[PATCH 0/3] latest cpufeatures patch series

[PATCH 0/3] latest cpufeatures patch series

[Nicholas Piggin]

Hi,

This is the latest cpufeatures series for Linux. It should be
close to merge now I hope, but another round of review would
be good.

If we can merge the first minor patches and get those out of
the way it would be helpful.

Thanks,
Nick

[PATCH 1/3] powerpc/64s: POWER9 no LPCR VRMASD bits

[Nicholas Piggin]

POWER9/ISAv3 has no VRMASD field in LPCR. Don't set reserved bits.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/kernel/cpu_setup_power.S | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 7fe8c79e6937..3737685e1f54 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -29,7 +29,7 @@ _GLOBAL(__setup_cpu_power7)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA206
 	bl	__init_tlb_power7
 	mtlr	r11
 	blr
@@ -42,7 +42,7 @@ _GLOBAL(__restore_cpu_power7)
 	li	r0,0
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA206
 	bl	__init_tlb_power7
 	mtlr	r11
 	blr
@@ -59,7 +59,7 @@ _GLOBAL(__setup_cpu_power8)
 	mtspr	SPRN_LPID,r0
 	mfspr	r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
 	bl	__init_PMU_HV
@@ -80,7 +80,7 @@ _GLOBAL(__restore_cpu_power8)
 	mtspr	SPRN_LPID,r0
 	mfspr   r3,SPRN_LPCR
 	ori	r3, r3, LPCR_PECEDH
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA206
 	bl	__init_HFSCR
 	bl	__init_tlb_power8
 	bl	__init_PMU_HV
@@ -103,7 +103,7 @@ _GLOBAL(__setup_cpu_power9)
 	or	r3, r3, r4
 	LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
 	andc	r3, r3, r4
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
 	bl	__init_PMU_HV
@@ -126,7 +126,7 @@ _GLOBAL(__restore_cpu_power9)
 	or	r3, r3, r4
 	LOAD_REG_IMMEDIATE(r4, LPCR_UPRT | LPCR_HR)
 	andc	r3, r3, r4
-	bl	__init_LPCR
+	bl	__init_LPCR_ISA300
 	bl	__init_HFSCR
 	bl	__init_tlb_power9
 	bl	__init_PMU_HV
@@ -144,7 +144,7 @@ __init_hvmode_206:
 	std	r5,CPU_SPEC_FEATURES(r4)
 	blr
 
-__init_LPCR:
+__init_LPCR_ISA206:
 	/* Setup a sane LPCR:
 	 *   Called with initial LPCR in R3
 	 *
@@ -157,6 +157,11 @@ __init_LPCR:
 	 *
 	 * Other bits untouched for now
 	 */
+	li	r5,0x10
+	rldimi	r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
+
+	/* POWER9 has no VRMASD */
+__init_LPCR_ISA300:
 	li	r5,1
 	rldimi	r3,r5, LPCR_LPES_SH, 64-LPCR_LPES_SH-2
 	ori	r3,r3,(LPCR_PECE0|LPCR_PECE1|LPCR_PECE2)
@@ -165,8 +170,6 @@ __init_LPCR:
 	clrrdi	r3,r3,1		/* clear HDICE */
 	li	r5,4
 	rldimi	r3,r5, LPCR_VC_SH, 0
-	li	r5,0x10
-	rldimi	r3,r5, LPCR_VRMASD_SH, 64-LPCR_VRMASD_SH-5
 	mtspr	SPRN_LPCR,r3
 	isync
 	blr
-- 
2.11.0

[PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Nicholas Piggin]

Introduce primitives for FDT parsing. These will be used for powerpc
cpufeatures node scanning, which has quite complex structure but should
be processed early.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 drivers/of/fdt.c       | 39 +++++++++++++++++++++++++++++++++++++++
 include/linux/of_fdt.h |  6 ++++++
 2 files changed, 45 insertions(+)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index e5ce4b59e162..a45854fe5156 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -754,6 +754,37 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 }
 
 /**
+ * of_scan_flat_dt_subnodes - scan sub-nodes of a node call callback on each.
+ * @it: callback function
+ * @data: context data pointer
+ *
+ * This function is used to scan sub-nodes of a node.
+ */
+int __init of_scan_flat_dt_subnodes(unsigned long node,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data)
+{
+	const void *blob = initial_boot_params;
+	const char *pathp;
+	int offset, rc = 0;
+
+	offset = node;
+        for (offset = fdt_first_subnode(blob, offset);
+             offset >= 0 && !rc;
+             offset = fdt_next_subnode(blob, offset)) {
+
+		pathp = fdt_get_name(blob, offset, NULL);
+		if (*pathp == '/')
+			pathp = kbasename(pathp);
+		rc = it(offset, pathp, data);
+	}
+	return rc;
+}
+
+
+/**
  * of_get_flat_dt_subnode_by_name - get the subnode by given name
  *
  * @node: the parent node
@@ -812,6 +843,14 @@ int __init of_flat_dt_match(unsigned long node, const char *const *compat)
 	return of_fdt_match(initial_boot_params, node, compat);
 }
 
+/**
+ * of_get_flat_dt_prop - Given a node in the flat blob, return the phandle
+ */
+uint32_t __init of_get_flat_dt_phandle(unsigned long node)
+{
+	return fdt_get_phandle(initial_boot_params, node);
+}
+
 struct fdt_scan_status {
 	const char *name;
 	int namelen;
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 271b3fdf0070..1dfbfd0d8040 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -54,6 +54,11 @@ extern char __dtb_end[];
 extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
 				     int depth, void *data),
 			   void *data);
+extern int of_scan_flat_dt_subnodes(unsigned long node,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data);
 extern int of_get_flat_dt_subnode_by_name(unsigned long node,
 					  const char *uname);
 extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
@@ -62,6 +67,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
 extern int of_get_flat_dt_size(void);
+extern uint32_t of_get_flat_dt_phandle(unsigned long node);
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
-- 
2.11.0

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Rob Herring]

On Wed, Apr 5, 2017 at 9:32 AM, Nicholas Piggin <npiggin@gmail.com> wrote:
> On Wed, 5 Apr 2017 08:35:06 -0500
> Rob Herring <robh+dt@kernel.org> wrote:
>
>> On Wed, Apr 5, 2017 at 7:37 AM, Nicholas Piggin <npiggin@gmail.com> wrote:
>> > Introduce primitives for FDT parsing. These will be used for powerpc
>> > cpufeatures node scanning, which has quite complex structure but should
>> > be processed early.
>>
>> Have you looked at unflattening the FDT earlier?
>
> Hi, thanks for taking a look. Did you mean to trim the cc list?

Ugg, no. I've added everyone back.

> It may be possible but I'd like to avoid it if we can. There might
> turn out to be some errata or feature that requires early setup. And
> the current cpu feature parsing code does it with flat dt.

Well, I'd like to avoid expanding usage of flat DT parsing in the
kernel. But you could just put this function into arch/powerpc and I'd
never see it, but I like that even less. Mainly, I just wanted to
raise the point.

Your argument works until you need that setup in assembly code, then
you are in the situation that you need to either handle the setup in
bootloader/firmware or have an simple way to determine that condition.

Rob

>
>> > Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
>> > ---
>> >  drivers/of/fdt.c       | 39 +++++++++++++++++++++++++++++++++++++++
>> >  include/linux/of_fdt.h |  6 ++++++
>> >  2 files changed, 45 insertions(+)
>> >
>> > diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
>> > index e5ce4b59e162..a45854fe5156 100644
>> > --- a/drivers/of/fdt.c
>> > +++ b/drivers/of/fdt.c
>> > @@ -754,6 +754,37 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
>> >  }
>> >
>> >  /**
>> > + * of_scan_flat_dt_subnodes - scan sub-nodes of a node call callback on each.
>> > + * @it: callback function
>> > + * @data: context data pointer
>> > + *
>> > + * This function is used to scan sub-nodes of a node.
>> > + */
>> > +int __init of_scan_flat_dt_subnodes(unsigned long node,
>> > +                                   int (*it)(unsigned long node,
>> > +                                             const char *uname,
>> > +                                             void *data),
>> > +                                   void *data)
>> > +{
>> > +       const void *blob = initial_boot_params;
>> > +       const char *pathp;
>> > +       int offset, rc = 0;
>> > +
>> > +       offset = node;
>> > +        for (offset = fdt_first_subnode(blob, offset);
>> > +             offset >= 0 && !rc;
>> > +             offset = fdt_next_subnode(blob, offset)) {
>>
>> fdt_for_each_subnode()
>
> Got it.
>
>>
>> > +
>> > +               pathp = fdt_get_name(blob, offset, NULL);
>> > +               if (*pathp == '/')
>> > +                       pathp = kbasename(pathp);
>>
>> Seems a bit odd that you parse the name in this function. Perhaps the
>> caller should do that, or if you want subnodes matching a certain
>> name, then do the matching here. But you didn't copy me on the rest of
>> the series, so I don't know how you are using this.
>
> Hmm, it was a while since writing that part. I guess I just copied
> of_scan_flat_dt interface.
>
> Caller is in this patch:
>
> https://patchwork.ozlabs.org/patch/747262/
>
> I'll include you in subsequent post if you prefer.
>
> Thanks,
> Nick

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Benjamin Herrenschmidt]

On Wed, 2017-04-05 at 10:58 -0500, Rob Herring wrote:
> Well, I'd like to avoid expanding usage of flat DT parsing in the
> kernel. But you could just put this function into arch/powerpc and I'd
> never see it, but I like that even less. Mainly, I just wanted to
> raise the point.
> 
> Your argument works until you need that setup in assembly code, then
> you are in the situation that you need to either handle the setup in
> bootloader/firmware or have an simple way to determine that condition.

The main issue is that changing that is a very very invasive change in
an extremely fragile and rather nasty area of code shared by 32 and 64-
bit for which we don't even have easy access to all the machines to
test with anymore :)

It's probably not impossible, but it would delay the new cpu feature
stuff that Nick is making by a lot, probably monthes, making it nearly
impossible to get back into distros etc... 

So while it might be something to consider, I would definitely keep
that as a separate unit of work to do later.

Cheers,
Ben.

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Nicholas Piggin]

On Thu, 06 Apr 2017 06:58:01 +1000
Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:

> On Wed, 2017-04-05 at 10:58 -0500, Rob Herring wrote:
> > Well, I'd like to avoid expanding usage of flat DT parsing in the
> > kernel. But you could just put this function into arch/powerpc and I'd
> > never see it, but I like that even less. Mainly, I just wanted to
> > raise the point.
> > 
> > Your argument works until you need that setup in assembly code, then
> > you are in the situation that you need to either handle the setup in
> > bootloader/firmware or have an simple way to determine that condition.  
> 
> The main issue is that changing that is a very very invasive change in
> an extremely fragile and rather nasty area of code shared by 32 and 64-
> bit for which we don't even have easy access to all the machines to
> test with anymore :)
> 
> It's probably not impossible, but it would delay the new cpu feature
> stuff that Nick is making by a lot, probably monthes, making it nearly
> impossible to get back into distros etc... 
> 
> So while it might be something to consider, I would definitely keep
> that as a separate unit of work to do later.

Yeah, it's no longer a "drop in" replacement for existing features
testing if we do this, which makes it hard to backport too (we will
need this for compatibility with future firmware, so it will have to
go into distro kernels.)

Given that it's quite a small addition to of/fdt code, hopefully
that gives you a reasonable justification to accept it.

If you prefer not to, that's okay, but I think we would have to carry
it in arch/powerpc at least for a time, because of the schedule we're
working to for POWER9 enablement. As a longer term item I agree with you
and Ben, it would be worth considering unflattening earlier.

Thanks,
Nick

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Rob Herring]

On Wed, Apr 5, 2017 at 7:38 PM, Nicholas Piggin <npiggin@gmail.com> wrote:
> On Thu, 06 Apr 2017 06:58:01 +1000
> Benjamin Herrenschmidt <benh@kernel.crashing.org> wrote:
>
>> On Wed, 2017-04-05 at 10:58 -0500, Rob Herring wrote:
>> > Well, I'd like to avoid expanding usage of flat DT parsing in the
>> > kernel. But you could just put this function into arch/powerpc and I'd
>> > never see it, but I like that even less. Mainly, I just wanted to
>> > raise the point.
>> >
>> > Your argument works until you need that setup in assembly code, then
>> > you are in the situation that you need to either handle the setup in
>> > bootloader/firmware or have an simple way to determine that condition.
>>
>> The main issue is that changing that is a very very invasive change in
>> an extremely fragile and rather nasty area of code shared by 32 and 64-
>> bit for which we don't even have easy access to all the machines to
>> test with anymore :)
>>
>> It's probably not impossible, but it would delay the new cpu feature
>> stuff that Nick is making by a lot, probably monthes, making it nearly
>> impossible to get back into distros etc...
>>
>> So while it might be something to consider, I would definitely keep
>> that as a separate unit of work to do later.
>
> Yeah, it's no longer a "drop in" replacement for existing features
> testing if we do this, which makes it hard to backport too (we will
> need this for compatibility with future firmware, so it will have to
> go into distro kernels.)
>
> Given that it's quite a small addition to of/fdt code, hopefully
> that gives you a reasonable justification to accept it.
>
> If you prefer not to, that's okay, but I think we would have to carry
> it in arch/powerpc at least for a time, because of the schedule we're
> working to for POWER9 enablement. As a longer term item I agree with you
> and Ben, it would be worth considering unflattening earlier.

As I mentioned, keeping it in arch/powerpc I like even less. So this is fine.

Rob

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Nicholas Piggin]

On Thu, 6 Apr 2017 09:09:41 -0500
Rob Herring <robh+dt@kernel.org> wrote:

> On Wed, Apr 5, 2017 at 7:38 PM, Nicholas Piggin <npiggin@gmail.com> wrote:
> > Given that it's quite a small addition to of/fdt code, hopefully
> > that gives you a reasonable justification to accept it.
> >
> > If you prefer not to, that's okay, but I think we would have to carry
> > it in arch/powerpc at least for a time, because of the schedule we're
> > working to for POWER9 enablement. As a longer term item I agree with you
> > and Ben, it would be worth considering unflattening earlier.  
> 
> As I mentioned, keeping it in arch/powerpc I like even less. So this is fine.

Here is the patch with the change you suggested. Can I add your
ack and send it via the powerpc tree with the change that uses
these interfaces?

Thanks,
Nick

---
 drivers/of/fdt.c       | 38 ++++++++++++++++++++++++++++++++++++++
 include/linux/of_fdt.h |  6 ++++++
 2 files changed, 44 insertions(+)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index e5ce4b59e162..961ca97072a9 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -754,6 +754,36 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 }
 
 /**
+ * of_scan_flat_dt_subnodes - scan sub-nodes of a node call callback on each.
+ * @it: callback function
+ * @data: context data pointer
+ *
+ * This function is used to scan sub-nodes of a node.
+ */
+int __init of_scan_flat_dt_subnodes(unsigned long parent,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data)
+{
+	const void *blob = initial_boot_params;
+	int node;
+
+	fdt_for_each_subnode(node, blob, parent) {
+		const char *pathp;
+		int rc;
+
+		pathp = fdt_get_name(blob, node, NULL);
+		if (*pathp == '/')
+			pathp = kbasename(pathp);
+		rc = it(node, pathp, data);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+/**
  * of_get_flat_dt_subnode_by_name - get the subnode by given name
  *
  * @node: the parent node
@@ -812,6 +842,14 @@ int __init of_flat_dt_match(unsigned long node, const char *const *compat)
 	return of_fdt_match(initial_boot_params, node, compat);
 }
 
+/**
+ * of_get_flat_dt_prop - Given a node in the flat blob, return the phandle
+ */
+uint32_t __init of_get_flat_dt_phandle(unsigned long node)
+{
+	return fdt_get_phandle(initial_boot_params, node);
+}
+
 struct fdt_scan_status {
 	const char *name;
 	int namelen;
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 271b3fdf0070..1dfbfd0d8040 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -54,6 +54,11 @@ extern char __dtb_end[];
 extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
 				     int depth, void *data),
 			   void *data);
+extern int of_scan_flat_dt_subnodes(unsigned long node,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data);
 extern int of_get_flat_dt_subnode_by_name(unsigned long node,
 					  const char *uname);
 extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
@@ -62,6 +67,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
 extern int of_get_flat_dt_size(void);
+extern uint32_t of_get_flat_dt_phandle(unsigned long node);
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
-- 
2.11.0

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Rob Herring]

On Mon, Apr 10, 2017 at 12:43 AM, Nicholas Piggin <npiggin@gmail.com> wrote:
> On Thu, 6 Apr 2017 09:09:41 -0500
> Rob Herring <robh+dt@kernel.org> wrote:
>
>> On Wed, Apr 5, 2017 at 7:38 PM, Nicholas Piggin <npiggin@gmail.com> wrote:
>> > Given that it's quite a small addition to of/fdt code, hopefully
>> > that gives you a reasonable justification to accept it.
>> >
>> > If you prefer not to, that's okay, but I think we would have to carry
>> > it in arch/powerpc at least for a time, because of the schedule we're
>> > working to for POWER9 enablement. As a longer term item I agree with you
>> > and Ben, it would be worth considering unflattening earlier.
>>
>> As I mentioned, keeping it in arch/powerpc I like even less. So this is fine.
>
> Here is the patch with the change you suggested. Can I add your
> ack and send it via the powerpc tree with the change that uses
> these interfaces?

Acked-by: Rob Herring <robh@kernel.org>

Re: [PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Michael Ellerman]

Rob Herring <robh+dt@kernel.org> writes:

> On Wed, Apr 5, 2017 at 9:32 AM, Nicholas Piggin <npiggin@gmail.com> wrote:
>> On Wed, 5 Apr 2017 08:35:06 -0500
>> Rob Herring <robh+dt@kernel.org> wrote:
>>
>>> On Wed, Apr 5, 2017 at 7:37 AM, Nicholas Piggin <npiggin@gmail.com> wrote:
>>> > Introduce primitives for FDT parsing. These will be used for powerpc
>>> > cpufeatures node scanning, which has quite complex structure but should
>>> > be processed early.
>>>
>>> Have you looked at unflattening the FDT earlier?
>>
>> Hi, thanks for taking a look. Did you mean to trim the cc list?
>
> Ugg, no. I've added everyone back.
>
>> It may be possible but I'd like to avoid it if we can. There might
>> turn out to be some errata or feature that requires early setup. And
>> the current cpu feature parsing code does it with flat dt.
>
> Well, I'd like to avoid expanding usage of flat DT parsing in the
> kernel. But you could just put this function into arch/powerpc and I'd
> never see it, but I like that even less. Mainly, I just wanted to
> raise the point.
>
> Your argument works until you need that setup in assembly code, then
> you are in the situation that you need to either handle the setup in
> bootloader/firmware or have an simple way to determine that condition.

Where Nick does this FDT parsing is literally the first C code that runs
in the kernel. The MMU is off, we don't even know how much memory we
have, or where it is.

So it's basically impossible to do the unflattening earlier. What we
could do is move the CPU feature setup *later*.

As Ben & Nick said that would be a pretty intrusive change, and
definitely not something we want to do now.

What we could probably do is split some of the flat tree parsing, so
that we discover memory, even just some of it, then unflatten, and then
do more setup using the unflattened tree.

But that will require a lot of delicate work. So we'd definitely like to
do that separately from this series.

cheers

[PATCH 3/3] powerpc/64s: cpufeatures: add initial implementation for cpufeatures

[Nicholas Piggin]

The /cpus/features dt binding describes architected CPU features along
with some compatibility, privilege, and enablement properties that allow
flexibility with discovering and enabling capabilities.

Presence of this feature implies a base level of functionality, then
additional feature nodes advertise the presence of new features.

A given feature and its setup procedure is defined once and used by all
CPUs which are compatible by that feature. Features that follow a
supported "prescription" can be enabled by a hypervisor or OS that
does not understand them natively.

---
Since last post:
- Update to v3.0B ISA.
- Removed PVR tests for MCE and PMU, and add specific features for those.
- Fixed CPU state restore.
- Changed dt bit number specification for hfscr/fscr/aux to LSB0.
- Broke the of/fdt changes into another patch.
- Added a proper dependency checker.
- Resolved most of the register/feature bits differences, made a patch
  for VRMASD.
- Didn't think of a better name.

Before/after this patch differences:

- PPC_FEATURE2_EBB is set independent of PMU init. EBB facility is
  theoretically more general than PMU, I don't think this should be
  a problem?

POWER8 (all mambo issues):
- HFSCR bit 54 and 57 are now clear (mambo sets at init)
- PMAO_BUG is set. This is due to mambo setting architected POWER8 mode
  and POWER8E PVR. Current kernels lose PMAO_BUG bit.
- CI_LARGE_PAGE is now set (mambo boot does not set).

POWER9
- Privileged Doorbell Exit Enable is set in LPCR.

---
 .../devicetree/bindings/powerpc/cpufeatures.txt    | 264 +++++++++
 arch/powerpc/include/asm/cpu_has_feature.h         |   4 +-
 arch/powerpc/include/asm/cpufeatures.h             |  58 ++
 arch/powerpc/include/asm/cputable.h                |   1 +
 arch/powerpc/kernel/Makefile                       |   1 +
 arch/powerpc/kernel/cpufeatures.c                  | 618 +++++++++++++++++++++
 arch/powerpc/kernel/cputable.c                     |  14 +-
 arch/powerpc/kernel/prom.c                         | 297 +++++++++-
 arch/powerpc/kernel/setup-common.c                 |   2 +-
 arch/powerpc/kernel/setup_64.c                     |  21 +-
 10 files changed, 1261 insertions(+), 19 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/powerpc/cpufeatures.txt
 create mode 100644 arch/powerpc/include/asm/cpufeatures.h
 create mode 100644 arch/powerpc/kernel/cpufeatures.c

diff --git a/Documentation/devicetree/bindings/powerpc/cpufeatures.txt b/Documentation/devicetree/bindings/powerpc/cpufeatures.txt
new file mode 100644
index 000000000000..325b263f4cdf
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/cpufeatures.txt
@@ -0,0 +1,264 @@
+powerpc cpu features binding
+============================
+
+The device tree describes supported CPU features as nodes containing
+compatibility and enablement information as properties.
+
+The binding specifies features common to all CPUs in the system.
+Heterogeneous CPU features are not supported at present (such could be added
+by providing nodes with additional features and linking those to particular
+CPUs).
+
+This binding is intended to provide fine grained control of CPU features at
+all levels of the stack (firmware, hypervisor, OS, userspace), with the
+ability for new CPU features to be used by some components without all
+components being upgraded (e.g., a new floating point instruction could be
+used by userspace math library without upgrading kernel and hypervisor).
+
+The binding is passed to the hypervisor by firmware. The hypervisor must
+remove any features that require hypervisor enablement but that it does not
+enable. It must remove any features that depend on removed features. It may
+pass remaining features usable to the OS and PR to guests, depending on
+configuration policy (not specified here).
+
+The modified binding is passed to the guest by hypervisor, with HV bit
+cleared from the usable-mask and the hv-support and hfscr-bit properties
+removed. The guest must similarly rmeove features that require OS enablement
+that it does not enable. The OS may pass PR usable features to userspace via
+ELF AUX vectors AT_HWCAP, AT_HWCAP2, AT_HWCAP3, etc., or use some other
+method (outside the scope of this specification).
+
+The binding will specify a "base" level of features that will be present
+when the cpu features binding exists. Additional features will be explicitly
+specified.
+
+/cpus/features node binding
+---------------------------
+
+Node: features
+
+Description: Container of CPU feature nodes.
+
+The node name must be "features" and it must be a child of the node "/cpus".
+
+The node is optional but should be provided by new firmware.
+
+Each child node of cpufeatures represents an architected CPU feature (e.g.,
+a new set of vector instructions) or an important CPU performance
+characteristic (e.g., fast unaligned memory operations). The specification
+of each feature (instructions, registers, exceptions, etc.) will be
+documented with device tree bindings.
+
+As a rough guide, features should be based on functional groups of changes,
+those that share common enablement requirements, that share particular
+registers or functionality. For example, "POWER9" would be too general, and
+a new feature for every instruction would be too specific. The "summary of
+changes" preface in Power ISA specification is a good guideline for the
+architected features.
+
+Features should be "positive" where possible. For example the presence of a
+feature node should indicate the presence of a new CPU feature (e.g., a
+new instruction or register). An errata workaround for example would then
+remove that feature from the device tree to disable it. "Negative" features
+may be unavoidable in some cases.
+
+Properties:
+
+- device_type
+  Usage: required
+  Value type: string
+  Definition: "cpu-features"
+
+- isa
+  Usage: required
+  Value type: <u32>
+  Definition:
+
+  isa that the CPU is currently running in. This provides instruction set
+  compatibility, less the individual feature nodes. For example, an ISA v3.0
+  implementation that lacks the "transactional-memory" cpufeature node
+  should not use transactional memory facilities.
+
+  Value corresponds to the "Power ISA Version" multiplied by 1000.
+  For example, <3000> corresponds to Version 3.0, <2070> to Version 2.07.
+  The minor digit is available for revisions.
+
+/cpus/features/feature node bindings
+------------------------------------
+
+Node: A string describing an architected CPU feature, e.g., "vsx".
+
+Description: An architected feature supported by the CPUs.
+
+The name of the node will follow a convention such that software will
+match known features by a string comparison with the node name. Presence
+of the node indicates the feature is available to use (XXX: could
+advertise all supported by hardware, with disabled/enabled status
+property).
+
+The name of the child node corresponds to the name of the feature.
+Software will detect known features by string matching.
+
+Properties:
+
+- isa
+  Usage: required
+  Value type: <u32>
+  Definition:
+
+  First level of the Power ISA that the feature appears in.
+  Software should filter out features when constraining the
+  environment to a particular ISA version.
+
+  Value is defined similarly to /cpus/features/isa
+
+- usable-mask
+  Usage: required
+  Value type: <u32> bit mask
+  Definition:
+              Bit numbers are LSB0
+              bit 0 - PR (problem state / user mode)
+              bit 1 - OS (privileged state)
+              bit 2 - HV (hypervisor state)
+              All other bits reserved and should be zero.
+
+  This property describes the privilege levels and/or software components
+  that can use the feature.
+
+  If bit 0 is set, then the hwcap-bit-nr property will exist.
+
+  Reserved bits must be treated as the feature being unsupported.
+
+- hv-support
+  Usage: optional
+  Value type: <u32>
+  Definition:
+              1 -  Custom
+              2 -  HFSCR
+              Other values reserved.
+
+  This property describes the HV privilege state support required to
+  enable the feature. If the property does not exist then no support is
+  required.
+
+  If the value of this property is 1, then the hypervisor must have
+  explicit support for this feature.
+
+  If the value of this property is 2, then the hfscr-bit-nr property
+  will exist.
+
+  Reserved values must be treated as the feature being unsupported.
+
+- os-support
+  Usage: optional
+  Value type: <u32>
+  Definition:
+              1 -  Custom
+              2 -  FSCR
+              Other values reserved.
+
+  This property describes the OS privilege state support required to
+  enable the feature. If the property does not exist then no support is
+  required.
+
+  If the value of this property is 1, then the operating system must
+  have explicit support for this feature.
+
+  If the value of this property is 2, then the fscr-bit-nr property will
+  exist.
+
+  Reserved values must be treated as the feature being unsupported.
+
+- hfscr-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: HFSCR bit position (LSB0)
+
+  This property exists when the hv-support property value is 2. This
+  property describes the bit number in the HFSCR register that the
+  hypervisor must set in order to enable this feature.
+
+- fscr-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: FSCR bit position (LSB0)
+
+  This property exists when the os-support property value is 2. This
+  property describes the bit number in the FSCR register that the
+  operating system must set in order to enable this feature.
+
+- hwcap-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: AUX vector bit position (LSB0)
+
+  This property may exist when the usable-mask property value has bit 0
+  (PR) set. This property describes the bit number that should be set in
+  the ELF AUX hardware capability vectors in order to advertise this
+  feature to userspace. Bits 0-31 correspond to bits 0-31 in AT_HWCAP
+  vector. Bits 32-63 correspond to 0-31 in AT_HWCAP2 vector, and so on.
+  Missing AT_HWCAPx vectors implies that the feature is not enabled or
+  can not be advertised. Operating systems may provide a number of
+  unassigned hardware capability bits to allow for new features to be
+  advertised.
+
+  Some properties representing features created before this binding are
+  advertised to userspace without a one-to-one hwcap bit number may not
+  specify this bit. Operating system will handle those bits specifically.
+  All new features usable by userspace will have a hwcap-bit-nr property.
+
+- dependencies
+  Usage: optional
+  Value type: <prop-encoded-array>
+  Definition:
+
+  If this property exists then it is a list of phandles to cpu feature
+  nodes that must be enabled for this feature to be enabled.
+
+
+Example
+-------
+
+	/cpus/features {
+		device_type = "cpu-features";
+
+		isa = <3020>;
+
+		darn {
+			isa = <3000>;
+			usable-mask = <1 | 2 | 4>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		scv {
+			isa = <3000>;
+			usable-mask = <1 | 2>;
+			os-support = <1>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		stop {
+			isa = <3000>;
+			usable-mask = <2 | 4>;
+			hv-support = <1>;
+			os-support = <1>;
+		};
+
+		vsx2 (hypothetical) {
+			isa = <3010>;
+			usable-mask = <1 | 2 | 4>;
+			hv-support = <1>;
+			os-support = <1>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		vsx2-newinsns {
+			isa = <3020>;
+			usable-mask = <1 | 2 | 4>;
+			os-support = <2>;
+			fscr-bit-nr = <xx>;
+			hwcap-bit-nr = <xx>;
+			dependencies = <&vsx2>;
+		};
+
+	};
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 6e834caa3720..445495aa2bbf 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_POWERPC_CPUFEATURES_H
-#define __ASM_POWERPC_CPUFEATURES_H
+#ifndef __ASM_POWERPC_CPU_HAS_FEATURE_H
+#define __ASM_POWERPC_CPU_HAS_FEATURE_H
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/cpufeatures.h b/arch/powerpc/include/asm/cpufeatures.h
new file mode 100644
index 000000000000..810e7637a2b1
--- /dev/null
+++ b/arch/powerpc/include/asm/cpufeatures.h
@@ -0,0 +1,58 @@
+#ifndef __ASM_POWERPC_CPUFEATURES_H
+#define __ASM_POWERPC_CPUFEATURES_H
+
+/*
+ *  Copyright 2017, IBM Corporation
+ *  cpufeatures is the new way to discover CPU features with /cpus/features
+ *  devicetree. This supersedes PVR based discovery ("cputable"), and other
+ *  devic tree feature advertisement.
+ */
+
+#include <linux/types.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+#include <uapi/asm/cputable.h>
+
+extern void cpufeatures_setup_cpu(void);
+
+/* Types for device tree parsing */
+#define USABLE_PR               (1U << 0)
+#define USABLE_OS               (1U << 1)
+#define USABLE_HV               (1U << 2)
+
+#define HV_SUPPORT_NONE         0
+#define HV_SUPPORT_CUSTOM       1
+#define HV_SUPPORT_HFSCR        2
+
+#define OS_SUPPORT_NONE         0
+#define OS_SUPPORT_CUSTOM       1
+#define OS_SUPPORT_FSCR         2
+
+#define ISA_BASE                0
+#define ISA_V207                2070
+#define ISA_V3                  3000
+
+struct dt_cpu_feature {
+	const char *name;
+	uint32_t isa;
+	uint32_t usable_mask;
+	uint32_t hv_support;
+	uint32_t os_support;
+	uint32_t hfscr_bit_nr;
+	uint32_t fscr_bit_nr;
+	uint32_t hwcap_bit_nr;
+	/* fdt parsing */
+	unsigned long node;
+	uint32_t phandle;
+	int enabled;
+	int disabled;
+};
+
+extern void cpufeatures_setup_start(u32 isa);
+extern int cpufeatures_process_feature(struct dt_cpu_feature *f);
+extern void cpufeatures_setup_finished(void);
+
+/* kernel/prom.c */
+extern int early_init_devtree_check_cpu_features_exists(void);
+
+#endif
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index ab68d0ee7725..10b9a4be3434 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -118,6 +118,7 @@ extern struct cpu_spec		*cur_cpu_spec;
 
 extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
 
+extern void set_cur_cpu_spec(struct cpu_spec *s);
 extern struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr);
 extern void do_feature_fixups(unsigned long value, void *fixup_start,
 			      void *fixup_end);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 811f441a125f..cc3584820220 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -44,6 +44,7 @@ obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 obj-$(CONFIG_VDSO32)		+= vdso32/
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)	+= hw_breakpoint.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_ppc970.o cpu_setup_pa6t.o
+obj-$(CONFIG_PPC_BOOK3S_64)	+= cpufeatures.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= cpu_setup_power.o
 obj-$(CONFIG_PPC_BOOK3S_64)	+= mce.o mce_power.o
 obj-$(CONFIG_PPC_BOOK3E_64)	+= exceptions-64e.o idle_book3e.o
diff --git a/arch/powerpc/kernel/cpufeatures.c b/arch/powerpc/kernel/cpufeatures.c
new file mode 100644
index 000000000000..99ebf3f2dca7
--- /dev/null
+++ b/arch/powerpc/kernel/cpufeatures.c
@@ -0,0 +1,618 @@
+/*
+ *  Copyright 2017, IBM Corporation
+ */
+
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/jump_label.h>
+
+#include <asm/cpufeatures.h>
+#include <asm/cputable.h>
+#include <asm/prom.h>		/* for PTRRELOC on ARCH=ppc */
+#include <asm/oprofile_impl.h>
+#include <asm/mmu.h>
+#include <asm/setup.h>
+
+#ifndef CONFIG_PPC_BOOK3S_64
+#error "BOOK3S_64 only"
+#endif
+
+#ifdef DEBUG
+#define DBG(fmt...) pr_err(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+#define CPU_FTRS_BASE \
+	   (CPU_FTR_USE_TB | \
+	    CPU_FTR_LWSYNC | \
+	    CPU_FTR_FPU_UNAVAILABLE |\
+	    CPU_FTR_NODSISRALIGN |\
+	    CPU_FTR_NOEXECUTE |\
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS |\
+	    CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_206 |\
+	    CPU_FTR_ARCH_207S)
+
+#define MMU_FTRS_HASH_BASE (MMU_FTRS_POWER8)
+
+#define COMMON_USER_BASE	(PPC_FEATURE_32 | PPC_FEATURE_64 | \
+				 PPC_FEATURE_ARCH_2_06 |\
+				 PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER2_BASE	(PPC_FEATURE2_ARCH_2_07 | \
+				 PPC_FEATURE2_ISEL)
+/*
+ * Set up the base CPU
+ */
+
+extern void __flush_tlb_power8(unsigned int action);
+extern void __flush_tlb_power9(unsigned int action);
+extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
+
+static int hv_mode;
+
+static struct {
+	u64	hfscr;
+	u64	fscr;
+	u64	lpcr;
+} system_registers;
+
+static void (*init_pm_registers)(void);
+
+static void __restore_cpu_cpufeatures(void)
+{
+	if (hv_mode) {
+		mtspr(SPRN_LPID, 0);
+		mtspr(SPRN_HFSCR, system_registers.hfscr);
+	}
+	mtspr(SPRN_FSCR, system_registers.fscr);
+	mtspr(SPRN_LPCR, system_registers.lpcr);
+
+	if (init_pm_registers)
+		init_pm_registers();
+}
+
+void __init cpufeatures_setup_cpu(void)
+{
+	/* XXX: CPU name gets populated from device tree, but that's not
+	 * backward compatible if anything parses it. Must special case for
+	 * P8/9 and get from DT in future */
+	static char cpu_name_array[32] = "PowerPC (unknown)";
+	struct cpu_spec s = {
+		.cpu_name		= cpu_name_array,
+		.cpu_features		= CPU_FTRS_BASE,
+		.cpu_user_features	= COMMON_USER_BASE,
+		.cpu_user_features2	= COMMON_USER2_BASE,
+		.mmu_features		= 0,
+		.icache_bsize		= 32, /* minimum block size, fixed by */
+		.dcache_bsize		= 32, /* cache info init.             */
+		.num_pmcs		= 0,
+		.pmc_type		= PPC_PMC_DEFAULT,
+		.oprofile_cpu_type	= NULL,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= NULL,
+		.cpu_restore		= __restore_cpu_cpufeatures,
+		.flush_tlb		= NULL,
+		.machine_check_early	= NULL,
+		.platform		= NULL,
+	};
+
+	set_cur_cpu_spec(&s);
+
+	/* Initialize the base environment -- clear FSCR/HFSCR.  */
+	hv_mode = !!(mfmsr() & MSR_HV);
+	if (hv_mode)
+		mtspr(SPRN_HFSCR, 0);
+	mtspr(SPRN_FSCR, 0);
+}
+
+static int __init feat_try_enable_unknown(struct dt_cpu_feature *f)
+{
+	if (f->hv_support == HV_SUPPORT_NONE) {
+	} else if (f->hv_support == HV_SUPPORT_HFSCR) {
+		u64 hfscr = mfspr(SPRN_HFSCR);
+		hfscr |= 1UL << f->hfscr_bit_nr;
+		mtspr(SPRN_HFSCR, hfscr);
+	} else {
+		return 0;
+	}
+
+	if (f->os_support == OS_SUPPORT_NONE) {
+	} else if (f->os_support == OS_SUPPORT_FSCR) {
+		u64 fscr = mfspr(SPRN_FSCR);
+		fscr |= 1UL << f->fscr_bit_nr;
+		mtspr(SPRN_FSCR, fscr);
+	} else {
+		return 0;
+	}
+
+	if ((f->usable_mask & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_enable(struct dt_cpu_feature *f)
+{
+	if (f->hv_support) {
+		if (f->hfscr_bit_nr != -1) {
+			u64 hfscr = mfspr(SPRN_HFSCR);
+			hfscr |= 1UL << f->hfscr_bit_nr;
+			mtspr(SPRN_HFSCR, hfscr);
+		}
+	}
+
+	if (f->os_support) {
+		if (f->fscr_bit_nr != -1) {
+			u64 fscr = mfspr(SPRN_FSCR);
+			fscr |= 1UL << f->fscr_bit_nr;
+			mtspr(SPRN_FSCR, fscr);
+		}
+	}
+
+	if ((f->usable_mask & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_disable(struct dt_cpu_feature *f)
+{
+	return 0;
+}
+
+static int __initdata prereq_pece_msgp = 0;
+
+static int __init feat_enable_hv(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	if (!hv_mode) {
+		pr_err("CPU feature hypervisor present in device tree but HV mode not enabled in the CPU. Ignoring.\n");
+		return 0;
+	}
+
+	mtspr(SPRN_LPID, 0);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &=  ~LPCR_LPES0; /* HV external interrupts */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+
+	return 1;
+}
+
+static int __init feat_enable_le(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_TRUE_LE;
+	return 1;
+}
+
+static int __init feat_enable_smt(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_SMT;
+	return 1;
+}
+
+static int __init feat_enable_idle_nap(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISA 207 */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_align_dsisr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_NODSISRALIGN;
+
+	return 1;
+}
+
+static int __init feat_enable_idle_stop(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISA 300 */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	prereq_pece_msgp++;
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+
+	/* VRMASD */
+	lpcr |= LPCR_VPM0;
+	lpcr &= ~LPCR_VPM1;
+	lpcr |= 0x10UL << LPCR_VRMASD_SH; /* L=1 LP=00 */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+
+static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_RADIX_MMU
+	cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_dscr(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	feat_enable(f);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_DPFD;
+	lpcr |=  (4UL << LPCR_DPFD_SH);
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static void hfscr_pm_enable(void)
+{
+	u64 hfscr = mfspr(SPRN_HFSCR);
+	hfscr |= PPC_BIT(60);
+	mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_pm_power8(void)
+{
+	if (hv_mode) {
+		mtspr(SPRN_MMCRC, 0);
+		mtspr(SPRN_MMCRH, 0);
+	}
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+	mtspr(SPRN_MMCRS, 0);
+}
+
+static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power8";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power8;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
+
+	return 1;
+}
+
+static int __init feat_enable_pm_power8(struct dt_cpu_feature *f)
+{
+	hfscr_pm_enable();
+
+	init_pm_power8();
+	init_pm_registers = init_pm_power8;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+	if (pvr_version_is(PVR_POWER8E))
+		cur_cpu_spec->cpu_features |= CPU_FTR_PMAO_BUG;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power8";
+
+	return 1;
+}
+
+static void init_pm_power9(void)
+{
+	if (hv_mode)
+		mtspr(SPRN_MMCRC, 0);
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+}
+
+static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power9";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power9;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
+
+	return 1;
+}
+
+static int __init feat_enable_pm_power9(struct dt_cpu_feature *f)
+{
+	hfscr_pm_enable();
+
+	init_pm_power9();
+	init_pm_registers = init_pm_power9;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power9";
+
+	return 1;
+}
+
+static int __init feat_enable_tm(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	feat_enable(f);
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_HTM_NOSC;
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_fp(struct dt_cpu_feature *f)
+{
+	feat_enable(f);
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_FPU_UNAVAILABLE;
+
+	return 1;
+}
+
+static int __init feat_enable_vector(struct dt_cpu_feature *f)
+{
+#if defined(CONFIG_ALTIVEC) && defined(CONFIG_VSX)
+	feat_enable(f);
+	cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
+	cur_cpu_spec->cpu_features |= CPU_FTR_VSX;
+	cur_cpu_spec->cpu_features |= CPU_FTR_VMX_COPY;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_VSX;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_purr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_PURR | CPU_FTR_SPURR;
+
+	return 1;
+}
+
+static int __init feat_enable_dbell(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* P9 has an HFSCR for privileged state */
+	feat_enable(f);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_DBELL;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECEDH; /* hyp doorbell wakeup */
+	mtspr(SPRN_LPCR, lpcr);
+
+	prereq_pece_msgp++;
+
+	return 1;
+}
+
+static int __init feat_enable_hvi(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE_HVEE | LPCR_HVICE;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_large_ci(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->mmu_features |= MMU_FTR_CI_LARGE_PAGE;
+
+	return 1;
+}
+
+struct dt_cpu_feature_match {
+	const char *name;
+	int (*enable)(struct dt_cpu_feature *f);
+	u64 cpu_ftr_bit_mask;
+};
+
+static struct dt_cpu_feature_match __initdata
+		dt_cpu_feature_match_table[] = {
+	{"hypervisor", feat_enable_hv, 0},
+	{"big-endian", feat_enable, 0},
+	{"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
+	{"smt", feat_enable_smt, 0},
+	{"come-from-address-register", feat_enable, CPU_FTR_CFAR},
+	{"floating-point", feat_enable_fp, 0},
+	{"vector", feat_enable_vector, 0},
+	{"decimal-floating-point", feat_enable, 0},
+	{"decimal-integer", feat_enable, 0},
+	{"vector-crypto", feat_enable, 0},
+	{"mmu-hash", feat_enable_mmu_hash, 0},
+	{"mmu-radix", feat_enable_mmu_radix, 0},
+	{"mmu-hash-v3", feat_enable_mmu_hash_v3, 0},
+	{"transactional-memory", feat_enable_tm, CPU_FTR_TM},
+	{"transactional-memory-v3", feat_enable_tm, 0},
+	{"idle-nap", feat_enable_idle_nap, 0},
+	{"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0},
+	{"idle-stop", feat_enable_idle_stop, 0},
+	{"machine-check-power8", feat_enable_mce_power8, 0},
+	{"performance-monitor-power8", feat_enable_pm_power8, 0},
+	{"data-stream-control-register", feat_enable_dscr, CPU_FTR_DSCR},
+	{"event-based-branch", feat_enable, 0},
+	{"target-address-register", feat_enable, 0},
+	{"branch-history-rolling-buffer", feat_enable, 0},
+	{"control-register", feat_enable, CPU_FTR_CTRL},
+	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
+	{"subcore", feat_enable, CPU_FTR_SUBCORE},
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
+	{"initiate-coprocessor-store-word", feat_enable, CPU_FTR_ICSWX},
+	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
+	{"program-priority-register", feat_enable, CPU_FTR_HAS_PPR},
+	{"wait", feat_enable, 0},
+	{"atomic-memory-operations", feat_enable, 0},
+	{"branch-v3", feat_enable, 0},
+	{"copy-paste", feat_enable, 0},
+	{"decimal-floating-point-v3", feat_enable, 0},
+	{"decimal-integer-v3", feat_enable, 0},
+	{"fixed-point-v3", feat_enable, 0},
+	{"floating-point-v3", feat_enable, 0},
+	{"group-start-register", feat_enable, 0},
+	{"pc-relative-addressing", feat_enable, 0},
+	{"machine-check-power9", feat_enable_mce_power9, 0},
+	{"performance-monitor-power9", feat_enable_pm_power9, 0},
+	{"event-based-branch-v3", feat_enable, 0},
+	{"large-decrementer", feat_enable, 0},
+	{"random-number-generator", feat_enable, 0},
+	{"system-call-vectored", feat_disable, 0},
+	{"trace-interrupt-v3", feat_enable, 0},
+	{"vector-v3", feat_enable, 0},
+	{"vector-binary128", feat_enable, 0},
+	{"vector-binary16", feat_enable, 0},
+	{"wait-v3", feat_enable, 0},
+};
+
+/* XXX: how to configure this? Default + boot time? */
+#define CPU_FEATURE_ENABLE_UNKNOWN 1
+
+void __init cpufeatures_setup_start(u32 isa)
+{
+	DBG("CPUFEATURES setup for isa %d\n", isa);
+
+	if (isa >= 3000) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
+		cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
+	}
+}
+
+int __init cpufeatures_process_feature(struct dt_cpu_feature *f)
+{
+	const struct dt_cpu_feature_match *m;
+	int known = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dt_cpu_feature_match_table); i++) {
+		m = &dt_cpu_feature_match_table[i];
+		if (!strcmp(f->name, m->name)) {
+			known = 1;
+			if (m->enable(f))
+				goto enabled;
+			goto not_enabled;
+		}
+	}
+
+	if (CPU_FEATURE_ENABLE_UNKNOWN) {
+		if (feat_try_enable_unknown(f))
+			goto enabled;
+	}
+
+not_enabled:
+	if (known)
+		DBG("CPU feature not enabling:%s (disabled or unsupported by kernel)\n", f->name);
+	else
+		DBG("CPU feature not enabling:%s (unknown and unsupported by kernel)\n", f->name);
+
+	return 0;
+
+enabled:
+	if (m->cpu_ftr_bit_mask)
+		cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
+	if (known)
+		DBG("CPU feature enabling:%s\n", f->name);
+	else
+		DBG("CPU feature enabling:%s (unknown)\n", f->name);
+
+	return 1;
+}
+
+void __init cpufeatures_setup_finished(void)
+{
+	if (hv_mode && !(cur_cpu_spec->cpu_features & CPU_FTR_HVMODE)) {
+		pr_err("CPU feature hypervisor not present in device tree but HV mode is enabled in the CPU. Enabling.\n");
+		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+	}
+
+	if (prereq_pece_msgp == 2) { /* doorbell and stop */
+		u64 lpcr;
+
+		lpcr = mfspr(SPRN_LPCR);
+		lpcr |=  LPCR_PECEDP; /* priv doorbell wakeup */
+		mtspr(SPRN_LPCR, lpcr);
+	}
+
+	system_registers.hfscr = mfspr(SPRN_HFSCR);
+	system_registers.fscr = mfspr(SPRN_FSCR);
+	system_registers.lpcr = mfspr(SPRN_LPCR);
+}
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e79b9daa873c..ca95c1fa3e13 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -23,7 +23,9 @@
 #include <asm/mmu.h>
 #include <asm/setup.h>
 
