* [PATCH 09/11] docs/mm: memblock: add kernel-doc description for memblock types
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
include/linux/memblock.h | 37 +++++++++++++++++++++++++++++++++----
1 file changed, 33 insertions(+), 4 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 63704c6..5169205 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -20,7 +20,13 @@
#define INIT_MEMBLOCK_REGIONS 128
#define INIT_PHYSMEM_REGIONS 4
-/* Definition of memblock flags. */
+/**
+ * enum memblock_flags - definition of memory region attributes
+ * @MEMBLOCK_NONE: no special request
+ * @MEMBLOCK_HOTPLUG: hotpluggable region
+ * @MEMBLOCK_MIRROR: mirrored region
+ * @MEMBLOCK_NOMAP: don't add to kernel direct mapping
+ */
enum memblock_flags {
MEMBLOCK_NONE = 0x0, /* No special request */
MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */
@@ -28,6 +34,13 @@ enum memblock_flags {
MEMBLOCK_NOMAP = 0x4, /* don't add to kernel direct mapping */
};
+/**
+ * struct memblock_region - represents a memory region
+ * @base: physical address of the region
+ * @size: size of the region
+ * @flags: memory region attributes
+ * @nid: NUMA node id
+ */
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
@@ -37,14 +50,30 @@ struct memblock_region {
#endif
};
+/**
+ * struct memblock_type - collection of memory regions of certain type
+ * @cnt: number of regions
+ * @max: size of the allocated array
+ * @total_size: size of all regions
+ * @regions: array of regions
+ * @name: the memory type symbolic name
+ */
struct memblock_type {
- unsigned long cnt; /* number of regions */
- unsigned long max; /* size of the allocated array */
- phys_addr_t total_size; /* size of all regions */
+ unsigned long cnt;
+ unsigned long max;
+ phys_addr_t total_size;
struct memblock_region *regions;
char *name;
};
+/**
+ * struct memblock - memblock allocator metadata
+ * @bottom_up: is bottom up direction?
+ * @current_limit: physical address of the current allocation limit
+ * @memory: usabe memory regions
+ * @reserved: reserved memory regions
+ * @physmem: all physical memory
+ */
struct memblock {
bool bottom_up; /* is bottom up direction? */
phys_addr_t current_limit;
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 07/11] docs/mm: memblock: update kernel-doc comments
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
* make memblock_discard description kernel-doc compatible
* add brief description for memblock_setclr_flag and describe its
parameters
* fixup return value descriptions
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
include/linux/memblock.h | 17 +++++++---
mm/memblock.c | 84 +++++++++++++++++++++++++++---------------------
2 files changed, 59 insertions(+), 42 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8b8fbce..63704c6 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -239,7 +239,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
/**
* for_each_resv_unavail_range - iterate through reserved and unavailable memory
* @i: u64 used as loop variable
- * @flags: pick from blocks based on memory attributes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
*
@@ -367,8 +366,10 @@ phys_addr_t memblock_get_current_limit(void);
*/
/**
- * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region
+ * memblock_region_memory_base_pfn - get the lowest pfn of the memory region
* @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the memory region
*/
static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
{
@@ -376,8 +377,10 @@ static inline unsigned long memblock_region_memory_base_pfn(const struct membloc
}
/**
- * memblock_region_memory_end_pfn - Return the end_pfn this region
+ * memblock_region_memory_end_pfn - get the end pfn of the memory region
* @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
*/
static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
{
@@ -385,8 +388,10 @@ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock
}
/**
- * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region
+ * memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region
* @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the reserved region
*/
static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
{
@@ -394,8 +399,10 @@ static inline unsigned long memblock_region_reserved_base_pfn(const struct membl
}
/**
- * memblock_region_reserved_end_pfn - Return the end_pfn this region
+ * memblock_region_reserved_end_pfn - get the end pfn of the reserved region
* @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
*/
static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
{
diff --git a/mm/memblock.c b/mm/memblock.c
index fc5d966..3d6deff 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -92,10 +92,11 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
return i < type->cnt;
}
-/*
+/**
* __memblock_find_range_bottom_up - find free area utility in bottom-up
* @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ * %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -103,7 +104,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
*
* Utility called from memblock_find_in_range_node(), find free area bottom-up.
*
- * RETURNS:
+ * Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
@@ -129,7 +130,8 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
/**
* __memblock_find_range_top_down - find free area utility, in top-down
* @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ * %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -137,7 +139,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
*
* Utility called from memblock_find_in_range_node(), find free area top-down.
*
- * RETURNS:
+ * Return:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
@@ -169,7 +171,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
* @size: size of free area to find
* @align: alignment of free area to find
* @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ * %MEMBLOCK_ALLOC_ACCESSIBLE
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
* @flags: pick from blocks based on memory attributes
*
@@ -183,7 +186,7 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
*
* If bottom-up allocation failed, will try to allocate memory top-down.
*
- * RETURNS:
+ * Return:
* Found address on success, 0 on failure.
*/
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
@@ -238,13 +241,14 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
/**
* memblock_find_in_range - find free area in given range
* @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ * %MEMBLOCK_ALLOC_ACCESSIBLE
* @size: size of free area to find
* @align: alignment of free area to find
*
* Find @size free area aligned to @align in the specified range.
*
- * RETURNS:
+ * Return:
* Found address on success, 0 on failure.
*/
phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
@@ -288,7 +292,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
/**
- * Discard memory and reserved arrays if they were allocated
+ * memblock_discard - discard memory and reserved arrays if they were allocated
*/
void __init memblock_discard(void)
{
@@ -318,11 +322,11 @@ void __init memblock_discard(void)
*
* Double the size of the @type regions array. If memblock is being used to
* allocate memory for a new reserved regions array and there is a previously
- * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * allocated memory range [@new_area_start, @new_area_start + @new_area_size]
* waiting to be reserved, ensure the memory used by the new array does
* not overlap.
*
- * RETURNS:
+ * Return:
* 0 on success, -1 on failure.
*/
static int __init_memblock memblock_double_array(struct memblock_type *type,
@@ -467,7 +471,7 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
* @nid: node id of the new region
* @flags: flags of the new region
*
- * Insert new memblock region [@base,@base+@size) into @type at @idx.
+ * Insert new memblock region [@base, @base + @size) into @type at @idx.
* @type must already have extra room to accommodate the new region.
*/
static void __init_memblock memblock_insert_region(struct memblock_type *type,
@@ -496,12 +500,12 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
* @nid: nid of the new region
* @flags: flags of the new region
*
- * Add new memblock region [@base,@base+@size) into @type. The new region
+ * Add new memblock region [@base, @base + @size) into @type. The new region
* is allowed to overlap with existing ones - overlaps don't affect already
* existing regions. @type is guaranteed to be minimal (all neighbouring
* compatible regions are merged) after the addition.
*
- * RETURNS:
+ * Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_range(struct memblock_type *type,
@@ -615,11 +619,11 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
* @end_rgn: out parameter for the end of isolated region
*
* Walk @type and ensure that regions don't cross the boundaries defined by
- * [@base,@base+@size). Crossing regions are split at the boundaries,
+ * [@base, @base + @size). Crossing regions are split at the boundaries,
* which may create at most two more regions. The index of the first
* region inside the range is returned in *@start_rgn and end in *@end_rgn.
*
- * RETURNS:
+ * Return:
* 0 on success, -errno on failure.
*/
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
@@ -725,10 +729,15 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
}
/**
+ * memblock_setclr_flag - set or clear flag for a memory region
+ * @base: base address of the region
+ * @size: size of the region
+ * @set: set or clear the flag
+ * @flag: the flag to udpate
*
* This function isolates region [@base, @base + @size), and sets/clears flag
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
static int __init_memblock memblock_setclr_flag(phys_addr_t base,
phys_addr_t size, int set, int flag)
@@ -755,7 +764,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base,
* @base: the base phys addr of the region
* @size: the size of the region
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
{
@@ -767,7 +776,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
* @base: the base phys addr of the region
* @size: the size of the region
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
{
@@ -779,7 +788,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
* @base: the base phys addr of the region
* @size: the size of the region
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
{
@@ -793,7 +802,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
* @base: the base phys addr of the region
* @size: the size of the region
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
{
@@ -805,7 +814,7 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
* @base: the base phys addr of the region
* @size: the size of the region
*
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
*/
int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
{
@@ -966,9 +975,6 @@ void __init_memblock __next_mem_range(u64 *idx, int nid,
/**
* __next_mem_range_rev - generic next function for for_each_*_range_rev()
*
- * Finds the next range from type_a which is not marked as unsuitable
- * in type_b.
- *
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @flags: pick from blocks based on memory attributes
@@ -978,6 +984,9 @@ void __init_memblock __next_mem_range(u64 *idx, int nid,
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
* Reverse of __next_mem_range().
*/
void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
@@ -1113,10 +1122,10 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
* @type: memblock type to set node ID for
* @nid: node ID to set
*
- * Set the nid of memblock @type regions in [@base,@base+@size) to @nid.
+ * Set the nid of memblock @type regions in [@base, @base + @size) to @nid.
* Regions which cross the area boundaries are split as necessary.
*
- * RETURNS:
+ * Return:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
@@ -1240,7 +1249,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
* The allocation is performed from memory region limited by
* memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
*
- * The memory block is aligned on SMP_CACHE_BYTES if @align == 0.
+ * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0.
*
* The phys address of allocated boot memory block is converted to virtual and
* allocated memory is reset to 0.
@@ -1248,7 +1257,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
* In addition, function sets the min_count to 0 using kmemleak_alloc for
* allocated boot memory block, so that it is never reported as leaks.
*
- * RETURNS:
+ * Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
static void * __init memblock_virt_alloc_internal(
@@ -1333,7 +1342,7 @@ static void * __init memblock_virt_alloc_internal(
* info), if enabled. Does not zero allocated memory, does not panic if request
* cannot be satisfied.
*
- * RETURNS:
+ * Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid_raw(
@@ -1370,7 +1379,7 @@ void * __init memblock_virt_alloc_try_nid_raw(
* Public function, provides additional debug information (including caller
* info), if enabled. This function zeroes the allocated memory.
*
- * RETURNS:
+ * Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid_nopanic(
@@ -1406,7 +1415,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic(
* which provides debug information (including caller info), if enabled,
* and panics if the request can not be satisfied.
*
- * RETURNS:
+ * Return:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid(
@@ -1663,9 +1672,9 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
* @base: base of region to check
* @size: size of region to check
*
- * Check if the region [@base, @base+@size) is a subset of a memory block.
+ * Check if the region [@base, @base + @size) is a subset of a memory block.
*
- * RETURNS:
+ * Return:
* 0 if false, non-zero if true
*/
bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
@@ -1684,9 +1693,10 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz
* @base: base of region to check
* @size: size of region to check
*
- * Check if the region [@base, @base+@size) intersects a reserved memory block.
+ * Check if the region [@base, @base + @size) intersects a reserved
+ * memory block.
*
- * RETURNS:
+ * Return:
* True if they intersect, false if not.
