powerpc: rewrite LOAD_REG_IMMEDIATE() as an intelligent macro

Today LOAD_REG_IMMEDIATE() is a basic #define which loads all
parts on a value into a register, including the parts that are NUL.

This means always 2 instructions on PPC32 and always 5 instructions
on PPC64. And those instructions cannot run in parallele as they are
updating the same register.

Ex: LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) in head_64.S results in:

3c 20 00 00     lis     r1,0
60 21 00 00     ori     r1,r1,0
78 21 07 c6     rldicr  r1,r1,32,31
64 21 00 00     oris    r1,r1,0
60 21 40 00     ori     r1,r1,16384

Rewrite LOAD_REG_IMMEDIATE() with GAS macro in order to skip
the parts that are NUL.

Rename existing LOAD_REG_IMMEDIATE() as LOAD_REG_IMMEDIATE_SYM()
and use that one for loading value of symbols which are not known
at compile time.

Now LOAD_REG_IMMEDIATE(r1,THREAD_SIZE) in head_64.S results in:

38 20 40 00     li      r1,16384
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/d60ce8dd3a383c7adbfc322bf1d53d81724a6000.1566311636.git.christophe.leroy@c-s.fr

arch/powerpc/include/asm/ppc_asm.h

@@ -311,13 +311,43 @@ GLUE(.,name):
 	addis	reg,reg,(name - 0b)@ha;		\
 	addi	reg,reg,(name - 0b)@l;
 
-#ifdef __powerpc64__
-#ifdef HAVE_AS_ATHIGH
+#if defined(__powerpc64__) && defined(HAVE_AS_ATHIGH)
 #define __AS_ATHIGH high
 #else
 #define __AS_ATHIGH h
 #endif
-#define LOAD_REG_IMMEDIATE(reg,expr)		\
+
+.macro __LOAD_REG_IMMEDIATE_32 r, x
+	.if (\x) >= 0x8000 || (\x) < -0x8000
+		lis \r, (\x)@__AS_ATHIGH
+		.if (\x) & 0xffff != 0
+			ori \r, \r, (\x)@l
+		.endif
+	.else
+		li \r, (\x)@l
+	.endif
+.endm
+
+.macro __LOAD_REG_IMMEDIATE r, x
+	.if (\x) >= 0x80000000 || (\x) < -0x80000000
+		__LOAD_REG_IMMEDIATE_32 \r, (\x) >> 32
+		sldi	\r, \r, 32
+		.if (\x) & 0xffff0000 != 0
+			oris \r, \r, (\x)@__AS_ATHIGH
+		.endif
+		.if (\x) & 0xffff != 0
+			ori \r, \r, (\x)@l
+		.endif
+	.else
+		__LOAD_REG_IMMEDIATE_32 \r, \x
+	.endif
+.endm
+
+#ifdef __powerpc64__
+
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg,expr)	\
 	lis     reg,(expr)@highest;		\
 	ori     reg,reg,(expr)@higher;	\
 	rldicr  reg,reg,32,31;		\
@@ -335,11 +365,13 @@ GLUE(.,name):
 
 #else /* 32-bit */
 
-#define LOAD_REG_IMMEDIATE(reg,expr)		\
+#define LOAD_REG_IMMEDIATE(reg, expr) __LOAD_REG_IMMEDIATE_32 reg, expr
+
+#define LOAD_REG_IMMEDIATE_SYM(reg,expr)		\
 	lis	reg,(expr)@ha;		\
 	addi	reg,reg,(expr)@l;
 
-#define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE(reg, name)
+#define LOAD_REG_ADDR(reg,name)		LOAD_REG_IMMEDIATE_SYM(reg, name)
 
 #define LOAD_REG_ADDRBASE(reg, name)	lis	reg,name@ha
 #define ADDROFF(name)			name@l

arch/powerpc/kernel/exceptions-64e.S

@@ -751,8 +751,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 	ld	r14,interrupt_base_book3e@got(r15)
 	ld	r15,__end_interrupts@got(r15)
 #else
-	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
-	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+	LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
+	LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
 #endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
@@ -821,8 +821,8 @@ kernel_dbg_exc:
 	ld	r14,interrupt_base_book3e@got(r15)
 	ld	r15,__end_interrupts@got(r15)
 #else
-	LOAD_REG_IMMEDIATE(r14,interrupt_base_book3e)
-	LOAD_REG_IMMEDIATE(r15,__end_interrupts)
+	LOAD_REG_IMMEDIATE_SYM(r14,interrupt_base_book3e)
+	LOAD_REG_IMMEDIATE_SYM(r15,__end_interrupts)
 #endif
 	cmpld	cr0,r10,r14
 	cmpld	cr1,r10,r15
@@ -1449,7 +1449,7 @@ a2_tlbinit_code_start:
 a2_tlbinit_after_linear_map:
 
 	/* Now we branch the new virtual address mapped by this entry */
-	LOAD_REG_IMMEDIATE(r3,1f)
+	LOAD_REG_IMMEDIATE_SYM(r3,1f)
 	mtctr	r3
 	bctr
 

arch/powerpc/kernel/head_64.S

@@ -635,7 +635,7 @@ __after_prom_start:
 	sub	r5,r5,r11
 #else
 	/* just copy interrupts */
-	LOAD_REG_IMMEDIATE(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+	LOAD_REG_IMMEDIATE_SYM(r5, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
 #endif
 	b	5f
 3: