From: Uros Bizjak <ubizjak@gmail.com>
To: Peter Zijlstra <peterz@infradead.org>, x86@kernel.org
Cc: kys@microsoft.com, haiyangz@microsoft.com, wei.liu@kernel.org,
decui@microsoft.com, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, dave.hansen@linux.intel.com, hpa@zytor.com,
jpoimboe@kernel.org, pawan.kumar.gupta@linux.intel.com,
seanjc@google.com, pbonzini@redhat.com, ardb@kernel.org,
kees@kernel.org, Arnd Bergmann <arnd@arndb.de>,
gregkh@linuxfoundation.org, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
linux-efi@vger.kernel.org, samitolvanen@google.com,
ojeda@kernel.org
Subject: Re: [PATCH 4/6] x86,hyperv: Clean up hv_do_hypercall()
Date: Mon, 14 Apr 2025 16:06:41 +0200 [thread overview]
Message-ID: <01c65464-8535-28d8-a9b5-eb4f90114e2d@gmail.com> (raw)
In-Reply-To: <20250414113754.285564821@infradead.org>
On 14. 04. 25 13:11, Peter Zijlstra wrote:
> What used to be a simple few instructions has turned into a giant mess
> (for x86_64). Not only does it use static_branch wrong, it mixes it
> with dynamic branches for no apparent reason.
>
> Notably it uses static_branch through an out-of-line function call,
> which completely defeats the purpose, since instead of a simple
> JMP/NOP site, you get a CALL+RET+TEST+Jcc sequence in return, which is
> absolutely idiotic.
>
> Add to that a dynamic test of hyperv_paravisor_present, something
> which is set once and never changed.
>
> Replace all this idiocy with a single direct function call to the
> right hypercall variant.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
> arch/x86/hyperv/hv_init.c | 21 ++++++
> arch/x86/hyperv/ivm.c | 14 ++++
> arch/x86/include/asm/mshyperv.h | 137 +++++++++++-----------------------------
> arch/x86/kernel/cpu/mshyperv.c | 18 +++--
> 4 files changed, 88 insertions(+), 102 deletions(-)
>
> --- a/arch/x86/hyperv/hv_init.c
> +++ b/arch/x86/hyperv/hv_init.c
> @@ -35,7 +35,28 @@
> #include <linux/highmem.h>
>
> void *hv_hypercall_pg;
> +
> +#ifdef CONFIG_X86_64
> +u64 hv_pg_hypercall(u64 control, u64 param1, u64 param2)
> +{
> + u64 hv_status;
> +
> + if (!hv_hypercall_pg)
> + return U64_MAX;
> +
> + register u64 __r8 asm("r8") = param2;
> + asm volatile (CALL_NOSPEC
> + : "=a" (hv_status), ASM_CALL_CONSTRAINT,
> + "+c" (control), "+d" (param1)
> + : "r" (__r8),
r8 is call-clobbered register, so you should use "+r" (__r8) to properly
clobber it:
"+c" (control), "+d" (param1), "+r" (__r8)
: THUNK_TARGET(hv_hypercall_pg)
> + : "cc", "memory", "r9", "r10", "r11");
> +
> + return hv_status;
> +}
> +#else
> EXPORT_SYMBOL_GPL(hv_hypercall_pg);
> +#endif
>
> union hv_ghcb * __percpu *hv_ghcb_pg;
>
> --- a/arch/x86/hyperv/ivm.c
> +++ b/arch/x86/hyperv/ivm.c
> @@ -376,6 +376,20 @@ int hv_snp_boot_ap(u32 cpu, unsigned lon
> return ret;
> }
>
> +u64 hv_snp_hypercall(u64 control, u64 param1, u64 param2)
> +{
> + u64 hv_status;
> +
> + register u64 __r8 asm("r8") = param2;
> + asm volatile("vmmcall"
> + : "=a" (hv_status), ASM_CALL_CONSTRAINT,
> + "+c" (control), "+d" (param1)
> + : "r" (__r8)
Also here:
"+c" (control), "+d" (param1), "+r" (__r8)
:
> + : "cc", "memory", "r9", "r10", "r11");
> +
> + return hv_status;
> +}
Uros.
next prev parent reply other threads:[~2025-04-14 14:06 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-04-14 11:11 [PATCH 0/6] objtool: Detect and warn about indirect calls in __nocfi functions Peter Zijlstra
2025-04-14 11:11 ` [PATCH 1/6] x86/nospec: JMP_NOSPEC Peter Zijlstra
2025-04-14 11:11 ` [PATCH 2/6] x86/kvm/emulate: Implement test_cc() in C Peter Zijlstra
2025-04-14 11:11 ` [PATCH 3/6] x86/kvm/emulate: Avoid RET for fastops Peter Zijlstra
2025-04-14 22:36 ` Josh Poimboeuf
2025-04-15 7:44 ` Peter Zijlstra
2025-04-15 14:39 ` Josh Poimboeuf
2025-04-16 8:38 ` Peter Zijlstra
2025-04-26 10:01 ` Peter Zijlstra
2025-04-28 17:13 ` Sean Christopherson
2025-04-29 10:09 ` Peter Zijlstra
2025-04-29 14:05 ` Sean Christopherson
2025-04-29 14:46 ` Peter Zijlstra
2025-04-29 17:16 ` Sean Christopherson
2025-04-14 11:11 ` [PATCH 4/6] x86,hyperv: Clean up hv_do_hypercall() Peter Zijlstra
2025-04-14 11:47 ` Peter Zijlstra
2025-04-14 14:06 ` Uros Bizjak [this message]
2025-04-14 14:08 ` Peter Zijlstra
2025-04-21 18:27 ` Michael Kelley
2025-04-25 13:50 ` Peter Zijlstra
2025-04-29 15:18 ` Peter Zijlstra
2025-04-29 20:36 ` Michael Kelley
2025-04-14 11:11 ` [PATCH 5/6] x86_64,hyperv: Use direct call to hypercall-page Peter Zijlstra
2025-04-21 18:28 ` Michael Kelley
2025-04-25 14:03 ` Peter Zijlstra
2025-04-25 14:32 ` Michael Kelley
2025-04-27 3:58 ` Michael Kelley
2025-04-29 15:19 ` Peter Zijlstra
2025-04-14 11:11 ` [PATCH 6/6] objtool: Validate kCFI calls Peter Zijlstra
2025-04-14 23:43 ` Josh Poimboeuf
2025-04-29 16:10 ` Peter Zijlstra
2025-04-29 16:18 ` Peter Zijlstra
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=01c65464-8535-28d8-a9b5-eb4f90114e2d@gmail.com \
--to=ubizjak@gmail.com \
--cc=ardb@kernel.org \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=dave.hansen@linux.intel.com \
--cc=decui@microsoft.com \
--cc=gregkh@linuxfoundation.org \
--cc=haiyangz@microsoft.com \
--cc=hpa@zytor.com \
--cc=jpoimboe@kernel.org \
--cc=kees@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=kys@microsoft.com \
--cc=linux-efi@vger.kernel.org \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=ojeda@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=samitolvanen@google.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=wei.liu@kernel.org \
--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
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