Merge branch 'parisc-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux

Pull parisc updates from Helge Deller:
 "Lots of small fixes and enhancements, most noteably:

   - Many TLB and cache flush optimizations (Dave)

   - Fixed HPMC/crash handler on 64-bit kernel (Dave and myself)

   - Added alternative infrastructre. The kernel now live-patches itself
     for various situations, e.g. replace SMP code when running on one
     CPU only or drop cache flushes when system has no cache installed.

   - vmlinuz now contains a full copy of the compressed vmlinux file.
     This simplifies debugging the currently booted kernel.

   - Unused driver removal (Christoph)

   - Reduced warnings of Dino PCI bridge when running in qemu

   - Removed gcc version check (Masahiro)"

* 'parisc-4.20-1' of git://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux: (23 commits)
  parisc: Retrieve and display the PDC PAT capabilities
  parisc: Optimze cache flush algorithms
  parisc: Remove pte_inserted define
  parisc: Add PDC PAT cell_info() and pd_get_pdc_revisions() functions
  parisc: Drop two instructions from pte lookup code
  parisc: Use zdep for shlw macro on PA1.1 and PA2.0
  parisc: Add alternative coding infrastructure
  parisc: Include compressed vmlinux file in vmlinuz boot kernel
  extract-vmlinux: Check for uncompressed image as fallback
  parisc: Fix address in HPMC IVA
  parisc: Fix exported address of os_hpmc handler
  parisc: Fix map_pages() to not overwrite existing pte entries
  parisc: Purge TLB entries after updating page table entry and set page accessed flag in TLB handler
  parisc: Release spinlocks using ordered store
  parisc: Ratelimit dino stuck interrupt warnings
  parisc: dino: Utilize DINO_MASK_IRQ() macro
  parisc: Clean up crash header output
  parisc: Add SYSTEM_INFO and REGISTER TOC PAT functions
  parisc: Remove PTE load and fault check from L2_ptep macro
  parisc: Reorder TLB flush timing calculation
  ...

arch/parisc/Makefile

@@ -156,12 +156,3 @@ define archhelp
 	@echo  '		  copy to $$(INSTALL_PATH)'
 	@echo  '  zinstall	- Install compressed vmlinuz kernel'
 endef
-
-# we require gcc 3.3 or above to compile the kernel
-archprepare: checkbin
-checkbin:
-	@if test "$(cc-version)" -lt "0303"; then \
-		echo -n "Sorry, GCC v3.3 or above is required to build " ; \
-		echo "the kernel." ; \
-		false ; \
-	fi

arch/parisc/boot/compressed/Makefile

@@ -14,7 +14,7 @@ targets += misc.o piggy.o sizes.h head.o real2.o firmware.o
 
 KBUILD_CFLAGS := -D__KERNEL__ -O2 -DBOOTLOADER
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
+KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -fno-builtin-printf
 KBUILD_CFLAGS += -fno-PIE -mno-space-regs -mdisable-fpregs -Os
 ifndef CONFIG_64BIT
 KBUILD_CFLAGS += -mfast-indirect-calls
@@ -22,7 +22,6 @@ endif
 
 OBJECTS += $(obj)/head.o $(obj)/real2.o $(obj)/firmware.o $(obj)/misc.o $(obj)/piggy.o
 
-# LDFLAGS_vmlinux := -X --whole-archive -e startup -T
 LDFLAGS_vmlinux := -X -e startup --as-needed -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS) $(LIBGCC)
 	$(call if_changed,ld)
@@ -55,7 +54,6 @@ $(obj)/misc.o: $(obj)/sizes.h
 CPPFLAGS_vmlinux.lds += -I$(objtree)/$(obj) -DBOOTLOADER
 $(obj)/vmlinux.lds: $(obj)/sizes.h
 
-OBJCOPYFLAGS_vmlinux.bin := -O binary -R .comment -S
 $(obj)/vmlinux.bin: vmlinux
 	$(call if_changed,objcopy)
 

arch/parisc/boot/compressed/misc.c

@@ -5,6 +5,7 @@
  */
 
 #include <linux/uaccess.h>
+#include <linux/elf.h>
 #include <asm/unaligned.h>
 #include <asm/page.h>
 #include "sizes.h"
@@ -227,13 +228,62 @@ static void flush_data_cache(char *start, unsigned long length)
 	asm ("sync");
 }
 
+static void parse_elf(void *output)
+{
+#ifdef CONFIG_64BIT
+	Elf64_Ehdr ehdr;
+	Elf64_Phdr *phdrs, *phdr;
+#else
+	Elf32_Ehdr ehdr;
+	Elf32_Phdr *phdrs, *phdr;
+#endif
+	void *dest;
+	int i;
+
+	memcpy(&ehdr, output, sizeof(ehdr));
+	if (ehdr.e_ident[EI_MAG0] != ELFMAG0 ||
+	   ehdr.e_ident[EI_MAG1] != ELFMAG1 ||
+	   ehdr.e_ident[EI_MAG2] != ELFMAG2 ||
+	   ehdr.e_ident[EI_MAG3] != ELFMAG3) {
+		error("Kernel is not a valid ELF file");
+		return;
+	}
+
+#ifdef DEBUG
+	printf("Parsing ELF... ");
+#endif
+
+	phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum);
+	if (!phdrs)
+		error("Failed to allocate space for phdrs");
+
+	memcpy(phdrs, output + ehdr.e_phoff, sizeof(*phdrs) * ehdr.e_phnum);
+
+	for (i = 0; i < ehdr.e_phnum; i++) {
+		phdr = &phdrs[i];
+
+		switch (phdr->p_type) {
+		case PT_LOAD:
+			dest = (void *)((unsigned long) phdr->p_paddr &
+					(__PAGE_OFFSET_DEFAULT-1));
+			memmove(dest, output + phdr->p_offset, phdr->p_filesz);
+			break;
+		default:
+			break;
+		}
+	}
+
+	free(phdrs);
+}
+
 unsigned long decompress_kernel(unsigned int started_wide,
 		unsigned int command_line,
 		const unsigned int rd_start,
 		const unsigned int rd_end)
 {
 	char *output;
-	unsigned long len, len_all;
+	unsigned long vmlinux_addr, vmlinux_len;
+	unsigned long kernel_addr, kernel_len;
 
 #ifdef CONFIG_64BIT
 	parisc_narrow_firmware = 0;
@@ -241,27 +291,29 @@ unsigned long decompress_kernel(unsigned int started_wide,
 
 	set_firmware_width_unlocked();
 