-struct cpu_spec* cur_cpu_spec = NULL;
+static struct cpu_spec the_cpu_spec __read_mostly;
+
+struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
@@ -2179,7 +2181,15 @@ static struct cpu_spec __initdata cpu_specs[] = {
 #endif /* CONFIG_E500 */
 };
 
-static struct cpu_spec the_cpu_spec;
+void __init set_cur_cpu_spec(struct cpu_spec *s)
+{
+	struct cpu_spec *t = &the_cpu_spec;
+
+	t = PTRRELOC(t);
+	*t = *s;
+
+	*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+}
 
 static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 					       struct cpu_spec *s)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f5d399e46193..444775a3b501 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -58,6 +58,7 @@
 #include <asm/debug.h>
 #include <asm/epapr_hcalls.h>
 #include <asm/firmware.h>
+#include <asm/cpufeatures.h>
 
 #include <mm/mmu_decl.h>
 
@@ -70,6 +71,7 @@
 #ifdef CONFIG_PPC64
 int __initdata iommu_is_off;
 int __initdata iommu_force_on;
+int __initdata has_cpufeatures_node = 0;
 unsigned long tce_alloc_start, tce_alloc_end;
 u64 ppc64_rma_size;
 #endif
@@ -300,6 +302,255 @@ static void __init check_cpu_feature_properties(unsigned long node)
 	}
 }
 
+#define CPUFT_WARN(str, name) printk(KERN_WARNING "WARNING: /cpus/features/%s dt:%s\n", name, str)
+
+static int nr_dt_cpu_features;
+static struct dt_cpu_feature *dt_cpu_features;
+
+static int __init process_cpufeatures_node(unsigned long node,
+					  const char *uname, int i)
+{
+	const __be32 *prop;
+	struct dt_cpu_feature *f;
+	int len;
+
+	f = &dt_cpu_features[i];
+	memset(f, 0, sizeof(struct dt_cpu_feature));
+
+	f->node = node;
+
+	f->name = uname;
+
+	prop = of_get_flat_dt_prop(node, "isa", &len);
+	if (!prop) {
+		CPUFT_WARN("missing isa property", uname);
+		return 0;
+	}
+	f->isa = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "usable-mask", &len);
+	if (!prop) {
+		CPUFT_WARN("missing usable-mask property", uname);
+		return 0;
+	}
+	f->usable_mask = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "hv-support", &len);
+	if (prop)
+		f->hv_support = be32_to_cpup(prop);
+	prop = of_get_flat_dt_prop(node, "os-support", &len);
+	if (prop)
+		f->os_support = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "hfscr-bit-nr", &len);
+	if (prop)
+		f->hfscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->hfscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "fscr-bit-nr", &len);
+	if (prop)
+		f->fscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->fscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "hwcap-bit-nr", &len);
+	if (prop)
+		f->hwcap_bit_nr = be32_to_cpup(prop);
+	else
+		f->hwcap_bit_nr = -1;
+
+	if (f->usable_mask & USABLE_HV) {
+		if (!(mfmsr() & MSR_HV)) {
+			CPUFT_WARN("HV feature passed to guest\n", uname);
+			return 0;
+		}
+
+		if (!f->hv_support && f->hfscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted hfscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->hv_support == HV_SUPPORT_HFSCR) {
+			if (f->hfscr_bit_nr == -1) {
+				CPUFT_WARN("missing hfscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->hv_support != HV_SUPPORT_NONE || f->hfscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted hv_support/hfscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (f->usable_mask & USABLE_OS) {
+		if (!f->os_support && f->fscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted fscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->os_support == OS_SUPPORT_FSCR) {
+			if (f->fscr_bit_nr == -1) {
+				CPUFT_WARN("missing fscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->os_support != OS_SUPPORT_NONE || f->fscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted os_support/fscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (!(f->usable_mask & USABLE_PR)) {
+		if (f->hwcap_bit_nr != -1) {
+			CPUFT_WARN("unwanted hwcap_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	/* Do all the independent features in the first pass */
+	if (!of_get_flat_dt_prop(node, "dependencies", &len)) {
+		if (cpufeatures_process_feature(f))
+			f->enabled = 1;
+		else
+			f->disabled = 1;
+	}
+
+	return 0;
+}
+
+static void __init cpufeatures_deps_enable(struct dt_cpu_feature *f)
+{
+	const __be32 *prop;
+	int len;
+	int nr_deps;
+	int i;
+
+	if (f->enabled || f->disabled)
+		return;
+
+	prop = of_get_flat_dt_prop(f->node, "dependencies", &len);
+	if (!prop) {
+		CPUFT_WARN("missing dependencies property", f->name);
+		return;
+	}
+
+	nr_deps = len / sizeof(int);
+
+	for (i = 0; i < nr_deps; i++) {
+		unsigned long phandle = be32_to_cpu(prop[i]);
+		int j;
+
+		for (j = 0; j < nr_dt_cpu_features; j++) {
+			struct dt_cpu_feature *d = &dt_cpu_features[j];
+
+			if (of_get_flat_dt_phandle(d->node) == phandle) {
+				cpufeatures_deps_enable(d);
+				if (d->disabled) {
+					f->disabled = 1;
+					return;
+				}
+			}
+		}
+	}
+
+	if (cpufeatures_process_feature(f))
+		f->enabled = 1;
+	else
+		f->disabled = 1;
+}
+
+static int __init scan_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	process_cpufeatures_node(node, uname, *count);
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init count_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init early_init_dt_scan_cpufeatures(unsigned long node,
+					  const char *uname, int depth,
+					  void *data)
+{
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int count, i;
+	u32 isa;
+
+	/* We are scanning "features" nodes only */
+	if (type == NULL || strcmp(type, "cpu-features") != 0)
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "isa", NULL);
+	if (!prop) {
+		printk("cpu-features node has missing property \"isa\"\n");
+		return 0;
+	}
+
+	isa = be32_to_cpup(prop);
+
+	has_cpufeatures_node = 1;
+
+	/* Count and allocate space for cpu features */
+	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
+						&nr_dt_cpu_features);
+	dt_cpu_features = __va(
+		memblock_alloc(sizeof(struct dt_cpu_feature)*
+				nr_dt_cpu_features, PAGE_SIZE));
+
+	cpufeatures_setup_start(isa);
+
+	/* Scan nodes into dt_cpu_features and enable those without deps  */
+	count = 0;
+	of_scan_flat_dt_subnodes(node, scan_cpufeatures_subnodes, &count);
+
+	/* Recursive enable remaining features with dependencies */
+	for (i = 0; i < nr_dt_cpu_features; i++) {
+		struct dt_cpu_feature *f = &dt_cpu_features[i];
+
+		cpufeatures_deps_enable(f);
+	}
+
+	cpufeatures_setup_finished();
+
+	memblock_free(__pa(dt_cpu_features),
+			sizeof(struct dt_cpu_feature)*nr_dt_cpu_features);
+
+	return 0;
+}
+
+static int __init early_init_dt_scan_cpufeatures_exists(unsigned long node,
+					  const char *uname, int depth,
+					  void *data)
+{
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	int *exists = data;
+
+	/* We are scanning "features" nodes only */
+	if (type == NULL || strcmp(type, "cpu-features") != 0)
+		return 0;
+
+	*exists = 1;
+
+	return 0;
+}
+
 static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
@@ -377,22 +628,32 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	 * uses the 0x0f000002 PVR value; in POWER5+ mode
 	 * it uses 0x0f000001.
 	 */
-	prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
-	if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
-		identify_cpu(0, be32_to_cpup(prop));
+	if (!has_cpufeatures_node) {
+		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+			identify_cpu(0, be32_to_cpup(prop));
+		identical_pvr_fixup(node);
 
-	identical_pvr_fixup(node);
-
-	check_cpu_feature_properties(node);
-	check_cpu_pa_features(node);
-	init_mmu_slb_size(node);
+		check_cpu_feature_properties(node);
+		check_cpu_pa_features(node);
 
 #ifdef CONFIG_PPC64
-	if (nthreads > 1)
-		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
-	else
-		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+		if (nthreads > 1)
+			cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+		else
+			cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+#endif
+	} else {
+		strcpy(cur_cpu_spec->cpu_name, uname);
+#ifdef CONFIG_PPC64
+		if (nthreads == 1)
+			cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
 #endif
+	}
+
+
+	init_mmu_slb_size(node);
+
 	return 0;
 }
 
@@ -648,6 +909,16 @@ static void __init early_reserve_mem(void)
 #endif
 }
 
+/*
+ * Does the /cpus/features/ node exist?
+ */
+int __init early_init_devtree_check_cpu_features_exists(void)
+{
+	int exists = 0;
+	of_scan_flat_dt(early_init_dt_scan_cpufeatures_exists, &exists);
+	return exists;
+}
+
 void __init early_init_devtree(void *params)
 {
 	phys_addr_t limit;
@@ -722,6 +993,8 @@ void __init early_init_devtree(void *params)
 
 	DBG("Scanning CPUs ...\n");
 
+	of_scan_flat_dt(early_init_dt_scan_cpufeatures, NULL);
+
 	/* Retrieve CPU related informations from the flat tree
 	 * (altivec support, boot CPU ID, ...)
 	 */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 4697da895133..fe52229681da 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -256,7 +256,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "cpu\t\t: ");
 
-	if (cur_cpu_spec->pvr_mask)
+	if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name)
 		seq_printf(m, "%s", cur_cpu_spec->cpu_name);
 	else
 		seq_printf(m, "unknown (%08x)", pvr);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 9cfaa8b69b5f..ae0409789365 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -49,6 +49,7 @@
 #include <asm/paca.h>
 #include <asm/time.h>
 #include <asm/cputable.h>
+#include <asm/cpufeatures.h>
 #include <asm/sections.h>
 #include <asm/btext.h>
 #include <asm/nvram.h>
@@ -262,11 +263,22 @@ static void cpu_ready_for_interrupts(void)
 void __init early_setup(unsigned long dt_ptr)
 {
 	static __initdata struct paca_struct boot_paca;
+	int cpufeatures = 0;
 
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Identify CPU type */
-	identify_cpu(0, mfspr(SPRN_PVR));
+#ifdef CONFIG_PPC_BOOK3S_64
+	/* Setup flat device-tree pointer */
+	initial_boot_params = __va(dt_ptr);
+	if (early_init_devtree_check_cpu_features_exists()) {
+		cpufeatures = 1;
+		cpufeatures_setup_cpu();
+	} else
+#endif
+	{
+		/* Legacy table-based approach when /cpus/features is missing */
+		identify_cpu(0, mfspr(SPRN_PVR));
+	}
 
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	initialise_paca(&boot_paca, 0);
@@ -280,6 +292,8 @@ void __init early_setup(unsigned long dt_ptr)
 
  	DBG(" -> early_setup(), dt_ptr: 0x%lx\n", dt_ptr);
 
+	printk("cpufeatures:%d\n", cpufeatures);
+
 	/*
 	 * Do early initialization using the flattened device
 	 * tree, such as retrieving the physical memory map or
@@ -532,6 +546,9 @@ void __init initialize_cache_info(void)
 	dcache_bsize = ppc64_caches.l1d.block_size;
 	icache_bsize = ppc64_caches.l1i.block_size;
 
+	cur_cpu_spec->dcache_bsize = dcache_bsize;
+	cur_cpu_spec->icache_bsize = icache_bsize;
+
 	DBG(" <- initialize_cache_info()\n");
 }
 
-- 
2.11.0

Re: [PATCH 3/3] powerpc/64s: cpufeatures: add initial implementation for cpufeatures

[kbuild test robot]

[-- Attachment #1: Type: text/plain, Size: 1933 bytes --]

Hi Nicholas,

[auto build test ERROR on powerpc/next]
[also build test ERROR on v4.11-rc5 next-20170406]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Nicholas-Piggin/latest-cpufeatures-patch-series/20170406-140710
base:   https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-allnoconfig (attached as .config)
compiler: powerpc-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
        wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=powerpc 

All errors (new ones prefixed by >>):

   arch/powerpc/kernel/prom.c: In function 'early_init_dt_scan_cpufeatures':
>> arch/powerpc/kernel/prom.c:508:2: error: 'has_cpufeatures_node' undeclared (first use in this function)
     has_cpufeatures_node = 1;
     ^~~~~~~~~~~~~~~~~~~~
   arch/powerpc/kernel/prom.c:508:2: note: each undeclared identifier is reported only once for each function it appears in
   arch/powerpc/kernel/prom.c: In function 'early_init_dt_scan_cpus':
   arch/powerpc/kernel/prom.c:631:7: error: 'has_cpufeatures_node' undeclared (first use in this function)
     if (!has_cpufeatures_node) {
          ^~~~~~~~~~~~~~~~~~~~

vim +/has_cpufeatures_node +508 arch/powerpc/kernel/prom.c

   502			printk("cpu-features node has missing property \"isa\"\n");
   503			return 0;
   504		}
   505	
   506		isa = be32_to_cpup(prop);
   507	
 > 508		has_cpufeatures_node = 1;
   509	
   510		/* Count and allocate space for cpu features */
   511		of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation

[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 6124 bytes --]

Re: [PATCH 3/3] powerpc/64s: cpufeatures: add initial implementation for cpufeatures

[Nicholas Piggin]

On Wed,  5 Apr 2017 22:37:06 +1000
Nicholas Piggin <npiggin@gmail.com> wrote:

> The /cpus/features dt binding describes architected CPU features along
> with some compatibility, privilege, and enablement properties that allow
> flexibility with discovering and enabling capabilities.
> 
> Presence of this feature implies a base level of functionality, then
> additional feature nodes advertise the presence of new features.
> 
> A given feature and its setup procedure is defined once and used by all
> CPUs which are compatible by that feature. Features that follow a
> supported "prescription" can be enabled by a hypervisor or OS that
> does not understand them natively.
> 
> ---
> Since last post:
> - Update to v3.0B ISA.
> - Removed PVR tests for MCE and PMU, and add specific features for those.
> - Fixed CPU state restore.
> - Changed dt bit number specification for hfscr/fscr/aux to LSB0.
> - Broke the of/fdt changes into another patch.
> - Added a proper dependency checker.
> - Resolved most of the register/feature bits differences, made a patch
>   for VRMASD.
> - Didn't think of a better name.

Here's the latest version, which has some build and config cleanups
and updated with some more optional features.

Since last post:
- Fixed 32-bit build
- Made configurable on Book3s (for now)
- Updated base set of features


---
 .../devicetree/bindings/powerpc/cpufeatures.txt    | 264 +++++++++
 arch/powerpc/Kconfig                               |  16 +
 arch/powerpc/include/asm/cpu_has_feature.h         |   4 +-
 arch/powerpc/include/asm/cpufeatures.h             |  57 ++
 arch/powerpc/include/asm/cputable.h                |   1 +
 arch/powerpc/kernel/Makefile                       |   1 +
 arch/powerpc/kernel/cpufeatures.c                  | 625 +++++++++++++++++++++
 arch/powerpc/kernel/cputable.c                     |  14 +-
 arch/powerpc/kernel/prom.c                         | 307 +++++++++-
 arch/powerpc/kernel/setup-common.c                 |   2 +-
 arch/powerpc/kernel/setup_64.c                     |  15 +-
 11 files changed, 1288 insertions(+), 18 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/powerpc/cpufeatures.txt
 create mode 100644 arch/powerpc/include/asm/cpufeatures.h
 create mode 100644 arch/powerpc/kernel/cpufeatures.c

diff --git a/Documentation/devicetree/bindings/powerpc/cpufeatures.txt b/Documentation/devicetree/bindings/powerpc/cpufeatures.txt
new file mode 100644
index 000000000000..325b263f4cdf
--- /dev/null
+++ b/Documentation/devicetree/bindings/powerpc/cpufeatures.txt
@@ -0,0 +1,264 @@
+powerpc cpu features binding
+============================
+
+The device tree describes supported CPU features as nodes containing
+compatibility and enablement information as properties.
+
+The binding specifies features common to all CPUs in the system.
+Heterogeneous CPU features are not supported at present (such could be added
+by providing nodes with additional features and linking those to particular
+CPUs).
+
+This binding is intended to provide fine grained control of CPU features at
+all levels of the stack (firmware, hypervisor, OS, userspace), with the
+ability for new CPU features to be used by some components without all
+components being upgraded (e.g., a new floating point instruction could be
+used by userspace math library without upgrading kernel and hypervisor).
+
+The binding is passed to the hypervisor by firmware. The hypervisor must
+remove any features that require hypervisor enablement but that it does not
+enable. It must remove any features that depend on removed features. It may
+pass remaining features usable to the OS and PR to guests, depending on
+configuration policy (not specified here).
+
+The modified binding is passed to the guest by hypervisor, with HV bit
+cleared from the usable-mask and the hv-support and hfscr-bit properties
+removed. The guest must similarly rmeove features that require OS enablement
+that it does not enable. The OS may pass PR usable features to userspace via
+ELF AUX vectors AT_HWCAP, AT_HWCAP2, AT_HWCAP3, etc., or use some other
+method (outside the scope of this specification).
+
+The binding will specify a "base" level of features that will be present
+when the cpu features binding exists. Additional features will be explicitly
+specified.
+
+/cpus/features node binding
+---------------------------
+
+Node: features
+
+Description: Container of CPU feature nodes.
+
+The node name must be "features" and it must be a child of the node "/cpus".
+
+The node is optional but should be provided by new firmware.
+
+Each child node of cpufeatures represents an architected CPU feature (e.g.,
+a new set of vector instructions) or an important CPU performance
+characteristic (e.g., fast unaligned memory operations). The specification
+of each feature (instructions, registers, exceptions, etc.) will be
+documented with device tree bindings.
+
+As a rough guide, features should be based on functional groups of changes,
+those that share common enablement requirements, that share particular
+registers or functionality. For example, "POWER9" would be too general, and
+a new feature for every instruction would be too specific. The "summary of
+changes" preface in Power ISA specification is a good guideline for the
+architected features.
+
+Features should be "positive" where possible. For example the presence of a
+feature node should indicate the presence of a new CPU feature (e.g., a
+new instruction or register). An errata workaround for example would then
+remove that feature from the device tree to disable it. "Negative" features
+may be unavoidable in some cases.
+
+Properties:
+
+- device_type
+  Usage: required
+  Value type: string
+  Definition: "cpu-features"
+
+- isa
+  Usage: required
+  Value type: <u32>
+  Definition:
+
+  isa that the CPU is currently running in. This provides instruction set
+  compatibility, less the individual feature nodes. For example, an ISA v3.0
+  implementation that lacks the "transactional-memory" cpufeature node
+  should not use transactional memory facilities.
+
+  Value corresponds to the "Power ISA Version" multiplied by 1000.
+  For example, <3000> corresponds to Version 3.0, <2070> to Version 2.07.
+  The minor digit is available for revisions.
+
+/cpus/features/feature node bindings
+------------------------------------
+
+Node: A string describing an architected CPU feature, e.g., "vsx".
+
+Description: An architected feature supported by the CPUs.
+
+The name of the node will follow a convention such that software will
+match known features by a string comparison with the node name. Presence
+of the node indicates the feature is available to use (XXX: could
+advertise all supported by hardware, with disabled/enabled status
+property).
+
+The name of the child node corresponds to the name of the feature.
+Software will detect known features by string matching.
+
+Properties:
+
+- isa
+  Usage: required
+  Value type: <u32>
+  Definition:
+
+  First level of the Power ISA that the feature appears in.
+  Software should filter out features when constraining the
+  environment to a particular ISA version.
+
+  Value is defined similarly to /cpus/features/isa
+
+- usable-mask
+  Usage: required
+  Value type: <u32> bit mask
+  Definition:
+              Bit numbers are LSB0
+              bit 0 - PR (problem state / user mode)
+              bit 1 - OS (privileged state)
+              bit 2 - HV (hypervisor state)
+              All other bits reserved and should be zero.
+
+  This property describes the privilege levels and/or software components
+  that can use the feature.
+
+  If bit 0 is set, then the hwcap-bit-nr property will exist.
+
+  Reserved bits must be treated as the feature being unsupported.
+
+- hv-support
+  Usage: optional
+  Value type: <u32>
+  Definition:
+              1 -  Custom
+              2 -  HFSCR
+              Other values reserved.
+
+  This property describes the HV privilege state support required to
+  enable the feature. If the property does not exist then no support is
+  required.
+
+  If the value of this property is 1, then the hypervisor must have
+  explicit support for this feature.
+
+  If the value of this property is 2, then the hfscr-bit-nr property
+  will exist.
+
+  Reserved values must be treated as the feature being unsupported.
+
+- os-support
+  Usage: optional
+  Value type: <u32>
+  Definition:
+              1 -  Custom
+              2 -  FSCR
+              Other values reserved.
+
+  This property describes the OS privilege state support required to
+  enable the feature. If the property does not exist then no support is
+  required.
+
+  If the value of this property is 1, then the operating system must
+  have explicit support for this feature.
+
+  If the value of this property is 2, then the fscr-bit-nr property will
+  exist.
+
+  Reserved values must be treated as the feature being unsupported.
+
+- hfscr-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: HFSCR bit position (LSB0)
+
+  This property exists when the hv-support property value is 2. This
+  property describes the bit number in the HFSCR register that the
+  hypervisor must set in order to enable this feature.
+
+- fscr-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: FSCR bit position (LSB0)
+
+  This property exists when the os-support property value is 2. This
+  property describes the bit number in the FSCR register that the
+  operating system must set in order to enable this feature.
+
+- hwcap-bit-nr
+  Usage: optional
+  Value type: <u32>
+  Definition: AUX vector bit position (LSB0)
+
+  This property may exist when the usable-mask property value has bit 0
+  (PR) set. This property describes the bit number that should be set in
+  the ELF AUX hardware capability vectors in order to advertise this
+  feature to userspace. Bits 0-31 correspond to bits 0-31 in AT_HWCAP
+  vector. Bits 32-63 correspond to 0-31 in AT_HWCAP2 vector, and so on.
+  Missing AT_HWCAPx vectors implies that the feature is not enabled or
+  can not be advertised. Operating systems may provide a number of
+  unassigned hardware capability bits to allow for new features to be
+  advertised.
+
+  Some properties representing features created before this binding are
+  advertised to userspace without a one-to-one hwcap bit number may not
+  specify this bit. Operating system will handle those bits specifically.
+  All new features usable by userspace will have a hwcap-bit-nr property.
+
+- dependencies
+  Usage: optional
+  Value type: <prop-encoded-array>
+  Definition:
+
+  If this property exists then it is a list of phandles to cpu feature
+  nodes that must be enabled for this feature to be enabled.
+
+
+Example
+-------
+
+	/cpus/features {
+		device_type = "cpu-features";
+
+		isa = <3020>;
+
+		darn {
+			isa = <3000>;
+			usable-mask = <1 | 2 | 4>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		scv {
+			isa = <3000>;
+			usable-mask = <1 | 2>;
+			os-support = <1>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		stop {
+			isa = <3000>;
+			usable-mask = <2 | 4>;
+			hv-support = <1>;
+			os-support = <1>;
+		};
+
+		vsx2 (hypothetical) {
+			isa = <3010>;
+			usable-mask = <1 | 2 | 4>;
+			hv-support = <1>;
+			os-support = <1>;
+			hwcap-bit-nr = <xx>;
+		};
+
+		vsx2-newinsns {
+			isa = <3020>;
+			usable-mask = <1 | 2 | 4>;
+			os-support = <2>;
+			fscr-bit-nr = <xx>;
+			hwcap-bit-nr = <xx>;
+			dependencies = <&vsx2>;
+		};
+
+	};
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 97a8bc8a095c..c4804cd65b9a 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -330,6 +330,22 @@ source "arch/powerpc/platforms/Kconfig"
 
 menu "Kernel options"
 
+config PPC_CPUFEATURES_DT
+	bool "cpufeatures cpu setup and device tree support (UNSTABLE)"
+	depends on PPC_BOOK3S_64
+	default n
+	---help---
+	  cpufeatures is a proposed new device tree binding for describing
+	  CPU compatibility and features. Saying y here will attempt to use
+	  cpufeatures binding if the firmware provides it. This binding is
+	  not stable, so a kernel built with this option may not function
+	  properly with future firmware.
+
+config PPC_CPUFEATURES_ENABLE_UNKNOWN
+	bool "cpufeatures pass through unknown features to guest/userspace"
+	depends on PPC_CPUFEATURES_DT
+	default y
+
 config HIGHMEM
 	bool "High memory support"
 	depends on PPC32
diff --git a/arch/powerpc/include/asm/cpu_has_feature.h b/arch/powerpc/include/asm/cpu_has_feature.h
index 6e834caa3720..445495aa2bbf 100644
--- a/arch/powerpc/include/asm/cpu_has_feature.h
+++ b/arch/powerpc/include/asm/cpu_has_feature.h
@@ -1,5 +1,5 @@
-#ifndef __ASM_POWERPC_CPUFEATURES_H
-#define __ASM_POWERPC_CPUFEATURES_H
+#ifndef __ASM_POWERPC_CPU_HAS_FEATURE_H
+#define __ASM_POWERPC_CPU_HAS_FEATURE_H
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/powerpc/include/asm/cpufeatures.h b/arch/powerpc/include/asm/cpufeatures.h
new file mode 100644
index 000000000000..4c45a781a3b2
--- /dev/null
+++ b/arch/powerpc/include/asm/cpufeatures.h
@@ -0,0 +1,57 @@
+#ifndef __ASM_POWERPC_CPUFEATURES_H
+#define __ASM_POWERPC_CPUFEATURES_H
+
+/*
+ *  Copyright 2017, IBM Corporation
+ *  cpufeatures is the new way to discover CPU features with /cpus/features
+ *  devicetree. This supersedes PVR based discovery ("cputable"), and other
+ *  devic tree feature advertisement.
+ */
+
+#include <linux/types.h>
+#include <asm/asm-compat.h>
+#include <asm/feature-fixups.h>
+#include <uapi/asm/cputable.h>
+
+extern void cpufeatures_setup_cpu(void);
+
+/* Types for device tree parsing */
+#define USABLE_PR               (1U << 0)
+#define USABLE_OS               (1U << 1)
+#define USABLE_HV               (1U << 2)
+
+#define HV_SUPPORT_NONE         0
+#define HV_SUPPORT_CUSTOM       1
+#define HV_SUPPORT_HFSCR        2
+
+#define OS_SUPPORT_NONE         0
+#define OS_SUPPORT_CUSTOM       1
+#define OS_SUPPORT_FSCR         2
+
+#define ISA_BASE                0
+#define ISA_V207                2070
+#define ISA_V3                  3000
+
+struct dt_cpu_feature {
+	const char *name;
+	uint32_t isa;
+	uint32_t usable_mask;
+	uint32_t hv_support;
+	uint32_t os_support;
+	uint32_t hfscr_bit_nr;
+	uint32_t fscr_bit_nr;
+	uint32_t hwcap_bit_nr;
+	/* fdt parsing */
+	unsigned long node;
+	int enabled;
+	int disabled;
+};
+
+extern void cpufeatures_setup_start(u32 isa);
+extern int cpufeatures_process_feature(struct dt_cpu_feature *f);
+extern void cpufeatures_setup_finished(void);
+
+/* kernel/prom.c */
+extern int early_init_devtree_check_cpu_features_exists(void);
+
+#endif
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index ab68d0ee7725..10b9a4be3434 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -118,6 +118,7 @@ extern struct cpu_spec		*cur_cpu_spec;
 
 extern unsigned int __start___ftr_fixup, __stop___ftr_fixup;
 
+extern void set_cur_cpu_spec(struct cpu_spec *s);
 extern struct cpu_spec *identify_cpu(unsigned long offset, unsigned int pvr);
 extern void do_feature_fixups(unsigned long value, void *fixup_start,
 			      void *fixup_end);
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 811f441a125f..9b264ebe6ac1 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -58,6 +58,7 @@ obj-$(CONFIG_PPC_RTAS)		+= rtas.o rtas-rtc.o $(rtaspci-y-y)
 obj-$(CONFIG_PPC_RTAS_DAEMON)	+= rtasd.o
 obj-$(CONFIG_RTAS_FLASH)	+= rtas_flash.o
 obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
+obj-$(CONFIG_PPC_CPUFEATURES_DT)	+= cpufeatures.o
 obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
 				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
diff --git a/arch/powerpc/kernel/cpufeatures.c b/arch/powerpc/kernel/cpufeatures.c
new file mode 100644
index 000000000000..ed015e0628be
--- /dev/null
+++ b/arch/powerpc/kernel/cpufeatures.c
@@ -0,0 +1,625 @@
+/*
+ *  Copyright 2017, IBM Corporation
+ */
+
+#include <linux/string.h>
+#include <linux/sched.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/jump_label.h>
+
+#include <asm/cpufeatures.h>
+#include <asm/cputable.h>
+#include <asm/prom.h>		/* for PTRRELOC on ARCH=ppc */
+#include <asm/oprofile_impl.h>
+#include <asm/mmu.h>
+#include <asm/setup.h>
+
+#ifdef DEBUG
+#define DBG(fmt...) pr_err(fmt)
+#else
+#define DBG(fmt...)
+#endif
+
+#define CPU_FTRS_BASE \
+	   (CPU_FTR_USE_TB | \
+	    CPU_FTR_LWSYNC | \
+	    CPU_FTR_FPU_UNAVAILABLE |\
+	    CPU_FTR_NODSISRALIGN |\
+	    CPU_FTR_NOEXECUTE |\
+	    CPU_FTR_COHERENT_ICACHE | \
+	    CPU_FTR_STCX_CHECKS_ADDRESS |\
+	    CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
+	    CPU_FTR_DAWR | \
+	    CPU_FTR_ARCH_206 |\
+	    CPU_FTR_ARCH_207S)
+
+#define MMU_FTRS_HASH_BASE (MMU_FTRS_POWER8)
+
+#define COMMON_USER_BASE	(PPC_FEATURE_32 | PPC_FEATURE_64 | \
+				 PPC_FEATURE_ARCH_2_06 |\
+				 PPC_FEATURE_ICACHE_SNOOP)
+#define COMMON_USER2_BASE	(PPC_FEATURE2_ARCH_2_07 | \
+				 PPC_FEATURE2_ISEL)
+/*
+ * Set up the base CPU
+ */
+
+extern void __flush_tlb_power8(unsigned int action);
+extern void __flush_tlb_power9(unsigned int action);
+extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
+extern long __machine_check_early_realmode_p9(struct pt_regs *regs);
+
+static int hv_mode;
+
+static struct {
+	u64	hfscr;
+	u64	fscr;
+	u64	lpcr;
+} system_registers;
+
+static void (*init_pm_registers)(void);
+
+static void __restore_cpu_cpufeatures(void)
+{
+	if (hv_mode) {
+		mtspr(SPRN_LPID, 0);
+		mtspr(SPRN_HFSCR, system_registers.hfscr);
+	}
+	mtspr(SPRN_FSCR, system_registers.fscr);
+	mtspr(SPRN_LPCR, system_registers.lpcr);
+
+	if (init_pm_registers)
+		init_pm_registers();
+}
+
+void __init cpufeatures_setup_cpu(void)
+{
+	/* XXX: CPU name gets populated from device tree, but that's not
+	 * backward compatible if anything parses it. Must special case for
+	 * P8/9 and get from DT in future */
+	static char cpu_name_array[32] = "PowerPC (unknown)";
+	struct cpu_spec s = {
+		.cpu_name		= cpu_name_array,
+		.cpu_features		= CPU_FTRS_BASE,
+		.cpu_user_features	= COMMON_USER_BASE,
+		.cpu_user_features2	= COMMON_USER2_BASE,
+		.mmu_features		= 0,
+		.icache_bsize		= 32, /* minimum block size, fixed by */
+		.dcache_bsize		= 32, /* cache info init.             */
+		.num_pmcs		= 0,
+		.pmc_type		= PPC_PMC_DEFAULT,
+		.oprofile_cpu_type	= NULL,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= NULL,
+		.cpu_restore		= __restore_cpu_cpufeatures,
+		.flush_tlb		= NULL,
+		.machine_check_early	= NULL,
+		.platform		= NULL,
+	};
+
+	set_cur_cpu_spec(&s);
+
+	/* Initialize the base environment -- clear FSCR/HFSCR.  */
+	hv_mode = !!(mfmsr() & MSR_HV);
+	if (hv_mode)
+		mtspr(SPRN_HFSCR, 0);
+	mtspr(SPRN_FSCR, 0);
+}
+
+static int __init feat_try_enable_unknown(struct dt_cpu_feature *f)
+{
+	if (f->hv_support == HV_SUPPORT_NONE) {
+	} else if (f->hv_support == HV_SUPPORT_HFSCR) {
+		u64 hfscr = mfspr(SPRN_HFSCR);
+		hfscr |= 1UL << f->hfscr_bit_nr;
+		mtspr(SPRN_HFSCR, hfscr);
+	} else {
+		return 0;
+	}
+
+	if (f->os_support == OS_SUPPORT_NONE) {
+	} else if (f->os_support == OS_SUPPORT_FSCR) {
+		u64 fscr = mfspr(SPRN_FSCR);
+		fscr |= 1UL << f->fscr_bit_nr;
+		mtspr(SPRN_FSCR, fscr);
+	} else {
+		return 0;
+	}
+
+	if ((f->usable_mask & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_enable(struct dt_cpu_feature *f)
+{
+	if (f->hv_support) {
+		if (f->hfscr_bit_nr != -1) {
+			u64 hfscr = mfspr(SPRN_HFSCR);
+			hfscr |= 1UL << f->hfscr_bit_nr;
+			mtspr(SPRN_HFSCR, hfscr);
+		}
+	}
+
+	if (f->os_support) {
+		if (f->fscr_bit_nr != -1) {
+			u64 fscr = mfspr(SPRN_FSCR);
+			fscr |= 1UL << f->fscr_bit_nr;
+			mtspr(SPRN_FSCR, fscr);
+		}
+	}
+
+	if ((f->usable_mask & USABLE_PR) && (f->hwcap_bit_nr != -1)) {
+		uint32_t word = f->hwcap_bit_nr / 32;
+		uint32_t bit = f->hwcap_bit_nr % 32;
+
+		if (word == 0)
+			cur_cpu_spec->cpu_user_features |= 1U << bit;
+		else if (word == 1)
+			cur_cpu_spec->cpu_user_features2 |= 1U << bit;
+		else
+			pr_err("CPU feature: %s could not advertise to user (no hwcap bits)\n", f->name);
+	}
+
+	return 1;
+}
+
+static int __init feat_disable(struct dt_cpu_feature *f)
+{
+	return 0;
+}
+
+static int __initdata prereq_pece_msgp = 0;
+
+static int __init feat_enable_hv(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	if (!hv_mode) {
+		pr_err("CPU feature hypervisor present in device tree but HV mode not enabled in the CPU. Ignoring.\n");
+		return 0;
+	}
+
+	mtspr(SPRN_LPID, 0);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &=  ~LPCR_LPES0; /* HV external interrupts */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+
+	return 1;
+}
+
+static int __init feat_enable_le(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_TRUE_LE;
+	return 1;
+}
+
+static int __init feat_enable_smt(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_SMT;
+	return 1;
+}
+
+static int __init feat_enable_idle_nap(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISA 207 */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_align_dsisr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_NODSISRALIGN;
+
+	return 1;
+}
+
+static int __init feat_enable_idle_stop(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* Set PECE wakeup modes for ISA 300 */
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE0;
+	lpcr |=  LPCR_PECE1;
+	lpcr |=  LPCR_PECE2;
+	mtspr(SPRN_LPCR, lpcr);
+
+	prereq_pece_msgp++;
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+
+	/* VRMASD */
+	lpcr |= LPCR_VPM0;
+	lpcr &= ~LPCR_VPM1;
+	lpcr |= 0x10UL << LPCR_VRMASD_SH; /* L=1 LP=00 */
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+static int __init feat_enable_mmu_hash_v3(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_ISL;
+	mtspr(SPRN_LPCR, lpcr);
+
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+}
+
+
+static int __init feat_enable_mmu_radix(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_RADIX_MMU
+	cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	cur_cpu_spec->mmu_features |= MMU_FTRS_HASH_BASE;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_MMU;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_dscr(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	feat_enable(f);
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr &= ~LPCR_DPFD;
+	lpcr |=  (4UL << LPCR_DPFD_SH);
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static void hfscr_pm_enable(void)
+{
+	u64 hfscr = mfspr(SPRN_HFSCR);
+	hfscr |= PPC_BIT(60);
+	mtspr(SPRN_HFSCR, hfscr);
+}
+
+static void init_pm_power8(void)
+{
+	if (hv_mode) {
+		mtspr(SPRN_MMCRC, 0);
+		mtspr(SPRN_MMCRH, 0);
+	}
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+	mtspr(SPRN_MMCRS, 0);
+}
+
+static int __init feat_enable_mce_power8(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power8";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power8;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p8;
+
+	return 1;
+}
+
+static int __init feat_enable_pm_power8(struct dt_cpu_feature *f)
+{
+	hfscr_pm_enable();
+
+	init_pm_power8();
+	init_pm_registers = init_pm_power8;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+	if (pvr_version_is(PVR_POWER8E))
+		cur_cpu_spec->cpu_features |= CPU_FTR_PMAO_BUG;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power8";
+
+	return 1;
+}
+
+static void init_pm_power9(void)
+{
+	if (hv_mode)
+		mtspr(SPRN_MMCRC, 0);
+
+	mtspr(SPRN_MMCRA, 0);
+	mtspr(SPRN_MMCR0, 0);
+	mtspr(SPRN_MMCR1, 0);
+	mtspr(SPRN_MMCR2, 0);
+}
+
+static int __init feat_enable_mce_power9(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->platform = "power9";
+	cur_cpu_spec->flush_tlb = __flush_tlb_power9;
+	cur_cpu_spec->machine_check_early = __machine_check_early_realmode_p9;
+
+	return 1;
+}
+
+static int __init feat_enable_pm_power9(struct dt_cpu_feature *f)
+{
+	hfscr_pm_enable();
+
+	init_pm_power9();
+	init_pm_registers = init_pm_power9;
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_MMCRA;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_PSERIES_PERFMON_COMPAT;
+
+	cur_cpu_spec->num_pmcs		= 6;
+	cur_cpu_spec->pmc_type		= PPC_PMC_IBM;
+	cur_cpu_spec->oprofile_cpu_type	= "ppc64/power9";
+
+	return 1;
+}
+
+static int __init feat_enable_tm(struct dt_cpu_feature *f)
+{
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	feat_enable(f);
+	cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_HTM_NOSC;
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_fp(struct dt_cpu_feature *f)
+{
+	feat_enable(f);
+	cur_cpu_spec->cpu_features &= ~CPU_FTR_FPU_UNAVAILABLE;
+
+	return 1;
+}
+
+static int __init feat_enable_vector(struct dt_cpu_feature *f)
+{
+#if defined(CONFIG_ALTIVEC) && defined(CONFIG_VSX)
+	feat_enable(f);
+	cur_cpu_spec->cpu_features |= CPU_FTR_ALTIVEC;
+	cur_cpu_spec->cpu_features |= CPU_FTR_VSX;
+	cur_cpu_spec->cpu_features |= CPU_FTR_VMX_COPY;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_ALTIVEC;
+	cur_cpu_spec->cpu_user_features |= PPC_FEATURE_HAS_VSX;
+
+	return 1;
+#endif
+	return 0;
+}
+
+static int __init feat_enable_purr(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->cpu_features |= CPU_FTR_PURR | CPU_FTR_SPURR;
+
+	return 1;
+}
+
+static int __init feat_enable_dbell(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	/* P9 has an HFSCR for privileged state */
+	feat_enable(f);
+
+	cur_cpu_spec->cpu_features |= CPU_FTR_DBELL;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECEDH; /* hyp doorbell wakeup */
+	mtspr(SPRN_LPCR, lpcr);
+
+	prereq_pece_msgp++;
+
+	return 1;
+}
+
+static int __init feat_enable_hvi(struct dt_cpu_feature *f)
+{
+	u64 lpcr;
+
+	lpcr = mfspr(SPRN_LPCR);
+	lpcr |=  LPCR_PECE_HVEE | LPCR_HVICE;
+	mtspr(SPRN_LPCR, lpcr);
+
+	return 1;
+}
+
+static int __init feat_enable_large_ci(struct dt_cpu_feature *f)
+{
+	cur_cpu_spec->mmu_features |= MMU_FTR_CI_LARGE_PAGE;
+
+	return 1;
+}
+
+struct dt_cpu_feature_match {
+	const char *name;
+	int (*enable)(struct dt_cpu_feature *f);
+	u64 cpu_ftr_bit_mask;
+};
+
+static struct dt_cpu_feature_match __initdata
+		dt_cpu_feature_match_table[] = {
+	{"hypervisor", feat_enable_hv, 0},
+	{"big-endian", feat_enable, 0},
+	{"little-endian", feat_enable_le, CPU_FTR_REAL_LE},
+	{"smt", feat_enable_smt, 0},
+	{"interrupt-facilities", feat_enable, 0},
+	{"timer-facilities", feat_enable, 0},
+	{"timer-facilities-v3", feat_enable, 0},
+	{"debug-facilities", feat_enable, 0},
+	{"come-from-address-register", feat_enable, CPU_FTR_CFAR},
+	{"debug-facilities-v3", feat_enable, 0},
+	{"branch-tracing", feat_enable, 0},
+	{"floating-point", feat_enable_fp, 0},
+	{"vector", feat_enable_vector, 0},
+	{"decimal-floating-point", feat_enable, 0},
+	{"decimal-integer", feat_enable, 0},
+	{"vector-crypto", feat_enable, 0},
+	{"mmu-hash", feat_enable_mmu_hash, 0},
+	{"mmu-radix", feat_enable_mmu_radix, 0},
+	{"mmu-hash-v3", feat_enable_mmu_hash_v3, 0},
+	{"virtual-page-class-key-protection", feat_enable, 0},
+	{"transactional-memory", feat_enable_tm, CPU_FTR_TM},
+	{"transactional-memory-v3", feat_enable_tm, 0},
+	{"idle-nap", feat_enable_idle_nap, 0},
+	{"alignment-interrupt-dsisr", feat_enable_align_dsisr, 0},
+	{"idle-stop", feat_enable_idle_stop, 0},
+	{"machine-check-power8", feat_enable_mce_power8, 0},
+	{"performance-monitor-power8", feat_enable_pm_power8, 0},
+	{"data-stream-control-register", feat_enable_dscr, CPU_FTR_DSCR},
+	{"event-based-branch", feat_enable, 0},
+	{"target-address-register", feat_enable, 0},
+	{"branch-history-rolling-buffer", feat_enable, 0},
+	{"control-register", feat_enable, CPU_FTR_CTRL},
+	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
+	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
+	{"subcore", feat_enable, CPU_FTR_SUBCORE},
+	{"no-execute", feat_enable, 0},
+	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
+	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
+	{"coprocessor-icswx", feat_enable, CPU_FTR_ICSWX},
+	{"hypervisor-virtualization-interrupt", feat_enable_hvi, 0},
+	{"program-priority-register", feat_enable, CPU_FTR_HAS_PPR},
+	{"wait", feat_enable, 0},
+	{"atomic-memory-operations", feat_enable, 0},
+	{"branch-v3", feat_enable, 0},
+	{"copy-paste", feat_enable, 0},
+	{"decimal-floating-point-v3", feat_enable, 0},
+	{"decimal-integer-v3", feat_enable, 0},
+	{"fixed-point-v3", feat_enable, 0},
+	{"floating-point-v3", feat_enable, 0},
+	{"group-start-register", feat_enable, 0},
+	{"pc-relative-addressing", feat_enable, 0},
+	{"machine-check-power9", feat_enable_mce_power9, 0},
+	{"performance-monitor-power9", feat_enable_pm_power9, 0},
+	{"event-based-branch-v3", feat_enable, 0},
+	{"random-number-generator", feat_enable, 0},
+	{"system-call-vectored", feat_disable, 0},
+	{"trace-interrupt-v3", feat_enable, 0},
+	{"vector-v3", feat_enable, 0},
+	{"vector-binary128", feat_enable, 0},
+	{"vector-binary16", feat_enable, 0},
+	{"wait-v3", feat_enable, 0},
+};
+
+/* XXX: how to configure this? Default + boot time? */
+#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
+#define CPU_FEATURE_ENABLE_UNKNOWN 1
+#else
+#define CPU_FEATURE_ENABLE_UNKNOWN 0
+#endif
+
+void __init cpufeatures_setup_start(u32 isa)
+{
+	DBG("CPUFEATURES setup for isa %d\n", isa);
+
+	if (isa >= 3000) {
+		cur_cpu_spec->cpu_features |= CPU_FTR_ARCH_300;
+		cur_cpu_spec->cpu_user_features2 |= PPC_FEATURE2_ARCH_3_00;
+	}
+}
+
+int __init cpufeatures_process_feature(struct dt_cpu_feature *f)
+{
+	const struct dt_cpu_feature_match *m;
+	int known = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dt_cpu_feature_match_table); i++) {
+		m = &dt_cpu_feature_match_table[i];
+		if (!strcmp(f->name, m->name)) {
+			known = 1;
+			if (m->enable(f))
+				goto enabled;
+			goto not_enabled;
+		}
+	}
+
+	if (CPU_FEATURE_ENABLE_UNKNOWN) {
+		if (feat_try_enable_unknown(f))
+			goto enabled;
+	}
+
+not_enabled:
+	if (known)
+		DBG("CPU feature not enabling:%s (disabled or unsupported by kernel)\n", f->name);
+	else
+		DBG("CPU feature not enabling:%s (unknown and unsupported by kernel)\n", f->name);
+
+	return 0;
+
+enabled:
+	if (m->cpu_ftr_bit_mask)
+		cur_cpu_spec->cpu_features |= m->cpu_ftr_bit_mask;
+	if (known)
+		DBG("CPU feature enabling:%s\n", f->name);
+	else
+		DBG("CPU feature enabling:%s (unknown)\n", f->name);
+
+	return 1;
+}
+
+void __init cpufeatures_setup_finished(void)
+{
+	if (hv_mode && !(cur_cpu_spec->cpu_features & CPU_FTR_HVMODE)) {
+		pr_err("CPU feature hypervisor not present in device tree but HV mode is enabled in the CPU. Enabling.\n");
+		cur_cpu_spec->cpu_features |= CPU_FTR_HVMODE;
+	}
+
+	if (prereq_pece_msgp == 2) { /* doorbell and stop */
+		u64 lpcr;
+
+		lpcr = mfspr(SPRN_LPCR);
+		lpcr |=  LPCR_PECEDP; /* priv doorbell wakeup */
+		mtspr(SPRN_LPCR, lpcr);
+	}
+
+	system_registers.hfscr = mfspr(SPRN_HFSCR);
+	system_registers.fscr = mfspr(SPRN_FSCR);
+	system_registers.lpcr = mfspr(SPRN_LPCR);
+}
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index e79b9daa873c..ca95c1fa3e13 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -23,7 +23,9 @@
 #include <asm/mmu.h>
 #include <asm/setup.h>
 
-struct cpu_spec* cur_cpu_spec = NULL;
+static struct cpu_spec the_cpu_spec __read_mostly;
+
+struct cpu_spec* cur_cpu_spec __read_mostly = NULL;
 EXPORT_SYMBOL(cur_cpu_spec);
 
 /* The platform string corresponding to the real PVR */
@@ -2179,7 +2181,15 @@ static struct cpu_spec __initdata cpu_specs[] = {
 #endif /* CONFIG_E500 */
 };
 
-static struct cpu_spec the_cpu_spec;
+void __init set_cur_cpu_spec(struct cpu_spec *s)
+{
+	struct cpu_spec *t = &the_cpu_spec;
+
+	t = PTRRELOC(t);
+	*t = *s;
+
+	*PTRRELOC(&cur_cpu_spec) = &the_cpu_spec;
+}
 
 static struct cpu_spec * __init setup_cpu_spec(unsigned long offset,
 					       struct cpu_spec *s)
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f5d399e46193..a60b3ad98df5 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -58,6 +58,7 @@
 #include <asm/debug.h>
 #include <asm/epapr_hcalls.h>
 #include <asm/firmware.h>
+#include <asm/cpufeatures.h>
 
 #include <mm/mmu_decl.h>
 
@@ -67,6 +68,12 @@
 #define DBG(fmt...)
 #endif
 
+#ifdef CONFIG_PPC_CPUFEATURES_DT
+int __initdata has_cpufeatures_node = 0;
+#else
+static const int has_cpufeatures_node = 0;
+#endif
+
 #ifdef CONFIG_PPC64
 int __initdata iommu_is_off;
 int __initdata iommu_force_on;
@@ -300,6 +307,268 @@ static void __init check_cpu_feature_properties(unsigned long node)
 	}
 }
 
+#ifdef CONFIG_PPC_CPUFEATURES_DT
+#define CPUFT_WARN(str, name) printk(KERN_WARNING "WARNING: /cpus/features/%s dt:%s\n", name, str)
+
+static int nr_dt_cpu_features;
+static struct dt_cpu_feature *dt_cpu_features;
+
+static int __init process_cpufeatures_node(unsigned long node,
+					  const char *uname, int i)
+{
+	const __be32 *prop;
+	struct dt_cpu_feature *f;
+	int len;
+
+	f = &dt_cpu_features[i];
+	memset(f, 0, sizeof(struct dt_cpu_feature));
+
+	f->node = node;
+
+	f->name = uname;
+
+	prop = of_get_flat_dt_prop(node, "isa", &len);
+	if (!prop) {
+		CPUFT_WARN("missing isa property", uname);
+		return 0;
+	}
+	f->isa = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "usable-mask", &len);
+	if (!prop) {
+		CPUFT_WARN("missing usable-mask property", uname);
+		return 0;
+	}
+	f->usable_mask = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "hv-support", &len);
+	if (prop)
+		f->hv_support = be32_to_cpup(prop);
+	prop = of_get_flat_dt_prop(node, "os-support", &len);
+	if (prop)
+		f->os_support = be32_to_cpup(prop);
+
+	prop = of_get_flat_dt_prop(node, "hfscr-bit-nr", &len);
+	if (prop)
+		f->hfscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->hfscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "fscr-bit-nr", &len);
+	if (prop)
+		f->fscr_bit_nr = be32_to_cpup(prop);
+	else
+		f->fscr_bit_nr = -1;
+	prop = of_get_flat_dt_prop(node, "hwcap-bit-nr", &len);
+	if (prop)
+		f->hwcap_bit_nr = be32_to_cpup(prop);
+	else
+		f->hwcap_bit_nr = -1;
+
+	if (f->usable_mask & USABLE_HV) {
+		if (!(mfmsr() & MSR_HV)) {
+			CPUFT_WARN("HV feature passed to guest\n", uname);
+			return 0;
+		}
+
+		if (!f->hv_support && f->hfscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted hfscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->hv_support == HV_SUPPORT_HFSCR) {
+			if (f->hfscr_bit_nr == -1) {
+				CPUFT_WARN("missing hfscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->hv_support != HV_SUPPORT_NONE || f->hfscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted hv_support/hfscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (f->usable_mask & USABLE_OS) {
+		if (!f->os_support && f->fscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted fscr_bit_nr\n", uname);
+			return 0;
+		}
+
+		if (f->os_support == OS_SUPPORT_FSCR) {
+			if (f->fscr_bit_nr == -1) {
+				CPUFT_WARN("missing fscr_bit_nr\n", uname);
+				return 0;
+			}
+		}
+	} else {
+		if (f->os_support != OS_SUPPORT_NONE || f->fscr_bit_nr != -1) {
+			CPUFT_WARN("unwanted os_support/fscr_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	if (!(f->usable_mask & USABLE_PR)) {
+		if (f->hwcap_bit_nr != -1) {
+			CPUFT_WARN("unwanted hwcap_bit_nr\n", uname);
+			return 0;
+		}
+	}
+
+	/* Do all the independent features in the first pass */
+	if (!of_get_flat_dt_prop(node, "dependencies", &len)) {
+		if (cpufeatures_process_feature(f))
+			f->enabled = 1;
+		else
+			f->disabled = 1;
+	}
+
+	return 0;
+}
+
+static void __init cpufeatures_deps_enable(struct dt_cpu_feature *f)
+{
+	const __be32 *prop;
+	int len;
+	int nr_deps;
+	int i;
+
+	if (f->enabled || f->disabled)
+		return;
+
+	prop = of_get_flat_dt_prop(f->node, "dependencies", &len);
+	if (!prop) {
+		CPUFT_WARN("missing dependencies property", f->name);
+		return;
+	}
+
+	nr_deps = len / sizeof(int);
+
+	for (i = 0; i < nr_deps; i++) {
+		unsigned long phandle = be32_to_cpu(prop[i]);
+		int j;
+
+		for (j = 0; j < nr_dt_cpu_features; j++) {
+			struct dt_cpu_feature *d = &dt_cpu_features[j];
+
+			if (of_get_flat_dt_phandle(d->node) == phandle) {
+				cpufeatures_deps_enable(d);
+				if (d->disabled) {
+					f->disabled = 1;
+					return;
+				}
+			}
+		}
+	}
+
+	if (cpufeatures_process_feature(f))
+		f->enabled = 1;
+	else
+		f->disabled = 1;
+}
+
+static int __init scan_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	process_cpufeatures_node(node, uname, *count);
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init count_cpufeatures_subnodes(unsigned long node,
+					  const char *uname,
+					  void *data)
+{
+	int *count = data;
+
+	(*count)++;
+
+	return 0;
+}
+
+static int __init early_init_dt_scan_cpufeatures(unsigned long node,
+					  const char *uname, int depth,
+					  void *data)
+{
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	const __be32 *prop;
+	int count, i;
+	u32 isa;
+
+	/* We are scanning "features" nodes only */
+	if (type == NULL || strcmp(type, "cpu-features") != 0)
+		return 0;
+
+	prop = of_get_flat_dt_prop(node, "isa", NULL);
+	if (!prop) {
+		printk("cpu-features node has missing property \"isa\"\n");
+		return 0;
+	}
+
+	isa = be32_to_cpup(prop);
+
+	has_cpufeatures_node = 1;
+
+	/* Count and allocate space for cpu features */
+	of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes,
+						&nr_dt_cpu_features);
+	dt_cpu_features = __va(
+		memblock_alloc(sizeof(struct dt_cpu_feature)*
+				nr_dt_cpu_features, PAGE_SIZE));
+
+	cpufeatures_setup_start(isa);
+
+	/* Scan nodes into dt_cpu_features and enable those without deps  */
+	count = 0;
+	of_scan_flat_dt_subnodes(node, scan_cpufeatures_subnodes, &count);
+
+	/* Recursive enable remaining features with dependencies */
+	for (i = 0; i < nr_dt_cpu_features; i++) {
+		struct dt_cpu_feature *f = &dt_cpu_features[i];
+
+		cpufeatures_deps_enable(f);
+	}
+
+	cpufeatures_setup_finished();
+
+	memblock_free(__pa(dt_cpu_features),
+			sizeof(struct dt_cpu_feature)*nr_dt_cpu_features);
+
+	return 0;
+}
+
+static int __init early_init_dt_scan_cpufeatures_exists(unsigned long node,
+					  const char *uname, int depth,
+					  void *data)
+{
+	const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
+	int *exists = data;
+
+	/* We are scanning "features" nodes only */
+	if (type == NULL || strcmp(type, "cpu-features") != 0)
+		return 0;
+
+	*exists = 1;
+
+	return 0;
+}
+
+/*
+ * Does the /cpus/features/ node exist?
+ */
+int __init early_init_devtree_check_cpu_features_exists(void)
+{
+	int exists = 0;
+	of_scan_flat_dt(early_init_dt_scan_cpufeatures_exists, &exists);
+	return exists;
+}
+
+#endif /* CONFIG_PPC_CPUFEATURES_DT */
+
 static int __init early_init_dt_scan_cpus(unsigned long node,
 					  const char *uname, int depth,
 					  void *data)
@@ -377,22 +646,32 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
 	 * uses the 0x0f000002 PVR value; in POWER5+ mode
 	 * it uses 0x0f000001.
 	 */
-	prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
-	if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
-		identify_cpu(0, be32_to_cpup(prop));
+	if (!has_cpufeatures_node) {
+		prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+		if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000)
+			identify_cpu(0, be32_to_cpup(prop));
+		identical_pvr_fixup(node);
 
-	identical_pvr_fixup(node);
-
-	check_cpu_feature_properties(node);
-	check_cpu_pa_features(node);
-	init_mmu_slb_size(node);
+		check_cpu_feature_properties(node);
+		check_cpu_pa_features(node);
 
 #ifdef CONFIG_PPC64
-	if (nthreads > 1)
-		cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
-	else
-		cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+		if (nthreads > 1)
+			cur_cpu_spec->cpu_features |= CPU_FTR_SMT;
+		else
+			cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
+#endif
+	} else {
+		strcpy(cur_cpu_spec->cpu_name, uname);
+#ifdef CONFIG_PPC64
+		if (nthreads == 1)
+			cur_cpu_spec->cpu_features &= ~CPU_FTR_SMT;
 #endif
+	}
+
+
+	init_mmu_slb_size(node);
+
 	return 0;
 }
 
@@ -722,6 +1001,10 @@ void __init early_init_devtree(void *params)
 
 	DBG("Scanning CPUs ...\n");
 
+#ifdef CONFIG_PPC_CPUFEATURES_DT
+	of_scan_flat_dt(early_init_dt_scan_cpufeatures, NULL);
+#endif
+
 	/* Retrieve CPU related informations from the flat tree
 	 * (altivec support, boot CPU ID, ...)
 	 */
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 4697da895133..fe52229681da 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -256,7 +256,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 	seq_printf(m, "processor\t: %lu\n", cpu_id);
 	seq_printf(m, "cpu\t\t: ");
 
-	if (cur_cpu_spec->pvr_mask)
+	if (cur_cpu_spec->pvr_mask && cur_cpu_spec->cpu_name)
 		seq_printf(m, "%s", cur_cpu_spec->cpu_name);
 	else
 		seq_printf(m, "unknown (%08x)", pvr);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f997154dfc41..f3e65de63ce8 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -49,6 +49,7 @@
 #include <asm/paca.h>
 #include <asm/time.h>
 #include <asm/cputable.h>
+#include <asm/cpufeatures.h>
 #include <asm/sections.h>
 #include <asm/btext.h>
 #include <asm/nvram.h>
@@ -274,8 +275,17 @@ void __init early_setup(unsigned long dt_ptr)
 
 	/* -------- printk is _NOT_ safe to use here ! ------- */
 
-	/* Identify CPU type */
+#ifdef CONFIG_PPC_CPUFEATURES_DT
+	/* Setup flat device-tree pointer */
+	initial_boot_params = __va(dt_ptr);
+	if (early_init_devtree_check_cpu_features_exists())
+		cpufeatures_setup_cpu();
+	else
+		/* Legacy table-based approach when /cpus/features is missing */
+		identify_cpu(0, mfspr(SPRN_PVR));
+#else
 	identify_cpu(0, mfspr(SPRN_PVR));
+#endif
 
 	/* Assume we're on cpu 0 for now. Don't write to the paca yet! */
 	initialise_paca(&boot_paca, 0);
@@ -541,6 +551,9 @@ void __init initialize_cache_info(void)
 	dcache_bsize = ppc64_caches.l1d.block_size;
 	icache_bsize = ppc64_caches.l1i.block_size;
 
+	cur_cpu_spec->dcache_bsize = dcache_bsize;
+	cur_cpu_spec->icache_bsize = icache_bsize;
+
 	DBG(" <- initialize_cache_info()\n");
 }
 
-- 
2.11.0

[PATCH 0/3] cpufeatures merge candidate

[Nicholas Piggin]

I expect this will require still some more changes, but I think it's
getting close to polished. Intention is to make it default off and
unsupported at the initial merge, to give a new more weeks to test
then freeze the format.

I included the firmware cpufeatures patch here as well.

Thanks,
Nick

[PATCH 2/3] of/fdt: introduce of_scan_flat_dt_subnodes and of_get_flat_dt_phandle

[Nicholas Piggin]

Introduce primitives for FDT parsing. These will be used for powerpc
cpufeatures node scanning, which has quite complex structure but should
be processed early.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 drivers/of/fdt.c       | 38 ++++++++++++++++++++++++++++++++++++++
 include/linux/of_fdt.h |  6 ++++++
 2 files changed, 44 insertions(+)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index e5ce4b59e162..961ca97072a9 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -754,6 +754,36 @@ int __init of_scan_flat_dt(int (*it)(unsigned long node,
 }
 
 /**
+ * of_scan_flat_dt_subnodes - scan sub-nodes of a node call callback on each.
+ * @it: callback function
+ * @data: context data pointer
+ *
+ * This function is used to scan sub-nodes of a node.
+ */
+int __init of_scan_flat_dt_subnodes(unsigned long parent,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data)
+{
+	const void *blob = initial_boot_params;
+	int node;
+
+	fdt_for_each_subnode(node, blob, parent) {
+		const char *pathp;
+		int rc;
+
+		pathp = fdt_get_name(blob, node, NULL);
+		if (*pathp == '/')
+			pathp = kbasename(pathp);
+		rc = it(node, pathp, data);
+		if (rc)
+			return rc;
+	}
+	return 0;
+}
+
+/**
  * of_get_flat_dt_subnode_by_name - get the subnode by given name
  *
  * @node: the parent node
@@ -812,6 +842,14 @@ int __init of_flat_dt_match(unsigned long node, const char *const *compat)
 	return of_fdt_match(initial_boot_params, node, compat);
 }
 
+/**
+ * of_get_flat_dt_prop - Given a node in the flat blob, return the phandle
+ */
+uint32_t __init of_get_flat_dt_phandle(unsigned long node)
+{
+	return fdt_get_phandle(initial_boot_params, node);
+}
+
 struct fdt_scan_status {
 	const char *name;
 	int namelen;
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index 271b3fdf0070..1dfbfd0d8040 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -54,6 +54,11 @@ extern char __dtb_end[];
 extern int of_scan_flat_dt(int (*it)(unsigned long node, const char *uname,
 				     int depth, void *data),
 			   void *data);
+extern int of_scan_flat_dt_subnodes(unsigned long node,
+				    int (*it)(unsigned long node,
+					      const char *uname,
+					      void *data),
+				    void *data);
 extern int of_get_flat_dt_subnode_by_name(unsigned long node,
 					  const char *uname);
 extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
@@ -62,6 +67,7 @@ extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern int of_flat_dt_match(unsigned long node, const char *const *matches);
 extern unsigned long of_get_flat_dt_root(void);
 extern int of_get_flat_dt_size(void);
+extern uint32_t of_get_flat_dt_phandle(unsigned long node);
 
 extern int early_init_dt_scan_chosen(unsigned long node, const char *uname,
 				     int depth, void *data);
-- 
2.11.0