aboutsummaryrefslogtreecommitdiff
path: root/gold
diff options
context:
space:
mode:
authorAlan Modra <amodra@gmail.com>2018-01-13 18:53:41 +1030
committerAlan Modra <amodra@gmail.com>2018-01-17 18:51:04 +1030
commit9e390558cef76767a98123994c422d0642d86cf8 (patch)
treefa46b2f2c764e30be6e6e512fe29a01de0b4ad04 /gold
parent78742b93a5fef4b88b1391817e7bcc6738000044 (diff)
downloadbinutils-9e390558cef76767a98123994c422d0642d86cf8.zip
binutils-9e390558cef76767a98123994c422d0642d86cf8.tar.gz
binutils-9e390558cef76767a98123994c422d0642d86cf8.tar.bz2
PowerPC PLT stub tidy
This is in preparation for the next patch adding Spectre variant 2 mitigation for PowerPC and PowerPC64. Besides tidying code involved in stub output (to reduce the number of places where bctr is output), the patch adds some user visible features: 1) PowerPC64 ELFv2 global entry stubs now are aligned under the control of --plt-align, with a default alignment of 32 bytes. 2) PowerPC64 __glink_PLTresolve is no longer padded out with nops. 3) PowerPC32 PLT stubs are aligned under the control of --plt-align, with the default alignment being 16 bytes as before. 4) The PowerPC32 branch/nop table emitted before __glink_PLTresolve is now smaller in many cases. It was sized incorrectly when the __tls_get_addr_opt stub was used, and unnecessarily included space for local ifuncs. bfd/ * elf32-ppc.c (GLINK_ENTRY_SIZE): Add parameters, handle __tls_get_addr_opt, and alignment sizing. (TLS_GET_ADDR_GLINK_SIZE): Delete. (is_nonpic_glink_stub): Don't use GLINK_ENTRY_SIZE. (ppc_elf_get_synthetic_symtab): Recognize stubs spaced at 4, 6, or 8 insns. (ppc_elf_link_hash_table_create): Init new ppc_elf_params field. (allocate_dynrelocs): Use new GLINK_ENTRY_SIZE. (ppc_elf_size_dynamic_sections): Likewise. Size branch table by PLT reloc count. (write_glink_stub): Handle __tls_get_addr_opt stub. Pad out to size given by GLINK_ENTRY_SIZE. (ppc_elf_relocate_section): Adjust write_glink_stub call. (ppc_elf_finish_dynamic_symbol): Likewise. (ppc_elf_finish_dynamic_sections): Write PLTresolve without using insn array since so many need rewriting. * elf32-ppc.h (struct ppc_elf_params): Add plt_stub_align. * elf64-ppc.c (GLINK_PLTRESOLVE_SIZE): Rename from GLINK_CALL_STUB_SIZE. Add htab param and evaluate to size without nops. Adjust all uses. (ppc64_elf_get_synthetic_symtab): Don't use GLINK_CALL_STUB_SIZE in glink_vma calculation. (struct ppc_link_hash_table): Add global_entry section pointer. (create_linkage_sections): Create separate section for global entry stubs. (PPC_LO, PPC_HI, PPC_HA): Move earlier. (size_global_entry_stubs): Handle sizing for aligned stubs. (ppc64_elf_size_dynamic_sections): Handle global_entry alloc, and don't stash end of glink branch table in rawsize. (ppc_build_one_stub): Rewrite stub size calculations. (build_global_entry_stubs): Use new section. (ppc64_elf_build_stubs): Don't pad __glink_PLTresolve with nops. Build lazy link stubs out to end of section. Build global entry stubs in new section. gold/ * options.h (plt_align): Support for PowerPC32 too. * powerpc.cc (Stub_table::stub_align): Heed --plt-align for 32-bit. (Stub_table::plt_call_size, branch_stub_size): Tidy. (Stub_table::plt_call_align): Implement using stub_align. (Output_data_glink::global_entry_align): New function. (Output_data_glink::global_entry_off): New function. (Output_data_glink::global_entry_address): Use global_entry_off. (Output_data_glink::pltresolve_size): New function, replacing pltresolve_size_ constant. Update all uses. (Output_data_glink::add_global_entry): Align offset. (Output_data_glink::set_final_data_size): Use global_entry_align. (Stub_table::do_write): Don't pad __glink_PLTrelsolve with nops. Tidy stub output. Use global_entry_off. ld/ * emultempl/ppc32elf.em (params): Init new field. (enum ppc32_opt): New enum to define OPTION_* values. Add OPTION_PLT_ALIGN and OPTION_NO_PLT_ALIGN. (PARSE_AND_LIST_LONGOPTS): Handle new options. (PARSE_AND_LIST_ARGS_CASES): Likewise. (PARSE_AND_LIST_OPTIONS): Likewise. Break up help output. * emultempl/ppc64elf.em (ppc_add_stub_section): Init alignment correctly for negative --plt-stub-align. * testsuite/ld-powerpc/elfv2exe.d, * testsuite/ld-powerpc/elfv2so.d, * testsuite/ld-powerpc/relbrlt.d, * testsuite/ld-powerpc/relbrlt.s, * testsuite/ld-powerpc/tlsexe.d, * testsuite/ld-powerpc/tlsexe.r, * testsuite/ld-powerpc/tlsexe32.d, * testsuite/ld-powerpc/tlsexe32.g, * testsuite/ld-powerpc/tlsexe32.r, * testsuite/ld-powerpc/tlsexetoc.d, * testsuite/ld-powerpc/tlsexetoc.r, * testsuite/ld-powerpc/tlsopt5_32.d, * testsuite/ld-powerpc/tlsso.d, * testsuite/ld-powerpc/tlstocso.d: Update for changed stub order.
Diffstat (limited to 'gold')
-rw-r--r--gold/ChangeLog16
-rw-r--r--gold/options.h2
-rw-r--r--gold/powerpc.cc225
3 files changed, 149 insertions, 94 deletions
diff --git a/gold/ChangeLog b/gold/ChangeLog
index 6494b20..fff66e1 100644
--- a/gold/ChangeLog
+++ b/gold/ChangeLog
@@ -1,3 +1,19 @@
+2018-01-17 Alan Modra <amodra@gmail.com>
+
+ * options.h (plt_align): Support for PowerPC32 too.
+ * powerpc.cc (Stub_table::stub_align): Heed --plt-align for 32-bit.
+ (Stub_table::plt_call_size, branch_stub_size): Tidy.
+ (Stub_table::plt_call_align): Implement using stub_align.
+ (Output_data_glink::global_entry_align): New function.
+ (Output_data_glink::global_entry_off): New function.
+ (Output_data_glink::global_entry_address): Use global_entry_off.
+ (Output_data_glink::pltresolve_size): New function, replacing
+ pltresolve_size_ constant. Update all uses.
+ (Output_data_glink::add_global_entry): Align offset.
+ (Output_data_glink::set_final_data_size): Use global_entry_align.
+ (Stub_table::do_write): Don't pad __glink_PLTrelsolve with nops.
+ Tidy stub output. Use global_entry_off.
+
2018-01-15 Cary Coutant <ccoutant@gmail.com>
PR gold/22694
diff --git a/gold/options.h b/gold/options.h
index feb60cc..b39d5ff 100644
--- a/gold/options.h
+++ b/gold/options.h
@@ -1101,7 +1101,7 @@ class General_options
NULL, N_("(ARM only) Ignore for backward compatibility"));
DEFINE_var(plt_align, options::TWO_DASHES, '\0', 0, "5",
- N_("(PowerPC64 only) Align PLT call stubs to fit cache lines"),
+ N_("(PowerPC only) Align PLT call stubs to fit cache lines"),
N_("[=P2ALIGN]"), true, int, int, options::parse_uint, false);
DEFINE_bool(plt_localentry, options::TWO_DASHES, '\0', false,
diff --git a/gold/powerpc.cc b/gold/powerpc.cc
index 94efcdf..9ed5b21 100644
--- a/gold/powerpc.cc
+++ b/gold/powerpc.cc
@@ -3524,7 +3524,7 @@ Target_powerpc<size, big_endian>::do_relax(int pass,
if (this->glink_ != NULL)
{
- int stub_size = this->glink_->pltresolve_size;
+ int stub_size = this->glink_->pltresolve_size();
Address value = -stub_size;
if (size == 64)
{
@@ -3580,7 +3580,7 @@ Target_powerpc<size, big_endian>::do_plt_fde_location(const Output_data* plt,
// There are two FDEs for a position independent glink.
// The first covers the branch table, the second
// __glink_PLTresolve at the end of glink.
- off_t resolve_size = this->glink_->pltresolve_size;
+ off_t resolve_size = this->glink_->pltresolve_size();
if (oview[9] == elfcpp::DW_CFA_nop)
len -= resolve_size;
else
@@ -4391,9 +4391,9 @@ class Stub_table : public Output_relaxed_input_section
unsigned int
stub_align() const
{
- if (size == 32)
- return 16;
- unsigned int min_align = 32;
+ unsigned int min_align = 4;
+ if (!parameters->options().user_set_plt_align())
+ return size == 64 ? 32 : min_align;
unsigned int user_align = 1 << parameters->options().plt_align();
return std::max(user_align, min_align);
}
@@ -4425,9 +4425,8 @@ class Stub_table : public Output_relaxed_input_section
if (size == 32)
{
const Symbol* gsym = p->first.sym_;
- if (this->targ_->is_tls_get_addr_opt(gsym))
- return 12 * 4;
- return 4 * 4;
+ return (4 * 4
+ + (this->targ_->is_tls_get_addr_opt(gsym) ? 8 * 4 : 0));
}
bool is_iplt;
@@ -4460,10 +4459,8 @@ class Stub_table : public Output_relaxed_input_section
unsigned int
plt_call_align(unsigned int bytes) const
{
- unsigned int align = 1 << parameters->options().plt_align();
- if (align > 1)
- bytes = (bytes + align - 1) & -align;
- return bytes;
+ unsigned int align = this->stub_align();
+ return (bytes + align - 1) & -align;
}
// Return long branch stub size.
@@ -4473,9 +4470,10 @@ class Stub_table : public Output_relaxed_input_section
Address loc = this->stub_address() + this->last_plt_size_ + p->second;
if (p->first.dest_ - loc + (1 << 25) < 2 << 25)
return 4;
- if (size == 64 || !parameters->options().output_is_position_independent())
- return 16;
- return 32;
+ unsigned int bytes = 16;
+ if (size == 32 && parameters->options().output_is_position_independent())
+ bytes += 16;
+ return bytes;
}
// Write out stubs.
@@ -4884,7 +4882,6 @@ class Output_data_glink : public Output_section_data
public:
typedef typename elfcpp::Elf_types<size>::Elf_Addr Address;
static const Address invalid_address = static_cast<Address>(0) - 1;
- static const int pltresolve_size = 16*4;
Output_data_glink(Target_powerpc<size, big_endian>* targ)
: Output_section_data(16), targ_(targ), global_entry_stubs_(),
@@ -4900,12 +4897,35 @@ class Output_data_glink : public Output_section_data
Address
find_global_entry(const Symbol*) const;
+ unsigned int
+ global_entry_align(unsigned int off) const
+ {
+ unsigned int align = 1 << parameters->options().plt_align();
+ if (!parameters->options().user_set_plt_align())
+ align = size == 64 ? 32 : 4;
+ return (off + align - 1) & -align;
+ }
+
+ unsigned int
+ global_entry_off() const
+ {
+ return this->global_entry_align(this->end_branch_table_);
+ }
+
Address
global_entry_address() const
{
gold_assert(this->is_data_size_valid());
- unsigned int global_entry_off = (this->end_branch_table_ + 15) & -16;
- return this->address() + global_entry_off;
+ return this->address() + this->global_entry_off();
+ }
+
+ int
+ pltresolve_size() const
+ {
+ if (size == 64)
+ return (8
+ + (this->targ_->abiversion() < 2 ? 11 * 4 : 14 * 4));
+ return 16 * 4;
}
protected:
@@ -4977,10 +4997,11 @@ template<int size, bool big_endian>
void
Output_data_glink<size, big_endian>::add_global_entry(const Symbol* gsym)
{
+ unsigned int off = this->global_entry_align(this->ge_size_);
std::pair<typename Global_entry_stub_entries::iterator, bool> p
- = this->global_entry_stubs_.insert(std::make_pair(gsym, this->ge_size_));
+ = this->global_entry_stubs_.insert(std::make_pair(gsym, off));
if (p.second)
- this->ge_size_ += 16;
+ this->ge_size_ = off + 16;
}
template<int size, bool big_endian>
@@ -5007,11 +5028,11 @@ Output_data_glink<size, big_endian>::set_final_data_size()
total += 4 * (count - 1);
total += -total & 15;
- total += this->pltresolve_size;
+ total += this->pltresolve_size();
}
else
{
- total += this->pltresolve_size;
+ total += this->pltresolve_size();
// space for branch table
total += 4 * count;
@@ -5024,7 +5045,7 @@ Output_data_glink<size, big_endian>::set_final_data_size()
}
}
this->end_branch_table_ = total;
- total = (total + 15) & -16;
+ total = this->global_entry_align(total);
total += this->ge_size_;
this->set_data_size(total);
@@ -5175,7 +5196,7 @@ Stub_table<size, big_endian>::do_write(Output_file* of)
= ((pltoff - this->targ_->first_plt_entry_offset())
/ this->targ_->plt_entry_size());
Address glinkoff
- = (this->targ_->glink_section()->pltresolve_size
+ = (this->targ_->glink_section()->pltresolve_size()
+ pltindex * 8);
if (pltindex > 32768)
glinkoff += (pltindex - 32768) * 4;
@@ -5441,26 +5462,24 @@ Stub_table<size, big_endian>::do_write(Output_file* of)
Address off = plt_addr - got_addr;
if (ha(off) == 0)
- {
- write_insn<big_endian>(p + 0, lwz_11_30 + l(off));
- write_insn<big_endian>(p + 4, mtctr_11);
- write_insn<big_endian>(p + 8, bctr);
- }
+ write_insn<big_endian>(p, lwz_11_30 + l(off));
else
{
- write_insn<big_endian>(p + 0, addis_11_30 + ha(off));
- write_insn<big_endian>(p + 4, lwz_11_11 + l(off));
- write_insn<big_endian>(p + 8, mtctr_11);
- write_insn<big_endian>(p + 12, bctr);
+ write_insn<big_endian>(p, addis_11_30 + ha(off));
+ p += 4;
+ write_insn<big_endian>(p, lwz_11_11 + l(off));
}
}
else
{
- write_insn<big_endian>(p + 0, lis_11 + ha(plt_addr));
- write_insn<big_endian>(p + 4, lwz_11_11 + l(plt_addr));
- write_insn<big_endian>(p + 8, mtctr_11);
- write_insn<big_endian>(p + 12, bctr);
+ write_insn<big_endian>(p, lis_11 + ha(plt_addr));
+ p += 4;
+ write_insn<big_endian>(p, lwz_11_11 + l(plt_addr));
}
+ p += 4;
+ write_insn<big_endian>(p, mtctr_11);
+ p += 4;
+ write_insn<big_endian>(p, bctr);
}
}
@@ -5479,23 +5498,29 @@ Stub_table<size, big_endian>::do_write(Output_file* of)
write_insn<big_endian>(p, b | (delta & 0x3fffffc));
else if (!parameters->options().output_is_position_independent())
{
- write_insn<big_endian>(p + 0, lis_12 + ha(bs->first.dest_));
- write_insn<big_endian>(p + 4, addi_12_12 + l(bs->first.dest_));
- write_insn<big_endian>(p + 8, mtctr_12);
- write_insn<big_endian>(p + 12, bctr);
+ write_insn<big_endian>(p, lis_12 + ha(bs->first.dest_));
+ p += 4;
+ write_insn<big_endian>(p, addi_12_12 + l(bs->first.dest_));
}
else
{
delta -= 8;
- write_insn<big_endian>(p + 0, mflr_0);
- write_insn<big_endian>(p + 4, bcl_20_31);
- write_insn<big_endian>(p + 8, mflr_12);
- write_insn<big_endian>(p + 12, addis_12_12 + ha(delta));
- write_insn<big_endian>(p + 16, addi_12_12 + l(delta));
- write_insn<big_endian>(p + 20, mtlr_0);
- write_insn<big_endian>(p + 24, mtctr_12);
- write_insn<big_endian>(p + 28, bctr);
+ write_insn<big_endian>(p, mflr_0);
+ p += 4;
+ write_insn<big_endian>(p, bcl_20_31);
+ p += 4;
+ write_insn<big_endian>(p, mflr_12);
+ p += 4;
+ write_insn<big_endian>(p, addis_12_12 + ha(delta));
+ p += 4;
+ write_insn<big_endian>(p, addi_12_12 + l(delta));
+ p += 4;
+ write_insn<big_endian>(p, mtlr_0);
}
+ p += 4;
+ write_insn<big_endian>(p, mtctr_12);
+ p += 4;
+ write_insn<big_endian>(p, bctr);
}
}
if (this->need_save_res_)
@@ -5563,8 +5588,7 @@ Output_data_glink<size, big_endian>::do_write(Output_file* of)
write_insn<big_endian>(p, ld_11_11 + 8), p += 4;
}
write_insn<big_endian>(p, bctr), p += 4;
- while (p < oview + this->pltresolve_size)
- write_insn<big_endian>(p, nop), p += 4;
+ gold_assert(p == oview + this->pltresolve_size());
// Write lazy link call stubs.
uint32_t indx = 0;
@@ -5590,7 +5614,7 @@ Output_data_glink<size, big_endian>::do_write(Output_file* of)
Address plt_base = this->targ_->plt_section()->address();
Address iplt_base = invalid_address;
- unsigned int global_entry_off = (this->end_branch_table_ + 15) & -16;
+ unsigned int global_entry_off = this->global_entry_off();
Address global_entry_base = this->address() + global_entry_off;
typename Global_entry_stub_entries::const_iterator ge;
for (ge = this->global_entry_stubs_.begin();
@@ -5631,7 +5655,7 @@ Output_data_glink<size, big_endian>::do_write(Output_file* of)
// Write out pltresolve branch table.
p = oview;
- unsigned int the_end = oview_size - this->pltresolve_size;
+ unsigned int the_end = oview_size - this->pltresolve_size();
unsigned char* end_p = oview + the_end;
while (p < end_p - 8 * 4)
write_insn<big_endian>(p, b + end_p - p), p += 4;
@@ -5639,68 +5663,85 @@ Output_data_glink<size, big_endian>::do_write(Output_file* of)
write_insn<big_endian>(p, nop), p += 4;
// Write out pltresolve call stub.
+ end_p = oview + oview_size;
if (parameters->options().output_is_position_independent())
{
Address res0_off = 0;
Address after_bcl_off = the_end + 12;
Address bcl_res0 = after_bcl_off - res0_off;
- write_insn<big_endian>(p + 0, addis_11_11 + ha(bcl_res0));
- write_insn<big_endian>(p + 4, mflr_0);
- write_insn<big_endian>(p + 8, bcl_20_31);
- write_insn<big_endian>(p + 12, addi_11_11 + l(bcl_res0));
- write_insn<big_endian>(p + 16, mflr_12);
- write_insn<big_endian>(p + 20, mtlr_0);
- write_insn<big_endian>(p + 24, sub_11_11_12);
+ write_insn<big_endian>(p, addis_11_11 + ha(bcl_res0));
+ p += 4;
+ write_insn<big_endian>(p, mflr_0);
+ p += 4;
+ write_insn<big_endian>(p, bcl_20_31);
+ p += 4;
+ write_insn<big_endian>(p, addi_11_11 + l(bcl_res0));
+ p += 4;
+ write_insn<big_endian>(p, mflr_12);
+ p += 4;
+ write_insn<big_endian>(p, mtlr_0);
+ p += 4;
+ write_insn<big_endian>(p, sub_11_11_12);
+ p += 4;
Address got_bcl = g_o_t + 4 - (after_bcl_off + this->address());
- write_insn<big_endian>(p + 28, addis_12_12 + ha(got_bcl));
+ write_insn<big_endian>(p, addis_12_12 + ha(got_bcl));
+ p += 4;
if (ha(got_bcl) == ha(got_bcl + 4))
{
- write_insn<big_endian>(p + 32, lwz_0_12 + l(got_bcl));
- write_insn<big_endian>(p + 36, lwz_12_12 + l(got_bcl + 4));
+ write_insn<big_endian>(p, lwz_0_12 + l(got_bcl));
+ p += 4;
+ write_insn<big_endian>(p, lwz_12_12 + l(got_bcl + 4));
}
else
{
- write_insn<big_endian>(p + 32, lwzu_0_12 + l(got_bcl));
- write_insn<big_endian>(p + 36, lwz_12_12 + 4);
+ write_insn<big_endian>(p, lwzu_0_12 + l(got_bcl));
+ p += 4;
+ write_insn<big_endian>(p, lwz_12_12 + 4);
}
- write_insn<big_endian>(p + 40, mtctr_0);
- write_insn<big_endian>(p + 44, add_0_11_11);
- write_insn<big_endian>(p + 48, add_11_0_11);
- write_insn<big_endian>(p + 52, bctr);
- write_insn<big_endian>(p + 56, nop);
- write_insn<big_endian>(p + 60, nop);
+ p += 4;
+ write_insn<big_endian>(p, mtctr_0);
+ p += 4;
+ write_insn<big_endian>(p, add_0_11_11);
+ p += 4;
+ write_insn<big_endian>(p, add_11_0_11);
}
else
{
Address res0 = this->address();
- write_insn<big_endian>(p + 0, lis_12 + ha(g_o_t + 4));
- write_insn<big_endian>(p + 4, addis_11_11 + ha(-res0));
+ write_insn<big_endian>(p, lis_12 + ha(g_o_t + 4));
+ p += 4;
+ write_insn<big_endian>(p, addis_11_11 + ha(-res0));
+ p += 4;
if (ha(g_o_t + 4) == ha(g_o_t + 8))
- write_insn<big_endian>(p + 8, lwz_0_12 + l(g_o_t + 4));
+ write_insn<big_endian>(p, lwz_0_12 + l(g_o_t + 4));
else
- write_insn<big_endian>(p + 8, lwzu_0_12 + l(g_o_t + 4));
- write_insn<big_endian>(p + 12, addi_11_11 + l(-res0));
- write_insn<big_endian>(p + 16, mtctr_0);
- write_insn<big_endian>(p + 20, add_0_11_11);
+ write_insn<big_endian>(p, lwzu_0_12 + l(g_o_t + 4));
+ p += 4;
+ write_insn<big_endian>(p, addi_11_11 + l(-res0));
+ p += 4;
+ write_insn<big_endian>(p, mtctr_0);
+ p += 4;
+ write_insn<big_endian>(p, add_0_11_11);
+ p += 4;
if (ha(g_o_t + 4) == ha(g_o_t + 8))
- write_insn<big_endian>(p + 24, lwz_12_12 + l(g_o_t + 8));
+ write_insn<big_endian>(p, lwz_12_12 + l(g_o_t + 8));
else
- write_insn<big_endian>(p + 24, lwz_12_12 + 4);
- write_insn<big_endian>(p + 28, add_11_0_11);
- write_insn<big_endian>(p + 32, bctr);
- write_insn<big_endian>(p + 36, nop);
- write_insn<big_endian>(p + 40, nop);
- write_insn<big_endian>(p + 44, nop);
- write_insn<big_endian>(p + 48, nop);
- write_insn<big_endian>(p + 52, nop);
- write_insn<big_endian>(p + 56, nop);
- write_insn<big_endian>(p + 60, nop);
+ write_insn<big_endian>(p, lwz_12_12 + 4);
+ p += 4;
+ write_insn<big_endian>(p, add_11_0_11);
+ }
+ p += 4;
+ write_insn<big_endian>(p, bctr);
+ p += 4;
+ while (p < end_p)
+ {
+ write_insn<big_endian>(p, nop);
+ p += 4;
}
- p += 64;
}
of->write_output_view(off, oview_size, oview);
@@ -8161,7 +8202,7 @@ Target_powerpc<size, big_endian>::do_finalize_sections(
this->glink_->finalize_data_size();
odyn->add_section_plus_offset(elfcpp::DT_PPC64_GLINK,
this->glink_,
- (this->glink_->pltresolve_size
+ (this->glink_->pltresolve_size()
- 32));
}
if (this->has_localentry0_ || this->has_tls_get_addr_opt_)
@@ -10187,8 +10228,6 @@ Target_selector_powerpc<64, false> target_selector_ppc64le;
// Instantiate these constants for -O0
template<int size, bool big_endian>
-const int Output_data_glink<size, big_endian>::pltresolve_size;
-template<int size, bool big_endian>
const typename Output_data_glink<size, big_endian>::Address
Output_data_glink<size, big_endian>::invalid_address;
template<int size, bool big_endian>