-	putchar('U');	/* if you get this p and no more, string storage */
+	putchar('D');	/* if you get this D and no more, string storage */
 			/* in $GLOBAL$ is wrong or %dp is wrong */
-	puts("ncompressing ...\n");
-
-	output = (char *) KERNEL_BINARY_TEXT_START;
-	len_all = __pa(SZ_end) - __pa(SZparisc_kernel_start);
+	puts("ecompressing Linux... ");
 
-	if ((unsigned long) &_startcode_end > (unsigned long) output)
+	/* where the final bits are stored */
+	kernel_addr = KERNEL_BINARY_TEXT_START;
+	kernel_len = __pa(SZ_end) - __pa(SZparisc_kernel_start);
+	if ((unsigned long) &_startcode_end > kernel_addr)
 		error("Bootcode overlaps kernel code");
 
-	len = get_unaligned_le32(&output_len);
-	if (len > len_all)
-		error("Output len too big.");
-	else
-		memset(&output[len], 0, len_all - len);
+	/*
+	 * Calculate addr to where the vmlinux ELF file shall be decompressed.
+	 * Assembly code in head.S positioned the stack directly behind bss, so
+	 * leave 2 MB for the stack.
+	 */
+	vmlinux_addr = (unsigned long) &_ebss + 2*1024*1024;
+	vmlinux_len = get_unaligned_le32(&output_len);
+	output = (char *) vmlinux_addr;
 
 	/*
 	 * Initialize free_mem_ptr and free_mem_end_ptr.
 	 */
-	free_mem_ptr = (unsigned long) &_ebss;
-	free_mem_ptr += 2*1024*1024;	/* leave 2 MB for stack */
+	free_mem_ptr = vmlinux_addr + vmlinux_len;
 
 	/* Limit memory for bootoader to 1GB */
 	#define ARTIFICIAL_LIMIT (1*1024*1024*1024)
@@ -275,7 +327,11 @@ unsigned long decompress_kernel(unsigned int started_wide,
 		free_mem_end_ptr = rd_start;
 #endif
 
+	if (free_mem_ptr >= free_mem_end_ptr)
+		error("Kernel too big for machine.");
+
 #ifdef DEBUG
+	printf("\n");
 	printf("startcode_end = %x\n", &_startcode_end);
 	printf("commandline   = %x\n", command_line);
 	printf("rd_start      = %x\n", rd_start);
@@ -287,16 +343,19 @@ unsigned long decompress_kernel(unsigned int started_wide,
 	printf("input_data    = %x\n", input_data);
 	printf("input_len     = %x\n", input_len);
 	printf("output        = %x\n", output);
-	printf("output_len    = %x\n", len);
-	printf("output_max    = %x\n", len_all);
+	printf("output_len    = %x\n", vmlinux_len);
+	printf("kernel_addr   = %x\n", kernel_addr);
+	printf("kernel_len    = %x\n", kernel_len);
 #endif
 
 	__decompress(input_data, input_len, NULL, NULL,
 			output, 0, NULL, error);
+	parse_elf(output);
 
-	flush_data_cache(output, len);
+	output = (char *) kernel_addr;
+	flush_data_cache(output, kernel_len);
 
-	printf("Booting kernel ...\n\n");
+	printf("done.\nBooting the kernel.\n");
 
 	return (unsigned long) output;
 }

arch/parisc/boot/compressed/vmlinux.lds.S

@@ -42,6 +42,12 @@ SECTIONS
 #endif
 	_startcode_end = .;
 
+	/* vmlinux.bin.gz is here */
+	. = ALIGN(8);
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
+
 	/* bootloader code and data starts behind area of extracted kernel */
 	. = (SZ_end - SZparisc_kernel_start + KERNEL_BINARY_TEXT_START);
 
@@ -68,10 +74,6 @@ SECTIONS
 		_erodata = . ;
 	}
 	. = ALIGN(8);
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
-	. = ALIGN(8);
 	.bss : {
 		_bss = . ;
 		*(.bss)

arch/parisc/include/asm/alternative.h

@@ -0,0 +1,47 @@
+/* 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/assembly.h

@@ -129,15 +129,8 @@
 	.macro	debug value
 	.endm
 
-
-	/* Shift Left - note the r and t can NOT be the same! */
-	.macro shl r, sa, t
-	dep,z	\r, 31-(\sa), 32-(\sa), \t
-	.endm
-
-	/* The PA 2.0 shift left */
 	.macro shlw r, sa, t
-	depw,z	\r, 31-(\sa), 32-(\sa), \t
+	zdep	\r, 31-(\sa), 32-(\sa), \t
 	.endm
 
 	/* And the PA 2.0W shift left */

arch/parisc/include/asm/cache.h

@@ -6,6 +6,7 @@
 #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
@@ -41,9 +42,24 @@ extern int icache_stride;
 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/page.h

@@ -117,14 +117,16 @@ extern int npmem_ranges;
 /* This governs the relationship between virtual and physical addresses.
  * If you alter it, make sure to take care of our various fixed mapping
  * segments in fixmap.h */
-#if defined(BOOTLOADER)
-#define __PAGE_OFFSET	(0)		/* bootloader uses physical addresses */
-#else
 #ifdef CONFIG_64BIT
-#define __PAGE_OFFSET	(0x40000000)	/* 1GB */
+#define __PAGE_OFFSET_DEFAULT	(0x40000000)	/* 1GB */
 #else
-#define __PAGE_OFFSET	(0x10000000)	/* 256MB */
+#define __PAGE_OFFSET_DEFAULT	(0x10000000)	/* 256MB */
 #endif
+
+#if defined(BOOTLOADER)
+#define __PAGE_OFFSET	(0)	/* bootloader uses physical addresses */
+#else
+#define __PAGE_OFFSET	__PAGE_OFFSET_DEFAULT
 #endif /* BOOTLOADER */
 
 #define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)

arch/parisc/include/asm/pdc.h

@@ -11,6 +11,7 @@ extern int parisc_narrow_firmware;
 extern int pdc_type;
 extern unsigned long parisc_cell_num; /* cell number the CPU runs on (PAT) */
 extern unsigned long parisc_cell_loc; /* cell location of CPU (PAT)	   */
+extern unsigned long parisc_pat_pdc_cap; /* PDC capabilities (PAT) */
 
