Message-Id: <6596E9D7-E0B9-4AEA-BC39-2A637B401DC1@zytor.com>
Date: Wed, 22 Oct 2025 18:20:43 -0700
From: Xin Li <xin@...or.com>
To: linux-kernel@...r.kernel.org, kvm@...r.kernel.org,
        linux-doc@...r.kernel.org, Dave Hansen <dave.hansen@...ux.intel.com>
Cc: pbonzini@...hat.com, seanjc@...gle.com, corbet@....net, tglx@...utronix.de,
        mingo@...hat.com, bp@...en8.de, x86@...nel.org, hpa@...or.com,
        luto@...nel.org, peterz@...radead.org, andrew.cooper3@...rix.com,
        chao.gao@...el.com, hch@...radead.org
Subject: Re: [PATCH v8 05/21] x86/cea: Export API for per-CPU exception stacks for KVM


> Convert the __this_cpu_ist_{top,bottom}_va() macros into proper functions,
> and export __this_cpu_ist_top_va() to allow KVM to retrieve the top of the
> per-CPU exception stack.
> 
> FRED introduced new fields in the host-state area of the VMCS for stack
> levels 1->3 (HOST_IA32_FRED_RSP[123]), each respectively corresponding to
> per-CPU exception stacks for #DB, NMI and #DF.  KVM must populate these
> fields each time a vCPU is loaded onto a CPU.
> 
> To simplify access to the exception stacks in struct cea_exception_stacks,
> a union is used to create an array alias, enabling array-style indexing of
> the stack entries.
> 
> Signed-off-by: Xin Li (Intel) <xin@...or.com>

Dave, can you please help to review patch 4 & 5?

Thanks!
Xin

> ---
> 
> Change in v7:
> * Remove Suggested-bys (Dave Hansen).
> * Move rename code in a separate patch (Dave Hansen).
> * Access cea_exception_stacks using array indexing (Dave Hansen).
> * Use BUILD_BUG_ON(ESTACK_DF != 0) to ensure the starting index is 0
>  (Dave Hansen).
> 
> Change in v5:
> * Export accessor instead of data (Christoph Hellwig).
> * Add TB from Xuelian Guo.
> 
> Change in v4:
> * Rewrite the change log and add comments to the export (Dave Hansen).
> ---
> arch/x86/include/asm/cpu_entry_area.h | 51 +++++++++++++--------------
> arch/x86/mm/cpu_entry_area.c          | 25 +++++++++++++
> 2 files changed, 50 insertions(+), 26 deletions(-)
> 
> diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
> index d0f884c28178..58cd71144e5e 100644
> --- a/arch/x86/include/asm/cpu_entry_area.h
> +++ b/arch/x86/include/asm/cpu_entry_area.h
> @@ -16,6 +16,19 @@
> #define VC_EXCEPTION_STKSZ    0
> #endif
> 
> +/*
> + * The exception stack ordering in [cea_]exception_stacks
> + */
> +enum exception_stack_ordering {
> +    ESTACK_DF,
> +    ESTACK_NMI,
> +    ESTACK_DB,
> +    ESTACK_MCE,
> +    ESTACK_VC,
> +    ESTACK_VC2,
> +    N_EXCEPTION_STACKS
> +};
> +
> /* Macro to enforce the same ordering and stack sizes */
> #define ESTACKS_MEMBERS(guardsize, optional_stack_size)        \
>    char    ESTACK_DF_stack_guard[guardsize];        \
> @@ -39,37 +52,29 @@ struct exception_stacks {
> 
> /* The effective cpu entry area mapping with guard pages. */
> struct cea_exception_stacks {
> -    ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
> -};
> -
> -/*
> - * The exception stack ordering in [cea_]exception_stacks
> - */
> -enum exception_stack_ordering {
> -    ESTACK_DF,
> -    ESTACK_NMI,
> -    ESTACK_DB,
> -    ESTACK_MCE,
> -    ESTACK_VC,
> -    ESTACK_VC2,
> -    N_EXCEPTION_STACKS
> +    union{
> +        struct {
> +            ESTACKS_MEMBERS(PAGE_SIZE, EXCEPTION_STKSZ)
> +        };
> +        struct {
> +            char stack_guard[PAGE_SIZE];
> +            char stack[EXCEPTION_STKSZ];
> +        } event_stacks[N_EXCEPTION_STACKS];
> +    };
> };
> 
> #define CEA_ESTACK_SIZE(st)                    \
>    sizeof(((struct cea_exception_stacks *)0)->st## _stack)
> 
> -#define CEA_ESTACK_BOT(ceastp, st)                \
> -    ((unsigned long)&(ceastp)->st## _stack)
> -
> -#define CEA_ESTACK_TOP(ceastp, st)                \
> -    (CEA_ESTACK_BOT(ceastp, st) + CEA_ESTACK_SIZE(st))
> -
> #define CEA_ESTACK_OFFS(st)                    \
>    offsetof(struct cea_exception_stacks, st## _stack)
> 
> #define CEA_ESTACK_PAGES                    \
>    (sizeof(struct cea_exception_stacks) / PAGE_SIZE)
> 
> +extern unsigned long __this_cpu_ist_top_va(enum exception_stack_ordering stack);
> +extern unsigned long __this_cpu_ist_bottom_va(enum exception_stack_ordering stack);
> +
> #endif
> 
> #ifdef CONFIG_X86_32
> @@ -144,10 +149,4 @@ static __always_inline struct entry_stack *cpu_entry_stack(int cpu)
>    return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
> }
> 
> -#define __this_cpu_ist_top_va(name)                    \
> -    CEA_ESTACK_TOP(__this_cpu_read(cea_exception_stacks), name)
> -
> -#define __this_cpu_ist_bottom_va(name)                    \
> -    CEA_ESTACK_BOT(__this_cpu_read(cea_exception_stacks), name)
> -
> #endif
> diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c
> index 9fa371af8abc..595c2e03ddd5 100644
> --- a/arch/x86/mm/cpu_entry_area.c
> +++ b/arch/x86/mm/cpu_entry_area.c
> @@ -18,6 +18,31 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage)
> static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks);
> DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks);
> 
> +/*
> + * FRED introduced new fields in the host-state area of the VMCS for
> + * stack levels 1->3 (HOST_IA32_FRED_RSP[123]), each respectively
> + * corresponding to per CPU stacks for #DB, NMI and #DF.  KVM must
> + * populate these each time a vCPU is loaded onto a CPU.
> + *
> + * Called from entry code, so must be noinstr.
> + */
> +noinstr unsigned long __this_cpu_ist_bottom_va(enum exception_stack_ordering stack)
> +{
> +    struct cea_exception_stacks *s;
> +
> +    BUILD_BUG_ON(ESTACK_DF != 0);
> +
> +    s = __this_cpu_read(cea_exception_stacks);
> +
> +    return (unsigned long)&s->event_stacks[stack].stack;
> +}
> +
> +noinstr unsigned long __this_cpu_ist_top_va(enum exception_stack_ordering stack)
> +{
> +    return __this_cpu_ist_bottom_va(stack) + EXCEPTION_STKSZ;
> +}
> +EXPORT_SYMBOL(__this_cpu_ist_top_va);
> +
> static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, _cea_offset);
> 
> static __always_inline unsigned int cea_offset(unsigned int cpu)
> --
> 2.51.0
> 
> 

Powered by blists - more mailing lists