8 files changed, 129 insertions, 84 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2a7c3afa62e2..8ef4369a4f06 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -90,7 +90,6 @@ obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-y				+= apic/
 obj-$(CONFIG_X86_REBOOTFIXUPS)	+= reboot_fixups_32.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
-obj-$(CONFIG_LIVEPATCH)	+= livepatch.o
 obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace_$(BITS).o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
 obj-$(CONFIG_FTRACE_SYSCALLS)	+= ftrace.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 7867dfb3963e..cd617979b7fc 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -783,6 +783,61 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
 	}
 }
 
+typedef struct {
+	struct mm_struct *mm;
+} temp_mm_state_t;
+
+/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down.
+ *
+ * Context: The temporary mm needs to be used exclusively by a single core. To
+ *          harden security IRQs must be disabled while the temporary mm is
+ *          loaded, thereby preventing interrupt handler bugs from overriding
+ *          the kernel memory protection.
+ */
+static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
+{
+	temp_mm_state_t temp_state;
+
+	lockdep_assert_irqs_disabled();
+	temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+	switch_mm_irqs_off(NULL, mm, current);
+
+	/*
+	 * If breakpoints are enabled, disable them while the temporary mm is
+	 * used. Userspace might set up watchpoints on addresses that are used
+	 * in the temporary mm, which would lead to wrong signals being sent or
+	 * crashes.
+	 *
+	 * Note that breakpoints are not disabled selectively, which also causes
+	 * kernel breakpoints (e.g., perf's) to be disabled. This might be
+	 * undesirable, but still seems reasonable as the code that runs in the
+	 * temporary mm should be short.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_disable();
+
+	return temp_state;
+}
+
+static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
+{
+	lockdep_assert_irqs_disabled();
+	switch_mm_irqs_off(NULL, prev_state.mm, current);
+
+	/*
+	 * Restore the breakpoints if they were disabled before the temporary mm
+	 * was loaded.
+	 */
+	if (hw_breakpoint_active())
+		hw_breakpoint_restore();
+}
+
 __ro_after_init struct mm_struct *poking_mm;
 __ro_after_init unsigned long poking_addr;
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index d07809286b95..74682b8d09b0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -387,7 +387,30 @@ set_register:
 			  bits_missing);
 	}
 }
-EXPORT_SYMBOL(native_write_cr4);
+#if IS_MODULE(CONFIG_LKDTM)
+EXPORT_SYMBOL_GPL(native_write_cr4);
+#endif
+
+void cr4_update_irqsoff(unsigned long set, unsigned long clear)
+{
+	unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4);
+
+	lockdep_assert_irqs_disabled();
+
+	newval = (cr4 & ~clear) | set;
+	if (newval != cr4) {
+		this_cpu_write(cpu_tlbstate.cr4, newval);
+		__write_cr4(newval);
+	}
+}
+EXPORT_SYMBOL(cr4_update_irqsoff);
+
+/* Read the CR4 shadow. */
+unsigned long cr4_read_shadow(void)
+{
+	return this_cpu_read(cpu_tlbstate.cr4);
+}
+EXPORT_SYMBOL_GPL(cr4_read_shadow);
 
 void cr4_init(void)
 {
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 51b9190c628b..23ad8e953dfb 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -761,7 +761,7 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Flush all TLBs via a mov %cr3, %reg; mov %reg, %cr3 */
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
+	flush_tlb_local();
 
 	/* Save MTRR state */
 	rdmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
@@ -778,7 +778,7 @@ static void post_set(void) __releases(set_atomicity_lock)
 {
 	/* Flush TLBs (no need to flush caches - they are disabled) */
 	count_vm_tlb_event(NR_TLB_LOCAL_FLUSH_ALL);
-	__flush_tlb();
+	flush_tlb_local();
 
 	/* Intel (P6) standard MTRRs */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo, deftype_hi);
diff --git a/arch/x86/kernel/livepatch.c b/arch/x86/kernel/livepatch.c
deleted file mode 100644
index 6a68e41206e7..000000000000
--- a/arch/x86/kernel/livepatch.c
+++ /dev/null
@@ -1,53 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * livepatch.c - x86-specific Kernel Live Patching Core
- */
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/livepatch.h>
-#include <asm/text-patching.h>
-
-/* Apply per-object alternatives. Based on x86 module_finalize() */
-void arch_klp_init_object_loaded(struct klp_patch *patch,
-				 struct klp_object *obj)
-{
-	int cnt;
-	struct klp_modinfo *info;
-	Elf_Shdr *s, *alt = NULL, *para = NULL;
-	void *aseg, *pseg;
-	const char *objname;
-	char sec_objname[MODULE_NAME_LEN];
-	char secname[KSYM_NAME_LEN];
-
-	info = patch->mod->klp_info;
-	objname = obj->name ? obj->name : "vmlinux";
-
-	/* See livepatch core code for BUILD_BUG_ON() explanation */
-	BUILD_BUG_ON(MODULE_NAME_LEN < 56 || KSYM_NAME_LEN != 128);
-
-	for (s = info->sechdrs; s < info->sechdrs + info->hdr.e_shnum; s++) {
-		/* Apply per-object .klp.arch sections */
-		cnt = sscanf(info->secstrings + s->sh_name,
-			     ".klp.arch.%55[^.].%127s",
-			     sec_objname, secname);
-		if (cnt != 2)
-			continue;
-		if (strcmp(sec_objname, objname))
-			continue;
-		if (!strcmp(".altinstructions", secname))
-			alt = s;
-		if (!strcmp(".parainstructions", secname))
-			para = s;
-	}
-
-	if (alt) {
-		aseg = (void *) alt->sh_addr;
-		apply_alternatives(aseg, aseg + alt->sh_size);
-	}
-
-	if (para) {
-		pseg = (void *) para->sh_addr;
-		apply_paravirt(pseg, pseg + para->sh_size);
-	}
-}
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d5c72cb877b3..23c95a53d20e 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -18,6 +18,7 @@
 #include <linux/gfp.h>
 #include <linux/jump_label.h>
 #include <linux/random.h>
+#include <linux/memory.h>
 
 #include <asm/text-patching.h>
 #include <asm/page.h>
@@ -126,11 +127,12 @@ int apply_relocate(Elf32_Shdr *sechdrs,
 	return 0;
 }
 #else /*X86_64*/
-int apply_relocate_add(Elf64_Shdr *sechdrs,
+static int __apply_relocate_add(Elf64_Shdr *sechdrs,
 		   const char *strtab,
 		   unsigned int symindex,
 		   unsigned int relsec,
-		   struct module *me)
+		   struct module *me,
+		   void *(*write)(void *dest, const void *src, size_t len))
 {
 	unsigned int i;
 	Elf64_Rela *rel = (void *)sechdrs[relsec].sh_addr;
@@ -162,19 +164,19 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 		case R_X86_64_64:
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		case R_X86_64_32:
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 			if (val != *(u32 *)loc)
 				goto overflow;
 			break;
 		case R_X86_64_32S:
 			if (*(s32 *)loc != 0)
 				goto invalid_relocation;
-			*(s32 *)loc = val;
+			write(loc, &val, 4);
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
 			break;
@@ -183,7 +185,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u32 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u32 *)loc = val;
+			write(loc, &val, 4);
 #if 0
 			if ((s64)val != *(s32 *)loc)
 				goto overflow;
@@ -193,7 +195,7 @@ int apply_relocate_add(Elf64_Shdr *sechdrs,
 			if (*(u64 *)loc != 0)
 				goto invalid_relocation;
 			val -= (u64)loc;
-			*(u64 *)loc = val;
+			write(loc, &val, 8);
 			break;
 		default:
 			pr_err("%s: Unknown rela relocation: %llu\n",
@@ -215,6 +217,33 @@ overflow:
 	       me->name);
 	return -ENOEXEC;
 }
+
+int apply_relocate_add(Elf64_Shdr *sechdrs,
+		   const char *strtab,
+		   unsigned int symindex,
+		   unsigned int relsec,
+		   struct module *me)
+{
+	int ret;
+	bool early = me->state == MODULE_STATE_UNFORMED;
+	void *(*write)(void *, const void *, size_t) = memcpy;
+
+	if (!early) {
+		write = text_poke;
+		mutex_lock(&text_mutex);
+	}
+
+	ret = __apply_relocate_add(sechdrs, strtab, symindex, relsec, me,
+				   write);
+
+	if (!early) {
+		text_poke_sync();
+		mutex_unlock(&text_mutex);
+	}
+
+	return ret;
+}
+
 #endif
 
 int module_finalize(const Elf_Ehdr *hdr,
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c131ba4e70ef..5638e4ae2ea6 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -160,25 +160,6 @@ unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
 	return insn_len;
 }
 
-static void native_flush_tlb(void)
-{
-	__native_flush_tlb();
-}
-
-/*
- * Global pages have to be flushed a bit differently. Not a real
- * performance problem because this does not happen often.
- */
-static void native_flush_tlb_global(void)
-{
-	__native_flush_tlb_global();
-}
-
-static void native_flush_tlb_one_user(unsigned long addr)
-{
-	__native_flush_tlb_one_user(addr);
-}
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -359,7 +340,7 @@ struct paravirt_patch_template pv_ops = {
 #endif /* CONFIG_PARAVIRT_XXL */
 
 	/* Mmu ops. */
-	.mmu.flush_tlb_user	= native_flush_tlb,
+	.mmu.flush_tlb_user	= native_flush_tlb_local,
 	.mmu.flush_tlb_kernel	= native_flush_tlb_global,
 	.mmu.flush_tlb_one_user	= native_flush_tlb_one_user,
 	.mmu.flush_tlb_others	= native_flush_tlb_others,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ce6cd220f722..8e3d0347b664 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -612,6 +612,17 @@ void speculation_ctrl_update_current(void)
 	preempt_enable();
 }
 
+static inline void cr4_toggle_bits_irqsoff(unsigned long mask)
+{
+	unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4);
+
+	newval = cr4 ^ mask;
+	if (newval != cr4) {
+		this_cpu_write(cpu_tlbstate.cr4, newval);
+		__write_cr4(newval);
+	}
+}
+
 void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	unsigned long tifp, tifn;