* [PATCH v1 02/15] powerpc/mm: define __pud_free_tlb() at all time on nohash/64
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
CONFIG_PPC_64K_PAGES is not selectable on nohash/64, so get
__pud_free_tlb() defined at all time.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/64/pgalloc.h | 3 ---
1 file changed, 3 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 66d086f85bd5..ded453f9b5a8 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -171,12 +171,9 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
#define __pmd_free_tlb(tlb, pmd, addr) \
pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
-#ifndef CONFIG_PPC_64K_PAGES
#define __pud_free_tlb(tlb, pud, addr) \
pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
-#endif /* CONFIG_PPC_64K_PAGES */
-
#define check_pgt_cache() do { } while (0)
#endif /* _ASM_POWERPC_PGALLOC_64_H */
--
2.13.3
^ permalink raw reply related
* [PATCH v1 03/15] powerpc/mm: convert Book3E 64 to pte_fragment
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
Book3E 64 is the only subarch not using pte_fragment. In order
to allow refactorisation, this patch converts it to pte_fragment.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/mmu_context.h | 6 -----
arch/powerpc/include/asm/nohash/64/mmu.h | 4 +++-
arch/powerpc/include/asm/nohash/64/pgalloc.h | 33 ++++++++++------------------
arch/powerpc/mm/Makefile | 4 ++--
arch/powerpc/mm/mmu_context.c | 2 +-
5 files changed, 18 insertions(+), 31 deletions(-)
diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
index 6ee8195a2ffb..66a3805dc935 100644
--- a/arch/powerpc/include/asm/mmu_context.h
+++ b/arch/powerpc/include/asm/mmu_context.h
@@ -228,13 +228,7 @@ static inline void enter_lazy_tlb(struct mm_struct *mm,
#endif
}
-#ifdef CONFIG_PPC_BOOK3E_64
-static inline void arch_exit_mmap(struct mm_struct *mm)
-{
-}
-#else
extern void arch_exit_mmap(struct mm_struct *mm);
-#endif
static inline void arch_unmap(struct mm_struct *mm,
struct vm_area_struct *vma,
diff --git a/arch/powerpc/include/asm/nohash/64/mmu.h b/arch/powerpc/include/asm/nohash/64/mmu.h
index e6585480dfc4..3376f5222d24 100644
--- a/arch/powerpc/include/asm/nohash/64/mmu.h
+++ b/arch/powerpc/include/asm/nohash/64/mmu.h
@@ -2,11 +2,13 @@
#ifndef _ASM_POWERPC_NOHASH_64_MMU_H_
#define _ASM_POWERPC_NOHASH_64_MMU_H_
+#include <asm/page.h>
+
/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
#include <asm/nohash/mmu-book3e.h>
#ifndef __ASSEMBLY__
-typedef struct page *pgtable_t;
+typedef pte_t *pgtable_t;
#endif
#endif /* _ASM_POWERPC_NOHASH_64_MMU_H_ */
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index ded453f9b5a8..7fb87235f845 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -76,10 +76,10 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
pgtable_t pte_page)
{
- pmd_set(pmd, (unsigned long)page_address(pte_page));
+ pmd_set(pmd, (unsigned long)pte_page);
}
-#define pmd_pgtable(pmd) pmd_page(pmd)
+#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
@@ -92,44 +92,35 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
}
+pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
{
- return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+ return (pte_t *)pte_fragment_alloc(mm, 1);
}
static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
{
- struct page *page;
- pte_t *pte;
-
- pte = (pte_t *)__get_free_page(GFP_KERNEL | __GFP_ZERO | __GFP_ACCOUNT);
- if (!pte)
- return NULL;
- page = virt_to_page(pte);
- if (!pgtable_page_ctor(page)) {
- __free_page(page);
- return NULL;
- }
- return page;
+ return (pgtable_t)pte_fragment_alloc(mm, 0);
}
+void pte_frag_destroy(void *pte_frag);
+void pte_fragment_free(unsigned long *table, int kernel);
+
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
{
- free_page((unsigned long)pte);
+ pte_fragment_free((unsigned long *)pte, 1);
}
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
{
- pgtable_page_dtor(ptepage);
- __free_page(ptepage);
+ pte_fragment_free((unsigned long *)ptepage, 0);
}
static inline void pgtable_free(void *table, int shift)
{
if (!shift) {
- pgtable_page_dtor(virt_to_page(table));
- free_page((unsigned long)table);
+ pte_fragment_free((unsigned long *)table, 0);
} else {
BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
kmem_cache_free(PGT_CACHE(shift), table);
@@ -166,7 +157,7 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
tlb_flush_pgtable(tlb, address);
- pgtable_free_tlb(tlb, page_address(table), 0);
+ pgtable_free_tlb(tlb, table, 0);
}
#define __pmd_free_tlb(tlb, pmd, addr) \
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 3c1bd9fa23cd..138c772d58d1 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -9,6 +9,7 @@ CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
obj-y := fault.o mem.o pgtable.o mmap.o \
init_$(BITS).o pgtable_$(BITS).o \
+ pgtable-frag.o \
init-common.o mmu_context.o drmem.o
obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \
tlb_nohash_low.o
@@ -17,8 +18,7 @@ hash64-$(CONFIG_PPC_NATIVE) := hash_native_64.o
obj-$(CONFIG_PPC_BOOK3E_64) += pgtable-book3e.o
obj-$(CONFIG_PPC_BOOK3S_64) += pgtable-hash64.o hash_utils_64.o slb.o \
$(hash64-y) mmu_context_book3s64.o \
- pgtable-book3s64.o pgtable-frag.o
-obj-$(CONFIG_PPC32) += pgtable-frag.o
+ pgtable-book3s64.o
obj-$(CONFIG_PPC_RADIX_MMU) += pgtable-radix.o tlb-radix.o
obj-$(CONFIG_PPC_BOOK3S_32) += ppc_mmu_32.o hash_low_32.o mmu_context_hash32.o
obj-$(CONFIG_PPC_BOOK3S) += tlb_hash$(BITS).o
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index bb52320b7369..6b049d82b98a 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -98,7 +98,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
switch_mmu_context(prev, next, tsk);
}
-#ifdef CONFIG_PPC32
+#ifndef CONFIG_PPC_BOOK3S_64
void arch_exit_mmap(struct mm_struct *mm)
{
void *frag = pte_frag_get(&mm->context);
--
2.13.3
^ permalink raw reply related
* [PATCH v1 01/15] powerpc/mm: drop __bad_pte()
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
This has never been called (since Kernel has been in git at least),
drop it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgalloc.h | 2 --
arch/powerpc/include/asm/nohash/32/pgalloc.h | 2 --
2 files changed, 4 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 3633502e102c..645af86cd072 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -22,8 +22,6 @@
*/
#define MAX_PGTABLE_INDEX_SIZE 0xf
-extern void __bad_pte(pmd_t *pmd);
-
extern struct kmem_cache *pgtable_cache[];
#define PGT_CACHE(shift) pgtable_cache[shift]
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index bd186e85b4f7..ea265a578eb0 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -22,8 +22,6 @@
*/
#define MAX_PGTABLE_INDEX_SIZE 0xf
-extern void __bad_pte(pmd_t *pmd);
-
extern struct kmem_cache *pgtable_cache[];
#define PGT_CACHE(shift) pgtable_cache[shift]
--
2.13.3
^ permalink raw reply related
* [PATCH v1 07/15] powerpc/book3e: move early_alloc_pgtable() to init section
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
early_alloc_pgtable() is only used during init.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/pgtable-book3e.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/mm/pgtable-book3e.c b/arch/powerpc/mm/pgtable-book3e.c
index 1032ef7aaf62..f6fc709697ee 100644
--- a/arch/powerpc/mm/pgtable-book3e.c
+++ b/arch/powerpc/mm/pgtable-book3e.c
@@ -55,7 +55,7 @@ void vmemmap_remove_mapping(unsigned long start,
#endif
#endif /* CONFIG_SPARSEMEM_VMEMMAP */
-static __ref void *early_alloc_pgtable(unsigned long size)
+static void __init *early_alloc_pgtable(unsigned long size)
{
void *ptr;
@@ -74,7 +74,7 @@ static __ref void *early_alloc_pgtable(unsigned long size)
* map_kernel_page adds an entry to the ioremap page table
* and adds an entry to the HPT, possibly bolting it
*/
-int map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
+int __ref map_kernel_page(unsigned long ea, unsigned long pa, pgprot_t prot)
{
pgd_t *pgdp;
pud_t *pudp;
--
2.13.3
^ permalink raw reply related
* [PATCH v1 06/15] powerpc/Kconfig: select PPC_MM_SLICES from subarch type
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
Lets select PPC_MM_SLICES from the subarch config item instead of
doing it via defaults declaration in the PPC_MM_SLICES item itself.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/platforms/Kconfig.cputype | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 842b2c7e156a..a46a0adb634d 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -34,6 +34,7 @@ config PPC_8xx
bool "Freescale 8xx"
select FSL_SOC
select SYS_SUPPORTS_HUGETLBFS
+ select PPC_MM_SLICES if HUGETLB_PAGE
config 40x
bool "AMCC 40x"
@@ -75,6 +76,7 @@ config PPC_BOOK3S_64
select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE
select ARCH_SUPPORTS_NUMA_BALANCING
select IRQ_WORK
+ select PPC_MM_SLICES
config PPC_BOOK3E_64
bool "Embedded processors"
@@ -360,8 +362,6 @@ config PPC_BOOK3E_MMU
config PPC_MM_SLICES
bool
- default y if PPC_BOOK3S_64
- default y if PPC_8xx && HUGETLB_PAGE
config PPC_HAVE_PMU_SUPPORT
bool
--
2.13.3
^ permalink raw reply related
* [PATCH v1 05/15] powerpc/mm: get rid of nohash/32/mmu.h and nohash/64/mmu.h
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
Those files have no real added values, especially the 64 bit
which only includes the common book3e mmu.h which is also
included from 32 bits side.
