parisc: Implement new LWS CAS supporting 64 bit operations.

The current LWS cas only works correctly for 32bit. The new LWS allows
for CAS operations of variable size.
Signed-off-by: Guy Martin <gmsoft@tuxicoman.be>
Cc: <stable@vger.kernel.org> # 3.13+
Signed-off-by: Helge Deller <deller@gmx.de>

arch/parisc/kernel/syscall.S

@@ -74,7 +74,7 @@ ENTRY(linux_gateway_page)
 	/* ADDRESS 0xb0 to 0xb8, lws uses two insns for entry */
 	/* Light-weight-syscall entry must always be located at 0xb0 */
 	/* WARNING: Keep this number updated with table size changes */
-#define __NR_lws_entries (2)
+#define __NR_lws_entries (3)
 
 lws_entry:
 	gate	lws_start, %r0		/* increase privilege */
@@ -502,7 +502,7 @@ lws_exit:
 
 	
 	/***************************************************
-		Implementing CAS as an atomic operation:
+		Implementing 32bit CAS as an atomic operation:
 
 		%r26 - Address to examine
 		%r25 - Old value to check (old)
@@ -659,6 +659,230 @@ cas_action:
 	ASM_EXCEPTIONTABLE_ENTRY(2b-linux_gateway_page, 3b-linux_gateway_page)
 
 
+	/***************************************************
+		New CAS implementation which uses pointers and variable size
+		information. The value pointed by old and new MUST NOT change
+		while performing CAS. The lock only protect the value at %r26.
+
+		%r26 - Address to examine
+		%r25 - Pointer to the value to check (old)
+		%r24 - Pointer to the value to set (new)
+		%r23 - Size of the variable (0/1/2/3 for 8/16/32/64 bit)
+		%r28 - Return non-zero on failure
+		%r21 - Kernel error code
+
+		%r21 has the following meanings:
+
+		EAGAIN - CAS is busy, ldcw failed, try again.
+		EFAULT - Read or write failed.
+
+		Scratch: r20, r22, r28, r29, r1, fr4 (32bit for 64bit CAS only)
+
+	****************************************************/
+
+	/* ELF32 Process entry path */
+lws_compare_and_swap_2:
+#ifdef CONFIG_64BIT
+	/* Clip the input registers */
+	depdi	0, 31, 32, %r26
+	depdi	0, 31, 32, %r25
+	depdi	0, 31, 32, %r24
+	depdi	0, 31, 32, %r23
+#endif
+
+	/* Check the validity of the size pointer */
+	subi,>>= 4, %r23, %r0
+	b,n	lws_exit_nosys
+
+	/* Jump to the functions which will load the old and new values into
+	   registers depending on the their size */
+	shlw	%r23, 2, %r29
+	blr	%r29, %r0
+	nop
+
+	/* 8bit load */
+4:	ldb	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+5:	ldb	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 16bit load */
+6:	ldh	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+7:	ldh	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 32bit load */
+8:	ldw	0(%sr3,%r25), %r25
+	b	cas2_lock_start
+9:	ldw	0(%sr3,%r24), %r24
+	nop
+	nop
+	nop
+	nop
+	nop
+
+	/* 64bit load */
+#ifdef CONFIG_64BIT
+10:	ldd	0(%sr3,%r25), %r25
+11:	ldd	0(%sr3,%r24), %r24
+#else
+	/* Load new value into r22/r23 - high/low */
+10:	ldw	0(%sr3,%r25), %r22
+11:	ldw	4(%sr3,%r25), %r23
+	/* Load new value into fr4 for atomic store later */
+12:	flddx	0(%sr3,%r24), %fr4
+#endif
+
+cas2_lock_start:
+	/* Load start of lock table */
+	ldil	L%lws_lock_start, %r20
+	ldo	R%lws_lock_start(%r20), %r28
+
+	/* Extract four bits from r26 and hash lock (Bits 4-7) */
+	extru  %r26, 27, 4, %r20
+
+	/* Find lock to use, the hash is either one of 0 to
+	   15, multiplied by 16 (keep it 16-byte aligned)
+	   and add to the lock table offset. */
+	shlw	%r20, 4, %r20
+	add	%r20, %r28, %r20
+
+	rsm	PSW_SM_I, %r0			/* Disable interrupts */
+	/* COW breaks can cause contention on UP systems */
+	LDCW	0(%sr2,%r20), %r28		/* Try to acquire the lock */
+	cmpb,<>,n	%r0, %r28, cas2_action	/* Did we get it? */
+cas2_wouldblock:
+	ldo	2(%r0), %r28			/* 2nd case */
+	ssm	PSW_SM_I, %r0
+	b	lws_exit			/* Contended... */
+	ldo	-EAGAIN(%r0), %r21		/* Spin in userspace */
+
+	/*
+		prev = *addr;
+		if ( prev == old )
+		  *addr = new;
+		return prev;
+	*/
+
+	/* NOTES:
+		This all works becuse intr_do_signal
+		and schedule both check the return iasq
+		and see that we are on the kernel page
+		so this process is never scheduled off
+		or is ever sent any signal of any sort,
+		thus it is wholly atomic from usrspaces
+		perspective
+	*/
+cas2_action:
+	/* Jump to the correct function */
+	blr	%r29, %r0
+	/* Set %r28 as non-zero for now */
+	ldo	1(%r0),%r28
+
+	/* 8bit CAS */
+13:	ldb,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+14:	stb,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 16bit CAS */
+15:	ldh,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+16:	sth,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 32bit CAS */
+17:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+18:	stw,ma	%r24, 0(%sr3,%r26)
+	b	cas2_end
+	copy	%r0, %r28
+	nop
+	nop
+
+	/* 64bit CAS */
+#ifdef CONFIG_64BIT
+19:	ldd,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r25, %r0
+	b,n	cas2_end
+20:	std,ma	%r24, 0(%sr3,%r26)
+	copy	%r0, %r28
+#else
+	/* Compare first word */
+19:	ldw,ma	0(%sr3,%r26), %r29
+	sub,=	%r29, %r22, %r0
+	b,n	cas2_end
+	/* Compare second word */
+20:	ldw,ma	4(%sr3,%r26), %r29
+	sub,=	%r29, %r23, %r0
+	b,n	cas2_end
+	/* Perform the store */
+21:	fstdx	%fr4, 0(%sr3,%r26)
+	copy	%r0, %r28
+#endif
+
+cas2_end:
+	/* Free lock */
+	stw,ma	%r20, 0(%sr2,%r20)
+	/* Enable interrupts */
+	ssm	PSW_SM_I, %r0
+	/* Return to userspace, set no error */
+	b	lws_exit
+	copy	%r0, %r21
+
+22:
+	/* Error occurred on load or store */
+	/* Free lock */
+	stw	%r20, 0(%sr2,%r20)
+	ssm	PSW_SM_I, %r0
+	ldo	1(%r0),%r28
+	b	lws_exit
+	ldo	-EFAULT(%r0),%r21	/* set errno */
+	nop
+	nop
+	nop
+
+	/* Exception table entries, for the load and store, return EFAULT.
+	   Each of the entries must be relocated. */
+	ASM_EXCEPTIONTABLE_ENTRY(4b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(5b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(6b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(7b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(8b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(9b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(10b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(11b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(13b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(14b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(15b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(16b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(17b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(18b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(19b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(20b-linux_gateway_page, 22b-linux_gateway_page)
+#ifndef CONFIG_64BIT
+	ASM_EXCEPTIONTABLE_ENTRY(12b-linux_gateway_page, 22b-linux_gateway_page)
+	ASM_EXCEPTIONTABLE_ENTRY(21b-linux_gateway_page, 22b-linux_gateway_page)
+#endif
+
 	/* Make sure nothing else is placed on this page */
 	.align PAGE_SIZE
 END(linux_gateway_page)
@@ -675,8 +899,9 @@ ENTRY(end_linux_gateway_page)
 	/* Light-weight-syscall table */
 	/* Start of lws table. */
 ENTRY(lws_table)
-	LWS_ENTRY(compare_and_swap32)	/* 0 - ELF32 Atomic compare and swap */
-	LWS_ENTRY(compare_and_swap64)	/* 1 - ELF64 Atomic compare and swap */
+	LWS_ENTRY(compare_and_swap32)		/* 0 - ELF32 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap64)		/* 1 - ELF64 Atomic 32bit CAS */
+	LWS_ENTRY(compare_and_swap_2)		/* 2 - ELF32 Atomic 64bit CAS */
 END(lws_table)
 	/* End of lws table */