LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH v3 01/11] hugetlb: Harmonize hugetlb.h arch specific defines with pgtable.h
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

asm-generic/hugetlb.h proposes generic implementations of hugetlb
related functions: use __HAVE_ARCH_HUGE* defines in order to make arch
specific implementations of hugetlb functions consistent with pgtable.h
scheme.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm64/include/asm/hugetlb.h | 2 +-
 include/asm-generic/hugetlb.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index e73f68569624..3fcf14663dfa 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -81,9 +81,9 @@ extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
 extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 				  unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
-#define huge_pte_clear huge_pte_clear
 extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 9d0cde8ab716..3da7cff52360 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -32,7 +32,7 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
-#ifndef huge_pte_clear
+#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, unsigned long sz)
 {
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 02/11] hugetlb: Introduce generic version of hugetlb_free_pgd_range
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, arm64, mips, parisc, sh, x86 architectures use the
same version of hugetlb_free_pgd_range, so move this generic
implementation into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb.h     | 12 ++----------
 arch/arm64/include/asm/hugetlb.h   | 10 ----------
 arch/ia64/include/asm/hugetlb.h    |  5 +++--
 arch/mips/include/asm/hugetlb.h    | 13 ++-----------
 arch/parisc/include/asm/hugetlb.h  | 12 ++----------
 arch/powerpc/include/asm/hugetlb.h |  4 +++-
 arch/sh/include/asm/hugetlb.h      | 12 ++----------
 arch/sparc/include/asm/hugetlb.h   |  4 +++-
 arch/x86/include/asm/hugetlb.h     | 11 ++---------
 include/asm-generic/hugetlb.h      | 11 +++++++++++
 10 files changed, 30 insertions(+), 64 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 7d26f6c4f0f5..047b893ef95d 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -23,19 +23,9 @@
 #define _ASM_ARM_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 #include <asm/hugetlb-3level.h>
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr, unsigned long len)
 {
@@ -68,4 +58,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_ARM_HUGETLB_H */
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 3fcf14663dfa..4af1a800a900 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -25,16 +25,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return READ_ONCE(*ptep);
 }
 
-
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr, unsigned long len)
 {
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 74d2a5540aaf..afe9fa4d969b 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -3,9 +3,8 @@
 #define _ASM_IA64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
@@ -70,4 +69,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_IA64_HUGETLB_H */
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 982bc0685330..53764050243e 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -10,8 +10,6 @@
 #define __ASM_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
@@ -38,15 +36,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr,
-					  unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
@@ -114,4 +103,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* __ASM_HUGETLB_H */
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 58e0f4620426..28c23b68d38d 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -3,8 +3,6 @@
 #define _ASM_PARISC64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
@@ -32,14 +30,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
@@ -71,4 +61,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_PARISC64_HUGETLB_H */
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 3225eb6402cc..de46ee16b615 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -4,7 +4,6 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 extern struct kmem_cache *hugepte_cache;
 
@@ -113,6 +112,7 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 #endif
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
@@ -193,4 +193,6 @@ static inline pte_t *hugepte_offset(hugepd_t hpd, unsigned long addr,
 }
 #endif /* CONFIG_HUGETLB_PAGE */
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_POWERPC_HUGETLB_H */
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 735939c0f513..f6a51b609409 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -4,8 +4,6 @@
 
 #include <asm/cacheflush.h>
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
@@ -27,14 +25,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
@@ -85,4 +75,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_SH_HUGETLB_H */
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 300557c66698..59d89b52ccb7 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -3,7 +3,6 @@
 #define _ASM_SPARC64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 #ifdef CONFIG_HUGETLB_PAGE
 struct pud_huge_patch_entry {
@@ -84,8 +83,11 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_SPARC64_HUGETLB_H */
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 5ed826da5e07..996ce8e15365 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 #define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)
 
@@ -28,14 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 				   pte_t *ptep, pte_t pte)
 {
@@ -90,4 +81,6 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 static inline bool gigantic_page_supported(void) { return true; }
 #endif
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_X86_HUGETLB_H */
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 3da7cff52360..c697ca9dda18 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -40,4 +40,15 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+		unsigned long addr, unsigned long end,
+		unsigned long floor, unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* Re: [PATCH kernel v3 2/2] KVM: PPC: Check if IOMMU page is contained in the pinned physical page
From: Alexey Kardashevskiy @ 2018-07-05  5:19 UTC (permalink / raw)
  To: David Gibson
  Cc: linuxppc-dev, kvm-ppc, Alex Williamson, Michael Ellerman,
	Paul Mackerras
In-Reply-To: <20180705024220.GF3450@umbus.fritz.box>

[-- Attachment #1: Type: text/plain, Size: 4745 bytes --]

On Thu, 5 Jul 2018 12:42:20 +1000
David Gibson <david@gibson.dropbear.id.au> wrote:

> On Wed, Jul 04, 2018 at 03:00:52PM +1000, Alexey Kardashevskiy wrote:
> > A VM which has:
> >  - a DMA capable device passed through to it (eg. network card);
> >  - running a malicious kernel that ignores H_PUT_TCE failure;
> >  - capability of using IOMMU pages bigger that physical pages
> > can create an IOMMU mapping that exposes (for example) 16MB of
> > the host physical memory to the device when only 64K was allocated to the VM.
> > 
> > The remaining 16MB - 64K will be some other content of host memory, possibly
> > including pages of the VM, but also pages of host kernel memory, host
> > programs or other VMs.
> > 
> > The attacking VM does not control the location of the page it can map,
> > and is only allowed to map as many pages as it has pages of RAM.
> > 
> > We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that
> > an IOMMU page is contained in the physical page so the PCI hardware won't
> > get access to unassigned host memory; however this check is missing in
> > the KVM fastpath (H_PUT_TCE accelerated code). We were lucky so far and
> > did not hit this yet as the very first time when the mapping happens
> > we do not have tbl::it_userspace allocated yet and fall back to
> > the userspace which in turn calls VFIO IOMMU driver, this fails and
> > the guest does not retry,
> > 
> > This stores the smallest preregistered page size in the preregistered
> > region descriptor and changes the mm_iommu_xxx API to check this against
> > the IOMMU page size. This only allows huge pages use if the entire
> > preregistered block is backed with huge pages which are completely
> > contained the preregistered chunk; otherwise this defaults to PAGE_SIZE.
> > 
> > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>  
> 
> Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> 
> On the grounds that I think this version is safe, which the old one
> wasn't.  However it still has some flaws..
> 
> [snip]
> > @@ -125,7 +126,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> >  {
> >  	struct mm_iommu_table_group_mem_t *mem;
> >  	long i, j, ret = 0, locked_entries = 0;
> > -	struct page *page = NULL;
> > +	unsigned int pageshift;
> > +	struct page *page = NULL, *head = NULL;
> >  
> >  	mutex_lock(&mem_list_mutex);
> >  
> > @@ -159,6 +161,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> >  		goto unlock_exit;
> >  	}
> >  
> > +	mem->pageshift = 64;
> >  	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
> >  	if (!mem->hpas) {
> >  		kfree(mem);
> > @@ -199,9 +202,35 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> >  			}
> >  		}
> >  populate:
> > +		pageshift = PAGE_SHIFT;
> > +		if (PageCompound(page)) {
> > +			/* Make sure huge page is contained completely */
> > +			struct page *tmphead = compound_head(page);
> > +			unsigned int n = compound_order(tmphead);
> > +
> > +			if (!head) {
> > +				/* Is it a head of a huge page? */
> > +				if (page == tmphead) {
> > +					head = tmphead;
> > +					pageshift += n;
> > +				}
> > +			} else if (head == tmphead) {
> > +				/* Still same huge page, good */
> > +				pageshift += n;
> > +
> > +				/* End of the huge page */
> > +				if (page - head == (1UL << n) - 1)
> > +					head = NULL;
> > +			}
> > +		}
> > +		mem->pageshift = min(mem->pageshift, pageshift);
> >  		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
> >  	}
> >  
> > +	/* We have an incomplete huge page, default to PAGE_SHIFT */
> > +	if (head)
> > +		mem->pageshift = PAGE_SHIFT;
> > +  
> 
> So, if the user attempts to prereg a region which starts or ends in
> the middle of a hugepage, this logic will clamp the region's max page
> shift down to PAGE_SHIFT.  That's safe, but not optimal.
> 
> Suppose userspace had an area backed with 16MiB hugepages, and wanted
> to pre-reg a window that was 2MiB aligned, but not 16MiB aligned.  It
> would still be safe to allow 2MiB TCEs, but the code above would clamp
> it down to 64kiB (or 4kiB).
> 
> The code to do it is also pretty convoluted.
> 
> I think you'd be better off initializing mem->pageshift to the largest
> possible natural alignment of the region:
> 	mem->pageshift = ctz64(ua | (entries << PAGE_SHIFT));
> 
> Then it should just be sufficient to clamp pageshift down to
> compound_order() + PAGE_SHIFT for each entry.


I like this better, just one question - does hugetlbfs guarantee the @ua
alignment if backed with an actual huge page?


--
Alexey

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* [PATCH v3 03/11] hugetlb: Introduce generic version of set_huge_pte_at
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, ia64, mips, powerpc, sh, x86 architectures use the
same version of set_huge_pte_at, so move this generic
implementation into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h | 6 ------
 arch/arm64/include/asm/hugetlb.h      | 1 +
 arch/ia64/include/asm/hugetlb.h       | 6 ------
 arch/mips/include/asm/hugetlb.h       | 6 ------
 arch/parisc/include/asm/hugetlb.h     | 1 +
 arch/powerpc/include/asm/hugetlb.h    | 6 ------
 arch/sh/include/asm/hugetlb.h         | 6 ------
 arch/sparc/include/asm/hugetlb.h      | 1 +
 arch/x86/include/asm/hugetlb.h        | 6 ------
 include/asm-generic/hugetlb.h         | 8 +++++++-
 10 files changed, 10 insertions(+), 37 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index d4014fbe5ea3..398fb06e8207 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -37,12 +37,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return retval;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 4af1a800a900..874661a1dff1 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -60,6 +60,7 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 				struct page *page, int writable);
 #define arch_make_huge_pte arch_make_huge_pte
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte);
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index afe9fa4d969b..a235d6f60fb3 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -20,12 +20,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 53764050243e..8ea439041d5d 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -36,12 +36,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 28c23b68d38d..77c8adbac7c3 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -4,6 +4,7 @@
 
 #include <asm/page.h>
 
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index de46ee16b615..ba7d5d8b543f 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -132,12 +132,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index f6a51b609409..bc552e37c1c9 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -25,12 +25,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 59d89b52ccb7..16b0c53ea6c9 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -12,6 +12,7 @@ struct pud_huge_patch_entry {
 extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
 #endif
 
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 996ce8e15365..554d5614b375 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -27,12 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index c697ca9dda18..ee010b756246 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -47,8 +47,14 @@ static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
 {
 	free_pgd_range(tlb, addr, end, floor, ceiling);
 }
+#endif
 
-
+#ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
 #endif
 
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 04/11] hugetlb: Introduce generic version of huge_ptep_get_and_clear
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, ia64, sh, x86 architectures use the
same version of huge_ptep_get_and_clear, so move this generic
implementation into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h | 6 ------
 arch/arm64/include/asm/hugetlb.h      | 1 +
 arch/ia64/include/asm/hugetlb.h       | 6 ------
 arch/mips/include/asm/hugetlb.h       | 1 +
 arch/parisc/include/asm/hugetlb.h     | 1 +
 arch/powerpc/include/asm/hugetlb.h    | 1 +
 arch/sh/include/asm/hugetlb.h         | 6 ------
 arch/sparc/include/asm/hugetlb.h      | 1 +
 arch/x86/include/asm/hugetlb.h        | 6 ------
 include/asm-generic/hugetlb.h         | 8 ++++++++
 10 files changed, 13 insertions(+), 24 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index 398fb06e8207..ad36e84b819a 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -49,12 +49,6 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	ptep_set_wrprotect(mm, addr, ptep);
 }
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 874661a1dff1..6ae0bcafe162 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -66,6 +66,7 @@ extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 				     unsigned long addr, pte_t *ptep);
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index a235d6f60fb3..6719c74da0de 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -20,12 +20,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 8ea439041d5d..0959cc5a41fa 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -36,6 +36,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 77c8adbac7c3..6e281e1bb336 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -8,6 +8,7 @@
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ba7d5d8b543f..ec3e0c2e78f8 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -132,6 +132,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index bc552e37c1c9..08ee6c00b5e9 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -25,12 +25,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 16b0c53ea6c9..944e3a4bfaff 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -16,6 +16,7 @@ extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 554d5614b375..48b8d9b13cc6 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -27,12 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index ee010b756246..0f6f151780dd 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -57,4 +57,12 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 05/11] hugetlb: Introduce generic version of huge_ptep_clear_flush
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, x86 architectures use the same version of
huge_ptep_clear_flush, so move this generic implementation into
asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h | 6 ------
 arch/arm64/include/asm/hugetlb.h      | 1 +
 arch/ia64/include/asm/hugetlb.h       | 1 +
 arch/mips/include/asm/hugetlb.h       | 1 +
 arch/parisc/include/asm/hugetlb.h     | 1 +
 arch/powerpc/include/asm/hugetlb.h    | 1 +
 arch/sh/include/asm/hugetlb.h         | 1 +
 arch/sparc/include/asm/hugetlb.h      | 1 +
 arch/x86/include/asm/hugetlb.h        | 6 ------
 include/asm-generic/hugetlb.h         | 8 ++++++++
 10 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index ad36e84b819a..b897541520ef 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -37,12 +37,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return retval;
 }
 
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 6ae0bcafe162..4c8dd488554d 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -71,6 +71,7 @@ extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 				     unsigned long addr, pte_t *ptep);
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 				  unsigned long addr, pte_t *ptep);
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 6719c74da0de..41b5f6adeee4 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -20,6 +20,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 0959cc5a41fa..7df1f116a3cc 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -48,6 +48,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 6e281e1bb336..9afff26747a1 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -32,6 +32,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index ec3e0c2e78f8..de0769f0b5b2 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -143,6 +143,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 #endif
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 08ee6c00b5e9..9abf9c86b769 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -25,6 +25,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 944e3a4bfaff..651a9593fcee 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -42,6 +42,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 48b8d9b13cc6..8347d5abf882 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -27,12 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
 static inline int huge_pte_none(pte_t pte)
 {
 	return pte_none(pte);
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 0f6f151780dd..ffa63fd8388d 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -65,4 +65,12 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 06/11] hugetlb: Introduce generic version of huge_pte_none
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, arm64, ia64, parisc, powerpc, sh, sparc, x86 architectures
use the same version of huge_pte_none, so move this generic
implementation into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb.h     | 5 -----
 arch/arm64/include/asm/hugetlb.h   | 5 -----
 arch/ia64/include/asm/hugetlb.h    | 5 -----
 arch/mips/include/asm/hugetlb.h    | 1 +
 arch/parisc/include/asm/hugetlb.h  | 5 -----
 arch/powerpc/include/asm/hugetlb.h | 5 -----
 arch/sh/include/asm/hugetlb.h      | 5 -----
 arch/sparc/include/asm/hugetlb.h   | 5 -----
 arch/x86/include/asm/hugetlb.h     | 5 -----
 include/asm-generic/hugetlb.h      | 7 +++++++
 10 files changed, 8 insertions(+), 40 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 047b893ef95d..3d2ce4dbc145 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -43,11 +43,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 4c8dd488554d..49247c6f94db 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,11 +42,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 41b5f6adeee4..bf573500b3c4 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -26,11 +26,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 7df1f116a3cc..1c9c4531376c 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -55,6 +55,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	flush_tlb_page(vma, addr & huge_page_mask(hstate_vma(vma)));
 }
 
+#define __HAVE_ARCH_HUGE_PTE_NONE
 static inline int huge_pte_none(pte_t pte)
 {
 	unsigned long val = pte_val(pte) & ~_PAGE_GLOBAL;
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 9afff26747a1..c09d8c74553c 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -38,11 +38,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index de0769f0b5b2..530b817e097c 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -152,11 +152,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	flush_hugetlb_page(vma, addr);
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 9abf9c86b769..a9f8266f33cf 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -31,11 +31,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 651a9593fcee..11115bbd712e 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -48,11 +48,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 8347d5abf882..c5fdc53b6e41 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -27,11 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
 static inline pte_t huge_pte_wrprotect(pte_t pte)
 {
 	return pte_wrprotect(pte);
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index ffa63fd8388d..2fc3d68424e9 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -73,4 +73,11 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTE_NONE
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 07/11] hugetlb: Introduce generic version of huge_pte_wrprotect
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, arm64, ia64, mips, parisc, powerpc, sh, sparc, x86
architectures use the same version of huge_pte_wrprotect, so move
this generic implementation into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb.h     | 5 -----
 arch/arm64/include/asm/hugetlb.h   | 5 -----
 arch/ia64/include/asm/hugetlb.h    | 5 -----
 arch/mips/include/asm/hugetlb.h    | 5 -----
 arch/parisc/include/asm/hugetlb.h  | 5 -----
 arch/powerpc/include/asm/hugetlb.h | 5 -----
 arch/sh/include/asm/hugetlb.h      | 5 -----
 arch/sparc/include/asm/hugetlb.h   | 5 -----
 arch/x86/include/asm/hugetlb.h     | 5 -----
 include/asm-generic/hugetlb.h      | 7 +++++++
 10 files changed, 7 insertions(+), 45 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 3d2ce4dbc145..1e718a626ef9 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -43,11 +43,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 49247c6f94db..1fd64ebf0cd7 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,11 +42,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index bf573500b3c4..82fe3d7a38d9 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -26,11 +26,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 1c9c4531376c..b3d6bb53ee6e 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -62,11 +62,6 @@ static inline int huge_pte_none(pte_t pte)
 	return !val || (val == (unsigned long)invalid_pte_table);
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index c09d8c74553c..5a102d7251e4 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -38,11 +38,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep);
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 530b817e097c..6f056dc44345 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -152,11 +152,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	flush_hugetlb_page(vma, addr);
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index a9f8266f33cf..54f65094efe6 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -31,11 +31,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 11115bbd712e..f661362376e0 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -48,11 +48,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index c5fdc53b6e41..19668672ab37 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -27,11 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 2fc3d68424e9..cd9697672b79 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -80,4 +80,11 @@ static inline int huge_pte_none(pte_t pte)
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 08/11] hugetlb: Introduce generic version of prepare_hugepage_range
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, arm64, powerpc, sparc, x86 architectures use the same version of
prepare_hugepage_range, so move this generic implementation into
asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb.h     | 11 -----------
 arch/arm64/include/asm/hugetlb.h   | 11 -----------
 arch/ia64/include/asm/hugetlb.h    |  1 +
 arch/mips/include/asm/hugetlb.h    |  1 +
 arch/parisc/include/asm/hugetlb.h  |  1 +
 arch/powerpc/include/asm/hugetlb.h | 15 ---------------
 arch/sh/include/asm/hugetlb.h      |  1 +
 arch/sparc/include/asm/hugetlb.h   | 16 ----------------
 arch/x86/include/asm/hugetlb.h     | 15 ---------------
 include/asm-generic/hugetlb.h      | 15 +++++++++++++++
 10 files changed, 19 insertions(+), 68 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
index 1e718a626ef9..34fb401efe81 100644
--- a/arch/arm/include/asm/hugetlb.h
+++ b/arch/arm/include/asm/hugetlb.h
@@ -32,17 +32,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 1fd64ebf0cd7..3e7f6e69b28d 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -31,17 +31,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 82fe3d7a38d9..cbe296271030 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -9,6 +9,7 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len);
 
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index b3d6bb53ee6e..6ff2531cfb1d 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -18,6 +18,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 					 unsigned long addr,
 					 unsigned long len)
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5a102d7251e4..fb7e0fd858a3 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -22,6 +22,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 6f056dc44345..9fcb5fee2e33 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -117,21 +117,6 @@ void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 54f65094efe6..f1bbd255ee43 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -15,6 +15,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index f661362376e0..2101ea217f33 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -26,22 +26,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 19668672ab37..2e5117d37c7d 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -12,21 +12,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index cd9697672b79..6c0c8b0c71e0 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -87,4 +87,19 @@ static inline pte_t huge_pte_wrprotect(pte_t pte)
 }
 #endif
 
+#ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
+static inline int prepare_hugepage_range(struct file *file,
+		unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+
+	return 0;
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 09/11] hugetlb: Introduce generic version of huge_ptep_set_wrprotect
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, ia64, mips, sh, x86 architectures use the same version
of huge_ptep_set_wrprotect, so move this generic implementation into
asm-generic/hugetlb.h.
Note: powerpc uses twice for book3s/32 and nohash/32 the same version as
the above architectures, but the modification was not straightforward
and hence has not been done.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h        | 6 ------
 arch/arm64/include/asm/hugetlb.h             | 1 +
 arch/ia64/include/asm/hugetlb.h              | 6 ------
 arch/mips/include/asm/hugetlb.h              | 6 ------
 arch/parisc/include/asm/hugetlb.h            | 1 +
 arch/powerpc/include/asm/book3s/32/pgtable.h | 2 ++
 arch/powerpc/include/asm/book3s/64/pgtable.h | 1 +
 arch/powerpc/include/asm/nohash/32/pgtable.h | 2 ++
 arch/powerpc/include/asm/nohash/64/pgtable.h | 1 +
 arch/sh/include/asm/hugetlb.h                | 6 ------
 arch/sparc/include/asm/hugetlb.h             | 1 +
 arch/x86/include/asm/hugetlb.h               | 6 ------
 include/asm-generic/hugetlb.h                | 8 ++++++++
 13 files changed, 17 insertions(+), 30 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index b897541520ef..8247cd6a2ac6 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -37,12 +37,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return retval;
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 3e7f6e69b28d..f4f69ae5466e 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -48,6 +48,7 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 				     unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index cbe296271030..49d1f7949f3a 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -27,12 +27,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 6ff2531cfb1d..3dcf5debf8c4 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -63,12 +63,6 @@ static inline int huge_pte_none(pte_t pte)
 	return !val || (val == (unsigned long)invalid_pte_table);
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr,
 					     pte_t *ptep, pte_t pte,
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index fb7e0fd858a3..9c3950ca2974 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -39,6 +39,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep);
 
diff --git a/arch/powerpc/include/asm/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 02f5acd7ccc4..d2cd1d0226e9 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -228,6 +228,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 {
 	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
 }
+
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 42aafba7a308..7d957f7c47cd 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -451,6 +451,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/powerpc/include/asm/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index 7c46a98cc7f4..f39e200d9591 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -249,6 +249,8 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 {
 	pte_update(ptep, (_PAGE_RW | _PAGE_HWWRITE), _PAGE_RO);
 }
+
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index dd0c7236208f..69fbf7e9b4db 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -238,6 +238,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index f1bbd255ee43..8df4004977b9 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -32,12 +32,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 2101ea217f33..c41754a113f3 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -32,6 +32,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 2e5117d37c7d..de370836a17d 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -12,12 +12,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 6c0c8b0c71e0..9b9039845278 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -102,4 +102,12 @@ static inline int prepare_hugepage_range(struct file *file,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 10/11] hugetlb: Introduce generic version of huge_ptep_set_access_flags
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

arm, ia64, sh, x86 architectures use the same version
of huge_ptep_set_access_flags, so move this generic implementation
into asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h | 7 -------
 arch/arm64/include/asm/hugetlb.h      | 1 +
 arch/ia64/include/asm/hugetlb.h       | 7 -------
 arch/mips/include/asm/hugetlb.h       | 1 +
 arch/parisc/include/asm/hugetlb.h     | 1 +
 arch/powerpc/include/asm/hugetlb.h    | 1 +
 arch/sh/include/asm/hugetlb.h         | 7 -------
 arch/sparc/include/asm/hugetlb.h      | 1 +
 arch/x86/include/asm/hugetlb.h        | 7 -------
 include/asm-generic/hugetlb.h         | 9 +++++++++
 10 files changed, 14 insertions(+), 28 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index 8247cd6a2ac6..54e4b097b1f5 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -37,11 +37,4 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return retval;
 }
 
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
 #endif /* _ASM_ARM_HUGETLB_3LEVEL_H */
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index f4f69ae5466e..80887abcef7f 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,6 +42,7 @@ extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 #define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte);
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index 49d1f7949f3a..e9b42750fdf5 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -27,13 +27,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	return *ptep;
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 3dcf5debf8c4..120adc3b2ffd 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -63,6 +63,7 @@ static inline int huge_pte_none(pte_t pte)
 	return !val || (val == (unsigned long)invalid_pte_table);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr,
 					     pte_t *ptep, pte_t pte,
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 9c3950ca2974..165b4e5a6f32 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -43,6 +43,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep);
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty);
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 9fcb5fee2e33..9898e234df90 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -137,6 +137,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	flush_hugetlb_page(vma, addr);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index 8df4004977b9..c87195ae0cfa 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -32,13 +32,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	return *ptep;
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c41754a113f3..028a1465fbe7 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -40,6 +40,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index de370836a17d..1df8944904c6 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -12,13 +12,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	return *ptep;
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 9b9039845278..f3c99a03ee83 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -110,4 +110,13 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep,
+		pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* [PATCH v3 11/11] hugetlb: Introduce generic version of huge_ptep_get
From: Alexandre Ghiti @ 2018-07-05  5:16 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
  Cc: Alexandre Ghiti
In-Reply-To: <20180705051640.790-1-alex@ghiti.fr>

ia64, mips, parisc, powerpc, sh, sparc, x86 architectures use the
same version of huge_ptep_get, so move this generic implementation into
asm-generic/hugetlb.h.

Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
---
 arch/arm/include/asm/hugetlb-3level.h | 1 +
 arch/arm64/include/asm/hugetlb.h      | 1 +
 arch/ia64/include/asm/hugetlb.h       | 5 -----
 arch/mips/include/asm/hugetlb.h       | 5 -----
 arch/parisc/include/asm/hugetlb.h     | 5 -----
 arch/powerpc/include/asm/hugetlb.h    | 5 -----
 arch/sh/include/asm/hugetlb.h         | 5 -----
 arch/sparc/include/asm/hugetlb.h      | 5 -----
 arch/x86/include/asm/hugetlb.h        | 5 -----
 include/asm-generic/hugetlb.h         | 7 +++++++
 10 files changed, 9 insertions(+), 35 deletions(-)

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index 54e4b097b1f5..0d9f3918fa7e 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/arch/arm/include/asm/hugetlb-3level.h
@@ -29,6 +29,7 @@
  * ptes.
  * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
  */
+#define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	pte_t retval = *ptep;
diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 80887abcef7f..fb6609875455 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -20,6 +20,7 @@
 
 #include <asm/page.h>
 
+#define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	return READ_ONCE(*ptep);
diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
index e9b42750fdf5..36cc0396b214 100644
--- a/arch/ia64/include/asm/hugetlb.h
+++ b/arch/ia64/include/asm/hugetlb.h
@@ -27,11 +27,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index 120adc3b2ffd..425bb6fc3bda 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -82,11 +82,6 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 165b4e5a6f32..7cb595dcb7d7 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -48,11 +48,6 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty);
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index 9898e234df90..d0032f6f61b2 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -142,11 +142,6 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
index c87195ae0cfa..6f025fe18146 100644
--- a/arch/sh/include/asm/hugetlb.h
+++ b/arch/sh/include/asm/hugetlb.h
@@ -32,11 +32,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 {
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index 028a1465fbe7..3963f80d1cb3 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -53,11 +53,6 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 1df8944904c6..c97b34a29054 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -12,11 +12,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index f3c99a03ee83..71d7b77eea50 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -119,4 +119,11 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGE_PTEP_GET
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */
-- 
2.16.2

^ permalink raw reply related

* Re: [PATCH v2 06/11] hugetlb: Introduce generic version of huge_pte_none
From: Alex Ghiti @ 2018-07-05  5:37 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
In-Reply-To: <20180705051242.694-6-alex@ghiti.fr>

Please drop this serie, sorry for the noise.


On 07/05/2018 05:12 AM, Alexandre Ghiti wrote:
> arm, arm64, ia64, parisc, powerpc, sh, sparc, x86 architectures
> use the same version of huge_pte_none, so move this generic
> implementation into asm-generic/hugetlb.h.
>
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> ---
>   arch/arm/include/asm/hugetlb.h     | 5 -----
>   arch/arm64/include/asm/hugetlb.h   | 5 -----
>   arch/ia64/include/asm/hugetlb.h    | 5 -----
>   arch/mips/include/asm/hugetlb.h    | 1 +
>   arch/parisc/include/asm/hugetlb.h  | 5 -----
>   arch/powerpc/include/asm/hugetlb.h | 5 -----
>   arch/sh/include/asm/hugetlb.h      | 5 -----
>   arch/sparc/include/asm/hugetlb.h   | 5 -----
>   arch/x86/include/asm/hugetlb.h     | 5 -----
>   include/asm-generic/hugetlb.h      | 7 +++++++
>   10 files changed, 8 insertions(+), 40 deletions(-)
>
> diff --git a/arch/arm/include/asm/hugetlb.h b/arch/arm/include/asm/hugetlb.h
> index 047b893ef95d..3d2ce4dbc145 100644
> --- a/arch/arm/include/asm/hugetlb.h
> +++ b/arch/arm/include/asm/hugetlb.h
> @@ -43,11 +43,6 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
> index 4c8dd488554d..49247c6f94db 100644
> --- a/arch/arm64/include/asm/hugetlb.h
> +++ b/arch/arm64/include/asm/hugetlb.h
> @@ -42,11 +42,6 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
> index 41b5f6adeee4..bf573500b3c4 100644
> --- a/arch/ia64/include/asm/hugetlb.h
> +++ b/arch/ia64/include/asm/hugetlb.h
> @@ -26,11 +26,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   {
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
> index 7df1f116a3cc..1c9c4531376c 100644
> --- a/arch/mips/include/asm/hugetlb.h
> +++ b/arch/mips/include/asm/hugetlb.h
> @@ -55,6 +55,7 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   	flush_tlb_page(vma, addr & huge_page_mask(hstate_vma(vma)));
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTE_NONE
>   static inline int huge_pte_none(pte_t pte)
>   {
>   	unsigned long val = pte_val(pte) & ~_PAGE_GLOBAL;
> diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
> index 9afff26747a1..c09d8c74553c 100644
> --- a/arch/parisc/include/asm/hugetlb.h
> +++ b/arch/parisc/include/asm/hugetlb.h
> @@ -38,11 +38,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   {
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
> index de0769f0b5b2..530b817e097c 100644
> --- a/arch/powerpc/include/asm/hugetlb.h
> +++ b/arch/powerpc/include/asm/hugetlb.h
> @@ -152,11 +152,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   	flush_hugetlb_page(vma, addr);
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
> index 9abf9c86b769..a9f8266f33cf 100644
> --- a/arch/sh/include/asm/hugetlb.h
> +++ b/arch/sh/include/asm/hugetlb.h
> @@ -31,11 +31,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   {
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
> index 651a9593fcee..11115bbd712e 100644
> --- a/arch/sparc/include/asm/hugetlb.h
> +++ b/arch/sparc/include/asm/hugetlb.h
> @@ -48,11 +48,6 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   {
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
> index 8347d5abf882..c5fdc53b6e41 100644
> --- a/arch/x86/include/asm/hugetlb.h
> +++ b/arch/x86/include/asm/hugetlb.h
> @@ -27,11 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> -static inline int huge_pte_none(pte_t pte)
> -{
> -	return pte_none(pte);
> -}
> -
>   static inline pte_t huge_pte_wrprotect(pte_t pte)
>   {
>   	return pte_wrprotect(pte);
> diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
> index ffa63fd8388d..2fc3d68424e9 100644
> --- a/include/asm-generic/hugetlb.h
> +++ b/include/asm-generic/hugetlb.h
> @@ -73,4 +73,11 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   }
>   #endif
>   
> +#ifndef __HAVE_ARCH_HUGE_PTE_NONE
> +static inline int huge_pte_none(pte_t pte)
> +{
> +	return pte_none(pte);
> +}
> +#endif
> +
>   #endif /* _ASM_GENERIC_HUGETLB_H */

^ permalink raw reply

* Re: [PATCH 05/11] hugetlb: Introduce generic version of huge_ptep_clear_flush
From: Alex Ghiti @ 2018-07-05  5:38 UTC (permalink / raw)
  To: linux, catalin.marinas, will.deacon, tony.luck, fenghua.yu, ralf,
	paul.burton, jhogan, jejb, deller, benh, paulus, mpe, ysato,
	dalias, davem, tglx, mingo, hpa, x86, arnd, linux-arm-kernel,
	linux-kernel, linux-ia64, linux-mips, linux-parisc, linuxppc-dev,
	linux-sh, sparclinux, linux-arch
In-Reply-To: <20180705045847.32575-6-alex@ghiti.fr>

Please drop this serie, sorry for the noise.


