[1/7] powerpc: introduce pte_set_hash_slot() helper

Message ID 1504910713-7094-2-git-send-email-linuxram@us.ibm.com
State Changes Requested
Headers show
Series
  • powerpc: Free up RPAGE_RSV bits
Related show

Commit Message

Ram Pai Sept. 8, 2017, 10:44 p.m.
Introduce pte_set_hash_slot().It  sets the (H_PAGE_F_SECOND|H_PAGE_F_GIX)
bits at  the   appropriate   location   in   the   PTE  of  4K  PTE.  For
64K PTE, it  sets  the  bits  in  the  second  part  of  the  PTE. Though
the implementation  for the former just needs the slot parameter, it does
take some additional parameters to keep the prototype consistent.

This function  will  be  handy  as  we   work   towards  re-arranging the
bits in the later patches.

Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Ram Pai <linuxram@us.ibm.com>
---
 arch/powerpc/include/asm/book3s/64/hash-4k.h  |   15 +++++++++++++++
 arch/powerpc/include/asm/book3s/64/hash-64k.h |   25 +++++++++++++++++++++++++
 2 files changed, 40 insertions(+), 0 deletions(-)

Comments

Balbir Singh Sept. 13, 2017, 7:55 a.m. | #1
On Sat, Sep 9, 2017 at 8:44 AM, Ram Pai <linuxram@us.ibm.com> wrote:
> Introduce pte_set_hash_slot().It  sets the (H_PAGE_F_SECOND|H_PAGE_F_GIX)
> bits at  the   appropriate   location   in   the   PTE  of  4K  PTE.  For
> 64K PTE, it  sets  the  bits  in  the  second  part  of  the  PTE. Though
> the implementation  for the former just needs the slot parameter, it does
> take some additional parameters to keep the prototype consistent.
>
> This function  will  be  handy  as  we   work   towards  re-arranging the
> bits in the later patches.
>
> Reviewed-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
> Signed-off-by: Ram Pai <linuxram@us.ibm.com>
> ---
>  arch/powerpc/include/asm/book3s/64/hash-4k.h  |   15 +++++++++++++++
>  arch/powerpc/include/asm/book3s/64/hash-64k.h |   25 +++++++++++++++++++++++++
>  2 files changed, 40 insertions(+), 0 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
> index 0c4e470..8909039 100644
> --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
> +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
> @@ -48,6 +48,21 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
>  }
>  #endif
>
> +/*
> + * 4k pte format is  different  from  64k  pte  format.  Saving  the
> + * hash_slot is just a matter of returning the pte bits that need to
> + * be modified. On 64k pte, things are a  little  more  involved and
> + * hence  needs   many   more  parameters  to  accomplish  the  same.
> + * However we  want  to abstract this out from the caller by keeping
> + * the prototype consistent across the two formats.
> + */
> +static inline unsigned long pte_set_hash_slot(pte_t *ptep, real_pte_t rpte,
> +                       unsigned int subpg_index, unsigned long slot)
> +{
> +       return (slot << H_PAGE_F_GIX_SHIFT) &
> +               (H_PAGE_F_SECOND | H_PAGE_F_GIX);
> +}
> +
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>
>  static inline char *get_hpte_slot_array(pmd_t *pmdp)
> diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> index 9732837..6652669 100644
> --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
> +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> @@ -74,6 +74,31 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
>         return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
>  }
>
> +/*
> + * Commit the hash slot and return pte bits that needs to be modified.
> + * The caller is expected to modify the pte bits accordingly and
> + * commit the pte to memory.
> + */
> +static inline unsigned long pte_set_hash_slot(pte_t *ptep, real_pte_t rpte,
> +               unsigned int subpg_index, unsigned long slot)
> +{
> +       unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
> +
> +       rpte.hidx &= ~(0xfUL << (subpg_index << 2));
> +       *hidxp = rpte.hidx  | (slot << (subpg_index << 2));
> +       /*
> +        * Commit the hidx bits to memory before returning.
> +        * Anyone reading  pte  must  ensure hidx bits are
> +        * read  only  after  reading the pte by using the

Can you lose the only and make it "read after reading the pte"
read only is easy to confuse as read-only

> +        * read-side  barrier  smp_rmb(). __real_pte() can
> +        * help ensure that.
> +        */
> +       smp_wmb();
> +
> +       /* no pte bits to be modified, return 0x0UL */
> +       return 0x0UL;

Acked-by: Balbir Singh <bsingharora@gmail.com>

Balbir Singh.
Michael Ellerman Oct. 19, 2017, 4:52 a.m. | #2
Ram Pai <linuxram@us.ibm.com> writes:
> diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> index 9732837..6652669 100644
> --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
> +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
> @@ -74,6 +74,31 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
>  	return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
>  }
>  
> +/*
> + * Commit the hash slot and return pte bits that needs to be modified.
> + * The caller is expected to modify the pte bits accordingly and
> + * commit the pte to memory.
> + */
> +static inline unsigned long pte_set_hash_slot(pte_t *ptep, real_pte_t rpte,
> +		unsigned int subpg_index, unsigned long slot)
> +{
> +	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
> +
> +	rpte.hidx &= ~(0xfUL << (subpg_index << 2));
> +	*hidxp = rpte.hidx  | (slot << (subpg_index << 2));
                           ^
                           stray space here
> +	/*
> +	 * Commit the hidx bits to memory before returning.

I'd prefer we didn't use "commit", it implies the bits are actually
written to memory by the barrier, which is not true. The barrier is just
a barrier or fence which prevents some reorderings of the things before
it and the things after it.

> +	 * Anyone reading  pte  must  ensure hidx bits are
> +	 * read  only  after  reading the pte by using the
> +	 * read-side  barrier  smp_rmb().

That seems OK. Though I'm reminded that I dislike your justified
comments, the odd spacing is jarring to read.

>          __real_pte() can
> +	 * help ensure that.

It doesn't help, it *does* do that.

cheers

Patch

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 0c4e470..8909039 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -48,6 +48,21 @@  static inline int hash__hugepd_ok(hugepd_t hpd)
 }
 #endif
 
+/*
+ * 4k pte format is  different  from  64k  pte  format.  Saving  the
+ * hash_slot is just a matter of returning the pte bits that need to
+ * be modified. On 64k pte, things are a  little  more  involved and
+ * hence  needs   many   more  parameters  to  accomplish  the  same.
+ * However we  want  to abstract this out from the caller by keeping
+ * the prototype consistent across the two formats.
+ */
+static inline unsigned long pte_set_hash_slot(pte_t *ptep, real_pte_t rpte,
+			unsigned int subpg_index, unsigned long slot)
+{
+	return (slot << H_PAGE_F_GIX_SHIFT) &
+		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
+}
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 static inline char *get_hpte_slot_array(pmd_t *pmdp)
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 9732837..6652669 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -74,6 +74,31 @@  static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
 	return (pte_val(rpte.pte) >> H_PAGE_F_GIX_SHIFT) & 0xf;
 }
 
+/*
+ * Commit the hash slot and return pte bits that needs to be modified.
+ * The caller is expected to modify the pte bits accordingly and
+ * commit the pte to memory.
+ */
+static inline unsigned long pte_set_hash_slot(pte_t *ptep, real_pte_t rpte,
+		unsigned int subpg_index, unsigned long slot)
+{
+	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+
+	rpte.hidx &= ~(0xfUL << (subpg_index << 2));
+	*hidxp = rpte.hidx  | (slot << (subpg_index << 2));
+	/*
+	 * Commit the hidx bits to memory before returning.
+	 * Anyone reading  pte  must  ensure hidx bits are
+	 * read  only  after  reading the pte by using the
+	 * read-side  barrier  smp_rmb(). __real_pte() can
+	 * help ensure that.
+	 */
+	smp_wmb();
+
+	/* no pte bits to be modified, return 0x0UL */
+	return 0x0UL;
+}
+
 #define __rpte_to_pte(r)	((r).pte)
 extern bool __rpte_sub_valid(real_pte_t rpte, unsigned long index);
 /*