 /* Values for pdc_type */
 #define PDC_TYPE_ILLEGAL	-1

arch/parisc/include/asm/pdcpat.h

@@ -173,6 +173,16 @@
 /* PDC PAT PD */
 #define PDC_PAT_PD		74L         /* Protection Domain Info   */
 #define PDC_PAT_PD_GET_ADDR_MAP		0L  /* Get Address Map          */
+#define PDC_PAT_PD_GET_PDC_INTERF_REV	1L  /* Get PDC Interface Revisions */
+
+#define PDC_PAT_CAPABILITY_BIT_PDC_SERIALIZE	(1UL << 0)
+#define PDC_PAT_CAPABILITY_BIT_PDC_POLLING	(1UL << 1)
+#define PDC_PAT_CAPABILITY_BIT_PDC_NBC		(1UL << 2) /* non-blocking calls */
+#define PDC_PAT_CAPABILITY_BIT_PDC_UFO		(1UL << 3)
+#define PDC_PAT_CAPABILITY_BIT_PDC_IODC_32	(1UL << 4)
+#define PDC_PAT_CAPABILITY_BIT_PDC_IODC_64	(1UL << 5)
+#define PDC_PAT_CAPABILITY_BIT_PDC_HPMC_RENDEZ	(1UL << 6)
+#define PDC_PAT_CAPABILITY_BIT_SIMULTANEOUS_PTLB (1UL << 7)
 
 /* PDC_PAT_PD_GET_ADDR_MAP entry types */
 #define PAT_MEMORY_DESCRIPTOR		1   
@@ -186,6 +196,14 @@
 #define PAT_MEMUSE_GI			128
 #define PAT_MEMUSE_GNI			129
 
+/* PDC PAT REGISTER TOC */
+#define PDC_PAT_REGISTER_TOC	75L
+#define PDC_PAT_TOC_REGISTER_VECTOR	0L /* Register TOC Vector */
+#define PDC_PAT_TOC_READ_VECTOR		1L /* Read TOC Vector     */
+
+/* PDC PAT SYSTEM_INFO */
+#define PDC_PAT_SYSTEM_INFO	76L
+/* PDC_PAT_SYSTEM_INFO uses the same options as PDC_SYSTEM_INFO function. */
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
@@ -297,18 +315,29 @@ struct pdc_pat_pd_addr_map_entry {
 ** PDC_PAT_CELL_GET_INFO return block
 */
 typedef struct pdc_pat_cell_info_rtn_block {
-	unsigned long cpu_info;
-	unsigned long cell_info;
-	unsigned long cell_location;
-	unsigned long reo_location;
-	unsigned long mem_size;
-	unsigned long dimm_status;
 	unsigned long pdc_rev;
-	unsigned long fabric_info0;
-	unsigned long fabric_info1;
-	unsigned long fabric_info2;
-	unsigned long fabric_info3;
-	unsigned long reserved[21];
+	unsigned long capabilities; /* see PDC_PAT_CAPABILITY_BIT_* */
+	unsigned long reserved0[2];
+	unsigned long cell_info;	/* 0x20 */
+	unsigned long cell_phys_location;
+	unsigned long cpu_info;
+	unsigned long cpu_speed;
+	unsigned long io_chassis_phys_location;
+	unsigned long cell_io_information;
+	unsigned long reserved1[2];
+	unsigned long io_slot_info_size; /* 0x60 */
+	struct {
+		unsigned long header, info0, info1;
+		unsigned long phys_loc, hw_path;
+	} io_slot[16];
+	unsigned long cell_mem_size;	/* 0x2e8 */
+	unsigned long cell_dimm_info_size;
+	unsigned long dimm_info[16];
+	unsigned long fabric_info_size;	/* 0x3f8 */
+	struct {			/* 0x380 */
+		unsigned long fabric_info_xbc_port;
+		unsigned long rc_attached_to_xbc;
+	} xbc[8*4];
 } pdc_pat_cell_info_rtn_block_t;
 
 
@@ -326,12 +355,19 @@ typedef struct pdc_pat_cell_mod_maddr_block pdc_pat_cell_mod_maddr_block_t;
 
 extern int pdc_pat_chassis_send_log(unsigned long status, unsigned long data);
 extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info);
-extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long mod, unsigned long view_type, void *mem_addr);
+extern int pdc_pat_cell_info(struct pdc_pat_cell_info_rtn_block *info,
+		unsigned long *actcnt, unsigned long offset,
+		unsigned long cell_number);
+extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc,
+		unsigned long mod, unsigned long view_type, void *mem_addr);
 extern int pdc_pat_cell_num_to_loc(void *, unsigned long);
 
 extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, unsigned long hpa);
 
-extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset);
+extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr,
+		unsigned long count, unsigned long offset);
+extern int pdc_pat_pd_get_pdc_revisions(unsigned long *legacy_rev,
+		unsigned long *pat_rev, unsigned long *pdc_cap);
 
 extern int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *val); 
 extern int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val); 

arch/parisc/include/asm/pgtable.h

@@ -43,8 +43,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 {
 	mtsp(mm->context, 1);
 	pdtlb(addr);
-	if (unlikely(split_tlb))
-		pitlb(addr);
+	pitlb(addr);
 }
 
 /* Certain architectures need to do special things when PTEs
@@ -56,19 +55,14 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
                 *(pteptr) = (pteval);                           \
         } while(0)
 
-#define pte_inserted(x)						\
-	((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED))		\
-	 == (_PAGE_PRESENT|_PAGE_ACCESSED))
-
 #define set_pte_at(mm, addr, ptep, pteval)			\
 	do {							\
 		pte_t old_pte;					\
 		unsigned long flags;				\
 		spin_lock_irqsave(&pa_tlb_lock, flags);		\
 		old_pte = *ptep;				\
-		if (pte_inserted(old_pte))			\
-			purge_tlb_entries(mm, addr);		\
 		set_pte(ptep, pteval);				\
+		purge_tlb_entries(mm, addr);			\
 		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
@@ -202,7 +196,7 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 #define _PAGE_HUGE     (1 << xlate_pabit(_PAGE_HPAGE_BIT))
 #define _PAGE_USER     (1 << xlate_pabit(_PAGE_USER_BIT))
 
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_ACCESSED)
+#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED)
 #define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
 #define _PAGE_KERNEL_RO	(_PAGE_PRESENT | _PAGE_READ | _PAGE_DIRTY | _PAGE_ACCESSED)
 #define _PAGE_KERNEL_EXEC	(_PAGE_KERNEL_RO | _PAGE_EXEC)
@@ -227,22 +221,22 @@ static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
 
 #ifndef __ASSEMBLY__
 
-#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_ACCESSED)
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_USER)
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE)
 /* Others seem to make this executable, I don't know if that's correct
    or not.  The stack is mapped this way though so this is necessary
    in the short term - dhd@linuxcare.com, 2000-08-08 */
-#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_ACCESSED)
-#define PAGE_WRITEONLY  __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITE | _PAGE_ACCESSED)
-#define PAGE_EXECREAD   __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_EXEC |_PAGE_ACCESSED)
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ)
+#define PAGE_WRITEONLY  __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITE)
+#define PAGE_EXECREAD   __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_EXEC)
 #define PAGE_COPY       PAGE_EXECREAD
-#define PAGE_RWX        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_EXEC |_PAGE_ACCESSED)
+#define PAGE_RWX        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_EXEC)
 #define PAGE_KERNEL	__pgprot(_PAGE_KERNEL)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_KERNEL_EXEC)
 #define PAGE_KERNEL_RWX	__pgprot(_PAGE_KERNEL_RWX)
 #define PAGE_KERNEL_RO	__pgprot(_PAGE_KERNEL_RO)
 #define PAGE_KERNEL_UNC	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
-#define PAGE_GATEWAY    __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_GATEWAY| _PAGE_READ)
+#define PAGE_GATEWAY    __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_GATEWAY| _PAGE_READ)
 
 
 /*
@@ -479,8 +473,8 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
 		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
-	purge_tlb_entries(vma->vm_mm, addr);
 	set_pte(ptep, pte_mkold(pte));
+	purge_tlb_entries(vma->vm_mm, addr);
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
@@ -493,9 +487,8 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 
 	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	if (pte_inserted(old_pte))
-		purge_tlb_entries(mm, addr);
 	set_pte(ptep, __pte(0));
+	purge_tlb_entries(mm, addr);
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
@@ -505,8 +498,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 {
 	unsigned long flags;
 	spin_lock_irqsave(&pa_tlb_lock, flags);
-	purge_tlb_entries(mm, addr);
 	set_pte(ptep, pte_wrprotect(*ptep));
+	purge_tlb_entries(mm, addr);
 	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 

arch/parisc/include/asm/sections.h

@@ -5,6 +5,8 @@
 /* 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/spinlock.h

@@ -37,8 +37,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 
 	a = __ldcw_align(x);
-	mb();
-	*a = 1;
+	/* Release with ordered store. */
+	__asm__ __volatile__("stw,ma %0,0(%1)" : : "r"(1), "r"(a) : "memory");
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)

arch/parisc/include/asm/tlbflush.h

@@ -85,8 +85,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	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

@@ -36,6 +36,7 @@ EXPORT_SYMBOL(dcache_stride);
 
 void flush_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 EXPORT_SYMBOL(flush_dcache_page_asm);
+void purge_dcache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 void flush_icache_page_asm(unsigned long phys_addr, unsigned long vaddr);
 
 
@@ -303,6 +304,17 @@ __flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
 	preempt_enable();
 }
 
+static inline void
+__purge_cache_page(struct vm_area_struct *vma, unsigned long vmaddr,
+		   unsigned long physaddr)
+{
+	preempt_disable();
+	purge_dcache_page_asm(physaddr, vmaddr);
+	if (vma->vm_flags & VM_EXEC)
+		flush_icache_page_asm(physaddr, vmaddr);
+	preempt_enable();
+}
+
 void flush_dcache_page(struct page *page)
 {
 	struct address_space *mapping = page_mapping_file(page);
@@ -364,7 +376,7 @@ EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
 static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
 
-#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+#define FLUSH_TLB_THRESHOLD (16*1024) /* 16 KiB minimum TLB threshold */
 static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
 
 void __init parisc_setup_cache_timing(void)
@@ -404,10 +416,6 @@ void __init parisc_setup_cache_timing(void)
 		goto set_tlb_threshold;
 	}
 
-	alltime = mfctl(16);
-	flush_tlb_all();
-	alltime = mfctl(16) - alltime;
-
 	size = 0;
 	start = (unsigned long) _text;
 	rangetime = mfctl(16);
@@ -418,13 +426,19 @@ void __init parisc_setup_cache_timing(void)
 	}
 	rangetime = mfctl(16) - rangetime;
 
-	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+	alltime = mfctl(16);
+	flush_tlb_all();
+	alltime = mfctl(16) - alltime;
+
+	printk(KERN_INFO "Whole TLB flush %lu cycles, Range flush %lu bytes %lu cycles\n",
 		alltime, size, rangetime);
 
-	threshold = PAGE_ALIGN(num_online_cpus() * size * alltime / rangetime);
+	threshold = PAGE_ALIGN((num_online_cpus() * size * alltime) / rangetime);
+	printk(KERN_INFO "Calculated TLB flush threshold %lu KiB\n",
+		threshold/1024);
 
 set_tlb_threshold:
-	if (threshold)
+	if (threshold > parisc_tlb_flush_threshold)
 		parisc_tlb_flush_threshold = threshold;
 	printk(KERN_INFO "TLB flush threshold set to %lu KiB\n",
 		parisc_tlb_flush_threshold/1024);
@@ -477,18 +491,6 @@ int __flush_tlb_range(unsigned long sid, unsigned long start,
 	/* 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);
@@ -573,9 +575,12 @@ void flush_cache_mm(struct mm_struct *mm)
 			pfn = pte_pfn(*ptep);
 			if (!pfn_valid(pfn))
 				continue;
-			if (unlikely(mm->context))
+			if (unlikely(mm->context)) {
 				flush_tlb_page(vma, addr);
-			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+			} else {
+				__purge_cache_page(vma, addr, PFN_PHYS(pfn));
+			}
 		}
 	}
 }
@@ -610,9 +615,12 @@ void flush_cache_range(struct vm_area_struct *vma,
 			continue;
 		pfn = pte_pfn(*ptep);
 		if (pfn_valid(pfn)) {
-			if (unlikely(vma->vm_mm->context))
+			if (unlikely(vma->vm_mm->context)) {
 				flush_tlb_page(vma, addr);
-			__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+				__flush_cache_page(vma, addr, PFN_PHYS(pfn));
+			} else {
+				__purge_cache_page(vma, addr, PFN_PHYS(pfn));
+			}
 		}
 	}
 }
@@ -621,9 +629,12 @@ void
 flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn)
 {
 	if (pfn_valid(pfn)) {
-		if (likely(vma->vm_mm->context))
+		if (likely(vma->vm_mm->context)) {
 			flush_tlb_page(vma, vmaddr);
-		__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+			__flush_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+		} else {
+			__purge_cache_page(vma, vmaddr, PFN_PHYS(pfn));
+		}
 	}
 }
 

arch/parisc/kernel/entry.S

@@ -38,6 +38,7 @@
 #include <asm/ldcw.h>
 #include <asm/traps.h>
 #include <asm/thread_info.h>
+#include <asm/alternative.h>
 
 #include <linux/linkage.h>
 
@@ -186,7 +187,7 @@
 	bv,n	0(%r3)
 	nop
 	.word	0		/* checksum (will be patched) */
-	.word	PA(os_hpmc)	/* address of handler */
+	.word	0		/* address of handler */
 	.word	0		/* length of handler */
 	.endm
 
