[RFC PATCH 0.9/2] arm64: fpsimd: Expose CPU / FPSIMD state association helpers

Oops, forgot to post this patch that goes before patch 1 in the series. --8<-- Expose an interface for associating an FPSIMD context with a CPU and checking the association, for use by KVM. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/include/asm/fpsimd.h | 5 ++

[RFC PATCH 2/2] KVM: arm64: Eliminate most redundant FPSIMD saves and restores

, provding that doesn't happen the reload cost is at least saved on the next run loop iteration. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- Caveat: this does *not* currently deal properly with host SVE state, though supporting that shouldn't be drastically different. --- arch

[RFC PATCH 1/2] KVM: arm64: Convert lazy FPSIMD context switch trap to C

To make the lazt FPSIMD context switch trap code easier to hack on, this patch converts it to C. This is not amazingly efficient, but the trap should typically only be taken once per host context switch. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/kvm/hyp/entry.S

[RFC PATCH 0/2] KVM: arm64: Optime FPSIMD context handling

poke holes it... Dave Martin (2): KVM: arm64: Convert lazy FPSIMD context switch trap to C KVM: arm64: Eliminate most redundant FPSIMD saves and restores arch/arm64/include/asm/fpsimd.h | 1 + arch/arm64/include/asm/kvm_host.h| 10 ++- arch/arm64/include/asm/thread_info.h | 1 + arch/arm

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

On Wed, Feb 14, 2018 at 06:38:11PM +0100, Christoffer Dall wrote: > On Wed, Feb 14, 2018 at 02:43:42PM +0000, Dave Martin wrote: > > [CC Ard, in case he has a view on how much we care about softirq NEON > > performance regressions ... and whether my suggestions make sense] > >

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

[CC Ard, in case he has a view on how much we care about softirq NEON performance regressions ... and whether my suggestions make sense] On Wed, Feb 14, 2018 at 11:15:54AM +0100, Christoffer Dall wrote: > On Tue, Feb 13, 2018 at 02:08:47PM +0000, Dave Martin wrote: > > On Tue, Feb 13, 2

Re: [PATCH v3 26/41] KVM: arm64: Introduce framework for accessing deferred sysregs

On Tue, Feb 13, 2018 at 09:55:02AM +0100, Christoffer Dall wrote: > On Fri, Feb 09, 2018 at 04:17:39PM +0000, Dave Martin wrote: > > On Thu, Jan 25, 2018 at 08:54:13PM +0100, Christoffer Dall wrote: > > > On Tue, Jan 23, 2018 at 04:04:40PM +, Dave Martin wrote: [...] >

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

On Tue, Feb 13, 2018 at 09:51:30AM +0100, Christoffer Dall wrote: > On Fri, Feb 09, 2018 at 03:59:30PM +0000, Dave Martin wrote: > > On Wed, Feb 07, 2018 at 06:56:44PM +0100, Christoffer Dall wrote: > > > On Wed, Feb 07, 2018 at 04:49:55PM +, Dave Martin wrote: [...] &

Re: [PATCH v3 26/41] KVM: arm64: Introduce framework for accessing deferred sysregs

On Thu, Jan 25, 2018 at 08:54:13PM +0100, Christoffer Dall wrote: > On Tue, Jan 23, 2018 at 04:04:40PM +0000, Dave Martin wrote: > > On Fri, Jan 12, 2018 at 01:07:32PM +0100, Christoffer Dall wrote: > > > We are about to defer saving and restoring some groups of system > >

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

On Wed, Feb 07, 2018 at 06:56:44PM +0100, Christoffer Dall wrote: > On Wed, Feb 07, 2018 at 04:49:55PM +0000, Dave Martin wrote: > > On Thu, Jan 25, 2018 at 08:46:53PM +0100, Christoffer Dall wrote: > > > On Mon, Jan 22, 2018 at 05:33:28PM +, Dave Martin wrote: > >

Re: [RFC v2 REPOST] arm64: KVM: KVM API extensions for SVE

On Wed, Feb 07, 2018 at 05:17:50PM +0100, Christoffer Dall wrote: > On Wed, Feb 07, 2018 at 03:34:03PM +0000, Dave Martin wrote: > > On Wed, Feb 07, 2018 at 03:58:31PM +0100, Christoffer Dall wrote: > > > On Wed, Feb 07, 2018 at 11:33:28AM +, Dave Martin wrote: [...] >

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

On Thu, Jan 25, 2018 at 08:46:53PM +0100, Christoffer Dall wrote: > On Mon, Jan 22, 2018 at 05:33:28PM +0000, Dave Martin wrote: > > On Fri, Jan 12, 2018 at 01:07:15PM +0100, Christoffer Dall wrote: > > > Avoid saving the guest VFP registers and restoring the host VFP > > &

Re: [RFC v2 REPOST] arm64: KVM: KVM API extensions for SVE

On Wed, Feb 07, 2018 at 03:58:31PM +0100, Christoffer Dall wrote: > On Wed, Feb 07, 2018 at 11:33:28AM +0000, Dave Martin wrote: [...] > > What if KVM_ARM_SVE_SET_VLS() were to yield 0 if the exact requested set > > of VLs was configured, -ERANGE if some subset was configur

Re: [RFC v2 REPOST] arm64: KVM: KVM API extensions for SVE

On Tue, Feb 06, 2018 at 02:17:57PM +0100, Christoffer Dall wrote: > On Tue, Feb 06, 2018 at 11:43:16AM +0000, Dave Martin wrote: > > On Mon, Feb 05, 2018 at 05:13:08PM +0100, Christoffer Dall wrote: > > > Hi Dave, > > > > > > On Fri, Jan 26, 2018 at

Re: [RFC v2 REPOST] arm64: KVM: KVM API extensions for SVE

On Mon, Feb 05, 2018 at 05:13:08PM +0100, Christoffer Dall wrote: > Hi Dave, > > On Fri, Jan 26, 2018 at 05:28:49PM +0000, Dave Martin wrote: > > New feature KVM_ARM_VCPU_SVE: > > > > * enables exposure of SVE to the guest > > > > * enables visibility

[RFC v2 REPOST] arm64: KVM: KVM API extensions for SVE

Hi all, Reposting this to give people another chance to comment before I move ahead... ---8<--- Here's a second, slightly more complete stab at the KVM API extensions for SVE. I haven't started implementing in earnest yet, so any comments at this stage would be very helpful. [libvir-list

Re: [PATCH v3 15/41] KVM: arm64: Remove kern_hyp_va() use in VHE switch function

On Fri, Jan 12, 2018 at 01:07:21PM +0100, Christoffer Dall wrote: > VHE kernels run completely in EL2 and therefore don't have a notion of > kernel and hyp addresses, they are all just kernel addresses. Therefore > don't call kern_hyp_va() in the VHE switch function. Isn't this an example of

Re: [PATCH v3 14/41] KVM: arm64: Introduce VHE-specific kvm_vcpu_run

On Fri, Jan 12, 2018 at 01:07:20PM +0100, Christoffer Dall wrote: > So far this is just a copy of the legacy non-VHE switch function, but we > will start reworking these functions in separate directions to work on > VHE and non-VHE in the most optimal way in later patches. I'd be concerned that

Re: [PATCH v3 09/41] KVM: arm64: Defer restoring host VFP state to vcpu_put

On Fri, Jan 12, 2018 at 01:07:15PM +0100, Christoffer Dall wrote: > Avoid saving the guest VFP registers and restoring the host VFP > registers on every exit from the VM. Only when we're about to run > userspace or other threads in the kernel do we really have to switch the > state back to the

Re: [PATCH v5 00/30] ARM Scalable Vector Extension (SVE)

On Tue, Jan 16, 2018 at 01:11:49PM +0300, Yury Norov wrote: > On Mon, Jan 15, 2018 at 05:22:01PM +0000, Dave Martin wrote: [...] > > I'll take a look at your code anyway in case there's something > > else one of us didn't think of. > > Thanks, Dave. > > This is the b

Re: [PATCH v5 00/30] ARM Scalable Vector Extension (SVE)

On Tue, Jan 09, 2018 at 07:51:20PM +0300, Yury Norov wrote: > On Mon, Jan 08, 2018 at 05:49:05PM +0300, Yury Norov wrote: > > On Tue, Oct 31, 2017 at 03:50:52PM +0000, Dave Martin wrote: > > > This series implements Linux kernel support for the ARM Scalable Vector > &g

Re: [PATCH v5 00/30] ARM Scalable Vector Extension (SVE)

On Mon, Jan 08, 2018 at 05:49:05PM +0300, Yury Norov wrote: > On Tue, Oct 31, 2017 at 03:50:52PM +0000, Dave Martin wrote: > > This series implements Linux kernel support for the ARM Scalable Vector > > Extension (SVE). [1] It supersedes the previous v3: see [3] for link > >

Re: [RFC v2] arm64: KVM: KVM API extensions for SVE

On Wed, Dec 13, 2017 at 04:58:16PM +, Peter Maydell wrote: > On 13 December 2017 at 16:55, Dave Martin <dave.mar...@arm.com> wrote: > > Vector length control: > > > > Some means is needed to determine the set of vector lengths visible > > to guest softwar

[RFC v2] arm64: KVM: KVM API extensions for SVE

Hi all, Here's a second, slightly more complete stab at the KVM API extensions for SVE. I haven't started implementing in earnest yet, so any comments at this stage would be very helpful. [libvir-list readers: this is a proposal for extending the KVM API on AArch64 systems to support the

Re: [RFC] KVM API extensions for SVE

On Mon, Dec 11, 2017 at 08:24:32PM +0100, Christoffer Dall wrote: > On Mon, Dec 11, 2017 at 02:51:36PM +0000, Dave Martin wrote: > > On Fri, Nov 24, 2017 at 03:45:38PM +0100, Christoffer Dall wrote: [...] > > > So you're saying even if we try the "expose full width and

Re: [PATCH v5 15/30] arm64/sve: Signal handling support

On Tue, Dec 12, 2017 at 10:40:30AM +, Will Deacon wrote: > On Mon, Dec 11, 2017 at 11:23:09AM -0800, Kees Cook wrote: > > On Mon, Dec 11, 2017 at 6:07 AM, Will Deacon wrote: > > > On Thu, Dec 07, 2017 at 10:50:38AM -0800, Kees Cook wrote: > > >> My question is mainly: why

Re: [RFC] KVM API extensions for SVE

On Fri, Nov 24, 2017 at 03:45:38PM +0100, Christoffer Dall wrote: > On Thu, Nov 23, 2017 at 06:40:50PM +0000, Dave Martin wrote: > > On Wed, Nov 22, 2017 at 08:52:30PM +0100, Christoffer Dall wrote: > > > Hi Dave, > > > > > > On Tue, Nov 21, 2017 at 01:49:16PM

Re: [PATCH v5 15/30] arm64/sve: Signal handling support

On Thu, Dec 07, 2017 at 10:49:48AM +, Will Deacon wrote: > Hi Kees, > > On Wed, Dec 06, 2017 at 11:56:50AM -0800, Kees Cook wrote: > > On Tue, Oct 31, 2017 at 8:51 AM, Dave Martin <dave.mar...@arm.com> wrote: > > > Miscellaneous: > > > > >

[PATCH 3/3] arm64/sve: Avoid dereference of dead task_struct in KVM guest entry

, although this patch is not a KVM fix per se, this means that this check is now done safely in the KVM world switch path (which is currently the only user of this code). Signed-off-by: Dave Martin <dave.mar...@arm.com> Cc: Ard Biesheuvel <ard.biesheu...@linaro.org> Cc: Christoffer Dall &l

[PATCH 1/3] arm64: fpsimd: Prevent registers leaking from dead tasks

e task_struct freeing work into the context switch critical section, or otherwise some deferred cleanup mechanism would need to be introduced, neither of which seems obviously justified. Fixes: 005f78cd8849 ("arm64: defer reloading a task's FPSIMD state to userland resume") Signed-off-by: Dave M

[PATCH v2 0/3] arm64: SVE fixes for v4.15-rc2

://lists.infradead.org/pipermail/linux-arm-kernel/2017-December/545126.html Dave Martin (3): arm64: fpsimd: Prevent registers leaking from dead tasks arm64: fpsimd: Abstract out binding of task's fpsimd context to the cpu. arm64/sve: Avoid dereference of dead task_struct in KVM guest entry

Re: [PATCH 1/3] arm64: KVM: Move CPU ID reg trap setup off the world switch path

On Wed, Dec 06, 2017 at 11:53:00AM +0100, Christoffer Dall wrote: > On Tue, Dec 05, 2017 at 12:31:51PM +0000, Dave Martin wrote: > > On Tue, Dec 05, 2017 at 10:09:15AM +0100, Christoffer Dall wrote: > > > On Fri, Dec 01, 2017 at 03:19:40PM +, Dave Martin wrote: > > &

Re: [PATCH 3/3] arm64/sve: KVM: Avoid dereference of dead task during guest entry

