Merge tag 'x86_mm_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 LAM (Linear Address Masking) support from Dave Hansen:
 "Add support for the new Linear Address Masking CPU feature.

  This is similar to ARM's Top Byte Ignore and allows userspace to store
  metadata in some bits of pointers without masking it out before use"

* tag 'x86_mm_for_6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm/iommu/sva: Do not allow to set FORCE_TAGGED_SVA bit from outside
  x86/mm/iommu/sva: Fix error code for LAM enabling failure due to SVA
  selftests/x86/lam: Add test cases for LAM vs thread creation
  selftests/x86/lam: Add ARCH_FORCE_TAGGED_SVA test cases for linear-address masking
  selftests/x86/lam: Add inherit test cases for linear-address masking
  selftests/x86/lam: Add io_uring test cases for linear-address masking
  selftests/x86/lam: Add mmap and SYSCALL test cases for linear-address masking
  selftests/x86/lam: Add malloc and tag-bits test cases for linear-address masking
  x86/mm/iommu/sva: Make LAM and SVA mutually exclusive
  iommu/sva: Replace pasid_valid() helper with mm_valid_pasid()
  mm: Expose untagging mask in /proc/$PID/status
  x86/mm: Provide arch_prctl() interface for LAM
  x86/mm: Reduce untagged_addr() overhead for systems without LAM
  x86/uaccess: Provide untagged_addr() and remove tags before address check
  mm: Introduce untagged_addr_remote()
  x86/mm: Handle LAM on context switch
  x86: CPUID and CR3/CR4 flags for Linear Address Masking
  x86: Allow atomic MM_CONTEXT flags setting
  x86/mm: Rework address range check in get_user() and put_user()

9 files changed, 187 insertions, 8 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 73c9672c123b..353b054812de 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -321,6 +321,7 @@
 #define X86_FEATURE_LKGS		(12*32+18) /* "" Load "kernel" (userspace) GS */
 #define X86_FEATURE_AMX_FP16		(12*32+21) /* "" AMX fp16 Support */
 #define X86_FEATURE_AVX_IFMA            (12*32+23) /* "" Support for VPMADD52[H,L]UQ */
+#define X86_FEATURE_LAM			(12*32+26) /* Linear Address Masking */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 5dfa4fb76f4b..fafe9be7a6f4 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -75,6 +75,12 @@
 # define DISABLE_CALL_DEPTH_TRACKING	(1 << (X86_FEATURE_CALL_DEPTH & 31))
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+# define DISABLE_LAM		0
+#else
+# define DISABLE_LAM		(1 << (X86_FEATURE_LAM & 31))
+#endif
+
 #ifdef CONFIG_INTEL_IOMMU_SVM
 # define DISABLE_ENQCMD		0
 #else
@@ -115,7 +121,7 @@
 #define DISABLED_MASK10	0
 #define DISABLED_MASK11	(DISABLE_RETPOLINE|DISABLE_RETHUNK|DISABLE_UNRET| \
 			 DISABLE_CALL_DEPTH_TRACKING)
-#define DISABLED_MASK12	0
+#define DISABLED_MASK12	(DISABLE_LAM)
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 5d7494631ea9..0da5c227f490 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,9 +9,13 @@
 #include <linux/bits.h>
 
 /* Uprobes on this MM assume 32-bit code */
-#define MM_CONTEXT_UPROBE_IA32	BIT(0)
+#define MM_CONTEXT_UPROBE_IA32		0
 /* vsyscall page is accessible on this MM */
-#define MM_CONTEXT_HAS_VSYSCALL	BIT(1)
+#define MM_CONTEXT_HAS_VSYSCALL		1
+/* Do not allow changing LAM mode */
+#define MM_CONTEXT_LOCK_LAM		2
+/* Allow LAM and SVA coexisting */
+#define MM_CONTEXT_FORCE_TAGGED_SVA	3
 
 /*
  * x86 has arch-specific MMU state beyond what lives in mm_struct.
@@ -39,7 +43,15 @@ typedef struct {
 #endif
 
 #ifdef CONFIG_X86_64
-	unsigned short flags;
+	unsigned long flags;
+#endif
+
+#ifdef CONFIG_ADDRESS_MASKING
+	/* Active LAM mode:  X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
+	unsigned long lam_cr3_mask;
+
+	/* Significant bits of the virtual address. Excludes tag bits. */
+	u64 untag_mask;
 #endif
 
 	struct mutex lock;
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index c3ad8a526378..1d29dc791f5a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -85,6 +85,51 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 }
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+	return mm->context.lam_cr3_mask;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+	mm->context.lam_cr3_mask = oldmm->context.lam_cr3_mask;
+	mm->context.untag_mask = oldmm->context.untag_mask;
+}
+
+#define mm_untag_mask mm_untag_mask
+static inline unsigned long mm_untag_mask(struct mm_struct *mm)
+{
+	return mm->context.untag_mask;
+}
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+	mm->context.untag_mask = -1UL;
+}
+
+#define arch_pgtable_dma_compat arch_pgtable_dma_compat
+static inline bool arch_pgtable_dma_compat(struct mm_struct *mm)
+{
+	return !mm_lam_cr3_mask(mm) ||
+		test_bit(MM_CONTEXT_FORCE_TAGGED_SVA, &mm->context.flags);
+}
+#else
+
+static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)
+{
+}
+
+static inline void mm_reset_untag_mask(struct mm_struct *mm)
+{
+}
+#endif
+
 #define enter_lazy_tlb enter_lazy_tlb
 extern void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk);
 
