This is the mail archive of the
libc-alpha@sourceware.org
mailing list for the glibc project.
Re: [PATCH v2 10/28] arm64/sve: Low-level CPU setup
- From: Dave Martin <Dave dot Martin at arm dot com>
- To: Catalin Marinas <catalin dot marinas at arm dot com>
- Cc: linux-arch at vger dot kernel dot org, libc-alpha at sourceware dot org, Ard Biesheuvel <ard dot biesheuvel at linaro dot org>, Szabolcs Nagy <szabolcs dot nagy at arm dot com>, Richard Sandiford <richard dot sandiford at arm dot com>, Will Deacon <will dot deacon at arm dot com>, Alex Bennée <alex dot bennee at linaro dot org>, kvmarm at lists dot cs dot columbia dot edu, linux-arm-kernel at lists dot infradead dot org
- Date: Wed, 13 Sep 2017 20:21:11 +0100
- Subject: Re: [PATCH v2 10/28] arm64/sve: Low-level CPU setup
- Authentication-results: sourceware.org; auth=none
- References: <1504198860-12951-1-git-send-email-Dave.Martin@arm.com> <1504198860-12951-11-git-send-email-Dave.Martin@arm.com> <20170913133206.rwobtu7ft5nrsh4p@localhost>
On Wed, Sep 13, 2017 at 06:32:06AM -0700, Catalin Marinas wrote:
> On Thu, Aug 31, 2017 at 06:00:42PM +0100, Dave P Martin wrote:
> > diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
> > index 877d42f..dd22ef2 100644
> > --- a/arch/arm64/mm/proc.S
> > +++ b/arch/arm64/mm/proc.S
> > @@ -27,6 +27,7 @@
> > #include <asm/pgtable-hwdef.h>
> > #include <asm/cpufeature.h>
> > #include <asm/alternative.h>
> > +#include <asm/sysreg.h>
> >
> > #ifdef CONFIG_ARM64_64K_PAGES
> > #define TCR_TG_FLAGS TCR_TG0_64K | TCR_TG1_64K
> > @@ -186,8 +187,17 @@ ENTRY(__cpu_setup)
> > tlbi vmalle1 // Invalidate local TLB
> > dsb nsh
> >
> > - mov x0, #3 << 20
> > - msr cpacr_el1, x0 // Enable FP/ASIMD
> > + mov x0, #3 << 20 // FEN
> > +
> > + /* SVE */
> > + mrs x5, id_aa64pfr0_el1
> > + ubfx x5, x5, #ID_AA64PFR0_SVE_SHIFT, #4
> > + cbz x5, 1f
> > +
> > + bic x0, x0, #CPACR_EL1_ZEN
> > + orr x0, x0, #CPACR_EL1_ZEN_EL1EN // SVE: trap for EL0, not EL1
> > +1: msr cpacr_el1, x0 // Enable FP/ASIMD
>
> For EL1, I wonder whether we could move this later to cpufeature.c. IIRC
> I tried to do the same with FPSIMD but hit an issue with EFI run-time
> services (I may be wrong though).
I'll take a look at this -- I believe it should be safe to disable this
trap for EL1 relatively late. This is needed before probing for
available vector lengths, but apart from that the kernel shouldn't touch
SVE until/unless some user task uses SVE.
This would change if we eventually enable kernel-mode SVE, but I wouldn't
expect that to get used in early boot before the cpufeatures code runs.
Ard may have a view on this.
Cheers
---Dave