lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <48e9f8e8-be1e-fa62-1cbd-61be4a73658e@oracle.com>
Date:   Wed, 26 Jan 2022 09:18:18 -0600
From:   john.p.donnelly@...cle.com
To:     Zhen Lei <thunder.leizhen@...wei.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        x86@...nel.org, "H . Peter Anvin" <hpa@...or.com>,
        linux-kernel@...r.kernel.org, Dave Young <dyoung@...hat.com>,
        Baoquan He <bhe@...hat.com>, Vivek Goyal <vgoyal@...hat.com>,
        Eric Biederman <ebiederm@...ssion.com>,
        kexec@...ts.infradead.org,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        linux-arm-kernel@...ts.infradead.org,
        Rob Herring <robh+dt@...nel.org>,
        Frank Rowand <frowand.list@...il.com>,
        devicetree@...r.kernel.org, Jonathan Corbet <corbet@....net>,
        linux-doc@...r.kernel.org
Cc:     Randy Dunlap <rdunlap@...radead.org>,
        Feng Zhou <zhoufeng.zf@...edance.com>,
        Kefeng Wang <wangkefeng.wang@...wei.com>,
        Chen Zhou <dingguo.cz@...group.com>,
        Dave Kleikamp <dave.kleikamp@...cle.com>
Subject: Re: [PATCH v20 3/5] arm64: kdump: reimplement crashkernel=X

On 1/24/22 2:47 AM, Zhen Lei wrote:
> From: Chen Zhou <chenzhou10@...wei.com>
> 
> There are following issues in arm64 kdump:
> 1. We use crashkernel=X to reserve crashkernel below 4G, which
> will fail when there is no enough low memory.
> 2. If reserving crashkernel above 4G, in this case, crash dump
> kernel will boot failure because there is no low memory available
> for allocation.
> 
> To solve these issues, change the behavior of crashkernel=X and
> introduce crashkernel=X,[high,low]. crashkernel=X tries low allocation
> in DMA zone, and fall back to high allocation if it fails.
> We can also use "crashkernel=X,high" to select a region above DMA zone,
> which also tries to allocate at least 256M in DMA zone automatically.
> "crashkernel=Y,low" can be used to allocate specified size low memory.
> 
> Signed-off-by: Chen Zhou <chenzhou10@...wei.com>
> Co-developed-by: Zhen Lei <thunder.leizhen@...wei.com>
> Signed-off-by: Zhen Lei <thunder.leizhen@...wei.com>


Acked-by: John Donnelly  <john.p.donnelly@...cle.com>

> ---
>   arch/arm64/kernel/machine_kexec.c      |  9 +++-
>   arch/arm64/kernel/machine_kexec_file.c | 12 ++++-
>   arch/arm64/mm/init.c                   | 68 ++++++++++++++++++++++++--
>   3 files changed, 81 insertions(+), 8 deletions(-)
> 
> diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
> index e16b248699d5c3c..19c2d487cb08feb 100644
> --- a/arch/arm64/kernel/machine_kexec.c
> +++ b/arch/arm64/kernel/machine_kexec.c
> @@ -329,8 +329,13 @@ bool crash_is_nosave(unsigned long pfn)
>   
>   	/* in reserved memory? */
>   	addr = __pfn_to_phys(pfn);
> -	if ((addr < crashk_res.start) || (crashk_res.end < addr))
> -		return false;
> +	if ((addr < crashk_res.start) || (crashk_res.end < addr)) {
> +		if (!crashk_low_res.end)
> +			return false;
> +
> +		if ((addr < crashk_low_res.start) || (crashk_low_res.end < addr))
> +			return false;
> +	}
>   
>   	if (!kexec_crash_image)
>   		return true;
> diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c
> index 59c648d51848886..889951291cc0f9c 100644
> --- a/arch/arm64/kernel/machine_kexec_file.c
> +++ b/arch/arm64/kernel/machine_kexec_file.c
> @@ -65,10 +65,18 @@ static int prepare_elf_headers(void **addr, unsigned long *sz)
>   
>   	/* Exclude crashkernel region */
>   	ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end);
> +	if (ret)
> +		goto out;
> +
> +	if (crashk_low_res.end) {
> +		ret = crash_exclude_mem_range(cmem, crashk_low_res.start, crashk_low_res.end);
> +		if (ret)
> +			goto out;
> +	}
>   
> -	if (!ret)
> -		ret =  crash_prepare_elf64_headers(cmem, true, addr, sz);
> +	ret = crash_prepare_elf64_headers(cmem, true, addr, sz);
>   
> +out:
>   	kfree(cmem);
>   	return ret;
>   }
> diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
> index 6c653a2c7cff052..a5d43feac0d7d96 100644
> --- a/arch/arm64/mm/init.c
> +++ b/arch/arm64/mm/init.c
> @@ -71,6 +71,30 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init;
>   #define CRASH_ADDR_LOW_MAX	arm64_dma_phys_limit
>   #define CRASH_ADDR_HIGH_MAX	MEMBLOCK_ALLOC_ACCESSIBLE
>   
> +static int __init reserve_crashkernel_low(unsigned long long low_size)
> +{
> +	unsigned long long low_base;
> +
> +	/* 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 allocate crashkernel low memory (size:0x%llx).\n", low_size);
> +		return -ENOMEM;
> +	}
> +
> +	pr_info("crashkernel low memory reserved: 0x%llx - 0x%llx (%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;
> +	insert_resource(&iomem_resource, &crashk_low_res);
> +
> +	return 0;
> +}
> +
>   /*
>    * reserve_crashkernel() - reserves memory for crash kernel
>    *
> @@ -81,29 +105,62 @@ phys_addr_t arm64_dma_phys_limit __ro_after_init;
>   static void __init reserve_crashkernel(void)
>   {
>   	unsigned long long crash_base, crash_size;
> +	unsigned long long crash_low_size = SZ_256M;
>   	unsigned long long crash_max = CRASH_ADDR_LOW_MAX;
>   	int ret;
> +	bool fixed_base;
> +	char *cmdline = boot_command_line;
>   
> -	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
> +	/* crashkernel=X[@offset] */
> +	ret = parse_crashkernel(cmdline, memblock_phys_mem_size(),
>   				&crash_size, &crash_base);
> -	/* no crashkernel= or invalid value specified */
> -	if (ret || !crash_size)
> -		return;
> +	if (ret || !crash_size) {
> +		unsigned long long low_size;
>   
> +		/* crashkernel=X,high */
> +		ret = parse_crashkernel_high(cmdline, 0, &crash_size, &crash_base);
> +		if (ret || !crash_size)
> +			return;
> +
> +		/* crashkernel=X,low */
> +		ret = parse_crashkernel_low(cmdline, 0, &low_size, &crash_base);
> +		if (!ret)
> +			crash_low_size = low_size;
> +
> +		crash_max = CRASH_ADDR_HIGH_MAX;
> +	}
> +
> +	fixed_base = !!crash_base;
>   	crash_size = PAGE_ALIGN(crash_size);
>   
>   	/* User specifies base address explicitly. */
>   	if (crash_base)
>   		crash_max = crash_base + crash_size;
>   
> +retry:
>   	crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN,
>   					       crash_base, crash_max);
>   	if (!crash_base) {
> +		/*
> +		 * Attempt to fully allocate low memory failed, fall back
> +		 * to high memory, the minimum required low memory will be
> +		 * reserved later.
> +		 */
> +		if (!fixed_base && (crash_max == CRASH_ADDR_LOW_MAX)) {
> +			crash_max = CRASH_ADDR_HIGH_MAX;
> +			goto retry;
> +		}
> +
>   		pr_warn("cannot allocate crashkernel (size:0x%llx)\n",
>   			crash_size);
>   		return;
>   	}
>   
> +	if (crash_base >= SZ_4G && 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",
>   		crash_base, crash_base + crash_size, crash_size >> 20);
>   
> @@ -112,6 +169,9 @@ static void __init reserve_crashkernel(void)
>   	 * map. Inform kmemleak so that it won't try to access it.
>   	 */
>   	kmemleak_ignore_phys(crash_base);
> +	if (crashk_low_res.end)
> +		kmemleak_ignore_phys(crashk_low_res.start);
> +
>   	crashk_res.start = crash_base;
>   	crashk_res.end = crash_base + crash_size - 1;
>   	insert_resource(&iomem_resource, &crashk_res);

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