lib: Unify log2() and related functions

This patch adds a few bit counting functions that are commonly needed
for certain register calculations. We previously had a log2()
implementation already, but it was awkwardly split between some C code
that's only available in ramstage and an optimized x86-specific
implementation in pre-RAM that prevented other archs from pulling it
into earlier stages.

Using __builtin_clz() as the baseline allows GCC to inline optimized
assembly for most archs (including CLZ on ARM/ARM64 and BSR on x86), and
to perform constant-folding if possible. What was previously named log2f
on pre-RAM x86 is now ffs, since that's the standard name for that
operation and I honestly don't have the slightest idea how it could've
ever ended up being called log2f (which in POSIX is 'binary(2) LOGarithm
with Float result, whereas the Find First Set operation has no direct
correlation to logarithms that I know of). Make ffs result 0-based
instead of the POSIX standard's 1-based since that is consistent with
clz, log2 and the former log2f, and generally closer to what you want
for most applications (a value that can directly be used as a shift to
reach the found bit). Call it __ffs() instead of ffs() to avoid problems
when importing code, since that's what Linux uses for the 0-based
operation.

CQ-DEPEND=CL:273023
BRANCH=None
BUG=None
TEST=Built on Big, Falco, Jerry, Oak and Urara. Compared old and new
log2() and __ffs() results on Falco for a bunch of test values.

Change-Id: I599209b342059e17b3130621edb6b6bbeae26876
Signed-off-by: Patrick Georgi <pgeorgi@chromium.org>
Original-Commit-Id: 3701a16ae944ecff9c54fa9a50d28015690fcb2f
Original-Change-Id: I60f7cf893792508188fa04d088401a8bca4b4af6
Original-Signed-off-by: Julius Werner <jwerner@chromium.org>
Original-Reviewed-on: https://chromium-review.googlesource.com/273008
Original-Reviewed-by: Patrick Georgi <pgeorgi@chromium.org>
Reviewed-on: http://review.coreboot.org/10394
Tested-by: build bot (Jenkins)
Reviewed-by: Stefan Reinauer <stefan.reinauer@coreboot.org>

4 files changed, 6 insertions, 2 deletions

diff --git a/src/northbridge/amd/amdk8/coherent_ht.c b/src/northbridge/amd/amdk8/coherent_ht.c
index a8d8700..6554e07 100644
--- a/src/northbridge/amd/amdk8/coherent_ht.c
+++ b/src/northbridge/amd/amdk8/coherent_ht.c
@@ -66,6 +66,7 @@
 #include <device/pci_def.h>
 #include <device/pci_ids.h>
 #include <device/hypertransport_def.h>
+#include <lib.h>
 #include <stdlib.h>
 #include <arch/io.h>
 #include <pc80/mc146818rtc.h>
diff --git a/src/northbridge/amd/amdk8/raminit.c b/src/northbridge/amd/amdk8/raminit.c
index 4213cfb..c58abb1 100644
--- a/src/northbridge/amd/amdk8/raminit.c
+++ b/src/northbridge/amd/amdk8/raminit.c
@@ -7,6 +7,7 @@
 #include <cpu/x86/cache.h>
 #include <cpu/x86/mtrr.h>
 #include <cpu/amd/mtrr.h>
+#include <lib.h>
 #include <stdlib.h>
 #include <arch/acpi.h>
 #include <reset.h>
@@ -1655,7 +1656,7 @@ static struct spd_set_memclk_result spd_set_memclk(const struct mem_controller *
 	/* if the next lower frequency gives a CL at least one whole cycle
 	 * shorter, select that (see end of BKDG 4.1.1.1) */
 	if (freq < sizeof(cl_at_freq)-1 && cl_at_freq[freq+1] &&
-		log2f(cl_at_freq[freq]) - log2f(cl_at_freq[freq+1]) >= 2)
+		__ffs(cl_at_freq[freq]) - __ffs(cl_at_freq[freq+1]) >= 2)
 			freq++;
 
 	if (freq == sizeof(cl_at_freq))
@@ -1690,7 +1691,7 @@ static struct spd_set_memclk_result spd_set_memclk(const struct mem_controller *
 	/* Update DRAM Timing Low with our selected cas latency */
 	value = pci_read_config32(ctrl->f2, DRAM_TIMING_LOW);
 	value &= ~(DTL_TCL_MASK << DTL_TCL_SHIFT);
-	value |= latencies[log2f(cl_at_freq[freq]) - 2] << DTL_TCL_SHIFT;
+	value |= latencies[__ffs(cl_at_freq[freq]) - 2] << DTL_TCL_SHIFT;
 	pci_write_config32(ctrl->f2, DRAM_TIMING_LOW, value);
 
 	result.dimm_mask = dimm_mask;
diff --git a/src/northbridge/amd/amdk8/raminit_f.c b/src/northbridge/amd/amdk8/raminit_f.c
index 1469684..1c1a6ea 100644
--- a/src/northbridge/amd/amdk8/raminit_f.c
+++ b/src/northbridge/amd/amdk8/raminit_f.c
@@ -25,6 +25,7 @@
 #include <cpu/x86/tsc.h>
 #include <cpu/amd/mtrr.h>
 
+#include <lib.h>
 #include <stdlib.h>
 #include <arch/acpi.h>
 #include "raminit.h"
diff --git a/src/northbridge/amd/amdk8/raminit_test.c b/src/northbridge/amd/amdk8/raminit_test.c
index be46f27..87e281d 100644
--- a/src/northbridge/amd/amdk8/raminit_test.c
+++ b/src/northbridge/amd/amdk8/raminit_test.c
@@ -1,5 +1,6 @@
 #include <unistd.h>
 #include <limits.h>
+#include <lib.h>
 #include <stdint.h>
 #include <string.h>
 #include <setjmp.h>