So lets do the final inclusion directly from nohash/mmu.h
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/32/mmu.h | 19 -------------------
arch/powerpc/include/asm/nohash/64/mmu.h | 8 --------
arch/powerpc/include/asm/nohash/mmu.h | 16 ++++++++++++----
3 files changed, 12 insertions(+), 31 deletions(-)
delete mode 100644 arch/powerpc/include/asm/nohash/32/mmu.h
delete mode 100644 arch/powerpc/include/asm/nohash/64/mmu.h
diff --git a/arch/powerpc/include/asm/nohash/32/mmu.h b/arch/powerpc/include/asm/nohash/32/mmu.h
deleted file mode 100644
index af0e8b54876a..000000000000
--- a/arch/powerpc/include/asm/nohash/32/mmu.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_32_MMU_H_
-#define _ASM_POWERPC_NOHASH_32_MMU_H_
-
-#if defined(CONFIG_40x)
-/* 40x-style software loaded TLB */
-#include <asm/nohash/32/mmu-40x.h>
-#elif defined(CONFIG_44x)
-/* 44x-style software loaded TLB */
-#include <asm/nohash/32/mmu-44x.h>
-#elif defined(CONFIG_PPC_BOOK3E_MMU)
-/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
-#include <asm/nohash/mmu-book3e.h>
-#elif defined (CONFIG_PPC_8xx)
-/* Motorola/Freescale 8xx software loaded TLB */
-#include <asm/nohash/32/mmu-8xx.h>
-#endif
-
-#endif /* _ASM_POWERPC_NOHASH_32_MMU_H_ */
diff --git a/arch/powerpc/include/asm/nohash/64/mmu.h b/arch/powerpc/include/asm/nohash/64/mmu.h
deleted file mode 100644
index 87871d027b75..000000000000
--- a/arch/powerpc/include/asm/nohash/64/mmu.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_NOHASH_64_MMU_H_
-#define _ASM_POWERPC_NOHASH_64_MMU_H_
-
-/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
-#include <asm/nohash/mmu-book3e.h>
-
-#endif /* _ASM_POWERPC_NOHASH_64_MMU_H_ */
diff --git a/arch/powerpc/include/asm/nohash/mmu.h b/arch/powerpc/include/asm/nohash/mmu.h
index a037cb1efb57..edc793e5f08f 100644
--- a/arch/powerpc/include/asm/nohash/mmu.h
+++ b/arch/powerpc/include/asm/nohash/mmu.h
@@ -2,10 +2,18 @@
#ifndef _ASM_POWERPC_NOHASH_MMU_H_
#define _ASM_POWERPC_NOHASH_MMU_H_
-#ifdef CONFIG_PPC64
-#include <asm/nohash/64/mmu.h>
-#else
-#include <asm/nohash/32/mmu.h>
+#if defined(CONFIG_40x)
+/* 40x-style software loaded TLB */
+#include <asm/nohash/32/mmu-40x.h>
+#elif defined(CONFIG_44x)
+/* 44x-style software loaded TLB */
+#include <asm/nohash/32/mmu-44x.h>
+#elif defined(CONFIG_PPC_BOOK3E_MMU)
+/* Freescale Book-E software loaded TLB or Book-3e (ISA 2.06+) MMU */
+#include <asm/nohash/mmu-book3e.h>
+#elif defined (CONFIG_PPC_8xx)
+/* Motorola/Freescale 8xx software loaded TLB */
+#include <asm/nohash/32/mmu-8xx.h>
#endif
#endif /* _ASM_POWERPC_NOHASH_MMU_H_ */
--
2.13.3
^ permalink raw reply related
* [PATCH v1 09/15] powerpc/mm: inline pte_alloc_one_kernel() and pte_alloc_one() on PPC32
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
pte_alloc_one_kernel() and pte_alloc_one() are simple calls to
pte_fragment_alloc(), so they are good candidates for inlining as
already done on PPC64.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgalloc.h | 15 ++++++++++++---
arch/powerpc/include/asm/nohash/32/pgalloc.h | 15 ++++++++++++---
arch/powerpc/mm/pgtable_32.c | 10 ----------
3 files changed, 24 insertions(+), 16 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 645af86cd072..0ed856068bb8 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -59,10 +59,19 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm);
-void pte_frag_destroy(void *pte_frag);
pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+ return (pte_t *)pte_fragment_alloc(mm, 1);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+ return (pgtable_t)pte_fragment_alloc(mm, 0);
+}
+
+void pte_frag_destroy(void *pte_frag);
void pte_fragment_free(unsigned long *table, int kernel);
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index ea265a578eb0..1d41508f0676 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -77,10 +77,19 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
#endif
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm);
-extern pgtable_t pte_alloc_one(struct mm_struct *mm);
-void pte_frag_destroy(void *pte_frag);
pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+ return (pte_t *)pte_fragment_alloc(mm, 1);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+ return (pgtable_t)pte_fragment_alloc(mm, 0);
+}
+
+void pte_frag_destroy(void *pte_frag);
void pte_fragment_free(unsigned long *table, int kernel);
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index a1c3062f0665..d02fe3ce64db 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -43,16 +43,6 @@ EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
extern char etext[], _stext[], _sinittext[], _einittext[];
-pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)pte_fragment_alloc(mm, 1);
-}
-
-pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- return (pgtable_t)pte_fragment_alloc(mm, 0);
-}
-
void __iomem *
ioremap(phys_addr_t addr, unsigned long size)
{
--
2.13.3
^ permalink raw reply related
* [PATCH v1 10/15] powerpc/mm: refactor pte_alloc_one() and pte_free() families definition.
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
Functions pte_alloc_one(), pte_alloc_one_kernel(), pte_free(),
pte_free_kernel() are identical for the four subarches.
This patch moves their definition in a common place.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgalloc.h | 25 -------------------------
arch/powerpc/include/asm/book3s/64/pgalloc.h | 22 ----------------------
arch/powerpc/include/asm/nohash/32/pgalloc.h | 25 -------------------------
arch/powerpc/include/asm/nohash/64/pgalloc.h | 25 -------------------------
arch/powerpc/include/asm/pgalloc.h | 25 +++++++++++++++++++++++++
5 files changed, 25 insertions(+), 97 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 0ed856068bb8..46422309d6e0 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -59,31 +59,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)pte_fragment_alloc(mm, 1);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- return (pgtable_t)pte_fragment_alloc(mm, 0);
-}
-
-void pte_frag_destroy(void *pte_frag);
-void pte_fragment_free(unsigned long *table, int kernel);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- pte_fragment_free((unsigned long *)pte, 1);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
- pte_fragment_free((unsigned long *)ptepage, 0);
-}
-
static inline void pgtable_free(void *table, unsigned index_size)
{
if (!index_size) {
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index 138bc2ecc0c4..cfd48d8cc055 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -39,9 +39,7 @@ extern struct vmemmap_backing *vmemmap_list;
extern struct kmem_cache *pgtable_cache[];
#define PGT_CACHE(shift) pgtable_cache[shift]
-extern pte_t *pte_fragment_alloc(struct mm_struct *, int);
extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
-extern void pte_fragment_free(unsigned long *, int);
extern void pmd_fragment_free(unsigned long *);
extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
#ifdef CONFIG_SMP
@@ -190,26 +188,6 @@ static inline pgtable_t pmd_pgtable(pmd_t pmd)
return (pgtable_t)pmd_page_vaddr(pmd);
}
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)pte_fragment_alloc(mm, 1);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- return (pgtable_t)pte_fragment_alloc(mm, 0);
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- pte_fragment_free((unsigned long *)pte, 1);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
- pte_fragment_free((unsigned long *)ptepage, 0);
-}
-
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 1d41508f0676..e96ef2fde2ca 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -77,31 +77,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
#endif
-pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)pte_fragment_alloc(mm, 1);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- return (pgtable_t)pte_fragment_alloc(mm, 0);
-}
-
-void pte_frag_destroy(void *pte_frag);
-void pte_fragment_free(unsigned long *table, int kernel);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- pte_fragment_free((unsigned long *)pte, 1);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
- pte_fragment_free((unsigned long *)ptepage, 0);
-}
-
static inline void pgtable_free(void *table, unsigned index_size)
{
if (!index_size) {
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 7fb87235f845..98de4f3b0306 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -92,31 +92,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
}
-pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
-
-static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
-{
- return (pte_t *)pte_fragment_alloc(mm, 1);
-}
-
-static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
-{
- return (pgtable_t)pte_fragment_alloc(mm, 0);
-}
-
-void pte_frag_destroy(void *pte_frag);
-void pte_fragment_free(unsigned long *table, int kernel);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
- pte_fragment_free((unsigned long *)pte, 1);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
-{
- pte_fragment_free((unsigned long *)ptepage, 0);
-}
-
static inline void pgtable_free(void *table, int shift)
{
if (!shift) {
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index e11f03007b57..c2c6fd438840 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -20,6 +20,31 @@ static inline gfp_t pgtable_gfp_flags(struct mm_struct *mm, gfp_t gfp)
#define PGALLOC_GFP (GFP_KERNEL | __GFP_ZERO)
+pte_t *pte_fragment_alloc(struct mm_struct *mm, int kernel);
+
+static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+{
+ return (pte_t *)pte_fragment_alloc(mm, 1);
+}
+
+static inline pgtable_t pte_alloc_one(struct mm_struct *mm)
+{
+ return (pgtable_t)pte_fragment_alloc(mm, 0);
+}
+
+void pte_frag_destroy(void *pte_frag);
+void pte_fragment_free(unsigned long *table, int kernel);
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+ pte_fragment_free((unsigned long *)pte, 1);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
+{
+ pte_fragment_free((unsigned long *)ptepage, 0);
+}
+
#ifdef CONFIG_PPC_BOOK3S
#include <asm/book3s/pgalloc.h>
#else
--
2.13.3
^ permalink raw reply related
* [PATCH v1 08/15] powerpc/mm: don't use pte_alloc_kernel() until slab is available on PPC32
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
In the same way as PPC64, implement early allocation functions and
avoid calling pte_alloc_kernel() before slab is available.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/mm/pgtable_32.c | 34 ++++++++++++++++++++++++++++------
1 file changed, 28 insertions(+), 6 deletions(-)
