[PATCH 3/7] [RFC][V2] add support for BlueGene/P Double FPU

From: Eric Van Hensbergen
Date: Thu May 19 2011 - 17:41:38 EST

Next message: Jim Cromie: "[PATCH 04/23] use register_chrdev_ids in drivers/tty/"
Previous message: Serge E. Hallyn: "Re: [PATCH v5 03/21] evm: re-release"
In reply to: Benjamin Herrenschmidt: "Re: [PATCH 3/7] [RFC] add support for BlueGene/P FPU"
Next in thread: Eric Van Hensbergen: "[PATCH 5/7] [RFC] force 32-byte aligned kmallocs"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

This patch adds save/restore register support for the BlueGene/P
double FPU. Since there are two FPUs, we need to save and restore
twice the registers. Fortunately BG/P gives us some opcodes to
assist with that task.

Signed-off-by: Eric Van Hensbergen <ericvh@xxxxxxxxx>
---
arch/powerpc/include/asm/ppc-opcode.h | 9 +++++++++
arch/powerpc/include/asm/ppc_asm.h | 32 ++++++++++++++++++++------------
arch/powerpc/kernel/fpu.S | 8 ++++----
arch/powerpc/platforms/44x/Kconfig | 9 +++++++++
arch/powerpc/platforms/Kconfig.cputype | 4 ++++
5 files changed, 46 insertions(+), 16 deletions(-)

diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index 1255569..12a3cc9 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -56,6 +56,9 @@
#define PPC_INST_TLBSRX_DOT 0x7c0006a5
#define PPC_INST_XXLOR 0xf0000510

+#define PPC_INST_LFPDX 0x7c00039c
+#define PPC_INST_STFPDX 0x7c00079c
+
/* macros to insert fields into opcodes */
#define __PPC_RA(a) (((a) & 0x1f) << 16)
#define __PPC_RB(b) (((b) & 0x1f) << 11)
@@ -126,4 +129,10 @@
#define XXLOR(t, a, b) stringify_in_c(.long PPC_INST_XXLOR | \
VSX_XX3((t), (a), (b)))

+#define LFPDX(t, a, b) stringify_in_c(.long PPC_INST_LFPDX | \
+ __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)))
+#define STFPDX(t, a, b) stringify_in_c(.long PPC_INST_STFPDX | \
+ __PPC_RT(t) | __PPC_RA(a) | __PPC_RB(b)))
+
+
#endif /* _ASM_POWERPC_PPC_OPCODE_H */
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index 9821006..c5f05ad 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -97,18 +97,26 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
#define REST_8GPRS(n, base) REST_4GPRS(n, base); REST_4GPRS(n+4, base)
#define REST_10GPRS(n, base) REST_8GPRS(n, base); REST_2GPRS(n+8, base)

-#define SAVE_FPR(n, base) stfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
-#define SAVE_2FPRS(n, base) SAVE_FPR(n, base); SAVE_FPR(n+1, base)
-#define SAVE_4FPRS(n, base) SAVE_2FPRS(n, base); SAVE_2FPRS(n+2, base)
-#define SAVE_8FPRS(n, base) SAVE_4FPRS(n, base); SAVE_4FPRS(n+4, base)
-#define SAVE_16FPRS(n, base) SAVE_8FPRS(n, base); SAVE_8FPRS(n+8, base)
-#define SAVE_32FPRS(n, base) SAVE_16FPRS(n, base); SAVE_16FPRS(n+16, base)
-#define REST_FPR(n, base) lfd n,THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
-#define REST_2FPRS(n, base) REST_FPR(n, base); REST_FPR(n+1, base)
-#define REST_4FPRS(n, base) REST_2FPRS(n, base); REST_2FPRS(n+2, base)
-#define REST_8FPRS(n, base) REST_4FPRS(n, base); REST_4FPRS(n+4, base)
-#define REST_16FPRS(n, base) REST_8FPRS(n, base); REST_8FPRS(n+8, base)
-#define REST_32FPRS(n, base) REST_16FPRS(n, base); REST_16FPRS(n+16, base)
+#ifdef CONFIG_DOUBLE_FPU
+#define SAVE_FPR(n, b, base) li b, THREAD_FPR0+(16*(n)); STFPDX(n, base, b)
+#define REST_FPR(n, b, base) li b, THREAD_FPR0+(16*(n)); LFPDX(n, base, b)
+#else /* CONFIG_DOUBLE_FPU */
+#define SAVE_FPR(n, b, base) stfd n, THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#define REST_FPR(n, b, base) lfd n, THREAD_FPR0+8*TS_FPRWIDTH*(n)(base)
+#endif /* CONFIG_DOUBLE_FPU */
+
+#define SAVE_2FPRS(n, b, base) SAVE_FPR(n, b, base); SAVE_FPR(n+1, b, base)
+#define SAVE_4FPRS(n, b, base) SAVE_2FPRS(n, b, base); SAVE_2FPRS(n+2, b, base)
+#define SAVE_8FPRS(n, b, base) SAVE_4FPRS(n, b, base); SAVE_4FPRS(n+4, b, base)
+#define SAVE_16FPRS(n, b, base) SAVE_8FPRS(n, b, base); SAVE_8FPRS(n+8, b, base)
+#define SAVE_32FPRS(n, b, base) SAVE_16FPRS(n, b, base); \
+ SAVE_16FPRS(n+16, b, base)
+#define REST_2FPRS(n, b, base) REST_FPR(n, b, base); REST_FPR(n+1, b, base)
+#define REST_4FPRS(n, b, base) REST_2FPRS(n, b, base); REST_2FPRS(n+2, b, base)
+#define REST_8FPRS(n, b, base) REST_4FPRS(n, b, base); REST_4FPRS(n+4, b, base)
+#define REST_16FPRS(n, b, base) REST_8FPRS(n, b, base); REST_8FPRS(n+8, b, base)
+#define REST_32FPRS(n, b, base) REST_16FPRS(n, b, base); \
+ REST_16FPRS(n+16, b, base)

#define SAVE_VR(n,b,base) li b,THREAD_VR0+(16*(n)); stvx n,base,b
#define SAVE_2VRS(n,b,base) SAVE_VR(n,b,base); SAVE_VR(n+1,b,base)
diff --git a/arch/powerpc/kernel/fpu.S b/arch/powerpc/kernel/fpu.S
index de36955..9f11c66 100644
--- a/arch/powerpc/kernel/fpu.S
+++ b/arch/powerpc/kernel/fpu.S
@@ -30,7 +30,7 @@
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
- REST_32FPRS(n,base); \
+ REST_32FPRS(n,c,base); \
b 3f; \
2: REST_32VSRS(n,c,base); \
3:
@@ -39,13 +39,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
BEGIN_FTR_SECTION \
b 2f; \
END_FTR_SECTION_IFSET(CPU_FTR_VSX); \
- SAVE_32FPRS(n,base); \
+ SAVE_32FPRS(n,c,base); \
b 3f; \
2: SAVE_32VSRS(n,c,base); \
3:
#else
-#define REST_32FPVSRS(n,b,base) REST_32FPRS(n, base)
-#define SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n, base)
+#define REST_32FPVSRS(n,b,base) REST_32FPRS(n,b,base)
+#define SAVE_32FPVSRS(n,b,base) SAVE_32FPRS(n,b,base)
#endif

/*
diff --git a/arch/powerpc/platforms/44x/Kconfig b/arch/powerpc/platforms/44x/Kconfig
index f485fc5f..24a515e 100644
--- a/arch/powerpc/platforms/44x/Kconfig
+++ b/arch/powerpc/platforms/44x/Kconfig
@@ -169,6 +169,15 @@ config YOSEMITE
help
This option enables support for the AMCC PPC440EP evaluation board.

+config BGP
+ bool "Blue Gene/P"
+ depends on 44x
+ default n
+ select PPC_FPU
+ select PPC_DOUBLE_FPU
+ help
+ This option enables support for the IBM BlueGene/P supercomputer.
+
config ISS4xx
bool "ISS 4xx Simulator"
depends on (44x || 40x)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 111138c..1ae59c5 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -137,6 +137,10 @@ config PPC_FPU
bool
default y if PPC64

+config PPC_DOUBLE_FPU
+ bool "Bluegene/P Double FPU Support"
+ depends on BGP
+
config FSL_EMB_PERFMON
bool "Freescale Embedded Perfmon"
depends on E500 || PPC_83xx
--
1.7.4.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

Next message: Jim Cromie: "[PATCH 04/23] use register_chrdev_ids in drivers/tty/"
Previous message: Serge E. Hallyn: "Re: [PATCH v5 03/21] evm: re-release"
In reply to: Benjamin Herrenschmidt: "Re: [PATCH 3/7] [RFC] add support for BlueGene/P FPU"
Next in thread: Eric Van Hensbergen: "[PATCH 5/7] [RFC] force 32-byte aligned kmallocs"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]