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:   Thu, 21 Jun 2018 10:47:13 +0800
From:   Baoquan He <bhe@redhat.com>
To:     Lianbo Jiang <lijiang@redhat.com>
Cc:     linux-kernel@vger.kernel.org, thomas.lendacky@amd.com,
        iommu@lists.linux-foundation.org, dyoung@redhat.com,
        kexec@lists.infradead.org
Subject: Re: [PATCH 4/4 V3] Help to dump the old memory encrypted into vmcore
 file
Message-ID: <20180621024713.GI29979@MiWiFi-R3L-srv>
References: <20180616082714.32035-1-lijiang@redhat.com>
 <20180616082714.32035-5-lijiang@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20180616082714.32035-5-lijiang@redhat.com>
User-Agent: Mutt/1.9.1 (2017-09-22)
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 06/16/18 at 04:27pm, Lianbo Jiang wrote:
> In kdump mode, we need to dump the old memory into vmcore file,
> if SME is enabled in the first kernel, we must remap the old
> memory in encrypted manner, which will be automatically decrypted
> when we read from DRAM. It helps to parse the vmcore for some tools.

It implies 2nd kernel is sme enabled, right?

Then what if 1st kernel has no sme enabled?

> 
> Signed-off-by: Lianbo Jiang <lijiang@redhat.com>
> ---
> Some changes:
> 1. add a new file and modify Makefile.
> 2. remove some code in sev_active().
> 
>  arch/x86/kernel/Makefile             |  1 +
>  arch/x86/kernel/crash_dump_encrypt.c | 53 ++++++++++++++++++++++++++++++++++++
>  fs/proc/vmcore.c                     | 20 ++++++++++----
>  include/linux/crash_dump.h           | 11 ++++++++
>  4 files changed, 79 insertions(+), 6 deletions(-)
>  create mode 100644 arch/x86/kernel/crash_dump_encrypt.c
> 
> diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
> index 02d6f5c..afb5bad 100644
> --- a/arch/x86/kernel/Makefile
> +++ b/arch/x86/kernel/Makefile
> @@ -96,6 +96,7 @@ obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec_$(BITS).o
>  obj-$(CONFIG_KEXEC_CORE)	+= relocate_kernel_$(BITS).o crash.o
>  obj-$(CONFIG_KEXEC_FILE)	+= kexec-bzimage64.o
>  obj-$(CONFIG_CRASH_DUMP)	+= crash_dump_$(BITS).o
> +obj-$(CONFIG_AMD_MEM_ENCRYPT)	+= crash_dump_encrypt.o
>  obj-y				+= kprobes/
>  obj-$(CONFIG_MODULES)		+= module.o
>  obj-$(CONFIG_DOUBLEFAULT)	+= doublefault.o
> diff --git a/arch/x86/kernel/crash_dump_encrypt.c b/arch/x86/kernel/crash_dump_encrypt.c
> new file mode 100644
> index 0000000..e44ef33
> --- /dev/null
> +++ b/arch/x86/kernel/crash_dump_encrypt.c
> @@ -0,0 +1,53 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + *	Memory preserving reboot related code.
> + *
> + *	Created by: Lianbo Jiang (lijiang@redhat.com)
> + *	Copyright (C) RedHat Corporation, 2018. All rights reserved
> + */
> +
> +#include <linux/errno.h>
> +#include <linux/crash_dump.h>
> +#include <linux/uaccess.h>
> +#include <linux/io.h>
> +
> +/**
> + * copy_oldmem_page_encrypted - copy one page from "oldmem encrypted"
> + * @pfn: page frame number to be copied
> + * @buf: target memory address for the copy; this can be in kernel address
> + *	space or user address space (see @userbuf)
> + * @csize: number of bytes to copy
> + * @offset: offset in bytes into the page (based on pfn) to begin the copy
> + * @userbuf: if set, @buf is in user address space, use copy_to_user(),
> + *	otherwise @buf is in kernel address space, use memcpy().
> + *
> + * Copy a page from "oldmem encrypted". For this page, there is no pte
> + * mapped in the current kernel. We stitch up a pte, similar to
> + * kmap_atomic.
> + */
> +
> +ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf,
> +		size_t csize, unsigned long offset, int userbuf)
> +{
> +	void  *vaddr;
> +
> +	if (!csize)
> +		return 0;
> +
> +	vaddr = (__force void *)ioremap_encrypted(pfn << PAGE_SHIFT,
> +						  PAGE_SIZE);
> +	if (!vaddr)
> +		return -ENOMEM;
> +
> +	if (userbuf) {
> +		if (copy_to_user((void __user *)buf, vaddr + offset, csize)) {
> +			iounmap((void __iomem *)vaddr);
> +			return -EFAULT;
> +		}
> +	} else
> +		memcpy(buf, vaddr + offset, csize);
> +
> +	set_iounmap_nonlazy();
> +	iounmap((void __iomem *)vaddr);
> +	return csize;
> +}
> diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
> index a45f0af..5200266 100644
> --- a/fs/proc/vmcore.c
> +++ b/fs/proc/vmcore.c
> @@ -25,6 +25,8 @@
>  #include <linux/uaccess.h>
>  #include <asm/io.h>
>  #include "internal.h"
> +#include <linux/mem_encrypt.h>
> +#include <asm/pgtable.h>
>  
>  /* List representing chunks of contiguous memory areas and their offsets in
>   * vmcore file.
> @@ -86,7 +88,8 @@ static int pfn_is_ram(unsigned long pfn)
>  
>  /* Reads a page from the oldmem device from given offset. */
>  static ssize_t read_from_oldmem(char *buf, size_t count,
> -				u64 *ppos, int userbuf)
> +				u64 *ppos, int userbuf,
> +				bool encrypted)
>  {
>  	unsigned long pfn, offset;
>  	size_t nr_bytes;
> @@ -108,8 +111,11 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
>  		if (pfn_is_ram(pfn) == 0)
>  			memset(buf, 0, nr_bytes);
>  		else {
> -			tmp = copy_oldmem_page(pfn, buf, nr_bytes,
> -						offset, userbuf);
> +			tmp = encrypted ? copy_oldmem_page_encrypted(pfn,
> +					    buf, nr_bytes, offset, userbuf)
> +					: copy_oldmem_page(pfn, buf, nr_bytes,
> +							   offset, userbuf);
> +
>  			if (tmp < 0)
>  				return tmp;
>  		}
> @@ -143,7 +149,7 @@ void __weak elfcorehdr_free(unsigned long long addr)
>   */
>  ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
>  {
> -	return read_from_oldmem(buf, count, ppos, 0);
> +	return read_from_oldmem(buf, count, ppos, 0, false);
>  }
>  
>  /*
> @@ -151,7 +157,7 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
>   */
>  ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
>  {
> -	return read_from_oldmem(buf, count, ppos, 0);
> +	return read_from_oldmem(buf, count, ppos, 0, sme_active());
>  }
>  
>  /*
> @@ -161,6 +167,7 @@ int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
>  				  unsigned long from, unsigned long pfn,
>  				  unsigned long size, pgprot_t prot)
>  {
> +	prot = pgprot_encrypted(prot);
>  	return remap_pfn_range(vma, from, pfn, size, prot);
>  }
>  
> @@ -235,7 +242,8 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
>  					    m->offset + m->size - *fpos,
>  					    buflen);
>  			start = m->paddr + *fpos - m->offset;
> -			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
> +			tmp = read_from_oldmem(buffer, tsz, &start, userbuf,
> +						sme_active());
>  			if (tmp < 0)
>  				return tmp;
>  			buflen -= tsz;
> diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
> index f7ac2aa..f3414ff 100644
> --- a/include/linux/crash_dump.h
> +++ b/include/linux/crash_dump.h
> @@ -25,6 +25,17 @@ extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
>  
>  extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
>  						unsigned long, int);
> +#ifdef CONFIG_AMD_MEM_ENCRYPT
> +extern ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf,
> +					   size_t csize, unsigned long offset,
> +					   int userbuf);
> +#else
> +static inline ssize_t copy_oldmem_page_encrypted(unsigned long pfn, char *buf,
> +					size_t csize, unsigned long offset,
> +					int userbuf) {
> +	return csize;
> +}
> +#endif
>  void vmcore_cleanup(void);
>  
>  /* Architecture code defines this if there are other possible ELF
> -- 
> 2.9.5
> 
> 
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec