Merge branch 'for-next/zone-dma' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux into dma-mapping-for-next

Pull in a stable branch from the arm64 tree that adds the zone_dma_bits
variable to avoid creating hard to resolve conflicts with that addition.

6 files changed, 73 insertions, 40 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 57606307fe34..ed5706ebf551 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -265,6 +265,10 @@ config GENERIC_CSUM
 config GENERIC_CALIBRATE_DELAY
 	def_bool y
 
+config ZONE_DMA
+	bool "Support DMA zone" if EXPERT
+	default y
+
 config ZONE_DMA32
 	bool "Support DMA32 zone" if EXPERT
 	default y
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 45c00a54909c..d933589c48e8 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -20,6 +20,7 @@
 #include <linux/sort.h>
 #include <linux/of.h>
 #include <linux/of_fdt.h>
+#include <linux/dma-direct.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
@@ -41,6 +42,8 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
+#define ARM64_ZONE_DMA_BITS	30
+
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
@@ -56,7 +59,14 @@ EXPORT_SYMBOL(physvirt_offset);
 struct page *vmemmap __ro_after_init;
 EXPORT_SYMBOL(vmemmap);
 
+/*
+ * We create both ZONE_DMA and ZONE_DMA32. ZONE_DMA covers the first 1G of
+ * memory as some devices, namely the Raspberry Pi 4, have peripherals with
+ * this limited view of the memory. ZONE_DMA32 will cover the rest of the 32
+ * bit addressable memory area.
+ */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
+static phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -81,7 +91,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
+		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -169,15 +179,16 @@ static void __init reserve_elfcorehdr(void)
 {
 }
 #endif /* CONFIG_CRASH_DUMP */
+
 /*
- * Return the maximum physical address for ZONE_DMA32 (DMA_BIT_MASK(32)). It
- * currently assumes that for memory starting above 4G, 32-bit devices will
- * use a DMA offset.
+ * Return the maximum physical address for a zone with a given address size
+ * limit. It currently assumes that for memory starting above 4G, 32-bit
+ * devices will use a DMA offset.
  */
-static phys_addr_t __init max_zone_dma_phys(void)
+static phys_addr_t __init max_zone_phys(unsigned int zone_bits)
 {
-	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, 32);
-	return min(offset + (1ULL << 32), memblock_end_of_DRAM());
+	phys_addr_t offset = memblock_start_of_DRAM() & GENMASK_ULL(63, zone_bits);
+	return min(offset + (1ULL << zone_bits), memblock_end_of_DRAM());
 }
 
 #ifdef CONFIG_NUMA
@@ -186,8 +197,11 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 
+#ifdef CONFIG_ZONE_DMA
+	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
+#endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(max_zone_dma_phys());
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
 #endif
 	max_zone_pfns[ZONE_NORMAL] = max;
 
@@ -200,16 +214,21 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma = min;
+	unsigned long max_dma32 = min;
+	unsigned long __maybe_unused max_dma = min;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
-	/* 4GB maximum for 32-bit only capable devices */
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 	max_dma = PFN_DOWN(arm64_dma_phys_limit);
-	zone_size[ZONE_DMA32] = max_dma - min;
+	zone_size[ZONE_DMA] = max_dma - min;
+	max_dma32 = max_dma;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+	max_dma32 = PFN_DOWN(arm64_dma32_phys_limit);
+	zone_size[ZONE_DMA32] = max_dma32 - max_dma;
 #endif
-	zone_size[ZONE_NORMAL] = max - max_dma;
+	zone_size[ZONE_NORMAL] = max - max_dma32;
 
 	memcpy(zhole_size, zone_size, sizeof(zhole_size));
 
@@ -219,16 +238,22 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 
 		if (start >= max)
 			continue;
-
-#ifdef CONFIG_ZONE_DMA32
+#ifdef CONFIG_ZONE_DMA
 		if (start < max_dma) {
-			unsigned long dma_end = min(end, max_dma);
-			zhole_size[ZONE_DMA32] -= dma_end - start;
+			unsigned long dma_end = min_not_zero(end, max_dma);
+			zhole_size[ZONE_DMA] -= dma_end - start;
 		}
 #endif
-		if (end > max_dma) {
+#ifdef CONFIG_ZONE_DMA32
+		if (start < max_dma32) {
+			unsigned long dma32_end = min(end, max_dma32);
+			unsigned long dma32_start = max(start, max_dma);
+			zhole_size[ZONE_DMA32] -= dma32_end - dma32_start;
+		}
+#endif
+		if (end > max_dma32) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma);
+			unsigned long normal_start = max(start, max_dma32);
 			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
 		}
 	}
@@ -418,11 +443,15 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	/* 4GB maximum for 32-bit only capable devices */
+	if (IS_ENABLED(CONFIG_ZONE_DMA)) {
+		zone_dma_bits = ARM64_ZONE_DMA_BITS;
+		arm64_dma_phys_limit = max_zone_phys(ARM64_ZONE_DMA_BITS);
+	}
+
 	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma_phys_limit = max_zone_dma_phys();
+		arm64_dma32_phys_limit = max_zone_phys(32);
 	else
-		arm64_dma_phys_limit = PHYS_MASK + 1;
+		arm64_dma32_phys_limit = PHYS_MASK + 1;
 
 	reserve_crashkernel();
 
@@ -430,7 +459,7 @@ void __init arm64_memblock_init(void)
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 
-	dma_contiguous_reserve(arm64_dma_phys_limit);
+	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -534,7 +563,7 @@ static void __init free_unused_memmap(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > (arm64_dma_phys_limit >> PAGE_SHIFT))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index c8bb14ff4713..f6c562acc3f8 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -329,13 +329,4 @@ struct vm_area_struct;
 #endif /* __ASSEMBLY__ */
 #include <asm/slice.h>
 
-/*
- * Allow 30-bit DMA for very limited Broadcom wifi chips on many powerbooks.
- */
-#ifdef CONFIG_PPC32
-#define ARCH_ZONE_DMA_BITS 30
-#else
-#define ARCH_ZONE_DMA_BITS 31
-#endif
-
 #endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index be941d382c8d..c95b7fe9f298 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>
@@ -201,10 +202,10 @@ 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];
 
@@ -237,9 +238,18 @@ 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
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index 823578c6b9e2..a4d38092530a 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -177,8 +177,6 @@ static inline int devmem_is_allowed(unsigned long pfn)
 #define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | \
 				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define ARCH_ZONE_DMA_BITS	31
-
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
 
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index a124f19f7b3c..f0ce22220565 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -118,6 +118,7 @@ void __init paging_init(void)
 
 	sparse_memory_present_with_active_regions(MAX_NUMNODES);
 	sparse_init();
+	zone_dma_bits = 31;
 	memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(MAX_DMA_ADDRESS);
 	max_zone_pfns[ZONE_NORMAL] = max_low_pfn;