Re: [Xen-devel] [PATCH 4/4] xen: Drop un-informative message during boot

Juergen Gross <jgr...@suse.com> writes: > On 21/07/17 12:12, Punit Agrawal wrote: >> Boris Ostrovsky <boris.ostrov...@oracle.com> writes: >> >>> On 07/20/2017 07:04 AM, Punit Agrawal wrote: >>>> On systems that are not booted as a Xen domain, th

Re: [Xen-devel] [PATCH 4/4] xen: Drop un-informative message during boot

Boris Ostrovsky <boris.ostrov...@oracle.com> writes: > On 07/20/2017 07:04 AM, Punit Agrawal wrote: >> On systems that are not booted as a Xen domain, the xenfs driver prints >> the following message during boot. >> >> [3.460595] xenfs: not registeri

[Xen-devel] [PATCH 4/4] xen: Drop un-informative message during boot

-off-by: Punit Agrawal <punit.agra...@arm.com> Cc: Boris Ostrovsky <boris.ostrov...@oracle.com> Cc: Juergen Gross <jgr...@suse.com> --- drivers/xen/xenfs/super.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/xen/xenfs/super.c b/drivers/xen/xenfs/super.c index 967f0693

[Xen-devel] [PATCH 0/4] Drop uninformative messages from bootlog

merged. Thanks, Punit Punit Agrawal (4): arm64/numa: Drop duplicate message mailbox: pcc: Drop uninformative output during boot ACPI / APEI: Drop uninformative messages during boot xen: Drop un-informative message during boot arch/arm64/mm/numa.c | 7 +-- drivers/acpi/apei

[Xen-devel] Notes from PCI Passthrough design discussion at Xen Summit

I took some notes for the PCI Passthrough design discussion at Xen Summit. Due to the wide range of topics covered, the notes got sparser towards the end of the session. I've tried to attribute names against comments but have very likely got things mixed up. Apologies in advance. Although the

[Xen-devel] [For Xen-4.10 PATCH] memory: Re-introduce an erroneously dropped line

the missing hunk. Fixes: 726b737574 ("Avoid excess icache flushes in populate_physmap() before domain has been created") Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/common/memory.c | 1 + 1 file changed, 1 insertion(+) diff --git a/xen/common/memory.c b/xen/commo

Re: [Xen-devel] [For Xen-4.10 PATCH v2 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

Julien Grall <julien.gr...@arm.com> writes: > On 07/06/17 12:19, Andrew Cooper wrote: >> On 26/05/17 12:14, Punit Agrawal wrote: >>> @@ -211,7 +221,6 @@ static void populate_physmap(struct memop_args *a) >>> } >>> >>>

Re: [Xen-devel] [For Xen-4.10 PATCH v2 0/3] Reduce unnecessary icache maintenance operations

Stefano Stabellini <sstabell...@kernel.org> writes: > On Tue, 6 Jun 2017, Julien Grall wrote: >> On 26/05/17 12:14, Punit Agrawal wrote: >> > Hi, >> >> Hi, >> >> It looks like this patch series has been fully acked. Can someone apply it? > >

[Xen-devel] [For Xen-4.10 PATCH] Ensure invalidate_icache() definition is visible only when !__ASSEMBLY__

Avoid excess icache flushes in populate_physmap() before domain has been created") Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- Hi Stefano, Jan, This commit fixes the build breakage in staging for me. I'm not sure whether staging gets rebased so sending this as a separate comm

Re: [Xen-devel] [For Xen-4.10 PATCH v2 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

"Jan Beulich" writes: On 26.05.17 at 13:14, wrote: >> --- a/xen/include/asm-x86/page.h >> +++ b/xen/include/asm-x86/page.h >> @@ -375,6 +375,14 @@ perms_strictly_increased(uint32_t old_flags, uint32_t >> new_flags) >> >> #define PAGE_ALIGN(x)

[Xen-devel] [For Xen-4.10 PATCH v2 2/3] arm: p2m: Prevent redundant icache flushes

icache operations by flush_page_to_ram(). Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Reviewed-by: Stefano Stabellini <sstabell...@kernel.org> --- xen/arch/arm/p2m.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/xen/arch/arm/p2m.c b/xen/arch/arm/p2m.c inde

[Xen-devel] [For Xen-4.10 PATCH v2 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

ne concern is the lack of synchronisation around testing for "creation_finished". But it seems, in practice the window where it is out of sync should be small enough to not matter. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Reviewed-by: Stefano Stabellini <sstabell..

[Xen-devel] [For Xen-4.10 PATCH v2 1/3] Allow control of icache invalidations when calling flush_page_to_ram()

. This is in preparations for adding logic to make the callers perform the necessary icache maintenance operations. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Acked-by: Jan Beulich <jbeul...@suse.com> Reviewed-by: Stefano Stabellini <sstabell...@kernel.org> ---

[Xen-devel] [For Xen-4.10 PATCH v2 0/3] Reduce unnecessary icache maintenance operations

tml [1] https://www.mail-archive.com/xen-devel@lists.xen.org/msg102934.html Punit Agrawal (3): Allow control of icache invalidations when calling flush_page_to_ram() arm: p2m: Prevent redundant icache flushes Avoid excess icache flushes in populate_physmap() before domain has been created

Re: [Xen-devel] [For Xen-4.10 Resend PATCH 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

Stefano Stabellini <sstabell...@kernel.org> writes: > On Mon, 15 May 2017, Punit Agrawal wrote: >> populate_physmap() calls alloc_heap_pages() per requested >> extent. alloc_heap_pages() invalidates the entire icache per >> extent. During domain creation, the icache in

Re: [Xen-devel] [For Xen-4.10 Resend PATCH 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

"Jan Beulich" writes: On 17.05.17 at 18:15, wrote: >> Jan Beulich writes: >> >> On 15.05.17 at 16:10, wrote: --- a/xen/include/asm-x86/page.h +++ b/xen/include/asm-x86/page.h @@ -375,6

Re: [Xen-devel] [For Xen-4.10 Resend PATCH 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

Jan Beulich writes: On 15.05.17 at 16:10, wrote: >> --- a/xen/include/asm-x86/page.h >> +++ b/xen/include/asm-x86/page.h >> @@ -375,6 +375,10 @@ perms_strictly_increased(uint32_t old_flags, uint32_t >> new_flags) >> >> #define PAGE_ALIGN(x)

[Xen-devel] [For Xen-4.10 Resend PATCH 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

ne concern is the lack of synchronisation around testing for "creation_finished". But it seems, in practice the window where it is out of sync should be small enough to not matter. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/common/memory.c| 31 ++

[Xen-devel] [For Xen-4.10 Resend PATCH 2/3] arm: p2m: Prevent redundant icache flushes

icache operations by flush_page_to_ram(). Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Reviewed-by: Stefano Stabellini <sstabell...@kernel.org> --- xen/arch/arm/p2m.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/xen/arch/arm/p2m.c b/xen/arch/arm/p2m.c inde

[Xen-devel] [For Xen-4.10 Resend PATCH 1/3] Allow control of icache invalidations when calling flush_page_to_ram()

. This is in preparations for adding logic to make the callers perform the necessary icache maintenance operations. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/arch/arm/mm.c | 5 +++-- xen/arch/arm/p2m.c | 2 +- xen/common/page_alloc.c| 2 +

[Xen-devel] [For Xen-4.10 Resend PATCH 0/3] Reduce unnecessary icache maintenance operations

in populate_physmap() during domain creation. As I couldn't find icache maintenance operations for x86, an empty helper is introduced. Thanks, Punit [0] https://www.mail-archive.com/xen-devel@lists.xen.org/msg102934.html Punit Agrawal (3): Allow control of icache invalidations when calling

Re: [Xen-devel] [For Xen-4.10 PATCH 0/3] Reduce unnecessary icache maintenance operations

Looks like I've got Konrad's email wrong. Please ignore this thread. I'll repost with the right address. :( Apologies for the spam. Punit Punit Agrawal <punit.agra...@arm.com> writes: > Hi, > > This series was previously posted as an RFC[0]. An issue was discovered >

[Xen-devel] [For Xen-4.10 PATCH 3/3] Avoid excess icache flushes in populate_physmap() before domain has been created

ne concern is the lack of synchronisation around testing for "creation_finished". But it seems, in practice the window where it is out of sync should be small enough to not matter. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/common/memory.c| 31 ++

[Xen-devel] [For Xen-4.10 PATCH 0/3] Reduce unnecessary icache maintenance operations

in populate_physmap() during domain creation. As I couldn't find icache maintenance operations for x86, an empty helper is introduced. Thanks, Punit [0] https://www.mail-archive.com/xen-devel@lists.xen.org/msg102934.html Punit Agrawal (3): Allow control of icache invalidations when calling

[Xen-devel] [For Xen-4.10 PATCH 2/3] arm: p2m: Prevent redundant icache flushes

icache operations by flush_page_to_ram(). Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Reviewed-by: Stefano Stabellini <sstabell...@kernel.org> --- xen/arch/arm/p2m.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/xen/arch/arm/p2m.c b/xen/arch/arm/p2m.c inde

[Xen-devel] [For Xen-4.10 PATCH 1/3] Allow control of icache invalidations when calling flush_page_to_ram()

. This is in preparations for adding logic to make the callers perform the necessary icache maintenance operations. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/arch/arm/mm.c | 5 +++-- xen/arch/arm/p2m.c | 2 +- xen/common/page_alloc.c| 2 +

Re: [Xen-devel] [For Xen-4.10 RFC PATCH 3/3] Prevent redundant icache flushes in populate_physmap()

Hi Julien, Julien Grall <julien.gr...@arm.com> writes: > Hi Punit, > > Sorry for the late answer. > > On 31/03/17 11:24, Punit Agrawal wrote: >> populate_physmap() calls alloc_heap_pages() per requested extent. As >> alloc_heap_pages() performs icache

Re: [Xen-devel] [PATCH v2 for-4.9] xen/arm: Don't unflatten DT when booting with ACPI

Stefano Stabellini <sstabell...@kernel.org> writes: > On Fri, 21 Apr 2017, Punit Agrawal wrote: >> Unflattening the device tree when booting with "acpi=force" leads to the >> following stack trace on AMD Seattle platform - >> >> (XEN) Xen

[Xen-devel] [PATCH v2 for-4.9] xen/arm: Don't unflatten DT when booting with ACPI

nflatten the device tree only when acpi is disabled. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> Reviewed-by: Julien Grall <julien.gr...@arm.com> --- v1 -> v2 * Changed tab to spaces * Added tag --- xen/arch/arm/setup.c | 12 +++- 1 file changed, 7 insertions(+), 5 deletion

[Xen-devel] [PATCH] xen/arm: Don't unflatten DT when booting with ACPI

nflatten the device tree only when acpi is disabled. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/arch/arm/setup.c | 12 +++- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/xen/arch/arm/setup.c b/xen/arch/arm/setup.c index 92a2de6b70..4d62ea8157 100644 --

Re: [Xen-devel] [For Xen-4.10 RFC PATCH 2/3] arm: p2m: Prevent redundant icache flushes

Hi Stefano, Stefano Stabellini <sstabell...@kernel.org> writes: > On Fri, 31 Mar 2017, Punit Agrawal wrote: >> When toolstack requests flushing the caches, flush_page_to_ram() is >> called for each page of the requested domain. This needs to unnecessary >> ica

Re: [Xen-devel] [For Xen-4.10 RFC PATCH 3/3] Prevent redundant icache flushes in populate_physmap()

Wei Liu <wei.l...@citrix.com> writes: > On Fri, Mar 31, 2017 at 02:53:55PM +0100, Punit Agrawal wrote: > [...] >> >> Correct! >> >> invalidate_icache() flushes the entire instruction cache which ends up >> being called each time flush_page_to

Re: [Xen-devel] [For Xen-4.10 RFC PATCH 3/3] Prevent redundant icache flushes in populate_physmap()

Hi Wei, Thanks for taking a look at this RFC. Responses/questions below... Wei Liu <wei.l...@citrix.com> writes: > On Fri, Mar 31, 2017 at 11:24:24AM +0100, Punit Agrawal wrote: >> populate_physmap() calls alloc_heap_pages() per requested extent. As >> alloc_heap_pa

[Xen-devel] [For Xen-4.10 RFC PATCH 1/3] Allow control of icache invalidations when calling flush_page_to_ram()

. This is in preparations for adding logic to make the callers perform the necessary icache maintenance operations. Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/arch/arm/mm.c | 5 +++-- xen/arch/arm/p2m.c | 2 +- xen/common/page_alloc.c| 2 +

[Xen-devel] [For Xen-4.10 RFC PATCH 2/3] arm: p2m: Prevent redundant icache flushes

icache operations by flush_page_to_ram(). Signed-off-by: Punit Agrawal <punit.agra...@arm.com> --- xen/arch/arm/p2m.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/xen/arch/arm/p2m.c b/xen/arch/arm/p2m.c index 76cd1c34f3..8136522ed8 100644 --- a/xen/arch/arm/p2m.c +++

[Xen-devel] [For Xen-4.10 RFC PATCH 0/3] Reduce unnecessary icache maintenance operations

) might not be equivalent. This is my first contribution to Xen, so please go gentle if I've missed something obvious. Thanks, Punit Punit Agrawal (3): Allow control of icache invalidations when calling flush_page_to_ram() arm: p2m: Prevent redundant icache flushes Prevent redundant icache

[Xen-devel] [For Xen-4.10 RFC PATCH 3/3] Prevent redundant icache flushes in populate_physmap()

a new flag "MEMF_no_icache_flush" which can be used prevent alloc_heap_pages() to perform unnecessary icache maintenance operations. Use the flag in populate_physmap() and perform the required icache maintenance function at the end of the operation. Signed-off-by: Punit Agrawal &

Re: [Xen-devel] Xen on ARM IRQ latency and scheduler overhead

Dario Faggioli writes: > On Fri, 2017-02-17 at 19:44 +, Julien Grall wrote: >> On 02/17/2017 06:40 PM, Dario Faggioli wrote: >> > Does ARM >> > have frequency scaling (I did remember something on xen-devel, but >> > I am >> > not sure whether it landed upstream)?