1 files changed, 206 insertions, 78 deletions

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 9191a66b3bc5..ef7b1119b2e2 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -31,6 +31,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/memremap.h>
+#include <linux/dma-direct.h>
 
 #include <asm/pgalloc.h>
 #include <asm/prom.h>
@@ -48,6 +49,7 @@
 #include <asm/fixmap.h>
 #include <asm/swiotlb.h>
 #include <asm/rtas.h>
+#include <asm/kasan.h>
 
 #include <mm/mmu_decl.h>
 
@@ -104,6 +106,27 @@ int __weak remove_section_mapping(unsigned long start, unsigned long end)
 	return -ENODEV;
 }
 
+#define FLUSH_CHUNK_SIZE SZ_1G
+/**
+ * flush_dcache_range_chunked(): Write any modified data cache blocks out to
+ * memory and invalidate them, in chunks of up to FLUSH_CHUNK_SIZE
+ * Does not invalidate the corresponding instruction cache blocks.
+ *
+ * @start: the start address
+ * @stop: the stop address (exclusive)
+ * @chunk: the max size of the chunks
+ */
+static void flush_dcache_range_chunked(unsigned long start, unsigned long stop,
+				       unsigned long chunk)
+{
+	unsigned long i;
+
+	for (i = start; i < stop; i += chunk) {
+		flush_dcache_range(i, min(stop, i + chunk));
+		cond_resched();
+	}
+}
+
 int __ref arch_add_memory(int nid, u64 start, u64 size,
 			struct mhp_restrictions *restrictions)
 {
@@ -120,7 +143,6 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 			start, start + size, rc);
 		return -EFAULT;
 	}
-	flush_dcache_range(start, start + size);
 
 	return __add_pages(nid, start_pfn, nr_pages, restrictions);
 }
@@ -130,14 +152,14 @@ void __ref arch_remove_memory(int nid, u64 start, u64 size,
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
-	struct page *page = pfn_to_page(start_pfn) + vmem_altmap_offset(altmap);
 	int ret;
 
-	__remove_pages(page_zone(page), start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap);
 
 	/* Remove htab bolted mappings for this section of memory */
 	start = (unsigned long)__va(start);
-	flush_dcache_range(start, start + size);
+	flush_dcache_range_chunked(start, start + size, FLUSH_CHUNK_SIZE);
+
 	ret = remove_section_mapping(start, start + size);
 	WARN_ON_ONCE(ret);
 
@@ -201,10 +223,10 @@ static int __init mark_nonram_nosave(void)
  * everything else. GFP_DMA32 page allocations automatically fall back to
  * ZONE_DMA.
  *
- * By using 31-bit unconditionally, we can exploit ARCH_ZONE_DMA_BITS to
- * inform the generic DMA mapping code.  32-bit only devices (if not handled
- * by an IOMMU anyway) will take a first dip into ZONE_NORMAL and get
- * otherwise served by ZONE_DMA.
+ * By using 31-bit unconditionally, we can exploit zone_dma_bits to inform the
+ * generic DMA mapping code.  32-bit only devices (if not handled by an IOMMU
+ * anyway) will take a first dip into ZONE_NORMAL and get otherwise served by
+ * ZONE_DMA.
  */
 static unsigned long max_zone_pfns[MAX_NR_ZONES];
 
@@ -216,15 +238,13 @@ void __init paging_init(void)
 	unsigned long long total_ram = memblock_phys_mem_size();
 	phys_addr_t top_of_ram = memblock_end_of_DRAM();
 
-#ifdef CONFIG_PPC32
-	unsigned long v = __fix_to_virt(__end_of_fixed_addresses - 1);
-	unsigned long end = __fix_to_virt(FIX_HOLE);
+#ifdef CONFIG_HIGHMEM
+	unsigned long v = __fix_to_virt(FIX_KMAP_END);
+	unsigned long end = __fix_to_virt(FIX_KMAP_BEGIN);
 
 	for (; v < end; v += PAGE_SIZE)
 		map_kernel_page(v, 0, __pgprot(0)); /* XXX gross */
-#endif
 
-#ifdef CONFIG_HIGHMEM
 	map_kernel_page(PKMAP_BASE, 0, __pgprot(0));	/* XXX gross */
 	pkmap_page_table = virt_to_kpte(PKMAP_BASE);
 
@@ -237,9 +257,18 @@ void __init paging_init(void)
 	printk(KERN_DEBUG "Memory hole size: %ldMB\n",
 	       (long int)((top_of_ram - total_ram) >> 20));
 
+	/*
+	 * Allow 30-bit DMA for very limited Broadcom wifi chips on many
+	 * powerbooks.
+	 */
+	if (IS_ENABLED(CONFIG_PPC32))
+		zone_dma_bits = 30;
+	else
+		zone_dma_bits = 31;
+
 #ifdef CONFIG_ZONE_DMA
 	max_zone_pfns[ZONE_DMA]	= min(max_low_pfn,
-				      1UL << (ARCH_ZONE_DMA_BITS - PAGE_SHIFT));
+				      1UL << (zone_dma_bits - PAGE_SHIFT));
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
 #ifdef CONFIG_HIGHMEM
@@ -260,11 +289,22 @@ void __init mem_init(void)
 	BUILD_BUG_ON(MMU_PAGE_COUNT > 16);
 
 #ifdef CONFIG_SWIOTLB
+	/*
+	 * Some platforms (e.g. 85xx) limit DMA-able memory way below
+	 * 4G. We force memblock to bottom-up mode to ensure that the
+	 * memory allocated in swiotlb_init() is DMA-able.
+	 * As it's the last memblock allocation, no need to reset it
+	 * back to to-down.
+	 */
+	memblock_set_bottom_up(true);
 	swiotlb_init(0);
 #endif
 
 	high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 	set_max_mapnr(max_pfn);
+
+	kasan_late_init();
+
 	memblock_free_all();
 
 #ifdef CONFIG_HIGHMEM
@@ -302,12 +342,9 @@ void __init mem_init(void)
 	pr_info("  * 0x%08lx..0x%08lx  : highmem PTEs\n",
 		PKMAP_BASE, PKMAP_ADDR(LAST_PKMAP));
 #endif /* CONFIG_HIGHMEM */
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	pr_info("  * 0x%08lx..0x%08lx  : consistent mem\n",
-		IOREMAP_TOP, IOREMAP_TOP + CONFIG_CONSISTENT_SIZE);
-#endif /* CONFIG_NOT_COHERENT_CACHE */
-	pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
-		ioremap_bot, IOREMAP_TOP);
+	if (ioremap_bot != IOREMAP_TOP)
+		pr_info("  * 0x%08lx..0x%08lx  : early ioremap\n",
+			ioremap_bot, IOREMAP_TOP);
 	pr_info("  * 0x%08lx..0x%08lx  : vmalloc & ioremap\n",
 		VMALLOC_START, VMALLOC_END);
 #endif /* CONFIG_PPC32 */
@@ -321,6 +358,120 @@ 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
@@ -353,12 +504,46 @@ 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);
@@ -407,63 +592,6 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 EXPORT_SYMBOL(flush_icache_user_range);
 
 /*
- * This is called at the end of handling a user page fault, when the
- * fault has been handled by updating a PTE in the linux page tables.
- * We use it to preload an HPTE into the hash table corresponding to
- * the updated linux PTE.
- * 
- * This must always be called with the pte lock held.
- */
-void update_mmu_cache(struct vm_area_struct *vma, unsigned long address,
-		      pte_t *ptep)
-{
-#ifdef CONFIG_PPC_BOOK3S
-	/*
-	 * We don't need to worry about _PAGE_PRESENT here because we are
-	 * called with either mm->page_table_lock held or ptl lock held
-	 */
-	unsigned long trap;
-	bool is_exec;
-
-	if (radix_enabled()) {
-		prefetch((void *)address);
-		return;
-	}
-
-	/* We only want HPTEs for linux PTEs that have _PAGE_ACCESSED set */
-	if (!pte_young(*ptep) || address >= TASK_SIZE)
-		return;
-
-	/* We try to figure out if we are coming from an instruction
-	 * access fault and pass that down to __hash_page so we avoid
-	 * double-faulting on execution of fresh text. We have to test
-	 * for regs NULL since init will get here first thing at boot
-	 *
-	 * We also avoid filling the hash if not coming from a fault
-	 */
-
-	trap = current->thread.regs ? TRAP(current->thread.regs) : 0UL;
-	switch (trap) {
-	case 0x300:
-		is_exec = false;
-		break;
-	case 0x400:
-		is_exec = true;
-		break;
-	default:
-		return;
-	}
-
-	hash_preload(vma->vm_mm, address, is_exec, trap);
-#endif /* CONFIG_PPC_BOOK3S */
-#if (defined(CONFIG_PPC_BOOK3E_64) || defined(CONFIG_PPC_FSL_BOOK3E)) \
-	&& defined(CONFIG_HUGETLB_PAGE)
-	if (is_vm_hugetlb_page(vma))
-		book3e_hugetlb_preload(vma, address, *ptep);
-#endif
-}
-
-/*
  * System memory should not be in /proc/iomem but various tools expect it
  * (eg kdump).
  */