powerpc: Convert flush_icache_range & friends to C

Similar to commit 22e9c88d486a
("powerpc/64: reuse PPC32 static inline flush_dcache_range()")
this patch converts the following ASM symbols to C:
    flush_icache_range()
    __flush_dcache_icache()
    __flush_dcache_icache_phys()

This was done as we discovered a long-standing bug where the length of the
range was truncated due to using a 32 bit shift instead of a 64 bit one.

By converting these functions to C, it becomes easier to maintain.

flush_dcache_icache_phys() retains a critical assembler section as we must
ensure there are no memory accesses while the data MMU is disabled
(authored by Christophe Leroy). Since this has no external callers, it has
also been made static, allowing the compiler to inline it within
flush_dcache_icache_page().

Signed-off-by: Alastair D'Silva <alastair@d-silva.org>
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
[mpe: Minor fixups, don't export __flush_dcache_icache()]
Link: https://lore.kernel.org/r/20191104023305.9581-5-alastair@au1.ibm.com

1 files changed, 149 insertions, 1 deletions

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index be941d382c8d1..3392cacabe606 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -318,6 +318,120 @@ void free_initmem(void)
 	free_initmem_default(POISON_FREE_INITMEM);
 }
 
+/**
+ * flush_coherent_icache() - if a CPU has a coherent icache, flush it
+ * @addr: The base address to use (can be any valid address, the whole cache will be flushed)
+ * Return true if the cache was flushed, false otherwise
+ */
+static inline bool flush_coherent_icache(unsigned long addr)
+{
+	/*
+	 * For a snooping icache, we still need a dummy icbi to purge all the
+	 * prefetched instructions from the ifetch buffers. We also need a sync
+	 * before the icbi to order the the actual stores to memory that might
+	 * have modified instructions with the icbi.
+	 */
+	if (cpu_has_feature(CPU_FTR_COHERENT_ICACHE)) {
+		mb(); /* sync */
+		icbi((void *)addr);
+		mb(); /* sync */
+		isync();
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * invalidate_icache_range() - Flush the icache by issuing icbi across an address range
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ */
+static void invalidate_icache_range(unsigned long start, unsigned long stop)
+{
+	unsigned long shift = l1_icache_shift();
+	unsigned long bytes = l1_icache_bytes();
+	char *addr = (char *)(start & ~(bytes - 1));
+	unsigned long size = stop - (unsigned long)addr + (bytes - 1);
+	unsigned long i;
+
+	for (i = 0; i < size >> shift; i++, addr += bytes)
+		icbi(addr);
+
+	mb(); /* sync */
+	isync();
+}
+
+/**
+ * flush_icache_range: Write any modified data cache blocks out to memory
+ * and invalidate the corresponding blocks in the instruction cache
+ *
+ * Generic code will call this after writing memory, before executing from it.
+ *
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ */
+void flush_icache_range(unsigned long start, unsigned long stop)
+{
+	if (flush_coherent_icache(start))
+		return;
+
+	clean_dcache_range(start, stop);
+
+	if (IS_ENABLED(CONFIG_44x)) {
+		/*
+		 * Flash invalidate on 44x because we are passed kmapped
+		 * addresses and this doesn't work for userspace pages due to
+		 * the virtually tagged icache.
+		 */
+		iccci((void *)start);
+		mb(); /* sync */
+		isync();
+	} else
+		invalidate_icache_range(start, stop);
+}
+EXPORT_SYMBOL(flush_icache_range);
+
+#if !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC64)
+/**
+ * flush_dcache_icache_phys() - Flush a page by it's physical address
+ * @physaddr: the physical address of the page
+ */
+static void flush_dcache_icache_phys(unsigned long physaddr)
+{
+	unsigned long bytes = l1_dcache_bytes();
+	unsigned long nb = PAGE_SIZE / bytes;
+	unsigned long addr = physaddr & PAGE_MASK;
+	unsigned long msr, msr0;
+	unsigned long loop1 = addr, loop2 = addr;
+
+	msr0 = mfmsr();
+	msr = msr0 & ~MSR_DR;
+	/*
+	 * This must remain as ASM to prevent potential memory accesses
+	 * while the data MMU is disabled
+	 */
+	asm volatile(
+		"   mtctr %2;\n"
+		"   mtmsr %3;\n"
+		"   isync;\n"
+		"0: dcbst   0, %0;\n"
+		"   addi    %0, %0, %4;\n"
+		"   bdnz    0b;\n"
+		"   sync;\n"
+		"   mtctr %2;\n"
+		"1: icbi    0, %1;\n"
+		"   addi    %1, %1, %4;\n"
+		"   bdnz    1b;\n"
+		"   sync;\n"
+		"   mtmsr %5;\n"
+		"   isync;\n"
+		: "+&r" (loop1), "+&r" (loop2)
+		: "r" (nb), "r" (msr), "i" (bytes), "r" (msr0)
+		: "ctr", "memory");
+}
+#endif // !defined(CONFIG_PPC_8xx) && !defined(CONFIG_PPC64)
+
 /*
  * This is called when a page has been modified by the kernel.
  * It just marks the page as not i-cache clean.  We do the i-cache
@@ -350,12 +464,46 @@ void flush_dcache_icache_page(struct page *page)
 		__flush_dcache_icache(start);
 		kunmap_atomic(start);
 	} else {
-		__flush_dcache_icache_phys(page_to_pfn(page) << PAGE_SHIFT);
+		unsigned long addr = page_to_pfn(page) << PAGE_SHIFT;
+
+		if (flush_coherent_icache(addr))
+			return;
+		flush_dcache_icache_phys(addr);
 	}
 #endif
 }
 EXPORT_SYMBOL(flush_dcache_icache_page);
 
+/**
+ * __flush_dcache_icache(): Flush a particular page from the data cache to RAM.
+ * Note: this is necessary because the instruction cache does *not*
+ * snoop from the data cache.
+ *
+ * @page: the address of the page to flush
+ */
+void __flush_dcache_icache(void *p)
+{
+	unsigned long addr = (unsigned long)p;
+
+	if (flush_coherent_icache(addr))
+		return;
+
+	clean_dcache_range(addr, addr + PAGE_SIZE);
+
+	/*
+	 * We don't flush the icache on 44x. Those have a virtual icache and we
+	 * don't have access to the virtual address here (it's not the page
+	 * vaddr but where it's mapped in user space). The flushing of the
+	 * icache on these is handled elsewhere, when a change in the address
+	 * space occurs, before returning to user space.
+	 */
+
+	if (cpu_has_feature(MMU_FTR_TYPE_44x))
+		return;
+
+	invalidate_icache_range(addr, addr + PAGE_SIZE);
+}
+
 void clear_user_page(void *page, unsigned long vaddr, struct page *pg)
 {
 	clear_page(page);