about summary refs log tree commit diff
diff options
context:
space:
mode:
authorChris Metcalf <cmetcalf@tilera.com>2012-11-05 10:43:40 -0500
committerChris Metcalf <cmetcalf@tilera.com>2012-11-06 09:48:49 -0500
commitfedff58953bf60c99498c018b6d787db117c8932 (patch)
tree008a20415ff04434f98dcad935bf4fb548dc5685
parente7776fefa76a5815493b463049fd7ced67cb31a2 (diff)
downloadglibc-fedff58953bf60c99498c018b6d787db117c8932.tar.gz
glibc-fedff58953bf60c99498c018b6d787db117c8932.tar.xz
glibc-fedff58953bf60c99498c018b6d787db117c8932.zip
tile: support very large shared objects
With gcc 4.8 tilegx has support for -mcmodel=large, to tolerate very
large shared objects.  This option changes the compiler output to
not include direct jump instructions, which have a range of only
2^30, i.e +/- 512MB.  Instead the compiler marshalls the target PCs
into registers and then uses jump- or call-to-register instructions.

For glibc, the upshot is that we need to arrange for a few functions
to tolerate the possibility of a large range between the PC and
the target.  In particular, the crti.S and start.S code needs
to be able to reach from .init to the PLT, as does gmon-start.c.
The elf-init.c code has the reverse problem, needing to call from
libc_nonshared.a (linked at the end of shared objects) back to the
_init section at the beginning.

No other functions in *_nonshared.a need to be built this way, as
they only call the PLT (or potentially each other), but all of that
code is linked at the very end of the shared object.

We don't build the standard -static archives with this option as the
performance cost is high enough and the use case is rare enough that
it doesn't seem worthwhile.  Instead, we would encourage developers
who need the -static model with huge executables to build a private
copy of glibc and configure it with -mcmodel=large.

Note that libc.so et al don't need any changes; the only changes
are for code that is statically linked into user code built with
-mcmodel=large.

For the assembly code, I just rewrote it so that it unconditionally
uses the large model.  To be able to pass -mcmodel=large to
csu/elf-init.c and csu/gmon-start.c, I need to check to see if the
compiler supports that flag, since gcc 4.7 doesn't; I added the
support by creating a small Makefile fragment that just runs the
compiler to check.
-rw-r--r--ports/ChangeLog.tile7
-rw-r--r--ports/sysdeps/tile/crti.S23
-rw-r--r--ports/sysdeps/tile/start.S23
-rw-r--r--ports/sysdeps/tile/tilegx/Makefile18
4 files changed, 59 insertions, 12 deletions
diff --git a/ports/ChangeLog.tile b/ports/ChangeLog.tile
index 71aaf56db3..fd722b3e84 100644
--- a/ports/ChangeLog.tile
+++ b/ports/ChangeLog.tile
@@ -1,3 +1,10 @@
+2012-11-05  Chris Metcalf  <cmetcalf@tilera.com>
+
+	* sysdeps/tile/tilegx/Makefile: Generate Makefile fragment to determine
+	whether to build elf-init.c and gmon-start.c with -mcmodel=large.
+	* sysdeps/tile/crti.S: Support large memory model.
+	* sysdeps/tile/start.S: Likewise.
+
 2012-11-02  Chris Metcalf  <cmetcalf@tilera.com>
 
 	* sysdeps/tile/dl-runtime.c (_dl_after_load): Handle simulator
diff --git a/ports/sysdeps/tile/crti.S b/ports/sysdeps/tile/crti.S
index ccb4464bb7..467816c787 100644
--- a/ports/sysdeps/tile/crti.S
+++ b/ports/sysdeps/tile/crti.S
@@ -70,16 +70,17 @@ _init:
 #if PREINIT_FUNCTION_WEAK
 	lnk r2
 0:
-#ifdef __tilegx__
+# ifdef __tilegx__
+	moveli r1, hw2_last(_GLOBAL_OFFSET_TABLE_ - 0b)
 	{
-	 moveli r1, hw1_last(_GLOBAL_OFFSET_TABLE_ - 0b)
+	 shl16insli r1, r1, hw1(_GLOBAL_OFFSET_TABLE_ - 0b)
 	 moveli r0, hw1_last_got(PREINIT_FUNCTION)
 	}
 	{
 	 shl16insli r1, r1, hw0(_GLOBAL_OFFSET_TABLE_ - 0b)
 	 shl16insli r0, r0, hw0_got(PREINIT_FUNCTION)
 	}
-#else
+# else
 	{
 	 moveli r1, lo16(_GLOBAL_OFFSET_TABLE_ - 0b)
 	 moveli r0, got_lo16(PREINIT_FUNCTION)
@@ -88,13 +89,25 @@ _init:
 	 auli r1, r1, ha16(_GLOBAL_OFFSET_TABLE_ - 0b)
 	 auli r0, r0, got_ha16(PREINIT_FUNCTION)
 	}
-#endif
+# endif
 	ADD_PTR r0, r0, r1
 	ADD_PTR r0, r0, r2
 	LD_PTR r0, r0
 	BEQZ r0, .Lno_weak_fn
-#endif
+	jalr r0
+#elif defined(__tilegx__)
+	/* Since we are calling from the start of the object to the PLT,
+	   call by loading the full address into a register.  */
+	lnk r2
+0:
+	moveli r0, hw2_last_plt(PREINIT_FUNCTION - 0b)
+	shl16insli r0, r0, hw1_plt(PREINIT_FUNCTION - 0b)
+	shl16insli r0, r0, hw0_plt(PREINIT_FUNCTION - 0b)
+	add r0, r0, r2
+	jalr r0
+#else
 	jal plt(PREINIT_FUNCTION)
+#endif
 .Lno_weak_fn:
 
 	.section .fini,"ax",@progbits
diff --git a/ports/sysdeps/tile/start.S b/ports/sysdeps/tile/start.S
index 999bb535ca..54f015f4d0 100644
--- a/ports/sysdeps/tile/start.S
+++ b/ports/sysdeps/tile/start.S
@@ -126,27 +126,37 @@ _start:
 	 moveli r0, hw2_last(main - .Lmy_pc)
 	}
 	{
-	 moveli r3, hw2_last(__libc_csu_init - .Lmy_pc)
 	 shl16insli r0, r0, hw1(main - .Lmy_pc)
+	 moveli r3, hw2_last(__libc_csu_init - .Lmy_pc)
 	}
 	{
-	 shl16insli r3, r3, hw1(__libc_csu_init - .Lmy_pc)
 	 shl16insli r0, r0, hw0(main - .Lmy_pc)
+	 shl16insli r3, r3, hw1(__libc_csu_init - .Lmy_pc)
 	}
 	{
+	 ADD_PTR r0, r0, r13
 	 shl16insli r3, r3, hw0(__libc_csu_init - .Lmy_pc)
+	}
+	{
+	 moveli r12, hw2_last_plt(__libc_start_main - .Lmy_pc)
+	 ADD_PTR r3, r3, r13
+	}
+	{
+	 shl16insli r12, r12, hw1_plt(__libc_start_main - .Lmy_pc)
 	 moveli r4, hw2_last(__libc_csu_fini - .Lmy_pc)
 	}
 	{
-	 ADD_PTR r0, r0, r13
+	 shl16insli r12, r12, hw0_plt(__libc_start_main - .Lmy_pc)
 	 shl16insli r4, r4, hw1(__libc_csu_fini - .Lmy_pc)
 	}
 	{
-	 ADD_PTR r3, r3, r13
+	 ADD_PTR r12, r12, r13
 	 shl16insli r4, r4, hw0(__libc_csu_fini - .Lmy_pc)
 	}
 	{
 	 ADD_PTR r4, r4, r13
+	 jalr r12
+	}
 #else
 	 addli r0, r13, lo16(main - .Lmy_pc)
 	}
@@ -160,13 +170,12 @@ _start:
 	}
 	{
 	 auli r4, r4, ha16(__libc_csu_fini - .Lmy_pc)
-
-#endif
-
 	 /* Call the user's main function, and exit with its value.
 	    But let the libc call main. */
 	 j plt(__libc_start_main)
 	}
+#endif
+
 	{
 	 /* Tell backtracer to give up (_start has no caller). */
 	 info INFO_OP_CANNOT_BACKTRACE
diff --git a/ports/sysdeps/tile/tilegx/Makefile b/ports/sysdeps/tile/tilegx/Makefile
new file mode 100644
index 0000000000..d3a0e970a7
--- /dev/null
+++ b/ports/sysdeps/tile/tilegx/Makefile
@@ -0,0 +1,18 @@
+include $(common-objpfx)cflags-mcmodel-large.mk
+
+$(common-objpfx)cflags-mcmodel-large.mk: $(common-objpfx)config.make
+	mcmodel=no; \
+	$(CC) -S -o /dev/null -xc /dev/null -mcmodel=large && mcmodel=yes; \
+	echo "cflags-mcmodel-large = $$mcmodel" > $@
+
+ifeq ($(subdir),csu)
+ifeq (yes,$(cflags-mcmodel-large))
+# elf-init.c is in libc_nonshared.o (the end of the shared object) but
+# must reach the _init symbol at the very start of the shared object.
+CFLAGS-elf-init.c += -mcmodel=large
+
+# __gmon_start__ is at the very start of the shared object when linked
+# with profiling, but calls to libc.so via the PLT at the very end.
+CFLAGS-gmon-start.c += -mcmodel=large
+endif
+endif