+         }
        else
-         // We are in 64 bits
-         result = addr + section_header->sh_addr + addr_offset;
+         ABG_ASSERT_NOT_REACHED;
       }
 
     return result;