PGMPool.cpp@ 85179

Last change on this file since 85179 was 85179, checked in by vboxsync, 4 years ago
VMM/PGMPool.cpp: fall thru fix for Clang 11. bugref:9790
Property svn:eol-style set to `native` Property svn:keywords set to `Id Revision`
File size: 54.1 KB

Line
1	/* $Id: PGMPool.cpp 85179 2020-07-10 13:19:09Z vboxsync $ */
2	/** @file
3	* PGM Shadow Page Pool.
4	*/
5
6	/*
7	* Copyright (C) 2006-2020 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
117	static FNDBGCCMD pgmR3PoolCmdCheck;
118	#endif
119
120	#ifdef VBOX_WITH_DEBUGGER
121	/** Command descriptors. */
122	static 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	*/
135	int 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	AssertCompile(RT_IS_POWER_OF_TWO(PGMPOOL_CFG_MAX_GROW));
173	if (cMaxPages < PGMPOOL_IDX_LAST)
174	cMaxPages = RT_ALIGN(cMaxPages, PGMPOOL_CFG_MAX_GROW / 2);
175	if (cMaxPages > PGMPOOL_IDX_LAST)
176	cMaxPages = PGMPOOL_IDX_LAST;
177	LogRel(("PGM: PGMPool: cMaxPages=%u (u64MaxPages=%llu)\n", cMaxPages, u64MaxPages));
178
179	/** @todo
180	* We need to be much more careful with our allocation strategy here.
181	* For nested paging we don't need pool user info nor extents at all, but
182	* we can't check for nested paging here (too early during init to get a
183	* confirmation it can be used). The default for large memory configs is a
184	* bit large for shadow paging, so I've restricted the extent maximum to 8k
185	* (8k * 16 = 128k of hyper heap).
186	*
187	* Also when large page support is enabled, we typically don't need so much,
188	* although that depends on the availability of 2 MB chunks on the host.
189	*/
190
191	/** @cfgm{/PGM/Pool/MaxUsers, uint16_t, \#users, MaxUsers, 32K, MaxPages*2}
192	* The max number of shadow page user tracking records. Each shadow page has
193	* zero of other shadow pages (or CR3s) that references it, or uses it if you
194	* like. The structures describing these relationships are allocated from a
195	* fixed sized pool. This configuration variable defines the pool size.
196	*/
197	uint16_t cMaxUsers;
198	rc = CFGMR3QueryU16Def(pCfg, "MaxUsers", &cMaxUsers, cMaxPages * 2);
199	AssertLogRelRCReturn(rc, rc);
200	AssertLogRelMsgReturn(cMaxUsers >= cMaxPages && cMaxPages <= _32K,
201	("cMaxUsers=%u (%#x)\n", cMaxUsers, cMaxUsers), VERR_INVALID_PARAMETER);
202
203	/** @cfgm{/PGM/Pool/MaxPhysExts, uint16_t, \#extents, 16, MaxPages * 2, MIN(MaxPages*2\,8192)}
204	* The max number of extents for tracking aliased guest pages.
205	*/
206	uint16_t cMaxPhysExts;
207	rc = CFGMR3QueryU16Def(pCfg, "MaxPhysExts", &cMaxPhysExts,
208	RT_MIN(cMaxPages * 2, 8192 /* 8Ki max as this eat too much hyper heap */));
209	AssertLogRelRCReturn(rc, rc);
210	AssertLogRelMsgReturn(cMaxPhysExts >= 16 && cMaxPhysExts <= PGMPOOL_IDX_LAST,
211	("cMaxPhysExts=%u (%#x)\n", cMaxPhysExts, cMaxPhysExts), VERR_INVALID_PARAMETER);
212
213	/** @cfgm{/PGM/Pool/ChacheEnabled, bool, true}
214	* Enables or disabling caching of shadow pages. Caching means that we will try
215	* reuse shadow pages instead of recreating them everything SyncCR3, SyncPT or
216	* SyncPage requests one. When reusing a shadow page, we can save time
217	* reconstructing it and it's children.
218	*/
219	bool fCacheEnabled;
220	rc = CFGMR3QueryBoolDef(pCfg, "CacheEnabled", &fCacheEnabled, true);
221	AssertLogRelRCReturn(rc, rc);
222
223	LogRel(("PGM: pgmR3PoolInit: cMaxPages=%#RX16 cMaxUsers=%#RX16 cMaxPhysExts=%#RX16 fCacheEnable=%RTbool\n",
224	cMaxPages, cMaxUsers, cMaxPhysExts, fCacheEnabled));
225
226	/*
227	* Allocate the data structures.
228	*/
229	uint32_t cb = RT_UOFFSETOF_DYN(PGMPOOL, aPages[cMaxPages]);
230	cb += cMaxUsers * sizeof(PGMPOOLUSER);
231	cb += cMaxPhysExts * sizeof(PGMPOOLPHYSEXT);
232	PPGMPOOL pPool;
233	rc = MMR3HyperAllocOnceNoRel(pVM, cb, 0, MM_TAG_PGM_POOL, (void **)&pPool);
234	if (RT_FAILURE(rc))
235	return rc;
236	pVM->pgm.s.pPoolR3 = pPool;
237	pVM->pgm.s.pPoolR0 = MMHyperR3ToR0(pVM, pPool);
238
239	/*
240	* Initialize it.
241	*/
242	pPool->pVMR3 = pVM;
243	pPool->pVMR0 = pVM->pVMR0ForCall;
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	for (unsigned i = 0; i < cMaxUsers; i++)
252	{
253	paUsers[i].iNext = i + 1;
254	paUsers[i].iUser = NIL_PGMPOOL_IDX;
255	paUsers[i].iUserTable = 0xfffffffe;
256	}
257	paUsers[cMaxUsers - 1].iNext = NIL_PGMPOOL_USER_INDEX;
258	pPool->iPhysExtFreeHead = 0;
259	pPool->cMaxPhysExts = cMaxPhysExts;
260	PPGMPOOLPHYSEXT paPhysExts = (PPGMPOOLPHYSEXT)&paUsers[cMaxUsers];
261	pPool->paPhysExtsR3 = paPhysExts;
262	pPool->paPhysExtsR0 = MMHyperR3ToR0(pVM, paPhysExts);
263	for (unsigned i = 0; i < cMaxPhysExts; i++)
264	{
265	paPhysExts[i].iNext = i + 1;
266	paPhysExts[i].aidx[0] = NIL_PGMPOOL_IDX;
267	paPhysExts[i].apte[0] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
268	paPhysExts[i].aidx[1] = NIL_PGMPOOL_IDX;
269	paPhysExts[i].apte[1] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
270	paPhysExts[i].aidx[2] = NIL_PGMPOOL_IDX;
271	paPhysExts[i].apte[2] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
272	}
273	paPhysExts[cMaxPhysExts - 1].iNext = NIL_PGMPOOL_PHYSEXT_INDEX;
274	for (unsigned i = 0; i < RT_ELEMENTS(pPool->aiHash); i++)
275	pPool->aiHash[i] = NIL_PGMPOOL_IDX;
276	pPool->iAgeHead = NIL_PGMPOOL_IDX;
277	pPool->iAgeTail = NIL_PGMPOOL_IDX;
278	pPool->fCacheEnabled = fCacheEnabled;
279
280	pPool->hAccessHandlerType = NIL_PGMPHYSHANDLERTYPE;
281	rc = PGMR3HandlerPhysicalTypeRegister(pVM, PGMPHYSHANDLERKIND_WRITE,
282	pgmPoolAccessHandler,
283	NULL, "pgmPoolAccessHandler", "pgmRZPoolAccessPfHandler",
284	NULL, "pgmPoolAccessHandler", "pgmRZPoolAccessPfHandler",
285	"Guest Paging Access Handler",
286	&pPool->hAccessHandlerType);
287	AssertLogRelRCReturn(rc, rc);
288
289	pPool->HCPhysTree = 0;
290
291	/*
292	* The NIL entry.
293	*/
294	Assert(NIL_PGMPOOL_IDX == 0);
295	pPool->aPages[NIL_PGMPOOL_IDX].enmKind = PGMPOOLKIND_INVALID;
296	pPool->aPages[NIL_PGMPOOL_IDX].idx = NIL_PGMPOOL_IDX;
297	pPool->aPages[NIL_PGMPOOL_IDX].Core.Key = NIL_RTHCPHYS;
298	pPool->aPages[NIL_PGMPOOL_IDX].GCPhys = NIL_RTGCPHYS;
299	pPool->aPages[NIL_PGMPOOL_IDX].iNext = NIL_PGMPOOL_IDX;
300	/* pPool->aPages[NIL_PGMPOOL_IDX].cLocked = INT32_MAX; - test this out... */
301	pPool->aPages[NIL_PGMPOOL_IDX].pvPageR3 = 0;
302	pPool->aPages[NIL_PGMPOOL_IDX].iUserHead = NIL_PGMPOOL_USER_INDEX;
303	pPool->aPages[NIL_PGMPOOL_IDX].iModifiedNext = NIL_PGMPOOL_IDX;
304	pPool->aPages[NIL_PGMPOOL_IDX].iModifiedPrev = NIL_PGMPOOL_IDX;
305	pPool->aPages[NIL_PGMPOOL_IDX].iMonitoredNext = NIL_PGMPOOL_IDX;
306	pPool->aPages[NIL_PGMPOOL_IDX].iMonitoredPrev = NIL_PGMPOOL_IDX;
307	pPool->aPages[NIL_PGMPOOL_IDX].iAgeNext = NIL_PGMPOOL_IDX;
308	pPool->aPages[NIL_PGMPOOL_IDX].iAgePrev = NIL_PGMPOOL_IDX;
309
310	Assert(pPool->aPages[NIL_PGMPOOL_IDX].idx == NIL_PGMPOOL_IDX);
311	Assert(pPool->aPages[NIL_PGMPOOL_IDX].GCPhys == NIL_RTGCPHYS);
312	Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fSeenNonGlobal);
313	Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fMonitored);
314	Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fCached);
315	Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fZeroed);
316	Assert(!pPool->aPages[NIL_PGMPOOL_IDX].fReusedFlushPending);
317
318	/*
319	* Register statistics.
320	*/
321	STAM_REL_REG(pVM, &pPool->StatGrow, STAMTYPE_PROFILE, "/PGM/Pool/Grow", STAMUNIT_TICKS, "Profiling PGMR0PoolGrow");
322	#ifdef VBOX_WITH_STATISTICS
323	STAM_REG(pVM, &pPool->cCurPages, STAMTYPE_U16, "/PGM/Pool/cCurPages", STAMUNIT_PAGES, "Current pool size.");
324	STAM_REG(pVM, &pPool->cMaxPages, STAMTYPE_U16, "/PGM/Pool/cMaxPages", STAMUNIT_PAGES, "Max pool size.");
325	STAM_REG(pVM, &pPool->cUsedPages, STAMTYPE_U16, "/PGM/Pool/cUsedPages", STAMUNIT_PAGES, "The number of pages currently in use.");
326	STAM_REG(pVM, &pPool->cUsedPagesHigh, STAMTYPE_U16_RESET, "/PGM/Pool/cUsedPagesHigh", STAMUNIT_PAGES, "The high watermark for cUsedPages.");
327	STAM_REG(pVM, &pPool->StatAlloc, STAMTYPE_PROFILE_ADV, "/PGM/Pool/Alloc", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolAlloc.");
328	STAM_REG(pVM, &pPool->StatClearAll, STAMTYPE_PROFILE, "/PGM/Pool/ClearAll", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmR3PoolClearAll.");
329	STAM_REG(pVM, &pPool->StatR3Reset, STAMTYPE_PROFILE, "/PGM/Pool/R3Reset", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmR3PoolReset.");
330	STAM_REG(pVM, &pPool->StatFlushPage, STAMTYPE_PROFILE, "/PGM/Pool/FlushPage", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolFlushPage.");
331	STAM_REG(pVM, &pPool->StatFree, STAMTYPE_PROFILE, "/PGM/Pool/Free", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolFree.");
332	STAM_REG(pVM, &pPool->StatForceFlushPage, STAMTYPE_COUNTER, "/PGM/Pool/FlushForce", STAMUNIT_OCCURENCES, "Counting explicit flushes by PGMPoolFlushPage().");
333	STAM_REG(pVM, &pPool->StatForceFlushDirtyPage, STAMTYPE_COUNTER, "/PGM/Pool/FlushForceDirty", STAMUNIT_OCCURENCES, "Counting explicit flushes of dirty pages by PGMPoolFlushPage().");
334	STAM_REG(pVM, &pPool->StatForceFlushReused, STAMTYPE_COUNTER, "/PGM/Pool/FlushReused", STAMUNIT_OCCURENCES, "Counting flushes for reused pages.");
335	STAM_REG(pVM, &pPool->StatZeroPage, STAMTYPE_PROFILE, "/PGM/Pool/ZeroPage", STAMUNIT_TICKS_PER_CALL, "Profiling time spent zeroing pages. Overlaps with Alloc.");
336	STAM_REG(pVM, &pPool->cMaxUsers, STAMTYPE_U16, "/PGM/Pool/Track/cMaxUsers", STAMUNIT_COUNT, "Max user tracking records.");
337	STAM_REG(pVM, &pPool->cPresent, STAMTYPE_U32, "/PGM/Pool/Track/cPresent", STAMUNIT_COUNT, "Number of present page table entries.");
338	STAM_REG(pVM, &pPool->StatTrackDeref, STAMTYPE_PROFILE, "/PGM/Pool/Track/Deref", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackDeref.");
339	STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPT, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPT", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPT.");
340	STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPTs, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPTs", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPTs.");
341	STAM_REG(pVM, &pPool->StatTrackFlushGCPhysPTsSlow, STAMTYPE_PROFILE, "/PGM/Pool/Track/FlushGCPhysPTsSlow", STAMUNIT_TICKS_PER_CALL, "Profiling of pgmPoolTrackFlushGCPhysPTsSlow.");
342	STAM_REG(pVM, &pPool->StatTrackFlushEntry, STAMTYPE_COUNTER, "/PGM/Pool/Track/Entry/Flush", STAMUNIT_COUNT, "Nr of flushed entries.");
343	STAM_REG(pVM, &pPool->StatTrackFlushEntryKeep, STAMTYPE_COUNTER, "/PGM/Pool/Track/Entry/Update", STAMUNIT_COUNT, "Nr of updated entries.");
344	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.");
345	STAM_REG(pVM, &pPool->StatTrackDerefGCPhys, STAMTYPE_PROFILE, "/PGM/Pool/Track/DrefGCPhys", STAMUNIT_TICKS_PER_CALL, "Profiling deref activity related tracking GC physical pages.");
346	STAM_REG(pVM, &pPool->StatTrackLinearRamSearches, STAMTYPE_COUNTER, "/PGM/Pool/Track/LinearRamSearches", STAMUNIT_OCCURENCES, "The number of times we had to do linear ram searches.");
347	STAM_REG(pVM, &pPool->StamTrackPhysExtAllocFailures,STAMTYPE_COUNTER, "/PGM/Pool/Track/PhysExtAllocFailures", STAMUNIT_OCCURENCES, "The number of failing pgmPoolTrackPhysExtAlloc calls.");
348
349	STAM_REG(pVM, &pPool->StatMonitorPfRZ, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/#PF", STAMUNIT_TICKS_PER_CALL, "Profiling the RC/R0 #PF access handler.");
350	STAM_REG(pVM, &pPool->StatMonitorPfRZEmulateInstr, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/EmulateInstr", STAMUNIT_OCCURENCES, "Times we've failed interpreting the instruction.");
351	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.");
352	STAM_REG(pVM, &pPool->StatMonitorPfRZFlushReinit, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/FlushReinit", STAMUNIT_OCCURENCES, "Times we've detected a page table reinit.");
353	STAM_REG(pVM, &pPool->StatMonitorPfRZFlushModOverflow,STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/FlushOverflow", STAMUNIT_OCCURENCES, "Counting flushes for pages that are modified too often.");
354	STAM_REG(pVM, &pPool->StatMonitorPfRZFork, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/Fork", STAMUNIT_OCCURENCES, "Times we've detected fork().");
355	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).");
356	STAM_REG(pVM, &pPool->StatMonitorPfRZIntrFailPatch1, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/#PF/IntrFailPatch1", STAMUNIT_OCCURENCES, "Times we've failed interpreting a patch code instruction.");
357	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.");
358	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.");
359	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.");
360
361	STAM_REG(pVM, &pPool->StatMonitorRZ, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM", STAMUNIT_TICKS_PER_CALL, "Profiling the regular access handler.");
362	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.");
363	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size01", STAMUNIT_OCCURENCES, "Number of 1 byte accesses.");
364	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size02", STAMUNIT_OCCURENCES, "Number of 2 byte accesses.");
365	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size03", STAMUNIT_OCCURENCES, "Number of 3 byte accesses.");
366	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size04", STAMUNIT_OCCURENCES, "Number of 4 byte accesses.");
367	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size05", STAMUNIT_OCCURENCES, "Number of 5 byte accesses.");
368	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size06", STAMUNIT_OCCURENCES, "Number of 6 byte accesses.");
369	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size07", STAMUNIT_OCCURENCES, "Number of 7 byte accesses.");
370	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[7], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size08", STAMUNIT_OCCURENCES, "Number of 8 byte accesses.");
371	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[8], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size09", STAMUNIT_OCCURENCES, "Number of 9 byte accesses.");
372	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[9], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0a", STAMUNIT_OCCURENCES, "Number of 10 byte accesses.");
373	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[10], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0b", STAMUNIT_OCCURENCES, "Number of 11 byte accesses.");
374	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[11], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0c", STAMUNIT_OCCURENCES, "Number of 12 byte accesses.");
375	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[12], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0d", STAMUNIT_OCCURENCES, "Number of 13 byte accesses.");
376	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[13], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0e", STAMUNIT_OCCURENCES, "Number of 14 byte accesses.");
377	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[14], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size0f", STAMUNIT_OCCURENCES, "Number of 15 byte accesses.");
378	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[15], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size10", STAMUNIT_OCCURENCES, "Number of 16 byte accesses.");
379	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[16], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size11-2f", STAMUNIT_OCCURENCES, "Number of 17-31 byte accesses.");
380	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[17], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size20-3f", STAMUNIT_OCCURENCES, "Number of 32-63 byte accesses.");
381	STAM_REG(pVM, &pPool->aStatMonitorRZSizes[18], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Size40+", STAMUNIT_OCCURENCES, "Number of 64+ byte accesses.");
382	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned1", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 1.");
383	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned2", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 2.");
384	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned3", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 3.");
385	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned4", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 4.");
386	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned5", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 5.");
387	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned6", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 6.");
388	STAM_REG(pVM, &pPool->aStatMonitorRZMisaligned[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/RZ/IEM/Misaligned7", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 7.");
389
390	STAM_REG(pVM, &pPool->StatMonitorRZFaultPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PT", STAMUNIT_OCCURENCES, "Nr of handled PT faults.");
391	STAM_REG(pVM, &pPool->StatMonitorRZFaultPD, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PD", STAMUNIT_OCCURENCES, "Nr of handled PD faults.");
392	STAM_REG(pVM, &pPool->StatMonitorRZFaultPDPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PDPT", STAMUNIT_OCCURENCES, "Nr of handled PDPT faults.");
393	STAM_REG(pVM, &pPool->StatMonitorRZFaultPML4, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/RZ/Fault/PML4", STAMUNIT_OCCURENCES, "Nr of handled PML4 faults.");
394
395	STAM_REG(pVM, &pPool->StatMonitorR3, STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3", STAMUNIT_TICKS_PER_CALL, "Profiling the R3 access handler.");
396	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.");
397	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size01", STAMUNIT_OCCURENCES, "Number of 1 byte accesses (R3).");
398	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size02", STAMUNIT_OCCURENCES, "Number of 2 byte accesses (R3).");
399	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size03", STAMUNIT_OCCURENCES, "Number of 3 byte accesses (R3).");
400	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size04", STAMUNIT_OCCURENCES, "Number of 4 byte accesses (R3).");
401	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size05", STAMUNIT_OCCURENCES, "Number of 5 byte accesses (R3).");
402	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size06", STAMUNIT_OCCURENCES, "Number of 6 byte accesses (R3).");
403	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size07", STAMUNIT_OCCURENCES, "Number of 7 byte accesses (R3).");
404	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[7], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size08", STAMUNIT_OCCURENCES, "Number of 8 byte accesses (R3).");
405	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[8], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size09", STAMUNIT_OCCURENCES, "Number of 9 byte accesses (R3).");
406	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[9], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0a", STAMUNIT_OCCURENCES, "Number of 10 byte accesses (R3).");
407	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[10], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0b", STAMUNIT_OCCURENCES, "Number of 11 byte accesses (R3).");
408	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[11], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0c", STAMUNIT_OCCURENCES, "Number of 12 byte accesses (R3).");
409	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[12], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0d", STAMUNIT_OCCURENCES, "Number of 13 byte accesses (R3).");
410	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[13], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0e", STAMUNIT_OCCURENCES, "Number of 14 byte accesses (R3).");
411	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[14], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size0f", STAMUNIT_OCCURENCES, "Number of 15 byte accesses (R3).");
412	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[15], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size10", STAMUNIT_OCCURENCES, "Number of 16 byte accesses (R3).");
413	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[16], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size11-2f", STAMUNIT_OCCURENCES, "Number of 17-31 byte accesses.");
414	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[17], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size20-3f", STAMUNIT_OCCURENCES, "Number of 32-63 byte accesses.");
415	STAM_REG(pVM, &pPool->aStatMonitorR3Sizes[18], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Size40+", STAMUNIT_OCCURENCES, "Number of 64+ byte accesses.");
416	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[0], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned1", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 1 in R3.");
417	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[1], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned2", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 2 in R3.");
418	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[2], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned3", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 3 in R3.");
419	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[3], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned4", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 4 in R3.");
420	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[4], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned5", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 5 in R3.");
421	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[5], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned6", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 6 in R3.");
422	STAM_REG(pVM, &pPool->aStatMonitorR3Misaligned[6], STAMTYPE_PROFILE, "/PGM/Pool/Monitor/R3/Misaligned7", STAMUNIT_OCCURENCES, "Number of misaligned access with offset 7 in R3.");
423
424	STAM_REG(pVM, &pPool->StatMonitorR3FaultPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PT", STAMUNIT_OCCURENCES, "Nr of handled PT faults.");
425	STAM_REG(pVM, &pPool->StatMonitorR3FaultPD, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PD", STAMUNIT_OCCURENCES, "Nr of handled PD faults.");
426	STAM_REG(pVM, &pPool->StatMonitorR3FaultPDPT, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PDPT", STAMUNIT_OCCURENCES, "Nr of handled PDPT faults.");
427	STAM_REG(pVM, &pPool->StatMonitorR3FaultPML4, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/R3/Fault/PML4", STAMUNIT_OCCURENCES, "Nr of handled PML4 faults.");
428
429	STAM_REG(pVM, &pPool->cModifiedPages, STAMTYPE_U16, "/PGM/Pool/Monitor/cModifiedPages", STAMUNIT_PAGES, "The current cModifiedPages value.");
430	STAM_REG(pVM, &pPool->cModifiedPagesHigh, STAMTYPE_U16_RESET, "/PGM/Pool/Monitor/cModifiedPagesHigh", STAMUNIT_PAGES, "The high watermark for cModifiedPages.");
431	STAM_REG(pVM, &pPool->StatResetDirtyPages, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/Resets", STAMUNIT_OCCURENCES, "Times we've called pgmPoolResetDirtyPages (and there were dirty page).");
432	STAM_REG(pVM, &pPool->StatDirtyPage, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/Pages", STAMUNIT_OCCURENCES, "Times we've called pgmPoolAddDirtyPage.");
433	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.");
434	STAM_REG(pVM, &pPool->StatDirtyPageOverFlowFlush, STAMTYPE_COUNTER, "/PGM/Pool/Monitor/Dirty/FlushOverflow",STAMUNIT_OCCURENCES, "Times we've had to flush because of overflow.");
435	STAM_REG(pVM, &pPool->StatCacheHits, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Hits", STAMUNIT_OCCURENCES, "The number of pgmPoolAlloc calls satisfied by the cache.");
436	STAM_REG(pVM, &pPool->StatCacheMisses, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Misses", STAMUNIT_OCCURENCES, "The number of pgmPoolAlloc calls not statisfied by the cache.");
437	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!)");
438	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.");
439	STAM_REG(pVM, &pPool->StatCacheCacheable, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Cacheable", STAMUNIT_OCCURENCES, "The number of cacheable allocations.");
440	STAM_REG(pVM, &pPool->StatCacheUncacheable, STAMTYPE_COUNTER, "/PGM/Pool/Cache/Uncacheable", STAMUNIT_OCCURENCES, "The number of uncacheable allocations.");
441	#endif /* VBOX_WITH_STATISTICS */
442
443	#ifdef VBOX_WITH_DEBUGGER
444	/*
445	* Debugger commands.
446	*/
447	static bool s_fRegisteredCmds = false;
448	if (!s_fRegisteredCmds)
449	{
450	rc = DBGCRegisterCommands(&g_aCmds[0], RT_ELEMENTS(g_aCmds));
451	if (RT_SUCCESS(rc))
452	s_fRegisteredCmds = true;
453	}
454	#endif
455
456	return VINF_SUCCESS;
457	}
458
459
460	/**
461	* Relocate the page pool data.
462	*
463	* @param pVM The cross context VM structure.
464	*/
465	void pgmR3PoolRelocate(PVM pVM)
466	{
467	RT_NOREF(pVM);
468	}
469
470
471	/**
472	* Grows the shadow page pool.
473	*
474	* I.e. adds more pages to it, assuming that hasn't reached cMaxPages yet.
475	*
476	* @returns VBox status code.
477	* @param pVM The cross context VM structure.
478	* @param pVCpu The cross context virtual CPU structure of the calling EMT.
479	*/
480	VMMR3_INT_DECL(int) PGMR3PoolGrow(PVM pVM, PVMCPU pVCpu)
481	{
482	/* This used to do a lot of stuff, but it has moved to ring-0 (PGMR0PoolGrow). */
483	AssertReturn(pVM->pgm.s.pPoolR3->cCurPages < pVM->pgm.s.pPoolR3->cMaxPages, VERR_PGM_POOL_MAXED_OUT_ALREADY);
484	int rc = VMMR3CallR0Emt(pVM, pVCpu, VMMR0_DO_PGM_POOL_GROW, 0, NULL);
485	if (rc == VINF_SUCCESS)
486	return rc;
487	LogRel(("PGMR3PoolGrow: rc=%Rrc cCurPages=%#x cMaxPages=%#x\n",
488	rc, pVM->pgm.s.pPoolR3->cCurPages, pVM->pgm.s.pPoolR3->cMaxPages));
489	if (pVM->pgm.s.pPoolR3->cCurPages > 128 && RT_FAILURE_NP(rc))
490	return -rc;
491	return rc;
492	}
493
494
495	/**
496	* Rendezvous callback used by pgmR3PoolClearAll that clears all shadow pages
497	* and all modification counters.
498	*
499	* This is only called on one of the EMTs while the other ones are waiting for
500	* it to complete this function.
501	*
502	* @returns VINF_SUCCESS (VBox strict status code).
503	* @param pVM The cross context VM structure.
504	* @param pVCpu The cross context virtual CPU structure of the calling EMT. Unused.
505	* @param fpvFlushRemTlb When not NULL, we'll flush the REM TLB as well.
506	* (This is the pvUser, so it has to be void *.)
507	*
508	*/
509	DECLCALLBACK(VBOXSTRICTRC) pgmR3PoolClearAllRendezvous(PVM pVM, PVMCPU pVCpu, void *fpvFlushRemTlb)
510	{
511	PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
512	STAM_PROFILE_START(&pPool->StatClearAll, c);
513	NOREF(pVCpu);
514
515	pgmLock(pVM);
516	Log(("pgmR3PoolClearAllRendezvous: cUsedPages=%d fpvFlushRemTlb=%RTbool\n", pPool->cUsedPages, !!fpvFlushRemTlb));
517
518	/*
519	* Iterate all the pages until we've encountered all that are in use.
520	* This is a simple but not quite optimal solution.
521	*/
522	unsigned cModifiedPages = 0; NOREF(cModifiedPages);
523	unsigned cLeft = pPool->cUsedPages;
524	uint32_t iPage = pPool->cCurPages;
525	while (--iPage >= PGMPOOL_IDX_FIRST)
526	{
527	PPGMPOOLPAGE pPage = &pPool->aPages[iPage];
528	if (pPage->GCPhys != NIL_RTGCPHYS)
529	{
530	switch (pPage->enmKind)
531	{
532	/*
533	* We only care about shadow page tables that reference physical memory
534	*/
535	#ifdef PGM_WITH_LARGE_PAGES
536	case PGMPOOLKIND_EPT_PD_FOR_PHYS: /* Large pages reference 2 MB of physical memory, so we must clear them. */
537	if (pPage->cPresent)
538	{
539	PX86PDPAE pShwPD = (PX86PDPAE)PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
540	for (unsigned i = 0; i < RT_ELEMENTS(pShwPD->a); i++)
541	{
542	if ( pShwPD->a[i].n.u1Present
543	&& pShwPD->a[i].b.u1Size)
544	{
545	Assert(!(pShwPD->a[i].u & PGM_PDFLAGS_MAPPING));
546	pShwPD->a[i].u = 0;
547	Assert(pPage->cPresent);
548	pPage->cPresent--;
549	}
550	}
551	if (pPage->cPresent == 0)
552	pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
553	}
554	goto default_case;
555
556	case PGMPOOLKIND_PAE_PD_PHYS: /* Large pages reference 2 MB of physical memory, so we must clear them. */
557	if (pPage->cPresent)
558	{
559	PEPTPD pShwPD = (PEPTPD)PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
560	for (unsigned i = 0; i < RT_ELEMENTS(pShwPD->a); i++)
561	{
562	Assert((pShwPD->a[i].u & UINT64_C(0xfff0000000000f80)) == 0);
563	if ( pShwPD->a[i].n.u1Present
564	&& pShwPD->a[i].b.u1Size)
565	{
566	Assert(!(pShwPD->a[i].u & PGM_PDFLAGS_MAPPING));
567	pShwPD->a[i].u = 0;
568	Assert(pPage->cPresent);
569	pPage->cPresent--;
570	}
571	}
572	if (pPage->cPresent == 0)
573	pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
574	}
575	goto default_case;
576	#endif /* PGM_WITH_LARGE_PAGES */
577
578	case PGMPOOLKIND_32BIT_PT_FOR_32BIT_PT:
579	case PGMPOOLKIND_32BIT_PT_FOR_32BIT_4MB:
580	case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
581	case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
582	case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
583	case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
584	case PGMPOOLKIND_32BIT_PT_FOR_PHYS:
585	case PGMPOOLKIND_PAE_PT_FOR_PHYS:
586	case PGMPOOLKIND_EPT_PT_FOR_PHYS:
587	{
588	if (pPage->cPresent)
589	{
590	void *pvShw = PGMPOOL_PAGE_2_PTR_V2(pPool->CTX_SUFF(pVM), pVCpu, pPage);
591	STAM_PROFILE_START(&pPool->StatZeroPage, z);
592	#if 0
593	/* Useful check for leaking references; very expensive though. */
594	switch (pPage->enmKind)
595	{
596	case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
597	case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
598	case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
599	case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
600	case PGMPOOLKIND_PAE_PT_FOR_PHYS:
601	{
602	bool fFoundFirst = false;
603	PPGMSHWPTPAE pPT = (PPGMSHWPTPAE)pvShw;
604	for (unsigned ptIndex = 0; ptIndex < RT_ELEMENTS(pPT->a); ptIndex++)
605	{
606	if (pPT->a[ptIndex].u)
607	{
608	if (!fFoundFirst)
609	{
610	AssertFatalMsg(pPage->iFirstPresent <= ptIndex, ("ptIndex = %d first present = %d\n", ptIndex, pPage->iFirstPresent));
611	if (pPage->iFirstPresent != ptIndex)
612	Log(("ptIndex = %d first present = %d\n", ptIndex, pPage->iFirstPresent));
613	fFoundFirst = true;
614	}
615	if (PGMSHWPTEPAE_IS_P(pPT->a[ptIndex]))
616	{
617	pgmPoolTracDerefGCPhysHint(pPool, pPage, PGMSHWPTEPAE_GET_HCPHYS(pPT->a[ptIndex]), NIL_RTGCPHYS);
618	if (pPage->iFirstPresent == ptIndex)
619	pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
620	}
621	}
622	}
623	AssertFatalMsg(pPage->cPresent == 0, ("cPresent = %d pPage = %RGv\n", pPage->cPresent, pPage->GCPhys));
624	break;
625	}
626	default:
627	break;
628	}
629	#endif
630	ASMMemZeroPage(pvShw);
631	STAM_PROFILE_STOP(&pPool->StatZeroPage, z);
632	pPage->cPresent = 0;
633	pPage->iFirstPresent = NIL_PGMPOOL_PRESENT_INDEX;
634	}
635	}
636	RT_FALL_THRU();
637	default:
638	#ifdef PGM_WITH_LARGE_PAGES
639	default_case:
640	#endif
641	Assert(!pPage->cModifications \|\| ++cModifiedPages);
642	Assert(pPage->iModifiedNext == NIL_PGMPOOL_IDX \|\| pPage->cModifications);
643	Assert(pPage->iModifiedPrev == NIL_PGMPOOL_IDX \|\| pPage->cModifications);
644	pPage->iModifiedNext = NIL_PGMPOOL_IDX;
645	pPage->iModifiedPrev = NIL_PGMPOOL_IDX;
646	pPage->cModifications = 0;
647	break;
648
649	}
650	if (!--cLeft)
651	break;
652	}
653	}
654
655	#ifndef DEBUG_michael
656	AssertMsg(cModifiedPages == pPool->cModifiedPages, ("%d != %d\n", cModifiedPages, pPool->cModifiedPages));
657	#endif
658	pPool->iModifiedHead = NIL_PGMPOOL_IDX;
659	pPool->cModifiedPages = 0;
660
661	/*
662	* Clear all the GCPhys links and rebuild the phys ext free list.
663	*/
664	for (PPGMRAMRANGE pRam = pPool->CTX_SUFF(pVM)->pgm.s.CTX_SUFF(pRamRangesX);
665	pRam;
666	pRam = pRam->CTX_SUFF(pNext))
667	{
668	iPage = pRam->cb >> PAGE_SHIFT;
669	while (iPage-- > 0)
670	PGM_PAGE_SET_TRACKING(pVM, &pRam->aPages[iPage], 0);
671	}
672
673	pPool->iPhysExtFreeHead = 0;
674	PPGMPOOLPHYSEXT paPhysExts = pPool->CTX_SUFF(paPhysExts);
675	const unsigned cMaxPhysExts = pPool->cMaxPhysExts;
676	for (unsigned i = 0; i < cMaxPhysExts; i++)
677	{
678	paPhysExts[i].iNext = i + 1;
679	paPhysExts[i].aidx[0] = NIL_PGMPOOL_IDX;
680	paPhysExts[i].apte[0] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
681	paPhysExts[i].aidx[1] = NIL_PGMPOOL_IDX;
682	paPhysExts[i].apte[1] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
683	paPhysExts[i].aidx[2] = NIL_PGMPOOL_IDX;
684	paPhysExts[i].apte[2] = NIL_PGMPOOL_PHYSEXT_IDX_PTE;
685	}
686	paPhysExts[cMaxPhysExts - 1].iNext = NIL_PGMPOOL_PHYSEXT_INDEX;
687
688
689	#ifdef PGMPOOL_WITH_OPTIMIZED_DIRTY_PT
690	/* Reset all dirty pages to reactivate the page monitoring. */
691	/* Note: we must do this after clearing all page references and shadow page tables as there might be stale references to
692	* recently removed MMIO ranges around that might otherwise end up asserting in pgmPoolTracDerefGCPhysHint
693	*/
694	for (unsigned i = 0; i < RT_ELEMENTS(pPool->aDirtyPages); i++)
695	{
696	unsigned idxPage = pPool->aidxDirtyPages[i];
697	if (idxPage == NIL_PGMPOOL_IDX)
698	continue;
699
700	PPGMPOOLPAGE pPage = &pPool->aPages[idxPage];
701	Assert(pPage->idx == idxPage);
702	Assert(pPage->iMonitoredNext == NIL_PGMPOOL_IDX && pPage->iMonitoredPrev == NIL_PGMPOOL_IDX);
703
704	AssertMsg(pPage->fDirty, ("Page %RGp (slot=%d) not marked dirty!", pPage->GCPhys, i));
705
706	Log(("Reactivate dirty page %RGp\n", pPage->GCPhys));
707
708	/* First write protect the page again to catch all write accesses. (before checking for changes -> SMP) */
709	int rc = PGMHandlerPhysicalReset(pVM, pPage->GCPhys & PAGE_BASE_GC_MASK);
710	AssertRCSuccess(rc);
711	pPage->fDirty = false;
712
713	pPool->aidxDirtyPages[i] = NIL_PGMPOOL_IDX;
714	}
715
716	/* Clear all dirty pages. */
717	pPool->idxFreeDirtyPage = 0;
718	pPool->cDirtyPages = 0;
719	#endif
720
721	/* Clear the PGM_SYNC_CLEAR_PGM_POOL flag on all VCPUs to prevent redundant flushes. */
722	for (VMCPUID idCpu = 0; idCpu < pVM->cCpus; idCpu++)
723	pVM->apCpusR3[idCpu]->pgm.s.fSyncFlags &= ~PGM_SYNC_CLEAR_PGM_POOL;
724
725	/* Flush job finished. */
726	VM_FF_CLEAR(pVM, VM_FF_PGM_POOL_FLUSH_PENDING);
727	pPool->cPresent = 0;
728	pgmUnlock(pVM);
729
730	PGM_INVL_ALL_VCPU_TLBS(pVM);
731
732	if (fpvFlushRemTlb)
733	for (VMCPUID idCpu = 0; idCpu < pVM->cCpus; idCpu++)
734	CPUMSetChangedFlags(pVM->apCpusR3[idCpu], CPUM_CHANGED_GLOBAL_TLB_FLUSH);
735
736	STAM_PROFILE_STOP(&pPool->StatClearAll, c);
737	return VINF_SUCCESS;
738	}
739
740
741	/**
742	* Clears the shadow page pool.
743	*
744	* @param pVM The cross context VM structure.
745	* @param fFlushRemTlb When set, the REM TLB is scheduled for flushing as
746	* well.
747	*/
748	void pgmR3PoolClearAll(PVM pVM, bool fFlushRemTlb)
749	{
750	int rc = VMMR3EmtRendezvous(pVM, VMMEMTRENDEZVOUS_FLAGS_TYPE_ONCE, pgmR3PoolClearAllRendezvous, &fFlushRemTlb);
751	AssertRC(rc);
752	}
753
754
755	/**
756	* Protect all pgm pool page table entries to monitor writes
757	*
758	* @param pVM The cross context VM structure.
759	*
760	* @remarks ASSUMES the caller will flush all TLBs!!
761	*/
762	void pgmR3PoolWriteProtectPages(PVM pVM)
763	{
764	PGM_LOCK_ASSERT_OWNER(pVM);
765	PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
766	unsigned cLeft = pPool->cUsedPages;
767	unsigned iPage = pPool->cCurPages;
768	while (--iPage >= PGMPOOL_IDX_FIRST)
769	{
770	PPGMPOOLPAGE pPage = &pPool->aPages[iPage];
771	if ( pPage->GCPhys != NIL_RTGCPHYS
772	&& pPage->cPresent)
773	{
774	union
775	{
776	void *pv;
777	PX86PT pPT;
778	PPGMSHWPTPAE pPTPae;
779	PEPTPT pPTEpt;
780	} uShw;
781	uShw.pv = PGMPOOL_PAGE_2_PTR(pVM, pPage);
782
783	switch (pPage->enmKind)
784	{
785	/*
786	* We only care about shadow page tables.
787	*/
788	case PGMPOOLKIND_32BIT_PT_FOR_32BIT_PT:
789	case PGMPOOLKIND_32BIT_PT_FOR_32BIT_4MB:
790	case PGMPOOLKIND_32BIT_PT_FOR_PHYS:
791	for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPT->a); iShw++)
792	{
793	if (uShw.pPT->a[iShw].n.u1Present)
794	uShw.pPT->a[iShw].n.u1Write = 0;
795	}
796	break;
797
798	case PGMPOOLKIND_PAE_PT_FOR_32BIT_PT:
799	case PGMPOOLKIND_PAE_PT_FOR_32BIT_4MB:
800	case PGMPOOLKIND_PAE_PT_FOR_PAE_PT:
801	case PGMPOOLKIND_PAE_PT_FOR_PAE_2MB:
802	case PGMPOOLKIND_PAE_PT_FOR_PHYS:
803	for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPTPae->a); iShw++)
804	{
805	if (PGMSHWPTEPAE_IS_P(uShw.pPTPae->a[iShw]))
806	PGMSHWPTEPAE_SET_RO(uShw.pPTPae->a[iShw]);
807	}
808	break;
809
810	case PGMPOOLKIND_EPT_PT_FOR_PHYS:
811	for (unsigned iShw = 0; iShw < RT_ELEMENTS(uShw.pPTEpt->a); iShw++)
812	{
813	if (uShw.pPTEpt->a[iShw].n.u1Present)
814	uShw.pPTEpt->a[iShw].n.u1Write = 0;
815	}
816	break;
817
818	default:
819	break;
820	}
821	if (!--cLeft)
822	break;
823	}
824	}
825	}
826
827	#ifdef VBOX_WITH_DEBUGGER
828	/**
829	* @callback_method_impl{FNDBGCCMD, The '.pgmpoolcheck' command.}
830	*/
831	static DECLCALLBACK(int) pgmR3PoolCmdCheck(PCDBGCCMD pCmd, PDBGCCMDHLP pCmdHlp, PUVM pUVM, PCDBGCVAR paArgs, unsigned cArgs)
832	{
833	DBGC_CMDHLP_REQ_UVM_RET(pCmdHlp, pCmd, pUVM);
834	PVM pVM = pUVM->pVM;
835	VM_ASSERT_VALID_EXT_RETURN(pVM, VERR_INVALID_VM_HANDLE);
836	DBGC_CMDHLP_ASSERT_PARSER_RET(pCmdHlp, pCmd, -1, cArgs == 0);
837	uint32_t cErrors = 0;
838	NOREF(paArgs);
839
840	PPGMPOOL pPool = pVM->pgm.s.CTX_SUFF(pPool);
841	for (unsigned i = 0; i < pPool->cCurPages; i++)
842	{
843	PPGMPOOLPAGE pPage = &pPool->aPages[i];
844	bool fFirstMsg = true;
845
846	/** @todo cover other paging modes too. */
847	if (pPage->enmKind == PGMPOOLKIND_PAE_PT_FOR_PAE_PT)
848	{
849	PPGMSHWPTPAE pShwPT = (PPGMSHWPTPAE)PGMPOOL_PAGE_2_PTR(pPool->CTX_SUFF(pVM), pPage);
850	{
851	PX86PTPAE pGstPT;
852	PGMPAGEMAPLOCK LockPage;
853	int rc = PGMPhysGCPhys2CCPtrReadOnly(pVM, pPage->GCPhys, (const void **)&pGstPT, &LockPage); AssertReleaseRC(rc);
854
855	/* Check if any PTEs are out of sync. */
856	for (unsigned j = 0; j < RT_ELEMENTS(pShwPT->a); j++)
857	{
858	if (PGMSHWPTEPAE_IS_P(pShwPT->a[j]))
859	{
860	RTHCPHYS HCPhys = NIL_RTHCPHYS;
861	rc = PGMPhysGCPhys2HCPhys(pPool->CTX_SUFF(pVM), pGstPT->a[j].u & X86_PTE_PAE_PG_MASK, &HCPhys);
862	if ( rc != VINF_SUCCESS
863	\|\| PGMSHWPTEPAE_GET_HCPHYS(pShwPT->a[j]) != HCPhys)
864	{
865	if (fFirstMsg)
866	{
867	DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
868	fFirstMsg = false;
869	}
870	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);
871	cErrors++;
872	}
873	else if ( PGMSHWPTEPAE_IS_RW(pShwPT->a[j])
874	&& !pGstPT->a[j].n.u1Write)
875	{
876	if (fFirstMsg)
877	{
878	DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
879	fFirstMsg = false;
880	}
881	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);
882	cErrors++;
883	}
884	}
885	}
886	PGMPhysReleasePageMappingLock(pVM, &LockPage);
887	}
888
889	/* Make sure this page table can't be written to from any shadow mapping. */
890	RTHCPHYS HCPhysPT = NIL_RTHCPHYS;
891	int rc = PGMPhysGCPhys2HCPhys(pPool->CTX_SUFF(pVM), pPage->GCPhys, &HCPhysPT);
892	AssertMsgRC(rc, ("PGMPhysGCPhys2HCPhys failed with rc=%d for %RGp\n", rc, pPage->GCPhys));
893	if (rc == VINF_SUCCESS)
894	{
895	for (unsigned j = 0; j < pPool->cCurPages; j++)
896	{
897	PPGMPOOLPAGE pTempPage = &pPool->aPages[j];
898
899	if (pTempPage->enmKind == PGMPOOLKIND_PAE_PT_FOR_PAE_PT)
900	{
901	PPGMSHWPTPAE pShwPT2 = (PPGMSHWPTPAE)PGMPOOL_PAGE_2_PTR(pPool->CTX_SUFF(pVM), pTempPage);
902
903	for (unsigned k = 0; k < RT_ELEMENTS(pShwPT->a); k++)
904	{
905	if ( PGMSHWPTEPAE_IS_P_RW(pShwPT2->a[k])
906	# ifdef PGMPOOL_WITH_OPTIMIZED_DIRTY_PT
907	&& !pPage->fDirty
908	# endif
909	&& PGMSHWPTEPAE_GET_HCPHYS(pShwPT2->a[k]) == HCPhysPT)
910	{
911	if (fFirstMsg)
912	{
913	DBGCCmdHlpPrintf(pCmdHlp, "Check pool page %RGp\n", pPage->GCPhys);
914	fFirstMsg = false;
915	}
916	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]));
917	cErrors++;
918	}
919	}
920	}
921	}
922	}
923	}
924	}
925	if (cErrors > 0)
926	return DBGCCmdHlpFail(pCmdHlp, pCmd, "Found %#x errors", cErrors);
927	return VINF_SUCCESS;
928	}
929	#endif /* VBOX_WITH_DEBUGGER */

Note: See TracBrowser for help on using the repository browser.

source: vbox/trunk/src/VBox/VMM/VMMR3/PGMPool.cpp@ 85179

Download in other formats: