* Re: Git tree for the 32/64 merge
From: Kumar Gala @ 2005-09-19 2:36 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev, linuxppc64-dev
In-Reply-To: <17197.65270.548340.377011@cargo.ozlabs.ibm.com>
Can you get this tree added to gitweb on kernel.org
- kumar
On Sep 18, 2005, at 6:57 PM, Paul Mackerras wrote:
> I have created a git tree on kernel.org as a place to accumulate the
> patches for the ppc32/ppc64 merge. It is at:
>
> rsync://rsync.kernel.org/pub/scm/linux/kernel/git/paulus/powerpc-
> merge.g
> it
>
> It doesn't include the objects in Linus' tree; instead it has an
> objects/info/alternates file pointing to Linus' tree.
>
> This tree contains all the patches I found in a scan through my inbox
> that relate to the merge and haven't already gone to Linus. If you
> have a patch that should go in, please resend it.
>
> Paul.
> _______________________________________________
> Linuxppc-dev mailing list
> Linuxppc-dev@ozlabs.org
> https://ozlabs.org/mailman/listinfo/linuxppc-dev
>
^ permalink raw reply
* Re: Git tree for the 32/64 merge
From: Jon Loeliger @ 2005-09-19 3:27 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev, linuxppc64-dev
In-Reply-To: <17197.65270.548340.377011@cargo.ozlabs.ibm.com>
So, like, the other day Paul Mackerras mumbled:
>
> This tree contains all the patches I found in a scan through my inbox
> that relate to the merge and haven't already gone to Linus. If you
> have a patch that should go in, please resend it.
I think you might have missed my posix_types.h merge
patch of Sep 10. Would you like a repost?
Thanks,
jdl
^ permalink raw reply
* System RAM requirement for PBX - Router Application product
From: ganeshkumar @ 2005-09-19 4:33 UTC (permalink / raw)
To: Linuxppc-dev
Dear All,
I'm working on MPC860P with 8MB of FLash ROM and 16MB of RAM
on our system running Mvista Linux. Our Product is an Integrated Access
Device
with the following features built in:
1) ISDN PRI on E1 interface with 15 channels for Voice & 15
Channels for Data
2) LAN to WAN Router and vice versa, serving Internet users on
the LAN side.
3) Built in PABx functionality serving upto 60 extensions
4) Embedded mySQL database for Call details and Records,
5) An IDE interface supporting a 80GB HDD
6) Web server for configuration (Boa)
So for a product with the above configuration/features , what is the minimum
amount memory that is needed to run without any flaws?
Currently we have 8MB Flash, 16MB SD-RAM with MPC860P running @ 40MHz
Is 16MB SD-RAM enough for this type of an Application? or we need to
increase our SD-RAM size?
Thanks in Advance!
Thanks & Best regards,
Ganesh
^ permalink raw reply
* Cartoes UOL
From: cartoes @ 2005-09-19 4:41 UTC (permalink / raw)
To: linuxppc-embedded
[-- Attachment #1: Type: text/html, Size: 6105 bytes --]
^ permalink raw reply
* [PATCH] powerpc: Move arch/ppc*/kernel/vecemu.c to arch/powerpc
From: Stephen Rothwell @ 2005-09-19 7:33 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
This file is the same in both architectures so create arch/powerpc/kernel
and move it there.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/powerpc/kernel/vecemu.c | 345 ++++++++++++++++++++++++++++++++++++++++++
arch/ppc/kernel/Makefile | 2
arch/ppc/kernel/vecemu.c | 345 ------------------------------------------
arch/ppc64/kernel/Makefile | 3
arch/ppc64/kernel/vecemu.c | 346 ------------------------------------------
5 files changed, 350 insertions(+), 691 deletions(-)
create mode 100644 arch/powerpc/kernel/vecemu.c
delete mode 100644 arch/ppc/kernel/vecemu.c
delete mode 100644 arch/ppc64/kernel/vecemu.c
Compiled for ppc defconfig, iSeries (almost defconfig), pSeries defconfig and g5 defconfig.
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
672ea98fe3cd3ce7371198fc000d37808667f64c
diff --git a/arch/powerpc/kernel/vecemu.c b/arch/powerpc/kernel/vecemu.c
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/kernel/vecemu.c
@@ -0,0 +1,345 @@
+/*
+ * Routines to emulate some Altivec/VMX instructions, specifically
+ * those that can trap when given denormalized operands in Java mode.
+ */
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <asm/ptrace.h>
+#include <asm/processor.h>
+#include <asm/uaccess.h>
+
+/* Functions in vector.S */
+extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b);
+extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
+extern void vrefp(vector128 *dst, vector128 *src);
+extern void vrsqrtefp(vector128 *dst, vector128 *src);
+extern void vexptep(vector128 *dst, vector128 *src);
+
+static unsigned int exp2s[8] = {
+ 0x800000,
+ 0x8b95c2,
+ 0x9837f0,
+ 0xa5fed7,
+ 0xb504f3,
+ 0xc5672a,
+ 0xd744fd,
+ 0xeac0c7
+};
+
+/*
+ * Computes an estimate of 2^x. The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int eexp2(unsigned int s)
+{
+ int exp, pwr;
+ unsigned int mant, frac;
+
+ /* extract exponent field from input */
+ exp = ((s >> 23) & 0xff) - 127;
+ if (exp > 7) {
+ /* check for NaN input */
+ if (exp == 128 && (s & 0x7fffff) != 0)
+ return s | 0x400000; /* return QNaN */
+ /* 2^-big = 0, 2^+big = +Inf */
+ return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */
+ }
+ if (exp < -23)
+ return 0x3f800000; /* 1.0 */
+
+ /* convert to fixed point integer in 9.23 representation */
+ pwr = (s & 0x7fffff) | 0x800000;
+ if (exp > 0)
+ pwr <<= exp;
+ else
+ pwr >>= -exp;
+ if (s & 0x80000000)
+ pwr = -pwr;
+
+ /* extract integer part, which becomes exponent part of result */
+ exp = (pwr >> 23) + 126;
+ if (exp >= 254)
+ return 0x7f800000;
+ if (exp < -23)
+ return 0;
+
+ /* table lookup on top 3 bits of fraction to get mantissa */
+ mant = exp2s[(pwr >> 20) & 7];
+
+ /* linear interpolation using remaining 20 bits of fraction */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" (pwr << 12), "r" (0x172b83ff));
+ asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant));
+ mant += frac;
+
+ if (exp >= 0)
+ return mant + (exp << 23);
+
+ /* denormalized result */
+ exp = -exp;
+ mant += 1 << (exp - 1);
+ return mant >> exp;
+}
+
+/*
+ * Computes an estimate of log_2(x). The `s' argument is the 32-bit
+ * single-precision floating-point representation of x.
+ */
+static unsigned int elog2(unsigned int s)
+{
+ int exp, mant, lz, frac;
+
+ exp = s & 0x7f800000;
+ mant = s & 0x7fffff;
+ if (exp == 0x7f800000) { /* Inf or NaN */
+ if (mant != 0)
+ s |= 0x400000; /* turn NaN into QNaN */
+ return s;
+ }
+ if ((exp | mant) == 0) /* +0 or -0 */
+ return 0xff800000; /* return -Inf */
+
+ if (exp == 0) {
+ /* denormalized */
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant));
+ mant <<= lz - 8;
+ exp = (-118 - lz) << 23;
+ } else {
+ mant |= 0x800000;
+ exp -= 127 << 23;
+ }
+
+ if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */
+ exp |= 0x400000; /* 0.5 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */
+ }
+ if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */
+ exp |= 0x200000; /* 0.25 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */
+ }
+ if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */
+ exp |= 0x100000; /* 0.125 * 2^23 */
+ asm("mulhwu %0,%1,%2" : "=r" (mant)
+ : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */
+ }
+ if (mant > 0x800000) { /* 1.0 * 2^23 */
+ /* calculate (mant - 1) * 1.381097463 */
+ /* 1.381097463 == 0.125 / (2^0.125 - 1) */
+ asm("mulhwu %0,%1,%2" : "=r" (frac)
+ : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a));
+ exp += frac;
+ }
+ s = exp & 0x80000000;
+ if (exp != 0) {
+ if (s)
+ exp = -exp;
+ asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp));
+ lz = 8 - lz;
+ if (lz > 0)
+ exp >>= lz;
+ else if (lz < 0)
+ exp <<= -lz;
+ s += ((lz + 126) << 23) + exp;
+ }
+ return s;
+}
+
+#define VSCR_SAT 1
+
+static int ctsxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp, mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (exp >= 31) {
+ /* saturate, unless the result would be -2^31 */
+ if (x + (scale << 23) != 0xcf000000)
+ *vscrp |= VSCR_SAT;
+ return (x & 0x80000000)? 0x80000000: 0x7fffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 7) >> (30 - exp);
+ return (x & 0x80000000)? -mant: mant;
+}
+
+static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp)
+{
+ int exp;
+ unsigned int mant;
+
+ exp = (x >> 23) & 0xff;
+ mant = x & 0x7fffff;
+ if (exp == 255 && mant != 0)
+ return 0; /* NaN -> 0 */
+ exp = exp - 127 + scale;
+ if (exp < 0)
+ return 0; /* round towards zero */
+ if (x & 0x80000000) {
+ /* negative => saturate to 0 */
+ *vscrp |= VSCR_SAT;
+ return 0;
+ }
+ if (exp >= 32) {
+ /* saturate */
+ *vscrp |= VSCR_SAT;
+ return 0xffffffff;
+ }
+ mant |= 0x800000;
+ mant = (mant << 8) >> (31 - exp);
+ return mant;
+}
+
+/* Round to floating integer, towards 0 */
+static unsigned int rfiz(unsigned int x)
+{
+ int exp;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < 0)
+ return x & 0x80000000; /* |x| < 1.0 rounds to 0 */
+ return x & ~(0x7fffff >> exp);
+}
+
+/* Round to floating integer, towards +/- Inf */
+static unsigned int rfii(unsigned int x)
+{
+ int exp, mask;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if ((x & 0x7fffffff) == 0)
+ return x; /* +/-0 -> +/-0 */
+ if (exp < 0)
+ /* 0 < |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ mask = 0x7fffff >> exp;
+ /* mantissa overflows into exponent - that's OK,
+ it can't overflow into the sign bit */
+ return (x + mask) & ~mask;
+}
+
+/* Round to floating integer, to nearest */
+static unsigned int rfin(unsigned int x)
+{
+ int exp, half;
+
+ exp = ((x >> 23) & 0xff) - 127;
+ if (exp == 128 && (x & 0x7fffff) != 0)
+ return x | 0x400000; /* NaN -> make it a QNaN */
+ if (exp >= 23)
+ return x; /* it's an integer already (or Inf) */
+ if (exp < -1)
+ return x & 0x80000000; /* |x| < 0.5 -> +/-0 */
+ if (exp == -1)
+ /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */
+ return (x & 0x80000000) | 0x3f800000;
+ half = 0x400000 >> exp;
+ /* add 0.5 to the magnitude and chop off the fraction bits */
+ return (x + half) & ~(0x7fffff >> exp);
+}
+
+int emulate_altivec(struct pt_regs *regs)
+{
+ unsigned int instr, i;
+ unsigned int va, vb, vc, vd;
+ vector128 *vrs;
+
+ if (get_user(instr, (unsigned int __user *) regs->nip))
+ return -EFAULT;
+ if ((instr >> 26) != 4)
+ return -EINVAL; /* not an altivec instruction */
+ vd = (instr >> 21) & 0x1f;
+ va = (instr >> 16) & 0x1f;
+ vb = (instr >> 11) & 0x1f;
+ vc = (instr >> 6) & 0x1f;
+
+ vrs = current->thread.vr;
+ switch (instr & 0x3f) {
+ case 10:
+ switch (vc) {
+ case 0: /* vaddfp */
+ vaddfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 1: /* vsubfp */
+ vsubfp(&vrs[vd], &vrs[va], &vrs[vb]);
+ break;
+ case 4: /* vrefp */
+ vrefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 5: /* vrsqrtefp */
+ vrsqrtefp(&vrs[vd], &vrs[vb]);
+ break;
+ case 6: /* vexptefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = eexp2(vrs[vb].u[i]);
+ break;
+ case 7: /* vlogefp */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = elog2(vrs[vb].u[i]);
+ break;
+ case 8: /* vrfin */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfin(vrs[vb].u[i]);
+ break;
+ case 9: /* vrfiz */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = rfiz(vrs[vb].u[i]);
+ break;
+ case 10: /* vrfip */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfiz(x): rfii(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 11: /* vrfim */
+ for (i = 0; i < 4; ++i) {
+ u32 x = vrs[vb].u[i];
+ x = (x & 0x80000000)? rfii(x): rfiz(x);
+ vrs[vd].u[i] = x;
+ }
+ break;
+ case 14: /* vctuxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
+ ¤t->thread.vscr.u[3]);
+ break;
+ case 15: /* vctsxs */
+ for (i = 0; i < 4; ++i)
+ vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
+ ¤t->thread.vscr.u[3]);
+ break;
+ default:
+ return -EINVAL;
+ }
+ break;
+ case 46: /* vmaddfp */
+ vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ case 47: /* vnmsubfp */
+ vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
diff --git a/arch/ppc/kernel/Makefile b/arch/ppc/kernel/Makefile
--- a/arch/ppc/kernel/Makefile
+++ b/arch/ppc/kernel/Makefile
@@ -36,3 +36,5 @@ ifndef CONFIG_MATH_EMULATION
obj-$(CONFIG_8xx) += softemu8xx.o
endif
+# These are here while we do the architecture merge
+vecemu-y += ../../powerpc/kernel/vecemu.o
diff --git a/arch/ppc/kernel/vecemu.c b/arch/ppc/kernel/vecemu.c
deleted file mode 100644
--- a/arch/ppc/kernel/vecemu.c
+++ /dev/null
@@ -1,345 +0,0 @@
-/*
- * Routines to emulate some Altivec/VMX instructions, specifically
- * those that can trap when given denormalized operands in Java mode.
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <asm/ptrace.h>
-#include <asm/processor.h>
-#include <asm/uaccess.h>
-
-/* Functions in vector.S */
-extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
-extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b);
-extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
-extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
-extern void vrefp(vector128 *dst, vector128 *src);
-extern void vrsqrtefp(vector128 *dst, vector128 *src);
-extern void vexptep(vector128 *dst, vector128 *src);
-
-static unsigned int exp2s[8] = {
- 0x800000,
- 0x8b95c2,
- 0x9837f0,
- 0xa5fed7,
- 0xb504f3,
- 0xc5672a,
- 0xd744fd,
- 0xeac0c7
-};
-
-/*
- * Computes an estimate of 2^x. The `s' argument is the 32-bit
- * single-precision floating-point representation of x.
- */
-static unsigned int eexp2(unsigned int s)
-{
- int exp, pwr;
- unsigned int mant, frac;
-
- /* extract exponent field from input */
- exp = ((s >> 23) & 0xff) - 127;
- if (exp > 7) {
- /* check for NaN input */
- if (exp == 128 && (s & 0x7fffff) != 0)
- return s | 0x400000; /* return QNaN */
- /* 2^-big = 0, 2^+big = +Inf */
- return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */
- }
- if (exp < -23)
- return 0x3f800000; /* 1.0 */
-
- /* convert to fixed point integer in 9.23 representation */
- pwr = (s & 0x7fffff) | 0x800000;
- if (exp > 0)
- pwr <<= exp;
- else
- pwr >>= -exp;
- if (s & 0x80000000)
- pwr = -pwr;
-
- /* extract integer part, which becomes exponent part of result */
- exp = (pwr >> 23) + 126;
- if (exp >= 254)
- return 0x7f800000;
- if (exp < -23)
- return 0;
-
- /* table lookup on top 3 bits of fraction to get mantissa */
- mant = exp2s[(pwr >> 20) & 7];
-
- /* linear interpolation using remaining 20 bits of fraction */
- asm("mulhwu %0,%1,%2" : "=r" (frac)
- : "r" (pwr << 12), "r" (0x172b83ff));
- asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant));
- mant += frac;
-
- if (exp >= 0)
- return mant + (exp << 23);
-
- /* denormalized result */
- exp = -exp;
- mant += 1 << (exp - 1);
- return mant >> exp;
-}
-
-/*
- * Computes an estimate of log_2(x). The `s' argument is the 32-bit
- * single-precision floating-point representation of x.
- */
-static unsigned int elog2(unsigned int s)
-{
- int exp, mant, lz, frac;
-
- exp = s & 0x7f800000;
- mant = s & 0x7fffff;
- if (exp == 0x7f800000) { /* Inf or NaN */
- if (mant != 0)
- s |= 0x400000; /* turn NaN into QNaN */
- return s;
- }
- if ((exp | mant) == 0) /* +0 or -0 */
- return 0xff800000; /* return -Inf */
-
- if (exp == 0) {
- /* denormalized */
- asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant));
- mant <<= lz - 8;
- exp = (-118 - lz) << 23;
- } else {
- mant |= 0x800000;
- exp -= 127 << 23;
- }
-
- if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */
- exp |= 0x400000; /* 0.5 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */
- }
- if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */
- exp |= 0x200000; /* 0.25 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */
- }
- if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */
- exp |= 0x100000; /* 0.125 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */
- }
- if (mant > 0x800000) { /* 1.0 * 2^23 */
- /* calculate (mant - 1) * 1.381097463 */
- /* 1.381097463 == 0.125 / (2^0.125 - 1) */
- asm("mulhwu %0,%1,%2" : "=r" (frac)
- : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a));
- exp += frac;
- }
- s = exp & 0x80000000;
- if (exp != 0) {
- if (s)
- exp = -exp;
- asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp));
- lz = 8 - lz;
- if (lz > 0)
- exp >>= lz;
- else if (lz < 0)
- exp <<= -lz;
- s += ((lz + 126) << 23) + exp;
- }
- return s;
-}
-
-#define VSCR_SAT 1
-
-static int ctsxs(unsigned int x, int scale, unsigned int *vscrp)
-{
- int exp, mant;
-
- exp = (x >> 23) & 0xff;
- mant = x & 0x7fffff;
- if (exp == 255 && mant != 0)
- return 0; /* NaN -> 0 */
- exp = exp - 127 + scale;
- if (exp < 0)
- return 0; /* round towards zero */
- if (exp >= 31) {
- /* saturate, unless the result would be -2^31 */
- if (x + (scale << 23) != 0xcf000000)
- *vscrp |= VSCR_SAT;
- return (x & 0x80000000)? 0x80000000: 0x7fffffff;
- }
- mant |= 0x800000;
- mant = (mant << 7) >> (30 - exp);
- return (x & 0x80000000)? -mant: mant;
-}
-
-static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp)
-{
- int exp;
- unsigned int mant;
-
- exp = (x >> 23) & 0xff;
- mant = x & 0x7fffff;
- if (exp == 255 && mant != 0)
- return 0; /* NaN -> 0 */
- exp = exp - 127 + scale;
- if (exp < 0)
- return 0; /* round towards zero */
- if (x & 0x80000000) {
- /* negative => saturate to 0 */
- *vscrp |= VSCR_SAT;
- return 0;
- }
- if (exp >= 32) {
- /* saturate */
- *vscrp |= VSCR_SAT;
- return 0xffffffff;
- }
- mant |= 0x800000;
- mant = (mant << 8) >> (31 - exp);
- return mant;
-}
-
-/* Round to floating integer, towards 0 */
-static unsigned int rfiz(unsigned int x)
-{
- int exp;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if (exp < 0)
- return x & 0x80000000; /* |x| < 1.0 rounds to 0 */
- return x & ~(0x7fffff >> exp);
-}
-
-/* Round to floating integer, towards +/- Inf */
-static unsigned int rfii(unsigned int x)
-{
- int exp, mask;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if ((x & 0x7fffffff) == 0)
- return x; /* +/-0 -> +/-0 */
- if (exp < 0)
- /* 0 < |x| < 1.0 rounds to +/- 1.0 */
- return (x & 0x80000000) | 0x3f800000;
- mask = 0x7fffff >> exp;
- /* mantissa overflows into exponent - that's OK,
- it can't overflow into the sign bit */
- return (x + mask) & ~mask;
-}
-
-/* Round to floating integer, to nearest */
-static unsigned int rfin(unsigned int x)
-{
- int exp, half;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if (exp < -1)
- return x & 0x80000000; /* |x| < 0.5 -> +/-0 */
- if (exp == -1)
- /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */
- return (x & 0x80000000) | 0x3f800000;
- half = 0x400000 >> exp;
- /* add 0.5 to the magnitude and chop off the fraction bits */
- return (x + half) & ~(0x7fffff >> exp);
-}
-
-int emulate_altivec(struct pt_regs *regs)
-{
- unsigned int instr, i;
- unsigned int va, vb, vc, vd;
- vector128 *vrs;
-
- if (get_user(instr, (unsigned int __user *) regs->nip))
- return -EFAULT;
- if ((instr >> 26) != 4)
- return -EINVAL; /* not an altivec instruction */
- vd = (instr >> 21) & 0x1f;
- va = (instr >> 16) & 0x1f;
- vb = (instr >> 11) & 0x1f;
- vc = (instr >> 6) & 0x1f;
-
- vrs = current->thread.vr;
- switch (instr & 0x3f) {
- case 10:
- switch (vc) {
- case 0: /* vaddfp */
- vaddfp(&vrs[vd], &vrs[va], &vrs[vb]);
- break;
- case 1: /* vsubfp */
- vsubfp(&vrs[vd], &vrs[va], &vrs[vb]);
- break;
- case 4: /* vrefp */
- vrefp(&vrs[vd], &vrs[vb]);
- break;
- case 5: /* vrsqrtefp */
- vrsqrtefp(&vrs[vd], &vrs[vb]);
- break;
- case 6: /* vexptefp */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = eexp2(vrs[vb].u[i]);
- break;
- case 7: /* vlogefp */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = elog2(vrs[vb].u[i]);
- break;
- case 8: /* vrfin */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = rfin(vrs[vb].u[i]);
- break;
- case 9: /* vrfiz */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = rfiz(vrs[vb].u[i]);
- break;
- case 10: /* vrfip */
- for (i = 0; i < 4; ++i) {
- u32 x = vrs[vb].u[i];
- x = (x & 0x80000000)? rfiz(x): rfii(x);
- vrs[vd].u[i] = x;
- }
- break;
- case 11: /* vrfim */
- for (i = 0; i < 4; ++i) {
- u32 x = vrs[vb].u[i];
- x = (x & 0x80000000)? rfii(x): rfiz(x);
- vrs[vd].u[i] = x;
- }
- break;
- case 14: /* vctuxs */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
- break;
- case 15: /* vctsxs */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
- break;
- default:
- return -EINVAL;
- }
- break;
- case 46: /* vmaddfp */
- vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
- break;
- case 47: /* vnmsubfp */
- vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
diff --git a/arch/ppc64/kernel/Makefile b/arch/ppc64/kernel/Makefile
--- a/arch/ppc64/kernel/Makefile
+++ b/arch/ppc64/kernel/Makefile
@@ -83,3 +83,6 @@ ifeq ($(CONFIG_PPC_ISERIES),y)
arch/ppc64/kernel/head.o: arch/ppc64/kernel/lparmap.s
AFLAGS_head.o += -Iarch/ppc64/kernel
endif
+
+# These are here while we do the architecture merge
+vecemu-y += ../../powerpc/kernel/vecemu.o
diff --git a/arch/ppc64/kernel/vecemu.c b/arch/ppc64/kernel/vecemu.c
deleted file mode 100644
--- a/arch/ppc64/kernel/vecemu.c
+++ /dev/null
@@ -1,346 +0,0 @@
-/*
- * Routines to emulate some Altivec/VMX instructions, specifically
- * those that can trap when given denormalized operands in Java mode.
- */
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/sched.h>
-#include <asm/ptrace.h>
-#include <asm/processor.h>
-#include <asm/uaccess.h>
-
-/* Functions in vector.S */
-extern void vaddfp(vector128 *dst, vector128 *a, vector128 *b);
-extern void vsubfp(vector128 *dst, vector128 *a, vector128 *b);
-extern void vmaddfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
-extern void vnmsubfp(vector128 *dst, vector128 *a, vector128 *b, vector128 *c);
-extern void vrefp(vector128 *dst, vector128 *src);
-extern void vrsqrtefp(vector128 *dst, vector128 *src);
-extern void vexptep(vector128 *dst, vector128 *src);
-
-static unsigned int exp2s[8] = {
- 0x800000,
- 0x8b95c2,
- 0x9837f0,
- 0xa5fed7,
- 0xb504f3,
- 0xc5672a,
- 0xd744fd,
- 0xeac0c7
-};
-
-/*
- * Computes an estimate of 2^x. The `s' argument is the 32-bit
- * single-precision floating-point representation of x.
- */
-static unsigned int eexp2(unsigned int s)
-{
- int exp, pwr;
- unsigned int mant, frac;
-
- /* extract exponent field from input */
- exp = ((s >> 23) & 0xff) - 127;
- if (exp > 7) {
- /* check for NaN input */
- if (exp == 128 && (s & 0x7fffff) != 0)
- return s | 0x400000; /* return QNaN */
- /* 2^-big = 0, 2^+big = +Inf */
- return (s & 0x80000000)? 0: 0x7f800000; /* 0 or +Inf */
- }
- if (exp < -23)
- return 0x3f800000; /* 1.0 */
-
- /* convert to fixed point integer in 9.23 representation */
- pwr = (s & 0x7fffff) | 0x800000;
- if (exp > 0)
- pwr <<= exp;
- else
- pwr >>= -exp;
- if (s & 0x80000000)
- pwr = -pwr;
-
- /* extract integer part, which becomes exponent part of result */
- exp = (pwr >> 23) + 126;
- if (exp >= 254)
- return 0x7f800000;
- if (exp < -23)
- return 0;
-
- /* table lookup on top 3 bits of fraction to get mantissa */
- mant = exp2s[(pwr >> 20) & 7];
-
- /* linear interpolation using remaining 20 bits of fraction */
- asm("mulhwu %0,%1,%2" : "=r" (frac)
- : "r" (pwr << 12), "r" (0x172b83ff));
- asm("mulhwu %0,%1,%2" : "=r" (frac) : "r" (frac), "r" (mant));
- mant += frac;
-
- if (exp >= 0)
- return mant + (exp << 23);
-
- /* denormalized result */
- exp = -exp;
- mant += 1 << (exp - 1);
- return mant >> exp;
-}
-
-/*
- * Computes an estimate of log_2(x). The `s' argument is the 32-bit
- * single-precision floating-point representation of x.
- */
-static unsigned int elog2(unsigned int s)
-{
- int exp, mant, lz, frac;
-
- exp = s & 0x7f800000;
- mant = s & 0x7fffff;
- if (exp == 0x7f800000) { /* Inf or NaN */
- if (mant != 0)
- s |= 0x400000; /* turn NaN into QNaN */
- return s;
- }
- if ((exp | mant) == 0) /* +0 or -0 */
- return 0xff800000; /* return -Inf */
-
- if (exp == 0) {
- /* denormalized */
- asm("cntlzw %0,%1" : "=r" (lz) : "r" (mant));
- mant <<= lz - 8;
- exp = (-118 - lz) << 23;
- } else {
- mant |= 0x800000;
- exp -= 127 << 23;
- }
-
- if (mant >= 0xb504f3) { /* 2^0.5 * 2^23 */
- exp |= 0x400000; /* 0.5 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xb504f334)); /* 2^-0.5 * 2^32 */
- }
- if (mant >= 0x9837f0) { /* 2^0.25 * 2^23 */
- exp |= 0x200000; /* 0.25 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xd744fccb)); /* 2^-0.25 * 2^32 */
- }
- if (mant >= 0x8b95c2) { /* 2^0.125 * 2^23 */
- exp |= 0x100000; /* 0.125 * 2^23 */
- asm("mulhwu %0,%1,%2" : "=r" (mant)
- : "r" (mant), "r" (0xeac0c6e8)); /* 2^-0.125 * 2^32 */
- }
- if (mant > 0x800000) { /* 1.0 * 2^23 */
- /* calculate (mant - 1) * 1.381097463 */
- /* 1.381097463 == 0.125 / (2^0.125 - 1) */
- asm("mulhwu %0,%1,%2" : "=r" (frac)
- : "r" ((mant - 0x800000) << 1), "r" (0xb0c7cd3a));
- exp += frac;
- }
- s = exp & 0x80000000;
- if (exp != 0) {
- if (s)
- exp = -exp;
- asm("cntlzw %0,%1" : "=r" (lz) : "r" (exp));
- lz = 8 - lz;
- if (lz > 0)
- exp >>= lz;
- else if (lz < 0)
- exp <<= -lz;
- s += ((lz + 126) << 23) + exp;
- }
- return s;
-}
-
-#define VSCR_SAT 1
-
-static int ctsxs(unsigned int x, int scale, unsigned int *vscrp)
-{
- int exp, mant;
-
- exp = (x >> 23) & 0xff;
- mant = x & 0x7fffff;
- if (exp == 255 && mant != 0)
- return 0; /* NaN -> 0 */
- exp = exp - 127 + scale;
- if (exp < 0)
- return 0; /* round towards zero */
- if (exp >= 31) {
- /* saturate, unless the result would be -2^31 */
- if (x + (scale << 23) != 0xcf000000)
- *vscrp |= VSCR_SAT;
- return (x & 0x80000000)? 0x80000000: 0x7fffffff;
- }
- mant |= 0x800000;
- mant = (mant << 7) >> (30 - exp);
- return (x & 0x80000000)? -mant: mant;
-}
-
-static unsigned int ctuxs(unsigned int x, int scale, unsigned int *vscrp)
-{
- int exp;
- unsigned int mant;
-
- exp = (x >> 23) & 0xff;
- mant = x & 0x7fffff;
- if (exp == 255 && mant != 0)
- return 0; /* NaN -> 0 */
- exp = exp - 127 + scale;
- if (exp < 0)
- return 0; /* round towards zero */
- if (x & 0x80000000) {
- /* negative => saturate to 0 */
- *vscrp |= VSCR_SAT;
- return 0;
- }
- if (exp >= 32) {
- /* saturate */
- *vscrp |= VSCR_SAT;
- return 0xffffffff;
- }
- mant |= 0x800000;
- mant = (mant << 8) >> (31 - exp);
- return mant;
-}
-
-/* Round to floating integer, towards 0 */
-static unsigned int rfiz(unsigned int x)
-{
- int exp;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if (exp < 0)
- return x & 0x80000000; /* |x| < 1.0 rounds to 0 */
- return x & ~(0x7fffff >> exp);
-}
-
-/* Round to floating integer, towards +/- Inf */
-static unsigned int rfii(unsigned int x)
-{
- int exp, mask;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if ((x & 0x7fffffff) == 0)
- return x; /* +/-0 -> +/-0 */
- if (exp < 0)
- /* 0 < |x| < 1.0 rounds to +/- 1.0 */
- return (x & 0x80000000) | 0x3f800000;
- mask = 0x7fffff >> exp;
- /* mantissa overflows into exponent - that's OK,
- it can't overflow into the sign bit */
- return (x + mask) & ~mask;
-}
-
-/* Round to floating integer, to nearest */
-static unsigned int rfin(unsigned int x)
-{
- int exp, half;
-
- exp = ((x >> 23) & 0xff) - 127;
- if (exp == 128 && (x & 0x7fffff) != 0)
- return x | 0x400000; /* NaN -> make it a QNaN */
- if (exp >= 23)
- return x; /* it's an integer already (or Inf) */
- if (exp < -1)
- return x & 0x80000000; /* |x| < 0.5 -> +/-0 */
- if (exp == -1)
- /* 0.5 <= |x| < 1.0 rounds to +/- 1.0 */
- return (x & 0x80000000) | 0x3f800000;
- half = 0x400000 >> exp;
- /* add 0.5 to the magnitude and chop off the fraction bits */
- return (x + half) & ~(0x7fffff >> exp);
-}
-
-int
-emulate_altivec(struct pt_regs *regs)
-{
- unsigned int instr, i;
- unsigned int va, vb, vc, vd;
- vector128 *vrs;
-
- if (get_user(instr, (unsigned int __user *) regs->nip))
- return -EFAULT;
- if ((instr >> 26) != 4)
- return -EINVAL; /* not an altivec instruction */
- vd = (instr >> 21) & 0x1f;
- va = (instr >> 16) & 0x1f;
- vb = (instr >> 11) & 0x1f;
- vc = (instr >> 6) & 0x1f;
-
- vrs = current->thread.vr;
- switch (instr & 0x3f) {
- case 10:
- switch (vc) {
- case 0: /* vaddfp */
- vaddfp(&vrs[vd], &vrs[va], &vrs[vb]);
- break;
- case 1: /* vsubfp */
- vsubfp(&vrs[vd], &vrs[va], &vrs[vb]);
- break;
- case 4: /* vrefp */
- vrefp(&vrs[vd], &vrs[vb]);
- break;
- case 5: /* vrsqrtefp */
- vrsqrtefp(&vrs[vd], &vrs[vb]);
- break;
- case 6: /* vexptefp */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = eexp2(vrs[vb].u[i]);
- break;
- case 7: /* vlogefp */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = elog2(vrs[vb].u[i]);
- break;
- case 8: /* vrfin */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = rfin(vrs[vb].u[i]);
- break;
- case 9: /* vrfiz */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = rfiz(vrs[vb].u[i]);
- break;
- case 10: /* vrfip */
- for (i = 0; i < 4; ++i) {
- u32 x = vrs[vb].u[i];
- x = (x & 0x80000000)? rfiz(x): rfii(x);
- vrs[vd].u[i] = x;
- }
- break;
- case 11: /* vrfim */
- for (i = 0; i < 4; ++i) {
- u32 x = vrs[vb].u[i];
- x = (x & 0x80000000)? rfii(x): rfiz(x);
- vrs[vd].u[i] = x;
- }
- break;
- case 14: /* vctuxs */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = ctuxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
- break;
- case 15: /* vctsxs */
- for (i = 0; i < 4; ++i)
- vrs[vd].u[i] = ctsxs(vrs[vb].u[i], va,
- ¤t->thread.vscr.u[3]);
- break;
- default:
- return -EINVAL;
- }
- break;
- case 46: /* vmaddfp */
- vmaddfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
- break;
- case 47: /* vnmsubfp */
- vnmsubfp(&vrs[vd], &vrs[va], &vrs[vb], &vrs[vc]);
- break;
- default:
- return -EINVAL;
- }
-
- return 0;
-}
^ permalink raw reply
* [PATCH] powerpc: Merge include/asm-ppc*/a.out.h into include/asm-powerpc
From: Stephen Rothwell @ 2005-09-19 7:50 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
include/asm-powerpc/a.out.h | 36 ++++++++++++++++++++++++++++++++++++
include/asm-ppc/a.out.h | 26 --------------------------
include/asm-ppc64/a.out.h | 39 ---------------------------------------
3 files changed, 36 insertions(+), 65 deletions(-)
create mode 100644 include/asm-powerpc/a.out.h
delete mode 100644 include/asm-ppc/a.out.h
delete mode 100644 include/asm-ppc64/a.out.h
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
e4be8c960725725bccb547e84104e3fefca27f1
diff --git a/include/asm-powerpc/a.out.h b/include/asm-powerpc/a.out.h
new file mode 100644
--- /dev/null
+++ b/include/asm-powerpc/a.out.h
@@ -0,0 +1,36 @@
+#ifndef _ASM_POWERPC_A_OUT_H
+#define _ASM_POWERPC_A_OUT_H
+
+struct exec
+{
+ unsigned long a_info; /* Use macros N_MAGIC, etc for access */
+ unsigned a_text; /* length of text, in bytes */
+ unsigned a_data; /* length of data, in bytes */
+ unsigned a_bss; /* length of uninitialized data area for file, in bytes */
+ unsigned a_syms; /* length of symbol table data in file, in bytes */
+ unsigned a_entry; /* start address */
+ unsigned a_trsize; /* length of relocation info for text, in bytes */
+ unsigned a_drsize; /* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a) ((a).a_trsize)
+#define N_DRSIZE(a) ((a).a_drsize)
+#define N_SYMSIZE(a) ((a).a_syms)
+
+#ifdef __KERNEL__
+#ifdef __powerpc64__
+
+#define STACK_TOP_USER64 TASK_SIZE_USER64
+#define STACK_TOP_USER32 TASK_SIZE_USER32
+
+#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
+ STACK_TOP_USER32 : STACK_TOP_USER64)
+
+#else /* __powerpc64__ */
+
+#define STACK_TOP TASK_SIZE
+
+#endif /* __powerpc64__ */
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_POWERPC_A_OUT_H */
diff --git a/include/asm-ppc/a.out.h b/include/asm-ppc/a.out.h
deleted file mode 100644
--- a/include/asm-ppc/a.out.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef __PPC_A_OUT_H__
-#define __PPC_A_OUT_H__
-
-/* grabbed from the intel stuff */
-#define STACK_TOP TASK_SIZE
-
-
-struct exec
-{
- unsigned long a_info; /* Use macros N_MAGIC, etc for access */
- unsigned a_text; /* length of text, in bytes */
- unsigned a_data; /* length of data, in bytes */
- unsigned a_bss; /* length of uninitialized data area for file, in bytes */
- unsigned a_syms; /* length of symbol table data in file, in bytes */
- unsigned a_entry; /* start address */
- unsigned a_trsize; /* length of relocation info for text, in bytes */
- unsigned a_drsize; /* length of relocation info for data, in bytes */
-};
-
-
-#define N_TRSIZE(a) ((a).a_trsize)
-#define N_DRSIZE(a) ((a).a_drsize)
-#define N_SYMSIZE(a) ((a).a_syms)
-
-
-#endif
diff --git a/include/asm-ppc64/a.out.h b/include/asm-ppc64/a.out.h
deleted file mode 100644
--- a/include/asm-ppc64/a.out.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef __PPC64_A_OUT_H__
-#define __PPC64_A_OUT_H__
-
-/*
- * c 2001 PPC 64 Team, IBM Corp
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-struct exec
-{
- unsigned long a_info; /* Use macros N_MAGIC, etc for access */
- unsigned a_text; /* length of text, in bytes */
- unsigned a_data; /* length of data, in bytes */
- unsigned a_bss; /* length of uninitialized data area for file, in bytes */
- unsigned a_syms; /* length of symbol table data in file, in bytes */
- unsigned a_entry; /* start address */
- unsigned a_trsize; /* length of relocation info for text, in bytes */
- unsigned a_drsize; /* length of relocation info for data, in bytes */
-};
-
-#define N_TRSIZE(a) ((a).a_trsize)
-#define N_DRSIZE(a) ((a).a_drsize)
-#define N_SYMSIZE(a) ((a).a_syms)
-
-#ifdef __KERNEL__
-
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#define STACK_TOP_USER32 TASK_SIZE_USER32
-
-#define STACK_TOP (test_thread_flag(TIF_32BIT) ? \
- STACK_TOP_USER32 : STACK_TOP_USER64)
-
-#endif /* __KERNEL__ */
-
-#endif /* __PPC64_A_OUT_H__ */
^ permalink raw reply
* ATI Radeon M6-C16h for PPC 440GX
From: Roberto Pavon Sierra @ 2005-09-19 8:56 UTC (permalink / raw)
To: linuxppc-embedded
Hello,
i´m using on my custom board with PPC 440GX a ATI M6 Mobility Radeon with
kernel 2.6.12.
Now i have to initialize the ati and configure the kernel to support it.
I don´t have the BIOS of ATI for PPC and i like to simulate this BIOS with
U-boot. How can i configure the U-boot for ATI to initialize or how can i
write the programm for ATI- EEPROM BIOS?
must i install a XF86-Simulator on my board?
^ permalink raw reply
* Re: Reminder: removal of APUS and Gemini still pending
From: Christoph Hellwig @ 2005-09-19 9:10 UTC (permalink / raw)
To: Paul Mackerras; +Cc: ppc-dev list
In-Reply-To: <17197.58312.715169.991104@cargo.ozlabs.ibm.com>
On Mon, Sep 19, 2005 at 08:01:44AM +1000, Paul Mackerras wrote:
> That sounds like a mistake to me...
>
> > get proper changesets with attribution instead of a big patch (the plan
> > is to forward-merge the changes until after the transition, then turn
> > them back into a diff and apply them step by step).
>
> One of the things I particularly want to do is to remove the special
> cases in the virtual<->physical address translations for APUS.
> Perhaps the sparsemem or discontigmem code could be used instead?
The apus codedrop Sven put into the Debian Kernel SVN repo has this
removed, see:
http://svn.debian.org/wsvn/kernel/dists/trunk/linux-2.6/debian/patches-debian/powerpc-apus.patch?op=file&rev=0&sc=0
even if apus folks don't want to merge now all the core touching parts
of that patch should go in as they clanup the ifdef APUS mess quite a
lot.
^ permalink raw reply
* ATI Radeon M6-C16h for PPC 440GX
From: Roberto Pavon Sierra @ 2005-09-19 9:17 UTC (permalink / raw)
To: linuxppc-dev
Hello,
i´m using on my custom board with PPC 440GX a ATI M6 Mobility Radeon with
kernel 2.6.12.
Now i have to initialize the ati and configure the kernel to support it.
I don´t have the BIOS of ATI for PPC and i like to simulate this BIOS with
U-boot. How can i configure the U-boot for ATI to initialize or how can i
write the programm for ATI- EEPROM BIOS?
must i install a XF86-Simulator on my board?
Yours sincerely,
Roberto Pavon
^ permalink raw reply
* kernel 2.6.12.2, octobus ppc405EP: GUNZIP ERROR - must RESET board to recover
From: Peter Fercher @ 2005-09-19 9:16 UTC (permalink / raw)
To: linux-ppc-embedded
hi,
trying to run a 2.6.12.2 on a octubus board i get.. (console print =
follows)
U-Boot 1.1.0 (May 11 2004 - 12:01:24)
=20
CPU: IBM PowerPC 405EP Rev. B at 133.333 MHz (PLB=3D133, OPB=3D66, =
EBC=3D33 MHz)
IIC Boot EEPROM disabled
PCI async ext clock used, internal PCI arbiter enabled
16 kB I-Cache 16 kB D-Cache
OCTOBUS Board: ### No HW ID - assuming OCTOBUS HPPC405
I2C: ready
DRAM: 32 MB
FLASH: 4 MB
Hit any key to stop autoboot: 0
ENET Speed is 100 Mbps - FULL duplex connection
BOOTP broadcast 1
TFTP from server 192.168.1.1; our IP address is 192.168.1.2
Filename 'uImage-2.6.12.2'.
Load address: 0x100000
Loading: =
#################################################################
=
#################################################################
##################################################
done
Bytes transferred =3D 919248 (e06d0 hex)
## Booting image at 00100000 ...
Image Name: Linux-2.6.12.2
Created: 2005-09-19 9:03:08 UTC
Image Type: PowerPC Linux Kernel Image (gzip compressed)
Data Size: 919184 Bytes =3D 897.6 kB
Load Address: 00000000
Entry Point: 00000000
Verifying Checksum ... OK
Uncompressing Kernel Image ... Error: inflate() returned -3
GUNZIP ERROR - must RESET board to recover.
any hints ?
cheers, peter
^ permalink raw reply
* Which way to store log in flash on mpc8xx?
From: David Jander @ 2005-09-19 9:55 UTC (permalink / raw)
To: linuxppc-embedded
Hi all,
I am looking for a reliable way to store logfiles in flash. The logfiles are
written by syslogd.
The problem is that I am running on a MPC8xx processor, and kernel 2.6 is not
quite there yet for that processor, so I have to stick with 2.4.
Kernel of choice seems to be denx linuxppc_2_4_devel, but I cannot trust the
version of jffs2 used in that kernel anymore. Somtimes gc.c crashes with a
BUG() in line 139, and sometimes processes are frozen for a looong time
waiting for GC. I have debugged that problem a little bit, and definitely,
the FLASH access works ok, and the chip is new. No CRC- or read-errors, but
still gc.c crashes.
The version of mtd/jffs2 drivers in that kernel seem to be from march/2005 cvs
code, but when I read the following, I get even more scared:
http://www.linux-mtd.infradead.org/source.html#kernelversions
So, I need something different. jffs (1) maybe ?
This must be a very common task (to store logfiles in flash), but I just can't
seem to find the right way to do it.
Any advice is highly appreciated.
Sincerely,
--
David Jander
Protonic Holland.
^ permalink raw reply
* Re: [PATCH] ppc32: cleanup AMCC PPC4xx eval boards to better support U-Boot
From: Stefan Roese @ 2005-09-19 11:02 UTC (permalink / raw)
To: linuxppc-embedded
In-Reply-To: <20050916162733.GA8019@gate.ebshome.net>
Hi Eugene,
On Friday 16 September 2005 18:27, Eugene Surovegin wrote:
> On Fri, Sep 16, 2005 at 01:06:16PM +0200, Stefan Roese wrote:
> > Add U-Boot support to AMCC PPC405 eval boards (bubinga, sycamore and
> > walnut) and cleanup PPC440 eval boards (bamboo, ebony, luan and ocotea)
> > to better support U-Boot as bootloader.
>
> In general, 44x pieces look OK, but 40x aren't. Notice, that we don't
> have any #ifdef CONFIG_UBOOT in 44x sources. Let's not add them for
> 40x, try to replicate the same boot-wrapper approach as Matt used for
> 44x.
OK. I'll split the patch in two (44x and 40x stuff) so we can get the 44x
pieces on the way.
Just to be sure: The 44x boot-wrapper approach you mention is
"boot/simple/pibs.c"?
<snip>
> [snip]
>
> > --- a/arch/ppc/platforms/4xx/bubinga.c
> > +++ b/arch/ppc/platforms/4xx/bubinga.c
> > @@ -89,7 +89,11 @@ bubinga_early_serial_map(void)
> > * by 16.
> > */
> > uart_div = (mfdcr(DCRN_CPC0_UCR_BASE) & DCRN_CPC0_UCR_U0DIV);
> > +#ifdef CONFIG_UBOOT
> > + uart_clock = __res.bi_procfreq / uart_div;
> > +#else
> > uart_clock = __res.bi_pllouta_freq / uart_div;
> > +#endif
>
> Why not just rename this field and skip this ugly ifdefing?
That's better. Will be updated in next try.
Best regards,
Stefan
^ permalink raw reply
* [PATCH] ppc32: cleanup AMCC PPC44x eval boards to better support U-Boot
From: Stefan Roese @ 2005-09-19 11:20 UTC (permalink / raw)
To: linuxppc-embedded
In-Reply-To: <20050915092555.A27452@cox.net>
[-- Attachment #1: Type: text/plain, Size: 164 bytes --]
Cleanup PPC440 eval boards (bamboo, ebony, luan and ocotea) to better
support U-Boot as bootloader.
Signed-off-by: Stefan Roese <sr@denx.de>
Best regards,
Stefan
[-- Attachment #2: ppc44x_u-boot.patch --]
[-- Type: text/x-diff, Size: 6951 bytes --]
[PATCH] ppc32: cleanup AMCC PPC44x eval boards to better support U-Boot
Cleanup PPC440 eval boards (bamboo, ebony, luan and ocotea) to better
support U-Boot as bootloader.
Signed-off-by: Stefan Roese <sr@denx.de>
---
commit bd7c0c4a9e3dac8549cc0c557ab809d4d0785005
tree cb6578ee063c0975a1e951785d6ab18c921d8e62
parent d8ac10639b6a1ed900efbee38c18baaca31e64dc
author Stefan Roese <sr@denx.de> Mon, 19 Sep 2005 13:11:52 +0200
committer Stefan Roese <sr@denx.de> Mon, 19 Sep 2005 13:11:52 +0200
arch/ppc/platforms/4xx/bamboo.c | 14 ++------------
arch/ppc/platforms/4xx/ebony.c | 13 ++-----------
arch/ppc/platforms/4xx/luan.c | 13 ++-----------
arch/ppc/platforms/4xx/ocotea.c | 31 +++++++++++--------------------
arch/ppc/syslib/ibm44x_common.c | 35 ++++++++++++++++++++++++++++++++++-
arch/ppc/syslib/ibm44x_common.h | 3 ++-
6 files changed, 53 insertions(+), 56 deletions(-)
diff --git a/arch/ppc/platforms/4xx/bamboo.c b/arch/ppc/platforms/4xx/bamboo.c
--- a/arch/ppc/platforms/4xx/bamboo.c
+++ b/arch/ppc/platforms/4xx/bamboo.c
@@ -52,7 +52,7 @@
#include <syslib/gen550.h>
#include <syslib/ibm440gx_common.h>
-bd_t __res;
+extern bd_t __res;
static struct ibm44x_clocks clocks __initdata;
@@ -426,17 +426,7 @@ bamboo_setup_arch(void)
void __init platform_init(unsigned long r3, unsigned long r4,
unsigned long r5, unsigned long r6, unsigned long r7)
{
- parse_bootinfo(find_bootinfo());
-
- /*
- * If we were passed in a board information, copy it into the
- * residual data area.
- */
- if (r3)
- __res = *(bd_t *)(r3 + KERNELBASE);
-
-
- ibm44x_platform_init();
+ ibm44x_platform_init(r3, r4, r5, r6, r7);
ppc_md.setup_arch = bamboo_setup_arch;
ppc_md.show_cpuinfo = bamboo_show_cpuinfo;
diff --git a/arch/ppc/platforms/4xx/ebony.c b/arch/ppc/platforms/4xx/ebony.c
--- a/arch/ppc/platforms/4xx/ebony.c
+++ b/arch/ppc/platforms/4xx/ebony.c
@@ -55,7 +55,7 @@
#include <syslib/gen550.h>
#include <syslib/ibm440gp_common.h>
-bd_t __res;
+extern bd_t __res;
static struct ibm44x_clocks clocks __initdata;
@@ -318,16 +318,7 @@ ebony_setup_arch(void)
void __init platform_init(unsigned long r3, unsigned long r4,
unsigned long r5, unsigned long r6, unsigned long r7)
{
- parse_bootinfo(find_bootinfo());
-
- /*
- * If we were passed in a board information, copy it into the
- * residual data area.
- */
- if (r3)
- __res = *(bd_t *)(r3 + KERNELBASE);
-
- ibm44x_platform_init();
+ ibm44x_platform_init(r3, r4, r5, r6, r7);
ppc_md.setup_arch = ebony_setup_arch;
ppc_md.show_cpuinfo = ebony_show_cpuinfo;
diff --git a/arch/ppc/platforms/4xx/luan.c b/arch/ppc/platforms/4xx/luan.c
--- a/arch/ppc/platforms/4xx/luan.c
+++ b/arch/ppc/platforms/4xx/luan.c
@@ -53,7 +53,7 @@
#include <syslib/ibm440gx_common.h>
#include <syslib/ibm440sp_common.h>
-bd_t __res;
+extern bd_t __res;
static struct ibm44x_clocks clocks __initdata;
@@ -356,16 +356,7 @@ luan_setup_arch(void)
void __init platform_init(unsigned long r3, unsigned long r4,
unsigned long r5, unsigned long r6, unsigned long r7)
{
- parse_bootinfo(find_bootinfo());
-
- /*
- * If we were passed in a board information, copy it into the
- * residual data area.
- */
- if (r3)
- __res = *(bd_t *)(r3 + KERNELBASE);
-
- ibm44x_platform_init();
+ ibm44x_platform_init(r3, r4, r5, r6, r7);
ppc_md.setup_arch = luan_setup_arch;
ppc_md.show_cpuinfo = luan_show_cpuinfo;
diff --git a/arch/ppc/platforms/4xx/ocotea.c b/arch/ppc/platforms/4xx/ocotea.c
--- a/arch/ppc/platforms/4xx/ocotea.c
+++ b/arch/ppc/platforms/4xx/ocotea.c
@@ -53,7 +53,7 @@
#include <syslib/gen550.h>
#include <syslib/ibm440gx_common.h>
-bd_t __res;
+extern bd_t __res;
static struct ibm44x_clocks clocks __initdata;
@@ -287,6 +287,15 @@ ocotea_setup_arch(void)
ibm440gx_tah_enable();
+ /*
+ * Determine various clocks.
+ * To be completely correct we should get SysClk
+ * from FPGA, because it can be changed by on-board switches
+ * --ebs
+ */
+ ibm440gx_get_clocks(&clocks, 33333333, 6 * 1843200);
+ ocp_sys_info.opb_bus_freq = clocks.opb;
+
/* Setup TODC access */
TODC_INIT(TODC_TYPE_DS1743,
0,
@@ -325,25 +334,7 @@ static void __init ocotea_init(void)
void __init platform_init(unsigned long r3, unsigned long r4,
unsigned long r5, unsigned long r6, unsigned long r7)
{
- parse_bootinfo(find_bootinfo());
-
- /*
- * If we were passed in a board information, copy it into the
- * residual data area.
- */
- if (r3)
- __res = *(bd_t *)(r3 + KERNELBASE);
-
- /*
- * Determine various clocks.
- * To be completely correct we should get SysClk
- * from FPGA, because it can be changed by on-board switches
- * --ebs
- */
- ibm440gx_get_clocks(&clocks, 33333333, 6 * 1843200);
- ocp_sys_info.opb_bus_freq = clocks.opb;
-
- ibm44x_platform_init();
+ ibm44x_platform_init(r3, r4, r5, r6, r7);
ppc_md.setup_arch = ocotea_setup_arch;
ppc_md.show_cpuinfo = ocotea_show_cpuinfo;
diff --git a/arch/ppc/syslib/ibm44x_common.c b/arch/ppc/syslib/ibm44x_common.c
--- a/arch/ppc/syslib/ibm44x_common.c
+++ b/arch/ppc/syslib/ibm44x_common.c
@@ -27,9 +27,14 @@
#include <asm/time.h>
#include <asm/ppc4xx_pic.h>
#include <asm/param.h>
+#include <asm/bootinfo.h>
+#include <asm/ppcboot.h>
#include <syslib/gen550.h>
+/* Global Variables */
+bd_t __res;
+
phys_addr_t fixup_bigphys_addr(phys_addr_t addr, phys_addr_t size)
{
phys_addr_t page_4gb = 0;
@@ -150,8 +155,36 @@ static unsigned long __init ibm44x_find_
return mem_size;
}
-void __init ibm44x_platform_init(void)
+void __init ibm44x_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+ unsigned long r6, unsigned long r7)
{
+ parse_bootinfo(find_bootinfo());
+
+ /*
+ * If we were passed in a board information, copy it into the
+ * residual data area.
+ */
+ if (r3)
+ __res = *(bd_t *)(r3 + KERNELBASE);
+
+#if defined(CONFIG_BLK_DEV_INITRD)
+ /*
+ * If the init RAM disk has been configured in, and there's a valid
+ * starting address for it, set it up.
+ */
+ if (r4) {
+ initrd_start = r4 + KERNELBASE;
+ initrd_end = r5 + KERNELBASE;
+ }
+#endif /* CONFIG_BLK_DEV_INITRD */
+
+ /* Copy the kernel command line arguments to a safe place. */
+
+ if (r6) {
+ *(char *) (r7 + KERNELBASE) = 0;
+ strcpy(cmd_line, (char *) (r6 + KERNELBASE));
+ }
+
ppc_md.init_IRQ = ppc4xx_pic_init;
ppc_md.find_end_of_memory = ibm44x_find_end_of_memory;
ppc_md.restart = ibm44x_restart;
diff --git a/arch/ppc/syslib/ibm44x_common.h b/arch/ppc/syslib/ibm44x_common.h
--- a/arch/ppc/syslib/ibm44x_common.h
+++ b/arch/ppc/syslib/ibm44x_common.h
@@ -36,7 +36,8 @@ struct ibm44x_clocks {
};
/* common 44x platform init */
-void ibm44x_platform_init(void) __init;
+void ibm44x_platform_init(unsigned long r3, unsigned long r4, unsigned long r5,
+ unsigned long r6, unsigned long r7) __init;
/* initialize decrementer and tick-related variables */
void ibm44x_calibrate_decr(unsigned int freq) __init;
^ permalink raw reply
* Re: ATI Radeon M6-C16h for PPC 440GX
From: Simon Richter @ 2005-09-19 12:06 UTC (permalink / raw)
To: Roberto Pavon Sierra; +Cc: linuxppc-dev
In-Reply-To: <000501c5bcfa$e70dbbd0$8700a8c0@SN7855>
[-- Attachment #1: Type: text/plain, Size: 191 bytes --]
Hi,
Roberto Pavon Sierra wrote:
> must i install a XF86-Simulator on my board?
Yes. ATI's init code is handwritten x86 assembler and comes with a
license to use verbatim only.
Simon
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 307 bytes --]
^ permalink raw reply
* [PATCH 0/6] powerpc: merge arch/ppc*/oprofile directories
From: Stephen Rothwell @ 2005-09-19 13:10 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
This series of patches merge the arch/ppc*/oprofile directories into arch/powerpc.
arch/powerpc/oprofile/Kconfig | 23 ++
arch/powerpc/oprofile/Makefile | 11 +
arch/powerpc/oprofile/common.c | 227 +++++++++++++++++++--
arch/powerpc/oprofile/op_model_fsl_booke.c | 183 +++++++++++++++++
arch/powerpc/oprofile/op_model_power4.c | 309 ++++++++++++++++++++++++++++
arch/powerpc/oprofile/op_model_rs64.c | 218 ++++++++++++++++++++
arch/ppc/Kconfig | 2
arch/ppc/Makefile | 2
arch/ppc/kernel/perfmon.c | 10
arch/ppc/oprofile/Kconfig | 23 --
arch/ppc/oprofile/Makefile | 16 -
arch/ppc/oprofile/common.c | 165 ---------------
arch/ppc/oprofile/op_impl.h | 47 ----
arch/ppc/oprofile/op_model_fsl_booke.c | 188 -----------------
arch/ppc64/Kconfig | 2
arch/ppc64/Makefile | 2
arch/ppc64/oprofile/Kconfig | 23 --
arch/ppc64/oprofile/Makefile | 11 -
arch/ppc64/oprofile/common.c | 147 -------------
arch/ppc64/oprofile/op_model_power4.c | 311 -----------------------------
arch/ppc64/oprofile/op_model_rs64.c | 220 --------------------
include/asm-powerpc/oprofile_impl.h | 123 +++++++++++
include/asm-ppc/perfmon.h | 6
include/asm-ppc64/cputable.h | 4
include/asm-ppc64/oprofile_impl.h | 121 -----------
25 files changed, 1108 insertions(+), 1286 deletions(-)
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
^ permalink raw reply
* [PATCH 1/6] powerpc: Move arch/ppc*/oprofile/Kconfig to arch/powerpc
From: Stephen Rothwell @ 2005-09-19 13:13 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
These files are identical.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/powerpc/oprofile/Kconfig | 23 +++++++++++++++++++++++
arch/ppc/Kconfig | 2 +-
arch/ppc/oprofile/Kconfig | 23 -----------------------
arch/ppc64/Kconfig | 2 +-
arch/ppc64/oprofile/Kconfig | 23 -----------------------
5 files changed, 25 insertions(+), 48 deletions(-)
create mode 100644 arch/powerpc/oprofile/Kconfig
delete mode 100644 arch/ppc/oprofile/Kconfig
delete mode 100644 arch/ppc64/oprofile/Kconfig
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
51b2e663af2bae454a5e4737dfb0b7e0c4898b2f
diff --git a/arch/powerpc/oprofile/Kconfig b/arch/powerpc/oprofile/Kconfig
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/Kconfig
@@ -0,0 +1,23 @@
+
+menu "Profiling support"
+ depends on EXPERIMENTAL
+
+config PROFILING
+ bool "Profiling support (EXPERIMENTAL)"
+ help
+ Say Y here to enable the extended profiling support mechanisms used
+ by profilers such as OProfile.
+
+
+config OPROFILE
+ tristate "OProfile system profiling (EXPERIMENTAL)"
+ depends on PROFILING
+ help
+ OProfile is a profiling system capable of profiling the
+ whole system, include the kernel, kernel modules, libraries,
+ and applications.
+
+ If unsure, say N.
+
+endmenu
+
diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -1370,7 +1370,7 @@ endmenu
source "lib/Kconfig"
-source "arch/ppc/oprofile/Kconfig"
+source "arch/powerpc/oprofile/Kconfig"
source "arch/ppc/Kconfig.debug"
diff --git a/arch/ppc/oprofile/Kconfig b/arch/ppc/oprofile/Kconfig
deleted file mode 100644
--- a/arch/ppc/oprofile/Kconfig
+++ /dev/null
@@ -1,23 +0,0 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
-config PROFILING
- bool "Profiling support (EXPERIMENTAL)"
- help
- Say Y here to enable the extended profiling support mechanisms used
- by profilers such as OProfile.
-
-
-config OPROFILE
- tristate "OProfile system profiling (EXPERIMENTAL)"
- depends on PROFILING
- help
- OProfile is a profiling system capable of profiling the
- whole system, include the kernel, kernel modules, libraries,
- and applications.
-
- If unsure, say N.
-
-endmenu
-
diff --git a/arch/ppc64/Kconfig b/arch/ppc64/Kconfig
--- a/arch/ppc64/Kconfig
+++ b/arch/ppc64/Kconfig
@@ -461,7 +461,7 @@ config VIOPATH
depends on VIOCONS || VIODASD || VIOCD || VIOTAPE || VETH
default y
-source "arch/ppc64/oprofile/Kconfig"
+source "arch/powerpc/oprofile/Kconfig"
source "arch/ppc64/Kconfig.debug"
diff --git a/arch/ppc64/oprofile/Kconfig b/arch/ppc64/oprofile/Kconfig
deleted file mode 100644
--- a/arch/ppc64/oprofile/Kconfig
+++ /dev/null
@@ -1,23 +0,0 @@
-
-menu "Profiling support"
- depends on EXPERIMENTAL
-
-config PROFILING
- bool "Profiling support (EXPERIMENTAL)"
- help
- Say Y here to enable the extended profiling support mechanisms used
- by profilers such as OProfile.
-
-
-config OPROFILE
- tristate "OProfile system profiling (EXPERIMENTAL)"
- depends on PROFILING
- help
- OProfile is a profiling system capable of profiling the
- whole system, include the kernel, kernel modules, libraries,
- and applications.
-
- If unsure, say N.
-
-endmenu
-
^ permalink raw reply
* [PATCH 2/6] Merge arch/ppc*/oprofile/Makefile into arch/powerpc/oprofile
From: Stephen Rothwell @ 2005-09-19 13:15 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/powerpc/oprofile/Makefile | 11 +++++++++++
arch/ppc/oprofile/Makefile | 15 +--------------
arch/ppc64/oprofile/Makefile | 10 +---------
3 files changed, 13 insertions(+), 23 deletions(-)
create mode 100644 arch/powerpc/oprofile/Makefile
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
03447d2b4ddb0a51f7316c32c280dbc497ce8d83
diff --git a/arch/powerpc/oprofile/Makefile b/arch/powerpc/oprofile/Makefile
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/Makefile
@@ -0,0 +1,11 @@
+obj-$(CONFIG_OPROFILE) += oprofile.o
+
+DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
+ oprof.o cpu_buffer.o buffer_sync.o \
+ event_buffer.o oprofile_files.o \
+ oprofilefs.o oprofile_stats.o \
+ timer_int.o )
+
+oprofile-y := $(DRIVER_OBJS) common.o
+oprofile-$(CONFIG_PPC64) += op_model_rs64.o op_model_power4.o
+oprofile-$(CONFIG_FSL_BOOKE) += op_model_fsl_booke.o
diff --git a/arch/ppc/oprofile/Makefile b/arch/ppc/oprofile/Makefile
--- a/arch/ppc/oprofile/Makefile
+++ b/arch/ppc/oprofile/Makefile
@@ -1,14 +1 @@
-obj-$(CONFIG_OPROFILE) += oprofile.o
-
-DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
- oprof.o cpu_buffer.o buffer_sync.o \
- event_buffer.o oprofile_files.o \
- oprofilefs.o oprofile_stats.o \
- timer_int.o )
-
-oprofile-y := $(DRIVER_OBJS) common.o
-
-ifeq ($(CONFIG_FSL_BOOKE),y)
- oprofile-y += op_model_fsl_booke.o
-endif
-
+include arch/powerpc/oprofile/Makefile
diff --git a/arch/ppc64/oprofile/Makefile b/arch/ppc64/oprofile/Makefile
--- a/arch/ppc64/oprofile/Makefile
+++ b/arch/ppc64/oprofile/Makefile
@@ -1,9 +1 @@
-obj-$(CONFIG_OPROFILE) += oprofile.o
-
-DRIVER_OBJS := $(addprefix ../../../drivers/oprofile/, \
- oprof.o cpu_buffer.o buffer_sync.o \
- event_buffer.o oprofile_files.o \
- oprofilefs.o oprofile_stats.o \
- timer_int.o )
-
-oprofile-y := $(DRIVER_OBJS) common.o op_model_rs64.o op_model_power4.o
+include arch/powerpc/oprofile/Makefile
^ permalink raw reply
* [PATCH 3/6] powerpc: rename op_ppc{32, 64}_model to op_powerpc_model
From: Stephen Rothwell @ 2005-09-19 13:18 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/ppc/oprofile/common.c | 2 +-
arch/ppc/oprofile/op_impl.h | 2 +-
arch/ppc/oprofile/op_model_fsl_booke.c | 2 +-
arch/ppc64/oprofile/common.c | 2 +-
arch/ppc64/oprofile/op_model_power4.c | 2 +-
arch/ppc64/oprofile/op_model_rs64.c | 2 +-
include/asm-ppc/perfmon.h | 2 +-
include/asm-ppc64/cputable.h | 4 ++--
include/asm-ppc64/oprofile_impl.h | 6 +++---
9 files changed, 12 insertions(+), 12 deletions(-)
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
2be7f59a0dbd2d2b0eb48384c64977980cca061e
diff --git a/arch/ppc/oprofile/common.c b/arch/ppc/oprofile/common.c
--- a/arch/ppc/oprofile/common.c
+++ b/arch/ppc/oprofile/common.c
@@ -25,7 +25,7 @@
#include "op_impl.h"
-static struct op_ppc32_model *model;
+static struct op_powerpc_model *model;
static struct op_counter_config ctr[OP_MAX_COUNTER];
static struct op_system_config sys;
diff --git a/arch/ppc/oprofile/op_impl.h b/arch/ppc/oprofile/op_impl.h
--- a/arch/ppc/oprofile/op_impl.h
+++ b/arch/ppc/oprofile/op_impl.h
@@ -31,7 +31,7 @@ struct op_system_config {
};
/* Per-arch configuration */
-struct op_ppc32_model {
+struct op_powerpc_model {
void (*reg_setup) (struct op_counter_config *,
struct op_system_config *,
int num_counters);
diff --git a/arch/ppc/oprofile/op_model_fsl_booke.c b/arch/ppc/oprofile/op_model_fsl_booke.c
--- a/arch/ppc/oprofile/op_model_fsl_booke.c
+++ b/arch/ppc/oprofile/op_model_fsl_booke.c
@@ -176,7 +176,7 @@ static void fsl_booke_handle_interrupt(s
pmc_start_ctrs(1);
}
-struct op_ppc32_model op_model_fsl_booke = {
+struct op_powerpc_model op_model_fsl_booke = {
.reg_setup = fsl_booke_reg_setup,
.start = fsl_booke_start,
.stop = fsl_booke_stop,
diff --git a/arch/ppc64/oprofile/common.c b/arch/ppc64/oprofile/common.c
--- a/arch/ppc64/oprofile/common.c
+++ b/arch/ppc64/oprofile/common.c
@@ -19,7 +19,7 @@
#include <asm/cputable.h>
#include <asm/oprofile_impl.h>
-static struct op_ppc64_model *model;
+static struct op_powerpc_model *model;
static struct op_counter_config ctr[OP_MAX_COUNTER];
static struct op_system_config sys;
diff --git a/arch/ppc64/oprofile/op_model_power4.c b/arch/ppc64/oprofile/op_model_power4.c
--- a/arch/ppc64/oprofile/op_model_power4.c
+++ b/arch/ppc64/oprofile/op_model_power4.c
@@ -300,7 +300,7 @@ static void power4_handle_interrupt(stru
mtspr(SPRN_MMCR0, mmcr0);
}
-struct op_ppc64_model op_model_power4 = {
+struct op_powerpc_model op_model_power4 = {
.reg_setup = power4_reg_setup,
.cpu_setup = power4_cpu_setup,
.start = power4_start,
diff --git a/arch/ppc64/oprofile/op_model_rs64.c b/arch/ppc64/oprofile/op_model_rs64.c
--- a/arch/ppc64/oprofile/op_model_rs64.c
+++ b/arch/ppc64/oprofile/op_model_rs64.c
@@ -209,7 +209,7 @@ static void rs64_handle_interrupt(struct
mtspr(SPRN_MMCR0, mmcr0);
}
-struct op_ppc64_model op_model_rs64 = {
+struct op_powerpc_model op_model_rs64 = {
.reg_setup = rs64_reg_setup,
.cpu_setup = rs64_cpu_setup,
.start = rs64_start,
diff --git a/include/asm-ppc/perfmon.h b/include/asm-ppc/perfmon.h
--- a/include/asm-ppc/perfmon.h
+++ b/include/asm-ppc/perfmon.h
@@ -16,7 +16,7 @@ void pmc_start_ctrs(int enable);
void pmc_stop_ctrs(void);
void dump_pmcs(void);
-extern struct op_ppc32_model op_model_fsl_booke;
+extern struct op_powerpc_model op_model_fsl_booke;
#endif
#endif /* __PERFMON_H */
diff --git a/include/asm-ppc64/cputable.h b/include/asm-ppc64/cputable.h
--- a/include/asm-ppc64/cputable.h
+++ b/include/asm-ppc64/cputable.h
@@ -36,7 +36,7 @@
* via the mkdefs mechanism.
