LoongArch: Use TLB for ioremap()

We can support more cache attributes (e.g., CC, SUC and WUC) and page
protection when we use TLB for ioremap(). The implementation is based
on GENERIC_IOREMAP.

The existing simple ioremap() implementation has better performance so
we keep it and introduce ARCH_IOREMAP to control the selection.

We move pagetable_init() earlier to make early ioremap() works, and we
modify the PCI ecam mapping because the TLB-based version of ioremap()
will actually take the size into account.

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

3 files changed, 36 insertions, 51 deletions

diff --git a/arch/loongarch/include/asm/fixmap.h b/arch/loongarch/include/asm/fixmap.h
index b3541dfa2013..d2e55ae55bb9 100644
--- a/arch/loongarch/include/asm/fixmap.h
+++ b/arch/loongarch/include/asm/fixmap.h
@@ -10,4 +10,19 @@
 
 #define NR_FIX_BTMAPS 64
 
+enum fixed_addresses {
+	FIX_HOLE,
+	FIX_EARLYCON_MEM_BASE,
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+#define FIXMAP_PAGE_IO	PAGE_KERNEL_SUC
+
+extern void __set_fixmap(enum fixed_addresses idx,
+			 phys_addr_t phys, pgprot_t flags);
+
+#include <asm-generic/fixmap.h>
+
 #endif
diff --git a/arch/loongarch/include/asm/io.h b/arch/loongarch/include/asm/io.h
index 398d1a7b3dd6..402a7d9e3a53 100644
--- a/arch/loongarch/include/asm/io.h
+++ b/arch/loongarch/include/asm/io.h
@@ -27,71 +27,38 @@ extern void __init early_iounmap(void __iomem *addr, unsigned long size);
 #define early_memremap early_ioremap
 #define early_memunmap early_iounmap
 
+#ifdef CONFIG_ARCH_IOREMAP
+
 static inline void __iomem *ioremap_prot(phys_addr_t offset, unsigned long size,
 					 unsigned long prot_val)
 {
-	if (prot_val == _CACHE_CC)
+	if (prot_val & _CACHE_CC)
 		return (void __iomem *)(unsigned long)(CACHE_BASE + offset);
 	else
 		return (void __iomem *)(unsigned long)(UNCACHE_BASE + offset);
 }
 
-/*
- * ioremap -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- */
-#define ioremap(offset, size)					\
-	ioremap_prot((offset), (size), _CACHE_SUC)
+#define ioremap(offset, size)		\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_SUC))
 
-/*
- * ioremap_wc - map bus memory into CPU space
- * @offset:     bus address of the memory
- * @size:       size of the resource to map
- *
- * ioremap_wc performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * This version of ioremap ensures that the memory is marked uncachable
- * but accelerated by means of write-combining feature. It is specifically
- * useful for PCIe prefetchable windows, which may vastly improve a
- * communications performance. If it was determined on boot stage, what
- * CPU CCA doesn't support WUC, the method shall fall-back to the
- * _CACHE_SUC option (see cpu_probe() method).
- */
-#define ioremap_wc(offset, size)				\
-	ioremap_prot((offset), (size), _CACHE_WUC)
+#define iounmap(addr) 			((void)(addr))
+
+#endif
 
 /*
- * ioremap_cache -  map bus memory into CPU space
- * @offset:	    bus address of the memory
- * @size:	    size of the resource to map
- *
- * ioremap_cache performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
+ * On LoongArch, ioremap() has two variants, ioremap_wc() and ioremap_cache().
+ * They map bus memory into CPU space, the mapped memory is marked uncachable
+ * (_CACHE_SUC), uncachable but accelerated by write-combine (_CACHE_WUC) and
+ * cachable (_CACHE_CC) respectively for CPU access.
  *
- * This version of ioremap ensures that the memory is marked cachable by
- * the CPU.  Also enables full write-combining.	 Useful for some
- * memory-like regions on I/O busses.
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
  */
-#define ioremap_cache(offset, size)				\
-	ioremap_prot((offset), (size), _CACHE_CC)
+#define ioremap_wc(offset, size)	\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL_WUC))
 
-static inline void iounmap(const volatile void __iomem *addr)
-{
-}
+#define ioremap_cache(offset, size)	\
+	ioremap_prot((offset), (size), pgprot_val(PAGE_KERNEL))
 
 #define mmiowb() asm volatile ("dbar 0" ::: "memory")
 
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 9ca147a29bab..3d1e0a69975a 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -83,8 +83,11 @@
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_SUC)
 #define PAGE_KERNEL_WUC __pgprot(_PAGE_PRESENT | __READABLE | __WRITEABLE | \
 				 _PAGE_GLOBAL | _PAGE_KERN |  _CACHE_WUC)
+
 #ifndef __ASSEMBLY__
 
+#define _PAGE_IOREMAP		pgprot_val(PAGE_KERNEL_SUC)
+
 #define pgprot_noncached pgprot_noncached
 
 static inline pgprot_t pgprot_noncached(pgprot_t _prot)