lkml.org 
[lkml]   [2022]   [Sep]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCHv8 00/11] Linear Address Masking enabling
On Mon, Sep 05, 2022 at 07:47:08PM +0300, Kirill A. Shutemov wrote:

> Fair enough. How about this?
>
> diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
> index 803241dfc473..1a03c65a9c0f 100644
> --- a/arch/x86/include/asm/uaccess.h
> +++ b/arch/x86/include/asm/uaccess.h
> @@ -22,6 +22,8 @@ static inline bool pagefault_disabled(void);
> #endif
>
> #ifdef CONFIG_X86_64
> +DECLARE_STATIC_KEY_FALSE(tagged_addr_key);
> +
> /*
> * Mask out tag bits from the address.
> *
> @@ -30,8 +32,10 @@ static inline bool pagefault_disabled(void);
> */
> #define untagged_addr(mm, addr) ({ \
> u64 __addr = (__force u64)(addr); \
> - s64 sign = (s64)__addr >> 63; \
> - __addr &= (mm)->context.untag_mask | sign; \
> + if (static_branch_unlikely(&tagged_addr_key)) { \
> + s64 sign = (s64)__addr >> 63; \
> + __addr &= (mm)->context.untag_mask | sign; \
> + } \
> (__force __typeof__(addr))__addr; \
> })
>
> diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
> index 337f80a0862f..63194bf43c9a 100644
> --- a/arch/x86/kernel/process_64.c
> +++ b/arch/x86/kernel/process_64.c
> @@ -742,6 +742,9 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
> }
> #endif
>
> +DEFINE_STATIC_KEY_FALSE(tagged_addr_key);

So here you use the: false-unlikely scenario which seems suboptimal in
this case, I was thinking the false-likely case would generate better
code (see the comment in linux/jump_label.h).

> +EXPORT_SYMBOL_GPL(tagged_addr_key);
> +
> static void enable_lam_func(void *mm)
> {
> struct mm_struct *loaded_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
> @@ -813,6 +816,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
> }
>
> on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true);
> + static_branch_enable(&tagged_addr_key);
> out:
> mutex_unlock(&mm->context.lock);
> mmap_write_unlock(mm);

Aside from the one nit above, this looks about right.

\
 
 \ /
  Last update: 2022-09-06 10:45    [W:0.121 / U:0.376 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site