From: Ammar Faizi <ammarfaizi2@gnuweeb.org>
To: "H. Peter Anvin" <hpa@zytor.com>
Cc: Dave Hansen <dave.hansen@intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
Xin Li <xin3.li@intel.com>, Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
Peter Zijlstra <peterz@infradead.org>,
x86 Mailing List <x86@kernel.org>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: the x86 sysret_rip test fails on the Intel FRED architecture
Date: Tue, 24 Jan 2023 06:43:02 +0700 [thread overview]
Message-ID: <Y88bhrDoPw5tOyKu@biznet-home.integral.gnuweeb.org> (raw)
In-Reply-To: <F554C5FE-5074-410A-B0B5-EFE983D57946@zytor.com>
On Mon, Jan 23, 2023 at 11:43:35AM -0800, H. Peter Anvin wrote:
> Good spotting. %rax needs to be marked clobbered, too.
Yeah, that 'syscall' variable should be using a "+a" constraint.
But anyway, I found something wrong with this. I was playing with your
code and I found it failed to assert that %r11 == rflags_sentinel on a
non-FRED system. It happens because "popf" doesn't set the %rflags
to the expected value.
I tried to simplify it like this:
pushq $0x200893
popf # This popf sets %rflags to 0x200a93, not to 0x200893.
pushf
popq %r11
# Now %r11 == 0x200a93,
# but the expected value is %r11 == 0x200893.
Looking into their bits:
(gdb) p/t 0x200893
$1 = 1000000000100010010011
(gdb) p/t 0x200a93
$2 = 1000000000101010010011
Align them to spot differences:
0x200893 = 0b1000000000100010010011
0x200a93 = 0b1000000000101010010011
^
Or just xor them to find the differences:
(gdb) p/x 0x200893 ^ 0x200a93
$3 = 0x200
** Checks my Intel SDM cheat sheets. **
Then, I was like "Oh, that's (1 << 9) a.k.a. IF. Of course we can't
change rflags[IF] from userspace!!!".
In short, we can't use 0x200893 as the rflags_sentinel value because it
clears the interrupt flag.
--
Ammar Faizi
next prev parent reply other threads:[~2023-01-23 23:43 UTC|newest]
Thread overview: 88+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <SA1PR11MB6734FA9139B9C9F6CC2ED123A8C59@SA1PR11MB6734.namprd11.prod.outlook.com>
2023-01-20 17:45 ` Dave Hansen
[not found] ` <eb81f7f2-d266-d999-b41a-e6eae086e731@citrix.com>
2023-01-20 20:50 ` H. Peter Anvin
2023-01-20 21:10 ` Andrew Cooper
2023-01-20 21:17 ` H. Peter Anvin
2023-01-20 21:29 ` Andrew Cooper
2023-01-21 4:59 ` H. Peter Anvin
2023-01-21 16:46 ` Dave Hansen
2023-01-21 21:47 ` Brian Gerst
2023-01-22 3:01 ` Li, Xin3
2023-01-22 3:28 ` H. Peter Anvin
2023-01-22 3:38 ` Li, Xin3
2023-01-22 4:34 ` Dave Hansen
2023-01-22 4:44 ` H. Peter Anvin
2023-01-22 8:22 ` Li, Xin3
2023-01-22 8:54 ` Ammar Faizi
2023-01-22 9:40 ` H. Peter Anvin
2023-01-22 23:45 ` H. Peter Anvin
2023-01-23 9:02 ` Ammar Faizi
2023-01-23 19:43 ` H. Peter Anvin
2023-01-23 23:43 ` Ammar Faizi [this message]
2023-01-23 23:58 ` H. Peter Anvin
2023-01-24 0:26 ` [RFC PATCH v1 0/2] selftests/x86: sysret_rip update for FRED system Ammar Faizi
2023-01-24 0:26 ` [RFC PATCH v1 1/2] selftests/x86: sysret_rip: Handle syscall in a " Ammar Faizi
2023-01-24 1:40 ` H. Peter Anvin
2023-01-24 2:31 ` Ammar Faizi
2023-01-26 20:08 ` Ammar Faizi
2023-02-15 9:17 ` Andrew Cooper
2023-02-15 10:29 ` Andrew Cooper
2023-02-15 10:44 ` Ammar Faizi
2023-02-15 10:42 ` Ammar Faizi
2023-01-26 20:16 ` Ammar Faizi
2023-01-24 0:26 ` [RFC PATCH v1 2/2] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-23 23:53 ` the x86 sysret_rip test fails on the Intel FRED architecture Andrew Cooper
2023-01-24 0:01 ` H. Peter Anvin
2023-01-24 2:27 ` [RFC PATCH v2 0/2] selftests/x86: sysret_rip update for FRED system Ammar Faizi
2023-01-24 2:27 ` [RFC PATCH v2 1/2] selftests/x86: sysret_rip: Handle syscall in a " Ammar Faizi
2023-01-24 5:44 ` H. Peter Anvin
2023-01-24 2:27 ` [RFC PATCH v2 2/2] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-24 6:16 ` H. Peter Anvin
2023-01-24 6:41 ` Ammar Faizi
2023-01-24 6:47 ` Ammar Faizi
2023-01-24 9:07 ` H. Peter Anvin
2023-01-24 9:12 ` Ammar Faizi
2023-01-24 10:09 ` [RFC PATCH v3 0/2] selftests/x86: sysret_rip update for FRED system Ammar Faizi
2023-01-24 10:09 ` [RFC PATCH v3 1/2] selftests/x86: sysret_rip: Handle syscall in a " Ammar Faizi
2023-01-24 10:09 ` [RFC PATCH v3 2/2] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-24 20:59 ` H. Peter Anvin
2023-01-25 3:29 ` Ammar Faizi
2023-01-24 21:32 ` [RFC PATCH v3 0/2] selftests/x86: sysret_rip update for FRED system Li, Xin3
2023-01-24 21:37 ` H. Peter Anvin
2023-01-24 23:20 ` Li, Xin3
2023-01-25 3:27 ` Ammar Faizi
2023-01-24 21:51 ` Andrew Cooper
2023-01-24 23:58 ` Li, Xin3
2023-01-25 3:22 ` [RFC PATCH v4 0/2] sysret_rip update for the Intel FRED architecture Ammar Faizi
2023-01-25 3:22 ` [RFC PATCH v4 1/2] selftests/x86: sysret_rip: Handle syscall in a FRED system Ammar Faizi
2023-01-25 3:37 ` Ammar Faizi
2023-01-25 3:44 ` Ammar Faizi
2023-01-25 3:22 ` [RFC PATCH v4 2/2] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-25 3:49 ` [RFC PATCH v5 0/2] sysret_rip update for the Intel FRED architecture Ammar Faizi
2023-01-25 3:49 ` [RFC PATCH v5 1/2] selftests/x86: sysret_rip: Handle syscall in a FRED system Ammar Faizi
2023-01-25 8:39 ` H. Peter Anvin
2023-01-25 8:53 ` Ammar Faizi
2023-01-25 9:57 ` Ammar Faizi
2023-01-25 10:01 ` Ammar Faizi
2023-01-25 10:17 ` H. Peter Anvin
2023-01-25 11:37 ` Ammar Faizi
2023-01-25 17:25 ` H. Peter Anvin
2023-01-25 3:49 ` [RFC PATCH v5 2/2] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-25 8:22 ` [RFC PATCH v5 0/2] sysret_rip update for the Intel FRED architecture Li, Xin3
2023-01-25 8:32 ` Ammar Faizi
2023-01-25 17:07 ` Li, Xin3
2023-01-25 17:24 ` H. Peter Anvin
2023-01-25 17:41 ` Ammar Faizi
2023-01-25 17:48 ` Li, Xin3
2023-02-15 7:42 ` Li, Xin3
2023-02-15 7:51 ` Ammar Faizi
2023-02-18 4:27 ` Ammar Faizi
2023-02-18 4:51 ` H. Peter Anvin
2023-01-25 21:17 ` [RFC PATCH v6 0/3] " Ammar Faizi
2023-01-25 21:17 ` [RFC PATCH v6 1/3] selftests/x86: sysret_rip: Handle syscall in a FRED system Ammar Faizi
2023-01-25 23:01 ` Ammar Faizi
2023-01-25 21:17 ` [RFC PATCH v6 2/3] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-25 21:17 ` [RFC PATCH v6 3/3] selftests/x86: sysret_rip: Test opportunistic SYSRET Ammar Faizi
2023-01-25 23:24 ` [RFC PATCH v7 0/3] sysret_rip update for the Intel FRED architecture Ammar Faizi
2023-01-25 23:24 ` [RFC PATCH v7 1/3] selftests/x86: sysret_rip: Handle syscall in a FRED system Ammar Faizi
2023-01-25 23:24 ` [RFC PATCH v7 2/3] selftests/x86: sysret_rip: Add more syscall tests with respect to `%rcx` and `%r11` Ammar Faizi
2023-01-25 23:24 ` [RFC PATCH v7 3/3] selftests/x86: sysret_rip: Test SYSRET with a signal handler Ammar Faizi
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=Y88bhrDoPw5tOyKu@biznet-home.integral.gnuweeb.org \
--to=ammarfaizi2@gnuweeb.org \
--cc=bp@alien8.de \
--cc=dave.hansen@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=hpa@zytor.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
--cc=tglx@linutronix.de \
--cc=x86@kernel.org \
--cc=xin3.li@intel.com \
/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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®