*/
bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 08/11] docs/mm: memblock: add kernel-doc comments for memblock_add[_node]
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
mm/memblock.c | 27 +++++++++++++++++++++++++--
1 file changed, 25 insertions(+), 2 deletions(-)
diff --git a/mm/memblock.c b/mm/memblock.c
index 3d6deff..c4838a9 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -594,12 +594,35 @@ int __init_memblock memblock_add_range(struct memblock_type *type,
}
}
+/**
+ * memblock_add_node - add new memblock region within a NUMA node
+ * @base: base address of the new region
+ * @size: size of the new region
+ * @nid: nid of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid)
{
return memblock_add_range(&memblock.memory, base, size, nid, 0);
}
+/**
+ * memblock_add - add new memblock region
+ * @base: base address of the new region
+ * @size: size of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
phys_addr_t end = base + size - 1;
@@ -1458,9 +1481,9 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
memblock_remove_range(&memblock.reserved, base, size);
}
-/*
+/**
* __memblock_free_late - free bootmem block pages directly to buddy allocator
- * @addr: phys starting address of the boot memory block
+ * @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* This is only useful when the bootmem allocator has already been torn
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 06/11] mm/memblock: add a name for memblock flags enumeration
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Since kernel-doc does not like anonymous enums the name is required for
adding documentation. While on it, I've also updated all the function
declarations to use 'enum memblock_flags' instead of unsigned long.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
include/linux/memblock.h | 22 +++++++++++-----------
mm/memblock.c | 37 +++++++++++++++++++++----------------
mm/nobootmem.c | 2 +-
3 files changed, 33 insertions(+), 28 deletions(-)
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ca59883..8b8fbce 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -21,7 +21,7 @@
#define INIT_PHYSMEM_REGIONS 4
/* Definition of memblock flags. */
-enum {
+enum memblock_flags {
MEMBLOCK_NONE = 0x0, /* No special request */
MEMBLOCK_HOTPLUG = 0x1, /* hotpluggable region */
MEMBLOCK_MIRROR = 0x2, /* mirrored region */
@@ -31,7 +31,7 @@ enum {
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
- unsigned long flags;
+ enum memblock_flags flags;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int nid;
#endif
@@ -72,7 +72,7 @@ void memblock_discard(void);
phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
- int nid, ulong flags);
+ int nid, enum memblock_flags flags);
phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align);
void memblock_allow_resize(void);
@@ -89,19 +89,19 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
-ulong choose_memblock_flags(void);
+enum memblock_flags choose_memblock_flags(void);
/* Low level functions */
int memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
- int nid, unsigned long flags);
+ int nid, enum memblock_flags flags);
-void __next_mem_range(u64 *idx, int nid, ulong flags,
+void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
-void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
@@ -253,13 +253,13 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
static inline void memblock_set_region_flags(struct memblock_region *r,
- unsigned long flags)
+ enum memblock_flags flags)
{
r->flags |= flags;
}
static inline void memblock_clear_region_flags(struct memblock_region *r,
- unsigned long flags)
+ enum memblock_flags flags)
{
r->flags &= ~flags;
}
@@ -317,10 +317,10 @@ static inline bool memblock_bottom_up(void)
phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
- ulong flags);
+ enum memblock_flags flags);
phys_addr_t memblock_alloc_base_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t max_addr,
- int nid, ulong flags);
+ int nid, enum memblock_flags flags);
phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
phys_addr_t max_addr);
phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
diff --git a/mm/memblock.c b/mm/memblock.c
index 5108356..fc5d966 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -60,7 +60,7 @@ static int memblock_can_resize __initdata_memblock;
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;
-ulong __init_memblock choose_memblock_flags(void)
+enum memblock_flags __init_memblock choose_memblock_flags(void)
{
return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
}
@@ -109,7 +109,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
- ulong flags)
+ enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
@@ -143,7 +143,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid,
- ulong flags)
+ enum memblock_flags flags)
{
phys_addr_t this_start, this_end, cand;
u64 i;
@@ -188,7 +188,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
*/
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
- phys_addr_t end, int nid, ulong flags)
+ phys_addr_t end, int nid,
+ enum memblock_flags flags)
{
phys_addr_t kernel_end, ret;
@@ -251,7 +252,7 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
phys_addr_t align)
{
phys_addr_t ret;
- ulong flags = choose_memblock_flags();
+ enum memblock_flags flags = choose_memblock_flags();
again:
ret = memblock_find_in_range_node(size, align, start, end,
@@ -472,7 +473,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
static void __init_memblock memblock_insert_region(struct memblock_type *type,
int idx, phys_addr_t base,
phys_addr_t size,
- int nid, unsigned long flags)
+ int nid,
+ enum memblock_flags flags)
{
struct memblock_region *rgn = &type->regions[idx];
@@ -504,7 +506,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
*/
int __init_memblock memblock_add_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
- int nid, unsigned long flags)
+ int nid, enum memblock_flags flags)
{
bool insert = false;
phys_addr_t obase = base;
@@ -868,7 +870,8 @@ void __init_memblock __next_reserved_mem_region(u64 *idx,
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
-void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range(u64 *idx, int nid,
+ enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
@@ -977,7 +980,8 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
*
* Reverse of __next_mem_range().
*/
-void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
+ enum memblock_flags flags,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
@@ -1135,7 +1139,8 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
- phys_addr_t end, int nid, ulong flags)
+ phys_addr_t end, int nid,
+ enum memblock_flags flags)
{
phys_addr_t found;
@@ -1157,7 +1162,7 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end,
- ulong flags)
+ enum memblock_flags flags)
{
return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE,
flags);
@@ -1165,14 +1170,14 @@ phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t max_addr,
- int nid, ulong flags)
+ int nid, enum memblock_flags flags)
{
return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags);
}
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
{
- ulong flags = choose_memblock_flags();
+ enum memblock_flags flags = choose_memblock_flags();
phys_addr_t ret;
again:
@@ -1253,7 +1258,7 @@ static void * __init memblock_virt_alloc_internal(
{
phys_addr_t alloc;
void *ptr;
- ulong flags = choose_memblock_flags();
+ enum memblock_flags flags = choose_memblock_flags();
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
@@ -1728,7 +1733,7 @@ phys_addr_t __init_memblock memblock_get_current_limit(void)
static void __init_memblock memblock_dump(struct memblock_type *type)
{
phys_addr_t base, end, size;
- unsigned long flags;
+ enum memblock_flags flags;
int idx;
struct memblock_region *rgn;
@@ -1746,7 +1751,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
snprintf(nid_buf, sizeof(nid_buf), " on node %d",
memblock_get_region_node(rgn));
#endif
- pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n",
+ pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n",
type->name, idx, &base, &end, &size, nid_buf, flags);
}
}
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index c2cfa04..439af3b 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -42,7 +42,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
{
void *ptr;
u64 addr;
- ulong flags = choose_memblock_flags();
+ enum memblock_flags flags = choose_memblock_flags();
if (limit > memblock.current_limit)
limit = memblock.current_limit;
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 04/11] docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data'
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
include/linux/bootmem.h | 17 ++++++++++++++---
1 file changed, 14 insertions(+), 3 deletions(-)
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 7942a96..1526ba1 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -27,9 +27,20 @@ extern unsigned long max_pfn;
extern unsigned long long max_possible_pfn;
#ifndef CONFIG_NO_BOOTMEM
-/*
- * node_bootmem_map is a map pointer - the bits represent all physical
- * memory pages (including holes) on the node.
+/**
+ * struct bootmem_data - per-node information used by the bootmem allocator
+ * @node_min_pfn: the starting physical address of the node's memory
+ * @node_low_pfn: the end physical address of the directly addressable memory
+ * @node_bootmem_map: is a bitmap pointer - the bits represent all physical
+ * memory pages (including holes) on the node.
+ * @last_end_off: the offset within the page of the end of the last allocation;
+ * if 0, the page used is full
+ * @hint_idx: the the PFN of the page used with the last allocation;
+ * together with using this with the @last_end_offset field,
+ * a test can be made to see if allocations can be merged
+ * with the page used for the last allocation rather than
+ * using up a full new page.
+ * @list: list entry in the linked list ordered by the memory addresses
*/
typedef struct bootmem_data {
unsigned long node_min_pfn;
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 05/11] docs/mm: bootmem: add overview documentation
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
mm/bootmem.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 47 insertions(+)
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 76fc17e..423cb5f 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -21,6 +21,53 @@
#include "internal.h"
+/**
+ * DOC: bootmem overview
+ *
+ * Bootmem is a boot-time physical memory allocator and configurator.
+ *
+ * It is used early in the boot process before the page allocator is
+ * set up.
+ *
+ * The bootmem is based on the most basic of allocators, a First Fit
+ * allocator which uses a bitmap to represent memory. If a bit is 1,
+ * the page is allocated and 0 if unallocated. To satisfy allocations
+ * of sizes smaller than a page, the allocator records the Page Frame
+ * Number (PFN) of the last allocation and the offset the allocation
+ * ended at. Subsequent small allocations are merged together and
+ * stored on the same page.
+ *
+ * The information used by the bootmem allocator is represented by
+ * :c:type:`struct bootmem_data`. An array to hold up to %MAX_NUMNODES
+ * such structures is statically allocated and then it is discarded
+ * when the system initialization completes. Each entry in this array
+ * corresponds to a node with memory. For UMA systems only entry 0 is
+ * used.
+ *
+ * The bootmem allocator is initialized during early architecture
+ * specific setup. Each architecture is required to supply a
+ * :c:func:`setup_arch` function which, among other tasks, is
+ * responsible for acquiring the necessary parameters to initialise
+ * the boot memory allocator. These parameters define limits of usable
+ * physical memory:
+ *
+ * * @min_low_pfn - the lowest PFN that is available in the system
+ * * @max_low_pfn - the highest PFN that may be addressed by low
+ * memory (%ZONE_NORMAL)
+ * * @max_pfn - the last PFN available to the system.
+ *
+ * After those limits are determined, the :c:func:`init_bootmem` or
+ * :c:func:`init_bootmem_node` function should be called to initialize
+ * the bootmem allocator. The UMA case should use the `init_bootmem`
+ * function. It will initialize ``contig_page_data`` structure that
+ * represents the only memory node in the system. In the NUMA case the
+ * `init_bootmem_node` function should be called to initialize the
+ * bootmem allocator for each node.
+ *
+ * Once the allocator is set up, it is possible to use either single
+ * node or NUMA variant of the allocation APIs.
+ */
+
#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data = {
.bdata = &bootmem_node_data[0]
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 02/11] docs/mm: nobootmem: fixup kernel-doc comments
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
* add kernel-doc marking to free_bootmem_late() description
* add return value descriptions
* mention that address parameter of free_bootmem{_node} is a physical address
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
mm/nobootmem.c | 18 +++++++++++++-----
1 file changed, 13 insertions(+), 5 deletions(-)
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 9b02fda..c2cfa04 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -72,7 +72,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
return ptr;
}
-/*
+/**
* free_bootmem_late - free bootmem pages directly to page allocator
* @addr: starting address of the range
* @size: size of the range in bytes
@@ -176,7 +176,7 @@ void __init reset_all_zones_managed_pages(void)
/**
* free_all_bootmem - release free pages to the buddy allocator
*
- * Returns the number of pages actually released.
+ * Return: the number of pages actually released.
*/
unsigned long __init free_all_bootmem(void)
{
@@ -193,7 +193,7 @@ unsigned long __init free_all_bootmem(void)
/**
* free_bootmem_node - mark a page range as usable
* @pgdat: node the range resides on
- * @physaddr: starting address of the range
+ * @physaddr: starting physical address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
@@ -208,7 +208,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
/**
* free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
@@ -256,7 +256,7 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
*
* Allocation may happen on any node in the system.
*
- * Returns NULL on failure.
+ * Return: address of the allocated region or %NULL on failure.
*/
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
unsigned long goal)
@@ -293,6 +293,8 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
*/
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal)
@@ -367,6 +369,8 @@ static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
*/
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
@@ -396,6 +400,8 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
*/
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
unsigned long goal)
@@ -425,6 +431,8 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
*/
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 01/11] mm/bootmem: drop duplicated kernel-doc comments
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
In-Reply-To: <1529341199-17682-1-git-send-email-rppt@linux.vnet.ibm.com>
Parts of the bootmem interfaces are duplicated in nobootmem.c along with
the kernel-doc comments. There is no point to keep two copies of the
comments, so let's drop the bootmem.c copy.
Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
---
mm/bootmem.c | 102 -----------------------------------------------------------
1 file changed, 102 deletions(-)
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 9e19798..42ab0da 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -143,15 +143,6 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
}
-/*
- * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * This is only useful when the bootmem allocator has already been torn
- * down, but we are still initializing the system. Pages are given directly
- * to the page allocator, no bootmem metadata is updated because it is gone.
- */
void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
{
unsigned long cursor, end;
@@ -264,11 +255,6 @@ void __init reset_all_zones_managed_pages(void)
reset_managed_pages_done = 1;
}
-/**
- * free_all_bootmem - release free pages to the buddy allocator
- *
- * Returns the number of pages actually released.
- */
unsigned long __init free_all_bootmem(void)
{
unsigned long total_pages = 0;
@@ -385,16 +371,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
BUG();
}
-/**
- * free_bootmem_node - mark a page range as usable
- * @pgdat: node the range resides on
- * @physaddr: starting address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must reside completely on the specified node.
- */
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size)
{
@@ -408,15 +384,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
}
-/**
- * free_bootmem - mark a page range as usable
- * @physaddr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must be contiguous but may span node boundaries.
- */
void __init free_bootmem(unsigned long physaddr, unsigned long size)
{
unsigned long start, end;
@@ -646,19 +613,6 @@ static void * __init ___alloc_bootmem_nopanic(unsigned long size,
return NULL;
}
-/**
- * __alloc_bootmem_nopanic - allocate boot memory without panicking
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * Returns NULL on failure.
- */
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
unsigned long goal)
{
@@ -682,19 +636,6 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
return NULL;
}
-/**
- * __alloc_bootmem - allocate boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal)
{
@@ -754,21 +695,6 @@ void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
return NULL;
}
-/**
- * __alloc_bootmem_node - allocate boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
@@ -807,19 +733,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
}
-/**
- * __alloc_bootmem_low - allocate low boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
unsigned long goal)
{
@@ -834,21 +747,6 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
ARCH_LOW_ADDRESS_LIMIT);
}
-/**
- * __alloc_bootmem_low_node - allocate low boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH 00/11] docs/mm: add boot time memory management docs
From: Mike Rapoport @ 2018-06-18 16:59 UTC (permalink / raw)
To: Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml, Mike Rapoport
Hi,
Both bootmem and memblock have pretty good documentation coverage. With
some fixups and additions we get a nice overall description.
The last commit in the series that creates the boot-time-mm.rst depends on
the 'nodoc' sphix directive patch [1] I've sent earlier
While working on the docs, I've noticed that both bootmem and nobootmem
implement some one-line wrappers for the core allocation methods as a
global functions rather than 'static inline'. I wonder whether I miss
something important here is it just a historic thing?
[1] https://marc.info/?l=linux-doc&m=152932901214922&w=2
Mike Rapoport (11):
mm/bootmem: drop duplicated kernel-doc comments
docs/mm: nobootmem: fixup kernel-doc comments
docs/mm: bootmem: fix kernel-doc warnings
docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data'
docs/mm: bootmem: add overview documentation
mm/memblock: add a name for memblock flags enumeration
docs/mm: memblock: update kernel-doc comments
docs/mm: memblock: add kernel-doc comments for memblock_add[_node]
docs/mm: memblock: add kernel-doc description for memblock types
docs/mm: memblock: add overview documentation
docs/mm: add description of boot time memory management
Documentation/core-api/boot-time-mm.rst | 92 +++++++++++++++
Documentation/core-api/index.rst | 1 +
include/linux/bootmem.h | 17 ++-
include/linux/memblock.h | 76 ++++++++----
mm/bootmem.c | 159 +++++++++----------------
mm/memblock.c | 203 +++++++++++++++++++++++---------
mm/nobootmem.c | 20 +++-
7 files changed, 380 insertions(+), 188 deletions(-)
create mode 100644 Documentation/core-api/boot-time-mm.rst
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 0/2] Documentation/sphinx: add "nodocs" directive
From: Matthew Wilcox @ 2018-06-18 17:10 UTC (permalink / raw)
To: Mike Rapoport; +Cc: Jonathan Corbet, Matthew Wilcox, Jani Nikula, linux-doc
In-Reply-To: <1529328996-16247-1-git-send-email-rppt@linux.vnet.ibm.com>
On Mon, Jun 18, 2018 at 04:36:34PM +0300, Mike Rapoport wrote:
> Hi,
>
> These patches allow passing "-no-doc-sections" option to scripts/kernel-doc
> from the sphinx generator.
>
> This allows to avoid duplicated DOC: sections when "kernel-doc:" directive
> is used without explicit selection of functions or function types. For
> instance, [1] has "IDA description" and "idr synchronization" twice.
Hah, I just found an abandoned patch for this in a disused git tree.
I was wondering whether I needed to resurrect it. Enthusiastically,
Acked-by: Matthew Wilcox <willy@infradead.org>
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 05/11] docs/mm: bootmem: add overview documentation
From: Randy Dunlap @ 2018-06-18 17:15 UTC (permalink / raw)
To: Mike Rapoport, Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml
In-Reply-To: <1529341199-17682-6-git-send-email-rppt@linux.vnet.ibm.com>
Hi,
On 06/18/2018 09:59 AM, Mike Rapoport wrote:
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> mm/bootmem.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 47 insertions(+)
>
> diff --git a/mm/bootmem.c b/mm/bootmem.c
> index 76fc17e..423cb5f 100644
> --- a/mm/bootmem.c
> +++ b/mm/bootmem.c
> @@ -21,6 +21,53 @@
>
> #include "internal.h"
>
> +/**
> + * DOC: bootmem overview
> + *
> + * Bootmem is a boot-time physical memory allocator and configurator.
> + *
> + * It is used early in the boot process before the page allocator is
> + * set up.
> + *
> + * The bootmem is based on the most basic of allocators, a First Fit
* Bootmem is based on
or
* The bootmem allocator is based on
> + * allocator which uses a bitmap to represent memory. If a bit is 1,
> + * the page is allocated and 0 if unallocated. To satisfy allocations
> + * of sizes smaller than a page, the allocator records the Page Frame
> + * Number (PFN) of the last allocation and the offset the allocation
> + * ended at. Subsequent small allocations are merged together and
> + * stored on the same page.
--
~Randy
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 10/11] docs/mm: memblock: add overview documentation
From: Randy Dunlap @ 2018-06-18 17:21 UTC (permalink / raw)
To: Mike Rapoport, Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml
In-Reply-To: <1529341199-17682-11-git-send-email-rppt@linux.vnet.ibm.com>
Hi,
On 06/18/2018 09:59 AM, Mike Rapoport wrote:
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> mm/memblock.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 55 insertions(+)
>
> diff --git a/mm/memblock.c b/mm/memblock.c
> index c4838a9..8bfeb82 100644
> --- a/mm/memblock.c
> +++ b/mm/memblock.c
> @@ -26,6 +26,61 @@
>
> #include "internal.h"
>
> +/**
> + * DOC: memblock overview
> + *
> + * Memblock is a method of managing memory regions during the early
> + * boot period when the usual kernel memory allocators are not up and
> + * running.
> + *
> + * Memblock views the system memory as collections of contiguous
> + * regions. There are several types of these collections:
> + *
> + * * ``memory`` - describes the physical memory available to the
> + * kernel; this may differ from the actual physical memory installed
> + * in the system, for instance when the memory is restricted with
> + * ``mem=`` command line parameter
> + * * ``reserved`` - describes the regions that were allocated
> + * * ``physmap`` - describes the actual physical memory regardless of
> + * the possible restrictions; the ``physmap`` type is only available
> + * on some architectures.
> + *
> + * Each region is represented by :c:type:`struct memblock_region` that
> + * defines the region extents, its attributes and NUMA node id on NUMA
> + * systems. Every memory type is described by the :c:type:`struct
> + * memblock_type` which contains an array of memory regions along with
> + * the allocator metadata. The memory types are nicely wrapped with
> + * :c:type:`struct memblock`. This structure is statically initialzed
> + * at build time. The region arrays for the "memory" and "reserved"
> + * types are initially sized to %INIT_MEMBLOCK_REGIONS and for the
> + * "physmap" type to %INIT_PHYSMEM_REGIONS.
> + * The :c:func:`memblock_allow_resize` enables automatic resizing of
> + * the region arrays during addition of new regions. This feature
> + * should be used with care so that memory allocated for the region
> + * array will not overlap with areas that should be reserved, for
> + * example initrd.
> + *
> + * The early architecture setup should tell memblock what is the
The early architecture setup should tell memblock what the physical
memory layout is by using :c:func:`memblock_add` or
> + * physical memory layout using :c:func:`memblock_add` or
> + * :c:func:`memblock_add_node` functions. The first function does not
> + * assign the region to a NUMA node and it is approptiate for UMA
appropriate
> + * systems. Yet, it is possible to use it on NUMA systems as well and
> + * assign the region to a NUMA node later in the setup process using
> + * :c:func:`memblock_set_node`. The :c:func:`memblock_add_node`
> + * performs such an assignment directly.
> + *
> + * Once memblock is setup the memory can be allocated using either
> + * memblock or bootmem APIs.
> + *
> + * As the system boot progresses, the architecture specific
> + * :c:func:`mem_init` function frees all the memory to the buddy page
> + * allocator.
> + *
> + * If an architecure enables %CONFIG_ARCH_DISCARD_MEMBLOCK, the
> + * memblock data structures will be discarded after the system
> + * intialization compltes
initialization completes.
> + */
> +
> static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
> static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
> #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
>
--
~Randy
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 04/11] docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data'
From: Randy Dunlap @ 2018-06-18 17:25 UTC (permalink / raw)
To: Mike Rapoport, Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml
In-Reply-To: <1529341199-17682-5-git-send-email-rppt@linux.vnet.ibm.com>
On 06/18/2018 09:59 AM, Mike Rapoport wrote:
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> include/linux/bootmem.h | 17 ++++++++++++++---
> 1 file changed, 14 insertions(+), 3 deletions(-)
>
> diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
> index 7942a96..1526ba1 100644
> --- a/include/linux/bootmem.h
> +++ b/include/linux/bootmem.h
> @@ -27,9 +27,20 @@ extern unsigned long max_pfn;
> extern unsigned long long max_possible_pfn;
>
> #ifndef CONFIG_NO_BOOTMEM
> -/*
> - * node_bootmem_map is a map pointer - the bits represent all physical
> - * memory pages (including holes) on the node.
> +/**
> + * struct bootmem_data - per-node information used by the bootmem allocator
> + * @node_min_pfn: the starting physical address of the node's memory
> + * @node_low_pfn: the end physical address of the directly addressable memory
> + * @node_bootmem_map: is a bitmap pointer - the bits represent all physical
> + * memory pages (including holes) on the node.
> + * @last_end_off: the offset within the page of the end of the last allocation;
> + * if 0, the page used is full
> + * @hint_idx: the the PFN of the page used with the last allocation;
drop one "the" above.
> + * together with using this with the @last_end_offset field,
> + * a test can be made to see if allocations can be merged
> + * with the page used for the last allocation rather than
> + * using up a full new page.
> + * @list: list entry in the linked list ordered by the memory addresses
> */
> typedef struct bootmem_data {
> unsigned long node_min_pfn;
>
--
~Randy
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH 11/11] docs/mm: add description of boot time memory management
From: Randy Dunlap @ 2018-06-18 17:32 UTC (permalink / raw)
To: Mike Rapoport, Jonathan Corbet; +Cc: Andrew Morton, linux-doc, linux-mm, lkml
In-Reply-To: <1529341199-17682-12-git-send-email-rppt@linux.vnet.ibm.com>
On 06/18/2018 09:59 AM, Mike Rapoport wrote:
> Both bootmem and memblock are have pretty good internal documentation
> coverage. With addition of some overview we get a nice description of the
> early memory management.
>
> Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
> ---
> Documentation/core-api/boot-time-mm.rst | 92 +++++++++++++++++++++++++++++++++
> Documentation/core-api/index.rst | 1 +
> 2 files changed, 93 insertions(+)
> create mode 100644 Documentation/core-api/boot-time-mm.rst
>
> diff --git a/Documentation/core-api/boot-time-mm.rst b/Documentation/core-api/boot-time-mm.rst
> new file mode 100644
> index 0000000..379e5a3
> --- /dev/null
> +++ b/Documentation/core-api/boot-time-mm.rst
> @@ -0,0 +1,92 @@
> +===========================
> +Boot time memory management
> +===========================
> +
> +Early system initialization cannot use "normal" memory management
> +simply because it is not set up yet. But there is still need to
> +allocate memory for various data structures, for instance for the
> +physical page allocator. To address this, a specialized allocator
> +called the :ref:`Boot Memory Allocator <bootmem>`, or bootmem, was
> +introduced. Several years later PowerPC developers added a "Logical
> +Memory Blocks" which was later adopted by other architectures and
Memory Blocks" allocator, which was later ...
> +renamed to :ref:`memblock <memblock>`. There is also a compatibility
> +layer called `nobootmem` that translates bootmem allocation interfaces
> +to memblock calls.
> +
> +The selection of the early alocator is done using
allocator
> +``CONFIG_NO_BOOTMEM`` and ``CONFIG_HAVE_MEMBLOCK`` kernel
> +configuration options. These options are enabled or disabled
> +statically by the architectures' Kconfig files.
> +
> +* Architectures that rely only on bootmem select ``CONFIG_NO_BOOTMEM=n
> + && CONFIG_HAVE_MEMBLOCK=n``.
> +* The users of memblock with the nobootmem compatibility layer set
> + ``CONFIG_NO_BOOTMEM=y && CONFIG_HAVE_MEMBLOCK=y``.
> +* And for those that use both memblock and bootmem the configuration
> + includes ``CONFIG_NO_BOOTMEM=n && CONFIG_HAVE_MEMBLOCK=y
fix ending: =y``.
> +
> +Whichever allocator is used, it is the responsibility of the
> +architecture specific initialization to set it up in
> +:c:func:`setup_arch` and tear it down in :c:func:`mem_init` functions.
> +
> +Once the early memory manegement is available it offers variety of
management offers a variety of
> +functions and macros for memory allocations. The allocation request
> +may be directed to the first (and probably the only) node or to a
> +particular node in a NUMA system. There are API variants that panic
> +when an allocation fails and those that don't. And more recent and
> +advanced memblock even allows controlling its own behaviour.
> +
> +.. _bootmem:
> +
> +Bootmem
> +=======
> +
> +(mostly stolen from Mel Gorman's "Understanding the Linux Virtual
> +Memory Manager" `book`_)
> +
> +.. _book: https://www.kernel.org/doc/gorman/
> +
> +.. kernel-doc:: mm/bootmem.c
> + :doc: bootmem overview
> +
> +.. _memblock:
> +
> +Memblock
> +========
> +
> +.. kernel-doc:: mm/memblock.c
> + :doc: memblock overview
> +
> +
> +Functions and structures
> +========================
> +
> +Common API
> +----------
> +
> +The functions that are described in this section are available
> +regardless of what early memory manager is enabled.
> +
> +.. kernel-doc:: mm/nobootmem.c
> +
> +Bootmem specific API
> +--------------------
> +
> +The interfaces available only with bootmem, i.e when ``CONFIG_NO_BOOTMEM=n``
i.e.
How about:
These interfaces are available only with bootmem, i.e. when ``CONFIG_NO_BOOTMEM=n``.
> +
> +.. kernel-doc:: include/linux/bootmem.h
> +.. kernel-doc:: mm/bootmem.c
> + :nodocs:
> +
> +Memblock specific API
> +---------------------
> +
> +Here is the description of memblock data structures, functions and
> +macros. Some of them are actually internal, but since they are
> +documented it would be silly to omit them. Besides, reading the
> +descriptions for the internal functions can help to understand what
> +really happens under the hood.
> +
> +.. kernel-doc:: include/linux/memblock.h
> +.. kernel-doc:: mm/memblock.c
> + :nodocs:
> diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
> index f5a66b7..93d5a46 100644
> --- a/Documentation/core-api/index.rst
> +++ b/Documentation/core-api/index.rst
> @@ -28,6 +28,7 @@ Core utilities
> printk-formats
> circular-buffers
> gfp_mask-from-fs-io
> + boot-time-mm
>
> Interfaces for kernel debugging
> ===============================
>
--
~Randy
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 03/10] PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq() signatures
From: kbuild test robot @ 2018-06-18 18:17 UTC (permalink / raw)
To: Gustavo Pimentel
Cc: kbuild-all, bhelgaas, lorenzo.pieralisi, Joao.Pinto, jingoohan1,
kishon, adouglas, jesper.nilsson, linux-pci, linux-doc,
linux-kernel, Gustavo Pimentel
In-Reply-To: <5bfa0cf053878e0e859a8b97227ca03ea4d50e92.1529329262.git.gustavo.pimentel@synopsys.com>
[-- Attachment #1: Type: text/plain, Size: 3383 bytes --]
Hi Gustavo,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on pci/next]
[also build test ERROR on v4.18-rc1 next-20180618]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Gustavo-Pimentel/Add-MSI-X-support-on-pcitest-tool/20180619-004625
base: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git next
config: ia64-allmodconfig (attached as .config)
compiler: ia64-linux-gcc (GCC) 8.1.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=8.1.0 make.cross ARCH=ia64
All errors (new ones prefixed by >>):
>> drivers/pci/controller/pcie-rockchip-ep.c:516:15: error: initialization of 'int (*)(struct pci_epc *, u8, enum pci_epc_irq_type, u16)' {aka 'int (*)(struct pci_epc *, unsigned char, enum pci_epc_irq_type, short unsigned int)'} from incompatible pointer type 'int (*)(struct pci_epc *, u8, enum pci_epc_irq_type, u8)' {aka 'int (*)(struct pci_epc *, unsigned char, enum pci_epc_irq_type, unsigned char)'} [-Werror=incompatible-pointer-types]
.raise_irq = rockchip_pcie_ep_raise_irq,
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/pci/controller/pcie-rockchip-ep.c:516:15: note: (near initialization for 'rockchip_pcie_epc_ops.raise_irq')
cc1: some warnings being treated as errors
vim +516 drivers/pci/controller/pcie-rockchip-ep.c
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 507
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 508 static const struct pci_epc_ops rockchip_pcie_epc_ops = {
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 509 .write_header = rockchip_pcie_ep_write_header,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 510 .set_bar = rockchip_pcie_ep_set_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 511 .clear_bar = rockchip_pcie_ep_clear_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 512 .map_addr = rockchip_pcie_ep_map_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 513 .unmap_addr = rockchip_pcie_ep_unmap_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 514 .set_msi = rockchip_pcie_ep_set_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 515 .get_msi = rockchip_pcie_ep_get_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 @516 .raise_irq = rockchip_pcie_ep_raise_irq,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 517 .start = rockchip_pcie_ep_start,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 518 };
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 519
:::::: The code at line 516 was first introduced by commit
:::::: cf590b07839133146842d2d3d9a68f804c2edc4b PCI: rockchip: Add EP driver for Rockchip PCIe controller
:::::: TO: Shawn Lin <shawn.lin@rock-chips.com>
:::::: CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 50773 bytes --]
^ permalink raw reply
* Re: overlayfs: caller_credentials option bypass creator_cred
From: Vivek Goyal @ 2018-06-18 18:54 UTC (permalink / raw)
To: Mark Salyzyn
Cc: linux-kernel, Miklos Szeredi, Jonathan Corbet, linux-unionfs,
linux-doc
In-Reply-To: <20180618154222.19279-1-salyzyn@android.com>
On Mon, Jun 18, 2018 at 08:42:15AM -0700, Mark Salyzyn wrote:
> All accesses to the lower filesystems reference the creator (mount)
> and not the source context. This is a security issue.
Can you elaborate with an example that how this is a security issue.
mounter's check is in addition to caller's check. So we have two
checks in ovl_permission(). overlay inode gets the credentials from
underlying inode and we first check if caller is allowed to the
operation and if that's allowed, then we check if mounter is allowed
to do the operation.
IOW, mounter's check happen in addition to caller's checks. I am
wondering how did it end up being a security issue.
Vivek
>
> A module bool parameter and mount option caller_credentials is added
> to set the default, and to act as a presence check for this feature.
> The module parameter is used to change the default behavior because
> the 'normal' behavior of overlayfs is a _security_ violation
> providing the privileges of the creator to the user when accessing
> the files in the filesystems. But since I can not break user API,
> I have to preserve the original behavior as default.
>
> On MAC security model expect to set the caller_credentials to Y as
> part of early initialization to preserve security model when the
> option of iether caller_credentials or creator_credentials is not
> explicitly specified in the mount.
>
> Signed-off-by: Mark Salyzyn <salyzyn@android.com>
> Cc: Miklos Szeredi <miklos@szeredi.hu>
> Cc: Jonathan Corbet <corbet@lwn.net>
> Cc: linux-unionfs@vger.kernel.org
> Cc: linux-doc@vger.kernel.org
> Cc: linux-kernel@vger.kernel.org
> ---
> Documentation/filesystems/overlayfs.txt | 7 +++++++
> fs/overlayfs/copy_up.c | 3 ++-
> fs/overlayfs/dir.c | 12 ++++++++----
> fs/overlayfs/inode.c | 24 ++++++++++++++++--------
> fs/overlayfs/namei.c | 9 ++++++---
> fs/overlayfs/ovl_entry.h | 1 +
> fs/overlayfs/readdir.c | 6 ++++--
> fs/overlayfs/super.c | 22 ++++++++++++++++++++++
> fs/overlayfs/util.c | 8 ++++++--
> 9 files changed, 72 insertions(+), 20 deletions(-)
>
> diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
> index 72615a2c0752..4328be5cdaa9 100644
> --- a/Documentation/filesystems/overlayfs.txt
> +++ b/Documentation/filesystems/overlayfs.txt
> @@ -106,6 +106,13 @@ Only the lists of names from directories are merged. Other content
> such as metadata and extended attributes are reported for the upper
> directory only. These attributes of the lower directory are hidden.
>
> +credentials
> +-----------
> +
> +All access to the upper, lower and work directories is the creator's
> +credentials. If caller_credentials is set, then the access caller's
> +instance credentials will be used.
> +
> whiteouts and opaque directories
> --------------------------------
>
> diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
> index ddaddb4ce4c3..abc21844f712 100644
> --- a/fs/overlayfs/copy_up.c
> +++ b/fs/overlayfs/copy_up.c
> @@ -790,7 +790,8 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
> dput(parent);
> dput(next);
> }
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return err;
> }
> diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
> index f480b1a2cd2e..97473bb2ee60 100644
> --- a/fs/overlayfs/dir.c
> +++ b/fs/overlayfs/dir.c
> @@ -561,7 +561,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
> override_cred->fsgid = inode->i_gid;
> if (!attr->hardlink) {
> err = security_dentry_create_files_as(dentry,
> - attr->mode, &dentry->d_name, old_cred,
> + stat->mode, &dentry->d_name,
> + old_cred ? old_cred : current_cred(),
> override_cred);
> if (err) {
> put_cred(override_cred);
> @@ -577,7 +578,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
> err = ovl_create_over_whiteout(dentry, inode, attr);
> }
> out_revert_creds:
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> return err;
> }
>
> @@ -824,7 +826,8 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
> err = ovl_remove_upper(dentry, is_dir, &list);
> else
> err = ovl_remove_and_whiteout(dentry, &list);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> if (!err) {
> if (is_dir)
> clear_nlink(dentry->d_inode);
> @@ -1150,7 +1153,8 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
> out_unlock:
> unlock_rename(new_upperdir, old_upperdir);
> out_revert_creds:
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> ovl_nlink_end(new, locked);
> out_drop_write:
> ovl_drop_write(old);
> diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
> index ed16a898caeb..222678b6e67e 100644
> --- a/fs/overlayfs/inode.c
> +++ b/fs/overlayfs/inode.c
> @@ -49,7 +49,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
> inode_lock(upperdentry->d_inode);
> old_cred = ovl_override_creds(dentry->d_sb);
> err = notify_change(upperdentry, attr, NULL);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> if (!err)
> ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
> inode_unlock(upperdentry->d_inode);
> @@ -208,7 +209,8 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
> stat->nlink = dentry->d_inode->i_nlink;
>
> out:
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return err;
> }
> @@ -242,7 +244,8 @@ int ovl_permission(struct inode *inode, int mask)
> mask |= MAY_READ;
> }
> err = inode_permission(realinode, mask);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return err;
> }
> @@ -259,7 +262,8 @@ static const char *ovl_get_link(struct dentry *dentry,
>
> old_cred = ovl_override_creds(dentry->d_sb);
> p = vfs_get_link(ovl_dentry_real(dentry), done);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> return p;
> }
>
> @@ -302,7 +306,8 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
> WARN_ON(flags != XATTR_REPLACE);
> err = vfs_removexattr(realdentry, name);
> }
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> out_drop_write:
> ovl_drop_write(dentry);
> @@ -320,7 +325,8 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
>
> old_cred = ovl_override_creds(dentry->d_sb);
> res = vfs_getxattr(realdentry, name, value, size);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> return res;
> }
>
> @@ -344,7 +350,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
>
> old_cred = ovl_override_creds(dentry->d_sb);
> res = vfs_listxattr(realdentry, list, size);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> if (res <= 0 || size == 0)
> return res;
>
> @@ -379,7 +386,8 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
>
> old_cred = ovl_override_creds(inode->i_sb);
> acl = get_acl(realinode, type);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return acl;
> }
> diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
> index c993dd8db739..c8b84d262ec2 100644
> --- a/fs/overlayfs/namei.c
> +++ b/fs/overlayfs/namei.c
> @@ -1024,7 +1024,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
> OVL_I(inode)->redirect = upperredirect;
> }
>
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> dput(index);
> kfree(stack);
> kfree(d.redirect);
> @@ -1043,7 +1044,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
> kfree(upperredirect);
> out:
> kfree(d.redirect);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> return ERR_PTR(err);
> }
>
> @@ -1097,7 +1099,8 @@ bool ovl_lower_positive(struct dentry *dentry)
> dput(this);
> }
> }
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return positive;
> }
> diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
> index 41655a7d6894..7e17db561a04 100644
> --- a/fs/overlayfs/ovl_entry.h
> +++ b/fs/overlayfs/ovl_entry.h
> @@ -18,6 +18,7 @@ struct ovl_config {
> const char *redirect_mode;
> bool index;
> bool nfs_export;
> + bool caller_credentials;
> int xino;
> };
>
> diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
> index ef1fe42ff7bb..af3874d589ad 100644
> --- a/fs/overlayfs/readdir.c
> +++ b/fs/overlayfs/readdir.c
> @@ -289,7 +289,8 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
> }
> inode_unlock(dir->d_inode);
> }
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> return err;
> }
> @@ -906,7 +907,8 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
>
> old_cred = ovl_override_creds(dentry->d_sb);
> err = ovl_dir_read_merged(dentry, list, &root);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> if (err)
> return err;
>
> diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
> index 704b37311467..184688ab35cb 100644
> --- a/fs/overlayfs/super.c
> +++ b/fs/overlayfs/super.c
> @@ -56,6 +56,11 @@ module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644);
> MODULE_PARM_DESC(ovl_xino_auto_def,
> "Auto enable xino feature");
>
> +static bool __read_mostly ovl_caller_credentials;
> +module_param_named(caller_credentials, ovl_caller_credentials, bool, 0644);
> +MODULE_PARM_DESC(ovl_caller_credentials,
> + "Use caller credentials rather than creator credentials for accesses");
> +
> static void ovl_entry_stack_free(struct ovl_entry *oe)
> {
> unsigned int i;
> @@ -376,6 +381,10 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
> "on" : "off");
> if (ofs->config.xino != ovl_xino_def())
> seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
> + if (ofs->config.caller_credentials)
> + seq_puts(m, ",caller_credentials");
> + else
> + seq_puts(m, ",creator_credentials");
> return 0;
> }
>
> @@ -413,6 +422,8 @@ enum {
> OPT_XINO_ON,
> OPT_XINO_OFF,
> OPT_XINO_AUTO,
> + OPT_CREATOR_CREDENTIALS,
> + OPT_CALLER_CREDENTIALS,
> OPT_ERR,
> };
>
> @@ -429,6 +440,8 @@ static const match_table_t ovl_tokens = {
> {OPT_XINO_ON, "xino=on"},
> {OPT_XINO_OFF, "xino=off"},
> {OPT_XINO_AUTO, "xino=auto"},
> + {OPT_CREATOR_CREDENTIALS, "creator_credentials"},
> + {OPT_CALLER_CREDENTIALS, "caller_credentials"},
> {OPT_ERR, NULL}
> };
>
> @@ -486,6 +499,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
> if (!config->redirect_mode)
> return -ENOMEM;
>
> + config->caller_credentials = ovl_caller_credentials;
> while ((p = ovl_next_opt(&opt)) != NULL) {
> int token;
> substring_t args[MAX_OPT_ARGS];
> @@ -555,6 +569,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
> config->xino = OVL_XINO_AUTO;
> break;
>
> + case OPT_CREATOR_CREDENTIALS:
> + config->caller_credentials = false;
> + break;
> +
> + case OPT_CALLER_CREDENTIALS:
> + config->caller_credentials = true;
> + break;
> +
> default:
> pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
> return -EINVAL;
> diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
> index 6f1078028c66..538802289511 100644
> --- a/fs/overlayfs/util.c
> +++ b/fs/overlayfs/util.c
> @@ -40,6 +40,8 @@ const struct cred *ovl_override_creds(struct super_block *sb)
> {
> struct ovl_fs *ofs = sb->s_fs_info;
>
> + if (ofs->config.caller_credentials)
> + return NULL;
> return override_creds(ofs->creator_cred);
> }
>
> @@ -630,7 +632,8 @@ int ovl_nlink_start(struct dentry *dentry, bool *locked)
> * value relative to the upper inode nlink in an upper inode xattr.
> */
> err = ovl_set_nlink_upper(dentry);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
>
> out:
> if (err)
> @@ -650,7 +653,8 @@ void ovl_nlink_end(struct dentry *dentry, bool locked)
>
> old_cred = ovl_override_creds(dentry->d_sb);
> ovl_cleanup_index(dentry);
> - revert_creds(old_cred);
> + if (old_cred)
> + revert_creds(old_cred);
> }
>
> mutex_unlock(&OVL_I(d_inode(dentry))->lock);
> --
> 2.18.0.rc1.244.gcf134e6275-goog
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-unionfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: overlayfs: caller_credentials option bypass creator_cred
From: kbuild test robot @ 2018-06-18 18:57 UTC (permalink / raw)
To: Mark Salyzyn
Cc: kbuild-all, linux-kernel, Mark Salyzyn, Miklos Szeredi,
Jonathan Corbet, linux-unionfs, linux-doc
In-Reply-To: <20180618154222.19279-1-salyzyn@android.com>
[-- Attachment #1: Type: text/plain, Size: 2808 bytes --]
Hi Mark,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on linus/master]
[also build test ERROR on v4.18-rc1]
[cannot apply to miklos-vfs/overlayfs-next next-20180618]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Mark-Salyzyn/overlayfs-caller_credentials-option-bypass-creator_cred/20180619-012937
config: i386-randconfig-x014-201824 (attached as .config)
compiler: gcc-7 (Debian 7.3.0-16) 7.3.0
reproduce:
# save the attached .config to linux build tree
make ARCH=i386
All errors (new ones prefixed by >>):
fs//overlayfs/dir.c: In function 'ovl_create_or_link':
>> fs//overlayfs/dir.c:564:6: error: 'stat' undeclared (first use in this function)
stat->mode, &dentry->d_name,
^~~~
fs//overlayfs/dir.c:564:6: note: each undeclared identifier is reported only once for each function it appears in
vim +/stat +564 fs//overlayfs/dir.c
532
533 static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
534 struct ovl_cattr *attr, bool origin)
535 {
536 int err;
537 const struct cred *old_cred;
538 struct cred *override_cred;
539 struct dentry *parent = dentry->d_parent;
540
541 err = ovl_copy_up(parent);
542 if (err)
543 return err;
544
545 old_cred = ovl_override_creds(dentry->d_sb);
546
547 /*
548 * When linking a file with copy up origin into a new parent, mark the
549 * new parent dir "impure".
550 */
551 if (origin) {
552 err = ovl_set_impure(parent, ovl_dentry_upper(parent));
553 if (err)
554 goto out_revert_creds;
555 }
556
557 err = -ENOMEM;
558 override_cred = prepare_creds();
559 if (override_cred) {
560 override_cred->fsuid = inode->i_uid;
561 override_cred->fsgid = inode->i_gid;
562 if (!attr->hardlink) {
563 err = security_dentry_create_files_as(dentry,
> 564 stat->mode, &dentry->d_name,
565 old_cred ? old_cred : current_cred(),
566 override_cred);
567 if (err) {
568 put_cred(override_cred);
569 goto out_revert_creds;
570 }
571 }
572 put_cred(override_creds(override_cred));
573 put_cred(override_cred);
574
575 if (!ovl_dentry_is_whiteout(dentry))
576 err = ovl_create_upper(dentry, inode, attr);
577 else
578 err = ovl_create_over_whiteout(dentry, inode, attr);
579 }
580 out_revert_creds:
581 if (old_cred)
582 revert_creds(old_cred);
583 return err;
584 }
585
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 27478 bytes --]
^ permalink raw reply
* Re: [PATCH v4 03/10] PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq() signatures
From: kbuild test robot @ 2018-06-18 18:57 UTC (permalink / raw)
To: Gustavo Pimentel
Cc: kbuild-all, bhelgaas, lorenzo.pieralisi, Joao.Pinto, jingoohan1,
kishon, adouglas, jesper.nilsson, linux-pci, linux-doc,
linux-kernel, Gustavo Pimentel
In-Reply-To: <5bfa0cf053878e0e859a8b97227ca03ea4d50e92.1529329262.git.gustavo.pimentel@synopsys.com>
[-- Attachment #1: Type: text/plain, Size: 3091 bytes --]
Hi Gustavo,
Thank you for the patch! Yet something to improve:
[auto build test ERROR on pci/next]
[also build test ERROR on v4.18-rc1 next-20180618]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Gustavo-Pimentel/Add-MSI-X-support-on-pcitest-tool/20180619-004625
base: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git next
config: arm-allmodconfig (attached as .config)
compiler: arm-linux-gnueabi-gcc (Debian 7.2.0-11) 7.2.0
reproduce:
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
GCC_VERSION=7.2.0 make.cross ARCH=arm
All errors (new ones prefixed by >>):
>> drivers/pci/controller/pcie-rockchip-ep.c:516:15: error: initialization from incompatible pointer type [-Werror=incompatible-pointer-types]
.raise_irq = rockchip_pcie_ep_raise_irq,
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/pci/controller/pcie-rockchip-ep.c:516:15: note: (near initialization for 'rockchip_pcie_epc_ops.raise_irq')
cc1: some warnings being treated as errors
vim +516 drivers/pci/controller/pcie-rockchip-ep.c
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 507
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 508 static const struct pci_epc_ops rockchip_pcie_epc_ops = {
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 509 .write_header = rockchip_pcie_ep_write_header,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 510 .set_bar = rockchip_pcie_ep_set_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 511 .clear_bar = rockchip_pcie_ep_clear_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 512 .map_addr = rockchip_pcie_ep_map_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 513 .unmap_addr = rockchip_pcie_ep_unmap_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 514 .set_msi = rockchip_pcie_ep_set_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 515 .get_msi = rockchip_pcie_ep_get_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 @516 .raise_irq = rockchip_pcie_ep_raise_irq,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 517 .start = rockchip_pcie_ep_start,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 518 };
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 519
:::::: The code at line 516 was first introduced by commit
:::::: cf590b07839133146842d2d3d9a68f804c2edc4b PCI: rockchip: Add EP driver for Rockchip PCIe controller
:::::: TO: Shawn Lin <shawn.lin@rock-chips.com>
:::::: CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 65887 bytes --]
^ permalink raw reply
* [RFC PATCH] PCI: dwc: dw_pcie_ep_find_capability() can be static
From: kbuild test robot @ 2018-06-18 19:12 UTC (permalink / raw)
To: Gustavo Pimentel
Cc: kbuild-all, bhelgaas, lorenzo.pieralisi, Joao.Pinto, jingoohan1,
kishon, adouglas, jesper.nilsson, linux-pci, linux-doc,
linux-kernel, Gustavo Pimentel
In-Reply-To: <5beae521c5ee475b1c0e04f5eec07d0120b0fa2b.1529329262.git.gustavo.pimentel@synopsys.com>
Fixes: 43f8cf4686e0 ("PCI: dwc: Add MSI-X callbacks handler")
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
---
pcie-designware-ep.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index beee64e..ffc2065 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -59,7 +59,7 @@ static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr,
return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
}
-u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap)
+static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap)
{
u8 next_cap_ptr;
u16 reg;
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: overlayfs: caller_credentials option bypass creator_cred
From: Mark Salyzyn @ 2018-06-18 19:18 UTC (permalink / raw)
To: Vivek Goyal
Cc: linux-kernel, Miklos Szeredi, Jonathan Corbet, linux-unionfs,
linux-doc
In-Reply-To: <20180618185448.GA8749@redhat.com>
On 06/18/2018 11:54 AM, Vivek Goyal wrote:
> On Mon, Jun 18, 2018 at 08:42:15AM -0700, Mark Salyzyn wrote:
>> All accesses to the lower filesystems reference the creator (mount)
>> and not the source context. This is a security issue.
> Can you elaborate with an example that how this is a security issue.
> mounter's check is in addition to caller's check. So we have two
> checks in ovl_permission(). overlay inode gets the credentials from
> underlying inode and we first check if caller is allowed to the
> operation and if that's allowed, then we check if mounter is allowed
> to do the operation.
init which does the mount and represents the creator_cred which is
granted a restricted MAC to do just what it needs to do, eg mount, but
not be able to access the files. The caller comes in and is rejected
because init domain is not allowed, even though the caller's domain is.
MAC does not require overlap in privileges between the creator and the user.
-- Mark
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v2] overlayfs: caller_credentials option bypass creator_cred
From: Mark Salyzyn @ 2018-06-18 19:27 UTC (permalink / raw)
To: linux-kernel
Cc: Mark Salyzyn, Miklos Szeredi, Jonathan Corbet, Vivek Goyal,
linux-unionfs, linux-doc
All accesses to the lower filesystems reference the creator (mount)
context. This is a security issue as the user context does not
overlay the creator context.
A module bool parameter and mount option caller_credentials is added
to set the default, and to act as a presence check for this "feature".
The module parameter is used to change the default behavior, But
since I can not break user API, I have to preserve the original
behavior as default.
On MAC security model expect to set the caller_credentials to Y as
part of early initialization to preserve security model when the
option of iether caller_credentials or creator_credentials is not
explicitly specified in the mount.
Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Cc: Miklos Szeredi <miklos@szeredi.hu>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: linux-unionfs@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
v2:
- forward port changed attr to stat, resulting in a build error
- wording in commit message was too adversarial and needed correction
---
Documentation/filesystems/overlayfs.txt | 7 +++++++
fs/overlayfs/copy_up.c | 3 ++-
fs/overlayfs/dir.c | 12 ++++++++----
fs/overlayfs/inode.c | 24 ++++++++++++++++--------
fs/overlayfs/namei.c | 9 ++++++---
fs/overlayfs/ovl_entry.h | 1 +
fs/overlayfs/readdir.c | 6 ++++--
fs/overlayfs/super.c | 22 ++++++++++++++++++++++
fs/overlayfs/util.c | 8 ++++++--
9 files changed, 72 insertions(+), 20 deletions(-)
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 72615a2c0752..4328be5cdaa9 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -106,6 +106,13 @@ Only the lists of names from directories are merged. Other content
such as metadata and extended attributes are reported for the upper
directory only. These attributes of the lower directory are hidden.
+credentials
+-----------
+
+All access to the upper, lower and work directories is the creator's
+credentials. If caller_credentials is set, then the access caller's
+instance credentials will be used.
+
whiteouts and opaque directories
--------------------------------
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index ddaddb4ce4c3..abc21844f712 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -790,7 +790,8 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
dput(parent);
dput(next);
}
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return err;
}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index f480b1a2cd2e..8b75e0899ee1 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -561,7 +561,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
override_cred->fsgid = inode->i_gid;
if (!attr->hardlink) {
err = security_dentry_create_files_as(dentry,
- attr->mode, &dentry->d_name, old_cred,
+ attr->mode, &dentry->d_name,
+ old_cred ? old_cred : current_cred(),
override_cred);
if (err) {
put_cred(override_cred);
@@ -577,7 +578,8 @@ static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
err = ovl_create_over_whiteout(dentry, inode, attr);
}
out_revert_creds:
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return err;
}
@@ -824,7 +826,8 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
err = ovl_remove_upper(dentry, is_dir, &list);
else
err = ovl_remove_and_whiteout(dentry, &list);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
if (!err) {
if (is_dir)
clear_nlink(dentry->d_inode);
@@ -1150,7 +1153,8 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
out_unlock:
unlock_rename(new_upperdir, old_upperdir);
out_revert_creds:
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
ovl_nlink_end(new, locked);
out_drop_write:
ovl_drop_write(old);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index ed16a898caeb..222678b6e67e 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -49,7 +49,8 @@ int ovl_setattr(struct dentry *dentry, struct iattr *attr)
inode_lock(upperdentry->d_inode);
old_cred = ovl_override_creds(dentry->d_sb);
err = notify_change(upperdentry, attr, NULL);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
if (!err)
ovl_copyattr(upperdentry->d_inode, dentry->d_inode);
inode_unlock(upperdentry->d_inode);
@@ -208,7 +209,8 @@ int ovl_getattr(const struct path *path, struct kstat *stat,
stat->nlink = dentry->d_inode->i_nlink;
out:
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return err;
}
@@ -242,7 +244,8 @@ int ovl_permission(struct inode *inode, int mask)
mask |= MAY_READ;
}
err = inode_permission(realinode, mask);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return err;
}
@@ -259,7 +262,8 @@ static const char *ovl_get_link(struct dentry *dentry,
old_cred = ovl_override_creds(dentry->d_sb);
p = vfs_get_link(ovl_dentry_real(dentry), done);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return p;
}
@@ -302,7 +306,8 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
WARN_ON(flags != XATTR_REPLACE);
err = vfs_removexattr(realdentry, name);
}
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
out_drop_write:
ovl_drop_write(dentry);
@@ -320,7 +325,8 @@ int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_getxattr(realdentry, name, value, size);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return res;
}
@@ -344,7 +350,8 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
old_cred = ovl_override_creds(dentry->d_sb);
res = vfs_listxattr(realdentry, list, size);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
if (res <= 0 || size == 0)
return res;
@@ -379,7 +386,8 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
old_cred = ovl_override_creds(inode->i_sb);
acl = get_acl(realinode, type);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return acl;
}
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index c993dd8db739..c8b84d262ec2 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -1024,7 +1024,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
OVL_I(inode)->redirect = upperredirect;
}
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
dput(index);
kfree(stack);
kfree(d.redirect);
@@ -1043,7 +1044,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
kfree(upperredirect);
out:
kfree(d.redirect);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return ERR_PTR(err);
}
@@ -1097,7 +1099,8 @@ bool ovl_lower_positive(struct dentry *dentry)
dput(this);
}
}
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return positive;
}
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 41655a7d6894..7e17db561a04 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -18,6 +18,7 @@ struct ovl_config {
const char *redirect_mode;
bool index;
bool nfs_export;
+ bool caller_credentials;
int xino;
};
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index ef1fe42ff7bb..af3874d589ad 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -289,7 +289,8 @@ static int ovl_check_whiteouts(struct dentry *dir, struct ovl_readdir_data *rdd)
}
inode_unlock(dir->d_inode);
}
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
return err;
}
@@ -906,7 +907,8 @@ int ovl_check_empty_dir(struct dentry *dentry, struct list_head *list)
old_cred = ovl_override_creds(dentry->d_sb);
err = ovl_dir_read_merged(dentry, list, &root);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
if (err)
return err;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 704b37311467..184688ab35cb 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -56,6 +56,11 @@ module_param_named(xino_auto, ovl_xino_auto_def, bool, 0644);
MODULE_PARM_DESC(ovl_xino_auto_def,
"Auto enable xino feature");
+static bool __read_mostly ovl_caller_credentials;
+module_param_named(caller_credentials, ovl_caller_credentials, bool, 0644);
+MODULE_PARM_DESC(ovl_caller_credentials,
+ "Use caller credentials rather than creator credentials for accesses");
+
static void ovl_entry_stack_free(struct ovl_entry *oe)
{
unsigned int i;
@@ -376,6 +381,10 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
"on" : "off");
if (ofs->config.xino != ovl_xino_def())
seq_printf(m, ",xino=%s", ovl_xino_str[ofs->config.xino]);
+ if (ofs->config.caller_credentials)
+ seq_puts(m, ",caller_credentials");
+ else
+ seq_puts(m, ",creator_credentials");
return 0;
}
@@ -413,6 +422,8 @@ enum {
OPT_XINO_ON,
OPT_XINO_OFF,
OPT_XINO_AUTO,
+ OPT_CREATOR_CREDENTIALS,
+ OPT_CALLER_CREDENTIALS,
OPT_ERR,
};
@@ -429,6 +440,8 @@ static const match_table_t ovl_tokens = {
{OPT_XINO_ON, "xino=on"},
{OPT_XINO_OFF, "xino=off"},
{OPT_XINO_AUTO, "xino=auto"},
+ {OPT_CREATOR_CREDENTIALS, "creator_credentials"},
+ {OPT_CALLER_CREDENTIALS, "caller_credentials"},
{OPT_ERR, NULL}
};
@@ -486,6 +499,7 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
if (!config->redirect_mode)
return -ENOMEM;
+ config->caller_credentials = ovl_caller_credentials;
while ((p = ovl_next_opt(&opt)) != NULL) {
int token;
substring_t args[MAX_OPT_ARGS];
@@ -555,6 +569,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
config->xino = OVL_XINO_AUTO;
break;
+ case OPT_CREATOR_CREDENTIALS:
+ config->caller_credentials = false;
+ break;
+
+ case OPT_CALLER_CREDENTIALS:
+ config->caller_credentials = true;
+ break;
+
default:
pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
return -EINVAL;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 6f1078028c66..538802289511 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -40,6 +40,8 @@ const struct cred *ovl_override_creds(struct super_block *sb)
{
struct ovl_fs *ofs = sb->s_fs_info;
+ if (ofs->config.caller_credentials)
+ return NULL;
return override_creds(ofs->creator_cred);
}
@@ -630,7 +632,8 @@ int ovl_nlink_start(struct dentry *dentry, bool *locked)
* value relative to the upper inode nlink in an upper inode xattr.
*/
err = ovl_set_nlink_upper(dentry);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
out:
if (err)
@@ -650,7 +653,8 @@ void ovl_nlink_end(struct dentry *dentry, bool locked)
old_cred = ovl_override_creds(dentry->d_sb);
ovl_cleanup_index(dentry);
- revert_creds(old_cred);
+ if (old_cred)
+ revert_creds(old_cred);
}
mutex_unlock(&OVL_I(d_inode(dentry))->lock);
--
2.18.0.rc1.244.gcf134e6275-goog
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH v2] overlayfs: caller_credentials option bypass creator_cred
From: Mark Salyzyn @ 2018-06-18 19:32 UTC (permalink / raw)
To: linux-kernel
Cc: Miklos Szeredi, Jonathan Corbet, Vivek Goyal, linux-unionfs,
linux-doc
In-Reply-To: <20180618192726.67981-1-salyzyn@android.com>
On 06/18/2018 12:27 PM, Mark Salyzyn wrote:
> All accesses to the lower filesystems reference the creator (mount)
> context. This is a security issue as the user context does not
> overlay the creator context.
<sigh> been typing overlay far too many times, muscle memory struck!
"overlap the creator context."
-- Mark
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v4 03/10] PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq() signatures
From: kbuild test robot @ 2018-06-18 19:31 UTC (permalink / raw)
To: Gustavo Pimentel
Cc: kbuild-all, bhelgaas, lorenzo.pieralisi, Joao.Pinto, jingoohan1,
kishon, adouglas, jesper.nilsson, linux-pci, linux-doc,
linux-kernel, Gustavo Pimentel
In-Reply-To: <5bfa0cf053878e0e859a8b97227ca03ea4d50e92.1529329262.git.gustavo.pimentel@synopsys.com>
Hi Gustavo,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on pci/next]
[also build test WARNING on v4.18-rc1 next-20180618]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Gustavo-Pimentel/Add-MSI-X-support-on-pcitest-tool/20180619-004625
base: https://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci.git next
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
drivers/pci/controller/pcie-rockchip-ep.c:173:14: sparse: expression using sizeof(void)
>> drivers/pci/controller/pcie-rockchip-ep.c:516:27: sparse: incorrect type in initializer (incompatible argument 4 (different type sizes)) @@ expected int ( *raise_irq )( ... ) @@ got int ( *raise_irq )( ... ) @@
drivers/pci/controller/pcie-rockchip-ep.c:516:27: expected int ( *raise_irq )( ... )
drivers/pci/controller/pcie-rockchip-ep.c:516:27: got int ( *<noident> )( ... )
drivers/pci/controller/pcie-rockchip-ep.c:516:15: error: initialization from incompatible pointer type [-Werror=incompatible-pointer-types]
.raise_irq = rockchip_pcie_ep_raise_irq,
^~~~~~~~~~~~~~~~~~~~~~~~~~
drivers/pci/controller/pcie-rockchip-ep.c:516:15: note: (near initialization for 'rockchip_pcie_epc_ops.raise_irq')
cc1: some warnings being treated as errors
vim +516 drivers/pci/controller/pcie-rockchip-ep.c
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 507
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 508 static const struct pci_epc_ops rockchip_pcie_epc_ops = {
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 509 .write_header = rockchip_pcie_ep_write_header,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 510 .set_bar = rockchip_pcie_ep_set_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 511 .clear_bar = rockchip_pcie_ep_clear_bar,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 512 .map_addr = rockchip_pcie_ep_map_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 513 .unmap_addr = rockchip_pcie_ep_unmap_addr,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 514 .set_msi = rockchip_pcie_ep_set_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 515 .get_msi = rockchip_pcie_ep_get_msi,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 @516 .raise_irq = rockchip_pcie_ep_raise_irq,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 517 .start = rockchip_pcie_ep_start,
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 518 };
cf590b07 drivers/pci/host/pcie-rockchip-ep.c Shawn Lin 2018-05-09 519
:::::: The code at line 516 was first introduced by commit
:::::: cf590b07839133146842d2d3d9a68f804c2edc4b PCI: rockchip: Add EP driver for Rockchip PCIe controller
:::::: TO: Shawn Lin <shawn.lin@rock-chips.com>
:::::: CC: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH v3 1/3] PCI: Make specifying PCI devices in kernel parameters reusable
From: Logan Gunthorpe @ 2018-06-18 19:36 UTC (permalink / raw)
To: linux-kernel, linux-pci, linux-doc
Cc: Stephen Bates, Christoph Hellwig, Bjorn Helgaas, Jonathan Corbet,
Ingo Molnar, Thomas Gleixner, Paul E. McKenney, Marc Zyngier,
Kai-Heng Feng, Frederic Weisbecker, Dan Williams,
Jérôme Glisse, Benjamin Herrenschmidt, Alex Williamson,
Christian König, Logan Gunthorpe
In-Reply-To: <20180618193636.16210-1-logang@deltatee.com>
Separate out the code to match a PCI device with a string (typically
originating from a kernel parameter) from the
pci_specified_resource_alignment() function into its own helper
function.
While we are at it, this change fixes the kernel style of the function
(fixing a number of long lines and extra parentheses).
Additionally, make the analogous change to the kernel parameter
documentation: Separating the description of how to specify a PCI device
into it's own section at the head of the pci= parameter.
This patch should have no functional alterations.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Stephen Bates <sbates@raithlin.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
Documentation/admin-guide/kernel-parameters.txt | 26 +++-
drivers/pci/pci.c | 153 +++++++++++++++---------
2 files changed, 120 insertions(+), 59 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..760fb2b0b349 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2994,7 +2994,24 @@
See header of drivers/block/paride/pcd.c.
See also Documentation/blockdev/paride.txt.
- pci=option[,option...] [PCI] various PCI subsystem options:
+ pci=option[,option...] [PCI] various PCI subsystem options.
+
+ Some options herein operate on a specific device
+ or a set of devices (<pci_dev>). These are
+ specified in one of the following formats:
+
+ [<domain>:]<bus>:<slot>.<func>
+ pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+
+ Note: the first format specifies a PCI
+ bus/slot/function address which may change
+ if new hardware is inserted, if motherboard
+ firmware changes, or due to changes caused
+ by other kernel parameters. The second format
+ selects devices using IDs from the
+ configuration space which may match multiple
+ devices in the system.
+
earlydump [X86] dump PCI config space before the kernel
changes anything
off [X86] don't probe for the PCI bus
@@ -3123,11 +3140,10 @@
window. The default value is 64 megabytes.
resource_alignment=
Format:
- [<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
- [<order of align>@]pci:<vendor>:<device>\
- [:<subvendor>:<subdevice>][; ...]
+ [<order of align>@]<pci_dev>[; ...]
Specifies alignment and device to reassign
- aligned memory resources.
+ aligned memory resources. How to
+ specify the device is described above.
If <order of align> is not specified,
PAGE_SIZE is used as alignment.
PCI-PCI bridge can be specified, if resource
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..bec1bef6f326 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -191,6 +191,88 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
#endif
+/**
+ * pci_dev_str_match - test if a string matches a device
+ * @dev: the PCI device to test
+ * @p: string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) matches a
+ * specified. The string may be of one of two forms formats:
+ *
+ * [<domain>:]<bus>:<slot>.<func>
+ * pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+ *
+ * The first format specifies a PCI bus/slot/function address which
+ * may change if new hardware is inserted, if motherboard firmware changes,
+ * or due to changes caused in kernel parameters.
+ *
+ * The second format matches devices using IDs in the configuration
+ * space which may match multiple devices in the system. A value of 0
+ * for any field will match all devices.
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if the string cannot be parsed.
+ */
+static int pci_dev_str_match(struct pci_dev *dev, const char *p,
+ const char **endptr)
+{
+ int ret;
+ int seg, bus, slot, func, count;
+ unsigned short vendor, device, subsystem_vendor, subsystem_device;
+
+ if (strncmp(p, "pci:", 4) == 0) {
+ /* PCI vendor/device (subvendor/subdevice) ids are specified */
+ p += 4;
+ ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device,
+ &subsystem_vendor, &subsystem_device, &count);
+ if (ret != 4) {
+ ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count);
+ if (ret != 2)
+ return -EINVAL;
+
+ subsystem_vendor = 0;
+ subsystem_device = 0;
+ }
+
+ p += count;
+
+ if ((!vendor || vendor == dev->vendor) &&
+ (!device || device == dev->device) &&
+ (!subsystem_vendor ||
+ subsystem_vendor == dev->subsystem_vendor) &&
+ (!subsystem_device ||
+ subsystem_device == dev->subsystem_device))
+ goto found;
+
+ } else {
+ /* PCI Bus,Slot,Function ids are specified */
+ ret = sscanf(p, "%x:%x:%x.%x%n", &seg, &bus, &slot,
+ &func, &count);
+ if (ret != 4) {
+ seg = 0;
+ ret = sscanf(p, "%x:%x.%x%n", &bus, &slot,
+ &func, &count);
+ if (ret != 3)
+ return -EINVAL;
+ }
+
+ p += count;
+
+ if (seg == pci_domain_nr(dev->bus) &&
+ bus == dev->bus->number &&
+ slot == PCI_SLOT(dev->devfn) &&
+ func == PCI_FUNC(dev->devfn))
+ goto found;
+ }
+
+ *endptr = p;
+ return 0;
+
+found:
+ *endptr = p;
+ return 1;
+}
static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
u8 pos, int cap, int *ttl)
@@ -5454,10 +5536,10 @@ static DEFINE_SPINLOCK(resource_alignment_lock);
static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
bool *resize)
{
- int seg, bus, slot, func, align_order, count;
- unsigned short vendor, device, subsystem_vendor, subsystem_device;
+ int align_order, count;
resource_size_t align = pcibios_default_alignment();
- char *p;
+ const char *p;
+ int ret;
spin_lock(&resource_alignment_lock);
p = resource_alignment_param;
@@ -5477,58 +5559,21 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
} else {
align_order = -1;
}
- if (strncmp(p, "pci:", 4) == 0) {
- /* PCI vendor/device (subvendor/subdevice) ids are specified */
- p += 4;
- if (sscanf(p, "%hx:%hx:%hx:%hx%n",
- &vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) {
- if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) {
- printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n",
- p);
- break;
- }
- subsystem_vendor = subsystem_device = 0;
- }
- p += count;
- if ((!vendor || (vendor == dev->vendor)) &&
- (!device || (device == dev->device)) &&
- (!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) &&
- (!subsystem_device || (subsystem_device == dev->subsystem_device))) {
- *resize = true;
- if (align_order == -1)
- align = PAGE_SIZE;
- else
- align = 1 << align_order;
- /* Found */
- break;
- }
- }
- else {
- if (sscanf(p, "%x:%x:%x.%x%n",
- &seg, &bus, &slot, &func, &count) != 4) {
- seg = 0;
- if (sscanf(p, "%x:%x.%x%n",
- &bus, &slot, &func, &count) != 3) {
- /* Invalid format */
- printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
- p);
- break;
- }
- }
- p += count;
- if (seg == pci_domain_nr(dev->bus) &&
- bus == dev->bus->number &&
- slot == PCI_SLOT(dev->devfn) &&
- func == PCI_FUNC(dev->devfn)) {
- *resize = true;
- if (align_order == -1)
- align = PAGE_SIZE;
- else
- align = 1 << align_order;
- /* Found */
- break;
- }
+
+ ret = pci_dev_str_match(dev, p, &p);
+ if (ret == 1) {
+ *resize = true;
+ if (align_order == -1)
+ align = PAGE_SIZE;
+ else
+ align = 1 << align_order;
+ break;
+ } else if (ret < 0) {
+ pr_info("PCI: Can't parse resource_alignment parameter: pci:%s\n",
+ p);
+ break;
}
+
if (*p != ';' && *p != ',') {
/* End of param or invalid format */
break;
--
2.11.0
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH v3 3/3] PCI: Introduce the disable_acs_redir parameter
From: Logan Gunthorpe @ 2018-06-18 19:36 UTC (permalink / raw)
To: linux-kernel, linux-pci, linux-doc
Cc: Stephen Bates, Christoph Hellwig, Bjorn Helgaas, Jonathan Corbet,
Ingo Molnar, Thomas Gleixner, Paul E. McKenney, Marc Zyngier,
Kai-Heng Feng, Frederic Weisbecker, Dan Williams,
Jérôme Glisse, Benjamin Herrenschmidt, Alex Williamson,
Christian König, Logan Gunthorpe
In-Reply-To: <20180618193636.16210-1-logang@deltatee.com>
In order to support P2P traffic on a segment of the PCI hierarchy,
we must be able to disable the ACS redirect bits for select
PCI bridges. The bridges must be selected before the devices are
discovered by the kernel and the IOMMU groups created. Therefore,
a kernel command line parameter is created to specify devices
which must have their ACS bits disabled.
The new parameter takes a list of devices separated by a semicolon.
Each device specified will have it's ACS redirect bits disabled.
This is similar to the existing 'resource_alignment' parameter and just
like it we also create a sysfs bus attribute which can be used to
read the parameter. Writing the parameter is not supported
as it would require forcibly hot plugging the affected device as
well as all devices whose IOMMU groups might change.
The ACS Request P2P Request Redirect, P2P Completion Redirect and P2P
Egress Control bits are disabled which is sufficient to always allow
passing P2P traffic uninterrupted. The bits are set after the kernel
(optionally) enables the ACS bits itself. It is also done regardless of
whether the kernel sets the bits or not seeing some BIOS firmware is known
to set the bits on boot.
Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Stephen Bates <sbates@raithlin.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
Documentation/admin-guide/kernel-parameters.txt | 9 +++
drivers/pci/pci.c | 103 +++++++++++++++++++++++-
2 files changed, 110 insertions(+), 2 deletions(-)
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index d45285e1ab6a..2ec36e258bb0 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3190,6 +3190,15 @@
Adding the window is slightly risky (it may
conflict with unreported devices), so this
taints the kernel.
+ disable_acs_redir=<pci_dev>[; ...]
+ Specify one or more PCI devices (in the format
+ specified above) separated by semicolons.
+ Each device specified will have the PCI ACS
+ redirect capabilities forced off which will
+ allow P2P traffic between devices through
+ bridges without forcing it upstream. Note:
+ this removes isolation between devices and
+ will make the IOMMU groups less granular.
pcie_aspm= [PCIE] Forcibly enable or disable PCIe Active State Power
Management.
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 6fbad0492461..eb85bf507398 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2982,6 +2982,92 @@ void pci_request_acs(void)
pci_acs_enable = 1;
}
+#define DISABLE_ACS_REDIR_PARAM_SIZE COMMAND_LINE_SIZE
+static char disable_acs_redir_param[DISABLE_ACS_REDIR_PARAM_SIZE] = {0};
+static DEFINE_SPINLOCK(disable_acs_redir_lock);
+
+static ssize_t pci_set_disable_acs_redir_param(const char *buf, size_t count)
+{
+ if (count > DISABLE_ACS_REDIR_PARAM_SIZE - 1)
+ count = DISABLE_ACS_REDIR_PARAM_SIZE - 1;
+ spin_lock(&disable_acs_redir_lock);
+ strncpy(disable_acs_redir_param, buf, count);
+ disable_acs_redir_param[count] = '\0';
+ spin_unlock(&disable_acs_redir_lock);
+ return count;
+}
+
+static ssize_t pci_disable_acs_redir_show(struct bus_type *bus, char *buf)
+{
+ size_t count;
+
+ spin_lock(&disable_acs_redir_lock);
+ count = snprintf(buf, PAGE_SIZE, "%s\n", disable_acs_redir_param);
+ spin_unlock(&disable_acs_redir_lock);
+ return count;
+}
+
+static BUS_ATTR(disable_acs_redir, 0444, pci_disable_acs_redir_show, NULL);
+
+static int __init pci_disable_acs_redir_sysfs_init(void)
+{
+ return bus_create_file(&pci_bus_type, &bus_attr_disable_acs_redir);
+}
+late_initcall(pci_disable_acs_redir_sysfs_init);
+
+/**
+ * pci_disable_acs_redir - disable ACS redirect capabilities
+ * @dev: the PCI device
+ *
+ * For only devices specified in the disable_acs_redir parameter.
+ */
+static void pci_disable_acs_redir(struct pci_dev *dev)
+{
+ int ret = 0;
+ const char *p;
+ int pos;
+ u16 ctrl;
+
+ spin_lock(&disable_acs_redir_lock);
+
+ p = disable_acs_redir_param;
+ while (*p) {
+ ret = pci_dev_str_match(dev, p, &p);
+ if (ret < 0) {
+ pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
+ disable_acs_redir_param);
+
+ break;
+ } else if (ret == 1) {
+ /* Found a match */
+ break;
+ }
+
+ if (*p != ';' && *p != ',') {
+ /* End of param or invalid format */
+ break;
+ }
+ p++;
+ }
+ spin_unlock(&disable_acs_redir_lock);
+
+ if (ret != 1)
+ return;
+
+ pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+ if (!pos)
+ return;
+
+ pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+ /* P2P Request & Completion Redirect */
+ ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+ pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+ pci_info(dev, "disabled ACS redirect\n");
+}
+
/**
* pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
* @dev: the PCI device
@@ -3021,12 +3107,22 @@ static void pci_std_enable_acs(struct pci_dev *dev)
void pci_enable_acs(struct pci_dev *dev)
{
if (!pci_acs_enable)
- return;
+ goto disable_acs_redir;
if (!pci_dev_specific_enable_acs(dev))
- return;
+ goto disable_acs_redir;
pci_std_enable_acs(dev);
+
+disable_acs_redir:
+ /*
+ * Note: pci_disable_acs_redir() must be called even if
+ * ACS is not enabled by the kernel because the firmware
+ * may have unexpectedly set the flags. So if we are told
+ * to disable it, we should always disable it after setting
+ * the kernel's default preferences.
+ */
+ pci_disable_acs_redir(dev);
}
static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
@@ -5966,6 +6062,9 @@ static int __init pci_setup(char *str)
pcie_bus_config = PCIE_BUS_PEER2PEER;
} else if (!strncmp(str, "pcie_scan_all", 13)) {
pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+ } else if (!strncmp(str, "disable_acs_redir=", 18)) {
+ pci_set_disable_acs_redir_param(str + 18,
+ strlen(str + 18));
} else {
printk(KERN_ERR "PCI: Unknown option `%s'\n",
str);
--
2.11.0
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox