kmalloc分配物理内存与高端内存映射--Linux内存管理(十八)

//  http://lxr.free-electrons.com/source/include/linux/gfp.h?v=4.7

/*  line 12 ~ line 44  第一部分
 *  定义可掩码所在位的信息, 每个掩码对应一位为1
 *  定义形式为  #define  ___GFP_XXX      0x01u
 */
/* Plain integer GFP bitmasks. Do not use this directly. */
#define ___GFP_DMA              0x01u
#define ___GFP_HIGHMEM          0x02u
#define ___GFP_DMA32            0x04u
#define ___GFP_MOVABLE          0x08u
/*  ......  */

/*  line 46 ~ line 192  第二部分
 *  定义掩码和MASK信息, 第二部分的某些宏可能是第一部分一个或者几个的组合
 *  定义形式为  #define  __GFP_XXX        ((__force gfp_t)___GFP_XXX)
 */
#define __GFP_DMA       ((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM   ((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32     ((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE   ((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
#define GFP_ZONEMASK    (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)

/*  line 194 ~ line 260  第三部分
 *  定义掩码
 *  定义形式为  #define  GFP_XXX      __GFP_XXX
 */
#define GFP_DMA         __GFP_DMA
#define GFP_DMA32       __GFP_DMA32

/*
* Physical address zone modifiers (see linux/mmzone.h - low four bits)
*
* Do not put any conditional on these. If necessary modify the definitions
* without the underscores and use them consistently. The definitions here may
* be used in bit comparisons.
* 定义区描述符
*/
#define __GFP_DMA       ((__force gfp_t)___GFP_DMA)
#define __GFP_HIGHMEM   ((__force gfp_t)___GFP_HIGHMEM)
#define __GFP_DMA32     ((__force gfp_t)___GFP_DMA32)
#define __GFP_MOVABLE   ((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
#define GFP_ZONEMASK    (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)

/*
* Page mobility and placement hints
*
* These flags provide hints about how mobile the page is. Pages with similar
* mobility are placed within the same pageblocks to minimise problems due
* to external fragmentation.
*
* __GFP_MOVABLE (also a zone modifier) indicates that the page can be
*   moved by page migration during memory compaction or can be reclaimed.
*
* __GFP_RECLAIMABLE is used for slab allocations that specify
*   SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
*
* __GFP_WRITE indicates the caller intends to dirty the page. Where possible,
*   these pages will be spread between local zones to avoid all the dirty
*   pages being in one zone (fair zone allocation policy).
*
* __GFP_HARDWALL enforces the cpuset memory allocation policy.
*
* __GFP_THISNODE forces the allocation to be satisified from the requested
*   node with no fallbacks or placement policy enforcements.
*
* __GFP_ACCOUNT causes the allocation to be accounted to kmemcg (only relevant
*   to kmem allocations).
*/
#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
#define __GFP_WRITE     ((__force gfp_t)___GFP_WRITE)
#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
#define __GFP_THISNODE  ((__force gfp_t)___GFP_THISNODE)
#define __GFP_ACCOUNT   ((__force gfp_t)___GFP_ACCOUNT)

/*
* Watermark modifiers -- controls access to emergency reserves
*
* __GFP_HIGH indicates that the caller is high-priority and that granting
*   the request is necessary before the system can make forward progress.
*   For example, creating an IO context to clean pages.
*
* __GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
*   high priority. Users are typically interrupt handlers. This may be
*   used in conjunction with __GFP_HIGH
 *
 * __GFP_MEMALLOC allows access to all memory. This should only be used when
 *   the caller guarantees the allocation will allow more memory to be freed
 *   very shortly e.g. process exiting or swapping. Users either should
 *   be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
 *
 * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
 *   This takes precedence over the __GFP_MEMALLOC flag if both are set.
 */
#define __GFP_ATOMIC    ((__force gfp_t)___GFP_ATOMIC)
#define __GFP_HIGH      ((__force gfp_t)___GFP_HIGH)
#define __GFP_MEMALLOC  ((__force gfp_t)___GFP_MEMALLOC)
#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)

/*
 * Reclaim modifiers
 *
 * __GFP_IO can start physical IO.
 *
 * __GFP_FS can call down to the low-level FS. Clearing the flag avoids the
 *   allocator recursing into the filesystem which might already be holding
 *   locks.
 *
 * __GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
 *   This flag can be cleared to avoid unnecessary delays when a fallback
 *   option is available.
 *
 * __GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
 *   the low watermark is reached and have it reclaim pages until the high
 *   watermark is reached. A caller may wish to clear this flag when fallback
 *   options are available and the reclaim is likely to disrupt the system. The
 *   canonical example is THP allocation where a fallback is cheap but
 *   reclaim/compaction may cause indirect stalls.
 *
 * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
 *
 * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
 *   _might_ fail.  This depends upon the particular VM implementation.
 *
 * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
 *   cannot handle allocation failures. New users should be evaluated carefully
 *   (and the flag should be used only when there is no reasonable failure
 *   policy) but it is definitely preferable to use the flag rather than
 *   opencode endless loop around allocator.
 *
 * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
 *   return NULL when direct reclaim and memory compaction have failed to allow
 *   the allocation to succeed.  The OOM killer is not called with the current
 *   implementation.
 */
#define __GFP_IO        ((__force gfp_t)___GFP_IO)
#define __GFP_FS        ((__force gfp_t)___GFP_FS)
#define __GFP_DIRECT_RECLAIM    ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
#define __GFP_KSWAPD_RECLAIM    ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
#define __GFP_REPEAT    ((__force gfp_t)___GFP_REPEAT)
#define __GFP_NOFAIL    ((__force gfp_t)___GFP_NOFAIL)
#define __GFP_NORETRY   ((__force gfp_t)___GFP_NORETRY)

/*
 * Action modifiers
 *
 * __GFP_COLD indicates that the caller does not expect to be used in the near
 *   future. Where possible, a cache-cold page will be returned.
 *
 * __GFP_NOWARN suppresses allocation failure reports.
 *
 * __GFP_COMP address compound page metadata.
 *
 * __GFP_ZERO returns a zeroed page on success.
 *
 * __GFP_NOTRACK avoids tracking with kmemcheck.
 *
 * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
 *   distinguishing in the source between false positives and allocations that
 *   cannot be supported (e.g. page tables).
 *
 * __GFP_OTHER_NODE is for allocations that are on a remote node but that
 *   should not be accounted for as a remote allocation in vmstat. A
 *   typical user would be khugepaged collapsing a huge page on a remote
 *   node.
 */
#define __GFP_COLD      ((__force gfp_t)___GFP_COLD)
#define __GFP_NOWARN    ((__force gfp_t)___GFP_NOWARN)
#define __GFP_COMP      ((__force gfp_t)___GFP_COMP)
#define __GFP_ZERO      ((__force gfp_t)___GFP_ZERO)
#define __GFP_NOTRACK   ((__force gfp_t)___GFP_NOTRACK)
#define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE)

/* Room for N __GFP_FOO bits */
#define __GFP_BITS_SHIFT 26
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))

#define GFP_ZONEMASK    (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)

/* Room for N __GFP_FOO bits */
#define __GFP_BITS_SHIFT 26
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))

ptr = kmalloc(size, __GFP_IO | __GFP_FS);

#define GFP_ATOMIC      (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
#define GFP_KERNEL      (__GFP_RECLAIM | __GFP_IO | __GFP_FS)
#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
#define GFP_NOWAIT      (__GFP_KSWAPD_RECLAIM)
#define GFP_NOIO        (__GFP_RECLAIM)
#define GFP_NOFS        (__GFP_RECLAIM | __GFP_IO)
#define GFP_TEMPORARY   (__GFP_RECLAIM | __GFP_IO | __GFP_FS | \
                         __GFP_RECLAIMABLE)
#define GFP_USER        (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
#define GFP_DMA         __GFP_DMA
#define GFP_DMA32       __GFP_DMA32
#define GFP_HIGHUSER    (GFP_USER | __GFP_HIGHMEM)
#define GFP_HIGHUSER_MOVABLE    (GFP_HIGHUSER | __GFP_MOVABLE)
#define GFP_TRANSHUGE   ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
                         __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
                         ~__GFP_RECLAIM)

/* Convert GFP flags to their corresponding migrate type */
#define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
#define GFP_MOVABLE_SHIFT 3

bit       result
=================
0x0    => NORMAL
0x1    => DMA or NORMAL
0x2    => HIGHMEM or NORMAL
0x3    => BAD (DMA+HIGHMEM)
0x4    => DMA32 or DMA or NORMAL
0x5    => BAD (DMA+DMA32)
0x6    => BAD (HIGHMEM+DMA32)
0x7    => BAD (HIGHMEM+DMA32+DMA)
0x8    => NORMAL (MOVABLE+0)
0x9    => DMA or NORMAL (MOVABLE+DMA)
0xa    => MOVABLE (Movable is valid only if HIGHMEM is set too)
0xb    => BAD (MOVABLE+HIGHMEM+DMA)
0xc    => DMA32 (MOVABLE+DMA32)
0xd    => BAD (MOVABLE+DMA32+DMA)
0xe    => BAD (MOVABLE+DMA32+HIGHMEM)
0xf    => BAD (MOVABLE+DMA32+HIGHMEM+DMA)

GFP_ZONES_SHIFT must be <= 2 on 32 bit platforms.

static inline enum zone_type gfp_zone(gfp_t flags)
{
    enum zone_type z;
    int bit = (__force int) (flags & GFP_ZONEMASK);

    z = (GFP_ZONE_TABLE >> (bit * GFP_ZONES_SHIFT)) &
                     ((1 << GFP_ZONES_SHIFT) - 1);
    VM_BUG_ON((GFP_ZONE_BAD >> bit) & 1);
    return z;
}

#if defined(CONFIG_ZONE_DEVICE) && (MAX_NR_ZONES-1) <= 4
/* ZONE_DEVICE is not a valid GFP zone specifier */
#define GFP_ZONES_SHIFT 2
#else
#define GFP_ZONES_SHIFT ZONES_SHIFT
#endif

#if 16 * GFP_ZONES_SHIFT > BITS_PER_LONG
#error GFP_ZONES_SHIFT too large to create GFP_ZONE_TABLE integer
#endif