arm64: kdump: reimplement crashkernel=X

maillist inclusion
category: feature
bugzilla: 47954
Reference: https://lkml.org/lkml/2021/1/30/53

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

There are following issues in arm64 kdump:
1. We use crashkernel=X to reserve crashkernel below 4G, which
will fail when there is no enough low memory.
2. If reserving crashkernel above 4G, in this case, crash dump
kernel will boot failure because there is no low memory available
for allocation.
3. Since commit 1a8e1cef ("arm64: use both ZONE_DMA and ZONE_DMA32"),
if the memory reserved for crash dump kernel falled in ZONE_DMA32,
the devices in crash dump kernel need to use ZONE_DMA will alloc
fail.

To solve these issues, change the behavior of crashkernel=X and
introduce crashkernel=X,[high,low]. crashkernel=X tries low allocation
in DMA zone or DMA32 zone if CONFIG_ZONE_DMA is disabled, and fall back
to high allocation if it fails.
We can also use "crashkernel=X,high" to select a region above DMA zone,
which also tries to allocate at least 256M in DMA zone automatically
(or the DMA32 zone if CONFIG_ZONE_DMA is disabled).
"crashkernel=Y,low" can be used to allocate specified size low memory.

Another minor change, there may be two regions reserved for crash
dump kernel, in order to distinct from the high region and make no
effect to the use of existing kexec-tools, rename the low region as
"Crash kernel (low)".
Signed-off-by: NChen Zhou <chenzhou10@huawei.com>
Tested-by: NJohn Donnelly <John.p.donnelly@oracle.com>
Signed-off-by: NChen Zhou <chenzhou10@huawei.com>
Acked-by: NXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/arm64/include/asm/kexec.h

@@ -28,7 +28,12 @@
 /* 2M alignment for crash kernel regions */
 #define CRASH_ALIGN	SZ_2M
 
+#ifdef CONFIG_ZONE_DMA
+#define CRASH_ADDR_LOW_MAX	arm64_dma_phys_limit
+#else
 #define CRASH_ADDR_LOW_MAX	arm64_dma32_phys_limit
+#endif
+
 #define CRASH_ADDR_HIGH_MAX	MEMBLOCK_ALLOC_ACCESSIBLE
 
 #ifndef __ASSEMBLY__
@@ -96,6 +101,10 @@ static inline void crash_prepare_suspend(void) {}
 static inline void crash_post_resume(void) {}
 #endif
 
+#ifdef CONFIG_KEXEC_CORE
+extern void __init reserve_crashkernel(void);
+#endif
+
 #ifdef CONFIG_KEXEC_FILE
 #define ARCH_HAS_KIMAGE_ARCH
 

arch/arm64/kernel/setup.c

@@ -238,7 +238,18 @@ static void __init request_standard_resources(void)
 		    kernel_data.end <= res->end)
 			request_resource(res, &kernel_data);
 #ifdef CONFIG_KEXEC_CORE
-		/* Userspace will find "Crash kernel" region in /proc/iomem. */
+		/*
+		 * Userspace will find "Crash kernel" or "Crash kernel (low)"
+		 * region in /proc/iomem.
+		 * In order to distinct from the high region and make no effect
+		 * to the use of existing kexec-tools, rename the low region as
+		 * "Crash kernel (low)".
+		 */
+		if (crashk_low_res.end && crashk_low_res.start >= res->start &&
+				crashk_low_res.end <= res->end) {
+			crashk_low_res.name = "Crash kernel (low)";
+			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);

arch/arm64/mm/init.c

@@ -34,6 +34,7 @@
 #include <asm/fixmap.h>
 #include <asm/kasan.h>
 #include <asm/kernel-pgtable.h>
+#include <asm/kexec.h>
 #include <asm/memory.h>
 #include <asm/numa.h>
 #include <asm/sections.h>
@@ -62,66 +63,11 @@ EXPORT_SYMBOL(memstart_addr);
 phys_addr_t arm64_dma_phys_limit __ro_after_init;
 phys_addr_t arm64_dma32_phys_limit __ro_after_init;
 
-#ifdef CONFIG_KEXEC_CORE
-/*
- * reserve_crashkernel() - reserves memory for crash kernel
- *
- * This function reserves memory area given in "crashkernel=" kernel command
- * line parameter. The memory reserved is used by dump capture kernel when
- * primary kernel is crashing.
- */
-static void __init reserve_crashkernel(void)
-{
-	unsigned long long crash_base, crash_size;
-	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;
-
-	crash_size = PAGE_ALIGN(crash_size);
-
-	if (crash_base == 0) {
-		/* Current arm64 boot protocol requires 2MB alignment */
-		crash_base = memblock_find_in_range(CRASH_ALIGN, CRASH_ADDR_LOW_MAX,
-				crash_size, CRASH_ALIGN);
-		if (crash_base == 0) {
-			pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
-				crash_size);
-			return;
-		}
-	} else {
-		/* User specifies base address explicitly. */
-		if (!memblock_is_region_memory(crash_base, crash_size)) {
-			pr_warn("cannot reserve crashkernel: region is not memory\n");
-			return;
-		}
-
-		if (memblock_is_region_reserved(crash_base, crash_size)) {
-			pr_warn("cannot reserve crashkernel: region overlaps reserved memory\n");
-			return;
-		}
-
-		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);
-
-	pr_info("crashkernel reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
-		crash_base, crash_base + crash_size, crash_size >> 20);
-
-	crashk_res.start = crash_base;
-	crashk_res.end = crash_base + crash_size - 1;
-}
-#else
+#ifndef CONFIG_KEXEC_CORE
 static void __init reserve_crashkernel(void)
 {
 }
-#endif /* CONFIG_KEXEC_CORE */
+#endif
 
 #ifdef CONFIG_CRASH_DUMP
 static int __init early_init_dt_scan_elfcorehdr(unsigned long node,

arch/arm64/mm/mmu.c

@@ -488,6 +488,10 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
 #ifdef CONFIG_KEXEC_CORE
+	if (crashk_low_res.end)
+		memblock_mark_nomap(crashk_low_res.start,
+				    resource_size(&crashk_low_res));
+
 	if (crashk_res.end)
 		memblock_mark_nomap(crashk_res.start,
 				    resource_size(&crashk_res));

kernel/crash_core.c

@@ -322,10 +322,10 @@ int __init parse_crashkernel_low(char *cmdline,
 
 #ifdef CONFIG_KEXEC_CORE
 
-#ifdef CONFIG_X86
+#if defined(CONFIG_X86) || defined(CONFIG_ARM64)
 static int __init reserve_crashkernel_low(void)
 {
-#ifdef CONFIG_X86_64
+#ifdef CONFIG_64BIT
 	unsigned long long base, low_base = 0, low_size = 0;
 	unsigned long low_mem_limit;
 	int ret;
@@ -450,7 +450,7 @@ void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end   = crash_base + crash_size - 1;
 }
-#endif /* CONFIG_X86 */
+#endif
 #endif /* CONFIG_KEXEC_CORE */
 
 Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,