On 07/05/2018 04:58 AM, Alexandre Ghiti wrote:
> arm, x86 architectures use the same version of
> huge_ptep_clear_flush, so move this generic implementation into
> asm-generic/hugetlb.h.
>
> Signed-off-by: Alexandre Ghiti <alex@ghiti.fr>
> ---
>   arch/arm/include/asm/hugetlb-3level.h | 6 ------
>   arch/arm64/include/asm/hugetlb.h      | 1 +
>   arch/ia64/include/asm/hugetlb.h       | 1 +
>   arch/mips/include/asm/hugetlb.h       | 1 +
>   arch/parisc/include/asm/hugetlb.h     | 1 +
>   arch/powerpc/include/asm/hugetlb.h    | 1 +
>   arch/sh/include/asm/hugetlb.h         | 1 +
>   arch/sparc/include/asm/hugetlb.h      | 1 +
>   arch/x86/include/asm/hugetlb.h        | 6 ------
>   include/asm-generic/hugetlb.h         | 8 ++++++++
>   10 files changed, 15 insertions(+), 12 deletions(-)
>
> diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
> index ad36e84b819a..b897541520ef 100644
> --- a/arch/arm/include/asm/hugetlb-3level.h
> +++ b/arch/arm/include/asm/hugetlb-3level.h
> @@ -37,12 +37,6 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
>   	return retval;
>   }
>   
> -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
> -					 unsigned long addr, pte_t *ptep)
> -{
> -	ptep_clear_flush(vma, addr, ptep);
> -}
> -
>   static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
>   					   unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
> index 6ae0bcafe162..4c8dd488554d 100644
> --- a/arch/arm64/include/asm/hugetlb.h
> +++ b/arch/arm64/include/asm/hugetlb.h
> @@ -71,6 +71,7 @@ extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
>   				     unsigned long addr, pte_t *ptep);
>   extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
>   				    unsigned long addr, pte_t *ptep);
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   				  unsigned long addr, pte_t *ptep);
>   #define __HAVE_ARCH_HUGE_PTE_CLEAR
> diff --git a/arch/ia64/include/asm/hugetlb.h b/arch/ia64/include/asm/hugetlb.h
> index 6719c74da0de..41b5f6adeee4 100644
> --- a/arch/ia64/include/asm/hugetlb.h
> +++ b/arch/ia64/include/asm/hugetlb.h
> @@ -20,6 +20,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
>   		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
> index 0959cc5a41fa..7df1f116a3cc 100644
> --- a/arch/mips/include/asm/hugetlb.h
> +++ b/arch/mips/include/asm/hugetlb.h
> @@ -48,6 +48,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
>   	return pte;
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
> index 6e281e1bb336..9afff26747a1 100644
> --- a/arch/parisc/include/asm/hugetlb.h
> +++ b/arch/parisc/include/asm/hugetlb.h
> @@ -32,6 +32,7 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
> index ec3e0c2e78f8..de0769f0b5b2 100644
> --- a/arch/powerpc/include/asm/hugetlb.h
> +++ b/arch/powerpc/include/asm/hugetlb.h
> @@ -143,6 +143,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
>   #endif
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/sh/include/asm/hugetlb.h b/arch/sh/include/asm/hugetlb.h
> index 08ee6c00b5e9..9abf9c86b769 100644
> --- a/arch/sh/include/asm/hugetlb.h
> +++ b/arch/sh/include/asm/hugetlb.h
> @@ -25,6 +25,7 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
> index 944e3a4bfaff..651a9593fcee 100644
> --- a/arch/sparc/include/asm/hugetlb.h
> +++ b/arch/sparc/include/asm/hugetlb.h
> @@ -42,6 +42,7 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> +#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
>   static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
>   					 unsigned long addr, pte_t *ptep)
>   {
> diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
> index 48b8d9b13cc6..8347d5abf882 100644
> --- a/arch/x86/include/asm/hugetlb.h
> +++ b/arch/x86/include/asm/hugetlb.h
> @@ -27,12 +27,6 @@ static inline int prepare_hugepage_range(struct file *file,
>   	return 0;
>   }
>   
> -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
> -					 unsigned long addr, pte_t *ptep)
> -{
> -	ptep_clear_flush(vma, addr, ptep);
> -}
> -
>   static inline int huge_pte_none(pte_t pte)
>   {
>   	return pte_none(pte);
> diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
> index 0f6f151780dd..ffa63fd8388d 100644
> --- a/include/asm-generic/hugetlb.h
> +++ b/include/asm-generic/hugetlb.h
> @@ -65,4 +65,12 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
>   }
>   #endif
>   
> +#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
> +static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
> +		unsigned long addr, pte_t *ptep)
> +{
> +	ptep_clear_flush(vma, addr, ptep);
> +}
> +#endif
> +
>   #endif /* _ASM_GENERIC_HUGETLB_H */

^ permalink raw reply

* Re: [PATCH] cxl: Fix wrong comparison in cxl_adapter_context_get()
From: Frederic Barrat @ 2018-07-05  7:29 UTC (permalink / raw)
  To: Vaibhav Jain, linuxppc-dev, Andrew Donnellan, Dan Carpenter
  Cc: Christophe Lombard, Philippe Bergheaud, Alastair D'Silva,
	stable
In-Reply-To: <20180704152833.2288-1-vaibhav@linux.ibm.com>



Le 04/07/2018 à 17:28, Vaibhav Jain a écrit :
> Function atomic_inc_unless_negative() returns a bool to indicate
> success/failure. However cxl_adapter_context_get() wrongly compares
> the return value against '>=0' which will always be true. The patch
> fixes this comparison to '==0' there by also fixing this compile time
> warning:
> 
> 	drivers/misc/cxl/main.c:290 cxl_adapter_context_get()
> 	warn: 'atomic_inc_unless_negative(&adapter->contexts_num)' is unsigned
> 
> Cc: stable@vger.kernel.org
> Fixes: 70b565bbdb91 ("cxl: Prevent adapter reset if an active context exists")
> Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
> Signed-off-by: Vaibhav Jain <vaibhav@linux.ibm.com>
> ---

Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com>


>   drivers/misc/cxl/main.c | 2 +-
>   1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
> index c1ba0d42cbc8..e0f29b8a872d 100644
> --- a/drivers/misc/cxl/main.c
> +++ b/drivers/misc/cxl/main.c
> @@ -287,7 +287,7 @@ int cxl_adapter_context_get(struct cxl *adapter)
>   	int rc;
>   
>   	rc = atomic_inc_unless_negative(&adapter->contexts_num);
> -	return rc >= 0 ? 0 : -EBUSY;
> +	return rc ? 0 : -EBUSY;
>   }
>   
>   void cxl_adapter_context_put(struct cxl *adapter)
> 

^ permalink raw reply

* [PATCH kernel v4 0/2] KVM: PPC: Check if IOMMU page is contained in the pinned physical page
From: Alexey Kardashevskiy @ 2018-07-05  8:01 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Alexey Kardashevskiy, David Gibson, kvm-ppc, Alex Williamson,
	Michael Ellerman, Paul Mackerras

This is to improve page boundaries checking and should probably
be cc:stable. I came accross this while debugging nvlink2 passthrough
but the lack of checking might be exploited by the existing userspace.

Changes:
v4:
* 2/2: implemented less strict but still safe max pageshift as David suggested

v3:
* enforced huge pages not to cross preregistered chunk boundaries

v2:
* 2/2: explicitly check for compound pages before calling compound_order()


This is based on sha1
021c917 Linus Torvalds "Linux 4.18-rc3".

Please comment. Thanks.



Alexey Kardashevskiy (2):
  vfio/spapr: Use IOMMU pageshift rather than pagesize
  KVM: PPC: Check if IOMMU page is contained in the pinned physical page

 arch/powerpc/include/asm/mmu_context.h |  4 ++--
 arch/powerpc/kvm/book3s_64_vio.c       |  2 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c    |  6 ++++--
 arch/powerpc/mm/mmu_context_iommu.c    | 23 ++++++++++++++++++++---
 drivers/vfio/vfio_iommu_spapr_tce.c    | 10 +++++-----
 5 files changed, 32 insertions(+), 13 deletions(-)

-- 
2.11.0

^ permalink raw reply

* [PATCH kernel v4 1/2] vfio/spapr: Use IOMMU pageshift rather than pagesize
From: Alexey Kardashevskiy @ 2018-07-05  8:01 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Alexey Kardashevskiy, David Gibson, kvm-ppc, Alex Williamson,
	Michael Ellerman, Paul Mackerras
In-Reply-To: <20180705080133.18690-1-aik@ozlabs.ru>

The size is always equal to 1 page so let's use this. Later on this will
be used for other checks which use page shifts to check the granularity
of access.

This should cause no behavioral change.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---

As Alex suggested, this should go via the ppc tree which the next patch
is going to (which is ppc-kvm).
---
 drivers/vfio/vfio_iommu_spapr_tce.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 759a5bd..2da5f05 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -457,13 +457,13 @@ static void tce_iommu_unuse_page(struct tce_container *container,
 }
 
 static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
-		unsigned long tce, unsigned long size,
+		unsigned long tce, unsigned long shift,
 		unsigned long *phpa, struct mm_iommu_table_group_mem_t **pmem)
 {
 	long ret = 0;
 	struct mm_iommu_table_group_mem_t *mem;
 
-	mem = mm_iommu_lookup(container->mm, tce, size);
+	mem = mm_iommu_lookup(container->mm, tce, 1ULL << shift);
 	if (!mem)
 		return -EINVAL;
 
@@ -487,7 +487,7 @@ static void tce_iommu_unuse_page_v2(struct tce_container *container,
 	if (!pua)
 		return;
 
-	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, IOMMU_PAGE_SIZE(tbl),
+	ret = tce_iommu_prereg_ua_to_hpa(container, *pua, tbl->it_page_shift,
 			&hpa, &mem);
 	if (ret)
 		pr_debug("%s: tce %lx at #%lx was not cached, ret=%d\n",
@@ -611,7 +611,7 @@ static long tce_iommu_build_v2(struct tce_container *container,
 				entry + i);
 
 		ret = tce_iommu_prereg_ua_to_hpa(container,
-				tce, IOMMU_PAGE_SIZE(tbl), &hpa, &mem);
+				tce, tbl->it_page_shift, &hpa, &mem);
 		if (ret)
 			break;
 
-- 
2.11.0

^ permalink raw reply related

* [PATCH kernel v4 2/2] KVM: PPC: Check if IOMMU page is contained in the pinned physical page
From: Alexey Kardashevskiy @ 2018-07-05  8:01 UTC (permalink / raw)
  To: linuxppc-dev
  Cc: Alexey Kardashevskiy, David Gibson, kvm-ppc, Alex Williamson,
	Michael Ellerman, Paul Mackerras
In-Reply-To: <20180705080133.18690-1-aik@ozlabs.ru>

A VM which has:
 - a DMA capable device passed through to it (eg. network card);
 - running a malicious kernel that ignores H_PUT_TCE failure;
 - capability of using IOMMU pages bigger that physical pages
can create an IOMMU mapping that exposes (for example) 16MB of
the host physical memory to the device when only 64K was allocated to
the VM.

The remaining 16MB - 64K will be some other content of host memory,
possibly including pages of the VM, but also pages of host kernel memory,
host programs or other VMs.

The attacking VM does not control the location of the page it can map,
and is only allowed to map as many pages as it has pages of RAM.

We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that
an IOMMU page is contained in the physical page so the PCI hardware won't
get access to unassigned host memory; however this check is missing in
the KVM fastpath (H_PUT_TCE accelerated code). We were lucky so far and
did not hit this yet as the very first time when the mapping happens
we do not have tbl::it_userspace allocated yet and fall back to
the userspace which in turn calls VFIO IOMMU driver, this fails and
the guest does not retry,

This stores the smallest preregistered page size in the preregistered
region descriptor and changes the mm_iommu_xxx API to check this against
the IOMMU page size. This calculates maximum page size as a minimum of
the natural region alignment and compound page size.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v4:
* reimplemented max pageshift calculation

v3:
* fixed upper limit for the page size
* added checks that we don't register parts of a huge page

v2:
* explicitely check for compound pages before calling compound_order()

---
The bug is: run QEMU _without_ hugepages (no -mempath) and tell it to
advertise 16MB pages to the guest; a typical pseries guest will use 16MB
for IOMMU pages without checking the mmu pagesize and this will fail
at https://git.qemu.org/?p=qemu.git;a=blob;f=hw/vfio/common.c;h=fb396cf00ac40eb35967a04c9cc798ca896eed57;hb=refs/heads/master#l256

With the change, mapping will fail in KVM and the guest will print:

mlx5_core 0000:00:00.0: ibm,create-pe-dma-window(2027) 0 8000000 20000000 18 1f returned 0 (liobn = 0x80000001 starting addr = 8000000 0)
mlx5_core 0000:00:00.0: created tce table LIOBN 0x80000001 for /pci@800000020000000/ethernet@0
mlx5_core 0000:00:00.0: failed to map direct window for /pci@800000020000000/ethernet@0: -1
---
 arch/powerpc/include/asm/mmu_context.h |  4 ++--
 arch/powerpc/kvm/book3s_64_vio.c       |  2 +-
 arch/powerpc/kvm/book3s_64_vio_hv.c    |  6 ++++--
 arch/powerpc/mm/mmu_context_iommu.c    | 23 ++++++++++++++++++++---
 drivers/vfio/vfio_iommu_spapr_tce.c    |  2 +-
 5 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 896efa5..79d570c 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -35,9 +35,9 @@ extern struct mm_iommu_table_group_mem_t *mm_iommu_lookup_rm(
 extern struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 		unsigned long ua, unsigned long entries);
 extern long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa);
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa);
 extern long mm_iommu_mapped_inc(struct mm_iommu_table_group_mem_t *mem);
 extern void mm_iommu_mapped_dec(struct mm_iommu_table_group_mem_t *mem);
 #endif
diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c
index d066e37..8c456fa 100644
--- a/arch/powerpc/kvm/book3s_64_vio.c
+++ b/arch/powerpc/kvm/book3s_64_vio.c
@@ -449,7 +449,7 @@ long kvmppc_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 		/* This only handles v2 IOMMU type, v1 is handled via ioctl() */
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, &hpa)))
+	if (WARN_ON_ONCE(mm_iommu_ua_to_hpa(mem, ua, tbl->it_page_shift, &hpa)))
 		return H_HARDWARE;
 
 	if (mm_iommu_mapped_inc(mem))
diff --git a/arch/powerpc/kvm/book3s_64_vio_hv.c b/arch/powerpc/kvm/book3s_64_vio_hv.c
index 925fc31..5b298f5 100644
--- a/arch/powerpc/kvm/book3s_64_vio_hv.c
+++ b/arch/powerpc/kvm/book3s_64_vio_hv.c
@@ -279,7 +279,8 @@ static long kvmppc_rm_tce_iommu_do_map(struct kvm *kvm, struct iommu_table *tbl,
 	if (!mem)
 		return H_TOO_HARD;
 
-	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, &hpa)))
+	if (WARN_ON_ONCE_RM(mm_iommu_ua_to_hpa_rm(mem, ua, tbl->it_page_shift,
+			&hpa)))
 		return H_HARDWARE;
 
 	pua = (void *) vmalloc_to_phys(pua);
@@ -469,7 +470,8 @@ long kvmppc_rm_h_put_tce_indirect(struct kvm_vcpu *vcpu,
 
 		mem = mm_iommu_lookup_rm(vcpu->kvm->mm, ua, IOMMU_PAGE_SIZE_4K);
 		if (mem)
-			prereg = mm_iommu_ua_to_hpa_rm(mem, ua, &tces) == 0;
+			prereg = mm_iommu_ua_to_hpa_rm(mem, ua,
+					IOMMU_PAGE_SHIFT_4K, &tces) == 0;
 	}
 
 	if (!prereg) {
diff --git a/arch/powerpc/mm/mmu_context_iommu.c b/arch/powerpc/mm/mmu_context_iommu.c
index abb4364..11e1029 100644
--- a/arch/powerpc/mm/mmu_context_iommu.c
+++ b/arch/powerpc/mm/mmu_context_iommu.c
@@ -27,6 +27,7 @@ struct mm_iommu_table_group_mem_t {
 	struct rcu_head rcu;
 	unsigned long used;
 	atomic64_t mapped;
+	unsigned int pageshift;
 	u64 ua;			/* userspace address */
 	u64 entries;		/* number of entries in hpas[] */
 	u64 *hpas;		/* vmalloc'ed */
@@ -125,7 +126,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 {
 	struct mm_iommu_table_group_mem_t *mem;
 	long i, j, ret = 0, locked_entries = 0;
-	struct page *page = NULL;
+	unsigned int pageshift;
+	struct page *page = NULL, *head = NULL;
 
 	mutex_lock(&mem_list_mutex);
 
@@ -159,6 +161,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 		goto unlock_exit;
 	}
 
+	mem->pageshift = __builtin_ctzl(ua | (entries << PAGE_SHIFT));
 	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
 	if (!mem->hpas) {
 		kfree(mem);
@@ -199,9 +202,17 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
 			}
 		}
 populate:
+		pageshift = PAGE_SHIFT;
+		if (PageCompound(page))
+			pageshift += compound_order(compound_head(page));
+		mem->pageshift = min(mem->pageshift, pageshift);
 		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
 	}
 
+	/* We have an incomplete huge page, default to PAGE_SHIFT */
+	if (head)
+		mem->pageshift = PAGE_SHIFT;
+
 	atomic64_set(&mem->mapped, 1);
 	mem->used = 1;
 	mem->ua = ua;
@@ -349,7 +360,7 @@ struct mm_iommu_table_group_mem_t *mm_iommu_find(struct mm_struct *mm,
 EXPORT_SYMBOL_GPL(mm_iommu_find);
 
 long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	u64 *va = &mem->hpas[entry];
@@ -357,6 +368,9 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	*hpa = *va | (ua & ~PAGE_MASK);
 
 	return 0;
@@ -364,7 +378,7 @@ long mm_iommu_ua_to_hpa(struct mm_iommu_table_group_mem_t *mem,
 EXPORT_SYMBOL_GPL(mm_iommu_ua_to_hpa);
 
 long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
-		unsigned long ua, unsigned long *hpa)
+		unsigned long ua, unsigned int pageshift, unsigned long *hpa)
 {
 	const long entry = (ua - mem->ua) >> PAGE_SHIFT;
 	void *va = &mem->hpas[entry];
@@ -373,6 +387,9 @@ long mm_iommu_ua_to_hpa_rm(struct mm_iommu_table_group_mem_t *mem,
 	if (entry >= mem->entries)
 		return -EFAULT;
 
+	if (pageshift > mem->pageshift)
+		return -EFAULT;
+
 	pa = (void *) vmalloc_to_phys(va);
 	if (!pa)
 		return -EFAULT;
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 2da5f05..7cd63b0 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -467,7 +467,7 @@ static int tce_iommu_prereg_ua_to_hpa(struct tce_container *container,
 	if (!mem)
 		return -EINVAL;
 
-	ret = mm_iommu_ua_to_hpa(mem, tce, phpa);
+	ret = mm_iommu_ua_to_hpa(mem, tce, shift, phpa);
 	if (ret)
 		return -EINVAL;
 
-- 
2.11.0

^ permalink raw reply related

* Re: [PATCH kernel v3 2/2] KVM: PPC: Check if IOMMU page is contained in the pinned physical page
From: Alexey Kardashevskiy @ 2018-07-05  8:04 UTC (permalink / raw)
  To: David Gibson
  Cc: linuxppc-dev, kvm-ppc, Alex Williamson, Michael Ellerman,
	Paul Mackerras
In-Reply-To: <20180705151904.17de7322@aik.ozlabs.ibm.com>

[-- Attachment #1: Type: text/plain, Size: 5122 bytes --]

On Thu, 5 Jul 2018 15:19:04 +1000
Alexey Kardashevskiy <aik@ozlabs.ru> wrote:

> On Thu, 5 Jul 2018 12:42:20 +1000
> David Gibson <david@gibson.dropbear.id.au> wrote:
> 
> > On Wed, Jul 04, 2018 at 03:00:52PM +1000, Alexey Kardashevskiy wrote:  
> > > A VM which has:
> > >  - a DMA capable device passed through to it (eg. network card);
> > >  - running a malicious kernel that ignores H_PUT_TCE failure;
> > >  - capability of using IOMMU pages bigger that physical pages
> > > can create an IOMMU mapping that exposes (for example) 16MB of
> > > the host physical memory to the device when only 64K was allocated to the VM.
> > > 
> > > The remaining 16MB - 64K will be some other content of host memory, possibly
> > > including pages of the VM, but also pages of host kernel memory, host
> > > programs or other VMs.
> > > 
> > > The attacking VM does not control the location of the page it can map,
> > > and is only allowed to map as many pages as it has pages of RAM.
> > > 
> > > We already have a check in drivers/vfio/vfio_iommu_spapr_tce.c that
> > > an IOMMU page is contained in the physical page so the PCI hardware won't
> > > get access to unassigned host memory; however this check is missing in
> > > the KVM fastpath (H_PUT_TCE accelerated code). We were lucky so far and
> > > did not hit this yet as the very first time when the mapping happens
> > > we do not have tbl::it_userspace allocated yet and fall back to
> > > the userspace which in turn calls VFIO IOMMU driver, this fails and
> > > the guest does not retry,
> > > 
> > > This stores the smallest preregistered page size in the preregistered
> > > region descriptor and changes the mm_iommu_xxx API to check this against
> > > the IOMMU page size. This only allows huge pages use if the entire
> > > preregistered block is backed with huge pages which are completely
> > > contained the preregistered chunk; otherwise this defaults to PAGE_SIZE.
> > > 
> > > Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>    
> > 
> > Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
> > 
> > On the grounds that I think this version is safe, which the old one
> > wasn't.  However it still has some flaws..
> > 
> > [snip]  
> > > @@ -125,7 +126,8 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> > >  {
> > >  	struct mm_iommu_table_group_mem_t *mem;
> > >  	long i, j, ret = 0, locked_entries = 0;
> > > -	struct page *page = NULL;
> > > +	unsigned int pageshift;
> > > +	struct page *page = NULL, *head = NULL;
> > >  
> > >  	mutex_lock(&mem_list_mutex);
> > >  
> > > @@ -159,6 +161,7 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> > >  		goto unlock_exit;
> > >  	}
> > >  
> > > +	mem->pageshift = 64;
> > >  	mem->hpas = vzalloc(array_size(entries, sizeof(mem->hpas[0])));
> > >  	if (!mem->hpas) {
> > >  		kfree(mem);
> > > @@ -199,9 +202,35 @@ long mm_iommu_get(struct mm_struct *mm, unsigned long ua, unsigned long entries,
> > >  			}
> > >  		}
> > >  populate:
> > > +		pageshift = PAGE_SHIFT;
> > > +		if (PageCompound(page)) {
> > > +			/* Make sure huge page is contained completely */
> > > +			struct page *tmphead = compound_head(page);
> > > +			unsigned int n = compound_order(tmphead);
> > > +
> > > +			if (!head) {
> > > +				/* Is it a head of a huge page? */
> > > +				if (page == tmphead) {
> > > +					head = tmphead;
> > > +					pageshift += n;
> > > +				}
> > > +			} else if (head == tmphead) {
> > > +				/* Still same huge page, good */
> > > +				pageshift += n;
> > > +
> > > +				/* End of the huge page */
> > > +				if (page - head == (1UL << n) - 1)
> > > +					head = NULL;
> > > +			}
> > > +		}
> > > +		mem->pageshift = min(mem->pageshift, pageshift);
> > >  		mem->hpas[i] = page_to_pfn(page) << PAGE_SHIFT;
> > >  	}
> > >  
> > > +	/* We have an incomplete huge page, default to PAGE_SHIFT */
> > > +	if (head)
> > > +		mem->pageshift = PAGE_SHIFT;
> > > +    
> > 
> > So, if the user attempts to prereg a region which starts or ends in
> > the middle of a hugepage, this logic will clamp the region's max page
> > shift down to PAGE_SHIFT.  That's safe, but not optimal.
> > 
> > Suppose userspace had an area backed with 16MiB hugepages, and wanted
> > to pre-reg a window that was 2MiB aligned, but not 16MiB aligned.  It
> > would still be safe to allow 2MiB TCEs, but the code above would clamp
> > it down to 64kiB (or 4kiB).
> > 
> > The code to do it is also pretty convoluted.
> > 
> > I think you'd be better off initializing mem->pageshift to the largest
> > possible natural alignment of the region:
> > 	mem->pageshift = ctz64(ua | (entries << PAGE_SHIFT));
> > 
> > Then it should just be sufficient to clamp pageshift down to
> > compound_order() + PAGE_SHIFT for each entry.  
> 
> 
> I like this better, just one question - does hugetlbfs guarantee the @ua
> alignment if backed with an actual huge page?


Turns out it does, never mind, posted v4. Cheers.



--
Alexey

[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 833 bytes --]

^ permalink raw reply

* [PATCH v7 1/4] selftests/powerpc: add test for 32 bits memcmp
From: Christophe Leroy @ 2018-07-05  8:28 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	wei.guo.simon, segher
  Cc: linux-kernel, linuxppc-dev

This patch renames memcmp test to memcmp_64 and adds
a memcmp_32 test for testing the 32 bits version of memcmp()

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 v7: no change
 v6: no change
 v5: no change
 v4: new

 tools/testing/selftests/powerpc/stringloops/Makefile    | 14 +++++++++++---
 tools/testing/selftests/powerpc/stringloops/memcmp_32.S |  1 +
 2 files changed, 12 insertions(+), 3 deletions(-)
 create mode 120000 tools/testing/selftests/powerpc/stringloops/memcmp_32.S

diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 1125e489055e..1e7301d4bac9 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -1,10 +1,18 @@
 # SPDX-License-Identifier: GPL-2.0
 # The loops are all 64-bit code
-CFLAGS += -m64
 CFLAGS += -I$(CURDIR)
 
-TEST_GEN_PROGS := memcmp
-EXTRA_SOURCES := memcmp_64.S ../harness.c
+EXTRA_SOURCES := ../harness.c
+
+$(OUTPUT)/memcmp_64: memcmp.c
+$(OUTPUT)/memcmp_64: CFLAGS += -m64
+
+$(OUTPUT)/memcmp_32: memcmp.c
+$(OUTPUT)/memcmp_32: CFLAGS += -m32
+
+ASFLAGS = $(CFLAGS)
+
+TEST_GEN_PROGS := memcmp_32 memcmp_64
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/stringloops/memcmp_32.S b/tools/testing/selftests/powerpc/stringloops/memcmp_32.S
new file mode 120000
index 000000000000..056f2b3af789
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/memcmp_32.S
@@ -0,0 +1 @@
+../../../../../arch/powerpc/lib/memcmp_32.S
\ No newline at end of file
-- 
2.13.3

^ permalink raw reply related

* [PATCH v7 2/4] selftests/powerpc: Add test for strlen()
From: Christophe Leroy @ 2018-07-05  8:29 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	wei.guo.simon, segher
  Cc: linux-kernel, linuxppc-dev
In-Reply-To: <9f98f2bd0e9948b8042773f6190c0416d2577b5e.1530777873.git.christophe.leroy@c-s.fr>

This patch adds a test for strlen()

string.c contains a copy of strlen() from lib/string.c

The test first tests the correctness of strlen() by comparing
the result with libc strlen(). It tests all cases of alignment.

It them tests the duration of an aligned strlen() on a 4 bytes string,
on a 16 bytes string and on a 256 bytes string.

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 v7: no change
 v6: refactorised the benchmark test
 v5: no change
 v4: new

 .../testing/selftests/powerpc/stringloops/Makefile |   5 +-
 .../testing/selftests/powerpc/stringloops/string.c |  36 ++++++
 .../testing/selftests/powerpc/stringloops/strlen.c | 127 +++++++++++++++++++++
 3 files changed, 167 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/powerpc/stringloops/string.c
 create mode 100644 tools/testing/selftests/powerpc/stringloops/strlen.c

diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index 1e7301d4bac9..df663ee9ddb3 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -10,9 +10,12 @@ $(OUTPUT)/memcmp_64: CFLAGS += -m64
 $(OUTPUT)/memcmp_32: memcmp.c
 $(OUTPUT)/memcmp_32: CFLAGS += -m32
 
+$(OUTPUT)/strlen: strlen.c string.o
+$(OUTPUT)/string.o: string.c
+
 ASFLAGS = $(CFLAGS)
 
-TEST_GEN_PROGS := memcmp_32 memcmp_64
+TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/stringloops/string.c b/tools/testing/selftests/powerpc/stringloops/string.c
new file mode 100644
index 000000000000..d05200481017
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/string.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/lib/string.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * stupid library routines.. The optimized versions should generally be found
+ * as inline code in <asm-xx/string.h>
+ *
+ * These are buggy as well..
+ *
+ * * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de>
+ * -  Added strsep() which will replace strtok() soon (because strsep() is
+ *    reentrant and should be faster). Use only strsep() in new code, please.
+ *
+ * * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>,
+ *                    Matthew Hawkins <matt@mh.dropbear.id.au>
+ * -  Kissed strtok() goodbye
+ */
+
+#include <stddef.h>
+
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t test_strlen(const char *s)
+{
+	const char *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
diff --git a/tools/testing/selftests/powerpc/stringloops/strlen.c b/tools/testing/selftests/powerpc/stringloops/strlen.c
new file mode 100644
index 000000000000..9055ebc484d0
--- /dev/null
+++ b/tools/testing/selftests/powerpc/stringloops/strlen.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <malloc.h>
+#include <stdlib.h>
+#include <string.h>
+#include <time.h>
+#include "utils.h"
+
+#define SIZE 256
+#define ITERATIONS 1000
+#define ITERATIONS_BENCH 100000
+
+int test_strlen(const void *s);
+
+/* test all offsets and lengths */
+static void test_one(char *s)
+{
+	unsigned long offset;
+
+	for (offset = 0; offset < SIZE; offset++) {
+		int x, y;
+		unsigned long i;
+
+		y = strlen(s + offset);
+		x = test_strlen(s + offset);
+
+		if (x != y) {
+			printf("strlen() returned %d, should have returned %d (%p offset %ld)\n", x, y, s, offset);
+
+			for (i = offset; i < SIZE; i++)
+				printf("%02x ", s[i]);
+			printf("\n");
+		}
+	}
+}
+
+static void bench_test(char *s)
+{
+	struct timespec ts_start, ts_end;
+	int i;
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_start);
+
+	for (i = 0; i < ITERATIONS_BENCH; i++)
+		test_strlen(s);
+
+	clock_gettime(CLOCK_MONOTONIC, &ts_end);
+
+	printf("len %3.3d : time = %.6f\n", test_strlen(s), ts_end.tv_sec - ts_start.tv_sec + (ts_end.tv_nsec - ts_start.tv_nsec) / 1e9);
+}
+
+static int testcase(void)
+{
+	char *s;
+	unsigned long i;
+
+	s = memalign(128, SIZE);
+	if (!s) {
+		perror("memalign");
+		exit(1);
+	}
+
+	srandom(1);
+
+	memset(s, 0, SIZE);
+	for (i = 0; i < SIZE; i++) {
+		char c;
+
+		do {
+			c = random() & 0x7f;
+		} while (!c);
+		s[i] = c;
+		test_one(s);
+	}
+
+	for (i = 0; i < ITERATIONS; i++) {
+		unsigned long j;
+
+		for (j = 0; j < SIZE; j++) {
+			char c;
+
+			do {
+				c = random() & 0x7f;
+			} while (!c);
+			s[j] = c;
+		}
+		for (j = 0; j < sizeof(long); j++) {
+			s[SIZE - 1 - j] = 0;
+			test_one(s);
+		}
+	}
+
+	for (i = 0; i < SIZE; i++) {
+		char c;
+
+		do {
+			c = random() & 0x7f;
+		} while (!c);
+		s[i] = c;
+	}
+
+	bench_test(s);
+
+	s[16] = 0;
+	bench_test(s);
+
+	s[8] = 0;
+	bench_test(s);
+
+	s[4] = 0;
+	bench_test(s);
+
+	s[3] = 0;
+	bench_test(s);
+
+	s[2] = 0;
+	bench_test(s);
+
+	s[1] = 0;
+	bench_test(s);
+
+	return 0;
+}
+
+int main(void)
+{
+	return test_harness(testcase, "strlen");
+}
-- 
2.13.3

^ permalink raw reply related

* [PATCH v7 3/4] powerpc/lib: implement strlen() in assembly for PPC32
From: Christophe Leroy @ 2018-07-05  8:29 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	wei.guo.simon, segher
  Cc: linux-kernel, linuxppc-dev
In-Reply-To: <9f98f2bd0e9948b8042773f6190c0416d2577b5e.1530777873.git.christophe.leroy@c-s.fr>

The generic implementation of strlen() reads strings byte per byte.

This patch implements strlen() in assembly based on a read of entire
words, in the same spirit as what some other arches and glibc do.

On a 8xx the time spent in strlen is reduced by 3/4 for long strings.

strlen() selftest on an 8xx provides the following values:

Before the patch (ie with the generic strlen() in lib/string.c):

len 256 : time = 1.195055
len 016 : time = 0.083745
len 008 : time = 0.046828
len 004 : time = 0.028390

After the patch:

len 256 : time = 0.272185 ==> 78% improvment
len 016 : time = 0.040632 ==> 51% improvment
len 008 : time = 0.033060 ==> 29% improvment
len 004 : time = 0.029149 ==> 2% degradation

On a 832x:

Before the patch:

len 256 : time = 0.236125
len 016 : time = 0.018136
len 008 : time = 0.011000
len 004 : time = 0.007229

After the patch:

len 256 : time = 0.094950 ==> 60% improvment
len 016 : time = 0.013357 ==> 26% improvment
len 008 : time = 0.010586 ==> 4% improvment
len 004 : time = 0.008784

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
Changes in v7:
 - Reduced the scope to PPC32
 - Modified the missalignment handling to be branchless and loopless

Changes in v6:
 - Reworked for having branchless conclusion

Changes in v5:
 - Fixed for PPC64 LITTLE ENDIAN

Changes in v4:
 - Added alignment of the loop
 - doing the andc only if still not 0 as it happends only for bytes above 0x7f which is pretty rare in a string

Changes in v3:
 - Made it common to PPC32 and PPC64

Changes in v2:
 - Moved handling of unaligned strings outside of the main path as it is very unlikely.
 - Removed the verification of the fourth byte in case none of the three first ones are NUL.

 arch/powerpc/include/asm/string.h |  2 +
 arch/powerpc/lib/Makefile         |  2 +-
 arch/powerpc/lib/strlen_32.S      | 78 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 81 insertions(+), 1 deletion(-)
 create mode 100644 arch/powerpc/lib/strlen_32.S

diff --git a/arch/powerpc/include/asm/string.h b/arch/powerpc/include/asm/string.h
index 9b8cedf618f4..1647de15a31e 100644
--- a/arch/powerpc/include/asm/string.h
+++ b/arch/powerpc/include/asm/string.h
@@ -50,6 +50,8 @@ static inline void *memset64(uint64_t *p, uint64_t v, __kernel_size_t n)
 	return __memset64(p, v, n * 8);
 }
 #else
+#define __HAVE_ARCH_STRLEN
+
 extern void *memset16(uint16_t *, uint16_t, __kernel_size_t);
 #endif
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index d0ca13ad8231..670286808928 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -12,7 +12,7 @@ CFLAGS_REMOVE_feature-fixups.o = $(CC_FLAGS_FTRACE)
 
 obj-y += string.o alloc.o code-patching.o feature-fixups.o
 
-obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o
+obj-$(CONFIG_PPC32)	+= div64.o copy_32.o crtsavres.o strlen_32.o
 
 # See corresponding test in arch/powerpc/Makefile
 # 64-bit linker creates .sfpr on demand for final link (vmlinux),
diff --git a/arch/powerpc/lib/strlen_32.S b/arch/powerpc/lib/strlen_32.S
new file mode 100644
index 000000000000..0a8d3f64d493
--- /dev/null
+++ b/arch/powerpc/lib/strlen_32.S
@@ -0,0 +1,78 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * strlen() for PPC32
+ *
+ * Copyright (C) 2018 Christophe Leroy CS Systemes d'Information.
+ *
+ * Inspired from glibc implementation
+ */
+#include <asm/ppc_asm.h>
+#include <asm/export.h>
+#include <asm/cache.h>
+
+	.text
+
+/*
+ * Algorithm:
+ *
+ * 1) Given a word 'x', we can test to see if it contains any 0 bytes
+ *    by subtracting 0x01010101, and seeing if any of the high bits of each
+ *    byte changed from 0 to 1. This works because the least significant
+ *    0 byte must have had no incoming carry (otherwise it's not the least
+ *    significant), so it is 0x00 - 0x01 == 0xff. For all other
+ *    byte values, either they have the high bit set initially, or when
+ *    1 is subtracted you get a value in the range 0x00-0x7f, none of which
+ *    have their high bit set. The expression here is
+ *    (x - 0x01010101) & ~x & 0x80808080), which gives 0x00000000 when
+ *    there were no 0x00 bytes in the word.  You get 0x80 in bytes that
+ *    match, but possibly false 0x80 matches in the next more significant
+ *    byte to a true match due to carries.  For little-endian this is
+ *    of no consequence since the least significant match is the one
+ *    we're interested in, but big-endian needs method 2 to find which
+ *    byte matches.
+ * 2) Given a word 'x', we can test to see _which_ byte was zero by
+ *    calculating ~(((x & ~0x80808080) - 0x80808080 - 1) | x | ~0x80808080).
+ *    This produces 0x80 in each byte that was zero, and 0x00 in all
+ *    the other bytes. The '| ~0x80808080' clears the low 7 bits in each
+ *    byte, and the '| x' part ensures that bytes with the high bit set
+ *    produce 0x00. The addition will carry into the high bit of each byte
+ *    iff that byte had one of its low 7 bits set. We can then just see
+ *    which was the most significant bit set and divide by 8 to find how
+ *    many to add to the index.
+ *    This is from the book 'The PowerPC Compiler Writer's Guide',
+ *    by Steve Hoxey, Faraydon Karim, Bill Hay and Hank Warren.
+ */
+
+_GLOBAL(strlen)
+	andi.   r0, r3, 3
+	lis	r7, 0x0101
+	addi	r10, r3, -4
+	addic	r7, r7, 0x0101	/* r7 = 0x01010101 (lomagic) & clear XER[CA] */
+	rotlwi	r6, r7, 31 	/* r6 = 0x80808080 (himagic) */
+	bne-	3f
+	.balign IFETCH_ALIGN_BYTES
+1:	lwzu	r9, 4(r10)
+2:	subf	r8, r7, r9
+	and.	r8, r8, r6
+	beq+	1b
+	andc.	r8, r8, r9
+	beq+	1b
+	andc	r8, r9, r6
+	orc	r9, r9, r6
+	subfe	r8, r6, r8
+	nor	r8, r8, r9
+	cntlzw	r8, r8
+	subf	r3, r3, r10
+	srwi	r8, r8, 3
+	add	r3, r3, r8
+	blr
+
+	/* Missaligned string: make sure bytes before string are seen not 0 */
+3:	xor	r10, r10, r0
+	orc	r8, r8, r8
+	lwzu	r9, 4(r10)
+	slwi	r0, r0, 3
+	srw	r8, r8, r0
+	orc	r9, r9, r8
+	b	2b
+EXPORT_SYMBOL(strlen)
-- 
2.13.3

^ permalink raw reply related

* [PATCH v7 4/4] selftests/powerpc: update strlen() test to test the new assembly function for PPC32
From: Christophe Leroy @ 2018-07-05  8:29 UTC (permalink / raw)
  To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
	wei.guo.simon, segher
  Cc: linux-kernel, linuxppc-dev
In-Reply-To: <9f98f2bd0e9948b8042773f6190c0416d2577b5e.1530777873.git.christophe.leroy@c-s.fr>

This patch adds a test for testing the new assembly strlen() for PPC32

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
 v7: reduced the scope to PPC32
 v6: added additional necessary defines in ppc_asm.h
 v5: no change
 v4: new

 tools/testing/selftests/powerpc/stringloops/Makefile      |  5 ++++-
 tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h | 10 ++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/powerpc/stringloops/Makefile b/tools/testing/selftests/powerpc/stringloops/Makefile
index df663ee9ddb3..2f0bd203e18a 100644
--- a/tools/testing/selftests/powerpc/stringloops/Makefile
+++ b/tools/testing/selftests/powerpc/stringloops/Makefile
@@ -13,9 +13,12 @@ $(OUTPUT)/memcmp_32: CFLAGS += -m32
 $(OUTPUT)/strlen: strlen.c string.o
 $(OUTPUT)/string.o: string.c
 
+$(OUTPUT)/strlen_32: strlen.c
+$(OUTPUT)/strlen_32: CFLAGS += -m32
+
 ASFLAGS = $(CFLAGS)
 
-TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen
+TEST_GEN_PROGS := memcmp_32 memcmp_64 strlen strlen_32
 
 include ../../lib.mk
 
diff --git a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
index 136242ec4b0e..161a7ee54005 100644
--- a/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
+++ b/tools/testing/selftests/powerpc/stringloops/asm/ppc_asm.h
@@ -1,4 +1,5 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+
 #include <ppc-asm.h>
 
 #ifndef r1
@@ -6,3 +7,12 @@
 #endif
 
 #define _GLOBAL(A) FUNC_START(test_ ## A)
+
+#ifndef __powerpc64__
+#define SZL		4
+#define PPC_LLU		lwzu
+#define PPC_LCMPI	cmplwi
+#define PPC_ROTLI	rotlwi
+#define PPC_CNTLZL	cntlzw
+#define PPC_SRLI	srwi
+#endif
-- 
2.13.3

^ permalink raw reply related

* Re: [PATCH v3 02/11] hugetlb: Introduce generic version of hugetlb_free_pgd_range
From: kbuild test robot @ 2018-07-05  8:29 UTC (permalink / raw)
  To: Alexandre Ghiti
  Cc: kbuild-all, linux, catalin.marinas, will.deacon, tony.luck,
	fenghua.yu, ralf, paul.burton, jhogan, jejb, deller, benh, paulus,
	mpe, ysato, dalias, davem, tglx, mingo, hpa, x86, arnd,
	linux-arm-kernel, linux-kernel, linux-ia64, linux-mips,
	linux-parisc, linuxppc-dev, linux-sh, sparclinux, linux-arch,
	Alexandre Ghiti
In-Reply-To: <20180705051640.790-3-alex@ghiti.fr>

[-- Attachment #1: Type: text/plain, Size: 3890 bytes --]

Hi Alexandre,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v4.18-rc3 next-20180704]
[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/Alexandre-Ghiti/hugetlb-Factorize-hugetlb-architecture-primitives/20180705-135909
config: powerpc-mpc8540_ads_defconfig (attached as .config)
compiler: powerpc-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        GCC_VERSION=7.2.0 make.cross ARCH=powerpc 

All error/warnings (new ones prefixed by >>):

   In file included from arch/powerpc/kernel/setup-common.c:37:0:
>> include/linux/hugetlb.h:191:65: error: expected identifier or '(' before '{' token
    #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
                                                                    ^
>> include/asm-generic/hugetlb.h:44:20: note: in expansion of macro 'hugetlb_free_pgd_range'
    static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
                       ^~~~~~~~~~~~~~~~~~~~~~

vim +191 include/linux/hugetlb.h

^1da177e Linus Torvalds    2005-04-16  172  
87ffc118 Andrea Arcangeli  2017-02-22  173  #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n)	({ BUG(); 0; })
^1da177e Linus Torvalds    2005-04-16  174  #define follow_huge_addr(mm, addr, write)	ERR_PTR(-EINVAL)
^1da177e Linus Torvalds    2005-04-16  175  #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
e1759c21 Alexey Dobriyan   2008-10-15  176  static inline void hugetlb_report_meminfo(struct seq_file *m)
e1759c21 Alexey Dobriyan   2008-10-15  177  {
e1759c21 Alexey Dobriyan   2008-10-15  178  }
^1da177e Linus Torvalds    2005-04-16  179  #define hugetlb_report_node_meminfo(n, buf)	0
949f7ec5 David Rientjes    2013-04-29  180  static inline void hugetlb_show_meminfo(void)
949f7ec5 David Rientjes    2013-04-29  181  {
949f7ec5 David Rientjes    2013-04-29  182  }
4dc71451 Aneesh Kumar K.V  2017-07-06  183  #define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL
e66f17ff Naoya Horiguchi   2015-02-11  184  #define follow_huge_pmd(mm, addr, pmd, flags)	NULL
e66f17ff Naoya Horiguchi   2015-02-11  185  #define follow_huge_pud(mm, addr, pud, flags)	NULL
faaa5b62 Anshuman Khandual 2017-07-06  186  #define follow_huge_pgd(mm, addr, pgd, flags)	NULL
a5516438 Andi Kleen        2008-07-23  187  #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
^1da177e Linus Torvalds    2005-04-16  188  #define pmd_huge(x)	0
ceb86879 Andi Kleen        2008-07-23  189  #define pud_huge(x)	0
^1da177e Linus Torvalds    2005-04-16  190  #define is_hugepage_only_range(mm, addr, len)	0
9da61aef David Gibson      2006-03-22 @191  #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
788c7df4 Hugh Dickins      2009-06-23  192  #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
8fb5debc Mike Kravetz      2017-02-22  193  #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
8fb5debc Mike Kravetz      2017-02-22  194  				src_addr, pagep)	({ BUG(); 0; })
7868a208 Punit Agrawal     2017-07-06  195  #define huge_pte_offset(mm, address, sz)	0
24669e58 Aneesh Kumar K.V  2012-07-31  196  

:::::: The code at line 191 was first introduced by commit
:::::: 9da61aef0fd5b17dd4bf4baf33db12c470def774 [PATCH] hugepage: Fix hugepage logic in free_pgtables()

:::::: TO: David Gibson <david@gibson.dropbear.id.au>
:::::: CC: Linus Torvalds <torvalds@g5.osdl.org>

---
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: 10925 bytes --]

^ permalink raw reply

* [PATCH] powerpc/64s: remove POWER9 DD1 support
From: Nicholas Piggin @ 2018-07-05  8:47 UTC (permalink / raw)
  To: linuxppc-dev; +Cc: Nicholas Piggin, Benjamin Herrenschmidt

POWER9 DD1 was never a product. It is no longer supported by upstream
firmware, and it is not effectively supported in Linux due to lack of
testing.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
Since RFC:
- Change xive comments to explain why the DD1 cases are being
  kept, from Ben. 

 arch/powerpc/include/asm/book3s/64/hugetlb.h  | 15 +----
 arch/powerpc/include/asm/book3s/64/pgtable.h  |  5 +-
 arch/powerpc/include/asm/book3s/64/radix.h    | 35 ++---------
 .../include/asm/book3s/64/tlbflush-radix.h    |  2 -
 arch/powerpc/include/asm/cputable.h           | 13 ++--
 arch/powerpc/include/asm/paca.h               |  5 --
 arch/powerpc/kernel/asm-offsets.c             |  1 -
 arch/powerpc/kernel/cputable.c                | 19 ------
 arch/powerpc/kernel/dt_cpu_ftrs.c             |  4 +-
 arch/powerpc/kernel/exceptions-64s.S          |  4 +-
 arch/powerpc/kernel/idle_book3s.S             | 50 ----------------
 arch/powerpc/kernel/process.c                 | 10 +---
 arch/powerpc/kvm/book3s_64_mmu_radix.c        | 15 +----
 arch/powerpc/kvm/book3s_hv.c                  | 10 ----
 arch/powerpc/kvm/book3s_hv_rmhandlers.S       | 16 +----
 arch/powerpc/kvm/book3s_xive_template.c       | 39 ++++--------
 arch/powerpc/mm/hash_utils_64.c               | 30 ----------
 arch/powerpc/mm/hugetlbpage.c                 |  9 +--
 arch/powerpc/mm/mmu_context_book3s64.c        | 12 +---
 arch/powerpc/mm/pgtable-radix.c               | 60 +------------------
 arch/powerpc/mm/tlb-radix.c                   | 18 ------
 arch/powerpc/perf/core-book3s.c               | 34 -----------
 arch/powerpc/perf/isa207-common.c             | 12 ++--
 arch/powerpc/perf/isa207-common.h             |  5 --
 arch/powerpc/perf/power9-pmu.c                | 54 +----------------
 arch/powerpc/platforms/powernv/idle.c         | 28 ---------
 arch/powerpc/platforms/powernv/smp.c          | 27 +--------
 arch/powerpc/sysdev/xive/common.c             |  8 +--
 arch/powerpc/xmon/xmon.c                      |  1 -
 drivers/misc/cxl/cxl.h                        |  8 ---
 drivers/misc/cxl/cxllib.c                     |  4 --
 drivers/misc/cxl/pci.c                        | 41 +++++--------
 32 files changed, 67 insertions(+), 527 deletions(-)

diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index c459f937d484..8000aa4990d2 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -36,20 +36,7 @@ static inline int hstate_get_psize(struct hstate *hstate)
 static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 				       struct page *page, int writable)
 {
-	unsigned long page_shift;
-
-	if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return entry;
-
-	page_shift = huge_page_shift(hstate_vma(vma));
-	/*
-	 * We don't support 1G hugetlb pages yet.
-	 */
-	VM_WARN_ON(page_shift == mmu_psize_defs[MMU_PAGE_1G].shift);
-	if (page_shift == mmu_psize_defs[MMU_PAGE_2M].shift)
-		return __pte(pte_val(entry) | R_PAGE_LARGE);
-	else
-		return entry;
+	return entry;
 }
 