*/
struct cpu_spec;
-struct op_ppc64_model;
+struct op_powerpc_model;
typedef void (*cpu_setup_t)(unsigned long offset, struct cpu_spec* spec);
@@ -65,7 +65,7 @@ struct cpu_spec {
char *oprofile_cpu_type;
/* Processor specific oprofile operations */
- struct op_ppc64_model *oprofile_model;
+ struct op_powerpc_model *oprofile_model;
};
extern struct cpu_spec cpu_specs[];
diff --git a/include/asm-ppc64/oprofile_impl.h b/include/asm-ppc64/oprofile_impl.h
--- a/include/asm-ppc64/oprofile_impl.h
+++ b/include/asm-ppc64/oprofile_impl.h
@@ -37,7 +37,7 @@ struct op_system_config {
};
/* Per-arch configuration */
-struct op_ppc64_model {
+struct op_powerpc_model {
void (*reg_setup) (struct op_counter_config *,
struct op_system_config *,
int num_counters);
@@ -49,8 +49,8 @@ struct op_ppc64_model {
int num_counters;
};
-extern struct op_ppc64_model op_model_rs64;
-extern struct op_ppc64_model op_model_power4;
+extern struct op_powerpc_model op_model_rs64;
+extern struct op_powerpc_model op_model_power4;
static inline unsigned int ctr_read(unsigned int i)
{
^ permalink raw reply
* [PATCH 4/6] powerpc: merge oprofile headers
From: Stephen Rothwell @ 2005-09-19 13:21 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
Merge include/asm-ppc64/oprofile_ipml.h and arch/ppc/oprofile/op_impl.h
into include/asm-powerpc/oprofile_ipml.h
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/ppc/oprofile/common.c | 3 -
arch/ppc/oprofile/op_impl.h | 45 ------------
arch/ppc/oprofile/op_model_fsl_booke.c | 3 -
include/asm-powerpc/oprofile_impl.h | 123 ++++++++++++++++++++++++++++++++
include/asm-ppc64/oprofile_impl.h | 111 -----------------------------
5 files changed, 125 insertions(+), 160 deletions(-)
delete mode 100644 arch/ppc/oprofile/op_impl.h
create mode 100644 include/asm-powerpc/oprofile_impl.h
delete mode 100644 include/asm-ppc64/oprofile_impl.h
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
9f08e21e6ba1a97e62f77066ac8c915149908223
diff --git a/arch/ppc/oprofile/common.c b/arch/ppc/oprofile/common.c
--- a/arch/ppc/oprofile/common.c
+++ b/arch/ppc/oprofile/common.c
@@ -22,8 +22,7 @@
#include <asm/system.h>
#include <asm/perfmon.h>
#include <asm/cputable.h>
-
-#include "op_impl.h"
+#include <asm/oprofile_impl.h>
static struct op_powerpc_model *model;
diff --git a/arch/ppc/oprofile/op_impl.h b/arch/ppc/oprofile/op_impl.h
deleted file mode 100644
--- a/arch/ppc/oprofile/op_impl.h
+++ /dev/null
@@ -1,45 +0,0 @@
-/*
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * Based on alpha version.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef OP_IMPL_H
-#define OP_IMPL_H 1
-
-#define OP_MAX_COUNTER 8
-
-/* Per-counter configuration as set via oprofilefs. */
-struct op_counter_config {
- unsigned long enabled;
- unsigned long event;
- unsigned long count;
- unsigned long kernel;
- unsigned long user;
- unsigned long unit_mask;
-};
-
-/* System-wide configuration as set via oprofilefs. */
-struct op_system_config {
- unsigned long enable_kernel;
- unsigned long enable_user;
-};
-
-/* Per-arch configuration */
-struct op_powerpc_model {
- void (*reg_setup) (struct op_counter_config *,
- struct op_system_config *,
- int num_counters);
- void (*start) (struct op_counter_config *);
- void (*stop) (void);
- void (*handle_interrupt) (struct pt_regs *,
- struct op_counter_config *);
- int num_counters;
-};
-
-#endif /* OP_IMPL_H */
diff --git a/arch/ppc/oprofile/op_model_fsl_booke.c b/arch/ppc/oprofile/op_model_fsl_booke.c
--- a/arch/ppc/oprofile/op_model_fsl_booke.c
+++ b/arch/ppc/oprofile/op_model_fsl_booke.c
@@ -25,8 +25,7 @@
#include <asm/reg_booke.h>
#include <asm/page.h>
#include <asm/perfmon.h>
-
-#include "op_impl.h"
+#include <asm/oprofile_impl.h>
static unsigned long reset_value[OP_MAX_COUNTER];
diff --git a/include/asm-powerpc/oprofile_impl.h b/include/asm-powerpc/oprofile_impl.h
new file mode 100644
--- /dev/null
+++ b/include/asm-powerpc/oprofile_impl.h
@@ -0,0 +1,123 @@
+/*
+ * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * Based on alpha version.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#ifndef _ASM_POWERPC_OPROFILE_IMPL_H
+#define _ASM_POWERPC_OPROFILE_IMPL_H
+
+#define OP_MAX_COUNTER 8
+
+/* Per-counter configuration as set via oprofilefs. */
+struct op_counter_config {
+#ifdef __powerpc64__
+ unsigned long valid;
+#endif
+ unsigned long enabled;
+ unsigned long event;
+ unsigned long count;
+ unsigned long kernel;
+#ifdef __powerpc64__
+ /* We dont support per counter user/kernel selection */
+#endif
+ unsigned long user;
+ unsigned long unit_mask;
+};
+
+/* System-wide configuration as set via oprofilefs. */
+struct op_system_config {
+#ifdef __powerpc64__
+ unsigned long mmcr0;
+ unsigned long mmcr1;
+ unsigned long mmcra;
+#endif
+ unsigned long enable_kernel;
+ unsigned long enable_user;
+#ifdef __powerpc64__
+ unsigned long backtrace_spinlocks;
+#endif
+};
+
+/* Per-arch configuration */
+struct op_powerpc_model {
+ void (*reg_setup) (struct op_counter_config *,
+ struct op_system_config *,
+ int num_counters);
+#ifdef __powerpc64__
+ void (*cpu_setup) (void *);
+#endif
+ void (*start) (struct op_counter_config *);
+ void (*stop) (void);
+ void (*handle_interrupt) (struct pt_regs *,
+ struct op_counter_config *);
+ int num_counters;
+};
+
+#ifdef __powerpc64__
+extern struct op_powerpc_model op_model_rs64;
+extern struct op_powerpc_model op_model_power4;
+
+static inline unsigned int ctr_read(unsigned int i)
+{
+ switch(i) {
+ case 0:
+ return mfspr(SPRN_PMC1);
+ case 1:
+ return mfspr(SPRN_PMC2);
+ case 2:
+ return mfspr(SPRN_PMC3);
+ case 3:
+ return mfspr(SPRN_PMC4);
+ case 4:
+ return mfspr(SPRN_PMC5);
+ case 5:
+ return mfspr(SPRN_PMC6);
+ case 6:
+ return mfspr(SPRN_PMC7);
+ case 7:
+ return mfspr(SPRN_PMC8);
+ default:
+ return 0;
+ }
+}
+
+static inline void ctr_write(unsigned int i, unsigned int val)
+{
+ switch(i) {
+ case 0:
+ mtspr(SPRN_PMC1, val);
+ break;
+ case 1:
+ mtspr(SPRN_PMC2, val);
+ break;
+ case 2:
+ mtspr(SPRN_PMC3, val);
+ break;
+ case 3:
+ mtspr(SPRN_PMC4, val);
+ break;
+ case 4:
+ mtspr(SPRN_PMC5, val);
+ break;
+ case 5:
+ mtspr(SPRN_PMC6, val);
+ break;
+ case 6:
+ mtspr(SPRN_PMC7, val);
+ break;
+ case 7:
+ mtspr(SPRN_PMC8, val);
+ break;
+ default:
+ break;
+ }
+}
+#endif /* __powerpc64__ */
+
+#endif /* _ASM_POWERPC_OPROFILE_IMPL_H */
diff --git a/include/asm-ppc64/oprofile_impl.h b/include/asm-ppc64/oprofile_impl.h
deleted file mode 100644
--- a/include/asm-ppc64/oprofile_impl.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * Based on alpha version.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#ifndef OP_IMPL_H
-#define OP_IMPL_H 1
-
-#define OP_MAX_COUNTER 8
-
-/* Per-counter configuration as set via oprofilefs. */
-struct op_counter_config {
- unsigned long valid;
- unsigned long enabled;
- unsigned long event;
- unsigned long count;
- unsigned long kernel;
- /* We dont support per counter user/kernel selection */
- unsigned long user;
- unsigned long unit_mask;
-};
-
-/* System-wide configuration as set via oprofilefs. */
-struct op_system_config {
- unsigned long mmcr0;
- unsigned long mmcr1;
- unsigned long mmcra;
- unsigned long enable_kernel;
- unsigned long enable_user;
- unsigned long backtrace_spinlocks;
-};
-
-/* Per-arch configuration */
-struct op_powerpc_model {
- void (*reg_setup) (struct op_counter_config *,
- struct op_system_config *,
- int num_counters);
- void (*cpu_setup) (void *);
- void (*start) (struct op_counter_config *);
- void (*stop) (void);
- void (*handle_interrupt) (struct pt_regs *,
- struct op_counter_config *);
- int num_counters;
-};
-
-extern struct op_powerpc_model op_model_rs64;
-extern struct op_powerpc_model op_model_power4;
-
-static inline unsigned int ctr_read(unsigned int i)
-{
- switch(i) {
- case 0:
- return mfspr(SPRN_PMC1);
- case 1:
- return mfspr(SPRN_PMC2);
- case 2:
- return mfspr(SPRN_PMC3);
- case 3:
- return mfspr(SPRN_PMC4);
- case 4:
- return mfspr(SPRN_PMC5);
- case 5:
- return mfspr(SPRN_PMC6);
- case 6:
- return mfspr(SPRN_PMC7);
- case 7:
- return mfspr(SPRN_PMC8);
- default:
- return 0;
- }
-}
-
-static inline void ctr_write(unsigned int i, unsigned int val)
-{
- switch(i) {
- case 0:
- mtspr(SPRN_PMC1, val);
- break;
- case 1:
- mtspr(SPRN_PMC2, val);
- break;
- case 2:
- mtspr(SPRN_PMC3, val);
- break;
- case 3:
- mtspr(SPRN_PMC4, val);
- break;
- case 4:
- mtspr(SPRN_PMC5, val);
- break;
- case 5:
- mtspr(SPRN_PMC6, val);
- break;
- case 6:
- mtspr(SPRN_PMC7, val);
- break;
- case 7:
- mtspr(SPRN_PMC8, val);
- break;
- default:
- break;
- }
-}
-
-#endif
^ permalink raw reply
* [PATCH 5/6] powerpc: merge the rest of arch/ppc*/oprofile
From: Stephen Rothwell @ 2005-09-19 13:24 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
- merge common.c
- move model specific files
- remove stub Makefiles
- clean up arch/ppc*/Makefile
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/powerpc/oprofile/common.c | 214 +++++++++++++++++++
arch/powerpc/oprofile/op_model_fsl_booke.c | 183 +++++++++++++++++
arch/powerpc/oprofile/op_model_power4.c | 309 ++++++++++++++++++++++++++++
arch/powerpc/oprofile/op_model_rs64.c | 218 ++++++++++++++++++++
arch/ppc/Makefile | 2
arch/ppc/oprofile/Makefile | 1
arch/ppc/oprofile/common.c | 160 --------------
arch/ppc/oprofile/op_model_fsl_booke.c | 183 -----------------
arch/ppc64/Makefile | 2
arch/ppc64/oprofile/Makefile | 1
arch/ppc64/oprofile/common.c | 145 -------------
arch/ppc64/oprofile/op_model_power4.c | 309 ----------------------------
arch/ppc64/oprofile/op_model_rs64.c | 218 --------------------
13 files changed, 926 insertions(+), 1019 deletions(-)
create mode 100644 arch/powerpc/oprofile/common.c
create mode 100644 arch/powerpc/oprofile/op_model_fsl_booke.c
create mode 100644 arch/powerpc/oprofile/op_model_power4.c
create mode 100644 arch/powerpc/oprofile/op_model_rs64.c
delete mode 100644 arch/ppc/oprofile/Makefile
delete mode 100644 arch/ppc/oprofile/common.c
delete mode 100644 arch/ppc/oprofile/op_model_fsl_booke.c
delete mode 100644 arch/ppc64/oprofile/Makefile
delete mode 100644 arch/ppc64/oprofile/common.c
delete mode 100644 arch/ppc64/oprofile/op_model_power4.c
delete mode 100644 arch/ppc64/oprofile/op_model_rs64.c
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
6dc3424cfdea7aedd29e9aad5eb93c84f922bdd1
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/common.c
@@ -0,0 +1,214 @@
+/*
+ * PPC 64 oprofile support:
+ * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
+ * PPC 32 oprofile support: (based on PPC 64 support)
+ * Copyright (C) Freescale Semiconductor, Inc 2004
+ * Author: Andy Fleming
+ *
+ * Based on alpha version.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/oprofile.h>
+#ifndef __powerpc64__
+#include <linux/slab.h>
+#endif /* ! __powerpc64__ */
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+#ifdef __powerpc64__
+#include <asm/pmc.h>
+#else /* __powerpc64__ */
+#include <asm/perfmon.h>
+#endif /* __powerpc64__ */
+#include <asm/cputable.h>
+#include <asm/oprofile_impl.h>
+
+static struct op_powerpc_model *model;
+
+static struct op_counter_config ctr[OP_MAX_COUNTER];
+static struct op_system_config sys;
+
+#ifndef __powerpc64__
+static char *cpu_type;
+#endif /* ! __powerpc64__ */
+
+static void op_handle_interrupt(struct pt_regs *regs)
+{
+ model->handle_interrupt(regs, ctr);
+}
+
+static int op_powerpc_setup(void)
+{
+#ifdef __powerpc64__
+ int err;
+
+ /* Grab the hardware */
+ err = reserve_pmc_hardware(op_handle_interrupt);
+ if (err)
+ return err;
+#else /* __powerpc64__ */
+ /* Install our interrupt handler into the existing hook. */
+ if (request_perfmon_irq(&op_handle_interrupt))
+ return -EBUSY;
+ mb();
+#endif /* __powerpc64__ */
+
+ /* Pre-compute the values to stuff in the hardware registers. */
+ model->reg_setup(ctr, &sys, model->num_counters);
+
+ /* Configure the registers on all cpus. */
+#ifdef __powerpc64__
+ on_each_cpu(model->cpu_setup, NULL, 0, 1);
+#else /* __powerpc64__ */
+#if 0
+ /* FIXME: Make multi-cpu work */
+ on_each_cpu(model->reg_setup, NULL, 0, 1);
+#endif
+#endif /* __powerpc64__ */
+
+ return 0;
+}
+
+static void op_powerpc_shutdown(void)
+{
+#ifdef __powerpc64__
+ release_pmc_hardware();
+#else /* __powerpc64__ */
+ mb();
+ /* Remove our interrupt handler. We may be removing this module. */
+ free_perfmon_irq();
+#endif /* __powerpc64__ */
+}
+
+static void op_powerpc_cpu_start(void *dummy)
+{
+ model->start(ctr);
+}
+
+static int op_powerpc_start(void)
+{
+ on_each_cpu(op_powerpc_cpu_start, NULL, 0, 1);
+ return 0;
+}
+
+static inline void op_powerpc_cpu_stop(void *dummy)
+{
+ model->stop();
+}
+
+static void op_powerpc_stop(void)
+{
+ on_each_cpu(op_powerpc_cpu_stop, NULL, 0, 1);
+}
+
+static int op_powerpc_create_files(struct super_block *sb, struct dentry *root)
+{
+ int i;
+
+#ifdef __powerpc64__
+ /*
+ * There is one mmcr0, mmcr1 and mmcra for setting the events for
+ * all of the counters.
+ */
+ oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0);
+ oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1);
+ oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra);
+#endif /* __powerpc64__ */
+
+ for (i = 0; i < model->num_counters; ++i) {
+ struct dentry *dir;
+ char buf[3];
+
+ snprintf(buf, sizeof buf, "%d", i);
+ dir = oprofilefs_mkdir(sb, root, buf);
+
+ oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
+ oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
+ oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
+#ifdef __powerpc64__
+ /*
+ * We dont support per counter user/kernel selection, but
+ * we leave the entries because userspace expects them
+ */
+#endif /* __powerpc64__ */
+ oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
+ oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
+
+#ifndef __powerpc64__
+ /* FIXME: Not sure if this is used */
+#endif /* ! __powerpc64__ */
+ oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
+ }
+
+ oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
+ oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
+#ifdef __powerpc64__
+ oprofilefs_create_ulong(sb, root, "backtrace_spinlocks",
+ &sys.backtrace_spinlocks);
+#endif /* __powerpc64__ */
+
+ /* Default to tracing both kernel and user */
+ sys.enable_kernel = 1;
+ sys.enable_user = 1;
+#ifdef __powerpc64__
+ /* Turn on backtracing through spinlocks by default */
+ sys.backtrace_spinlocks = 1;
+#endif /* __powerpc64__ */
+
+ return 0;
+}
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+#ifndef __powerpc64__
+ int cpu_id = smp_processor_id();
+
+#ifdef CONFIG_FSL_BOOKE
+ model = &op_model_fsl_booke;
+#else
+ return -ENODEV;
+#endif
+
+ cpu_type = kmalloc(32, GFP_KERNEL);
+ if (NULL == cpu_type)
+ return -ENOMEM;
+
+ sprintf(cpu_type, "ppc/%s", cur_cpu_spec[cpu_id]->cpu_name);
+
+ model->num_counters = cur_cpu_spec[cpu_id]->num_pmcs;
+
+ ops->cpu_type = cpu_type;
+#else /* __powerpc64__ */
+ if (!cur_cpu_spec->oprofile_model || !cur_cpu_spec->oprofile_cpu_type)
+ return -ENODEV;
+ model = cur_cpu_spec->oprofile_model;
+ model->num_counters = cur_cpu_spec->num_pmcs;
+
+ ops->cpu_type = cur_cpu_spec->oprofile_cpu_type;
+#endif /* __powerpc64__ */
+ ops->create_files = op_powerpc_create_files;
+ ops->setup = op_powerpc_setup;
+ ops->shutdown = op_powerpc_shutdown;
+ ops->start = op_powerpc_start;
+ ops->stop = op_powerpc_stop;
+
+ printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
+ ops->cpu_type);
+
+ return 0;
+}
+
+void oprofile_arch_exit(void)
+{
+#ifndef __powerpc64__
+ kfree(cpu_type);
+ cpu_type = NULL;
+#endif /* ! __powerpc64__ */
+}
diff --git a/arch/powerpc/oprofile/op_model_fsl_booke.c b/arch/powerpc/oprofile/op_model_fsl_booke.c
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/op_model_fsl_booke.c
@@ -0,0 +1,183 @@
+/*
+ * oprofile/op_model_e500.c
+ *
+ * Freescale Book-E oprofile support, based on ppc64 oprofile support
+ * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * Copyright (c) 2004 Freescale Semiconductor, Inc
+ *
+ * Author: Andy Fleming
+ * Maintainer: Kumar Gala <Kumar.Gala@freescale.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/reg_booke.h>
+#include <asm/page.h>
+#include <asm/perfmon.h>
+#include <asm/oprofile_impl.h>
+
+static unsigned long reset_value[OP_MAX_COUNTER];
+
+static int num_counters;
+static int oprofile_running;
+
+static inline unsigned int ctr_read(unsigned int i)
+{
+ switch(i) {
+ case 0:
+ return mfpmr(PMRN_PMC0);
+ case 1:
+ return mfpmr(PMRN_PMC1);
+ case 2:
+ return mfpmr(PMRN_PMC2);
+ case 3:
+ return mfpmr(PMRN_PMC3);
+ default:
+ return 0;
+ }
+}
+
+static inline void ctr_write(unsigned int i, unsigned int val)
+{
+ switch(i) {
+ case 0:
+ mtpmr(PMRN_PMC0, val);
+ break;
+ case 1:
+ mtpmr(PMRN_PMC1, val);
+ break;
+ case 2:
+ mtpmr(PMRN_PMC2, val);
+ break;
+ case 3:
+ mtpmr(PMRN_PMC3, val);
+ break;
+ default:
+ break;
+ }
+}
+
+
+static void fsl_booke_reg_setup(struct op_counter_config *ctr,
+ struct op_system_config *sys,
+ int num_ctrs)
+{
+ int i;
+
+ num_counters = num_ctrs;
+
+ /* freeze all counters */
+ pmc_stop_ctrs();
+
+ /* Our counters count up, and "count" refers to
+ * how much before the next interrupt, and we interrupt
+ * on overflow. So we calculate the starting value
+ * which will give us "count" until overflow.
+ * Then we set the events on the enabled counters */
+ for (i = 0; i < num_counters; ++i) {
+ reset_value[i] = 0x80000000UL - ctr[i].count;
+
+ init_pmc_stop(i);
+
+ set_pmc_event(i, ctr[i].event);
+
+ set_pmc_user_kernel(i, ctr[i].user, ctr[i].kernel);
+ }
+}
+
+static void fsl_booke_start(struct op_counter_config *ctr)
+{
+ int i;
+
+ mtmsr(mfmsr() | MSR_PMM);
+
+ for (i = 0; i < num_counters; ++i) {
+ if (ctr[i].enabled) {
+ ctr_write(i, reset_value[i]);
+ /* Set Each enabled counterd to only
+ * count when the Mark bit is not set */
+ set_pmc_marked(i, 1, 0);
+ pmc_start_ctr(i, 1);
+ } else {
+ ctr_write(i, 0);
+
+ /* Set the ctr to be stopped */
+ pmc_start_ctr(i, 0);
+ }
+ }
+
+ /* Clear the freeze bit, and enable the interrupt.
+ * The counters won't actually start until the rfi clears
+ * the PMM bit */
+ pmc_start_ctrs(1);
+
+ oprofile_running = 1;
+
+ pr_debug("start on cpu %d, pmgc0 %x\n", smp_processor_id(),
+ mfpmr(PMRN_PMGC0));
+}
+
+static void fsl_booke_stop(void)
+{
+ /* freeze counters */
+ pmc_stop_ctrs();
+
+ oprofile_running = 0;
+
+ pr_debug("stop on cpu %d, pmgc0 %x\n", smp_processor_id(),
+ mfpmr(PMRN_PMGC0));
+
+ mb();
+}
+
+
+static void fsl_booke_handle_interrupt(struct pt_regs *regs,
+ struct op_counter_config *ctr)
+{
+ unsigned long pc;
+ int is_kernel;
+ int val;
+ int i;
+
+ /* set the PMM bit (see comment below) */
+ mtmsr(mfmsr() | MSR_PMM);
+
+ pc = regs->nip;
+ is_kernel = (pc >= KERNELBASE);
+
+ for (i = 0; i < num_counters; ++i) {
+ val = ctr_read(i);
+ if (val < 0) {
+ if (oprofile_running && ctr[i].enabled) {
+ oprofile_add_pc(pc, is_kernel, i);
+ ctr_write(i, reset_value[i]);
+ } else {
+ ctr_write(i, 0);
+ }
+ }
+ }
+
+ /* The freeze bit was set by the interrupt. */
+ /* Clear the freeze bit, and reenable the interrupt.
