linux_old1/include/linux/vmalloc.h

192 lines
5.5 KiB
C
Raw Normal View History

#ifndef _LINUX_VMALLOC_H
#define _LINUX_VMALLOC_H
#include <linux/spinlock.h>
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
#include <linux/init.h>
#include <linux/list.h>
#include <asm/page.h> /* pgprot_t */
#include <linux/rbtree.h>
struct vm_area_struct; /* vma defining user mapping in mm_types.h */
/* bits in flags of vmalloc's vm_struct below */
#define VM_IOREMAP 0x00000001 /* ioremap() and friends */
#define VM_ALLOC 0x00000002 /* vmalloc() */
#define VM_MAP 0x00000004 /* vmap()ed pages */
#define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */
#define VM_VPAGES 0x00000010 /* buffer for pages was vmalloc'ed */
#define VM_UNLIST 0x00000020 /* vm_struct is not listed in vmlist */
/* bits [20..32] reserved for arch specific ioremap internals */
/*
* Maximum alignment for ioremap() regions.
* Can be overriden by arch-specific value.
*/
#ifndef IOREMAP_MAX_ORDER
#define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */
#endif
struct vm_struct {
struct vm_struct *next;
void *addr;
unsigned long size;
unsigned long flags;
struct page **pages;
unsigned int nr_pages;
phys_addr_t phys_addr;
const void *caller;
};
struct vmap_area {
unsigned long va_start;
unsigned long va_end;
unsigned long flags;
struct rb_node rb_node; /* address sorted rbtree */
struct list_head list; /* address sorted list */
struct list_head purge_list; /* "lazy purge" list */
struct vm_struct *vm;
struct rcu_head rcu_head;
};
/*
* Highlevel APIs for driver use
*/
mm: rewrite vmap layer Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and provide a fast, scalable percpu frontend for small vmaps (requires a slightly different API, though). The biggest problem with vmap is actually vunmap. Presently this requires a global kernel TLB flush, which on most architectures is a broadcast IPI to all CPUs to flush the cache. This is all done under a global lock. As the number of CPUs increases, so will the number of vunmaps a scaled workload will want to perform, and so will the cost of a global TLB flush. This gives terrible quadratic scalability characteristics. Another problem is that the entire vmap subsystem works under a single lock. It is a rwlock, but it is actually taken for write in all the fast paths, and the read locking would likely never be run concurrently anyway, so it's just pointless. This is a rewrite of vmap subsystem to solve those problems. The existing vmalloc API is implemented on top of the rewritten subsystem. The TLB flushing problem is solved by using lazy TLB unmapping. vmap addresses do not have to be flushed immediately when they are vunmapped, because the kernel will not reuse them again (would be a use-after-free) until they are reallocated. So the addresses aren't allocated again until a subsequent TLB flush. A single TLB flush then can flush multiple vunmaps from each CPU. XEN and PAT and such do not like deferred TLB flushing because they can't always handle multiple aliasing virtual addresses to a physical address. They now call vm_unmap_aliases() in order to flush any deferred mappings. That call is very expensive (well, actually not a lot more expensive than a single vunmap under the old scheme), however it should be OK if not called too often. The virtual memory extent information is stored in an rbtree rather than a linked list to improve the algorithmic scalability. There is a per-CPU allocator for small vmaps, which amortizes or avoids global locking. To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces must be used in place of vmap and vunmap. Vmalloc does not use these interfaces at the moment, so it will not be quite so scalable (although it will use lazy TLB flushing). As a quick test of performance, I ran a test that loops in the kernel, linearly mapping then touching then unmapping 4 pages. Different numbers of tests were run in parallel on an 4 core, 2 socket opteron. Results are in nanoseconds per map+touch+unmap. threads vanilla vmap rewrite 1 14700 2900 2 33600 3000 4 49500 2800 8 70631 2900 So with a 8 cores, the rewritten version is already 25x faster. In a slightly more realistic test (although with an older and less scalable version of the patch), I ripped the not-very-good vunmap batching code out of XFS, and implemented the large buffer mapping with vm_map_ram and vm_unmap_ram... along with a couple of other tricks, I was able to speed up a large directory workload by 20x on a 64 CPU system. I believe vmap/vunmap is actually sped up a lot more than 20x on such a system, but I'm running into other locks now. vmap is pretty well blown off the profiles. Before: 1352059 total 0.1401 798784 _write_lock 8320.6667 <- vmlist_lock 529313 default_idle 1181.5022 15242 smp_call_function 15.8771 <- vmap tlb flushing 2472 __get_vm_area_node 1.9312 <- vmap 1762 remove_vm_area 4.5885 <- vunmap 316 map_vm_area 0.2297 <- vmap 312 kfree 0.1950 300 _spin_lock 3.1250 252 sn_send_IPI_phys 0.4375 <- tlb flushing 238 vmap 0.8264 <- vmap 216 find_lock_page 0.5192 196 find_next_bit 0.3603 136 sn2_send_IPI 0.2024 130 pio_phys_write_mmr 2.0312 118 unmap_kernel_range 0.1229 After: 78406 total 0.0081 40053 default_idle 89.4040 33576 ia64_spinlock_contention 349.7500 1650 _spin_lock 17.1875 319 __reg_op 0.5538 281 _atomic_dec_and_lock 1.0977 153 mutex_unlock 1.5938 123 iget_locked 0.1671 117 xfs_dir_lookup 0.1662 117 dput 0.1406 114 xfs_iget_core 0.0268 92 xfs_da_hashname 0.1917 75 d_alloc 0.0670 68 vmap_page_range 0.0462 <- vmap 58 kmem_cache_alloc 0.0604 57 memset 0.0540 52 rb_next 0.1625 50 __copy_user 0.0208 49 bitmap_find_free_region 0.2188 <- vmap 46 ia64_sn_udelay 0.1106 45 find_inode_fast 0.1406 42 memcmp 0.2188 42 finish_task_switch 0.1094 42 __d_lookup 0.0410 40 radix_tree_lookup_slot 0.1250 37 _spin_unlock_irqrestore 0.3854 36 xfs_bmapi 0.0050 36 kmem_cache_free 0.0256 35 xfs_vn_getattr 0.0322 34 radix_tree_lookup 0.1062 33 __link_path_walk 0.0035 31 xfs_da_do_buf 0.0091 30 _xfs_buf_find 0.0204 28 find_get_page 0.0875 27 xfs_iread 0.0241 27 __strncpy_from_user 0.2812 26 _xfs_buf_initialize 0.0406 24 _xfs_buf_lookup_pages 0.0179 24 vunmap_page_range 0.0250 <- vunmap 23 find_lock_page 0.0799 22 vm_map_ram 0.0087 <- vmap 20 kfree 0.0125 19 put_page 0.0330 18 __kmalloc 0.0176 17 xfs_da_node_lookup_int 0.0086 17 _read_lock 0.0885 17 page_waitqueue 0.0664 vmap has gone from being the top 5 on the profiles and flushing the crap out of all TLBs, to using less than 1% of kernel time. [akpm@linux-foundation.org: cleanups, section fix] [akpm@linux-foundation.org: fix build on alpha] Signed-off-by: Nick Piggin <npiggin@suse.de> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Krzysztof Helt <krzysztof.h1@poczta.fm> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-10-19 11:27:03 +08:00
extern void vm_unmap_ram(const void *mem, unsigned int count);
extern void *vm_map_ram(struct page **pages, unsigned int count,
int node, pgprot_t prot);
extern void vm_unmap_aliases(void);
#ifdef CONFIG_MMU
extern void __init vmalloc_init(void);
#else
static inline void vmalloc_init(void)
{
}
#endif
extern void *vmalloc(unsigned long size);
extern void *vzalloc(unsigned long size);
extern void *vmalloc_user(unsigned long size);
extern void *vmalloc_node(unsigned long size, int node);
extern void *vzalloc_node(unsigned long size, int node);
extern void *vmalloc_exec(unsigned long size);
extern void *vmalloc_32(unsigned long size);
extern void *vmalloc_32_user(unsigned long size);
extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
unsigned long start, unsigned long end, gfp_t gfp_mask,
pgprot_t prot, int node, const void *caller);
extern void vfree(const void *addr);
extern void *vmap(struct page **pages, unsigned int count,
unsigned long flags, pgprot_t prot);
extern void vunmap(const void *addr);
extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
unsigned long pgoff);
void vmalloc_sync_all(void);
/*
* Lowlevel-APIs (not for driver use!)
*/
static inline size_t get_vm_area_size(const struct vm_struct *area)
{
/* return actual size without guard page */
return area->size - PAGE_SIZE;
}
extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags);
vmallocinfo: add caller information Add caller information so that /proc/vmallocinfo shows where the allocation request for a slice of vmalloc memory originated. Results in output like this: 0xffffc20000000000-0xffffc20000801000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20000801000-0xffffc20000806000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000806000-0xffffc20000c07000 4198400 alloc_large_system_hash+0x127/0x246 pages=1024 vmalloc vpages 0xffffc20000c07000-0xffffc20000c0a000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c0a000-0xffffc20000c0c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c0c000-0xffffc20000c0f000 12288 acpi_os_map_memory+0x13/0x1c phys=cff64000 ioremap 0xffffc20000c10000-0xffffc20000c15000 20480 acpi_os_map_memory+0x13/0x1c phys=cff65000 ioremap 0xffffc20000c16000-0xffffc20000c18000 8192 acpi_os_map_memory+0x13/0x1c phys=cff69000 ioremap 0xffffc20000c18000-0xffffc20000c1a000 8192 acpi_os_map_memory+0x13/0x1c phys=fed1f000 ioremap 0xffffc20000c1a000-0xffffc20000c1c000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1c000-0xffffc20000c1e000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c1e000-0xffffc20000c20000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c20000-0xffffc20000c22000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c22000-0xffffc20000c24000 8192 acpi_os_map_memory+0x13/0x1c phys=cff68000 ioremap 0xffffc20000c24000-0xffffc20000c26000 8192 acpi_os_map_memory+0x13/0x1c phys=e0081000 ioremap 0xffffc20000c26000-0xffffc20000c28000 8192 acpi_os_map_memory+0x13/0x1c phys=e0080000 ioremap 0xffffc20000c28000-0xffffc20000c2d000 20480 alloc_large_system_hash+0x127/0x246 pages=4 vmalloc 0xffffc20000c2d000-0xffffc20000c31000 16384 tcp_init+0xd5/0x31c pages=3 vmalloc 0xffffc20000c31000-0xffffc20000c34000 12288 alloc_large_system_hash+0x127/0x246 pages=2 vmalloc 0xffffc20000c34000-0xffffc20000c36000 8192 init_vdso_vars+0xde/0x1f1 0xffffc20000c36000-0xffffc20000c38000 8192 pci_iomap+0x8a/0xb4 phys=d8e00000 ioremap 0xffffc20000c38000-0xffffc20000c3a000 8192 usb_hcd_pci_probe+0x139/0x295 [usbcore] phys=d8e00000 ioremap 0xffffc20000c3a000-0xffffc20000c3e000 16384 sys_swapon+0x509/0xa15 pages=3 vmalloc 0xffffc20000c40000-0xffffc20000c61000 135168 e1000_probe+0x1c4/0xa32 phys=d8a20000 ioremap 0xffffc20000c61000-0xffffc20000c6a000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c6a000-0xffffc20000c73000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c73000-0xffffc20000c7c000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20000c7c000-0xffffc20000c7f000 12288 e1000e_setup_tx_resources+0x29/0xbe pages=2 vmalloc 0xffffc20000c80000-0xffffc20001481000 8392704 pci_mmcfg_arch_init+0x90/0x118 phys=e0000000 ioremap 0xffffc20001481000-0xffffc20001682000 2101248 alloc_large_system_hash+0x127/0x246 pages=512 vmalloc 0xffffc20001682000-0xffffc20001e83000 8392704 alloc_large_system_hash+0x127/0x246 pages=2048 vmalloc vpages 0xffffc20001e83000-0xffffc20002204000 3674112 alloc_large_system_hash+0x127/0x246 pages=896 vmalloc vpages 0xffffc20002204000-0xffffc2000220d000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000220d000-0xffffc20002216000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002216000-0xffffc2000221f000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc2000221f000-0xffffc20002228000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002228000-0xffffc20002231000 36864 _xfs_buf_map_pages+0x8e/0xc0 vmap 0xffffc20002231000-0xffffc20002234000 12288 e1000e_setup_rx_resources+0x35/0x122 pages=2 vmalloc 0xffffc20002240000-0xffffc20002261000 135168 e1000_probe+0x1c4/0xa32 phys=d8a60000 ioremap 0xffffc20002261000-0xffffc2000270c000 4894720 sys_swapon+0x509/0xa15 pages=1194 vmalloc vpages 0xffffffffa0000000-0xffffffffa0022000 139264 module_alloc+0x4f/0x55 pages=33 vmalloc 0xffffffffa0022000-0xffffffffa0029000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc 0xffffffffa002b000-0xffffffffa0034000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa0034000-0xffffffffa003d000 36864 module_alloc+0x4f/0x55 pages=8 vmalloc 0xffffffffa003d000-0xffffffffa0049000 49152 module_alloc+0x4f/0x55 pages=11 vmalloc 0xffffffffa0049000-0xffffffffa0050000 28672 module_alloc+0x4f/0x55 pages=6 vmalloc [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Christoph Lameter <clameter@sgi.com> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hugh Dickins <hugh@veritas.com> Cc: Nick Piggin <nickpiggin@yahoo.com.au> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-04-28 17:12:42 +08:00
extern struct vm_struct *get_vm_area_caller(unsigned long size,
unsigned long flags, const void *caller);
extern struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end);
extern struct vm_struct *__get_vm_area_caller(unsigned long size,
unsigned long flags,
unsigned long start, unsigned long end,
const void *caller);
extern struct vm_struct *remove_vm_area(const void *addr);
extern struct vm_struct *find_vm_area(const void *addr);
extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
struct page ***pages);
#ifdef CONFIG_MMU
extern int map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages);
extern void unmap_kernel_range_noflush(unsigned long addr, unsigned long size);
extern void unmap_kernel_range(unsigned long addr, unsigned long size);
#else
static inline int
map_kernel_range_noflush(unsigned long start, unsigned long size,
pgprot_t prot, struct page **pages)
{
return size >> PAGE_SHIFT;
}
static inline void
unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
{
}
static inline void
unmap_kernel_range(unsigned long addr, unsigned long size)
{
}
#endif
/* Allocate/destroy a 'vmalloc' VM area. */
extern struct vm_struct *alloc_vm_area(size_t size, pte_t **ptes);
extern void free_vm_area(struct vm_struct *area);
/* for /dev/kmem */
extern long vread(char *buf, char *addr, unsigned long count);
extern long vwrite(char *buf, char *addr, unsigned long count);
/*
* Internals. Dont't use..
*/
extern struct list_head vmap_area_list;
extern __init void vm_area_add_early(struct vm_struct *vm);
extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
#ifdef CONFIG_SMP
# ifdef CONFIG_MMU
struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align);
void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
# else
static inline struct vm_struct **
pcpu_get_vm_areas(const unsigned long *offsets,
const size_t *sizes, int nr_vms,
size_t align)
{
return NULL;
}
static inline void
pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
{
}
# endif
#endif
struct vmalloc_info {
unsigned long used;
unsigned long largest_chunk;
};
#ifdef CONFIG_MMU
#define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START)
extern void get_vmalloc_info(struct vmalloc_info *vmi);
#else
#define VMALLOC_TOTAL 0UL
#define get_vmalloc_info(vmi) \
do { \
(vmi)->used = 0; \
(vmi)->largest_chunk = 0; \
} while (0)
#endif
#endif /* _LINUX_VMALLOC_H */