parisc: Add alternative coding infrastructure

This patch adds the necessary code to patch a running kernel at runtime
to improve performance.

The current implementation offers a few optimizations variants:

- When running a SMP kernel on a single UP processor, unwanted assembler
statements like locking functions are overwritten with NOPs. When
multiple instructions shall be skipped, one branch instruction is used
instead of multiple nop instructions.

- In the UP case, some pdtlb and pitlb instructions are patched to
become pdtlb,l and pitlb,l which only flushes the CPU-local tlb
entries instead of broadcasting the flush to other CPUs in the system
and thus may improve performance.

- fic and fdc instructions are skipped if no I- or D-caches are
installed. This should speed up qemu emulation and cacheless systems.

- If no cache coherence is needed for IO operations, the relevant fdc
and sync instructions in the sba and ccio drivers are replaced by
nops.

- On systems which share I- and D-TLBs and thus don't have a seperate
instruction TLB, the pitlb instruction is replaced by a nop.

Live-patching is done early in the boot process, just after having run
the system inventory. No drivers are running and thus no external
interrupts should arrive. So the hope is that no TLB exceptions will
occur during the patching. If this turns out to be wrong we will
probably need to do the patching in real-mode.

Signed-off-by: Helge Deller <[e-mail]>

arch/parisc/include/asm/alternative.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ASM_PARISC_ALTERNATIVE_H
+#define __ASM_PARISC_ALTERNATIVE_H
+
+#define ALT_COND_NO_SMP		0x01	/* when running UP instead of SMP */
+#define ALT_COND_NO_DCACHE	0x02	/* if system has no d-cache  */
+#define ALT_COND_NO_ICACHE	0x04	/* if system has no i-cache  */
+#define ALT_COND_NO_SPLIT_TLB	0x08	/* if split_tlb == 0  */
+#define ALT_COND_NO_IOC_FDC	0x10	/* if I/O cache does not need flushes */
+
+#define INSN_PxTLB	0x02		/* modify pdtlb, pitlb */
+#define INSN_NOP	0x08000240	/* nop */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/stringify.h>
+
+struct alt_instr {
+	s32 orig_offset;	/* offset to original instructions */
+	u32 len;		/* end of original instructions */
+	u32 cond;		/* see ALT_COND_XXX */
+	u32 replacement;	/* replacement instruction or code */
+};
+
+void set_kernel_text_rw(int enable_read_write);
+
+/* Alternative SMP implementation. */
+#define ALTERNATIVE(cond, replacement)		"!0:"	\
+	".section .altinstructions, \"aw\"	!"	\
+	".word (0b-4-.), 1, " __stringify(cond) ","	\
+		__stringify(replacement) "	!"	\
+	".previous"
+
+#else
+
+#define ALTERNATIVE(from, to, cond, replacement)\
+	.section .altinstructions, "aw"	!	\
+	.word (from - .), (to - from)/4	!	\
+	.word cond, replacement		!	\
+	.previous
+
+#endif  /*  __ASSEMBLY__  */
+
+#endif /* __ASM_PARISC_ALTERNATIVE_H */

arch/parisc/include/asm/cache.h

···
 #ifndef __ARCH_PARISC_CACHE_H
 #define __ARCH_PARISC_CACHE_H
 
+#include <asm/alternative.h>
 
 /*
  * PA 2.0 processors have 64 and 128-byte L2 cachelines; PA 1.1 processors
···
 extern struct pdc_cache_info cache_info;
 void parisc_setup_cache_timing(void);
 
-#define pdtlb(addr)         asm volatile("pdtlb 0(%%sr1,%0)" : : "r" (addr));
-#define pitlb(addr)         asm volatile("pitlb 0(%%sr1,%0)" : : "r" (addr));
-#define pdtlb_kernel(addr)  asm volatile("pdtlb 0(%0)" : : "r" (addr));
+#define pdtlb(addr)	asm volatile("pdtlb 0(%%sr1,%0)" \
+			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
+			: : "r" (addr))
+#define pitlb(addr)	asm volatile("pitlb 0(%%sr1,%0)" \
+			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
+			ALTERNATIVE(ALT_COND_NO_SPLIT_TLB, INSN_NOP) \
+			: : "r" (addr))
+#define pdtlb_kernel(addr)  asm volatile("pdtlb 0(%0)"   \
+			ALTERNATIVE(ALT_COND_NO_SMP, INSN_PxTLB) \
+			: : "r" (addr))
+
+#define asm_io_fdc(addr) asm volatile("fdc %%r0(%0)" \
+			ALTERNATIVE(ALT_COND_NO_DCACHE, INSN_NOP) \
+			ALTERNATIVE(ALT_COND_NO_IOC_FDC, INSN_NOP) \
+			: : "r" (addr))
+#define asm_io_sync()	asm volatile("sync" \
+			ALTERNATIVE(ALT_COND_NO_DCACHE, INSN_NOP) \
+			ALTERNATIVE(ALT_COND_NO_IOC_FDC, INSN_NOP) :: )
 
 #endif /* ! __ASSEMBLY__ */
 

arch/parisc/include/asm/pgtable.h

···
 {
 	mtsp(mm->context, 1);
 	pdtlb(addr);
-	if (unlikely(split_tlb))
-		pitlb(addr);
+	pitlb(addr);
 }
 
 /* Certain architectures need to do special things when PTEs

arch/parisc/include/asm/sections.h

···
 /* nothing to see, move along */
 #include <asm-generic/sections.h>
 
+extern char __alt_instructions[], __alt_instructions_end[];
+
 #ifdef CONFIG_64BIT
 
 #define HAVE_DEREFERENCE_FUNCTION_DESCRIPTOR 1

arch/parisc/include/asm/tlbflush.h

···
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	if (unlikely(split_tlb))
-		pitlb(addr);
+	pitlb(addr);
 	purge_tlb_end(flags);
 }
 #endif

arch/parisc/kernel/cache.c

···
 	/* Purge TLB entries for small ranges using the pdtlb and
 	   pitlb instructions.  These instructions execute locally
 	   but cause a purge request to be broadcast to other TLBs.  */
-	if (likely(!split_tlb)) {
-		while (start < end) {
-			purge_tlb_start(flags);
-			mtsp(sid, 1);
-			pdtlb(start);
-			purge_tlb_end(flags);
-			start += PAGE_SIZE;
-		}
-		return 0;
-	}
-
-	/* split TLB case */
 	while (start < end) {
 		purge_tlb_start(flags);
 		mtsp(sid, 1);

arch/parisc/kernel/entry.S

···
 #include <asm/ldcw.h>
 #include <asm/traps.h>
 #include <asm/thread_info.h>
+#include <asm/alternative.h>
 
 #include <linux/linkage.h>
 
···
 	/* Acquire pa_tlb_lock lock and check page is present. */
 	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
-	cmpib,COND(=),n	0,\spc,2f
+98:	cmpib,COND(=),n	0,\spc,2f
 	load_pa_tlb_lock \tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
···
 	bb,<,n		\pte,_PAGE_PRESENT_BIT,3f
 	b		\fault
 	stw,ma		\spc,0(\tmp)
+99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 2:	LDREG		0(\ptp),\pte
 	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
···
 	/* Release pa_tlb_lock lock without reloading lock address. */
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
+98:	or,COND(=)	%r0,\spc,%r0
 	stw,ma		\spc,0(\tmp)
+99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 	.endm
 
 	/* Release pa_tlb_lock lock. */
 	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load_pa_tlb_lock \tmp
+98:	load_pa_tlb_lock \tmp
+99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 	tlb_unlock0	\spc,\tmp
 #endif
 	.endm

arch/parisc/kernel/pacache.S

···
 #include <asm/pgtable.h>
 #include <asm/cache.h>
 #include <asm/ldcw.h>
+#include <asm/alternative.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
 
···
 	.import cache_info,data
 
 ENTRY_CFI(flush_instruction_cache_local)
-	load32		cache_info, %r1
+88:	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
 
···
 fisync:
 	sync
 	mtsm		%r22			/* restore I-bit */
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_instruction_cache_local)
···
 
 	.import cache_info, data
 ENTRY_CFI(flush_data_cache_local)
-	load32		cache_info, %r1
+88:	load32		cache_info, %r1
 
 	/* Flush Data Cache */
 
···
 	syncdma
 	sync
 	mtsm		%r22			/* restore I-bit */
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_data_cache_local)
···
 
 	.macro	tlb_lock	la,flags,tmp
 #ifdef CONFIG_SMP
+98:
 #if __PA_LDCW_ALIGNMENT > 4
 	load32		pa_tlb_lock + __PA_LDCW_ALIGNMENT-1, \la
 	depi		0,31,__PA_LDCW_ALIGN_ORDER, \la
···
 	nop
 	b,n		2b
 3:
+99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 	.endm
 
 	.macro	tlb_unlock	la,flags,tmp
 #ifdef CONFIG_SMP
-	ldi		1,\tmp
+98:	ldi		1,\tmp
 	sync
 	stw		\tmp,0(\la)
 	mtsm		\flags
+99:	ALTERNATIVE(98b, 99b, ALT_COND_NO_SMP, INSN_NOP)
 #endif
 	.endm
 
···
 	pdtlb,l		%r0(%r29)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		%r0(%r28)
-	pdtlb		%r0(%r29)
+0:	pdtlb		%r0(%r28)
+1:	pdtlb		%r0(%r29)
 	tlb_unlock	%r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
+	ALTERNATIVE(1b, 1b+4, ALT_COND_NO_SMP, INSN_PxTLB)
 #endif
 
 #ifdef CONFIG_64BIT
···
 	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		%r0(%r28)
+0:	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
 #endif
 
 #ifdef CONFIG_64BIT
···
 	pdtlb,l		%r0(%r28)
 #else
 	tlb_lock	%r20,%r21,%r22
-	pdtlb		%r0(%r28)
+0:	pdtlb		%r0(%r28)
 	tlb_unlock	%r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
 #endif
 
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), r31
 
 #ifdef CONFIG_64BIT
···
 	cmpb,COND(<<)	%r28, %r25,1b
 	fdc,m		r31(%r28)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
···
 
 #ifdef CONFIG_PA20
 	pdtlb,l		%r0(%r28)
-	pitlb,l         %r0(%sr4,%r28)
+1:	pitlb,l         %r0(%sr4,%r28)
+	ALTERNATIVE(1b, 1b+4, ALT_COND_NO_SPLIT_TLB, INSN_NOP)
 #else
 	tlb_lock        %r20,%r21,%r22
-	pdtlb		%r0(%r28)
-	pitlb           %r0(%sr4,%r28)
+0:	pdtlb		%r0(%r28)
+1:	pitlb           %r0(%sr4,%r28)
 	tlb_unlock      %r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
+	ALTERNATIVE(1b, 1b+4, ALT_COND_NO_SMP, INSN_PxTLB)
+	ALTERNATIVE(1b, 1b+4, ALT_COND_NO_SPLIT_TLB, INSN_NOP)
 #endif
 
-	ldil		L%icache_stride, %r1
+88:	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r31
 
 #ifdef CONFIG_64BIT
···
 	cmpb,COND(<<)	%r28, %r25,1b
 	fic,m		%r31(%sr4,%r28)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_icache_page_asm)
 
 ENTRY_CFI(flush_kernel_dcache_page_asm)
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
 #ifdef CONFIG_64BIT
···
 	cmpb,COND(<<)		%r26, %r25,1b
 	fdc,m		%r23(%r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_kernel_dcache_page_asm)
 
 ENTRY_CFI(purge_kernel_dcache_page_asm)
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
 #ifdef CONFIG_64BIT
···
 	cmpb,COND(<<)		%r26, %r25, 1b
 	pdc,m		%r23(%r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(purge_kernel_dcache_page_asm)
 
 ENTRY_CFI(flush_user_dcache_range_asm)
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
···
 1:      cmpb,COND(<<),n	%r26, %r25, 1b
 	fdc,m		%r23(%sr3, %r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_user_dcache_range_asm)
 
 ENTRY_CFI(flush_kernel_dcache_range_asm)
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
···
 	fdc,m		%r23(%r26)
 
 	sync
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	syncdma
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
 ENTRY_CFI(purge_kernel_dcache_range_asm)
-	ldil		L%dcache_stride, %r1
+88:	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
···
 	pdc,m		%r23(%r26)
 
 	sync
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	syncdma
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(purge_kernel_dcache_range_asm)
 
 ENTRY_CFI(flush_user_icache_range_asm)
-	ldil		L%icache_stride, %r1
+88:	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
···
 1:      cmpb,COND(<<),n	%r26, %r25,1b
 	fic,m		%r23(%sr3, %r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_user_icache_range_asm)
 
 ENTRY_CFI(flush_kernel_icache_page)
-	ldil		L%icache_stride, %r1
+88:	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 
 #ifdef CONFIG_64BIT
···
 	cmpb,COND(<<)		%r26, %r25, 1b
 	fic,m		%r23(%sr4, %r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_kernel_icache_page)
 
 ENTRY_CFI(flush_kernel_icache_range_asm)
-	ldil		L%icache_stride, %r1
+88:	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
 	ANDCM		%r26, %r21, %r26
···
 1:      cmpb,COND(<<),n	%r26, %r25, 1b
 	fic,m		%r23(%sr4, %r26)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_ICACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop

arch/parisc/kernel/setup.c

···
 	return 0;
 }
 
+static int no_alternatives __initdata;
+static int __init setup_no_alternatives(char *str)
+{
+	no_alternatives = 1;
+	return 1;
+}
+__setup("no-alternatives", setup_no_alternatives);
+
+static void __init apply_alternatives_all(void)
+{
+	struct alt_instr *entry;
+	int index = 0, applied = 0;
+
+
+	pr_info("alternatives: %spatching kernel code\n",
+		no_alternatives ? "NOT " : "");
+	if (no_alternatives)
+		return;
+
+	set_kernel_text_rw(1);
+
+	for (entry = (struct alt_instr *) &__alt_instructions;
+		entry < (struct alt_instr *) &__alt_instructions_end;
+		entry++, index++) {
+
+		u32 *from, len, cond, replacement;
+
+		from = (u32 *)((ulong)&entry->orig_offset + entry->orig_offset);
+		len = entry->len;
+		cond = entry->cond;
+		replacement = entry->replacement;
+
+		WARN_ON(!cond);
+		pr_debug("Check %d: Cond 0x%x, Replace %02d instructions @ 0x%px with 0x%08x\n",
+			index, cond, len, from, replacement);
+
+		if ((cond & ALT_COND_NO_SMP) && (num_online_cpus() != 1))
+			continue;
+		if ((cond & ALT_COND_NO_DCACHE) && (cache_info.dc_size != 0))
+			continue;
+		if ((cond & ALT_COND_NO_ICACHE) && (cache_info.ic_size != 0))
+			continue;
+
+		/*
+		 * If the PDC_MODEL capabilities has Non-coherent IO-PDIR bit
+		 * set (bit #61, big endian), we have to flush and sync every
+		 * time IO-PDIR is changed in Ike/Astro.
+		 */
+		if ((cond & ALT_COND_NO_IOC_FDC) &&
+			(boot_cpu_data.pdc.capabilities & PDC_MODEL_IOPDIR_FDC))
+			continue;
+
+		/* Want to replace pdtlb by a pdtlb,l instruction? */
+		if (replacement == INSN_PxTLB) {
+			replacement = *from;
+			if (boot_cpu_data.cpu_type >= pcxu) /* >= pa2.0 ? */
+				replacement |= (1 << 10); /* set el bit */
+		}
+
+		/*
+		 * Replace instruction with NOPs?
+		 * For long distance insert a branch instruction instead.
+		 */
+		if (replacement == INSN_NOP && len > 1)
+			replacement = 0xe8000002 + (len-2)*8; /* "b,n .+8" */
+
+		pr_debug("Do    %d: Cond 0x%x, Replace %02d instructions @ 0x%px with 0x%08x\n",
+			index, cond, len, from, replacement);
+
+		/* Replace instruction */
+		*from = replacement;
+		applied++;
+	}
+
+	pr_info("alternatives: applied %d out of %d patches\n", applied, index);
+
+	set_kernel_text_rw(0);
+}
+
+
 extern void gsc_init(void);
 extern void processor_init(void);
 extern void ccio_init(void);
···
 			boot_cpu_data.cpu_hz / 1000000,
 			boot_cpu_data.cpu_hz % 1000000	);
 
+	apply_alternatives_all();
 	parisc_setup_cache_timing();
 
 	/* These are in a non-obvious order, will fix when we have an iotree */

arch/parisc/kernel/signal.c

···
 #define INSN_LDI_R25_1	 0x34190002 /* ldi  1,%r25 (in_syscall=1) */
 #define INSN_LDI_R20	 0x3414015a /* ldi  __NR_rt_sigreturn,%r20 */
 #define INSN_BLE_SR2_R0  0xe4008200 /* be,l 0x100(%sr2,%r0),%sr0,%r31 */
-#define INSN_NOP	 0x08000240 /* nop */
 /* For debugging */
 #define INSN_DIE_HORRIBLY 0x68000ccc /* stw %r0,0x666(%sr0,%r0) */
 

arch/parisc/kernel/vmlinux.lds.S

···
 		EXIT_DATA
 	}
 	PERCPU_SECTION(8)
+	. = ALIGN(4);
+	.altinstructions : {
+		__alt_instructions = .;
+		*(.altinstructions)
+		__alt_instructions_end = .;
+	}
 	. = ALIGN(HUGEPAGE_SIZE);
 	__init_end = .;
 	/* freed after init ends here */

arch/parisc/mm/init.c

···
 	}
 }
 
+void __init set_kernel_text_rw(int enable_read_write)
+{
+	unsigned long start = (unsigned long)_stext;
+	unsigned long end   = (unsigned long)_etext;
+
+	map_pages(start, __pa(start), end-start,
+		PAGE_KERNEL_RWX, enable_read_write ? 1:0);
+
+	/* force the kernel to see the new TLB entries */
+	__flush_tlb_range(0, start, end);
+
+	/* dump old cached instructions */
+	flush_icache_range(start, end);
+}
+
 void __ref free_initmem(void)
 {
 	unsigned long init_begin = (unsigned long)__init_begin;

drivers/parisc/ccio-dma.c

···
 	**        PCX-T'? Don't know. (eg C110 or similar K-class)
 	**
 	** See PDC_MODEL/option 0/SW_CAP word for "Non-coherent IO-PDIR bit".
-	** Hopefully we can patch (NOP) these out at boot time somehow.
 	**
 	** "Since PCX-U employs an offset hash that is incompatible with
 	** the real mode coherence index generation of U2, the PDIR entry
 	** must be flushed to memory to retain coherence."
 	*/
-	asm volatile("fdc %%r0(%0)" : : "r" (pdir_ptr));
-	asm volatile("sync");
+	asm_io_fdc(pdir_ptr);
+	asm_io_sync();
 }
 
 /**
···
 		** FIXME: PCX_W platforms don't need FDC/SYNC. (eg C360)
 		**   PCX-U/U+ do. (eg C200/C240)
 		** See PDC_MODEL/option 0/SW_CAP for "Non-coherent IO-PDIR bit".
-		**
-		** Hopefully someone figures out how to patch (NOP) the
-		** FDC/SYNC out at boot time.
 		*/
-		asm volatile("fdc %%r0(%0)" : : "r" (pdir_ptr[7]));
+		asm_io_fdc(pdir_ptr);
 
 		iovp     += IOVP_SIZE;
 		byte_cnt -= IOVP_SIZE;
 	}
 
-	asm volatile("sync");
+	asm_io_sync();
 	ccio_clear_io_tlb(ioc, CCIO_IOVP(iova), saved_byte_cnt);
 }
 

drivers/parisc/sba_iommu.c

···
 	 * (bit #61, big endian), we have to flush and sync every time
 	 * IO-PDIR is changed in Ike/Astro.
 	 */
-	if (ioc_needs_fdc)
-		asm volatile("fdc %%r0(%0)" : : "r" (pdir_ptr));
+	asm_io_fdc(pdir_ptr);
 }
 
 
···
 		do {
 			/* clear I/O Pdir entry "valid" bit first */
 			((u8 *) pdir_ptr)[7] = 0;
+			asm_io_fdc(pdir_ptr);
 			if (ioc_needs_fdc) {
-				asm volatile("fdc %%r0(%0)" : : "r" (pdir_ptr));
 #if 0
 				entries_per_cacheline = L1_CACHE_SHIFT - 3;
 #endif
···
 	** could dump core on HPMC.
 	*/
 	((u8 *) pdir_ptr)[7] = 0;
-	if (ioc_needs_fdc)
-		asm volatile("fdc %%r0(%0)" : : "r" (pdir_ptr));
+	asm_io_fdc(pdir_ptr);
 
 	WRITE_REG( SBA_IOVA(ioc, iovp, 0, 0), ioc->ioc_hpa+IOC_PCOM);
 }
···
 	}
 
 	/* force FDC ops in io_pdir_entry() to be visible to IOMMU */
-	if (ioc_needs_fdc)
-		asm volatile("sync" : : );
+	asm_io_sync();
 
 #ifdef ASSERT_PDIR_SANITY
 	sba_check_pdir(ioc,"Check after sba_map_single()");
···
 	sba_free_range(ioc, iova, size);
 
 	/* If fdc's were issued, force fdc's to be visible now */
-	if (ioc_needs_fdc)
-		asm volatile("sync" : : );
+	asm_io_sync();
 
 	READ_REG(ioc->ioc_hpa+IOC_PCOM);	/* flush purges */
 #endif /* DELAYED_RESOURCE_CNT == 0 */
···
 	filled = iommu_fill_pdir(ioc, sglist, nents, 0, sba_io_pdir_entry);
 
 	/* force FDC ops in io_pdir_entry() to be visible to IOMMU */
-	if (ioc_needs_fdc)
-		asm volatile("sync" : : );
+	asm_io_sync();
 
 #ifdef ASSERT_PDIR_SANITY
 	if (sba_check_pdir(ioc,"Check after sba_map_sg()"))