+ * The counters won't actually start until the rfi clears
+ * the PMM bit */
+ pmc_start_ctrs(1);
+}
+
+struct op_powerpc_model op_model_fsl_booke = {
+ .reg_setup = fsl_booke_reg_setup,
+ .start = fsl_booke_start,
+ .stop = fsl_booke_stop,
+ .handle_interrupt = fsl_booke_handle_interrupt,
+};
diff --git a/arch/powerpc/oprofile/op_model_power4.c b/arch/powerpc/oprofile/op_model_power4.c
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/op_model_power4.c
@@ -0,0 +1,309 @@
+/*
+ * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/systemcfg.h>
+#include <asm/rtas.h>
+#include <asm/oprofile_impl.h>
+
+#define dbg(args...)
+
+static unsigned long reset_value[OP_MAX_COUNTER];
+
+static int oprofile_running;
+static int mmcra_has_sihv;
+
+/* mmcr values are set in power4_reg_setup, used in power4_cpu_setup */
+static u32 mmcr0_val;
+static u64 mmcr1_val;
+static u32 mmcra_val;
+
+/*
+ * Since we do not have an NMI, backtracing through spinlocks is
+ * only a best guess. In light of this, allow it to be disabled at
+ * runtime.
+ */
+static int backtrace_spinlocks;
+
+static void power4_reg_setup(struct op_counter_config *ctr,
+ struct op_system_config *sys,
+ int num_ctrs)
+{
+ int i;
+
+ /*
+ * SIHV / SIPR bits are only implemented on POWER4+ (GQ) and above.
+ * However we disable it on all POWER4 until we verify it works
+ * (I was seeing some strange behaviour last time I tried).
+ *
+ * It has been verified to work on POWER5 so we enable it there.
+ */
+ if (cpu_has_feature(CPU_FTR_MMCRA_SIHV))
+ mmcra_has_sihv = 1;
+
+ /*
+ * The performance counter event settings are given in the mmcr0,
+ * mmcr1 and mmcra values passed from the user in the
+ * op_system_config structure (sys variable).
+ */
+ mmcr0_val = sys->mmcr0;
+ mmcr1_val = sys->mmcr1;
+ mmcra_val = sys->mmcra;
+
+ backtrace_spinlocks = sys->backtrace_spinlocks;
+
+ for (i = 0; i < cur_cpu_spec->num_pmcs; ++i)
+ reset_value[i] = 0x80000000UL - ctr[i].count;
+
+ /* setup user and kernel profiling */
+ if (sys->enable_kernel)
+ mmcr0_val &= ~MMCR0_KERNEL_DISABLE;
+ else
+ mmcr0_val |= MMCR0_KERNEL_DISABLE;
+
+ if (sys->enable_user)
+ mmcr0_val &= ~MMCR0_PROBLEM_DISABLE;
+ else
+ mmcr0_val |= MMCR0_PROBLEM_DISABLE;
+}
+
+extern void ppc64_enable_pmcs(void);
+
+static void power4_cpu_setup(void *unused)
+{
+ unsigned int mmcr0 = mmcr0_val;
+ unsigned long mmcra = mmcra_val;
+
+ ppc64_enable_pmcs();
+
+ /* set the freeze bit */
+ mmcr0 |= MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ mmcr0 |= MMCR0_FCM1|MMCR0_PMXE|MMCR0_FCECE;
+ mmcr0 |= MMCR0_PMC1CE|MMCR0_PMCjCE;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ mtspr(SPRN_MMCR1, mmcr1_val);
+
+ mmcra |= MMCRA_SAMPLE_ENABLE;
+ mtspr(SPRN_MMCRA, mmcra);
+
+ dbg("setup on cpu %d, mmcr0 %lx\n", smp_processor_id(),
+ mfspr(SPRN_MMCR0));
+ dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
+ mfspr(SPRN_MMCR1));
+ dbg("setup on cpu %d, mmcra %lx\n", smp_processor_id(),
+ mfspr(SPRN_MMCRA));
+}
+
+static void power4_start(struct op_counter_config *ctr)
+{
+ int i;
+ unsigned int mmcr0;
+
+ /* set the PMM bit (see comment below) */
+ mtmsrd(mfmsr() | MSR_PMM);
+
+ for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
+ if (ctr[i].enabled) {
+ ctr_write(i, reset_value[i]);
+ } else {
+ ctr_write(i, 0);
+ }
+ }
+
+ mmcr0 = mfspr(SPRN_MMCR0);
+
+ /*
+ * We must clear the PMAO bit on some (GQ) chips. Just do it
+ * all the time
+ */
+ mmcr0 &= ~MMCR0_PMAO;
+
+ /*
+ * now clear the freeze bit, counting will not start until we
+ * rfid from this excetion, because only at that point will
+ * the PMM bit be cleared
+ */
+ mmcr0 &= ~MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ oprofile_running = 1;
+
+ dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+}
+
+static void power4_stop(void)
+{
+ unsigned int mmcr0;
+
+ /* freeze counters */
+ mmcr0 = mfspr(SPRN_MMCR0);
+ mmcr0 |= MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ oprofile_running = 0;
+
+ dbg("stop on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+
+ mb();
+}
+
+/* Fake functions used by canonicalize_pc */
+static void __attribute_used__ hypervisor_bucket(void)
+{
+}
+
+static void __attribute_used__ rtas_bucket(void)
+{
+}
+
+static void __attribute_used__ kernel_unknown_bucket(void)
+{
+}
+
+static unsigned long check_spinlock_pc(struct pt_regs *regs,
+ unsigned long profile_pc)
+{
+ unsigned long pc = instruction_pointer(regs);
+
+ /*
+ * If both the SIAR (sampled instruction) and the perfmon exception
+ * occurred in a spinlock region then we account the sample to the
+ * calling function. This isnt 100% correct, we really need soft
+ * IRQ disable so we always get the perfmon exception at the
+ * point at which the SIAR is set.
+ */
+ if (backtrace_spinlocks && in_lock_functions(pc) &&
+ in_lock_functions(profile_pc))
+ return regs->link;
+ else
+ return profile_pc;
+}
+
+/*
+ * On GQ and newer the MMCRA stores the HV and PR bits at the time
+ * the SIAR was sampled. We use that to work out if the SIAR was sampled in
+ * the hypervisor, our exception vectors or RTAS.
+ */
+static unsigned long get_pc(struct pt_regs *regs)
+{
+ unsigned long pc = mfspr(SPRN_SIAR);
+ unsigned long mmcra;
+
+ /* Cant do much about it */
+ if (!mmcra_has_sihv)
+ return check_spinlock_pc(regs, pc);
+
+ mmcra = mfspr(SPRN_MMCRA);
+
+ /* Were we in the hypervisor? */
+ if ((systemcfg->platform == PLATFORM_PSERIES_LPAR) &&
+ (mmcra & MMCRA_SIHV))
+ /* function descriptor madness */
+ return *((unsigned long *)hypervisor_bucket);
+
+ /* We were in userspace, nothing to do */
+ if (mmcra & MMCRA_SIPR)
+ return pc;
+
+#ifdef CONFIG_PPC_RTAS
+ /* Were we in RTAS? */
+ if (pc >= rtas.base && pc < (rtas.base + rtas.size))
+ /* function descriptor madness */
+ return *((unsigned long *)rtas_bucket);
+#endif
+
+ /* Were we in our exception vectors or SLB real mode miss handler? */
+ if (pc < 0x1000000UL)
+ return (unsigned long)__va(pc);
+
+ /* Not sure where we were */
+ if (pc < KERNELBASE)
+ /* function descriptor madness */
+ return *((unsigned long *)kernel_unknown_bucket);
+
+ return check_spinlock_pc(regs, pc);
+}
+
+static int get_kernel(unsigned long pc)
+{
+ int is_kernel;
+
+ if (!mmcra_has_sihv) {
+ is_kernel = (pc >= KERNELBASE);
+ } else {
+ unsigned long mmcra = mfspr(SPRN_MMCRA);
+ is_kernel = ((mmcra & MMCRA_SIPR) == 0);
+ }
+
+ return is_kernel;
+}
+
+static void power4_handle_interrupt(struct pt_regs *regs,
+ struct op_counter_config *ctr)
+{
+ unsigned long pc;
+ int is_kernel;
+ int val;
+ int i;
+ unsigned int mmcr0;
+
+ pc = get_pc(regs);
+ is_kernel = get_kernel(pc);
+
+ /* set the PMM bit (see comment below) */
+ mtmsrd(mfmsr() | MSR_PMM);
+
+ for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
+ val = ctr_read(i);
+ if (val < 0) {
+ if (oprofile_running && ctr[i].enabled) {
+ oprofile_add_pc(pc, is_kernel, i);
+ ctr_write(i, reset_value[i]);
+ } else {
+ ctr_write(i, 0);
+ }
+ }
+ }
+
+ mmcr0 = mfspr(SPRN_MMCR0);
+
+ /* reset the perfmon trigger */
+ mmcr0 |= MMCR0_PMXE;
+
+ /*
+ * We must clear the PMAO bit on some (GQ) chips. Just do it
+ * all the time
+ */
+ mmcr0 &= ~MMCR0_PMAO;
+
+ /*
+ * now clear the freeze bit, counting will not start until we
+ * rfid from this exception, because only at that point will
+ * the PMM bit be cleared
+ */
+ mmcr0 &= ~MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+}
+
+struct op_powerpc_model op_model_power4 = {
+ .reg_setup = power4_reg_setup,
+ .cpu_setup = power4_cpu_setup,
+ .start = power4_start,
+ .stop = power4_stop,
+ .handle_interrupt = power4_handle_interrupt,
+};
diff --git a/arch/powerpc/oprofile/op_model_rs64.c b/arch/powerpc/oprofile/op_model_rs64.c
new file mode 100644
--- /dev/null
+++ b/arch/powerpc/oprofile/op_model_rs64.c
@@ -0,0 +1,218 @@
+/*
+ * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/oprofile.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <asm/ptrace.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/cputable.h>
+#include <asm/oprofile_impl.h>
+
+#define dbg(args...)
+
+static void ctrl_write(unsigned int i, unsigned int val)
+{
+ unsigned int tmp = 0;
+ unsigned long shift = 0, mask = 0;
+
+ dbg("ctrl_write %d %x\n", i, val);
+
+ switch(i) {
+ case 0:
+ tmp = mfspr(SPRN_MMCR0);
+ shift = 6;
+ mask = 0x7F;
+ break;
+ case 1:
+ tmp = mfspr(SPRN_MMCR0);
+ shift = 0;
+ mask = 0x3F;
+ break;
+ case 2:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 4;
+ mask = 0x1F;
+ break;
+ case 3:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 9;
+ mask = 0x1F;
+ break;
+ case 4:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 14;
+ mask = 0x1F;
+ break;
+ case 5:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 19;
+ mask = 0x1F;
+ break;
+ case 6:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 24;
+ mask = 0x1F;
+ break;
+ case 7:
+ tmp = mfspr(SPRN_MMCR1);
+ shift = 31 - 28;
+ mask = 0xF;
+ break;
+ }
+
+ tmp = tmp & ~(mask << shift);
+ tmp |= val << shift;
+
+ switch(i) {
+ case 0:
+ case 1:
+ mtspr(SPRN_MMCR0, tmp);
+ break;
+ default:
+ mtspr(SPRN_MMCR1, tmp);
+ }
+
+ dbg("ctrl_write mmcr0 %lx mmcr1 %lx\n", mfspr(SPRN_MMCR0),
+ mfspr(SPRN_MMCR1));
+}
+
+static unsigned long reset_value[OP_MAX_COUNTER];
+
+static int num_counters;
+
+static void rs64_reg_setup(struct op_counter_config *ctr,
+ struct op_system_config *sys,
+ int num_ctrs)
+{
+ int i;
+
+ num_counters = num_ctrs;
+
+ for (i = 0; i < num_counters; ++i)
+ reset_value[i] = 0x80000000UL - ctr[i].count;
+
+ /* XXX setup user and kernel profiling */
+}
+
+static void rs64_cpu_setup(void *unused)
+{
+ unsigned int mmcr0;
+
+ /* reset MMCR0 and set the freeze bit */
+ mmcr0 = MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ /* reset MMCR1, MMCRA */
+ mtspr(SPRN_MMCR1, 0);
+
+ if (cpu_has_feature(CPU_FTR_MMCRA))
+ mtspr(SPRN_MMCRA, 0);
+
+ mmcr0 |= MMCR0_FCM1|MMCR0_PMXE|MMCR0_FCECE;
+ /* Only applies to POWER3, but should be safe on RS64 */
+ mmcr0 |= MMCR0_PMC1CE|MMCR0_PMCjCE;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ dbg("setup on cpu %d, mmcr0 %lx\n", smp_processor_id(),
+ mfspr(SPRN_MMCR0));
+ dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
+ mfspr(SPRN_MMCR1));
+}
+
+static void rs64_start(struct op_counter_config *ctr)
+{
+ int i;
+ unsigned int mmcr0;
+
+ /* set the PMM bit (see comment below) */
+ mtmsrd(mfmsr() | MSR_PMM);
+
+ for (i = 0; i < num_counters; ++i) {
+ if (ctr[i].enabled) {
+ ctr_write(i, reset_value[i]);
+ ctrl_write(i, ctr[i].event);
+ } else {
+ ctr_write(i, 0);
+ }
+ }
+
+ mmcr0 = mfspr(SPRN_MMCR0);
+
+ /*
+ * now clear the freeze bit, counting will not start until we
+ * rfid from this excetion, because only at that point will
+ * the PMM bit be cleared
+ */
+ mmcr0 &= ~MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+}
+
+static void rs64_stop(void)
+{
+ unsigned int mmcr0;
+
+ /* freeze counters */
+ mmcr0 = mfspr(SPRN_MMCR0);
+ mmcr0 |= MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+
+ dbg("stop on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
+
+ mb();
+}
+
+static void rs64_handle_interrupt(struct pt_regs *regs,
+ struct op_counter_config *ctr)
+{
+ unsigned int mmcr0;
+ int val;
+ int i;
+ unsigned long pc = mfspr(SPRN_SIAR);
+ int is_kernel = (pc >= KERNELBASE);
+
+ /* set the PMM bit (see comment below) */
+ mtmsrd(mfmsr() | MSR_PMM);
+
+ for (i = 0; i < num_counters; ++i) {
+ val = ctr_read(i);
+ if (val < 0) {
+ if (ctr[i].enabled) {
+ oprofile_add_pc(pc, is_kernel, i);
+ ctr_write(i, reset_value[i]);
+ } else {
+ ctr_write(i, 0);
+ }
+ }
+ }
+
+ mmcr0 = mfspr(SPRN_MMCR0);
+
+ /* reset the perfmon trigger */
+ mmcr0 |= MMCR0_PMXE;
+
+ /*
+ * now clear the freeze bit, counting will not start until we
+ * rfid from this exception, because only at that point will
+ * the PMM bit be cleared
+ */
+ mmcr0 &= ~MMCR0_FC;
+ mtspr(SPRN_MMCR0, mmcr0);
+}
+
+struct op_powerpc_model op_model_rs64 = {
+ .reg_setup = rs64_reg_setup,
+ .cpu_setup = rs64_cpu_setup,
+ .start = rs64_start,
+ .stop = rs64_stop,
+ .handle_interrupt = rs64_handle_interrupt,
+};
diff --git a/arch/ppc/Makefile b/arch/ppc/Makefile
--- a/arch/ppc/Makefile
+++ b/arch/ppc/Makefile
@@ -71,7 +71,7 @@ drivers-$(CONFIG_8xx) += arch/ppc/8xx_i
drivers-$(CONFIG_4xx) += arch/ppc/4xx_io/
drivers-$(CONFIG_CPM2) += arch/ppc/8260_io/
-drivers-$(CONFIG_OPROFILE) += arch/ppc/oprofile/
+drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/
BOOT_TARGETS = zImage zImage.initrd znetboot znetboot.initrd vmlinux.sm
diff --git a/arch/ppc/oprofile/Makefile b/arch/ppc/oprofile/Makefile
deleted file mode 100644
--- a/arch/ppc/oprofile/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-include arch/powerpc/oprofile/Makefile
diff --git a/arch/ppc/oprofile/common.c b/arch/ppc/oprofile/common.c
deleted file mode 100644
--- a/arch/ppc/oprofile/common.c
+++ /dev/null
@@ -1,160 +0,0 @@
-/*
- * PPC 32 oprofile support
- * Based on PPC64 oprofile support
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * Copyright (C) Freescale Semiconductor, Inc 2004
- *
- * Author: Andy Fleming
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/oprofile.h>
-#include <linux/slab.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <asm/ptrace.h>
-#include <asm/system.h>
-#include <asm/perfmon.h>
-#include <asm/cputable.h>
-#include <asm/oprofile_impl.h>
-
-static struct op_powerpc_model *model;
-
-static struct op_counter_config ctr[OP_MAX_COUNTER];
-static struct op_system_config sys;
-
-static void op_handle_interrupt(struct pt_regs *regs)
-{
- model->handle_interrupt(regs, ctr);
-}
-
-static int op_ppc32_setup(void)
-{
- /* Install our interrupt handler into the existing hook. */
- if(request_perfmon_irq(&op_handle_interrupt))
- return -EBUSY;
-
- mb();
-
- /* Pre-compute the values to stuff in the hardware registers. */
- model->reg_setup(ctr, &sys, model->num_counters);
-
-#if 0
- /* FIXME: Make multi-cpu work */
- /* Configure the registers on all cpus. */
- on_each_cpu(model->reg_setup, NULL, 0, 1);
-#endif
-
- return 0;
-}
-
-static void op_ppc32_shutdown(void)
-{
- mb();
-
- /* Remove our interrupt handler. We may be removing this module. */
- free_perfmon_irq();
-}
-
-static void op_ppc32_cpu_start(void *dummy)
-{
- model->start(ctr);
-}
-
-static int op_ppc32_start(void)
-{
- on_each_cpu(op_ppc32_cpu_start, NULL, 0, 1);
- return 0;
-}
-
-static inline void op_ppc32_cpu_stop(void *dummy)
-{
- model->stop();
-}
-
-static void op_ppc32_stop(void)
-{
- on_each_cpu(op_ppc32_cpu_stop, NULL, 0, 1);
-}
-
-static int op_ppc32_create_files(struct super_block *sb, struct dentry *root)
-{
- int i;
-
- for (i = 0; i < model->num_counters; ++i) {
- struct dentry *dir;
- char buf[3];
-
- snprintf(buf, sizeof buf, "%d", i);
- dir = oprofilefs_mkdir(sb, root, buf);
-
- oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
- oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
- oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
- oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
- oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-
- /* FIXME: Not sure if this is used */
- oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
- }
-
- oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
- oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
-
- /* Default to tracing both kernel and user */
- sys.enable_kernel = 1;
- sys.enable_user = 1;
-
- return 0;
-}
-
-static struct oprofile_operations oprof_ppc32_ops = {
- .create_files = op_ppc32_create_files,
- .setup = op_ppc32_setup,
- .shutdown = op_ppc32_shutdown,
- .start = op_ppc32_start,
- .stop = op_ppc32_stop,
- .cpu_type = NULL /* To be filled in below. */
-};
-
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
- char *name;
- int cpu_id = smp_processor_id();
-
-#ifdef CONFIG_FSL_BOOKE
- model = &op_model_fsl_booke;
-#else
- return -ENODEV;
-#endif
-
- name = kmalloc(32, GFP_KERNEL);
-
- if (NULL == name)
- return -ENOMEM;
-
- sprintf(name, "ppc/%s", cur_cpu_spec[cpu_id]->cpu_name);
-
- oprof_ppc32_ops.cpu_type = name;
-
- model->num_counters = cur_cpu_spec[cpu_id]->num_pmcs;
-
- *ops = oprof_ppc32_ops;
-
- printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
- oprof_ppc32_ops.cpu_type);
-
- return 0;
-}
-
-void oprofile_arch_exit(void)
-{
- kfree(oprof_ppc32_ops.cpu_type);
- oprof_ppc32_ops.cpu_type = NULL;
-}
diff --git a/arch/ppc/oprofile/op_model_fsl_booke.c b/arch/ppc/oprofile/op_model_fsl_booke.c
deleted file mode 100644
--- a/arch/ppc/oprofile/op_model_fsl_booke.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * oprofile/op_model_e500.c
- *
- * Freescale Book-E oprofile support, based on ppc64 oprofile support
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * Copyright (c) 2004 Freescale Semiconductor, Inc
- *
- * Author: Andy Fleming
- * Maintainer: Kumar Gala <Kumar.Gala@freescale.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/oprofile.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <asm/ptrace.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/cputable.h>
-#include <asm/reg_booke.h>
-#include <asm/page.h>
-#include <asm/perfmon.h>
-#include <asm/oprofile_impl.h>
-
-static unsigned long reset_value[OP_MAX_COUNTER];
-
-static int num_counters;
-static int oprofile_running;
-
-static inline unsigned int ctr_read(unsigned int i)
-{
- switch(i) {
- case 0:
- return mfpmr(PMRN_PMC0);
- case 1:
- return mfpmr(PMRN_PMC1);
- case 2:
- return mfpmr(PMRN_PMC2);
- case 3:
- return mfpmr(PMRN_PMC3);
- default:
- return 0;
- }
-}
-
-static inline void ctr_write(unsigned int i, unsigned int val)
-{
- switch(i) {
- case 0:
- mtpmr(PMRN_PMC0, val);
- break;
- case 1:
- mtpmr(PMRN_PMC1, val);
- break;
- case 2:
- mtpmr(PMRN_PMC2, val);
- break;
- case 3:
- mtpmr(PMRN_PMC3, val);
- break;
- default:
- break;
- }
-}
-
-
-static void fsl_booke_reg_setup(struct op_counter_config *ctr,
- struct op_system_config *sys,
- int num_ctrs)
-{
- int i;
-
- num_counters = num_ctrs;
-
- /* freeze all counters */
- pmc_stop_ctrs();
-
- /* Our counters count up, and "count" refers to
- * how much before the next interrupt, and we interrupt
- * on overflow. So we calculate the starting value
- * which will give us "count" until overflow.
- * Then we set the events on the enabled counters */
- for (i = 0; i < num_counters; ++i) {
- reset_value[i] = 0x80000000UL - ctr[i].count;
-
- init_pmc_stop(i);
-
- set_pmc_event(i, ctr[i].event);
-
- set_pmc_user_kernel(i, ctr[i].user, ctr[i].kernel);
- }
-}
-
-static void fsl_booke_start(struct op_counter_config *ctr)
-{
- int i;
-
- mtmsr(mfmsr() | MSR_PMM);
-
- for (i = 0; i < num_counters; ++i) {
- if (ctr[i].enabled) {
- ctr_write(i, reset_value[i]);
- /* Set Each enabled counterd to only
- * count when the Mark bit is not set */
- set_pmc_marked(i, 1, 0);
- pmc_start_ctr(i, 1);
- } else {
- ctr_write(i, 0);
-
- /* Set the ctr to be stopped */
- pmc_start_ctr(i, 0);
- }
- }
-
- /* Clear the freeze bit, and enable the interrupt.
- * The counters won't actually start until the rfi clears
- * the PMM bit */
- pmc_start_ctrs(1);
-
- oprofile_running = 1;
-
- pr_debug("start on cpu %d, pmgc0 %x\n", smp_processor_id(),
- mfpmr(PMRN_PMGC0));
-}
-
-static void fsl_booke_stop(void)
-{
- /* freeze counters */
- pmc_stop_ctrs();
-
- oprofile_running = 0;
-
- pr_debug("stop on cpu %d, pmgc0 %x\n", smp_processor_id(),
- mfpmr(PMRN_PMGC0));
-
- mb();
-}
-
-
-static void fsl_booke_handle_interrupt(struct pt_regs *regs,
- struct op_counter_config *ctr)
-{
- unsigned long pc;
- int is_kernel;
- int val;
- int i;
-
- /* set the PMM bit (see comment below) */
- mtmsr(mfmsr() | MSR_PMM);
-
- pc = regs->nip;
- is_kernel = (pc >= KERNELBASE);
-
- for (i = 0; i < num_counters; ++i) {
- val = ctr_read(i);
- if (val < 0) {
- if (oprofile_running && ctr[i].enabled) {
- oprofile_add_pc(pc, is_kernel, i);
- ctr_write(i, reset_value[i]);
- } else {
- ctr_write(i, 0);
- }
- }
- }
-
- /* The freeze bit was set by the interrupt. */
- /* Clear the freeze bit, and reenable the interrupt.
- * The counters won't actually start until the rfi clears
- * the PMM bit */
- pmc_start_ctrs(1);
-}
-
-struct op_powerpc_model op_model_fsl_booke = {
- .reg_setup = fsl_booke_reg_setup,
- .start = fsl_booke_start,
- .stop = fsl_booke_stop,
- .handle_interrupt = fsl_booke_handle_interrupt,
-};
diff --git a/arch/ppc64/Makefile b/arch/ppc64/Makefile
--- a/arch/ppc64/Makefile
+++ b/arch/ppc64/Makefile
@@ -85,7 +85,7 @@ libs-y += arch/ppc64/lib/
core-y += arch/ppc64/kernel/
core-y += arch/ppc64/mm/
core-$(CONFIG_XMON) += arch/ppc64/xmon/
-drivers-$(CONFIG_OPROFILE) += arch/ppc64/oprofile/
+drivers-$(CONFIG_OPROFILE) += arch/powerpc/oprofile/
boot := arch/ppc64/boot
diff --git a/arch/ppc64/oprofile/Makefile b/arch/ppc64/oprofile/Makefile
deleted file mode 100644
--- a/arch/ppc64/oprofile/Makefile
+++ /dev/null
@@ -1 +0,0 @@
-include arch/powerpc/oprofile/Makefile
diff --git a/arch/ppc64/oprofile/common.c b/arch/ppc64/oprofile/common.c
deleted file mode 100644
--- a/arch/ppc64/oprofile/common.c
+++ /dev/null
@@ -1,145 +0,0 @@
-/*
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * Based on alpha version.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/oprofile.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <asm/ptrace.h>
-#include <asm/system.h>
-#include <asm/pmc.h>
-#include <asm/cputable.h>
-#include <asm/oprofile_impl.h>
-
-static struct op_powerpc_model *model;
-
-static struct op_counter_config ctr[OP_MAX_COUNTER];
-static struct op_system_config sys;
-
-static void op_handle_interrupt(struct pt_regs *regs)
-{
- model->handle_interrupt(regs, ctr);
-}
-
-static int op_ppc64_setup(void)
-{
- int err;
-
- /* Grab the hardware */
- err = reserve_pmc_hardware(op_handle_interrupt);
- if (err)
- return err;
-
- /* Pre-compute the values to stuff in the hardware registers. */
- model->reg_setup(ctr, &sys, model->num_counters);
-
- /* Configure the registers on all cpus. */
- on_each_cpu(model->cpu_setup, NULL, 0, 1);
-
- return 0;
-}
-
-static void op_ppc64_shutdown(void)
-{
- release_pmc_hardware();
-}
-
-static void op_ppc64_cpu_start(void *dummy)
-{
- model->start(ctr);
-}
-
-static int op_ppc64_start(void)
-{
- on_each_cpu(op_ppc64_cpu_start, NULL, 0, 1);
- return 0;
-}
-
-static inline void op_ppc64_cpu_stop(void *dummy)
-{
- model->stop();
-}
-
-static void op_ppc64_stop(void)
-{
- on_each_cpu(op_ppc64_cpu_stop, NULL, 0, 1);
-}
-
-static int op_ppc64_create_files(struct super_block *sb, struct dentry *root)
-{
- int i;
-
- /*
- * There is one mmcr0, mmcr1 and mmcra for setting the events for
- * all of the counters.
- */
- oprofilefs_create_ulong(sb, root, "mmcr0", &sys.mmcr0);
- oprofilefs_create_ulong(sb, root, "mmcr1", &sys.mmcr1);
- oprofilefs_create_ulong(sb, root, "mmcra", &sys.mmcra);
-
- for (i = 0; i < model->num_counters; ++i) {
- struct dentry *dir;
- char buf[3];
-
- snprintf(buf, sizeof buf, "%d", i);
- dir = oprofilefs_mkdir(sb, root, buf);
-
- oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
- oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
- oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
- /*
- * We dont support per counter user/kernel selection, but
- * we leave the entries because userspace expects them
- */
- oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
- oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
- oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
- }
-
- oprofilefs_create_ulong(sb, root, "enable_kernel", &sys.enable_kernel);
- oprofilefs_create_ulong(sb, root, "enable_user", &sys.enable_user);
- oprofilefs_create_ulong(sb, root, "backtrace_spinlocks",
- &sys.backtrace_spinlocks);
-
- /* Default to tracing both kernel and user */
- sys.enable_kernel = 1;
- sys.enable_user = 1;
-
- /* Turn on backtracing through spinlocks by default */
- sys.backtrace_spinlocks = 1;
-
- return 0;
-}
-
-int __init oprofile_arch_init(struct oprofile_operations *ops)
-{
- if (!cur_cpu_spec->oprofile_model || !cur_cpu_spec->oprofile_cpu_type)
- return -ENODEV;
-
- model = cur_cpu_spec->oprofile_model;
- model->num_counters = cur_cpu_spec->num_pmcs;
-
- ops->cpu_type = cur_cpu_spec->oprofile_cpu_type;
- ops->create_files = op_ppc64_create_files;
- ops->setup = op_ppc64_setup;
- ops->shutdown = op_ppc64_shutdown;
- ops->start = op_ppc64_start;
- ops->stop = op_ppc64_stop;
-
- printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
- ops->cpu_type);
-
- return 0;
-}
-
-void oprofile_arch_exit(void)
-{
-}
diff --git a/arch/ppc64/oprofile/op_model_power4.c b/arch/ppc64/oprofile/op_model_power4.c
deleted file mode 100644
--- a/arch/ppc64/oprofile/op_model_power4.c
+++ /dev/null
@@ -1,309 +0,0 @@
-/*
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/oprofile.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <asm/ptrace.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/cputable.h>
-#include <asm/systemcfg.h>
-#include <asm/rtas.h>
-#include <asm/oprofile_impl.h>
-
-#define dbg(args...)
-
-static unsigned long reset_value[OP_MAX_COUNTER];
-
-static int oprofile_running;
-static int mmcra_has_sihv;
-
-/* mmcr values are set in power4_reg_setup, used in power4_cpu_setup */
-static u32 mmcr0_val;
-static u64 mmcr1_val;
-static u32 mmcra_val;
-
-/*
- * Since we do not have an NMI, backtracing through spinlocks is
- * only a best guess. In light of this, allow it to be disabled at
- * runtime.
- */
-static int backtrace_spinlocks;
-
-static void power4_reg_setup(struct op_counter_config *ctr,
- struct op_system_config *sys,
- int num_ctrs)
-{
- int i;
-
- /*
- * SIHV / SIPR bits are only implemented on POWER4+ (GQ) and above.
- * However we disable it on all POWER4 until we verify it works
- * (I was seeing some strange behaviour last time I tried).
- *
- * It has been verified to work on POWER5 so we enable it there.
- */
- if (cpu_has_feature(CPU_FTR_MMCRA_SIHV))
- mmcra_has_sihv = 1;
-
- /*
- * The performance counter event settings are given in the mmcr0,
- * mmcr1 and mmcra values passed from the user in the
- * op_system_config structure (sys variable).
- */
- mmcr0_val = sys->mmcr0;
- mmcr1_val = sys->mmcr1;
- mmcra_val = sys->mmcra;
-
- backtrace_spinlocks = sys->backtrace_spinlocks;
-
- for (i = 0; i < cur_cpu_spec->num_pmcs; ++i)
- reset_value[i] = 0x80000000UL - ctr[i].count;
-
- /* setup user and kernel profiling */
- if (sys->enable_kernel)
- mmcr0_val &= ~MMCR0_KERNEL_DISABLE;
- else
- mmcr0_val |= MMCR0_KERNEL_DISABLE;
-
- if (sys->enable_user)
- mmcr0_val &= ~MMCR0_PROBLEM_DISABLE;
- else
- mmcr0_val |= MMCR0_PROBLEM_DISABLE;
-}
-
-extern void ppc64_enable_pmcs(void);
-
-static void power4_cpu_setup(void *unused)
-{
- unsigned int mmcr0 = mmcr0_val;
- unsigned long mmcra = mmcra_val;
-
- ppc64_enable_pmcs();
-
- /* set the freeze bit */
- mmcr0 |= MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- mmcr0 |= MMCR0_FCM1|MMCR0_PMXE|MMCR0_FCECE;
- mmcr0 |= MMCR0_PMC1CE|MMCR0_PMCjCE;
- mtspr(SPRN_MMCR0, mmcr0);
-
- mtspr(SPRN_MMCR1, mmcr1_val);
-
- mmcra |= MMCRA_SAMPLE_ENABLE;
- mtspr(SPRN_MMCRA, mmcra);
-
- dbg("setup on cpu %d, mmcr0 %lx\n", smp_processor_id(),
- mfspr(SPRN_MMCR0));
- dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
- mfspr(SPRN_MMCR1));
- dbg("setup on cpu %d, mmcra %lx\n", smp_processor_id(),
- mfspr(SPRN_MMCRA));
-}
-
-static void power4_start(struct op_counter_config *ctr)
-{
- int i;
- unsigned int mmcr0;
-
- /* set the PMM bit (see comment below) */
- mtmsrd(mfmsr() | MSR_PMM);
-
- for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
- if (ctr[i].enabled) {
- ctr_write(i, reset_value[i]);
- } else {
- ctr_write(i, 0);
- }
- }
-
- mmcr0 = mfspr(SPRN_MMCR0);
-
- /*
- * We must clear the PMAO bit on some (GQ) chips. Just do it
- * all the time
- */
- mmcr0 &= ~MMCR0_PMAO;
-
- /*
- * now clear the freeze bit, counting will not start until we
- * rfid from this excetion, because only at that point will
- * the PMM bit be cleared
- */
- mmcr0 &= ~MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- oprofile_running = 1;
-
- dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
-}
-
-static void power4_stop(void)
-{
- unsigned int mmcr0;
-
- /* freeze counters */
- mmcr0 = mfspr(SPRN_MMCR0);
- mmcr0 |= MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- oprofile_running = 0;
-
- dbg("stop on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
-
- mb();
-}
-
-/* Fake functions used by canonicalize_pc */
-static void __attribute_used__ hypervisor_bucket(void)
-{
-}
-
-static void __attribute_used__ rtas_bucket(void)
-{
-}
-
-static void __attribute_used__ kernel_unknown_bucket(void)
-{
-}
-
-static unsigned long check_spinlock_pc(struct pt_regs *regs,
- unsigned long profile_pc)
-{
- unsigned long pc = instruction_pointer(regs);
-
- /*
- * If both the SIAR (sampled instruction) and the perfmon exception
- * occurred in a spinlock region then we account the sample to the
- * calling function. This isnt 100% correct, we really need soft
- * IRQ disable so we always get the perfmon exception at the
- * point at which the SIAR is set.
- */
- if (backtrace_spinlocks && in_lock_functions(pc) &&
- in_lock_functions(profile_pc))
- return regs->link;
- else
- return profile_pc;
-}
-
-/*
- * On GQ and newer the MMCRA stores the HV and PR bits at the time
- * the SIAR was sampled. We use that to work out if the SIAR was sampled in
- * the hypervisor, our exception vectors or RTAS.
- */
-static unsigned long get_pc(struct pt_regs *regs)
-{
- unsigned long pc = mfspr(SPRN_SIAR);
- unsigned long mmcra;
-
- /* Cant do much about it */
- if (!mmcra_has_sihv)
- return check_spinlock_pc(regs, pc);
-
- mmcra = mfspr(SPRN_MMCRA);
-
- /* Were we in the hypervisor? */
- if ((systemcfg->platform == PLATFORM_PSERIES_LPAR) &&
- (mmcra & MMCRA_SIHV))
- /* function descriptor madness */
- return *((unsigned long *)hypervisor_bucket);
-
- /* We were in userspace, nothing to do */
- if (mmcra & MMCRA_SIPR)
- return pc;
-
-#ifdef CONFIG_PPC_RTAS
- /* Were we in RTAS? */
- if (pc >= rtas.base && pc < (rtas.base + rtas.size))
- /* function descriptor madness */
- return *((unsigned long *)rtas_bucket);
-#endif
-
- /* Were we in our exception vectors or SLB real mode miss handler? */
- if (pc < 0x1000000UL)
- return (unsigned long)__va(pc);
-
- /* Not sure where we were */
- if (pc < KERNELBASE)
- /* function descriptor madness */
- return *((unsigned long *)kernel_unknown_bucket);
-
- return check_spinlock_pc(regs, pc);
-}
-
-static int get_kernel(unsigned long pc)
-{
- int is_kernel;
-
- if (!mmcra_has_sihv) {
- is_kernel = (pc >= KERNELBASE);
- } else {
- unsigned long mmcra = mfspr(SPRN_MMCRA);
- is_kernel = ((mmcra & MMCRA_SIPR) == 0);
- }
-
- return is_kernel;
-}
-
-static void power4_handle_interrupt(struct pt_regs *regs,
- struct op_counter_config *ctr)
-{
- unsigned long pc;
- int is_kernel;
- int val;
- int i;
- unsigned int mmcr0;
-
- pc = get_pc(regs);
- is_kernel = get_kernel(pc);
-
- /* set the PMM bit (see comment below) */
- mtmsrd(mfmsr() | MSR_PMM);
-
- for (i = 0; i < cur_cpu_spec->num_pmcs; ++i) {
- val = ctr_read(i);
- if (val < 0) {
- if (oprofile_running && ctr[i].enabled) {
- oprofile_add_pc(pc, is_kernel, i);
- ctr_write(i, reset_value[i]);
- } else {
- ctr_write(i, 0);
- }
- }
- }
-
- mmcr0 = mfspr(SPRN_MMCR0);
-
- /* reset the perfmon trigger */
- mmcr0 |= MMCR0_PMXE;
-
- /*
- * We must clear the PMAO bit on some (GQ) chips. Just do it
- * all the time
- */
- mmcr0 &= ~MMCR0_PMAO;
-
- /*
- * now clear the freeze bit, counting will not start until we
- * rfid from this exception, because only at that point will
- * the PMM bit be cleared
- */
- mmcr0 &= ~MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-}
-
-struct op_powerpc_model op_model_power4 = {
- .reg_setup = power4_reg_setup,
- .cpu_setup = power4_cpu_setup,
- .start = power4_start,
- .stop = power4_stop,
- .handle_interrupt = power4_handle_interrupt,
-};
diff --git a/arch/ppc64/oprofile/op_model_rs64.c b/arch/ppc64/oprofile/op_model_rs64.c
deleted file mode 100644
--- a/arch/ppc64/oprofile/op_model_rs64.c
+++ /dev/null
@@ -1,218 +0,0 @@
-/*
- * Copyright (C) 2004 Anton Blanchard <anton@au.ibm.com>, IBM
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- */
-
-#include <linux/oprofile.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-#include <asm/ptrace.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/cputable.h>
-#include <asm/oprofile_impl.h>
-
-#define dbg(args...)
-
-static void ctrl_write(unsigned int i, unsigned int val)
-{
- unsigned int tmp = 0;
- unsigned long shift = 0, mask = 0;
-
- dbg("ctrl_write %d %x\n", i, val);
-
- switch(i) {
- case 0:
- tmp = mfspr(SPRN_MMCR0);
- shift = 6;
- mask = 0x7F;
- break;
- case 1:
- tmp = mfspr(SPRN_MMCR0);
- shift = 0;
- mask = 0x3F;
- break;
- case 2:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 4;
- mask = 0x1F;
- break;
- case 3:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 9;
- mask = 0x1F;
- break;
- case 4:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 14;
- mask = 0x1F;
- break;
- case 5:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 19;
- mask = 0x1F;
- break;
- case 6:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 24;
- mask = 0x1F;
- break;
- case 7:
- tmp = mfspr(SPRN_MMCR1);
- shift = 31 - 28;
- mask = 0xF;
- break;
- }
-
- tmp = tmp & ~(mask << shift);
- tmp |= val << shift;
-
- switch(i) {
- case 0:
- case 1:
- mtspr(SPRN_MMCR0, tmp);
- break;
- default:
- mtspr(SPRN_MMCR1, tmp);
- }
-
- dbg("ctrl_write mmcr0 %lx mmcr1 %lx\n", mfspr(SPRN_MMCR0),
- mfspr(SPRN_MMCR1));
-}
-
-static unsigned long reset_value[OP_MAX_COUNTER];
-
-static int num_counters;
-
-static void rs64_reg_setup(struct op_counter_config *ctr,
- struct op_system_config *sys,
- int num_ctrs)
-{
- int i;
-
- num_counters = num_ctrs;
-
- for (i = 0; i < num_counters; ++i)
- reset_value[i] = 0x80000000UL - ctr[i].count;
-
- /* XXX setup user and kernel profiling */
-}
-
-static void rs64_cpu_setup(void *unused)
-{
- unsigned int mmcr0;
-
- /* reset MMCR0 and set the freeze bit */
- mmcr0 = MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- /* reset MMCR1, MMCRA */
- mtspr(SPRN_MMCR1, 0);
-
- if (cpu_has_feature(CPU_FTR_MMCRA))
- mtspr(SPRN_MMCRA, 0);
-
- mmcr0 |= MMCR0_FCM1|MMCR0_PMXE|MMCR0_FCECE;
- /* Only applies to POWER3, but should be safe on RS64 */
- mmcr0 |= MMCR0_PMC1CE|MMCR0_PMCjCE;
- mtspr(SPRN_MMCR0, mmcr0);
-
- dbg("setup on cpu %d, mmcr0 %lx\n", smp_processor_id(),
- mfspr(SPRN_MMCR0));
- dbg("setup on cpu %d, mmcr1 %lx\n", smp_processor_id(),
- mfspr(SPRN_MMCR1));
-}
-
-static void rs64_start(struct op_counter_config *ctr)
-{
- int i;
- unsigned int mmcr0;
-
- /* set the PMM bit (see comment below) */
- mtmsrd(mfmsr() | MSR_PMM);
-
- for (i = 0; i < num_counters; ++i) {
- if (ctr[i].enabled) {
- ctr_write(i, reset_value[i]);
- ctrl_write(i, ctr[i].event);
- } else {
- ctr_write(i, 0);
- }
- }
-
- mmcr0 = mfspr(SPRN_MMCR0);
-
- /*
- * now clear the freeze bit, counting will not start until we
- * rfid from this excetion, because only at that point will
- * the PMM bit be cleared
- */
- mmcr0 &= ~MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- dbg("start on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
-}
-
-static void rs64_stop(void)
-{
- unsigned int mmcr0;
-
- /* freeze counters */
- mmcr0 = mfspr(SPRN_MMCR0);
- mmcr0 |= MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-
- dbg("stop on cpu %d, mmcr0 %x\n", smp_processor_id(), mmcr0);
-
- mb();
-}
-
-static void rs64_handle_interrupt(struct pt_regs *regs,
- struct op_counter_config *ctr)
-{
- unsigned int mmcr0;
- int val;
- int i;
- unsigned long pc = mfspr(SPRN_SIAR);
- int is_kernel = (pc >= KERNELBASE);
-
- /* set the PMM bit (see comment below) */
- mtmsrd(mfmsr() | MSR_PMM);
-
- for (i = 0; i < num_counters; ++i) {
- val = ctr_read(i);
- if (val < 0) {
- if (ctr[i].enabled) {
- oprofile_add_pc(pc, is_kernel, i);
- ctr_write(i, reset_value[i]);
- } else {
- ctr_write(i, 0);
- }
- }
- }
-
- mmcr0 = mfspr(SPRN_MMCR0);
-
- /* reset the perfmon trigger */
- mmcr0 |= MMCR0_PMXE;
-
- /*
- * now clear the freeze bit, counting will not start until we
- * rfid from this exception, because only at that point will
- * the PMM bit be cleared
- */
- mmcr0 &= ~MMCR0_FC;
- mtspr(SPRN_MMCR0, mmcr0);
-}
-
-struct op_powerpc_model op_model_rs64 = {
- .reg_setup = rs64_reg_setup,
- .cpu_setup = rs64_cpu_setup,
- .start = rs64_start,
- .stop = rs64_stop,
- .handle_interrupt = rs64_handle_interrupt,
-};
^ permalink raw reply
* [PATCH 6/6] powerpc: reduce oprofile/common.c differences
From: Stephen Rothwell @ 2005-09-19 13:28 UTC (permalink / raw)
To: paulus; +Cc: ppc64-dev, ppc-dev
In-Reply-To: <20050919231051.28fcdf30.sfr@canb.auug.org.au>
Rename and slightly modify {request,free}_perfmon_irq in the ppc code.
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
arch/powerpc/oprofile/common.c | 13 -------------
arch/ppc/kernel/perfmon.c | 10 +++++-----
include/asm-ppc/perfmon.h | 4 ++--
3 files changed, 7 insertions(+), 20 deletions(-)
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
http://www.canb.auug.org.au/~sfr/
b3a2095ea11906c79fd1c43819e9b9c8d4f0ab51
diff --git a/arch/powerpc/oprofile/common.c b/arch/powerpc/oprofile/common.c
--- a/arch/powerpc/oprofile/common.c
+++ b/arch/powerpc/oprofile/common.c
@@ -46,19 +46,12 @@ static void op_handle_interrupt(struct p
static int op_powerpc_setup(void)
{
-#ifdef __powerpc64__
int err;
/* Grab the hardware */
err = reserve_pmc_hardware(op_handle_interrupt);
if (err)
return err;
-#else /* __powerpc64__ */
- /* Install our interrupt handler into the existing hook. */
- if (request_perfmon_irq(&op_handle_interrupt))
- return -EBUSY;
- mb();
-#endif /* __powerpc64__ */
/* Pre-compute the values to stuff in the hardware registers. */
model->reg_setup(ctr, &sys, model->num_counters);
@@ -78,13 +71,7 @@ static int op_powerpc_setup(void)
static void op_powerpc_shutdown(void)
{
-#ifdef __powerpc64__
release_pmc_hardware();
-#else /* __powerpc64__ */
- mb();
- /* Remove our interrupt handler. We may be removing this module. */
- free_perfmon_irq();
-#endif /* __powerpc64__ */
}
static void op_powerpc_cpu_start(void *dummy)
diff --git a/arch/ppc/kernel/perfmon.c b/arch/ppc/kernel/perfmon.c
--- a/arch/ppc/kernel/perfmon.c
+++ b/arch/ppc/kernel/perfmon.c
@@ -61,7 +61,7 @@ void (*perf_irq)(struct pt_regs *) = dum
/* Grab the interrupt, if it's free.
* Returns 0 on success, -1 if the interrupt is taken already */
-int request_perfmon_irq(void (*handler)(struct pt_regs *))
+int reserve_pmc_hardware(void (*handler)(struct pt_regs *))
{
int err = 0;
@@ -71,7 +71,7 @@ int request_perfmon_irq(void (*handler)(
perf_irq = handler;
else {
pr_info("perfmon irq already handled by %p\n", perf_irq);
- err = -1;
+ err = -EBUSY;
}
spin_unlock(&perfmon_lock);
@@ -79,7 +79,7 @@ int request_perfmon_irq(void (*handler)(
return err;
}
-void free_perfmon_irq(void)
+void release_pmc_hardware(void)
{
spin_lock(&perfmon_lock);
@@ -89,5 +89,5 @@ void free_perfmon_irq(void)
}
EXPORT_SYMBOL(perf_irq);
-EXPORT_SYMBOL(request_perfmon_irq);
-EXPORT_SYMBOL(free_perfmon_irq);
+EXPORT_SYMBOL(reserve_pmc_hardware);
+EXPORT_SYMBOL(release_pmc_hardware);
diff --git a/include/asm-ppc/perfmon.h b/include/asm-ppc/perfmon.h
--- a/include/asm-ppc/perfmon.h
+++ b/include/asm-ppc/perfmon.h
@@ -3,8 +3,8 @@
extern void (*perf_irq)(struct pt_regs *);
-int request_perfmon_irq(void (*handler)(struct pt_regs *));
-void free_perfmon_irq(void);
+int reserve_pmc_hardware(void (*handler)(struct pt_regs *));
+void release_pmc_hardware(void);
#ifdef CONFIG_FSL_BOOKE
void init_pmc_stop(int ctr);
^ permalink raw reply
* emac driver broken in 2.6.12.2 ?
From: Peter Fercher @ 2005-09-19 13:37 UTC (permalink / raw)
To: benh; +Cc: linux-ppc-embedded
[-- Attachment #1: Type: text/plain, Size: 836 bytes --]
hi,
i have problems with the IBM EMAC with 2.6.12.2 (the driver worked with
2.4.25)
running on ppc405EP octobus board. Cross compiled on x86 using the eldk-3.1
toolchain
any hints ?
emac: IBM EMAC Ethernet driver, version 2.0
Maintained by Benjamin Herrenschmidt <benh@kernel.crashing.org>
eth0: IBM emac, MAC 00:00:00:00:00:00
eth0: Found Generic MII PHY (0x00)
eth1: IBM emac, MAC 00:00:00:00:00:00
eth1: Found Generic MII PHY (0x01)
cheers, peter
---------------------------------------------------------
Supercomputing Systems AG phone: +41 (0)43 456 16 31
Peter Fercher fax: +41 (0)43 456 16 10
Technoparkstrasse 1 email: peter.fercher@scs.ch
CH-8005 Zuerich url: http://www.scs.ch <http://www.scs.ch/>
---------------------------------------------------------
[-- Attachment #2: Type: text/html, Size: 3639 bytes --]
^ permalink raw reply
* Re: emac driver broken in 2.6.12.2 ?
From: Stefan Roese @ 2005-09-19 13:51 UTC (permalink / raw)
To: linuxppc-embedded; +Cc: Peter Fercher
In-Reply-To: <004101c5bd1f$3d1b91e0$dbe5fed4@scsad.scs.ch>
Hi Peter,
On Monday 19 September 2005 15:37, Peter Fercher wrote:
> i have problems with the IBM EMAC with 2.6.12.2 (the driver worked with
> 2.4.25)
> running on ppc405EP octobus board. Cross compiled on x86 using the eldk-3.1
> toolchain
>
> any hints ?
>
> emac: IBM EMAC Ethernet driver, version 2.0
>
> Maintained by Benjamin Herrenschmidt <benh@kernel.crashing.org>
>
> eth0: IBM emac, MAC 00:00:00:00:00:00
>
> eth0: Found Generic MII PHY (0x00)
>
> eth1: IBM emac, MAC 00:00:00:00:00:00
>
> eth1: Found Generic MII PHY (0x01)
Looks like your board platform file is not copying the MAC addresses into the
ocp struct. Take a look at bubinga_setup_arch() in platforms/4xx/bubinga.c.
Here ibm_ocp_set_emac() is used to copy the addresses.
Best regards,
Stefan
^ permalink raw reply
* RE: emac driver broken in 2.6.12.2 ?
From: Peter Fercher @ 2005-09-19 13:51 UTC (permalink / raw)
To: 'Josh Boyer'; +Cc: 'linux-ppc-embedded'
In-Reply-To: <1127137322.3211.0.camel@windu.rchland.ibm.com>
hi,
when you read the output I have pasted there you can see the following =
(also
in my origninal mail)
eth0: IBM emac, MAC 00:00:00:00:00:00
eth0: Found Generic MII PHY (0x00)
eth1: IBM emac, MAC 00:00:00:00:00:00
eth1: Found Generic MII PHY (0x01)
I think that this MAC addresses are crap (sorry if not formulated =
clearly
enough for you ;)
am I wrong ?
cheers, peter
> -----Original Message-----
> From: Josh Boyer [mailto:jwboyer@jdub.homelinux.org]=20
> Sent: Montag, 19. September 2005 15:42
> To: Peter Fercher
> Cc: benh@kernel.crashing.org; linux-ppc-embedded
> Subject: Re: emac driver broken in 2.6.12.2 ?
>=20
>=20
> On Mon, 2005-09-19 at 15:37 +0200, Peter Fercher wrote:
> > hi,
> > =20
> > i have problems with the IBM EMAC with 2.6.12.2 (the driver worked=20
> > with 2.4.25) running on ppc405EP octobus board. Cross=20
> compiled on x86=20
> > using the eldk-3.1 toolchain
> > =20
> > any hints ?
>=20
> I think you'd need to be more explicit about what "problems"=20
> means. Hard to give hints with what you have here.
>=20
> josh
>=20
>=20
>=20
hi,
=20
i have problems with the IBM EMAC with 2.6.12.2 (the driver worked with
2.4.25)
running on ppc405EP octobus board. Cross compiled on x86 using the =
eldk-3.1
toolchain
=20
any hints ?
=20
emac: IBM EMAC Ethernet driver, version 2.0
Maintained by Benjamin Herrenschmidt <benh@kernel.crashing.org>
eth0: IBM emac, MAC 00:00:00:00:00:00
eth0: Found Generic MII PHY (0x00)
eth1: IBM emac, MAC 00:00:00:00:00:00
eth1: Found Generic MII PHY (0x01)
=20
cheers, peter
---------------------------------------------------------
Supercomputing Systems AG phone: +41 (0)43 456 16 31
Peter Fercher fax: +41 (0)43 456 16 10
Technoparkstrasse 1 email: peter.fercher@scs.ch
CH-8005 Zuerich url: http://www.scs.ch=20
---------------------------------------------------------
=20
^ permalink raw reply
* Re: [PATCH] ppc32: cleanup AMCC PPC4xx eval boards to better support U-Boot
From: Matt Porter @ 2005-09-19 13:59 UTC (permalink / raw)
To: Stefan Roese; +Cc: linuxppc-embedded
In-Reply-To: <200509191302.15462.sr@denx.de>
On Mon, Sep 19, 2005 at 01:02:14PM +0200, Stefan Roese wrote:
> Hi Eugene,
>
> On Friday 16 September 2005 18:27, Eugene Surovegin wrote:
> > On Fri, Sep 16, 2005 at 01:06:16PM +0200, Stefan Roese wrote:
> > > Add U-Boot support to AMCC PPC405 eval boards (bubinga, sycamore and
> > > walnut) and cleanup PPC440 eval boards (bamboo, ebony, luan and ocotea)
> > > to better support U-Boot as bootloader.
> >
> > In general, 44x pieces look OK, but 40x aren't. Notice, that we don't
> > have any #ifdef CONFIG_UBOOT in 44x sources. Let's not add them for
> > 40x, try to replicate the same boot-wrapper approach as Matt used for
> > 44x.
>
> OK. I'll split the patch in two (44x and 40x stuff) so we can get the 44x
> pieces on the way.
>
> Just to be sure: The 44x boot-wrapper approach you mention is
> "boot/simple/pibs.c"?
Yes, there's both boot/simple/pibs.c and boot/simple/openbios.c that
were created so we could have the default firmware and u-boot use the
same kernel build.
-Matt
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox