5 files changed, 108 insertions, 6 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 48a386094fa3..1ea9f26d1b70 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -146,7 +146,7 @@ ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 
 /*
- *	__flush_kern_dcache_page(kaddr)
+ *	__flush_dcache_area(kaddr, size)
  *
  *	Ensure that the data held in the page kaddr is written back to the
  *	page in question.
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 4bd7579ec9e6..45b5ab54c9ee 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -21,6 +21,7 @@
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
+#include <linux/dma-contiguous.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
 
@@ -33,17 +34,47 @@ static void *arm64_swiotlb_alloc_coherent(struct device *dev, size_t size,
 					  dma_addr_t *dma_handle, gfp_t flags,
 					  struct dma_attrs *attrs)
 {
+	if (dev == NULL) {
+		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+		return NULL;
+	}
+
 	if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA32;
-	return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		struct page *page;
+
+		page = dma_alloc_from_contiguous(dev, size >> PAGE_SHIFT,
+							get_order(size));
+		if (!page)
+			return NULL;
+
+		*dma_handle = phys_to_dma(dev, page_to_phys(page));
+		return page_address(page);
+	} else {
+		return swiotlb_alloc_coherent(dev, size, dma_handle, flags);
+	}
 }
 
 static void arm64_swiotlb_free_coherent(struct device *dev, size_t size,
 					void *vaddr, dma_addr_t dma_handle,
 					struct dma_attrs *attrs)
 {
-	swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	if (dev == NULL) {
+		WARN_ONCE(1, "Use an actual device structure for DMA allocation\n");
+		return;
+	}
+
+	if (IS_ENABLED(CONFIG_DMA_CMA)) {
+		phys_addr_t paddr = dma_to_phys(dev, dma_handle);
+
+		dma_release_from_contiguous(dev,
+					phys_to_page(paddr),
+					size >> PAGE_SHIFT);
+	} else {
+		swiotlb_free_coherent(dev, size, vaddr, dma_handle);
+	}
 }
 
 static struct dma_map_ops arm64_swiotlb_dma_ops = {
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 0cb8742de4f2..d0b4c2efda90 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -30,6 +30,7 @@
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-contiguous.h>
 
 #include <asm/sections.h>
 #include <asm/setup.h>
@@ -159,6 +160,8 @@ void __init arm64_memblock_init(void)
 		memblock_reserve(base, size);
 	}
 
+	dma_contiguous_reserve(0);
+
 	memblock_allow_resize();
 	memblock_dump_all();
 }
diff --git a/arch/arm64/mm/proc-macros.S b/arch/arm64/mm/proc-macros.S
index 8957b822010b..005d29e2977d 100644
--- a/arch/arm64/mm/proc-macros.S
+++ b/arch/arm64/mm/proc-macros.S
@@ -38,8 +38,7 @@
  */
 	.macro	dcache_line_size, reg, tmp
 	mrs	\tmp, ctr_el0			// read CTR
-	lsr	\tmp, \tmp, #16
-	and	\tmp, \tmp, #0xf		// cache line size encoding
+	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
 	mov	\reg, #4			// bytes per word
 	lsl	\reg, \reg, \tmp		// actual cache line size
 	.endm
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 0f7fec52c7f8..1333e6f9a8e5 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -80,8 +80,77 @@ ENTRY(cpu_do_idle)
 	ret
 ENDPROC(cpu_do_idle)
 
+#ifdef CONFIG_ARM64_CPU_SUSPEND
+/**
+ * cpu_do_suspend - save CPU registers context
+ *
+ * x0: virtual address of context pointer
+ */
+ENTRY(cpu_do_suspend)
+	mrs	x2, tpidr_el0
+	mrs	x3, tpidrro_el0
+	mrs	x4, contextidr_el1
+	mrs	x5, mair_el1
+	mrs	x6, cpacr_el1
+	mrs	x7, ttbr1_el1
+	mrs	x8, tcr_el1
+	mrs	x9, vbar_el1
+	mrs	x10, mdscr_el1
+	mrs	x11, oslsr_el1
+	mrs	x12, sctlr_el1
+	stp	x2, x3, [x0]
+	stp	x4, x5, [x0, #16]
+	stp	x6, x7, [x0, #32]
+	stp	x8, x9, [x0, #48]
+	stp	x10, x11, [x0, #64]
+	str	x12, [x0, #80]
+	ret
+ENDPROC(cpu_do_suspend)
+
+/**
+ * cpu_do_resume - restore CPU register context
+ *
+ * x0: Physical address of context pointer
+ * x1: ttbr0_el1 to be restored
+ *
+ * Returns:
+ *	sctlr_el1 value in x0
+ */
+ENTRY(cpu_do_resume)
+	/*
+	 * Invalidate local tlb entries before turning on MMU
+	 */
+	tlbi	vmalle1
+	ldp	x2, x3, [x0]
+	ldp	x4, x5, [x0, #16]
+	ldp	x6, x7, [x0, #32]
+	ldp	x8, x9, [x0, #48]
+	ldp	x10, x11, [x0, #64]
+	ldr	x12, [x0, #80]
+	msr	tpidr_el0, x2
+	msr	tpidrro_el0, x3
+	msr	contextidr_el1, x4
+	msr	mair_el1, x5
+	msr	cpacr_el1, x6
+	msr	ttbr0_el1, x1
+	msr	ttbr1_el1, x7
+	msr	tcr_el1, x8
+	msr	vbar_el1, x9
+	msr	mdscr_el1, x10
+	/*
+	 * Restore oslsr_el1 by writing oslar_el1
+	 */
+	ubfx	x11, x11, #1, #1
+	msr	oslar_el1, x11
+	mov	x0, x12
+	dsb	nsh		// Make sure local tlb invalidation completed
+	isb
+	ret
+ENDPROC(cpu_do_resume)
+#endif
+
 /*
- *	cpu_switch_mm(pgd_phys, tsk)
+ *	cpu_do_switch_mm(pgd_phys, tsk)
  *
  *	Set the translation table base pointer to be pgd_phys.
  *