Re: [PATCH 1/2] powerpc/mm: Fix crashes with PUD level hugetlb config

["Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>]

"Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com> writes:

> To support memory keys, we moved the hash pte slot information to the second
> half of the page table. This was ok with PTE entries at level 4 and level 3.
> We already allocate larger page table pages at those level to accomodate extra
> details. For level 4 we already have the extra space which was used to track
> 4k hash page table entry details and at pmd level the extra space was allocated
> to track the THP details.
>
> With hugetlbfs PTE, we used this extra space at the PMD level to store the
> slot details. But we also support hugetlbfs PTE at PUD leve and PUD level page
> didn't allocate extra space. This resulted in memory corruption.
>
> Fix this by allocating extra space at PUD level when HUGETLB is enabled. We
> may need further changes to allocate larger space at PMD level when we enable
> HUGETLB. That will be done in next patch.
>
> Fixes:bf9a95f9a6481bc6e(" powerpc: Free up four 64K PTE bits in 64K backed HPTE pages")
>
> Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

Another fix, I still get random memory corruption with hugetlb test with
16G hugepage config.

commit f9484ac6b06bfacfeb82f1116bfc95e396fe7453
Author: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Date:   Thu Feb 8 19:36:22 2018 +0530

    powerpc/mm/hash64: Store the slot information at the right offset.
    
    The hugetlb pte entries are at the PMD and PUD level. Use the right offset
    for them to get the second half of the table.
    
    Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>

diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index 949d691094a4..67c5475311ee 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -63,7 +63,8 @@ static inline int hash__hugepd_ok(hugepd_t hpd)
  * keeping the prototype consistent across the two formats.
  */
 static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
-			unsigned int subpg_index, unsigned long hidx)
+					 unsigned int subpg_index, unsigned long hidx,
+					 int offset)
 {
 	return (hidx << H_PAGE_F_GIX_SHIFT) &
 		(H_PAGE_F_SECOND | H_PAGE_F_GIX);
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index ee440fb3d240..3bcf269f8f55 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -45,7 +45,7 @@
  * generic accessors and iterators here
  */
 #define __real_pte __real_pte
-static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
+static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep, int offset)
 {
 	real_pte_t rpte;
 	unsigned long *hidxp;
@@ -59,7 +59,7 @@ static inline real_pte_t __real_pte(pte_t pte, pte_t *ptep)
 	 */
 	smp_rmb();
 
-	hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	hidxp = (unsigned long *)(ptep + offset);
 	rpte.hidx = *hidxp;
 	return rpte;
 }
@@ -86,9 +86,10 @@ static inline unsigned long __rpte_to_hidx(real_pte_t rpte, unsigned long index)
  * expected to modify the PTE bits accordingly and commit the PTE to memory.
  */
 static inline unsigned long pte_set_hidx(pte_t *ptep, real_pte_t rpte,
-		unsigned int subpg_index, unsigned long hidx)
+					 unsigned int subpg_index,
+					 unsigned long hidx, int offset)
 {
-	unsigned long *hidxp = (unsigned long *)(ptep + PTRS_PER_PTE);
+	unsigned long *hidxp = (unsigned long *)(ptep + offset);
 
 	rpte.hidx &= ~HIDX_BITS(0xfUL, subpg_index);
 	*hidxp = rpte.hidx  | HIDX_BITS(HIDX_SHIFT_BY_ONE(hidx), subpg_index);
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 3c14663d457d..d92707aff762 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -350,7 +350,7 @@ extern unsigned long pci_io_base;
  */
 #ifndef __real_pte
 
-#define __real_pte(e,p)		((real_pte_t){(e)})
+#define __real_pte(e, p, o)		((real_pte_t){(e)})
 #define __rpte_to_pte(r)	((r).pte)
 #define __rpte_to_hidx(r,index)	(pte_val(__rpte_to_pte(r)) >> H_PAGE_F_GIX_SHIFT)
 
diff --git a/arch/powerpc/mm/hash64_4k.c b/arch/powerpc/mm/hash64_4k.c
index 5a69b51d08a3..d573d7d07f25 100644
--- a/arch/powerpc/mm/hash64_4k.c
+++ b/arch/powerpc/mm/hash64_4k.c
@@ -55,7 +55,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 	 * need to add in 0x1 if it's a read-only user page
 	 */
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -117,7 +117,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hash64_64k.c b/arch/powerpc/mm/hash64_64k.c
index 2253bbc6a599..e601d95c3b20 100644
--- a/arch/powerpc/mm/hash64_64k.c
+++ b/arch/powerpc/mm/hash64_64k.c
@@ -86,7 +86,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 
 	subpg_index = (ea & (PAGE_SIZE - 1)) >> shift;
 	vpn  = hpt_vpn(ea, vsid, ssize);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 	/*
 	 *None of the sub 4k page is hashed
 	 */
@@ -214,7 +214,7 @@ int __hash_page_4K(unsigned long ea, unsigned long access, unsigned long vsid,
 		return -1;
 	}
 
-	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot);
+	new_pte |= pte_set_hidx(ptep, rpte, subpg_index, slot, PTRS_PER_PTE);
 	new_pte |= H_PAGE_HASHPTE;
 
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
@@ -262,7 +262,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 	} while (!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	rpte = __real_pte(__pte(old_pte), ptep, PTRS_PER_PTE);
 
 	if (cpu_has_feature(CPU_FTR_NOEXECUTE) &&
 	    !cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -327,7 +327,7 @@ int __hash_page_64K(unsigned long ea, unsigned long access,
 		}
 
 		new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | H_PAGE_HASHPTE;
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, PTRS_PER_PTE);
 	}
 	*ptep = __pte(new_pte & ~H_PAGE_BUSY);
 	return 0;
diff --git a/arch/powerpc/mm/hugetlbpage-hash64.c b/arch/powerpc/mm/hugetlbpage-hash64.c
index 12511f5a015f..b320f5097a06 100644
--- a/arch/powerpc/mm/hugetlbpage-hash64.c
+++ b/arch/powerpc/mm/hugetlbpage-hash64.c
@@ -27,7 +27,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	unsigned long vpn;
 	unsigned long old_pte, new_pte;
 	unsigned long rflags, pa, sz;
-	long slot;
+	long slot, offset;
 
 	BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
 
@@ -63,7 +63,11 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 	} while(!pte_xchg(ptep, __pte(old_pte), __pte(new_pte)));
 
 	rflags = htab_convert_pte_flags(new_pte);
-	rpte = __real_pte(__pte(old_pte), ptep);
+	if (unlikely(mmu_psize == MMU_PAGE_16G))
+		offset = PTRS_PER_PUD;
+	else
+		offset = PTRS_PER_PMD;
+	rpte = __real_pte(__pte(old_pte), ptep, offset);
 
 	sz = ((1UL) << shift);
 	if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
@@ -104,7 +108,7 @@ int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
 			return -1;
 		}
 
-		new_pte |= pte_set_hidx(ptep, rpte, 0, slot);
+		new_pte |= pte_set_hidx(ptep, rpte, 0, slot, offset);
 	}
 
 	/*
diff --git a/arch/powerpc/mm/tlb_hash64.c b/arch/powerpc/mm/tlb_hash64.c
index 881ebd53ffc2..9b23f12e863c 100644
--- a/arch/powerpc/mm/tlb_hash64.c
+++ b/arch/powerpc/mm/tlb_hash64.c
@@ -51,7 +51,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	unsigned int psize;
 	int ssize;
 	real_pte_t rpte;
-	int i;
+	int i, offset;
 
 	i = batch->index;
 
@@ -67,6 +67,10 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 		psize = get_slice_psize(mm, addr);
 		/* Mask the address for the correct page size */
 		addr &= ~((1UL << mmu_psize_defs[psize].shift) - 1);
+		if (unlikely(psize == MMU_PAGE_16G))
+			offset = PTRS_PER_PUD;
+		else
+			offset = PTRS_PER_PMD;
 #else
 		BUG();
 		psize = pte_pagesize_index(mm, addr, pte); /* shutup gcc */
@@ -78,6 +82,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 		 * support 64k pages, this might be different from the
 		 * hardware page size encoded in the slice table. */
 		addr &= PAGE_MASK;
+		offset = PTRS_PER_PTE;
 	}
 
 
@@ -91,7 +96,7 @@ void hpte_need_flush(struct mm_struct *mm, unsigned long addr,
 	}
 	WARN_ON(vsid == 0);
 	vpn = hpt_vpn(addr, vsid, ssize);
-	rpte = __real_pte(__pte(pte), ptep);
+	rpte = __real_pte(__pte(pte), ptep, offset);
 
 	/*
 	 * Check if we have an active batch on this CPU. If not, just