| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 1 | /* | 
|  | 2 | * VMware Balloon driver. | 
|  | 3 | * | 
|  | 4 | * Copyright (C) 2000-2010, VMware, Inc. All Rights Reserved. | 
|  | 5 | * | 
|  | 6 | * This program is free software; you can redistribute it and/or modify it | 
|  | 7 | * under the terms of the GNU General Public License as published by the | 
|  | 8 | * Free Software Foundation; version 2 of the License and no later version. | 
|  | 9 | * | 
|  | 10 | * This program is distributed in the hope that it will be useful, but | 
|  | 11 | * WITHOUT ANY WARRANTY; without even the implied warranty of | 
|  | 12 | * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or | 
|  | 13 | * NON INFRINGEMENT.  See the GNU General Public License for more | 
|  | 14 | * details. | 
|  | 15 | * | 
|  | 16 | * You should have received a copy of the GNU General Public License | 
|  | 17 | * along with this program; if not, write to the Free Software | 
|  | 18 | * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA. | 
|  | 19 | * | 
|  | 20 | * Maintained by: Dmitry Torokhov <dtor@vmware.com> | 
|  | 21 | */ | 
|  | 22 |  | 
|  | 23 | /* | 
|  | 24 | * This is VMware physical memory management driver for Linux. The driver | 
|  | 25 | * acts like a "balloon" that can be inflated to reclaim physical pages by | 
|  | 26 | * reserving them in the guest and invalidating them in the monitor, | 
|  | 27 | * freeing up the underlying machine pages so they can be allocated to | 
|  | 28 | * other guests.  The balloon can also be deflated to allow the guest to | 
|  | 29 | * use more physical memory. Higher level policies can control the sizes | 
|  | 30 | * of balloons in VMs in order to manage physical memory resources. | 
|  | 31 | */ | 
|  | 32 |  | 
|  | 33 | //#define DEBUG | 
|  | 34 | #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt | 
|  | 35 |  | 
|  | 36 | #include <linux/types.h> | 
|  | 37 | #include <linux/kernel.h> | 
|  | 38 | #include <linux/mm.h> | 
|  | 39 | #include <linux/sched.h> | 
|  | 40 | #include <linux/module.h> | 
|  | 41 | #include <linux/workqueue.h> | 
|  | 42 | #include <linux/debugfs.h> | 
|  | 43 | #include <linux/seq_file.h> | 
| H. Peter Anvin | a10a569 | 2010-05-09 01:13:42 -0700 | [diff] [blame] | 44 | #include <asm/hypervisor.h> | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 45 |  | 
|  | 46 | MODULE_AUTHOR("VMware, Inc."); | 
|  | 47 | MODULE_DESCRIPTION("VMware Memory Control (Balloon) Driver"); | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 48 | MODULE_VERSION("1.2.1.3-k"); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 49 | MODULE_ALIAS("dmi:*:svnVMware*:*"); | 
|  | 50 | MODULE_ALIAS("vmware_vmmemctl"); | 
|  | 51 | MODULE_LICENSE("GPL"); | 
|  | 52 |  | 
|  | 53 | /* | 
|  | 54 | * Various constants controlling rate of inflaint/deflating balloon, | 
|  | 55 | * measured in pages. | 
|  | 56 | */ | 
|  | 57 |  | 
|  | 58 | /* | 
|  | 59 | * Rate of allocating memory when there is no memory pressure | 
|  | 60 | * (driver performs non-sleeping allocations). | 
|  | 61 | */ | 
|  | 62 | #define VMW_BALLOON_NOSLEEP_ALLOC_MAX	16384U | 
|  | 63 |  | 
|  | 64 | /* | 
|  | 65 | * Rates of memory allocaton when guest experiences memory pressure | 
|  | 66 | * (driver performs sleeping allocations). | 
|  | 67 | */ | 
|  | 68 | #define VMW_BALLOON_RATE_ALLOC_MIN	512U | 
|  | 69 | #define VMW_BALLOON_RATE_ALLOC_MAX	2048U | 
|  | 70 | #define VMW_BALLOON_RATE_ALLOC_INC	16U | 
|  | 71 |  | 
|  | 72 | /* | 
|  | 73 | * Rates for releasing pages while deflating balloon. | 
|  | 74 | */ | 
|  | 75 | #define VMW_BALLOON_RATE_FREE_MIN	512U | 
|  | 76 | #define VMW_BALLOON_RATE_FREE_MAX	16384U | 
|  | 77 | #define VMW_BALLOON_RATE_FREE_INC	16U | 
|  | 78 |  | 
|  | 79 | /* | 
|  | 80 | * When guest is under memory pressure, use a reduced page allocation | 
|  | 81 | * rate for next several cycles. | 
|  | 82 | */ | 
|  | 83 | #define VMW_BALLOON_SLOW_CYCLES		4 | 
|  | 84 |  | 
|  | 85 | /* | 
|  | 86 | * Use __GFP_HIGHMEM to allow pages from HIGHMEM zone. We don't | 
|  | 87 | * allow wait (__GFP_WAIT) for NOSLEEP page allocations. Use | 
|  | 88 | * __GFP_NOWARN, to suppress page allocation failure warnings. | 
|  | 89 | */ | 
|  | 90 | #define VMW_PAGE_ALLOC_NOSLEEP		(__GFP_HIGHMEM|__GFP_NOWARN) | 
|  | 91 |  | 
|  | 92 | /* | 
|  | 93 | * Use GFP_HIGHUSER when executing in a separate kernel thread | 
|  | 94 | * context and allocation can sleep.  This is less stressful to | 
|  | 95 | * the guest memory system, since it allows the thread to block | 
|  | 96 | * while memory is reclaimed, and won't take pages from emergency | 
|  | 97 | * low-memory pools. | 
|  | 98 | */ | 
|  | 99 | #define VMW_PAGE_ALLOC_CANSLEEP		(GFP_HIGHUSER) | 
|  | 100 |  | 
|  | 101 | /* Maximum number of page allocations without yielding processor */ | 
|  | 102 | #define VMW_BALLOON_YIELD_THRESHOLD	1024 | 
|  | 103 |  | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 104 | /* Maximum number of refused pages we accumulate during inflation cycle */ | 
|  | 105 | #define VMW_BALLOON_MAX_REFUSED		16 | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 106 |  | 
|  | 107 | /* | 
|  | 108 | * Hypervisor communication port definitions. | 
|  | 109 | */ | 
|  | 110 | #define VMW_BALLOON_HV_PORT		0x5670 | 
|  | 111 | #define VMW_BALLOON_HV_MAGIC		0x456c6d6f | 
|  | 112 | #define VMW_BALLOON_PROTOCOL_VERSION	2 | 
|  | 113 | #define VMW_BALLOON_GUEST_ID		1	/* Linux */ | 
|  | 114 |  | 
|  | 115 | #define VMW_BALLOON_CMD_START		0 | 
|  | 116 | #define VMW_BALLOON_CMD_GET_TARGET	1 | 
|  | 117 | #define VMW_BALLOON_CMD_LOCK		2 | 
|  | 118 | #define VMW_BALLOON_CMD_UNLOCK		3 | 
|  | 119 | #define VMW_BALLOON_CMD_GUEST_ID	4 | 
|  | 120 |  | 
|  | 121 | /* error codes */ | 
|  | 122 | #define VMW_BALLOON_SUCCESS		0 | 
|  | 123 | #define VMW_BALLOON_FAILURE		-1 | 
|  | 124 | #define VMW_BALLOON_ERROR_CMD_INVALID	1 | 
|  | 125 | #define VMW_BALLOON_ERROR_PPN_INVALID	2 | 
|  | 126 | #define VMW_BALLOON_ERROR_PPN_LOCKED	3 | 
|  | 127 | #define VMW_BALLOON_ERROR_PPN_UNLOCKED	4 | 
|  | 128 | #define VMW_BALLOON_ERROR_PPN_PINNED	5 | 
|  | 129 | #define VMW_BALLOON_ERROR_PPN_NOTNEEDED	6 | 
|  | 130 | #define VMW_BALLOON_ERROR_RESET		7 | 
|  | 131 | #define VMW_BALLOON_ERROR_BUSY		8 | 
|  | 132 |  | 
|  | 133 | #define VMWARE_BALLOON_CMD(cmd, data, result)		\ | 
|  | 134 | ({							\ | 
|  | 135 | unsigned long __stat, __dummy1, __dummy2;	\ | 
|  | 136 | __asm__ __volatile__ ("inl (%%dx)" :		\ | 
|  | 137 | "=a"(__stat),				\ | 
|  | 138 | "=c"(__dummy1),				\ | 
|  | 139 | "=d"(__dummy2),				\ | 
|  | 140 | "=b"(result) :				\ | 
|  | 141 | "0"(VMW_BALLOON_HV_MAGIC),		\ | 
|  | 142 | "1"(VMW_BALLOON_CMD_##cmd),		\ | 
|  | 143 | "2"(VMW_BALLOON_HV_PORT),		\ | 
|  | 144 | "3"(data) :				\ | 
|  | 145 | "memory");				\ | 
|  | 146 | result &= -1UL;					\ | 
|  | 147 | __stat & -1UL;					\ | 
|  | 148 | }) | 
|  | 149 |  | 
|  | 150 | #ifdef CONFIG_DEBUG_FS | 
|  | 151 | struct vmballoon_stats { | 
|  | 152 | unsigned int timer; | 
|  | 153 |  | 
| Rakib Mullick | 2ca02df | 2011-11-02 13:40:07 -0700 | [diff] [blame] | 154 | /* allocation statistics */ | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 155 | unsigned int alloc; | 
|  | 156 | unsigned int alloc_fail; | 
|  | 157 | unsigned int sleep_alloc; | 
|  | 158 | unsigned int sleep_alloc_fail; | 
|  | 159 | unsigned int refused_alloc; | 
|  | 160 | unsigned int refused_free; | 
|  | 161 | unsigned int free; | 
|  | 162 |  | 
|  | 163 | /* monitor operations */ | 
|  | 164 | unsigned int lock; | 
|  | 165 | unsigned int lock_fail; | 
|  | 166 | unsigned int unlock; | 
|  | 167 | unsigned int unlock_fail; | 
|  | 168 | unsigned int target; | 
|  | 169 | unsigned int target_fail; | 
|  | 170 | unsigned int start; | 
|  | 171 | unsigned int start_fail; | 
|  | 172 | unsigned int guest_type; | 
|  | 173 | unsigned int guest_type_fail; | 
|  | 174 | }; | 
|  | 175 |  | 
|  | 176 | #define STATS_INC(stat) (stat)++ | 
|  | 177 | #else | 
|  | 178 | #define STATS_INC(stat) | 
|  | 179 | #endif | 
|  | 180 |  | 
|  | 181 | struct vmballoon { | 
|  | 182 |  | 
|  | 183 | /* list of reserved physical pages */ | 
|  | 184 | struct list_head pages; | 
|  | 185 |  | 
|  | 186 | /* transient list of non-balloonable pages */ | 
|  | 187 | struct list_head refused_pages; | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 188 | unsigned int n_refused_pages; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 189 |  | 
|  | 190 | /* balloon size in pages */ | 
|  | 191 | unsigned int size; | 
|  | 192 | unsigned int target; | 
|  | 193 |  | 
|  | 194 | /* reset flag */ | 
|  | 195 | bool reset_required; | 
|  | 196 |  | 
|  | 197 | /* adjustment rates (pages per second) */ | 
|  | 198 | unsigned int rate_alloc; | 
|  | 199 | unsigned int rate_free; | 
|  | 200 |  | 
|  | 201 | /* slowdown page allocations for next few cycles */ | 
|  | 202 | unsigned int slow_allocation_cycles; | 
|  | 203 |  | 
|  | 204 | #ifdef CONFIG_DEBUG_FS | 
|  | 205 | /* statistics */ | 
|  | 206 | struct vmballoon_stats stats; | 
|  | 207 |  | 
|  | 208 | /* debugfs file exporting statistics */ | 
|  | 209 | struct dentry *dbg_entry; | 
|  | 210 | #endif | 
|  | 211 |  | 
|  | 212 | struct sysinfo sysinfo; | 
|  | 213 |  | 
|  | 214 | struct delayed_work dwork; | 
|  | 215 | }; | 
|  | 216 |  | 
|  | 217 | static struct vmballoon balloon; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 218 |  | 
|  | 219 | /* | 
|  | 220 | * Send "start" command to the host, communicating supported version | 
|  | 221 | * of the protocol. | 
|  | 222 | */ | 
|  | 223 | static bool vmballoon_send_start(struct vmballoon *b) | 
|  | 224 | { | 
|  | 225 | unsigned long status, dummy; | 
|  | 226 |  | 
|  | 227 | STATS_INC(b->stats.start); | 
|  | 228 |  | 
|  | 229 | status = VMWARE_BALLOON_CMD(START, VMW_BALLOON_PROTOCOL_VERSION, dummy); | 
|  | 230 | if (status == VMW_BALLOON_SUCCESS) | 
|  | 231 | return true; | 
|  | 232 |  | 
|  | 233 | pr_debug("%s - failed, hv returns %ld\n", __func__, status); | 
|  | 234 | STATS_INC(b->stats.start_fail); | 
|  | 235 | return false; | 
|  | 236 | } | 
|  | 237 |  | 
|  | 238 | static bool vmballoon_check_status(struct vmballoon *b, unsigned long status) | 
|  | 239 | { | 
|  | 240 | switch (status) { | 
|  | 241 | case VMW_BALLOON_SUCCESS: | 
|  | 242 | return true; | 
|  | 243 |  | 
|  | 244 | case VMW_BALLOON_ERROR_RESET: | 
|  | 245 | b->reset_required = true; | 
|  | 246 | /* fall through */ | 
|  | 247 |  | 
|  | 248 | default: | 
|  | 249 | return false; | 
|  | 250 | } | 
|  | 251 | } | 
|  | 252 |  | 
|  | 253 | /* | 
|  | 254 | * Communicate guest type to the host so that it can adjust ballooning | 
|  | 255 | * algorithm to the one most appropriate for the guest. This command | 
|  | 256 | * is normally issued after sending "start" command and is part of | 
|  | 257 | * standard reset sequence. | 
|  | 258 | */ | 
|  | 259 | static bool vmballoon_send_guest_id(struct vmballoon *b) | 
|  | 260 | { | 
|  | 261 | unsigned long status, dummy; | 
|  | 262 |  | 
|  | 263 | status = VMWARE_BALLOON_CMD(GUEST_ID, VMW_BALLOON_GUEST_ID, dummy); | 
|  | 264 |  | 
|  | 265 | STATS_INC(b->stats.guest_type); | 
|  | 266 |  | 
|  | 267 | if (vmballoon_check_status(b, status)) | 
|  | 268 | return true; | 
|  | 269 |  | 
|  | 270 | pr_debug("%s - failed, hv returns %ld\n", __func__, status); | 
|  | 271 | STATS_INC(b->stats.guest_type_fail); | 
|  | 272 | return false; | 
|  | 273 | } | 
|  | 274 |  | 
|  | 275 | /* | 
|  | 276 | * Retrieve desired balloon size from the host. | 
|  | 277 | */ | 
|  | 278 | static bool vmballoon_send_get_target(struct vmballoon *b, u32 *new_target) | 
|  | 279 | { | 
|  | 280 | unsigned long status; | 
|  | 281 | unsigned long target; | 
|  | 282 | unsigned long limit; | 
|  | 283 | u32 limit32; | 
|  | 284 |  | 
|  | 285 | /* | 
|  | 286 | * si_meminfo() is cheap. Moreover, we want to provide dynamic | 
|  | 287 | * max balloon size later. So let us call si_meminfo() every | 
|  | 288 | * iteration. | 
|  | 289 | */ | 
|  | 290 | si_meminfo(&b->sysinfo); | 
|  | 291 | limit = b->sysinfo.totalram; | 
|  | 292 |  | 
|  | 293 | /* Ensure limit fits in 32-bits */ | 
|  | 294 | limit32 = (u32)limit; | 
|  | 295 | if (limit != limit32) | 
|  | 296 | return false; | 
|  | 297 |  | 
|  | 298 | /* update stats */ | 
|  | 299 | STATS_INC(b->stats.target); | 
|  | 300 |  | 
|  | 301 | status = VMWARE_BALLOON_CMD(GET_TARGET, limit, target); | 
|  | 302 | if (vmballoon_check_status(b, status)) { | 
|  | 303 | *new_target = target; | 
|  | 304 | return true; | 
|  | 305 | } | 
|  | 306 |  | 
|  | 307 | pr_debug("%s - failed, hv returns %ld\n", __func__, status); | 
|  | 308 | STATS_INC(b->stats.target_fail); | 
|  | 309 | return false; | 
|  | 310 | } | 
|  | 311 |  | 
|  | 312 | /* | 
|  | 313 | * Notify the host about allocated page so that host can use it without | 
|  | 314 | * fear that guest will need it. Host may reject some pages, we need to | 
|  | 315 | * check the return value and maybe submit a different page. | 
|  | 316 | */ | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 317 | static int vmballoon_send_lock_page(struct vmballoon *b, unsigned long pfn, | 
| Dmitry Torokhov | d27a0c0 | 2011-01-12 17:01:07 -0800 | [diff] [blame] | 318 | unsigned int *hv_status) | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 319 | { | 
|  | 320 | unsigned long status, dummy; | 
|  | 321 | u32 pfn32; | 
|  | 322 |  | 
|  | 323 | pfn32 = (u32)pfn; | 
|  | 324 | if (pfn32 != pfn) | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 325 | return -1; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 326 |  | 
|  | 327 | STATS_INC(b->stats.lock); | 
|  | 328 |  | 
| Dmitry Torokhov | d27a0c0 | 2011-01-12 17:01:07 -0800 | [diff] [blame] | 329 | *hv_status = status = VMWARE_BALLOON_CMD(LOCK, pfn, dummy); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 330 | if (vmballoon_check_status(b, status)) | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 331 | return 0; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 332 |  | 
|  | 333 | pr_debug("%s - ppn %lx, hv returns %ld\n", __func__, pfn, status); | 
|  | 334 | STATS_INC(b->stats.lock_fail); | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 335 | return 1; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 336 | } | 
|  | 337 |  | 
|  | 338 | /* | 
|  | 339 | * Notify the host that guest intends to release given page back into | 
|  | 340 | * the pool of available (to the guest) pages. | 
|  | 341 | */ | 
|  | 342 | static bool vmballoon_send_unlock_page(struct vmballoon *b, unsigned long pfn) | 
|  | 343 | { | 
|  | 344 | unsigned long status, dummy; | 
|  | 345 | u32 pfn32; | 
|  | 346 |  | 
|  | 347 | pfn32 = (u32)pfn; | 
|  | 348 | if (pfn32 != pfn) | 
|  | 349 | return false; | 
|  | 350 |  | 
|  | 351 | STATS_INC(b->stats.unlock); | 
|  | 352 |  | 
|  | 353 | status = VMWARE_BALLOON_CMD(UNLOCK, pfn, dummy); | 
|  | 354 | if (vmballoon_check_status(b, status)) | 
|  | 355 | return true; | 
|  | 356 |  | 
|  | 357 | pr_debug("%s - ppn %lx, hv returns %ld\n", __func__, pfn, status); | 
|  | 358 | STATS_INC(b->stats.unlock_fail); | 
|  | 359 | return false; | 
|  | 360 | } | 
|  | 361 |  | 
|  | 362 | /* | 
|  | 363 | * Quickly release all pages allocated for the balloon. This function is | 
|  | 364 | * called when host decides to "reset" balloon for one reason or another. | 
|  | 365 | * Unlike normal "deflate" we do not (shall not) notify host of the pages | 
|  | 366 | * being released. | 
|  | 367 | */ | 
|  | 368 | static void vmballoon_pop(struct vmballoon *b) | 
|  | 369 | { | 
|  | 370 | struct page *page, *next; | 
|  | 371 | unsigned int count = 0; | 
|  | 372 |  | 
|  | 373 | list_for_each_entry_safe(page, next, &b->pages, lru) { | 
|  | 374 | list_del(&page->lru); | 
|  | 375 | __free_page(page); | 
|  | 376 | STATS_INC(b->stats.free); | 
|  | 377 | b->size--; | 
|  | 378 |  | 
|  | 379 | if (++count >= b->rate_free) { | 
|  | 380 | count = 0; | 
|  | 381 | cond_resched(); | 
|  | 382 | } | 
|  | 383 | } | 
|  | 384 | } | 
|  | 385 |  | 
|  | 386 | /* | 
|  | 387 | * Perform standard reset sequence by popping the balloon (in case it | 
|  | 388 | * is not  empty) and then restarting protocol. This operation normally | 
|  | 389 | * happens when host responds with VMW_BALLOON_ERROR_RESET to a command. | 
|  | 390 | */ | 
|  | 391 | static void vmballoon_reset(struct vmballoon *b) | 
|  | 392 | { | 
|  | 393 | /* free all pages, skipping monitor unlock */ | 
|  | 394 | vmballoon_pop(b); | 
|  | 395 |  | 
|  | 396 | if (vmballoon_send_start(b)) { | 
|  | 397 | b->reset_required = false; | 
|  | 398 | if (!vmballoon_send_guest_id(b)) | 
|  | 399 | pr_err("failed to send guest ID to the host\n"); | 
|  | 400 | } | 
|  | 401 | } | 
|  | 402 |  | 
|  | 403 | /* | 
|  | 404 | * Allocate (or reserve) a page for the balloon and notify the host.  If host | 
|  | 405 | * refuses the page put it on "refuse" list and allocate another one until host | 
|  | 406 | * is satisfied. "Refused" pages are released at the end of inflation cycle | 
|  | 407 | * (when we allocate b->rate_alloc pages). | 
|  | 408 | */ | 
|  | 409 | static int vmballoon_reserve_page(struct vmballoon *b, bool can_sleep) | 
|  | 410 | { | 
|  | 411 | struct page *page; | 
|  | 412 | gfp_t flags; | 
| Dmitry Torokhov | d27a0c0 | 2011-01-12 17:01:07 -0800 | [diff] [blame] | 413 | unsigned int hv_status; | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 414 | int locked; | 
| Rakib Mullick | 6d994a7 | 2011-11-02 13:40:04 -0700 | [diff] [blame] | 415 | flags = can_sleep ? VMW_PAGE_ALLOC_CANSLEEP : VMW_PAGE_ALLOC_NOSLEEP; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 416 |  | 
|  | 417 | do { | 
|  | 418 | if (!can_sleep) | 
|  | 419 | STATS_INC(b->stats.alloc); | 
|  | 420 | else | 
|  | 421 | STATS_INC(b->stats.sleep_alloc); | 
|  | 422 |  | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 423 | page = alloc_page(flags); | 
|  | 424 | if (!page) { | 
|  | 425 | if (!can_sleep) | 
|  | 426 | STATS_INC(b->stats.alloc_fail); | 
|  | 427 | else | 
|  | 428 | STATS_INC(b->stats.sleep_alloc_fail); | 
|  | 429 | return -ENOMEM; | 
|  | 430 | } | 
|  | 431 |  | 
|  | 432 | /* inform monitor */ | 
| Dmitry Torokhov | d27a0c0 | 2011-01-12 17:01:07 -0800 | [diff] [blame] | 433 | locked = vmballoon_send_lock_page(b, page_to_pfn(page), &hv_status); | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 434 | if (locked > 0) { | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 435 | STATS_INC(b->stats.refused_alloc); | 
|  | 436 |  | 
| Dmitry Torokhov | d27a0c0 | 2011-01-12 17:01:07 -0800 | [diff] [blame] | 437 | if (hv_status == VMW_BALLOON_ERROR_RESET || | 
|  | 438 | hv_status == VMW_BALLOON_ERROR_PPN_NOTNEEDED) { | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 439 | __free_page(page); | 
|  | 440 | return -EIO; | 
|  | 441 | } | 
|  | 442 |  | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 443 | /* | 
|  | 444 | * Place page on the list of non-balloonable pages | 
|  | 445 | * and retry allocation, unless we already accumulated | 
|  | 446 | * too many of them, in which case take a breather. | 
|  | 447 | */ | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 448 | list_add(&page->lru, &b->refused_pages); | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 449 | if (++b->n_refused_pages >= VMW_BALLOON_MAX_REFUSED) | 
|  | 450 | return -EIO; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 451 | } | 
| Danny Kukawka | 3e5ba46 | 2012-01-30 23:00:08 +0100 | [diff] [blame] | 452 | } while (locked != 0); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 453 |  | 
|  | 454 | /* track allocated page */ | 
|  | 455 | list_add(&page->lru, &b->pages); | 
|  | 456 |  | 
|  | 457 | /* update balloon size */ | 
|  | 458 | b->size++; | 
|  | 459 |  | 
|  | 460 | return 0; | 
|  | 461 | } | 
|  | 462 |  | 
|  | 463 | /* | 
|  | 464 | * Release the page allocated for the balloon. Note that we first notify | 
|  | 465 | * the host so it can make sure the page will be available for the guest | 
|  | 466 | * to use, if needed. | 
|  | 467 | */ | 
|  | 468 | static int vmballoon_release_page(struct vmballoon *b, struct page *page) | 
|  | 469 | { | 
|  | 470 | if (!vmballoon_send_unlock_page(b, page_to_pfn(page))) | 
|  | 471 | return -EIO; | 
|  | 472 |  | 
|  | 473 | list_del(&page->lru); | 
|  | 474 |  | 
|  | 475 | /* deallocate page */ | 
|  | 476 | __free_page(page); | 
|  | 477 | STATS_INC(b->stats.free); | 
|  | 478 |  | 
|  | 479 | /* update balloon size */ | 
|  | 480 | b->size--; | 
|  | 481 |  | 
|  | 482 | return 0; | 
|  | 483 | } | 
|  | 484 |  | 
|  | 485 | /* | 
|  | 486 | * Release pages that were allocated while attempting to inflate the | 
|  | 487 | * balloon but were refused by the host for one reason or another. | 
|  | 488 | */ | 
|  | 489 | static void vmballoon_release_refused_pages(struct vmballoon *b) | 
|  | 490 | { | 
|  | 491 | struct page *page, *next; | 
|  | 492 |  | 
|  | 493 | list_for_each_entry_safe(page, next, &b->refused_pages, lru) { | 
|  | 494 | list_del(&page->lru); | 
|  | 495 | __free_page(page); | 
|  | 496 | STATS_INC(b->stats.refused_free); | 
|  | 497 | } | 
| Dmitry Torokhov | 55adaa4 | 2010-06-04 14:14:52 -0700 | [diff] [blame] | 498 |  | 
|  | 499 | b->n_refused_pages = 0; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 500 | } | 
|  | 501 |  | 
|  | 502 | /* | 
|  | 503 | * Inflate the balloon towards its target size. Note that we try to limit | 
|  | 504 | * the rate of allocation to make sure we are not choking the rest of the | 
|  | 505 | * system. | 
|  | 506 | */ | 
|  | 507 | static void vmballoon_inflate(struct vmballoon *b) | 
|  | 508 | { | 
|  | 509 | unsigned int goal; | 
|  | 510 | unsigned int rate; | 
|  | 511 | unsigned int i; | 
|  | 512 | unsigned int allocations = 0; | 
|  | 513 | int error = 0; | 
|  | 514 | bool alloc_can_sleep = false; | 
|  | 515 |  | 
|  | 516 | pr_debug("%s - size: %d, target %d\n", __func__, b->size, b->target); | 
|  | 517 |  | 
|  | 518 | /* | 
|  | 519 | * First try NOSLEEP page allocations to inflate balloon. | 
|  | 520 | * | 
|  | 521 | * If we do not throttle nosleep allocations, we can drain all | 
|  | 522 | * free pages in the guest quickly (if the balloon target is high). | 
|  | 523 | * As a side-effect, draining free pages helps to inform (force) | 
|  | 524 | * the guest to start swapping if balloon target is not met yet, | 
|  | 525 | * which is a desired behavior. However, balloon driver can consume | 
|  | 526 | * all available CPU cycles if too many pages are allocated in a | 
|  | 527 | * second. Therefore, we throttle nosleep allocations even when | 
|  | 528 | * the guest is not under memory pressure. OTOH, if we have already | 
|  | 529 | * predicted that the guest is under memory pressure, then we | 
|  | 530 | * slowdown page allocations considerably. | 
|  | 531 | */ | 
|  | 532 |  | 
|  | 533 | goal = b->target - b->size; | 
|  | 534 | /* | 
|  | 535 | * Start with no sleep allocation rate which may be higher | 
|  | 536 | * than sleeping allocation rate. | 
|  | 537 | */ | 
|  | 538 | rate = b->slow_allocation_cycles ? | 
|  | 539 | b->rate_alloc : VMW_BALLOON_NOSLEEP_ALLOC_MAX; | 
|  | 540 |  | 
|  | 541 | pr_debug("%s - goal: %d, no-sleep rate: %d, sleep rate: %d\n", | 
|  | 542 | __func__, goal, rate, b->rate_alloc); | 
|  | 543 |  | 
|  | 544 | for (i = 0; i < goal; i++) { | 
|  | 545 |  | 
|  | 546 | error = vmballoon_reserve_page(b, alloc_can_sleep); | 
|  | 547 | if (error) { | 
|  | 548 | if (error != -ENOMEM) { | 
|  | 549 | /* | 
|  | 550 | * Not a page allocation failure, stop this | 
|  | 551 | * cycle. Maybe we'll get new target from | 
|  | 552 | * the host soon. | 
|  | 553 | */ | 
|  | 554 | break; | 
|  | 555 | } | 
|  | 556 |  | 
|  | 557 | if (alloc_can_sleep) { | 
|  | 558 | /* | 
|  | 559 | * CANSLEEP page allocation failed, so guest | 
|  | 560 | * is under severe memory pressure. Quickly | 
|  | 561 | * decrease allocation rate. | 
|  | 562 | */ | 
|  | 563 | b->rate_alloc = max(b->rate_alloc / 2, | 
|  | 564 | VMW_BALLOON_RATE_ALLOC_MIN); | 
|  | 565 | break; | 
|  | 566 | } | 
|  | 567 |  | 
|  | 568 | /* | 
|  | 569 | * NOSLEEP page allocation failed, so the guest is | 
|  | 570 | * under memory pressure. Let us slow down page | 
|  | 571 | * allocations for next few cycles so that the guest | 
|  | 572 | * gets out of memory pressure. Also, if we already | 
|  | 573 | * allocated b->rate_alloc pages, let's pause, | 
|  | 574 | * otherwise switch to sleeping allocations. | 
|  | 575 | */ | 
|  | 576 | b->slow_allocation_cycles = VMW_BALLOON_SLOW_CYCLES; | 
|  | 577 |  | 
|  | 578 | if (i >= b->rate_alloc) | 
|  | 579 | break; | 
|  | 580 |  | 
|  | 581 | alloc_can_sleep = true; | 
|  | 582 | /* Lower rate for sleeping allocations. */ | 
|  | 583 | rate = b->rate_alloc; | 
|  | 584 | } | 
|  | 585 |  | 
|  | 586 | if (++allocations > VMW_BALLOON_YIELD_THRESHOLD) { | 
|  | 587 | cond_resched(); | 
|  | 588 | allocations = 0; | 
|  | 589 | } | 
|  | 590 |  | 
|  | 591 | if (i >= rate) { | 
|  | 592 | /* We allocated enough pages, let's take a break. */ | 
|  | 593 | break; | 
|  | 594 | } | 
|  | 595 | } | 
|  | 596 |  | 
|  | 597 | /* | 
|  | 598 | * We reached our goal without failures so try increasing | 
|  | 599 | * allocation rate. | 
|  | 600 | */ | 
|  | 601 | if (error == 0 && i >= b->rate_alloc) { | 
|  | 602 | unsigned int mult = i / b->rate_alloc; | 
|  | 603 |  | 
|  | 604 | b->rate_alloc = | 
|  | 605 | min(b->rate_alloc + mult * VMW_BALLOON_RATE_ALLOC_INC, | 
|  | 606 | VMW_BALLOON_RATE_ALLOC_MAX); | 
|  | 607 | } | 
|  | 608 |  | 
|  | 609 | vmballoon_release_refused_pages(b); | 
|  | 610 | } | 
|  | 611 |  | 
|  | 612 | /* | 
|  | 613 | * Decrease the size of the balloon allowing guest to use more memory. | 
|  | 614 | */ | 
|  | 615 | static void vmballoon_deflate(struct vmballoon *b) | 
|  | 616 | { | 
|  | 617 | struct page *page, *next; | 
|  | 618 | unsigned int i = 0; | 
|  | 619 | unsigned int goal; | 
|  | 620 | int error; | 
|  | 621 |  | 
|  | 622 | pr_debug("%s - size: %d, target %d\n", __func__, b->size, b->target); | 
|  | 623 |  | 
|  | 624 | /* limit deallocation rate */ | 
|  | 625 | goal = min(b->size - b->target, b->rate_free); | 
|  | 626 |  | 
|  | 627 | pr_debug("%s - goal: %d, rate: %d\n", __func__, goal, b->rate_free); | 
|  | 628 |  | 
|  | 629 | /* free pages to reach target */ | 
|  | 630 | list_for_each_entry_safe(page, next, &b->pages, lru) { | 
|  | 631 | error = vmballoon_release_page(b, page); | 
|  | 632 | if (error) { | 
|  | 633 | /* quickly decrease rate in case of error */ | 
|  | 634 | b->rate_free = max(b->rate_free / 2, | 
|  | 635 | VMW_BALLOON_RATE_FREE_MIN); | 
|  | 636 | return; | 
|  | 637 | } | 
|  | 638 |  | 
|  | 639 | if (++i >= goal) | 
|  | 640 | break; | 
|  | 641 | } | 
|  | 642 |  | 
|  | 643 | /* slowly increase rate if there were no errors */ | 
|  | 644 | b->rate_free = min(b->rate_free + VMW_BALLOON_RATE_FREE_INC, | 
|  | 645 | VMW_BALLOON_RATE_FREE_MAX); | 
|  | 646 | } | 
|  | 647 |  | 
|  | 648 | /* | 
|  | 649 | * Balloon work function: reset protocol, if needed, get the new size and | 
|  | 650 | * adjust balloon as needed. Repeat in 1 sec. | 
|  | 651 | */ | 
|  | 652 | static void vmballoon_work(struct work_struct *work) | 
|  | 653 | { | 
|  | 654 | struct delayed_work *dwork = to_delayed_work(work); | 
|  | 655 | struct vmballoon *b = container_of(dwork, struct vmballoon, dwork); | 
|  | 656 | unsigned int target; | 
|  | 657 |  | 
|  | 658 | STATS_INC(b->stats.timer); | 
|  | 659 |  | 
|  | 660 | if (b->reset_required) | 
|  | 661 | vmballoon_reset(b); | 
|  | 662 |  | 
|  | 663 | if (b->slow_allocation_cycles > 0) | 
|  | 664 | b->slow_allocation_cycles--; | 
|  | 665 |  | 
|  | 666 | if (vmballoon_send_get_target(b, &target)) { | 
|  | 667 | /* update target, adjust size */ | 
|  | 668 | b->target = target; | 
|  | 669 |  | 
|  | 670 | if (b->size < target) | 
|  | 671 | vmballoon_inflate(b); | 
|  | 672 | else if (b->size > target) | 
|  | 673 | vmballoon_deflate(b); | 
|  | 674 | } | 
|  | 675 |  | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 676 | /* | 
|  | 677 | * We are using a freezable workqueue so that balloon operations are | 
|  | 678 | * stopped while the system transitions to/from sleep/hibernation. | 
|  | 679 | */ | 
|  | 680 | queue_delayed_work(system_freezable_wq, | 
|  | 681 | dwork, round_jiffies_relative(HZ)); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 682 | } | 
|  | 683 |  | 
|  | 684 | /* | 
|  | 685 | * DEBUGFS Interface | 
|  | 686 | */ | 
|  | 687 | #ifdef CONFIG_DEBUG_FS | 
|  | 688 |  | 
|  | 689 | static int vmballoon_debug_show(struct seq_file *f, void *offset) | 
|  | 690 | { | 
|  | 691 | struct vmballoon *b = f->private; | 
|  | 692 | struct vmballoon_stats *stats = &b->stats; | 
|  | 693 |  | 
|  | 694 | /* format size info */ | 
|  | 695 | seq_printf(f, | 
|  | 696 | "target:             %8d pages\n" | 
|  | 697 | "current:            %8d pages\n", | 
|  | 698 | b->target, b->size); | 
|  | 699 |  | 
|  | 700 | /* format rate info */ | 
|  | 701 | seq_printf(f, | 
|  | 702 | "rateNoSleepAlloc:   %8d pages/sec\n" | 
|  | 703 | "rateSleepAlloc:     %8d pages/sec\n" | 
|  | 704 | "rateFree:           %8d pages/sec\n", | 
|  | 705 | VMW_BALLOON_NOSLEEP_ALLOC_MAX, | 
|  | 706 | b->rate_alloc, b->rate_free); | 
|  | 707 |  | 
|  | 708 | seq_printf(f, | 
|  | 709 | "\n" | 
|  | 710 | "timer:              %8u\n" | 
|  | 711 | "start:              %8u (%4u failed)\n" | 
|  | 712 | "guestType:          %8u (%4u failed)\n" | 
|  | 713 | "lock:               %8u (%4u failed)\n" | 
|  | 714 | "unlock:             %8u (%4u failed)\n" | 
|  | 715 | "target:             %8u (%4u failed)\n" | 
|  | 716 | "primNoSleepAlloc:   %8u (%4u failed)\n" | 
|  | 717 | "primCanSleepAlloc:  %8u (%4u failed)\n" | 
|  | 718 | "primFree:           %8u\n" | 
|  | 719 | "errAlloc:           %8u\n" | 
|  | 720 | "errFree:            %8u\n", | 
|  | 721 | stats->timer, | 
|  | 722 | stats->start, stats->start_fail, | 
|  | 723 | stats->guest_type, stats->guest_type_fail, | 
|  | 724 | stats->lock,  stats->lock_fail, | 
|  | 725 | stats->unlock, stats->unlock_fail, | 
|  | 726 | stats->target, stats->target_fail, | 
|  | 727 | stats->alloc, stats->alloc_fail, | 
|  | 728 | stats->sleep_alloc, stats->sleep_alloc_fail, | 
|  | 729 | stats->free, | 
|  | 730 | stats->refused_alloc, stats->refused_free); | 
|  | 731 |  | 
|  | 732 | return 0; | 
|  | 733 | } | 
|  | 734 |  | 
|  | 735 | static int vmballoon_debug_open(struct inode *inode, struct file *file) | 
|  | 736 | { | 
|  | 737 | return single_open(file, vmballoon_debug_show, inode->i_private); | 
|  | 738 | } | 
|  | 739 |  | 
|  | 740 | static const struct file_operations vmballoon_debug_fops = { | 
|  | 741 | .owner		= THIS_MODULE, | 
|  | 742 | .open		= vmballoon_debug_open, | 
|  | 743 | .read		= seq_read, | 
|  | 744 | .llseek		= seq_lseek, | 
|  | 745 | .release	= single_release, | 
|  | 746 | }; | 
|  | 747 |  | 
|  | 748 | static int __init vmballoon_debugfs_init(struct vmballoon *b) | 
|  | 749 | { | 
|  | 750 | int error; | 
|  | 751 |  | 
|  | 752 | b->dbg_entry = debugfs_create_file("vmmemctl", S_IRUGO, NULL, b, | 
|  | 753 | &vmballoon_debug_fops); | 
|  | 754 | if (IS_ERR(b->dbg_entry)) { | 
|  | 755 | error = PTR_ERR(b->dbg_entry); | 
|  | 756 | pr_err("failed to create debugfs entry, error: %d\n", error); | 
|  | 757 | return error; | 
|  | 758 | } | 
|  | 759 |  | 
|  | 760 | return 0; | 
|  | 761 | } | 
|  | 762 |  | 
|  | 763 | static void __exit vmballoon_debugfs_exit(struct vmballoon *b) | 
|  | 764 | { | 
|  | 765 | debugfs_remove(b->dbg_entry); | 
|  | 766 | } | 
|  | 767 |  | 
|  | 768 | #else | 
|  | 769 |  | 
|  | 770 | static inline int vmballoon_debugfs_init(struct vmballoon *b) | 
|  | 771 | { | 
|  | 772 | return 0; | 
|  | 773 | } | 
|  | 774 |  | 
|  | 775 | static inline void vmballoon_debugfs_exit(struct vmballoon *b) | 
|  | 776 | { | 
|  | 777 | } | 
|  | 778 |  | 
|  | 779 | #endif	/* CONFIG_DEBUG_FS */ | 
|  | 780 |  | 
|  | 781 | static int __init vmballoon_init(void) | 
|  | 782 | { | 
|  | 783 | int error; | 
|  | 784 |  | 
|  | 785 | /* | 
|  | 786 | * Check if we are running on VMware's hypervisor and bail out | 
|  | 787 | * if we are not. | 
|  | 788 | */ | 
| H. Peter Anvin | a10a569 | 2010-05-09 01:13:42 -0700 | [diff] [blame] | 789 | if (x86_hyper != &x86_hyper_vmware) | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 790 | return -ENODEV; | 
|  | 791 |  | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 792 | INIT_LIST_HEAD(&balloon.pages); | 
|  | 793 | INIT_LIST_HEAD(&balloon.refused_pages); | 
|  | 794 |  | 
|  | 795 | /* initialize rates */ | 
|  | 796 | balloon.rate_alloc = VMW_BALLOON_RATE_ALLOC_MAX; | 
|  | 797 | balloon.rate_free = VMW_BALLOON_RATE_FREE_MAX; | 
|  | 798 |  | 
|  | 799 | INIT_DELAYED_WORK(&balloon.dwork, vmballoon_work); | 
|  | 800 |  | 
|  | 801 | /* | 
|  | 802 | * Start balloon. | 
|  | 803 | */ | 
|  | 804 | if (!vmballoon_send_start(&balloon)) { | 
|  | 805 | pr_err("failed to send start command to the host\n"); | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 806 | return -EIO; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 807 | } | 
|  | 808 |  | 
|  | 809 | if (!vmballoon_send_guest_id(&balloon)) { | 
|  | 810 | pr_err("failed to send guest ID to the host\n"); | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 811 | return -EIO; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 812 | } | 
|  | 813 |  | 
|  | 814 | error = vmballoon_debugfs_init(&balloon); | 
|  | 815 | if (error) | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 816 | return error; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 817 |  | 
| Dmitry Torokhov | beda94d | 2011-07-26 16:08:56 -0700 | [diff] [blame] | 818 | queue_delayed_work(system_freezable_wq, &balloon.dwork, 0); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 819 |  | 
|  | 820 | return 0; | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 821 | } | 
|  | 822 | module_init(vmballoon_init); | 
|  | 823 |  | 
|  | 824 | static void __exit vmballoon_exit(void) | 
|  | 825 | { | 
|  | 826 | cancel_delayed_work_sync(&balloon.dwork); | 
| Dmitry Torokhov | 453dc65 | 2010-04-23 13:18:08 -0400 | [diff] [blame] | 827 |  | 
|  | 828 | vmballoon_debugfs_exit(&balloon); | 
|  | 829 |  | 
|  | 830 | /* | 
|  | 831 | * Deallocate all reserved memory, and reset connection with monitor. | 
|  | 832 | * Reset connection before deallocating memory to avoid potential for | 
|  | 833 | * additional spurious resets from guest touching deallocated pages. | 
|  | 834 | */ | 
|  | 835 | vmballoon_send_start(&balloon); | 
|  | 836 | vmballoon_pop(&balloon); | 
|  | 837 | } | 
|  | 838 | module_exit(vmballoon_exit); |