LinuxPPC-Dev Archive on lore.kernel.org
 help / color / mirror / Atom feed
* [PATCH 14/29] mm: rename vmap_page_range to map_kernel_range
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

This matches the map_kernel_range_noflush API.  Also change to pass
a size instead of the end, similar to the noflush version.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 mm/vmalloc.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 55df5dc6a9fc..a3d810def567 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -272,13 +272,13 @@ int map_kernel_range_noflush(unsigned long addr, unsigned long size,
 	return nr;
 }
 
-static int vmap_page_range(unsigned long start, unsigned long end,
+static int map_kernel_range(unsigned long start, unsigned long size,
 			   pgprot_t prot, struct page **pages)
 {
 	int ret;
 
-	ret = map_kernel_range_noflush(start, end - start, prot, pages);
-	flush_cache_vmap(start, end);
+	ret = map_kernel_range_noflush(start, size, prot, pages);
+	flush_cache_vmap(start, start + size);
 	return ret;
 }
 
@@ -1866,7 +1866,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro
 
 	kasan_unpoison_vmalloc(mem, size);
 
-	if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
+	if (map_kernel_range(addr, size, prot, pages) < 0) {
 		vm_unmap_ram(mem, count);
 		return NULL;
 	}
@@ -2030,10 +2030,9 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)
 int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
 {
 	unsigned long addr = (unsigned long)area->addr;
-	unsigned long end = addr + get_vm_area_size(area);
 	int err;
 
-	err = vmap_page_range(addr, end, prot, pages);
+	err = map_kernel_range(addr, get_vm_area_size(area), prot, pages);
 
 	return err > 0 ? 0 : err;
 }
-- 
2.25.1


^ permalink raw reply related

* [PATCH 12/29] mm: pass addr as unsigned long to vb_free
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Ever use of addr in vb_free casts to unsigned long first, and the caller
has an unsigned long version of the address available anyway.  Just pass
that and avoid all the casts.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 mm/vmalloc.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 9183fc0d365a..aada9e9144bd 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1664,7 +1664,7 @@ static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
 	return vaddr;
 }
 
-static void vb_free(const void *addr, unsigned long size)
+static void vb_free(unsigned long addr, unsigned long size)
 {
 	unsigned long offset;
 	unsigned long vb_idx;
@@ -1674,24 +1674,22 @@ static void vb_free(const void *addr, unsigned long size)
 	BUG_ON(offset_in_page(size));
 	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
 
-	flush_cache_vunmap((unsigned long)addr, (unsigned long)addr + size);
+	flush_cache_vunmap(addr, addr + size);
 
 	order = get_order(size);
 
-	offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
-	offset >>= PAGE_SHIFT;
+	offset = (addr & (VMAP_BLOCK_SIZE - 1)) >> PAGE_SHIFT;
 
-	vb_idx = addr_to_vb_idx((unsigned long)addr);
+	vb_idx = addr_to_vb_idx(addr);
 	rcu_read_lock();
 	vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
 	rcu_read_unlock();
 	BUG_ON(!vb);
 
-	vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
+	vunmap_page_range(addr, addr + size);
 
 	if (debug_pagealloc_enabled_static())
-		flush_tlb_kernel_range((unsigned long)addr,
-					(unsigned long)addr + size);
+		flush_tlb_kernel_range(addr, addr + size);
 
 	spin_lock(&vb->lock);
 
@@ -1791,7 +1789,7 @@ void vm_unmap_ram(const void *mem, unsigned int count)
 
 	if (likely(count <= VMAP_MAX_ALLOC)) {
 		debug_check_no_locks_freed(mem, size);
-		vb_free(mem, size);
+		vb_free(addr, size);
 		return;
 	}
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH 11/29] mm: only allow page table mappings for built-in zsmalloc
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

This allows to unexport map_vm_area and unmap_kernel_range, which are
rather deep internal and should not be available to modules, as they for
example allow fine grained control of mapping permissions, and also
allow splitting the setup of a vmalloc area and the actual mapping and
thus expose vmalloc internals.

zsmalloc is typically built-in and continues to work (just like the
percpu-vm code using a similar patter), while modular zsmalloc also
continues to work, but must use copies.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 mm/Kconfig   | 2 +-
 mm/vmalloc.c | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/mm/Kconfig b/mm/Kconfig
index 09a9edfb8461..5c0362bd8d56 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -707,7 +707,7 @@ config ZSMALLOC
 
 config ZSMALLOC_PGTABLE_MAPPING
 	bool "Use page table mapping to access object in zsmalloc"
-	depends on ZSMALLOC
+	depends on ZSMALLOC=y
 	help
 	  By default, zsmalloc uses a copy-based object mapping method to
 	  access allocations that span two pages. However, if a particular
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3375f9508ef6..9183fc0d365a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2046,7 +2046,6 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)
 	vunmap_page_range(addr, end);
 	flush_tlb_kernel_range(addr, end);
 }
-EXPORT_SYMBOL_GPL(unmap_kernel_range);
 
 int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
 {
@@ -2058,7 +2057,6 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page **pages)
 
 	return err > 0 ? 0 : err;
 }
-EXPORT_SYMBOL_GPL(map_vm_area);
 
 static inline void setup_vmalloc_vm_locked(struct vm_struct *vm,
 	struct vmap_area *va, unsigned long flags, const void *caller)
-- 
2.25.1


^ permalink raw reply related

* [PATCH 09/29] mm: unexport unmap_kernel_range_noflush
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

There are no modular users of this function.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 mm/vmalloc.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index d1534d610b48..3375f9508ef6 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2029,7 +2029,6 @@ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
 {
 	vunmap_page_range(addr, addr + size);
 }
-EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush);
 
 /**
  * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
-- 
2.25.1


^ permalink raw reply related

* [PATCH 10/29] mm: rename CONFIG_PGTABLE_MAPPING to CONFIG_ZSMALLOC_PGTABLE_MAPPING
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Rename the Kconfig variable to clarify the scope.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Minchan Kim <minchan@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/arm/configs/omap2plus_defconfig | 2 +-
 include/linux/zsmalloc.h             | 2 +-
 mm/Kconfig                           | 2 +-
 mm/zsmalloc.c                        | 8 ++++----
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 3cc3ca5fa027..583d8abd80a4 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -81,7 +81,7 @@ CONFIG_PARTITION_ADVANCED=y
 CONFIG_BINFMT_MISC=y
 CONFIG_CMA=y
 CONFIG_ZSMALLOC=m
-CONFIG_PGTABLE_MAPPING=y
+CONFIG_ZSMALLOC_PGTABLE_MAPPING=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 2219cce81ca4..0fdbf653b173 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -20,7 +20,7 @@
  * zsmalloc mapping modes
  *
  * NOTE: These only make a difference when a mapped object spans pages.
- * They also have no effect when PGTABLE_MAPPING is selected.
+ * They also have no effect when ZSMALLOC_PGTABLE_MAPPING is selected.
  */
 enum zs_mapmode {
 	ZS_MM_RW, /* normal read-write mapping */
diff --git a/mm/Kconfig b/mm/Kconfig
index c1acc34c1c35..09a9edfb8461 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -705,7 +705,7 @@ config ZSMALLOC
 	  returned by an alloc().  This handle must be mapped in order to
 	  access the allocated space.
 
-config PGTABLE_MAPPING
+config ZSMALLOC_PGTABLE_MAPPING
 	bool "Use page table mapping to access object in zsmalloc"
 	depends on ZSMALLOC
 	help
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 2f836a2b993f..ac0524330b9b 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -293,7 +293,7 @@ struct zspage {
 };
 
 struct mapping_area {
-#ifdef CONFIG_PGTABLE_MAPPING
+#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
 	struct vm_struct *vm; /* vm area for mapping object that span pages */
 #else
 	char *vm_buf; /* copy buffer for objects that span pages */
@@ -1113,7 +1113,7 @@ static struct zspage *find_get_zspage(struct size_class *class)
 	return zspage;
 }
 
-#ifdef CONFIG_PGTABLE_MAPPING
+#ifdef CONFIG_ZSMALLOC_PGTABLE_MAPPING
 static inline int __zs_cpu_up(struct mapping_area *area)
 {
 	/*
@@ -1151,7 +1151,7 @@ static inline void __zs_unmap_object(struct mapping_area *area,
 	unmap_kernel_range(addr, PAGE_SIZE * 2);
 }
 
-#else /* CONFIG_PGTABLE_MAPPING */
+#else /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
 
 static inline int __zs_cpu_up(struct mapping_area *area)
 {
@@ -1233,7 +1233,7 @@ static void __zs_unmap_object(struct mapping_area *area,
 	pagefault_enable();
 }
 
-#endif /* CONFIG_PGTABLE_MAPPING */
+#endif /* CONFIG_ZSMALLOC_PGTABLE_MAPPING */
 
 static int zs_cpu_prepare(unsigned int cpu)
 {
-- 
2.25.1


^ permalink raw reply related

* [PATCH 08/29] mm: remove __get_vm_area
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Switch the two remaining callers to use __get_vm_area_caller instead.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/powerpc/kernel/pci_64.c | 3 ++-
 arch/sh/kernel/cpu/sh4/sq.c  | 3 ++-
 include/linux/vmalloc.h      | 2 --
 mm/vmalloc.c                 | 8 --------
 4 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 2a976314f169..d9ac980c398c 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -132,7 +132,8 @@ void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
 	 * address decoding but I'd rather not deal with those outside of the
 	 * reserved 64K legacy region.
 	 */
-	area = __get_vm_area(size, 0, PHB_IO_BASE, PHB_IO_END);
+	area = __get_vm_area_caller(size, 0, PHB_IO_BASE, PHB_IO_END,
+				    __builtin_return_address(0));
 	if (!area)
 		return NULL;
 
diff --git a/arch/sh/kernel/cpu/sh4/sq.c b/arch/sh/kernel/cpu/sh4/sq.c
index 934ff84844fa..d432164b23b7 100644
--- a/arch/sh/kernel/cpu/sh4/sq.c
+++ b/arch/sh/kernel/cpu/sh4/sq.c
@@ -103,7 +103,8 @@ static int __sq_remap(struct sq_mapping *map, pgprot_t prot)
 #if defined(CONFIG_MMU)
 	struct vm_struct *vma;
 
-	vma = __get_vm_area(map->size, VM_ALLOC, map->sq_addr, SQ_ADDRMAX);
+	vma = __get_vm_area_caller(map->size, VM_ALLOC, map->sq_addr,
+			SQ_ADDRMAX, __builtin_return_address(0));
 	if (!vma)
 		return -ENOMEM;
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 0507a162ccd0..3070b4dbc2d9 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -161,8 +161,6 @@ static inline size_t get_vm_area_size(const struct vm_struct *area)
 extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
 extern struct vm_struct *get_vm_area_caller(unsigned long size,
 					unsigned long flags, const void *caller);
-extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
-					unsigned long start, unsigned long end);
 extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long flags,
 					unsigned long start, unsigned long end,
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 399f219544f7..d1534d610b48 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2127,14 +2127,6 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 	return area;
 }
 
-struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
-				unsigned long start, unsigned long end)
-{
-	return __get_vm_area_node(size, 1, flags, start, end, NUMA_NO_NODE,
-				  GFP_KERNEL, __builtin_return_address(0));
-}
-EXPORT_SYMBOL_GPL(__get_vm_area);
-
 struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
 				       unsigned long start, unsigned long end,
 				       const void *caller)
-- 
2.25.1


^ permalink raw reply related

* [PATCH 07/29] powerpc: remove __ioremap_at and __iounmap_at
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

These helpers are only used for remapping the ISA I/O base.  Replace
the mapping side with a remap_isa_range helper in isa-bridge.c that
hard codes all the known arguments, and just remove __iounmap_at in
favour of open coding it in the only caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/powerpc/include/asm/io.h    |  8 -----
 arch/powerpc/kernel/isa-bridge.c | 28 +++++++++++++-----
 arch/powerpc/mm/ioremap_64.c     | 50 --------------------------------
 3 files changed, 21 insertions(+), 65 deletions(-)

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 91320985d33f..13f90dd03450 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -699,10 +699,6 @@ static inline void iosync(void)
  *
  * * iounmap undoes such a mapping and can be hooked
  *
- * * __ioremap_at (and the pending __iounmap_at) are low level functions to
- *   create hand-made mappings for use only by the PCI code and cannot
- *   currently be hooked. Must be page aligned.
- *
  * * __ioremap_caller is the same as above but takes an explicit caller
  *   reference rather than using __builtin_return_address(0)
  *
@@ -729,10 +725,6 @@ void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
 extern void __iomem *__ioremap_caller(phys_addr_t, unsigned long size,
 				      pgprot_t prot, void *caller);
 
-extern void __iomem * __ioremap_at(phys_addr_t pa, void *ea,
-				   unsigned long size, pgprot_t prot);
-extern void __iounmap_at(void *ea, unsigned long size);
-
 /*
  * When CONFIG_PPC_INDIRECT_PIO is set, we use the generic iomap implementation
  * which needs some additional definitions here. They basically allow PIO
diff --git a/arch/powerpc/kernel/isa-bridge.c b/arch/powerpc/kernel/isa-bridge.c
index 773671b512df..2257d24e6a26 100644
--- a/arch/powerpc/kernel/isa-bridge.c
+++ b/arch/powerpc/kernel/isa-bridge.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/notifier.h>
+#include <linux/vmalloc.h>
 
 #include <asm/processor.h>
 #include <asm/io.h>
@@ -38,6 +39,22 @@ EXPORT_SYMBOL_GPL(isa_bridge_pcidev);
 #define ISA_SPACE_MASK 0x1
 #define ISA_SPACE_IO 0x1
 
+static void remap_isa_base(phys_addr_t pa, unsigned long size)
+{
+	WARN_ON_ONCE(ISA_IO_BASE & ~PAGE_MASK);
+	WARN_ON_ONCE(pa & ~PAGE_MASK);
+	WARN_ON_ONCE(size & ~PAGE_MASK);
+
+	if (slab_is_available()) {
+		if (ioremap_page_range(ISA_IO_BASE, ISA_IO_BASE + size, pa,
+				pgprot_noncached(PAGE_KERNEL)))
+			unmap_kernel_range(ISA_IO_BASE, size);
+	} else {
+		early_ioremap_range(ISA_IO_BASE, pa, size,
+				pgprot_noncached(PAGE_KERNEL));
+	}
+}
+
 static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
 				      unsigned long phb_io_base_phys)
 {
@@ -105,15 +122,13 @@ static void pci_process_ISA_OF_ranges(struct device_node *isa_node,
 	if (size > 0x10000)
 		size = 0x10000;
 
-	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     size, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(phb_io_base_phys, size);
 	return;
 
 inval_range:
 	printk(KERN_ERR "no ISA IO ranges or unexpected isa range, "
 	       "mapping 64k\n");
-	__ioremap_at(phb_io_base_phys, (void *)ISA_IO_BASE,
-		     0x10000, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(phb_io_base_phys, 0x10000);
 }
 
 
@@ -248,8 +263,7 @@ void __init isa_bridge_init_non_pci(struct device_node *np)
 	 * and map it
 	 */
 	isa_io_base = ISA_IO_BASE;
-	__ioremap_at(pbase, (void *)ISA_IO_BASE,
-		     size, pgprot_noncached(PAGE_KERNEL));
+	remap_isa_base(pbase, size);
 
 	pr_debug("ISA: Non-PCI bridge is %pOF\n", np);
 }
@@ -297,7 +311,7 @@ static void isa_bridge_remove(void)
 	isa_bridge_pcidev = NULL;
 
 	/* Unmap the ISA area */
-	__iounmap_at((void *)ISA_IO_BASE, 0x10000);
+	unmap_kernel_range(ISA_IO_BASE, 0x10000);
 }
 
 /**
diff --git a/arch/powerpc/mm/ioremap_64.c b/arch/powerpc/mm/ioremap_64.c
index 50a99d9684f7..ba5cbb0d66bd 100644
--- a/arch/powerpc/mm/ioremap_64.c
+++ b/arch/powerpc/mm/ioremap_64.c
@@ -4,56 +4,6 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 
-/**
- * Low level function to establish the page tables for an IO mapping
- */
-void __iomem *__ioremap_at(phys_addr_t pa, void *ea, unsigned long size, pgprot_t prot)
-{
-	int ret;
-	unsigned long va = (unsigned long)ea;
-
-	/* We don't support the 4K PFN hack with ioremap */
-	if (pgprot_val(prot) & H_PAGE_4K_PFN)
-		return NULL;
-
-	if ((ea + size) >= (void *)IOREMAP_END) {
-		pr_warn("Outside the supported range\n");
-		return NULL;
-	}
-
-	WARN_ON(pa & ~PAGE_MASK);
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	if (slab_is_available()) {
-		ret = ioremap_page_range(va, va + size, pa, prot);
-		if (ret)
-			unmap_kernel_range(va, size);
-	} else {
-		ret = early_ioremap_range(va, pa, size, prot);
-	}
-
-	if (ret)
-		return NULL;
-
-	return (void __iomem *)ea;
-}
-EXPORT_SYMBOL(__ioremap_at);
-
-/**
- * Low level function to tear down the page tables for an IO mapping. This is
- * used for mappings that are manipulated manually, like partial unmapping of
- * PCI IOs or ISA space.
- */
-void __iounmap_at(void *ea, unsigned long size)
-{
-	WARN_ON(((unsigned long)ea) & ~PAGE_MASK);
-	WARN_ON(size & ~PAGE_MASK);
-
-	unmap_kernel_range((unsigned long)ea, size);
-}
-EXPORT_SYMBOL(__iounmap_at);
-
 void __iomem *__ioremap_caller(phys_addr_t addr, unsigned long size,
 			       pgprot_t prot, void *caller)
 {
-- 
2.25.1


^ permalink raw reply related

* [PATCH 06/29] powerpc: add an ioremap_phb helper
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Factor code shared between pci_64 and electra_cf into a ioremap_pbh
helper that follows the normal ioremap semantics, and returns a
useful __iomem pointer.  Note that it opencodes __ioremap_at as
we know from the callers the slab is available.  Switch pci_64
to also store the result as __iomem pointer, and unmap the result
using iounmap instead of force casting and using vmalloc APIs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/powerpc/include/asm/io.h         |  2 +
 arch/powerpc/include/asm/pci-bridge.h |  2 +-
 arch/powerpc/kernel/pci_64.c          | 53 ++++++++++++++++++---------
 drivers/pcmcia/electra_cf.c           | 45 ++++++++---------------
 4 files changed, 54 insertions(+), 48 deletions(-)

diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h
index 635969b5b58e..91320985d33f 100644
--- a/arch/powerpc/include/asm/io.h
+++ b/arch/powerpc/include/asm/io.h
@@ -719,6 +719,8 @@ void __iomem *ioremap_coherent(phys_addr_t address, unsigned long size);
 
 extern void iounmap(volatile void __iomem *addr);
 
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size);
+
 int early_ioremap_range(unsigned long ea, phys_addr_t pa,
 			unsigned long size, pgprot_t prot);
 void __iomem *do_ioremap(phys_addr_t pa, phys_addr_t offset, unsigned long size,
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 69f4cb3b7c56..b92e81b256e5 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -66,7 +66,7 @@ struct pci_controller {
 
 	void __iomem *io_base_virt;
 #ifdef CONFIG_PPC64
-	void *io_base_alloc;
+	void __iomem *io_base_alloc;
 #endif
 	resource_size_t io_base_phys;
 	resource_size_t pci_io_size;
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index f83d1f69b1dd..2a976314f169 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -109,23 +109,46 @@ int pcibios_unmap_io_space(struct pci_bus *bus)
 	/* Get the host bridge */
 	hose = pci_bus_to_host(bus);
 
-	/* Check if we have IOs allocated */
-	if (hose->io_base_alloc == NULL)
-		return 0;
-
 	pr_debug("IO unmapping for PHB %pOF\n", hose->dn);
 	pr_debug("  alloc=0x%p\n", hose->io_base_alloc);
 
-	/* This is a PHB, we fully unmap the IO area */
-	vunmap(hose->io_base_alloc);
-
+	iounmap(hose->io_base_alloc);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pcibios_unmap_io_space);
 
-static int pcibios_map_phb_io_space(struct pci_controller *hose)
+void __iomem *ioremap_phb(phys_addr_t paddr, unsigned long size)
 {
 	struct vm_struct *area;
+	unsigned long addr;
+
+	WARN_ON_ONCE(paddr & ~PAGE_MASK);
+	WARN_ON_ONCE(size & ~PAGE_MASK);
+
+	/*
+	 * Let's allocate some IO space for that guy. We don't pass VM_IOREMAP
+	 * because we don't care about alignment tricks that the core does in
+	 * that case.  Maybe we should due to stupid card with incomplete
+	 * address decoding but I'd rather not deal with those outside of the
+	 * reserved 64K legacy region.
+	 */
+	area = __get_vm_area(size, 0, PHB_IO_BASE, PHB_IO_END);
+	if (!area)
+		return NULL;
+
+	addr = (unsigned long)area->addr;
+	if (ioremap_page_range(addr, addr + size, paddr,
+			pgprot_noncached(PAGE_KERNEL))) {
+		unmap_kernel_range(addr, size);
+		return NULL;
+	}
+
+	return (void __iomem *)addr;
+}
+EXPORT_SYMBOL_GPL(ioremap_phb);
+
+static int pcibios_map_phb_io_space(struct pci_controller *hose)
+{
 	unsigned long phys_page;
 	unsigned long size_page;
 	unsigned long io_virt_offset;
@@ -146,12 +169,11 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
 	 * with incomplete address decoding but I'd rather not deal with
 	 * those outside of the reserved 64K legacy region.
 	 */
-	area = __get_vm_area(size_page, 0, PHB_IO_BASE, PHB_IO_END);
-	if (area == NULL)
+	hose->io_base_alloc = ioremap_phb(phys_page, size_page);
+	if (!hose->io_base_alloc)
 		return -ENOMEM;
-	hose->io_base_alloc = area->addr;
-	hose->io_base_virt = (void __iomem *)(area->addr +
-					      hose->io_base_phys - phys_page);
+	hose->io_base_virt = hose->io_base_alloc +
+				hose->io_base_phys - phys_page;
 
 	pr_debug("IO mapping for PHB %pOF\n", hose->dn);
 	pr_debug("  phys=0x%016llx, virt=0x%p (alloc=0x%p)\n",
@@ -159,11 +181,6 @@ static int pcibios_map_phb_io_space(struct pci_controller *hose)
 	pr_debug("  size=0x%016llx (alloc=0x%016lx)\n",
 		 hose->pci_io_size, size_page);
 
-	/* Establish the mapping */
-	if (__ioremap_at(phys_page, area->addr, size_page,
-			 pgprot_noncached(PAGE_KERNEL)) == NULL)
-		return -ENOMEM;
-
 	/* Fixup hose IO resource */
 	io_virt_offset = pcibios_io_space_offset(hose);
 	hose->io_resource.start += io_virt_offset;
diff --git a/drivers/pcmcia/electra_cf.c b/drivers/pcmcia/electra_cf.c
index f2741c04289d..35158cfd9c1a 100644
--- a/drivers/pcmcia/electra_cf.c
+++ b/drivers/pcmcia/electra_cf.c
@@ -178,10 +178,9 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	struct device_node *np = ofdev->dev.of_node;
 	struct electra_cf_socket   *cf;
 	struct resource mem, io;
-	int status;
+	int status = -ENOMEM;
 	const unsigned int *prop;
 	int err;
-	struct vm_struct *area;
 
 	err = of_address_to_resource(np, 0, &mem);
 	if (err)
@@ -202,30 +201,19 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	cf->mem_phys = mem.start;
 	cf->mem_size = PAGE_ALIGN(resource_size(&mem));
 	cf->mem_base = ioremap(cf->mem_phys, cf->mem_size);
+	if (!cf->mem_base)
+		goto out_free_cf;
 	cf->io_size = PAGE_ALIGN(resource_size(&io));
-
-	area = __get_vm_area(cf->io_size, 0, PHB_IO_BASE, PHB_IO_END);
-	if (area == NULL) {
-		status = -ENOMEM;
-		goto fail1;
-	}
-
-	cf->io_virt = (void __iomem *)(area->addr);
+	cf->io_virt = ioremap_phb(io.start, cf->io_size);
+	if (!cf->io_virt)
+		goto out_unmap_mem;
 
 	cf->gpio_base = ioremap(0xfc103000, 0x1000);
+	if (!cf->gpio_base)
+		goto out_unmap_virt;
 	dev_set_drvdata(device, cf);
 
-	if (!cf->mem_base || !cf->io_virt || !cf->gpio_base ||
-	    (__ioremap_at(io.start, cf->io_virt, cf->io_size,
-			  pgprot_noncached(PAGE_KERNEL)) == NULL)) {
-		dev_err(device, "can't ioremap ranges\n");
-		status = -ENOMEM;
-		goto fail1;
-	}
-
-
 	cf->io_base = (unsigned long)cf->io_virt - VMALLOC_END;
-
 	cf->iomem.start = (unsigned long)cf->mem_base;
 	cf->iomem.end = (unsigned long)cf->mem_base + (mem.end - mem.start);
 	cf->iomem.flags = IORESOURCE_MEM;
@@ -305,14 +293,13 @@ static int electra_cf_probe(struct platform_device *ofdev)
 	if (cf->irq)
 		free_irq(cf->irq, cf);
 
-	if (cf->io_virt)
-		__iounmap_at(cf->io_virt, cf->io_size);
-	if (cf->mem_base)
-		iounmap(cf->mem_base);
-	if (cf->gpio_base)
-		iounmap(cf->gpio_base);
-	if (area)
-		device_init_wakeup(&ofdev->dev, 0);
+	iounmap(cf->gpio_base);
+out_unmap_virt:
+	device_init_wakeup(&ofdev->dev, 0);
+	iounmap(cf->io_virt);
+out_unmap_mem:
+	iounmap(cf->mem_base);
+out_free_cf:
 	kfree(cf);
 	return status;
 
@@ -330,7 +317,7 @@ static int electra_cf_remove(struct platform_device *ofdev)
 	free_irq(cf->irq, cf);
 	del_timer_sync(&cf->timer);
 
-	__iounmap_at(cf->io_virt, cf->io_size);
+	iounmap(cf->io_virt);
 	iounmap(cf->mem_base);
 	iounmap(cf->gpio_base);
 	release_mem_region(cf->mem_phys, cf->mem_size);
-- 
2.25.1


^ permalink raw reply related

* [PATCH 05/29] dma-mapping: use vmap insted of reimplementing it
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Replace the open coded instance of vmap with the actual function.  In
the non-contiguous (IOMMU) case this requires an extra find_vm_area,
but given that this isn't a fast path function that is a small price
to pay.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/dma/remap.c | 48 ++++++++++++----------------------------------
 1 file changed, 12 insertions(+), 36 deletions(-)

diff --git a/kernel/dma/remap.c b/kernel/dma/remap.c
index d14cbc83986a..914ff5a58dd5 100644
--- a/kernel/dma/remap.c
+++ b/kernel/dma/remap.c
@@ -20,23 +20,6 @@ struct page **dma_common_find_pages(void *cpu_addr)
 	return area->pages;
 }
 
-static struct vm_struct *__dma_common_pages_remap(struct page **pages,
-			size_t size, pgprot_t prot, const void *caller)
-{
-	struct vm_struct *area;
-
-	area = get_vm_area_caller(size, VM_DMA_COHERENT, caller);
-	if (!area)
-		return NULL;
-
-	if (map_vm_area(area, prot, pages)) {
-		vunmap(area->addr);
-		return NULL;
-	}
-
-	return area;
-}
-
 /*
  * Remaps an array of PAGE_SIZE pages into another vm_area.
  * Cannot be used in non-sleeping contexts
@@ -44,15 +27,12 @@ static struct vm_struct *__dma_common_pages_remap(struct page **pages,
 void *dma_common_pages_remap(struct page **pages, size_t size,
 			 pgprot_t prot, const void *caller)
 {
-	struct vm_struct *area;
+	void *vaddr;
 
-	area = __dma_common_pages_remap(pages, size, prot, caller);
-	if (!area)
-		return NULL;
-
-	area->pages = pages;
-
-	return area->addr;
+	vaddr = vmap(pages, size >> PAGE_SHIFT, VM_DMA_COHERENT, prot);
+	if (vaddr)
+		find_vm_area(vaddr)->pages = pages;
+	return vaddr;
 }
 
 /*
@@ -62,24 +42,20 @@ void *dma_common_pages_remap(struct page **pages, size_t size,
 void *dma_common_contiguous_remap(struct page *page, size_t size,
 			pgprot_t prot, const void *caller)
 {
-	int i;
+	int count = size >> PAGE_SHIFT;
 	struct page **pages;
-	struct vm_struct *area;
+	void *vaddr;
+	int i;
 
-	pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+	pages = kmalloc_array(count, sizeof(struct page *), GFP_KERNEL);
 	if (!pages)
 		return NULL;
-
-	for (i = 0; i < (size >> PAGE_SHIFT); i++)
+	for (i = 0; i < count; i++)
 		pages[i] = nth_page(page, i);
-
-	area = __dma_common_pages_remap(pages, size, prot, caller);
-
+	vaddr = vmap(pages, count, VM_DMA_COHERENT, prot);
 	kfree(pages);
 
-	if (!area)
-		return NULL;
-	return area->addr;
+	return vaddr;
 }
 
 /*
-- 
2.25.1


^ permalink raw reply related

* [PATCH 04/29] staging: media: ipu3: use vmap instead of reimplementing it
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Just use vmap instead of messing with vmalloc internals.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 drivers/staging/media/ipu3/ipu3-css-pool.h |  4 +--
 drivers/staging/media/ipu3/ipu3-dmamap.c   | 30 ++++++----------------
 2 files changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/staging/media/ipu3/ipu3-css-pool.h b/drivers/staging/media/ipu3/ipu3-css-pool.h
index f4a60b41401b..a8ccd4f70320 100644
--- a/drivers/staging/media/ipu3/ipu3-css-pool.h
+++ b/drivers/staging/media/ipu3/ipu3-css-pool.h
@@ -15,14 +15,12 @@ struct imgu_device;
  * @size:		size of the buffer in bytes.
  * @vaddr:		kernel virtual address.
  * @daddr:		iova dma address to access IPU3.
- * @vma:		private, a pointer to &struct vm_struct,
- *			used for imgu_dmamap_free.
  */
 struct imgu_css_map {
 	size_t size;
 	void *vaddr;
 	dma_addr_t daddr;
-	struct vm_struct *vma;
+	struct page **pages;
 };
 
 /**
diff --git a/drivers/staging/media/ipu3/ipu3-dmamap.c b/drivers/staging/media/ipu3/ipu3-dmamap.c
index 7431322379f6..8a19b0024152 100644
--- a/drivers/staging/media/ipu3/ipu3-dmamap.c
+++ b/drivers/staging/media/ipu3/ipu3-dmamap.c
@@ -96,6 +96,7 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map,
 	unsigned long shift = iova_shift(&imgu->iova_domain);
 	struct device *dev = &imgu->pci_dev->dev;
 	size_t size = PAGE_ALIGN(len);
+	int count = size >> PAGE_SHIFT;
 	struct page **pages;
 	dma_addr_t iovaddr;
 	struct iova *iova;
@@ -114,7 +115,7 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map,
 
 	/* Call IOMMU driver to setup pgt */
 	iovaddr = iova_dma_addr(&imgu->iova_domain, iova);
-	for (i = 0; i < size / PAGE_SIZE; ++i) {
+	for (i = 0; i < count; ++i) {
 		rval = imgu_mmu_map(imgu->mmu, iovaddr,
 				    page_to_phys(pages[i]), PAGE_SIZE);
 		if (rval)
@@ -123,33 +124,23 @@ void *imgu_dmamap_alloc(struct imgu_device *imgu, struct imgu_css_map *map,
 		iovaddr += PAGE_SIZE;
 	}
 
-	/* Now grab a virtual region */
-	map->vma = __get_vm_area(size, VM_USERMAP, VMALLOC_START, VMALLOC_END);
-	if (!map->vma)
+	map->vaddr = vmap(pages, count, VM_USERMAP, PAGE_KERNEL);
+	if (!map->vaddr)
 		goto out_unmap;
 
-	map->vma->pages = pages;
-	/* And map it in KVA */
-	if (map_vm_area(map->vma, PAGE_KERNEL, pages))
-		goto out_vunmap;
-
+	map->pages = pages;
 	map->size = size;
 	map->daddr = iova_dma_addr(&imgu->iova_domain, iova);
-	map->vaddr = map->vma->addr;
 
 	dev_dbg(dev, "%s: allocated %zu @ IOVA %pad @ VA %p\n", __func__,
-		size, &map->daddr, map->vma->addr);
-
-	return map->vma->addr;
+		size, &map->daddr, map->vaddr);
 
-out_vunmap:
-	vunmap(map->vma->addr);
+	return map->vaddr;
 
 out_unmap:
 	imgu_dmamap_free_buffer(pages, size);
 	imgu_mmu_unmap(imgu->mmu, iova_dma_addr(&imgu->iova_domain, iova),
 		       i * PAGE_SIZE);
-	map->vma = NULL;
 
 out_free_iova:
 	__free_iova(&imgu->iova_domain, iova);
@@ -177,8 +168,6 @@ void imgu_dmamap_unmap(struct imgu_device *imgu, struct imgu_css_map *map)
  */
 void imgu_dmamap_free(struct imgu_device *imgu, struct imgu_css_map *map)
 {
-	struct vm_struct *area = map->vma;
-
 	dev_dbg(&imgu->pci_dev->dev, "%s: freeing %zu @ IOVA %pad @ VA %p\n",
 		__func__, map->size, &map->daddr, map->vaddr);
 
@@ -187,11 +176,8 @@ void imgu_dmamap_free(struct imgu_device *imgu, struct imgu_css_map *map)
 
 	imgu_dmamap_unmap(imgu, map);
 
-	if (WARN_ON(!area) || WARN_ON(!area->pages))
-		return;
-
-	imgu_dmamap_free_buffer(area->pages, map->size);
 	vunmap(map->vaddr);
+	imgu_dmamap_free_buffer(map->pages, map->size);
 	map->vaddr = NULL;
 }
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH 03/29] staging: android: ion: use vmap instead of vm_map_ram
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, Greg Kroah-Hartman, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

vm_map_ram can keep mappings around after the vm_unmap_ram.  Using that
with non-PAGE_KERNEL mappings can lead to all kinds of aliasing issues.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 drivers/staging/android/ion/ion_heap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/android/ion/ion_heap.c b/drivers/staging/android/ion/ion_heap.c
index 473b465724f1..0755b11348ed 100644
--- a/drivers/staging/android/ion/ion_heap.c
+++ b/drivers/staging/android/ion/ion_heap.c
@@ -99,12 +99,12 @@ int ion_heap_map_user(struct ion_heap *heap, struct ion_buffer *buffer,
 
 static int ion_heap_clear_pages(struct page **pages, int num, pgprot_t pgprot)
 {
-	void *addr = vm_map_ram(pages, num, -1, pgprot);
+	void *addr = vmap(pages, num, VM_MAP, pgprot);
 
 	if (!addr)
 		return -ENOMEM;
 	memset(addr, 0, PAGE_SIZE * num);
-	vm_unmap_ram(addr, num);
+	vunmap(addr);
 
 	return 0;
 }
-- 
2.25.1


^ permalink raw reply related

* [PATCH 02/29] x86: fix vmap arguments in map_irq_stack
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

vmap does not take a gfp_t, the flags argument is for VM_* flags.

Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/x86/kernel/irq_64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 12df3a4abfdd..6b32ab009c19 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -43,7 +43,7 @@ static int map_irq_stack(unsigned int cpu)
 		pages[i] = pfn_to_page(pa >> PAGE_SHIFT);
 	}
 
-	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
+	va = vmap(pages, IRQ_STACK_SIZE / PAGE_SIZE, VM_MAP, PAGE_KERNEL);
 	if (!va)
 		return -ENOMEM;
 
-- 
2.25.1


^ permalink raw reply related

* [PATCH 01/29] x86/hyperv: use vmalloc_exec for the hypercall page
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, Michael Kelley,
	linaro-mm-sig, linux-mm, iommu, bpf, Robin Murphy,
	linux-arm-kernel
In-Reply-To: <20200414131348.444715-1-hch@lst.de>

Use the designated helper for allocating executable kernel memory, and
remove the now unused PAGE_KERNEL_RX define.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Acked-by: Wei Liu <wei.liu@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 arch/x86/hyperv/hv_init.c            | 2 +-
 arch/x86/include/asm/pgtable_types.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index b0da5320bcff..5a4b363ba67b 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -355,7 +355,7 @@ void __init hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
-	hv_hypercall_pg  = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_RX);
+	hv_hypercall_pg = vmalloc_exec(PAGE_SIZE);
 	if (hv_hypercall_pg == NULL) {
 		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 		goto remove_cpuhp_state;
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b6606fe6cfdf..947867f112ea 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -194,7 +194,6 @@ enum page_cache_mode {
 #define _PAGE_TABLE_NOENC	 (__PP|__RW|_USR|___A|   0|___D|   0|   0)
 #define _PAGE_TABLE		 (__PP|__RW|_USR|___A|   0|___D|   0|   0| _ENC)
 #define __PAGE_KERNEL_RO	 (__PP|   0|   0|___A|__NX|___D|   0|___G)
-#define __PAGE_KERNEL_RX	 (__PP|   0|   0|___A|   0|___D|   0|___G)
 #define __PAGE_KERNEL_NOCACHE	 (__PP|__RW|   0|___A|__NX|___D|   0|___G| __NC)
 #define __PAGE_KERNEL_VVAR	 (__PP|   0|_USR|___A|__NX|___D|   0|___G)
 #define __PAGE_KERNEL_LARGE	 (__PP|__RW|   0|___A|__NX|___D|_PSE|___G)
@@ -220,7 +219,6 @@ enum page_cache_mode {
 #define PAGE_KERNEL_RO		__pgprot_mask(__PAGE_KERNEL_RO         | _ENC)
 #define PAGE_KERNEL_EXEC	__pgprot_mask(__PAGE_KERNEL_EXEC       | _ENC)
 #define PAGE_KERNEL_EXEC_NOENC	__pgprot_mask(__PAGE_KERNEL_EXEC       |    0)
-#define PAGE_KERNEL_RX		__pgprot_mask(__PAGE_KERNEL_RX         | _ENC)
 #define PAGE_KERNEL_NOCACHE	__pgprot_mask(__PAGE_KERNEL_NOCACHE    | _ENC)
 #define PAGE_KERNEL_LARGE	__pgprot_mask(__PAGE_KERNEL_LARGE      | _ENC)
 #define PAGE_KERNEL_LARGE_EXEC	__pgprot_mask(__PAGE_KERNEL_LARGE_EXEC | _ENC)
-- 
2.25.1


^ permalink raw reply related

* decruft the vmalloc API v2
From: Christoph Hellwig @ 2020-04-14 13:13 UTC (permalink / raw)
  To: Andrew Morton, K. Y. Srinivasan, Haiyang Zhang, Stephen Hemminger,
	Wei Liu, x86, David Airlie, Daniel Vetter, Laura Abbott,
	Sumit Semwal, Sakari Ailus, Minchan Kim, Nitin Gupta
  Cc: linux-arch, linux-hyperv, linux-s390, Peter Zijlstra,
	linuxppc-dev, linux-kernel, dri-devel, linaro-mm-sig, linux-mm,
	iommu, bpf, Robin Murphy, linux-arm-kernel

Hi all,

Peter noticed that with some dumb luck you can toast the kernel address
space with exported vmalloc symbols.

I used this as an opportunity to decruft the vmalloc.c API and make it
much more systematic.  This also removes any chance to create vmalloc
mappings outside the designated areas or using executable permissions
from modules.  Besides that it removes more than 300 lines of code.

A git tree is also available here:

    git://git.infradead.org/users/hch/misc.git sanitize-vmalloc-api.2

Gitweb:

    http://git.infradead.org/users/hch/misc.git/shortlog/refs/heads/sanitize-vmalloc-api.2

Changes since v1:
 - implement pgprot_nx for arm64 (Mark Rutland)
 - fix a patch description
 - properly pass pgprot to vmap in ion
 - add a new patch to fix vmap() API misuse
 - fix a vmap argument in x86
 - two more vmalloc cleanups
 - cleanup use of the unmap_kernel_range API
 - rename ioremap_pbh to ioremap_phb

^ permalink raw reply

* Re: [PATCH 1/2] mm, treewide: Rename kzfree() to kfree_sensitive()
From: David Howells @ 2020-04-14 13:06 UTC (permalink / raw)
  To: Waiman Long, herbert
  Cc: linux-btrfs, Jarkko Sakkinen, virtualization, David Howells,
	linux-mm, linux-sctp, keyrings, kasan-dev, samba-technical,
	linux-stm32, devel, linux-s390, linux-scsi, x86, James Morris,
	Matthew Wilcox, cocci, linux-wpan, intel-wired-lan,
	David Rientjes, Serge E. Hallyn, linux-pm, ecryptfs, linux-nfs,
	linux-fscrypt, linux-mediatek, linux-amlogic, linux-integrity,
	linux-arm-kernel, linux-cifs, Linus Torvalds, linux-wireless,
	linux-kernel, linux-bluetooth, linux-security-module,
	target-devel, tipc-discussion, linux-crypto, netdev, Joe Perches,
	Andrew Morton, linuxppc-dev, wireguard, linux-ppp
In-Reply-To: <20200413211550.8307-2-longman@redhat.com>

Waiman Long <longman@redhat.com> wrote:

> As said by Linus:
> 
>   A symmetric naming is only helpful if it implies symmetries in use.
>   Otherwise it's actively misleading.
> 
>   In "kzalloc()", the z is meaningful and an important part of what the
>   caller wants.
> 
>   In "kzfree()", the z is actively detrimental, because maybe in the
>   future we really _might_ want to use that "memfill(0xdeadbeef)" or
>   something. The "zero" part of the interface isn't even _relevant_.
> 
> The main reason that kzfree() exists is to clear sensitive information
> that should not be leaked to other future users of the same memory
> objects.
> 
> Rename kzfree() to kfree_sensitive() to follow the example of the
> recently added kvfree_sensitive() and make the intention of the API
> more explicit. In addition, memzero_explicit() is used to clear the
> memory to make sure that it won't get optimized away by the compiler.
> 
> The renaming is done by using the command sequence:
> 
>   git grep -w --name-only kzfree |\
>   xargs sed -i 's/\bkzfree\b/kfree_sensitive/'
> 
> followed by some editing of the kfree_sensitive() kerneldoc and the
> use of memzero_explicit() instead of memset().
> 
> Suggested-by: Joe Perches <joe@perches.com>
> Signed-off-by: Waiman Long <longman@redhat.com>

Since this changes a lot of crypto stuff, does it make sense for it to go via
the crypto tree?

Acked-by: David Howells <dhowells@redhat.com>


^ permalink raw reply

* Re: [PATCH v2 4/4] mm/vmalloc: Hugepage vmalloc mappings
From: Christoph Hellwig @ 2020-04-14 13:02 UTC (permalink / raw)
  To: Nicholas Piggin
  Cc: linux-arch, Will Deacon, Catalin Marinas, x86, linux-kernel,
	Christoph Hellwig, linux-mm, Ingo Molnar, Borislav Petkov,
	H. Peter Anvin, Thomas Gleixner, linuxppc-dev, linux-arm-kernel
In-Reply-To: <1586864403.0qfilei2ft.astroid@bobo.none>

On Tue, Apr 14, 2020 at 10:13:44PM +1000, Nicholas Piggin wrote:
> Which case? Usually the answer would be because you don't want to use
> contiguous physical memory and/or you don't want to use the linear 
> mapping.

But with huge pages you do by definition already use large contiguous
areas.  So you want allocations larger than "small" huge pages but not
using gigantic pages using vmalloc?

^ permalink raw reply

* [PATCH 8/8] tracefs: switch to simplefs inode creation API
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:43 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

There is no semantic change intended; the code in the simplefs.c functions in
fact was derived from debugfs and tracefs code.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 fs/tracefs/inode.c | 86 ++++------------------------------------------
 1 file changed, 7 insertions(+), 79 deletions(-)

diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index a30837a8e1d4..69e2215c797b 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -298,57 +298,6 @@ static struct file_system_type trace_fs_type = {
 };
 MODULE_ALIAS_FS("tracefs");
 
-static struct dentry *start_creating(const char *name, struct dentry *parent)
-{
-	struct dentry *dentry;
-	int error;
-
-	pr_debug("tracefs: creating file '%s'\n",name);
-
-	error = simple_pin_fs(&tracefs, &trace_fs_type);
-	if (error)
-		return ERR_PTR(error);
-
-	/* If the parent is not specified, we create it in the root.
-	 * We need the root dentry to do this, which is in the super
-	 * block. A pointer to that is in the struct vfsmount that we
-	 * have around.
-	 */
-	if (!parent)
-		parent = tracefs.mount->mnt_root;
-
-	inode_lock(parent->d_inode);
-	if (unlikely(IS_DEADDIR(parent->d_inode)))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry) && dentry->d_inode) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry)) {
-		inode_unlock(parent->d_inode);
-		simple_release_fs(&tracefs);
-	}
-
-	return dentry;
-}
-
-static struct dentry *failed_creating(struct dentry *dentry)
-{
-	inode_unlock(dentry->d_parent->d_inode);
-	dput(dentry);
-	simple_release_fs(&tracefs);
-	return NULL;
-}
-
-static struct dentry *end_creating(struct dentry *dentry)
-{
-	inode_unlock(dentry->d_parent->d_inode);
-	return dentry;
-}
-
 /**
  * tracefs_create_file - create a file in the tracefs filesystem
  * @name: a pointer to a string containing the name of the file to create.
@@ -385,49 +334,28 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (security_locked_down(LOCKDOWN_TRACEFS))
 		return NULL;
 
-	if (!(mode & S_IFMT))
-		mode |= S_IFREG;
-	BUG_ON(!S_ISREG(mode));
-	dentry = start_creating(name, parent);
-
+	dentry = simplefs_create_file(&tracefs, &trace_fs_type,
+				      name, mode, parent, data, &inode);
 	if (IS_ERR(dentry))
 		return NULL;
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
-
-	inode->i_mode = mode;
 	inode->i_fop = fops ? fops : &tracefs_file_operations;
-	inode->i_private = data;
-	d_instantiate(dentry, inode);
-	fsnotify_create(dentry->d_parent->d_inode, dentry);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 
 static struct dentry *__create_dir(const char *name, struct dentry *parent,
 				   const struct inode_operations *ops)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry;
 	struct inode *inode;
 