 #ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 42aafba7a308..676118743a06 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -479,9 +479,8 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
 {
 	if (full && radix_enabled()) {
 		/*
-		 * Let's skip the DD1 style pte update here. We know that
-		 * this is a full mm pte clear and hence can be sure there is
-		 * no parallel set_pte.
+		 * We know that this is a full mm pte clear and
+		 * hence can be sure there is no parallel set_pte.
 		 */
 		return radix__ptep_get_and_clear_full(mm, addr, ptep, full);
 	}
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index ef9f96742ce1..3ab3f7aef022 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -12,12 +12,6 @@
 #include <asm/book3s/64/radix-4k.h>
 #endif
 
-/*
- * For P9 DD1 only, we need to track whether the pte's huge.
- */
-#define R_PAGE_LARGE	_RPAGE_RSV1
-
-
 #ifndef __ASSEMBLY__
 #include <asm/book3s/64/tlbflush-radix.h>
 #include <asm/cpu_has_feature.h>
@@ -154,20 +148,7 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
 {
 	unsigned long old_pte;
 
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-
-		unsigned long new_pte;
-
-		old_pte = __radix_pte_update(ptep, ~0ul, 0);
-		/*
-		 * new value of pte
-		 */
-		new_pte = (old_pte | set) & ~clr;
-		radix__flush_tlb_pte_p9_dd1(old_pte, mm, addr);
-		if (new_pte)
-			__radix_pte_update(ptep, 0, new_pte);
-	} else
-		old_pte = __radix_pte_update(ptep, clr, set);
+	old_pte = __radix_pte_update(ptep, clr, set);
 	if (!huge)
 		assert_pte_locked(mm, addr);
 
@@ -253,8 +234,6 @@ static inline int radix__pmd_trans_huge(pmd_t pmd)
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 {
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return __pmd(pmd_val(pmd) | _PAGE_PTE | R_PAGE_LARGE);
 	return __pmd(pmd_val(pmd) | _PAGE_PTE);
 }
 
@@ -285,18 +264,14 @@ static inline unsigned long radix__get_tree_size(void)
 	unsigned long rts_field;
 	/*
 	 * We support 52 bits, hence:
-	 *  DD1    52-28 = 24, 0b11000
-	 *  Others 52-31 = 21, 0b10101
+	 * bits 52 - 31 = 21, 0b10101
 	 * RTS encoding details
 	 * bits 0 - 3 of rts -> bits 6 - 8 unsigned long
 	 * bits 4 - 5 of rts -> bits 62 - 63 of unsigned long
 	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		rts_field = (0x3UL << 61);
-	else {
-		rts_field = (0x5UL << 5); /* 6 - 8 bits */
-		rts_field |= (0x2UL << 61);
-	}
+	rts_field = (0x5UL << 5); /* 6 - 8 bits */
+	rts_field |= (0x2UL << 61);
+
 	return rts_field;
 }
 
diff --git a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
index ef5c3f2994c9..1154a6dc6d26 100644
--- a/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
+++ b/arch/powerpc/include/asm/book3s/64/tlbflush-radix.h
@@ -48,8 +48,6 @@ extern void radix__flush_tlb_page_psize(struct mm_struct *mm, unsigned long vmad
 extern void radix__flush_tlb_pwc(struct mmu_gather *tlb, unsigned long addr);
 extern void radix__flush_tlb_collapsed_pmd(struct mm_struct *mm, unsigned long addr);
 extern void radix__flush_tlb_all(void);
-extern void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
-					unsigned long address);
 
 extern void radix__flush_tlb_lpid_page(unsigned int lpid,
 					unsigned long addr,
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 9c0a3083571b..f980f91cad8a 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -210,7 +210,6 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0000008000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0000010000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x0000020000000000)
-#define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x0000040000000000)
 #define CPU_FTR_POWER9_DD2_1		LONG_ASM_CONST(0x0000080000000000)
 #define CPU_FTR_P9_TM_HV_ASSIST		LONG_ASM_CONST(0x0000100000000000)
 #define CPU_FTR_P9_TM_XER_SO_BUG	LONG_ASM_CONST(0x0000200000000000)
@@ -464,8 +463,6 @@ static inline void cpu_feature_keys_init(void) { }
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_ARCH_207S | \
 	    CPU_FTR_TM_COMP | CPU_FTR_ARCH_300 | CPU_FTR_PKEY | \
 	    CPU_FTR_P9_TLBIE_BUG | CPU_FTR_P9_TIDR)
-#define CPU_FTRS_POWER9_DD1 ((CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD1) & \
-			     (~CPU_FTR_SAO))
 #define CPU_FTRS_POWER9_DD2_0 CPU_FTRS_POWER9
 #define CPU_FTRS_POWER9_DD2_1 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1)
 #define CPU_FTRS_POWER9_DD2_2 (CPU_FTRS_POWER9 | CPU_FTR_POWER9_DD2_1 | \
@@ -489,16 +486,14 @@ static inline void cpu_feature_keys_init(void) { }
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | CPU_FTRS_POWER8 | \
 	     CPU_FTRS_POWER8_DD1 | CPU_FTR_ALTIVEC_COMP | CPU_FTR_VSX_COMP | \
-	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
-	     CPU_FTRS_POWER9_DD2_2)
+	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2)
 #else
 #define CPU_FTRS_POSSIBLE	\
 	    (CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
 	     CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
 	     CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \
 	     CPU_FTRS_PA6T | CPU_FTR_VSX_COMP | CPU_FTR_ALTIVEC_COMP | \
-	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1 | CPU_FTRS_POWER9_DD2_1 | \
-	     CPU_FTRS_POWER9_DD2_2)
+	     CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD2_1 | CPU_FTRS_POWER9_DD2_2)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
 #else
@@ -567,7 +562,7 @@ enum {
 #define CPU_FTRS_ALWAYS \
 	    (CPU_FTRS_POSSIBLE & ~CPU_FTR_HVMODE & CPU_FTRS_POWER7 & \
 	     CPU_FTRS_POWER8E & CPU_FTRS_POWER8 & CPU_FTRS_POWER8_DD1 & \
-	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & \
 	     CPU_FTRS_DT_CPU_BASE)
 #else
 #define CPU_FTRS_ALWAYS		\
@@ -575,7 +570,7 @@ enum {
 	     CPU_FTRS_POWER6 & CPU_FTRS_POWER7 & CPU_FTRS_CELL & \
 	     CPU_FTRS_PA6T & CPU_FTRS_POWER8 & CPU_FTRS_POWER8E & \
 	     CPU_FTRS_POWER8_DD1 & ~CPU_FTR_HVMODE & CPU_FTRS_POSSIBLE & \
-	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD1 & CPU_FTRS_POWER9_DD2_1 & \
+	     CPU_FTRS_POWER9 & CPU_FTRS_POWER9_DD2_1 & \
 	     CPU_FTRS_DT_CPU_BASE)
 #endif /* CONFIG_CPU_LITTLE_ENDIAN */
 #endif
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 6d34bd71139d..4e9cede5a7e7 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -187,11 +187,6 @@ struct paca_struct {
 	u8 subcore_sibling_mask;
 	/* Flag to request this thread not to stop */
 	atomic_t dont_stop;
-	/*
-	 * Pointer to an array which contains pointer
-	 * to the sibling threads' paca.
-	 */
-	struct paca_struct **thread_sibling_pacas;
 	/* The PSSCR value that the kernel requested before going to stop */
 	u64 requested_psscr;
 
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 0a0544335950..89cf15566c4e 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -766,7 +766,6 @@ int main(void)
 	OFFSET(PACA_THREAD_IDLE_STATE, paca_struct, thread_idle_state);
 	OFFSET(PACA_THREAD_MASK, paca_struct, thread_mask);
 	OFFSET(PACA_SUBCORE_SIBLING_MASK, paca_struct, subcore_sibling_mask);
-	OFFSET(PACA_SIBLING_PACA_PTRS, paca_struct, thread_sibling_pacas);
 	OFFSET(PACA_REQ_PSSCR, paca_struct, requested_psscr);
 	OFFSET(PACA_DONT_STOP, paca_struct, dont_stop);
 #define STOP_SPR(x, f)	OFFSET(x, paca_struct, stop_sprs.f)
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c8fc9691f8c7..bc75a2908a7e 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -485,25 +485,6 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.machine_check_early	= __machine_check_early_realmode_p8,
 		.platform		= "power8",
 	},
-	{	/* Power9 DD1*/
-		.pvr_mask		= 0xffffff00,
-		.pvr_value		= 0x004e0100,
-		.cpu_name		= "POWER9 (raw)",
-		.cpu_features		= CPU_FTRS_POWER9_DD1,
-		.cpu_user_features	= COMMON_USER_POWER9,
-		.cpu_user_features2	= COMMON_USER2_POWER9,
-		.mmu_features		= MMU_FTRS_POWER9,
-		.icache_bsize		= 128,
-		.dcache_bsize		= 128,
-		.num_pmcs		= 6,
-		.pmc_type		= PPC_PMC_IBM,
-		.oprofile_cpu_type	= "ppc64/power9",
-		.oprofile_type		= PPC_OPROFILE_INVALID,
-		.cpu_setup		= __setup_cpu_power9,
-		.cpu_restore		= __restore_cpu_power9,
-		.machine_check_early	= __machine_check_early_realmode_p9,
-		.platform		= "power9",
-	},
 	{	/* Power9 DD2.0 */
 		.pvr_mask		= 0xffffefff,
 		.pvr_value		= 0x004e0200,
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 96dd3d871986..f432054234a4 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -701,9 +701,7 @@ static __init void cpufeatures_cpu_quirks(void)
 	/*
 	 * Not all quirks can be derived from the cpufeatures device tree.
 	 */
-	if ((version & 0xffffff00) == 0x004e0100)
-		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD1;
-	else if ((version & 0xffffefff) == 0x004e0200)
+	if ((version & 0xffffefff) == 0x004e0200)
 		; /* DD2.0 has no feature flag */
 	else if ((version & 0xffffefff) == 0x004e0201)
 		cur_cpu_spec->cpu_features |= CPU_FTR_POWER9_DD2_1;
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 285c6465324a..76a14702cb9c 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -276,9 +276,7 @@ BEGIN_FTR_SECTION
 	 *
 	 * This interrupt can wake directly from idle. If that is the case,
 	 * the machine check is handled then the idle wakeup code is called
-	 * to restore state. In that case, the POWER9 DD1 idle PACA workaround
-	 * is not applied in the early machine check code, which will cause
-	 * bugs.
+	 * to restore state.
 	 */
 	mr	r11,r1			/* Save r1 */
 	lhz	r10,PACA_IN_MCE(r13)
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index e734f6e45abc..d85d5515a091 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -466,43 +466,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_P9_TM_XER_SO_BUG)
 	blr		/* return 0 for wakeup cause / SRR1 value */
 #endif
 
-/*
- * On waking up from stop 0,1,2 with ESL=1 on POWER9 DD1,
- * HSPRG0 will be set to the HSPRG0 value of one of the
- * threads in this core. Thus the value we have in r13
- * may not be this thread's paca pointer.
- *
- * Fortunately, the TIR remains invariant. Since this thread's
- * paca pointer is recorded in all its sibling's paca, we can
- * correctly recover this thread's paca pointer if we
- * know the index of this thread in the core.
- *
- * This index can be obtained from the TIR.
- *
- * i.e, thread's position in the core = TIR.
- * If this value is i, then this thread's paca is
- * paca->thread_sibling_pacas[i].
- */
-power9_dd1_recover_paca:
-	mfspr	r4, SPRN_TIR
-	/*
-	 * Since each entry in thread_sibling_pacas is 8 bytes
-	 * we need to left-shift by 3 bits. Thus r4 = i * 8
-	 */
-	sldi	r4, r4, 3
-	/* Get &paca->thread_sibling_pacas[0] in r5 */
-	ld	r5, PACA_SIBLING_PACA_PTRS(r13)
-	/* Load paca->thread_sibling_pacas[i] into r13 */
-	ldx	r13, r4, r5
-	SET_PACA(r13)
-	/*
-	 * Indicate that we have lost NVGPR state
-	 * which needs to be restored from the stack.
-	 */
-	li	r3, 1
-	stb	r3,PACA_NAPSTATELOST(r13)
-	blr
-
 /*
  * Called from machine check handler for powersave wakeups.
  * Low level machine check processing has already been done. Now just
@@ -537,9 +500,6 @@ pnv_powersave_wakeup:
 	ld	r2, PACATOC(r13)
 
 BEGIN_FTR_SECTION
-BEGIN_FTR_SECTION_NESTED(70)
-	bl	power9_dd1_recover_paca
-END_FTR_SECTION_NESTED_IFSET(CPU_FTR_POWER9_DD1, 70)
 	bl	pnv_restore_hyp_resource_arch300
 FTR_SECTION_ELSE
 	bl	pnv_restore_hyp_resource_arch207
@@ -602,22 +562,12 @@ END_FTR_SECTION_IFCLR(CPU_FTR_POWER9_DD2_1)
 	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 
-BEGIN_FTR_SECTION_NESTED(71)
-	/*
-	 * Assume that we are waking up from the state
-	 * same as the Requested Level (RL) in the PSSCR
-	 * which are Bits 60-63
-	 */
-	ld	r5,PACA_REQ_PSSCR(r13)
-	rldicl  r5,r5,0,60
-FTR_SECTION_ELSE_NESTED(71)
 	/*
 	 * 0-3 bits correspond to Power-Saving Level Status
 	 * which indicates the idle state we are waking up from
 	 */
 	mfspr	r5, SPRN_PSSCR
 	rldicl  r5,r5,4,60
-ALT_FTR_SECTION_END_NESTED_IFSET(CPU_FTR_POWER9_DD1, 71)
 	li	r0, 0		/* clear requested_psscr to say we're awake */
 	std	r0, PACA_REQ_PSSCR(r13)
 	cmpd	cr4,r5,r4
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 9ef4aea9fffe..27f0caee55ea 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1250,17 +1250,9 @@ struct task_struct *__switch_to(struct task_struct *prev,
 		 * mappings. If the new process has the foreign real address
 		 * mappings, we must issue a cp_abort to clear any state and
 		 * prevent snooping, corruption or a covert channel.
-		 *
-		 * DD1 allows paste into normal system memory so we do an
-		 * unpaired copy, rather than cp_abort, to clear the buffer,
-		 * since cp_abort is quite expensive.
 		 */
-		if (current_thread_info()->task->thread.used_vas) {
+		if (current_thread_info()->task->thread.used_vas)
 			asm volatile(PPC_CP_ABORT);
-		} else if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-			asm volatile(PPC_COPY(%0, %1)
-					: : "r"(dummy_copy_buffer), "r"(0));
-		}
 	}
 #endif /* CONFIG_PPC_BOOK3S_64 */
 
diff --git a/arch/powerpc/kvm/book3s_64_mmu_radix.c b/arch/powerpc/kvm/book3s_64_mmu_radix.c
index 176f911ee983..0af1c0aea1fe 100644
--- a/arch/powerpc/kvm/book3s_64_mmu_radix.c
+++ b/arch/powerpc/kvm/book3s_64_mmu_radix.c
@@ -66,10 +66,7 @@ int kvmppc_mmu_radix_xlate(struct kvm_vcpu *vcpu, gva_t eaddr,
 	bits = root & RPDS_MASK;
 	root = root & RPDB_MASK;
 
-	/* P9 DD1 interprets RTS (radix tree size) differently */
 	offset = rts + 31;
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		offset -= 3;
 
 	/* current implementations only support 52-bit space */
 	if (offset != 52)
@@ -160,17 +157,7 @@ static unsigned long kvmppc_radix_update_pte(struct kvm *kvm, pte_t *ptep,
 				      unsigned long clr, unsigned long set,
 				      unsigned long addr, unsigned int shift)
 {
-	unsigned long old = 0;
-
-	if (!(clr & _PAGE_PRESENT) && cpu_has_feature(CPU_FTR_POWER9_DD1) &&
-	    pte_present(*ptep)) {
-		/* have to invalidate it first */
-		old = __radix_pte_update(ptep, _PAGE_PRESENT, 0);
-		kvmppc_radix_tlbie_page(kvm, addr, shift);
-		set |= _PAGE_PRESENT;
-		old &= _PAGE_PRESENT;
-	}
-	return __radix_pte_update(ptep, clr, set) | old;
+	return __radix_pte_update(ptep, clr, set);
 }
 
 void kvmppc_radix_set_pte_at(struct kvm *kvm, unsigned long addr,
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de686b340f4a..b568582120a3 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1693,14 +1693,6 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
 	case KVM_REG_PPC_TB_OFFSET:
-		/*
-		 * POWER9 DD1 has an erratum where writing TBU40 causes
-		 * the timebase to lose ticks.  So we don't let the
-		 * timebase offset be changed on P9 DD1.  (It is
-		 * initialized to zero.)
-		 */
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-			break;
 		/* round up to multiple of 2^24 */
 		vcpu->arch.vcore->tb_offset =
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
@@ -2026,8 +2018,6 @@ static struct kvm_vcpu *kvmppc_core_vcpu_create_hv(struct kvm *kvm,
 	/*
 	 * Set the default HFSCR for the guest from the host value.
 	 * This value is only used on POWER9.
-	 * On POWER9 DD1, TM doesn't work, so we make sure to
-	 * prevent the guest from using it.
 	 * On POWER9, we want to virtualize the doorbell facility, so we
 	 * turn off the HFSCR bit, which causes those instructions to trap.
 	 */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 153988d878e8..6e4554b273f1 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -916,9 +916,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DAWR)
 	mtspr	SPRN_BESCR, r6
 	mtspr	SPRN_PID, r7
 	mtspr	SPRN_WORT, r8
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
 BEGIN_FTR_SECTION
 	/* POWER8-only registers */
 	ld	r5, VCPU_TCSCR(r4)
@@ -1912,7 +1909,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	ld	r5, VCPU_KVM(r9)
 	lbz	r0, KVM_RADIX(r5)
 	cmpwi	cr2, r0, 0
-	beq	cr2, 4f
+	beq	cr2, 2f
 
 	/*
 	 * Radix: do eieio; tlbsync; ptesync sequence in case we
@@ -1952,11 +1949,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	bdnz	1b
 	ptesync
 
-2:	/* Flush the ERAT on radix P9 DD1 guest exit */
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-4:
+2:
 #endif /* CONFIG_PPC_RADIX_MMU */
 
 	/*
@@ -3367,11 +3360,6 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	mtspr	SPRN_CIABR, r0
 	mtspr	SPRN_DAWRX, r0
 
-	/* Flush the ERAT on radix P9 DD1 guest exit */
-BEGIN_FTR_SECTION
-	PPC_INVALIDATE_ERAT
-END_FTR_SECTION_IFSET(CPU_FTR_POWER9_DD1)
-
 BEGIN_MMU_FTR_SECTION
 	b	4f
 END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
diff --git a/arch/powerpc/kvm/book3s_xive_template.c b/arch/powerpc/kvm/book3s_xive_template.c
index 6e41ba7ec8f4..4171ede8722b 100644
--- a/arch/powerpc/kvm/book3s_xive_template.c
+++ b/arch/powerpc/kvm/book3s_xive_template.c
@@ -25,18 +25,6 @@ static void GLUE(X_PFX,ack_pending)(struct kvmppc_xive_vcpu *xc)
 	 */
 	eieio();
 
-	/*
-	 * DD1 bug workaround: If PIPR is less favored than CPPR
-	 * ignore the interrupt or we might incorrectly lose an IPB
-	 * bit.
-	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		__be64 qw1 = __x_readq(__x_tima + TM_QW1_OS);
-		u8 pipr = be64_to_cpu(qw1) & 0xff;
-		if (pipr >= xc->hw_cppr)
-			return;
-	}
-
 	/* Perform the acknowledge OS to register cycle. */
 	ack = be16_to_cpu(__x_readw(__x_tima + TM_SPC_ACK_OS_REG));
 
@@ -89,8 +77,15 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
 	/* If the XIVE supports the new "store EOI facility, use it */
 	if (xd->flags & XIVE_IRQ_FLAG_STORE_EOI)
 		__x_writeq(0, __x_eoi_page(xd) + XIVE_ESB_STORE_EOI);
-	else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW) {
+	else if (hw_irq && xd->flags & XIVE_IRQ_FLAG_EOI_FW)
 		opal_int_eoi(hw_irq);
+	else if (xd->flags & XIVE_IRQ_FLAG_LSI) {
+		/*
+		 * For LSIs the HW EOI cycle is used rather than PQ bits,
+		 * as they are automatically re-triggred in HW when still
+		 * pending.
+		 */
+		__x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI);
 	} else {
 		uint64_t eoi_val;
 
@@ -102,20 +97,12 @@ static void GLUE(X_PFX,source_eoi)(u32 hw_irq, struct xive_irq_data *xd)
 		 *
 		 * This allows us to then do a re-trigger if Q was set
 		 * rather than synthetizing an interrupt in software
-		 *
-		 * For LSIs, using the HW EOI cycle works around a problem
-		 * on P9 DD1 PHBs where the other ESB accesses don't work
-		 * properly.
 		 */
-		if (xd->flags & XIVE_IRQ_FLAG_LSI)
-			__x_readq(__x_eoi_page(xd) + XIVE_ESB_LOAD_EOI);
-		else {
-			eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
-
-			/* Re-trigger if needed */
-			if ((eoi_val & 1) && __x_trig_page(xd))
-				__x_writeq(0, __x_trig_page(xd));
-		}
+		eoi_val = GLUE(X_PFX,esb_load)(xd, XIVE_ESB_SET_PQ_00);
+
+		/* Re-trigger if needed */
+		if ((eoi_val & 1) && __x_trig_page(xd))
+			__x_writeq(0, __x_trig_page(xd));
 	}
 }
 
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index 8318716e5075..5a72e980e25a 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -808,31 +808,6 @@ int hash__remove_section_mapping(unsigned long start, unsigned long end)
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-static void update_hid_for_hash(void)
-{
-	unsigned long hid0;
-	unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */
-
-	asm volatile("ptesync": : :"memory");
-	/* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(0), "i"(0), "i"(2), "r"(0) : "memory");
-	asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory");
-	trace_tlbie(0, 0, rb, 0, 2, 0, 0);
-
-	/*
-	 * now switch the HID
-	 */
-	hid0  = mfspr(SPRN_HID0);
-	hid0 &= ~HID0_POWER9_RADIX;
-	mtspr(SPRN_HID0, hid0);
-	asm volatile("isync": : :"memory");
-
-	/* Wait for it to happen */
-	while ((mfspr(SPRN_HID0) & HID0_POWER9_RADIX))
-		cpu_relax();
-}
-
 static void __init hash_init_partition_table(phys_addr_t hash_table,
 					     unsigned long htab_size)
 {
@@ -845,8 +820,6 @@ static void __init hash_init_partition_table(phys_addr_t hash_table,
 	htab_size =  __ilog2(htab_size) - 18;
 	mmu_partition_table_set_entry(0, hash_table | htab_size, 0);
 	pr_info("Partition table %p\n", partition_tb);
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		update_hid_for_hash();
 }
 
 static void __init htab_initialize(void)
@@ -1077,9 +1050,6 @@ void hash__early_init_mmu_secondary(void)
 	/* Initialize hash table for that CPU */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-			update_hid_for_hash();
-
 		if (!cpu_has_feature(CPU_FTR_ARCH_300))
 			mtspr(SPRN_SDR1, _SDR1);
 		else
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8a9a49c13865..f425b5b37d58 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -621,15 +621,12 @@ static int __init add_huge_page_size(unsigned long long size)
 	 * firmware we only add hugetlb support for page sizes that can be
 	 * supported by linux page table layout.
 	 * For now we have
-	 * Radix: 2M
+	 * Radix: 2M and 1G
 	 * Hash: 16M and 16G
 	 */
 	if (radix_enabled()) {
-		if (mmu_psize != MMU_PAGE_2M) {
-			if (cpu_has_feature(CPU_FTR_POWER9_DD1) ||
-			    (mmu_psize != MMU_PAGE_1G))
-				return -EINVAL;
-		}
+		if (mmu_psize != MMU_PAGE_2M && mmu_psize != MMU_PAGE_1G)
+			return -EINVAL;
 	} else {
 		if (mmu_psize != MMU_PAGE_16M && mmu_psize != MMU_PAGE_16G)
 			return -EINVAL;
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index f3d4b4a0e561..39e9ef0eb78b 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -273,15 +273,7 @@ void arch_exit_mmap(struct mm_struct *mm)
 #ifdef CONFIG_PPC_RADIX_MMU
 void radix__switch_mmu_context(struct mm_struct *prev, struct mm_struct *next)
 {
-
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		isync();
-		mtspr(SPRN_PID, next->context.id);
-		isync();
-		asm volatile(PPC_INVALIDATE_ERAT : : :"memory");
-	} else {
-		mtspr(SPRN_PID, next->context.id);
-		isync();
-	}
+	mtspr(SPRN_PID, next->context.id);
+	isync();
 }
 #endif
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 96f68c5aa1f5..bba168d02235 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -226,16 +226,6 @@ void radix__mark_rodata_ro(void)
 {
 	unsigned long start, end;
 
-	/*
-	 * mark_rodata_ro() will mark itself as !writable at some point.
-	 * Due to DD1 workaround in radix__pte_update(), we'll end up with
-	 * an invalid pte and the system will crash quite severly.
-	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		pr_warn("Warning: Unable to mark rodata read only on P9 DD1\n");
-		return;
-	}
-
 	start = (unsigned long)_stext;
 	end = (unsigned long)__init_begin;
 
@@ -533,35 +523,6 @@ void __init radix__early_init_devtree(void)
 	return;
 }
 
-static void update_hid_for_radix(void)
-{
-	unsigned long hid0;
-	unsigned long rb = 3UL << PPC_BITLSHIFT(53); /* IS = 3 */
-
-	asm volatile("ptesync": : :"memory");
-	/* prs = 0, ric = 2, rs = 0, r = 1 is = 3 */
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(1), "i"(0), "i"(2), "r"(0) : "memory");
-	/* prs = 1, ric = 2, rs = 0, r = 1 is = 3 */
-	asm volatile(PPC_TLBIE_5(%0, %4, %3, %2, %1)
-		     : : "r"(rb), "i"(1), "i"(1), "i"(2), "r"(0) : "memory");
-	asm volatile("eieio; tlbsync; ptesync; isync; slbia": : :"memory");
-	trace_tlbie(0, 0, rb, 0, 2, 0, 1);
-	trace_tlbie(0, 0, rb, 0, 2, 1, 1);
-
-	/*
-	 * now switch the HID
-	 */
-	hid0  = mfspr(SPRN_HID0);
-	hid0 |= HID0_POWER9_RADIX;
-	mtspr(SPRN_HID0, hid0);
-	asm volatile("isync": : :"memory");
-
-	/* Wait for it to happen */
-	while (!(mfspr(SPRN_HID0) & HID0_POWER9_RADIX))
-		cpu_relax();
-}
-
 static void radix_init_amor(void)
 {
 	/*
@@ -576,22 +537,12 @@ static void radix_init_amor(void)
 
 static void radix_init_iamr(void)
 {
-	unsigned long iamr;
-
-	/*
-	 * The IAMR should set to 0 on DD1.
-	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-		iamr = 0;
-	else
-		iamr = (1ul << 62);
-
 	/*
 	 * Radix always uses key0 of the IAMR to determine if an access is
 	 * allowed. We set bit 0 (IBM bit 1) of key0, to prevent instruction
 	 * fetch.
 	 */
-	mtspr(SPRN_IAMR, iamr);
+	mtspr(SPRN_IAMR, (1ul << 62));
 }
 
 void __init radix__early_init_mmu(void)
@@ -644,8 +595,6 @@ void __init radix__early_init_mmu(void)
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
 		radix_init_native();
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-			update_hid_for_radix();
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 		radix_init_partition_table();
@@ -671,10 +620,6 @@ void radix__early_init_mmu_secondary(void)
 	 * update partition table control register and UPRT
 	 */
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-
-		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-			update_hid_for_radix();
-
 		lpcr = mfspr(SPRN_LPCR);
 		mtspr(SPRN_LPCR, lpcr | LPCR_UPRT | LPCR_HR);
 
@@ -1095,8 +1040,7 @@ void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep,
 	 * To avoid NMMU hang while relaxing access, we need mark
 	 * the pte invalid in between.
 	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1) ||
-	    atomic_read(&mm->context.copros) > 0) {
+	if (atomic_read(&mm->context.copros) > 0) {
 		unsigned long old_pte, new_pte;
 
 		old_pte = __radix_pte_update(ptep, ~0, 0);
diff --git a/arch/powerpc/mm/tlb-radix.c b/arch/powerpc/mm/tlb-radix.c
index 1135b43a597c..fef3e1eb3a19 100644
--- a/arch/powerpc/mm/tlb-radix.c
+++ b/arch/powerpc/mm/tlb-radix.c
@@ -1048,24 +1048,6 @@ void radix__flush_tlb_all(void)
 	asm volatile("eieio; tlbsync; ptesync": : :"memory");
 }
 
-void radix__flush_tlb_pte_p9_dd1(unsigned long old_pte, struct mm_struct *mm,
-				 unsigned long address)
-{
-	/*
-	 * We track page size in pte only for DD1, So we can
-	 * call this only on DD1.
-	 */
-	if (!cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		VM_WARN_ON(1);
-		return;
-	}
-
-	if (old_pte & R_PAGE_LARGE)
-		radix__flush_tlb_page_psize(mm, address, MMU_PAGE_2M);
-	else
-		radix__flush_tlb_page_psize(mm, address, mmu_virtual_psize);
-}
-
 #ifdef CONFIG_KVM_BOOK3S_HV_POSSIBLE
 extern void radix_kvm_prefetch_workaround(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3f66fcf8ad99..01f92c4a9f02 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -128,10 +128,6 @@ static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
 static void power_pmu_sched_task(struct perf_event_context *ctx, bool sched_in) {}
 static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
-static bool use_ic(u64 event)
-{
-	return false;
-}
 #endif /* CONFIG_PPC32 */
 
 static bool regs_use_siar(struct pt_regs *regs)
@@ -714,14 +710,6 @@ static void pmao_restore_workaround(bool ebb)
 	mtspr(SPRN_PMC6, pmcs[5]);
 }
 
-static bool use_ic(u64 event)
-{
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1) &&
-			(event == 0x200f2 || event == 0x300f2))
-		return true;
-
-	return false;
-}
 #endif /* CONFIG_PPC64 */
 
 static void perf_event_interrupt(struct pt_regs *regs);
@@ -1046,7 +1034,6 @@ static u64 check_and_compute_delta(u64 prev, u64 val)
 static void power_pmu_read(struct perf_event *event)
 {
 	s64 val, delta, prev;
-	struct cpu_hw_events *cpuhw = this_cpu_ptr(&cpu_hw_events);
 
 	if (event->hw.state & PERF_HES_STOPPED)
 		return;
@@ -1056,13 +1043,6 @@ static void power_pmu_read(struct perf_event *event)
 
 	if (is_ebb_event(event)) {
 		val = read_pmc(event->hw.idx);
-		if (use_ic(event->attr.config)) {
-			val = mfspr(SPRN_IC);
-			if (val > cpuhw->ic_init)
-				val = val - cpuhw->ic_init;
-			else
-				val = val + (0 - cpuhw->ic_init);
-		}
 		local64_set(&event->hw.prev_count, val);
 		return;
 	}
@@ -1076,13 +1056,6 @@ static void power_pmu_read(struct perf_event *event)
 		prev = local64_read(&event->hw.prev_count);
 		barrier();
 		val = read_pmc(event->hw.idx);
-		if (use_ic(event->attr.config)) {
-			val = mfspr(SPRN_IC);
-			if (val > cpuhw->ic_init)
-				val = val - cpuhw->ic_init;
-			else
-				val = val + (0 - cpuhw->ic_init);
-		}
 		delta = check_and_compute_delta(prev, val);
 		if (!delta)
 			return;
@@ -1535,13 +1508,6 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
 					event->attr.branch_sample_type);
 	}
 
-	/*
-	 * Workaround for POWER9 DD1 to use the Instruction Counter
-	 * register value for instruction counting
-	 */
-	if (use_ic(event->attr.config))
-		cpuhw->ic_init = mfspr(SPRN_IC);
-
 	perf_pmu_enable(event->pmu);
 	local_irq_restore(flags);
 	return ret;
diff --git a/arch/powerpc/perf/isa207-common.c b/arch/powerpc/perf/isa207-common.c
index 2efee3f196f5..177de814286f 100644
--- a/arch/powerpc/perf/isa207-common.c
+++ b/arch/powerpc/perf/isa207-common.c
@@ -59,7 +59,7 @@ static bool is_event_valid(u64 event)
 {
 	u64 valid_mask = EVENT_VALID_MASK;
 
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		valid_mask = p9_EVENT_VALID_MASK;
 
 	return !(event & ~valid_mask);
@@ -86,8 +86,6 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
 	 * Incase of Power9:
 	 * Marked event: MMCRA[SDAR_MODE] will be set to 0b00 ('No Updates'),
 	 *               or if group already have any marked events.
-	 * Non-Marked events (for DD1):
-	 *	MMCRA[SDAR_MODE] will be set to 0b01
 	 * For rest
 	 *	MMCRA[SDAR_MODE] will be set from event code.
 	 *      If sdar_mode from event is zero, default to 0b01. Hardware
@@ -96,7 +94,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
 	if (cpu_has_feature(CPU_FTR_ARCH_300)) {
 		if (is_event_marked(event) || (*mmcra & MMCRA_SAMPLE_ENABLE))
 			*mmcra &= MMCRA_SDAR_MODE_NO_UPDATES;
-		else if (!cpu_has_feature(CPU_FTR_POWER9_DD1) && p9_SDAR_MODE(event))
+		else if (p9_SDAR_MODE(event))
 			*mmcra |=  p9_SDAR_MODE(event) << MMCRA_SDAR_MODE_SHIFT;
 		else
 			*mmcra |= MMCRA_SDAR_MODE_DCACHE;
@@ -106,7 +104,7 @@ static void mmcra_sdar_mode(u64 event, unsigned long *mmcra)
 
 static u64 thresh_cmp_val(u64 value)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		return value << p9_MMCRA_THR_CMP_SHIFT;
 
 	return value << MMCRA_THR_CMP_SHIFT;
@@ -114,7 +112,7 @@ static u64 thresh_cmp_val(u64 value)
 
 static unsigned long combine_from_event(u64 event)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		return p9_EVENT_COMBINE(event);
 
 	return EVENT_COMBINE(event);
@@ -122,7 +120,7 @@ static unsigned long combine_from_event(u64 event)
 
 static unsigned long combine_shift(unsigned long pmc)
 {
-	if (cpu_has_feature(CPU_FTR_ARCH_300) && !cpu_has_feature(CPU_FTR_POWER9_DD1))
+	if (cpu_has_feature(CPU_FTR_ARCH_300))
 		return p9_MMCR1_COMBINE_SHIFT(pmc);
 
 	return MMCR1_COMBINE_SHIFT(pmc);
diff --git a/arch/powerpc/perf/isa207-common.h b/arch/powerpc/perf/isa207-common.h
index 6a0b586c935a..0028f4b9490d 100644
--- a/arch/powerpc/perf/isa207-common.h
+++ b/arch/powerpc/perf/isa207-common.h
@@ -158,11 +158,6 @@
 	CNST_PMC_VAL(1) | CNST_PMC_VAL(2) | CNST_PMC_VAL(3) | \
 	CNST_PMC_VAL(4) | CNST_PMC_VAL(5) | CNST_PMC_VAL(6) | CNST_NC_VAL
 
-/*
- * Lets restrict use of PMC5 for instruction counting.
- */
-#define P9_DD1_TEST_ADDER	(ISA207_TEST_ADDER | CNST_PMC_VAL(5))
-
 /* Bits in MMCR1 for PowerISA v2.07 */
 #define MMCR1_UNIT_SHIFT(pmc)		(60 - (4 * ((pmc) - 1)))
 #define MMCR1_COMBINE_SHIFT(pmc)	(35 - ((pmc) - 1))
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 2ca0b33b4efb..e012b1030a5b 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -219,12 +219,6 @@ static struct attribute_group power9_pmu_events_group = {
 	.attrs = power9_events_attr,
 };
 
-static const struct attribute_group *power9_isa207_pmu_attr_groups[] = {
-	&isa207_pmu_format_group,
-	&power9_pmu_events_group,
-	NULL,
-};
-
 PMU_FORMAT_ATTR(event,		"config:0-51");
 PMU_FORMAT_ATTR(pmcxsel,	"config:0-7");
 PMU_FORMAT_ATTR(mark,		"config:8");
@@ -267,17 +261,6 @@ static const struct attribute_group *power9_pmu_attr_groups[] = {
 	NULL,
 };
 
-static int power9_generic_events_dd1[] = {
-	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
-	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PM_ICT_NOSLOT_CYC,
-	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =	PM_CMPLU_STALL,
-	[PERF_COUNT_HW_INSTRUCTIONS] =			PM_INST_DISP,
-	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] =		PM_BR_CMPL_ALT,
-	[PERF_COUNT_HW_BRANCH_MISSES] =			PM_BR_MPRED_CMPL,
-	[PERF_COUNT_HW_CACHE_REFERENCES] =		PM_LD_REF_L1,
-	[PERF_COUNT_HW_CACHE_MISSES] =			PM_LD_MISS_L1_FIN,
-};
-
 static int power9_generic_events[] = {
 	[PERF_COUNT_HW_CPU_CYCLES] =			PM_CYC,
 	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =	PM_ICT_NOSLOT_CYC,
@@ -439,25 +422,6 @@ static int power9_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
 
 #undef C
 
-static struct power_pmu power9_isa207_pmu = {
-	.name			= "POWER9",
-	.n_counter		= MAX_PMU_COUNTERS,
-	.add_fields		= ISA207_ADD_FIELDS,
-	.test_adder		= P9_DD1_TEST_ADDER,
-	.compute_mmcr		= isa207_compute_mmcr,
-	.config_bhrb		= power9_config_bhrb,
-	.bhrb_filter_map	= power9_bhrb_filter_map,
-	.get_constraint		= isa207_get_constraint,
-	.get_alternatives	= power9_get_alternatives,
-	.disable_pmc		= isa207_disable_pmc,
-	.flags			= PPMU_NO_SIAR | PPMU_ARCH_207S,
-	.n_generic		= ARRAY_SIZE(power9_generic_events_dd1),
-	.generic_events		= power9_generic_events_dd1,
-	.cache_events		= &power9_cache_events,
-	.attr_groups		= power9_isa207_pmu_attr_groups,
-	.bhrb_nr		= 32,
-};
-
 static struct power_pmu power9_pmu = {
 	.name			= "POWER9",
 	.n_counter		= MAX_PMU_COUNTERS,
@@ -500,23 +464,7 @@ static int __init init_power9_pmu(void)
 		}
 	}
 
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		/*
-		 * Since PM_INST_CMPL may not provide right counts in all
-		 * sampling scenarios in power9 DD1, instead use PM_INST_DISP.
-		 */
-		EVENT_VAR(PM_INST_CMPL, _g).id = PM_INST_DISP;
-		/*
-		 * Power9 DD1 should use PM_BR_CMPL_ALT event code for
-		 * "branches" to provide correct counter value.
-		 */
-		EVENT_VAR(PM_BR_CMPL, _g).id = PM_BR_CMPL_ALT;
-		EVENT_VAR(PM_BR_CMPL, _c).id = PM_BR_CMPL_ALT;
-		rc = register_power_pmu(&power9_isa207_pmu);
-	} else {
-		rc = register_power_pmu(&power9_pmu);
-	}
-
+	rc = register_power_pmu(&power9_pmu);
 	if (rc)
 		return rc;
 
diff --git a/arch/powerpc/platforms/powernv/idle.c b/arch/powerpc/platforms/powernv/idle.c
index 1c5d0675b43c..12f13acee1f6 100644
--- a/arch/powerpc/platforms/powernv/idle.c
+++ b/arch/powerpc/platforms/powernv/idle.c
@@ -177,11 +177,6 @@ static void pnv_alloc_idle_core_states(void)
 			paca_ptrs[cpu]->core_idle_state_ptr = core_idle_state;
 			paca_ptrs[cpu]->thread_idle_state = PNV_THREAD_RUNNING;
 			paca_ptrs[cpu]->thread_mask = 1 << j;
-			if (!cpu_has_feature(CPU_FTR_POWER9_DD1))
-				continue;
-			paca_ptrs[cpu]->thread_sibling_pacas =
-				kmalloc_node(paca_ptr_array_size,
-					     GFP_KERNEL, node);
 		}
 	}
 
@@ -805,29 +800,6 @@ static int __init pnv_init_idle_states(void)
 
 	pnv_alloc_idle_core_states();
 
-	/*
-	 * For each CPU, record its PACA address in each of it's
-	 * sibling thread's PACA at the slot corresponding to this
-	 * CPU's index in the core.
-	 */
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		int cpu;
-
-		pr_info("powernv: idle: Saving PACA pointers of all CPUs in their thread sibling PACA\n");
-		for_each_present_cpu(cpu) {
-			int base_cpu = cpu_first_thread_sibling(cpu);
-			int idx = cpu_thread_in_core(cpu);
-			int i;
-
-			for (i = 0; i < threads_per_core; i++) {
-				int j = base_cpu + i;
-
-				paca_ptrs[j]->thread_sibling_pacas[idx] =
-					paca_ptrs[cpu];
-			}
-		}
-	}
-
 	if (supported_cpuidle_states & OPAL_PM_NAP_ENABLED)
 		ppc_md.power_save = power7_idle;
 
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index b80909957792..0d354e19ef92 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -283,23 +283,6 @@ static void pnv_cause_ipi(int cpu)
 	ic_cause_ipi(cpu);
 }
 
-static void pnv_p9_dd1_cause_ipi(int cpu)
-{
-	int this_cpu = get_cpu();
-
-	/*
-	 * POWER9 DD1 has a global addressed msgsnd, but for now we restrict
-	 * IPIs to same core, because it requires additional synchronization
-	 * for inter-core doorbells which we do not implement.
-	 */
-	if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu)))
-		doorbell_global_ipi(cpu);
-	else
-		ic_cause_ipi(cpu);
-
-	put_cpu();
-}
-
 static void __init pnv_smp_probe(void)
 {
 	if (xive_enabled())
@@ -311,14 +294,10 @@ static void __init pnv_smp_probe(void)
 		ic_cause_ipi = smp_ops->cause_ipi;
 		WARN_ON(!ic_cause_ipi);
 
-		if (cpu_has_feature(CPU_FTR_ARCH_300)) {
-			if (cpu_has_feature(CPU_FTR_POWER9_DD1))
-				smp_ops->cause_ipi = pnv_p9_dd1_cause_ipi;
-			else
-				smp_ops->cause_ipi = doorbell_global_ipi;
-		} else {
+		if (cpu_has_feature(CPU_FTR_ARCH_300))
+			smp_ops->cause_ipi = doorbell_global_ipi;
+		else
 			smp_ops->cause_ipi = pnv_cause_ipi;
-		}
 	}
 }
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index 3459015092fa..4758173df426 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -319,7 +319,7 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
 		 * The FW told us to call it. This happens for some
 		 * interrupt sources that need additional HW whacking
 		 * beyond the ESB manipulation. For example LPC interrupts
-		 * on P9 DD1.0 need a latch to be clared in the LPC bridge
+		 * on P9 DD1.0 needed a latch to be clared in the LPC bridge
 		 * itself. The Firmware will take care of it.
 		 */
 		if (WARN_ON_ONCE(!xive_ops->eoi))
@@ -337,9 +337,9 @@ void xive_do_source_eoi(u32 hw_irq, struct xive_irq_data *xd)
 		 * This allows us to then do a re-trigger if Q was set
 		 * rather than synthesizing an interrupt in software
 		 *
-		 * For LSIs, using the HW EOI cycle works around a problem
-		 * on P9 DD1 PHBs where the other ESB accesses don't work
-		 * properly.
+		 * For LSIs the HW EOI cycle is used rather than PQ bits,
+		 * as they are automatically re-triggred in HW when still
+		 * pending.
 		 */
 		if (xd->flags & XIVE_IRQ_FLAG_LSI)
 			xive_esb_read(xd, XIVE_ESB_LOAD_EOI);
diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
index 47166ad2a669..21119cfe8474 100644
--- a/arch/powerpc/xmon/xmon.c
+++ b/arch/powerpc/xmon/xmon.c
@@ -2429,7 +2429,6 @@ static void dump_one_paca(int cpu)
 	DUMP(p, thread_idle_state, "%#-*x");
 	DUMP(p, thread_mask, "%#-*x");
 	DUMP(p, subcore_sibling_mask, "%#-*x");
-	DUMP(p, thread_sibling_pacas, "%-*px");
 	DUMP(p, requested_psscr, "%#-*llx");
 	DUMP(p, stop_sprs.pid, "%#-*llx");
 	DUMP(p, stop_sprs.ldbar, "%#-*llx");
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 918d4fb742d1..505f973e13f3 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -865,14 +865,6 @@ static inline bool cxl_is_power9(void)
 	return false;
 }
 
-static inline bool cxl_is_power9_dd1(void)
-{
-	if ((pvr_version_is(PVR_POWER9)) &&
-	    cpu_has_feature(CPU_FTR_POWER9_DD1))
-		return true;
-	return false;
-}
-
 ssize_t cxl_pci_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
 				loff_t off, size_t count);
 
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
index 0bc7c31cf739..5a3f91255258 100644
--- a/drivers/misc/cxl/cxllib.c
+++ b/drivers/misc/cxl/cxllib.c
@@ -102,10 +102,6 @@ int cxllib_get_xsl_config(struct pci_dev *dev, struct cxllib_xsl_config *cfg)
 	rc = cxl_get_xsl9_dsnctl(dev, capp_unit_id, &cfg->dsnctl);
 	if (rc)
 		return rc;
-	if (cpu_has_feature(CPU_FTR_POWER9_DD1)) {
-		/* workaround for DD1 - nbwind = capiind */
-		cfg->dsnctl |= ((u64)0x02 << (63-47));
-	}
 
 	cfg->version  = CXL_XSL_CONFIG_CURRENT_VERSION;
 	cfg->log_bar_size = CXL_CAPI_WINDOW_LOG_SIZE;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 429d6de1dde7..2af0d4c47b76 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -465,23 +465,21 @@ int cxl_get_xsl9_dsnctl(struct pci_dev *dev, u64 capp_unit_id, u64 *reg)
 	/* nMMU_ID Defaults to: b’000001001’*/
 	xsl_dsnctl |= ((u64)0x09 << (63-28));
 
-	if (!(cxl_is_power9_dd1())) {
-		/*
-		 * Used to identify CAPI packets which should be sorted into
-		 * the Non-Blocking queues by the PHB. This field should match
-		 * the PHB PBL_NBW_CMPM register
-		 * nbwind=0x03, bits [57:58], must include capi indicator.
-		 * Not supported on P9 DD1.
-		 */
-		xsl_dsnctl |= (nbwind << (63-55));
+	/*
+	 * Used to identify CAPI packets which should be sorted into
+	 * the Non-Blocking queues by the PHB. This field should match
+	 * the PHB PBL_NBW_CMPM register
+	 * nbwind=0x03, bits [57:58], must include capi indicator.
+	 * Not supported on P9 DD1.
+	 */
+	xsl_dsnctl |= (nbwind << (63-55));
 
-		/*
-		 * Upper 16b address bits of ASB_Notify messages sent to the
-		 * system. Need to match the PHB’s ASN Compare/Mask Register.
-		 * Not supported on P9 DD1.
-		 */
-		xsl_dsnctl |= asnind;
-	}
+	/*
+	 * Upper 16b address bits of ASB_Notify messages sent to the
+	 * system. Need to match the PHB’s ASN Compare/Mask Register.
+	 * Not supported on P9 DD1.
+	 */
+	xsl_dsnctl |= asnind;
 
 	*reg = xsl_dsnctl;
 	return 0;
@@ -539,15 +537,8 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter,
 	/* Snoop machines */
 	cxl_p1_write(adapter, CXL_PSL9_APCDEDALLOC, 0x800F000200000000ULL);
 
-	if (cxl_is_power9_dd1()) {
-		/* Disabling deadlock counter CAR */
-		cxl_p1_write(adapter, CXL_PSL9_GP_CT, 0x0020000000000001ULL);
-		/* Enable NORST */
-		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0x8000000000000000ULL);
-	} else {
-		/* Enable NORST and DD2 features */
-		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0xC000000000000000ULL);
-	}
+	/* Enable NORST and DD2 features */
+	cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0xC000000000000000ULL);
 
 	/*
 	 * Check if PSL has data-cache. We need to flush adapter datacache
-- 
2.17.0

^ permalink raw reply related


This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox