[PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[David Miller]

When a vmalloc'd area is mmap'd into userspace, some kind of
co-ordination is necessary for this to work on platforms with cpu
D-caches which can have aliases.

Otherwise kernel side writes won't be seen properly in userspace and
vice versa.

If the kernel side mapping and the user side one have the same
alignment, modulo SHMLBA, this can work as long as VM_SHARED is
shared of VMA and for all current users this is true.  VM_SHARED
will force SHMLBA alignment of the user side mmap on platforms
with D-cache aliasing matters.

The bulk of this patch is just making it so that a specific alignment
can be passed down into __get_vm_area_node().  All existing callers
pass in '1' which preserves existing behavior.  vmalloc_user() gives
SHMLBA for the alignment.

As a side effect this should get the video media drivers and other
vmalloc_user() users into more working shape on such systems.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 mm/vmalloc.c |   48 ++++++++++++++++++++++++++----------------------
 1 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index f8189a4..be15e03 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -29,6 +29,7 @@
 #include <asm/atomic.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
+#include <asm/shmparam.h>
 
 
 /*** Page table manipulation functions ***/
@@ -1123,13 +1124,12 @@ DEFINE_RWLOCK(vmlist_lock);
 struct vm_struct *vmlist;
 
 static struct vm_struct *__get_vm_area_node(unsigned long size,
-		unsigned long flags, unsigned long start, unsigned long end,
-		int node, gfp_t gfp_mask, void *caller)
+		unsigned long align, unsigned long flags, unsigned long start,
+		unsigned long end, int node, gfp_t gfp_mask, void *caller)
 {
 	static struct vmap_area *va;
 	struct vm_struct *area;
 	struct vm_struct *tmp, **p;
-	unsigned long align = 1;
 
 	BUG_ON(in_interrupt());
 	if (flags & VM_IOREMAP) {
@@ -1187,7 +1187,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
 struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
 				unsigned long start, unsigned long end)
 {
-	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
 						__builtin_return_address(0));
 }
 EXPORT_SYMBOL_GPL(__get_vm_area);
@@ -1196,7 +1196,7 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
 				       unsigned long start, unsigned long end,
 				       void *caller)
 {
-	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
 				  caller);
 }
 
@@ -1211,22 +1211,22 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
  */
 struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
 {
-	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
 				-1, GFP_KERNEL, __builtin_return_address(0));
 }
 
 struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 				void *caller)
 {
-	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
 						-1, GFP_KERNEL, caller);
 }
 
 struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
 				   int node, gfp_t gfp_mask)
 {
-	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
-				  gfp_mask, __builtin_return_address(0));
+	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+				  node, gfp_mask, __builtin_return_address(0));
 }
 
 static struct vm_struct *find_vm_area(const void *addr)
@@ -1385,7 +1385,8 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
-static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node, void *caller)
@@ -1399,7 +1400,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	area->nr_pages = nr_pages;
 	/* Please note that the recursion is strictly bounded. */
 	if (array_size > PAGE_SIZE) {
-		pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
+		pages = __vmalloc_node(array_size, 1, gfp_mask | __GFP_ZERO,
 				PAGE_KERNEL, node, caller);
 		area->flags |= VM_VPAGES;
 	} else {
@@ -1458,6 +1459,7 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
 /**
  *	__vmalloc_node  -  allocate virtually contiguous memory
  *	@size:		allocation size
+ *	@align:		desired alignment
  *	@gfp_mask:	flags for the page level allocator
  *	@prot:		protection mask for the allocated pages
  *	@node:		node to use for allocation or -1
@@ -1467,8 +1469,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  */
-static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
-						int node, void *caller)
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
+			    int node, void *caller)
 {
 	struct vm_struct *area;
 	void *addr;
@@ -1478,8 +1481,8 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 	if (!size || (size >> PAGE_SHIFT) > num_physpages)
 		return NULL;
 