@@ -109,6 +154,7 @@ static inline int init_new_context(struct task_struct *tsk,
 		mm->context.execute_only_pkey = -1;
 	}
 #endif
+	mm_reset_untag_mask(mm);
 	init_new_context_ldt(mm);
 	return 0;
 }
@@ -162,6 +208,7 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm)
 {
 	arch_dup_pkeys(oldmm, mm);
 	paravirt_enter_mmap(mm);
+	dup_lam(oldmm, mm);
 	return ldt_dup_context(oldmm, mm);
 }
 
@@ -175,7 +222,7 @@ static inline void arch_exit_mmap(struct mm_struct *mm)
 static inline bool is_64bit_mm(struct mm_struct *mm)
 {
 	return	!IS_ENABLED(CONFIG_IA32_EMULATION) ||
-		!(mm->context.flags & MM_CONTEXT_UPROBE_IA32);
+		!test_bit(MM_CONTEXT_UPROBE_IA32, &mm->context.flags);
 }
 #else
 static inline bool is_64bit_mm(struct mm_struct *mm)
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index a7f3d9100adb..d8cccadc83a6 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -28,6 +28,8 @@
  * On systems with SME, one bit (in a variable position!) is stolen to indicate
  * that the top-level paging structure is encrypted.
  *
+ * On systemms with LAM, bits 61 and 62 are used to indicate LAM mode.
+ *
  * All of the remaining bits indicate the physical address of the top-level
  * paging structure.
  *
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index cda3118f3b27..75bfaa421030 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -2,7 +2,7 @@
 #ifndef _ASM_X86_TLBFLUSH_H
 #define _ASM_X86_TLBFLUSH_H
 
-#include <linux/mm.h>
+#include <linux/mm_types.h>
 #include <linux/sched.h>
 
 #include <asm/processor.h>
@@ -12,6 +12,7 @@
 #include <asm/invpcid.h>
 #include <asm/pti.h>
 #include <asm/processor-flags.h>
+#include <asm/pgtable.h>
 
 void __flush_tlb_all(void);
 
@@ -53,6 +54,15 @@ static inline void cr4_clear_bits(unsigned long mask)
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_ADDRESS_MASKING
+DECLARE_PER_CPU(u64, tlbstate_untag_mask);
+
+static inline u64 current_untag_mask(void)
+{
+	return this_cpu_read(tlbstate_untag_mask);
+}
+#endif
+
 #ifndef MODULE
 /*
  * 6 because 6 should be plenty and struct tlb_state will fit in two cache
@@ -101,6 +111,16 @@ struct tlb_state {
 	 */
 	bool invalidate_other;
 
+#ifdef CONFIG_ADDRESS_MASKING
+	/*
+	 * Active LAM mode.
+	 *
+	 * X86_CR3_LAM_U57/U48 shifted right by X86_CR3_LAM_U57_BIT or 0 if LAM
+	 * disabled.
+	 */
+	u8 lam;
+#endif
+
 	/*
 	 * Mask that contains TLB_NR_DYN_ASIDS+1 bits to indicate
 	 * the corresponding user PCID needs a flush next time we
@@ -357,6 +377,32 @@ static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd)
 }
 #define huge_pmd_needs_flush huge_pmd_needs_flush
 
+#ifdef CONFIG_ADDRESS_MASKING
+static inline  u64 tlbstate_lam_cr3_mask(void)
+{
+	u64 lam = this_cpu_read(cpu_tlbstate.lam);
+
+	return lam << X86_CR3_LAM_U57_BIT;
+}
+
+static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+{
+	this_cpu_write(cpu_tlbstate.lam,
+		       mm->context.lam_cr3_mask >> X86_CR3_LAM_U57_BIT);
+	this_cpu_write(tlbstate_untag_mask, mm->context.untag_mask);
+}
+
+#else
+
+static inline u64 tlbstate_lam_cr3_mask(void)
+{
+	return 0;
+}
+
+static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+{
+}
+#endif
 #endif /* !MODULE */
 
 static inline void __native_tlb_flush_global(unsigned long cr4)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 1cc756eafa44..457e814712af 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -7,11 +7,14 @@
 #include <linux/compiler.h>
 #include <linux/instrumented.h>
 #include <linux/kasan-checks.h>
+#include <linux/mm_types.h>
 #include <linux/string.h>
+#include <linux/mmap_lock.h>
 #include <asm/asm.h>
 #include <asm/page.h>
 #include <asm/smap.h>
 #include <asm/extable.h>
+#include <asm/tlbflush.h>
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 static inline bool pagefault_disabled(void);
@@ -21,6 +24,57 @@ static inline bool pagefault_disabled(void);
 # define WARN_ON_IN_IRQ()
 #endif
 
+#ifdef CONFIG_ADDRESS_MASKING
+/*
+ * Mask out tag bits from the address.
+ *
+ * Magic with the 'sign' allows to untag userspace pointer without any branches
+ * while leaving kernel addresses intact.
+ */
+static inline unsigned long __untagged_addr(unsigned long addr)
+{
+	long sign;
+
+	/*
+	 * Refer tlbstate_untag_mask directly to avoid RIP-relative relocation
+	 * in alternative instructions. The relocation gets wrong when gets
+	 * copied to the target place.
+	 */
+	asm (ALTERNATIVE("",
+			 "sar $63, %[sign]\n\t" /* user_ptr ? 0 : -1UL */
+			 "or %%gs:tlbstate_untag_mask, %[sign]\n\t"
+			 "and %[sign], %[addr]\n\t", X86_FEATURE_LAM)
+	     : [addr] "+r" (addr), [sign] "=r" (sign)
+	     : "m" (tlbstate_untag_mask), "[sign]" (addr));
+
+	return addr;
+}
+
+#define untagged_addr(addr)	({					\
+	unsigned long __addr = (__force unsigned long)(addr);		\
+	(__force __typeof__(addr))__untagged_addr(__addr);		\
+})
+
+static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
+						   unsigned long addr)
+{
+	long sign = addr >> 63;
+
+	mmap_assert_locked(mm);
+	addr &= (mm)->context.untag_mask | sign;
+
+	return addr;
+}
+
+#define untagged_addr_remote(mm, addr)	({				\
+	unsigned long __addr = (__force unsigned long)(addr);		\
+	(__force __typeof__(addr))__untagged_addr_remote(mm, __addr);	\
+})
+
+#else
+#define untagged_addr(addr)	(addr)
+#endif
+
 /**
  * access_ok - Checks if a user space pointer is valid
  * @addr: User space pointer to start of block to check
@@ -38,10 +92,10 @@ static inline bool pagefault_disabled(void);
  * Return: true (nonzero) if the memory block may be valid, false (zero)
  * if it is definitely invalid.
  */
-#define access_ok(addr, size)					\
+#define access_ok(addr, size)						\
 ({									\
 	WARN_ON_IN_IRQ();						\
-	likely(__access_ok(addr, size));				\
+	likely(__access_ok(untagged_addr(addr), size));			\
 })
 
 #include <asm-generic/access_ok.h>
diff --git a/arch/x86/include/uapi/asm/prctl.h b/arch/x86/include/uapi/asm/prctl.h
index f298c778f856..e8d7ebbca1a4 100644
--- a/arch/x86/include/uapi/asm/prctl.h
+++ b/arch/x86/include/uapi/asm/prctl.h
@@ -23,4 +23,9 @@
 #define ARCH_MAP_VDSO_32		0x2002
 #define ARCH_MAP_VDSO_64		0x2003
 
+#define ARCH_GET_UNTAG_MASK		0x4001
+#define ARCH_ENABLE_TAGGED_ADDR		0x4002
+#define ARCH_GET_MAX_TAG_BITS		0x4003
+#define ARCH_FORCE_TAGGED_SVA		0x4004
+
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/uapi/asm/processor-flags.h b/arch/x86/include/uapi/asm/processor-flags.h
index c47cc7f2feeb..d898432947ff 100644
--- a/arch/x86/include/uapi/asm/processor-flags.h
+++ b/arch/x86/include/uapi/asm/processor-flags.h
@@ -82,6 +82,10 @@
 #define X86_CR3_PCID_BITS	12
 #define X86_CR3_PCID_MASK	(_AC((1UL << X86_CR3_PCID_BITS) - 1, UL))
 
+#define X86_CR3_LAM_U57_BIT	61 /* Activate LAM for userspace, 62:57 bits masked */
+#define X86_CR3_LAM_U57		_BITULL(X86_CR3_LAM_U57_BIT)
+#define X86_CR3_LAM_U48_BIT	62 /* Activate LAM for userspace, 62:48 bits masked */
+#define X86_CR3_LAM_U48		_BITULL(X86_CR3_LAM_U48_BIT)
 #define X86_CR3_PCID_NOFLUSH_BIT 63 /* Preserve old PCID */
 #define X86_CR3_PCID_NOFLUSH    _BITULL(X86_CR3_PCID_NOFLUSH_BIT)
 
@@ -132,6 +136,8 @@
 #define X86_CR4_PKE		_BITUL(X86_CR4_PKE_BIT)
 #define X86_CR4_CET_BIT		23 /* enable Control-flow Enforcement Technology */
 #define X86_CR4_CET		_BITUL(X86_CR4_CET_BIT)
+#define X86_CR4_LAM_SUP_BIT	28 /* LAM for supervisor pointers */
+#define X86_CR4_LAM_SUP		_BITUL(X86_CR4_LAM_SUP_BIT)
 
 /*
  * x86-64 Task Priority Register, CR8