[PATCH v2 1/3] arm64: kdump: support reserving crashkernel above 4G

[Chen Zhou]

When crashkernel is reserved above 4G in memory, kernel should
reserve some amount of low memory for swiotlb and some DMA buffers.

Kernel would try to allocate at least 256M below 4G automatically
as x86_64 if crashkernel is above 4G. Meanwhile, support
crashkernel=X,[high,low] in arm64.

Signed-off-by: Chen Zhou <chenzhou10@xxxxxxxxxx>
---
 arch/arm64/include/asm/kexec.h |  3 ++
 arch/arm64/kernel/setup.c      |  3 ++
 arch/arm64/mm/init.c           | 26 +++++++++++++----
 arch/x86/include/asm/kexec.h   |  3 ++
 arch/x86/kernel/setup.c        | 66 +++++-------------------------------------
 include/linux/kexec.h          |  1 +
 kernel/kexec_core.c            | 53 +++++++++++++++++++++++++++++++++
 7 files changed, 91 insertions(+), 64 deletions(-)

diff --git a/arch/arm64/include/asm/kexec.h b/arch/arm64/include/asm/kexec.h
index 67e4cb7..32949bf 100644
--- a/arch/arm64/include/asm/kexec.h
+++ b/arch/arm64/include/asm/kexec.h
@@ -28,6 +28,9 @@
 
 #define KEXEC_ARCH KEXEC_ARCH_AARCH64
 
+/* 2M alignment for crash kernel regions */
+#define CRASH_ALIGN	SZ_2M
+
 #ifndef __ASSEMBLY__
 
 /**
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 413d566..82cd9a0 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -243,6 +243,9 @@ static void __init request_standard_resources(void)
 			request_resource(res, &kernel_data);
 #ifdef CONFIG_KEXEC_CORE
 		/* Userspace will find "Crash kernel" region in /proc/iomem. */
+		if (crashk_low_res.end && crashk_low_res.start >= res->start &&
+		    crashk_low_res.end <= res->end)
+			request_resource(res, &crashk_low_res);
 		if (crashk_res.end && crashk_res.start >= res->start &&
 		    crashk_res.end <= res->end)
 			request_resource(res, &crashk_res);
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 972bf43..3bebddf 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -64,6 +64,7 @@ EXPORT_SYMBOL(memstart_addr);
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -74,20 +75,30 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init;
 static void __init reserve_crashkernel(void)
 {
 	unsigned long long crash_base, crash_size;
+	bool high = false;
 	int ret;
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
 	/* no crashkernel= or invalid value specified */
-	if (ret || !crash_size)
-		return;
+	if (ret || !crash_size) {
+		/* crashkernel=X,high */
+		ret = parse_crashkernel_high(boot_command_line,
+				memblock_phys_mem_size(),
+				&crash_size, &crash_base);
+		if (ret || !crash_size)
+			return;
+		high = true;
+	}
 
 	crash_size = PAGE_ALIGN(crash_size);
 
 	if (crash_base == 0) {
 		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(0, ARCH_LOW_ADDRESS_LIMIT,
-				crash_size, SZ_2M);
+		crash_base = memblock_find_in_range(0,
+				high ? memblock_end_of_DRAM()
+				: ARCH_LOW_ADDRESS_LIMIT,
+				crash_size, CRASH_ALIGN);
 		if (crash_base == 0) {
 			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
 				crash_size);
@@ -105,13 +116,18 @@ static void __init reserve_crashkernel(void)
 			return;
 		}
 
-		if (!IS_ALIGNED(crash_base, SZ_2M)) {
+		if (!IS_ALIGNED(crash_base, CRASH_ALIGN)) {
 			pr_warn("cannot reserve crashkernel: base address is not 2MB aligned\n");
 			return;
 		}
 	}
 	memblock_reserve(crash_base, crash_size);
 
+	if (crash_base >= SZ_4G && reserve_crashkernel_low()) {
+		memblock_free(crash_base, crash_size);
+		return;
+	}
+
 	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
 		crash_base, crash_base + crash_size, crash_size >> 20);
 
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 003f2da..485a514 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -18,6 +18,9 @@
 
 # define KEXEC_CONTROL_CODE_MAX_SIZE	2048
 
+/* 16M alignment for crash kernel regions */
+#define CRASH_ALIGN		(16 << 20)
+
 #ifndef __ASSEMBLY__
 
 #include <linux/string.h>
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3773905..4182035 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -447,9 +447,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 
 #ifdef CONFIG_KEXEC_CORE
 
-/* 16M alignment for crash kernel regions */
-#define CRASH_ALIGN		(16 << 20)
-
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
@@ -463,59 +460,6 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 # define CRASH_ADDR_HIGH_MAX	MAXMEM
 #endif
 
-static int __init reserve_crashkernel_low(void)
-{
-#ifdef CONFIG_X86_64
-	unsigned long long base, low_base = 0, low_size = 0;
-	unsigned long total_low_mem;
-	int ret;
-
-	total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT));
-
-	/* crashkernel=Y,low */
-	ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base);
-	if (ret) {
-		/*
-		 * two parts from lib/swiotlb.c:
-		 * -swiotlb size: user-specified with swiotlb= or default.
-		 *
-		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
-		 * to 8M for other buffers that may need to stay low too. Also
-		 * make sure we allocate enough extra low memory so that we
-		 * don't run out of DMA buffers for 32-bit devices.
-		 */
-		low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
-	} else {
-		/* passed with crashkernel=0,low ? */
-		if (!low_size)
-			return 0;
-	}
-
-	low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN);
-	if (!low_base) {
-		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
-		       (unsigned long)(low_size >> 20));
-		return -ENOMEM;
-	}
-
-	ret = memblock_reserve(low_base, low_size);
-	if (ret) {
-		pr_err("%s: Error reserving crashkernel low memblock.\n", __func__);
-		return ret;
-	}
-
-	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
-		(unsigned long)(low_size >> 20),
-		(unsigned long)(low_base >> 20),
-		(unsigned long)(total_low_mem >> 20));
-
-	crashk_low_res.start = low_base;
-	crashk_low_res.end   = low_base + low_size - 1;
-	insert_resource(&iomem_resource, &crashk_low_res);
-#endif
-	return 0;
-}
-
 static void __init reserve_crashkernel(void)
 {
 	unsigned long long crash_size, crash_base, total_mem;
@@ -573,9 +517,13 @@ static void __init reserve_crashkernel(void)
 		return;
 	}
 
-	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
-		memblock_free(crash_base, crash_size);
-		return;
+	if (crash_base >= (1ULL << 32)) {
+		if (reserve_crashkernel_low()) {
+			memblock_free(crash_base, crash_size);
+			return;
+		}
+
+		insert_resource(&iomem_resource, &crashk_low_res);
 	}
 
 	pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index b9b1bc5..6140cf8 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -281,6 +281,7 @@ extern void __crash_kexec(struct pt_regs *);
 extern void crash_kexec(struct pt_regs *);
 int kexec_should_crash(struct task_struct *);
 int kexec_crash_loaded(void);
+int __init reserve_crashkernel_low(void);
 void crash_save_cpu(struct pt_regs *regs, int cpu);
 extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
 
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index d714044..f8e8f80 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -39,6 +39,8 @@
 #include <linux/compiler.h>
 #include <linux/hugetlb.h>
 #include <linux/frame.h>
+#include <linux/memblock.h>
+#include <linux/swiotlb.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -96,6 +98,57 @@ int kexec_crash_loaded(void)
 }
 EXPORT_SYMBOL_GPL(kexec_crash_loaded);
 
+int __init reserve_crashkernel_low(void)
+{
+	unsigned long long base, low_base = 0, low_size = 0;
+	unsigned long total_low_mem;
+	int ret;
+
+	total_low_mem = memblock_mem_size(1UL << (32 - PAGE_SHIFT));
+
+	/* crashkernel=Y,low */
+	ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base);
+	if (ret) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 * -swiotlb size: user-specified with swiotlb= or default.
+		 *
+		 * -swiotlb overflow buffer: now hardcoded to 32k. We round it
+		 * to 8M for other buffers that may need to stay low too. Also
+		 * make sure we allocate enough extra low memory so that we
+		 * don't run out of DMA buffers for 32-bit devices.
+		 */
+		low_size = max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
+	} else {
+		/* passed with crashkernel=0,low ? */
+		if (!low_size)
+			return 0;
+	}
+
+	low_base = memblock_find_in_range(0, 1ULL << 32, low_size, CRASH_ALIGN);
+	if (!low_base) {
+		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
+		       (unsigned long)(low_size >> 20));
+		return -ENOMEM;
+	}
+
+	ret = memblock_reserve(low_base, low_size);
+	if (ret) {
+		pr_err("%s: Error reserving crashkernel low memblock.\n", __func__);
+		return ret;
+	}
+
+	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (System low RAM: %ldMB)\n",
+		(unsigned long)(low_size >> 20),
+		(unsigned long)(low_base >> 20),
+		(unsigned long)(total_low_mem >> 20));
+
+	crashk_low_res.start = low_base;
+	crashk_low_res.end   = low_base + low_size - 1;
+
+	return 0;
+}
+
 /*
  * When kexec transitions to the new kernel there is a one-to-one
  * mapping between physical and virtual addresses.  On processors
-- 
2.7.4