Linux-Sgx Archive on lore.kernel.org
 help / color / Atom feed
From: Jarkko Sakkinen <jarkko@kernel.org>
To: Hillf Danton <hdanton@sina.com>
Cc: x86@kernel.org, linux-sgx@vger.kernel.org,
	linux-kernel@vger.kernel.org,
	Sean Christopherson <sean.j.christopherson@intel.com>,
	Jethro Beekman <jethro@fortanix.com>,
	Serge Ayoun <serge.ayoun@intel.com>,
	akpm@linux-foundation.org
Subject: Re: [PATCH v41 06/24] x86/mm: x86/sgx: Signal SIGSEGV with PF_SGX
Date: Tue, 17 Nov 2020 20:12:58 +0200
Message-ID: <20201117181258.GE8524@kernel.org> (raw)
In-Reply-To: <20201114090708.8684-1-hdanton@sina.com>

On Sat, Nov 14, 2020 at 05:07:08PM +0800, Hillf Danton wrote:
> On Fri, 13 Nov 2020 00:01:17 +0200 
> > 
> > From: Sean Christopherson <sean.j.christopherson@intel.com>
> > 
> > The x86 architecture has a set of page fault error codes.  These indicate
> > things like whether the fault occurred from a write, or whether it
> > originated in userspace.
> > 
> > The SGX hardware architecture has its own per-page memory management
> > metadata (EPCM) [*] and hardware which is separate from the normal x86 MMU.
> > The architecture has a new page fault error code: PF_SGX.  This new error
> > code bit is set whenever a page fault occurs as the result of the SGX MMU.
> > 
> > These faults occur for a variety of reasons.  For instance, an access
> > attempt to enclave memory from outside the enclave causes a PF_SGX fault.
> > PF_SGX would also be set for permission conflicts, such as if a write to an
> > enclave page occurs and the page is marked read-write in the x86 page
> > tables but is read-only in the EPCM.
> > 
> > These faults do not always indicate errors, though.  SGX pages are
> > encrypted with a key that is destroyed at hardware reset, including
> > suspend. Throwing a SIGSEGV allows user space software to react and recover
> > when these events occur.
> > 
> > Include PF_SGX in the PF error codes list and throw SIGSEGV when it is
> > encountered.
> > 
> > [*] Intel SDM: 36.5.1 Enclave Page Cache Map (EPCM)
> > 
> > Acked-by: Jethro Beekman <jethro@fortanix.com> # v40
> > # Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
> > Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
> > ---
> >  arch/x86/include/asm/trap_pf.h |  1 +
> >  arch/x86/mm/fault.c            | 12 ++++++++++++
> >  2 files changed, 13 insertions(+)
> > 
> > diff --git a/arch/x86/include/asm/trap_pf.h b/arch/x86/include/asm/trap_pf.h
> > index 305bc1214aef..1794777b2a85 100644
> > --- a/arch/x86/include/asm/trap_pf.h
> > +++ b/arch/x86/include/asm/trap_pf.h
> > @@ -19,6 +19,7 @@ enum x86_pf_error_code {
> >  	X86_PF_RSVD	=		1 << 3,
> >  	X86_PF_INSTR	=		1 << 4,
> >  	X86_PF_PK	=		1 << 5,
> > +	X86_PF_SGX	=		1 << 15,
> >  };
> >  
> >  #endif /* _ASM_X86_TRAP_PF_H */
> > diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
> > index 82bf37a5c9ec..9339fee83784 100644
> > --- a/arch/x86/mm/fault.c
> > +++ b/arch/x86/mm/fault.c
> > @@ -1101,6 +1101,18 @@ access_error(unsigned long error_code, struct vm_area_struct *vma)
> >  	if (error_code & X86_PF_PK)
> >  		return 1;
> >  
> > +	/*
> > +	 * SGX hardware blocked the access.  This usually happens
> > +	 * when the enclave memory contents have been destroyed, like
> > +	 * after a suspend/resume cycle. In any case, the kernel can't
> > +	 * fix the cause of the fault.  Handle the fault as an access
> > +	 * error even in cases where no actual access violation
> > +	 * occurred.  This allows userspace to rebuild the enclave in
> > +	 * response to the signal.
> > +	 */
> 
> Given SIGSEGV, it helps much understand PF_SGX to specify the rebuild
> in userspace a bit more.

I'm sorry but I'm not exactly sure what you are suggesting.

/Jarkko

  parent reply index

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-11-12 22:01 [PATCH v41 00/24] Intel SGX foundations Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 01/24] x86/sgx: Add SGX architectural data structures Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 02/24] x86/sgx: Add wrappers for ENCLS functions Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 03/24] x86/cpufeatures: x86/msr: Add Intel SGX hardware bits Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 04/24] x86/cpufeatures: x86/msr: Add Intel SGX Launch Control " Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 05/24] x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Jarkko Sakkinen
2020-11-16 22:25   ` [PATCH] x86/sgx: clarify 'laundry_list' locking Dave Hansen
2020-11-17 19:29     ` Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 06/24] x86/mm: x86/sgx: Signal SIGSEGV with PF_SGX Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 07/24] x86/cpu/intel: Detect SGX support Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 08/24] x86/cpu/intel: Add nosgx kernel parameter Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 09/24] x86/sgx: Add SGX page allocator functions Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 10/24] mm: Add 'mprotect' hook to struct vm_operations_struct Jarkko Sakkinen
2020-11-13 10:25   ` Mel Gorman
2020-11-17 18:16     ` Jarkko Sakkinen
2020-11-15 17:08   ` Dr. Greg
2020-11-15 17:32   ` Matthew Wilcox
2020-11-15 18:36     ` Dave Hansen
2020-11-16 10:09       ` Mel Gorman
2020-11-17 19:15         ` Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 11/24] x86/sgx: Add SGX misc driver interface Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 12/24] x86/sgx: Add SGX_IOC_ENCLAVE_CREATE Jarkko Sakkinen
     [not found]   ` <20201115044044.11040-1-hdanton@sina.com>
2020-11-17 17:35     ` Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 13/24] x86/sgx: Add SGX_IOC_ENCLAVE_ADD_PAGES Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 14/24] x86/sgx: Add SGX_IOC_ENCLAVE_INIT Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 15/24] x86/sgx: Add SGX_IOC_ENCLAVE_PROVISION Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 16/24] x86/vdso: Add support for exception fixup in vDSO functions Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 17/24] x86/fault: Add helper function to sanitize error code Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 18/24] x86/traps: Attempt to fixup exceptions in vDSO before signaling Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 19/24] x86/vdso: Implement a vDSO for Intel SGX enclave call Jarkko Sakkinen
2020-11-17 13:14   ` Borislav Petkov
2020-11-17 19:41     ` Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 20/24] selftests/x86: Add a selftest for SGX Jarkko Sakkinen
2020-11-16 18:19   ` Shuah Khan
2020-11-17 13:22     ` Borislav Petkov
2020-11-17 19:42     ` Jarkko Sakkinen
2020-11-17 17:26   ` Borislav Petkov
2020-11-17 21:27     ` Jarkko Sakkinen
2020-11-17 21:38     ` Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 21/24] x86/sgx: Add a page reclaimer Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 22/24] x86/sgx: Add ptrace() support for the SGX driver Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 23/24] docs: x86/sgx: Document SGX kernel architecture Jarkko Sakkinen
2020-11-12 22:01 ` [PATCH v41 24/24] x86/sgx: Update MAINTAINERS Jarkko Sakkinen
2020-11-16 16:55 ` [PATCH v41 00/24] Intel SGX foundations Borislav Petkov
2020-11-16 17:21   ` Dave Hansen
2020-11-16 17:28     ` Borislav Petkov
2020-11-17 19:20       ` Jarkko Sakkinen
     [not found] ` <20201114084211.5284-1-hdanton@sina.com>
2020-11-16 18:33   ` [PATCH v41 05/24] x86/sgx: Initialize metadata for Enclave Page Cache (EPC) sections Dave Hansen
     [not found] ` <20201115040127.7804-1-hdanton@sina.com>
2020-11-16 21:11   ` [PATCH v41 11/24] x86/sgx: Add SGX misc driver interface Dave Hansen
     [not found] ` <20201114090708.8684-1-hdanton@sina.com>
2020-11-17 18:12   ` Jarkko Sakkinen [this message]
     [not found] ` <20201114093256.7800-1-hdanton@sina.com>
2020-11-17 18:14   ` [PATCH v41 09/24] x86/sgx: Add SGX page allocator functions Jarkko Sakkinen
     [not found] ` <20201115030548.1572-1-hdanton@sina.com>
2020-11-17 18:22   ` [PATCH v41 10/24] mm: Add 'mprotect' hook to struct vm_operations_struct Jarkko Sakkinen
2020-12-15  5:38 ` [PATCH v41 00/24] Intel SGX foundations Hui, Chunyang
2020-12-15  5:43 ` Hui, Chunyang
2020-12-15 15:58   ` Jarkko Sakkinen

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=20201117181258.GE8524@kernel.org \
    --to=jarkko@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=hdanton@sina.com \
    --cc=jethro@fortanix.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-sgx@vger.kernel.org \
    --cc=sean.j.christopherson@intel.com \
    --cc=serge.ayoun@intel.com \
    --cc=x86@kernel.org \
    /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

Linux-Sgx Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-sgx/0 linux-sgx/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-sgx linux-sgx/ https://lore.kernel.org/linux-sgx \
		linux-sgx@vger.kernel.org
	public-inbox-index linux-sgx

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-sgx


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git