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:   Baoquan He <bhe@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     catalin.marinas@arm.com, thunder.leizhen@huawei.com,
        John.p.donnelly@oracle.com, kexec@lists.infradead.org,
        linux-arm-kernel@lists.infradead.org, horms@kernel.org,
        chenjiahao16@huawei.com, linux-riscv@lists.infradead.org,
        x86@kernel.org, bp@alien8.de, Baoquan He <bhe@redhat.com>
Subject: [RFC PATCH 4/4] x86: kdump: use generic interfaces to simplify crashkernel reservation code
Date:   Mon, 19 Jun 2023 13:59:51 +0800
Message-Id: <20230619055951.45620-5-bhe@redhat.com>
In-Reply-To: <20230619055951.45620-1-bhe@redhat.com>
References: <20230619055951.45620-1-bhe@redhat.com>
MIME-Version: 1.0
Content-type: text/plain
Content-Transfer-Encoding: 8bit
Precedence: bulk

With the help of generic functions parse_crashkernel_generic() and
reserve_crashkernel_generic(), crashkernel reservation can be
simplified by steps:

1) Provide CRASH_ALIGN, CRASH_ADDR_LOW_MAX, CRASH_ADDR_HIGH_MAX and
   DEFAULT_CRASH_KERNEL_LOW_SIZE in <asm/kexec.h>;

2) Add arch_reserve_crashkernel() to call parse_crashkernel_generic()
   and reserve_crashkernel_generic(), and do the ARCH specific work if
   needed.

3) Add ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION Kconfig in
   arch/x86/Kconfig.

When adding DEFAULT_CRASH_KERNEL_LOW_SIZE, add crash_low_size_default()
to calculate crashkernel low memory because x86_64 has special
requirement.

The old reserve_crashkernel_low() and reserve_crashkernel() can be
removed.

Signed-off-by: Baoquan He <bhe@redhat.com>
---
 arch/x86/Kconfig             |   3 +
 arch/x86/include/asm/kexec.h |  32 ++++++++
 arch/x86/kernel/setup.c      | 142 ++++-------------------------------
 3 files changed, 50 insertions(+), 127 deletions(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 53bab123a8ee..fb91a5064c8d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2076,6 +2076,9 @@ config KEXEC_FILE
 config ARCH_HAS_KEXEC_PURGATORY
 	def_bool KEXEC_FILE
 
+config ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+	def_bool CRASH_CORE
+
 config KEXEC_SIG
 	bool "Verify kernel signature during kexec_file_load() syscall"
 	depends on KEXEC_FILE
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5b77bbc28f96..84a7d1f6f153 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -66,6 +66,37 @@ struct kimage;
 # define KEXEC_ARCH KEXEC_ARCH_X86_64
 #endif
 
+/*
+ * --------- Crashkernel reservation ------------------------------
+ */
+
+/* 16M alignment for crash kernel regions */
+#define CRASH_ALIGN             SZ_16M
+
+/*
+ * Keep the crash kernel below this limit.
+ *
+ * Earlier 32-bits kernels would limit the kernel to the low 512 MB range
+ * due to mapping restrictions.
+ *
+ * 64-bit kdump kernels need to be restricted to be under 64 TB, which is
+ * the upper limit of system RAM in 4-level paging mode. Since the kdump
+ * jump could be from 5-level paging to 4-level paging, the jump will fail if
+ * the kernel is put above 64 TB, and during the 1st kernel bootup there's
+ * no good way to detect the paging mode of the target kernel which will be
+ * loaded for dumping.
+ */
+
+#ifdef CONFIG_X86_32
+# define CRASH_ADDR_LOW_MAX     SZ_512M
+# define CRASH_ADDR_HIGH_MAX    SZ_512M
+#else
+# define CRASH_ADDR_LOW_MAX     SZ_4G
+# define CRASH_ADDR_HIGH_MAX    SZ_64T
+#endif
+
+# define DEFAULT_CRASH_KERNEL_LOW_SIZE crash_low_size_default()
+
 /*
  * This function is responsible for capturing register states if coming
  * via panic otherwise just fix up the ss and sp if coming via kernel
@@ -209,6 +240,7 @@ typedef void crash_vmclear_fn(void);
 extern crash_vmclear_fn __rcu *crash_vmclear_loaded_vmcss;
 extern void kdump_nmi_shootdown_cpus(void);
 
+extern unsigned long crash_low_size_default(void);
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index b2b67b8c1c1e..11ae1f0c9487 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -475,151 +475,39 @@ static void __init memblock_x86_reserve_range_setup_data(void)
  * --------- Crashkernel reservation ------------------------------
  */
 
-/* 16M alignment for crash kernel regions */
-#define CRASH_ALIGN		SZ_16M
-
-/*
- * Keep the crash kernel below this limit.
- *
- * Earlier 32-bits kernels would limit the kernel to the low 512 MB range
- * due to mapping restrictions.
- *
- * 64-bit kdump kernels need to be restricted to be under 64 TB, which is
- * the upper limit of system RAM in 4-level paging mode. Since the kdump
- * jump could be from 5-level paging to 4-level paging, the jump will fail if
- * the kernel is put above 64 TB, and during the 1st kernel bootup there's
- * no good way to detect the paging mode of the target kernel which will be
- * loaded for dumping.
- */
-#ifdef CONFIG_X86_32
-# define CRASH_ADDR_LOW_MAX	SZ_512M
-# define CRASH_ADDR_HIGH_MAX	SZ_512M
-#else
-# define CRASH_ADDR_LOW_MAX	SZ_4G
-# define CRASH_ADDR_HIGH_MAX	SZ_64T
-#endif
-
-static int __init reserve_crashkernel_low(void)
+unsigned long crash_low_size_default(void)
 {
 #ifdef CONFIG_X86_64
-	unsigned long long base, low_base = 0, low_size = 0;
-	unsigned long low_mem_limit;
-	int ret;
-
-	low_mem_limit = min(memblock_phys_mem_size(), CRASH_ADDR_LOW_MAX);
-
-	/* crashkernel=Y,low */
-	ret = parse_crashkernel_low(boot_command_line, low_mem_limit, &low_size, &base);
-	if (ret) {
-		/*
-		 * two parts from kernel/dma/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_phys_alloc_range(low_size, CRASH_ALIGN, 0, CRASH_ADDR_LOW_MAX);
-	if (!low_base) {
-		pr_err("Cannot reserve %ldMB crashkernel low memory, please try smaller size.\n",
-		       (unsigned long)(low_size >> 20));
-		return -ENOMEM;
-	}
-
-	pr_info("Reserving %ldMB of low memory at %ldMB for crashkernel (low RAM limit: %ldMB)\n",
-		(unsigned long)(low_size >> 20),
-		(unsigned long)(low_base >> 20),
-		(unsigned long)(low_mem_limit >> 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 max(swiotlb_size_or_default() + (8UL << 20), 256UL << 20);
+#else
 	return 0;
+#endif
 }
 
-static void __init reserve_crashkernel(void)
+static void __init arch_reserve_crashkernel(void)
 {
-	unsigned long long crash_size, crash_base, total_mem;
+	unsigned long long crash_base, crash_size, low_size = 0;
+	char *cmdline = boot_command_line;
 	bool high = false;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
 		return;
 
-	total_mem = memblock_phys_mem_size();
-
-	/* crashkernel=XM */
-	ret = parse_crashkernel_common(boot_command_line, total_mem,
-				       &crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0) {
-		/* crashkernel=X,high */
-		ret = parse_crashkernel_high(boot_command_line, total_mem,
-					     &crash_size, &crash_base);
-		if (ret != 0 || crash_size <= 0)
-			return;
-		high = true;
-	}
+	ret = parse_crashkernel_generic(cmdline, &crash_size, &crash_base,
+					&low_size, &high);
+	if (ret)
+		return;
 
 	if (xen_pv_domain()) {
 		pr_info("Ignoring crashkernel for a Xen PV domain\n");
 		return;
 	}
 
-	/* 0 means: find the address automatically */
-	if (!crash_base) {
-		/*
-		 * Set CRASH_ADDR_LOW_MAX upper bound for crash memory,
-		 * crashkernel=x,high reserves memory over 4G, also allocates
-		 * 256M extra low memory for DMA buffers and swiotlb.
-		 * But the extra memory is not required for all machines.
-		 * So try low memory first and fall back to high memory
-		 * unless "crashkernel=size[KMG],high" is specified.
-		 */
-		if (!high)
-			crash_base = memblock_phys_alloc_range(crash_size,
-						CRASH_ALIGN, CRASH_ALIGN,
-						CRASH_ADDR_LOW_MAX);
-		if (!crash_base)
-			crash_base = memblock_phys_alloc_range(crash_size,
-						CRASH_ALIGN, CRASH_ALIGN,
-						CRASH_ADDR_HIGH_MAX);
-		if (!crash_base) {
-			pr_info("crashkernel reservation failed - No suitable area found.\n");
-			return;
-		}
-	} else {
-		unsigned long long start;
-
-		start = memblock_phys_alloc_range(crash_size, SZ_1M, crash_base,
-						  crash_base + crash_size);
-		if (start != crash_base) {
-			pr_info("crashkernel reservation failed - memory is in use.\n");
-			return;
-		}
-	}
-
-	if (crash_base >= (1ULL << 32) && reserve_crashkernel_low()) {
-		memblock_phys_free(crash_base, crash_size);
-		return;
-	}
-
-	pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n",
-		(unsigned long)(crash_size >> 20),
-		(unsigned long)(crash_base >> 20),
-		(unsigned long)(total_mem >> 20));
+	reserve_crashkernel_generic(cmdline, crash_size, crash_base,
+				    low_size, high);
 
-	crashk_res.start = crash_base;
-	crashk_res.end   = crash_base + crash_size - 1;
-	insert_resource(&iomem_resource, &crashk_res);
+	return;
 }
 
 static struct resource standard_io_resources[] = {
@@ -1229,7 +1117,7 @@ void __init setup_arch(char **cmdline_p)
 	 * Reserve memory for crash kernel after SRAT is parsed so that it
 	 * won't consume hotpluggable memory.
 	 */
-	reserve_crashkernel();
+	arch_reserve_crashkernel();
 
 	memblock_find_dma_reserve();
 
-- 
2.34.1