* [PATCH 09/16] sparc64: define untagged_addr()
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
Add a helper to untag a user pointer. This is needed for ADI support
in get_user_pages_fast.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/sparc/include/asm/pgtable_64.h | 22 ++++++++++++++++++++++
1 file changed, 22 insertions(+)
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index dcf970e82262..a93eca29e85a 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -1076,6 +1076,28 @@ static inline int io_remap_pfn_range(struct vm_area_struct *vma,
}
#define io_remap_pfn_range io_remap_pfn_range
+static inline unsigned long untagged_addr(unsigned long start)
+{
+ if (adi_capable()) {
+ long addr = start;
+
+ /* If userspace has passed a versioned address, kernel
+ * will not find it in the VMAs since it does not store
+ * the version tags in the list of VMAs. Storing version
+ * tags in list of VMAs is impractical since they can be
+ * changed any time from userspace without dropping into
+ * kernel. Any address search in VMAs will be done with
+ * non-versioned addresses. Ensure the ADI version bits
+ * are dropped here by sign extending the last bit before
+ * ADI bits. IOMMU does not implement version tags.
+ */
+ return (addr << (long)adi_nbits()) >> (long)adi_nbits();
+ }
+
+ return start;
+}
+#define untagged_addr untagged_addr
+
#include <asm/tlbflush.h>
#include <asm-generic/pgtable.h>
--
2.20.1
^ permalink raw reply related
* [PATCH 10/16] sparc64: use the generic get_user_pages_fast code
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
The sparc64 code is mostly equivalent to the generic one, minus various
bugfixes and two arch overrides that this patch adds to pgtable.h.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/sparc/Kconfig | 1 +
arch/sparc/include/asm/pgtable_64.h | 18 ++
arch/sparc/mm/Makefile | 2 +-
arch/sparc/mm/gup.c | 340 ----------------------------
4 files changed, 20 insertions(+), 341 deletions(-)
delete mode 100644 arch/sparc/mm/gup.c
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 26ab6f5bbaaf..22435471f942 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -28,6 +28,7 @@ config SPARC
select RTC_DRV_M48T59
select RTC_SYSTOHC
select HAVE_ARCH_JUMP_LABEL if SPARC64
+ select HAVE_GENERIC_GUP if SPARC64
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select GENERIC_PCI_IOMAP
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index a93eca29e85a..2301ab5250e4 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -1098,6 +1098,24 @@ static inline unsigned long untagged_addr(unsigned long start)
}
#define untagged_addr untagged_addr
+static inline bool pte_access_permitted(pte_t pte, bool write)
+{
+ u64 prot;
+
+ if (tlb_type == hypervisor) {
+ prot = _PAGE_PRESENT_4V | _PAGE_P_4V;
+ if (prot)
+ prot |= _PAGE_WRITE_4V;
+ } else {
+ prot = _PAGE_PRESENT_4U | _PAGE_P_4U;
+ if (write)
+ prot |= _PAGE_WRITE_4U;
+ }
+
+ return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot;
+}
+#define pte_access_permitted pte_access_permitted
+
#include <asm/tlbflush.h>
#include <asm-generic/pgtable.h>
diff --git a/arch/sparc/mm/Makefile b/arch/sparc/mm/Makefile
index d39075b1e3b7..b078205b70e0 100644
--- a/arch/sparc/mm/Makefile
+++ b/arch/sparc/mm/Makefile
@@ -5,7 +5,7 @@
asflags-y := -ansi
ccflags-y := -Werror
-obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o gup.o
+obj-$(CONFIG_SPARC64) += ultra.o tlb.o tsb.o
obj-y += fault_$(BITS).o
obj-y += init_$(BITS).o
obj-$(CONFIG_SPARC32) += extable.o srmmu.o iommu.o io-unit.o
diff --git a/arch/sparc/mm/gup.c b/arch/sparc/mm/gup.c
deleted file mode 100644
index 1e770a517d4a..000000000000
--- a/arch/sparc/mm/gup.c
+++ /dev/null
@@ -1,340 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Lockless get_user_pages_fast for sparc, cribbed from powerpc
- *
- * Copyright (C) 2008 Nick Piggin
- * Copyright (C) 2008 Novell Inc.
- */
-
-#include <linux/sched.h>
-#include <linux/mm.h>
-#include <linux/vmstat.h>
-#include <linux/pagemap.h>
-#include <linux/rwsem.h>
-#include <asm/pgtable.h>
-#include <asm/adi.h>
-
-/*
- * The performance critical leaf functions are made noinline otherwise gcc
- * inlines everything into a single function which results in too much
- * register pressure.
- */
-static noinline int gup_pte_range(pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long mask, result;
- pte_t *ptep;
-
- if (tlb_type == hypervisor) {
- result = _PAGE_PRESENT_4V|_PAGE_P_4V;
- if (write)
- result |= _PAGE_WRITE_4V;
- } else {
- result = _PAGE_PRESENT_4U|_PAGE_P_4U;
- if (write)
- result |= _PAGE_WRITE_4U;
- }
- mask = result | _PAGE_SPECIAL;
-
- ptep = pte_offset_kernel(&pmd, addr);
- do {
- struct page *page, *head;
- pte_t pte = *ptep;
-
- if ((pte_val(pte) & mask) != result)
- return 0;
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- /* The hugepage case is simplified on sparc64 because
- * we encode the sub-page pfn offsets into the
- * hugepage PTEs. We could optimize this in the future
- * use page_cache_add_speculative() for the hugepage case.
- */
- page = pte_page(pte);
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
- return 0;
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- put_page(head);
- return 0;
- }
-
- pages[*nr] = page;
- (*nr)++;
- } while (ptep++, addr += PAGE_SIZE, addr != end);
-
- return 1;
-}
-
-static int gup_huge_pmd(pmd_t *pmdp, pmd_t pmd, unsigned long addr,
- unsigned long end, int write, struct page **pages,
- int *nr)
-{
- struct page *head, *page;
- int refs;
-
- if (!(pmd_val(pmd) & _PAGE_VALID))
- return 0;
-
- if (write && !pmd_write(pmd))
- return 0;
-
- refs = 0;
- page = pmd_page(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
- head = compound_head(page);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pmd_val(pmd) != pmd_val(*pmdp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-static int gup_huge_pud(pud_t *pudp, pud_t pud, unsigned long addr,
- unsigned long end, int write, struct page **pages,
- int *nr)
-{
- struct page *head, *page;
- int refs;
-
- if (!(pud_val(pud) & _PAGE_VALID))
- return 0;
-
- if (write && !pud_write(pud))
- return 0;
-
- refs = 0;
- page = pud_page(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
- head = compound_head(page);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pud_val(pud) != pud_val(*pudp))) {
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pmd_t *pmdp;
-
- pmdp = pmd_offset(&pud, addr);
- do {
- pmd_t pmd = *pmdp;
-
- next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
- return 0;
- if (unlikely(pmd_large(pmd))) {
- if (!gup_huge_pmd(pmdp, pmd, addr, next,
- write, pages, nr))
- return 0;
- } else if (!gup_pte_range(pmd, addr, next, write,
- pages, nr))
- return 0;
- } while (pmdp++, addr = next, addr != end);
-
- return 1;
-}
-
-static int gup_pud_range(pgd_t pgd, unsigned long addr, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- unsigned long next;
- pud_t *pudp;
-
- pudp = pud_offset(&pgd, addr);
- do {
- pud_t pud = *pudp;
-
- next = pud_addr_end(addr, end);
- if (pud_none(pud))
- return 0;
- if (unlikely(pud_large(pud))) {
- if (!gup_huge_pud(pudp, pud, addr, next,
- write, pages, nr))
- return 0;
- } else if (!gup_pmd_range(pud, addr, next, write, pages, nr))
- return 0;
- } while (pudp++, addr = next, addr != end);
-
- return 1;
-}
-
-/*
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- */
-int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
- struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next, flags;
- pgd_t *pgdp;
- int nr = 0;
-
-#ifdef CONFIG_SPARC64
- if (adi_capable()) {
- long addr = start;
-
- /* If userspace has passed a versioned address, kernel
- * will not find it in the VMAs since it does not store
- * the version tags in the list of VMAs. Storing version
- * tags in list of VMAs is impractical since they can be
- * changed any time from userspace without dropping into
- * kernel. Any address search in VMAs will be done with
- * non-versioned addresses. Ensure the ADI version bits
- * are dropped here by sign extending the last bit before
- * ADI bits. IOMMU does not implement version tags.
- */
- addr = (addr << (long)adi_nbits()) >> (long)adi_nbits();
- start = addr;
- }
-#endif
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- local_irq_save(flags);
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- break;
- if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
- break;
- } while (pgdp++, addr = next, addr != end);
- local_irq_restore(flags);
-
- return nr;
-}
-
-int get_user_pages_fast(unsigned long start, int nr_pages,
- unsigned int gup_flags, struct page **pages)
-{
- struct mm_struct *mm = current->mm;
- unsigned long addr, len, end;
- unsigned long next;
- pgd_t *pgdp;
- int nr = 0;
-
-#ifdef CONFIG_SPARC64
- if (adi_capable()) {
- long addr = start;
-
- /* If userspace has passed a versioned address, kernel
- * will not find it in the VMAs since it does not store
- * the version tags in the list of VMAs. Storing version
- * tags in list of VMAs is impractical since they can be
- * changed any time from userspace without dropping into
- * kernel. Any address search in VMAs will be done with
- * non-versioned addresses. Ensure the ADI version bits
- * are dropped here by sign extending the last bit before
- * ADI bits. IOMMU does not implements version tags,
- */
- addr = (addr << (long)adi_nbits()) >> (long)adi_nbits();
- start = addr;
- }
-#endif
- start &= PAGE_MASK;
- addr = start;
- len = (unsigned long) nr_pages << PAGE_SHIFT;
- end = start + len;
-
- /*
- * XXX: batch / limit 'nr', to avoid large irq off latency
- * needs some instrumenting to determine the common sizes used by
- * important workloads (eg. DB2), and whether limiting the batch size
- * will decrease performance.
- *
- * It seems like we're in the clear for the moment. Direct-IO is
- * the main guy that batches up lots of get_user_pages, and even
- * they are limited to 64-at-a-time which is not so many.
- */
- /*
- * This doesn't prevent pagetable teardown, but does prevent
- * the pagetables from being freed on sparc.
- *
- * So long as we atomically load page table pointers versus teardown,
- * we can follow the address down to the the page and take a ref on it.
- */
- local_irq_disable();
-
- pgdp = pgd_offset(mm, addr);
- do {
- pgd_t pgd = *pgdp;
-
- next = pgd_addr_end(addr, end);
- if (pgd_none(pgd))
- goto slow;
- if (!gup_pud_range(pgd, addr, next, gup_flags & FOLL_WRITE,
- pages, &nr))
- goto slow;
- } while (pgdp++, addr = next, addr != end);
-
- local_irq_enable();
-
- VM_BUG_ON(nr != (end - start) >> PAGE_SHIFT);
- return nr;
-
- {
- int ret;
-
-slow:
- local_irq_enable();
-
- /* Try to get the remaining pages with get_user_pages */
- start += nr << PAGE_SHIFT;
- pages += nr;
-
- ret = get_user_pages_unlocked(start,
- (end - start) >> PAGE_SHIFT, pages,
- gup_flags);
-
- /* Have to be a bit careful with return values */
- if (nr > 0) {
- if (ret < 0)
- ret = nr;
- else
- ret += nr;
- }
-
- return ret;
- }
-}
--
2.20.1
^ permalink raw reply related
* [PATCH 11/16] mm: rename CONFIG_HAVE_GENERIC_GUP to CONFIG_HAVE_FAST_GUP
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
We only support the generic GUP now, so rename the config option to
be more clear, and always use the mm/Kconfig definition of the
symbol and select it from the arch Kconfigs.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/arm/Kconfig | 5 +----
arch/arm64/Kconfig | 4 +---
arch/mips/Kconfig | 2 +-
arch/powerpc/Kconfig | 2 +-
arch/s390/Kconfig | 2 +-
arch/sh/Kconfig | 2 +-
arch/sparc/Kconfig | 2 +-
arch/x86/Kconfig | 4 +---
mm/Kconfig | 2 +-
mm/gup.c | 4 ++--
10 files changed, 11 insertions(+), 18 deletions(-)
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 8869742a85df..3879a3e2c511 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -73,6 +73,7 @@ config ARM
select HAVE_DYNAMIC_FTRACE_WITH_REGS if HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP if ARM_LPAE
select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
select HAVE_FUNCTION_TRACER if !XIP_KERNEL
@@ -1596,10 +1597,6 @@ config ARCH_SELECT_MEMORY_MODEL
config HAVE_ARCH_PFN_VALID
def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
-config HAVE_GENERIC_GUP
- def_bool y
- depends on ARM_LPAE
-
config HIGHMEM
bool "High Memory Support"
depends on MMU
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 697ea0510729..4a6ee3e92757 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -140,6 +140,7 @@ config ARM64
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EFFICIENT_UNALIGNED_ACCESS
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_TRACER
select HAVE_FUNCTION_GRAPH_TRACER
@@ -262,9 +263,6 @@ config GENERIC_CALIBRATE_DELAY
config ZONE_DMA32
def_bool y
-config HAVE_GENERIC_GUP
- def_bool y
-
config ARCH_ENABLE_MEMORY_HOTPLUG
def_bool y
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 64108a2a16d4..b1e42f0e4ed0 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -54,10 +54,10 @@ config MIPS
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
- select HAVE_GENERIC_GUP
select HAVE_IDE
select HAVE_IOREMAP_PROT
select HAVE_IRQ_EXIT_ON_IRQ_STACK
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 8c1c636308c8..992a04796e56 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -185,12 +185,12 @@ config PPC
select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
select HAVE_EBPF_JIT if PPC64
select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+ select HAVE_FAST_GUP
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_ERROR_INJECTION
select HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_TRACER
select HAVE_GCC_PLUGINS if GCC_VERSION >= 50200 # plugin support on gcc <= 5.1 is buggy on PPC
- select HAVE_GENERIC_GUP
select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
select HAVE_IDE
select HAVE_IOREMAP_PROT
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 109243fdb6ec..aaff0376bf53 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -137,6 +137,7 @@ config S390
select HAVE_DMA_CONTIGUOUS
select HAVE_DYNAMIC_FTRACE
select HAVE_DYNAMIC_FTRACE_WITH_REGS
+ select HAVE_FAST_GUP
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_FENTRY
select HAVE_FTRACE_MCOUNT_RECORD
@@ -144,7 +145,6 @@ config S390
select HAVE_FUNCTION_TRACER
select HAVE_FUTEX_CMPXCHG if FUTEX
select HAVE_GCC_PLUGINS
- select HAVE_GENERIC_GUP
select HAVE_KERNEL_BZIP2
select HAVE_KERNEL_GZIP
select HAVE_KERNEL_LZ4
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 6fddfc3c9710..56712f3c9838 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -14,7 +14,7 @@ config SUPERH
select HAVE_ARCH_TRACEHOOK
select HAVE_PERF_EVENTS
select HAVE_DEBUG_BUGVERBOSE
- select HAVE_GENERIC_GUP
+ select HAVE_FAST_GUP
select ARCH_HAVE_CUSTOM_GPIO_H
select ARCH_HAVE_NMI_SAFE_CMPXCHG if (GUSA_RB || CPU_SH4A)
select ARCH_HAS_GCOV_PROFILE_ALL
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 22435471f942..659232b760e1 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -28,7 +28,7 @@ config SPARC
select RTC_DRV_M48T59
select RTC_SYSTOHC
select HAVE_ARCH_JUMP_LABEL if SPARC64
- select HAVE_GENERIC_GUP if SPARC64
+ select HAVE_FAST_GUP if SPARC64
select GENERIC_IRQ_SHOW
select ARCH_WANT_IPC_PARSE_VERSION
select GENERIC_PCI_IOMAP
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7cd53cc59f0f..44500e0ed630 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -157,6 +157,7 @@ config X86
select HAVE_EFFICIENT_UNALIGNED_ACCESS
select HAVE_EISA
select HAVE_EXIT_THREAD
+ select HAVE_FAST_GUP
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_TRACER
@@ -2874,9 +2875,6 @@ config HAVE_ATOMIC_IOMAP
config X86_DEV_DMA_OPS
bool
-config HAVE_GENERIC_GUP
- def_bool y
-
source "drivers/firmware/Kconfig"
source "arch/x86/kvm/Kconfig"
diff --git a/mm/Kconfig b/mm/Kconfig
index fe51f104a9e0..98dffb0f2447 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -132,7 +132,7 @@ config HAVE_MEMBLOCK_NODE_MAP
config HAVE_MEMBLOCK_PHYS_MAP
bool
-config HAVE_GENERIC_GUP
+config HAVE_FAST_GUP
bool
config ARCH_KEEP_MEMBLOCK
diff --git a/mm/gup.c b/mm/gup.c
index a86d65cd7051..a24f52292c7f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1650,7 +1650,7 @@ struct page *get_dump_page(unsigned long addr)
#endif /* CONFIG_ELF_CORE */
/*
- * Generic Fast GUP
+ * Fast GUP
*
* get_user_pages_fast attempts to pin user pages by walking the page
* tables directly and avoids taking locks. Thus the walker needs to be
@@ -1682,7 +1682,7 @@ struct page *get_dump_page(unsigned long addr)
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
-#ifdef CONFIG_HAVE_GENERIC_GUP
+#ifdef CONFIG_HAVE_FAST_GUP
#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
/*
* WARNING: only to be used in the get_user_pages_fast() implementation.
--
2.20.1
^ permalink raw reply related
* [PATCH 12/16] mm: consolidate the get_user_pages* implementations
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
Always build mm/gup.c, and move the nommu versions and replace the
separate stubs for various functions by the default ones, with the _fast
version always falling back to the slow path because gup_fast_permitted
always returns false now if HAVE_FAST_GUP is not set, and we use the
nommu version of __get_user_pages while keeping all the wrappers common.
This also ensures the new put_user_pages* helpers are available for
nommu, as those are currently missing, which would create a problem as
soon as we actually grew users for it.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
mm/Kconfig | 1 +
mm/Makefile | 4 +-
mm/gup.c | 476 +++++++++++++++++++++++++++++-----------------------
mm/nommu.c | 88 ----------
mm/util.c | 47 ------
5 files changed, 269 insertions(+), 347 deletions(-)
diff --git a/mm/Kconfig b/mm/Kconfig
index 98dffb0f2447..5c41409557da 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -133,6 +133,7 @@ config HAVE_MEMBLOCK_PHYS_MAP
bool
config HAVE_FAST_GUP
+ depends on MMU
bool
config ARCH_KEEP_MEMBLOCK
diff --git a/mm/Makefile b/mm/Makefile
index ac5e5ba78874..dc0746ca1109 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -22,7 +22,7 @@ KCOV_INSTRUMENT_mmzone.o := n
KCOV_INSTRUMENT_vmstat.o := n
mmu-y := nommu.o
-mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \
+mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \
mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
msync.o page_vma_mapped.o pagewalk.o \
pgtable-generic.o rmap.o vmalloc.o
@@ -39,7 +39,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \
mm_init.o mmu_context.o percpu.o slab_common.o \
compaction.o vmacache.o \
interval_tree.o list_lru.o workingset.o \
- debug.o $(mmu-y)
+ debug.o gup.o $(mmu-y)
# Give 'page_alloc' its own module-parameter namespace
page-alloc-y := page_alloc.o
diff --git a/mm/gup.c b/mm/gup.c
index a24f52292c7f..c8da7764de9c 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -134,6 +134,7 @@ void put_user_pages(struct page **pages, unsigned long npages)
}
EXPORT_SYMBOL(put_user_pages);
+#ifdef CONFIG_MMU
static struct page *no_page_table(struct vm_area_struct *vma,
unsigned int flags)
{
@@ -1099,86 +1100,6 @@ static __always_inline long __get_user_pages_locked(struct task_struct *tsk,
return pages_done;
}
-/*
- * We can leverage the VM_FAULT_RETRY functionality in the page fault
- * paths better by using either get_user_pages_locked() or
- * get_user_pages_unlocked().
- *
- * get_user_pages_locked() is suitable to replace the form:
- *
- * down_read(&mm->mmap_sem);
- * do_something()
- * get_user_pages(tsk, mm, ..., pages, NULL);
- * up_read(&mm->mmap_sem);
- *
- * to:
- *
- * int locked = 1;
- * down_read(&mm->mmap_sem);
- * do_something()
- * get_user_pages_locked(tsk, mm, ..., pages, &locked);
- * if (locked)
- * up_read(&mm->mmap_sem);
- */
-long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- int *locked)
-{
- /*
- * FIXME: Current FOLL_LONGTERM behavior is incompatible with
- * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
- * vmas. As there are no users of this flag in this call we simply
- * disallow this option for now.
- */
- if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
- return -EINVAL;
-
- return __get_user_pages_locked(current, current->mm, start, nr_pages,
- pages, NULL, locked,
- gup_flags | FOLL_TOUCH);
-}
-EXPORT_SYMBOL(get_user_pages_locked);
-
-/*
- * get_user_pages_unlocked() is suitable to replace the form:
- *
- * down_read(&mm->mmap_sem);
- * get_user_pages(tsk, mm, ..., pages, NULL);
- * up_read(&mm->mmap_sem);
- *
- * with:
- *
- * get_user_pages_unlocked(tsk, mm, ..., pages);
- *
- * It is functionally equivalent to get_user_pages_fast so
- * get_user_pages_fast should be used instead if specific gup_flags
- * (e.g. FOLL_FORCE) are not required.
- */
-long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- struct page **pages, unsigned int gup_flags)
-{
- struct mm_struct *mm = current->mm;
- int locked = 1;
- long ret;
-
- /*
- * FIXME: Current FOLL_LONGTERM behavior is incompatible with
- * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
- * vmas. As there are no users of this flag in this call we simply
- * disallow this option for now.
- */
- if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
- return -EINVAL;
-
- down_read(&mm->mmap_sem);
- ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
- &locked, gup_flags | FOLL_TOUCH);
- if (locked)
- up_read(&mm->mmap_sem);
- return ret;
-}
-EXPORT_SYMBOL(get_user_pages_unlocked);
-
/*
* get_user_pages_remote() - pin user pages in memory
* @tsk: the task_struct to use for page fault accounting, or
@@ -1255,6 +1176,199 @@ long get_user_pages_remote(struct task_struct *tsk, struct mm_struct *mm,
}
EXPORT_SYMBOL(get_user_pages_remote);
+/**
+ * populate_vma_page_range() - populate a range of pages in the vma.
+ * @vma: target vma
+ * @start: start address
+ * @end: end address
+ * @nonblocking:
+ *
+ * This takes care of mlocking the pages too if VM_LOCKED is set.
+ *
+ * return 0 on success, negative error code on error.
+ *
+ * vma->vm_mm->mmap_sem must be held.
+ *
+ * If @nonblocking is NULL, it may be held for read or write and will
+ * be unperturbed.
+ *
+ * If @nonblocking is non-NULL, it must held for read only and may be
+ * released. If it's released, *@nonblocking will be set to 0.
+ */
+long populate_vma_page_range(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end, int *nonblocking)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ unsigned long nr_pages = (end - start) / PAGE_SIZE;
+ int gup_flags;
+
+ VM_BUG_ON(start & ~PAGE_MASK);
+ VM_BUG_ON(end & ~PAGE_MASK);
+ VM_BUG_ON_VMA(start < vma->vm_start, vma);
+ VM_BUG_ON_VMA(end > vma->vm_end, vma);
+ VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
+
+ gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
+ if (vma->vm_flags & VM_LOCKONFAULT)
+ gup_flags &= ~FOLL_POPULATE;
+ /*
+ * We want to touch writable mappings with a write fault in order
+ * to break COW, except for shared mappings because these don't COW
+ * and we would not want to dirty them for nothing.
+ */
+ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+ gup_flags |= FOLL_WRITE;
+
+ /*
+ * We want mlock to succeed for regions that have any permissions
+ * other than PROT_NONE.
+ */
+ if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+ gup_flags |= FOLL_FORCE;
+
+ /*
+ * We made sure addr is within a VMA, so the following will
+ * not result in a stack expansion that recurses back here.
+ */
+ return __get_user_pages(current, mm, start, nr_pages, gup_flags,
+ NULL, NULL, nonblocking);
+}
+
+/*
+ * __mm_populate - populate and/or mlock pages within a range of address space.
+ *
+ * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
+ * flags. VMAs must be already marked with the desired vm_flags, and
+ * mmap_sem must not be held.
+ */
+int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
+{
+ struct mm_struct *mm = current->mm;
+ unsigned long end, nstart, nend;
+ struct vm_area_struct *vma = NULL;
+ int locked = 0;
+ long ret = 0;
+
+ end = start + len;
+
+ for (nstart = start; nstart < end; nstart = nend) {
+ /*
+ * We want to fault in pages for [nstart; end) address range.
+ * Find first corresponding VMA.
+ */
+ if (!locked) {
+ locked = 1;
+ down_read(&mm->mmap_sem);
+ vma = find_vma(mm, nstart);
+ } else if (nstart >= vma->vm_end)
+ vma = vma->vm_next;
+ if (!vma || vma->vm_start >= end)
+ break;
+ /*
+ * Set [nstart; nend) to intersection of desired address
+ * range with the first VMA. Also, skip undesirable VMA types.
+ */
+ nend = min(end, vma->vm_end);
+ if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+ continue;
+ if (nstart < vma->vm_start)
+ nstart = vma->vm_start;
+ /*
+ * Now fault in a range of pages. populate_vma_page_range()
+ * double checks the vma flags, so that it won't mlock pages
+ * if the vma was already munlocked.
+ */
+ ret = populate_vma_page_range(vma, nstart, nend, &locked);
+ if (ret < 0) {
+ if (ignore_errors) {
+ ret = 0;
+ continue; /* continue at next VMA */
+ }
+ break;
+ }
+ nend = nstart + ret * PAGE_SIZE;
+ ret = 0;
+ }
+ if (locked)
+ up_read(&mm->mmap_sem);
+ return ret; /* 0 or negative error code */
+}
+
+/**
+ * get_dump_page() - pin user page in memory while writing it to core dump
+ * @addr: user address
+ *
+ * Returns struct page pointer of user page pinned for dump,
+ * to be freed afterwards by put_page().
+ *
+ * Returns NULL on any kind of failure - a hole must then be inserted into
+ * the corefile, to preserve alignment with its headers; and also returns
+ * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
+ * allowing a hole to be left in the corefile to save diskspace.
+ *
+ * Called without mmap_sem, but after all other threads have been killed.
+ */
+#ifdef CONFIG_ELF_CORE
+struct page *get_dump_page(unsigned long addr)
+{
+ struct vm_area_struct *vma;
+ struct page *page;
+
+ if (__get_user_pages(current, current->mm, addr, 1,
+ FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
+ NULL) < 1)
+ return NULL;
+ flush_cache_page(vma, addr, page_to_pfn(page));
+ return page;
+}
+#endif /* CONFIG_ELF_CORE */
+
+#else /* CONFIG_MMU */
+static long __get_user_pages_locked(struct task_struct *tsk,
+ struct mm_struct *mm, unsigned long start,
+ unsigned long nr_pages, struct page **pages,
+ struct vm_area_struct **vmas, int *locked,
+ unsigned int foll_flags)
+{
+ struct vm_area_struct *vma;
+ unsigned long vm_flags;
+ int i;
+
+ /* calculate required read or write permissions.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
+ */
+ vm_flags = (foll_flags & FOLL_WRITE) ?
+ (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= (foll_flags & FOLL_FORCE) ?
+ (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+
+ for (i = 0; i < nr_pages; i++) {
+ vma = find_vma(mm, start);
+ if (!vma)
+ goto finish_or_fault;
+
+ /* protect what we can, including chardevs */
+ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+ !(vm_flags & vma->vm_flags))
+ goto finish_or_fault;
+
+ if (pages) {
+ pages[i] = virt_to_page(start);
+ if (pages[i])
+ get_page(pages[i]);
+ }
+ if (vmas)
+ vmas[i] = vma;
+ start = (start + PAGE_SIZE) & PAGE_MASK;
+ }
+
+ return i;
+
+finish_or_fault:
+ return i ? : -EFAULT;
+}
+#endif /* !CONFIG_MMU */
+
#if defined(CONFIG_FS_DAX) || defined (CONFIG_CMA)
static bool check_dax_vmas(struct vm_area_struct **vmas, long nr_pages)
{
@@ -1416,7 +1530,7 @@ static long check_and_migrate_cma_pages(struct task_struct *tsk,
{
return nr_pages;
}
-#endif
+#endif /* CONFIG_CMA */
/*
* __gup_longterm_locked() is a wrapper for __get_user_pages_locked which
@@ -1502,152 +1616,85 @@ long get_user_pages(unsigned long start, unsigned long nr_pages,
}
EXPORT_SYMBOL(get_user_pages);
-/**
- * populate_vma_page_range() - populate a range of pages in the vma.
- * @vma: target vma
- * @start: start address
- * @end: end address
- * @nonblocking:
- *
- * This takes care of mlocking the pages too if VM_LOCKED is set.
+/*
+ * We can leverage the VM_FAULT_RETRY functionality in the page fault
+ * paths better by using either get_user_pages_locked() or
+ * get_user_pages_unlocked().
*
- * return 0 on success, negative error code on error.
+ * get_user_pages_locked() is suitable to replace the form:
*
- * vma->vm_mm->mmap_sem must be held.
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
*
- * If @nonblocking is NULL, it may be held for read or write and will
- * be unperturbed.
+ * to:
*
- * If @nonblocking is non-NULL, it must held for read only and may be
- * released. If it's released, *@nonblocking will be set to 0.
+ * int locked = 1;
+ * down_read(&mm->mmap_sem);
+ * do_something()
+ * get_user_pages_locked(tsk, mm, ..., pages, &locked);
+ * if (locked)
+ * up_read(&mm->mmap_sem);
*/
-long populate_vma_page_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end, int *nonblocking)
+long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
+ unsigned int gup_flags, struct page **pages,
+ int *locked)
{
- struct mm_struct *mm = vma->vm_mm;
- unsigned long nr_pages = (end - start) / PAGE_SIZE;
- int gup_flags;
-
- VM_BUG_ON(start & ~PAGE_MASK);
- VM_BUG_ON(end & ~PAGE_MASK);
- VM_BUG_ON_VMA(start < vma->vm_start, vma);
- VM_BUG_ON_VMA(end > vma->vm_end, vma);
- VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_sem), mm);
-
- gup_flags = FOLL_TOUCH | FOLL_POPULATE | FOLL_MLOCK;
- if (vma->vm_flags & VM_LOCKONFAULT)
- gup_flags &= ~FOLL_POPULATE;
- /*
- * We want to touch writable mappings with a write fault in order
- * to break COW, except for shared mappings because these don't COW
- * and we would not want to dirty them for nothing.
- */
- if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
- gup_flags |= FOLL_WRITE;
-
/*
- * We want mlock to succeed for regions that have any permissions
- * other than PROT_NONE.
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
*/
- if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
- gup_flags |= FOLL_FORCE;
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
- /*
- * We made sure addr is within a VMA, so the following will
- * not result in a stack expansion that recurses back here.
- */
- return __get_user_pages(current, mm, start, nr_pages, gup_flags,
- NULL, NULL, nonblocking);
+ return __get_user_pages_locked(current, current->mm, start, nr_pages,
+ pages, NULL, locked,
+ gup_flags | FOLL_TOUCH);
}
+EXPORT_SYMBOL(get_user_pages_locked);
/*
- * __mm_populate - populate and/or mlock pages within a range of address space.
