arm64: Add memmap parameter and register pmem

hulk inclusion
category: feature
bugzilla: 48159
CVE: NA

------------------------------

Register pmem in arm64:
Use memmap(memmap=nn[KMG]!ss[KMG]) reserve memory and
e820(driver/nvdimm/e820.c) function to register persistent
memory in arm64. when the kernel restart or update, the data
in PMEM will not be lost and can be loaded faster. this is a
general features.

driver/nvdimm/e820.c:
The function of this file is scan "iomem_resource" and take
advantage of nvdimm resource discovery mechanism by registering
a resource named "Persistent Memory (legacy)", this function
doesn't depend on architecture.

We will push the feature to linux kernel community and discuss to
modify the file name. because people have a mistaken notion that
the e820.c is depend on x86.

If you want use this features, you need do as follows:
1.Reserve memory: add memmap to reserve memory in grub.cfg
  memmap=nn[KMG]!ss[KMG] exp:memmap=100K!0x1a0000000.
2.Insmod nd_e820.ko: modprobe nd_e820.
3.Check pmem device in /dev exp: /dev/pmem0
Signed-off-by: NZhuLing <zhuling8@huawei.com>
Signed-off-by: NSang Yan <sangyan@huawei.com>
Reviewed-by: NChen Wandun <chenwandun@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/arm64/Kconfig

@@ -1302,6 +1302,27 @@ config RODATA_FULL_DEFAULT_ENABLED
 	  This requires the linear region to be mapped down to pages,
 	  which may adversely affect performance in some cases.
 
+config ARM64_PMEM_RESERVE
+	bool "Reserve memory for persistent storage"
+	default n
+	help
+	  Use memmap=nn[KMG]!ss[KMG](memmap=100K!0x1a0000000) reserve
+	  memory for persistent storage.
+
+	  Say y here to enable this feature.
+
+config ARM64_PMEM_LEGACY_DEVICE
+	bool "Create persistent storage"
+	depends on BLK_DEV
+	depends on LIBNVDIMM
+	select ARM64_PMEM_RESERVE
+	help
+	  Use reserved memory for persistent storage when the kernel
+	  restart or update. the data in PMEM will not be lost and
+	  can be loaded faster.
+
+	  Say y if unsure.
+
 config ARM64_SW_TTBR0_PAN
 	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
 	help

arch/arm64/kernel/Makefile

@@ -68,6 +68,7 @@ obj-$(CONFIG_ARM64_PTR_AUTH)		+= pointer_auth.o
 obj-$(CONFIG_SHADOW_CALL_STACK)		+= scs.o
 obj-$(CONFIG_ARM64_MTE)			+= mte.o
 obj-$(CONFIG_MPAM)			+= mpam/
+obj-$(CONFIG_ARM64_PMEM_LEGACY_DEVICE)   += pmem.o
 
 obj-y					+= vdso/ probes/
 obj-$(CONFIG_COMPAT_VDSO)		+= vdso32/

arch/arm64/kernel/pmem.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright(c) 2021 Huawei Technologies Co., Ltd
+ *
+ * Derived from x86 and arm64 implement PMEM.
+ */
+#include <linux/platform_device.h>
+#include <linux/init.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+
+static int found(struct resource *res, void *data)
+{
+	return 1;
+}
+
+static int __init register_e820_pmem(void)
+{
+	struct platform_device *pdev;
+	int rc;
+
+	rc = walk_iomem_res_desc(IORES_DESC_PERSISTENT_MEMORY_LEGACY,
+				 IORESOURCE_MEM, 0, -1, NULL, found);
+	if (rc <= 0)
+		return 0;
+
+	/*
+	 * See drivers/nvdimm/e820.c for the implementation, this is
+	 * simply here to trigger the module to load on demand.
+	 */
+	pdev = platform_device_alloc("e820_pmem", -1);
+
+	return platform_device_add(pdev);
+}
+device_initcall(register_e820_pmem);

arch/arm64/kernel/setup.c

@@ -67,6 +67,10 @@ static int __init arm64_enable_cpu0_hotplug(char *str)
 __setup("arm64_cpu0_hotplug", arm64_enable_cpu0_hotplug);
 #endif
 
+#ifdef CONFIG_ARM64_PMEM_RESERVE
+extern struct resource pmem_res;
+#endif
+
 phys_addr_t __fdt_pointer __initdata;
 
 /*
@@ -274,6 +278,12 @@ static void __init request_standard_resources(void)
 			request_resource(res, &quick_kexec_res);
 #endif
 	}
+
+#ifdef CONFIG_ARM64_PMEM_RESERVE
+	if (pmem_res.end && pmem_res.start)
+		request_resource(&iomem_resource, &pmem_res);
+#endif
+
 }
 
 static int __init reserve_memblock_reserved_regions(void)

arch/arm64/mm/init.c

@@ -52,6 +52,7 @@
  */
 s64 memstart_addr __ro_after_init = -1;
 EXPORT_SYMBOL(memstart_addr);
+phys_addr_t start_at, mem_size;
 
 /*
  * If the corresponding config options are enabled, we create both ZONE_DMA
@@ -62,6 +63,18 @@ EXPORT_SYMBOL(memstart_addr);
  */
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
+static unsigned long long pmem_size, pmem_start;
+
+#ifdef CONFIG_ARM64_PMEM_RESERVE
+struct resource pmem_res = {
+	.name = "Persistent Memory (legacy)",
+	.start = 0,
+	.end = 0,
+	.flags = IORESOURCE_MEM,
+	.desc = IORES_DESC_PERSISTENT_MEMORY_LEGACY
+};
+#endif
+
 #ifndef CONFIG_KEXEC_CORE
 static void __init reserve_crashkernel(void)
 {
@@ -348,6 +361,83 @@ static int __init reserve_park_mem(void)
 }
 #endif
 
+static bool __init is_mem_valid(unsigned long long mem_size, unsigned long long mem_start)
+{
+	if (!memblock_is_region_memory(mem_start, mem_size)) {
+		pr_warn("cannot reserve mem: region is not memory!\n");
+		return false;
+	}
+
+	if (memblock_is_region_reserved(mem_start, mem_size)) {
+		pr_warn("cannot reserve mem: region overlaps reserved memory!\n");
+		return false;
+	}
+
+	if (!IS_ALIGNED(mem_start, SZ_2M)) {
+		pr_warn("cannot reserve mem: base address is not 2MB aligned!\n");
+		return false;
+	}
+
+	return true;
+}
+
+static int __init parse_memmap_one(char *p)
+{
+	char *oldp;
+
+	if (!p)
+		return -EINVAL;
+
+	oldp = p;
+	mem_size = memparse(p, &p);
+	if (p == oldp)
+		return -EINVAL;
+
+	if (!mem_size)
+		return -EINVAL;
+
+	mem_size = PAGE_ALIGN(mem_size);
+
+	if (*p == '!') {
+		start_at = memparse(p+1, &p);
+
+		pmem_start = start_at;
+		pmem_size = mem_size;
+	} else
+		pr_info("Unrecognized memmap option, please check the parameter.\n");
+
+	return *p == '\0' ? 0 : -EINVAL;
+}
+
+static int __init parse_memmap_opt(char *str)
+{
+	while (str) {
+		char *k = strchr(str, ',');
+
+		if (k)
+			*k++ = 0;
+		parse_memmap_one(str);
+		str = k;
+	}
+
+	return 0;
+}
+early_param("memmap", parse_memmap_opt);
+
+#ifdef CONFIG_ARM64_PMEM_RESERVE
+static void __init reserve_pmem(void)
+{
+	if (!is_mem_valid(mem_size, start_at))
+		return;
+
+	memblock_remove(pmem_start, pmem_size);
+	pr_info("pmem reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		pmem_start, pmem_start + pmem_size, pmem_size >> 20);
+	pmem_res.start = pmem_start;
+	pmem_res.end = pmem_start + pmem_size - 1;
+}
+#endif
+
 void __init arm64_memblock_init(void)
 {
 	const s64 linear_region_size = BIT(vabits_actual - 1);
@@ -521,6 +611,11 @@ void __init bootmem_init(void)
 #ifdef CONFIG_QUICK_KEXEC
 	reserve_quick_kexec();
 #endif
+
+#ifdef CONFIG_ARM64_PMEM_RESERVE
+	reserve_pmem();
+#endif
+
 	memblock_dump_all();
 }
 

drivers/nvdimm/Kconfig

@@ -132,3 +132,8 @@ config NVDIMM_TEST_BUILD
 	  infrastructure.
 
 endif
+
+config PMEM_LEGACY
+	tristate "Pmem_legacy"
+	select X86_PMEM_LEGACY if X86
+	select ARM64_PMEM_LEGACY_DEVICE if ARM64

drivers/nvdimm/Makefile

@@ -3,7 +3,7 @@ obj-$(CONFIG_LIBNVDIMM) += libnvdimm.o
 obj-$(CONFIG_BLK_DEV_PMEM) += nd_pmem.o
 obj-$(CONFIG_ND_BTT) += nd_btt.o
 obj-$(CONFIG_ND_BLK) += nd_blk.o
-obj-$(CONFIG_X86_PMEM_LEGACY) += nd_e820.o
+obj-$(CONFIG_PMEM_LEGACY) += nd_e820.o
 obj-$(CONFIG_OF_PMEM) += of_pmem.o
 obj-$(CONFIG_VIRTIO_PMEM) += virtio_pmem.o nd_virtio.o