On Tue, Dec 05, 2017 at 10:43:50AM +0100, Christoffer Dall wrote: > Hi Dave, > > On Mon, Dec 04, 2017 at 03:36:50PM +0000, Dave Martin wrote: > > On Mon, Dec 04, 2017 at 01:53:21PM +, Ard Biesheuvel wrote: > > > On 1 December 2017 at 15:19, Dave Martin <

Re: [PATCH 1/3] arm64: KVM: Move CPU ID reg trap setup off the world switch path

On Tue, Dec 05, 2017 at 10:09:15AM +0100, Christoffer Dall wrote: > On Fri, Dec 01, 2017 at 03:19:40PM +0000, Dave Martin wrote: > > The HCR_EL2.TID3 flag needs to be set when trapping guest access to > > the CPU ID registers is required. However, the decision about > > wh

Re: [PATCH 3/3] arm64/sve: KVM: Avoid dereference of dead task during guest entry

On Mon, Dec 04, 2017 at 01:53:21PM +, Ard Biesheuvel wrote: > On 1 December 2017 at 15:19, Dave Martin <dave.mar...@arm.com> wrote: > > When deciding whether to invalidate FPSIMD state cached in the cpu, > > the backend function sve_flush_cpu_state() attempts to dereferenc

[PATCH 2/3] arm64: fpsimd: Abstract out binding of task's fpsimd context to the cpu.

function fpsimd_bind_to_cpu(). Signed-off-by: Dave Martin <dave.mar...@arm.com> Cc: Ard Biesheuvel <ard.biesheu...@linaro.org> --- arch/arm64/kernel/fpsimd.c | 25 +++-- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/

[PATCH 1/3] arm64: KVM: Move CPU ID reg trap setup off the world switch path

. This patch moves the decision to vcpu_reset_hcr() and records the choice made in vcpu->arch.hcr_el2. The world switch code can then load this directly when switching to the guest without the need for conditional logic on the critical path. Signed-off-by: Dave Martin <dave.mar...@arm.com>

[PATCH 0/3] arm64: SVE fixes for v4.15-rc1

This mini-series contains a few fixes for known issues in the arm64 SVE patches that missed the merge window. They should be considered fixes for v4.15. Dave Martin (3): arm64: KVM: Move CPU ID reg trap setup off the world switch path arm64: fpsimd: Abstract out binding of task's fpsimd

Re: [PATCH v5 00/30] ARM Scalable Vector Extension (SVE)

On Wed, Nov 29, 2017 at 03:21:40PM +, Will Deacon wrote: > On Wed, Nov 29, 2017 at 03:04:12PM +, Alex Bennée wrote: > > > > Dave Martin <dave.mar...@arm.com> writes: > > > > > This series implements Linux kernel support for the ARM Scala

Re: [RFC] KVM API extensions for SVE

On Wed, Nov 22, 2017 at 08:52:30PM +0100, Christoffer Dall wrote: > Hi Dave, > > On Tue, Nov 21, 2017 at 01:49:16PM +0000, Dave Martin wrote: > > Hi all, > > > > SVE adds some new registers, and their size depends on the hardware ando > > on runtime sysreg

Re: [RFC PATCH 3/4] arm64/sve: KVM: Ensure user SVE use traps after vcpu execution

On Wed, Nov 22, 2017 at 08:23:44PM +0100, Christoffer Dall wrote: > On Fri, Nov 17, 2017 at 04:38:54PM +0000, Dave Martin wrote: > > Currently, SVE use can remain untrapped if a KVM vcpu thread is > > preempted inside the kernel and we then switch back to some user > > thread

Re: [RFC PATCH 2/4] arm64/sve: KVM: Avoid dereference of dead task during guest entry

On Wed, Nov 22, 2017 at 08:23:38PM +0100, Christoffer Dall wrote: > Hi Dave, > > On Fri, Nov 17, 2017 at 04:38:53PM +0000, Dave Martin wrote: > > When deciding whether to invalidate FPSIMD state cached in the cpu, > > the backend function sve_flush_cpu_state() at

[RFC] KVM API extensions for SVE

Hi all, SVE adds some new registers, and their size depends on the hardware ando on runtime sysreg settings. Before coding something, I'd like to get people's views on my current approach here. --8<-- New vcpu feature flag: /* * userspace can support regs up to at least 2048 bits in size via

