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

Author: torvalds

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_count;
+static int align_kern_enable = 1;
+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;
 }
 
@@ -226,14 +220,34 @@ 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) {
 		pr_err("%s get_user failed.\n", __func__);
 		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 = "kernel_enable",
+		.data = &align_kern_enable,
+		.maxlen = sizeof(align_kern_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
+	{
+		.procname = "user_enable",
+		.data = &align_usr_enable,
+		.maxlen = sizeof(align_usr_enable),
+		.mode = 0666,
+		.proc_handler = &proc_dointvec
+	},
 	{
-		.procname = "enable",
-		.data = &align_enable,
-		.maxlen = sizeof(align_enable),
+		.procname = "kernel_count",
+		.data = &align_kern_count,
+		.maxlen = sizeof(align_kern_count),
 		.mode = 0666,
 		.proc_handler = &proc_dointvec
 	},
 	{
-		.procname = "count",
-		.data = &align_count,
-		.maxlen = sizeof(align_count),
+		.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);
-	unsigned long addr;
+	struct address_space *mapping;
 
-	if (mapping && !mapping_mapped(mapping)) {
-		set_bit(PG_arch_1, &(page)->flags);
+	if (page == ZERO_PAGE(0))
 		return;
-	}
 
-	/*
-	 * 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);
+	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);
+	}
 }
+EXPORT_SYMBOL(flush_dcache_page);
 
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
-		      pte_t *pte)
+void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
+	pte_t *ptep)
 {
-	unsigned long addr;
+	unsigned long pfn = pte_pfn(*ptep);
 	struct page *page;
-	unsigned long pfn;
 
-	pfn = pte_pfn(*pte);
-	if (unlikely(!pfn_valid(pfn)))
+	if (!pfn_valid(pfn))
 		return;
 
 	page = pfn_to_page(pfn);
-	addr = (unsigned long) page_address(page);
+	if (page == ZERO_PAGE(0))
+		return;
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		dcache_wbinv_all();
 
-	if (vma->vm_flags & VM_EXEC ||
-	    pages_do_alias(addr, address & PAGE_MASK))
-		cache_wbinv_all();
+	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();
 
-	clear_bit(PG_arch_1, &(page)->flags);
+	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()
-#define flush_cache_vmap(start, end)		cache_wbinv_range(start, end)
-#define flush_cache_vunmap(start, end)		cache_wbinv_range(start, end)
+extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
+#define flush_cache_vmap(start, end)		cache_wbinv_all()
+#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) \
-				cache_wbinv_range(adr, adr + len)
+#define flush_icache_user_range(vma,page,addr,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,