+ * get_user_pages_unlocked() is suitable to replace the form:
*
- * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap
- * flags. VMAs must be already marked with the desired vm_flags, and
- * mmap_sem must not be held.
+ * down_read(&mm->mmap_sem);
+ * get_user_pages(tsk, mm, ..., pages, NULL);
+ * up_read(&mm->mmap_sem);
+ *
+ * with:
+ *
+ * get_user_pages_unlocked(tsk, mm, ..., pages);
+ *
+ * It is functionally equivalent to get_user_pages_fast so
+ * get_user_pages_fast should be used instead if specific gup_flags
+ * (e.g. FOLL_FORCE) are not required.
*/
-int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
+long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
+ struct page **pages, unsigned int gup_flags)
{
struct mm_struct *mm = current->mm;
- unsigned long end, nstart, nend;
- struct vm_area_struct *vma = NULL;
- int locked = 0;
- long ret = 0;
+ int locked = 1;
+ long ret;
- end = start + len;
+ /*
+ * FIXME: Current FOLL_LONGTERM behavior is incompatible with
+ * FAULT_FLAG_ALLOW_RETRY because of the FS DAX check requirement on
+ * vmas. As there are no users of this flag in this call we simply
+ * disallow this option for now.
+ */
+ if (WARN_ON_ONCE(gup_flags & FOLL_LONGTERM))
+ return -EINVAL;
- for (nstart = start; nstart < end; nstart = nend) {
- /*
- * We want to fault in pages for [nstart; end) address range.
- * Find first corresponding VMA.
- */
- if (!locked) {
- locked = 1;
- down_read(&mm->mmap_sem);
- vma = find_vma(mm, nstart);
- } else if (nstart >= vma->vm_end)
- vma = vma->vm_next;
- if (!vma || vma->vm_start >= end)
- break;
- /*
- * Set [nstart; nend) to intersection of desired address
- * range with the first VMA. Also, skip undesirable VMA types.
- */
- nend = min(end, vma->vm_end);
- if (vma->vm_flags & (VM_IO | VM_PFNMAP))
- continue;
- if (nstart < vma->vm_start)
- nstart = vma->vm_start;
- /*
- * Now fault in a range of pages. populate_vma_page_range()
- * double checks the vma flags, so that it won't mlock pages
- * if the vma was already munlocked.
- */
- ret = populate_vma_page_range(vma, nstart, nend, &locked);
- if (ret < 0) {
- if (ignore_errors) {
- ret = 0;
- continue; /* continue at next VMA */
- }
- break;
- }
- nend = nstart + ret * PAGE_SIZE;
- ret = 0;
- }
+ down_read(&mm->mmap_sem);
+ ret = __get_user_pages_locked(current, mm, start, nr_pages, pages, NULL,
+ &locked, gup_flags | FOLL_TOUCH);
if (locked)
up_read(&mm->mmap_sem);
- return ret; /* 0 or negative error code */
-}
-
-/**
- * get_dump_page() - pin user page in memory while writing it to core dump
- * @addr: user address
- *
- * Returns struct page pointer of user page pinned for dump,
- * to be freed afterwards by put_page().
- *
- * Returns NULL on any kind of failure - a hole must then be inserted into
- * the corefile, to preserve alignment with its headers; and also returns
- * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
- * allowing a hole to be left in the corefile to save diskspace.
- *
- * Called without mmap_sem, but after all other threads have been killed.
- */
-#ifdef CONFIG_ELF_CORE
-struct page *get_dump_page(unsigned long addr)
-{
- struct vm_area_struct *vma;
- struct page *page;
-
- if (__get_user_pages(current, current->mm, addr, 1,
- FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
- NULL) < 1)
- return NULL;
- flush_cache_page(vma, addr, page_to_pfn(page));
- return page;
+ return ret;
}
-#endif /* CONFIG_ELF_CORE */
+EXPORT_SYMBOL(get_user_pages_unlocked);
/*
* Fast GUP
@@ -1682,7 +1729,7 @@ struct page *get_dump_page(unsigned long addr)
*
* This code is based heavily on the PowerPC implementation by Nick Piggin.
*/
-#ifdef CONFIG_HAVE_FAST_GUP
+#if defined(CONFIG_MMU) && defined(CONFIG_HAVE_FAST_GUP)
#ifdef CONFIG_GUP_GET_PTE_LOW_HIGH
/*
* WARNING: only to be used in the get_user_pages_fast() implementation.
@@ -2159,6 +2206,12 @@ static void gup_pgd_range(unsigned long addr, unsigned long end,
return;
} while (pgdp++, addr = next, addr != end);
}
+#else
+static inline void gup_pgd_range(unsigned long addr, unsigned long end,
+ unsigned int flags, struct page **pages, int *nr)
+{
+}
+#endif /* CONFIG_HAVE_FAST_GUP */
#ifndef gup_fast_permitted
/*
@@ -2167,7 +2220,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end,
*/
static bool gup_fast_permitted(unsigned long start, unsigned long end)
{
- return true;
+ return IS_ENABLED(CONFIG_HAVE_FAST_GUP) ? true : false;
}
#endif
@@ -2176,6 +2229,9 @@ static bool gup_fast_permitted(unsigned long start, unsigned long end)
* the regular GUP.
* Note a difference with get_user_pages_fast: this always returns the
* number of pages pinned, 0 if no pages were pinned.
+ *
+ * If the architecture does not support this function, simply return with no
+ * pages pinned.
*/
int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages)
@@ -2213,6 +2269,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
return nr;
}
+EXPORT_SYMBOL_GPL(__get_user_pages_fast);
static int __gup_longterm_unlocked(unsigned long start, int nr_pages,
unsigned int gup_flags, struct page **pages)
@@ -2295,5 +2352,4 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
return ret;
}
-
-#endif /* CONFIG_HAVE_GENERIC_GUP */
+EXPORT_SYMBOL_GPL(get_user_pages_fast);
diff --git a/mm/nommu.c b/mm/nommu.c
index d8c02fbe03b5..07165ad2e548 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -111,94 +111,6 @@ unsigned int kobjsize(const void *objp)
return PAGE_SIZE << compound_order(page);
}
-static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, unsigned long nr_pages,
- unsigned int foll_flags, struct page **pages,
- struct vm_area_struct **vmas, int *nonblocking)
-{
- struct vm_area_struct *vma;
- unsigned long vm_flags;
- int i;
-
- /* calculate required read or write permissions.
- * If FOLL_FORCE is set, we only require the "MAY" flags.
- */
- vm_flags = (foll_flags & FOLL_WRITE) ?
- (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
- vm_flags &= (foll_flags & FOLL_FORCE) ?
- (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
-
- for (i = 0; i < nr_pages; i++) {
- vma = find_vma(mm, start);
- if (!vma)
- goto finish_or_fault;
-
- /* protect what we can, including chardevs */
- if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
- !(vm_flags & vma->vm_flags))
- goto finish_or_fault;
-
- if (pages) {
- pages[i] = virt_to_page(start);
- if (pages[i])
- get_page(pages[i]);
- }
- if (vmas)
- vmas[i] = vma;
- start = (start + PAGE_SIZE) & PAGE_MASK;
- }
-
- return i;
-
-finish_or_fault:
- return i ? : -EFAULT;
-}
-
-/*
- * get a list of pages in an address range belonging to the specified process
- * and indicate the VMA that covers each page
- * - this is potentially dodgy as we may end incrementing the page count of a
- * slab page or a secondary page from a compound page
- * - don't permit access to VMAs that don't support it, such as I/O mappings
- */
-long get_user_pages(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- struct vm_area_struct **vmas)
-{
- return __get_user_pages(current, current->mm, start, nr_pages,
- gup_flags, pages, vmas, NULL);
-}
-EXPORT_SYMBOL(get_user_pages);
-
-long get_user_pages_locked(unsigned long start, unsigned long nr_pages,
- unsigned int gup_flags, struct page **pages,
- int *locked)
-{
- return get_user_pages(start, nr_pages, gup_flags, pages, NULL);
-}
-EXPORT_SYMBOL(get_user_pages_locked);
-
-static long __get_user_pages_unlocked(struct task_struct *tsk,
- struct mm_struct *mm, unsigned long start,
- unsigned long nr_pages, struct page **pages,
- unsigned int gup_flags)
-{
- long ret;
- down_read(&mm->mmap_sem);
- ret = __get_user_pages(tsk, mm, start, nr_pages, gup_flags, pages,
- NULL, NULL);
- up_read(&mm->mmap_sem);
- return ret;
-}
-
-long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
- struct page **pages, unsigned int gup_flags)
-{
- return __get_user_pages_unlocked(current, current->mm, start, nr_pages,
- pages, gup_flags);
-}
-EXPORT_SYMBOL(get_user_pages_unlocked);
-
/**
* follow_pfn - look up PFN at a user virtual address
* @vma: memory mapping
diff --git a/mm/util.c b/mm/util.c
index 91682a2090ee..d58f5b0eb669 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -300,53 +300,6 @@ void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
}
#endif
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- * If the architecture does not support this function, simply return with no
- * pages pinned.
- */
-int __weak __get_user_pages_fast(unsigned long start,
- int nr_pages, int write, struct page **pages)
-{
- return 0;
-}
-EXPORT_SYMBOL_GPL(__get_user_pages_fast);
-
-/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @gup_flags: flags modifying pin behaviour
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
- *
- * get_user_pages_fast provides equivalent functionality to get_user_pages,
- * operating on current and current->mm, with force=0 and vma=NULL. However
- * unlike get_user_pages, it must be called without mmap_sem held.
- *
- * get_user_pages_fast may take mmap_sem and page table locks, so no
- * assumptions can be made about lack of locking. get_user_pages_fast is to be
- * implemented in a way that is advantageous (vs get_user_pages()) when the
- * user memory area is already faulted in and present in ptes. However if the
- * pages have to be faulted in, it may turn out to be slightly slower so
- * callers need to carefully consider what to use. On many architectures,
- * get_user_pages_fast simply falls back to get_user_pages.
- *
- * Return: number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
- */
-int __weak get_user_pages_fast(unsigned long start,
- int nr_pages, unsigned int gup_flags,
- struct page **pages)
-{
- return get_user_pages_unlocked(start, nr_pages, pages, gup_flags);
-}
-EXPORT_SYMBOL_GPL(get_user_pages_fast);
-
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)
--
2.20.1
^ permalink raw reply related
* [PATCH 13/16] mm: validate get_user_pages_fast flags
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
We can only deal with FOLL_WRITE and/or FOLL_LONGTERM in
get_user_pages_fast, so reject all other flags.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
mm/gup.c | 3 +++
1 file changed, 3 insertions(+)
diff --git a/mm/gup.c b/mm/gup.c
index c8da7764de9c..53b50c63ba51 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2316,6 +2316,9 @@ int get_user_pages_fast(unsigned long start, int nr_pages,
unsigned long addr, len, end;
int nr = 0, ret = 0;
+ if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM)))
+ return -EINVAL;
+
start = untagged_addr(start) & PAGE_MASK;
addr = start;
len = (unsigned long) nr_pages << PAGE_SHIFT;
--
2.20.1
^ permalink raw reply related
* [PATCH 14/16] mm: move the powerpc hugepd code to mm/gup.c
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
While only powerpc supports the hugepd case, the code is pretty
generic and I'd like to keep all GUP internals in one place.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
arch/powerpc/Kconfig | 1 +
arch/powerpc/mm/hugetlbpage.c | 72 ------------------------------
include/linux/hugetlb.h | 18 --------
mm/Kconfig | 10 +++++
mm/gup.c | 82 +++++++++++++++++++++++++++++++++++
5 files changed, 93 insertions(+), 90 deletions(-)
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 992a04796e56..4f1b00979cde 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -125,6 +125,7 @@ config PPC
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
select ARCH_HAS_KCOV
+ select ARCH_HAS_HUGEPD if HUGETLB_PAGE
select ARCH_HAS_MMIOWB if PPC64
select ARCH_HAS_PHYS_TO_DMA
select ARCH_HAS_PMEM_API if PPC64
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index b5d92dc32844..51716c11d0fb 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -511,13 +511,6 @@ struct page *follow_huge_pd(struct vm_area_struct *vma,
return page;
}
-static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
- unsigned long sz)
-{
- unsigned long __boundary = (addr + sz) & ~(sz-1);
- return (__boundary - 1 < end - 1) ? __boundary : end;
-}
-
#ifdef CONFIG_PPC_MM_SLICES
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
unsigned long len, unsigned long pgoff,
@@ -665,68 +658,3 @@ void flush_dcache_icache_hugepage(struct page *page)
}
}
}
-
-static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- unsigned long pte_end;
- struct page *head, *page;
- pte_t pte;
- int refs;
-
- pte_end = (addr + sz) & ~(sz-1);
- if (pte_end < end)
- end = pte_end;
-
- pte = READ_ONCE(*ptep);
-
- if (!pte_access_permitted(pte, write))
- return 0;
-
- /* hugepages are never "special" */
- VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
-
- refs = 0;
- head = pte_page(pte);
-
- page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
- do {
- VM_BUG_ON(compound_head(page) != head);
- pages[*nr] = page;
- (*nr)++;
- page++;
- refs++;
- } while (addr += PAGE_SIZE, addr != end);
-
- if (!page_cache_add_speculative(head, refs)) {
- *nr -= refs;
- return 0;
- }
-
- if (unlikely(pte_val(pte) != pte_val(*ptep))) {
- /* Could be optimized better */
- *nr -= refs;
- while (refs--)
- put_page(head);
- return 0;
- }
-
- return 1;
-}
-
-int gup_huge_pd(hugepd_t hugepd, unsigned long addr, unsigned int pdshift,
- unsigned long end, int write, struct page **pages, int *nr)
-{
- pte_t *ptep;
- unsigned long sz = 1UL << hugepd_shift(hugepd);
- unsigned long next;
-
- ptep = hugepte_offset(hugepd, addr, pdshift);
- do {
- next = hugepte_addr_end(addr, end, sz);
- if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
- return 0;
- } while (ptep++, addr = next, addr != end);
-
- return 1;
-}
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index edf476c8cfb9..0f91761e2c53 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -16,29 +16,11 @@ struct user_struct;
struct mmu_gather;
#ifndef is_hugepd
-/*
- * Some architectures requires a hugepage directory format that is
- * required to support multiple hugepage sizes. For example
- * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
- * introduced the same on powerpc. This allows for a more flexible hugepage
- * pagetable layout.
- */
typedef struct { unsigned long pd; } hugepd_t;
#define is_hugepd(hugepd) (0)
#define __hugepd(x) ((hugepd_t) { (x) })
-static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
- unsigned pdshift, unsigned long end,
- int write, struct page **pages, int *nr)
-{
- return 0;
-}
-#else
-extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
- unsigned pdshift, unsigned long end,
- int write, struct page **pages, int *nr);
#endif
-
#ifdef CONFIG_HUGETLB_PAGE
#include <linux/mempolicy.h>
diff --git a/mm/Kconfig b/mm/Kconfig
index 5c41409557da..44be3f01a2b2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -769,4 +769,14 @@ config GUP_GET_PTE_LOW_HIGH
config ARCH_HAS_PTE_SPECIAL
bool
+#
+# Some architectures require a special hugepage directory format that is
+# required to support multiple hugepage sizes. For example a4fe3ce76
+# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+# introduced it on powerpc. This allows for a more flexible hugepage
+# pagetable layouts.
+#
+config ARCH_HAS_HUGEPD
+ bool
+
endmenu
diff --git a/mm/gup.c b/mm/gup.c
index 53b50c63ba51..e03c7e6b1422 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1966,6 +1966,88 @@ static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
}
#endif
+#ifdef CONFIG_ARCH_HAS_HUGEPD
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+ unsigned long sz)
+{
+ unsigned long __boundary = (addr + sz) & ~(sz-1);
+ return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
+static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
+{
+ unsigned long pte_end;
+ struct page *head, *page;
+ pte_t pte;
+ int refs;
+
+ pte_end = (addr + sz) & ~(sz-1);
+ if (pte_end < end)
+ end = pte_end;
+
+ pte = READ_ONCE(*ptep);
+
+ if (!pte_access_permitted(pte, write))
+ return 0;
+
+ /* hugepages are never "special" */
+ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+ refs = 0;
+ head = pte_page(pte);
+
+ page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
+ do {
+ VM_BUG_ON(compound_head(page) != head);
+ pages[*nr] = page;
+ (*nr)++;
+ page++;
+ refs++;
+ } while (addr += PAGE_SIZE, addr != end);
+
+ if (!page_cache_add_speculative(head, refs)) {
+ *nr -= refs;
+ return 0;
+ }
+
+ if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+ /* Could be optimized better */
+ *nr -= refs;
+ while (refs--)
+ put_page(head);
+ return 0;
+ }
+
+ return 1;
+}
+
+static int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned int pdshift, unsigned long end, int write,
+ struct page **pages, int *nr)
+{
+ pte_t *ptep;
+ unsigned long sz = 1UL << hugepd_shift(hugepd);
+ unsigned long next;
+
+ ptep = hugepte_offset(hugepd, addr, pdshift);
+ do {
+ next = hugepte_addr_end(addr, end, sz);
+ if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
+ return 0;
+ } while (ptep++, addr = next, addr != end);
+
+ return 1;
+}
+#else
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+ unsigned pdshift, unsigned long end, int write,
+ struct page **pages, int *nr)
+{
+ return 0;
+}
+#endif /* CONFIG_ARCH_HAS_HUGEPD */
+
static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
unsigned long end, unsigned int flags, struct page **pages, int *nr)
{
--
2.20.1
^ permalink raw reply related
* [PATCH 15/16] mm: switch gup_hugepte to use try_get_compound_head
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
This applies the overflow fixes from 8fde12ca79aff
("mm: prevent get_user_pages() from overflowing page refcount")
to the powerpc hugepd code and brings it back in sync with the
other GUP cases.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
mm/gup.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/mm/gup.c b/mm/gup.c
index e03c7e6b1422..6090044227f1 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2006,7 +2006,8 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
refs++;
} while (addr += PAGE_SIZE, addr != end);
- if (!page_cache_add_speculative(head, refs)) {
+ head = try_get_compound_head(head, refs);
+ if (!head) {
*nr -= refs;
return 0;
}
--
2.20.1
^ permalink raw reply related
* [PATCH 16/16] mm: mark the page referenced in gup_hugepte
From: Christoph Hellwig @ 2019-06-01 7:49 UTC (permalink / raw)
To: Linus Torvalds, Paul Burton, James Hogan, Yoshinori Sato,
Rich Felker, David S. Miller
Cc: linux-sh, Andrey Konovalov, x86, linux-mips, Nicholas Piggin,
linux-kernel, linux-mm, Khalid Aziz, Paul Mackerras, sparclinux,
linuxppc-dev
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
All other get_user_page_fast cases mark the page referenced, so do
this here as well.
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
mm/gup.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/mm/gup.c b/mm/gup.c
index 6090044227f1..d1fc008de292 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2020,6 +2020,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
return 0;
}
+ SetPageReferenced(head);
return 1;
}
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 5.1 038/186] EDAC/mpc85xx: Prevent building as a module
From: Sasha Levin @ 2019-06-01 13:14 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Borislav Petkov, Johannes Thumshirn, linuxppc-dev,
morbidrsa, James Morse, Mauro Carvalho Chehab, linux-edac
In-Reply-To: <20190601131653.24205-1-sashal@kernel.org>
From: Michael Ellerman <mpe@ellerman.id.au>
[ Upstream commit 2b8358a951b1e2a534a54924cd8245e58a1c5fb8 ]
The mpc85xx EDAC driver can be configured as a module but then fails to
build because it uses two unexported symbols:
ERROR: ".pci_find_hose_for_OF_device" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
ERROR: ".early_find_capability" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
We don't want to export those symbols just for this driver, so make the
driver only configurable as a built-in.
This seems to have been broken since at least
c92132f59806 ("edac/85xx: Add PCIe error interrupt edac support")
(Nov 2013).
[ bp: make it depend on EDAC=y so that the EDAC core doesn't get built
as a module. ]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: linuxppc-dev@ozlabs.org
Cc: morbidrsa@gmail.com
Link: https://lkml.kernel.org/r/20190502141941.12927-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/edac/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 47eb4d13ed5f8..5e2e0348d460f 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -263,8 +263,8 @@ config EDAC_PND2
micro-server but may appear on others in the future.
config EDAC_MPC85XX
- tristate "Freescale MPC83xx / MPC85xx"
- depends on FSL_SOC
+ bool "Freescale MPC83xx / MPC85xx"
+ depends on FSL_SOC && EDAC=y
help
Support for error detection and correction on the Freescale
MPC8349, MPC8560, MPC8540, MPC8548, T4240
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 5.0 035/173] EDAC/mpc85xx: Prevent building as a module
From: Sasha Levin @ 2019-06-01 13:17 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Borislav Petkov, Johannes Thumshirn, linuxppc-dev,
morbidrsa, James Morse, Mauro Carvalho Chehab, linux-edac
In-Reply-To: <20190601131934.25053-1-sashal@kernel.org>
From: Michael Ellerman <mpe@ellerman.id.au>
[ Upstream commit 2b8358a951b1e2a534a54924cd8245e58a1c5fb8 ]
The mpc85xx EDAC driver can be configured as a module but then fails to
build because it uses two unexported symbols:
ERROR: ".pci_find_hose_for_OF_device" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
ERROR: ".early_find_capability" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
We don't want to export those symbols just for this driver, so make the
driver only configurable as a built-in.
This seems to have been broken since at least
c92132f59806 ("edac/85xx: Add PCIe error interrupt edac support")
(Nov 2013).
[ bp: make it depend on EDAC=y so that the EDAC core doesn't get built
as a module. ]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: linuxppc-dev@ozlabs.org
Cc: morbidrsa@gmail.com
Link: https://lkml.kernel.org/r/20190502141941.12927-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/edac/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index e286b5b990035..a3e6750393380 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -251,8 +251,8 @@ config EDAC_PND2
micro-server but may appear on others in the future.
config EDAC_MPC85XX
- tristate "Freescale MPC83xx / MPC85xx"
- depends on FSL_SOC
+ bool "Freescale MPC83xx / MPC85xx"
+ depends on FSL_SOC && EDAC=y
help
Support for error detection and correction on the Freescale
MPC8349, MPC8560, MPC8540, MPC8548, T4240
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 029/141] EDAC/mpc85xx: Prevent building as a module
From: Sasha Levin @ 2019-06-01 13:20 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Borislav Petkov, Johannes Thumshirn, linuxppc-dev,
morbidrsa, James Morse, Mauro Carvalho Chehab, linux-edac
In-Reply-To: <20190601132158.25821-1-sashal@kernel.org>
From: Michael Ellerman <mpe@ellerman.id.au>
[ Upstream commit 2b8358a951b1e2a534a54924cd8245e58a1c5fb8 ]
The mpc85xx EDAC driver can be configured as a module but then fails to
build because it uses two unexported symbols:
ERROR: ".pci_find_hose_for_OF_device" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
ERROR: ".early_find_capability" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
We don't want to export those symbols just for this driver, so make the
driver only configurable as a built-in.
This seems to have been broken since at least
c92132f59806 ("edac/85xx: Add PCIe error interrupt edac support")
(Nov 2013).
[ bp: make it depend on EDAC=y so that the EDAC core doesn't get built
as a module. ]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: linuxppc-dev@ozlabs.org
Cc: morbidrsa@gmail.com
Link: https://lkml.kernel.org/r/20190502141941.12927-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/edac/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 57304b2e989f2..b00cc03ad6b67 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -250,8 +250,8 @@ config EDAC_PND2
micro-server but may appear on others in the future.
config EDAC_MPC85XX
- tristate "Freescale MPC83xx / MPC85xx"
- depends on FSL_SOC
+ bool "Freescale MPC83xx / MPC85xx"
+ depends on FSL_SOC && EDAC=y
help
Support for error detection and correction on the Freescale
MPC8349, MPC8560, MPC8540, MPC8548, T4240
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.14 23/99] EDAC/mpc85xx: Prevent building as a module
From: Sasha Levin @ 2019-06-01 13:22 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Sasha Levin, Borislav Petkov, Johannes Thumshirn, linuxppc-dev,
morbidrsa, James Morse, Mauro Carvalho Chehab, linux-edac
In-Reply-To: <20190601132346.26558-1-sashal@kernel.org>
From: Michael Ellerman <mpe@ellerman.id.au>
[ Upstream commit 2b8358a951b1e2a534a54924cd8245e58a1c5fb8 ]
The mpc85xx EDAC driver can be configured as a module but then fails to
build because it uses two unexported symbols:
ERROR: ".pci_find_hose_for_OF_device" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
ERROR: ".early_find_capability" [drivers/edac/mpc85xx_edac_mod.ko] undefined!
We don't want to export those symbols just for this driver, so make the
driver only configurable as a built-in.
This seems to have been broken since at least
c92132f59806 ("edac/85xx: Add PCIe error interrupt edac support")
(Nov 2013).
[ bp: make it depend on EDAC=y so that the EDAC core doesn't get built
as a module. ]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Cc: James Morse <james.morse@arm.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: linuxppc-dev@ozlabs.org
Cc: morbidrsa@gmail.com
Link: https://lkml.kernel.org/r/20190502141941.12927-1-mpe@ellerman.id.au
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/edac/Kconfig | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index 96afb2aeed18a..aaaa8ce8d3fdd 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -246,8 +246,8 @@ config EDAC_PND2
micro-server but may appear on others in the future.
config EDAC_MPC85XX
- tristate "Freescale MPC83xx / MPC85xx"
- depends on FSL_SOC
+ bool "Freescale MPC83xx / MPC85xx"
+ depends on FSL_SOC && EDAC=y
help
Support for error detection and correction on the Freescale
MPC8349, MPC8560, MPC8540, MPC8548, T4240
--
2.20.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 39/56] PCI: rpadlpar: Fix leaked device_node references in add/remove paths
From: Sasha Levin @ 2019-06-01 13:25 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Bjorn Helgaas, Sasha Levin, linuxppc-dev, Tyrel Datwyler,
linux-pci
In-Reply-To: <20190601132600.27427-1-sashal@kernel.org>
From: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
[ Upstream commit fb26228bfc4ce3951544848555c0278e2832e618 ]
The find_dlpar_node() helper returns a device node with its reference
incremented. Both the add and remove paths use this helper for find the
appropriate node, but fail to release the reference when done.
Annotate the find_dlpar_node() helper with a comment about the incremented
reference count and call of_node_put() on the obtained device_node in the
add and remove paths. Also, fixup a reference leak in the find_vio_slot()
helper where we fail to call of_node_put() on the vdevice node after we
iterate over its children.
Signed-off-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/pci/hotplug/rpadlpar_core.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/pci/hotplug/rpadlpar_core.c b/drivers/pci/hotplug/rpadlpar_core.c
index f2fcbe944d940..aae295708ea7a 100644
--- a/drivers/pci/hotplug/rpadlpar_core.c
+++ b/drivers/pci/hotplug/rpadlpar_core.c
@@ -55,6 +55,7 @@ static struct device_node *find_vio_slot_node(char *drc_name)
if ((rc == 0) && (!strcmp(drc_name, name)))
break;
}
+ of_node_put(parent);
return dn;
}
@@ -78,6 +79,7 @@ static struct device_node *find_php_slot_pci_node(char *drc_name,
return np;
}
+/* Returns a device_node with its reference count incremented */
static struct device_node *find_dlpar_node(char *drc_name, int *node_type)
{
struct device_node *dn;
@@ -314,6 +316,7 @@ int dlpar_add_slot(char *drc_name)
rc = dlpar_add_phb(drc_name, dn);
break;
}
+ of_node_put(dn);
printk(KERN_INFO "%s: slot %s added\n", DLPAR_MODULE_NAME, drc_name);
exit:
@@ -447,6 +450,7 @@ int dlpar_remove_slot(char *drc_name)
rc = dlpar_remove_pci_slot(drc_name, dn);
break;
}
+ of_node_put(dn);
vm_unmap_aliases();
printk(KERN_INFO "%s: slot %s removed\n", DLPAR_MODULE_NAME, drc_name);
--
2.20.1
^ permalink raw reply related
* Re: [PATCH 03/16] mm: simplify gup_fast_permitted
From: Linus Torvalds @ 2019-06-01 16:14 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Rich Felker, Yoshinori Sato, Linux-sh list, James Hogan,
the arch/x86 maintainers, Khalid Aziz, Nicholas Piggin,
linux-mips, Linux-MM, Paul Burton, Paul Mackerras,
Andrey Konovalov, sparclinux, linuxppc-dev, David S. Miller,
Linux List Kernel Mailing
In-Reply-To: <20190601074959.14036-4-hch@lst.de>
On Sat, Jun 1, 2019 at 12:50 AM Christoph Hellwig <hch@lst.de> wrote:
>
> Pass in the already calculated end value instead of recomputing it, and
> leave the end > start check in the callers instead of duplicating them
> in the arch code.
Good cleanup, except it's wrong.
> - if (nr_pages <= 0)
> + if (end < start)
> return 0;
You moved the overflow test to generic code - good.
You removed the sign and zero test on nr_pages - bad.
The zero test in particular is _important_ - the GUP range operators
know and depend on the fact that they are passed a non-empty range.
The sign test it less so, but is definitely appropriate. It might be
even better to check that the "<< PAGE_SHIFT" doesn't overflow in
"long", of course, but with callers being supposed to be trusted, the
sign test at least checks for stupid underflow issues.
So at the very least that "(end < start)" needs to be "(end <=
start)", but honestly, I think the sign of the nr_pages should be
continued to be checked.
Linus
^ permalink raw reply
* Re: [PATCH 08/16] sparc64: add the missing pgd_page definition
From: Linus Torvalds @ 2019-06-01 16:28 UTC (permalink / raw)
To: Christoph Hellwig
Cc: Rich Felker, Yoshinori Sato, Linux-sh list, James Hogan,
the arch/x86 maintainers, Khalid Aziz, Nicholas Piggin,
linux-mips, Linux-MM, Paul Burton, Paul Mackerras,
Andrey Konovalov, sparclinux, linuxppc-dev, David S. Miller,
Linux List Kernel Mailing
In-Reply-To: <20190601074959.14036-9-hch@lst.de>
Both sparc64 and sh had this pattern, but now that I look at it more
closely, I think your version is wrong, or at least nonoptimal.
On Sat, Jun 1, 2019 at 12:50 AM Christoph Hellwig <hch@lst.de> wrote:
>
> +#define pgd_page(pgd) virt_to_page(__va(pgd_val(pgd)))
Going through the virtual address is potentially very inefficient, and
might in some cases just be wrong (ie it's definitely wrong for
HIGHMEM style setups).
It would likely be much better to go through the physical address and
use "pfn_to_page()". I realize that we don't have a "pgd to physical",
but neither do we really have a "pgd to virtual", and your
"__va(pgd_val(x))" thing is not at allguaranteed to work. You're
basically assuming that "pgd_val(x)" is the physical address, which is
likely not entirely incorrect, but it should be checked by the
architecture people.
The pgd value could easily have high bits with meaning, which would
also potentially screw up the __va(x) model.
So I thgink this would be better done with
#define pgd_page(pgd) pfn_to_page(pgd_pfn(pgd))
where that "pgd_pfn()" would need to be a new (but likely very
trivial) function. That's what we do for pte_pfn().
IOW, it would likely end up something like
#define pgd_to_pfn(pgd) (pgd_val(x) >> PFN_PGD_SHIFT)
David?
Linus
^ permalink raw reply
* Re: [PATCH 00/12] Secure Virtual Machine Enablement
From: Thiago Jung Bauermann @ 2019-06-01 17:11 UTC (permalink / raw)
To: linuxppc-dev
Cc: Anshuman Khandual, Alexey Kardashevskiy, Mike Anderson, Ram Pai,
linux-kernel, Claudio Carvalho, Paul Mackerras, Christoph Hellwig
In-Reply-To: <20190521044912.1375-1-bauerman@linux.ibm.com>
Hello,
Thiago Jung Bauermann <bauerman@linux.ibm.com> writes:
> This series enables Secure Virtual Machines (SVMs) on powerpc. SVMs use the
> Protected Execution Facility (PEF) and request to be migrated to secure
> memory during prom_init() so by default all of their memory is inaccessible
> to the hypervisor. There is an Ultravisor call that the VM can use to
> request certain pages to be made accessible to (or shared with) the
> hypervisor.
>
> The objective of these patches is to have the guest perform this request
> for buffers that need to be accessed by the hypervisor such as the LPPACAs,
> the SWIOTLB memory and the Debug Trace Log.
Ping? Any more comments on these patches? Or even acks? :-)
--
Thiago Jung Bauermann
IBM Linux Technology Center
^ permalink raw reply
* Re: RFC: switch the remaining architectures to use generic GUP v2
From: David Miller @ 2019-06-01 23:46 UTC (permalink / raw)
To: hch
Cc: x86, dalias, ysato, linux-sh, jhogan, linuxppc-dev, khalid.aziz,
npiggin, linux-mips, linux-mm, paul.burton, paulus, andreyknvl,
sparclinux, torvalds, linux-kernel
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 1 Jun 2019 09:49:43 +0200
> below is a series to switch mips, sh and sparc64 to use the generic
> GUP code so that we only have one codebase to touch for further
> improvements to this code. I don't have hardware for any of these
> architectures, and generally no clue about their page table
> management, so handle with care.
>
> Changes since v1:
> - fix various issues found by the build bot
> - cherry pick and use the untagged_addr helper form Andrey
> - add various refactoring patches to share more code over architectures
> - move the powerpc hugepd code to mm/gup.c and sync it with the generic
> hup semantics
I will today look seriously at the sparc64 stuff wrt. tagged pointers.
^ permalink raw reply
* [PATCH] powerpc/nvdimm: Add support for multibyte read/write for metadata
From: Aneesh Kumar K.V @ 2019-06-02 4:43 UTC (permalink / raw)
To: npiggin, paulus, mpe; +Cc: oohall, linuxppc-dev, Aneesh Kumar K.V
SCM_READ/WRITE_MEATADATA hcall supports multibyte read/write. This patch
updates the metadata read/write to use 1, 2, 4 or 8 byte read/write as
mentioned in PAPR document.
READ/WRITE_METADATA hcall supports the 1, 2, 4, or 8 bytes read/write.
For other values hcall results H_P3.
Hypervisor stores the metadata contents in big-endian format and in-order
to enable read/write in different granularity, we need to switch the contents
to big-endian before calling HCALL.
Based on an patch from Oliver O'Halloran <oohall@gmail.com>
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
---
arch/powerpc/platforms/pseries/papr_scm.c | 104 +++++++++++++++++-----
1 file changed, 82 insertions(+), 22 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/papr_scm.c b/arch/powerpc/platforms/pseries/papr_scm.c
index 0176ce66673f..e33cebb8ee6c 100644
--- a/arch/powerpc/platforms/pseries/papr_scm.c
+++ b/arch/powerpc/platforms/pseries/papr_scm.c
@@ -97,42 +97,102 @@ static int drc_pmem_unbind(struct papr_scm_priv *p)
}
static int papr_scm_meta_get(struct papr_scm_priv *p,
- struct nd_cmd_get_config_data_hdr *hdr)
+ struct nd_cmd_get_config_data_hdr *hdr)
{
unsigned long data[PLPAR_HCALL_BUFSIZE];
+ unsigned long offset, data_offset;
+ int len, read;
int64_t ret;
- if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+ if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
return -EINVAL;
- ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
- hdr->in_offset, 1);
-
- if (ret == H_PARAMETER) /* bad DRC index */
- return -ENODEV;
- if (ret)
- return -EINVAL; /* other invalid parameter */
-
- hdr->out_buf[0] = data[0] & 0xff;
-
+ for (len = hdr->in_length; len; len -= read) {
+
+ data_offset = hdr->in_length - len;
+ offset = hdr->in_offset + data_offset;
+
+ if (len >= 8)
+ read = 8;
+ else if (len >= 4)
+ read = 4;
+ else if ( len >= 2)
+ read = 2;
+ else
+ read = 1;
+
+ ret = plpar_hcall(H_SCM_READ_METADATA, data, p->drc_index,
+ offset, read);
+
+ if (ret == H_PARAMETER) /* bad DRC index */
+ return -ENODEV;
+ if (ret)
+ return -EINVAL; /* other invalid parameter */
+
+ switch (read) {
+ case 8:
+ *(uint64_t *)(hdr->out_buf + data_offset) = be64_to_cpu(data[0]);
+ break;
+ case 4:
+ *(uint32_t *)(hdr->out_buf + data_offset) = be32_to_cpu(data[0] & 0xffffffff);
+ break;
+
+ case 2:
+ *(uint16_t *)(hdr->out_buf + data_offset) = be16_to_cpu(data[0] & 0xffff);
+ break;
+
+ case 1:
+ *(uint32_t *)(hdr->out_buf + data_offset) = (data[0] & 0xff);
+ break;
+ }
+ }
return 0;
}
static int papr_scm_meta_set(struct papr_scm_priv *p,
- struct nd_cmd_set_config_hdr *hdr)
+ struct nd_cmd_set_config_hdr *hdr)
{
+ unsigned long offset, data_offset;
+ int len, wrote;
+ unsigned long data;
+ __be64 data_be;
int64_t ret;
- if (hdr->in_offset >= p->metadata_size || hdr->in_length != 1)
+ if ((hdr->in_offset + hdr->in_length) >= p->metadata_size)
return -EINVAL;
- ret = plpar_hcall_norets(H_SCM_WRITE_METADATA,
- p->drc_index, hdr->in_offset, hdr->in_buf[0], 1);
-
- if (ret == H_PARAMETER) /* bad DRC index */
- return -ENODEV;
- if (ret)
- return -EINVAL; /* other invalid parameter */
+ for (len = hdr->in_length; len; len -= wrote) {
+
+ data_offset = hdr->in_length - len;
+ offset = hdr->in_offset + data_offset;
+
+ if (len >= 8) {
+ data = *(uint64_t *)(hdr->in_buf + data_offset);
+ data_be = cpu_to_be64(data);
+ wrote = 8;
+ } else if (len >= 4) {
+ data = *(uint32_t *)(hdr->in_buf + data_offset);
+ data &= 0xffffffff;
+ data_be = cpu_to_be32(data);
+ wrote = 4;
+ } else if (len >= 2) {
+ data = *(uint16_t *)(hdr->in_buf + data_offset);
+ data &= 0xffff;
+ data_be = cpu_to_be16(data);
+ wrote = 2;
+ } else {
+ data_be = *(uint8_t *)(hdr->in_buf + data_offset);
+ data_be &= 0xff;
+ wrote = 1;
+ }
+
+ ret = plpar_hcall_norets(H_SCM_WRITE_METADATA, p->drc_index,
+ offset, data_be, wrote);
+ if (ret == H_PARAMETER) /* bad DRC index */
+ return -ENODEV;
+ if (ret)
+ return -EINVAL; /* other invalid parameter */
+ }
return 0;
}
@@ -154,7 +214,7 @@ int papr_scm_ndctl(struct nvdimm_bus_descriptor *nd_desc, struct nvdimm *nvdimm,
get_size_hdr = buf;
get_size_hdr->status = 0;
- get_size_hdr->max_xfer = 1;
+ get_size_hdr->max_xfer = 8;
get_size_hdr->config_size = p->metadata_size;
*cmd_rc = 0;
break;
--
2.21.0
^ permalink raw reply related
* Re: [PATCH 10/16] sparc64: use the generic get_user_pages_fast code
From: Hillf Danton @ 2019-06-02 7:39 UTC (permalink / raw)
To: Christoph Hellwig
Cc: x86, Rich Felker, Yoshinori Sato, linux-sh, James Hogan,
linuxppc-dev, Khalid Aziz, Nicholas Piggin, linux-mips, linux-mm,
Paul Burton, Paul Mackerras, Andrey Konovalov, sparclinux,
Linus Torvalds, David S. Miller, linux-kernel
In-Reply-To: <20190601074959.14036-1-hch@lst.de>
Hi Christoph
On Sat, 1 Jun 2019 09:49:53 +0200 Christoph Hellwig wrote:
>
> diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
> index a93eca29e85a..2301ab5250e4 100644
> --- a/arch/sparc/include/asm/pgtable_64.h
> +++ b/arch/sparc/include/asm/pgtable_64.h
> @@ -1098,6 +1098,24 @@ static inline unsigned long untagged_addr(unsigned long start)
> }
> #define untagged_addr untagged_addr
>
> +static inline bool pte_access_permitted(pte_t pte, bool write)
> +{
> + u64 prot;
> +
> + if (tlb_type == hypervisor) {
> + prot = _PAGE_PRESENT_4V | _PAGE_P_4V;
> + if (prot)
Feel free to correct me if I misread or miss anything.
It looks like a typo: s/prot/write/, as checking _PAGE_PRESENT_4V and
_PAGE_P_4V makes prot always have _PAGE_WRITE_4V set, regardless of write.
> + prot |= _PAGE_WRITE_4V;
> + } else {
> + prot = _PAGE_PRESENT_4U | _PAGE_P_4U;
> + if (write)
> + prot |= _PAGE_WRITE_4U;
> + }
> +
> + return (pte_val(pte) & (prot | _PAGE_SPECIAL)) == prot;
> +}
> +#define pte_access_permitted pte_access_permitted
> +
> #include <asm/tlbflush.h>
> #include <asm-generic/pgtable.h>
BR
Hillf
^ permalink raw reply
* [Bug 203517] WARNING: inconsistent lock state. inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} usage.
From: bugzilla-daemon @ 2019-06-02 10:00 UTC (permalink / raw)
To: linuxppc-dev
In-Reply-To: <bug-203517-206035@https.bugzilla.kernel.org/>
https://bugzilla.kernel.org/show_bug.cgi?id=203517
Michael Ellerman (michael@ellerman.id.au) changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |michael@ellerman.id.au
--- Comment #10 from Michael Ellerman (michael@ellerman.id.au) ---
No, it's in mainline since Friday so it will get picked up for stable in the
next week or so:
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=fee13fe96529523a709d1fff487f14a5e0d56d34
--
You are receiving this mail because:
You are watching the assignee of the bug.
^ permalink raw reply
* Re: [PATCH] scsi: ibmvscsi: Don't use rc uninitialized in ibmvscsi_do_work
From: Michael Ellerman @ 2019-06-02 10:15 UTC (permalink / raw)
To: Nathan Chancellor, Tyrel Datwyler, James E.J. Bottomley,
Martin K. Petersen
Cc: clang-built-linux, Nathan Chancellor, linuxppc-dev, linux-kernel,
linux-scsi
In-Reply-To: <20190531185306.41290-1-natechancellor@gmail.com>
Hi Nathan,
Nathan Chancellor <natechancellor@gmail.com> writes:
> clang warns:
>
> drivers/scsi/ibmvscsi/ibmvscsi.c:2126:7: warning: variable 'rc' is used
> uninitialized whenever switch case is taken [-Wsometimes-uninitialized]
> case IBMVSCSI_HOST_ACTION_NONE:
> ^~~~~~~~~~~~~~~~~~~~~~~~~
> drivers/scsi/ibmvscsi/ibmvscsi.c:2151:6: note: uninitialized use occurs
> here
> if (rc) {
> ^~
>
> Initialize rc to zero so that the atomic_set and dev_err statement don't
> trigger for the cases that just break.
>
> Fixes: 035a3c4046b5 ("scsi: ibmvscsi: redo driver work thread to use enum action states")
> Link: https://github.com/ClangBuiltLinux/linux/issues/502
> Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
> ---
> drivers/scsi/ibmvscsi/ibmvscsi.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
> index 727c31dc11a0..6714d8043e62 100644
> --- a/drivers/scsi/ibmvscsi/ibmvscsi.c
> +++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
> @@ -2118,7 +2118,7 @@ static unsigned long ibmvscsi_get_desired_dma(struct vio_dev *vdev)
> static void ibmvscsi_do_work(struct ibmvscsi_host_data *hostdata)
> {
> unsigned long flags;
> - int rc;
> + int rc = 0;
> char *action = "reset";
>
> spin_lock_irqsave(hostdata->host->host_lock, flags);
It's always preferable IMHO to keep any initialisation as localised as
possible, so that the compiler can continue to warn about uninitialised
usages elsewhere. In this case that would mean doing the rc = 0 in the
switch, something like:
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 727c31dc11a0..7ee5755cf636 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -2123,9 +2123,6 @@ static void ibmvscsi_do_work(struct ibmvscsi_host_data *hostdata)
spin_lock_irqsave(hostdata->host->host_lock, flags);
switch (hostdata->action) {
- case IBMVSCSI_HOST_ACTION_NONE:
- case IBMVSCSI_HOST_ACTION_UNBLOCK:
- break;
case IBMVSCSI_HOST_ACTION_RESET:
spin_unlock_irqrestore(hostdata->host->host_lock, flags);
rc = ibmvscsi_reset_crq_queue(&hostdata->queue, hostdata);
@@ -2142,7 +2139,10 @@ static void ibmvscsi_do_work(struct ibmvscsi_host_data *hostdata)
if (!rc)
rc = ibmvscsi_send_crq(hostdata, 0xC001000000000000LL, 0);
break;
+ case IBMVSCSI_HOST_ACTION_NONE:
+ case IBMVSCSI_HOST_ACTION_UNBLOCK:
default:
+ rc = 0;
break;
}
But then that makes me wonder if that's actually correct?
If we get an action that we don't recognise should we just throw it away
like that? (by doing hostdata->action = IBMVSCSI_HOST_ACTION_NONE). Tyrel?
cheers
^ permalink raw reply related
* [GIT PULL] Please pull powerpc/linux.git powerpc-5.2-3 tag
From: Michael Ellerman @ 2019-06-02 11:05 UTC (permalink / raw)
To: Linus Torvalds; +Cc: ravi.bangoria, anju, linuxppc-dev, linux-kernel, bauerman
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Hi Linus,
Please pull some more powerpc fixes for 5.2:
The following changes since commit a188339ca5a396acc588e5851ed7e19f66b0ebd9:
Linux 5.2-rc1 (2019-05-19 15:47:09 -0700)
are available in the git repository at:
https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git tags/powerpc-5.2-3
for you to fetch changes up to 8b909e3548706cbebc0a676067b81aadda57f47e:
powerpc/kexec: Fix loading of kernel + initramfs with kexec_file_load() (2019-05-23 14:00:32 +1000)
- ------------------------------------------------------------------
powerpc fixes for 5.2 #3
A minor fix to our IMC PMU code to print a less confusing error message when the
driver can't initialise properly.
A fix for a bug where a user requesting an unsupported branch sampling filter
can corrupt PMU state, preventing the PMU from counting properly.
And finally a fix for a bug in our support for kexec_file_load(), which
prevented loading a kernel and initramfs. Most versions of kexec don't yet use
kexec_file_load().
Thanks to:
Anju T Sudhakar, Dave Young, Madhavan Srinivasan, Ravi Bangoria, Thiago Jung
Bauermann.
- ------------------------------------------------------------------
Anju T Sudhakar (1):
powerpc/powernv: Return for invalid IMC domain
Ravi Bangoria (1):
powerpc/perf: Fix MMCRA corruption by bhrb_filter
Thiago Jung Bauermann (1):
powerpc/kexec: Fix loading of kernel + initramfs with kexec_file_load()
arch/powerpc/kernel/kexec_elf_64.c | 6 +++++-
arch/powerpc/perf/core-book3s.c | 6 ++++--
arch/powerpc/perf/power8-pmu.c | 3 +++
arch/powerpc/perf/power9-pmu.c | 3 +++
arch/powerpc/platforms/powernv/opal-imc.c | 4 ++++
5 files changed, 19 insertions(+), 3 deletions(-)
-----BEGIN PGP SIGNATURE-----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=qxoS
-----END PGP SIGNATURE-----
^ permalink raw reply
* Re: [GIT PULL] Please pull powerpc/linux.git powerpc-5.2-3 tag
From: pr-tracker-bot @ 2019-06-02 17:25 UTC (permalink / raw)
To: Michael Ellerman
Cc: ravi.bangoria, Linus Torvalds, linux-kernel, anju, linuxppc-dev,
bauerman
In-Reply-To: <878suknt7b.fsf@concordia.ellerman.id.au>
The pull request you sent on Sun, 02 Jun 2019 21:05:12 +1000:
> https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git tags/powerpc-5.2-3
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/460b48a0fefce25beb0fc0139e721c5691d65d7f
Thank you!
--
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker
^ permalink raw reply
* Re: [PATCH kernel] prom_init: Fetch flatten device tree from the system firmware
From: Segher Boessenkool @ 2019-06-02 23:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Alexey Kardashevskiy, linuxppc-dev, Suraj Jitindar Singh,
David Gibson
In-Reply-To: <43f037c57eed8ad2175470c940917dced947bb70.camel@kernel.crashing.org>
Hi!
On Fri, May 31, 2019 at 11:03:26AM +1000, Benjamin Herrenschmidt wrote:
> On Thu, 2019-05-30 at 14:37 -0500, Segher Boessenkool wrote:
> > On Thu, May 30, 2019 at 05:09:06PM +1000, Alexey Kardashevskiy wrote:
> > > so, it is sort-of nack from David and sort-of ack from Segher, what
> > > happens now?
> >
> > Maybe what we really need just a CI call to get all properties of a node
> > at once? Will that speed up things enough?
> >
> > That way you need no change at all in lifetime of properties and how they
> > are used, etc.; just a client getting the properties is a lot faster.
>
> Hrm... if we're going to create a new interface, let's go for what we
> need.
>
> What we need is the FDT. It's a rather ubiquitous thing these days, it
> makes sense to have a way to fetch an FDT directly from FW.
That is all you need if you do not want to use OF at all.
If you *do* want to keep having an Open Firmware, what we want or need
is a faster way to walk huge device trees.
> There is no use for the "fetch all properties" cases other than
> building an FDT that any of us can think of, and it would create a more
> complicated interface than just "fetch an FDT".
It is a simple way to speed up fetching the device tree enormously,
without needing big changes to either OF or the clients using it -- not
in the code, but importantly also not conceptually: everything works just
as before, just a lot faster.
> So I go for the simple one and agree with Alexey's idea.
When dealing with a whole device tree you have to know about the various
dynamically generated nodes and props, and handle each appropriately.
Segher
^ permalink raw reply
* Re: [PATCH 1/3] powerpc/pseries: Simplify cpu readd to use drc_index
From: Tyrel Datwyler @ 2019-06-03 0:11 UTC (permalink / raw)
To: Nathan Lynch, Tyrel Datwyler; +Cc: mingming.cao, linuxppc-dev
In-Reply-To: <87tvdpjhju.fsf@linux.ibm.com>
On 05/20/2019 08:01 AM, Nathan Lynch wrote:
> Tyrel Datwyler <tyreld@linux.vnet.ibm.com> writes:
>
>> On 05/16/2019 12:17 PM, Nathan Lynch wrote:
>>> Tyrel Datwyler <tyreld@linux.ibm.com> writes:
>>>> The current dlpar_cpu_readd() takes in a cpu_id and uses that to look up
>>>> the cpus device_node so that we can get at the ibm,my-drc-index
>>>> property. The only user of cpu readd is an OF notifier call back. This
>>>> call back already has a reference to the device_node and therefore can
>>>> retrieve the drc_index from the device_node.
>>>
>>> dlpar_cpu_readd is a hack to try to change the CPU-node relationship at
>>> runtime without destabilizing the system. It doesn't accomplish that and
>>> it should just be removed (and I'm working on that).
>>>
>>
>> I will politely disagree. We've done exactly this from userspace for
>> years. My experience still suggests that memory affinity is the
>> problem area, and that the work to push this all into the kernel
>> originally was poorly tested.
>
> Kernel implementation details aside, how do you change the cpu-node
> relationship at runtime without breaking NUMA-aware applications? Is
> this not a fundamental issue to address before adding code like this?
>
If that is the concern then hotplug in general already breaks them. Take for
example the removal of a faulty processor and then adding a new processor back.
It is quite possible that the new processor is in a different NUMA node. Keep in
mind that in this scenario the new processor and threads gets the same logical
cpu ids as the faulty processor we just removed.
Now we have to ask the question who is right and who is wrong. In this case the
kernel data structures reflect the correct NUMA topology. However, did the NUMA
aware application or libnuma make an assumption that specific sets of logical
cpu ids are always in the same NUMA node?
-Tyrel
^ 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