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 6e56a6240bfa..a1c3062f0665 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -43,11 +43,8 @@ EXPORT_SYMBOL(ioremap_bot); /* aka VMALLOC_END */
extern char etext[], _stext[], _sinittext[], _einittext[];
-__ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
+pte_t *pte_alloc_one_kernel(struct mm_struct *mm)
{
- if (!slab_is_available())
- return memblock_alloc(PTE_FRAG_SIZE, PTE_FRAG_SIZE);
-
return (pte_t *)pte_fragment_alloc(mm, 1);
}
@@ -205,7 +202,29 @@ void iounmap(volatile void __iomem *addr)
}
EXPORT_SYMBOL(iounmap);
-int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
+static void __init *early_alloc_pgtable(unsigned long size)
+{
+ void *ptr = memblock_alloc(size, size);
+
+ if (!ptr)
+ panic("%s: Failed to allocate %lu bytes align=0x%lx\n",
+ __func__, size, size);
+
+ return ptr;
+}
+
+static pte_t __init *early_pte_alloc_kernel(pmd_t *pmdp, unsigned long va)
+{
+ if (pmd_none(*pmdp)) {
+ pte_t *ptep = early_alloc_pgtable(PTE_FRAG_SIZE);
+
+ pmd_populate_kernel(&init_mm, pmdp, ptep);
+ }
+ return pte_offset_kernel(pmdp, va);
+}
+
+
+int __ref map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
{
pmd_t *pd;
pte_t *pg;
@@ -214,7 +233,10 @@ int map_kernel_page(unsigned long va, phys_addr_t pa, pgprot_t prot)
/* Use upper 10 bits of VA to index the first level map */
pd = pmd_offset(pud_offset(pgd_offset_k(va), va), va);
/* Use middle 10 bits of VA to index the second-level map */
- pg = pte_alloc_kernel(pd, va);
+ if (likely(slab_is_available()))
+ pg = pte_alloc_kernel(pd, va);
+ else
+ pg = early_pte_alloc_kernel(pd, va);
if (pg != 0) {
err = 0;
/* The PTE should never be already set nor present in the
--
2.13.3
^ permalink raw reply related
* [PATCH v1 11/15] powerpc/mm: refactor definition of pgtable_cache[]
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
pgtable_cache[] is the same for the 4 subarches, lets make it common.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgalloc.h | 21 ---------------------
arch/powerpc/include/asm/book3s/64/pgalloc.h | 22 ----------------------
arch/powerpc/include/asm/nohash/32/pgalloc.h | 21 ---------------------
arch/powerpc/include/asm/nohash/64/pgalloc.h | 22 ----------------------
arch/powerpc/include/asm/pgalloc.h | 21 +++++++++++++++++++++
5 files changed, 21 insertions(+), 86 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 46422309d6e0..1b9b5c228230 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -5,26 +5,6 @@
#include <linux/threads.h>
#include <linux/slab.h>
-/*
- * Functions that deal with pagetables that could be at any level of
- * the table need to be passed an "index_size" so they know how to
- * handle allocation. For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer. In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value. This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE 0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) pgtable_cache[shift]
-
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
@@ -69,7 +49,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
}
}
-#define check_pgt_cache() do { } while (0)
#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index cfd48d8cc055..df2dce6afe14 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -19,26 +19,6 @@ struct vmemmap_backing {
};
extern struct vmemmap_backing *vmemmap_list;
-/*
- * Functions that deal with pagetables that could be at any level of
- * the table need to be passed an "index_size" so they know how to
- * handle allocation. For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer. In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value. This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE 0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) pgtable_cache[shift]
-
extern pmd_t *pmd_fragment_alloc(struct mm_struct *, unsigned long);
extern void pmd_fragment_free(unsigned long *);
extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift);
@@ -199,8 +179,6 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
pgtable_free_tlb(tlb, table, PTE_INDEX);
}
-#define check_pgt_cache() do { } while (0)
-
extern atomic_long_t direct_pages_count[MMU_PAGE_COUNT];
static inline void update_page_count(int psize, long count)
{
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index e96ef2fde2ca..4615801aa953 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -5,26 +5,6 @@
#include <linux/threads.h>
#include <linux/slab.h>
-/*
- * Functions that deal with pagetables that could be at any level of
- * the table need to be passed an "index_size" so they know how to
- * handle allocation. For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer. In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value. This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE 0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) pgtable_cache[shift]
-
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
@@ -87,7 +67,6 @@ static inline void pgtable_free(void *table, unsigned index_size)
}
}
-#define check_pgt_cache() do { } while (0)
#define get_hugepd_cache_index(x) (x)
#ifdef CONFIG_SMP
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 98de4f3b0306..ffc86d42816d 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -18,26 +18,6 @@ struct vmemmap_backing {
};
extern struct vmemmap_backing *vmemmap_list;
-/*
- * Functions that deal with pagetables that could be at any level of
- * the table need to be passed an "index_size" so they know how to
- * handle allocation. For PTE pages (which are linked to a struct
- * page for now, and drawn from the main get_free_pages() pool), the
- * allocation size will be (2^index_size * sizeof(pointer)) and
- * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
- *
- * The maximum index size needs to be big enough to allow any
- * pagetable sizes we need, but small enough to fit in the low bits of
- * any page table pointer. In other words all pagetables, even tiny
- * ones, must be aligned to allow at least enough low 0 bits to
- * contain this value. This value is also used as a mask, so it must
- * be one less than a power of two.
- */
-#define MAX_PGTABLE_INDEX_SIZE 0xf
-
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) pgtable_cache[shift]
-
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
{
return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
@@ -140,6 +120,4 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
#define __pud_free_tlb(tlb, pud, addr) \
pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
-#define check_pgt_cache() do { } while (0)
-
#endif /* _ASM_POWERPC_PGALLOC_64_H */
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index c2c6fd438840..5761bee0f004 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -45,6 +45,27 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
pte_fragment_free((unsigned long *)ptepage, 0);
}
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation. For PTE pages, the allocation size will be
+ * (2^index_size * sizeof(pointer)) and allocations are drawn from
+ * the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer. In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value. This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE 0xf
+
+extern struct kmem_cache *pgtable_cache[];
+#define PGT_CACHE(shift) pgtable_cache[shift]
+
+static inline void check_pgt_cache(void) { }
+
#ifdef CONFIG_PPC_BOOK3S
#include <asm/book3s/pgalloc.h>
#else
--
2.13.3
^ permalink raw reply related
* [PATCH v1 12/15] powerpc/mm: Only keep one version of pmd_populate() functions on nohash/32
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
Use IS_ENABLED(CONFIG_BOOKE) to make single versions of
pmd_populate() and pmd_populate_kernel()
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/32/pgalloc.h | 28 ++++++++--------------------
1 file changed, 8 insertions(+), 20 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 4615801aa953..7ee8e27070f4 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -25,37 +25,25 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
#define __pmd_free_tlb(tlb,x,a) do { } while (0)
/* #define pgd_populate(mm, pmd, pte) BUG() */
-#ifndef CONFIG_BOOKE
-
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
pte_t *pte)
{
- *pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
+ if (IS_ENABLED(CONFIG_BOOKE))
+ *pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
+ else
+ *pmdp = __pmd(__pa(pte) | _PMD_PRESENT);
}
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
pgtable_t pte_page)
{
- *pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT);
+ if (IS_ENABLED(CONFIG_BOOKE))
+ *pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT);
+ else
+ *pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT);
}
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-#else
-
-static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp,
- pte_t *pte)
-{
- *pmdp = __pmd((unsigned long)pte | _PMD_PRESENT);
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
- pgtable_t pte_page)
-{
- *pmdp = __pmd((unsigned long)pte_page | _PMD_PRESENT);
-}
-
-#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-#endif
static inline void pgtable_free(void *table, unsigned index_size)
{
--
2.13.3
^ permalink raw reply related
* [PATCH v1 13/15] powerpc/mm: refactor pgtable freeing functions on nohash
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
pgtable_free() and others are identical on nohash/32 and 64,
so move them into asm/nohash/pgalloc.h
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/32/pgalloc.h | 43 ---------------------------
arch/powerpc/include/asm/nohash/64/pgalloc.h | 43 ---------------------------
arch/powerpc/include/asm/nohash/pgalloc.h | 44 ++++++++++++++++++++++++++++
3 files changed, 44 insertions(+), 86 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 7ee8e27070f4..6c0f5151dc1d 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -45,47 +45,4 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-static inline void pgtable_free(void *table, unsigned index_size)
-{
- if (!index_size) {
- pte_fragment_free((unsigned long *)table, 0);
- } else {
- BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
- kmem_cache_free(PGT_CACHE(index_size), table);
- }
-}
-
-#define get_hugepd_cache_index(x) (x)
-
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
- void *table, int shift)
-{
- unsigned long pgf = (unsigned long)table;
- BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
- pgf |= shift;
- tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
- void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
- unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
- pgtable_free(table, shift);
-}
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb,
- void *table, int shift)
-{
- pgtable_free(table, shift);
-}
-#endif
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
- unsigned long address)
-{
- tlb_flush_pgtable(tlb, address);
- pgtable_free_tlb(tlb, table, 0);
-}
#endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index ffc86d42816d..c636feced1ff 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -72,49 +72,6 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
kmem_cache_free(PGT_CACHE(PMD_CACHE_INDEX), pmd);
}
-static inline void pgtable_free(void *table, int shift)
-{
- if (!shift) {
- pte_fragment_free((unsigned long *)table, 0);
- } else {
- BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
- kmem_cache_free(PGT_CACHE(shift), table);
- }
-}
-
-#define get_hugepd_cache_index(x) (x)
-#ifdef CONFIG_SMP
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
- unsigned long pgf = (unsigned long)table;
-
- BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
- pgf |= shift;
- tlb_remove_table(tlb, (void *)pgf);
-}
-
-static inline void __tlb_remove_table(void *_table)
-{
- void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
- unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
-
- pgtable_free(table, shift);
-}
-
-#else
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
-{
- pgtable_free(table, shift);
-}
-#endif
-
-static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
- unsigned long address)
-{
- tlb_flush_pgtable(tlb, address);
- pgtable_free_tlb(tlb, table, 0);
-}
-
#define __pmd_free_tlb(tlb, pmd, addr) \
pgtable_free_tlb(tlb, pmd, PMD_CACHE_INDEX)
#define __pud_free_tlb(tlb, pud, addr) \
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 0634f2949438..4fccac6af3ad 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -21,4 +21,48 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
#else
#include <asm/nohash/32/pgalloc.h>
#endif
+
+static inline void pgtable_free(void *table, int shift)
+{
+ if (!shift) {
+ pte_fragment_free((unsigned long *)table, 0);
+ } else {
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ kmem_cache_free(PGT_CACHE(shift), table);
+ }
+}
+
+#define get_hugepd_cache_index(x) (x)
+
+#ifdef CONFIG_SMP
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+ unsigned long pgf = (unsigned long)table;
+
+ BUG_ON(shift > MAX_PGTABLE_INDEX_SIZE);
+ pgf |= shift;
+ tlb_remove_table(tlb, (void *)pgf);
+}
+
+static inline void __tlb_remove_table(void *_table)
+{
+ void *table = (void *)((unsigned long)_table & ~MAX_PGTABLE_INDEX_SIZE);
+ unsigned shift = (unsigned long)_table & MAX_PGTABLE_INDEX_SIZE;
+
+ pgtable_free(table, shift);
+}
+
+#else
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, int shift)
+{
+ pgtable_free(table, shift);
+}
+#endif
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
+ unsigned long address)
+{
+ tlb_flush_pgtable(tlb, address);
+ pgtable_free_tlb(tlb, table, 0);
+}
#endif /* _ASM_POWERPC_NOHASH_PGALLOC_H */
--
2.13.3
^ permalink raw reply related
* [PATCH v1 14/15] powerpc/mm: refactor pmd_pgtable()
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
pmd_pgtable() is identical on the 4 subarches, refactor it.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/book3s/32/pgalloc.h | 2 --
arch/powerpc/include/asm/book3s/64/pgalloc.h | 5 -----
arch/powerpc/include/asm/nohash/32/pgalloc.h | 2 --
arch/powerpc/include/asm/nohash/64/pgalloc.h | 2 --
arch/powerpc/include/asm/pgalloc.h | 5 +++++
5 files changed, 5 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index 1b9b5c228230..998317702630 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -37,8 +37,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
*pmdp = __pmd(__pa(pte_page) | _PMD_PRESENT);
}
-#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-
static inline void pgtable_free(void *table, unsigned index_size)
{
if (!index_size) {
diff --git a/arch/powerpc/include/asm/book3s/64/pgalloc.h b/arch/powerpc/include/asm/book3s/64/pgalloc.h
index df2dce6afe14..053a7940504e 100644
--- a/arch/powerpc/include/asm/book3s/64/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/64/pgalloc.h
@@ -163,11 +163,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
*pmd = __pmd(__pgtable_ptr_val(pte_page) | PMD_VAL_BITS);
}
-static inline pgtable_t pmd_pgtable(pmd_t pmd)
-{
- return (pgtable_t)pmd_page_vaddr(pmd);
-}
-
static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
unsigned long address)
{
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 6c0f5151dc1d..137761b01588 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -43,6 +43,4 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmdp,
*pmdp = __pmd(__pa(pte_page) | _PMD_USER | _PMD_PRESENT);
}
-#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-
#endif /* _ASM_POWERPC_PGALLOC_32_H */
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index c636feced1ff..5a0ea63c77c7 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -59,8 +59,6 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
pmd_set(pmd, (unsigned long)pte_page);
}
-#define pmd_pgtable(pmd) ((pgtable_t)pmd_page_vaddr(pmd))
-
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
{
return kmem_cache_alloc(PGT_CACHE(PMD_CACHE_INDEX),
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index 5761bee0f004..2b2c60a1a66d 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -72,4 +72,9 @@ static inline void check_pgt_cache(void) { }
#include <asm/nohash/pgalloc.h>
#endif
+static inline pgtable_t pmd_pgtable(pmd_t pmd)
+{
+ return (pgtable_t)pmd_page_vaddr(pmd);
+}
+
#endif /* _ASM_POWERPC_PGALLOC_H */
--
2.13.3
^ permalink raw reply related
* [PATCH v1 15/15] powerpc/mm: refactor pgd_alloc() and pgd_free() on nohash
From: Christophe Leroy @ 2019-04-03 20:06 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman,
aneesh.kumar
Cc: linuxppc-dev, linux-kernel
In-Reply-To: <cover.1554321743.git.christophe.leroy@c-s.fr>
pgd_alloc() and pgd_free() are identical on nohash 32 and 64.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
---
arch/powerpc/include/asm/nohash/32/pgalloc.h | 11 -----------
arch/powerpc/include/asm/nohash/64/pgalloc.h | 11 -----------
arch/powerpc/include/asm/nohash/pgalloc.h | 12 ++++++++++++
3 files changed, 12 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 137761b01588..11eac371e7e0 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -5,17 +5,6 @@
#include <linux/threads.h>
#include <linux/slab.h>
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
- pgtable_gfp_flags(mm, GFP_KERNEL));
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
- kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
-
/*
* We don't have any real pmd's, and this code never triggers because
* the pgd will always be present..
diff --git a/arch/powerpc/include/asm/nohash/64/pgalloc.h b/arch/powerpc/include/asm/nohash/64/pgalloc.h
index 5a0ea63c77c7..62321cd12da9 100644
--- a/arch/powerpc/include/asm/nohash/64/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/64/pgalloc.h
@@ -18,17 +18,6 @@ struct vmemmap_backing {
};
extern struct vmemmap_backing *vmemmap_list;
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
- return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
- pgtable_gfp_flags(mm, GFP_KERNEL));
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
- kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
-
#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, (unsigned long)PUD)
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
diff --git a/arch/powerpc/include/asm/nohash/pgalloc.h b/arch/powerpc/include/asm/nohash/pgalloc.h
index 4fccac6af3ad..332b13b4ecdb 100644
--- a/arch/powerpc/include/asm/nohash/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/pgalloc.h
@@ -3,6 +3,7 @@
#define _ASM_POWERPC_NOHASH_PGALLOC_H
#include <linux/mm.h>
+#include <linux/slab.h>
extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
#ifdef CONFIG_PPC64
@@ -16,6 +17,17 @@ static inline void tlb_flush_pgtable(struct mmu_gather *tlb,
}
#endif /* !CONFIG_PPC_BOOK3E */
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+ return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE),
+ pgtable_gfp_flags(mm, GFP_KERNEL));
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+ kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
+}
+
#ifdef CONFIG_PPC64
#include <asm/nohash/64/pgalloc.h>
#else
--
2.13.3
^ permalink raw reply related
* Re: [PATCH] powerpc: config: skiroot: Add (back) MLX5 ethernet support
From: Stewart Smith @ 2019-04-03 20:53 UTC (permalink / raw)
To: Mathieu Malaterre, Joel Stanley; +Cc: Carol L Soto, linuxppc-dev
In-Reply-To: <CA+7wUsymTA6XO21KRdwD9Pouv1e8w6VUKSA2wbaPHN7Bz215rw@mail.gmail.com>
Mathieu Malaterre <malat@debian.org> writes:
> On Wed, Apr 3, 2019 at 2:51 AM Joel Stanley <joel@jms.id.au> wrote:
>>
>> It turns out that some defconfig changes and kernel config option
>> changes meant we accidentally dropped Ethernet support for Mellanox CLX5
>> cards.
>>
>> Reported-by: Carol L Soto <clsoto@us.ibm.com>
>> Suggested-by: Carol L Soto <clsoto@us.ibm.com>
>> Signed-off-by: Stewart Smith <stewart@linux.ibm.com>
>> Signed-off-by: Joel Stanley <joel@jms.id.au>
>
> Fixes: cbc39809a398 ("powerpc/configs: Update skiroot defconfig")
>
> ?
Yes.
--
Stewart Smith
OPAL Architect, IBM.
^ permalink raw reply
* Re: [PATCH 0/4] Enabling secure boot on PowerNV systems
From: Claudio Carvalho @ 2019-04-03 21:48 UTC (permalink / raw)
To: Michael Ellerman, linuxppc-dev, linux-efi, linux-integrity,
linux-kernel
Cc: Ard Biesheuvel, Nayna Jain, Matthew Garret, Paul Mackerras,
Jeremy Kerr
In-Reply-To: <87r2aj1ayf.fsf@concordia.ellerman.id.au>
On 4/3/19 10:21 AM, Michael Ellerman wrote:
> Hi Claudio,
>
> Thanks for posting this.
>
> Claudio Carvalho <cclaudio@linux.ibm.com> writes:
>> This patch set is part of a series that implements secure boot on
>> PowerNV systems.
>>
>> In order to verify the OS kernel on PowerNV, secure boot requires X.509
>> certificates trusted by the platform, the secure boot modes, and several
>> other pieces of information. These are stored in secure variables
>> controlled by OPAL, also known as OPAL secure variables.
>>
>> This patch set adds the following features:
>>
>> 1. Enable efivarfs by selecting CONFIG_EFI in the CONFIG_OPAL_SECVAR
>> introduced in this patch set. With CONFIG_EFIVAR_FS, userspace tools can
>> be used to manage the secure variables.
>> 2. Add support for OPAL secure variables by overwriting the EFI hooks
>> (get_variable, get_next_variable, set_variable and query_variable_info)
>> with OPAL call wrappers. There is probably a better way to add this
>> support, for example, we are investigating if we could register the
>> efivar_operations rather than overwriting the EFI hooks. In this patch
>> set, CONFIG_OPAL_SECVAR selects CONFIG_EFI. If, instead, we registered
>> efivar_operations, CONFIG_EFIVAR_FS would need to depend on
>> CONFIG_EFI|| CONFIG_OPAL_SECVAR. Comments or suggestions on the
>> preferred technique would be greatly appreciated.
> I am *very* reluctant to start selecting CONFIG_EFI on powerpc.
>
> Simply because we don't actually have EFI, and I worry we're going to
> both break assumptions in the EFI code as well as impose requirements on
> the powerpc code that aren't really necessary.
Yes, we agree. We are working on the v2 and it is not going to depend on
CONFIG_EFI. Rather, the IMA arch policies will make the OPAL calls directly.
>
> So I'd definitely prefer we go the route of enabling efivarfs with an
> alternate backend.
Right, I'm investigating how we can do that, but it looks like we should
post that as a separate patchset to avoid delaying upstreaming signature
verification based on the secure boot variables.
Thanks,
Claudio
>
> Better still would be a generic secure variable interface as Matt
> suggests, if the userspace tools can be relatively easily adapted to use
> that interface.
>
> cheers
>
^ permalink raw reply
* Re: [PATCH 0/4] Enabling secure boot on PowerNV systems
From: Matthew Garrett @ 2019-04-03 22:27 UTC (permalink / raw)
To: Claudio Carvalho
Cc: linux-efi, Ard Biesheuvel, Nayna Jain, Linux Kernel Mailing List,
Matthew Garret, linuxppc-dev, Paul Mackerras, Jeremy Kerr,
linux-integrity
In-Reply-To: <2208f156-d441-3082-2f4c-8030c84ef788@linux.ibm.com>
On Tue, Apr 2, 2019 at 4:31 PM Claudio Carvalho <cclaudio@linux.ibm.com> wrote:
>
>
> On 4/2/19 6:51 PM, Matthew Garrett wrote:
> > So you implement the full PK/KEK/db/dbx/dbt infrastructure, and
> > updates are signed in the same way?
>
> For the first version, our firmware will implement a simplistic PK, KEK and
> db infrastructure (without dbx and dbt) where only the Setup and User modes
> will be supported.
Not supporting dbx seems like a pretty significant shortcoming. How
are signatures meant to be revoked?
> PK, KEK and db updates will be signed the same way, that is, using
> userspace tooling like efitools in PowerNV. As for the authentication
> descriptors, only the EFI_VARIABLE_AUTHENTICATION_2 descriptor will be
> supported.
Is this API documented?
> > In that case we might be better off with a generic interface for this
> > purpose that we can expose on all platforms that implement a secure
> > boot key hierarchy. Having an efivarfs that doesn't allow the creation
> > of arbitrary attributes may break other existing userland
> > expectations.
> >
> For what it's worth, gsmi uses the efivars infrastructure for EFI-like
> variables.
My recollection is that at the time the Chromebook firmware still had
EFI underpinnings and the gsmi code was largely just an alternate
mechanism for calling into something that was fundamentally the EFI
variable store. With hindsight I don't think layering this was the
right move - we've adjusted the semantics of efivarfs on more than one
occasion to deal with the behaviour of real-world EFI platforms, and I
don't think it's helpful to end up in a situation where we're trying
to keep behaviour consistent among entirely different firmware
interfaces.
> What might a generic interface look like? It would have to work for
> existing secure boot solutions - including EFI - which would seem to imply
> changes to userspace tools.
I think that depends on exactly what problem you're trying to solve.
Some aspects of the EFI secure boot design end up mirroring the
economics of the PC ecosystem rather than being inherently good design
goals, so it'd be helpful to know whether you're taking this solution
because you want the same three-level key infrastructure or because
that just leaves you compatible with the tooling.
^ permalink raw reply
* [PATCH] powerpc/powernv: Add mmap to opal export sysfs nodes
From: Jordan Niethe @ 2019-04-03 22:34 UTC (permalink / raw)
To: linuxppc-dev; +Cc: Jordan Niethe
The sysfs nodes created under /opal/exports/ do not currently support
mmap. Skiboot trace buffers are exported here with in the series
https://patchwork.ozlabs.org/cover/1073501/. Adding mmap support makes
it possible to use the functions for reading traces in external/trace.
This improves on the current read/lseek method as it handles cases like
the buffer wrapping and overflowing.
Signed-off-by: Jordan Niethe <jniethe5@gmail.com>
---
v2: ensure only whole pages can be mapped
---
arch/powerpc/platforms/powernv/opal.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 2b0eca104f86..3611b5b9c5d2 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -714,6 +714,15 @@ static ssize_t export_attr_read(struct file *fp, struct kobject *kobj,
bin_attr->size);
}
+static int export_attr_mmap(struct file *fp, struct kobject *kobj,
+ struct bin_attribute *attr,
+ struct vm_area_struct *vma)
+{
+ return remap_pfn_range(vma, vma->vm_start,
+ __pa(attr->private) >> PAGE_SHIFT,
+ attr->size, PAGE_READONLY);
+}
+
/*
* opal_export_attrs: creates a sysfs node for each property listed in
* the device-tree under /ibm,opal/firmware/exports/
@@ -759,6 +768,9 @@ static void opal_export_attrs(void)
attr->attr.name = kstrdup(prop->name, GFP_KERNEL);
attr->attr.mode = 0400;
attr->read = export_attr_read;
+ /* Ensure only whole pages are mapped */
+ if (vals[0] % PAGE_SIZE == 0 && vals[1] % PAGE_SIZE == 0)
+ attr->mmap = export_attr_mmap;
attr->private = __va(vals[0]);
attr->size = vals[1];
--
2.20.1
^ permalink raw reply related
* Re: [PATCH 5/6 v3] syscalls: Remove start and number from syscall_get_arguments() args
From: Paul Burton @ 2019-04-03 22:51 UTC (permalink / raw)
To: Steven Rostedt
Cc: linux-ia64@vger.kernel.org, Gustavo A. R. Silva, Peter Zijlstra,
Palmer Dabbelt, Dominik Brodowski, Oleg Nesterov, H. Peter Anvin,
sparclinux@vger.kernel.org, linux-riscv@lists.infradead.org,
Ingo Molnar, linux-arch@vger.kernel.org,
linux-s390@vger.kernel.org, linux-c6x-dev@linux-c6x.org,
linux-sh@vger.kernel.org, linux-hexagon@vger.kernel.org,
x86@kernel.org, Ingo Molnar, linux-snps-arc@lists.infradead.org,
Dave Martin, uclinux-h8-devel@lists.sourceforge.jp,
linux-xtensa@linux-xtensa.org, Kees Cook, Roland McGrath,
linux-um@lists.infradead.org, linux-mips@vger.kernel.org,
openrisc@lists.librecores.org, Borislav Petkov, Andy Lutomirski,
Thomas Gleixner, Dmitry V. Levin,
linux-arm-kernel@lists.infradead.org,
linux-parisc@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-kernel@vger.kernel.org, Andy Lutomirski, Eric W. Biederman,
nios2-dev@lists.rocketboards.org, Andrew Morton, Linus Torvalds
In-Reply-To: <20190401134421.278590567@goodmis.org>
Hi Steven,
On Mon, Apr 01, 2019 at 09:41:09AM -0400, Steven Rostedt wrote:
> From: "Steven Rostedt (Red Hat)" <rostedt@goodmis.org>
>
> At Linux Plumbers, Andy Lutomirski approached me and pointed out that the
> function call syscall_get_arguments() implemented in x86 was horribly
> written and not optimized for the standard case of passing in 0 and 6 for
> the starting index and the number of system calls to get. When looking at
> all the users of this function, I discovered that all instances pass in only
> 0 and 6 for these arguments. Instead of having this function handle
> different cases that are never used, simply rewrite it to return the first 6
> arguments of a system call.
>
> This should help out the performance of tracing system calls by ptrace,
> ftrace and perf.
>
> Link: http://lkml.kernel.org/r/20161107213233.754809394@goodmis.org
>
> Cc: Oleg Nesterov <oleg@redhat.com>
> Cc: Thomas Gleixner <tglx@linutronix.de>
> Cc: Kees Cook <keescook@chromium.org>
> Cc: Andy Lutomirski <luto@amacapital.net>
> Cc: Dominik Brodowski <linux@dominikbrodowski.net>
> Cc: Dave Martin <dave.martin@arm.com>
> Cc: "Dmitry V. Levin" <ldv@altlinux.org>
> Cc: x86@kernel.org
> Cc: linux-snps-arc@lists.infradead.org
> Cc: linux-kernel@vger.kernel.org
> Cc: linux-arm-kernel@lists.infradead.org
> Cc: linux-c6x-dev@linux-c6x.org
> Cc: uclinux-h8-devel@lists.sourceforge.jp
> Cc: linux-hexagon@vger.kernel.org
> Cc: linux-ia64@vger.kernel.org
> Cc: linux-mips@vger.kernel.org
> Cc: nios2-dev@lists.rocketboards.org
> Cc: openrisc@lists.librecores.org
> Cc: linux-parisc@vger.kernel.org
> Cc: linuxppc-dev@lists.ozlabs.org
> Cc: linux-riscv@lists.infradead.org
> Cc: linux-s390@vger.kernel.org
> Cc: linux-sh@vger.kernel.org
> Cc: sparclinux@vger.kernel.org
> Cc: linux-um@lists.infradead.org
> Cc: linux-xtensa@linux-xtensa.org
> Cc: linux-arch@vger.kernel.org
> Reported-by: Andy Lutomirski <luto@amacapital.net>
> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Paul Burton <paul.burton@mips.com> # MIPS parts
Thanks,
Paul
^ permalink raw reply
* Re: [PATCH] powerpc/xmon: add read-only mode
From: Andrew Donnellan @ 2019-04-03 23:59 UTC (permalink / raw)
To: Christopher M Riedl, linuxppc-dev
In-Reply-To: <302206558.18553.1554296553840@privateemail.com>
On 4/4/19 12:02 am, Christopher M Riedl wrote:
>
>> On March 29, 2019 at 12:49 AM Andrew Donnellan <andrew.donnellan@au1.ibm.com> wrote:
>>
>>
>> On 29/3/19 3:21 pm, cmr wrote:
>>> Operations which write to memory should be restricted on secure systems
>>> and optionally to avoid self-destructive behaviors.
>>
>> For reference:
>> - https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_linuxppc_issues_issues_219&d=DwICaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=-pHOU8dm1U-U1crivyxKr_-xvZrIBB8YUqvA3el0Ee0&m=zNkGBUKLoTqdSUy_VUpM8VLTEqy7sJfIXpWU-ujc6Rc&s=9jgy61R_p5jvtwOKCMFfnhmJegzCIIomcf4I1BRvBPg&e=
>> - https://urldefense.proofpoint.com/v2/url?u=https-3A__github.com_linuxppc_issues_issues_232&d=DwICaQ&c=jf_iaSHvJObTbx-siA1ZOg&r=-pHOU8dm1U-U1crivyxKr_-xvZrIBB8YUqvA3el0Ee0&m=zNkGBUKLoTqdSUy_VUpM8VLTEqy7sJfIXpWU-ujc6Rc&s=fFYm1ZTaEp6HbeZMV5JEmlbBtDwdehfiW1H3shFoFMM&e=
>>
>> Perhaps clarify what is meant here by "secure systems".
>>
>> Otherwise commit message looks good.
>>
>
> I will reword this for the next patch to reflect the verbiage in the referenced
> github issue -- ie. Secure Boot and not violating secure boot integrity by using xmon.
Sounds good.
>
>>
>>> ---
>>> arch/powerpc/Kconfig.debug | 7 +++++++
>>> arch/powerpc/xmon/xmon.c | 24 ++++++++++++++++++++++++
>>> 2 files changed, 31 insertions(+)
>>>
>>> diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
>>> index 4e00cb0a5464..33cc01adf4cb 100644
>>> --- a/arch/powerpc/Kconfig.debug
>>> +++ b/arch/powerpc/Kconfig.debug
>>> @@ -117,6 +117,13 @@ config XMON_DISASSEMBLY
>>> to say Y here, unless you're building for a memory-constrained
>>> system.
>>>
>>> +config XMON_RO
>>> + bool "Set xmon read-only mode"
>>> + depends on XMON
>>> + default y
>>> + help
>>> + Disable state- and memory-altering write operations in xmon.
>>
>> The meaning of this option is a bit unclear.
>>
>> From the code - it looks like what this option actually does is enable
>> RO mode *by default*. In which case it should probably be called
>> XMON_RO_DEFAULT and the description should note that RW mode can still
>> be enabled via a cmdline option.
>>
>
> Based on Christophe's feedback the default will change for this option in the
> next patch. I will also add the cmdline options to the description for clarity.
>
Yep, adding a description of the cmdline options is also a good idea.
>>
>>> +
>>> config DEBUGGER
>>> bool
>>> depends on KGDB || XMON
>>> diff --git a/arch/powerpc/xmon/xmon.c b/arch/powerpc/xmon/xmon.c
>>> index a0f44f992360..c13ee73cdfd4 100644
>>> --- a/arch/powerpc/xmon/xmon.c
>>> +++ b/arch/powerpc/xmon/xmon.c
>>> @@ -80,6 +80,7 @@ static int set_indicator_token = RTAS_UNKNOWN_SERVICE;
>>> #endif
>>> static unsigned long in_xmon __read_mostly = 0;
>>> static int xmon_on = IS_ENABLED(CONFIG_XMON_DEFAULT);
>>> +static int xmon_ro = IS_ENABLED(CONFIG_XMON_RO);
>>>
>>> static unsigned long adrs;
>>> static int size = 1;
>>> @@ -1042,6 +1043,8 @@ cmds(struct pt_regs *excp)
>>> set_lpp_cmd();
>>> break;
>>> case 'b':
>>> + if (xmon_ro == 1)
>>> + break;
>>
>> For all these cases - it would be much better to print an error message
>> somewhere when we abort due to read-only mode.
>>
>
> I included print messages initially but then thought about how xmon is intended
> for "power" users. I can add print statements to avoid confusion and frustration
> since the operations are just "silently" dropped -- *if* that aligns with xmon's
> "philosophy".
>
Power users often want a straightforward self-explanatory UX more than
anyone :)
--
Andrew Donnellan OzLabs, ADL Canberra
andrew.donnellan@au1.ibm.com IBM Australia Limited
^ permalink raw reply
* Re: [PATCH AUTOSEL 5.0 015/262] memblock: memblock_phys_alloc_try_nid(): don't panic
From: Sasha Levin @ 2019-04-04 0:57 UTC (permalink / raw)
To: Mike Rapoport
Cc: Rich Felker, Petr Mladek, Catalin Marinas, Heiko Carstens,
Max Filippov, Guo Ren, Christoph Hellwig, Rob Herring,
Yoshinori Sato, Richard Weinberger, Russell King,
Geert Uytterhoeven, Guo Ren, Mark Salter, Dennis Zhou,
Matt Turner, Juergen Gross, linuxppc-dev, Rob Herring,
Greentime Hu, Stafford Horne, Guan Xuetao, Michal Simek,
Tony Luck, linux-mm, Greg Kroah-Hartman, linux-kernel, stable,
Paul Burton, Vineet Gupta, Andrew Morton, Linus Torvalds,
David S. Miller
In-Reply-To: <20190328055720.GB14864@rapoport-lnx>
On Thu, Mar 28, 2019 at 07:57:21AM +0200, Mike Rapoport wrote:
>Hi,
>
>On Wed, Mar 27, 2019 at 01:57:50PM -0400, Sasha Levin wrote:
>> From: Mike Rapoport <rppt@linux.ibm.com>
>>
>> [ Upstream commit 337555744e6e39dd1d87698c6084dd88a606d60a ]
>>
>> The memblock_phys_alloc_try_nid() function tries to allocate memory from
>> the requested node and then falls back to allocation from any node in
>> the system. The memblock_alloc_base() fallback used by this function
>> panics if the allocation fails.
>>
>> Replace the memblock_alloc_base() fallback with the direct call to
>> memblock_alloc_range_nid() and update the memblock_phys_alloc_try_nid()
>> callers to check the returned value and panic in case of error.
>
>This is a part of memblock refactoring, I don't think it should be applied
>to -stable.
Dropped, thanks!
--
Thanks,
Sasha
^ permalink raw reply
* VLC doesn't play videos anymore since the PowerPC fixes 5.1-3
From: Christian Zigotzky @ 2019-04-04 0:58 UTC (permalink / raw)
To: Christophe Leroy, linuxppc-dev
In-Reply-To: <79a9370a-7c4b-80be-adab-6dcf3b0fa6f2@c-s.fr>
On 03 April 2019 at 07:05AM, Christophe Leroy wrote:
> Le 03/04/2019 à 05:52, Christian Zigotzky a écrit :
>> Please test VLC with the RC3 of kernel 5.1.
>>
>> The removing of the PowerPC fixes 5.1-3 has solved the VLC issue.
>> Another user has already confirmed that [1]. This isn’t an April
>> Fool‘s. ;-)
>
> Could you bisect to identify the guilty commit ?
>
> Thanks
> Christophe
>
>>
>> Thanks
>>
>> [1]
>> http://forum.hyperion-entertainment.com/viewtopic.php?f=58&t=4256&start=20#p47561
>>
>
Hello Christophe,
I have found the problematic patch. The following patch from the PowerPC
fixes 5.1-3 is responsible for the VLC issue.
diff --git a/arch/powerpc/include/asm/vdso_datapage.h
b/arch/powerpc/include/asm/vdso_datapage.h
index 1afe90ade595..bbc06bd72b1f 100644
--- a/arch/powerpc/include/asm/vdso_datapage.h
+++ b/arch/powerpc/include/asm/vdso_datapage.h
@@ -82,10 +82,10 @@ struct vdso_data {
__u32 icache_block_size; /* L1 i-cache block size */
__u32 dcache_log_block_size; /* L1 d-cache log block size */
__u32 icache_log_block_size; /* L1 i-cache log block size */
- __s32 wtom_clock_sec; /* Wall to monotonic clock */
- __s32 wtom_clock_nsec;
- struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
- __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
+ __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
+ __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */
+ __s64 wtom_clock_sec; /* Wall to monotonic clock sec */
+ struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
};
-----
Link:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/diff/arch/powerpc/include/asm/vdso_datapage.h?h=v5.1-rc2&id=a5ed1e96cafde5ba48638f486bfca0685dc6ddc9
I created a patch for solving the VLC issue today.
vdso_datapage_vlc.patch:
diff -rupN a/arch/powerpc/include/asm/vdso_datapage.h
b/arch/powerpc/include/asm/vdso_datapage.h
--- a/arch/powerpc/include/asm/vdso_datapage.h 2019-04-03
22:56:44.560645936 +0200
+++ b/arch/powerpc/include/asm/vdso_datapage.h 2019-04-04
02:20:09.479361827 +0200
@@ -82,10 +82,10 @@ struct vdso_data {
__u32 icache_block_size; /* L1 i-cache block
size */
__u32 dcache_log_block_size; /* L1 d-cache log block
size */
__u32 icache_log_block_size; /* L1 i-cache log block
size */
- __u32 stamp_sec_fraction; /* fractional seconds of
stamp_xtime */
- __s32 wtom_clock_nsec; /* Wall to monotonic
clock nsec */
- __s64 wtom_clock_sec; /* Wall to monotonic
clock sec */
- struct timespec stamp_xtime; /* xtime as at
tb_orig_stamp */
+ __s32 wtom_clock_sec; /* Wall to monotonic
clock */
+ __s32 wtom_clock_nsec;
+ struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
+ __u32 stamp_sec_fraction; /* fractional seconds of
stamp_xtime */
__u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
__u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
};
-----
Cheers,
Christian
^ permalink raw reply related
* Re: VLC doesn't play videos anymore since the PowerPC fixes 5.1-3
From: Christophe Leroy @ 2019-04-04 4:00 UTC (permalink / raw)
To: Christian Zigotzky, linuxppc-dev, Michael Ellerman
In-Reply-To: <0f0403a0-476a-6129-8dc6-866d894c9adc@xenosoft.de>
Le 04/04/2019 à 02:58, Christian Zigotzky a écrit :
> On 03 April 2019 at 07:05AM, Christophe Leroy wrote:
>> Le 03/04/2019 à 05:52, Christian Zigotzky a écrit :
>>> Please test VLC with the RC3 of kernel 5.1.
>>>
>>> The removing of the PowerPC fixes 5.1-3 has solved the VLC issue.
>>> Another user has already confirmed that [1]. This isn’t an April
>>> Fool‘s. ;-)
>>
>> Could you bisect to identify the guilty commit ?
>>
>> Thanks
>> Christophe
>>
>>>
>>> Thanks
>>>
>>> [1]
>>> http://forum.hyperion-entertainment.com/viewtopic.php?f=58&t=4256&start=20#p47561
>>>
>>>
>>
> Hello Christophe,
>
> I have found the problematic patch. The following patch from the PowerPC
> fixes 5.1-3 is responsible for the VLC issue.
That change is part of the following commit:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h=v5.1-rc2&id=b5b4453e7912f056da1ca7572574cada32ecb60c
Just changing back the type of wtom_clock_sec to 32 bits without
changing back the loading instruction is likely to give unexpected
results on PPC64.
Are you using 32 bits or 64 bits powerpc ?
Christophe
>
> diff --git a/arch/powerpc/include/asm/vdso_datapage.h
> b/arch/powerpc/include/asm/vdso_datapage.h
> index 1afe90ade595..bbc06bd72b1f 100644
> --- a/arch/powerpc/include/asm/vdso_datapage.h
> +++ b/arch/powerpc/include/asm/vdso_datapage.h
> @@ -82,10 +82,10 @@ struct vdso_data {
> __u32 icache_block_size; /* L1 i-cache block size */
> __u32 dcache_log_block_size; /* L1 d-cache log block size */
> __u32 icache_log_block_size; /* L1 i-cache log block size */
> - __s32 wtom_clock_sec; /* Wall to monotonic clock */
> - __s32 wtom_clock_nsec;
> - struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
> - __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
> + __u32 stamp_sec_fraction; /* fractional seconds of stamp_xtime */
> + __s32 wtom_clock_nsec; /* Wall to monotonic clock nsec */
> + __s64 wtom_clock_sec; /* Wall to monotonic clock sec */
> + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
> __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
> __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
> };
>
> -----
>
> Link:
> https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/diff/arch/powerpc/include/asm/vdso_datapage.h?h=v5.1-rc2&id=a5ed1e96cafde5ba48638f486bfca0685dc6ddc9
>
>
> I created a patch for solving the VLC issue today.
>
> vdso_datapage_vlc.patch:
>
> diff -rupN a/arch/powerpc/include/asm/vdso_datapage.h
> b/arch/powerpc/include/asm/vdso_datapage.h
> --- a/arch/powerpc/include/asm/vdso_datapage.h 2019-04-03
> 22:56:44.560645936 +0200
> +++ b/arch/powerpc/include/asm/vdso_datapage.h 2019-04-04
> 02:20:09.479361827 +0200
> @@ -82,10 +82,10 @@ struct vdso_data {
> __u32 icache_block_size; /* L1 i-cache block
> size */
> __u32 dcache_log_block_size; /* L1 d-cache log block
> size */
> __u32 icache_log_block_size; /* L1 i-cache log block
> size */
> - __u32 stamp_sec_fraction; /* fractional seconds of
> stamp_xtime */
> - __s32 wtom_clock_nsec; /* Wall to monotonic
> clock nsec */
> - __s64 wtom_clock_sec; /* Wall to monotonic
> clock sec */
> - struct timespec stamp_xtime; /* xtime as at
> tb_orig_stamp */
> + __s32 wtom_clock_sec; /* Wall to monotonic
> clock */
> + __s32 wtom_clock_nsec;
> + struct timespec stamp_xtime; /* xtime as at tb_orig_stamp */
> + __u32 stamp_sec_fraction; /* fractional seconds of
> stamp_xtime */
> __u32 syscall_map_64[SYSCALL_MAP_SIZE]; /* map of syscalls */
> __u32 syscall_map_32[SYSCALL_MAP_SIZE]; /* map of syscalls */
> };
>
> -----
>
> Cheers,
> Christian
^ permalink raw reply
* [RFC PATCH kernel v2] powerpc/powernv: Isolate NVLinks between GV100GL on Witherspoon
From: Alexey Kardashevskiy @ 2019-04-04 5:23 UTC (permalink / raw)
To: linuxppc-dev
Cc: Jose Ricardo Ziviani, kvm, Alexey Kardashevskiy,
Daniel Henrique Barboza, Piotr Jaroszynski, kvm-ppc, Sam Bobroff,
Alex Williamson, Leonardo Augusto Guimarães Garcia,
David Gibson
The NVIDIA V100 SXM2 GPUs are connected to the CPU via PCIe links and
(on POWER9) NVLinks. In addition to that, GPUs themselves have direct
peer to peer NVLinks in groups of 2 to 4 GPUs. At the moment the POWERNV
platform puts all interconnected GPUs to the same IOMMU group.
However the user may want to pass individual GPUs to the userspace so
in order to do so we need to put them into separate IOMMU groups and
cut off the interconnects.
Thankfully V100 GPUs implement an interface to do by programming link
disabling mask to BAR0 of a GPU. Once a link is disabled in a GPU using
this interface, it cannot be re-enabled until the secondary bus reset is
issued to the GPU.
This adds an extra step to the secondary bus reset handler (the one used
for such GPUs) to block NVLinks to GPUs which do not belong to the same
group as the GPU being reset.
This adds a new "isolate_nvlink" kernel parameter to allow GPU isolation;
when enabled, every GPU gets its own IOMMU group. The new parameter is off
by default to preserve the existing behaviour.
Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
Changes:
v2:
* this is rework of [PATCH kernel RFC 0/2] vfio, powerpc/powernv: Isolate GV100GL
but this time it is contained in the powernv platform
---
arch/powerpc/platforms/powernv/Makefile | 2 +-
arch/powerpc/platforms/powernv/pci.h | 1 +
arch/powerpc/platforms/powernv/eeh-powernv.c | 1 +
arch/powerpc/platforms/powernv/npu-dma.c | 24 +++-
arch/powerpc/platforms/powernv/nvlinkgpu.c | 131 +++++++++++++++++++
5 files changed, 156 insertions(+), 3 deletions(-)
create mode 100644 arch/powerpc/platforms/powernv/nvlinkgpu.c
diff --git a/arch/powerpc/platforms/powernv/Makefile b/arch/powerpc/platforms/powernv/Makefile
index da2e99efbd04..60a10d3b36eb 100644
--- a/arch/powerpc/platforms/powernv/Makefile
+++ b/arch/powerpc/platforms/powernv/Makefile
@@ -6,7 +6,7 @@ obj-y += opal-msglog.o opal-hmi.o opal-power.o opal-irqchip.o
obj-y += opal-kmsg.o opal-powercap.o opal-psr.o opal-sensor-groups.o
obj-$(CONFIG_SMP) += smp.o subcore.o subcore-asm.o
-obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o
+obj-$(CONFIG_PCI) += pci.o pci-ioda.o npu-dma.o pci-ioda-tce.o nvlinkgpu.o
obj-$(CONFIG_CXL_BASE) += pci-cxl.o
obj-$(CONFIG_EEH) += eeh-powernv.o
obj-$(CONFIG_PPC_SCOM) += opal-xscom.o
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 8e36da379252..9fd3f391482c 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -250,5 +250,6 @@ extern void pnv_pci_unlink_table_and_group(struct iommu_table *tbl,
extern void pnv_pci_setup_iommu_table(struct iommu_table *tbl,
void *tce_mem, u64 tce_size,
u64 dma_offset, unsigned int page_shift);
+extern void pnv_try_isolate_nvidia_v100(struct pci_dev *gpdev);
#endif /* __POWERNV_PCI_H */
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index f38078976c5d..464b097d9635 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -937,6 +937,7 @@ void pnv_pci_reset_secondary_bus(struct pci_dev *dev)
pnv_eeh_bridge_reset(dev, EEH_RESET_HOT);
pnv_eeh_bridge_reset(dev, EEH_RESET_DEACTIVATE);
}
+ pnv_try_isolate_nvidia_v100(dev);
}
static void pnv_eeh_wait_for_pending(struct pci_dn *pdn, const char *type,
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index dc23d9d2a7d9..017eae8197e7 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -529,6 +529,23 @@ static void pnv_comp_attach_table_group(struct npu_comp *npucomp,
++npucomp->pe_num;
}
+static bool isolate_nvlink;
+
+static int __init parse_isolate_nvlink(char *p)
+{
+ bool val;
+
+ if (!p)
+ val = true;
+ else if (kstrtobool(p, &val))
+ return -EINVAL;
+
+ isolate_nvlink = val;
+
+ return 0;
+}
+early_param("isolate_nvlink", parse_isolate_nvlink);
+
struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
{
struct iommu_table_group *table_group;
@@ -549,7 +566,7 @@ struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
hose = pci_bus_to_host(npdev->bus);
- if (hose->npu) {
+ if (hose->npu && !isolate_nvlink) {
table_group = &hose->npu->npucomp.table_group;
if (!table_group->group) {
@@ -559,7 +576,10 @@ struct iommu_table_group *pnv_try_setup_npu_table_group(struct pnv_ioda_pe *pe)
pe->pe_number);
}
} else {
- /* Create a group for 1 GPU and attached NPUs for POWER8 */
+ /*
+ * Create a group for 1 GPU and attached NPUs for
+ * POWER8 (always) or POWER9 (when isolate_nvlink).