-	area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END,
-						node, gfp_mask, caller);
+	area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START,
+				  VMALLOC_END, node, gfp_mask, caller);
 
 	if (!area)
 		return NULL;
@@ -1498,7 +1501,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
 
 void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 {
-	return __vmalloc_node(size, gfp_mask, prot, -1,
+	return __vmalloc_node(size, 1, gfp_mask, prot, -1,
 				__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__vmalloc);
@@ -1514,7 +1517,7 @@ EXPORT_SYMBOL(__vmalloc);
  */
 void *vmalloc(unsigned long size)
 {
-	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
 					-1, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc);
@@ -1531,7 +1534,8 @@ void *vmalloc_user(unsigned long size)
 	struct vm_struct *area;
 	void *ret;
 
-	ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+	ret = __vmalloc_node(size, SHMLBA,
+			     GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
 			     PAGE_KERNEL, -1, __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
@@ -1554,7 +1558,7 @@ EXPORT_SYMBOL(vmalloc_user);
  */
 void *vmalloc_node(unsigned long size, int node)
 {
-	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
 					node, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_node);
@@ -1577,7 +1581,7 @@ EXPORT_SYMBOL(vmalloc_node);
 
 void *vmalloc_exec(unsigned long size)
 {
-	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
+	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
 			      -1, __builtin_return_address(0));
 }
 
@@ -1598,7 +1602,7 @@ void *vmalloc_exec(unsigned long size)
  */
 void *vmalloc_32(unsigned long size)
 {
-	return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL,
+	return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
 			      -1, __builtin_return_address(0));
 }
 EXPORT_SYMBOL(vmalloc_32);
@@ -1615,7 +1619,7 @@ void *vmalloc_32_user(unsigned long size)
 	struct vm_struct *area;
 	void *ret;
 
-	ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
+	ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
 			     -1, __builtin_return_address(0));
 	if (ret) {
 		area = find_vm_area(ret);
-- 
1.6.4.2

Re: [PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[Ingo Molnar]

( Andrew, this patch has mm/* effects - any objections? Would still like
  to get this into v2.6.32. )

* David Miller <davem@davemloft.net> wrote:

> When a vmalloc'd area is mmap'd into userspace, some kind of 
> co-ordination is necessary for this to work on platforms with cpu 
> D-caches which can have aliases.
> 
> Otherwise kernel side writes won't be seen properly in userspace and
> vice versa.
> 
> If the kernel side mapping and the user side one have the same
> alignment, modulo SHMLBA, this can work as long as VM_SHARED is
> shared of VMA and for all current users this is true.  VM_SHARED
> will force SHMLBA alignment of the user side mmap on platforms
> with D-cache aliasing matters.
> 
> The bulk of this patch is just making it so that a specific alignment
> can be passed down into __get_vm_area_node().  All existing callers
> pass in '1' which preserves existing behavior.  vmalloc_user() gives
> SHMLBA for the alignment.
> 
> As a side effect this should get the video media drivers and other
> vmalloc_user() users into more working shape on such systems.
> 
> Signed-off-by: David S. Miller <davem@davemloft.net>
> ---
>  mm/vmalloc.c |   48 ++++++++++++++++++++++++++----------------------
>  1 files changed, 26 insertions(+), 22 deletions(-)
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index f8189a4..be15e03 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -29,6 +29,7 @@
>  #include <asm/atomic.h>
>  #include <asm/uaccess.h>
>  #include <asm/tlbflush.h>
> +#include <asm/shmparam.h>
>  
>  
>  /*** Page table manipulation functions ***/
> @@ -1123,13 +1124,12 @@ DEFINE_RWLOCK(vmlist_lock);
>  struct vm_struct *vmlist;
>  
>  static struct vm_struct *__get_vm_area_node(unsigned long size,
> -		unsigned long flags, unsigned long start, unsigned long end,
> -		int node, gfp_t gfp_mask, void *caller)
> +		unsigned long align, unsigned long flags, unsigned long start,
> +		unsigned long end, int node, gfp_t gfp_mask, void *caller)
>  {
>  	static struct vmap_area *va;
>  	struct vm_struct *area;
>  	struct vm_struct *tmp, **p;
> -	unsigned long align = 1;
>  
>  	BUG_ON(in_interrupt());
>  	if (flags & VM_IOREMAP) {
> @@ -1187,7 +1187,7 @@ static struct vm_struct *__get_vm_area_node(unsigned long size,
>  struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
>  				unsigned long start, unsigned long end)
>  {
> -	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
> +	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
>  						__builtin_return_address(0));
>  }
>  EXPORT_SYMBOL_GPL(__get_vm_area);
> @@ -1196,7 +1196,7 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
>  				       unsigned long start, unsigned long end,
>  				       void *caller)
>  {
> -	return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
> +	return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
>  				  caller);
>  }
>  
> @@ -1211,22 +1211,22 @@ struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags,
>   */
>  struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
>  {
> -	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
> +	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
>  				-1, GFP_KERNEL, __builtin_return_address(0));
>  }
>  
>  struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
>  				void *caller)
>  {
> -	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
> +	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
>  						-1, GFP_KERNEL, caller);
>  }
>  
>  struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
>  				   int node, gfp_t gfp_mask)
>  {
> -	return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
> -				  gfp_mask, __builtin_return_address(0));
> +	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
> +				  node, gfp_mask, __builtin_return_address(0));
>  }
>  
>  static struct vm_struct *find_vm_area(const void *addr)
> @@ -1385,7 +1385,8 @@ void *vmap(struct page **pages, unsigned int count,
>  }
>  EXPORT_SYMBOL(vmap);
>  
> -static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
> +static void *__vmalloc_node(unsigned long size, unsigned long align,
> +			    gfp_t gfp_mask, pgprot_t prot,
>  			    int node, void *caller);
>  static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
>  				 pgprot_t prot, int node, void *caller)
> @@ -1399,7 +1400,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
>  	area->nr_pages = nr_pages;
>  	/* Please note that the recursion is strictly bounded. */
>  	if (array_size > PAGE_SIZE) {
> -		pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
> +		pages = __vmalloc_node(array_size, 1, gfp_mask | __GFP_ZERO,
>  				PAGE_KERNEL, node, caller);
>  		area->flags |= VM_VPAGES;
>  	} else {
> @@ -1458,6 +1459,7 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
>  /**
>   *	__vmalloc_node  -  allocate virtually contiguous memory
>   *	@size:		allocation size
> + *	@align:		desired alignment
>   *	@gfp_mask:	flags for the page level allocator
>   *	@prot:		protection mask for the allocated pages
>   *	@node:		node to use for allocation or -1
> @@ -1467,8 +1469,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
>   *	allocator with @gfp_mask flags.  Map them into contiguous
>   *	kernel virtual space, using a pagetable protection of @prot.
>   */
> -static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
> -						int node, void *caller)
> +static void *__vmalloc_node(unsigned long size, unsigned long align,
> +			    gfp_t gfp_mask, pgprot_t prot,
> +			    int node, void *caller)
>  {
>  	struct vm_struct *area;
>  	void *addr;
> @@ -1478,8 +1481,8 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
>  	if (!size || (size >> PAGE_SHIFT) > num_physpages)
>  		return NULL;
>  
> -	area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END,
> -						node, gfp_mask, caller);
> +	area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START,
> +				  VMALLOC_END, node, gfp_mask, caller);
>  
>  	if (!area)
>  		return NULL;
> @@ -1498,7 +1501,7 @@ static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
>  
>  void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
>  {
> -	return __vmalloc_node(size, gfp_mask, prot, -1,
> +	return __vmalloc_node(size, 1, gfp_mask, prot, -1,
>  				__builtin_return_address(0));
>  }
>  EXPORT_SYMBOL(__vmalloc);
> @@ -1514,7 +1517,7 @@ EXPORT_SYMBOL(__vmalloc);
>   */
>  void *vmalloc(unsigned long size)
>  {
> -	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
> +	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
>  					-1, __builtin_return_address(0));
>  }
>  EXPORT_SYMBOL(vmalloc);
> @@ -1531,7 +1534,8 @@ void *vmalloc_user(unsigned long size)
>  	struct vm_struct *area;
>  	void *ret;
>  
> -	ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
> +	ret = __vmalloc_node(size, SHMLBA,
> +			     GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
>  			     PAGE_KERNEL, -1, __builtin_return_address(0));
>  	if (ret) {
>  		area = find_vm_area(ret);
> @@ -1554,7 +1558,7 @@ EXPORT_SYMBOL(vmalloc_user);
>   */
>  void *vmalloc_node(unsigned long size, int node)
>  {
> -	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
> +	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
>  					node, __builtin_return_address(0));
>  }
>  EXPORT_SYMBOL(vmalloc_node);
> @@ -1577,7 +1581,7 @@ EXPORT_SYMBOL(vmalloc_node);
>  
>  void *vmalloc_exec(unsigned long size)
>  {
> -	return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
> +	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
>  			      -1, __builtin_return_address(0));
>  }
>  
> @@ -1598,7 +1602,7 @@ void *vmalloc_exec(unsigned long size)
>   */
>  void *vmalloc_32(unsigned long size)
>  {
> -	return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL,
> +	return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
>  			      -1, __builtin_return_address(0));
>  }
>  EXPORT_SYMBOL(vmalloc_32);
> @@ -1615,7 +1619,7 @@ void *vmalloc_32_user(unsigned long size)
>  	struct vm_struct *area;
>  	void *ret;
>  
> -	ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
> +	ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
>  			     -1, __builtin_return_address(0));
>  	if (ret) {
>  		area = find_vm_area(ret);
> -- 
> 1.6.4.2

Re: [PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[Andrew Morton]

On Fri, 18 Sep 2009 14:17:09 +0200 Ingo Molnar <mingo@elte.hu> wrote:

> ( Andrew, this patch has mm/* effects - any objections? Would still like
>   to get this into v2.6.32. )

I queued this a week ago, along with
perf-allocate-mmap-buffer-using-vmalloc_user.patch.

If the latter gets quitably acked I can merge it, otherwise I'll spray
it at you guys.

Merging
mm-make-vmalloc_user-align-base-kernel-virtual-address-to-shmlba.patch
via another tree will cause a teeny reject at my end, not a problem.

Re: [PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[Peter Zijlstra]

On Fri, 2009-09-18 at 10:52 -0700, Andrew Morton wrote:
> On Fri, 18 Sep 2009 14:17:09 +0200 Ingo Molnar <mingo@elte.hu> wrote:
> 
> > ( Andrew, this patch has mm/* effects - any objections? Would still like
> >   to get this into v2.6.32. )
> 
> I queued this a week ago, along with
> perf-allocate-mmap-buffer-using-vmalloc_user.patch.
> 
> If the latter gets quitably acked I can merge it, otherwise I'll spray
> it at you guys.

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>

Re: [PATCH 1/2]: mm: Make vmalloc_user() align base kernel virtual address to SHMLBA.

[Ingo Molnar]

* Andrew Morton <akpm@linux-foundation.org> wrote:

> On Fri, 18 Sep 2009 14:17:09 +0200 Ingo Molnar <mingo@elte.hu> wrote:
> 
> > ( Andrew, this patch has mm/* effects - any objections? Would still like
> >   to get this into v2.6.32. )
> 
> I queued this a week ago, along with
> perf-allocate-mmap-buffer-using-vmalloc_user.patch.
> 
> If the latter gets quitably acked I can merge it, otherwise I'll spray
> it at you guys.
> 
> Merging
> mm-make-vmalloc_user-align-base-kernel-virtual-address-to-shmlba.patch
> via another tree will cause a teeny reject at my end, not a problem.

Please dont send this one yet, the fallout is still being discussed.

	Ingo