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

Author: torvalds

arch/x86/include/asm/fpu/signal.h

@@ -29,7 +29,7 @@ fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
 
 unsigned long fpu__get_fpstate_size(void);
 
-extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size);
+extern bool copy_fpstate_to_sigframe(void __user *buf, void __user *fp, int size, u32 pkru);
 extern void fpu__clear_user_states(struct fpu *fpu);
 extern bool fpu__restore_sig(void __user *buf, int ia32_frame);
 

arch/x86/include/asm/mmu_context.h

@@ -88,7 +88,13 @@ static inline void switch_ldt(struct mm_struct *prev, struct mm_struct *next)
 #ifdef CONFIG_ADDRESS_MASKING
 static inline unsigned long mm_lam_cr3_mask(struct mm_struct *mm)
 {
-	return mm->context.lam_cr3_mask;
+	/*
+	 * When switch_mm_irqs_off() is called for a kthread, it may race with
+	 * LAM enablement. switch_mm_irqs_off() uses the LAM mask to do two
+	 * things: populate CR3 and populate 'cpu_tlbstate.lam'. Make sure it
+	 * reads a single value for both.
+	 */
+	return READ_ONCE(mm->context.lam_cr3_mask);
 }
 
 static inline void dup_lam(struct mm_struct *oldmm, struct mm_struct *mm)

arch/x86/include/asm/pgtable_types.h

@@ -517,8 +517,6 @@ typedef struct page *pgtable_t;
 
 extern pteval_t __supported_pte_mask;
 extern pteval_t __default_kernel_pte_mask;
-extern void set_nx(void);
-extern int nx_enabled;
 
 #define pgprot_writecombine	pgprot_writecombine
 extern pgprot_t pgprot_writecombine(pgprot_t prot);

arch/x86/include/asm/tlbflush.h

@@ -399,11 +399,10 @@ static inline  u64 tlbstate_lam_cr3_mask(void)
 	return lam << X86_CR3_LAM_U57_BIT;
 }
 
-static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask)
 {
-	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);
+	this_cpu_write(cpu_tlbstate.lam, lam >> X86_CR3_LAM_U57_BIT);
+	this_cpu_write(tlbstate_untag_mask, untag_mask);
 }
 
 #else
@@ -413,7 +412,7 @@ static inline u64 tlbstate_lam_cr3_mask(void)
 	return 0;
 }
 
-static inline void set_tlbstate_lam_mode(struct mm_struct *mm)
+static inline void cpu_tlbstate_update_lam(unsigned long lam, u64 untag_mask)
 {
 }
 #endif

arch/x86/kernel/fpu/signal.c

@@ -63,6 +63,16 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
 	return true;
 }
 
+/*
+ * 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.
  */
@@ -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 @@ bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size)
 		fpregs_restore_userregs();
 
 	pagefault_disable();
-	ret = copy_fpregs_to_sigframe(buf_fx);
+	ret = copy_fpregs_to_sigframe(buf_fx, pkru);
 	pagefault_enable();
 	fpregs_unlock();
 

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
 
 /*

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;

arch/x86/kernel/machine_kexec_64.c

@@ -28,6 +28,7 @@
 #include <asm/setup.h>
 #include <asm/set_memory.h>
 #include <asm/cpu.h>
+#include <asm/efi.h>
 
 #ifdef CONFIG_ACPI
 /*
@@ -87,6 +88,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
 {
 #ifdef CONFIG_EFI
 	unsigned long mstart, mend;
+	void *kaddr;
+	int ret;
 
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
@@ -102,6 +105,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p)
 	if (!mstart)
 		return 0;
 
+	ret = kernel_ident_mapping_init(info, level4p, mstart, mend);
+	if (ret)
+		return ret;
+
+	kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB);
+	if (!kaddr) {
+		pr_err("Could not map UEFI system table\n");
+		return -ENOMEM;
+	}
+
+	mstart = efi_config_table;
+
+	if (efi_enabled(EFI_64BIT)) {
+		efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr;
+
+		mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables;
+	} else {
+		efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr;
+
+		mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables;
+	}
+
+	memunmap(kaddr);
+
 	return kernel_ident_mapping_init(info, level4p, mstart, mend);
 #endif
 	return 0;

arch/x86/kernel/process_64.c

@@ -798,6 +798,32 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
 
 #define LAM_U57_BITS 6
 
+static void enable_lam_func(void *__mm)
+{
+	struct mm_struct *mm = __mm;
+	unsigned long lam;
+
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) {
+		lam = mm_lam_cr3_mask(mm);
+		write_cr3(__read_cr3() | lam);
+		cpu_tlbstate_update_lam(lam, mm_untag_mask(mm));
+	}
+}
+
+static void mm_enable_lam(struct mm_struct *mm)
+{
+	mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
+	mm->context.untag_mask =  ~GENMASK(62, 57);
+
+	/*
+	 * Even though the process must still be single-threaded at this
+	 * point, kernel threads may be using the mm.  IPI those kernel
+	 * threads if they exist.
+	 */
+	on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true);
+	set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
+}
+
 static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 {
 	if (!cpu_feature_enabled(X86_FEATURE_LAM))
@@ -814,25 +840,21 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
 	if (mmap_write_lock_killable(mm))
 		return -EINTR;
 
+	/*
+	 * MM_CONTEXT_LOCK_LAM is set on clone.  Prevent LAM from
+	 * being enabled unless the process is single threaded:
+	 */
 	if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) {
 		mmap_write_unlock(mm);
 		return -EBUSY;
 	}
 
-	if (!nr_bits) {
-		mmap_write_unlock(mm);
-		return -EINVAL;
-	} else if (nr_bits <= LAM_U57_BITS) {
-		mm->context.lam_cr3_mask = X86_CR3_LAM_U57;
-		mm->context.untag_mask =  ~GENMASK(62, 57);
-	} else {
+	if (!nr_bits || nr_bits > LAM_U57_BITS) {
 		mmap_write_unlock(mm);
 		return -EINVAL;
 	}
 
-	write_cr3(__read_cr3() | mm->context.lam_cr3_mask);
-	set_tlbstate_lam_mode(mm);
-	set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
+	mm_enable_lam(mm);
 
 	mmap_write_unlock(mm);
 

arch/x86/kernel/signal.c

@@ -60,6 +60,24 @@ static inline int is_x32_frame(struct ksignal *ksig)
 		ksig->ka.sa.sa_flags & SA_X32_ABI;
 }
 
+/*
+ * Enable all pkeys temporarily, so as to ensure that both the current
+ * execution stack as well as the alternate signal stack are writeable.
+ * The application can use any of the available pkeys to protect the
+ * alternate signal stack, and we don't know which one it is, so enable
+ * all. The PKRU register will be reset to init_pkru later in the flow,
+ * in fpu__clear_user_states(), and it is the application's responsibility
+ * to enable the appropriate pkey as the first step in the signal handler
+ * so that the handler does not segfault.
+ */
+static inline u32 sig_prepare_pkru(void)
+{
+	u32 orig_pkru = read_pkru();
+
+	write_pkru(0);
+	return orig_pkru;
+}
+
 /*
  * Set up a signal frame.
  */
@@ -84,6 +102,7 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size,
 	unsigned long math_size = 0;
 	unsigned long sp = regs->sp;
 	unsigned long buf_fx = 0;
+	u32 pkru;
 
 	/* redzone */
 	if (!ia32_frame)
@@ -138,9 +157,17 @@ get_sigframe(struct ksignal *ksig, struct pt_regs *regs, size_t frame_size,
 		return (void __user *)-1L;
 	}
 
+	/* Update PKRU to enable access to the alternate signal stack. */
+	pkru = sig_prepare_pkru();
 	/* save i387 and extended state */
-	if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size))
+	if (!copy_fpstate_to_sigframe(*fpstate, (void __user *)buf_fx, math_size, pkru)) {
+		/*
+		 * Restore PKRU to the original, user-defined value; disable
+		 * extra pkeys enabled for the alternate signal stack, if any.
+		 */
+		write_pkru(pkru);
 		return (void __user *)-1L;
+	}
 
 	return (void __user *)sp;
 }