* [PATCH v2 rebased 1/9] powerpc/mm: Make slice specific to book3s/64
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 5:32 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 2/9] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c Christophe Leroy
` (7 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Since commit 555904d07eef ("powerpc/8xx: MM_SLICE is not needed
anymore") only book3s/64 selects CONFIG_PPC_MM_SLICES.
Move slice.c into mm/book3s64/
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2: Remove now unnecessary #ifdef CONFIG_PPC_BOOK3S_64 in slice.c
---
arch/powerpc/mm/Makefile | 1 -
arch/powerpc/mm/book3s64/Makefile | 1 +
arch/powerpc/mm/{ => book3s64}/slice.c | 2 --
arch/powerpc/mm/nohash/mmu_context.c | 9 ---------
arch/powerpc/mm/nohash/tlb.c | 4 ----
5 files changed, 1 insertion(+), 16 deletions(-)
rename arch/powerpc/mm/{ => book3s64}/slice.c (99%)
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index df8172da2301..d4c20484dad9 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -14,7 +14,6 @@ obj-$(CONFIG_PPC_MMU_NOHASH) += nohash/
obj-$(CONFIG_PPC_BOOK3S_32) += book3s32/
obj-$(CONFIG_PPC_BOOK3S_64) += book3s64/
obj-$(CONFIG_NUMA) += numa.o
-obj-$(CONFIG_PPC_MM_SLICES) += slice.o
obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
obj-$(CONFIG_NOT_COHERENT_CACHE) += dma-noncoherent.o
obj-$(CONFIG_PPC_COPRO_BASE) += copro_fault.o
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
index 2d50cac499c5..af2f3e75d458 100644
--- a/arch/powerpc/mm/book3s64/Makefile
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_PPC_RADIX_MMU) += radix_hugetlbpage.o
endif
obj-$(CONFIG_SPAPR_TCE_IOMMU) += iommu_api.o
obj-$(CONFIG_PPC_PKEY) += pkeys.o
+obj-$(CONFIG_PPC_MM_SLICES) += slice.o
# Instrumenting the SLB fault path can lead to duplicate SLB entries
KCOV_INSTRUMENT_slb.o := n
diff --git a/arch/powerpc/mm/slice.c b/arch/powerpc/mm/book3s64/slice.c
similarity index 99%
rename from arch/powerpc/mm/slice.c
rename to arch/powerpc/mm/book3s64/slice.c
index 82b45b1cb973..c83be371c6e7 100644
--- a/arch/powerpc/mm/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -712,7 +712,6 @@ void slice_init_new_context_exec(struct mm_struct *mm)
bitmap_fill(mask->high_slices, SLICE_NUM_HIGH);
}
-#ifdef CONFIG_PPC_BOOK3S_64
void slice_setup_new_exec(void)
{
struct mm_struct *mm = current->mm;
@@ -724,7 +723,6 @@ void slice_setup_new_exec(void)
mm_ctx_set_slb_addr_limit(&mm->context, DEFAULT_MAP_WINDOW);
}
-#endif
void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
unsigned long len, unsigned int psize)
diff --git a/arch/powerpc/mm/nohash/mmu_context.c b/arch/powerpc/mm/nohash/mmu_context.c
index 44b2b5e7cabe..dc3528e815b9 100644
--- a/arch/powerpc/mm/nohash/mmu_context.c
+++ b/arch/powerpc/mm/nohash/mmu_context.c
@@ -313,15 +313,6 @@ void switch_mmu_context(struct mm_struct *prev, struct mm_struct *next,
*/
int init_new_context(struct task_struct *t, struct mm_struct *mm)
{
- /*
- * We have MMU_NO_CONTEXT set to be ~0. Hence check
- * explicitly against context.id == 0. This ensures that we properly
- * initialize context slice details for newly allocated mm's (which will
- * have id == 0) and don't alter context slice inherited via fork (which
- * will have id != 0).
- */
- if (mm->context.id == 0)
- slice_init_new_context_exec(mm);
mm->context.id = MMU_NO_CONTEXT;
mm->context.active = 0;
pte_frag_set(&mm->context, NULL);
diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
index 311281063d48..3359cf7c2a61 100644
--- a/arch/powerpc/mm/nohash/tlb.c
+++ b/arch/powerpc/mm/nohash/tlb.c
@@ -773,9 +773,5 @@ void __init early_init_mmu(void)
#ifdef CONFIG_PPC_47x
early_init_mmu_47x();
#endif
-
-#ifdef CONFIG_PPC_MM_SLICES
- mm_ctx_set_slb_addr_limit(&init_mm.context, SLB_ADDR_LIMIT_DEFAULT);
-#endif
}
#endif /* CONFIG_PPC64 */
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v2 rebased 1/9] powerpc/mm: Make slice specific to book3s/64
2021-11-25 17:52 ` [PATCH v2 rebased 1/9] powerpc/mm: Make slice specific to book3s/64 Christophe Leroy
@ 2021-12-01 5:32 ` Nicholas Piggin
0 siblings, 0 replies; 16+ messages in thread
From: Nicholas Piggin @ 2021-12-01 5:32 UTC (permalink / raw)
To: alex, Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linux-kernel, linux-mm, linuxppc-dev
Excerpts from Christophe Leroy's message of November 26, 2021 3:52 am:
> Since commit 555904d07eef ("powerpc/8xx: MM_SLICE is not needed
> anymore") only book3s/64 selects CONFIG_PPC_MM_SLICES.
>
> Move slice.c into mm/book3s64/
>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
> ---
> v2: Remove now unnecessary #ifdef CONFIG_PPC_BOOK3S_64 in slice.c
> ---
> arch/powerpc/mm/Makefile | 1 -
> arch/powerpc/mm/book3s64/Makefile | 1 +
> arch/powerpc/mm/{ => book3s64}/slice.c | 2 --
> arch/powerpc/mm/nohash/mmu_context.c | 9 ---------
> arch/powerpc/mm/nohash/tlb.c | 4 ----
> 5 files changed, 1 insertion(+), 16 deletions(-)
> rename arch/powerpc/mm/{ => book3s64}/slice.c (99%)
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v2 rebased 2/9] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 1/9] powerpc/mm: Make slice specific to book3s/64 Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 5:43 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 3/9] powerpc/mm: Remove CONFIG_PPC_MM_SLICES Christophe Leroy
` (6 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
vma_mmu_pagesize() is only required for slices,
otherwise there is a generic weak version.
hugetlb_get_unmapped_area() is dedicated to slices.
radix__hugetlb_get_unmapped_area() as well.
Move them to slice.c
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/64/hugetlb.h | 4 --
arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 55 --------------
arch/powerpc/mm/book3s64/slice.c | 76 ++++++++++++++++++++
arch/powerpc/mm/hugetlbpage.c | 28 --------
4 files changed, 76 insertions(+), 87 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
index 12e150e615b7..b37a28f62cf6 100644
--- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
+++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
@@ -8,10 +8,6 @@
*/
void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
-extern unsigned long
-radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags);
extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
index 23d3e08911d3..d2fb776febb4 100644
--- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
+++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
@@ -41,61 +41,6 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st
radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
}
-/*
- * A vairant of hugetlb_get_unmapped_area doing topdown search
- * FIXME!! should we do as x86 does or non hugetlb area does ?
- * ie, use topdown or not based on mmap_is_legacy check ?
- */
-unsigned long
-radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- struct hstate *h = hstate_file(file);
- int fixed = (flags & MAP_FIXED);
- unsigned long high_limit;
- struct vm_unmapped_area_info info;
-
- high_limit = DEFAULT_MAP_WINDOW;
- if (addr >= high_limit || (fixed && (addr + len > high_limit)))
- high_limit = TASK_SIZE;
-
- if (len & ~huge_page_mask(h))
- return -EINVAL;
- if (len > high_limit)
- return -ENOMEM;
-
- if (fixed) {
- if (addr > high_limit - len)
- return -ENOMEM;
- if (prepare_hugepage_range(file, addr, len))
- return -EINVAL;
- return addr;
- }
-
- if (addr) {
- addr = ALIGN(addr, huge_page_size(h));
- vma = find_vma(mm, addr);
- if (high_limit - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
- /*
- * We are always doing an topdown search here. Slice code
- * does that too.
- */
- info.flags = VM_UNMAPPED_AREA_TOPDOWN;
- info.length = len;
- info.low_limit = max(PAGE_SIZE, mmap_min_addr);
- info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
- info.align_mask = PAGE_MASK & ~huge_page_mask(h);
- info.align_offset = 0;
-
- return vm_unmapped_area(&info);
-}
-
void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep,
pte_t old_pte, pte_t pte)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index c83be371c6e7..4c3e9601fdf6 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -777,4 +777,80 @@ int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
return !slice_check_range_fits(mm, maskp, addr, len);
}
+
+unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+{
+ /* With radix we don't use slice, so derive it from vma*/
+ if (radix_enabled())
+ return vma_kernel_pagesize(vma);
+
+ return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
+}
+
+/*
+ * A variant of hugetlb_get_unmapped_area() doing topdown search
+ * FIXME!! should we do as x86 does or non hugetlb area does ?
+ * ie, use topdown or not based on mmap_is_legacy check ?
+ */
+static unsigned long
+radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ struct hstate *h = hstate_file(file);
+ int fixed = (flags & MAP_FIXED);
+ unsigned long high_limit;
+ struct vm_unmapped_area_info info;
+
+ high_limit = DEFAULT_MAP_WINDOW;
+ if (addr >= high_limit || (fixed && (addr + len > high_limit)))
+ high_limit = TASK_SIZE;
+
+ if (len & ~huge_page_mask(h))
+ return -EINVAL;
+ if (len > high_limit)
+ return -ENOMEM;
+
+ if (fixed) {
+ if (addr > high_limit - len)
+ return -ENOMEM;
+ if (prepare_hugepage_range(file, addr, len))
+ return -EINVAL;
+ return addr;
+ }
+
+ if (addr) {
+ addr = ALIGN(addr, huge_page_size(h));
+ vma = find_vma(mm, addr);
+ if (high_limit - len >= addr && addr >= mmap_min_addr &&
+ (!vma || addr + len <= vm_start_gap(vma)))
+ return addr;
+ }
+ /*
+ * We are always doing an topdown search here. Slice code
+ * does that too.
+ */
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+ info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
+ info.align_mask = PAGE_MASK & ~huge_page_mask(h);
+ info.align_offset = 0;
+
+ return vm_unmapped_area(&info);
+}
+
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ struct hstate *hstate = hstate_file(file);
+ int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
+
+ if (radix_enabled())
+ return radix__hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
+
+ return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
+}
#endif
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 82d8b368ca6d..eb9de09e49a3 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -542,34 +542,6 @@ struct page *follow_huge_pd(struct vm_area_struct *vma,
return page;
}
-#ifdef CONFIG_PPC_MM_SLICES
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- struct hstate *hstate = hstate_file(file);
- int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
-
-#ifdef CONFIG_PPC_RADIX_MMU
- if (radix_enabled())
- return radix__hugetlb_get_unmapped_area(file, addr, len,
- pgoff, flags);
-#endif
- return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
-}
-#endif
-
-unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
-{
- /* With radix we don't use slice, so derive it from vma*/
- if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) {
- unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
-
- return 1UL << mmu_psize_to_shift(psize);
- }
- return vma_kernel_pagesize(vma);
-}
-
bool __init arch_hugetlb_valid_size(unsigned long size)
{
int shift = __ffs(size);
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v2 rebased 2/9] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c
2021-11-25 17:52 ` [PATCH v2 rebased 2/9] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c Christophe Leroy
@ 2021-12-01 5:43 ` Nicholas Piggin
0 siblings, 0 replies; 16+ messages in thread
From: Nicholas Piggin @ 2021-12-01 5:43 UTC (permalink / raw)
To: alex, Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linux-kernel, linux-mm, linuxppc-dev
Excerpts from Christophe Leroy's message of November 26, 2021 3:52 am:
> vma_mmu_pagesize() is only required for slices,
> otherwise there is a generic weak version.
Fine.
> hugetlb_get_unmapped_area() is dedicated to slices.
> radix__hugetlb_get_unmapped_area() as well.
Hmm, that's interesting. It would be nice if we could just use the
generic code version for it but that will require some hacking.
This means my patch series changes behaviour (as in the FIXME) when
HASH=n I think? I will have to fix that somehow.
Thanks,
Nick
>
> Move them to slice.c
>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
> arch/powerpc/include/asm/book3s/64/hugetlb.h | 4 --
> arch/powerpc/mm/book3s64/radix_hugetlbpage.c | 55 --------------
> arch/powerpc/mm/book3s64/slice.c | 76 ++++++++++++++++++++
> arch/powerpc/mm/hugetlbpage.c | 28 --------
> 4 files changed, 76 insertions(+), 87 deletions(-)
>
> diff --git a/arch/powerpc/include/asm/book3s/64/hugetlb.h b/arch/powerpc/include/asm/book3s/64/hugetlb.h
> index 12e150e615b7..b37a28f62cf6 100644
> --- a/arch/powerpc/include/asm/book3s/64/hugetlb.h
> +++ b/arch/powerpc/include/asm/book3s/64/hugetlb.h
> @@ -8,10 +8,6 @@
> */
> void radix__flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
> void radix__local_flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
> -extern unsigned long
> -radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
> - unsigned long len, unsigned long pgoff,
> - unsigned long flags);
>
> extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
> unsigned long addr, pte_t *ptep,
> diff --git a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
> index 23d3e08911d3..d2fb776febb4 100644
> --- a/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
> +++ b/arch/powerpc/mm/book3s64/radix_hugetlbpage.c
> @@ -41,61 +41,6 @@ void radix__flush_hugetlb_tlb_range(struct vm_area_struct *vma, unsigned long st
> radix__flush_tlb_range_psize(vma->vm_mm, start, end, psize);
> }
>
> -/*
> - * A vairant of hugetlb_get_unmapped_area doing topdown search
> - * FIXME!! should we do as x86 does or non hugetlb area does ?
> - * ie, use topdown or not based on mmap_is_legacy check ?
> - */
> -unsigned long
> -radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
> - unsigned long len, unsigned long pgoff,
> - unsigned long flags)
> -{
> - struct mm_struct *mm = current->mm;
> - struct vm_area_struct *vma;
> - struct hstate *h = hstate_file(file);
> - int fixed = (flags & MAP_FIXED);
> - unsigned long high_limit;
> - struct vm_unmapped_area_info info;
> -
> - high_limit = DEFAULT_MAP_WINDOW;
> - if (addr >= high_limit || (fixed && (addr + len > high_limit)))
> - high_limit = TASK_SIZE;
> -
> - if (len & ~huge_page_mask(h))
> - return -EINVAL;
> - if (len > high_limit)
> - return -ENOMEM;
> -
> - if (fixed) {
> - if (addr > high_limit - len)
> - return -ENOMEM;
> - if (prepare_hugepage_range(file, addr, len))
> - return -EINVAL;
> - return addr;
> - }
> -
> - if (addr) {
> - addr = ALIGN(addr, huge_page_size(h));
> - vma = find_vma(mm, addr);
> - if (high_limit - len >= addr && addr >= mmap_min_addr &&
> - (!vma || addr + len <= vm_start_gap(vma)))
> - return addr;
> - }
> - /*
> - * We are always doing an topdown search here. Slice code
> - * does that too.
> - */
> - info.flags = VM_UNMAPPED_AREA_TOPDOWN;
> - info.length = len;
> - info.low_limit = max(PAGE_SIZE, mmap_min_addr);
> - info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
> - info.align_mask = PAGE_MASK & ~huge_page_mask(h);
> - info.align_offset = 0;
> -
> - return vm_unmapped_area(&info);
> -}
> -
> void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
> unsigned long addr, pte_t *ptep,
> pte_t old_pte, pte_t pte)
> diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
> index c83be371c6e7..4c3e9601fdf6 100644
> --- a/arch/powerpc/mm/book3s64/slice.c
> +++ b/arch/powerpc/mm/book3s64/slice.c
> @@ -777,4 +777,80 @@ int slice_is_hugepage_only_range(struct mm_struct *mm, unsigned long addr,
>
> return !slice_check_range_fits(mm, maskp, addr, len);
> }
> +
> +unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
> +{
> + /* With radix we don't use slice, so derive it from vma*/
> + if (radix_enabled())
> + return vma_kernel_pagesize(vma);
> +
> + return 1UL << mmu_psize_to_shift(get_slice_psize(vma->vm_mm, vma->vm_start));
> +}
> +
> +/*
> + * A variant of hugetlb_get_unmapped_area() doing topdown search
> + * FIXME!! should we do as x86 does or non hugetlb area does ?
> + * ie, use topdown or not based on mmap_is_legacy check ?
> + */
> +static unsigned long
> +radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
> + unsigned long pgoff, unsigned long flags)
> +{
> + struct mm_struct *mm = current->mm;
> + struct vm_area_struct *vma;
> + struct hstate *h = hstate_file(file);
> + int fixed = (flags & MAP_FIXED);
> + unsigned long high_limit;
> + struct vm_unmapped_area_info info;
> +
> + high_limit = DEFAULT_MAP_WINDOW;
> + if (addr >= high_limit || (fixed && (addr + len > high_limit)))
> + high_limit = TASK_SIZE;
> +
> + if (len & ~huge_page_mask(h))
> + return -EINVAL;
> + if (len > high_limit)
> + return -ENOMEM;
> +
> + if (fixed) {
> + if (addr > high_limit - len)
> + return -ENOMEM;
> + if (prepare_hugepage_range(file, addr, len))
> + return -EINVAL;
> + return addr;
> + }
> +
> + if (addr) {
> + addr = ALIGN(addr, huge_page_size(h));
> + vma = find_vma(mm, addr);
> + if (high_limit - len >= addr && addr >= mmap_min_addr &&
> + (!vma || addr + len <= vm_start_gap(vma)))
> + return addr;
> + }
> + /*
> + * We are always doing an topdown search here. Slice code
> + * does that too.
> + */
> + info.flags = VM_UNMAPPED_AREA_TOPDOWN;
> + info.length = len;
> + info.low_limit = max(PAGE_SIZE, mmap_min_addr);
> + info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
> + info.align_mask = PAGE_MASK & ~huge_page_mask(h);
> + info.align_offset = 0;
> +
> + return vm_unmapped_area(&info);
> +}
> +
> +unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
> + unsigned long len, unsigned long pgoff,
> + unsigned long flags)
> +{
> + struct hstate *hstate = hstate_file(file);
> + int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
> +
> + if (radix_enabled())
> + return radix__hugetlb_get_unmapped_area(file, addr, len, pgoff, flags);
> +
> + return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
> +}
> #endif
> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index 82d8b368ca6d..eb9de09e49a3 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -542,34 +542,6 @@ struct page *follow_huge_pd(struct vm_area_struct *vma,
> return page;
> }
>
> -#ifdef CONFIG_PPC_MM_SLICES
> -unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
> - unsigned long len, unsigned long pgoff,
> - unsigned long flags)
> -{
> - struct hstate *hstate = hstate_file(file);
> - int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
> -
> -#ifdef CONFIG_PPC_RADIX_MMU
> - if (radix_enabled())
> - return radix__hugetlb_get_unmapped_area(file, addr, len,
> - pgoff, flags);
> -#endif
> - return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1);
> -}
> -#endif
> -
> -unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
> -{
> - /* With radix we don't use slice, so derive it from vma*/
> - if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled()) {
> - unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
> -
> - return 1UL << mmu_psize_to_shift(psize);
> - }
> - return vma_kernel_pagesize(vma);
> -}
> -
> bool __init arch_hugetlb_valid_size(unsigned long size)
> {
> int shift = __ffs(size);
> --
> 2.33.1
>
>
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v2 rebased 3/9] powerpc/mm: Remove CONFIG_PPC_MM_SLICES
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 1/9] powerpc/mm: Make slice specific to book3s/64 Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 2/9] powerpc/mm: Move vma_mmu_pagesize() and hugetlb_get_unmapped_area() to slice.c Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 5:50 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 4/9] powerpc/mm: Remove asm/slice.h Christophe Leroy
` (5 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
CONFIG_PPC_MM_SLICES is always selected by hash book3s/64.
CONFIG_PPC_MM_SLICES is never selected by other platforms.
Remove it.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/64/hash.h | 4 ++--
arch/powerpc/include/asm/hugetlb.h | 2 +-
arch/powerpc/include/asm/paca.h | 7 -------
arch/powerpc/include/asm/slice.h | 13 ++-----------
arch/powerpc/kernel/paca.c | 5 -----
arch/powerpc/mm/book3s64/Makefile | 3 +--
arch/powerpc/mm/book3s64/hash_utils.c | 14 --------------
arch/powerpc/platforms/Kconfig.cputype | 4 ----
8 files changed, 6 insertions(+), 46 deletions(-)
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 674fe0e890dc..97f2fc217a49 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -99,10 +99,10 @@
* Defines the address of the vmemap area, in its own region on
* hash table CPUs.
*/
-#ifdef CONFIG_PPC_MM_SLICES
+#ifdef CONFIG_PPC_64S_HASH_MMU
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-#endif /* CONFIG_PPC_MM_SLICES */
+#endif
/* PTEIDX nibble */
#define _PTEIDX_SECONDARY 0x8
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index f18c543bc01d..86a60ba6bd2a 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -24,7 +24,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
unsigned long addr,
unsigned long len)
{
- if (IS_ENABLED(CONFIG_PPC_MM_SLICES) && !radix_enabled())
+ if (IS_ENABLED(CONFIG_PPC_64S_HASH_MMU) && !radix_enabled())
return slice_is_hugepage_only_range(mm, addr, len);
return 0;
}
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index 295573a82c66..bd4dd02e61c8 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -152,16 +152,9 @@ struct paca_struct {
struct tlb_core_data tcd;
#endif /* CONFIG_PPC_BOOK3E */
-#ifdef CONFIG_PPC_BOOK3S
#ifdef CONFIG_PPC_64S_HASH_MMU
-#ifdef CONFIG_PPC_MM_SLICES
unsigned char mm_ctx_low_slices_psize[BITS_PER_LONG / BITS_PER_BYTE];
unsigned char mm_ctx_high_slices_psize[SLICE_ARRAY_SIZE];
-#else
- u16 mm_ctx_user_psize;
- u16 mm_ctx_sllp;
-#endif
-#endif
#endif
/*
diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h
index 0bdd9c62eca0..b15141f2bd76 100644
--- a/arch/powerpc/include/asm/slice.h
+++ b/arch/powerpc/include/asm/slice.h
@@ -10,7 +10,7 @@
struct mm_struct;
-#ifdef CONFIG_PPC_MM_SLICES
+#ifdef CONFIG_PPC_64S_HASH_MMU
#ifdef CONFIG_HUGETLB_PAGE
#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
@@ -30,16 +30,7 @@ void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
void slice_init_new_context_exec(struct mm_struct *mm);
void slice_setup_new_exec(void);
-#else /* CONFIG_PPC_MM_SLICES */
-
-static inline void slice_init_new_context_exec(struct mm_struct *mm) {}
-
-static inline unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr)
-{
- return 0;
-}
-
-#endif /* CONFIG_PPC_MM_SLICES */
+#endif /* CONFIG_PPC_64S_HASH_MMU */
#endif /* __ASSEMBLY__ */
diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c
index 39da688a9455..ba593fd60124 100644
--- a/arch/powerpc/kernel/paca.c
+++ b/arch/powerpc/kernel/paca.c
@@ -344,15 +344,10 @@ void copy_mm_to_paca(struct mm_struct *mm)
{
mm_context_t *context = &mm->context;
-#ifdef CONFIG_PPC_MM_SLICES
VM_BUG_ON(!mm_ctx_slb_addr_limit(context));
memcpy(&get_paca()->mm_ctx_low_slices_psize, mm_ctx_low_slices(context),
LOW_SLICE_ARRAY_SZ);
memcpy(&get_paca()->mm_ctx_high_slices_psize, mm_ctx_high_slices(context),
TASK_SLICE_ARRAY_SZ(context));
-#else /* CONFIG_PPC_MM_SLICES */
- get_paca()->mm_ctx_user_psize = context->user_psize;
- get_paca()->mm_ctx_sllp = context->sllp;
-#endif
}
#endif /* CONFIG_PPC_64S_HASH_MMU */
diff --git a/arch/powerpc/mm/book3s64/Makefile b/arch/powerpc/mm/book3s64/Makefile
index af2f3e75d458..d527dc8e30a8 100644
--- a/arch/powerpc/mm/book3s64/Makefile
+++ b/arch/powerpc/mm/book3s64/Makefile
@@ -5,7 +5,7 @@ ccflags-y := $(NO_MINIMAL_TOC)
obj-y += mmu_context.o pgtable.o trace.o
ifdef CONFIG_PPC_64S_HASH_MMU
CFLAGS_REMOVE_slb.o = $(CC_FLAGS_FTRACE)
-obj-y += hash_pgtable.o hash_utils.o hash_tlb.o slb.o
+obj-y += hash_pgtable.o hash_utils.o hash_tlb.o slb.o slice.o
obj-$(CONFIG_PPC_HASH_MMU_NATIVE) += hash_native.o
obj-$(CONFIG_PPC_4K_PAGES) += hash_4k.o
obj-$(CONFIG_PPC_64K_PAGES) += hash_64k.o
@@ -21,7 +21,6 @@ obj-$(CONFIG_PPC_RADIX_MMU) += radix_hugetlbpage.o
endif
obj-$(CONFIG_SPAPR_TCE_IOMMU) += iommu_api.o
obj-$(CONFIG_PPC_PKEY) += pkeys.o
-obj-$(CONFIG_PPC_MM_SLICES) += slice.o
# Instrumenting the SLB fault path can lead to duplicate SLB entries
KCOV_INSTRUMENT_slb.o := n
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index eced266dc5e9..7ecadf5e6bf9 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -1264,7 +1264,6 @@ unsigned int hash_page_do_lazy_icache(unsigned int pp, pte_t pte, int trap)
return pp;
}
-#ifdef CONFIG_PPC_MM_SLICES
static unsigned int get_paca_psize(unsigned long addr)
{
unsigned char *psizes;
@@ -1281,12 +1280,6 @@ static unsigned int get_paca_psize(unsigned long addr)
return (psizes[index >> 1] >> (mask_index * 4)) & 0xF;
}
-#else
-unsigned int get_paca_psize(unsigned long addr)
-{
- return get_paca()->mm_ctx_user_psize;
-}
-#endif
/*
* Demote a segment to using 4k pages.
@@ -1710,7 +1703,6 @@ DEFINE_INTERRUPT_HANDLER_RAW(do_hash_fault)
return 0;
}
-#ifdef CONFIG_PPC_MM_SLICES
static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
{
int psize = get_slice_psize(mm, ea);
@@ -1727,12 +1719,6 @@ static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
return true;
}
-#else
-static bool should_hash_preload(struct mm_struct *mm, unsigned long ea)
-{
- return true;
-}
-#endif
static void hash_preload(struct mm_struct *mm, pte_t *ptep, unsigned long ea,
bool is_exec, unsigned long trap)
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 7806a9661aa4..307e61ea65b8 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -374,7 +374,6 @@ config SPE
config PPC_64S_HASH_MMU
bool "Hash MMU Support"
depends on PPC_BOOK3S_64
- select PPC_MM_SLICES
default y
help
Enable support for the Power ISA Hash style MMU. This is implemented
@@ -451,9 +450,6 @@ config PPC_BOOK3E_MMU
def_bool y
depends on FSL_BOOKE || PPC_BOOK3E
-config PPC_MM_SLICES
- bool
-
config PPC_HAVE_PMU_SUPPORT
bool
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v2 rebased 3/9] powerpc/mm: Remove CONFIG_PPC_MM_SLICES
2021-11-25 17:52 ` [PATCH v2 rebased 3/9] powerpc/mm: Remove CONFIG_PPC_MM_SLICES Christophe Leroy
@ 2021-12-01 5:50 ` Nicholas Piggin
0 siblings, 0 replies; 16+ messages in thread
From: Nicholas Piggin @ 2021-12-01 5:50 UTC (permalink / raw)
To: alex, Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linux-kernel, linux-mm, linuxppc-dev
Excerpts from Christophe Leroy's message of November 26, 2021 3:52 am:
> CONFIG_PPC_MM_SLICES is always selected by hash book3s/64.
> CONFIG_PPC_MM_SLICES is never selected by other platforms.
>
> Remove it.
I guess there is some remnants of code/data to build 64s hash without
slices. Maybe without any huge page support? I guess it's probably
broken if it never =n, and not worth maintaining anyway?
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
> arch/powerpc/include/asm/book3s/64/hash.h | 4 ++--
> arch/powerpc/include/asm/hugetlb.h | 2 +-
> arch/powerpc/include/asm/paca.h | 7 -------
> arch/powerpc/include/asm/slice.h | 13 ++-----------
> arch/powerpc/kernel/paca.c | 5 -----
> arch/powerpc/mm/book3s64/Makefile | 3 +--
> arch/powerpc/mm/book3s64/hash_utils.c | 14 --------------
> arch/powerpc/platforms/Kconfig.cputype | 4 ----
> 8 files changed, 6 insertions(+), 46 deletions(-)
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v2 rebased 4/9] powerpc/mm: Remove asm/slice.h
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (2 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 3/9] powerpc/mm: Remove CONFIG_PPC_MM_SLICES Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 5:51 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 5/9] powerpc/mm: Call radix__arch_get_unmapped_area() from arch_get_unmapped_area() Christophe Leroy
` (4 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Move necessary stuff in asm/book3s/64/slice.h and
remove asm/slice.h
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/include/asm/book3s/64/hash.h | 3 ++
arch/powerpc/include/asm/book3s/64/mmu-hash.h | 1 +
arch/powerpc/include/asm/book3s/64/slice.h | 18 +++++++++
arch/powerpc/include/asm/page.h | 1 -
arch/powerpc/include/asm/slice.h | 37 -------------------
5 files changed, 22 insertions(+), 38 deletions(-)
delete mode 100644 arch/powerpc/include/asm/slice.h
diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h
index 97f2fc217a49..fab032f552f3 100644
--- a/arch/powerpc/include/asm/book3s/64/hash.h
+++ b/arch/powerpc/include/asm/book3s/64/hash.h
@@ -100,6 +100,9 @@
* hash table CPUs.
*/
#ifdef CONFIG_PPC_64S_HASH_MMU
+#ifdef CONFIG_HUGETLB_PAGE
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#endif
diff --git a/arch/powerpc/include/asm/book3s/64/mmu-hash.h b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
index 3004f3323144..b4b2ca111f75 100644
--- a/arch/powerpc/include/asm/book3s/64/mmu-hash.h
+++ b/arch/powerpc/include/asm/book3s/64/mmu-hash.h
@@ -18,6 +18,7 @@
* complete pgtable.h but only a portion of it.
*/
#include <asm/book3s/64/pgtable.h>
+#include <asm/book3s/64/slice.h>
#include <asm/task_size_64.h>
#include <asm/cpu_has_feature.h>
diff --git a/arch/powerpc/include/asm/book3s/64/slice.h b/arch/powerpc/include/asm/book3s/64/slice.h
index f0d3194ba41b..5b0f7105bc8b 100644
--- a/arch/powerpc/include/asm/book3s/64/slice.h
+++ b/arch/powerpc/include/asm/book3s/64/slice.h
@@ -2,6 +2,8 @@
#ifndef _ASM_POWERPC_BOOK3S_64_SLICE_H
#define _ASM_POWERPC_BOOK3S_64_SLICE_H
+#ifndef __ASSEMBLY__
+
#define SLICE_LOW_SHIFT 28
#define SLICE_LOW_TOP (0x100000000ul)
#define SLICE_NUM_LOW (SLICE_LOW_TOP >> SLICE_LOW_SHIFT)
@@ -13,4 +15,20 @@
#define SLB_ADDR_LIMIT_DEFAULT DEFAULT_MAP_WINDOW_USER64
+struct mm_struct;
+
+unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
+ unsigned long flags, unsigned int psize,
+ int topdown);
+
+unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
+
+void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
+ unsigned long len, unsigned int psize);
+
+void slice_init_new_context_exec(struct mm_struct *mm);
+void slice_setup_new_exec(void);
+
+#endif /* __ASSEMBLY__ */
+
#endif /* _ASM_POWERPC_BOOK3S_64_SLICE_H */
diff --git a/arch/powerpc/include/asm/page.h b/arch/powerpc/include/asm/page.h
index 254687258f42..62e0c6f12869 100644
--- a/arch/powerpc/include/asm/page.h
+++ b/arch/powerpc/include/asm/page.h
@@ -329,6 +329,5 @@ static inline unsigned long kaslr_offset(void)
#include <asm-generic/memory_model.h>
#endif /* __ASSEMBLY__ */
-#include <asm/slice.h>
#endif /* _ASM_POWERPC_PAGE_H */
diff --git a/arch/powerpc/include/asm/slice.h b/arch/powerpc/include/asm/slice.h
deleted file mode 100644
index b15141f2bd76..000000000000
--- a/arch/powerpc/include/asm/slice.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_POWERPC_SLICE_H
-#define _ASM_POWERPC_SLICE_H
-
-#ifdef CONFIG_PPC_BOOK3S_64
-#include <asm/book3s/64/slice.h>
-#endif
-
-#ifndef __ASSEMBLY__
-
-struct mm_struct;
-
-#ifdef CONFIG_PPC_64S_HASH_MMU
-
-#ifdef CONFIG_HUGETLB_PAGE
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-#define HAVE_ARCH_UNMAPPED_AREA
-#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-
-unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
- unsigned long flags, unsigned int psize,
- int topdown);
-
-unsigned int get_slice_psize(struct mm_struct *mm, unsigned long addr);
-
-void slice_set_range_psize(struct mm_struct *mm, unsigned long start,
- unsigned long len, unsigned int psize);
-
-void slice_init_new_context_exec(struct mm_struct *mm);
-void slice_setup_new_exec(void);
-
-#endif /* CONFIG_PPC_64S_HASH_MMU */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _ASM_POWERPC_SLICE_H */
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v2 rebased 5/9] powerpc/mm: Call radix__arch_get_unmapped_area() from arch_get_unmapped_area()
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (3 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 4/9] powerpc/mm: Remove asm/slice.h Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 6:00 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 6/9] mm: Allow arch specific arch_randomize_brk() with CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT Christophe Leroy
` (3 subsequent siblings)
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Instead of setting mm->get_unmapped_area() to either
arch_get_unmapped_area() or radix__arch_get_unmapped_area(),
always set it to arch_get_unmapped_area() and call
radix__arch_get_unmapped_area() from there when radix is enabled.
To keep radix__arch_get_unmapped_area() static, move it to slice.c
Do the same with radix__arch_get_unmapped_area_topdown()
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/book3s64/slice.c | 104 ++++++++++++++++++++++++++
arch/powerpc/mm/mmap.c | 123 -------------------------------
2 files changed, 104 insertions(+), 123 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index 4c3e9601fdf6..99742dde811c 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -639,12 +639,113 @@ unsigned long slice_get_unmapped_area(unsigned long addr, unsigned long len,
}
EXPORT_SYMBOL_GPL(slice_get_unmapped_area);
+/*
+ * Same function as generic code used only for radix, because we don't need to overload
+ * the generic one. But we will have to duplicate, because hash select
+ * HAVE_ARCH_UNMAPPED_AREA
+ */
+static unsigned long
+radix__arch_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len,
+ unsigned long pgoff, unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int fixed = (flags & MAP_FIXED);
+ unsigned long high_limit;
+ struct vm_unmapped_area_info info;
+
+ high_limit = DEFAULT_MAP_WINDOW;
+ if (addr >= high_limit || (fixed && (addr + len > high_limit)))
+ high_limit = TASK_SIZE;
+
+ if (len > high_limit)
+ return -ENOMEM;
+
+ if (fixed) {
+ if (addr > high_limit - len)
+ return -ENOMEM;
+ return addr;
+ }
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (high_limit - len >= addr && addr >= mmap_min_addr &&
+ (!vma || addr + len <= vm_start_gap(vma)))
+ return addr;
+ }
+
+ info.flags = 0;
+ info.length = len;
+ info.low_limit = mm->mmap_base;
+ info.high_limit = high_limit;
+ info.align_mask = 0;
+
+ return vm_unmapped_area(&info);
+}
+
+static unsigned long
+radix__arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
+ const unsigned long len, const unsigned long pgoff,
+ const unsigned long flags)
+{
+ struct vm_area_struct *vma;
+ struct mm_struct *mm = current->mm;
+ unsigned long addr = addr0;
+ int fixed = (flags & MAP_FIXED);
+ unsigned long high_limit;
+ struct vm_unmapped_area_info info;
+
+ high_limit = DEFAULT_MAP_WINDOW;
+ if (addr >= high_limit || (fixed && (addr + len > high_limit)))
+ high_limit = TASK_SIZE;
+
+ if (len > high_limit)
+ return -ENOMEM;
+
+ if (fixed) {
+ if (addr > high_limit - len)
+ return -ENOMEM;
+ return addr;
+ }
+
+ if (addr) {
+ addr = PAGE_ALIGN(addr);
+ vma = find_vma(mm, addr);
+ if (high_limit - len >= addr && addr >= mmap_min_addr &&
+ (!vma || addr + len <= vm_start_gap(vma)))
+ return addr;
+ }
+
+ info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+ info.length = len;
+ info.low_limit = max(PAGE_SIZE, mmap_min_addr);
+ info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
+ info.align_mask = 0;
+
+ addr = vm_unmapped_area(&info);
+ if (!(addr & ~PAGE_MASK))
+ return addr;
+ VM_BUG_ON(addr != -ENOMEM);
+
+ /*
+ * A failed mmap() very likely causes application failure,
+ * so fall back to the bottom-up function here. This scenario
+ * can happen with large stack limits and large mmap()
+ * allocations.
+ */
+ return radix__arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+}
+
unsigned long arch_get_unmapped_area(struct file *filp,
unsigned long addr,
unsigned long len,
unsigned long pgoff,
unsigned long flags)
{
+ if (radix_enabled())
+ return radix__arch_get_unmapped_area(filp, addr, len, pgoff, flags);
+
return slice_get_unmapped_area(addr, len, flags,
mm_ctx_user_psize(¤t->mm->context), 0);
}
@@ -655,6 +756,9 @@ unsigned long arch_get_unmapped_area_topdown(struct file *filp,
const unsigned long pgoff,
const unsigned long flags)
{
+ if (radix_enabled())
+ return radix__arch_get_unmapped_area_topdown(filp, addr0, len, pgoff, flags);
+
return slice_get_unmapped_area(addr0, len, flags,
mm_ctx_user_psize(¤t->mm->context), 1);
}
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
index ae683fdc716c..5972d619d274 100644
--- a/arch/powerpc/mm/mmap.c
+++ b/arch/powerpc/mm/mmap.c
@@ -80,126 +80,6 @@ static inline unsigned long mmap_base(unsigned long rnd,
return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
}
-#ifdef CONFIG_PPC_RADIX_MMU
-/*
- * Same function as generic code used only for radix, because we don't need to overload
- * the generic one. But we will have to duplicate, because hash select
- * HAVE_ARCH_UNMAPPED_AREA
- */
-static unsigned long
-radix__arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
-{
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- int fixed = (flags & MAP_FIXED);
- unsigned long high_limit;
- struct vm_unmapped_area_info info;
-
- high_limit = DEFAULT_MAP_WINDOW;
- if (addr >= high_limit || (fixed && (addr + len > high_limit)))
- high_limit = TASK_SIZE;
-
- if (len > high_limit)
- return -ENOMEM;
-
- if (fixed) {
- if (addr > high_limit - len)
- return -ENOMEM;
- return addr;
- }
-
- if (addr) {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (high_limit - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
- info.flags = 0;
- info.length = len;
- info.low_limit = mm->mmap_base;
- info.high_limit = high_limit;
- info.align_mask = 0;
-
- return vm_unmapped_area(&info);
-}
-
-static unsigned long
-radix__arch_get_unmapped_area_topdown(struct file *filp,
- const unsigned long addr0,
- const unsigned long len,
- const unsigned long pgoff,
- const unsigned long flags)
-{
- struct vm_area_struct *vma;
- struct mm_struct *mm = current->mm;
- unsigned long addr = addr0;
- int fixed = (flags & MAP_FIXED);
- unsigned long high_limit;
- struct vm_unmapped_area_info info;
-
- high_limit = DEFAULT_MAP_WINDOW;
- if (addr >= high_limit || (fixed && (addr + len > high_limit)))
- high_limit = TASK_SIZE;
-
- if (len > high_limit)
- return -ENOMEM;
-
- if (fixed) {
- if (addr > high_limit - len)
- return -ENOMEM;
- return addr;
- }
-
- if (addr) {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (high_limit - len >= addr && addr >= mmap_min_addr &&
- (!vma || addr + len <= vm_start_gap(vma)))
- return addr;
- }
-
- info.flags = VM_UNMAPPED_AREA_TOPDOWN;
- info.length = len;
- info.low_limit = max(PAGE_SIZE, mmap_min_addr);
- info.high_limit = mm->mmap_base + (high_limit - DEFAULT_MAP_WINDOW);
- info.align_mask = 0;
-
- addr = vm_unmapped_area(&info);
- if (!(addr & ~PAGE_MASK))
- return addr;
- VM_BUG_ON(addr != -ENOMEM);
-
- /*
- * A failed mmap() very likely causes application failure,
- * so fall back to the bottom-up function here. This scenario
- * can happen with large stack limits and large mmap()
- * allocations.
- */
- return radix__arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
-}
-
-static void radix__arch_pick_mmap_layout(struct mm_struct *mm,
- unsigned long random_factor,
- struct rlimit *rlim_stack)
-{
- if (mmap_is_legacy(rlim_stack)) {
- mm->mmap_base = TASK_UNMAPPED_BASE;
- mm->get_unmapped_area = radix__arch_get_unmapped_area;
- } else {
- mm->mmap_base = mmap_base(random_factor, rlim_stack);
- mm->get_unmapped_area = radix__arch_get_unmapped_area_topdown;
- }
-}
-#else
-/* dummy */
-extern void radix__arch_pick_mmap_layout(struct mm_struct *mm,
- unsigned long random_factor,
- struct rlimit *rlim_stack);
-#endif
/*
* This function, called very early during the creation of a new
* process VM image, sets up which VM layout function to use:
@@ -211,9 +91,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
if (current->flags & PF_RANDOMIZE)
random_factor = arch_mmap_rnd();
- if (radix_enabled())
- return radix__arch_pick_mmap_layout(mm, random_factor,
- rlim_stack);
/*
* Fall back to the standard layout if the personality
* bit is set, or if the expected stack growth is unlimited:
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v2 rebased 5/9] powerpc/mm: Call radix__arch_get_unmapped_area() from arch_get_unmapped_area()
2021-11-25 17:52 ` [PATCH v2 rebased 5/9] powerpc/mm: Call radix__arch_get_unmapped_area() from arch_get_unmapped_area() Christophe Leroy
@ 2021-12-01 6:00 ` Nicholas Piggin
0 siblings, 0 replies; 16+ messages in thread
From: Nicholas Piggin @ 2021-12-01 6:00 UTC (permalink / raw)
To: alex, Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linux-kernel, linux-mm, linuxppc-dev
Excerpts from Christophe Leroy's message of November 26, 2021 3:52 am:
> Instead of setting mm->get_unmapped_area() to either
> arch_get_unmapped_area() or radix__arch_get_unmapped_area(),
> always set it to arch_get_unmapped_area() and call
> radix__arch_get_unmapped_area() from there when radix is enabled.
>
> To keep radix__arch_get_unmapped_area() static, move it to slice.c
>
> Do the same with radix__arch_get_unmapped_area_topdown()
Same comment with this one really. It would be better if we can
reuse generic code.
Thanks,
Nick
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v2 rebased 6/9] mm: Allow arch specific arch_randomize_brk() with CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (4 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 5/9] powerpc/mm: Call radix__arch_get_unmapped_area() from arch_get_unmapped_area() Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 7/9] powerpc/mm: Convert to default topdown mmap layout Christophe Leroy
` (2 subsequent siblings)
8 siblings, 0 replies; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Commit e7142bf5d231 ("arm64, mm: make randomization selected by
generic topdown mmap layout") introduced a default version of
arch_randomize_brk() provided when
CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT is selected.
powerpc could select CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
but needs to provide its own arch_randomize_brk().
In order to allow that, define generic version of arch_randomize_brk()
as a __weak symbol.
Cc: Alexandre Ghiti <alex@ghiti.fr>
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2: Make the generic version of it a __weak symbol instead of a messy play with CONFIG_ items.
---
mm/util.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/mm/util.c b/mm/util.c
index e58151a61255..7eb69f697b38 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -344,7 +344,7 @@ unsigned long randomize_stack_top(unsigned long stack_top)
}
#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
-unsigned long arch_randomize_brk(struct mm_struct *mm)
+unsigned long __weak arch_randomize_brk(struct mm_struct *mm)
{
/* Is the current task 32bit ? */
if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v2 rebased 7/9] powerpc/mm: Convert to default topdown mmap layout
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (5 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 6/9] mm: Allow arch specific arch_randomize_brk() with CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-12-01 6:06 ` Nicholas Piggin
2021-11-25 17:52 ` [PATCH v2 rebased 8/9] powerpc/mm: Properly randomise mmap with slices Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 9/9] powerpc: Simplify and move arch_randomize_brk() Christophe Leroy
8 siblings, 1 reply; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Select CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT and
remove arch/powerpc/mm/mmap.c
This change provides standard randomisation of mmaps.
See commit 8b8addf891de ("x86/mm/32: Enable full randomization on i386
and X86_32") for all the benefits of mmap randomisation.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v2: Also remove selection of ARCH_HAS_ELF_RANDOMIZE as it is already selected by CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
---
arch/powerpc/Kconfig | 2 +-
arch/powerpc/include/asm/processor.h | 2 -
arch/powerpc/mm/Makefile | 2 +-
arch/powerpc/mm/mmap.c | 105 ---------------------------
4 files changed, 2 insertions(+), 109 deletions(-)
delete mode 100644 arch/powerpc/mm/mmap.c
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fb48823ccd62..20504a9901f2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -122,7 +122,6 @@ config PPC
select ARCH_HAS_DEBUG_WX if STRICT_KERNEL_RWX
select ARCH_HAS_DEVMEM_IS_ALLOWED
select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES
- select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_HUGEPD if HUGETLB_PAGE
@@ -158,6 +157,7 @@ config PPC
select ARCH_USE_MEMTEST
select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS
select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS
+ select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
select ARCH_WANT_IPC_PARSE_VERSION
select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
select ARCH_WANT_LD_ORPHAN_WARN
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index e39bd0ff69f3..d906b14dd599 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -378,8 +378,6 @@ static inline void prefetchw(const void *x)
#define spin_lock_prefetch(x) prefetchw(x)
-#define HAVE_ARCH_PICK_MMAP_LAYOUT
-
/* asm stubs */
extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index d4c20484dad9..503a6e249940 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -5,7 +5,7 @@
ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
-obj-y := fault.o mem.o pgtable.o mmap.o maccess.o pageattr.o \
+obj-y := fault.o mem.o pgtable.o maccess.o pageattr.o \
init_$(BITS).o pgtable_$(BITS).o \
pgtable-frag.o ioremap.o ioremap_$(BITS).o \
init-common.o mmu_context.o drmem.o \
diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
deleted file mode 100644
index 5972d619d274..000000000000
--- a/arch/powerpc/mm/mmap.c
+++ /dev/null
@@ -1,105 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * flexible mmap layout support
- *
- * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
- * All Rights Reserved.
- *
- * Started by Ingo Molnar <mingo@elte.hu>
- */
-
-#include <linux/personality.h>
-#include <linux/mm.h>
-#include <linux/random.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/mm.h>
-#include <linux/elf-randomize.h>
-#include <linux/security.h>
-#include <linux/mman.h>
-
-/*
- * Top of mmap area (just below the process stack).
- *
- * Leave at least a ~128 MB hole.
- */
-#define MIN_GAP (128*1024*1024)
-#define MAX_GAP (TASK_SIZE/6*5)
-
-static inline int mmap_is_legacy(struct rlimit *rlim_stack)
-{
- if (current->personality & ADDR_COMPAT_LAYOUT)
- return 1;
-
- if (rlim_stack->rlim_cur == RLIM_INFINITY)
- return 1;
-
- return sysctl_legacy_va_layout;
-}
-
-unsigned long arch_mmap_rnd(void)
-{
- unsigned long shift, rnd;
-
- shift = mmap_rnd_bits;
-#ifdef CONFIG_COMPAT
- if (is_32bit_task())
- shift = mmap_rnd_compat_bits;
-#endif
- rnd = get_random_long() % (1ul << shift);
-
- return rnd << PAGE_SHIFT;
-}
-
-static inline unsigned long stack_maxrandom_size(void)
-{
- if (!(current->flags & PF_RANDOMIZE))
- return 0;
-
- /* 8MB for 32bit, 1GB for 64bit */
- if (is_32bit_task())
- return (1<<23);
- else
- return (1<<30);
-}
-
-static inline unsigned long mmap_base(unsigned long rnd,
- struct rlimit *rlim_stack)
-{
- unsigned long gap = rlim_stack->rlim_cur;
- unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
-
- /* Values close to RLIM_INFINITY can overflow. */
- if (gap + pad > gap)
- gap += pad;
-
- if (gap < MIN_GAP)
- gap = MIN_GAP;
- else if (gap > MAX_GAP)
- gap = MAX_GAP;
-
- return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
-}
-
-/*
- * This function, called very early during the creation of a new
- * process VM image, sets up which VM layout function to use:
- */
-void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
-{
- unsigned long random_factor = 0UL;
-
- if (current->flags & PF_RANDOMIZE)
- random_factor = arch_mmap_rnd();
-
- /*
- * Fall back to the standard layout if the personality
- * bit is set, or if the expected stack growth is unlimited:
- */
- if (mmap_is_legacy(rlim_stack)) {
- mm->mmap_base = TASK_UNMAPPED_BASE;
- mm->get_unmapped_area = arch_get_unmapped_area;
- } else {
- mm->mmap_base = mmap_base(random_factor, rlim_stack);
- mm->get_unmapped_area = arch_get_unmapped_area_topdown;
- }
-}
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* Re: [PATCH v2 rebased 7/9] powerpc/mm: Convert to default topdown mmap layout
2021-11-25 17:52 ` [PATCH v2 rebased 7/9] powerpc/mm: Convert to default topdown mmap layout Christophe Leroy
@ 2021-12-01 6:06 ` Nicholas Piggin
0 siblings, 0 replies; 16+ messages in thread
From: Nicholas Piggin @ 2021-12-01 6:06 UTC (permalink / raw)
To: alex, Benjamin Herrenschmidt, Christophe Leroy, Michael Ellerman,
Paul Mackerras
Cc: linux-kernel, linux-mm, linuxppc-dev
Excerpts from Christophe Leroy's message of November 26, 2021 3:52 am:
> Select CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT and
> remove arch/powerpc/mm/mmap.c
>
> This change provides standard randomisation of mmaps.
>
> See commit 8b8addf891de ("x86/mm/32: Enable full randomization on i386
> and X86_32") for all the benefits of mmap randomisation.
What's the actual difference before/after this patch? The mm/util.c
code looks very similar to the code removed with a few small
differences. Can these differences be explained in this patch?
Thanks,
Nick
>
> Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
> ---
> v2: Also remove selection of ARCH_HAS_ELF_RANDOMIZE as it is already selected by CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
> ---
> arch/powerpc/Kconfig | 2 +-
> arch/powerpc/include/asm/processor.h | 2 -
> arch/powerpc/mm/Makefile | 2 +-
> arch/powerpc/mm/mmap.c | 105 ---------------------------
> 4 files changed, 2 insertions(+), 109 deletions(-)
> delete mode 100644 arch/powerpc/mm/mmap.c
>
> diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
> index fb48823ccd62..20504a9901f2 100644
> --- a/arch/powerpc/Kconfig
> +++ b/arch/powerpc/Kconfig
> @@ -122,7 +122,6 @@ config PPC
> select ARCH_HAS_DEBUG_WX if STRICT_KERNEL_RWX
> select ARCH_HAS_DEVMEM_IS_ALLOWED
> select ARCH_HAS_DMA_MAP_DIRECT if PPC_PSERIES
> - select ARCH_HAS_ELF_RANDOMIZE
> select ARCH_HAS_FORTIFY_SOURCE
> select ARCH_HAS_GCOV_PROFILE_ALL
> select ARCH_HAS_HUGEPD if HUGETLB_PAGE
> @@ -158,6 +157,7 @@ config PPC
> select ARCH_USE_MEMTEST
> select ARCH_USE_QUEUED_RWLOCKS if PPC_QUEUED_SPINLOCKS
> select ARCH_USE_QUEUED_SPINLOCKS if PPC_QUEUED_SPINLOCKS
> + select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
> select ARCH_WANT_IPC_PARSE_VERSION
> select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
> select ARCH_WANT_LD_ORPHAN_WARN
> diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
> index e39bd0ff69f3..d906b14dd599 100644
> --- a/arch/powerpc/include/asm/processor.h
> +++ b/arch/powerpc/include/asm/processor.h
> @@ -378,8 +378,6 @@ static inline void prefetchw(const void *x)
>
> #define spin_lock_prefetch(x) prefetchw(x)
>
> -#define HAVE_ARCH_PICK_MMAP_LAYOUT
> -
> /* asm stubs */
> extern unsigned long isa300_idle_stop_noloss(unsigned long psscr_val);
> extern unsigned long isa300_idle_stop_mayloss(unsigned long psscr_val);
> diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
> index d4c20484dad9..503a6e249940 100644
> --- a/arch/powerpc/mm/Makefile
> +++ b/arch/powerpc/mm/Makefile
> @@ -5,7 +5,7 @@
>
> ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
>
> -obj-y := fault.o mem.o pgtable.o mmap.o maccess.o pageattr.o \
> +obj-y := fault.o mem.o pgtable.o maccess.o pageattr.o \
> init_$(BITS).o pgtable_$(BITS).o \
> pgtable-frag.o ioremap.o ioremap_$(BITS).o \
> init-common.o mmu_context.o drmem.o \
> diff --git a/arch/powerpc/mm/mmap.c b/arch/powerpc/mm/mmap.c
> deleted file mode 100644
> index 5972d619d274..000000000000
> --- a/arch/powerpc/mm/mmap.c
> +++ /dev/null
> @@ -1,105 +0,0 @@
> -// SPDX-License-Identifier: GPL-2.0-or-later
> -/*
> - * flexible mmap layout support
> - *
> - * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
> - * All Rights Reserved.
> - *
> - * Started by Ingo Molnar <mingo@elte.hu>
> - */
> -
> -#include <linux/personality.h>
> -#include <linux/mm.h>
> -#include <linux/random.h>
> -#include <linux/sched/signal.h>
> -#include <linux/sched/mm.h>
> -#include <linux/elf-randomize.h>
> -#include <linux/security.h>
> -#include <linux/mman.h>
> -
> -/*
> - * Top of mmap area (just below the process stack).
> - *
> - * Leave at least a ~128 MB hole.
> - */
> -#define MIN_GAP (128*1024*1024)
> -#define MAX_GAP (TASK_SIZE/6*5)
> -
> -static inline int mmap_is_legacy(struct rlimit *rlim_stack)
> -{
> - if (current->personality & ADDR_COMPAT_LAYOUT)
> - return 1;
> -
> - if (rlim_stack->rlim_cur == RLIM_INFINITY)
> - return 1;
> -
> - return sysctl_legacy_va_layout;
> -}
> -
> -unsigned long arch_mmap_rnd(void)
> -{
> - unsigned long shift, rnd;
> -
> - shift = mmap_rnd_bits;
> -#ifdef CONFIG_COMPAT
> - if (is_32bit_task())
> - shift = mmap_rnd_compat_bits;
> -#endif
> - rnd = get_random_long() % (1ul << shift);
> -
> - return rnd << PAGE_SHIFT;
> -}
> -
> -static inline unsigned long stack_maxrandom_size(void)
> -{
> - if (!(current->flags & PF_RANDOMIZE))
> - return 0;
> -
> - /* 8MB for 32bit, 1GB for 64bit */
> - if (is_32bit_task())
> - return (1<<23);
> - else
> - return (1<<30);
> -}
> -
> -static inline unsigned long mmap_base(unsigned long rnd,
> - struct rlimit *rlim_stack)
> -{
> - unsigned long gap = rlim_stack->rlim_cur;
> - unsigned long pad = stack_maxrandom_size() + stack_guard_gap;
> -
> - /* Values close to RLIM_INFINITY can overflow. */
> - if (gap + pad > gap)
> - gap += pad;
> -
> - if (gap < MIN_GAP)
> - gap = MIN_GAP;
> - else if (gap > MAX_GAP)
> - gap = MAX_GAP;
> -
> - return PAGE_ALIGN(DEFAULT_MAP_WINDOW - gap - rnd);
> -}
> -
> -/*
> - * This function, called very early during the creation of a new
> - * process VM image, sets up which VM layout function to use:
> - */
> -void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
> -{
> - unsigned long random_factor = 0UL;
> -
> - if (current->flags & PF_RANDOMIZE)
> - random_factor = arch_mmap_rnd();
> -
> - /*
> - * Fall back to the standard layout if the personality
> - * bit is set, or if the expected stack growth is unlimited:
> - */
> - if (mmap_is_legacy(rlim_stack)) {
> - mm->mmap_base = TASK_UNMAPPED_BASE;
> - mm->get_unmapped_area = arch_get_unmapped_area;
> - } else {
> - mm->mmap_base = mmap_base(random_factor, rlim_stack);
> - mm->get_unmapped_area = arch_get_unmapped_area_topdown;
> - }
> -}
> --
> 2.33.1
>
>
>
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v2 rebased 8/9] powerpc/mm: Properly randomise mmap with slices
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (6 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 7/9] powerpc/mm: Convert to default topdown mmap layout Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
2021-11-25 17:52 ` [PATCH v2 rebased 9/9] powerpc: Simplify and move arch_randomize_brk() Christophe Leroy
8 siblings, 0 replies; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
Now that powerpc switched to default topdown mmap layout,
mm->mmap_base is properly randomised. However
slice_find_area_bottomup() doesn't use mm->mmap_base but
uses the fixed TASK_UNMAPPED_BASE instead.
slice_find_area_bottomup() being used as a fallback to
slice_find_area_topdown(), it can't use mm->mmap_base
directly.
Instead of always using TASK_UNMAPPED_BASE as base address, leave
it to the caller. When called from slice_find_area_topdown()
TASK_UNMAPPED_BASE is used. Otherwise mm->mmap_base is used.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/mm/book3s64/slice.c | 18 +++++++-----------
1 file changed, 7 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/mm/book3s64/slice.c b/arch/powerpc/mm/book3s64/slice.c
index 99742dde811c..997f40184e97 100644
--- a/arch/powerpc/mm/book3s64/slice.c
+++ b/arch/powerpc/mm/book3s64/slice.c
@@ -276,20 +276,18 @@ static bool slice_scan_available(unsigned long addr,
}
static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
- unsigned long len,
+ unsigned long addr, unsigned long len,
const struct slice_mask *available,
int psize, unsigned long high_limit)
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
- unsigned long addr, found, next_end;
+ unsigned long found, next_end;
struct vm_unmapped_area_info info;
info.flags = 0;
info.length = len;
info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
info.align_offset = 0;
-
- addr = TASK_UNMAPPED_BASE;
/*
* Check till the allow max value for this mmap request
*/
@@ -322,12 +320,12 @@ static unsigned long slice_find_area_bottomup(struct mm_struct *mm,
}
static unsigned long slice_find_area_topdown(struct mm_struct *mm,
- unsigned long len,
+ unsigned long addr, unsigned long len,
const struct slice_mask *available,
int psize, unsigned long high_limit)
{
int pshift = max_t(int, mmu_psize_defs[psize].shift, PAGE_SHIFT);
- unsigned long addr, found, prev;
+ unsigned long found, prev;
struct vm_unmapped_area_info info;
unsigned long min_addr = max(PAGE_SIZE, mmap_min_addr);
@@ -335,8 +333,6 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
info.length = len;
info.align_mask = PAGE_MASK & ((1ul << pshift) - 1);
info.align_offset = 0;
-
- addr = mm->mmap_base;
/*
* If we are trying to allocate above DEFAULT_MAP_WINDOW
* Add the different to the mmap_base.
@@ -377,7 +373,7 @@ static unsigned long slice_find_area_topdown(struct mm_struct *mm,
* can happen with large stack limits and large mmap()
* allocations.
*/
- return slice_find_area_bottomup(mm, len, available, psize, high_limit);
+ return slice_find_area_bottomup(mm, TASK_UNMAPPED_BASE, len, available, psize, high_limit);
}
@@ -386,9 +382,9 @@ static unsigned long slice_find_area(struct mm_struct *mm, unsigned long len,
int topdown, unsigned long high_limit)
{
if (topdown)
- return slice_find_area_topdown(mm, len, mask, psize, high_limit);
+ return slice_find_area_topdown(mm, mm->mmap_base, len, mask, psize, high_limit);
else
- return slice_find_area_bottomup(mm, len, mask, psize, high_limit);
+ return slice_find_area_bottomup(mm, mm->mmap_base, len, mask, psize, high_limit);
}
static inline void slice_copy_mask(struct slice_mask *dst,
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread* [PATCH v2 rebased 9/9] powerpc: Simplify and move arch_randomize_brk()
2021-11-25 17:52 [PATCH v2 rebased 0/9] Convert powerpc to default topdown mmap layout Christophe Leroy
` (7 preceding siblings ...)
2021-11-25 17:52 ` [PATCH v2 rebased 8/9] powerpc/mm: Properly randomise mmap with slices Christophe Leroy
@ 2021-11-25 17:52 ` Christophe Leroy
8 siblings, 0 replies; 16+ messages in thread
From: Christophe Leroy @ 2021-11-25 17:52 UTC (permalink / raw)
To: Benjamin Herrenschmidt, Paul Mackerras, Michael Ellerman, alex
Cc: Christophe Leroy, linux-kernel, linuxppc-dev, linux-mm
arch_randomize_brk() is only needed for hash on book3s/64, for other
platforms the one provided by the default mmap layout is good enough.
Move it to hash_utils.c and use randomize_page() like the generic one.
And properly opt out the radix case instead of making an assumption
on mmu_highuser_ssize.
Also change to a 32M range like most other architectures instead of 8M.
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
v3: Add missing include <linux/elf-randomize.h>
v2: New
Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu>
---
arch/powerpc/kernel/process.c | 41 ---------------------------
arch/powerpc/mm/book3s64/hash_utils.c | 19 +++++++++++++
include/linux/sizes.h | 2 ++
3 files changed, 21 insertions(+), 41 deletions(-)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a64cfbb85ca2..44c4bce5211d 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -34,10 +34,8 @@
#include <linux/ftrace.h>
#include <linux/kernel_stat.h>
#include <linux/personality.h>
-#include <linux/random.h>
#include <linux/hw_breakpoint.h>
#include <linux/uaccess.h>
-#include <linux/elf-randomize.h>
#include <linux/pkeys.h>
#include <linux/seq_buf.h>
@@ -2310,42 +2308,3 @@ unsigned long arch_align_stack(unsigned long sp)
sp -= get_random_int() & ~PAGE_MASK;
return sp & ~0xf;
}
-
-static inline unsigned long brk_rnd(void)
-{
- unsigned long rnd = 0;
-
- /* 8MB for 32bit, 1GB for 64bit */
- if (is_32bit_task())
- rnd = (get_random_long() % (1UL<<(23-PAGE_SHIFT)));
- else
- rnd = (get_random_long() % (1UL<<(30-PAGE_SHIFT)));
-
- return rnd << PAGE_SHIFT;
-}
-
-unsigned long arch_randomize_brk(struct mm_struct *mm)
-{
- unsigned long base = mm->brk;
- unsigned long ret;
-
-#ifdef CONFIG_PPC_BOOK3S_64
- /*
- * If we are using 1TB segments and we are allowed to randomise
- * the heap, we can put it above 1TB so it is backed by a 1TB
- * segment. Otherwise the heap will be in the bottom 1TB
- * which always uses 256MB segments and this may result in a
- * performance penalty.
- */
- if (!radix_enabled() && !is_32bit_task() && (mmu_highuser_ssize == MMU_SEGSIZE_1T))
- base = max_t(unsigned long, mm->brk, 1UL << SID_SHIFT_1T);
-#endif
-
- ret = PAGE_ALIGN(base + brk_rnd());
-
- if (ret < mm->brk)
- return mm->brk;
-
- return ret;
-}
-
diff --git a/arch/powerpc/mm/book3s64/hash_utils.c b/arch/powerpc/mm/book3s64/hash_utils.c
index 7ecadf5e6bf9..68a5468b0f19 100644
--- a/arch/powerpc/mm/book3s64/hash_utils.c
+++ b/arch/powerpc/mm/book3s64/hash_utils.c
@@ -37,6 +37,8 @@
#include <linux/cpu.h>
#include <linux/pgtable.h>
#include <linux/debugfs.h>
+#include <linux/random.h>
+#include <linux/elf-randomize.h>
#include <asm/interrupt.h>
#include <asm/processor.h>
@@ -2171,3 +2173,20 @@ void __init print_system_hash_info(void)
if (htab_hash_mask)
pr_info("htab_hash_mask = 0x%lx\n", htab_hash_mask);
}
+
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+ /*
+ * If we are using 1TB segments and we are allowed to randomise
+ * the heap, we can put it above 1TB so it is backed by a 1TB
+ * segment. Otherwise the heap will be in the bottom 1TB
+ * which always uses 256MB segments and this may result in a
+ * performance penalty.
+ */
+ if (is_32bit_task())
+ return randomize_page(mm->brk, SZ_32M);
+ else if (!radix_enabled() && mmu_highuser_ssize == MMU_SEGSIZE_1T)
+ return randomize_page(max_t(unsigned long, mm->brk, SZ_1T), SZ_1G);
+ else
+ return randomize_page(mm->brk, SZ_1G);
+}
diff --git a/include/linux/sizes.h b/include/linux/sizes.h
index 1ac79bcee2bb..84aa448d8bb3 100644
--- a/include/linux/sizes.h
+++ b/include/linux/sizes.h
@@ -47,6 +47,8 @@
#define SZ_8G _AC(0x200000000, ULL)
#define SZ_16G _AC(0x400000000, ULL)
#define SZ_32G _AC(0x800000000, ULL)
+
+#define SZ_1T _AC(0x10000000000, ULL)
#define SZ_64T _AC(0x400000000000, ULL)
#endif /* __LINUX_SIZES_H__ */
--
2.33.1
^ permalink raw reply related [flat|nested] 16+ messages in thread