@@ -426,13 +427,10 @@
 	ldw,s		\index(\pmd),\pmd
 	bb,>=,n		\pmd,_PxD_PRESENT_BIT,\fault
 	dep		%r0,31,PxD_FLAG_SHIFT,\pmd /* clear flags */
-	copy		\pmd,%r9
-	SHLREG		%r9,PxD_VALUE_SHIFT,\pmd
+	SHLREG		\pmd,PxD_VALUE_SHIFT,\pmd
 	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
 	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
-	LDREG		%r0(\pmd),\pte
-	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
 	.endm
 
 	/* Look up PTE in a 3-Level scheme.
@@ -448,7 +446,6 @@
 	.macro		L3_ptep pgd,pte,index,va,fault
 #if CONFIG_PGTABLE_LEVELS == 3 /* we might have a 2-Level scheme, e.g. with 16kb page size */
 	extrd,u		\va,63-ASM_PGDIR_SHIFT,ASM_BITS_PER_PGD,\index
-	copy		%r0,\pte
 	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
 	ldw,s		\index(\pgd),\pgd
 	extrd,u,*=	\va,63-ASM_PGDIR_SHIFT,64-ASM_PGDIR_SHIFT,%r0
@@ -463,36 +460,39 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_tlb_lock lock and recheck page is still present. */
+	/* 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
 	nop
 	LDREG		0(\ptp),\pte
-	bb,<,n		\pte,_PAGE_PRESENT_BIT,2f
+	bb,<,n		\pte,_PAGE_PRESENT_BIT,3f
 	b		\fault
-	stw		 \spc,0(\tmp)
-2:
+	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
+3:
 	.endm
 
 	/* Release pa_tlb_lock lock without reloading lock address. */
 	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	sync
-	or,COND(=)	%r0,\spc,%r0
-	stw             \spc,0(\tmp)
+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
@@ -1658,7 +1658,7 @@ dbit_fault:
 
 itlb_fault:
 	b               intr_save
-	ldi             6,%r8
+	ldi             PARISC_ITLB_TRAP,%r8
 
 nadtlb_fault:
 	b               intr_save

arch/parisc/kernel/firmware.c

@@ -1325,6 +1325,36 @@ int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long
 	return retval;
 }
 
+/**
+ * pdc_pat_cell_info - Retrieve the cell's information.
+ * @info: The pointer to a struct pdc_pat_cell_info_rtn_block.
+ * @actcnt: The number of bytes which should be written to info.
+ * @offset: offset of the structure.
+ * @cell_number: The cell number which should be asked, or -1 for current cell.
+ *
+ * This PDC call returns information about the given cell (or all cells).
+ */
+int pdc_pat_cell_info(struct pdc_pat_cell_info_rtn_block *info,
+		unsigned long *actcnt, unsigned long offset,
+		unsigned long cell_number)
+{
+	int retval;
+	unsigned long flags;
+	struct pdc_pat_cell_info_rtn_block result;
+
+	spin_lock_irqsave(&pdc_lock, flags);
+	retval = mem_pdc_call(PDC_PAT_CELL, PDC_PAT_CELL_GET_INFO,
+			__pa(pdc_result), __pa(&result), *actcnt,
+			offset, cell_number);
+	if (!retval) {
+		*actcnt = pdc_result[0];
+		memcpy(info, &result, *actcnt);
+	}
+	spin_unlock_irqrestore(&pdc_lock, flags);
+
+	return retval;
+}
+
 /**
  * pdc_pat_cpu_get_number - Retrieve the cpu number.
  * @cpu_info: The return buffer.
@@ -1412,6 +1442,33 @@ int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr,
 	return retval;
 }
 
+/**
+ * pdc_pat_pd_get_PDC_interface_revisions - Retrieve PDC interface revisions.
+ * @legacy_rev: The legacy revision.
+ * @pat_rev: The PAT revision.
+ * @pdc_cap: The PDC capabilities.
+ *
+ */
+int pdc_pat_pd_get_pdc_revisions(unsigned long *legacy_rev,
+		unsigned long *pat_rev, unsigned long *pdc_cap)
+{
+	int retval;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdc_lock, flags);
+	retval = mem_pdc_call(PDC_PAT_PD, PDC_PAT_PD_GET_PDC_INTERF_REV,
+				__pa(pdc_result));
+	if (retval == PDC_OK) {
+		*legacy_rev = pdc_result[0];
+		*pat_rev = pdc_result[1];
+		*pdc_cap = pdc_result[2];
+	}
+	spin_unlock_irqrestore(&pdc_lock, flags);
+
+	return retval;
+}
+
+
 /**
  * pdc_pat_io_pci_cfg_read - Read PCI configuration space.
  * @pci_addr: PCI configuration space address for which the read request is being made.

arch/parisc/kernel/hpmc.S

@@ -85,7 +85,7 @@ END(hpmc_pim_data)
 
 	.import intr_save, code
 	.align 16
-ENTRY_CFI(os_hpmc)
+ENTRY(os_hpmc)
 .os_hpmc:
 
 	/*
@@ -302,7 +302,6 @@ os_hpmc_6:
 	b .
 	nop
 	.align 16	/* make function length multiple of 16 bytes */
-ENDPROC_CFI(os_hpmc)
 .os_hpmc_end:
 
 

arch/parisc/kernel/inventory.c

@@ -43,6 +43,7 @@ int pdc_type __read_mostly = PDC_TYPE_ILLEGAL;
 /* cell number and location (PAT firmware only) */
 unsigned long parisc_cell_num __read_mostly;
 unsigned long parisc_cell_loc __read_mostly;
+unsigned long parisc_pat_pdc_cap __read_mostly;
 
 
 void __init setup_pdc(void)
@@ -81,12 +82,21 @@ void __init setup_pdc(void)
 #ifdef CONFIG_64BIT
 	status = pdc_pat_cell_get_number(&cell_info);
 	if (status == PDC_OK) {
+		unsigned long legacy_rev, pat_rev;
 		pdc_type = PDC_TYPE_PAT;
 		pr_cont("64 bit PAT.\n");
 		parisc_cell_num = cell_info.cell_num;
 		parisc_cell_loc = cell_info.cell_loc;
 		pr_info("PAT: Running on cell %lu and location %lu.\n",
 			parisc_cell_num, parisc_cell_loc);
+		status = pdc_pat_pd_get_pdc_revisions(&legacy_rev,
+			&pat_rev, &parisc_pat_pdc_cap);
+		pr_info("PAT: legacy revision 0x%lx, pat_rev 0x%lx, pdc_cap 0x%lx, S-PTLB %d, HPMC_RENDEZ %d.\n",
+			legacy_rev, pat_rev, parisc_pat_pdc_cap,
+			parisc_pat_pdc_cap
+			 & PDC_PAT_CAPABILITY_BIT_SIMULTANEOUS_PTLB ? 1:0,
+			parisc_pat_pdc_cap
+			 & PDC_PAT_CAPABILITY_BIT_PDC_HPMC_RENDEZ   ? 1:0);
 		return;
 	}
 #endif

arch/parisc/kernel/pacache.S

@@ -37,6 +37,7 @@
 #include <asm/pgtable.h>
 #include <asm/cache.h>
 #include <asm/ldcw.h>
+#include <asm/alternative.h>
 #include <linux/linkage.h>
 #include <linux/init.h>
 
@@ -190,7 +191,7 @@ ENDPROC_CFI(flush_tlb_all_local)
 	.import cache_info,data
 
 ENTRY_CFI(flush_instruction_cache_local)
-	load32		cache_info, %r1
+88:	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
 
@@ -243,6 +244,7 @@ fioneloop2:
 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)
@@ -250,7 +252,7 @@ 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 */
 
@@ -304,6 +306,7 @@ fdsync:
 	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)
@@ -312,6 +315,7 @@ 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
@@ -326,15 +330,17 @@ ENDPROC_CFI(flush_data_cache_local)
 	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
 
@@ -596,9 +602,11 @@ ENTRY_CFI(copy_user_page_asm)
 	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
@@ -736,8 +744,9 @@ ENTRY_CFI(clear_user_page_asm)
 	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
@@ -813,11 +822,12 @@ ENTRY_CFI(flush_dcache_page_asm)
 	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
@@ -828,8 +838,7 @@ ENTRY_CFI(flush_dcache_page_asm)
 	add		%r28, %r25, %r25
 	sub		%r25, r31, %r25
 
-
-1:      fdc,m		r31(%r28)
+1:	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
@@ -844,14 +853,76 @@ ENTRY_CFI(flush_dcache_page_asm)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
 	fdc,m		r31(%r28)
-	cmpb,COND(<<)	%r28, %r25,1b
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
 	fdc,m		r31(%r28)
 
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
 	sync
 	bv		%r0(%r2)
 	nop
 ENDPROC_CFI(flush_dcache_page_asm)
 
+ENTRY_CFI(purge_dcache_page_asm)
+	ldil		L%(TMPALIAS_MAP_START), %r28
+#ifdef CONFIG_64BIT
+#if (TMPALIAS_MAP_START >= 0x80000000)
+	depdi		0, 31,32, %r28		/* clear any sign extension */
+#endif
+	convert_phys_for_tlb_insert20 %r26	/* convert phys addr to tlb insert format */
+	depd		%r25, 63,22, %r28	/* Form aliased virtual address 'to' */
+	depdi		0, 63,PAGE_SHIFT, %r28	/* Clear any offset bits */
+#else
+	extrw,u		%r26, 24,25, %r26	/* convert phys addr to tlb insert format */
+	depw		%r25, 31,22, %r28	/* Form aliased virtual address 'to' */
+	depwi		0, 31,PAGE_SHIFT, %r28	/* Clear any offset bits */
+#endif
+
+	/* Purge any old translation */
+
+#ifdef CONFIG_PA20
+	pdtlb,l		%r0(%r28)
+#else
+	tlb_lock	%r20,%r21,%r22
+0:	pdtlb		%r0(%r28)
+	tlb_unlock	%r20,%r21,%r22
+	ALTERNATIVE(0b, 0b+4, ALT_COND_NO_SMP, INSN_PxTLB)
+#endif
+
+88:	ldil		L%dcache_stride, %r1
+	ldw		R%dcache_stride(%r1), r31
+
+#ifdef CONFIG_64BIT
+	depdi,z		1, 63-PAGE_SHIFT,1, %r25
+#else
+	depwi,z		1, 31-PAGE_SHIFT,1, %r25
+#endif
+	add		%r28, %r25, %r25
+	sub		%r25, r31, %r25
+
+1:      pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	pdc,m		r31(%r28)
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
+	pdc,m		r31(%r28)
+
+89:	ALTERNATIVE(88b, 89b, ALT_COND_NO_DCACHE, INSN_NOP)
+	sync
+	bv		%r0(%r2)
+	nop
+ENDPROC_CFI(purge_dcache_page_asm)
+
 ENTRY_CFI(flush_icache_page_asm)
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
@@ -874,15 +945,19 @@ ENTRY_CFI(flush_icache_page_asm)
 
 #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
@@ -893,7 +968,6 @@ ENTRY_CFI(flush_icache_page_asm)
 	add		%r28, %r25, %r25
 	sub		%r25, %r31, %r25
 
-
 	/* fic only has the type 26 form on PA1.1, requiring an
 	 * explicit space specification, so use %sr4 */
 1:      fic,m		%r31(%sr4,%r28)
@@ -911,16 +985,17 @@ ENTRY_CFI(flush_icache_page_asm)
 	fic,m		%r31(%sr4,%r28)
 	fic,m		%r31(%sr4,%r28)
 	fic,m		%r31(%sr4,%r28)
-	cmpb,COND(<<)	%r28, %r25,1b
+	cmpb,COND(>>)	%r25, %r28, 1b /* predict taken */
 	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
@@ -931,7 +1006,6 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	add		%r26, %r25, %r25
 	sub		%r25, %r23, %r25
 
-
 1:      fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
@@ -947,16 +1021,17 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
 	fdc,m		%r23(%r26)
-	cmpb,COND(<<)		%r26, %r25,1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	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
@@ -982,74 +1057,183 @@ ENTRY_CFI(purge_kernel_dcache_page_asm)
 	pdc,m		%r23(%r26)
 	pdc,m		%r23(%r26)
 	pdc,m		%r23(%r26)
-	cmpb,COND(<<)		%r26, %r25, 1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	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
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	fdc,m		%r23(%sr3, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
 	fdc,m		%r23(%sr3, %r26)
 
+2:	cmpb,COND(>>),n	%r25, %r26, 2b
+	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
 
-1:      cmpb,COND(<<),n	%r26, %r25,1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	fdc,m		%r23(%r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fdc,m		%r23(%r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	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
 
-1:      cmpb,COND(<<),n	%r26, %r25,1b
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	pdc,m		%r23(%r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	pdc,m		%r23(%r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	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
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	fic,m		%r23(%sr3, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fic,m		%r23(%sr3, %r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b
 	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
@@ -1076,23 +1260,51 @@ ENTRY_CFI(flush_kernel_icache_page)
 	fic,m		%r23(%sr4, %r26)
 	fic,m		%r23(%sr4, %r26)
 	fic,m		%r23(%sr4, %r26)
-	cmpb,COND(<<)		%r26, %r25, 1b
+	cmpb,COND(>>)	%r25, %r26, 1b /* predict taken */
 	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
+#ifdef CONFIG_64BIT
+	depd,z		%r23, 59, 60, %r21
+#else
+	depw,z		%r23, 27, 28, %r21
+#endif
+	add		%r26, %r21, %r22
+	cmpb,COND(>>),n	%r22, %r25, 2f /* predict not taken */
+1:	add		%r22, %r21, %r22
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	fic,m		%r23(%sr4, %r26)
+	cmpb,COND(<<=)	%r22, %r25, 1b /* predict taken */
+	fic,m		%r23(%sr4, %r26)
+
+2:	cmpb,COND(>>),n	%r25, %r26, 2b /* predict taken */
 	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

@@ -305,6 +305,86 @@ static int __init parisc_init_resources(void)
 	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);
@@ -346,6 +426,7 @@ static int __init parisc_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

@@ -65,7 +65,6 @@
 #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/syscall.S

@@ -640,8 +640,7 @@ cas_action:
 	sub,<>	%r28, %r25, %r0
 2:	stw	%r24, 0(%r26)
 	/* Free lock */
-	sync
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -655,8 +654,7 @@ cas_action:
 3:		
 	/* Error occurred on load or store */
 	/* Free lock */
-	sync
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	stw	%r0, 4(%sr2,%r20)
 #endif
@@ -857,8 +855,7 @@ cas2_action:
 
 cas2_end:
 	/* Free lock */
-	sync
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
@@ -868,8 +865,7 @@ cas2_end:
 22:
 	/* Error occurred on load or store */
 	/* Free lock */
-	sync
-	stw	%r20, 0(%sr2,%r20)
+	stw,ma	%r20, 0(%sr2,%r20)
 	ssm	PSW_SM_I, %r0
 	ldo	1(%r0),%r28
 	b	lws_exit

arch/parisc/kernel/traps.c

@@ -430,8 +430,8 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o
 	}
 
 	printk("\n");
-	pr_crit("%s: Code=%d (%s) regs=%p (Addr=" RFMT ")\n",
-		msg, code, trap_name(code), regs, offset);
+	pr_crit("%s: Code=%d (%s) at addr " RFMT "\n",
+		msg, code, trap_name(code), offset);
 	show_regs(regs);
 
 	spin_unlock(&terminate_lock);
@@ -802,7 +802,8 @@ void __init initialize_ivt(const void *iva)
 	 *    the Length/4 words starting at Address is zero.
 	 */
 
-	/* Compute Checksum for HPMC handler */
+	/* Setup IVA and compute checksum for HPMC handler */
+	ivap[6] = (u32)__pa(os_hpmc);
 	length = os_hpmc_size;
 	ivap[7] = length;
 

arch/parisc/kernel/vmlinux.lds.S

@@ -61,6 +61,12 @@ SECTIONS
 		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

@@ -494,12 +494,8 @@ static void __init map_pages(unsigned long start_vaddr,
 						pte = pte_mkhuge(pte);
 				}
 
-				if (address >= end_paddr) {
-					if (force)
-						break;
-					else
-						pte_val(pte) = 0;
-				}
+				if (address >= end_paddr)
+					break;
 
 				set_pte(pg_table, pte);
 
@@ -515,6 +511,21 @@ static void __init map_pages(unsigned long start_vaddr,
 	}
 }
 
+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/Makefile

@@ -8,9 +8,6 @@
 obj-$(CONFIG_IOSAPIC)		+= iosapic.o
 obj-$(CONFIG_IOMMU_SBA)		+= sba_iommu.o
 obj-$(CONFIG_PCI_LBA)		+= lba_pci.o
-
-# Only use one of them: ccio-rm-dma is for PCX-W systems *only*
-# obj-$(CONFIG_IOMMU_CCIO)	+= ccio-rm-dma.o
 obj-$(CONFIG_IOMMU_CCIO)	+= ccio-dma.o
 
 obj-$(CONFIG_GSC)		+= gsc.o

drivers/parisc/ccio-dma.c

@@ -609,14 +609,13 @@ ccio_io_pdir_entry(u64 *pdir_ptr, space_t sid, unsigned long vba,
 	**        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();
 }
 
 /**
@@ -682,17 +681,14 @@ ccio_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
 		** 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/ccio-rm-dma.c

@@ -1,202 +0,0 @@
-/*
- * ccio-rm-dma.c:
- *	DMA management routines for first generation cache-coherent machines.
- *	"Real Mode" operation refers to U2/Uturn chip operation. The chip
- *      can perform coherency checks w/o using the I/O MMU. That's all we
- *      need until support for more than 4GB phys mem is needed.
- * 
- *	This is the trivial case - basically what x86 does.
- *
- *	Drawbacks of using Real Mode are:
- *	o outbound DMA is slower since one isn't using the prefetching
- *	  U2 can do for outbound DMA.
- *	o Ability to do scatter/gather in HW is also lost.
- *      o only known to work with PCX-W processor. (eg C360)
- *        (PCX-U/U+ are not coherent with U2 in real mode.)
- *
- *
- * 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.
- *
- *
- * Original version/author:
- *      CVSROOT=:pserver:anonymous@198.186.203.37:/cvsroot/linux-parisc
- *      cvs -z3 co linux/arch/parisc/kernel/dma-rm.c
- *
- *	(C) Copyright 2000 Philipp Rumpf <prumpf@tux.org>
- *
- *
- * Adopted for The Puffin Group's parisc-linux port by Grant Grundler.
- *	(C) Copyright 2000 Grant Grundler <grundler@puffin.external.hp.com>
- *	
- */
-
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/pci.h>
-#include <linux/gfp.h>
-
-#include <linux/uaccess.h>
-
-#include <asm/io.h>
-#include <asm/hardware.h>
-#include <asm/page.h>
-
-/* Only chose "ccio" since that's what HP-UX calls it....
-** Make it easier for folks to migrate from one to the other :^)
-*/
-#define MODULE_NAME "ccio"
-
-#define U2_IOA_RUNWAY 0x580
-#define U2_BC_GSC     0x501
-#define UTURN_IOA_RUNWAY 0x581
-#define UTURN_BC_GSC     0x502
-
-#define IS_U2(id) ( \
-    (((id)->hw_type == HPHW_IOA) && ((id)->hversion == U2_IOA_RUNWAY)) || \
-    (((id)->hw_type == HPHW_BCPORT) && ((id)->hversion == U2_BC_GSC))  \
-)
-
-#define IS_UTURN(id) ( \
-    (((id)->hw_type == HPHW_IOA) && ((id)->hversion == UTURN_IOA_RUNWAY)) || \
-    (((id)->hw_type == HPHW_BCPORT) && ((id)->hversion == UTURN_BC_GSC))  \
-)
-
-static int ccio_dma_supported( struct pci_dev *dev, u64 mask)
-{
-	if (dev == NULL) {
-		printk(KERN_ERR MODULE_NAME ": EISA/ISA/et al not supported\n");
-		BUG();
-		return(0);
-	}
-
-	/* only support 32-bit devices (ie PCI/GSC) */
-	return((int) (mask >= 0xffffffffUL));
-}
-
-
-static void *ccio_alloc_consistent(struct pci_dev *dev, size_t size,
-				 dma_addr_t *handle)
-{
-	void *ret;
-	
-	ret = (void *)__get_free_pages(GFP_ATOMIC, get_order(size));
-
-	if (ret != NULL) {
-		memset(ret, 0, size);
-		*handle = virt_to_phys(ret);
-	}
-	return ret;
-}
-	
-static void ccio_free_consistent(struct pci_dev *dev, size_t size,
-			       void *vaddr, dma_addr_t handle)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-}
-
-static dma_addr_t ccio_map_single(struct pci_dev *dev, void *ptr, size_t size,
-			  int direction)
-{
-	return virt_to_phys(ptr);
-}
-
-static void ccio_unmap_single(struct pci_dev *dev, dma_addr_t dma_addr,
-			    size_t size, int direction)
-{
-	/* Nothing to do */
-}
-
-
-static int ccio_map_sg(struct pci_dev *dev, struct scatterlist *sglist, int nents, int direction)
-{
-	int tmp = nents;
-
-        /* KISS: map each buffer separately. */
-	while (nents) {
-		sg_dma_address(sglist) = ccio_map_single(dev, sglist->address, sglist->length, direction);
-		sg_dma_len(sglist) = sglist->length;
-		nents--;
-		sglist++;
-	}
-
-	return tmp;
-}
-
-
-static void ccio_unmap_sg(struct pci_dev *dev, struct scatterlist *sglist, int nents, int direction)
-{
-#if 0
-	while (nents) {
-		ccio_unmap_single(dev, sg_dma_address(sglist), sg_dma_len(sglist), direction);
-		nents--;
-		sglist++;
-	}
-	return;
-#else
-	/* Do nothing (copied from current ccio_unmap_single()  :^) */
-#endif
-}
-
-
-static struct pci_dma_ops ccio_ops = {
-	ccio_dma_supported,
-	ccio_alloc_consistent,
-	ccio_free_consistent,
-	ccio_map_single,
-	ccio_unmap_single,
-	ccio_map_sg,
-	ccio_unmap_sg,
-	NULL,                   /* dma_sync_single_for_cpu : NOP for U2 */
-	NULL,                   /* dma_sync_single_for_device : NOP for U2 */
-	NULL,                   /* dma_sync_sg_for_cpu     : ditto */
-	NULL,                   /* dma_sync_sg_for_device     : ditto */
-};
-
-
-/*
-** Determine if u2 should claim this chip (return 0) or not (return 1).
-** If so, initialize the chip and tell other partners in crime they
-** have work to do.
-*/
-static int __init
-ccio_probe(struct parisc_device *dev)
-{
-	printk(KERN_INFO "%s found %s at 0x%lx\n", MODULE_NAME,
-			dev->id.hversion == U2_BC_GSC ? "U2" : "UTurn",
-			dev->hpa.start);
-
-/*
-** FIXME - should check U2 registers to verify it's really running
-** in "Real Mode".
-*/
-
-#if 0
-/* will need this for "Virtual Mode" operation */
-	ccio_hw_init(ccio_dev);
-	ccio_common_init(ccio_dev);
-#endif
-	hppa_dma_ops = &ccio_ops;
-	return 0;
-}
-
-static const struct parisc_device_id ccio_tbl[] __initconst = {
-	{ HPHW_BCPORT, HVERSION_REV_ANY_ID, U2_BC_GSC, 0xc },
-	{ HPHW_BCPORT, HVERSION_REV_ANY_ID, UTURN_BC_GSC, 0xc },
-	{ 0, }
-};
-
-static struct parisc_driver ccio_driver __refdata = {
-	.name =		"U2/Uturn",
-	.id_table =	ccio_tbl,
-	.probe =	ccio_probe,
-};
-
-void __init ccio_init(void)
-{
-	register_parisc_driver(&ccio_driver);
-}

drivers/parisc/dino.c

@@ -382,7 +382,7 @@ ilr_again:
 		DBG(KERN_DEBUG "%s(%d, %p) mask 0x%x\n",
 			__func__, irq, intr_dev, mask);
 		generic_handle_irq(irq);
-		mask &= ~(1 << local_irq);
+		mask &= ~DINO_MASK_IRQ(local_irq);
 	} while (mask);
 
 	/* Support for level triggered IRQ lines.
@@ -396,9 +396,8 @@ ilr_again:
 	if (mask) {
 		if (--ilr_loop > 0)
 			goto ilr_again;
-		printk(KERN_ERR "Dino 0x%px: stuck interrupt %d\n",
+		pr_warn_ratelimited("Dino 0x%px: stuck interrupt %d\n",
 		       dino_dev->hba.base_addr, mask);
-		return IRQ_NONE;
 	}
 	return IRQ_HANDLED;
 }

drivers/parisc/sba_iommu.c

@@ -587,8 +587,7 @@ sba_io_pdir_entry(u64 *pdir_ptr, space_t sid, unsigned long vba,
 	 * (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);
 }
 
 
@@ -641,8 +640,8 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
 		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
@@ -661,8 +660,7 @@ sba_mark_invalid(struct ioc *ioc, dma_addr_t iova, size_t byte_cnt)
 	** 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);
 }
@@ -773,8 +771,7 @@ sba_map_single(struct device *dev, void *addr, size_t size,
 	}
 
 	/* 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()");
@@ -858,8 +855,7 @@ sba_unmap_page(struct device *dev, dma_addr_t iova, size_t size,
 	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 */
@@ -1008,8 +1004,7 @@ sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents,
 	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()"))

scripts/extract-vmlinux

@@ -48,9 +48,6 @@ fi
 tmp=$(mktemp /tmp/vmlinux-XXX)
 trap "rm -f $tmp" 0
 
-# Initial attempt for uncompressed images or objects:
-check_vmlinux $img
-
 # That didn't work, so retry after decompression.
 try_decompress '\037\213\010' xy    gunzip
 try_decompress '\3757zXZ\000' abcde unxz
@@ -60,5 +57,8 @@ try_decompress '\211\114\132' xy    'lzop -d'
 try_decompress '\002!L\030'   xxx   'lz4 -d'
 try_decompress '(\265/\375'   xxx   unzstd
 
+# Finally check for uncompressed images or objects:
+check_vmlinux $img
+
 # Bail out:
 echo "$me: Cannot find vmlinux." >&2