VirtualBox

source: vbox/trunk/src/VBox/VMM/VMMR3/PGMPool.cpp@ 72490

Last change on this file since 72490 was 69111, checked in by vboxsync, 7 years ago

(C) year

  • Property svn:eol-style set to native
  • Property svn:keywords set to Id Revision
File size: 56.0 KB
Line 
1/* $Id: PGMPool.cpp 69111 2017-10-17 14:26:02Z vboxsync $ */
2/** @file
3 * PGM Shadow Page Pool.
4 */
5
6/*
7 * Copyright (C) 2006-2017 Oracle Corporation
8 *
9 * This file is part of VirtualBox Open Source Edition (OSE), as
10 * available from http://www.virtualbox.org. This file is free software;
11 * you can redistribute it and/or modify it under the terms of the GNU
12 * General Public License (GPL) as published by the Free Software
13 * Foundation, in version 2 as it comes in the "COPYING" file of the
14 * VirtualBox OSE distribution. VirtualBox OSE is distributed in the
15 * hope that it will be useful, but WITHOUT ANY WARRANTY of any kind.
16 */
17
18/** @page pg_pgm_pool PGM Shadow Page Pool
19 *
20 * Motivations:
21 * -# Relationship between shadow page tables and physical guest pages. This
22 * should allow us to skip most of the global flushes now following access
23 * handler changes. The main expense is flushing shadow pages.
24 * -# Limit the pool size if necessary (default is kind of limitless).
25 * -# Allocate shadow pages from RC. We use to only do this in SyncCR3.
26 * -# Required for 64-bit guests.
27 * -# Combining the PD cache and page pool in order to simplify caching.
28 *
29 *
30 * @section sec_pgm_pool_outline Design Outline
31 *
32 * The shadow page pool tracks pages used for shadowing paging structures (i.e.
33 * page tables, page directory, page directory pointer table and page map
34 * level-4). Each page in the pool has an unique identifier. This identifier is
35 * used to link a guest physical page to a shadow PT. The identifier is a
36 * non-zero value and has a relativly low max value - say 14 bits. This makes it
37 * possible to fit it into the upper bits of the of the aHCPhys entries in the
38 * ram range.
39 *
40 * By restricting host physical memory to the first 48 bits (which is the
41 * announced physical memory range of the K8L chip (scheduled for 2008)), we
42 * can safely use the upper 16 bits for shadow page ID and reference counting.
43 *
44 * Update: The 48 bit assumption will be lifted with the new physical memory
45 * management (PGMPAGE), so we won't have any trouble when someone stuffs 2TB
46 * into a box in some years.
47 *
48 * Now, it's possible for a page to be aliased, i.e. mapped by more than one PT
49 * or PD. This is solved by creating a list of physical cross reference extents
50 * when ever this happens. Each node in the list (extent) is can contain 3 page
51 * pool indexes. The list it self is chained using indexes into the paPhysExt
52 * array.
53 *
54 *
55 * @section sec_pgm_pool_life Life Cycle of a Shadow Page
56 *
57 * -# The SyncPT function requests a page from the pool.
58 * The request includes the kind of page it is (PT/PD, PAE/legacy), the
59 * address of the page it's shadowing, and more.
60 * -# The pool responds to the request by allocating a new page.
61 * When the cache is enabled, it will first check if it's in the cache.
62 * Should the pool be exhausted, one of two things can be done:
63 * -# Flush the whole pool and current CR3.
64 * -# Use the cache to find a page which can be flushed (~age).
65 * -# The SyncPT function will sync one or more pages and insert it into the
66 * shadow PD.
67 * -# The SyncPage function may sync more pages on a later \#PFs.
68 * -# The page is freed / flushed in SyncCR3 (perhaps) and some other cases.
69 * When caching is enabled, the page isn't flush but remains in the cache.
70 *
71 *
72 * @section sec_pgm_pool_monitoring Monitoring
73 *
74 * We always monitor PAGE_SIZE chunks of memory. When we've got multiple shadow
75 * pages for the same PAGE_SIZE of guest memory (PAE and mixed PD/PT) the pages
76 * sharing the monitor get linked using the iMonitoredNext/Prev. The head page
77 * is the pvUser to the access handlers.
78 *
79 *
80 * @section sec_pgm_pool_impl Implementation
81 *
82 * The pool will take pages from the MM page pool. The tracking data
83 * (attributes, bitmaps and so on) are allocated from the hypervisor heap. The
84 * pool content can be accessed both by using the page id and the physical
85 * address (HC). The former is managed by means of an array, the latter by an
86 * offset based AVL tree.
87 *
88 * Flushing of a pool page means that we iterate the content (we know what kind
89 * it is) and updates the link information in the ram range.
90 *
91 * ...
92 */
93
94
95/*********************************************************************************************************************************
96* Header Files *
97*********************************************************************************************************************************/
98#define LOG_GROUP LOG_GROUP_PGM_POOL
99#include <VBox/vmm/pgm.h>
100#include <VBox/vmm/mm.h>
101#include "PGMInternal.h"
102#include <VBox/vmm/vm.h>
103#include <VBox/vmm/uvm.h>
104#include "PGMInline.h"
105
106#include <VBox/log.h>
107#include <VBox/err.h>
108#include <iprt/asm.h>
109#include <iprt/string.h>
110#include <VBox/dbg.h>
111
112
113/*********************************************************************************************************************************
114* Internal Functions *
115*********************************************************************************************************************************/
116#ifdef VBOX_WITH_DEBUGGER
117static FNDBGCCMD pgmR3PoolCmdCheck;
118#endif
119
120#ifdef VBOX_WITH_DEBUGGER
121/** Command descriptors. */
122static const DBGCCMD g_aCmds[] =
123{
124 /* pszCmd, cArgsMin, cArgsMax, paArgDesc, cArgDescs, fFlags, pfnHandler pszSyntax, ....pszDescription */
125 { "pgmpoolcheck", 0, 0, NULL, 0, 0, pgmR3PoolCmdCheck, "", "Check the pgm pool pages." },
126};
127#endif
128
129/**
130 * Initializes the pool
131 *
132 * @returns VBox status code.
133 * @param pVM The cross context VM structure.
134 */
135int pgmR3PoolInit(PVM pVM)
136{
137 int rc;
138
139 AssertCompile(NIL_PGMPOOL_IDX == 0);
140 /* pPage->cLocked is an unsigned byte. */
141 AssertCompile(VMM_MAX_CPU_COUNT <= 255);
142
143 /*
144 * Query Pool config.
145 */
146 PCFGMNODE pCfg = CFGMR3GetChild(CFGMR3GetRoot(pVM), "/PGM/Pool");
147
148 /* Default pgm pool size is 1024 pages (4MB). */
149 uint16_t cMaxPages = 1024;
150
151 /* Adjust it up relative to the RAM size, using the nested paging formula. */
152 uint64_t cbRam;
153 rc = CFGMR3QueryU64Def(CFGMR3GetRoot(pVM), "RamSize", &cbRam, 0); AssertRCReturn(rc, rc);
154 uint64_t u64MaxPages = (cbRam >> 9)
155 + (cbRam >> 18)
156 + (cbRam >> 27)
157 + 32 * PAGE_SIZE;
158 u64MaxPages >>= PAGE_SHIFT;
159 if (u64MaxPages > PGMPOOL_IDX_LAST)
160 cMaxPages = PGMPOOL_IDX_LAST;
161 else
162 cMaxPages = (uint16_t)u64MaxPages;
163
164 /** @cfgm{/PGM/Pool/MaxPages, uint16_t, \#pages, 16, 0x3fff, F(ram-size)}
165 * The max size of the shadow page pool in pages. The pool will grow dynamically
166 * up to this limit.
167 */
168 rc = CFGMR3QueryU16Def(pCfg, "MaxPages", &cMaxPages, cMaxPages);
169 AssertLogRelRCReturn(rc, rc);
170 AssertLogRelMsgReturn(cMaxPages <= PGMPOOL_IDX_LAST && cMaxPages >= RT_ALIGN(PGMPOOL_IDX_FIRST, 16),
171 ("cMaxPages=%u (%#x)\n", cMaxPages, cMaxPages), VERR_INVALID_PARAMETER);
172 cMaxPages = RT_ALIGN(cMaxPages, 16);
173 if (cMaxPages > PGMPOOL_IDX_LAST)
174 cMaxPages = PGMPOOL_IDX_LAST;
175 LogRel(("PGM: PGMPool: cMaxPages=%u (u64MaxPages=%llu)\n", cMaxPages, u64MaxPages));
176
177 /** @todo
178 * We need to be much more careful with our allocation strategy here.
179 * For nested paging we don't need pool user info nor extents at all, but
180 * we can't check for nested paging here (too early during init to get a
181 * confirmation it can be used). The default for large memory configs is a
182 * bit large for shadow paging, so I've restricted the extent maximum to 8k
183 * (8k * 16 = 128k of hyper heap).
184 *
185 * Also when large page support is enabled, we typically don't need so much,
186 * although that depends on the availability of 2 MB chunks on the host.
187 */
188
189 /** @cfgm{/PGM/Pool/MaxUsers, uint16_t, \#users, MaxUsers, 32K, MaxPages*2}
190 * The max number of shadow page user tracking records. Each shadow page has
191 * zero of other shadow pages (or CR3s) that references it, or uses it if you
192 * like. The structures describing these relationships are allocated from a
193 * fixed sized pool. This configuration variable defines the pool size.
194 */
195 uint16_t cMaxUsers;
196 rc = CFGMR3QueryU16Def(pCfg, "MaxUsers", &cMaxUsers, cMaxPages * 2);
197 AssertLogRelRCReturn(rc, rc);
198 AssertLogRelMsgReturn(cMaxUsers >= cMaxPages && cMaxPages <= _32K,
199 ("cMaxUsers=%u (%#x)\n", cMaxUsers, cMaxUsers), VERR_INVALID_PARAMETER);
200
201 /** @cfgm{/PGM/Pool/MaxPhysExts, uint16_t, \#extents, 16, MaxPages * 2, MIN(MaxPages*2\,8192)}
202 * The max number of extents for tracking aliased guest pages.
203 */
204 uint16_t cMaxPhysExts;
205 rc = CFGMR3QueryU16Def(pCfg, "MaxPhysExts", &cMaxPhysExts,
206 RT_MIN(cMaxPages * 2, 8192 /* 8Ki max as this eat too much hyper heap */));
207 AssertLogRelRCReturn(rc, rc);
208 AssertLogRelMsgReturn(cMaxPhysExts >= 16 && cMaxPhysExts <= PGMPOOL_IDX_LAST,
209 ("cMaxPhysExts=%u (%#x)\n", cMaxPhysExts, cMaxPhysExts), VERR_INVALID_PARAMETER);
210
211 /** @cfgm{/PGM/Pool/ChacheEnabled, bool, true}
212 * Enables or disabling caching of shadow pages. Caching means that we will try
213 * reuse shadow pages instead of recreating them everything SyncCR3, SyncPT or
214 * SyncPage requests one. When reusing a shadow page, we can save time
215 * reconstructing it and it's children.
216 */
217 bool fCacheEnabled;
218 rc = CFGMR3QueryBoolDef(pCfg, "CacheEnabled", &fCacheEnabled, true);
219 AssertLogRelRCReturn(rc, rc);
220
221 LogRel(("PGM: pgmR3PoolInit: cMaxPages=%#RX16 cMaxUsers=%#RX16 cMaxPhysExts=%#RX16 fCacheEnable=%RTbool\n",
222 cMaxPages, cMaxUsers, cMaxPhysExts, fCacheEnabled));
223
224 /*
225 * Allocate the data structures.
226 */
227 uint32_t cb = RT_OFFSETOF(PGMPOOL, aPages[cMaxPages]);
228 cb += cMaxUsers * sizeof(PGMPOOLUSER);
229 cb += cMaxPhysExts * sizeof(PGMPOOLPHYSEXT);
230 PPGMPOOL pPool;
231 rc = MMR3HyperAllocOnceNoRel(pVM, cb, 0, MM_TAG_PGM_POOL, (void **)&pPool);
232 if (RT_FAILURE(rc))
233 return rc;
234 pVM->pgm.s.pPoolR3 = pPool;
235 pVM->pgm.s.pPoolR0 = MMHyperR3ToR0(pVM, pPool);
236 pVM->pgm.s.pPoolRC = MMHyperR3ToRC(pVM, pPool);
237
238 /*
239 * Initialize it.
240 */
241 pPool->pVMR3 = pVM;
242 pPool->pVMR0 = pVM->pVMR0;
243 pPool->pVMRC = pVM->pVMRC;
244 pPool->cMaxPages = cMaxPages;
245 pPool->cCurPages = PGMPOOL_IDX_FIRST;
246 pPool->iUserFreeHead = 0;
247 pPool->cMaxUsers = cMaxUsers;
248 PPGMPOOLUSER paUsers = (PPGMPOOLUSER)&pPool->aPages[pPool->cMaxPages];
249 pPool->paUsersR3 = paUsers;
250 pPool->paUsersR0 = MMHyperR3ToR0(pVM, paUsers);
251 pPool->paUsersRC = MMHyperR3ToRC(pVM, paUsers);
252 for (unsigned i = 0; i < cMaxUsers; i++)
253 {
254 paUsers[i].iNext = i + 1;
255 paUsers[i].iUser = NIL_PGMPOOL_IDX;
256 paUsers[i].iUserTable = 0xfffffffe;
257 }
258 paUsers[cMaxUsers - 1].iNext = NIL_PGMPOOL_USER_INDEX;
259 pPool->iPhysExtFreeHead = 0;
260 pPool->cMaxPhysExts = cMaxPhysExts;
261 PPGMPOOLPHYSEXT paPhysExts = (PPGMPOOLPHYSEXT)&paUsers[cMaxUsers];
262 pPool->paPhysExtsR3 = paPhysExts;
263 pPool->paPhysExtsR0 = MMHyperR3ToR0(pVM, paPhysExts);
264 pPool->paPhysExtsRC = MMHyperR3ToRC(pVM, paPhysExts);
265 for (unsigned i = 0; i < cMaxPhysExts; i++)
266 {
267 paPhysExts[i].iNext = i + 1;
268 paPhysExts[i].aidx[0] = NIL_PGMPOOL_IDX;
269 paPhysExts[i].apte[0] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
270 paPhysExts[i].aidx[1] = NIL_PGMPOOL_IDX;
271 paPhysExts[i].apte[1] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
272 paPhysExts[i].aidx[2] = NIL_PGMPOOL_IDX;
273 paPhysExts[i].apte[2] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
274 }
275 paPhysExts[cMaxPhysExts - 1].iNext = NIL_PGMPOOL_PHYSEXT_INDEX;
276 for (unsigned i = 0; i < RT_ELEMENTS(pPool->aiHash); i++)
277 pPool->aiHash[i] = NIL_PGMPOOL_IDX;
278 pPool->iAgeHead = NIL_PGMPOOL_IDX;
279 pPool->iAgeTail = NIL_PGMPOOL_IDX;
280 pPool->fCacheEnabled = fCacheEnabled;
281
282 pPool->hAccessHandlerType = NIL_PGMPHYSHANDLERTYPE;
283 rc = PGMR3HandlerPhysicalTypeRegister(pVM, PGMPHYSHANDLERKIND_WRITE,
284 pgmPoolAccessHandler,
285 NULL, "pgmPoolAccessHandler", "pgmRZPoolAccessPfHandler",
286 NULL, "pgmPoolAccessHandler", "pgmRZPoolAccessPfHandler",
287 "Guest Paging Access Handler",
288 &pPool->hAccessHandlerType);
289 AssertLogRelRCReturn(rc, rc);
290
291 pPool->HCPhysTree = 0;
292
293 /*
294 * The NIL entry.
295 */
296 Assert(NIL_PGMPOOL_IDX == 0);
297 pPool->aPages[NIL_PGMPOOL_IDX].enmKind = PGMPOOLKIND_INVALID;
298 pPool->aPages[NIL_PGMPOOL_IDX].idx = NIL_PGMPOOL_IDX;
299 pPool->aPages[NIL_PGMPOOL_IDX].Core.Key = NIL_RTHCPHYS;
300 pPool->aPages[NIL_PGMPOOL_IDX].GCPhys = NIL_RTGCPHYS;
301 pPool->aPages[NIL_PGMPOOL_IDX].iNext = NIL_PGMPOOL_IDX;
302 /* pPool->aPages[NIL_PGMPOOL_IDX].cLocked = INT32_MAX; - test this out... */
303 pPool->aPages[NIL_PGMPOOL_IDX].pvPageR3 = 0;
304 pPool->aPages[NIL_PGMPOOL_IDX].iUserHead = NIL_PGMPOOL_USER_INDEX;
305 pPool->aPages[NIL_PGMPOOL_IDX].iModifiedNext = NIL_PGMPOOL_IDX;
306 pPool->aPages[NIL_PGMPOOL_IDX].iModifiedPrev = NIL_PGMPOOL_IDX;
307 pPool->aPages[NIL_PGMPOOL_IDX].iMonitoredNext = NIL_PGMPOOL_IDX;
308 pPool->aPages[NIL_PGMPOOL_IDX].iMonitoredPrev = NIL_PGMPOOL_IDX;
309 pPool->aPages[NIL_PGMPOOL_IDX].iAgeNext = NIL_PGMPOOL_IDX;
310 pPool->aPages[NIL_PGMPOOL_IDX].iAgePrev = NIL_PGMPOOL_IDX;
311
312 Assert(pPool->aPages[NIL_PGMPOOL_IDX].idx == NIL_PGMPOOL_IDX);
313 Assert(pPool->aPages[NIL_PGMPOOL_IDX].GCPhys == NIL_RTGCPHYS);
314 Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fSeenNonGlobal);
315 Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fMonitored);
316 Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fCached);
317 Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fZeroed);
318 Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fReusedFlushPending);
319
320#ifdef VBOX_WITH_STATISTICS
321 /*
322 * Register statistics.
323 */
324 STAM_REG(pVM, &pPool->cCurPages, STAMTYPE_U16, "/PGM/Pool/cCurPages", STAMUNIT_PAGES, "Current pool size.");
325 STAM_REG(pVM, &pPool->cMaxPages, STAMTYPE_U16, "/PGM/Pool/cMaxPages", STAMUNIT_PAGES, "Max pool size.");
326 STAM_REG(pVM, &pPool->cUsedPages, STAMTYPE_U16, "/PGM/Pool/cUsedPages", STAMUNIT_PAGES, "The number of pages currently in use.");
327 STAM_REG(pVM, &pPool->cUsedPagesHigh, STAMTYPE_U16_RESET, "/PGM/Pool/cUsedPagesHigh", STAMUNIT_PAGES, "The high watermark for cUsedPages.");
328 STAM_REG(pVM, &pPool->StatAlloc, STAMTYPE_PROFILE_ADV, "/PGM/Pool/Alloc", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolAlloc.");
329 STAM_REG(pVM, &pPool->StatClearAll, STAMTYPE_PROFILE, "/PGM/Pool/ClearAll", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmR3PoolClearAll.");
330 STAM_REG(pVM, &pPool->StatR3Reset, STAMTYPE_PROFILE, "/PGM/Pool/R3Reset", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmR3PoolReset.");
331 STAM_REG(pVM, &pPool->StatFlushPage, STAMTYPE_PROFILE, "/PGM/Pool/FlushPage", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolFlushPage.");
332 STAM_REG(pVM, &pPool->StatFree, STAMTYPE_PROFILE, "/PGM/Pool/Free", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolFree.");
333 STAM_REG(pVM, &pPool->StatForceFlushPage, STAMTYPE_COUNTER, "/PGM/Pool/FlushForce", STAMUNIT_OCCURENCES, "Counting explicit flushes by PGMPoolFlushPage().");
334 STAM_REG(pVM, &pPool->StatForceFlushDirtyPage, STAMTYPE_COUNTER, "/PGM/Pool/FlushForceDirty", STAMUNIT_OCCURENCES, "Counting explicit flushes of dirty pages by PGMPoolFlushPage().");
335 STAM_REG(pVM, &pPool->StatForceFlushReused, STAMTYPE_COUNTER, "/PGM/Pool/FlushReused", STAMUNIT_OCCURENCES, "Counting flushes for reused pages.");
336 STAM_REG(pVM, &pPool->StatZeroPage, STAMTYPE_PROFILE, "/PGM/Pool/ZeroPage", STAMUNIT_TICKS_PER_CALL, "Profiling time spent zeroing pages. Overlaps with Alloc.");
337 STAM_REG(pVM, &pPool->cMaxUsers, STAMTYPE_U16, "/PGM/Pool/Track/cMaxUsers", STAMUNIT_COUNT, "Max user tracking records.");
338 STAM_REG(pVM, &pPool->cPresent, STAMTYPE_U32, "/PGM/Pool/Track/cPresent", STAMUNIT_COUNT, "Number of present page table entries.");
339 STAM_REG(pVM, &pPool->StatTrackDeref, STAMTYPE_PROFILE, "/PGM/Pool/Track/Deref", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackDeref.");
340 STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPT, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPT", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPT.");
341 STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPTs, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPTs", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPTs.");
342 STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPTsSlow, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPTsSlow", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPTsSlow.");
343 STAM_REG(pVM, &pPool->StatTrackFlushEntry, STAMTYPE_COUNTER, "/PGM/Pool/Track/Entry/Flush", STAMUNIT_COUNT, "Nr of flushed entries.");
344 STAM_REG(pVM, &pPool->StatTrackFlushEntryKeep, STAMTYPE_COUNTER, "/PGM/Pool/Track/Entry/Update", STAMUNIT_COUNT, "Nr of updated entries.");
345 STAM_REG(pVM, &pPool->StatTrackFreeUpOneUser, STAMTYPE_COUNTER, "/PGM/Pool/Track/FreeUpOneUser", STAMUNIT_TICKS_PER_CALL, "The number of times we were out of user tracking records.");
346 STAM_REG(pVM, &pPool->StatTrackDerefGCPhys, STAMTYPE_PROFILE, "/PGM/Pool/Track/DrefGCPhys", STAMUNIT_TICKS_PER_CALL, "Profiling deref activity related tracking GC physical pages.");
347 STAM_REG(pVM, &pPool->StatTrackLinearRamSearches, STAMTYPE_COUNTER, "/PGM/Pool/Track/LinearRamSearches", STAMUNIT_OCCURENCES, "The number of times we had to do linear ram searches.");
348 STAM_REG(pVM, &pPool->StamTrackPhysExtAllocFailures,STAMTYPE_COUNTER, "/PGM/Pool/Track/PhysExtAllocFailures", STAMUNIT_OCCURENCES, "The number of failing pgmPoolTrackPhysExtAlloc calls.");
349
350 STAM_REG(pVM, &pPool->StatMonitorPfRZ, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/#PF", STAMUNIT_TICKS_PER_CALL, "Profiling the RC/R0 #PF access handler.");
351 STAM_REG(pVM, &pPool->StatMonitorPfRZEmulateInstr, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/EmulateInstr", STAMUNIT_OCCURENCES, "Times we've failed interpreting the instruction.");
352 STAM_REG(pVM, &pPool->StatMonitorPfRZFlushPage, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/#PF/FlushPage", STAMUNIT_TICKS_PER_CALL, "Profiling the pgmPoolFlushPage calls made from the RC/R0 access handler.");
353 STAM_REG(pVM, &pPool->StatMonitorPfRZFlushReinit, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/FlushReinit", STAMUNIT_OCCURENCES, "Times we've detected a page table reinit.");
354 STAM_REG(pVM, &pPool->StatMonitorPfRZFlushModOverflow,STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/FlushOverflow", STAMUNIT_OCCURENCES, "Counting flushes for pages that are modified too often.");
355 STAM_REG(pVM, &pPool->StatMonitorPfRZFork, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/Fork", STAMUNIT_OCCURENCES, "Times we've detected fork().");
356 STAM_REG(pVM, &pPool->StatMonitorPfRZHandled, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/#PF/Handled", STAMUNIT_TICKS_PER_CALL, "Profiling the RC/R0 #PF access we've handled (except REP STOSD).");
357 STAM_REG(pVM, &pPool->StatMonitorPfRZIntrFailPatch1, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/IntrFailPatch1", STAMUNIT_OCCURENCES, "Times we've failed interpreting a patch code instruction.");
358 STAM_REG(pVM, &pPool->StatMonitorPfRZIntrFailPatch2, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/IntrFailPatch2", STAMUNIT_OCCURENCES, "Times we've failed interpreting a patch code instruction during flushing.");
359 STAM_REG(pVM, &pPool->StatMonitorPfRZRepPrefix, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/RepPrefix", STAMUNIT_OCCURENCES, "The number of times we've seen rep prefixes we can't handle.");
360 STAM_REG(pVM, &pPool->StatMonitorPfRZRepStosd, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/#PF/RepStosd", STAMUNIT_TICKS_PER_CALL, "Profiling the REP STOSD cases we've handled.");
361
362 STAM_REG(pVM, &pPool->StatMonitorRZ, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM", STAMUNIT_TICKS_PER_CALL, "Profiling the regular access handler.");
363 STAM_REG(pVM, &pPool->StatMonitorRZFlushPage, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/FlushPage", STAMUNIT_TICKS_PER_CALL, "Profiling the pgmPoolFlushPage calls made from the regular access handler.");
364 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size01", STAMUNIT_OCCURENCES, "Number of 1 byte accesses.");
365 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size02", STAMUNIT_OCCURENCES, "Number of 2 byte accesses.");
366 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size03", STAMUNIT_OCCURENCES, "Number of 3 byte accesses.");
367 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size04", STAMUNIT_OCCURENCES, "Number of 4 byte accesses.");
368 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size05", STAMUNIT_OCCURENCES, "Number of 5 byte accesses.");
369 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size06", STAMUNIT_OCCURENCES, "Number of 6 byte accesses.");
370 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size07", STAMUNIT_OCCURENCES, "Number of 7 byte accesses.");
371 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[7], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size08", STAMUNIT_OCCURENCES, "Number of 8 byte accesses.");
372 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[8], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size09", STAMUNIT_OCCURENCES, "Number of 9 byte accesses.");
373 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[9], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0a", STAMUNIT_OCCURENCES, "Number of 10 byte accesses.");
374 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[10], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0b", STAMUNIT_OCCURENCES, "Number of 11 byte accesses.");
375 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[11], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0c", STAMUNIT_OCCURENCES, "Number of 12 byte accesses.");
376 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[12], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0d", STAMUNIT_OCCURENCES, "Number of 13 byte accesses.");
377 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[13], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0e", STAMUNIT_OCCURENCES, "Number of 14 byte accesses.");
378 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[14], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0f", STAMUNIT_OCCURENCES, "Number of 15 byte accesses.");
379 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[15], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size10", STAMUNIT_OCCURENCES, "Number of 16 byte accesses.");
380 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[16], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size11-2f", STAMUNIT_OCCURENCES, "Number of 17-31 byte accesses.");
381 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[17], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size20-3f", STAMUNIT_OCCURENCES, "Number of 32-63 byte accesses.");
382 STAM_REG(pVM, &pPool->aStatMonitorRZSizes[18], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size40+", STAMUNIT_OCCURENCES, "Number of 64+ byte accesses.");
383 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned1", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 1.");
384 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned2", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 2.");
385 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned3", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 3.");
386 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned4", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 4.");
387 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned5", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 5.");
388 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned6", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 6.");
389 STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned7", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 7.");
390
391 STAM_REG(pVM, &pPool->StatMonitorRZFaultPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PT", STAMUNIT_OCCURENCES, "Nr of handled PT faults.");
392 STAM_REG(pVM, &pPool->StatMonitorRZFaultPD, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PD", STAMUNIT_OCCURENCES, "Nr of handled PD faults.");
393 STAM_REG(pVM, &pPool->StatMonitorRZFaultPDPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PDPT", STAMUNIT_OCCURENCES, "Nr of handled PDPT faults.");
394 STAM_REG(pVM, &pPool->StatMonitorRZFaultPML4, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PML4", STAMUNIT_OCCURENCES, "Nr of handled PML4 faults.");
395
396 STAM_REG(pVM, &pPool->StatMonitorR3, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3", STAMUNIT_TICKS_PER_CALL, "Profiling the R3 access handler.");
397 STAM_REG(pVM, &pPool->StatMonitorR3FlushPage, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/FlushPage", STAMUNIT_TICKS_PER_CALL, "Profiling the pgmPoolFlushPage calls made from the R3 access handler.");
398 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size01", STAMUNIT_OCCURENCES, "Number of 1 byte accesses (R3).");
399 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size02", STAMUNIT_OCCURENCES, "Number of 2 byte accesses (R3).");
400 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size03", STAMUNIT_OCCURENCES, "Number of 3 byte accesses (R3).");
401 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size04", STAMUNIT_OCCURENCES, "Number of 4 byte accesses (R3).");
402 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size05", STAMUNIT_OCCURENCES, "Number of 5 byte accesses (R3).");
403 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size06", STAMUNIT_OCCURENCES, "Number of 6 byte accesses (R3).");
404 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size07", STAMUNIT_OCCURENCES, "Number of 7 byte accesses (R3).");
405 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[7], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size08", STAMUNIT_OCCURENCES, "Number of 8 byte accesses (R3).");
406 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[8], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size09", STAMUNIT_OCCURENCES, "Number of 9 byte accesses (R3).");
407 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[9], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0a", STAMUNIT_OCCURENCES, "Number of 10 byte accesses (R3).");
408 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[10], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0b", STAMUNIT_OCCURENCES, "Number of 11 byte accesses (R3).");
409 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[11], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0c", STAMUNIT_OCCURENCES, "Number of 12 byte accesses (R3).");
410 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[12], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0d", STAMUNIT_OCCURENCES, "Number of 13 byte accesses (R3).");
411 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[13], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0e", STAMUNIT_OCCURENCES, "Number of 14 byte accesses (R3).");
412 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[14], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0f", STAMUNIT_OCCURENCES, "Number of 15 byte accesses (R3).");
413 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[15], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size10", STAMUNIT_OCCURENCES, "Number of 16 byte accesses (R3).");
414 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[16], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size11-2f", STAMUNIT_OCCURENCES, "Number of 17-31 byte accesses.");
415 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[17], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size20-3f", STAMUNIT_OCCURENCES, "Number of 32-63 byte accesses.");
416 STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[18], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size40+", STAMUNIT_OCCURENCES, "Number of 64+ byte accesses.");
417 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned1", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 1 in R3.");
418 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned2", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 2 in R3.");
419 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned3", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 3 in R3.");
420 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned4", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 4 in R3.");
421 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned5", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 5 in R3.");
422 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned6", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 6 in R3.");
423 STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned7", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 7 in R3.");
424
425 STAM_REG(pVM, &pPool->StatMonitorR3FaultPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PT", STAMUNIT_OCCURENCES, "Nr of handled PT faults.");
426 STAM_REG(pVM, &pPool->StatMonitorR3FaultPD, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PD", STAMUNIT_OCCURENCES, "Nr of handled PD faults.");
427 STAM_REG(pVM, &pPool->StatMonitorR3FaultPDPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PDPT", STAMUNIT_OCCURENCES, "Nr of handled PDPT faults.");
428 STAM_REG(pVM, &pPool->StatMonitorR3FaultPML4, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PML4", STAMUNIT_OCCURENCES, "Nr of handled PML4 faults.");
429
430 STAM_REG(pVM, &pPool->cModifiedPages, STAMTYPE_U16, "/PGM/Pool/Monitor/cModifiedPages", STAMUNIT_PAGES, "The current cModifiedPages value.");
431 STAM_REG(pVM, &pPool->cModifiedPagesHigh, STAMTYPE_U16_RESET, "/PGM/Pool/Monitor/cModifiedPagesHigh", STAMUNIT_PAGES, "The high watermark for cModifiedPages.");
432 STAM_REG(pVM, &pPool->StatResetDirtyPages, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/Resets", STAMUNIT_OCCURENCES, "Times we've called pgmPoolResetDirtyPages (and there were dirty page).");
433 STAM_REG(pVM, &pPool->StatDirtyPage, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/Pages", STAMUNIT_OCCURENCES, "Times we've called pgmPoolAddDirtyPage.");
434 STAM_REG(pVM, &pPool->StatDirtyPageDupFlush, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/FlushDup", STAMUNIT_OCCURENCES, "Times we've had to flush duplicates for dirty page management.");
435 STAM_REG(pVM, &pPool->StatDirtyPageOverFlowFlush, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/FlushOverflow",STAMUNIT_OCCURENCES, "Times we've had to flush because of overflow.");
436 STAM_REG(pVM, &pPool->StatCacheHits, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Hits", STAMUNIT_OCCURENCES, "The number of pgmPoolAlloc calls satisfied by the cache.");
437 STAM_REG(pVM, &pPool->StatCacheMisses, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Misses", STAMUNIT_OCCURENCES, "The number of pgmPoolAlloc calls not statisfied by the cache.");
438 STAM_REG(pVM, &pPool->StatCacheKindMismatches, STAMTYPE_COUNTER, "/PGM/Pool/Cache/KindMismatches", STAMUNIT_OCCURENCES, "The number of shadow page kind mismatches. (Better be low, preferably 0!)");
439 STAM_REG(pVM, &pPool->StatCacheFreeUpOne, STAMTYPE_COUNTER, "/PGM/Pool/Cache/FreeUpOne", STAMUNIT_OCCURENCES, "The number of times the cache was asked to free up a page.");
440 STAM_REG(pVM, &pPool->StatCacheCacheable, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Cacheable", STAMUNIT_OCCURENCES, "The number of cacheable allocations.");
441 STAM_REG(pVM, &pPool->StatCacheUncacheable, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Uncacheable", STAMUNIT_OCCURENCES, "The number of uncacheable allocations.");
442#endif /* VBOX_WITH_STATISTICS */
443
444#ifdef VBOX_WITH_DEBUGGER
445 /*
446 * Debugger commands.
447 */
448 static bool s_fRegisteredCmds = false;
449 if (!s_fRegisteredCmds)
450 {
451 rc = DBGCRegisterCommands(&g_aCmds[0], RT_ELEMENTS(g_aCmds));
452 if (RT_SUCCESS(rc))
453 s_fRegisteredCmds = true;
454 }
455#endif
456
457 return VINF_SUCCESS;
458}
459
460
461/**
462 * Relocate the page pool data.
463 *
464 * @param pVM The cross context VM structure.
465 */
466void pgmR3PoolRelocate(PVM pVM)
467{
468 pVM->pgm.s.pPoolRC = MMHyperR3ToRC(pVM, pVM->pgm.s.pPoolR3);
469 pVM->pgm.s.pPoolR3->pVMRC = pVM->pVMRC;
470 pVM->pgm.s.pPoolR3->paUsersRC = MMHyperR3ToRC(pVM, pVM->pgm.s.pPoolR3->paUsersR3);
471 pVM->pgm.s.pPoolR3->paPhysExtsRC = MMHyperR3ToRC(pVM, pVM->pgm.s.pPoolR3->paPhysExtsR3);
472}
473
474
475/**
476 * Grows the shadow page pool.
477 *
478 * I.e. adds more pages to it, assuming that hasn't reached cMaxPages yet.
479 *
480 * @returns VBox status code.
481 * @param pVM The cross context VM structure.
482 */
483VMMR3DECL(int) PGMR3PoolGrow(PVM pVM)
484{
485 PPGMPOOL pPool = pVM->pgm.s.pPoolR3;
486 AssertReturn(pPool->cCurPages < pPool->cMaxPages, VERR_PGM_POOL_MAXED_OUT_ALREADY);
487
488 /* With 32-bit guests and no EPT, the CR3 limits the root pages to low
489 (below 4 GB) memory. */
490 /** @todo change the pool to handle ROOT page allocations specially when
491 * required. */
492 bool fCanUseHighMemory = HMIsNestedPagingActive(pVM)
493 && HMGetShwPagingMode(pVM) == PGMMODE_EPT;
494
495 pgmLock(pVM);
496
497 /*
498 * How much to grow it by?
499 */
500 uint32_t cPages = pPool->cMaxPages - pPool->cCurPages;
501 cPages = RT_MIN(PGMPOOL_CFG_MAX_GROW, cPages);
502 LogFlow(("PGMR3PoolGrow: Growing the pool by %d (%#x) pages. fCanUseHighMemory=%RTbool\n", cPages, cPages, fCanUseHighMemory));
503
504 for (unsigned i = pPool->cCurPages; cPages-- > 0; i++)
505 {
506 PPGMPOOLPAGE pPage = &pPool->aPages[i];
507
508 if (fCanUseHighMemory)
509 pPage->pvPageR3 = MMR3PageAlloc(pVM);
510 else
511 pPage->pvPageR3 = MMR3PageAllocLow(pVM);
512 if (!pPage->pvPageR3)
513 {
514 Log(("We're out of memory!! i=%d fCanUseHighMemory=%RTbool\n", i, fCanUseHighMemory));
515 pgmUnlock(pVM);
516 return i ? VINF_SUCCESS : VERR_NO_PAGE_MEMORY;
517 }
518 pPage->Core.Key = MMPage2Phys(pVM, pPage->pvPageR3);
519 AssertFatal(pPage->Core.Key < _4G || fCanUseHighMemory);
520 pPage->GCPhys = NIL_RTGCPHYS;
521 pPage->enmKind = PGMPOOLKIND_FREE;
522 pPage->idx = pPage - &pPool->aPages[0];
523 LogFlow(("PGMR3PoolGrow: insert page #%#x - %RHp\n", pPage->idx, pPage->Core.Key));
524 pPage->iNext = pPool->iFreeHead;
525 pPage->iUserHead = NIL_PGMPOOL_USER_INDEX;
526 pPage->iModifiedNext = NIL_PGMPOOL_IDX;
527 pPage->iModifiedPrev = NIL_PGMPOOL_IDX;
528 pPage->iMonitoredNext = NIL_PGMPOOL_IDX;
529 pPage->iMonitoredPrev = NIL_PGMPOOL_IDX;
530 pPage->iAgeNext = NIL_PGMPOOL_IDX;
531 pPage->iAgePrev = NIL_PGMPOOL_IDX;
532 /* commit it */
533 bool fRc = RTAvloHCPhysInsert(&pPool->HCPhysTree, &pPage->Core); Assert(fRc); NOREF(fRc);
534 pPool->iFreeHead = i;
535 pPool->cCurPages = i + 1;
536 }
537
538 pgmUnlock(pVM);
539 Assert(pPool->cCurPages <= pPool->cMaxPages);
540 return VINF_SUCCESS;
541}
542
543
544/**
545 * Rendezvous callback used by pgmR3PoolClearAll that clears all shadow pages
546 * and all modification counters.
547 *
548 * This is only called on one of the EMTs while the other ones are waiting for
549 * it to complete this function.
550 *
551 * @returns VINF_SUCCESS (VBox strict status code).
552 * @param pVM The cross context VM structure.
553 * @param pVCpu The cross context virtual CPU structure of the calling EMT. Unused.
554 * @param fpvFlushRemTlb When not NULL, we'll flush the REM TLB as well.
555 * (This is the pvUser, so it has to be void *.)
556 *
557 */
558DECLCALLBACK(VBOXSTRICTRC) pgmR3PoolClearAllRendezvous(PVM pVM, PVMCPU pVCpu, void *fpvFlushRemTlb)
559{
560 PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
561 STAM_PROFILE_START(&pPool->StatClearAll, c);
562 NOREF(pVCpu);
563
564 pgmLock(pVM);
565 Log(("pgmR3PoolClearAllRendezvous: cUsedPages=%d fpvFlushRemTlb=%RTbool\n", pPool->cUsedPages, !!fpvFlushRemTlb));
566
567 /*
568 * Iterate all the pages until we've encountered all that are in use.
569 * This is a simple but not quite optimal solution.
570 */
571 unsigned cModifiedPages = 0; NOREF(cModifiedPages);
572 unsigned cLeft = pPool->cUsedPages;
573 uint32_t iPage = pPool->cCurPages;
574 while (--iPage >= PGMPOOL_IDX_FIRST)
575 {
576 PPGMPOOLPAGE pPage = &pPool->aPages[iPage];
577 if (pPage->GCPhys != NIL_RTGCPHYS)
578 {
579 switch (pPage->enmKind)
580 {
581 /*
582 * We only care about shadow page tables that reference physical memory
583 */
584#ifdef PGM_WITH_LARGE_PAGES
585 case PGMPOOLKIND_EPT_PD_FOR_PHYS: /* Large pages reference 2 MB of physical memory, so we must clear them. */
586 if (pPage->cPresent)
587 {
588 PX86PDPAE pShwPD = (PX86PDPAE)PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
589 for (unsigned i = 0; i < RT_ELEMENTS(pShwPD->a); i++)
590 {
591 if ( pShwPD->a[i].n.u1Present
592 && pShwPD->a[i].b.u1Size)
593 {
594 Assert(!(pShwPD->a[i].u & PGM_PDFLAGS_MAPPING));
595 pShwPD->a[i].u = 0;
596 Assert(pPage->cPresent);
597 pPage->cPresent--;
598 }
599 }
600 if (pPage->cPresent == 0)
601 pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
602 }
603 goto default_case;
604
605 case PGMPOOLKIND_PAE_PD_PHYS: /* Large pages reference 2 MB of physical memory, so we must clear them. */
606 if (pPage->cPresent)
607 {
608 PEPTPD pShwPD = (PEPTPD)PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
609 for (unsigned i = 0; i < RT_ELEMENTS(pShwPD->a); i++)
610 {
611 Assert((pShwPD->a[i].u & UINT64_C(0xfff0000000000f80)) == 0);
612 if ( pShwPD->a[i].n.u1Present
613 && pShwPD->a[i].b.u1Size)
614 {
615 Assert(!(pShwPD->a[i].u & PGM_PDFLAGS_MAPPING));
616 pShwPD->a[i].u = 0;
617 Assert(pPage->cPresent);
618 pPage->cPresent--;
619 }
620 }
621 if (pPage->cPresent == 0)
622 pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
623 }
624 goto default_case;
625#endif /* PGM_WITH_LARGE_PAGES */
626
627 case PGMPOOLKIND_32BIT_PT_FOR_32BIT_PT:
628 case PGMPOOLKIND_32BIT_PT_FOR_32BIT_4MB:
629 case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
630 case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
631 case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
632 case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
633 case PGMPOOLKIND_32BIT_PT_FOR_PHYS:
634 case PGMPOOLKIND_PAE_PT_FOR_PHYS:
635 case PGMPOOLKIND_EPT_PT_FOR_PHYS:
636 {
637 if (pPage->cPresent)
638 {
639 void *pvShw = PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
640 STAM_PROFILE_START(&pPool->StatZeroPage, z);
641#if 0
642 /* Useful check for leaking references; *very* expensive though. */
643 switch (pPage->enmKind)
644 {
645 case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
646 case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
647 case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
648 case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
649 case PGMPOOLKIND_PAE_PT_FOR_PHYS:
650 {
651 bool fFoundFirst = false;
652 PPGMSHWPTPAE pPT = (PPGMSHWPTPAE)pvShw;
653 for (unsigned ptIndex = 0; ptIndex < RT_ELEMENTS(pPT->a); ptIndex++)
654 {
655 if (pPT->a[ptIndex].u)
656 {
657 if (!fFoundFirst)
658 {
659 AssertFatalMsg(pPage->iFirstPresent <= ptIndex, ("ptIndex = %d first present = %d\n", ptIndex, pPage->iFirstPresent));
660 if (pPage->iFirstPresent != ptIndex)
661 Log(("ptIndex = %d first present = %d\n", ptIndex, pPage->iFirstPresent));
662 fFoundFirst = true;
663 }
664 if (PGMSHWPTEPAE_IS_P(pPT->a[ptIndex]))
665 {
666 pgmPoolTracDerefGCPhysHint(pPool, pPage, PGMSHWPTEPAE_GET_HCPHYS(pPT->a[ptIndex]), NIL_RTGCPHYS);
667 if (pPage->iFirstPresent == ptIndex)
668 pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
669 }
670 }
671 }
672 AssertFatalMsg(pPage->cPresent == 0, ("cPresent = %d pPage = %RGv\n", pPage->cPresent, pPage->GCPhys));
673 break;
674 }
675 default:
676 break;
677 }
678#endif
679 ASMMemZeroPage(pvShw);
680 STAM_PROFILE_STOP(&pPool->StatZeroPage, z);
681 pPage->cPresent = 0;
682 pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
683 }
684 }
685 RT_FALL_THRU();
686#ifdef PGM_WITH_LARGE_PAGES
687 default_case:
688#endif
689 default:
690 Assert(!pPage->cModifications || ++cModifiedPages);
691 Assert(pPage->iModifiedNext == NIL_PGMPOOL_IDX || pPage->cModifications);
692 Assert(pPage->iModifiedPrev == NIL_PGMPOOL_IDX || pPage->cModifications);
693 pPage->iModifiedNext = NIL_PGMPOOL_IDX;
694 pPage->iModifiedPrev = NIL_PGMPOOL_IDX;
695 pPage->cModifications = 0;
696 break;
697
698 }
699 if (!--cLeft)
700 break;
701 }
702 }
703
704#ifndef DEBUG_michael
705 AssertMsg(cModifiedPages == pPool->cModifiedPages, ("%d != %d\n", cModifiedPages, pPool->cModifiedPages));
706#endif
707 pPool->iModifiedHead = NIL_PGMPOOL_IDX;
708 pPool->cModifiedPages = 0;
709
710 /*
711 * Clear all the GCPhys links and rebuild the phys ext free list.
712 */
713 for (PPGMRAMRANGE pRam = pPool->CTX_SUFF(pVM)->pgm.s.CTX_SUFF(pRamRangesX);
714 pRam;
715 pRam = pRam->CTX_SUFF(pNext))
716 {
717 iPage = pRam->cb >> PAGE_SHIFT;
718 while (iPage-- > 0)
719 PGM_PAGE_SET_TRACKING(pVM, &pRam->aPages[iPage], 0);
720 }
721
722 pPool->iPhysExtFreeHead = 0;
723 PPGMPOOLPHYSEXT paPhysExts = pPool->CTX_SUFF(paPhysExts);
724 const unsigned cMaxPhysExts = pPool->cMaxPhysExts;
725 for (unsigned i = 0; i < cMaxPhysExts; i++)
726 {
727 paPhysExts[i].iNext = i + 1;
728 paPhysExts[i].aidx[0] = NIL_PGMPOOL_IDX;
729 paPhysExts[i].apte[0] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
730 paPhysExts[i].aidx[1] = NIL_PGMPOOL_IDX;
731 paPhysExts[i].apte[1] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
732 paPhysExts[i].aidx[2] = NIL_PGMPOOL_IDX;
733 paPhysExts[i].apte[2] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
734 }
735 paPhysExts[cMaxPhysExts - 1].iNext = NIL_PGMPOOL_PHYSEXT_INDEX;
736
737
738#ifdef PGMPOOL_WITH_OPTIMIZED_DIRTY_PT
739 /* Reset all dirty pages to reactivate the page monitoring. */
740 /* Note: we must do this *after* clearing all page references and shadow page tables as there might be stale references to
741 * recently removed MMIO ranges around that might otherwise end up asserting in pgmPoolTracDerefGCPhysHint
742 */
743 for (unsigned i = 0; i < RT_ELEMENTS(pPool->aDirtyPages); i++)
744 {
745 PPGMPOOLPAGE pPage;
746 unsigned idxPage;
747
748 if (pPool->aDirtyPages[i].uIdx == NIL_PGMPOOL_IDX)
749 continue;
750
751 idxPage = pPool->aDirtyPages[i].uIdx;
752 AssertRelease(idxPage != NIL_PGMPOOL_IDX);
753 pPage = &pPool->aPages[idxPage];
754 Assert(pPage->idx == idxPage);
755 Assert(pPage->iMonitoredNext == NIL_PGMPOOL_IDX && pPage->iMonitoredPrev == NIL_PGMPOOL_IDX);
756
757 AssertMsg(pPage->fDirty, ("Page %RGp (slot=%d) not marked dirty!", pPage->GCPhys, i));
758
759 Log(("Reactivate dirty page %RGp\n", pPage->GCPhys));
760
761 /* First write protect the page again to catch all write accesses. (before checking for changes -> SMP) */
762 int rc = PGMHandlerPhysicalReset(pVM, pPage->GCPhys & PAGE_BASE_GC_MASK);
763 AssertRCSuccess(rc);
764 pPage->fDirty = false;
765
766 pPool->aDirtyPages[i].uIdx = NIL_PGMPOOL_IDX;
767 }
768
769 /* Clear all dirty pages. */
770 pPool->idxFreeDirtyPage = 0;
771 pPool->cDirtyPages = 0;
772#endif
773
774 /* Clear the PGM_SYNC_CLEAR_PGM_POOL flag on all VCPUs to prevent redundant flushes. */
775 for (VMCPUID idCpu = 0; idCpu < pVM->cCpus; idCpu++)
776 pVM->aCpus[idCpu].pgm.s.fSyncFlags &= ~PGM_SYNC_CLEAR_PGM_POOL;
777
778 /* Flush job finished. */
779 VM_FF_CLEAR(pVM, VM_FF_PGM_POOL_FLUSH_PENDING);
780 pPool->cPresent = 0;
781 pgmUnlock(pVM);
782
783 PGM_INVL_ALL_VCPU_TLBS(pVM);
784
785 if (fpvFlushRemTlb)
786 for (VMCPUID idCpu = 0; idCpu < pVM->cCpus; idCpu++)
787 CPUMSetChangedFlags(&pVM->aCpus[idCpu], CPUM_CHANGED_GLOBAL_TLB_FLUSH);
788
789 STAM_PROFILE_STOP(&pPool->StatClearAll, c);
790 return VINF_SUCCESS;
791}
792
793
794/**
795 * Clears the shadow page pool.
796 *
797 * @param pVM The cross context VM structure.
798 * @param fFlushRemTlb When set, the REM TLB is scheduled for flushing as
799 * well.
800 */
801void pgmR3PoolClearAll(PVM pVM, bool fFlushRemTlb)
802{
803 int rc = VMMR3EmtRendezvous(pVM, VMMEMTRENDEZVOUS_FLAGS_TYPE_ONCE, pgmR3PoolClearAllRendezvous, &fFlushRemTlb);
804 AssertRC(rc);
805}
806
807
808/**
809 * Protect all pgm pool page table entries to monitor writes
810 *
811 * @param pVM The cross context VM structure.
812 *
813 * @remarks ASSUMES the caller will flush all TLBs!!
814 */
815void pgmR3PoolWriteProtectPages(PVM pVM)
816{
817 PGM_LOCK_ASSERT_OWNER(pVM);
818 PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
819 unsigned cLeft = pPool->cUsedPages;
820 unsigned iPage = pPool->cCurPages;
821 while (--iPage >= PGMPOOL_IDX_FIRST)
822 {
823 PPGMPOOLPAGE pPage = &pPool->aPages[iPage];
824 if ( pPage->GCPhys != NIL_RTGCPHYS
825 && pPage->cPresent)
826 {
827 union
828 {
829 void *pv;
830 PX86PT pPT;
831 PPGMSHWPTPAE pPTPae;
832 PEPTPT pPTEpt;
833 } uShw;
834 uShw.pv = PGMPOOL_PAGE_2_PTR(pVM, pPage);
835
836 switch (pPage->enmKind)
837 {
838 /*
839 * We only care about shadow page tables.
840 */
841 case PGMPOOLKIND_32BIT_PT_FOR_32BIT_PT:
842 case PGMPOOLKIND_32BIT_PT_FOR_32BIT_4MB:
843 case PGMPOOLKIND_32BIT_PT_FOR_PHYS:
844 for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPT->a); iShw++)
845 {
846 if (uShw.pPT->a[iShw].n.u1Present)
847 uShw.pPT->a[iShw].n.u1Write = 0;
848 }
849 break;
850
851 case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
852 case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
853 case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
854 case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
855 case PGMPOOLKIND_PAE_PT_FOR_PHYS:
856 for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPTPae->a); iShw++)
857 {
858 if (PGMSHWPTEPAE_IS_P(uShw.pPTPae->a[iShw]))
859 PGMSHWPTEPAE_SET_RO(uShw.pPTPae->a[iShw]);
860 }
861 break;
862
863 case PGMPOOLKIND_EPT_PT_FOR_PHYS:
864 for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPTEpt->a); iShw++)
865 {
866 if (uShw.pPTEpt->a[iShw].n.u1Present)
867 uShw.pPTEpt->a[iShw].n.u1Write = 0;
868 }
869 break;
870
871 default:
872 break;
873 }
874 if (!--cLeft)
875 break;
876 }
877 }
878}
879
880#ifdef VBOX_WITH_DEBUGGER
881/**
882 * @callback_method_impl{FNDBGCCMD, The '.pgmpoolcheck' command.}
883 */
884static DECLCALLBACK(int) pgmR3PoolCmdCheck(PCDBGCCMD pCmd, PDBGCCMDHLP pCmdHlp, PUVM pUVM, PCDBGCVAR paArgs, unsigned cArgs)
885{
886 DBGC_CMDHLP_REQ_UVM_RET(pCmdHlp, pCmd, pUVM);
887 PVM pVM = pUVM->pVM;
888 VM_ASSERT_VALID_EXT_RETURN(pVM, VERR_INVALID_VM_HANDLE);
889 DBGC_CMDHLP_ASSERT_PARSER_RET(pCmdHlp, pCmd, -1, cArgs == 0);
890 uint32_t cErrors = 0;
891 NOREF(paArgs);
892
893 PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
894 for (unsigned i = 0; i < pPool->cCurPages; i++)
895 {
896 PPGMPOOLPAGE pPage = &pPool->aPages[i];
897 bool fFirstMsg = true;
898
899 /** @todo cover other paging modes too. */
900 if (pPage->enmKind == PGMPOOLKIND_PAE_PT_FOR_PAE_PT)
901 {
902 PPGMSHWPTPAE pShwPT = (PPGMSHWPTPAE)PGMPOOL_PAGE_2_PTR(pPool->CTX_SUFF(pVM), pPage);
903 {
904 PX86PTPAE pGstPT;
905 PGMPAGEMAPLOCK LockPage;
906 int rc = PGMPhysGCPhys2CCPtrReadOnly(pVM, pPage->GCPhys, (const void **)&pGstPT, &LockPage); AssertReleaseRC(rc);
907
908 /* Check if any PTEs are out of sync. */
909 for (unsigned j = 0; j < RT_ELEMENTS(pShwPT->a); j++)
910 {
911 if (PGMSHWPTEPAE_IS_P(pShwPT->a[j]))
912 {
913 RTHCPHYS HCPhys = NIL_RTHCPHYS;
914 rc = PGMPhysGCPhys2HCPhys(pPool->CTX_SUFF(pVM), pGstPT->a[j].u & X86_PTE_PAE_PG_MASK, &HCPhys);
915 if ( rc != VINF_SUCCESS
916 || PGMSHWPTEPAE_GET_HCPHYS(pShwPT->a[j]) != HCPhys)
917 {
918 if (fFirstMsg)
919 {
920 DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
921 fFirstMsg = false;
922 }
923 DBGCCmdHlpPrintf(pCmdHlp, "Mismatch HCPhys: rc=%Rrc idx=%d guest %RX64 shw=%RX64 vs %RHp\n", rc, j, pGstPT->a[j].u, PGMSHWPTEPAE_GET_LOG(pShwPT->a[j]), HCPhys);
924 cErrors++;
925 }
926 else if ( PGMSHWPTEPAE_IS_RW(pShwPT->a[j])
927 && !pGstPT->a[j].n.u1Write)
928 {
929 if (fFirstMsg)
930 {
931 DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
932 fFirstMsg = false;
933 }
934 DBGCCmdHlpPrintf(pCmdHlp, "Mismatch r/w gst/shw: idx=%d guest %RX64 shw=%RX64 vs %RHp\n", j, pGstPT->a[j].u, PGMSHWPTEPAE_GET_LOG(pShwPT->a[j]), HCPhys);
935 cErrors++;
936 }
937 }
938 }
939 PGMPhysReleasePageMappingLock(pVM, &LockPage);
940 }
941
942 /* Make sure this page table can't be written to from any shadow mapping. */
943 RTHCPHYS HCPhysPT = NIL_RTHCPHYS;
944 int rc = PGMPhysGCPhys2HCPhys(pPool->CTX_SUFF(pVM), pPage->GCPhys, &HCPhysPT);
945 AssertMsgRC(rc, ("PGMPhysGCPhys2HCPhys failed with rc=%d for %RGp\n", rc, pPage->GCPhys));
946 if (rc == VINF_SUCCESS)
947 {
948 for (unsigned j = 0; j < pPool->cCurPages; j++)
949 {
950 PPGMPOOLPAGE pTempPage = &pPool->aPages[j];
951
952 if (pTempPage->enmKind == PGMPOOLKIND_PAE_PT_FOR_PAE_PT)
953 {
954 PPGMSHWPTPAE pShwPT2 = (PPGMSHWPTPAE)PGMPOOL_PAGE_2_PTR(pPool->CTX_SUFF(pVM), pTempPage);
955
956 for (unsigned k = 0; k < RT_ELEMENTS(pShwPT->a); k++)
957 {
958 if ( PGMSHWPTEPAE_IS_P_RW(pShwPT2->a[k])
959# ifdef PGMPOOL_WITH_OPTIMIZED_DIRTY_PT
960 && !pPage->fDirty
961# endif
962 && PGMSHWPTEPAE_GET_HCPHYS(pShwPT2->a[k]) == HCPhysPT)
963 {
964 if (fFirstMsg)
965 {
966 DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
967 fFirstMsg = false;
968 }
969 DBGCCmdHlpPrintf(pCmdHlp, "Mismatch: r/w: GCPhys=%RGp idx=%d shw %RX64 %RX64\n", pTempPage->GCPhys, k, PGMSHWPTEPAE_GET_LOG(pShwPT->a[k]), PGMSHWPTEPAE_GET_LOG(pShwPT2->a[k]));
970 cErrors++;
971 }
972 }
973 }
974 }
975 }
976 }
977 }
978 if (cErrors > 0)
979 return DBGCCmdHlpFail(pCmdHlp, pCmd, "Found %#x errors", cErrors);
980 return VINF_SUCCESS;
981}
982#endif /* VBOX_WITH_DEBUGGER */
Note: See TracBrowser for help on using the repository browser.

© 2024 Oracle Support Privacy / Do Not Sell My Info Terms of Use Trademark Policy Automated Access Etiquette