| Message ID | 1502280338-23002-11-git-send-email-Dave.Martin@arm.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
Dave Martin <Dave.Martin@arm.com> writes: > To enable the kernel to use SVE, all SVE traps from EL1 must be > disabled. To take maximum advantage of the hardware, the full > available vector length also needs to be enabled for EL1 by > programming ZCR_EL2.LEN. (The kernel will program ZCR_EL1.LEN as > required, but this cannot override the limit set by ZCR_EL2.) > > In advance of full SVE support being implemented for userspace, it > also necessary to ensure that SVE traps from EL0 are enabled. > > This patch makes the appropriate changes to the primary and > secondary CPU initialisation code. > > Signed-off-by: Dave Martin <Dave.Martin@arm.com> > --- > arch/arm64/kernel/head.S | 13 ++++++++++++- > arch/arm64/mm/proc.S | 14 ++++++++++++-- > 2 files changed, 24 insertions(+), 3 deletions(-) > > diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S > index 973df7d..0ae1713 100644 > --- a/arch/arm64/kernel/head.S > +++ b/arch/arm64/kernel/head.S > @@ -514,8 +514,19 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems > mov x0, #0x33ff > msr cptr_el2, x0 // Disable copro. traps to EL2 > > + /* SVE register access */ > + mrs x1, id_aa64pfr0_el1 > + ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 > + cbz x1, 7f > + > + bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps > + msr cptr_el2, x0 // Disable copro. traps > to EL2 It seems a shame to write to cptr_el2 twice rather than compute and write. > + isb Especially as the second one needs an isb :-/ But I don't see a much neater way of doing it so: Reviewed-by: Alex Bennée <alex.bennee@linaro.org> > + mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector > + msr_s SYS_ZCR_EL2, x1 // length for EL1. > + > /* Hypervisor stub */ > - adr_l x0, __hyp_stub_vectors > +7: adr_l x0, __hyp_stub_vectors > msr vbar_el2, x0 > > /* spsr */ > 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 > + > mov x0, #1 << 12 // Reset mdscr_el1 and disable > msr mdscr_el1, x0 // access to the DCC from EL0 > isb // Unmask debug exceptions now, -- Alex Bennée
On Tue, Aug 22, 2017 at 04:04:28PM +0100, Alex Bennée wrote: > > Dave Martin <Dave.Martin@arm.com> writes: > > > To enable the kernel to use SVE, all SVE traps from EL1 must be > > disabled. To take maximum advantage of the hardware, the full > > available vector length also needs to be enabled for EL1 by > > programming ZCR_EL2.LEN. (The kernel will program ZCR_EL1.LEN as > > required, but this cannot override the limit set by ZCR_EL2.) > > > > In advance of full SVE support being implemented for userspace, it > > also necessary to ensure that SVE traps from EL0 are enabled. > > > > This patch makes the appropriate changes to the primary and > > secondary CPU initialisation code. > > > > Signed-off-by: Dave Martin <Dave.Martin@arm.com> > > --- > > arch/arm64/kernel/head.S | 13 ++++++++++++- > > arch/arm64/mm/proc.S | 14 ++++++++++++-- > > 2 files changed, 24 insertions(+), 3 deletions(-) > > > > diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S > > index 973df7d..0ae1713 100644 > > --- a/arch/arm64/kernel/head.S > > +++ b/arch/arm64/kernel/head.S > > @@ -514,8 +514,19 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems > > mov x0, #0x33ff > > msr cptr_el2, x0 // Disable copro. traps to EL2 > > > > + /* SVE register access */ > > + mrs x1, id_aa64pfr0_el1 > > + ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 > > + cbz x1, 7f > > + > > + bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps > > + msr cptr_el2, x0 // Disable copro. traps > > to EL2 > > It seems a shame to write to cptr_el2 twice rather than compute and > write. > > > + isb > > Especially as the second one needs an isb :-/ > > But I don't see a much neater way of doing it so: > > Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Thanks Originally I think I did merge the CPTR writes here, but since this is slow-path anyway, I figured it was better to keep the code simple rather than introducing new interdependencies. I could revisit it if someone has a strong view. Cheers ---Dave > > > + mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector > > + msr_s SYS_ZCR_EL2, x1 // length for EL1. > > + > > /* Hypervisor stub */ > > - adr_l x0, __hyp_stub_vectors > > +7: adr_l x0, __hyp_stub_vectors > > msr vbar_el2, x0 [...]
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index 973df7d..0ae1713 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -514,8 +514,19 @@ CPU_LE( movk x0, #0x30d0, lsl #16 ) // Clear EE and E0E on LE systems mov x0, #0x33ff msr cptr_el2, x0 // Disable copro. traps to EL2 + /* SVE register access */ + mrs x1, id_aa64pfr0_el1 + ubfx x1, x1, #ID_AA64PFR0_SVE_SHIFT, #4 + cbz x1, 7f + + bic x0, x0, #CPTR_EL2_TZ // Also disable SVE traps + msr cptr_el2, x0 // Disable copro. traps to EL2 + isb + mov x1, #ZCR_ELx_LEN_MASK // SVE: Enable full vector + msr_s SYS_ZCR_EL2, x1 // length for EL1. + /* Hypervisor stub */ - adr_l x0, __hyp_stub_vectors +7: adr_l x0, __hyp_stub_vectors msr vbar_el2, x0 /* spsr */ 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 + mov x0, #1 << 12 // Reset mdscr_el1 and disable msr mdscr_el1, x0 // access to the DCC from EL0 isb // Unmask debug exceptions now,
To enable the kernel to use SVE, all SVE traps from EL1 must be disabled. To take maximum advantage of the hardware, the full available vector length also needs to be enabled for EL1 by programming ZCR_EL2.LEN. (The kernel will program ZCR_EL1.LEN as required, but this cannot override the limit set by ZCR_EL2.) In advance of full SVE support being implemented for userspace, it also necessary to ensure that SVE traps from EL0 are enabled. This patch makes the appropriate changes to the primary and secondary CPU initialisation code. Signed-off-by: Dave Martin <Dave.Martin@arm.com> --- arch/arm64/kernel/head.S | 13 ++++++++++++- arch/arm64/mm/proc.S | 14 ++++++++++++-- 2 files changed, 24 insertions(+), 3 deletions(-)