Merge tag 'x86_shstk_for_6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 shadow stack support from Dave Hansen:
 "This is the long awaited x86 shadow stack support, part of Intel's
  Control-flow Enforcement Technology (CET).

  CET consists of two related security features: shadow stacks and
  indirect branch tracking. This series implements just the shadow stack
  part of this feature, and just for userspace.

  The main use case for shadow stack is providing protection against
  return oriented programming attacks. It works by maintaining a
  secondary (shadow) stack using a special memory type that has
  protections against modification. When executing a CALL instruction,
  the processor pushes the return address to both the normal stack and
  to the special permission shadow stack. Upon RET, the processor pops
  the shadow stack copy and compares it to the normal stack copy.

  For more information, refer to the links below for the earlier
  versions of this patch set"

Link: https://lore.kernel.org/lkml/20220130211838.8382-1-rick.p.edgecombe@intel.com/
Link: https://lore.kernel.org/lkml/20230613001108.3040476-1-rick.p.edgecombe@intel.com/

* tag 'x86_shstk_for_6.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  x86/shstk: Change order of __user in type
  x86/ibt: Convert IBT selftest to asm
  x86/shstk: Don't retry vm_munmap() on -EINTR
  x86/kbuild: Fix Documentation/ reference
  x86/shstk: Move arch detail comment out of core mm
  x86/shstk: Add ARCH_SHSTK_STATUS
  x86/shstk: Add ARCH_SHSTK_UNLOCK
  x86: Add PTRACE interface for shadow stack
  selftests/x86: Add shadow stack test
  x86/cpufeatures: Enable CET CR4 bit for shadow stack
  x86/shstk: Wire in shadow stack interface
  x86: Expose thread features in /proc/$PID/status
  x86/shstk: Support WRSS for userspace
  x86/shstk: Introduce map_shadow_stack syscall
  x86/shstk: Check that signal frame is shadow stack mem
  x86/shstk: Check that SSP is aligned on sigreturn
  x86/shstk: Handle signals for shadow stack
  x86/shstk: Introduce routines modifying shstk
  x86/shstk: Handle thread shadow stack
  x86/shstk: Add user-mode shadow stack support
  ...

3 files changed, 177 insertions, 48 deletions

diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 98e507cc7d34..a86d37052a64 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -552,8 +552,36 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 	}
 }
 
+/* A passed ssp of zero will not cause any update */
+static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
+{
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+	struct cet_user_state *xstate;
+
+	/* If ssp update is not needed. */
+	if (!ssp)
+		return 0;
+
+	xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave,
+				XFEATURE_CET_USER);
+
+	/*
+	 * If there is a non-zero ssp, then 'dst' must be configured with a shadow
+	 * stack and the fpu state should be up to date since it was just copied
+	 * from the parent in fpu_clone(). So there must be a valid non-init CET
+	 * state location in the buffer.
+	 */
+	if (WARN_ON_ONCE(!xstate))
+		return 1;
+
+	xstate->user_ssp = (u64)ssp;
+#endif
+	return 0;
+}
+
 /* Clone current's FPU state on fork */
-int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
+	      unsigned long ssp)
 {
 	struct fpu *src_fpu = &current->thread.fpu;
 	struct fpu *dst_fpu = &dst->thread.fpu;
@@ -613,6 +641,12 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
 	if (use_xsave())
 		dst_fpu->fpstate->regs.xsave.header.xfeatures &= ~XFEATURE_MASK_PASID;
 
+	/*
+	 * Update shadow stack pointer, in case it changed during clone.
+	 */
+	if (update_fpu_shstk(dst, ssp))
+		return 1;
+
 	trace_x86_fpu_copy_src(src_fpu);
 	trace_x86_fpu_copy_dst(dst_fpu);
 
@@ -753,6 +787,24 @@ void switch_fpu_return(void)
 }
 EXPORT_SYMBOL_GPL(switch_fpu_return);
 
+void fpregs_lock_and_load(void)
+{
+	/*
+	 * fpregs_lock() only disables preemption (mostly). So modifying state
+	 * in an interrupt could screw up some in progress fpregs operation.
+	 * Warn about it.
+	 */
+	WARN_ON_ONCE(!irq_fpu_usable());
+	WARN_ON_ONCE(current->flags & PF_KTHREAD);
+
+	fpregs_lock();
+
+	fpregs_assert_state_consistent();
+
+	if (test_thread_flag(TIF_NEED_FPU_LOAD))
+		fpregs_restore_userregs();
+}
+
 #ifdef CONFIG_X86_DEBUG_FPU
 /*
  * If current FPU state according to its tracking (loaded FPU context on this
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 6d056b68f4ed..6bc1eb2a21bd 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -8,6 +8,7 @@
 #include <asm/fpu/api.h>
 #include <asm/fpu/signal.h>
 #include <asm/fpu/regset.h>
+#include <asm/prctl.h>
 
 #include "context.h"
 #include "internal.h"
@@ -174,6 +175,86 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_X86_USER_SHADOW_STACK
+int ssp_active(struct task_struct *target, const struct user_regset *regset)
+{
+	if (target->thread.features & ARCH_SHSTK_SHSTK)
+		return regset->n;
+
+	return 0;
+}
+
+int ssp_get(struct task_struct *target, const struct user_regset *regset,
+	    struct membuf to)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct cet_user_state *cetregs;
+
+	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK))
+		return -ENODEV;
+
+	sync_fpstate(fpu);
+	cetregs = get_xsave_addr(&fpu->fpstate->regs.xsave, XFEATURE_CET_USER);
+	if (WARN_ON(!cetregs)) {
+		/*
+		 * This shouldn't ever be NULL because shadow stack was
+		 * verified to be enabled above. This means
+		 * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so
+		 * XFEATURE_CET_USER should not be in the init state.
+		 */
+		return -ENODEV;
+	}
+
+	return membuf_write(&to, (unsigned long *)&cetregs->user_ssp,
+			    sizeof(cetregs->user_ssp));
+}
+
+int ssp_set(struct task_struct *target, const struct user_regset *regset,
+	    unsigned int pos, unsigned int count,
+	    const void *kbuf, const void __user *ubuf)
+{
+	struct fpu *fpu = &target->thread.fpu;
+	struct xregs_state *xsave = &fpu->fpstate->regs.xsave;
+	struct cet_user_state *cetregs;
+	unsigned long user_ssp;
+	int r;
+
+	if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
+	    !ssp_active(target, regset))
+		return -ENODEV;
+
+	if (pos != 0 || count != sizeof(user_ssp))
+		return -EINVAL;
+
+	r = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_ssp, 0, -1);
+	if (r)
+		return r;
+
+	/*
+	 * Some kernel instructions (IRET, etc) can cause exceptions in the case
+	 * of disallowed CET register values. Just prevent invalid values.
+	 */
+	if (user_ssp >= TASK_SIZE_MAX || !IS_ALIGNED(user_ssp, 8))
+		return -EINVAL;
+
+	fpu_force_restore(fpu);
+
+	cetregs = get_xsave_addr(xsave, XFEATURE_CET_USER);
+	if (WARN_ON(!cetregs)) {
+		/*
+		 * This shouldn't ever be NULL because shadow stack was
+		 * verified to be enabled above. This means
+		 * MSR_IA32_U_CET.CET_SHSTK_EN should be 1 and so
+		 * XFEATURE_CET_USER should not be in the init state.
+		 */
+		return -ENODEV;
+	}
+
+	cetregs->user_ssp = user_ssp;
+	return 0;
+}
+#endif /* CONFIG_X86_USER_SHADOW_STACK */
+
 #if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
 
 /*
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 1afbc4866b10..41dac93b8ea4 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -39,26 +39,26 @@
  */
 static const char *xfeature_names[] =
 {
-	"x87 floating point registers"	,
-	"SSE registers"			,
-	"AVX registers"			,
-	"MPX bounds registers"		,
-	"MPX CSR"			,
-	"AVX-512 opmask"		,
-	"AVX-512 Hi256"			,
-	"AVX-512 ZMM_Hi256"		,
-	"Processor Trace (unused)"	,
+	"x87 floating point registers",
+	"SSE registers",
+	"AVX registers",
+	"MPX bounds registers",
+	"MPX CSR",
+	"AVX-512 opmask",
+	"AVX-512 Hi256",
+	"AVX-512 ZMM_Hi256",
+	"Processor Trace (unused)",
 	"Protection Keys User registers",
 	"PASID state",
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"unknown xstate feature"	,
-	"AMX Tile config"		,
-	"AMX Tile data"			,
-	"unknown xstate feature"	,
+	"Control-flow User registers",
+	"Control-flow Kernel registers (unused)",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"unknown xstate feature",
+	"AMX Tile config",
+	"AMX Tile data",
+	"unknown xstate feature",
 };
 
 static unsigned short xsave_cpuid_features[] __initdata = {
@@ -73,6 +73,7 @@ static unsigned short xsave_cpuid_features[] __initdata = {
 	[XFEATURE_PT_UNIMPLEMENTED_SO_FAR]	= X86_FEATURE_INTEL_PT,
 	[XFEATURE_PKRU]				= X86_FEATURE_PKU,
 	[XFEATURE_PASID]			= X86_FEATURE_ENQCMD,
+	[XFEATURE_CET_USER]			= X86_FEATURE_SHSTK,
 	[XFEATURE_XTILE_CFG]			= X86_FEATURE_AMX_TILE,
 	[XFEATURE_XTILE_DATA]			= X86_FEATURE_AMX_TILE,
 };
@@ -276,6 +277,7 @@ static void __init print_xstate_features(void)
 	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
 	print_xstate_feature(XFEATURE_MASK_PKRU);
 	print_xstate_feature(XFEATURE_MASK_PASID);
+	print_xstate_feature(XFEATURE_MASK_CET_USER);
 	print_xstate_feature(XFEATURE_MASK_XTILE_CFG);
 	print_xstate_feature(XFEATURE_MASK_XTILE_DATA);
 }
@@ -344,6 +346,7 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
 	 XFEATURE_MASK_BNDREGS |		\
 	 XFEATURE_MASK_BNDCSR |			\
 	 XFEATURE_MASK_PASID |			\
+	 XFEATURE_MASK_CET_USER |		\
 	 XFEATURE_MASK_XTILE)
 
 /*
@@ -446,14 +449,15 @@ static void __init __xstate_dump_leaves(void)
 	}									\
 } while (0)
 
-#define XCHECK_SZ(sz, nr, nr_macro, __struct) do {			\
-	if ((nr == nr_macro) &&						\
-	    WARN_ONCE(sz != sizeof(__struct),				\
-		"%s: struct is %zu bytes, cpu state %d bytes\n",	\
-		__stringify(nr_macro), sizeof(__struct), sz)) {		\
+#define XCHECK_SZ(sz, nr, __struct) ({					\
+	if (WARN_ONCE(sz != sizeof(__struct),				\
+	    "[%s]: struct is %zu bytes, cpu state %d bytes\n",		\
+	    xfeature_names[nr], sizeof(__struct), sz)) {		\
 		__xstate_dump_leaves();					\
 	}								\
-} while (0)
+	true;								\
+})
+
 
 /**
  * check_xtile_data_against_struct - Check tile data state size.
@@ -527,36 +531,28 @@ static bool __init check_xstate_against_struct(int nr)
 	 * Ask the CPU for the size of the state.
 	 */
 	int sz = xfeature_size(nr);
+
 	/*
 	 * Match each CPU state with the corresponding software
 	 * structure.
 	 */
-	XCHECK_SZ(sz, nr, XFEATURE_YMM,       struct ymmh_struct);
-	XCHECK_SZ(sz, nr, XFEATURE_BNDREGS,   struct mpx_bndreg_state);
-	XCHECK_SZ(sz, nr, XFEATURE_BNDCSR,    struct mpx_bndcsr_state);
-	XCHECK_SZ(sz, nr, XFEATURE_OPMASK,    struct avx_512_opmask_state);
-	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);
-	XCHECK_SZ(sz, nr, XFEATURE_XTILE_CFG, struct xtile_cfg);
-
-	/* The tile data size varies between implementations. */
-	if (nr == XFEATURE_XTILE_DATA)
-		check_xtile_data_against_struct(sz);
-
-	/*
-	 * Make *SURE* to add any feature numbers in below if
-	 * there are "holes" in the xsave state component
-	 * numbers.
-	 */
-	if ((nr < XFEATURE_YMM) ||
-	    (nr >= XFEATURE_MAX) ||
-	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR) ||
-	    ((nr >= XFEATURE_RSRVD_COMP_11) && (nr <= XFEATURE_RSRVD_COMP_16))) {
+	switch (nr) {
+	case XFEATURE_YMM:	  return XCHECK_SZ(sz, nr, struct ymmh_struct);
+	case XFEATURE_BNDREGS:	  return XCHECK_SZ(sz, nr, struct mpx_bndreg_state);
+	case XFEATURE_BNDCSR:	  return XCHECK_SZ(sz, nr, struct mpx_bndcsr_state);
+	case XFEATURE_OPMASK:	  return XCHECK_SZ(sz, nr, struct avx_512_opmask_state);
+	case XFEATURE_ZMM_Hi256:  return XCHECK_SZ(sz, nr, struct avx_512_zmm_uppers_state);
+	case XFEATURE_Hi16_ZMM:	  return XCHECK_SZ(sz, nr, struct avx_512_hi16_state);
+	case XFEATURE_PKRU:	  return XCHECK_SZ(sz, nr, struct pkru_state);
+	case XFEATURE_PASID:	  return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
+	case XFEATURE_XTILE_CFG:  return XCHECK_SZ(sz, nr, struct xtile_cfg);
+	case XFEATURE_CET_USER:	  return XCHECK_SZ(sz, nr, struct cet_user_state);
+	case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
+	default:
 		XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
 		return false;
 	}
+
 	return true;
 }