Re: [RFC PATCH 0/4] Initial KVM SVE support hacks

On Fri, Nov 17, 2017 at 04:38:51PM +, Dave Martin wrote: > Throwing out an RFC here now that I've got something _sort of_ working. > > This is based on the base SVE patches as now present in > torvalds/master [1], but not on Christoffer's SVE optimisations (for (That should be: C

[RFC PATCH 1/4] arm64: fpsimd: Abstract out binding of task's fpsimd context to the cpu.

function fpsimd_bind_to_cpu(). Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/kernel/fpsimd.c | 25 +++-- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 143b3e7..007140b 100644 ---

[RFC PATCH 4/4] arm64/sve: KVM: Basic SVE support

after boot via the ioctl interface: this breaks architectural assumptions in the guest, and should really be forbidden. Also, this is a latent trigger for buffer overruns, if creation of guests with limited VL is someday permitted. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch

[RFC PATCH 2/4] arm64/sve: KVM: Avoid dereference of dead task during guest entry

in fpsimd_last_state, which we can check without dereferencing the task pointer. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/kernel/fpsimd.c | 28 1 file changed, 16 insertions(+), 12 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fp

[RFC PATCH 3/4] arm64/sve: KVM: Ensure user SVE use traps after vcpu execution

by a signal etc. Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/kernel/fpsimd.c | 2 ++ virt/kvm/arm/arm.c | 6 +++--- 2 files changed, 5 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 3dc8058..3b135eb

[RFC PATCH 0/4] Initial KVM SVE support hacks

a bit of a hack today -- more detailed notes in the commit message. [1] c9b012e5f4a1 ("Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux") Dave Martin (4): arm64: fpsimd: Abstract out binding of task's fpsimd context to the cpu. arm64/sve:

Re: [PATCH v5 13/30] arm64/sve: Core task context handling

On Thu, Nov 09, 2017 at 05:16:40PM +, Alex Bennée wrote: > > Dave Martin <dave.mar...@arm.com> writes: > > > This patch adds the core support for switching and managing the SVE > > architectural state of user tasks. > > > > Calls to the existing

Re: [PATCH v5 15/30] arm64/sve: Signal handling support

On Tue, Nov 07, 2017 at 01:22:33PM +, Alex Bennée wrote: > > Dave Martin <dave.mar...@arm.com> writes: > > > This patch implements support for saving and restoring the SVE > > registers around signals. > > > > A fixed-size header struct sve_context is

Re: [PATCH v5 04/30] arm64: KVM: Hide unsupported AArch64 CPU features from guests

On Thu, Nov 02, 2017 at 09:15:57AM +0100, Christoffer Dall wrote: > On Wed, Nov 01, 2017 at 10:26:03AM +0000, Dave Martin wrote: > > On Wed, Nov 01, 2017 at 05:47:29AM +0100, Christoffer Dall wrote: > > > On Tue, Oct 31, 2017 at 03:50:56PM +, Dave Martin wrote: > >

Re: [PATCH v5 04/30] arm64: KVM: Hide unsupported AArch64 CPU features from guests

On Thu, Nov 02, 2017 at 09:15:57AM +0100, Christoffer Dall wrote: > On Wed, Nov 01, 2017 at 10:26:03AM +0000, Dave Martin wrote: > > On Wed, Nov 01, 2017 at 05:47:29AM +0100, Christoffer Dall wrote: > > > On Tue, Oct 31, 2017 at 03:50:56PM +, Dave Martin wrote: > >

Re: [PATCH v5 01/30] regset: Add support for dynamically sized regsets

e regset is dynamically sized or not. > > > > The only affected user of this interface is the ELF coredump code: > > This patch ports ELF coredump to dump regsets with their actual > > size in the coredump. This has no effect except for new regsets > > that are dynamically

Re: [PATCH v5 04/30] arm64: KVM: Hide unsupported AArch64 CPU features from guests

On Wed, Nov 01, 2017 at 05:47:29AM +0100, Christoffer Dall wrote: > On Tue, Oct 31, 2017 at 03:50:56PM +0000, Dave Martin wrote: > > Currently, a guest kernel sees the true CPU feature registers > > (ID_*_EL1) when it reads them using MRS instructions. This means > > that

[PATCH v5 20/30] arm64/sve: Preserve SVE registers around EFI runtime service calls

must be saved and restored too. No attempt is made to restore the restore the vector length after a call, for now. It is deemed rather insane for EFI to change it, and contemporary EFI implementations certainly won't. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex

[PATCH v5 26/30] arm64/sve: KVM: Hide SVE from CPU features exposed to guests

as reading as zero, which is consistent with SVE not being implemented. This is a temporary measure, and will be removed in a later series when full KVM support for SVE is implemented. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Ac

[RFC PATCH v5 30/30] arm64/sve: signal: Include SVE when computing AT_MINSIGSTKSZ

vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <dave.mar...@arm.com> Cc: Ard Biesheuvel <ard.biesheu...@linaro.org> Cc: Alex Bennée <alex.ben...@linaro.org&g

[PATCH v5 28/30] arm64/sve: Add documentation

This patch adds basic documentation of the user/kernel interface provided by the for SVE. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alan Hayward <alan.hayw...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.

[RFC PATCH v5 29/30] arm64: signal: Report signal frame size to userspace via auxv

s internal SIGFRAME_MAXSZ is supposed to sanity-check against generting frames that we consider _impossibly_ large. In this case, SIGSTKSZ is returned as a "reasonable guess that is at least bigger than MINSIGSTKSZ" and we WARN(). Signed-off-by: Dave Martin <dave.mar...@arm.com> -

[PATCH v5 27/30] arm64/sve: Detect SVE and activate runtime support

running on hardware that supports SVE, this enables runtime kernel support for SVE, and allows user tasks to execute SVE instructions and make of the of the SVE-specific user/kernel interface extensions implemented by this series. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by:

[PATCH v5 23/30] arm64/sve: Add sysctl to set the default vector length for new processes

the vector length of any existing process. The intended usage model is that if userspace is known to be fully SVE-tolerant (or a developer is curious to find out) then this parameter can be cranked up during system startup. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex

[PATCH v5 24/30] arm64/sve: KVM: Prevent guests from using SVE

, since cpu_pm_enter() is supposed to be called only with interrupts disabled. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Christoffer Dall <christoffer.d...@linaro.org> Acked-by: Catalin Marinas <catalin.mari...@ar

[PATCH v5 18/30] arm64/sve: Probe SVE capabilities and usable vector lengths

() remains hardwired to false. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Suzuki K Poulose <suzuki.poul...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> --- **Dropped at v3** Reviewed-b

[PATCH v5 25/30] arm64/sve: KVM: Treat guest SVE use as undefined instruction execution

When trapping forbidden attempts by a guest to use SVE, we want the guest to see a trap consistent with SVE not being implemented. This patch injects an undefined instruction exception into the guest in response to such an exception. Signed-off-by: Dave Martin <dave.mar...@arm.com> Re

[PATCH v5 21/30] arm64/sve: ptrace and ELF coredump support

, which the recipient can use to figure out the content, size and layout of the reset of the regset. Accessor macros are defined to allow the vector-length-dependent parts of the regset to be manipulated. Signed-off-by: Alan Hayward <alan.hayw...@arm.com> Signed-off-by: Dave Martin <dave.mar..

[PATCH v5 22/30] arm64/sve: Add prctl controls for userspace vector length management

instructions. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> --- **Dropped at v3** Reviewed-by: Alex Bennée <alex.ben...@linaro.org> See v3 posting for history. --- arch/arm64/incl

[PATCH v5 17/30] arm64: cpufeature: Move sys_caps_initialised declarations

booting a CPU, so that it can be updated appropriately. This patch simply moves the sys_caps_initialised stuff to the top of the file so that it can be used more widely. There doesn't seem to be a more obvious place to put it. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex

[PATCH v5 15/30] arm64/sve: Signal handling support

fpsimd_signal_preserve_current_state() is added to update _both_ the FPSIMD and SVE views in the task struct, to make it easier to populate this information into the signal frame. Because of the redundancy between the two views of the state, only one is updated otherwise. Signed-off-by: Dave Martin <dave.mar...@arm.com&

[PATCH v5 16/30] arm64/sve: Backend logic for setting the vector length

that are not a power of two. To handle this, logic is added to check a requested vector length against a possibly sparse bitmap of available vector lengths at runtime, so that the best supported value can be chosen. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <cat

[PATCH v5 07/30] arm64: fpsimd: Simplify uses of {set, clear}_ti_thread_flag()

. This should have no impact on behaviour. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Acked-by: Ard Biesheuvel <ard.biesheu...@linaro.org> --- arch/arm64/kerne

[PATCH v5 14/30] arm64/sve: Support vector length resetting for new processes

TIF_SVE_VL_INHERIT to control whether to inherit or reset the vector length. Currently these are inactive. Subsequent patches will provide the capability to configure them. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Cat

[PATCH v5 09/30] arm64/sve: Low-level SVE architectural state manipulation functions

the vector length. Setting of the vector length is done as part of register restore. Since people building kernels may not all get an SVE-enabled toolchain for a while, this patch uses macros that generate explicit opcodes in place of assembler mnemonics. Signed-off-by: Dave Martin <dave.mar...@arm.

[PATCH v5 08/30] arm64/sve: System register and exception syndrome definitions

The SVE architecture adds some system registers, ID register fields and a dedicated ESR exception class. This patch adds the appropriate definitions that will be needed by the kernel. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org&

[PATCH v5 19/30] arm64/sve: Preserve SVE registers around kernel-mode NEON use

. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Ard Biesheuvel <ard.biesheu...@linaro.org> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> --- arch/arm64/kernel/fpsimd.c | 6 -- 1 file changed, 4 in

[PATCH v5 11/30] arm64/sve: Signal frame and context structure definition

length, it is not possible to define a fixed C struct to describe all the registers. Instead, Macros are defined in sigcontext.h to facilitate access to the parts of the structure. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc:

[PATCH v5 13/30] arm64/sve: Core task context handling

* fork and clone Code is added to sync data between thread.fpsimd_state and thread.sve_state whenever enabling/disabling SVE, in a manner consistent with the SVE architectural programmer's model. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@ar

[PATCH v5 10/30] arm64/sve: Kconfig update and conditional compilation support

in a later patch, once SVE support is complete enough to be enabled safely. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> --- arch/arm64/Kconfig | 11 +

[PATCH v5 12/30] arm64/sve: Low-level CPU setup

the limit set by ZCR_EL2.) This patch makes the appropriate changes to the EL2 early setup code. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> --- **Dropped at v3** Reviewed-by: Ale

[PATCH v5 05/30] arm64: efi: Add missing Kconfig dependency on KERNEL_MODE_NEON

dependency. This will aid bisection of the patches implementing support for the ARM Scalable Vector Extension (SVE). Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Acked-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Ard Biesh

[PATCH v5 06/30] arm64: Port deprecated instruction emulation to new sysctl interface

rectories explicitly, which is ideal here. This patch ports register_insn_emulation_sysctl() over to the register_sysctl() interface and removes the redundant ctl_table for "abi". Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@l

[PATCH v5 03/30] arm64: signal: Verify extra data is user-readable in sys_rt_sigreturn

the potential for future surprises, this patch does an explicit access_ok() check on the extra data space when parsing an extra_context record. Fixes: 33f082614c34 ("arm64: signal: Allow expansion of the signal frame") Signed-off-by: Dave Martin <dave.mar...@arm.com> --- a

[PATCH v5 04/30] arm64: KVM: Hide unsupported AArch64 CPU features from guests

for AArch32: however, these could be handled in a similar way in future, as necessary. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Marc Zyngier <marc.zyng...@arm.com> Acked-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Christoffer Dall <christoffer.d...@linaro

[PATCH v5 01/30] regset: Add support for dynamically sized regsets

a get_size() implementation. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Oleg Nesterov <o...@redhat.com> Cc: Alexander Viro <v...@zeniv.linux.org.uk> Cc: Thoma

[PATCH v5 02/30] arm64: fpsimd: Correctly annotate exception helpers called from asm

asmlinkage annotations for do_fpsimd_acc() and do_fpsimd_exc(). Signed-off-by: Dave Martin <dave.mar...@arm.com> --- arch/arm64/kernel/fpsimd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 5d547de..e85

[PATCH v5 00/30] ARM Scalable Vector Extension (SVE)

git://linux-arm.org/linux-dm.git sve/v4+fixes Dave Martin (30): regset: Add support for dynamically sized regsets arm64: fpsimd: Correctly annotate exception helpers called from asm arm64: signal: Verify extra data is user-readable in sys_rt_sigreturn arm64: KVM: Hide unsupported AA

Re: [PATCH v4 20/28] arm64/sve: Add prctl controls for userspace vector length management

On Mon, Oct 30, 2017 at 04:12:13PM +, Alex Bennée wrote: > > Dave Martin <dave.mar...@arm.com> writes: > > > On Fri, Oct 27, 2017 at 06:52:50PM +0100, Alex Bennée wrote: > >> > >> Dave Martin <dave.mar...@arm.com> writes: > >> >

Re: [PATCH v4 20/28] arm64/sve: Add prctl controls for userspace vector length management

On Fri, Oct 27, 2017 at 06:52:50PM +0100, Alex Bennée wrote: > > Dave Martin <dave.mar...@arm.com> writes: > > > This patch adds two arm64-specific prctls, to permit userspace to > > control its vector length: > > > > * PR_SVE_SET_VL: set the thread's SVE

[RFC PATCH v4 28/28] arm64/sve: signal: Include SVE when computing AT_MINSIGSTKSZ

vector length: this determines the maximum size of SVE context block that can be observed in any signal frame for the lifetime of the process. Signed-off-by: Dave Martin <dave.mar...@arm.com> Cc: Ard Biesheuvel <ard.biesheu...@linaro.org> Cc: Alex Bennée <alex.ben...@linaro.org&g

[PATCH v4 15/28] arm64: cpufeature: Move sys_caps_initialised declarations

booting a CPU, so that it can be updated appropriately. This patch simply moves the sys_caps_initialised stuff to the top of the file so that it can be used more widely. There doesn't seem to be a more obvious place to put it. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex

[PATCH v4 10/28] arm64/sve: Low-level CPU setup

the limit set by ZCR_EL2.) This patch makes the appropriate changes to the EL2 early setup code. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> --- **Dropped at v3** Reviewed-by: Ale

[PATCH v4 21/28] arm64/sve: Add sysctl to set the default vector length for new processes

the vector length of any existing process. The intended usage model is that if userspace is known to be fully SVE-tolerant (or a developer is curious to find out) then this parameter can be cranked up during system startup. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex

[PATCH v4 25/28] arm64/sve: Detect SVE and activate runtime support

running on hardware that supports SVE, this enables runtime kernel support for SVE, and allows user tasks to execute SVE instructions and make of the of the SVE-specific user/kernel interface extensions implemented by this series. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by:

[PATCH v4 26/28] arm64/sve: Add documentation

This patch adds basic documentation of the user/kernel interface provided by the for SVE. Signed-off-by: Dave Martin <dave.mar...@arm.com> Cc: Alan Hayward <alan.hayw...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> Cc: Mark Rutland <mark.rutl...@arm.com> Cc: Mi

[PATCH v4 23/28] arm64/sve: KVM: Treat guest SVE use as undefined instruction execution

When trapping forbidden attempts by a guest to use SVE, we want the guest to see a trap consistent with SVE not being implemented. This patch injects an undefined instruction exception into the guest in response to such an exception. Signed-off-by: Dave Martin <dave.mar...@arm.com> Re

[PATCH v4 22/28] arm64/sve: KVM: Prevent guests from using SVE

, since cpu_pm_enter() is supposed to be called only with interrupts disabled. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Christoffer Dall <christoffer.d...@linaro.org> Acked-by: Catalin Marinas <catalin.mari...@ar

[PATCH v4 20/28] arm64/sve: Add prctl controls for userspace vector length management

instructions. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Cc: Alex Bennée <alex.ben...@linaro.org> --- **Dropped at v3** Reviewed-by: Alex Bennée <alex.ben...@linaro.org> due to non-trivial changes/fixes aft

[RFC PATCH v4 27/28] arm64: signal: Report signal frame size to userspace via auxv

s internal SIGFRAME_MAXSZ is supposed to sanity-check against generting frames that we consider _impossibly_ large. In this case, SIGSTKSZ is returned as a "reasonable guess that is at least bigger than MINSIGSTKSZ" and we WARN(). Signed-off-by: Dave Martin <dave.mar...@arm.com> -

[PATCH v4 12/28] arm64/sve: Support vector length resetting for new processes

TIF_SVE_VL_INHERIT to control whether to inherit or reset the vector length. Currently these are inactive. Subsequent patches will provide the capability to configure them. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Cat

[PATCH v4 05/28] arm64: fpsimd: Simplify uses of {set, clear}_ti_thread_flag()

. This should have no impact on behaviour. Signed-off-by: Dave Martin <dave.mar...@arm.com> Reviewed-by: Alex Bennée <alex.ben...@linaro.org> Reviewed-by: Catalin Marinas <catalin.mari...@arm.com> Acked-by: Ard Biesheuvel <ard.biesheu...@linaro.org> --- arch/arm64/kerne

<    3   4   5   6   7   8   9   10   >