[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <5e7e201d7e733e7b353b7446de701e0a2c6629f8.camel@intel.com>
Date: Mon, 18 Aug 2025 01:15:04 +0000
From: "Huang, Kai" <kai.huang@...el.com>
To: "bp@...en8.de" <bp@...en8.de>
CC: "kvm@...r.kernel.org" <kvm@...r.kernel.org>, "tglx@...utronix.de"
<tglx@...utronix.de>, "Hansen, Dave" <dave.hansen@...el.com>,
"thomas.lendacky@....com" <thomas.lendacky@....com>, "ashish.kalra@....com"
<ashish.kalra@....com>, "kas@...nel.org" <kas@...nel.org>, "Chatre, Reinette"
<reinette.chatre@...el.com>, "dwmw@...zon.co.uk" <dwmw@...zon.co.uk>,
"pbonzini@...hat.com" <pbonzini@...hat.com>, "seanjc@...gle.com"
<seanjc@...gle.com>, "Yamahata, Isaku" <isaku.yamahata@...el.com>,
"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"mingo@...hat.com" <mingo@...hat.com>, "nik.borisov@...e.com"
<nik.borisov@...e.com>, "hpa@...or.com" <hpa@...or.com>,
"peterz@...radead.org" <peterz@...radead.org>, "sagis@...gle.com"
<sagis@...gle.com>, "Chen, Farrah" <farrah.chen@...el.com>, "Edgecombe, Rick
P" <rick.p.edgecombe@...el.com>, "Gao, Chao" <chao.gao@...el.com>,
"x86@...nel.org" <x86@...nel.org>, "Williams, Dan J"
<dan.j.williams@...el.com>
Subject: Re: [PATCH v6 1/7] x86/kexec: Consolidate relocate_kernel() function
parameters
On Fri, 2025-08-15 at 12:46 +0200, Borislav Petkov wrote:
> On Thu, Aug 14, 2025 at 11:59:01AM +1200, Kai Huang wrote:
> > During kexec, the kernel jumps to the new kernel in relocate_kernel(),
> > which is implemented in assembly and both 32-bit and 64-bit have their
> > own version.
> >
> > Currently, for both 32-bit and 64-bit, the last two parameters of the
> > relocate_kernel() are both 'unsigned int' but actually they only convey
> > a boolean, i.e., one bit information. The 'unsigned int' has enough
> > space to carry two bits information therefore there's no need to pass
> > the two booleans in two separate 'unsigned int'.
> >
> > Consolidate the last two function parameters of relocate_kernel() into a
> > single 'unsigned int' and pass flags instead.
> >
> > Only consolidate the 64-bit version albeit the similar optimization can
> > be done for the 32-bit version too. Don't bother changing the 32-bit
> > version while it is working (since assembly code change is required).
> >
> > Signed-off-by: Kai Huang <kai.huang@...el.com>
> > Reviewed-by: Tom Lendacky <thomas.lendacky@....com>
> > ---
> >
> > v5 -> v6:
> > - Add Tom's RB.
> >
> > v4 -> v5:
> > - RELOC_KERNEL_HOST_MEM_ACTIVE -> RELOC_KERNEL_HOST_MEM_ENC_ACTIVE
> > (Tom)
> > - Add a comment to explain only RELOC_KERNEL_PRESERVE_CONTEXT is
> > restored after jumping back from peer kernel for preserved_context
> > kexec (pointed out by Tom).
> > - Use testb instead of testq when comparing the flag with R11 to save
> > 3 bytes (Hpa).
> >
> > v4:
> > - new patch
> >
> >
> > ---
> > arch/x86/include/asm/kexec.h | 12 ++++++++++--
> > arch/x86/kernel/machine_kexec_64.c | 22 +++++++++++++---------
> > arch/x86/kernel/relocate_kernel_64.S | 25 +++++++++++++++----------
> > 3 files changed, 38 insertions(+), 21 deletions(-)
>
> Reviewed-by: Borislav Petkov (AMD) <bp@...en8.de>
Thanks Boris!
Powered by blists - more mailing lists