Merge branch 'queue' into next

* queue: KVM: MMU: Eliminate pointless temporary 'ac' KVM: MMU: Avoid access/dirty update loop if all is well KVM: MMU: Eliminate eperm temporary KVM: MMU: Optimize is_last_gpte() KVM: MMU: Simplify walk_addr_generic() loop KVM: MMU: Optimize pte permission checks KVM: MMU: Update accessed and dirty bits after guest pagetable walk KVM: MMU: Move gpte_access() out of paging_tmpl.h KVM: MMU: Optimize gpte_access() slightly KVM: MMU: Push clean gpte write protection out of gpte_access() KVM: clarify kvmclock documentation KVM: make processes waiting on vcpu mutex killable KVM: SVM: Make use of asm.h KVM: VMX: Make use of asm.h KVM: VMX: Make lto-friendly Signed-off-by: Avi Kivity <[email protected]>
opendata26 · Sep 20, 2012 · 1d86b5c · 1d86b5c
2 parents ecba9a5 + c542151
commit 1d86b5c
Show file tree

Hide file tree

Showing 10 changed files with 300 additions and 220 deletions.
diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
@@ -34,9 +34,12 @@ MSR_KVM_WALL_CLOCK_NEW:   0x4b564d00
 		time information and check that they are both equal and even.
 		An odd version indicates an in-progress update.
 
-		sec: number of seconds for wallclock.
+		sec: number of seconds for wallclock at time of boot.
 
-		nsec: number of nanoseconds for wallclock.
+		nsec: number of nanoseconds for wallclock at time of boot.
+
+	In order to get the current wallclock time, the system_time from
+	MSR_KVM_SYSTEM_TIME_NEW needs to be added.
 
 	Note that although MSRs are per-CPU entities, the effect of this
 	particular MSR is global.
@@ -82,20 +85,25 @@ MSR_KVM_SYSTEM_TIME_NEW:  0x4b564d01
 		time at the time this structure was last updated. Unit is
 		nanoseconds.
 
-		tsc_to_system_mul: a function of the tsc frequency. One has
-		to multiply any tsc-related quantity by this value to get
-		a value in nanoseconds, besides dividing by 2^tsc_shift
+		tsc_to_system_mul: multiplier to be used when converting
+		tsc-related quantity to nanoseconds
 
-		tsc_shift: cycle to nanosecond divider, as a power of two, to
-		allow for shift rights. One has to shift right any tsc-related
-		quantity by this value to get a value in nanoseconds, besides
-		multiplying by tsc_to_system_mul.
+		tsc_shift: shift to be used when converting tsc-related
+		quantity to nanoseconds. This shift will ensure that
+		multiplication with tsc_to_system_mul does not overflow.
+		A positive value denotes a left shift, a negative value
+		a right shift.
 
-		With this information, guests can derive per-CPU time by
-		doing:
+		The conversion from tsc to nanoseconds involves an additional
+		right shift by 32 bits. With this information, guests can
+		derive per-CPU time by doing:
 
 			time = (current_tsc - tsc_timestamp)
-			time = (time * tsc_to_system_mul) >> tsc_shift
+			if (tsc_shift >= 0)
+				time <<= tsc_shift;
+			else
+				time >>= -tsc_shift;
+			time = (time * tsc_to_system_mul) >> 32
 			time = time + system_time
 
 		flags: bits in this field indicate extended capabilities

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
@@ -287,10 +287,24 @@ struct kvm_mmu {
 	union kvm_mmu_page_role base_role;
 	bool direct_map;
 
+	/*
+	 * Bitmap; bit set = permission fault
+	 * Byte index: page fault error code [4:1]
+	 * Bit index: pte permissions in ACC_* format
+	 */
+	u8 permissions[16];
+
 	u64 *pae_root;
 	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
 
+	/*
+	 * Bitmap: bit set = last pte in walk
+	 * index[0:1]: level (zero-based)
+	 * index[2]: pte.ps
+	 */
+	u8 last_pte_bitmap;
+
 	bool nx;
 
 	u64 pdptrs[4]; /* pae */

diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
@@ -3408,6 +3408,18 @@ static bool is_rsvd_bits_set(struct kvm_mmu *mmu, u64 gpte, int level)
 	return (gpte & mmu->rsvd_bits_mask[bit7][level-1]) != 0;
 }
 
+static inline void protect_clean_gpte(unsigned *access, unsigned gpte)
+{
+	unsigned mask;
+
+	BUILD_BUG_ON(PT_WRITABLE_MASK != ACC_WRITE_MASK);
+
+	mask = (unsigned)~ACC_WRITE_MASK;
+	/* Allow write access to dirty gptes */
+	mask |= (gpte >> (PT_DIRTY_SHIFT - PT_WRITABLE_SHIFT)) & PT_WRITABLE_MASK;
+	*access &= mask;
+}
+
 static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
 			   int *nr_present)
 {
@@ -3425,6 +3437,25 @@ static bool sync_mmio_spte(u64 *sptep, gfn_t gfn, unsigned access,
 	return false;
 }
 
