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;
Subject: Re: [PATCH 2/3] arm64: kdump: support more than one crash kernel
 regions
To:     Mike Rapoport <rppt@linux.ibm.com>
References: <20190403030546.23718-1-chenzhou10@huawei.com>
 <20190403030546.23718-3-chenzhou10@huawei.com>
 <20190403112929.GA7715@rapoport-lnx>
 <f98a5559-3659-fb35-3765-15861e70a796@huawei.com>
 <20190404144408.GA6433@rapoport-lnx>
CC:     <catalin.marinas@arm.com>, <will.deacon@arm.com>,
        <akpm@linux-foundation.org>, <ard.biesheuvel@linaro.org>,
        <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>
From:   Chen Zhou <chenzhou10@huawei.com>
Message-ID: <783b8712-ddb1-a52b-81ee-0c6a216e5b7d@huawei.com>
Date:   Fri, 5 Apr 2019 10:17:13 +0800
User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:45.0) Gecko/20100101
 Thunderbird/45.7.1
MIME-Version: 1.0
In-Reply-To: <20190404144408.GA6433@rapoport-lnx>
Content-Type: text/plain; charset="windows-1252"
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Hi Mike,

On 2019/4/4 22:44, Mike Rapoport wrote:
> Hi,
> 
> On Wed, Apr 03, 2019 at 09:51:27PM +0800, Chen Zhou wrote:
>> Hi Mike,
>>
>> On 2019/4/3 19:29, Mike Rapoport wrote:
>>> On Wed, Apr 03, 2019 at 11:05:45AM +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     | 37 +++++++++++++++++++++++++------------
>>>>  include/linux/memblock.h |  1 +
>>>>  mm/memblock.c            | 40 ++++++++++++++++++++++++++++++++++++++++
>>>>  3 files changed, 66 insertions(+), 12 deletions(-)
>>>>
>>>> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
>>>> index ceb2a25..769c77a 100644
>>>> --- a/arch/arm64/mm/init.c
>>>> +++ b/arch/arm64/mm/init.c
>>>> @@ -64,6 +64,8 @@ EXPORT_SYMBOL(memstart_addr);
>>>>  phys_addr_t arm64_dma_phys_limit __ro_after_init;
>>>>  
>>>>  #ifdef CONFIG_KEXEC_CORE
>>>> +# define CRASH_MAX_USABLE_RANGES        2
>>>> +
>>>>  static int __init reserve_crashkernel_low(void)
>>>>  {
>>>>  	unsigned long long base, low_base = 0, low_size = 0;
>>>> @@ -346,8 +348,8 @@ 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;
>>>> @@ -356,22 +358,33 @@ 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,
>>>> -	};
>>>> -
>>>> -	of_scan_flat_dt(early_init_dt_scan_usablemem, &reg);
>>>> -
>>>> -	if (reg.size)
>>>> -		memblock_cap_memory_range(reg.base, reg.size);
>>>> +	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)
>>>> +		memblock_cap_memory_ranges(regs, cnt);
>>>
>>> Why not simply call memblock_cap_memory_range() for each region?
>>
>> Function memblock_cap_memory_range() removes all memory type ranges except specified range.
>> So if we call memblock_cap_memory_range() for each region simply, there will be no usable-memory
>> on kdump capture kernel.
> 
> Thanks for the clarification.
> I still think that memblock_cap_memory_ranges() is overly complex. 
> 
> How about doing something like this:
> 
> Cap the memory range for [min(regs[*].start, max(regs[*].end)] and then
> removing the range in the middle?

Yes, that would be ok. But that would do one more memblock_cap_memory_range operation.
That is, if there are n regions, we need to do (n + 1) operations, which doesn't seem to
matter.

I agree with you, your idea is better.

Thanks,
Chen Zhou

>  
>> Thanks,
>> Chen Zhou
>>
>>>
>>>>  }
>>>>  
>>>>  void __init arm64_memblock_init(void)
>>>> diff --git a/include/linux/memblock.h b/include/linux/memblock.h
>>>> index 47e3c06..aeade34 100644
>>>> --- a/include/linux/memblock.h
>>>> +++ b/include/linux/memblock.h
>>>> @@ -446,6 +446,7 @@ 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_region *regs, int cnt);
>>>>  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 28fa8926..1a7f4ee7c 100644
>>>> --- a/mm/memblock.c
>>>> +++ b/mm/memblock.c
>>>> @@ -1697,6 +1697,46 @@ void __init memblock_cap_memory_range(phys_addr_t base, phys_addr_t size)
>>>>  			base + size, PHYS_ADDR_MAX);
>>>>  }
>>>>  
>>>> +void __init memblock_cap_memory_ranges(struct memblock_region *regs, int cnt)
>>>> +{
>>>> +	int start_rgn[INIT_MEMBLOCK_REGIONS], end_rgn[INIT_MEMBLOCK_REGIONS];
>>>> +	int i, j, ret, nr = 0;
>>>> +
>>>> +	for (i = 0; i < cnt; i++) {
>>>> +		ret = memblock_isolate_range(&memblock.memory, regs[i].base,
>>>> +				regs[i].size, &start_rgn[i], &end_rgn[i]);
>>>> +		if (ret)
>>>> +			break;
>>>> +		nr++;
>>>> +	}
>>>> +	if (!nr)
>>>> +		return;
>>>> +
>>>> +	/* remove all the MAP regions */
>>>> +	for (i = memblock.memory.cnt - 1; i >= end_rgn[nr - 1]; i--)
>>>> +		if (!memblock_is_nomap(&memblock.memory.regions[i]))
>>>> +			memblock_remove_region(&memblock.memory, i);
>>>> +
>>>> +	for (i = nr - 1; i > 0; i--)
>>>> +		for (j = start_rgn[i] - 1; j >= end_rgn[i - 1]; j--)
>>>> +			if (!memblock_is_nomap(&memblock.memory.regions[j]))
>>>> +				memblock_remove_region(&memblock.memory, j);
>>>> +
>>>> +	for (i = start_rgn[0] - 1; i >= 0; i--)
>>>> +		if (!memblock_is_nomap(&memblock.memory.regions[i]))
>>>> +			memblock_remove_region(&memblock.memory, i);
>>>> +
>>>> +	/* truncate the reserved regions */
>>>> +	memblock_remove_range(&memblock.reserved, 0, regs[0].base);
>>>> +
>>>> +	for (i = nr - 1; i > 0; i--)
>>>> +		memblock_remove_range(&memblock.reserved,
>>>> +				regs[i].base, regs[i - 1].base + regs[i - 1].size);
>>>> +
>>>> +	memblock_remove_range(&memblock.reserved,
>>>> +			regs[nr - 1].base + regs[nr - 1].size, PHYS_ADDR_MAX);
>>>> +}
>>>> +
>>>>  void __init memblock_mem_limit_remove_map(phys_addr_t limit)
>>>>  {
>>>>  	phys_addr_t max_addr;
>>>> -- 
>>>> 2.7.4
>>>>
>>>
>>
>