Merge tag 'x86_pasid_for_5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 PASID updates from Borislav Petkov:
 "Initial support for sharing virtual addresses between the CPU and
  devices which doesn't need pinning of pages for DMA anymore.

  Add support for the command submission to devices using new x86
  instructions like ENQCMD{,S} and MOVDIR64B. In addition, add support
  for process address space identifiers (PASIDs) which are referenced by
  those command submission instructions along with the handling of the
  PASID state on context switch as another extended state.

  Work by Fenghua Yu, Ashok Raj, Yu-cheng Yu and Dave Jiang"

* tag 'x86_pasid_for_5.10' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/asm: Add an enqcmds() wrapper for the ENQCMDS instruction
  x86/asm: Carve out a generic movdir64b() helper for general usage
  x86/mmu: Allocate/free a PASID
  x86/cpufeatures: Mark ENQCMD as disabled when configured out
  mm: Add a pasid member to struct mm_struct
  x86/msr-index: Define an IA32_PASID MSR
  x86/fpu/xstate: Add supervisor PASID state for ENQCMD
  x86/cpufeatures: Enumerate ENQCMD and ENQCMDS instructions
  Documentation/x86: Add documentation for SVA (Shared Virtual Addressing)
  iommu/vt-d: Change flags type to unsigned int in binding mm
  drm, iommu: Change type of pasid to u32

11 files changed, 172 insertions, 18 deletions

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 50b2a8d85ef0..a48458b04e1e 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -353,6 +353,7 @@
 #define X86_FEATURE_CLDEMOTE		(16*32+25) /* CLDEMOTE instruction */
 #define X86_FEATURE_MOVDIRI		(16*32+27) /* MOVDIRI instruction */
 #define X86_FEATURE_MOVDIR64B		(16*32+28) /* MOVDIR64B instruction */
+#define X86_FEATURE_ENQCMD		(16*32+29) /* ENQCMD and ENQCMDS instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000007 (EBX), word 17 */
 #define X86_FEATURE_OVERFLOW_RECOV	(17*32+ 0) /* MCA overflow recovery support */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 4ea8584682f9..5861d34f9771 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -56,6 +56,12 @@
 # define DISABLE_PTI		(1 << (X86_FEATURE_PTI & 31))
 #endif
 
+#ifdef CONFIG_IOMMU_SUPPORT
+# define DISABLE_ENQCMD	0
+#else
+# define DISABLE_ENQCMD (1 << (X86_FEATURE_ENQCMD & 31))
+#endif
+
 /*
  * Make sure to add features to the correct mask
  */
@@ -75,7 +81,8 @@
 #define DISABLED_MASK13	0
 #define DISABLED_MASK14	0
 #define DISABLED_MASK15	0
-#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP)
+#define DISABLED_MASK16	(DISABLE_PKU|DISABLE_OSPKE|DISABLE_LA57|DISABLE_UMIP| \
+			 DISABLE_ENQCMD)
 #define DISABLED_MASK17	0
 #define DISABLED_MASK18	0
 #define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 19)
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index b774c52e5411..dcd9503b1098 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -62,4 +62,16 @@ extern void switch_fpu_return(void);
  */
 extern int cpu_has_xfeatures(u64 xfeatures_mask, const char **feature_name);
 
+/*
+ * Tasks that are not using SVA have mm->pasid set to zero to note that they
+ * will not have the valid bit set in MSR_IA32_PASID while they are running.
+ */
+#define PASID_DISABLED	0
+
+#ifdef CONFIG_IOMMU_SUPPORT
+/* Update current's PASID MSR/state by mm's PASID. */
+void update_pasid(void);
+#else
+static inline void update_pasid(void) { }
+#endif
 #endif /* _ASM_X86_FPU_API_H */
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 21a8b5259477..eb1ed3bd8d96 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -583,6 +583,13 @@ static inline void switch_fpu_finish(struct fpu *new_fpu)
 			pkru_val = pk->pkru;
 	}
 	__write_pkru(pkru_val);
+
+	/*
+	 * Expensive PASID MSR write will be avoided in update_pasid() because
+	 * TIF_NEED_FPU_LOAD was set. And the PASID state won't be updated
+	 * unless it's different from mm->pasid to reduce overhead.
+	 */
+	update_pasid();
 }
 
 /*
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index c87364ea6446..f5a38a5f3ae1 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -114,7 +114,7 @@ enum xfeature {
 	XFEATURE_Hi16_ZMM,
 	XFEATURE_PT_UNIMPLEMENTED_SO_FAR,
 	XFEATURE_PKRU,
-	XFEATURE_RSRVD_COMP_10,
+	XFEATURE_PASID,
 	XFEATURE_RSRVD_COMP_11,
 	XFEATURE_RSRVD_COMP_12,
 	XFEATURE_RSRVD_COMP_13,
@@ -134,6 +134,7 @@ enum xfeature {
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
 #define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
+#define XFEATURE_MASK_PASID		(1 << XFEATURE_PASID)
 #define XFEATURE_MASK_LBR		(1 << XFEATURE_LBR)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
@@ -256,6 +257,14 @@ struct arch_lbr_state {
 	struct lbr_entry		entries[];
 } __packed;
 
+/*
+ * State component 10 is supervisor state used for context-switching the
+ * PASID state.
+ */
+struct ia32_pasid_state {
+	u64 pasid;
+} __packed;
+
 struct xstate_header {
 	u64				xfeatures;
 	u64				xcomp_bv;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 14ab815132d4..47a92232d595 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -35,7 +35,7 @@
 				      XFEATURE_MASK_BNDCSR)
 
 /* All currently supported supervisor features */
-#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (0)
+#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID)
 
 /*
  * A supervisor state component may not always contain valuable information,
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e1aa17a468a8..d726459d08e5 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -401,7 +401,7 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr,
 
 /**
  * iosubmit_cmds512 - copy data to single MMIO location, in 512-bit units
- * @__dst: destination, in MMIO space (must be 512-bit aligned)
+ * @dst: destination, in MMIO space (must be 512-bit aligned)
  * @src: source
  * @count: number of 512 bits quantities to submit
  *
@@ -412,25 +412,14 @@ extern bool phys_mem_access_encrypted(unsigned long phys_addr,
  * Warning: Do not use this helper unless your driver has checked that the CPU
  * instruction is supported on the platform.
  */
-static inline void iosubmit_cmds512(void __iomem *__dst, const void *src,
+static inline void iosubmit_cmds512(void __iomem *dst, const void *src,
 				    size_t count)
 {
-	/*
-	 * Note that this isn't an "on-stack copy", just definition of "dst"
-	 * as a pointer to 64-bytes of stuff that is going to be overwritten.
-	 * In the MOVDIR64B case that may be needed as you can use the
-	 * MOVDIR64B instruction to copy arbitrary memory around. This trick
-	 * lets the compiler know how much gets clobbered.
-	 */
-	volatile struct { char _[64]; } *dst = __dst;
 	const u8 *from = src;
 	const u8 *end = from + count * 64;
 
 	while (from < end) {
-		/* MOVDIR64B [rdx], rax */
-		asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
-			     : "=m" (dst)
-			     : "d" (from), "a" (dst));
+		movdir64b(dst, from);
 		from += 64;
 	}
 }
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 2859ee4f39a8..aaddc6a9e237 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -257,6 +257,9 @@
 #define MSR_IA32_LASTINTFROMIP		0x000001dd
 #define MSR_IA32_LASTINTTOIP		0x000001de
 
+#define MSR_IA32_PASID			0x00000d93
+#define MSR_IA32_PASID_VALID		BIT_ULL(31)
+
 /* DEBUGCTLMSR bits (others vary by model): */
 #define DEBUGCTLMSR_LBR			(1UL <<  0) /* last branch recording */
 #define DEBUGCTLMSR_BTF_SHIFT		1
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 5999b0b3dd4a..94624fb06fac 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -240,6 +240,70 @@ static inline void serialize(void)
 	asm volatile(".byte 0xf, 0x1, 0xe8" ::: "memory");
 }
 
+/* The dst parameter must be 64-bytes aligned */
+static inline void movdir64b(void *dst, const void *src)
+{
+	const struct { char _[64]; } *__src = src;
+	struct { char _[64]; } *__dst = dst;
+
+	/*
+	 * MOVDIR64B %(rdx), rax.
+	 *
+	 * Both __src and __dst must be memory constraints in order to tell the
+	 * compiler that no other memory accesses should be reordered around
+	 * this one.
+	 *
+	 * Also, both must be supplied as lvalues because this tells
+	 * the compiler what the object is (its size) the instruction accesses.
+	 * I.e., not the pointers but what they point to, thus the deref'ing '*'.
+	 */
+	asm volatile(".byte 0x66, 0x0f, 0x38, 0xf8, 0x02"
+		     : "+m" (*__dst)
+		     :  "m" (*__src), "a" (__dst), "d" (__src));
+}
+
+/**
+ * enqcmds - Enqueue a command in supervisor (CPL0) mode
+ * @dst: destination, in MMIO space (must be 512-bit aligned)
+ * @src: 512 bits memory operand
+ *
+ * The ENQCMDS instruction allows software to write a 512-bit command to
+ * a 512-bit-aligned special MMIO region that supports the instruction.
+ * A return status is loaded into the ZF flag in the RFLAGS register.
+ * ZF = 0 equates to success, and ZF = 1 indicates retry or error.
+ *
+ * This function issues the ENQCMDS instruction to submit data from
+ * kernel space to MMIO space, in a unit of 512 bits. Order of data access
+ * is not guaranteed, nor is a memory barrier performed afterwards. It
+ * returns 0 on success and -EAGAIN on failure.
+ *
+ * Warning: Do not use this helper unless your driver has checked that the
+ * ENQCMDS instruction is supported on the platform and the device accepts
+ * ENQCMDS.
+ */
+static inline int enqcmds(void __iomem *dst, const void *src)
+{
+	const struct { char _[64]; } *__src = src;
+	struct { char _[64]; } *__dst = dst;
+	int zf;
+
+	/*
+	 * ENQCMDS %(rdx), rax
+	 *
+	 * See movdir64b()'s comment on operand specification.
+	 */
+	asm volatile(".byte 0xf3, 0x0f, 0x38, 0xf8, 0x02, 0x66, 0x90"
+		     CC_SET(z)
+		     : CC_OUT(z) (zf), "+m" (*__dst)
+		     : "m" (*__src), "a" (__dst), "d" (__src));
+
+	/* Submission failure is indicated via EFLAGS.ZF=1 */
+	if (zf)
+		return -EAGAIN;
+
+	return 0;
+}
+
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 3cbe24ca80ab..3a02707c1f4d 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_CQM_MBM_TOTAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_CQM_MBM_LOCAL,		X86_FEATURE_CQM_LLC   },
 	{ X86_FEATURE_AVX512_BF16,		X86_FEATURE_AVX512VL  },
+	{ X86_FEATURE_ENQCMD,			X86_FEATURE_XSAVES    },
 	{}
 };
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 038e19c0019e..5d8047441a0a 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -37,6 +37,7 @@ static const char *xfeature_names[] =
 	"AVX-512 ZMM_Hi256"		,
 	"Processor Trace (unused)"	,
 	"Protection Keys User registers",
+	"PASID state",
 	"unknown xstate feature"	,
 };
 
@@ -51,6 +52,7 @@ static short xsave_cpuid_features[] __initdata = {
 	X86_FEATURE_AVX512F,
 	X86_FEATURE_INTEL_PT,
 	X86_FEATURE_PKU,
+	X86_FEATURE_ENQCMD,
 };
 
 /*
@@ -318,6 +320,7 @@ static void __init print_xstate_features(void)
 	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
 	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
 	print_xstate_feature(XFEATURE_MASK_PKRU);
+	print_xstate_feature(XFEATURE_MASK_PASID);
 }
 
 /*
@@ -592,6 +595,7 @@ static void check_xstate_against_struct(int nr)
 	XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
 	XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM,  struct avx_512_hi16_state);
 	XCHECK_SZ(sz, nr, XFEATURE_PKRU,      struct pkru_state);
+	XCHECK_SZ(sz, nr, XFEATURE_PASID,     struct ia32_pasid_state);
 
 	/*
 	 * Make *SURE* to add any feature numbers in below if
@@ -601,7 +605,7 @@ static void check_xstate_against_struct(int nr)
 	if ((nr < XFEATURE_YMM) ||
 	    (nr >= XFEATURE_MAX) ||
 	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
-	    ((nr >= XFEATURE_RSRVD_COMP_10) && (nr <= XFEATURE_LBR))) {
+	    ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_LBR))) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -1398,3 +1402,60 @@ int proc_pid_arch_status(struct seq_file *m, struct pid_namespace *ns,
 	return 0;
 }
 #endif /* CONFIG_PROC_PID_ARCH_STATUS */
+
+#ifdef CONFIG_IOMMU_SUPPORT
+void update_pasid(void)
+{
+	u64 pasid_state;
+	u32 pasid;
+
+	if (!cpu_feature_enabled(X86_FEATURE_ENQCMD))
+		return;
+
+	if (!current->mm)
+		return;
+
+	pasid = READ_ONCE(current->mm->pasid);
+	/* Set the valid bit in the PASID MSR/state only for valid pasid. */
+	pasid_state = pasid == PASID_DISABLED ?
+		      pasid : pasid | MSR_IA32_PASID_VALID;
+
+	/*
+	 * No need to hold fregs_lock() since the task's fpstate won't
+	 * be changed by others (e.g. ptrace) while the task is being
+	 * switched to or is in IPI.
+	 */
+	if (!test_thread_flag(TIF_NEED_FPU_LOAD)) {
+		/* The MSR is active and can be directly updated. */
+		wrmsrl(MSR_IA32_PASID, pasid_state);
+	} else {
+		struct fpu *fpu = &current->thread.fpu;
+		struct ia32_pasid_state *ppasid_state;
+		struct xregs_state *xsave;
+
+		/*
+		 * The CPU's xstate registers are not currently active. Just
+		 * update the PASID state in the memory buffer here. The
+		 * PASID MSR will be loaded when returning to user mode.
+		 */
+		xsave = &fpu->state.xsave;
+		xsave->header.xfeatures |= XFEATURE_MASK_PASID;
+		ppasid_state = get_xsave_addr(xsave, XFEATURE_PASID);
+		/*
+		 * Since XFEATURE_MASK_PASID is set in xfeatures, ppasid_state
+		 * won't be NULL and no need to check its value.
+		 *
+		 * Only update the task's PASID state when it's different
+		 * from the mm's pasid.
+		 */
+		if (ppasid_state->pasid != pasid_state) {
+			/*
+			 * Invalid fpregs so that state restoring will pick up
+			 * the PASID state.
+			 */
+			__fpu_invalidate_fpregs_state(fpu);
+			ppasid_state->pasid = pasid_state;
+		}
+	}
+}
+#endif /* CONFIG_IOMMU_SUPPORT */