Merge tag 'csky-for-linus-5.0-rc1' of git://github.com/c-sky/csky-linux

Pull arch/csky bug fixes from Guo Ren:
 "Here are some fixup patches for 5.0-rc1:

   - fix compile error with pte_alloc

   - fix handle_irq_perbit break irq flow

   - fix CACHEV1 store instruction fast retire

   - fix module relocation error with 807 & 860

   - add csky kernel features to documentation"

* tag 'csky-for-linus-5.0-rc1' of git://github.com/c-sky/csky-linux:
  irqchip/csky: fixup handle_irq_perbit break irq
  csky: fixup compile error with pte_alloc
  csky: fixup CACHEV1 store instruction fast retire
  csky: fixup relocation error with 807 & 860
  Documentation/features: Add csky kernel features

3 files changed, 65 insertions, 41 deletions

diff --git a/arch/csky/include/asm/io.h b/arch/csky/include/asm/io.h
index ecae6b358f95..c1dfa9c10e36 100644
--- a/arch/csky/include/asm/io.h
+++ b/arch/csky/include/asm/io.h
@@ -15,6 +15,31 @@ 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
+ * Normal memory access.
+ *
+ * For CACHEV1 (807, 810), store instruction could fast retire, so we need
+ * another mb() to prevent st fast retire.
+ *
+ * For CACHEV2 (860), store instruction with PAGE_ATTR_NO_BUFFERABLE won't
+ * fast retire.
+ */
+#define readb(c)		({ u8  __v = readb_relaxed(c); rmb(); __v; })
+#define readw(c)		({ u16 __v = readw_relaxed(c); rmb(); __v; })
+#define readl(c)		({ u32 __v = readl_relaxed(c); rmb(); __v; })
+
+#ifdef CONFIG_CPU_HAS_CACHEV2
+#define writeb(v,c)		({ wmb(); writeb_relaxed((v),(c)); })
+#define writew(v,c)		({ wmb(); writew_relaxed((v),(c)); })
+#define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); })
+#else
+#define writeb(v,c)		({ wmb(); writeb_relaxed((v),(c)); mb(); })
+#define writew(v,c)		({ wmb(); writew_relaxed((v),(c)); mb(); })
+#define writel(v,c)		({ wmb(); writel_relaxed((v),(c)); mb(); })
+#endif
+
 #define ioremap_nocache(phy, sz)	ioremap(phy, sz)
 #define ioremap_wc ioremap_nocache
 #define ioremap_wt ioremap_nocache
diff --git a/arch/csky/include/asm/pgalloc.h b/arch/csky/include/asm/pgalloc.h
index bf4f4a0e140e..d213bb47b717 100644
--- a/arch/csky/include/asm/pgalloc.h
+++ b/arch/csky/include/asm/pgalloc.h
@@ -24,41 +24,34 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 
 extern void pgd_init(unsigned long *p);
 
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
-					unsigned long address)
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
 {
 	pte_t *pte;
-	unsigned long *kaddr, i;
+	unsigned long i;
 
-	pte = (pte_t *) __get_free_pages(GFP_KERNEL | __GFP_RETRY_MAYFAIL,
-					 PTE_ORDER);
-	kaddr = (unsigned long *)pte;
-	if (address & 0x80000000)
-		for (i = 0; i < (PAGE_SIZE/4); i++)
-			*(kaddr + i) = 0x1;
-	else
-		clear_page(kaddr);
+	pte = (pte_t *) __get_free_page(GFP_KERNEL);
+	if (!pte)
+		return NULL;
+
+	for (i = 0; i < PAGE_SIZE/sizeof(pte_t); i++)
+		(pte + i)->pte_low = _PAGE_GLOBAL;
 
 	return pte;
 }
 
-static inline struct page *pte_alloc_one(struct mm_struct *mm,
-						unsigned long address)
+static inline struct page *pte_alloc_one(struct mm_struct *mm)
 {
 	struct page *pte;
-	unsigned long *kaddr, i;
-
-	pte = alloc_pages(GFP_KERNEL | __GFP_RETRY_MAYFAIL, PTE_ORDER);
-	if (pte) {
-		kaddr = kmap_atomic(pte);
-		if (address & 0x80000000) {
-			for (i = 0; i < (PAGE_SIZE/4); i++)
-				*(kaddr + i) = 0x1;
-		} else
-			clear_page(kaddr);
-		kunmap_atomic(kaddr);
-		pgtable_page_ctor(pte);
+
+	pte = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0);
+	if (!pte)
+		return NULL;
+
+	if (!pgtable_page_ctor(pte)) {
+		__free_page(pte);
+		return NULL;
 	}
+
 	return pte;
 }
 
diff --git a/arch/csky/kernel/module.c b/arch/csky/kernel/module.c
index 65abab0c7a47..0b028ee3c764 100644
--- a/arch/csky/kernel/module.c
+++ b/arch/csky/kernel/module.c
@@ -12,7 +12,7 @@
 #include <linux/spinlock.h>
 #include <asm/pgtable.h>
 
-#if defined(__CSKYABIV2__)
+#ifdef CONFIG_CPU_CK810
 #define IS_BSR32(hi16, lo16)		(((hi16) & 0xFC00) == 0xE000)
 #define IS_JSRI32(hi16, lo16)		((hi16) == 0xEAE0)
 
@@ -25,6 +25,26 @@
 	*(uint16_t *)(addr) = 0xE8Fa;		\
 	*((uint16_t *)(addr) + 1) = 0x0000;	\
 } while (0)
+
+static void jsri_2_lrw_jsr(uint32_t *location)
+{
+	uint16_t location_tmp = (uint16_t *)location;
+
+	if (IS_BSR32(*location_tmp, *(location_tmp + 1)))
+		return;
+
+	if (IS_JSRI32(*location_tmp, *(location_tmp + 1))) {
+		/* jsri 0x...  --> lrw r26, 0x... */
+		CHANGE_JSRI_TO_LRW(location);
+		/* lsli r0, r0 --> jsr r26 */
+		SET_JSR32_R26(location + 1);
+	}
+}
+#else
+static void inline jsri_2_lrw_jsr(uint32_t *location)
+{
+	return;
+}
 #endif
 
 int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
@@ -35,9 +55,6 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 	Elf32_Sym	*sym;
 	uint32_t	*location;
 	short		*temp;
-#if defined(__CSKYABIV2__)
-	uint16_t	*location_tmp;
-#endif
 
 	for (i = 0; i < sechdrs[relsec].sh_size / sizeof(*rel); i++) {
 		/* This is where to make the change */
@@ -59,18 +76,7 @@ int apply_relocate_add(Elf32_Shdr *sechdrs, const char *strtab,
 		case R_CSKY_PCRELJSR_IMM11BY2:
 			break;
 		case R_CSKY_PCRELJSR_IMM26BY2:
-#if defined(__CSKYABIV2__)
-			location_tmp = (uint16_t *)location;
-			if (IS_BSR32(*location_tmp, *(location_tmp + 1)))
-				break;
-
-			if (IS_JSRI32(*location_tmp, *(location_tmp + 1))) {
-				/* jsri 0x...  --> lrw r26, 0x... */
-				CHANGE_JSRI_TO_LRW(location);
-				/* lsli r0, r0 --> jsr r26 */
-				SET_JSR32_R26(location + 1);
-			}
-#endif
+			jsri_2_lrw_jsr(location);
 			break;
 		case R_CSKY_ADDR_HI16:
 			temp = ((short  *)location) + 1;