openrisc: Introduce new utility functions to flush and invalidate caches

According to the OpenRISC architecture manual, the dcache and icache may
not be present. When these caches are present, the invalidate and flush
registers may be absent. The current implementation does not perform
checks to verify their presence before utilizing cache registers, or
invalidating and flushing cache blocks.

Introduce new functions to detect the presence of cache components and
related special-purpose registers.

There are a few places where a range of addresses have to be flushed or
invalidated and the implementation is duplicated. Introduce new utility
functions and macros that generalize this implementation and reduce
duplication.

Signed-off-by: Sahil Siddiq <sahilcdq0@gmail.com>
Signed-off-by: Stafford Horne <shorne@gmail.com>

Author: valdaarhun

arch/openrisc/include/asm/cacheflush.h

@@ -23,6 +23,9 @@
  */
 extern void local_dcache_page_flush(struct page *page);
 extern void local_icache_page_inv(struct page *page);
+extern void local_dcache_range_flush(unsigned long start, unsigned long end);
+extern void local_dcache_range_inv(unsigned long start, unsigned long end);
+extern void local_icache_range_inv(unsigned long start, unsigned long end);
 
 /*
  * Data cache flushing always happen on the local cpu. Instruction cache
@@ -38,6 +41,20 @@ extern void local_icache_page_inv(struct page *page);
 extern void smp_icache_page_inv(struct page *page);
 #endif /* CONFIG_SMP */
 
+/*
+ * Even if the actual block size is larger than L1_CACHE_BYTES, paddr
+ * can be incremented by L1_CACHE_BYTES. When paddr is written to the
+ * invalidate register, the entire cache line encompassing this address
+ * is invalidated. Each subsequent reference to the same cache line will
+ * not affect the invalidation process.
+ */
+#define local_dcache_block_flush(addr) \
+	local_dcache_range_flush(addr, addr + L1_CACHE_BYTES)
+#define local_dcache_block_inv(addr) \
+	local_dcache_range_inv(addr, addr + L1_CACHE_BYTES)
+#define local_icache_block_inv(addr) \
+	local_icache_range_inv(addr, addr + L1_CACHE_BYTES)
+
 /*
  * Synchronizes caches. Whenever a cpu writes executable code to memory, this
  * should be called to make sure the processor sees the newly written code.

arch/openrisc/include/asm/cpuinfo.h

@@ -15,6 +15,9 @@
 #ifndef __ASM_OPENRISC_CPUINFO_H
 #define __ASM_OPENRISC_CPUINFO_H
 
+#include <asm/spr.h>
+#include <asm/spr_defs.h>
+
 struct cache_desc {
 	u32 size;
 	u32 sets;
@@ -34,4 +37,9 @@ struct cpuinfo_or1k {
 extern struct cpuinfo_or1k cpuinfo_or1k[NR_CPUS];
 extern void setup_cpuinfo(void);
 
+/*
+ * Check if the cache component exists.
+ */
+extern bool cpu_cache_is_present(const unsigned int cache_type);
+
 #endif /* __ASM_OPENRISC_CPUINFO_H */

arch/openrisc/kernel/dma.c

@@ -17,16 +17,14 @@
 #include <linux/pagewalk.h>
 
 #include <asm/cpuinfo.h>
+#include <asm/cacheflush.h>
 #include <asm/spr_defs.h>
 #include <asm/tlbflush.h>
 
 static int
 page_set_nocache(pte_t *pte, unsigned long addr,
 		 unsigned long next, struct mm_walk *walk)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	pte_val(*pte) |= _PAGE_CI;
 
 	/*
@@ -36,8 +34,7 @@ page_set_nocache(pte_t *pte, unsigned long addr,
 	flush_tlb_kernel_range(addr, addr + PAGE_SIZE);
 
 	/* Flush page out of dcache */
-	for (cl = __pa(addr); cl < __pa(next); cl += cpuinfo->dcache_block_size)
-		mtspr(SPR_DCBFR, cl);
+	local_dcache_range_flush(__pa(addr), __pa(next));
 
 	return 0;
 }
@@ -98,21 +95,14 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 void arch_sync_dma_for_device(phys_addr_t addr, size_t size,
 		enum dma_data_direction dir)
 {
-	unsigned long cl;
-	struct cpuinfo_or1k *cpuinfo = &cpuinfo_or1k[smp_processor_id()];
-
 	switch (dir) {
 	case DMA_TO_DEVICE:
 		/* Flush the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBFR, cl);
+		local_dcache_range_flush(addr, addr + size);
 		break;
 	case DMA_FROM_DEVICE:
 		/* Invalidate the dcache for the requested range */
-		for (cl = addr; cl < addr + size;
-		     cl += cpuinfo->dcache_block_size)
-			mtspr(SPR_DCBIR, cl);
+		local_dcache_range_inv(addr, addr + size);
 		break;
 	default:
 		/*

arch/openrisc/mm/cache.c

@@ -14,31 +14,70 @@
 #include <asm/spr_defs.h>
 #include <asm/cache.h>
 #include <asm/cacheflush.h>
+#include <asm/cpuinfo.h>
 #include <asm/tlbflush.h>
 
-static __always_inline void cache_loop(struct page *page, const unsigned int reg)
+/*
+ * Check if the cache component exists.
+ */
+bool cpu_cache_is_present(const unsigned int cache_type)
 {
-	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
-	unsigned long line = paddr & ~(L1_CACHE_BYTES - 1);
+	unsigned long upr = mfspr(SPR_UPR);
+	unsigned long mask = SPR_UPR_UP | cache_type;
+
+	return !((upr & mask) ^ mask);
+}
+
+static __always_inline void cache_loop(unsigned long paddr, unsigned long end,
+				       const unsigned short reg, const unsigned int cache_type)
+{
+	if (!cpu_cache_is_present(cache_type))
+		return;
 
-	while (line < paddr + PAGE_SIZE) {
-		mtspr(reg, line);
-		line += L1_CACHE_BYTES;
+	while (paddr < end) {
+		mtspr(reg, paddr);
+		paddr += L1_CACHE_BYTES;
 	}
 }
 
+static __always_inline void cache_loop_page(struct page *page, const unsigned short reg,
+					    const unsigned int cache_type)
+{
+	unsigned long paddr = page_to_pfn(page) << PAGE_SHIFT;
+	unsigned long end = paddr + PAGE_SIZE;
+
+	paddr &= ~(L1_CACHE_BYTES - 1);
+
+	cache_loop(paddr, end, reg, cache_type);
+}
+
 void local_dcache_page_flush(struct page *page)
 {
-	cache_loop(page, SPR_DCBFR);
+	cache_loop_page(page, SPR_DCBFR, SPR_UPR_DCP);
 }
 EXPORT_SYMBOL(local_dcache_page_flush);
 
 void local_icache_page_inv(struct page *page)
 {
-	cache_loop(page, SPR_ICBIR);
+	cache_loop_page(page, SPR_ICBIR, SPR_UPR_ICP);
 }
 EXPORT_SYMBOL(local_icache_page_inv);
 
+void local_dcache_range_flush(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBFR, SPR_UPR_DCP);
+}
+
+void local_dcache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_DCBIR, SPR_UPR_DCP);
+}
+
+void local_icache_range_inv(unsigned long start, unsigned long end)
+{
+	cache_loop(start, end, SPR_ICBIR, SPR_UPR_ICP);
+}
+
 void update_cache(struct vm_area_struct *vma, unsigned long address,
 	pte_t *pte)
 {
@@ -58,4 +97,3 @@ void update_cache(struct vm_area_struct *vma, unsigned long address,
 			sync_icache_dcache(folio_page(folio, nr));
 	}
 }
-

arch/openrisc/mm/init.c

@@ -35,6 +35,7 @@
 #include <asm/fixmap.h>
 #include <asm/tlbflush.h>
 #include <asm/sections.h>
+#include <asm/cacheflush.h>
 
 int mem_init_done;
 
@@ -176,8 +177,8 @@ void __init paging_init(void)
 	barrier();
 
 	/* Invalidate instruction caches after code modification */
-	mtspr(SPR_ICBIR, 0x900);
-	mtspr(SPR_ICBIR, 0xa00);
+	local_icache_block_inv(0x900);
+	local_icache_block_inv(0xa00);
 
 	/* New TLB miss handlers and kernel page tables are in now place.
 	 * Make sure that page flags get updated for all pages in TLB by