Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Wed, 10 Apr 2019 16:09:18 +0300
From:   Mike Rapoport <rppt@linux.ibm.com>
To:     Chen Zhou <chenzhou10@huawei.com>
Cc:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
        ebiederm@xmission.com, catalin.marinas@arm.com,
        will.deacon@arm.com, akpm@linux-foundation.org,
        ard.biesheuvel@linaro.org, horms@verge.net.au,
        takahiro.akashi@linaro.org, linux-arm-kernel@lists.infradead.org,
        linux-kernel@vger.kernel.org, kexec@lists.infradead.org,
        linux-mm@kvack.org, wangkefeng.wang@huawei.com
Subject: Re: [PATCH v3 3/4] arm64: kdump: support more than one crash kernel
 regions
References: <20190409102819.121335-1-chenzhou10@huawei.com>
 <20190409102819.121335-4-chenzhou10@huawei.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20190409102819.121335-4-chenzhou10@huawei.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Message-Id: <20190410130917.GC17196@rapoport-lnx>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi,

On Tue, Apr 09, 2019 at 06:28:18PM +0800, Chen Zhou wrote:
> 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];

I only now noticed that fdt_enforce_memory_region() uses memblock_region to
pass the ranges around. If we'd switch to memblock_type instead, the
implementation of memblock_cap_memory_ranges() would be really
straightforward. Can you check if the below patch works for you? 

From e476d584098e31273af573e1a78e308880c5cf28 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.ibm.com>
Date: Wed, 10 Apr 2019 16:02:32 +0300
Subject: [PATCH] memblock: extend memblock_cap_memory_range to multiple ranges

The memblock_cap_memory_range() removes all the memory except the range
passed to it. Extend this function to recieve memblock_type with the
regions that should be kept. This allows switching to simple iteration over
memblock arrays with 'for_each_mem_range' to remove the unneeded memory.

Enable use of this function in arm64 for reservation of multile regions for
the crash kernel.

Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
 arch/arm64/mm/init.c     | 34 ++++++++++++++++++++++++----------
 include/linux/memblock.h |  2 +-
 mm/memblock.c            | 45 ++++++++++++++++++++++-----------------------
 3 files changed, 47 insertions(+), 34 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 6bc1350..30a496f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -64,6 +64,10 @@ EXPORT_SYMBOL(memstart_addr);
 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
+
 /*
  * reserve_crashkernel() - reserves memory for crash kernel
  *
@@ -280,9 +284,9 @@ early_param("mem", early_mem);
 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;
+	struct memblock_type *usablemem = data;
+	const __be32 *reg, *endp;
+	int len, nr = 0;
 
 	if (depth != 1 || strcmp(uname, "chosen") != 0)
 		return 0;
@@ -291,22 +295,32 @@ 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)) {
+		unsigned long base = dt_mem_next_cell(dt_root_addr_cells, &reg);
+		unsigned long size = dt_mem_next_cell(dt_root_size_cells, &reg);
 
+		if (memblock_add_range(usablemem, base, size, NUMA_NO_NODE,
+				       MEMBLOCK_NONE))
+			return 0;
+		if (++nr >= CRASH_MAX_USABLE_RANGES)
+			break;
+	}
 	return 1;
 }
 
 static void __init fdt_enforce_memory_region(void)
 {
-	struct memblock_region reg = {
-		.size = 0,
+	struct memblock_region usable_regions[CRASH_MAX_USABLE_RANGES];
+	struct memblock_type usablemem = {
+		.max = CRASH_MAX_USABLE_RANGES,
+		.regions = usable_regions,
 	};
 
-	of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
+	of_scan_flat_dt(early_init_dt_scan_usablemem, &usablemem);
 
-	if (reg.size)
-		memblock_cap_memory_range(reg.base, reg.size);
+	if (usablemem.cnt)
+		memblock_cap_memory_ranges(&usablemem);
 }
 
 void __init arm64_memblock_init(void)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 294d5d8..a803ae9 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -404,7 +404,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
-void memblock_cap_memory_range(phys_addr_t base, phys_addr_t size);
+void memblock_cap_memory_ranges(struct memblock_type *regions_to_keep);
 void memblock_mem_limit_remove_map(phys_addr_t limit);
 bool memblock_is_memory(phys_addr_t addr);
 bool memblock_is_map_memory(phys_addr_t addr);
diff --git a/mm/memblock.c b/mm/memblock.c
index e7665cf..83d84d4 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -1605,36 +1605,34 @@ void __init memblock_enforce_memory_limit(phys_addr_t limit)
 			      PHYS_ADDR_MAX);
 }
 
-void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
+void __init memblock_cap_memory_ranges(struct memblock_type *regions_to_keep)
 {
-	int start_rgn, end_rgn;
-	int i, ret;
-
-	if (!size)
-		return;
-
-	ret = memblock_isolate_range(&memblock.memory, base, size,
-						&start_rgn, &end_rgn);
-	if (ret)
-		return;
-
-	/* remove all the MAP regions */
-	for (i = memblock.memory.cnt - 1; i >= end_rgn; i--)
-		if (!memblock_is_nomap(&memblock.memory.regions[i]))
-			memblock_remove_region(&memblock.memory, i);
+	phys_addr_t start, end;
+	u64 i;
 
-	for (i = start_rgn - 1; i >= 0; i--)
-		if (!memblock_is_nomap(&memblock.memory.regions[i]))
-			memblock_remove_region(&memblock.memory, i);
+	/* truncate memory while skipping NOMAP regions */
+	for_each_mem_range(i, &memblock.memory, regions_to_keep, NUMA_NO_NODE,
+			   MEMBLOCK_NONE, &start, &end, NULL)
+		memblock_remove(start, end);
 
 	/* truncate the reserved regions */
-	memblock_remove_range(&memblock.reserved, 0, base);
-	memblock_remove_range(&memblock.reserved,
-			base + size, PHYS_ADDR_MAX);
+	for_each_mem_range(i, &memblock.reserved, regions_to_keep, NUMA_NO_NODE,
+			   MEMBLOCK_NONE, &start, &end, NULL)
+		memblock_remove_range(&memblock.reserved, start, end);
 }
 
 void __init memblock_mem_limit_remove_map(phys_addr_t limit)
 {
+	struct memblock_region rgn = {
+		.base = 0,
+	};
+
+	struct memblock_type region_to_keep = {
+		.cnt = 1,
+		.max = 1,
+		.regions = &rgn,
+	};
+
 	phys_addr_t max_addr;
 
 	if (!limit)
@@ -1646,7 +1644,8 @@ void __init memblock_mem_limit_remove_map(phys_addr_t limit)
 	if (max_addr == PHYS_ADDR_MAX)
 		return;
 
-	memblock_cap_memory_range(0, max_addr);
+	region_to_keep.regions[0].size = max_addr;
+	memblock_cap_memory_ranges(&region_to_keep);
 }
 
 static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
-- 
2.7.4


-- 
Sincerely yours,
Mike.