Received-SPF: pass (google.com: domain of linux-kernel+bounces-26013-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Message-ID: <fa1e3873-6218-461b-85fa-1ff353380532@suse.com>
Date: Mon, 15 Jan 2024 15:19:43 +0200
Precedence: bulk
MIME-Version: 1.0
User-Agent: Mozilla Thunderbird
Subject: Re: [PATCHv5 16/16] x86/acpi: Add support for CPU offlining for ACPI
 MADT wakeup method
Content-Language: en-US
To: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
 Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
 Borislav Petkov <bp@alien8.de>, Dave Hansen <dave.hansen@linux.intel.com>,
 x86@kernel.org
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
 Peter Zijlstra <peterz@infradead.org>,
 Adrian Hunter <adrian.hunter@intel.com>,
 Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>,
 Elena Reshetova <elena.reshetova@intel.com>,
 Jun Nakajima <jun.nakajima@intel.com>,
 Rick Edgecombe <rick.p.edgecombe@intel.com>,
 Tom Lendacky <thomas.lendacky@amd.com>, "Kalra, Ashish"
 <ashish.kalra@amd.com>, Sean Christopherson <seanjc@google.com>,
 "Huang, Kai" <kai.huang@intel.com>, Baoquan He <bhe@redhat.com>,
 kexec@lists.infradead.org, linux-coco@lists.linux.dev,
 linux-kernel@vger.kernel.org
References: <20231222235209.32143-1-kirill.shutemov@linux.intel.com>
 <20231222235209.32143-17-kirill.shutemov@linux.intel.com>
From: Nikolay Borisov <nik.borisov@suse.com>
In-Reply-To: <20231222235209.32143-17-kirill.shutemov@linux.intel.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit


On 23.12.23 г. 1:52 ч., Kirill A. Shutemov wrote:
> MADT Multiprocessor Wakeup structure version 1 brings support of CPU
> offlining: BIOS provides a reset vector where the CPU has to jump to
> for offlining itself. The new TEST mailbox command can be used to test
> whether the CPU offlined itself which means the BIOS has control over
> the CPU and can online it again via the ACPI MADT wakeup method.
> 
> Add CPU offling support for the ACPI MADT wakeup method by implementing
> custom cpu_die(), play_dead() and stop_this_cpu() SMP operations.
> 
> CPU offlining makes is possible to hand over secondary CPUs over kexec,
> not limiting the second kernel to a single CPU.
> 
> The change conforms to the approved ACPI spec change proposal. See the
> Link.
> 
> Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
> Link: https://lore.kernel.org/all/13356251.uLZWGnKmhe@kreacher
> ---
>   arch/x86/include/asm/acpi.h          |   2 +
>   arch/x86/kernel/acpi/Makefile        |   2 +-
>   arch/x86/kernel/acpi/madt_playdead.S |  29 +++++
>   arch/x86/kernel/acpi/madt_wakeup.c   | 184 ++++++++++++++++++++++++++-
>   include/acpi/actbl2.h                |  15 ++-
>   5 files changed, 228 insertions(+), 4 deletions(-)
>   create mode 100644 arch/x86/kernel/acpi/madt_playdead.S
> 
> diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
> index 2625b915ae7f..021cafa214c2 100644
> --- a/arch/x86/include/asm/acpi.h
> +++ b/arch/x86/include/asm/acpi.h
> @@ -81,6 +81,8 @@ union acpi_subtable_headers;
>   int __init acpi_parse_mp_wake(union acpi_subtable_headers *header,
>   			      const unsigned long end);
>   
> +void asm_acpi_mp_play_dead(u64 reset_vector, u64 pgd_pa);
> +
>   /*
>    * Check if the CPU can handle C2 and deeper
>    */
> diff --git a/arch/x86/kernel/acpi/Makefile b/arch/x86/kernel/acpi/Makefile
> index 8c7329c88a75..37b1f28846de 100644
> --- a/arch/x86/kernel/acpi/Makefile
> +++ b/arch/x86/kernel/acpi/Makefile
> @@ -4,7 +4,7 @@ obj-$(CONFIG_ACPI)			+= boot.o
>   obj-$(CONFIG_ACPI_SLEEP)		+= sleep.o wakeup_$(BITS).o
>   obj-$(CONFIG_ACPI_APEI)			+= apei.o
>   obj-$(CONFIG_ACPI_CPPC_LIB)		+= cppc.o
> -obj-$(CONFIG_X86_ACPI_MADT_WAKEUP)	+= madt_wakeup.o
> +obj-$(CONFIG_X86_ACPI_MADT_WAKEUP)	+= madt_wakeup.o madt_playdead.o
>   
>   ifneq ($(CONFIG_ACPI_PROCESSOR),)
>   obj-y					+= cstate.o
> diff --git a/arch/x86/kernel/acpi/madt_playdead.S b/arch/x86/kernel/acpi/madt_playdead.S
> new file mode 100644
> index 000000000000..e48049959513
> --- /dev/null
> +++ b/arch/x86/kernel/acpi/madt_playdead.S
> @@ -0,0 +1,29 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +#include <linux/linkage.h>
> +#include <asm/nospec-branch.h>
> +#include <asm/page_types.h>
> +#include <asm/processor-flags.h>
> +
> +	.text
> +	.align PAGE_SIZE
> +
> +/*
> + * asm_acpi_mp_play_dead() - Hand over control of the CPU to the BIOS
> + *
> + * rdi: Address of the ACPI MADT MPWK ResetVector
> + * rsi: PGD of the identity mapping
> + */
> +SYM_FUNC_START(asm_acpi_mp_play_dead)
> +	/* Turn off global entries. Following CR3 write will flush them. */
> +	movq	%cr4, %rdx
> +	andq	$~(X86_CR4_PGE), %rdx
> +	movq	%rdx, %cr4
> +
> +	/* Switch to identity mapping */
> +	movq	%rsi, %rax
> +	movq	%rax, %cr3

nit: Can't you move directly to cr3

> +
> +	/* Jump to reset vector */
> +	ANNOTATE_RETPOLINE_SAFE
> +	jmp	*%rdi
> +SYM_FUNC_END(asm_acpi_mp_play_dead)

<snip>