提交 · 42bc47b35320e0e587a88e437e18f80f9c5bcbb2 · openeuler / Kernel

13 6月, 2018 3 次提交

treewide: Use array_size() in vmalloc() · 42bc47b3

由 Kees Cook 提交于 6月 12, 2018

The vmalloc() function has no 2-factor argument form, so multiplication
factors need to be wrapped in array_size(). This patch replaces cases of:

        vmalloc(a * b)

with:
        vmalloc(array_size(a, b))

as well as handling cases of:

        vmalloc(a * b * c)

with:

        vmalloc(array3_size(a, b, c))

This does, however, attempt to ignore constant size factors like:

        vmalloc(4 * 1024)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  vmalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  vmalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  vmalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  vmalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
  vmalloc(
-	sizeof(TYPE) * (COUNT_ID)
+	array_size(COUNT_ID, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * COUNT_ID
+	array_size(COUNT_ID, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * (COUNT_CONST)
+	array_size(COUNT_CONST, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * COUNT_CONST
+	array_size(COUNT_CONST, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(THING) * (COUNT_ID)
+	array_size(COUNT_ID, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * COUNT_ID
+	array_size(COUNT_ID, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * (COUNT_CONST)
+	array_size(COUNT_CONST, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * COUNT_CONST
+	array_size(COUNT_CONST, sizeof(THING))
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

  vmalloc(
-	SIZE * COUNT
+	array_size(COUNT, SIZE)
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  vmalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  vmalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  vmalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  vmalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  vmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  vmalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  vmalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  vmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  vmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  vmalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  vmalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  vmalloc(C1 * C2 * C3, ...)
|
  vmalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants.
@@
expression E1, E2;
constant C1, C2;
@@

(
  vmalloc(C1 * C2, ...)
|
  vmalloc(
-	E1 * E2
+	array_size(E1, E2)
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>

42bc47b3

treewide: kzalloc() -> kcalloc() · 6396bb22

由 Kees Cook 提交于 6月 12, 2018

The kzalloc() function has a 2-factor argument form, kcalloc(). This
patch replaces cases of:

        kzalloc(a * b, gfp)

with:
        kcalloc(a * b, gfp)

as well as handling cases of:

        kzalloc(a * b * c, gfp)

with:

        kzalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kzalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kzalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kzalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kzalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kzalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kzalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kzalloc
+ kcalloc
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kzalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kzalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kzalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kzalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kzalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kzalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kzalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kzalloc(sizeof(THING) * C2, ...)
|
  kzalloc(sizeof(TYPE) * C2, ...)
|
  kzalloc(C1 * C2 * C3, ...)
|
  kzalloc(C1 * C2, ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kzalloc
+ kcalloc
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>

6396bb22

treewide: kmalloc() -> kmalloc_array() · 6da2ec56

由 Kees Cook 提交于 6月 12, 2018

The kmalloc() function has a 2-factor argument form, kmalloc_array(). This
patch replaces cases of:

        kmalloc(a * b, gfp)

with:
        kmalloc_array(a * b, gfp)

as well as handling cases of:

        kmalloc(a * b * c, gfp)

with:

        kmalloc(array3_size(a, b, c), gfp)

as it's slightly less ugly than:

        kmalloc_array(array_size(a, b), c, gfp)

This does, however, attempt to ignore constant size factors like:

        kmalloc(4 * 1024, gfp)

though any constants defined via macros get caught up in the conversion.

Any factors with a sizeof() of "unsigned char", "char", and "u8" were
dropped, since they're redundant.

The tools/ directory was manually excluded, since it has its own
implementation of kmalloc().

The Coccinelle script used for this was:

// Fix redundant parens around sizeof().
@@
type TYPE;
expression THING, E;
@@

(
  kmalloc(
-	(sizeof(TYPE)) * E
+	sizeof(TYPE) * E
  , ...)
|
  kmalloc(
-	(sizeof(THING)) * E
+	sizeof(THING) * E
  , ...)
)

// Drop single-byte sizes and redundant parens.
@@
expression COUNT;
typedef u8;
typedef __u8;
@@

(
  kmalloc(
-	sizeof(u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * (COUNT)
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(__u8) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(char) * COUNT
+	COUNT
  , ...)
|
  kmalloc(
-	sizeof(unsigned char) * COUNT
+	COUNT
  , ...)
)

// 2-factor product with sizeof(type/expression) and identifier or constant.
@@
type TYPE;
expression THING;
identifier COUNT_ID;
constant COUNT_CONST;
@@

(
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_ID)
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_ID
+	COUNT_ID, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (COUNT_CONST)
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * COUNT_CONST
+	COUNT_CONST, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_ID)
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_ID
+	COUNT_ID, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (COUNT_CONST)
+	COUNT_CONST, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * COUNT_CONST
+	COUNT_CONST, sizeof(THING)
  , ...)
)

// 2-factor product, only identifiers.
@@
identifier SIZE, COUNT;
@@

- kmalloc
+ kmalloc_array
  (
-	SIZE * COUNT
+	COUNT, SIZE
  , ...)

// 3-factor product with 1 sizeof(type) or sizeof(expression), with
// redundant parens removed.
@@
expression THING;
identifier STRIDE, COUNT;
type TYPE;
@@

(
  kmalloc(
-	sizeof(TYPE) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(TYPE) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(TYPE))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * (COUNT) * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * (STRIDE)
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
|
  kmalloc(
-	sizeof(THING) * COUNT * STRIDE
+	array3_size(COUNT, STRIDE, sizeof(THING))
  , ...)
)

// 3-factor product with 2 sizeof(variable), with redundant parens removed.
@@
expression THING1, THING2;
identifier COUNT;
type TYPE1, TYPE2;
@@

(
  kmalloc(
-	sizeof(TYPE1) * sizeof(TYPE2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(THING1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(THING1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * COUNT
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
|
  kmalloc(
-	sizeof(TYPE1) * sizeof(THING2) * (COUNT)
+	array3_size(COUNT, sizeof(TYPE1), sizeof(THING2))
  , ...)
)

// 3-factor product, only identifiers, with redundant parens removed.
@@
identifier STRIDE, SIZE, COUNT;
@@

(
  kmalloc(
-	(COUNT) * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * STRIDE * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	(COUNT) * (STRIDE) * (SIZE)
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
|
  kmalloc(
-	COUNT * STRIDE * SIZE
+	array3_size(COUNT, STRIDE, SIZE)
  , ...)
)

// Any remaining multi-factor products, first at least 3-factor products,
// when they're not all constants...
@@
expression E1, E2, E3;
constant C1, C2, C3;
@@

(
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(
-	(E1) * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * E3
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	(E1) * (E2) * (E3)
+	array3_size(E1, E2, E3)
  , ...)
|
  kmalloc(
-	E1 * E2 * E3
+	array3_size(E1, E2, E3)
  , ...)
)

// And then all remaining 2 factors products when they're not all constants,
// keeping sizeof() as the second factor argument.
@@
expression THING, E1, E2;
type TYPE;
constant C1, C2, C3;
@@

(
  kmalloc(sizeof(THING) * C2, ...)
|
  kmalloc(sizeof(TYPE) * C2, ...)
|
  kmalloc(C1 * C2 * C3, ...)
|
  kmalloc(C1 * C2, ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * (E2)
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(TYPE) * E2
+	E2, sizeof(TYPE)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * (E2)
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	sizeof(THING) * E2
+	E2, sizeof(THING)
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * E2
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	(E1) * (E2)
+	E1, E2
  , ...)
|
- kmalloc
+ kmalloc_array
  (
-	E1 * E2
+	E1, E2
  , ...)
)
Signed-off-by: NKees Cook <keescook@chromium.org>

6da2ec56

08 6月, 2018 1 次提交

mm: introduce ARCH_HAS_PTE_SPECIAL · 3010a5ea

由 Laurent Dufour 提交于 6月 07, 2018

Currently the PTE special supports is turned on in per architecture
header files.  Most of the time, it is defined in
arch/*/include/asm/pgtable.h depending or not on some other per
architecture static definition.

This patch introduce a new configuration variable to manage this
directly in the Kconfig files.  It would later replace
__HAVE_ARCH_PTE_SPECIAL.

Here notes for some architecture where the definition of
__HAVE_ARCH_PTE_SPECIAL is not obvious:

arm
 __HAVE_ARCH_PTE_SPECIAL which is currently defined in
arch/arm/include/asm/pgtable-3level.h which is included by
arch/arm/include/asm/pgtable.h when CONFIG_ARM_LPAE is set.
So select ARCH_HAS_PTE_SPECIAL if ARM_LPAE.

powerpc
__HAVE_ARCH_PTE_SPECIAL is defined in 2 files:
 - arch/powerpc/include/asm/book3s/64/pgtable.h
 - arch/powerpc/include/asm/pte-common.h
The first one is included if (PPC_BOOK3S & PPC64) while the second is
included in all the other cases.
So select ARCH_HAS_PTE_SPECIAL all the time.

sparc:
__HAVE_ARCH_PTE_SPECIAL is defined if defined(__sparc__) &&
defined(__arch64__) which are defined through the compiler in
sparc/Makefile if !SPARC32 which I assume to be if SPARC64.
So select ARCH_HAS_PTE_SPECIAL if SPARC64

There is no functional change introduced by this patch.

Link: http://lkml.kernel.org/r/1523433816-14460-2-git-send-email-ldufour@linux.vnet.ibm.comSigned-off-by: NLaurent Dufour <ldufour@linux.vnet.ibm.com>
Suggested-by: NJerome Glisse <jglisse@redhat.com>
Reviewed-by: NJerome Glisse <jglisse@redhat.com>
Acked-by: NDavid Rientjes <rientjes@google.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: "Aneesh Kumar K . V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Albert Ou <albert@sifive.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Christophe LEROY <christophe.leroy@c-s.fr>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

3010a5ea

06 6月, 2018 4 次提交

powerpc: Wire up restartable sequences system call · bb862b02

由 Boqun Feng 提交于 6月 02, 2018

Wire up the rseq system call on powerpc.

This provides an ABI improving the speed of a user-space getcpu
operation on powerpc by skipping the getcpu system call on the fast
path, as well as improving the speed of user-space operations on per-cpu
data compared to using load-reservation/store-conditional atomics.
Signed-off-by: NBoqun Feng <boqun.feng@gmail.com>
Signed-off-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180602124408.8430-11-mathieu.desnoyers@efficios.com

bb862b02

powerpc: Add syscall detection for restartable sequences · 6f37be4b

由 Boqun Feng 提交于 6月 02, 2018

Syscalls are not allowed inside restartable sequences, so add a call to
rseq_syscall() at the very beginning of system call exiting path for
CONFIG_DEBUG_RSEQ=y kernel. This could help us to detect whether there
is a syscall issued inside restartable sequences.
Signed-off-by: NBoqun Feng <boqun.feng@gmail.com>
Signed-off-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180602124408.8430-10-mathieu.desnoyers@efficios.com

6f37be4b

powerpc: Add support for restartable sequences · 8a417c48

由 Boqun Feng 提交于 6月 02, 2018

Call the rseq_handle_notify_resume() function on return to userspace if
TIF_NOTIFY_RESUME thread flag is set.

Perform fixup on the pre-signal when a signal is delivered on top of a
restartable sequence critical section.
Signed-off-by: NBoqun Feng <boqun.feng@gmail.com>
Signed-off-by: NMathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Cc: Joel Fernandes <joelaf@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Watson <davejwatson@fb.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: Chris Lameter <cl@linux.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Andrew Hunter <ahh@google.com>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: "Paul E . McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Ben Maurer <bmaurer@fb.com>
Cc: linux-api@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180602124408.8430-9-mathieu.desnoyers@efficios.com

8a417c48

powerpc/64s/radix: Fix missing ptesync in flush_cache_vmap · ff5bc793

由 Nicholas Piggin 提交于 6月 06, 2018

There is a typo in f1cb8f9b ("powerpc/64s/radix: avoid ptesync after
set_pte and ptep_set_access_flags") config ifdef, which results in the
necessary ptesync not being issued after vmalloc.

This causes random kernel faults in module load, bpf load, anywhere
that vmalloc mappings are used.

After correcting the code, this survives a guest kernel booting
hundreds of times where previously there would be a crash every few
boots (I haven't noticed the crash on host, perhaps due to different
TLB and page table walking behaviour in hardware).

A memory clobber is also added to the flush, just to be sure it won't
be reordered with the pte set or the subsequent mapping access.

Fixes: f1cb8f9b ("powerpc/64s/radix: avoid ptesync after set_pte and ptep_set_access_flags")
Signed-off-by: NNicholas Piggin <npiggin@gmail.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

ff5bc793

05 6月, 2018 4 次提交

powerpc: fix build failure by disabling attribute-alias warning in pci_32 · 41552037

由 Christophe Leroy 提交于 6月 05, 2018

Commit 2479bfc9 ("powerpc: Fix build by disabling attribute-alias
warning for SYSCALL_DEFINEx") forgot arch/powerpc/kernel/pci_32.c

Latest GCC version emit the following warnings

As arch/powerpc code is built with -Werror, this breaks build with
GCC 8.1

This patch inhibits this warning

In file included from arch/powerpc/kernel/pci_32.c:14:
./include/linux/syscalls.h:233:18: error: 'sys_pciconfig_iobase' alias between functions of incompatible types 'long int(long int,  long unsigned int,  long unsigned int)' and 'long int(long int,  long int,  long int)' [-Werror=attribute-alias]
  asmlinkage long sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) \
                  ^~~
./include/linux/syscalls.h:222:2: note: in expansion of macro '__SYSCALL_DEFINEx'
  __SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
  ^~~~~~~~~~~~~~~~~
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

41552037

powerpc-opal: fix spelling mistake "Uniterrupted" -> "Uninterrupted" · b0c4acb1

由 Colin Ian King 提交于 5月 26, 2018

Trivial fix to spelling mistake in hmi_error_types text
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Reviewed-by: NStewart Smith <stewart@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

b0c4acb1

powerpc: fix spelling mistake: "Usupported" -> "Unsupported" · e6536a9f

由 Colin Ian King 提交于 3月 30, 2018

Trivial fix to spelling mistake in bootx_printf message text
Signed-off-by: NColin Ian King <colin.king@canonical.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

e6536a9f

powerpc/pkeys: Detach execute_only key on !PROT_EXEC · eabdb8ca

由 Ram Pai 提交于 5月 04, 2018

Disassociate the exec_key from a VMA if the VMA permission is not
PROT_EXEC anymore. Otherwise the exec_only key continues to be
associated with the vma, causing unexpected behavior.

The problem was reported on x86 by Shakeel Butt, which is also
applicable on powerpc.

Fixes: 5586cf61 ("powerpc: introduce execute-only pkey")
Cc: stable@vger.kernel.org # v4.16+
Reported-by: NShakeel Butt <shakeelb@google.com>
Signed-off-by: NRam Pai <linuxram@us.ibm.com>
Reviewed-by: NThiago Jung Bauermann <bauerman@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

eabdb8ca

04 6月, 2018 1 次提交

powerpc/powernv: copy/paste - Mask SO bit in CR · 75743649

由 Haren Myneni 提交于 6月 04, 2018

NX can set the 3rd bit in CR register for XER[SO] (Summary overflow)
which is not related to paste request. The current paste function
returns failure for a successful request when this bit is set. So mask
this bit and check the proper return status.

Fixes: 2392c8c8 ("powerpc/powernv/vas: Define copy/paste interfaces")
Cc: stable@vger.kernel.org # v4.14+
Signed-off-by: NHaren Myneni <haren@us.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

75743649

03 6月, 2018 27 次提交

powerpc: Remove core support for Marvell mv64x60 hostbridges · 04debf21

由 Mark Greer 提交于 4月 05, 2018

There are no longer any platforms that use Marvell's mv64x60
hostbridges so remove the supporting kernel code.

CC: Dale Farnsworth <dale@farnsworth.org>
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

04debf21

powerpc/boot: Remove core support for Marvell mv64x60 hostbridges · 297f8314

由 Mark Greer 提交于 4月 05, 2018

There are no longer any platforms that use Marvell's mv64x60
hostbridges so remove the supporting boot code.
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

297f8314

powerpc/boot: Remove support for Marvell mv64x60 i2c controller · 6bf17a83

由 Mark Greer 提交于 4月 05, 2018

There are no longer any platforms that use Marvell's mv64x60's i2c
controller so remove its driver.
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Acked-by: NDale Farnsworth <dale@farnsworth.org>
Signed-off-by: Mark Greer &lt;<a href="mailto:mgreer@animalcreek.com">mgreer@animalcreek.com</a>&gt;<br>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

6bf17a83

powerpc/boot: Remove support for Marvell MPSC serial controller · 30f4bbe0

由 Mark Greer 提交于 4月 05, 2018

There are no longer any platforms that use Marvell's MPSC serial
controller so remove its driver.
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

30f4bbe0

powerpc/embedded6xx: Remove C2K board support · 92c8c16f

由 Mark Greer 提交于 4月 05, 2018

The C2K platform appears to be orphaned so remove code supporting it.

CC: Remi Machet <rmachet@nvidia.com>
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Acked-by: NRemi Machet <remi@machet.us>
Signed-off-by: NMark Greer <mgreer@animalcreek.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

92c8c16f

powerpc/lib: optimise PPC32 memcmp · 2676b89e

由 Christophe Leroy 提交于 5月 30, 2018

At the time being, memcmp() compares two chunks of memory
byte per byte.

This patch optimises the comparison by comparing word by word.

On the same way as commit 15c2d45d ("powerpc: Add 64bit
optimised memcmp"), this patch moves memcmp() into a dedicated
file named memcmp_32.S

A small benchmark performed on an 8xx comparing two chuncks
of 512 bytes performed 100000 times gives:

Before : 5852274 TB ticks
After:   1488638 TB ticks

This is almost 4 times faster
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

2676b89e

powerpc/lib: optimise 32 bits __clear_user() · f36bbf21

由 Christophe Leroy 提交于 5月 30, 2018

Rewrite clear_user() on the same principle as memset(0), making use
of dcbz to clear complete cache lines.

This code is a copy/paste of memset(), with some modifications
in order to retrieve remaining number of bytes to be cleared,
as it needs to be returned in case of error.

On the same way as done on PPC64 in commit 17968fbb
("powerpc: 64bit optimised __clear_user"), the patch moves
__clear_user() into a dedicated file string_32.S

On a MPC885, throughput is almost doubled:

Before:
~# dd if=/dev/zero of=/dev/null bs=1M count=1000
1048576000 bytes (1000.0MB) copied, 18.990779 seconds, 52.7MB/s

After:
~# dd if=/dev/zero of=/dev/null bs=1M count=1000
1048576000 bytes (1000.0MB) copied, 9.611468 seconds, 104.0MB/s

On a MPC8321, throughput is multiplied by 2.12:

Before:
root@vgoippro:~# dd if=/dev/zero of=/dev/null bs=1M count=1000
1048576000 bytes (1000.0MB) copied, 6.844352 seconds, 146.1MB/s

After:
root@vgoippro:~# dd if=/dev/zero of=/dev/null bs=1M count=1000
1048576000 bytes (1000.0MB) copied, 3.218854 seconds, 310.7MB/s
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

f36bbf21

powerpc/time: inline arch_vtime_task_switch() · 60f1d289

由 Christophe Leroy 提交于 5月 29, 2018

arch_vtime_task_switch() is a small function which is called
only from vtime_common_task_switch(), so it is worth inlining
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

60f1d289

powerpc/Makefile: set -mcpu=860 flag for the 8xx · 1c389763

由 Christophe Leroy 提交于 5月 28, 2018

When compiled with GCC 8.1, vmlinux is significantly bigger than
with GCC 4.8.

When looking at the generated code with objdump, we notice that
all functions and loops when a 16 bytes alignment. This significantly
increases the size of the kernel. It is pointless and even
counterproductive as on the 8xx 'nop' also consumes one clock cycle.

Size of vmlinux with GCC 4.8:
   text	   data	    bss	    dec	    hex	filename
5801948	1626076	 457796	7885820	 7853fc	vmlinux

Size of vmlinux with GCC 8.1:
   text	   data	    bss	    dec	    hex	filename
6764592	1630652	 456476	8851720	 871108	vmlinux

Size of vmlinux with GCC 8.1 and this patch:
   text	   data	    bss	    dec	    hex	filename
6331544	1631756	 456476	8419776	 8079c0	vmlinux
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

1c389763

powerpc: Implement csum_ipv6_magic in assembly · e9c4943a

由 Christophe Leroy 提交于 5月 24, 2018

The generic csum_ipv6_magic() generates a pretty bad result

00000000 <csum_ipv6_magic>: (PPC32)
   0:	81 23 00 00 	lwz     r9,0(r3)
   4:	81 03 00 04 	lwz     r8,4(r3)
   8:	7c e7 4a 14 	add     r7,r7,r9
   c:	7d 29 38 10 	subfc   r9,r9,r7
  10:	7d 4a 51 10 	subfe   r10,r10,r10
  14:	7d 27 42 14 	add     r9,r7,r8
  18:	7d 2a 48 50 	subf    r9,r10,r9
  1c:	80 e3 00 08 	lwz     r7,8(r3)
  20:	7d 08 48 10 	subfc   r8,r8,r9
  24:	7d 4a 51 10 	subfe   r10,r10,r10
  28:	7d 29 3a 14 	add     r9,r9,r7
  2c:	81 03 00 0c 	lwz     r8,12(r3)
  30:	7d 2a 48 50 	subf    r9,r10,r9
  34:	7c e7 48 10 	subfc   r7,r7,r9
  38:	7d 4a 51 10 	subfe   r10,r10,r10
  3c:	7d 29 42 14 	add     r9,r9,r8
  40:	7d 2a 48 50 	subf    r9,r10,r9
  44:	80 e4 00 00 	lwz     r7,0(r4)
  48:	7d 08 48 10 	subfc   r8,r8,r9
  4c:	7d 4a 51 10 	subfe   r10,r10,r10
  50:	7d 29 3a 14 	add     r9,r9,r7
  54:	7d 2a 48 50 	subf    r9,r10,r9
  58:	81 04 00 04 	lwz     r8,4(r4)
  5c:	7c e7 48 10 	subfc   r7,r7,r9
  60:	7d 4a 51 10 	subfe   r10,r10,r10
  64:	7d 29 42 14 	add     r9,r9,r8
  68:	7d 2a 48 50 	subf    r9,r10,r9
  6c:	80 e4 00 08 	lwz     r7,8(r4)
  70:	7d 08 48 10 	subfc   r8,r8,r9
  74:	7d 4a 51 10 	subfe   r10,r10,r10
  78:	7d 29 3a 14 	add     r9,r9,r7
  7c:	7d 2a 48 50 	subf    r9,r10,r9
  80:	81 04 00 0c 	lwz     r8,12(r4)
  84:	7c e7 48 10 	subfc   r7,r7,r9
  88:	7d 4a 51 10 	subfe   r10,r10,r10
  8c:	7d 29 42 14 	add     r9,r9,r8
  90:	7d 2a 48 50 	subf    r9,r10,r9
  94:	7d 08 48 10 	subfc   r8,r8,r9
  98:	7d 4a 51 10 	subfe   r10,r10,r10
  9c:	7d 29 2a 14 	add     r9,r9,r5
  a0:	7d 2a 48 50 	subf    r9,r10,r9
  a4:	7c a5 48 10 	subfc   r5,r5,r9
  a8:	7c 63 19 10 	subfe   r3,r3,r3
  ac:	7d 29 32 14 	add     r9,r9,r6
  b0:	7d 23 48 50 	subf    r9,r3,r9
  b4:	7c c6 48 10 	subfc   r6,r6,r9
  b8:	7c 63 19 10 	subfe   r3,r3,r3
  bc:	7c 63 48 50 	subf    r3,r3,r9
  c0:	54 6a 80 3e 	rotlwi  r10,r3,16
  c4:	7c 63 52 14 	add     r3,r3,r10
  c8:	7c 63 18 f8 	not     r3,r3
  cc:	54 63 84 3e 	rlwinm  r3,r3,16,16,31
  d0:	4e 80 00 20 	blr

0000000000000000 <.csum_ipv6_magic>: (PPC64)
   0:	81 23 00 00 	lwz     r9,0(r3)
   4:	80 03 00 04 	lwz     r0,4(r3)
   8:	81 63 00 08 	lwz     r11,8(r3)
   c:	7c e7 4a 14 	add     r7,r7,r9
  10:	7f 89 38 40 	cmplw   cr7,r9,r7
  14:	7d 47 02 14 	add     r10,r7,r0
  18:	7d 30 10 26 	mfocrf  r9,1
  1c:	55 29 f7 fe 	rlwinm  r9,r9,30,31,31
  20:	7d 4a 4a 14 	add     r10,r10,r9
  24:	7f 80 50 40 	cmplw   cr7,r0,r10
  28:	7d 2a 5a 14 	add     r9,r10,r11
  2c:	80 03 00 0c 	lwz     r0,12(r3)
  30:	81 44 00 00 	lwz     r10,0(r4)
  34:	7d 10 10 26 	mfocrf  r8,1
  38:	55 08 f7 fe 	rlwinm  r8,r8,30,31,31
  3c:	7d 29 42 14 	add     r9,r9,r8
  40:	81 04 00 04 	lwz     r8,4(r4)
  44:	7f 8b 48 40 	cmplw   cr7,r11,r9
  48:	7d 29 02 14 	add     r9,r9,r0
  4c:	7d 70 10 26 	mfocrf  r11,1
  50:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  54:	7d 29 5a 14 	add     r9,r9,r11
  58:	7f 80 48 40 	cmplw   cr7,r0,r9
  5c:	7d 29 52 14 	add     r9,r9,r10
  60:	7c 10 10 26 	mfocrf  r0,1
  64:	54 00 f7 fe 	rlwinm  r0,r0,30,31,31
  68:	7d 69 02 14 	add     r11,r9,r0
  6c:	7f 8a 58 40 	cmplw   cr7,r10,r11
  70:	7c 0b 42 14 	add     r0,r11,r8
  74:	81 44 00 08 	lwz     r10,8(r4)
  78:	7c f0 10 26 	mfocrf  r7,1
  7c:	54 e7 f7 fe 	rlwinm  r7,r7,30,31,31
  80:	7c 00 3a 14 	add     r0,r0,r7
  84:	7f 88 00 40 	cmplw   cr7,r8,r0
  88:	7d 20 52 14 	add     r9,r0,r10
  8c:	80 04 00 0c 	lwz     r0,12(r4)
  90:	7d 70 10 26 	mfocrf  r11,1
  94:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  98:	7d 29 5a 14 	add     r9,r9,r11
  9c:	7f 8a 48 40 	cmplw   cr7,r10,r9
  a0:	7d 29 02 14 	add     r9,r9,r0
  a4:	7d 70 10 26 	mfocrf  r11,1
  a8:	55 6b f7 fe 	rlwinm  r11,r11,30,31,31
  ac:	7d 29 5a 14 	add     r9,r9,r11
  b0:	7f 80 48 40 	cmplw   cr7,r0,r9
  b4:	7d 29 2a 14 	add     r9,r9,r5
  b8:	7c 10 10 26 	mfocrf  r0,1
  bc:	54 00 f7 fe 	rlwinm  r0,r0,30,31,31
  c0:	7d 29 02 14 	add     r9,r9,r0
  c4:	7f 85 48 40 	cmplw   cr7,r5,r9
  c8:	7c 09 32 14 	add     r0,r9,r6
  cc:	7d 50 10 26 	mfocrf  r10,1
  d0:	55 4a f7 fe 	rlwinm  r10,r10,30,31,31
  d4:	7c 00 52 14 	add     r0,r0,r10
  d8:	7f 80 30 40 	cmplw   cr7,r0,r6
  dc:	7d 30 10 26 	mfocrf  r9,1
  e0:	55 29 ef fe 	rlwinm  r9,r9,29,31,31
  e4:	7c 09 02 14 	add     r0,r9,r0
  e8:	54 03 80 3e 	rotlwi  r3,r0,16
  ec:	7c 03 02 14 	add     r0,r3,r0
  f0:	7c 03 00 f8 	not     r3,r0
  f4:	78 63 84 22 	rldicl  r3,r3,48,48
  f8:	4e 80 00 20 	blr

This patch implements it in assembly for both PPC32 and PPC64

Link: https://github.com/linuxppc/linux/issues/9Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: NSegher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

e9c4943a

powerpc/32: Optimise __csum_partial() · 373e098e

由 Christophe Leroy 提交于 5月 24, 2018

Improve __csum_partial by interleaving loads and adds.

On a 8xx, it brings neither improvement nor degradation.
On a 83xx, it brings a 25% improvement.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: NSegher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

373e098e

powerpc/lib: Adjust .balign inside string functions for PPC32 · 1128bb78

由 Christophe Leroy 提交于 5月 18, 2018

commit 87a156fb ("Align hot loops of some string functions")
degraded the performance of string functions by adding useless
nops

A simple benchmark on an 8xx calling 100000x a memchr() that
matches the first byte runs in 41668 TB ticks before this patch
and in 35986 TB ticks after this patch. So this gives an
improvement of approx 10%

Another benchmark doing the same with a memchr() matching the 128th
byte runs in 1011365 TB ticks before this patch and 1005682 TB ticks
after this patch, so regardless on the number of loops, removing
those useless nops improves the test by 5683 TB ticks.

Fixes: 87a156fb ("Align hot loops of some string functions")
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

1128bb78

powerpc/signal32: Use fault_in_pages_readable() to prefault user context · 56b04d56

由 Christophe Leroy 提交于 4月 24, 2018

Use fault_in_pages_readable() to prefault user context
instead of open coding
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: NMathieu Malaterre <malat@debian.org>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

56b04d56

powerpc/8xx: Remove RTC clock on 88x · d04f11d2

由 Christophe Leroy 提交于 4月 17, 2018

The 885 familly processors don't have the Real Time Clock
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

d04f11d2

powerpc/boot: remove unused variable in mpc8xx · 169f438a

由 Christophe Leroy 提交于 4月 17, 2018

Variable div is set but never used. Remove it.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

169f438a

powerpc/misc: merge reloc_offset() and add_reloc_offset() · 0cc377d1

由 Christophe Leroy 提交于 4月 17, 2018

reloc_offset() is the same as add_reloc_offset(0)
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

0cc377d1

powerpc/64: optimises from64to32() · 55a0edf0

由 Christophe Leroy 提交于 4月 10, 2018

The current implementation of from64to32() gives a poor result:

0000000000000270 <.from64to32>:
 270:	38 00 ff ff 	li      r0,-1
 274:	78 69 00 22 	rldicl  r9,r3,32,32
 278:	78 00 00 20 	clrldi  r0,r0,32
 27c:	7c 60 00 38 	and     r0,r3,r0
 280:	7c 09 02 14 	add     r0,r9,r0
 284:	78 09 00 22 	rldicl  r9,r0,32,32
 288:	7c 00 4a 14 	add     r0,r0,r9
 28c:	78 03 00 20 	clrldi  r3,r0,32
 290:	4e 80 00 20 	blr

This patch modifies from64to32() to operate in the same
spirit as csum_fold()

It swaps the two 32-bit halves of sum then it adds it with the
unswapped sum. If there is a carry from adding the two 32-bit halves,
it will carry from the lower half into the upper half, giving us the
correct sum in the upper half.

The resulting code is:

0000000000000260 <.from64to32>:
 260:	78 60 00 02 	rotldi  r0,r3,32
 264:	7c 60 1a 14 	add     r3,r0,r3
 268:	78 63 00 22 	rldicl  r3,r3,32,32
 26c:	4e 80 00 20 	blr
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

55a0edf0

powerpc/mm: Remove stale_map[] handling on non SMP processors · c865c955

由 Christophe Leroy 提交于 3月 21, 2018

stale_map[] bits are only set in steal_context_smp() so
on UP processors this map is useless. Only manage it for SMP
processors.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

c865c955

powerpc/mm: constify LAST_CONTEXT in mmu_context_nohash · 9e4f02e2

由 Christophe Leroy 提交于 3月 21, 2018

last_context is 16 on the 8xx, 65535 on the 47x and 255 on other ones.

The kernel is exclusively built for the 8xx, for the 47x or for
another processor so the last context can be defined as a constant
depending on the processor.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
[mpe: Reformat old comment]
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

9e4f02e2

powerpc/mm: Avoid unnecessary test and reduce code size · 48bdcace

由 Christophe Leroy 提交于 3月 21, 2018

no_selective_tlbil hence the use of either steal_all_contexts()
or steal_context_up() depends on the subarch, it won't change
during run. Only the 8xx uses steal_all_contexts and CONFIG_PPC_8xx
is exclusive of other processors.

This patch replaces the test of no_selective_tlbil global var by
a test of CONFIG_PPC_8xx selection. It avoids the test and
removes unnecessary code.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

48bdcace

powerpc/mm: constify FIRST_CONTEXT in mmu_context_nohash · 8820a447

由 Christophe Leroy 提交于 3月 21, 2018

First context is now 1 for all supported platforms, so it
can be made a constant.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

8820a447

powerpc/dma: remove unnecessary BUG() · 9887334b

由 Christophe Leroy 提交于 2月 28, 2018

Direction is already checked in all calling functions in
include/linux/dma-mapping.h and also in called function __dma_sync()

So really no need to check it once more here.
Signed-off-by: NChristophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

9887334b

powerpc/sstep: Fix emulate_step test if VSX not present · 5a61640e

由 Ravi Bangoria 提交于 5月 21, 2018

emulate_step() tests are failing if VSX is not supported or disabled.

  emulate_step_test: lxvd2x         : FAIL
  emulate_step_test: stxvd2x        : FAIL

If !CPU_FTR_VSX, emulate_step() failure is expected and testcase should
PASS with a valid justification. After patch:

  emulate_step_test: lxvd2x         : PASS (!CPU_FTR_VSX)
  emulate_step_test: stxvd2x        : PASS (!CPU_FTR_VSX)
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

5a61640e

powerpc/sstep: Fix kernel crash if VSX is not present · 83afab4c

由 Ravi Bangoria 提交于 5月 21, 2018

emulate_step() is not checking runtime VSX feature flag before
emulating an instruction. This is causing kernel crash when kernel
is compiled with CONFIG_VSX=y but running on a machine where VSX
is not supported or disabled. Ex, while running emulate_step tests
on P6 machine:

  Oops: Exception in kernel mode, sig: 4 [#1]
  NIP [c000000000095c24] .load_vsrn+0x28/0x54
  LR [c000000000094bdc] .emulate_loadstore+0x167c/0x17b0
  Call Trace:
    0x40fe240c7ae147ae (unreliable)
    .emulate_loadstore+0x167c/0x17b0
    .emulate_step+0x25c/0x5bc
    .test_lxvd2x_stxvd2x+0x64/0x154
    .test_emulate_step+0x38/0x4c
    .do_one_initcall+0x5c/0x2c0
    .kernel_init_freeable+0x314/0x4cc
    .kernel_init+0x24/0x160
    .ret_from_kernel_thread+0x58/0xb4

With fix:
  emulate_step_test: lxvd2x         : FAIL
  emulate_step_test: stxvd2x        : FAIL
Reported-by: NMichael Ellerman <mpe@ellerman.id.au>
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

83afab4c

powerpc/sstep: Introduce GETTYPE macro · e6684d07

由 Ravi Bangoria 提交于 5月 21, 2018

Replace 'op->type & INSTR_TYPE_MASK' expression with GETTYPE(op->type)
macro.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

e6684d07

powerpc/64s: Enhance the information in cpu_show_spectre_v1() · a3775145

由 Michal Suchanek 提交于 5月 28, 2018

We now have barrier_nospec as mitigation so print it in
cpu_show_spectre_v1() when enabled.
Signed-off-by: NMichal Suchanek <msuchanek@suse.de>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

a3775145

powerpc/64: Use barrier_nospec in syscall entry · 51973a81

由 Michael Ellerman 提交于 4月 24, 2018

Our syscall entry is done in assembly so patch in an explicit
barrier_nospec.

Based on a patch by Michal Suchanek.
Signed-off-by: NMichal Suchanek <msuchanek@suse.de>
Signed-off-by: NMichael Ellerman <mpe@ellerman.id.au>

51973a81

openeuler / Kernel 接近 2 年 前同步成功

openeuler / Kernel
接近 2 年前同步成功