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:   Chen Jiahao <chenjiahao16@huawei.com>
To:     <linux-kernel@vger.kernel.org>, <linux-riscv@lists.infradead.org>,
        <kexec@lists.infradead.org>, <linux-doc@vger.kernel.org>
CC:     <paul.walmsley@sifive.com>, <palmer@dabbelt.com>,
        <conor.dooley@microchip.com>, <guoren@kernel.org>,
        <heiko@sntech.de>, <bjorn@rivosinc.com>, <alex@ghiti.fr>,
        <akpm@linux-foundation.org>, <atishp@rivosinc.com>,
        <bhe@redhat.com>, <thunder.leizhen@huawei.com>, <horms@kernel.org>
Subject: [PATCH -next v3 1/2] riscv: kdump: Implement crashkernel=X,[high,low]
Date:   Fri, 7 Apr 2023 06:02:05 +0800
Message-ID: <20230406220206.3067006-2-chenjiahao16@huawei.com>
In-Reply-To: <20230406220206.3067006-1-chenjiahao16@huawei.com>
References: <20230406220206.3067006-1-chenjiahao16@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

On riscv, the current crash kernel allocation logic is trying to
allocate within 32bit addressible memory region by default, if
failed, try to allocate without 4G restriction.

In need of saving DMA zone memory while allocating a relatively large
crash kernel region, allocating the reserved memory top down in
high memory, without overlapping the DMA zone, is a mature solution.
Here introduce the parameter option crashkernel=X,[high,low].

One can reserve the crash kernel from high memory above DMA zone range
by explicitly passing "crashkernel=X,high"; or reserve a memory range
below 4G with "crashkernel=X,low".

Signed-off-by: Chen Jiahao <chenjiahao16@huawei.com>
---
 arch/riscv/kernel/setup.c |  5 +++
 arch/riscv/mm/init.c      | 74 ++++++++++++++++++++++++++++++++++++---
 2 files changed, 74 insertions(+), 5 deletions(-)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 5d3184cbf518..ea84e5047c23 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -176,6 +176,11 @@ static void __init init_resources(void)
 		if (ret < 0)
 			goto error;
 	}
+	if (crashk_low_res.start != crashk_low_res.end) {
+		ret = add_resource(&iomem_resource, &crashk_low_res);
+		if (ret < 0)
+			goto error;
+	}
 #endif
 
 #ifdef CONFIG_CRASH_DUMP
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 478d6763a01a..b5b457193423 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1152,6 +1152,28 @@ static inline void setup_vm_final(void)
 }
 #endif /* CONFIG_MMU */
 
+/* Reserve 128M low memory by default for swiotlb buffer */
+#define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
+
+static int __init reserve_crashkernel_low(unsigned long long low_size)
+{
+	unsigned long long low_base;
+
+	low_base = memblock_phys_alloc_range(low_size, PMD_SIZE, 0, dma32_phys_limit);
+	if (!low_base) {
+		pr_err("cannot allocate crashkernel low memory (size:0x%llx).\n", low_size);
+		return -ENOMEM;
+	}
+
+	pr_info("crashkernel low memory reserved: 0x%016llx - 0x%016llx (%lld MB)\n",
+		low_base, low_base + low_size, low_size >> 20);
+
+	crashk_low_res.start = low_base;
+	crashk_low_res.end = low_base + low_size - 1;
+
+	return 0;
+}
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -1163,8 +1185,12 @@ static void __init reserve_crashkernel(void)
 {
 	unsigned long long crash_base = 0;
 	unsigned long long crash_size = 0;
+	unsigned long long crash_low_size = 0;
 	unsigned long search_start = memblock_start_of_DRAM();
 	unsigned long search_end = memblock_end_of_DRAM();
+	unsigned long search_low_max = (unsigned long)dma32_phys_limit;
+	char *cmdline = boot_command_line;
+	bool fixed_base = false;
 
 	int ret = 0;
 
@@ -1180,14 +1206,37 @@ static void __init reserve_crashkernel(void)
 		return;
 	}
 
-	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
+	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
 				&crash_size, &crash_base);
-	if (ret || !crash_size)
+	if (ret == -ENOENT) {
+		/*
+		 * crashkernel=X,[high,low] can be specified or not, but
+		 * invalid value is not allowed.
+		 */
+		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
+		if (ret || !crash_size)
+			return;
+
+		/*
+		 * crashkernel=Y,low is valid only when crashkernel=X,high
+		 * is passed and high memory is reserved successful.
+		 */
+		ret = parse_crashkernel_low(cmdline, 0, &crash_low_size, &crash_base);
+		if (ret == -ENOENT)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+		else if (ret)
+			return;
+
+		search_start = search_low_max;
+	} else if (ret || !crash_size) {
+		/* Invalid argument value specified */
 		return;
+	}
 
 	crash_size = PAGE_ALIGN(crash_size);
 
 	if (crash_base) {
+		fixed_base = true;
 		search_start = crash_base;
 		search_end = crash_base + crash_size;
 	}
@@ -1201,16 +1250,31 @@ static void __init reserve_crashkernel(void)
 	 */
 	crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
 					       search_start,
-					       min(search_end, (unsigned long) SZ_4G));
+					       min(search_end, search_low_max));
 	if (crash_base == 0) {
-		/* Try again without restricting region to 32bit addressible memory */
+		if (fixed_base) {
+			pr_warn("crashkernel: allocating failed with given size@offset\n");
+			return;
+		}
+
+		/* Try again above the region of 32bit addressible memory */
 		crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE,
-						search_start, search_end);
+						       max(search_start, search_low_max),
+						       search_end);
 		if (crash_base == 0) {
 			pr_warn("crashkernel: couldn't allocate %lldKB\n",
 				crash_size >> 10);
 			return;
 		}
+
+		if (!crash_low_size)
+			crash_low_size = DEFAULT_CRASH_KERNEL_LOW_SIZE;
+	}
+
+	if ((crash_base > dma32_phys_limit - crash_low_size) &&
+	    crash_low_size && reserve_crashkernel_low(crash_low_size)) {
+		memblock_phys_free(crash_base, crash_size);
+		return;
 	}
 
 	pr_info("crashkernel: reserved 0x%016llx - 0x%016llx (%lld MB)\n",
-- 
2.31.1