linux-kernel - Re: [PATCHv2] x86/trampoline: Bypass compat mode in trampoline

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Tue, 9 Jan 2024 00:58:26 +0300
From: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
To: Sean Christopherson <seanjc@...gle.com>
Cc: Thomas Gleixner <tglx@...utronix.de>, Ingo Molnar <mingo@...hat.com>,
	Borislav Petkov <bp@...en8.de>,
	Dave Hansen <dave.hansen@...ux.intel.com>, x86@...nel.org,
	"H. Peter Anvin" <hpa@...or.com>, linux-kernel@...r.kernel.org,
	Andi Kleen <ak@...ux.intel.com>
Subject: Re: [PATCHv2] x86/trampoline: Bypass compat mode in
 trampoline_start64() if not needed

On Mon, Jan 08, 2024 at 08:18:55AM -0800, Sean Christopherson wrote:
> On Sun, Jan 07, 2024, Kirill A. Shutemov wrote:
> > @@ -220,6 +222,33 @@ SYM_CODE_START(trampoline_start64)
> >  	lidt	tr_idt(%rip)
> >  	lgdt	tr_gdt64(%rip)
> >  
> > +	/* Check if paging mode has to be changed */
> > +	movq	%cr4, %rax
> > +	xorq	tr_cr4(%rip), %rax
> 
> This is buggy, tr_cr4 is only 4 bytes.  And even if tr_cr4 were 8 bytes, the reason
> why nothing showed up in testing is also why only 4 bytes need to be XOR'd: the
> upper 32 bits of the result are never consumed.

Oh. Good catch. Will fix.

tr_cr4 will need to be changed to 8 bytes soonish. FRED uses bit 32 of the
register.

> > +	andq	$X86_CR4_LA57, %rax
> 
> Nit, this can be TEST instead of AND, e.g. I was looking to see if RAX was used
> anywhere in the flow.  And in theory it's possible a CPU could support uop fusing
> for TEST+Jcc but not AND+Jcc, cause shaving a cycle in this code is obviously
> super important ;-)
> 
> And as above, testl, not testq.

Fair enough. Will use testl.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov