csky-for-linus-5.4-rc1: arch/csky patches for 5.4-rc1

This round of csky subsystem just some fixups.
 
 Fixup:
  - Fixup mb() synchronization problem
  - Fixup dma_alloc_coherent with PAGE_SO attribute
  - Fixup cache_op failed when cross memory ZONEs
  - Optimize arch_sync_dma_for_cpu/device with dma_inv_range
  - Fixup ioremap function losing
  - Fixup arch_get_unmapped_area() implementation
  - Fixup defer cache flush for 610
  - Support kernel non-aligned access
  - Fixup 610 vipt cache flush mechanism
  - Fixup add zero_fp fixup perf backtrace panic
  - Move static keyword to the front of declaration
  - Fixup csky_pmu.max_period assignment
  - Use generic free_initrd_mem()
  - entry: Remove unneeded need_resched() loop
 
 CI-Tested: https://gitlab.com/c-sky/buildroot/pipelines/77689888
 -----BEGIN PGP SIGNATURE-----
 
 iQJGBAABCAAwFiEE2KAv+isbWR/viAKHAXH1GYaIxXsFAl2Rfc0SHHJlbl9ndW9A
 Yy1za3kuY29tAAoJEAFx9RmGiMV7eEUQAIuuO1ym/o7zMWZsIRbISJYi6xuq752W
 RVhnPv957ktFYlqrtelDuZwkCPnK03YDTv8lPzcIhes+xYtuspN6NMum7SUWPt4c
 IbfQe4GmMwPGNrJ76NO9YcWQig8flT75wWE2CzOjhGpBfEkEHmtbOvOiZujcq4yN
 vhj8TKF9CjOSaDJNCOXinC6DeGoftRYTSRq6NMPfFfHIWqFcZIyb1Fz8tE/vFP4Y
 qEoG/ys/eu114DIZVnxr5ihmrJ4gjxmlXlnYA8WMRnRt6/oHEmmbtHLTT2eHbI2T
 u4TCssqrLoNADV7g7zyAyBnrgf4dXnJivGjc2NzVLAkgNbEJn+oGNYn+kdiRGd5X
 1CNVbzbZN0gHwLayDjJ4BWNxtpxxqmOjlDffjLVRW7dleTdfHvcxJwfhlvbQOPuq
 nMj4t1qJswn44f/bsj+F13hgXV0tWctYui/HS78xscE7t4yMNduf3JAm7TIxT0XN
 ej3102ffm4ycKZtfdwKwcACmMBJc+2QvGYmQo2L9pVLYIQe3QUWYs881V50PJXxV
 jdz4kmhpfKLie+yxmsdN1/8nTlcHF5wDiYwW9UColzfz1fCRkoPRx5tu/YI9zLoi
 K41CFEv4Z+aVzcp4HZNmOvVhGWgdmuwICMdY16wawhN6SAkvKJBFaP4g24h0J95M
 QyAPQl/VUMED
 =FLYg
 -----END PGP SIGNATURE-----

Merge tag 'csky-for-linus-5.4-rc1' of git://github.com/c-sky/csky-linux

Pull csky updates from Guo Ren:
 "This round of csky subsystem just some fixups:

   - Fix mb() synchronization problem

   - Fix dma_alloc_coherent with PAGE_SO attribute

   - Fix cache_op failed when cross memory ZONEs

   - Optimize arch_sync_dma_for_cpu/device with dma_inv_range

   - Fix ioremap function losing

   - Fix arch_get_unmapped_area() implementation

   - Fix defer cache flush for 610

   - Support kernel non-aligned access

   - Fix 610 vipt cache flush mechanism

   - Fix add zero_fp fixup perf backtrace panic

   - Move static keyword to the front of declaration

   - Fix csky_pmu.max_period assignment

   - Use generic free_initrd_mem()

   - entry: Remove unneeded need_resched() loop"

* tag 'csky-for-linus-5.4-rc1' of git://github.com/c-sky/csky-linux:
  csky: Move static keyword to the front of declaration
  csky: entry: Remove unneeded need_resched() loop
  csky: Fixup csky_pmu.max_period assignment
  csky: Fixup add zero_fp fixup perf backtrace panic
  csky: Use generic free_initrd_mem()
  csky: Fixup 610 vipt cache flush mechanism
  csky: Support kernel non-aligned access
  csky: Fixup defer cache flush for 610
  csky: Fixup arch_get_unmapped_area() implementation
  csky: Fixup ioremap function losing
  csky: Optimize arch_sync_dma_for_cpu/device with dma_inv_range
  csky/dma: Fixup cache_op failed when cross memory ZONEs
  csky: Fixup dma_alloc_coherent with PAGE_SO attribute
  csky: Fixup mb() synchronization problem

arch/csky/abiv1/alignment.c

@@ -5,8 +5,10 @@
 #include <linux/uaccess.h>
 #include <linux/ptrace.h>
 
-static int align_enable = 1;
+static int align_kern_enable = 1;
-static int align_count;
+static int align_usr_enable = 1;
+static int align_kern_count = 0;
+static int align_usr_count = 0;
 
 static inline uint32_t get_ptreg(struct pt_regs *regs, uint32_t rx)
 {
@@ -32,9 +34,6 @@ static int ldb_asm(uint32_t addr, uint32_t *valp)
 	uint32_t val;
 	int err;
 
-	if (!access_ok((void *)addr, 1))
-		return 1;
-
 	asm volatile (
 		"movi	%0, 0\n"
 		"1:\n"
@@ -67,9 +66,6 @@ static int stb_asm(uint32_t addr, uint32_t val)
 {
 	int err;
 
-	if (!access_ok((void *)addr, 1))
-		return 1;
-
 	asm volatile (
 		"movi	%0, 0\n"
 		"1:\n"
@@ -203,8 +199,6 @@ static int stw_c(struct pt_regs *regs, uint32_t rz, uint32_t addr)
 	if (stb_asm(addr, byte3))
 		return 1;
 
-	align_count++;
-
 	return 0;
 }
 
@@ -226,7 +220,14 @@ void csky_alignment(struct pt_regs *regs)
 	uint32_t addr   = 0;
 
 	if (!user_mode(regs))
+		goto kernel_area;
+
+	if (!align_usr_enable) {
+		pr_err("%s user disabled.\n", __func__);
 		goto bad_area;
+	}
+
+	align_usr_count++;
 
 	ret = get_user(tmp, (uint16_t *)instruction_pointer(regs));
 	if (ret) {
@@ -234,6 +235,19 @@ void csky_alignment(struct pt_regs *regs)
 		goto bad_area;
 	}
 
+	goto good_area;
+
+kernel_area:
+	if (!align_kern_enable) {
+		pr_err("%s kernel disabled.\n", __func__);
+		goto bad_area;
+	}
+
+	align_kern_count++;
+
+	tmp = *(uint16_t *)instruction_pointer(regs);
+
+good_area:
 	opcode = (uint32_t)tmp;
 
 	rx  = opcode & 0xf;
@@ -286,18 +300,32 @@ void csky_alignment(struct pt_regs *regs)
 	force_sig_fault(SIGBUS, BUS_ADRALN, (void __user *)addr);
 }
 
-static struct ctl_table alignment_tbl[4] = {
+static struct ctl_table alignment_tbl[5] = {
 	{
-		.procname = "enable",
+		.procname = "kernel_enable",
-		.data = &align_enable,
+		.data = &align_kern_enable,
-		.maxlen = sizeof(align_enable),
+		.maxlen = sizeof(align_kern_enable),
 		.mode = 0666,
 		.proc_handler = &proc_dointvec
 	},
 	{
-		.procname = "count",
+		.procname = "user_enable",
-		.data = &align_count,
+		.data = &align_usr_enable,
-		.maxlen = sizeof(align_count),
+		.maxlen = sizeof(align_usr_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "kernel_count",
+		.data = &align_kern_count,
+		.maxlen = sizeof(align_kern_count),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_count",
+		.data = &align_usr_count,
+		.maxlen = sizeof(align_usr_count),
 		.mode = 0666,
 		.proc_handler = &proc_dointvec
 	},

arch/csky/abiv1/cacheflush.c

@@ -11,42 +11,66 @@
 #include <asm/cacheflush.h>
 #include <asm/cachectl.h>
 
+#define PG_dcache_clean		PG_arch_1
+
 void flush_dcache_page(struct page *page)
 {
-	struct address_space *mapping = page_mapping(page);
+	struct address_space *mapping;
-	unsigned long addr;
 
-	if (mapping && !mapping_mapped(mapping)) {
+	if (page == ZERO_PAGE(0))
-		set_bit(PG_arch_1, &(page)->flags);
 		return;
+
+	mapping = page_mapping_file(page);
+
+	if (mapping && !page_mapcount(page))
+		clear_bit(PG_dcache_clean, &page->flags);
+	else {
+		dcache_wbinv_all();
+		if (mapping)
+			icache_inv_all();
+		set_bit(PG_dcache_clean, &page->flags);
 	}
-
-	/*
-	 * We could delay the flush for the !page_mapping case too.  But that
-	 * case is for exec env/arg pages and those are %99 certainly going to
-	 * get faulted into the tlb (and thus flushed) anyways.
-	 */
-	addr = (unsigned long) page_address(page);
-	dcache_wb_range(addr, addr + PAGE_SIZE);
 }
+EXPORT_SYMBOL(flush_dcache_page);
 
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
-		      pte_t *pte)
+	pte_t *ptep)
 {
-	unsigned long addr;
+	unsigned long pfn = pte_pfn(*ptep);
 	struct page *page;
-	unsigned long pfn;
 
-	pfn = pte_pfn(*pte);
+	if (!pfn_valid(pfn))
-	if (unlikely(!pfn_valid(pfn)))
 		return;
 
 	page = pfn_to_page(pfn);
-	addr = (unsigned long) page_address(page);
+	if (page == ZERO_PAGE(0))
+		return;
 
-	if (vma->vm_flags & VM_EXEC ||
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
-	    pages_do_alias(addr, address & PAGE_MASK))
+		dcache_wbinv_all();
-		cache_wbinv_all();
 
-	clear_bit(PG_arch_1, &(page)->flags);
+	if (page_mapping_file(page)) {
+		if (vma->vm_flags & VM_EXEC)
+			icache_inv_all();
+	}
+}
+
+void flush_kernel_dcache_page(struct page *page)
+{
+	struct address_space *mapping;
+
+	mapping = page_mapping_file(page);
+
+	if (!mapping || mapping_mapped(mapping))
+		dcache_wbinv_all();
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
+	unsigned long end)
+{
+	dcache_wbinv_all();
+
+	if (vma->vm_flags & VM_EXEC)
+		icache_inv_all();
 }

arch/csky/abiv1/inc/abi/cacheflush.h

@@ -4,46 +4,63 @@
 #ifndef __ABI_CSKY_CACHEFLUSH_H
 #define __ABI_CSKY_CACHEFLUSH_H
 
-#include <linux/compiler.h>
+#include <linux/mm.h>
 #include <asm/string.h>
 #include <asm/cache.h>
 
 #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1
 extern void flush_dcache_page(struct page *);
 
-#define flush_cache_mm(mm)			cache_wbinv_all()
+#define flush_cache_mm(mm)			dcache_wbinv_all()
 #define flush_cache_page(vma, page, pfn)	cache_wbinv_all()
 #define flush_cache_dup_mm(mm)			cache_wbinv_all()
 
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+extern void flush_kernel_dcache_page(struct page *);
+
+#define flush_dcache_mmap_lock(mapping)		xa_lock_irq(&mapping->i_pages)
+#define flush_dcache_mmap_unlock(mapping)	xa_unlock_irq(&mapping->i_pages)
+
+static inline void flush_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+static inline void invalidate_kernel_vmap_range(void *addr, int size)
+{
+	dcache_wbinv_all();
+}
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void flush_anon_page(struct vm_area_struct *vma,
+			 struct page *page, unsigned long vmaddr)
+{
+	if (PageAnon(page))
+		cache_wbinv_all();
+}
+
 /*
  * if (current_mm != vma->mm) cache_wbinv_range(start, end) will be broken.
  * Use cache_wbinv_all() here and need to be improved in future.
  */
-#define flush_cache_range(vma, start, end)	cache_wbinv_all()
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
-#define flush_cache_vmap(start, end)		cache_wbinv_range(start, end)
+#define flush_cache_vmap(start, end)		cache_wbinv_all()
-#define flush_cache_vunmap(start, end)		cache_wbinv_range(start, end)
+#define flush_cache_vunmap(start, end)		cache_wbinv_all()
 
-#define flush_icache_page(vma, page)		cache_wbinv_all()
+#define flush_icache_page(vma, page)		do {} while (0);
 #define flush_icache_range(start, end)		cache_wbinv_range(start, end)
 
-#define flush_icache_user_range(vma, pg, adr, len) \
+#define flush_icache_user_range(vma,page,addr,len) \
-				cache_wbinv_range(adr, adr + len)
+	flush_dcache_page(page)
 
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 do { \
-	cache_wbinv_all(); \
 	memcpy(dst, src, len); \
-	cache_wbinv_all(); \
 } while (0)
 
 #define copy_to_user_page(vma, page, vaddr, dst, src, len) \
 do { \
-	cache_wbinv_all(); \
 	memcpy(dst, src, len); \
 	cache_wbinv_all(); \
 } while (0)
 
-#define flush_dcache_mmap_lock(mapping)		do {} while (0)
-#define flush_dcache_mmap_unlock(mapping)	do {} while (0)
-
 #endif /* __ABI_CSKY_CACHEFLUSH_H */

arch/csky/abiv1/inc/abi/page.h

@@ -1,13 +1,14 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 // Copyright (C) 2018 Hangzhou C-SKY Microsystems co.,ltd.
 
-extern unsigned long shm_align_mask;
+#include <asm/shmparam.h>
+
 extern void flush_dcache_page(struct page *page);
 
 static inline unsigned long pages_do_alias(unsigned long addr1,
 					   unsigned long addr2)
 {
-	return (addr1 ^ addr2) & shm_align_mask;
+	return (addr1 ^ addr2) & (SHMLBA-1);
 }
 
 static inline void clear_user_page(void *addr, unsigned long vaddr,

arch/csky/abiv1/mmap.c

@@ -9,58 +9,63 @@
 #include <linux/random.h>
 #include <linux/io.h>
 
-unsigned long shm_align_mask = (0x4000 >> 1) - 1;   /* Sane caches */
+#define COLOUR_ALIGN(addr,pgoff)		\
+	((((addr)+SHMLBA-1)&~(SHMLBA-1)) +	\
+	 (((pgoff)<<PAGE_SHIFT) & (SHMLBA-1)))
 
-#define COLOUR_ALIGN(addr, pgoff) \
+/*
-	((((addr) + shm_align_mask) & ~shm_align_mask) + \
+ * We need to ensure that shared mappings are correctly aligned to
-	 (((pgoff) << PAGE_SHIFT) & shm_align_mask))
+ * avoid aliasing issues with VIPT caches.  We need to ensure that
-
+ * a specific page of an object is always mapped at a multiple of
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
+ * SHMLBA bytes.
+ *
+ * We unconditionally provide this function for all cases.
+ */
+unsigned long
+arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags)
 {
-	struct vm_area_struct *vmm;
+	struct mm_struct *mm = current->mm;
-	int do_color_align;
+	struct vm_area_struct *vma;
+	int do_align = 0;
+	struct vm_unmapped_area_info info;
 
+	/*
+	 * We only need to do colour alignment if either the I or D
+	 * caches alias.
+	 */
+	do_align = filp || (flags & MAP_SHARED);
+
+	/*
+	 * We enforce the MAP_FIXED case.
+	 */
 	if (flags & MAP_FIXED) {
-		/*
+		if (flags & MAP_SHARED &&
-		 * We do not accept a shared mapping if it would violate
+		    (addr - (pgoff << PAGE_SHIFT)) & (SHMLBA - 1))
-		 * cache aliasing constraints.
-		 */
-		if ((flags & MAP_SHARED) &&
-			((addr - (pgoff << PAGE_SHIFT)) & shm_align_mask))
 			return -EINVAL;
 		return addr;
 	}
 
 	if (len > TASK_SIZE)
 		return -ENOMEM;
-	do_color_align = 0;
+
-	if (filp || (flags & MAP_SHARED))
-		do_color_align = 1;
 	if (addr) {
-		if (do_color_align)
+		if (do_align)
 			addr = COLOUR_ALIGN(addr, pgoff);
 		else
 			addr = PAGE_ALIGN(addr);
-		vmm = find_vma(current->mm, addr);
-		if (TASK_SIZE - len >= addr &&
-				(!vmm || addr + len <= vmm->vm_start))
-			return addr;
-	}
-	addr = TASK_UNMAPPED_BASE;
-	if (do_color_align)
-		addr = COLOUR_ALIGN(addr, pgoff);
-	else
-		addr = PAGE_ALIGN(addr);
 
-	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
+		vma = find_vma(mm, addr);
-		/* At this point: (!vmm || addr < vmm->vm_end). */
+		if (TASK_SIZE - len >= addr &&
-		if (TASK_SIZE - len < addr)
+		    (!vma || addr + len <= vm_start_gap(vma)))
-			return -ENOMEM;
-		if (!vmm || addr + len <= vmm->vm_start)
 			return addr;
-		addr = vmm->vm_end;
-		if (do_color_align)
-			addr = COLOUR_ALIGN(addr, pgoff);
 	}
+
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = mm->mmap_base;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = do_align ? (PAGE_MASK & (SHMLBA - 1)) : 0;
+	info.align_offset = pgoff << PAGE_SHIFT;
+	return vm_unmapped_area(&info);
 }

arch/csky/include/asm/barrier.h

@@ -9,11 +9,12 @@
 #define nop()	asm volatile ("nop\n":::"memory")
 