+ */
pe->npucomp = kzalloc(sizeof(*pe->npucomp), GFP_KERNEL);
table_group = &pe->npucomp->table_group;
table_group->ops = &pnv_npu_peers_ops;
diff --git a/arch/powerpc/platforms/powernv/nvlinkgpu.c b/arch/powerpc/platforms/powernv/nvlinkgpu.c
new file mode 100644
index 000000000000..dbd8e9d47a05
--- /dev/null
+++ b/arch/powerpc/platforms/powernv/nvlinkgpu.c
@@ -0,0 +1,131 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * A helper to disable NVLinks between GPUs on IBM Withersponn platform.
+ *
+ * Copyright (C) 2019 IBM Corp. All rights reserved.
+ * Author: Alexey Kardashevskiy <aik@ozlabs.ru>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/iommu.h>
+#include <linux/pci.h>
+
+static int nvlinkgpu_is_ph_in_group(struct device *dev, void *data)
+{
+ return dev->of_node->phandle == *(phandle *) data;
+}
+
+static u32 nvlinkgpu_get_disable_mask(struct device *dev)
+{
+ int npu, peer;
+ u32 mask;
+ struct device_node *dn;
+ struct iommu_group *group;
+
+ dn = dev->of_node;
+ if (!of_find_property(dn, "ibm,nvlink-peers", NULL))
+ return 0;
+
+ group = iommu_group_get(dev);
+ if (!group)
+ return 0;
+
+ /*
+ * Collect links to keep which includes links to NPU and links to
+ * other GPUs in the same IOMMU group.
+ */
+ for (npu = 0, mask = 0; ; ++npu) {
+ u32 npuph = 0;
+
+ if (of_property_read_u32_index(dn, "ibm,npu", npu, &npuph))
+ break;
+
+ for (peer = 0; ; ++peer) {
+ u32 peerph = 0;
+
+ if (of_property_read_u32_index(dn, "ibm,nvlink-peers",
+ peer, &peerph))
+ break;
+
+ if (peerph != npuph &&
+ !iommu_group_for_each_dev(group, &peerph,
+ nvlinkgpu_is_ph_in_group))
+ continue;
+
+ mask |= 1 << (peer + 16);
+ }
+ }
+ iommu_group_put(group);
+
+ /* Disabling mechanism takes links to disable so invert it here */
+ mask = ~mask & 0x3F0000;
+
+ return mask;
+}
+
+void pnv_try_isolate_nvidia_v100(struct pci_dev *bridge)
+{
+ u32 mask;
+ void __iomem *bar0_0, *bar0_120000, *bar0_a00000;
+ struct pci_dev *pdev;
+
+ if (!bridge->subordinate)
+ return;
+
+ pdev = list_first_entry_or_null(&bridge->subordinate->devices,
+ struct pci_dev, bus_list);
+ if (!pdev)
+ return;
+
+ if (pdev->vendor != PCI_VENDOR_ID_NVIDIA)
+ return;
+
+ mask = nvlinkgpu_get_disable_mask(&pdev->dev);
+ if (!mask)
+ return;
+
+ bar0_0 = pci_iomap_range(pdev, 0, 0, 0x10000);
+ bar0_120000 = pci_iomap_range(pdev, 0, 0x120000, 0x10000);
+ bar0_a00000 = pci_iomap_range(pdev, 0, 0xA00000, 0x10000);
+
+ if (bar0_120000 && bar0_0 && bar0_a00000) {
+ u32 val;
+ u16 cmd = 0, cmdmask = PCI_COMMAND_MEMORY;
+
+ pci_restore_state(pdev);
+ pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+ if ((cmd & cmdmask) != cmdmask)
+ pci_write_config_word(pdev, PCI_COMMAND, cmd | cmdmask);
+
+ /*
+ * The sequence is from "Tesla P100 and V100 SXM2 NVLink
+ * Isolation on Multi-Tenant Systems".
+ * The register names are not provided there either,
+ * hence raw values.
+ */
+ iowrite32(0x4, bar0_120000 + 0x4C);
+ iowrite32(0x2, bar0_120000 + 0x2204);
+ val = ioread32(bar0_0 + 0x200);
+ val |= 0x02000000;
+ iowrite32(val, bar0_0 + 0x200);
+ val = ioread32(bar0_a00000 + 0x148);
+ val |= mask;
+ iowrite32(val, bar0_a00000 + 0x148);
+
+ if ((cmd | cmdmask) != cmd)
+ pci_write_config_word(pdev, PCI_COMMAND, cmd);
+ }
+
+ if (bar0_0)
+ pci_iounmap(pdev, bar0_0);
+ if (bar0_120000)
+ pci_iounmap(pdev, bar0_120000);
+ if (bar0_a00000)
+ pci_iounmap(pdev, bar0_a00000);
+}
--
2.17.1
^ permalink raw reply related
* Re: [PATCH 2/2] arch: add pidfd and io_uring syscalls everywhere
From: Michael Ellerman @ 2019-04-04 6:08 UTC (permalink / raw)
To: Jens Axboe, Will Deacon
Cc: Rich Felker, linux-ia64, linux-sh, Heiko Carstens, linux-mips,
James E . J . Bottomley, Max Filippov, Paul Mackerras, sparclinux,
linux-s390, Helge Deller, Russell King, Geert Uytterhoeven,
Catalin Marinas, James Hogan, Firoz Khan, Matt Turner, Fenghua Yu,
Arnd Bergmann, linux-m68k, Ivan Kokshaysky, linux-arm-kernel,
Richard Henderson, Michal Simek, Tony Luck, linux-parisc,
linux-kernel, Ralf Baechle, Paul Burton, linux-alpha,
Martin Schwidefsky, Andrew Morton, linuxppc-dev, David S . Miller
In-Reply-To: <9d673dfd-0051-3676-653e-6376430d73dd@kernel.dk>
Jens Axboe <axboe@kernel.dk> writes:
> On 4/3/19 5:11 AM, Will Deacon wrote:
>> On Wed, Apr 03, 2019 at 01:47:50PM +1100, Michael Ellerman wrote:
>>> Arnd Bergmann <arnd@arndb.de> writes:
>>>> diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
>>>> index b18abb0c3dae..00f5a63c8d9a 100644
>>>> --- a/arch/powerpc/kernel/syscalls/syscall.tbl
>>>> +++ b/arch/powerpc/kernel/syscalls/syscall.tbl
>>>> @@ -505,3 +505,7 @@
>>>> 421 32 rt_sigtimedwait_time64 sys_rt_sigtimedwait compat_sys_rt_sigtimedwait_time64
>>>> 422 32 futex_time64 sys_futex sys_futex
>>>> 423 32 sched_rr_get_interval_time64 sys_sched_rr_get_interval sys_sched_rr_get_interval
>>>> +424 common pidfd_send_signal sys_pidfd_send_signal
>>>> +425 common io_uring_setup sys_io_uring_setup
>>>> +426 common io_uring_enter sys_io_uring_enter
>>>> +427 common io_uring_register sys_io_uring_register
>>>
>>> Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
>>>
>>> Lightly tested.
>>>
>>> The pidfd_test selftest passes.
>>
>> That reports pass for me too, although it fails to unshare the pid ns, which I
>> assume is benign.
If you run it as root it should work?
>>> Ran the io_uring example from fio, which prints lots of:
>>
>> How did you invoke that? I had a play with the tests in:
>
> It's t/io_uring from the fio repo:
>
> git://git.kernel.dk/fio
>
> and you just run it ala:
>
> # make t/io_uring
> # t/io_uring /dev/some_device
Yeah that's all I did.
>> will@autoplooker:~/liburing/test$ ./io_uring_register
>> RELIMIT_MEMLOCK: 67108864 (67108864)
>> [ 35.477875] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000070
>> [ 35.478969] Mem abort info:
>> [ 35.479296] ESR = 0x96000004
>> [ 35.479785] Exception class = DABT (current EL), IL = 32 bits
>> [ 35.480528] SET = 0, FnV = 0
>> [ 35.480980] EA = 0, S1PTW = 0
>> [ 35.481345] Data abort info:
>> [ 35.481680] ISV = 0, ISS = 0x00000004
>> [ 35.482267] CM = 0, WnR = 0
>> [ 35.482618] user pgtable: 4k pages, 48-bit VAs, pgdp = (____ptrval____)
>> [ 35.483486] [0000000000000070] pgd=0000000000000000
>> [ 35.484041] Internal error: Oops: 96000004 [#1] PREEMPT SMP
>> [ 35.484788] Modules linked in:
>> [ 35.485311] CPU: 113 PID: 3973 Comm: io_uring_regist Not tainted 5.1.0-rc3-00012-g40b114779944 #1
>> [ 35.486712] Hardware name: linux,dummy-virt (DT)
>> [ 35.487450] pstate: 20400005 (nzCv daif +PAN -UAO)
>> [ 35.488228] pc : link_pwq+0x10/0x60
>> [ 35.488794] lr : apply_wqattrs_commit+0xe0/0x118
>> [ 35.489550] sp : ffff000017e2bbc0
>
> Huh, this looks odd, it's crashing inside the wq setup.
Looks like you found a bug :)
cheers
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox