[PATCH v2 0/3] support reserving crashkernel above 4G on arm64 kdump

[PATCH v2 0/3] support reserving crashkernel above 4G on arm64 kdump

[Chen Zhou]

When crashkernel is reserved above 4G in memory, kernel should reserve
some amount of low memory for swiotlb and some DMA buffers. So there may
be two crash kernel regions, one is below 4G, the other is above 4G.

Crash dump kernel reads more than one crash kernel regions via a dtb
property under node /chosen,
linux,usable-memory-range = <BASE1 SIZE1 [BASE2 SIZE2]>.

Besides, we need to modify kexec-tools:
  arm64: support more than one crash kernel regions(see [1])

Changes since [v1]:
- Move common reserve_crashkernel_low() code into kernel/kexec_core.c.
- Remove memblock_cap_memory_ranges() i added in v1 and implement that
  in fdt_enforce_memory_region().
  There are at most two crash kernel regions, for two crash kernel regions
  case, we cap the memory range [min(regs[*].start), max(regs[*].end)]
  and then remove the memory range in the middle.

[1]: http://lists.infradead.org/pipermail/kexec/2019-April/022792.html
[v1]: https://lkml.org/lkml/2019/4/8/628

Chen Zhou (3):
  arm64: kdump: support reserving crashkernel above 4G
  arm64: kdump: support more than one crash kernel regions
  kdump: update Documentation about crashkernel on arm64

 Documentation/admin-guide/kernel-parameters.txt |  4 +-
 arch/arm64/include/asm/kexec.h                  |  3 +
 arch/arm64/kernel/setup.c                       |  3 +
 arch/arm64/mm/init.c                            | 92 +++++++++++++++++++++----
 arch/x86/include/asm/kexec.h                    |  3 +
 arch/x86/kernel/setup.c                         | 66 ++----------------
 include/linux/kexec.h                           |  1 +
 include/linux/memblock.h                        |  6 ++
 kernel/kexec_core.c                             | 53 ++++++++++++++
 mm/memblock.c                                   |  7 +-
 10 files changed, 159 insertions(+), 79 deletions(-)

-- 
2.7.4


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[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@huawei.com>
---
 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


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 2/3] arm64: kdump: support more than one crash kernel regions

[Chen Zhou]

After commit (arm64: kdump: support reserving crashkernel above 4G),
there may be two crash kernel regions, one is below 4G, the other is
above 4G.

Crash dump kernel reads more than one crash kernel regions via a dtb
property under node /chosen,
linux,usable-memory-range = <BASE1 SIZE1 [BASE2 SIZE2]>

Signed-off-by: Chen Zhou <chenzhou10@huawei.com>
---
 arch/arm64/mm/init.c     | 66 ++++++++++++++++++++++++++++++++++++++++--------
 include/linux/memblock.h |  6 +++++
 mm/memblock.c            |  7 ++---
 3 files changed, 66 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 3bebddf..0f18665 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -65,6 +65,11 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_KEXEC_CORE
 
+/* at most two crash kernel regions, low_region and high_region */
+#define CRASH_MAX_USABLE_RANGES	2
+#define LOW_REGION_IDX			0
+#define HIGH_REGION_IDX			1
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -297,8 +302,8 @@ static int __init early_init_dt_scan_usablemem(unsigned long node,
 		const char *uname, int depth, void *data)
 {
 	struct memblock_region *usablemem = data;
-	const __be32 *reg;
-	int len;
+	const __be32 *reg, *endp;
+	int len, nr = 0;
 
 	if (depth != 1 || strcmp(uname, "chosen") != 0)
 		return 0;
@@ -307,22 +312,63 @@ static int __init early_init_dt_scan_usablemem(unsigned long node,
 	if (!reg || (len < (dt_root_addr_cells + dt_root_size_cells)))
 		return 1;
 
-	usablemem->base = dt_mem_next_cell(dt_root_addr_cells, &reg);
-	usablemem->size = dt_mem_next_cell(dt_root_size_cells, &reg);
+	endp = reg + (len / sizeof(__be32));
+	while ((endp - reg) >= (dt_root_addr_cells + dt_root_size_cells)) {
+		usablemem[nr].base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+		usablemem[nr].size = dt_mem_next_cell(dt_root_size_cells, &reg);
+
+		if (++nr >= CRASH_MAX_USABLE_RANGES)
+			break;
+	}
 
 	return 1;
 }
 
 static void __init fdt_enforce_memory_region(void)
 {
-	struct memblock_region reg = {
-		.size = 0,
-	};
+	int i, cnt = 0;
+	struct memblock_region regs[CRASH_MAX_USABLE_RANGES];
+
+	memset(regs, 0, sizeof(regs));
+	of_scan_flat_dt(early_init_dt_scan_usablemem, regs);
+
+	for (i = 0; i < CRASH_MAX_USABLE_RANGES; i++)
+		if (regs[i].size)
+			cnt++;
+		else
+			break;
+
+	if (cnt - 1 == LOW_REGION_IDX)
+		memblock_cap_memory_range(regs[LOW_REGION_IDX].base,
+				regs[LOW_REGION_IDX].size);
+	else if (cnt - 1 == HIGH_REGION_IDX) {
+		/*
+		 * Two crash kernel regions, cap the memory range
+		 * [regs[LOW_REGION_IDX].base, regs[HIGH_REGION_IDX].end]
+		 * and then remove the memory range in the middle.
+		 */
+		int start_rgn, end_rgn, i, ret;
+		phys_addr_t mid_base, mid_size;
+
+		mid_base = regs[LOW_REGION_IDX].base + regs[LOW_REGION_IDX].size;
+		mid_size = regs[HIGH_REGION_IDX].base - mid_base;
+		ret = memblock_isolate_range(&memblock.memory, mid_base,
+				mid_size, &start_rgn, &end_rgn);
 
-	of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+		if (ret)
+			return;
 
-	if (reg.size)
-		memblock_cap_memory_range(reg.base, reg.size);
+		memblock_cap_memory_range(regs[LOW_REGION_IDX].base,
+				regs[HIGH_REGION_IDX].base -
+				regs[LOW_REGION_IDX].base +
+				regs[HIGH_REGION_IDX].size);
+		for (i = end_rgn - 1; i >= start_rgn; i--) {
+			if (!memblock_is_nomap(&memblock.memory.regions[i]))
+				memblock_remove_region(&memblock.memory, i);
+		}
+		memblock_remove_range(&memblock.reserved, mid_base,
+				mid_base + mid_size);
+	}
 }
 
 void __init arm64_memblock_init(void)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 294d5d8..787d252 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -110,9 +110,15 @@ void memblock_discard(void);
 
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
+void memblock_remove_region(struct memblock_type *type, unsigned long r);
 void memblock_allow_resize(void);
 int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
 int memblock_add(phys_addr_t base, phys_addr_t size);
+int memblock_isolate_range(struct memblock_type *type,
+					phys_addr_t base, phys_addr_t size,
+					int *start_rgn, int *end_rgn);
+int memblock_remove_range(struct memblock_type *type,
+					phys_addr_t base, phys_addr_t size);
 int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
diff --git a/mm/memblock.c b/mm/memblock.c
index e7665cf..1846e2d 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -357,7 +357,8 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 	return ret;
 }
 
-static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
+void __init_memblock memblock_remove_region(struct memblock_type *type,
+					unsigned long r)
 {
 	type->total_size -= type->regions[r].size;
 	memmove(&type->regions[r], &type->regions[r + 1],
@@ -724,7 +725,7 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
  * Return:
  * 0 on success, -errno on failure.
  */
-static int __init_memblock memblock_isolate_range(struct memblock_type *type,
+int __init_memblock memblock_isolate_range(struct memblock_type *type,
 					phys_addr_t base, phys_addr_t size,
 					int *start_rgn, int *end_rgn)
 {
@@ -784,7 +785,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 	return 0;
 }
 
-static int __init_memblock memblock_remove_range(struct memblock_type *type,
+int __init_memblock memblock_remove_range(struct memblock_type *type,
 					  phys_addr_t base, phys_addr_t size)
 {
 	int start_rgn, end_rgn;
-- 
2.7.4


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

[PATCH v2 3/3] kdump: update Documentation about crashkernel on arm64

[Chen Zhou]

Now we support crashkernel=X,[high,low] on arm64, update the
Documentation.

Signed-off-by: Chen Zhou <chenzhou10@huawei.com>
---
 Documentation/admin-guide/kernel-parameters.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 060482d..d5c65e1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -715,14 +715,14 @@
 			Documentation/kdump/kdump.txt for an example.
 
 	crashkernel=size[KMG],high
-			[KNL, x86_64] range could be above 4G. Allow kernel
+			[KNL, x86_64, arm64] range could be above 4G. Allow kernel
 			to allocate physical memory region from top, so could
 			be above 4G if system have more than 4G ram installed.
 			Otherwise memory region will be allocated below 4G, if
 			available.
 			It will be ignored if crashkernel=X is specified.
 	crashkernel=size[KMG],low
-			[KNL, x86_64] range under 4G. When crashkernel=X,high
+			[KNL, x86_64, arm64] range under 4G. When crashkernel=X,high
 			is passed, kernel could allocate physical memory region
 			above 4G, that cause second kernel crash on system
 			that require some amount of low memory, e.g. swiotlb
-- 
2.7.4


_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel