LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
To: Dan Williams <dan.j.williams@intel.com>, akpm@linux-foundation.org
Cc: stable@vger.kernel.org, Piotr Balcer <piotr.balcer@intel.com>,
	Yan Ma <yan.ma@intel.com>,
	Chandan Rajendra <chandan@linux.ibm.com>, Jan Kara <jack@suse.cz>,
	Matthew Wilcox <willy@infradead.org>,
	Souptick Joarder <jrdr.linux@gmail.com>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	linux-fsdevel@vger.kernel.org
Subject: Re: [PATCH] mm/huge_memory: Fix vmf_insert_pfn_{pmd, pud}() crash, handle unaligned addresses
Date: Fri, 10 May 2019 16:02:50 -0500	[thread overview]
Message-ID: <87ef56c9ad.fsf@linux.ibm.com> (raw)
In-Reply-To: <155741946350.372037.11148198430068238140.stgit@dwillia2-desk3.amr.corp.intel.com>

Dan Williams <dan.j.williams@intel.com> writes:

> Starting with commit c6f3c5ee40c1 "mm/huge_memory.c: fix modifying of
> page protection by insert_pfn_pmd()" vmf_insert_pfn_pmd() internally
> calls pmdp_set_access_flags(). That helper enforces a pmd aligned
> @address argument via VM_BUG_ON() assertion.
>
> Update the implementation to take a 'struct vm_fault' argument directly
> and apply the address alignment fixup internally to fix crash signatures
> like:
>
>     kernel BUG at arch/x86/mm/pgtable.c:515!
>     invalid opcode: 0000 [#1] SMP NOPTI
>     CPU: 51 PID: 43713 Comm: java Tainted: G           OE     4.19.35 #1
>     [..]
>     RIP: 0010:pmdp_set_access_flags+0x48/0x50
>     [..]
>     Call Trace:
>      vmf_insert_pfn_pmd+0x198/0x350
>      dax_iomap_fault+0xe82/0x1190
>      ext4_dax_huge_fault+0x103/0x1f0
>      ? __switch_to_asm+0x40/0x70
>      __handle_mm_fault+0x3f6/0x1370
>      ? __switch_to_asm+0x34/0x70
>      ? __switch_to_asm+0x40/0x70
>      handle_mm_fault+0xda/0x200
>      __do_page_fault+0x249/0x4f0
>      do_page_fault+0x32/0x110
>      ? page_fault+0x8/0x30
>      page_fault+0x1e/0x30
>

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>

> Cc: <stable@vger.kernel.org>
> Fixes: c6f3c5ee40c1 ("mm/huge_memory.c: fix modifying of page protection by insert_pfn_pmd()")
> Reported-by: Piotr Balcer <piotr.balcer@intel.com>
> Tested-by: Yan Ma <yan.ma@intel.com>
> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
> Cc: Chandan Rajendra <chandan@linux.ibm.com>
> Cc: Jan Kara <jack@suse.cz>
> Cc: Andrew Morton <akpm@linux-foundation.org>
> Cc: Matthew Wilcox <willy@infradead.org>
> Cc: Souptick Joarder <jrdr.linux@gmail.com>
> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
> ---
>
>  drivers/dax/device.c    |    6 ++----
>  fs/dax.c                |    6 ++----
>  include/linux/huge_mm.h |    6 ++----
>  mm/huge_memory.c        |   16 ++++++++++------
>  4 files changed, 16 insertions(+), 18 deletions(-)
>
> diff --git a/drivers/dax/device.c b/drivers/dax/device.c
> index e428468ab661..996d68ff992a 100644
> --- a/drivers/dax/device.c
> +++ b/drivers/dax/device.c
> @@ -184,8 +184,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
>  
>  	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
>  
> -	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd, *pfn,
> -			vmf->flags & FAULT_FLAG_WRITE);
> +	return vmf_insert_pfn_pmd(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
>  }
>  
>  #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
> @@ -235,8 +234,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
>  
>  	*pfn = phys_to_pfn_t(phys, dax_region->pfn_flags);
>  
> -	return vmf_insert_pfn_pud(vmf->vma, vmf->address, vmf->pud, *pfn,
> -			vmf->flags & FAULT_FLAG_WRITE);
> +	return vmf_insert_pfn_pud(vmf, *pfn, vmf->flags & FAULT_FLAG_WRITE);
>  }
>  #else
>  static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
> diff --git a/fs/dax.c b/fs/dax.c
> index e5e54da1715f..83009875308c 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1575,8 +1575,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
>  		}
>  
>  		trace_dax_pmd_insert_mapping(inode, vmf, PMD_SIZE, pfn, entry);
> -		result = vmf_insert_pfn_pmd(vma, vmf->address, vmf->pmd, pfn,
> -					    write);
> +		result = vmf_insert_pfn_pmd(vmf, pfn, write);
>  		break;
>  	case IOMAP_UNWRITTEN:
>  	case IOMAP_HOLE:
> @@ -1686,8 +1685,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
>  		ret = vmf_insert_mixed_mkwrite(vmf->vma, vmf->address, pfn);
>  #ifdef CONFIG_FS_DAX_PMD
>  	else if (order == PMD_ORDER)
> -		ret = vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
> -			pfn, true);
> +		ret = vmf_insert_pfn_pmd(vmf, pfn, FAULT_FLAG_WRITE);
>  #endif
>  	else
>  		ret = VM_FAULT_FALLBACK;
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index 381e872bfde0..7cd5c150c21d 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -47,10 +47,8 @@ extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
>  extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
>  			unsigned long addr, pgprot_t newprot,
>  			int prot_numa);
> -vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
> -			pmd_t *pmd, pfn_t pfn, bool write);
> -vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
> -			pud_t *pud, pfn_t pfn, bool write);
> +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
> +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
>  enum transparent_hugepage_flag {
>  	TRANSPARENT_HUGEPAGE_FLAG,
>  	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index 165ea46bf149..4310c6e9e5a3 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -793,11 +793,13 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
>  		pte_free(mm, pgtable);
>  }
>  
> -vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
> -			pmd_t *pmd, pfn_t pfn, bool write)
> +vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
>  {
> +	unsigned long addr = vmf->address & PMD_MASK;
> +	struct vm_area_struct *vma = vmf->vma;
>  	pgprot_t pgprot = vma->vm_page_prot;
>  	pgtable_t pgtable = NULL;
> +
>  	/*
>  	 * If we had pmd_special, we could avoid all these restrictions,
>  	 * but we need to be consistent with PTEs and architectures that
> @@ -820,7 +822,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
>  
>  	track_pfn_insert(vma, &pgprot, pfn);
>  
> -	insert_pfn_pmd(vma, addr, pmd, pfn, pgprot, write, pgtable);
> +	insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable);
>  	return VM_FAULT_NOPAGE;
>  }
>  EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd);
> @@ -869,10 +871,12 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
>  	spin_unlock(ptl);
>  }
>  
> -vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
> -			pud_t *pud, pfn_t pfn, bool write)
> +vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
>  {
> +	unsigned long addr = vmf->address & PUD_MASK;
> +	struct vm_area_struct *vma = vmf->vma;
>  	pgprot_t pgprot = vma->vm_page_prot;
> +
>  	/*
>  	 * If we had pud_special, we could avoid all these restrictions,
>  	 * but we need to be consistent with PTEs and architectures that
> @@ -889,7 +893,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
>  
>  	track_pfn_insert(vma, &pgprot, pfn);
>  
> -	insert_pfn_pud(vma, addr, pud, pfn, pgprot, write);
> +	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
>  	return VM_FAULT_NOPAGE;
>  }
>  EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud);


      parent reply	other threads:[~2019-05-10 21:03 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-09 16:31 Dan Williams
2019-05-09 17:42 ` Matthew Wilcox
2019-05-09 19:32 ` Jan Kara
2019-05-10  5:42 ` Pankaj Gupta
2019-05-10 21:02 ` Aneesh Kumar K.V [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=87ef56c9ad.fsf@linux.ibm.com \
    --to=aneesh.kumar@linux.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=chandan@linux.ibm.com \
    --cc=dan.j.williams@intel.com \
    --cc=jack@suse.cz \
    --cc=jrdr.linux@gmail.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=piotr.balcer@intel.com \
    --cc=stable@vger.kernel.org \
    --cc=willy@infradead.org \
    --cc=yan.ma@intel.com \
    --subject='Re: [PATCH] mm/huge_memory: Fix vmf_insert_pfn_{pmd, pud}() crash, handle unaligned addresses' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).