 /*
- * sync:        completion barrier
+ * sync:        completion barrier, all sync.xx instructions
- * sync.s:      completion barrier and shareable to other cores
+ *              guarantee the last response recieved by bus transaction
- * sync.i:      completion barrier with flush cpu pipeline
+ *              made by ld/st instructions before sync.s
- * sync.is:     completion barrier with flush cpu pipeline and shareable to
+ * sync.s:      inherit from sync, but also shareable to other cores
- *		other cores
+ * sync.i:      inherit from sync, but also flush cpu pipeline
+ * sync.is:     the same with sync.i + sync.s
  *
  * bar.brwarw:  ordering barrier for all load/store instructions before it
  * bar.brwarws: ordering barrier for all load/store instructions before it
@@ -27,9 +28,7 @@
  */
 
 #ifdef CONFIG_CPU_HAS_CACHEV2
-#define mb()		asm volatile ("bar.brwarw\n":::"memory")
+#define mb()		asm volatile ("sync.s\n":::"memory")
-#define rmb()		asm volatile ("bar.brar\n":::"memory")
-#define wmb()		asm volatile ("bar.bwaw\n":::"memory")
 
 #ifdef CONFIG_SMP
 #define __smp_mb()	asm volatile ("bar.brwarws\n":::"memory")

arch/csky/include/asm/cache.h

@@ -24,6 +24,7 @@ void cache_wbinv_range(unsigned long start, unsigned long end);
 void cache_wbinv_all(void);
 
 void dma_wbinv_range(unsigned long start, unsigned long end);
+void dma_inv_range(unsigned long start, unsigned long end);
 void dma_wb_range(unsigned long start, unsigned long end);
 
 #endif

arch/csky/include/asm/io.h

@@ -4,17 +4,10 @@
 #ifndef __ASM_CSKY_IO_H
 #define __ASM_CSKY_IO_H
 
-#include <abi/pgtable-bits.h>
+#include <asm/pgtable.h>
 #include <linux/types.h>
 #include <linux/version.h>
 
-extern void __iomem *ioremap(phys_addr_t offset, size_t size);
-
-extern void iounmap(void *addr);
-
-extern int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
-		size_t size, unsigned long flags);
-
 /*
  * I/O memory access primitives. Reads are ordered relative to any
  * following Normal memory access. Writes are ordered relative to any prior
@@ -40,9 +33,17 @@ extern int remap_area_pages(unsigned long address, phys_addr_t phys_addr,
 #define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); mb(); })
 #endif
 
-#define ioremap_nocache(phy, sz)	ioremap(phy, sz)
+/*
-#define ioremap_wc ioremap_nocache
+ * I/O memory mapping functions.
-#define ioremap_wt ioremap_nocache
+ */
+extern void __iomem *ioremap_cache(phys_addr_t addr, size_t size);
+extern void __iomem *__ioremap(phys_addr_t addr, size_t size, pgprot_t prot);
+extern void iounmap(void *addr);
+
+#define ioremap(addr, size)		__ioremap((addr), (size), pgprot_noncached(PAGE_KERNEL))
+#define ioremap_wc(addr, size)		__ioremap((addr), (size), pgprot_writecombine(PAGE_KERNEL))
+#define ioremap_nocache(addr, size)	ioremap((addr), (size))
+#define ioremap_cache			ioremap_cache
 
 #include <asm-generic/io.h>
 

arch/csky/include/asm/pgtable.h

@@ -258,6 +258,16 @@ static inline pgprot_t pgprot_noncached(pgprot_t _prot)
 {
 	unsigned long prot = pgprot_val(_prot);
 
+	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED | _PAGE_SO;
+
+	return __pgprot(prot);
+}
+
+#define pgprot_writecombine pgprot_writecombine
+static inline pgprot_t pgprot_writecombine(pgprot_t _prot)
+{
+	unsigned long prot = pgprot_val(_prot);
+
 	prot = (prot & ~_CACHE_MASK) | _CACHE_UNCACHED;
 
 	return __pgprot(prot);

arch/csky/kernel/entry.S

@@ -17,6 +17,12 @@
 #define PTE_INDX_SHIFT  10
 #define _PGDIR_SHIFT    22
 
+.macro	zero_fp
+#ifdef CONFIG_STACKTRACE
+	movi	r8, 0
+#endif
+.endm
+
 .macro tlbop_begin name, val0, val1, val2
 ENTRY(csky_\name)
 	mtcr    a3, ss2
@@ -96,6 +102,7 @@ ENTRY(csky_\name)
 	SAVE_ALL 0
 .endm
 .macro tlbop_end is_write
+	zero_fp
 	RD_MEH	a2
 	psrset  ee, ie
 	mov     a0, sp
@@ -120,6 +127,7 @@ tlbop_end 1
 
 ENTRY(csky_systemcall)
 	SAVE_ALL TRAP0_SIZE
+	zero_fp
 
 	psrset  ee, ie
 
@@ -136,9 +144,9 @@ ENTRY(csky_systemcall)
 	mov     r9, sp
 	bmaski  r10, THREAD_SHIFT
 	andn    r9, r10
-	ldw     r8, (r9, TINFO_FLAGS)
+	ldw     r12, (r9, TINFO_FLAGS)
-	ANDI_R3	r8, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r8, 0
+	cmpnei	r12, 0
 	bt      csky_syscall_trace
 #if defined(__CSKYABIV2__)
 	subi    sp, 8
@@ -180,7 +188,7 @@ csky_syscall_trace:
 
 ENTRY(ret_from_kernel_thread)
 	jbsr	schedule_tail
-	mov	a0, r8
+	mov	a0, r10
 	jsr	r9
 	jbsr	ret_from_exception
 
@@ -189,9 +197,9 @@ ENTRY(ret_from_fork)
 	mov	r9, sp
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
-	ldw	r8, (r9, TINFO_FLAGS)
+	ldw	r12, (r9, TINFO_FLAGS)
-	ANDI_R3	r8, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
+	ANDI_R3	r12, (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_TRACEPOINT | _TIF_SYSCALL_AUDIT)
-	cmpnei	r8, 0
+	cmpnei	r12, 0
 	bf	ret_from_exception
 	mov	a0, sp			/* sp = pt_regs pointer */
 	jbsr	syscall_trace_exit
@@ -209,9 +217,9 @@ ret_from_exception:
 	bmaski	r10, THREAD_SHIFT
 	andn	r9, r10
 
-	ldw	r8, (r9, TINFO_FLAGS)
+	ldw	r12, (r9, TINFO_FLAGS)
-	andi	r8, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
+	andi	r12, (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED)
-	cmpnei	r8, 0
+	cmpnei	r12, 0
 	bt	exit_work
 1:
 	RESTORE_ALL
@@ -220,11 +228,11 @@ exit_work:
 	lrw	syscallid, ret_from_exception
 	mov	lr, syscallid
 
-	btsti	r8, TIF_NEED_RESCHED
+	btsti	r12, TIF_NEED_RESCHED
 	bt	work_resched
 
 	mov	a0, sp
-	mov	a1, r8
+	mov	a1, r12
 	jmpi	do_notify_resume
 
 work_resched:
@@ -232,6 +240,7 @@ work_resched:
 
 ENTRY(csky_trap)
 	SAVE_ALL 0
+	zero_fp
 	psrset	ee
 	mov	a0, sp                 /* Push Stack pointer arg */
 	jbsr	trap_c                 /* Call C-level trap handler */
@@ -265,6 +274,7 @@ ENTRY(csky_get_tls)
 
 ENTRY(csky_irq)
 	SAVE_ALL 0
+	zero_fp
 	psrset	ee
 
 #ifdef CONFIG_PREEMPT
@@ -276,27 +286,23 @@ ENTRY(csky_irq)
 	 * Get task_struct->stack.preempt_count for current,
 	 * and increase 1.
 	 */
-	ldw	r8, (r9, TINFO_PREEMPT)
+	ldw	r12, (r9, TINFO_PREEMPT)
-	addi	r8, 1
+	addi	r12, 1
-	stw	r8, (r9, TINFO_PREEMPT)
+	stw	r12, (r9, TINFO_PREEMPT)
 #endif
 
 	mov	a0, sp
 	jbsr	csky_do_IRQ
 
 #ifdef CONFIG_PREEMPT
-	subi	r8, 1
+	subi	r12, 1
-	stw	r8, (r9, TINFO_PREEMPT)
+	stw	r12, (r9, TINFO_PREEMPT)
-	cmpnei	r8, 0
+	cmpnei	r12, 0
 	bt	2f
-	ldw	r8, (r9, TINFO_FLAGS)
+	ldw	r12, (r9, TINFO_FLAGS)
-	btsti	r8, TIF_NEED_RESCHED
+	btsti	r12, TIF_NEED_RESCHED
 	bf	2f
-1:
 	jbsr	preempt_schedule_irq	/* irq en/disable is done inside */
-	ldw	r7, (r9, TINFO_FLAGS)	/* get new tasks TI_FLAGS */
-	btsti	r7, TIF_NEED_RESCHED
-	bt	1b			/* go again */
 #endif
 2:
 	jmpi	ret_from_exception

arch/csky/kernel/perf_event.c

@@ -1306,7 +1306,7 @@ int csky_pmu_device_probe(struct platform_device *pdev,
 				 &csky_pmu.count_width)) {
 		csky_pmu.count_width = DEFAULT_COUNT_WIDTH;
 	}
-	csky_pmu.max_period = BIT(csky_pmu.count_width) - 1;
+	csky_pmu.max_period = BIT_ULL(csky_pmu.count_width) - 1;
 
 	csky_pmu.plat_device = pdev;
 
@@ -1337,7 +1337,7 @@ int csky_pmu_device_probe(struct platform_device *pdev,
 	return ret;
 }
 
-const static struct of_device_id csky_pmu_of_device_ids[] = {
+static const struct of_device_id csky_pmu_of_device_ids[] = {
 	{.compatible = "csky,csky-pmu"},
 	{},
 };

arch/csky/kernel/process.c

@@ -55,7 +55,7 @@ int copy_thread(unsigned long clone_flags,
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childstack->r15 = (unsigned long) ret_from_kernel_thread;
-		childstack->r8 = kthread_arg;
+		childstack->r10 = kthread_arg;
 		childstack->r9 = usp;
 		childregs->sr = mfcr("psr");
 	} else {

arch/csky/mm/cachev1.c

@@ -120,7 +120,12 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
-	cache_op_range(start, end, DATA_CACHE|CACHE_INV, 1);
+	cache_op_range(start, end, DATA_CACHE|CACHE_CLR|CACHE_INV, 1);
 }

arch/csky/mm/cachev2.c

@@ -69,11 +69,20 @@ void dma_wbinv_range(unsigned long start, unsigned long end)
 	sync_is();
 }
 
+void dma_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
+
+	for (; i < end; i += L1_CACHE_BYTES)
+		asm volatile("dcache.iva %0\n"::"r"(i):"memory");
+	sync_is();
+}
+
 void dma_wb_range(unsigned long start, unsigned long end)
 {
 	unsigned long i = start & ~(L1_CACHE_BYTES - 1);
 
 	for (; i < end; i += L1_CACHE_BYTES)
-		asm volatile("dcache.civa %0\n"::"r"(i):"memory");
+		asm volatile("dcache.cva %0\n"::"r"(i):"memory");
 	sync_is();
 }

arch/csky/mm/dma-mapping.c

@@ -14,69 +14,50 @@
 #include <linux/version.h>
 #include <asm/cache.h>
 
-void arch_dma_prep_coherent(struct page *page, size_t size)
-{
-	if (PageHighMem(page)) {
-		unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-		do {
-			void *ptr = kmap_atomic(page);
-			size_t _size = (size < PAGE_SIZE) ? size : PAGE_SIZE;
-
-			memset(ptr, 0, _size);
-			dma_wbinv_range((unsigned long)ptr,
-					(unsigned long)ptr + _size);
-
-			kunmap_atomic(ptr);
-
-			page++;
-			size -= PAGE_SIZE;
-			count--;
-		} while (count);
-	} else {
-		void *ptr = page_address(page);
-
-		memset(ptr, 0, size);
-		dma_wbinv_range((unsigned long)ptr, (unsigned long)ptr + size);
-	}
-}
-
 static inline void cache_op(phys_addr_t paddr, size_t size,
 			    void (*fn)(unsigned long start, unsigned long end))
 {
-	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	struct page *page    = phys_to_page(paddr);
-	unsigned int offset = paddr & ~PAGE_MASK;
+	void *start          = __va(page_to_phys(page));
-	size_t left = size;
+	unsigned long offset = offset_in_page(paddr);
-	unsigned long start;
+	size_t left          = size;
 
 	do {
 		size_t len = left;
 
+		if (offset + len > PAGE_SIZE)
+			len = PAGE_SIZE - offset;
+
 		if (PageHighMem(page)) {
-			void *addr;
+			start = kmap_atomic(page);
 
-			if (offset + len > PAGE_SIZE) {
+			fn((unsigned long)start + offset,
-				if (offset >= PAGE_SIZE) {
+					(unsigned long)start + offset + len);
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
 
-			addr = kmap_atomic(page);
+			kunmap_atomic(start);
-			start = (unsigned long)(addr + offset);
-			fn(start, start + len);
-			kunmap_atomic(addr);
 		} else {
-			start = (unsigned long)phys_to_virt(paddr);
+			fn((unsigned long)start + offset,
-			fn(start, start + size);
+					(unsigned long)start + offset + len);
 		}
 		offset = 0;
+
 		page++;
+		start += PAGE_SIZE;
 		left -= len;
 	} while (left);
 }
 
+static void dma_wbinv_set_zero_range(unsigned long start, unsigned long end)
+{
+	memset((void *)start, 0, end - start);
+	dma_wbinv_range(start, end);
+}
+
+void arch_dma_prep_coherent(struct page *page, size_t size)
+{
+	cache_op(page_to_phys(page), size, dma_wbinv_set_zero_range);
+}
+
 void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
 			      size_t size, enum dma_data_direction dir)
 {
@@ -98,11 +79,10 @@ void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
 {
 	switch (dir) {
 	case DMA_TO_DEVICE:
-		cache_op(paddr, size, dma_wb_range);
+		return;
-		break;
 	case DMA_FROM_DEVICE:
 	case DMA_BIDIRECTIONAL:
-		cache_op(paddr, size, dma_wbinv_range);
+		cache_op(paddr, size, dma_inv_range);
 		break;
 	default:
 		BUG();

arch/csky/mm/init.c

@@ -60,22 +60,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-#ifdef CONFIG_BLK_DEV_INITRD
-void free_initrd_mem(unsigned long start, unsigned long end)
-{
-	if (start < end)
-		pr_info("Freeing initrd memory: %ldk freed\n",
-			(end - start) >> 10);
-
-	for (; start < end; start += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(start));
-		init_page_count(virt_to_page(start));
-		free_page(start);
-		totalram_pages_inc();
-	}
-}
-#endif
-
 extern char __init_begin[], __init_end[];
 
 void free_initmem(void)

arch/csky/mm/ioremap.c

@@ -8,12 +8,12 @@
 
 #include <asm/pgtable.h>
 
-void __iomem *ioremap(phys_addr_t addr, size_t size)
+static void __iomem *__ioremap_caller(phys_addr_t addr, size_t size,
+				      pgprot_t prot, void *caller)
 {
 	phys_addr_t last_addr;
 	unsigned long offset, vaddr;
 	struct vm_struct *area;
-	pgprot_t prot;
 
 	last_addr = addr + size - 1;
 	if (!size || last_addr < addr)
@@ -23,15 +23,12 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 	addr &= PAGE_MASK;
 	size = PAGE_ALIGN(size + offset);
 
-	area = get_vm_area_caller(size, VM_ALLOC, __builtin_return_address(0));
+	area = get_vm_area_caller(size, VM_IOREMAP, caller);
 	if (!area)
 		return NULL;
 
 	vaddr = (unsigned long)area->addr;
 
-	prot = __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE |
-			_PAGE_GLOBAL | _CACHE_UNCACHED | _PAGE_SO);
-
 	if (ioremap_page_range(vaddr, vaddr + size, addr, prot)) {
 		free_vm_area(area);
 		return NULL;
@@ -39,7 +36,20 @@ void __iomem *ioremap(phys_addr_t addr, size_t size)
 
 	return (void __iomem *)(vaddr + offset);
 }
-EXPORT_SYMBOL(ioremap);
+
+void __iomem *__ioremap(phys_addr_t phys_addr, size_t size, pgprot_t prot)
+{
+	return __ioremap_caller(phys_addr, size, prot,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(__ioremap);
+
+void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size)
+{
+	return __ioremap_caller(phys_addr, size, PAGE_KERNEL,
+				__builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
 
 void iounmap(void __iomem *addr)
 {
@@ -51,10 +61,9 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
 			      unsigned long size, pgprot_t vma_prot)
 {
 	if (!pfn_valid(pfn)) {
-		vma_prot.pgprot |= _PAGE_SO;
 		return pgprot_noncached(vma_prot);
 	} else if (file->f_flags & O_SYNC) {
-		return pgprot_noncached(vma_prot);
+		return pgprot_writecombine(vma_prot);
 	}
 
 	return vma_prot;