Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Feedback-ID: ie3994620:Fastmail
Date:   Mon, 5 Sep 2022 19:47:08 +0300
From:   "Kirill A. Shutemov" <kirill@shutemov.name>
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Bharata B Rao <bharata@amd.com>, ananth.narayan@amd.com,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
        Dave Hansen <dave.hansen@linux.intel.com>,
        Andy Lutomirski <luto@kernel.org>, x86@kernel.org,
        Kostya Serebryany <kcc@google.com>,
        Andrey Ryabinin <ryabinin.a.a@gmail.com>,
        Andrey Konovalov <andreyknvl@gmail.com>,
        Alexander Potapenko <glider@google.com>,
        Taras Madan <tarasmadan@google.com>,
        Dmitry Vyukov <dvyukov@google.com>,
        "H . J . Lu" <hjl.tools@gmail.com>,
        Andi Kleen <ak@linux.intel.com>,
        Rick Edgecombe <rick.p.edgecombe@intel.com>,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCHv8 00/11] Linear Address Masking enabling
Message-ID: <20220905164708.ewx5lulbqdjrk3mx@box.shutemov.name>
References: <20220830010104.1282-1-kirill.shutemov@linux.intel.com>
 <20220904010001.knlcejmw4lg2uzy3@box.shutemov.name>
 <64519d0b-b696-db47-52c2-303451e10c09@amd.com>
 <20220905134457.a2f7uluq42frsgwe@box.shutemov.name>
 <YxYIAVx2qJLMDJlC@hirez.programming.kicks-ass.net>
 <20220905153517.k6ctaqqtkcyu2zmn@box.shutemov.name>
 <YxYZ6Q+JVg79aDNS@hirez.programming.kicks-ass.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <YxYZ6Q+JVg79aDNS@hirez.programming.kicks-ass.net>
Precedence: bulk

On Mon, Sep 05, 2022 at 05:46:49PM +0200, Peter Zijlstra wrote:
> On Mon, Sep 05, 2022 at 06:35:17PM +0300, Kirill A. Shutemov wrote:
> > What about something like this?
> > 
> > diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
> > index 803241dfc473..868d2730884b 100644
> > --- a/arch/x86/include/asm/uaccess.h
> > +++ b/arch/x86/include/asm/uaccess.h
> > @@ -30,8 +30,10 @@ 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_cpu_has(X86_FEATURE_LAM)) {				\
> > +		s64 sign = (s64)__addr >> 63;				\
> > +		__addr &= (mm)->context.untag_mask | sign;		\
> > +	}								\
> >  	(__force __typeof__(addr))__addr;				\
> >  })
> 
> Well, if you go throught the trouble of adding it, might as well use a
> regular static branch and only enable it once there's an actual user,
> no?

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);
+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);
-- 
  Kiryl Shutsemau / Kirill A. Shutemov