Merge tag 'x86-urgent-2024-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull misc x86 fixes from Ingo Molnar:

 - Remove the broken vsyscall emulation code from
   the page fault code

 - Fix kexec crash triggered by certain SEV RMP
   table layouts

 - Fix unchecked MSR access error when disabling
   the x2APIC via iommu=off

* tag 'x86-urgent-2024-05-05' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/mm: Remove broken vsyscall emulation code from the page fault code
  x86/apic: Don't access the APIC when disabling x2APIC
  x86/sev: Add callback to apply RMP table fixups for kexec
  x86/e820: Add a new e820 table update helper

arch/x86/entry/vsyscall/vsyscall_64.c

@@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr)
 
 static bool write_ok_or_segv(unsigned long ptr, size_t size)
 {
-	/*
-	 * XXX: if access_ok, get_user, and put_user handled
-	 * sig_on_uaccess_err, this could go away.
-	 */
-
 	if (!access_ok((void __user *)ptr, size)) {
 		struct thread_struct *thread = &current->thread;
 
@@ -120,10 +115,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size)
 bool emulate_vsyscall(unsigned long error_code,
 		      struct pt_regs *regs, unsigned long address)
 {
-	struct task_struct *tsk;
 	unsigned long caller;
 	int vsyscall_nr, syscall_nr, tmp;
-	int prev_sig_on_uaccess_err;
 	long ret;
 	unsigned long orig_dx;
 
@@ -172,8 +165,6 @@ bool emulate_vsyscall(unsigned long error_code,
 		goto sigsegv;
 	}
 
-	tsk = current;
-
 	/*
 	 * Check for access_ok violations and find the syscall nr.
 	 *
@@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code,
 		goto do_ret;  /* skip requested */
 
 	/*
-	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
-	 * preserve that behavior to make writing exploits harder.
+	 * With a real vsyscall, page faults cause SIGSEGV.
 	 */
-	prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
-	current->thread.sig_on_uaccess_err = 1;
-
 	ret = -EFAULT;
 	switch (vsyscall_nr) {
 	case 0:
@@ -262,23 +249,12 @@ bool emulate_vsyscall(unsigned long error_code,
 		break;
 	}
 
-	current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
-
 check_fault:
 	if (ret == -EFAULT) {
 		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
 		warn_bad_vsyscall(KERN_INFO, regs,
 				  "vsyscall fault (exploit attempt?)");
-
-		/*
-		 * If we failed to generate a signal for any reason,
-		 * generate one here.  (This should be impossible.)
-		 */
-		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
-				 !sigismember(&tsk->pending.signal, SIGSEGV)))
 		goto sigsegv;
-
-		return true;  /* Don't emulate the ret. */
 	}
 
 	regs->ax = ret;

arch/x86/include/asm/e820/api.h

@@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type);
 extern void e820__range_add   (u64 start, u64 size, enum e820_type type);
 extern u64  e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
 extern u64  e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type);
+extern u64  e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type);
 
 extern void e820__print_table(char *who);
 extern int  e820__update_table(struct e820_table *table);

arch/x86/include/asm/processor.h

@@ -472,7 +472,6 @@ struct thread_struct {
 	unsigned long		iopl_emul;
 
 	unsigned int		iopl_warn:1;
-	unsigned int		sig_on_uaccess_err:1;
 
 	/*
 	 * Protection Keys Register for Userspace.  Loaded immediately on

arch/x86/include/asm/sev.h

@@ -269,6 +269,7 @@ int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immut
 int rmp_make_shared(u64 pfn, enum pg_level level);
 void snp_leak_pages(u64 pfn, unsigned int npages);
 void kdump_sev_callback(void);
+void snp_fixup_e820_tables(void);
 #else
 static inline bool snp_probe_rmptable_info(void) { return false; }
 static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; }
@@ -282,6 +283,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as
 static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; }
 static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
 static inline void kdump_sev_callback(void) { }
+static inline void snp_fixup_e820_tables(void) {}
 #endif
 
 #endif

arch/x86/kernel/apic/apic.c

@@ -1771,7 +1771,7 @@ void x2apic_setup(void)
 	__x2apic_enable();
 }
 
-static __init void apic_set_fixmap(void);
+static __init void apic_set_fixmap(bool read_apic);
 
 static __init void x2apic_disable(void)
 {
@@ -1793,7 +1793,12 @@ static __init void x2apic_disable(void)
 	}
 
 	__x2apic_disable();
-	apic_set_fixmap();
+	/*
+	 * Don't reread the APIC ID as it was already done from
+	 * check_x2apic() and the APIC driver still is a x2APIC variant,
+	 * which fails to do the read after x2APIC was disabled.
+	 */
+	apic_set_fixmap(false);
 }
 
 static __init void x2apic_enable(void)
@@ -2057,12 +2062,13 @@ void __init init_apic_mappings(void)
 	}
 }
 
-static __init void apic_set_fixmap(void)
+static __init void apic_set_fixmap(bool read_apic)
 {
 	set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr);
 	apic_mmio_base = APIC_BASE;
 	apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n",
 		    apic_mmio_base, mp_lapic_addr);
+	if (read_apic)
 		apic_read_boot_cpu_id(false);
 }
 
@@ -2073,7 +2079,7 @@ void __init register_lapic_address(unsigned long address)
 	mp_lapic_addr = address;
 
 	if (!x2apic_mode)
-		apic_set_fixmap();
+		apic_set_fixmap(true);
 }
 
 /*

arch/x86/kernel/e820.c

@@ -532,9 +532,10 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum
 	return __e820__range_update(e820_table, start, size, old_type, new_type);
 }
 
-static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type  new_type)
+u64 __init e820__range_update_table(struct e820_table *t, u64 start, u64 size,
+				    enum e820_type old_type, enum e820_type new_type)
 {
-	return __e820__range_update(e820_table_kexec, start, size, old_type, new_type);
+	return __e820__range_update(t, start, size, old_type, new_type);
 }
 
 /* Remove a range of memory from the E820 table: */
@@ -806,7 +807,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align)
 
 	addr = memblock_phys_alloc(size, align);
 	if (addr) {
-		e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		e820__range_update_table(e820_table_kexec, addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED);
 		pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n");
 		e820__update_table_kexec();
 	}

arch/x86/mm/fault.c

@@ -723,40 +723,9 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code,
 	WARN_ON_ONCE(user_mode(regs));
 
 	/* Are we prepared to handle this kernel fault? */
-	if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) {
-		/*
-		 * Any interrupt that takes a fault gets the fixup. This makes
-		 * the below recursive fault logic only apply to a faults from
-		 * task context.
-		 */
-		if (in_interrupt())
+	if (fixup_exception(regs, X86_TRAP_PF, error_code, address))
 		return;
 
-		/*
-		 * Per the above we're !in_interrupt(), aka. task context.
-		 *
-		 * In this case we need to make sure we're not recursively
-		 * faulting through the emulate_vsyscall() logic.
-		 */
-		if (current->thread.sig_on_uaccess_err && signal) {
-			sanitize_error_code(address, &error_code);
-
-			set_signal_archinfo(address, error_code);
-
-			if (si_code == SEGV_PKUERR) {
-				force_sig_pkuerr((void __user *)address, pkey);
-			} else {
-				/* XXX: hwpoison faults will set the wrong code. */
-				force_sig_fault(signal, si_code, (void __user *)address);
-			}
-		}
-
-		/*
-		 * Barring that, we can do the fixup and be happy.
-		 */
-		return;
-	}
-
 	/*
 	 * AMD erratum #91 manifests as a spurious page fault on a PREFETCH
 	 * instruction.

arch/x86/mm/mem_encrypt.c

@@ -102,6 +102,13 @@ void __init mem_encrypt_setup_arch(void)
 	phys_addr_t total_mem = memblock_phys_mem_size();
 	unsigned long size;
 
+	/*
+	 * Do RMP table fixups after the e820 tables have been setup by
+	 * e820__memory_setup().
+	 */
+	if (cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+		snp_fixup_e820_tables();
+
 	if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT))
 		return;
 

arch/x86/virt/svm/sev.c

@@ -163,6 +163,42 @@ bool snp_probe_rmptable_info(void)
 	return true;
 }
 
+static void __init __snp_fixup_e820_tables(u64 pa)
+{
+	if (IS_ALIGNED(pa, PMD_SIZE))
+		return;
+
+	/*
+	 * Handle cases where the RMP table placement by the BIOS is not
+	 * 2M aligned and the kexec kernel could try to allocate
+	 * from within that chunk which then causes a fatal RMP fault.
+	 *
+	 * The e820_table needs to be updated as it is converted to
+	 * kernel memory resources and used by KEXEC_FILE_LOAD syscall
+	 * to load kexec segments.
+	 *
+	 * The e820_table_firmware needs to be updated as it is exposed
+	 * to sysfs and used by the KEXEC_LOAD syscall to load kexec
+	 * segments.
+	 *
+	 * The e820_table_kexec needs to be updated as it passed to
+	 * the kexec-ed kernel.
+	 */
+	pa = ALIGN_DOWN(pa, PMD_SIZE);
+	if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) {
+		pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa);
+		e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+		e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED);
+	}
+}
+
+void __init snp_fixup_e820_tables(void)
+{
+	__snp_fixup_e820_tables(probed_rmp_base);
+	__snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size);
+}
+
 /*
  * Do the necessary preparations which are verified by the firmware as
  * described in the SNP_INIT_EX firmware command description in the SNP