+	dentry = simplefs_create_dir(&tracefs, &trace_fs_type,
+				     name, 0755, parent, &inode);
 	if (IS_ERR(dentry))
 		return NULL;
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode))
-		return failed_creating(dentry);
-
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
 	inode->i_op = ops;
-	inode->i_fop = &simple_dir_operations;
-
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(dentry->d_parent->d_inode);
-	fsnotify_mkdir(dentry->d_parent->d_inode, dentry);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 
 /**
-- 
2.25.2


^ permalink raw reply related

* [PATCH 7/8] debugfs: switch to simplefs inode creation API
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:43 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

The only difference, compared to the pre-existing code, is that symlink
creation now triggers fsnotify_create.  This was a bug in the debugfs
code, since for example vfs_symlink does call fsnotify_create.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 fs/debugfs/inode.c | 144 +++++----------------------------------------
 1 file changed, 15 insertions(+), 129 deletions(-)

diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 834b5872ca0d..7a2369373b85 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -294,68 +294,6 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
 }
 EXPORT_SYMBOL_GPL(debugfs_lookup);
 
-static struct dentry *start_creating(const char *name, struct dentry *parent)
-{
-	struct dentry *dentry;
-	int error;
-
-	pr_debug("creating file '%s'\n", name);
-
-	if (IS_ERR(parent))
-		return parent;
-
-	error = simple_pin_fs(&debugfs, &debug_fs_type);
-	if (error) {
-		pr_err("Unable to pin filesystem for file '%s'\n", name);
-		return ERR_PTR(error);
-	}
-
-	/* If the parent is not specified, we create it in the root.
-	 * We need the root dentry to do this, which is in the super
-	 * block. A pointer to that is in the struct vfsmount that we
-	 * have around.
-	 */
-	if (!parent)
-		parent = debugfs.mount->mnt_root;
-
-	inode_lock(d_inode(parent));
-	if (unlikely(IS_DEADDIR(d_inode(parent))))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_one_len(name, parent, strlen(name));
-	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
-		if (d_is_dir(dentry))
-			pr_err("Directory '%s' with parent '%s' already present!\n",
-			       name, parent->d_name.name);
-		else
-			pr_err("File '%s' in directory '%s' already present!\n",
-			       name, parent->d_name.name);
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry)) {
-		inode_unlock(d_inode(parent));
-		simple_release_fs(&debugfs);
-	}
-
-	return dentry;
-}
-
-static struct dentry *failed_creating(struct dentry *dentry)
-{
-	inode_unlock(d_inode(dentry->d_parent));
-	dput(dentry);
-	simple_release_fs(&debugfs);
-	return ERR_PTR(-ENOMEM);
-}
-
-static struct dentry *end_creating(struct dentry *dentry)
-{
-	inode_unlock(d_inode(dentry->d_parent));
-	return dentry;
-}
-
 static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 				struct dentry *parent, void *data,
 				const struct file_operations *proxy_fops,
@@ -364,32 +302,17 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	struct dentry *dentry;
 	struct inode *inode;
 
-	if (!(mode & S_IFMT))
-		mode |= S_IFREG;
-	BUG_ON(!S_ISREG(mode));
-	dentry = start_creating(name, parent);
-
+	dentry = simplefs_create_file(&debugfs, &debug_fs_type,
+				      name, mode, parent, data, &inode);
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		pr_err("out of free dentries, can not create file '%s'\n",
-		       name);
-		return failed_creating(dentry);
-	}
-
-	inode->i_mode = mode;
-	inode->i_private = data;
-
 	inode->i_op = &debugfs_file_inode_operations;
 	inode->i_fop = proxy_fops;
 	dentry->d_fsdata = (void *)((unsigned long)real_fops |
 				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
 
-	d_instantiate(dentry, inode);
-	fsnotify_create(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 
 /**
@@ -522,29 +445,16 @@ EXPORT_SYMBOL_GPL(debugfs_create_file_size);
  */
 struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry;
 	struct inode *inode;
 
+	dentry = simplefs_create_dir(&debugfs, &debug_fs_type,
+				     name, 0755, parent, &inode);
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		pr_err("out of free dentries, can not create directory '%s'\n",
-		       name);
-		return failed_creating(dentry);
-	}
-
-	inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO;
 	inode->i_op = &debugfs_dir_inode_operations;
-	inode->i_fop = &simple_dir_operations;
-
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(d_inode(dentry->d_parent));
-	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_dir);
 
@@ -564,29 +474,19 @@ struct dentry *debugfs_create_automount(const char *name,
 					debugfs_automount_t f,
 					void *data)
 {
-	struct dentry *dentry = start_creating(name, parent);
+	struct dentry *dentry;
 	struct inode *inode;
 
+	dentry = simplefs_create_dentry(&debugfs, &debug_fs_type, name, parent,
+					&inode);
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		pr_err("out of free dentries, can not create automount '%s'\n",
-		       name);
-		return failed_creating(dentry);
-	}
-
 	make_empty_dir_inode(inode);
 	inode->i_flags |= S_AUTOMOUNT;
 	inode->i_private = data;
 	dentry->d_fsdata = (void *)f;
-	/* directory inodes start off with i_nlink == 2 (for "." entry) */
-	inc_nlink(inode);
-	d_instantiate(dentry, inode);
-	inc_nlink(d_inode(dentry->d_parent));
-	fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 EXPORT_SYMBOL(debugfs_create_automount);
 
@@ -618,28 +518,14 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 {
 	struct dentry *dentry;
 	struct inode *inode;
-	char *link = kstrdup(target, GFP_KERNEL);
-	if (!link)
-		return ERR_PTR(-ENOMEM);
 
-	dentry = start_creating(name, parent);
-	if (IS_ERR(dentry)) {
-		kfree(link);
+	dentry = simplefs_create_symlink(&debugfs, &debug_fs_type,
+					 name, parent, target, &inode);
+	if (IS_ERR(dentry))
 		return dentry;
-	}
 
-	inode = simple_new_inode(dentry->d_sb);
-	if (unlikely(!inode)) {
-		pr_err("out of free dentries, can not create symlink '%s'\n",
-		       name);
-		kfree(link);
-		return failed_creating(dentry);
-	}
-	inode->i_mode = S_IFLNK | S_IRWXUGO;
 	inode->i_op = &debugfs_symlink_inode_operations;
-	inode->i_link = link;
-	d_instantiate(dentry, inode);
-	return end_creating(dentry);
+	return simplefs_finish_dentry(dentry, inode);
 }
 EXPORT_SYMBOL_GPL(debugfs_create_symlink);
 
-- 
2.25.2


^ permalink raw reply related

* [PATCH 6/8] simplefs: add file creation functions
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:43 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

A bunch of code is duplicated between debugfs and tracefs, unify it to the
simplefs library.

The code is very similar, except that dentry and inode creation are unified
into a single function (unlike start_creating in debugfs and tracefs, which
only takes care of dentries).  This adds an output parameter to the creation
functions, but pushes all error recovery into fs/simplefs.c.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 fs/simplefs.c            | 150 +++++++++++++++++++++++++++++++++++++++
 include/linux/simplefs.h |  19 +++++
 2 files changed, 169 insertions(+)

diff --git a/fs/simplefs.c b/fs/simplefs.c
index c59eb8d996be..3e48a288beb3 100644
--- a/fs/simplefs.c
+++ b/fs/simplefs.c
@@ -1,6 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/simplefs.h>
 #include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/fsnotify.h>
 
 static DEFINE_SPINLOCK(pin_fs_lock);
 
@@ -42,3 +44,151 @@ struct inode *simple_alloc_anon_inode(struct simple_fs *fs)
 	return alloc_anon_inode(fs->mount->mnt_sb);
 }
 EXPORT_SYMBOL(simple_alloc_anon_inode);
+
+static struct dentry *failed_creating(struct simple_fs *fs, struct dentry *dentry)
+{
+	inode_unlock(d_inode(dentry->d_parent));
+	dput(dentry);
+	simple_release_fs(fs);
+	return ERR_PTR(-ENOMEM);
+}
+
+struct dentry *simplefs_create_dentry(struct simple_fs *fs, struct file_system_type *type,
+				      const char *name, struct dentry *parent,
+				      struct inode **inode)
+{
+	struct dentry *dentry;
+	int error;
+
+	pr_debug("creating file '%s'\n", name);
+
+	if (IS_ERR(parent))
+		return parent;
+
+	error = simple_pin_fs(fs, type);
+	if (error) {
+		pr_err("Unable to pin filesystem for file '%s'\n", name);
+		return ERR_PTR(error);
+	}
+
+	/* If the parent is not specified, we create it in the root.
+	 * We need the root dentry to do this, which is in the super
+	 * block. A pointer to that is in the struct vfsmount that we
+	 * have around.
+	 */
+	if (!parent)
+		parent = fs->mount->mnt_root;
+
+	inode_lock(d_inode(parent));
+	dentry = lookup_one_len(name, parent, strlen(name));
+	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
+		if (d_is_dir(dentry))
+			pr_err("Directory '%s' with parent '%s' already present!\n",
+			       name, parent->d_name.name);
+		else
+			pr_err("File '%s' in directory '%s' already present!\n",
+			       name, parent->d_name.name);
+		dput(dentry);
+		dentry = ERR_PTR(-EEXIST);
+	}
+
+	if (IS_ERR(dentry)) {
+		inode_unlock(d_inode(parent));
+		simple_release_fs(fs);
+	}
+
+
+	if (IS_ERR(dentry))
+		return dentry;
+
+	*inode = simple_new_inode(fs->mount->mnt_sb);
+	if (unlikely(!(*inode))) {
+		pr_err("out of free inodes, can not create file '%s'\n",
+		       name);
+		return failed_creating(fs, dentry);
+	}
+
+	return dentry;
+}
+EXPORT_SYMBOL(simplefs_create_dentry);
+
+struct dentry *simplefs_create_file(struct simple_fs *fs, struct file_system_type *type,
+				    const char *name, umode_t mode,
+				    struct dentry *parent, void *data,
+				    struct inode **inode)
+{
+	struct dentry *dentry;
+
+	WARN_ON((mode & S_IFMT) && !S_ISREG(mode));
+	mode |= S_IFREG;
+
+	dentry = simplefs_create_dentry(fs, type, name, parent, inode);
+
+	if (IS_ERR(dentry))
+		return dentry;
+
+	(*inode)->i_mode = mode;
+	(*inode)->i_private = data;
+
+	return dentry;
+}
+EXPORT_SYMBOL(simplefs_create_file);
+
+struct dentry *simplefs_finish_dentry(struct dentry *dentry, struct inode *inode)
+{
+	d_instantiate(dentry, inode);
+	if (S_ISDIR(inode->i_mode)) {
+		inc_nlink(d_inode(dentry->d_parent));
+		fsnotify_mkdir(d_inode(dentry->d_parent), dentry);
+	} else {
+		fsnotify_create(d_inode(dentry->d_parent), dentry);
+	}
+	inode_unlock(d_inode(dentry->d_parent));
+	return dentry;
+}
+EXPORT_SYMBOL(simplefs_finish_dentry);
+
+struct dentry *simplefs_create_dir(struct simple_fs *fs, struct file_system_type *type,
+				   const char *name, umode_t mode, struct dentry *parent,
+				   struct inode **inode)
+{
+	struct dentry *dentry;
+
+	WARN_ON((mode & S_IFMT) && !S_ISDIR(mode));
+	mode |= S_IFDIR;
+
+	dentry = simplefs_create_dentry(fs, type, name, parent, inode);
+	if (IS_ERR(dentry))
+		return dentry;
+
+	(*inode)->i_mode = mode;
+	(*inode)->i_op = &simple_dir_inode_operations;
+	(*inode)->i_fop = &simple_dir_operations;
+
+	/* directory inodes start off with i_nlink == 2 (for "." entry) */
+	inc_nlink(*inode);
+	return dentry;
+}
+EXPORT_SYMBOL(simplefs_create_dir);
+
+struct dentry *simplefs_create_symlink(struct simple_fs *fs, struct file_system_type *type,
+				       const char *name, struct dentry *parent,
+				       const char *target, struct inode **inode)
+{
+	struct dentry *dentry;
+	char *link = kstrdup(target, GFP_KERNEL);
+	if (!link)
+		return ERR_PTR(-ENOMEM);
+
+	dentry = simplefs_create_dentry(fs, type, name, parent, inode);
+	if (IS_ERR(dentry)) {
+		kfree_link(link);
+		return dentry;
+	}
+
+	(*inode)->i_mode = S_IFLNK | S_IRWXUGO;
+	(*inode)->i_link = link;
+	(*inode)->i_op = &simple_symlink_inode_operations;
+	return dentry;
+}
+EXPORT_SYMBOL(simplefs_create_symlink);
diff --git a/include/linux/simplefs.h b/include/linux/simplefs.h
index c62ab526414e..cc53eed0bc3d 100644
--- a/include/linux/simplefs.h
+++ b/include/linux/simplefs.h
@@ -14,4 +14,23 @@ extern void simple_release_fs(struct simple_fs *);
 
 extern struct inode *simple_alloc_anon_inode(struct simple_fs *fs);
 
+extern struct dentry *simplefs_create_dentry(struct simple_fs *fs,
+					     struct file_system_type *type,
+					     const char *name, struct dentry *parent,
+					     struct inode **inode);
+struct dentry *simplefs_finish_dentry(struct dentry *dentry, struct inode *inode);
+
+extern struct dentry *simplefs_create_file(struct simple_fs *fs,
+					   struct file_system_type *type,
+					   const char *name, umode_t mode,
+					   struct dentry *parent, void *data,
+					   struct inode **inode);
+extern struct dentry *simplefs_create_dir(struct simple_fs *fs, struct file_system_type *type,
+					  const char *name, umode_t mode, struct dentry *parent,
+					  struct inode **inode);
+extern struct dentry *simplefs_create_symlink(struct simple_fs *fs, struct file_system_type *type,
+					      const char *name, struct dentry *parent,
+					      const char *target, struct inode **inode);
+
+
 #endif
-- 
2.25.2


^ permalink raw reply related

* [PATCH 5/8] simplefs: add alloc_anon_inode wrapper
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

Start adding file creation wrappers, the simplest returns an anonymous
inode.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 drivers/gpu/drm/drm_drv.c       | 2 +-
 drivers/misc/cxl/api.c          | 2 +-
 drivers/scsi/cxlflash/ocxl_hw.c | 2 +-
 fs/simplefs.c                   | 6 ++++++
 include/linux/simplefs.h        | 2 ++
 5 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index b4b357725be2..4e4ea1bf312c 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -539,7 +539,7 @@ static struct inode *drm_fs_inode_new(void)
 		return ERR_PTR(r);
 	}
 
-	inode = alloc_anon_inode(drm_fs.mount->mnt_sb);
+	inode = simple_alloc_anon_inode(&drm_fs);
 	if (IS_ERR(inode))
 		simple_release_fs(&drm_fs);
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 6c6566d8bc17..a3d2682eb3a7 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -73,7 +73,7 @@ static struct file *cxl_getfile(const char *name,
 		goto err_module;
 	}
 
-	inode = alloc_anon_inode(cxl_fs.mount->mnt_sb);
+	inode = simple_alloc_anon_inode(&cxl_fs);
 	if (IS_ERR(inode)) {
 		file = ERR_CAST(inode);
 		goto err_fs;
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 23afde0c6c0e..770fdf186028 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -86,7 +86,7 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err2;
 	}
 
-	inode = alloc_anon_inode(ocxlflash_fs.mount->mnt_sb);
+	inode = simple_alloc_anon_inode(&ocxlflash_fs);
 	if (IS_ERR(inode)) {
 		rc = PTR_ERR(inode);
 		dev_err(dev, "%s: alloc_anon_inode failed rc=%d\n",
diff --git a/fs/simplefs.c b/fs/simplefs.c
index 790d8beb9cc3..c59eb8d996be 100644
--- a/fs/simplefs.c
+++ b/fs/simplefs.c
@@ -36,3 +36,9 @@ void simple_release_fs(struct simple_fs *fs)
 	mntput(mnt);
 }
 EXPORT_SYMBOL(simple_release_fs);
+
+struct inode *simple_alloc_anon_inode(struct simple_fs *fs)
+{
+	return alloc_anon_inode(fs->mount->mnt_sb);
+}
+EXPORT_SYMBOL(simple_alloc_anon_inode);
diff --git a/include/linux/simplefs.h b/include/linux/simplefs.h
index 18010414a16f..c62ab526414e 100644
--- a/include/linux/simplefs.h
+++ b/include/linux/simplefs.h
@@ -12,4 +12,6 @@ struct simple_fs {
 extern int simple_pin_fs(struct simple_fs *, struct file_system_type *);
 extern void simple_release_fs(struct simple_fs *);
 
+extern struct inode *simple_alloc_anon_inode(struct simple_fs *fs);
+
 #endif
-- 
2.25.2


^ permalink raw reply related

* [PATCH 4/8] fs: introduce simple_new_inode
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

It is a common special case for new_inode to initialize the
time to the current time and the inode to get_next_ino().
Introduce a core function that does it and use it throughout
Linux.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 arch/powerpc/platforms/cell/spufs/inode.c |  4 +---
 arch/s390/hypfs/inode.c                   |  4 +---
 drivers/infiniband/hw/qib/qib_fs.c        |  6 +-----
 drivers/misc/ibmasm/ibmasmfs.c            |  8 +++-----
 drivers/oprofile/oprofilefs.c             |  8 +++-----
 drivers/usb/gadget/function/f_fs.c        |  8 +-------
 fs/autofs/inode.c                         |  4 +---
 fs/binfmt_misc.c                          | 16 ++--------------
 fs/debugfs/inode.c                        | 19 ++++---------------
 fs/efivarfs/inode.c                       |  4 +---
 fs/fuse/control.c                         |  4 +---
 fs/hugetlbfs/inode.c                      |  8 ++------
 fs/libfs.c                                | 12 ++++++++++++
 fs/ocfs2/dlmfs/dlmfs.c                    |  8 ++------
 fs/proc/base.c                            |  4 +---
 fs/proc/proc_sysctl.c                     |  5 +----
 fs/pstore/inode.c                         | 14 ++------------
 fs/ramfs/inode.c                          |  4 +---
 fs/tracefs/inode.c                        | 14 ++------------
 include/linux/fs.h                        |  1 +
 ipc/mqueue.c                              |  4 +---
 kernel/bpf/inode.c                        |  7 +------
 mm/shmem.c                                |  4 +---
 net/sunrpc/rpc_pipe.c                     |  4 +---
 security/apparmor/apparmorfs.c            |  8 ++------
 security/inode.c                          |  4 +---
 26 files changed, 50 insertions(+), 136 deletions(-)

diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 25390569e24c..5167b11d41ed 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -77,15 +77,13 @@ spufs_new_inode(struct super_block *sb, umode_t mode)
 {
 	struct inode *inode;
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (!inode)
 		goto out;
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 out:
 	return inode;
 }
diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 5c97f48cea91..97d11561f35c 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -93,15 +93,13 @@ static void hypfs_delete_tree(struct dentry *root)
 
 static struct inode *hypfs_make_inode(struct super_block *sb, umode_t mode)
 {
-	struct inode *ret = new_inode(sb);
+	struct inode *ret = simple_new_inode(sb);
 
 	if (ret) {
 		struct hypfs_sb_info *hypfs_info = sb->s_fs_info;
-		ret->i_ino = get_next_ino();
 		ret->i_mode = mode;
 		ret->i_uid = hypfs_info->uid;
 		ret->i_gid = hypfs_info->gid;
-		ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret);
 		if (S_ISDIR(mode))
 			set_nlink(ret, 2);
 	}
diff --git a/drivers/infiniband/hw/qib/qib_fs.c b/drivers/infiniband/hw/qib/qib_fs.c
index e336d778e076..d402c3b1c552 100644
--- a/drivers/infiniband/hw/qib/qib_fs.c
+++ b/drivers/infiniband/hw/qib/qib_fs.c
@@ -53,21 +53,17 @@ static int qibfs_mknod(struct inode *dir, struct dentry *dentry,
 		       void *data)
 {
 	int error;
-	struct inode *inode = new_inode(dir->i_sb);
+	struct inode *inode = simple_new_inode(dir->i_sb);
 
 	if (!inode) {
 		error = -EPERM;
 		goto bail;
 	}
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = GLOBAL_ROOT_UID;
 	inode->i_gid = GLOBAL_ROOT_GID;
 	inode->i_blocks = 0;
-	inode->i_atime = current_time(inode);
-	inode->i_mtime = inode->i_atime;
-	inode->i_ctime = inode->i_atime;
 	inode->i_private = data;
 	if (S_ISDIR(mode)) {
 		inode->i_op = &simple_dir_inode_operations;
diff --git a/drivers/misc/ibmasm/ibmasmfs.c b/drivers/misc/ibmasm/ibmasmfs.c
index 35fec1bf1b3d..72aa02505f45 100644
--- a/drivers/misc/ibmasm/ibmasmfs.c
+++ b/drivers/misc/ibmasm/ibmasmfs.c
@@ -134,13 +134,11 @@ static int ibmasmfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 static struct inode *ibmasmfs_make_inode(struct super_block *sb, int mode)
 {
-	struct inode *ret = new_inode(sb);
+	struct inode *ret = simple_new_inode(sb);
 
-	if (ret) {
-		ret->i_ino = get_next_ino();
+	if (ret)
 		ret->i_mode = mode;
-		ret->i_atime = ret->i_mtime = ret->i_ctime = current_time(ret);
-	}
+
 	return ret;
 }
 
diff --git a/drivers/oprofile/oprofilefs.c b/drivers/oprofile/oprofilefs.c
index 0875f2f122b3..a903dff693c9 100644
--- a/drivers/oprofile/oprofilefs.c
+++ b/drivers/oprofile/oprofilefs.c
@@ -26,13 +26,11 @@ DEFINE_RAW_SPINLOCK(oprofilefs_lock);
 
 static struct inode *oprofilefs_get_inode(struct super_block *sb, int mode)
 {
-	struct inode *inode = new_inode(sb);
+	struct inode *inode = simple_new_inode(sb);
 
-	if (inode) {
-		inode->i_ino = get_next_ino();
+	if (inode)
 		inode->i_mode = mode;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-	}
+
 	return inode;
 }
 
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index c81023b195c3..d5ca23682f28 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1385,18 +1385,12 @@ ffs_sb_make_inode(struct super_block *sb, void *data,
 
 	ENTER();
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 
 	if (likely(inode)) {
-		struct timespec64 ts = current_time(inode);
-
-		inode->i_ino	 = get_next_ino();
 		inode->i_mode    = perms->mode;
 		inode->i_uid     = perms->uid;
 		inode->i_gid     = perms->gid;
-		inode->i_atime   = ts;
-		inode->i_mtime   = ts;
-		inode->i_ctime   = ts;
 		inode->i_private = data;
 		if (fops)
 			inode->i_fop = fops;
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index 9edf243713eb..26710b7d5ade 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -359,7 +359,7 @@ int autofs_fill_super(struct super_block *s, void *data, int silent)
 
 struct inode *autofs_get_inode(struct super_block *sb, umode_t mode)
 {
-	struct inode *inode = new_inode(sb);
+	struct inode *inode = simple_new_inode(sb);
 
 	if (inode == NULL)
 		return NULL;
@@ -369,8 +369,6 @@ struct inode *autofs_get_inode(struct super_block *sb, umode_t mode)
 		inode->i_uid = d_inode(sb->s_root)->i_uid;
 		inode->i_gid = d_inode(sb->s_root)->i_gid;
 	}
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-	inode->i_ino = get_next_ino();
 
 	if (S_ISDIR(mode)) {
 		set_nlink(inode, 2);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 475096a02a1a..cd27039ffbdf 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -586,19 +586,6 @@ static void entry_status(Node *e, char *page)
 	}
 }
 
-static struct inode *bm_get_inode(struct super_block *sb, int mode)
-{
-	struct inode *inode = new_inode(sb);
-
-	if (inode) {
-		inode->i_ino = get_next_ino();
-		inode->i_mode = mode;
-		inode->i_atime = inode->i_mtime = inode->i_ctime =
-			current_time(inode);
-	}
-	return inode;
-}
-
 static void bm_evict_inode(struct inode *inode)
 {
 	Node *e = inode->i_private;
@@ -711,12 +698,13 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 	if (d_really_is_positive(dentry))
 		goto out2;
 
-	inode = bm_get_inode(sb, S_IFREG | 0644);
+	inode = simple_new_inode(sb);
 
 	err = -ENOMEM;
 	if (!inode)
 		goto out2;
 
+	inode->i_mode = S_IFREG | 0644;
 	err = simple_pin_fs(&bm_fs, &bm_fs_type);
 	if (err) {
 		iput(inode);
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index ea54efc74c0d..834b5872ca0d 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -61,17 +61,6 @@ static const struct inode_operations debugfs_symlink_inode_operations = {
 	.setattr	= debugfs_setattr,
 };
 
-static struct inode *debugfs_get_inode(struct super_block *sb)
-{
-	struct inode *inode = new_inode(sb);
-	if (inode) {
-		inode->i_ino = get_next_ino();
-		inode->i_atime = inode->i_mtime =
-			inode->i_ctime = current_time(inode);
-	}
-	return inode;
-}
-
 struct debugfs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
@@ -383,7 +372,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = debugfs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create file '%s'\n",
 		       name);
@@ -539,7 +528,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent)
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = debugfs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create directory '%s'\n",
 		       name);
@@ -581,7 +570,7 @@ struct dentry *debugfs_create_automount(const char *name,
 	if (IS_ERR(dentry))
 		return dentry;
 
-	inode = debugfs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create automount '%s'\n",
 		       name);
@@ -639,7 +628,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent,
 		return dentry;
 	}
 
-	inode = debugfs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode)) {
 		pr_err("out of free dentries, can not create symlink '%s'\n",
 		       name);
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 96c0c86f3fff..f8f459f43920 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -16,12 +16,10 @@ struct inode *efivarfs_get_inode(struct super_block *sb,
 				const struct inode *dir, int mode,
 				dev_t dev, bool is_removable)
 {
-	struct inode *inode = new_inode(sb);
+	struct inode *inode = simple_new_inode(sb);
 
 	if (inode) {
-		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_flags = is_removable ? 0 : S_IMMUTABLE;
 		switch (mode & S_IFMT) {
 		case S_IFREG:
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index c23f6f243ad4..6a9f35aca480 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -232,17 +232,15 @@ static struct dentry *fuse_ctl_add_dentry(struct dentry *parent,
 	if (!dentry)
 		return NULL;
 
-	inode = new_inode(fuse_control_sb);
+	inode = simple_new_inode(fuse_control_sb);
 	if (!inode) {
 		dput(dentry);
 		return NULL;
 	}
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = fc->user_id;
 	inode->i_gid = fc->group_id;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	/* setting ->i_op to NULL is not allowed */
 	if (iop)
 		inode->i_op = iop;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 991c60c7ffe0..4064389c2c23 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -739,13 +739,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 {
 	struct inode *inode;
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (inode) {
-		inode->i_ino = get_next_ino();
 		inode->i_mode = S_IFDIR | ctx->mode;
 		inode->i_uid = ctx->uid;
 		inode->i_gid = ctx->gid;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_op = &hugetlbfs_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -780,16 +778,14 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 			return NULL;
 	}
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (inode) {
 		struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode);
 
-		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
 				&hugetlbfs_i_mmap_rwsem_key);
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_mapping->private_data = resv_map;
 		info->seals = F_SEAL_SEAL;
 		switch (mode & S_IFMT) {
diff --git a/fs/libfs.c b/fs/libfs.c
index 26ec729f7bcd..20bdee9361d5 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -595,6 +595,18 @@ int simple_write_end(struct file *file, struct address_space *mapping,
 }
 EXPORT_SYMBOL(simple_write_end);
 
+struct inode *simple_new_inode(struct super_block *sb)
+{
+	struct inode *inode = new_inode(sb);
+	if (inode) {
+		inode->i_ino = get_next_ino();
+		inode->i_atime = inode->i_mtime =
+			inode->i_ctime = current_time(inode);
+	}
+	return inode;
+}
+EXPORT_SYMBOL(simple_new_inode);
+
 /*
  * the inodes created here are not hashed. If you use iunique to generate
  * unique inode values later for this filesystem, then you must take care
diff --git a/fs/ocfs2/dlmfs/dlmfs.c b/fs/ocfs2/dlmfs/dlmfs.c
index 8e4f1ace467c..6285c174f9f2 100644
--- a/fs/ocfs2/dlmfs/dlmfs.c
+++ b/fs/ocfs2/dlmfs/dlmfs.c
@@ -371,13 +371,11 @@ static void dlmfs_evict_inode(struct inode *inode)
 
 static struct inode *dlmfs_get_root_inode(struct super_block *sb)
 {
-	struct inode *inode = new_inode(sb);
+	struct inode *inode = simple_new_inode(sb);
 	umode_t mode = S_IFDIR | 0755;
 
 	if (inode) {
-		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, NULL, mode);
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inc_nlink(inode);
 
 		inode->i_fop = &simple_dir_operations;
@@ -392,15 +390,13 @@ static struct inode *dlmfs_get_inode(struct inode *parent,
 				     umode_t mode)
 {
 	struct super_block *sb = parent->i_sb;
-	struct inode * inode = new_inode(sb);
+	struct inode * inode = simple_new_inode(sb);
 	struct dlmfs_inode_private *ip;
 
 	if (!inode)
 		return NULL;
 
-	inode->i_ino = get_next_ino();
 	inode_init_owner(inode, parent, mode);
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 
 	ip = DLMFS_I(inode);
 	ip->ip_conn = DLMFS_I(parent)->ip_conn;
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 74f948a6b621..3ef16f4f14c9 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1856,15 +1856,13 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 
 	/* We need a new inode */
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (!inode)
 		goto out;
 
 	/* Common stuff */
 	ei = PROC_I(inode);
 	inode->i_mode = mode;
-	inode->i_ino = get_next_ino();
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_op = &proc_def_inode_operations;
 
 	/*
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index b6f5d459b087..3464ab94cf79 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -434,12 +434,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	struct inode *inode;
 	struct proc_inode *ei;
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 
-	inode->i_ino = get_next_ino();
-
 	ei = PROC_I(inode);
 
 	spin_lock(&sysctl_lock);
@@ -454,7 +452,6 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 	head->count++;
 	spin_unlock(&sysctl_lock);
 
-	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_mode = table->mode;
 	if (!S_ISDIR(table->mode)) {
 		inode->i_mode |= S_IFREG;
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index d99b5d39aa90..d6cad315a839 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -208,16 +208,6 @@ static const struct inode_operations pstore_dir_inode_operations = {
 	.unlink		= pstore_unlink,
 };
 
-static struct inode *pstore_get_inode(struct super_block *sb)
-{
-	struct inode *inode = new_inode(sb);
-	if (inode) {
-		inode->i_ino = get_next_ino();
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-	}
-	return inode;
-}
-
 enum {
 	Opt_kmsg_bytes, Opt_err
 };
@@ -316,7 +306,7 @@ int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 		return rc;
 
 	rc = -ENOMEM;
-	inode = pstore_get_inode(root->d_sb);
+	inode = simple_new_inode(root->d_sb);
 	if (!inode)
 		goto fail;
 	inode->i_mode = S_IFREG | 0444;
@@ -394,7 +384,7 @@ static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 
 	parse_options(data);
 
-	inode = pstore_get_inode(sb);
+	inode = simple_new_inode(sb);
 	if (inode) {
 		inode->i_mode = S_IFDIR | 0750;
 		inode->i_op = &pstore_dir_inode_operations;
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index ee179a81b3da..cf2ce7bc4c9d 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -63,15 +63,13 @@ static const struct address_space_operations ramfs_aops = {
 struct inode *ramfs_get_inode(struct super_block *sb,
 				const struct inode *dir, umode_t mode, dev_t dev)
 {
-	struct inode * inode = new_inode(sb);
+	struct inode * inode = simple_new_inode(sb);
 
 	if (inode) {
-		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_mapping->a_ops = &ramfs_aops;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
 		mapping_set_unevictable(inode->i_mapping);
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		switch (mode & S_IFMT) {
 		default:
 			init_special_inode(inode, mode, dev);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 40ccfe737c3a..a30837a8e1d4 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -124,16 +124,6 @@ static const struct inode_operations tracefs_dir_inode_operations = {
 	.rmdir		= tracefs_syscall_rmdir,
 };
 
-static struct inode *tracefs_get_inode(struct super_block *sb)
-{
-	struct inode *inode = new_inode(sb);
-	if (inode) {
-		inode->i_ino = get_next_ino();
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-	}
-	return inode;
-}
-
 struct tracefs_mount_opts {
 	kuid_t uid;
 	kgid_t gid;
@@ -403,7 +393,7 @@ struct dentry *tracefs_create_file(const char *name, umode_t mode,
 	if (IS_ERR(dentry))
 		return NULL;
 
-	inode = tracefs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
@@ -424,7 +414,7 @@ static struct dentry *__create_dir(const char *name, struct dentry *parent,
 	if (IS_ERR(dentry))
 		return NULL;
 
-	inode = tracefs_get_inode(dentry->d_sb);
+	inode = simple_new_inode(dentry->d_sb);
 	if (unlikely(!inode))
 		return failed_creating(dentry);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 55b679b89c8a..6136f5ba2680 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3088,6 +3088,7 @@ extern void clear_inode(struct inode *);
 extern void __destroy_inode(struct inode *);
 extern struct inode *new_inode_pseudo(struct super_block *sb);
 extern struct inode *new_inode(struct super_block *sb);
+extern struct inode *simple_new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_privs(struct file *);
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 49a05ba3000d..74c4f852a688 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -296,15 +296,13 @@ static struct inode *mqueue_get_inode(struct super_block *sb,
 	struct inode *inode;
 	int ret = -ENOMEM;
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (!inode)
 		goto err;
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
 	inode->i_uid = current_fsuid();
 	inode->i_gid = current_fsgid();
-	inode->i_mtime = inode->i_ctime = inode->i_atime = current_time(inode);
 
 	if (S_ISREG(mode)) {
 		struct mqueue_inode_info *info;
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 95087d9f4ed3..532a733c474a 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -112,15 +112,10 @@ static struct inode *bpf_get_inode(struct super_block *sb,
 		return ERR_PTR(-EINVAL);
 	}
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOSPC);
 
-	inode->i_ino = get_next_ino();
-	inode->i_atime = current_time(inode);
-	inode->i_mtime = inode->i_atime;
-	inode->i_ctime = inode->i_atime;
-
 	inode_init_owner(inode, dir, mode);
 
 	return inode;
diff --git a/mm/shmem.c b/mm/shmem.c
index f47347cb30f6..50ca377464e2 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2246,12 +2246,10 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 	if (shmem_reserve_inode(sb))
 		return NULL;
 
-	inode = new_inode(sb);
+	inode = simple_new_inode(sb);
 	if (inode) {
-		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
-		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_generation = prandom_u32();
 		info = SHMEM_I(inode);
 		memset(info, 0, (char *)inode - (char *)info);
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 39e14d5edaf1..fa48b8f55ba9 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -467,12 +467,10 @@ struct rpc_filelist {
 static struct inode *
 rpc_get_inode(struct super_block *sb, umode_t mode)
 {
-	struct inode *inode = new_inode(sb);
+	struct inode *inode = simple_new_inode(sb);
 	if (!inode)
 		return NULL;
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	switch (mode & S_IFMT) {
 	case S_IFDIR:
 		inode->i_fop = &simple_dir_operations;
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 75d70e6ba0a0..1a8afe9d7110 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -212,7 +212,7 @@ static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry,
 			       const struct file_operations *fops,
 			       const struct inode_operations *iops)
 {
-	struct inode *inode = new_inode(dir->i_sb);
+	struct inode *inode = simple_new_inode(dir->i_sb);
 
 	AA_BUG(!dir);
 	AA_BUG(!dentry);
@@ -220,9 +220,7 @@ static int __aafs_setup_d_inode(struct inode *dir, struct dentry *dentry,
 	if (!inode)
 		return -ENOMEM;
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	inode->i_private = data;
 	if (S_ISDIR(mode)) {
 		inode->i_op = iops ? iops : &simple_dir_inode_operations;
@@ -2540,15 +2538,13 @@ static int aa_mk_null_file(struct dentry *parent)
 		error = PTR_ERR(dentry);
 		goto out;
 	}
-	inode = new_inode(parent->d_inode->i_sb);
+	inode = simple_new_inode(parent->d_inode->i_sb);
 	if (!inode) {
 		error = -ENOMEM;
 		goto out1;
 	}
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = S_IFCHR | S_IRUGO | S_IWUGO;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	init_special_inode(inode, S_IFCHR | S_IRUGO | S_IWUGO,
 			   MKDEV(MEM_MAJOR, 3));
 	d_instantiate(dentry, inode);
diff --git a/security/inode.c b/security/inode.c
index 0fcd03299e0d..8a1a7f73ee9c 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -136,15 +136,13 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
 		goto out1;
 	}
 
-	inode = new_inode(dir->i_sb);
+	inode = simple_new_inode(dir->i_sb);
 	if (!inode) {
 		error = -ENOMEM;
 		goto out1;
 	}
 
-	inode->i_ino = get_next_ino();
 	inode->i_mode = mode;
-	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 	inode->i_private = data;
 	if (S_ISDIR(mode)) {
 		inode->i_op = &simple_dir_inode_operations;
-- 
2.25.2


^ permalink raw reply related

* [PATCH 3/8] fs: wrap simple_pin_fs/simple_release_fs arguments in a struct
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

Simplify passing the count and mount to simple_pin_fs and simple_release_fs,
in preparation for adding more high level operations to the simplefs API.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 drivers/gpu/drm/drm_drv.c       | 11 +++++------
 drivers/misc/cxl/api.c          | 13 ++++++-------
 drivers/scsi/cxlflash/ocxl_hw.c | 14 ++++++--------
 fs/binfmt_misc.c                |  9 ++++-----
 fs/configfs/mount.c             | 10 ++++------
 fs/debugfs/inode.c              | 22 ++++++++++------------
 fs/simplefs.c                   | 20 ++++++++++----------
 fs/tracefs/inode.c              | 18 ++++++++----------
 include/linux/simplefs.h        |  9 +++++++--
 security/apparmor/apparmorfs.c  | 25 ++++++++++++-------------
 security/inode.c                | 11 +++++------
 11 files changed, 77 insertions(+), 85 deletions(-)

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 187a61091b5c..b4b357725be2 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -514,8 +514,7 @@ EXPORT_SYMBOL(drm_dev_unplug);
  * iput(), but this way you'd end up with a new vfsmount for each inode.
  */
 
-static int drm_fs_cnt;
-static struct vfsmount *drm_fs_mnt;
+static struct simple_fs drm_fs;
 
 static int drm_fs_init_fs_context(struct fs_context *fc)
 {
@@ -534,15 +533,15 @@ static struct inode *drm_fs_inode_new(void)
 	struct inode *inode;
 	int r;
 
-	r = simple_pin_fs(&drm_fs_type, &drm_fs_mnt, &drm_fs_cnt);
+	r = simple_pin_fs(&drm_fs, &drm_fs_type);
 	if (r < 0) {
 		DRM_ERROR("Cannot mount pseudo fs: %d\n", r);
 		return ERR_PTR(r);
 	}
 
-	inode = alloc_anon_inode(drm_fs_mnt->mnt_sb);
+	inode = alloc_anon_inode(drm_fs.mount->mnt_sb);
 	if (IS_ERR(inode))
-		simple_release_fs(&drm_fs_mnt, &drm_fs_cnt);
+		simple_release_fs(&drm_fs);
 
 	return inode;
 }
@@ -551,7 +550,7 @@ static void drm_fs_inode_free(struct inode *inode)
 {
 	if (inode) {
 		iput(inode);
-		simple_release_fs(&drm_fs_mnt, &drm_fs_cnt);
+		simple_release_fs(&drm_fs);
 	}
 }
 
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 0b8f8de7475a..6c6566d8bc17 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -32,8 +32,7 @@
 
 #define CXL_PSEUDO_FS_MAGIC	0x1697697f
 
-static int cxl_fs_cnt;
-static struct vfsmount *cxl_vfs_mount;
+static struct simple_fs cxl_fs;
 
 static int cxl_fs_init_fs_context(struct fs_context *fc)
 {
@@ -51,7 +50,7 @@ static struct file_system_type cxl_fs_type = {
 void cxl_release_mapping(struct cxl_context *ctx)
 {
 	if (ctx->kernelapi && ctx->mapping)
-		simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
+		simple_release_fs(&cxl_fs);
 }
 
 static struct file *cxl_getfile(const char *name,
@@ -67,20 +66,20 @@ static struct file *cxl_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	rc = simple_pin_fs(&cxl_fs_type, &cxl_vfs_mount, &cxl_fs_cnt);
+	rc = simple_pin_fs(&cxl_fs, &cxl_fs_type);
 	if (rc < 0) {
 		pr_err("Cannot mount cxl pseudo filesystem: %d\n", rc);
 		file = ERR_PTR(rc);
 		goto err_module;
 	}
 
-	inode = alloc_anon_inode(cxl_vfs_mount->mnt_sb);
+	inode = alloc_anon_inode(cxl_fs.mount->mnt_sb);
 	if (IS_ERR(inode)) {
 		file = ERR_CAST(inode);
 		goto err_fs;
 	}
 
-	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+	file = alloc_file_pseudo(inode, cxl_fs.mount, name,
 				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
 		goto err_inode;
@@ -92,7 +91,7 @@ static struct file *cxl_getfile(const char *name,
 err_inode:
 	iput(inode);
 err_fs:
-	simple_release_fs(&cxl_vfs_mount, &cxl_fs_cnt);
+	simple_release_fs(&cxl_fs);
 err_module:
 	module_put(fops->owner);
 	return file;
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 429f55651090..23afde0c6c0e 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -30,8 +30,7 @@
 
 #define OCXLFLASH_FS_MAGIC      0x1697698f
 
-static int ocxlflash_fs_cnt;
-static struct vfsmount *ocxlflash_vfs_mount;
+static struct simple_fs ocxlflash_fs;
 
 static int ocxlflash_fs_init_fs_context(struct fs_context *fc)
 {
@@ -52,7 +51,7 @@ static struct file_system_type ocxlflash_fs_type = {
 static void ocxlflash_release_mapping(struct ocxlflash_context *ctx)
 {
 	if (ctx->mapping)
-		simple_release_fs(&ocxlflash_vfs_mount, &ocxlflash_fs_cnt);
+		simple_release_fs(&ocxlflash_fs);
 	ctx->mapping = NULL;
 }
 
@@ -80,15 +79,14 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err1;
 	}
 
-	rc = simple_pin_fs(&ocxlflash_fs_type, &ocxlflash_vfs_mount,
-			   &ocxlflash_fs_cnt);
+	rc = simple_pin_fs(&ocxlflash_fs, &ocxlflash_fs_type);
 	if (unlikely(rc < 0)) {
 		dev_err(dev, "%s: Cannot mount ocxlflash pseudofs rc=%d\n",
 			__func__, rc);
 		goto err2;
 	}
 
-	inode = alloc_anon_inode(ocxlflash_vfs_mount->mnt_sb);
+	inode = alloc_anon_inode(ocxlflash_fs.mount->mnt_sb);
 	if (IS_ERR(inode)) {
 		rc = PTR_ERR(inode);
 		dev_err(dev, "%s: alloc_anon_inode failed rc=%d\n",
@@ -96,7 +94,7 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+	file = alloc_file_pseudo(inode, ocxlflash_fs.mount, name,
 				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
@@ -111,7 +109,7 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 err4:
 	iput(inode);
 err3:
-	simple_release_fs(&ocxlflash_vfs_mount, &ocxlflash_fs_cnt);
+	simple_release_fs(&ocxlflash_fs);
 err2:
 	module_put(fops->owner);
 err1:
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index c764110f5f0b..475096a02a1a 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -64,8 +64,7 @@ typedef struct {
 
 static DEFINE_RWLOCK(entries_lock);
 static struct file_system_type bm_fs_type;
-static struct vfsmount *bm_mnt;
-static int entry_count;
+static struct simple_fs bm_fs;
 
 /*
  * Max length of the register string.  Determined by:
@@ -623,7 +622,7 @@ static void kill_node(Node *e)
 	drop_nlink(d_inode(dentry));
 	d_drop(dentry);
 	dput(dentry);
-	simple_release_fs(&bm_mnt, &entry_count);
+	simple_release_fs(&bm_fs);
 }
 
 /* /<entry> */
@@ -718,7 +717,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 	if (!inode)
 		goto out2;
 
-	err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count);
+	err = simple_pin_fs(&bm_fs, &bm_fs_type);
 	if (err) {
 		iput(inode);
 		inode = NULL;
@@ -732,7 +731,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer,
 		if (IS_ERR(f)) {
 			err = PTR_ERR(f);
 			pr_notice("register: failed to install interpreter file %s\n", e->interpreter);
-			simple_release_fs(&bm_mnt, &entry_count);
+			simple_release_fs(&bm_fs);
 			iput(inode);
 			inode = NULL;
 			goto out2;
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 331c2f064f02..a671974f5b6f 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -24,9 +24,8 @@
 /* Random magic number */
 #define CONFIGFS_MAGIC 0x62656570
 
-static struct vfsmount *configfs_mount = NULL;
+static struct simple_fs configfs_fs;
 struct kmem_cache *configfs_dir_cachep;
-static int configfs_mnt_count = 0;
 
 
 static void configfs_free_inode(struct inode *inode)
@@ -123,14 +122,13 @@ MODULE_ALIAS_FS("configfs");
 
 struct dentry *configfs_pin_fs(void)
 {
-	int err = simple_pin_fs(&configfs_fs_type, &configfs_mount,
-			     &configfs_mnt_count);
-	return err ? ERR_PTR(err) : configfs_mount->mnt_root;
+	int err = simple_pin_fs(&configfs_fs, &configfs_fs_type);
+	return err ? ERR_PTR(err) : configfs_fs.mount->mnt_root;
 }
 
 void configfs_release_fs(void)
 {
-	simple_release_fs(&configfs_mount, &configfs_mnt_count);
+	simple_release_fs(&configfs_fs);
 }
 
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 7b9fddced48f..ea54efc74c0d 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -32,8 +32,7 @@
 
 #define DEBUGFS_DEFAULT_MODE	0700
 
-static struct vfsmount *debugfs_mount;
-static int debugfs_mount_count;
+static struct simple_fs debugfs;
 static bool debugfs_registered;
 
 /*
@@ -297,7 +296,7 @@ struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
 		return NULL;
 
 	if (!parent)
-		parent = debugfs_mount->mnt_root;
+		parent = debugfs.mount->mnt_root;
 
 	dentry = lookup_positive_unlocked(name, parent, strlen(name));
 	if (IS_ERR(dentry))
@@ -316,8 +315,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	if (IS_ERR(parent))
 		return parent;
 
-	error = simple_pin_fs(&debug_fs_type, &debugfs_mount,
-			      &debugfs_mount_count);
+	error = simple_pin_fs(&debugfs, &debug_fs_type);
 	if (error) {
 		pr_err("Unable to pin filesystem for file '%s'\n", name);
 		return ERR_PTR(error);
@@ -329,7 +327,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	 * have around.
 	 */
 	if (!parent)
-		parent = debugfs_mount->mnt_root;
+		parent = debugfs.mount->mnt_root;
 
 	inode_lock(d_inode(parent));
 	if (unlikely(IS_DEADDIR(d_inode(parent))))
@@ -349,7 +347,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 
 	if (IS_ERR(dentry)) {
 		inode_unlock(d_inode(parent));
-		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+		simple_release_fs(&debugfs);
 	}
 
 	return dentry;
@@ -359,7 +357,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
 {
 	inode_unlock(d_inode(dentry->d_parent));
 	dput(dentry);
-	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	simple_release_fs(&debugfs);
 	return ERR_PTR(-ENOMEM);
 }
 
@@ -676,9 +674,9 @@ static void __debugfs_file_removed(struct dentry *dentry)
 
 static void remove_one(struct dentry *victim)
 {
-        if (d_is_reg(victim))
+    if (d_is_reg(victim))
 		__debugfs_file_removed(victim);
-	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	simple_release_fs(&debugfs);
 }
 
 /**
@@ -699,9 +697,9 @@ void debugfs_remove(struct dentry *dentry)
 	if (IS_ERR_OR_NULL(dentry))
 		return;
 
-	simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count);
+	simple_pin_fs(&debugfs, &debug_fs_type);
 	simple_recursive_removal(dentry, remove_one);
-	simple_release_fs(&debugfs_mount, &debugfs_mount_count);
+	simple_release_fs(&debugfs);
 }
 EXPORT_SYMBOL_GPL(debugfs_remove);
 
diff --git a/fs/simplefs.c b/fs/simplefs.c
index 226d18963801..790d8beb9cc3 100644
--- a/fs/simplefs.c
+++ b/fs/simplefs.c
@@ -4,34 +4,34 @@
 
 static DEFINE_SPINLOCK(pin_fs_lock);
 
-int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
+int simple_pin_fs(struct simple_fs *fs, struct file_system_type *type)
 {
 	struct vfsmount *mnt = NULL;
 	spin_lock(&pin_fs_lock);
-	if (unlikely(!*mount)) {
+	if (unlikely(!fs->mount)) {
 		spin_unlock(&pin_fs_lock);
 		mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
 		if (IS_ERR(mnt))
 			return PTR_ERR(mnt);
 		spin_lock(&pin_fs_lock);
-		if (!*mount)
-			*mount = mnt;
+		if (!fs->mount)
+			fs->mount = mnt;
 	}
-	mntget(*mount);
-	++*count;
+	mntget(fs->mount);
+	++fs->count;
 	spin_unlock(&pin_fs_lock);
 	mntput(mnt);
 	return 0;
 }
 EXPORT_SYMBOL(simple_pin_fs);
 
-void simple_release_fs(struct vfsmount **mount, int *count)
+void simple_release_fs(struct simple_fs *fs)
 {
 	struct vfsmount *mnt;
 	spin_lock(&pin_fs_lock);
-	mnt = *mount;
-	if (!--*count)
-		*mount = NULL;
+	mnt = fs->mount;
+	if (!--fs->count)
+		fs->mount = NULL;
 	spin_unlock(&pin_fs_lock);
 	mntput(mnt);
 }
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 4353ca81e1d7..40ccfe737c3a 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -24,8 +24,7 @@
 
 #define TRACEFS_DEFAULT_MODE	0700
 
-static struct vfsmount *tracefs_mount;
-static int tracefs_mount_count;
+static struct simple_fs tracefs;
 static bool tracefs_registered;
 
 static ssize_t default_read_file(struct file *file, char __user *buf,
@@ -316,8 +315,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 
 	pr_debug("tracefs: creating file '%s'\n",name);
 
-	error = simple_pin_fs(&trace_fs_type, &tracefs_mount,
-			      &tracefs_mount_count);
+	error = simple_pin_fs(&tracefs, &trace_fs_type);
 	if (error)
 		return ERR_PTR(error);
 
@@ -327,7 +325,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	 * have around.
 	 */
 	if (!parent)
-		parent = tracefs_mount->mnt_root;
+		parent = tracefs.mount->mnt_root;
 
 	inode_lock(parent->d_inode);
 	if (unlikely(IS_DEADDIR(parent->d_inode)))
@@ -341,7 +339,7 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 
 	if (IS_ERR(dentry)) {
 		inode_unlock(parent->d_inode);
-		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+		simple_release_fs(&tracefs);
 	}
 
 	return dentry;
@@ -351,7 +349,7 @@ static struct dentry *failed_creating(struct dentry *dentry)
 {
 	inode_unlock(dentry->d_parent->d_inode);
 	dput(dentry);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	simple_release_fs(&tracefs);
 	return NULL;
 }
 
@@ -504,7 +502,7 @@ __init struct dentry *tracefs_create_instance_dir(const char *name,
 
 static void remove_one(struct dentry *victim)
 {
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	simple_release_fs(&tracefs);
 }
 
 /**
@@ -520,9 +518,9 @@ void tracefs_remove(struct dentry *dentry)
 	if (IS_ERR_OR_NULL(dentry))
 		return;
 
-	simple_pin_fs(&trace_fs_type, &tracefs_mount, &tracefs_mount_count);
+	simple_pin_fs(&tracefs, &trace_fs_type);
 	simple_recursive_removal(dentry, remove_one);
-	simple_release_fs(&tracefs_mount, &tracefs_mount_count);
+	simple_release_fs(&tracefs);
 }
 
 /**
diff --git a/include/linux/simplefs.h b/include/linux/simplefs.h
index 1076a44db308..18010414a16f 100644
--- a/include/linux/simplefs.h
+++ b/include/linux/simplefs.h
@@ -4,7 +4,12 @@
 
 #include <linux/fs.h>
 
-extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
-extern void simple_release_fs(struct vfsmount **mount, int *count);
+struct simple_fs {
+	struct vfsmount *mount;
+	int count;
+};
+
+extern int simple_pin_fs(struct simple_fs *, struct file_system_type *);
+extern void simple_release_fs(struct simple_fs *);
 
 #endif
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index d62d3fca47f2..75d70e6ba0a0 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -140,8 +140,7 @@ static int mangle_name(const char *name, char *target)
  */
 
 #define AAFS_NAME		"apparmorfs"
-static struct vfsmount *aafs_mnt;
-static int aafs_count;
+static struct simple_fs aafs;
 
 
 static int aafs_show_path(struct seq_file *seq, struct dentry *dentry)
@@ -273,7 +272,7 @@ static struct dentry *aafs_create(const char *name, umode_t mode,
 	if (!(mode & S_IFMT))
 		mode = (mode & S_IALLUGO) | S_IFREG;
 
-	error = simple_pin_fs(&aafs_ops, &aafs_mnt, &aafs_count);
+	error = simple_pin_fs(&aafs, &aafs_ops);
 	if (error)
 		return ERR_PTR(error);
 
@@ -303,7 +302,7 @@ static struct dentry *aafs_create(const char *name, umode_t mode,
 
 fail_lock:
 	inode_unlock(dir);
-	simple_release_fs(&aafs_mnt, &aafs_count);
+	simple_release_fs(&aafs);
 
 	return ERR_PTR(error);
 }
@@ -395,7 +394,7 @@ static void aafs_remove(struct dentry *dentry)
 		dput(dentry);
 	}
 	inode_unlock(dir);
-	simple_release_fs(&aafs_mnt, &aafs_count);
+	simple_release_fs(&aafs);
 }
 
 
@@ -1824,7 +1823,7 @@ static int ns_mkdir_op(struct inode *dir, struct dentry *dentry, umode_t mode)
 	 * for pin_fs
 	 */
 	inode_unlock(dir);
-	error = simple_pin_fs(&aafs_ops, &aafs_mnt, &aafs_count);
+	error = simple_pin_fs(&aafs, &aafs_ops);
 	mutex_lock_nested(&parent->lock, parent->level);
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	if (error)
@@ -1845,7 +1844,7 @@ static int ns_mkdir_op(struct inode *dir, struct dentry *dentry, umode_t mode)
 	aa_put_ns(ns);		/* list ref remains */
 out_pin:
 	if (error)
-		simple_release_fs(&aafs_mnt, &aafs_count);
+		simple_release_fs(&aafs);
 out:
 	mutex_unlock(&parent->lock);
 	aa_put_ns(parent);
@@ -2580,7 +2579,7 @@ static const char *policy_get_link(struct dentry *dentry,
 		return ERR_PTR(-ECHILD);
 
 	ns = aa_get_current_ns();
-	path.mnt = mntget(aafs_mnt);
+	path.mnt = mntget(aafs.mount);
 	path.dentry = dget(ns_dir(ns));
 	error = nd_jump_link(&path);
 	aa_put_ns(ns);
@@ -2631,10 +2630,10 @@ static int __init aa_create_aafs(void)
 	}
 
 	/* setup apparmorfs used to virtualize policy/ */
-	aafs_mnt = kern_mount(&aafs_ops);
-	if (IS_ERR(aafs_mnt))
+	aafs.mount = kern_mount(&aafs_ops);
+	if (IS_ERR(aafs.mount))
 		panic("can't set apparmorfs up\n");
-	aafs_mnt->mnt_sb->s_flags &= ~SB_NOUSER;
+	aafs.mount->mnt_sb->s_flags &= ~SB_NOUSER;
 
 	/* Populate fs tree. */
 	error = entry_create_dir(&aa_sfs_entry, NULL);
@@ -2667,8 +2666,8 @@ static int __init aa_create_aafs(void)
 
 	/* policy tree referenced by magic policy symlink */
 	mutex_lock_nested(&root_ns->lock, root_ns->level);
-	error = __aafs_ns_mkdir(root_ns, aafs_mnt->mnt_root, ".policy",
-				aafs_mnt->mnt_root);
+	error = __aafs_ns_mkdir(root_ns, aafs.mount->mnt_root, ".policy",
+				aafs.mount->mnt_root);
 	mutex_unlock(&root_ns->lock);
 	if (error)
 		goto error;
diff --git a/security/inode.c b/security/inode.c
index a9a9ee4de21d..0fcd03299e0d 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -22,8 +22,7 @@
 #include <linux/lsm_hooks.h>
 #include <linux/magic.h>
 
-static struct vfsmount *mount;
-static int mount_count;
+static struct simple_fs securityfs;
 
 static void securityfs_free_inode(struct inode *inode)
 {
@@ -118,12 +117,12 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
 
 	pr_debug("securityfs: creating file '%s'\n",name);
 
-	error = simple_pin_fs(&fs_type, &mount, &mount_count);
+	error = simple_pin_fs(&securityfs, &fs_type);
 	if (error)
 		return ERR_PTR(error);
 
 	if (!parent)
-		parent = mount->mnt_root;
+		parent = securityfs.mount->mnt_root;
 
 	dir = d_inode(parent);
 
@@ -168,7 +167,7 @@ static struct dentry *securityfs_create_dentry(const char *name, umode_t mode,
 	dentry = ERR_PTR(error);
 out:
 	inode_unlock(dir);
-	simple_release_fs(&mount, &mount_count);
+	simple_release_fs(&securityfs);
 	return dentry;
 }
 
@@ -309,7 +308,7 @@ void securityfs_remove(struct dentry *dentry)
 		dput(dentry);
 	}
 	inode_unlock(dir);
-	simple_release_fs(&mount, &mount_count);
+	simple_release_fs(&securityfs);
 }
 EXPORT_SYMBOL_GPL(securityfs_remove);
 
-- 
2.25.2


^ permalink raw reply related

* [PATCH 2/8] fs: extract simple_pin/release_fs to separate files
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

We will augment this family of functions with inode management.  To avoid
littering include/linux/fs.h and fs/libfs.c, move them to a separate header,
with a Kconfig symbol to enable them.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 drivers/gpu/drm/Kconfig         |  1 +
 drivers/gpu/drm/drm_drv.c       |  2 +-
 drivers/misc/cxl/Kconfig        |  1 +
 drivers/misc/cxl/api.c          |  1 +
 drivers/misc/ocxl/Kconfig       |  1 +
 drivers/scsi/cxlflash/ocxl_hw.c |  1 +
 fs/Kconfig                      |  3 +++
 fs/Kconfig.binfmt               |  1 +
 fs/Makefile                     |  1 +
 fs/binfmt_misc.c                |  2 +-
 fs/configfs/Kconfig             |  1 +
 fs/configfs/mount.c             |  2 +-
 fs/debugfs/inode.c              |  2 +-
 fs/libfs.c                      | 36 +------------------------------
 fs/simplefs.c                   | 38 +++++++++++++++++++++++++++++++++
 fs/tracefs/inode.c              |  2 +-
 include/linux/fs.h              |  2 --
 include/linux/simplefs.h        | 10 +++++++++
 lib/Kconfig.debug               | 16 ++++++++------
 security/Kconfig                |  1 +
 security/apparmor/apparmorfs.c  |  3 ++-
 security/inode.c                |  2 +-
 22 files changed, 79 insertions(+), 50 deletions(-)
 create mode 100644 fs/simplefs.c
 create mode 100644 include/linux/simplefs.h

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 43594978958e..a6fe933de9da 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -14,6 +14,7 @@ menuconfig DRM
 	select I2C
 	select I2C_ALGOBIT
 	select DMA_SHARED_BUFFER
+	select SIMPLEFS
 	select SYNC_FILE
 	help
 	  Kernel-level support for the Direct Rendering Infrastructure (DRI)
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 7b1a628d1f6e..187a61091b5c 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -27,7 +27,7 @@
  */
 
 #include <linux/debugfs.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/mount.h>
diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index 39eec9031487..a62795079d9c 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -19,6 +19,7 @@ config CXL
 	select CXL_BASE
 	select CXL_AFU_DRIVER_OPS
 	select CXL_LIB
+	select SIMPLEFS
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index b493de962153..0b8f8de7475a 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -9,6 +9,7 @@
 #include <misc/cxl.h>
 #include <linux/module.h>
 #include <linux/mount.h>
+#include <linux/simplefs.h>
 #include <linux/pseudo_fs.h>
 #include <linux/sched/mm.h>
 #include <linux/mmu_context.h>
diff --git a/drivers/misc/ocxl/Kconfig b/drivers/misc/ocxl/Kconfig
index 2d2266c1439e..ddd9245fff3d 100644
--- a/drivers/misc/ocxl/Kconfig
+++ b/drivers/misc/ocxl/Kconfig
@@ -12,6 +12,7 @@ config OCXL
 	depends on PPC_POWERNV && PCI && EEH
 	select OCXL_BASE
 	select HOTPLUG_PCI_POWERNV
+	select SIMPLEFS
 	default m
 	help
 	  Select this option to enable the ocxl driver for Open
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 7018cd802569..429f55651090 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -12,6 +12,7 @@
 #include <linux/idr.h>
 #include <linux/module.h>
 #include <linux/mount.h>
+#include <linux/simplefs.h>
 #include <linux/pseudo_fs.h>
 #include <linux/poll.h>
 #include <linux/sched/signal.h>
diff --git a/fs/Kconfig b/fs/Kconfig
index f08fbbfafd9a..a6795ae312a2 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -218,6 +218,9 @@ config HUGETLB_PAGE
 config MEMFD_CREATE
 	def_bool TMPFS || HUGETLBFS
 
+config SIMPLEFS
+	bool
+
 config ARCH_HAS_GIGANTIC_PAGE
 	bool
 
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 62dc4f577ba1..af7b765de4d3 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -176,6 +176,7 @@ config BINFMT_EM86
 
 config BINFMT_MISC
 	tristate "Kernel support for MISC binaries"
+	select SIMPLEFS
 	---help---
 	  If you say Y here, it will be possible to plug wrapper-driven binary
 	  formats into the kernel. You will like this especially when you use
diff --git a/fs/Makefile b/fs/Makefile
index 2ce5112b02c8..c5c665984b9e 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_PROC_FS) += proc_namespace.o
 obj-y				+= notify/
 obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-y				+= anon_inodes.o
+obj-$(CONFIG_SIMPLEFS)		+= simplefs.o
 obj-$(CONFIG_SIGNALFD)		+= signalfd.o
 obj-$(CONFIG_TIMERFD)		+= timerfd.o
 obj-$(CONFIG_EVENTFD)		+= eventfd.o
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index cdb45829354d..c764110f5f0b 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -25,7 +25,7 @@
 #include <linux/mount.h>
 #include <linux/fs_context.h>
 #include <linux/syscalls.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/uaccess.h>
 
 #include "internal.h"
diff --git a/fs/configfs/Kconfig b/fs/configfs/Kconfig
index 272b64456999..3b461e4e3989 100644
--- a/fs/configfs/Kconfig
+++ b/fs/configfs/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config CONFIGFS_FS
 	tristate "Userspace-driven configuration filesystem"
+	select SIMPLEFS
 	select SYSFS
 	help
 	  configfs is a RAM-based filesystem that provides the converse
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index 0c6e8cf61953..331c2f064f02 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -10,7 +10,7 @@
  * configfs Copyright (C) 2005 Oracle.  All rights reserved.
  */
 
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/fs_context.h>
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index b7f2e971ecbc..7b9fddced48f 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -13,7 +13,7 @@
 #define pr_fmt(fmt)	"debugfs: " fmt
 
 #include <linux/module.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
diff --git a/fs/libfs.c b/fs/libfs.c
index 3759fbacf522..26ec729f7bcd 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -11,6 +11,7 @@
 #include <linux/cred.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
+#include <linux/simplefs.h>
 #include <linux/quotaops.h>
 #include <linux/mutex.h>
 #include <linux/namei.h>
@@ -663,41 +664,6 @@ int simple_fill_super(struct super_block *s, unsigned long magic,
 }
 EXPORT_SYMBOL(simple_fill_super);
 
-static DEFINE_SPINLOCK(pin_fs_lock);
-
-int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
-{
-	struct vfsmount *mnt = NULL;
-	spin_lock(&pin_fs_lock);
-	if (unlikely(!*mount)) {
-		spin_unlock(&pin_fs_lock);
-		mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
-		if (IS_ERR(mnt))
-			return PTR_ERR(mnt);
-		spin_lock(&pin_fs_lock);
-		if (!*mount)
-			*mount = mnt;
-	}
-	mntget(*mount);
-	++*count;
-	spin_unlock(&pin_fs_lock);
-	mntput(mnt);
-	return 0;
-}
-EXPORT_SYMBOL(simple_pin_fs);
-
-void simple_release_fs(struct vfsmount **mount, int *count)
-{
-	struct vfsmount *mnt;
-	spin_lock(&pin_fs_lock);
-	mnt = *mount;
-	if (!--*count)
-		*mount = NULL;
-	spin_unlock(&pin_fs_lock);
-	mntput(mnt);
-}
-EXPORT_SYMBOL(simple_release_fs);
-
 /**
  * simple_read_from_buffer - copy data from the buffer to user space
  * @to: the user space buffer to read to
diff --git a/fs/simplefs.c b/fs/simplefs.c
new file mode 100644
index 000000000000..226d18963801
--- /dev/null
+++ b/fs/simplefs.c
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/simplefs.h>
+#include <linux/mount.h>
+
+static DEFINE_SPINLOCK(pin_fs_lock);
+
+int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count)
+{
+	struct vfsmount *mnt = NULL;
+	spin_lock(&pin_fs_lock);
+	if (unlikely(!*mount)) {
+		spin_unlock(&pin_fs_lock);
+		mnt = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
+		if (IS_ERR(mnt))
+			return PTR_ERR(mnt);
+		spin_lock(&pin_fs_lock);
+		if (!*mount)
+			*mount = mnt;
+	}
+	mntget(*mount);
+	++*count;
+	spin_unlock(&pin_fs_lock);
+	mntput(mnt);
+	return 0;
+}
+EXPORT_SYMBOL(simple_pin_fs);
+
+void simple_release_fs(struct vfsmount **mount, int *count)
+{
+	struct vfsmount *mnt;
+	spin_lock(&pin_fs_lock);
+	mnt = *mount;
+	if (!--*count)
+		*mount = NULL;
+	spin_unlock(&pin_fs_lock);
+	mntput(mnt);
+}
+EXPORT_SYMBOL(simple_release_fs);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 0ee8c6dfb036..4353ca81e1d7 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/module.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/mount.h>
 #include <linux/kobject.h>
 #include <linux/namei.h>
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4f6f59b4f22a..55b679b89c8a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3363,8 +3363,6 @@ struct tree_descr { const char *name; const struct file_operations *ops; int mod
 struct dentry *d_alloc_name(struct dentry *, const char *);
 extern int simple_fill_super(struct super_block *, unsigned long,
 			     const struct tree_descr *);
-extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
-extern void simple_release_fs(struct vfsmount **mount, int *count);
 
 extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 			loff_t *ppos, const void *from, size_t available);
diff --git a/include/linux/simplefs.h b/include/linux/simplefs.h
new file mode 100644
index 000000000000..1076a44db308
--- /dev/null
+++ b/include/linux/simplefs.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SIMPLEFS_H
+#define _LINUX_SIMPLEFS_H
+
+#include <linux/fs.h>
+
+extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
+extern void simple_release_fs(struct vfsmount **mount, int *count);
+
+#endif
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index d1398cef3b18..fc38a6f0fc11 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -288,12 +288,16 @@ config STRIP_ASM_SYMS
 
 config READABLE_ASM
 	bool "Generate readable assembler code"
-	depends on DEBUG_KERNEL
-	help
-	  Disable some compiler optimizations that tend to generate human unreadable
-	  assembler output. This may make the kernel slightly slower, but it helps
-	  to keep kernel developers who have to stare a lot at assembler listings
-	  sane.
+    depends on DEBUG_KERNEL
+    help
+      Disable some compiler optimizations that tend to generate human unreadable
+      assembler output. This may make the kernel slightly slower, but it helps
+      to keep kernel developers who have to stare a lot at assembler listings
+      sane.
+	  
+config DEBUG_FS
+	bool "Debug Filesystem"
+	select SIMPLEFS
 
 config HEADERS_INSTALL
 	bool "Install uapi headers to usr/include"
diff --git a/security/Kconfig b/security/Kconfig
index cd3cc7da3a55..2c6713aa8b4f 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -39,6 +39,7 @@ config SECURITY_WRITABLE_HOOKS
 
 config SECURITYFS
 	bool "Enable the securityfs filesystem"
+	select SIMPLEFS
 	help
 	  This will build the securityfs filesystem.  It is currently used by
 	  various security modules (AppArmor, IMA, SafeSetID, TOMOYO, TPM).
diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 828bb1eb77ea..d62d3fca47f2 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -18,7 +18,7 @@
 #include <linux/namei.h>
 #include <linux/capability.h>
 #include <linux/rcupdate.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/fs_context.h>
 #include <linux/poll.h>
 #include <linux/zlib.h>
@@ -2529,6 +2529,7 @@ static int aa_mk_null_file(struct dentry *parent)
 	struct vfsmount *mount;
 	struct dentry *dentry;
 	struct inode *inode;
+	int error;
 
 	mount = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
 	if (IS_ERR(mount))
diff --git a/security/inode.c b/security/inode.c
index 6c326939750d..a9a9ee4de21d 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -12,7 +12,7 @@
 /* #define DEBUG */
 #include <linux/sysfs.h>
 #include <linux/kobject.h>
-#include <linux/fs.h>
+#include <linux/simplefs.h>
 #include <linux/fs_context.h>
 #include <linux/mount.h>
 #include <linux/pagemap.h>
-- 
2.25.2


^ permalink raw reply related

* [PATCH 1/8] apparmor: just use vfs_kern_mount to make .null
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker
In-Reply-To: <20200414124304.4470-1-eesposit@redhat.com>

aa_mk_null_file is using simple_pin_fs/simple_release_fs with local
variables as arguments, for what would amount to a simple
vfs_kern_mount/mntput pair if everything was inlined.  Just use
the normal filesystem API since the reference counting is not needed
here.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>
---
 security/apparmor/apparmorfs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
index 280741fc0f5f..828bb1eb77ea 100644
--- a/security/apparmor/apparmorfs.c
+++ b/security/apparmor/apparmorfs.c
@@ -2525,14 +2525,14 @@ struct path aa_null;
 
 static int aa_mk_null_file(struct dentry *parent)
 {
-	struct vfsmount *mount = NULL;
+	struct file_system_type *type = parent->d_sb->s_type;
+	struct vfsmount *mount;
 	struct dentry *dentry;
 	struct inode *inode;
-	int count = 0;
-	int error = simple_pin_fs(parent->d_sb->s_type, &mount, &count);
 
-	if (error)
-		return error;
+	mount = vfs_kern_mount(type, SB_KERNMOUNT, type->name, NULL);
+	if (IS_ERR(mount))
+		return PTR_ERR(mount);
 
 	inode_lock(d_inode(parent));
 	dentry = lookup_one_len(NULL_FILE_NAME, parent, strlen(NULL_FILE_NAME));
@@ -2561,7 +2561,7 @@ static int aa_mk_null_file(struct dentry *parent)
 	dput(dentry);
 out:
 	inode_unlock(d_inode(parent));
-	simple_release_fs(&mount, &count);
+	mntput(mount);
 	return error;
 }
 
-- 
2.25.2


^ permalink raw reply related

* [PATCH 0/8] Simplefs: group and simplify linux fs code
From: Emanuele Giuseppe Esposito @ 2020-04-14 12:42 UTC (permalink / raw)
  To: linux-nfs
  Cc: Song Liu, linux-usb, bpf, Rafael J. Wysocki, David Airlie,
	Heiko Carstens, Alexei Starovoitov, dri-devel, J. Bruce Fields,
	Joseph Qi, Hugh Dickins, Paul Mackerras, John Johansen, netdev,
	linux-s390, Christoph Hellwig, Andrew Donnellan,
	Emanuele Giuseppe Esposito, Matthew Garrett, linux-efi,
	Arnd Bergmann, Daniel Borkmann, Christian Borntraeger, linux-rdma,
	Mark Fasheh, Anton Vorontsov, John Fastabend, James Morris,
	Ard Biesheuvel, Jason Gunthorpe, Doug Ledford, oprofile-list,
	Yonghong Song, Ian Kent, Andrii Nakryiko, Alexey Dobriyan,
	Serge E. Hallyn, Robert Richter, Thomas Zimmermann, Vasily Gorbik,
	Tony Luck, Kees Cook, James E.J. Bottomley, autofs,
	Maarten Lankhorst, Uma Krishnan, Maxime Ripard, linux-fsdevel,
	Manoj N. Kumar, Alexander Viro, Jakub Kicinski, KP Singh,
	Trond Myklebust, Matthew R. Ochs, David S. Miller, Felipe Balbi,
	Mike Marciniszyn, Iurii Zaikin, linux-scsi, Martin K. Petersen,
	linux-mm, Greg Kroah-Hartman, Dennis Dalessandro, Miklos Szeredi,
	linux-security-module, linux-kernel, Anna Schumaker,
	Luis Chamberlain, Chuck Lever, Jeremy Kerr, Daniel Vetter,
	Colin Cross, Frederic Barrat, Paolo Bonzini, Andrew Morton,
	Mike Kravetz, linuxppc-dev, Martin KaFai Lau, ocfs2-devel,
	Joel Becker

This series of patches introduce wrappers for functions,
arguments simplification in functions calls and most importantly
groups duplicated code in a single header, simplefs, to avoid redundancy
in the linux fs, especially debugfs and tracefs.

Signed-off-by: Emanuele Giuseppe Esposito <eesposit@redhat.com>

Emanuele Giuseppe Esposito (8):
  apparmor: just use vfs_kern_mount to make .null
  fs: extract simple_pin/release_fs to separate files
  fs: wrap simple_pin_fs/simple_release_fs arguments in a struct
  fs: introduce simple_new_inode
  simplefs: add alloc_anon_inode wrapper
  simplefs: add file creation functions
  debugfs: switch to simplefs inode creation API
  tracefs: switch to simplefs inode creation API

 arch/powerpc/platforms/cell/spufs/inode.c |   4 +-
 arch/s390/hypfs/inode.c                   |   4 +-
 drivers/gpu/drm/Kconfig                   |   1 +
 drivers/gpu/drm/drm_drv.c                 |  13 +-
 drivers/infiniband/hw/qib/qib_fs.c        |   6 +-
 drivers/misc/cxl/Kconfig                  |   1 +
 drivers/misc/cxl/api.c                    |  14 +-
 drivers/misc/ibmasm/ibmasmfs.c            |   8 +-
 drivers/misc/ocxl/Kconfig                 |   1 +
 drivers/oprofile/oprofilefs.c             |   8 +-
 drivers/scsi/cxlflash/ocxl_hw.c           |  15 +-
 drivers/usb/gadget/function/f_fs.c        |   8 +-
 fs/Kconfig                                |   3 +
 fs/Kconfig.binfmt                         |   1 +
 fs/Makefile                               |   1 +
 fs/autofs/inode.c                         |   4 +-
 fs/binfmt_misc.c                          |  27 +--
 fs/configfs/Kconfig                       |   1 +
 fs/configfs/mount.c                       |  12 +-
 fs/debugfs/inode.c                        | 171 +++----------------
 fs/efivarfs/inode.c                       |   4 +-
 fs/fuse/control.c                         |   4 +-
 fs/hugetlbfs/inode.c                      |   8 +-
 fs/libfs.c                                |  48 ++----
 fs/ocfs2/dlmfs/dlmfs.c                    |   8 +-
 fs/proc/base.c                            |   4 +-
 fs/proc/proc_sysctl.c                     |   5 +-
 fs/pstore/inode.c                         |  14 +-
 fs/ramfs/inode.c                          |   4 +-
 fs/simplefs.c                             | 194 ++++++++++++++++++++++
 fs/tracefs/inode.c                        | 108 ++----------
 include/linux/fs.h                        |   3 +-
 include/linux/simplefs.h                  |  36 ++++
 ipc/mqueue.c                              |   4 +-
 kernel/bpf/inode.c                        |   7 +-
 lib/Kconfig.debug                         |  16 +-
 mm/shmem.c                                |   4 +-
 net/sunrpc/rpc_pipe.c                     |   4 +-
 security/Kconfig                          |   1 +
 security/apparmor/apparmorfs.c            |  48 +++---
 security/inode.c                          |  17 +-
 41 files changed, 385 insertions(+), 459 deletions(-)
 create mode 100644 fs/simplefs.c
 create mode 100644 include/linux/simplefs.h

-- 
2.25.2


^ permalink raw reply


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