Merge tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 memory management updates from Thomas Gleixner:

 - Make LAM enablement safe vs. kernel threads using a process mm
   temporarily as switching back to the process would not update CR3 and
   therefore not enable LAM causing faults in user space when using
   tagged pointers. Cure it by synchronizing LAM enablement via IPIs to
   all CPUs which use the related mm.

 - Cure a LAM harmless inconsistency between CR3 and the state during
   context switch. It's both confusing and prone to lead to real bugs

 - Handle alt stack handling for threads which run with a non-zero
   protection key. The non-zero key prevents the kernel to access the
   alternate stack. Cure it by temporarily enabling all protection keys
   for the alternate stack setup/restore operations.

 - Provide a EFI config table identity mapping for kexec kernel to
   prevent kexec fails because the new kernel cannot access the config
   table array

 - Use GB pages only when a full GB is mapped in the identity map as
   otherwise the CPU can speculate into reserved areas after the end of
   memory which causes malfunction on UV systems.

 - Remove the noisy and pointless SRAT table dump during boot

 - Use is_ioremap_addr() for iounmap() address range checks instead of
   high_memory. is_ioremap_addr() is more precise.

* tag 'x86-mm-2024-09-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/ioremap: Improve iounmap() address range checks
  x86/mm: Remove duplicate check from build_cr3()
  x86/mm: Remove unused NX related declarations
  x86/mm: Remove unused CR3_HW_ASID_BITS
  x86/mm: Don't print out SRAT table information
  x86/mm/ident_map: Use gbpages only where full GB page should be mapped.
  x86/kexec: Add EFI config table identity mapping for kexec kernel
  selftests/mm: Add new testcases for pkeys
  x86/pkeys: Restore altstack access in sigreturn()
  x86/pkeys: Update PKRU to enable all pkeys before XSAVE
  x86/pkeys: Add helper functions to update PKRU on the sigframe
  x86/pkeys: Add PKRU as a parameter in signal handling functions
  x86/mm: Cleanup prctl_enable_tagged_addr() nr_bits error checking
  x86/mm: Fix LAM inconsistency during context switch
  x86/mm: Use IPIs to synchronize LAM enablement

3 files changed, 37 insertions, 5 deletions

diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 247f2225aa9f..1065ab995305 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -64,6 +64,16 @@ setfx:
 }
 
 /*
+ * Update the value of PKRU register that was already pushed onto the signal frame.
+ */
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
+{
+	if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
+		return 0;
+	return __put_user(pkru, (unsigned int __user *)get_xsave_addr_user(buf, XFEATURE_PKRU));
+}
+
+/*
  * Signal frame handlers.
  */
 static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
@@ -156,10 +166,17 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
 	return !err;
 }
 
-static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
+static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pkru)
 {
-	if (use_xsave())
-		return xsave_to_user_sigframe(buf);
+	int err = 0;
+
+	if (use_xsave()) {
+		err = xsave_to_user_sigframe(buf);
+		if (!err)
+			err = update_pkru_in_sigframe(buf, pkru);
+		return err;
+	}
+
 	if (use_fxsr())
 		return fxsave_to_user_sigframe((struct fxregs_state __user *) buf);
 	else
@@ -185,7 +202,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf)
  * For [f]xsave state, update the SW reserved fields in the [f]xsave frame
  * indicating the absence/presence of the extended state to the user.
  */
-bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
+bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru)
 {
 	struct task_struct *tsk = current;
 	struct fpstate *fpstate = tsk->thread.fpu.fpstate;
@@ -228,7 +245,7 @@ retry:
 		fpregs_restore_userregs();
 
 	pagefault_disable();
-	ret = copy_fpregs_to_sigframe(buf_fx);
+	ret = copy_fpregs_to_sigframe(buf_fx, pkru);
 	pagefault_enable();
 	fpregs_unlock();
 
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 53d9f01d5988..22abb5ee0cf2 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -999,6 +999,19 @@ void *get_xsave_addr(struct xregs_state *xsave, int xfeature_nr)
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
+/*
+ * Given an xstate feature nr, calculate where in the xsave buffer the state is.
+ * The xsave buffer should be in standard format, not compacted (e.g. user mode
+ * signal frames).
+ */
+void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr)
+{
+	if (WARN_ON_ONCE(!xfeature_enabled(xfeature_nr)))
+		return NULL;
+
+	return (void __user *)xsave + xstate_offsets[xfeature_nr];
+}
+
 #ifdef CONFIG_ARCH_HAS_PKEYS
 
 /*
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index afb404cd2059..0b86a5002c84 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -54,6 +54,8 @@ extern int copy_sigframe_from_user_to_xstate(struct task_struct *tsk, const void
 extern void fpu__init_cpu_xstate(void);
 extern void fpu__init_system_xstate(unsigned int legacy_size);
 
+extern void __user *get_xsave_addr_user(struct xregs_state __user *xsave, int xfeature_nr);
+
 static inline u64 xfeatures_mask_supervisor(void)
 {
 	return fpu_kernel_cfg.max_features & XFEATURE_MASK_SUPERVISOR_SUPPORTED;