+static inline unsigned gpte_access(struct kvm_vcpu *vcpu, u64 gpte)
+{
+	unsigned access;
+
+	access = (gpte & (PT_WRITABLE_MASK | PT_USER_MASK)) | ACC_EXEC_MASK;
+	access &= ~(gpte >> PT64_NX_SHIFT);
+
+	return access;
+}
+
+static inline bool is_last_gpte(struct kvm_mmu *mmu, unsigned level, unsigned gpte)
+{
+	unsigned index;
+
+	index = level - 1;
+	index |= (gpte & PT_PAGE_SIZE_MASK) >> (PT_PAGE_SIZE_SHIFT - 2);
+	return mmu->last_pte_bitmap & (1 << index);
+}
+
 #define PTTYPE 64
 #include "paging_tmpl.h"
 #undef PTTYPE
@@ -3494,6 +3525,56 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
 	}
 }
 
+static void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	unsigned bit, byte, pfec;
+	u8 map;
+	bool fault, x, w, u, wf, uf, ff, smep;
+
+	smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
+		pfec = byte << 1;
+		map = 0;
+		wf = pfec & PFERR_WRITE_MASK;
+		uf = pfec & PFERR_USER_MASK;
+		ff = pfec & PFERR_FETCH_MASK;
+		for (bit = 0; bit < 8; ++bit) {
+			x = bit & ACC_EXEC_MASK;
+			w = bit & ACC_WRITE_MASK;
+			u = bit & ACC_USER_MASK;
+
+			/* Not really needed: !nx will cause pte.nx to fault */
+			x |= !mmu->nx;
+			/* Allow supervisor writes if !cr0.wp */
+			w |= !is_write_protection(vcpu) && !uf;
+			/* Disallow supervisor fetches of user code if cr4.smep */
+			x &= !(smep && u && !uf);
+
+			fault = (ff && !x) || (uf && !u) || (wf && !w);
+			map |= fault << bit;
+		}
+		mmu->permissions[byte] = map;
+	}
+}
+
+static void update_last_pte_bitmap(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
+{
+	u8 map;
+	unsigned level, root_level = mmu->root_level;
+	const unsigned ps_set_index = 1 << 2;  /* bit 2 of index: ps */
+
+	if (root_level == PT32E_ROOT_LEVEL)
+		--root_level;
+	/* PT_PAGE_TABLE_LEVEL always terminates */
+	map = 1 | (1 << ps_set_index);
+	for (level = PT_DIRECTORY_LEVEL; level <= root_level; ++level) {
+		if (level <= PT_PDPE_LEVEL
+		    && (mmu->root_level >= PT32E_ROOT_LEVEL || is_pse(vcpu)))
+			map |= 1 << (ps_set_index | (level - 1));
+	}
+	mmu->last_pte_bitmap = map;
+}
+
 static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 					struct kvm_mmu *context,
 					int level)
@@ -3502,6 +3583,8 @@ static int paging64_init_context_common(struct kvm_vcpu *vcpu,
 	context->root_level = level;
 
 	reset_rsvds_bits_mask(vcpu, context);
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	ASSERT(is_pae(vcpu));
 	context->new_cr3 = paging_new_cr3;
@@ -3530,6 +3613,8 @@ static int paging32_init_context(struct kvm_vcpu *vcpu,
 	context->root_level = PT32_ROOT_LEVEL;
 
 	reset_rsvds_bits_mask(vcpu, context);
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
 
 	context->new_cr3 = paging_new_cr3;
 	context->page_fault = paging32_page_fault;
@@ -3590,6 +3675,9 @@ static int init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 		context->gva_to_gpa = paging32_gva_to_gpa;
 	}
 
+	update_permission_bitmask(vcpu, context);
+	update_last_pte_bitmap(vcpu, context);
+
 	return 0;
 }
 
@@ -3665,6 +3753,9 @@ static int init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
 		g_context->gva_to_gpa = paging32_gva_to_gpa_nested;
 	}
 
+	update_permission_bitmask(vcpu, g_context);
+	update_last_pte_bitmap(vcpu, g_context);
+
 	return 0;
 }
 

diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
@@ -18,8 +18,10 @@
 #define PT_PCD_MASK (1ULL << 4)
 #define PT_ACCESSED_SHIFT 5
 #define PT_ACCESSED_MASK (1ULL << PT_ACCESSED_SHIFT)
-#define PT_DIRTY_MASK (1ULL << 6)
-#define PT_PAGE_SIZE_MASK (1ULL << 7)
+#define PT_DIRTY_SHIFT 6
+#define PT_DIRTY_MASK (1ULL << PT_DIRTY_SHIFT)
+#define PT_PAGE_SIZE_SHIFT 7
+#define PT_PAGE_SIZE_MASK (1ULL << PT_PAGE_SIZE_SHIFT)
 #define PT_PAT_MASK (1ULL << 7)
 #define PT_GLOBAL_MASK (1ULL << 8)
 #define PT64_NX_SHIFT 63
@@ -88,17 +90,14 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_WP);
 }
 
-static inline bool check_write_user_access(struct kvm_vcpu *vcpu,
-					   bool write_fault, bool user_fault,
-					   unsigned long pte)
+/*
+ * Will a fault with a given page-fault error code (pfec) cause a permission
+ * fault with the given access (in ACC_* format)?
+ */
+static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
+				    unsigned pfec)
 {
-	if (unlikely(write_fault && !is_writable_pte(pte)
-	      && (user_fault || is_write_protection(vcpu))))
-		return false;
-
-	if (unlikely(user_fault && !(pte & PT_USER_MASK)))
-		return false;
-
-	return true;
+	return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
 }
+
 #endif