Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jianmin Lv <lvjianmin@loongson.cn>
To:     lpieralisi@kernel.org, robin.murphy@arm.com, chenhuacai@loongson.cn
Cc:     guohanjun@huawei.com, sudeep.holla@arm.com, rafael@kernel.org,
        lenb@kernel.org, robert.moore@intel.com,
        linux-kernel@vger.kernel.org, linux-acpi@vger.kernel.org,
        loongarch@lists.linux.dev
Subject: [PATCH V3 2/2] LoongArch: Remove ARCH_HAS_PHYS_TO_DMA
Date:   Tue, 30 Aug 2022 11:01:39 +0800
Message-Id: <20220830030139.29899-3-lvjianmin@loongson.cn>
In-Reply-To: <20220830030139.29899-1-lvjianmin@loongson.cn>
References: <20220830030139.29899-1-lvjianmin@loongson.cn>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Use _DMA defined in ACPI spec for translation between
DMA address and CPU address, and implement acpi_arch_dma_setup
for initializing dev->dma_range_map, where acpi_dma_get_range
is called for parsing _DMA.

e.g.
If we have two dma ranges:
cpu address      dma address    size         offset
0x200080000000   0x2080000000   0x400000000  0x1fe000000000
0x400080000000   0x4080000000   0x400000000  0x3fc000000000

_DMA for pci devices should be declared in host bridge as
flowing:

Name (_DMA, ResourceTemplate() {
        QWordMemory (ResourceProducer,
            PosDecode,
            MinFixed,
            MaxFixed,
            NonCacheable,
            ReadWrite,
            0x0,
            0x4080000000,
            0x447fffffff,
            0x3fc000000000,
            0x400000000,
            ,
            ,
            )

        QWordMemory (ResourceProducer,
            PosDecode,
            MinFixed,
            MaxFixed,
            NonCacheable,
            ReadWrite,
            0x0,
            0x2080000000,
            0x247fffffff,
            0x1fe000000000,
            0x400000000,
            ,
            ,
            )
    })

Signed-off-by: Jianmin Lv <lvjianmin@loongson.cn>
---
 arch/loongarch/Kconfig        |  1 -
 arch/loongarch/kernel/dma.c   | 52 +++++++++++++++++--------------------------
 arch/loongarch/kernel/setup.c |  2 +-
 include/linux/acpi.h          |  9 +++++---
 4 files changed, 28 insertions(+), 36 deletions(-)

diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index b57daee..9dedcf9 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -7,7 +7,6 @@ config LOONGARCH
 	select ARCH_ENABLE_MEMORY_HOTPLUG
 	select ARCH_ENABLE_MEMORY_HOTREMOVE
 	select ARCH_HAS_ACPI_TABLE_UPGRADE	if ACPI
-	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_INLINE_READ_LOCK if !PREEMPTION
diff --git a/arch/loongarch/kernel/dma.c b/arch/loongarch/kernel/dma.c
index 8c9b531..7a9c6a9 100644
--- a/arch/loongarch/kernel/dma.c
+++ b/arch/loongarch/kernel/dma.c
@@ -2,39 +2,29 @@
 /*
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
-#include <linux/init.h>
+#include <linux/acpi.h>
 #include <linux/dma-direct.h>
-#include <linux/dma-mapping.h>
-#include <linux/dma-map-ops.h>
-#include <linux/swiotlb.h>
 
-#include <asm/bootinfo.h>
-#include <asm/dma.h>
-#include <asm/loongson.h>
-
-/*
- * We extract 4bit node id (bit 44~47) from Loongson-3's
- * 48bit physical address space and embed it into 40bit.
- */
-
-static int node_id_offset;
-
-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	long nid = (paddr >> 44) & 0xf;
-
-	return ((nid << 44) ^ paddr) | (nid << node_id_offset);
-}
-
-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
+void acpi_arch_dma_setup(struct device *dev)
 {
-	long nid = (daddr >> node_id_offset) & 0xf;
+	int ret;
+	u64 mask, end = 0;
+	const struct bus_dma_region *map = NULL;
+
+	ret = acpi_dma_get_range(dev, &map);
+	if (!ret && map) {
+		const struct bus_dma_region *r = map;
+
+		for (end = 0; r->size; r++) {
+			if (r->dma_start + r->size - 1 > end)
+				end = r->dma_start + r->size - 1;
+		}
+
+		mask = DMA_BIT_MASK(ilog2(end) + 1);
+		dev->bus_dma_limit = end;
+		dev->dma_range_map = map;
+		dev->coherent_dma_mask = min(dev->coherent_dma_mask, mask);
+		*dev->dma_mask = min(*dev->dma_mask, mask);
+	}
 
-	return ((nid << node_id_offset) ^ daddr) | (nid << 44);
-}
-
-void __init plat_swiotlb_setup(void)
-{
-	swiotlb_init(true, SWIOTLB_VERBOSE);
-	node_id_offset = ((readl(LS7A_DMA_CFG) & LS7A_DMA_NODE_MASK) >> LS7A_DMA_NODE_SHF) + 36;
 }
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index c74860b..974f085 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -247,7 +247,7 @@ static void __init arch_mem_init(char **cmdline_p)
 	sparse_init();
 	memblock_set_bottom_up(true);
 
-	plat_swiotlb_setup();
+	swiotlb_init(true, SWIOTLB_VERBOSE);
 
 	dma_contiguous_reserve(PFN_PHYS(max_low_pfn));
 
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 34e0545..33977b87 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -278,14 +278,17 @@ int acpi_table_parse_madt(enum acpi_madt_type id,
 
 void acpi_numa_x2apic_affinity_init(struct acpi_srat_x2apic_cpu_affinity *pa);
 
+#if defined(CONFIG_ARM64) || defined(CONFIG_LOONGARCH)
+void acpi_arch_dma_setup(struct device *dev);
+#else
+static inline void acpi_arch_dma_setup(struct device *dev) { }
+#endif
+
 #ifdef CONFIG_ARM64
 void acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa);
-void acpi_arch_dma_setup(struct device *dev);
 #else
 static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
-static inline void
-acpi_arch_dma_setup(struct device *dev) { }
 #endif
 
 int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
-- 
1.8.3.1