[PATCH] arm64: Remove arm64_dma32_phys_limit and its uses

[Catalin Marinas]

With the introduction of a dynamic ZONE_DMA range based on DT or IORT
information, there's no need for CMA allocations from the wider
ZONE_DMA32 since on most platforms ZONE_DMA will cover the 32-bit
addressable range. Remove the arm64_dma32_phys_limit and set
arm64_dma_phys_limit to cover the smallest DMA range required on the
platform. CMA allocation and crashkernel reservation now goes in
the dynamically sized ZONE_DMA.

Signed-off-by: Catalin Marinas <catalin.marinas at arm.com>
Cc: Nicolas Saenz Julienne <nsaenzjulienne at suse.de>
Cc: Chen Zhou <chenzhou10 at huawei.com>
---

This patch goes on top of the ARCH_LOW_ADDRESS_LIMIT fix from Nicolas,
already in the arm64 for-next/fixes which fixes a 5.5 issue with
!CONFIG_ZONE_DMA. The changes here depend on the patches in 5.11-rc1.
While they look mostly like clean-ups, they still fix a potential issue
with !CONFIG_ZONE_DMA32 configurations where arm64_dma32_phys_limit
would be equal to PHYS_MASK but we still have a limited ZONE_DMA. In
addition, it now allows proper CMA and crashkernel reservations for
RPi4.

 arch/arm64/include/asm/processor.h |  3 +--
 arch/arm64/mm/init.c               | 33 ++++++++++++++++--------------
 2 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 69ad25fbeae4..ca2cd75d3286 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -94,8 +94,7 @@
 #endif /* CONFIG_ARM64_FORCE_52BIT */
 
 extern phys_addr_t arm64_dma_phys_limit;
-extern phys_addr_t arm64_dma32_phys_limit;
-#define ARCH_LOW_ADDRESS_LIMIT	((arm64_dma_phys_limit ? : arm64_dma32_phys_limit) - 1)
+#define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
 
 struct debug_info {
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7deddf56f7c3..709d98fea90c 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -53,13 +53,13 @@ s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
 
 /*
- * 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.
+ * If the corresponding config options are enabled, we create both ZONE_DMA
+ * and ZONE_DMA32. By default ZONE_DMA covers the 32-bit addressable memory
+ * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
+ * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
+ * otherwise it is empty.
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
-phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -84,7 +84,7 @@ static void __init reserve_crashkernel(void)
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, arm64_dma32_phys_limit,
+		crash_base = memblock_find_in_range(0, arm64_dma_phys_limit,
 				crash_size, SZ_2M);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
@@ -196,6 +196,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	unsigned long max_zone_pfns[MAX_NR_ZONES]  = {0};
 	unsigned int __maybe_unused acpi_zone_dma_bits;
 	unsigned int __maybe_unused dt_zone_dma_bits;
+	phys_addr_t __maybe_unused dma32_phys_limit = max_zone_phys(32);
 
 #ifdef CONFIG_ZONE_DMA
 	acpi_zone_dma_bits = fls64(acpi_iort_dma_get_max_cpu_address());
@@ -205,8 +206,12 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	max_zone_pfns[ZONE_DMA] = PFN_DOWN(arm64_dma_phys_limit);
 #endif
 #ifdef CONFIG_ZONE_DMA32
-	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(arm64_dma32_phys_limit);
+	max_zone_pfns[ZONE_DMA32] = PFN_DOWN(dma32_phys_limit);
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
+	if (!arm64_dma_phys_limit)
+		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -394,16 +399,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
-	if (IS_ENABLED(CONFIG_ZONE_DMA32))
-		arm64_dma32_phys_limit = max_zone_phys(32);
-	else
-		arm64_dma32_phys_limit = PHYS_MASK + 1;
-
 	reserve_elfcorehdr();
 
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
-
-	dma_contiguous_reserve(arm64_dma32_phys_limit);
 }
 
 void __init bootmem_init(void)
@@ -438,6 +436,11 @@ void __init bootmem_init(void)
 	sparse_init();
 	zone_sizes_init(min, max);
 
+	/*
+	 * Reserve the CMA area after arm64_dma_phys_limit was initialised.
+	 */
+	dma_contiguous_reserve(arm64_dma_phys_limit);
+
 	/*
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
@@ -455,7 +458,7 @@ void __init bootmem_init(void)
 void __init mem_init(void)
 {
 	if (swiotlb_force == SWIOTLB_FORCE ||
-	    max_pfn > PFN_DOWN(arm64_dma_phys_limit ? : arm64_dma32_phys_limit))
+	    max_pfn > PFN_DOWN(arm64_dma_phys_limit))
 		swiotlb_init(1);
 	else
 		swiotlb_force = SWIOTLB_NO_FORCE;