Merge tag 'v5.10.28' into v5.10-rt

This is the 5.10.28 stable release

 Conflicts:
	kernel/trace/trace.c

Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

Makefile

@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 VERSION = 5
 PATCHLEVEL = 10
-SUBLEVEL = 27
+SUBLEVEL = 28
 EXTRAVERSION =
 NAME = Dare mighty things
 

arch/arm64/mm/mmu.c

@@ -1447,14 +1447,30 @@ static void __remove_pgd_mapping(pgd_t *pgdir, unsigned long start, u64 size)
 
 static bool inside_linear_region(u64 start, u64 size)
 {
+	u64 start_linear_pa = __pa(_PAGE_OFFSET(vabits_actual));
+	u64 end_linear_pa = __pa(PAGE_END - 1);
+
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
+		/*
+		 * Check for a wrap, it is possible because of randomized linear
+		 * mapping the start physical address is actually bigger than
+		 * the end physical address. In this case set start to zero
+		 * because [0, end_linear_pa] range must still be able to cover
+		 * all addressable physical addresses.
+		 */
+		if (start_linear_pa > end_linear_pa)
+			start_linear_pa = 0;
+	}
+
+	WARN_ON(start_linear_pa > end_linear_pa);
+
 	/*
 	 * Linear mapping region is the range [PAGE_OFFSET..(PAGE_END - 1)]
 	 * accommodating both its ends but excluding PAGE_END. Max physical
 	 * range which can be mapped inside this linear mapping range, must
 	 * also be derived from its end points.
 	 */
-	return start >= __pa(_PAGE_OFFSET(vabits_actual)) &&
-	       (start + size - 1) <= __pa(PAGE_END - 1);
+	return start >= start_linear_pa && (start + size - 1) <= end_linear_pa;
 }
 
 int arch_add_memory(int nid, u64 start, u64 size,

arch/riscv/include/asm/uaccess.h

@@ -306,7 +306,9 @@ do {								\
  * data types like structures or arrays.
  *
  * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
+ * to the result of dereferencing @ptr. The value of @x is copied to avoid
+ * re-ordering where @x is evaluated inside the block that enables user-space
+ * access (thus bypassing user space protection if @x is a function).
  *
  * Caller must check the pointer with access_ok() before calling this
  * function.
@@ -316,12 +318,13 @@ do {								\
 #define __put_user(x, ptr)					\
 ({								\
 	__typeof__(*(ptr)) __user *__gu_ptr = (ptr);		\
+	__typeof__(*__gu_ptr) __val = (x);			\
 	long __pu_err = 0;					\
 								\
 	__chk_user_ptr(__gu_ptr);				\
 								\
 	__enable_user_access();					\
-	__put_user_nocheck(x, __gu_ptr, __pu_err);		\
+	__put_user_nocheck(__val, __gu_ptr, __pu_err);		\
 	__disable_user_access();				\
 								\
 	__pu_err;						\

arch/s390/include/asm/vdso/data.h

@@ -6,7 +6,7 @@
 #include <vdso/datapage.h>
 
 struct arch_vdso_data {
-	__u64 tod_steering_delta;
+	__s64 tod_steering_delta;
 	__u64 tod_steering_end;
 };
 

arch/s390/kernel/time.c

@@ -398,6 +398,7 @@ static void clock_sync_global(unsigned long long delta)
 		      tod_steering_delta);
 	tod_steering_end = now + (abs(tod_steering_delta) << 15);
 	vdso_data->arch_data.tod_steering_end = tod_steering_end;
+	vdso_data->arch_data.tod_steering_delta = tod_steering_delta;
 
 	/* Update LPAR offset. */
 	if (ptff_query(PTFF_QTO) && ptff(&qto, sizeof(qto), PTFF_QTO) == 0)

arch/x86/include/asm/smp.h

@@ -132,6 +132,7 @@ void native_play_dead(void);
 void play_dead_common(void);
 void wbinvd_on_cpu(int cpu);
 int wbinvd_on_all_cpus(void);
+bool wakeup_cpu0(void);
 
 void native_smp_send_reschedule(int cpu);
 void native_send_call_func_ipi(const struct cpumask *mask);

arch/x86/kernel/acpi/boot.c

@@ -1554,10 +1554,18 @@ void __init acpi_boot_table_init(void)
 	/*
 	 * Initialize the ACPI boot-time table parser.
 	 */
-	if (acpi_table_init()) {
+	if (acpi_locate_initial_tables())
 		disable_acpi();
-		return;
-	}
+	else
+		acpi_reserve_initial_tables();
+}
+
+int __init early_acpi_boot_init(void)
+{
+	if (acpi_disabled)
+		return 1;
+
+	acpi_table_init_complete();
 
 	acpi_table_parse(ACPI_SIG_BOOT, acpi_parse_sbf);
 
@@ -1570,18 +1578,9 @@ void __init acpi_boot_table_init(void)
 		} else {
 			printk(KERN_WARNING PREFIX "Disabling ACPI support\n");
 			disable_acpi();
-			return;
+			return 1;
 		}
 	}
-}
-
-int __init early_acpi_boot_init(void)
-{
-	/*
-	 * If acpi_disabled, bail out
-	 */
-	if (acpi_disabled)
-		return 1;
 
 	/*
 	 * Process the Multiple APIC Description Table (MADT), if present

arch/x86/kernel/setup.c

@@ -1051,6 +1051,9 @@ void __init setup_arch(char **cmdline_p)
 
 	cleanup_highmap();
 
+	/* Look for ACPI tables and reserve memory occupied by them. */
+	acpi_boot_table_init();
+
 	memblock_set_current_limit(ISA_END_ADDRESS);
 	e820__memblock_setup();
 
@@ -1136,11 +1139,6 @@ void __init setup_arch(char **cmdline_p)
 
 	early_platform_quirks();
 
-	/*
-	 * Parse the ACPI tables for possible boot-time SMP configuration.
-	 */
-	acpi_boot_table_init();
-
 	early_acpi_boot_init();
 
 	initmem_init();

arch/x86/kernel/smpboot.c

@@ -1655,7 +1655,7 @@ void play_dead_common(void)
 	local_irq_disable();
 }
 
-static bool wakeup_cpu0(void)
+bool wakeup_cpu0(void)
 {
 	if (smp_processor_id() == 0 && enable_start_cpu0)
 		return true;

arch/x86/kvm/svm/nested.c

@@ -246,11 +246,18 @@ static bool nested_vmcb_check_controls(struct vmcb_control_area *control)
 	return true;
 }
 
-static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
+static bool nested_vmcb_check_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	bool vmcb12_lma;
 
+	/*
+	 * FIXME: these should be done after copying the fields,
+	 * to avoid TOC/TOU races.  For these save area checks
+	 * the possible damage is limited since kvm_set_cr0 and
+	 * kvm_set_cr4 handle failure; EFER_SVME is an exception
+	 * so it is force-set later in nested_prepare_vmcb_save.
+	 */
 	if ((vmcb12->save.efer & EFER_SVME) == 0)
 		return false;
 
@@ -271,7 +278,7 @@ static bool nested_vmcb_checks(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	if (kvm_valid_cr4(&svm->vcpu, vmcb12->save.cr4))
 		return false;
 
-	return nested_vmcb_check_controls(&vmcb12->control);
+	return true;
 }
 
 static void load_nested_vmcb_control(struct vcpu_svm *svm,
@@ -396,7 +403,14 @@ static void nested_prepare_vmcb_save(struct vcpu_svm *svm, struct vmcb *vmcb12)
 	svm->vmcb->save.gdtr = vmcb12->save.gdtr;
 	svm->vmcb->save.idtr = vmcb12->save.idtr;
 	kvm_set_rflags(&svm->vcpu, vmcb12->save.rflags);
-	svm_set_efer(&svm->vcpu, vmcb12->save.efer);
+
+	/*
+	 * Force-set EFER_SVME even though it is checked earlier on the
+	 * VMCB12, because the guest can flip the bit between the check
+	 * and now.  Clearing EFER_SVME would call svm_free_nested.
+	 */
+	svm_set_efer(&svm->vcpu, vmcb12->save.efer | EFER_SVME);
+
 	svm_set_cr0(&svm->vcpu, vmcb12->save.cr0);
 	svm_set_cr4(&svm->vcpu, vmcb12->save.cr4);
 	svm->vmcb->save.cr2 = svm->vcpu.arch.cr2 = vmcb12->save.cr2;
@@ -454,7 +468,6 @@ int enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb12_gpa,
 	int ret;
 
 	svm->nested.vmcb12_gpa = vmcb12_gpa;
-	load_nested_vmcb_control(svm, &vmcb12->control);
 	nested_prepare_vmcb_save(svm, vmcb12);
 	nested_prepare_vmcb_control(svm);
 
@@ -501,7 +514,10 @@ int nested_svm_vmrun(struct vcpu_svm *svm)
 	if (WARN_ON_ONCE(!svm->nested.initialized))
 		return -EINVAL;
 
-	if (!nested_vmcb_checks(svm, vmcb12)) {
+	load_nested_vmcb_control(svm, &vmcb12->control);
+
+	if (!nested_vmcb_check_save(svm, vmcb12) ||
+	    !nested_vmcb_check_controls(&svm->nested.ctl)) {
 		vmcb12->control.exit_code    = SVM_EXIT_ERR;
 		vmcb12->control.exit_code_hi = 0;
 		vmcb12->control.exit_info_1  = 0;
@@ -1205,6 +1221,8 @@ static int svm_set_nested_state(struct kvm_vcpu *vcpu,
 	 */
 	if (!(save->cr0 & X86_CR0_PG))
 		goto out_free;
+	if (!(save->efer & EFER_SVME))
+		goto out_free;
 
 	/*
 	 * All checks done, we can enter guest mode.  L1 control fields

arch/x86/net/bpf_jit_comp.c

@@ -1735,7 +1735,7 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
  * add rsp, 8                      // skip eth_type_trans's frame
  * ret                             // return to its caller
  */
-int arch_prepare_bpf_trampoline(void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_progs *tprogs,
 				void *orig_call)
@@ -1774,6 +1774,15 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 
 	save_regs(m, &prog, nr_args, stack_size);
 
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		/* arg1: mov rdi, im */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+		if (emit_call(&prog, __bpf_tramp_enter, prog)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
+	}
+
 	if (fentry->nr_progs)
 		if (invoke_bpf(m, &prog, fentry, stack_size))
 			return -EINVAL;
@@ -1792,8 +1801,7 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 	}
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {
-		if (fentry->nr_progs || fmod_ret->nr_progs)
-			restore_regs(m, &prog, nr_args, stack_size);
+		restore_regs(m, &prog, nr_args, stack_size);
 
 		/* call original function */
 		if (emit_call(&prog, orig_call, prog)) {
@@ -1802,6 +1810,9 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 		}
 		/* remember return value in a stack for bpf prog to access */
 		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -8);
+		im->ip_after_call = prog;
+		memcpy(prog, ideal_nops[NOP_ATOMIC5], X86_PATCH_SIZE);
+		prog += X86_PATCH_SIZE;
 	}
 
 	if (fmod_ret->nr_progs) {
@@ -1832,9 +1843,17 @@ int arch_prepare_bpf_trampoline(void *image, void *image_end,
 	 * the return value is only updated on the stack and still needs to be
 	 * restored to R0.
 	 */
-	if (flags & BPF_TRAMP_F_CALL_ORIG)
+	if (flags & BPF_TRAMP_F_CALL_ORIG) {
+		im->ip_epilogue = prog;
+		/* arg1: mov rdi, im */
+		emit_mov_imm64(&prog, BPF_REG_1, (long) im >> 32, (u32) (long) im);
+		if (emit_call(&prog, __bpf_tramp_exit, prog)) {
+			ret = -EINVAL;
+			goto cleanup;
+		}
 		/* restore original return value back into RAX */
 		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, -8);
+	}
 
 	EMIT1(0x5B); /* pop rbx */
 	EMIT1(0xC9); /* leave */

arch/xtensa/kernel/coprocessor.S

@@ -99,37 +99,6 @@
 	LOAD_CP_REGS_TAB(6)
 	LOAD_CP_REGS_TAB(7)
 
-/*
- * coprocessor_flush(struct thread_info*, index)
- *                             a2        a3
- *
- * Save coprocessor registers for coprocessor 'index'.
- * The register values are saved to or loaded from the coprocessor area 
- * inside the task_info structure.
- *
- * Note that this function doesn't update the coprocessor_owner information!
- *
- */
-
-ENTRY(coprocessor_flush)
-
-	/* reserve 4 bytes on stack to save a0 */
-	abi_entry(4)
-
-	s32i	a0, a1, 0
-	movi	a0, .Lsave_cp_regs_jump_table
-	addx8	a3, a3, a0
-	l32i	a4, a3, 4
-	l32i	a3, a3, 0
-	add	a2, a2, a4
-	beqz	a3, 1f
-	callx0	a3
-1:	l32i	a0, a1, 0
-
-	abi_ret(4)
-
-ENDPROC(coprocessor_flush)
-
 /*
  * Entry condition:
  *
@@ -245,6 +214,39 @@ ENTRY(fast_coprocessor)
 
 ENDPROC(fast_coprocessor)
 
+	.text
+
+/*
+ * coprocessor_flush(struct thread_info*, index)
+ *                             a2        a3
+ *
+ * Save coprocessor registers for coprocessor 'index'.
+ * The register values are saved to or loaded from the coprocessor area
+ * inside the task_info structure.
+ *
+ * Note that this function doesn't update the coprocessor_owner information!
+ *
+ */
+
+ENTRY(coprocessor_flush)
+
+	/* reserve 4 bytes on stack to save a0 */
+	abi_entry(4)
+
+	s32i	a0, a1, 0
+	movi	a0, .Lsave_cp_regs_jump_table
+	addx8	a3, a3, a0
+	l32i	a4, a3, 4
+	l32i	a3, a3, 0
+	add	a2, a2, a4
+	beqz	a3, 1f
+	callx0	a3
+1:	l32i	a0, a1, 0
+
+	abi_ret(4)
+
+ENDPROC(coprocessor_flush)
+
 	.data
 
 ENTRY(coprocessor_owner)

arch/xtensa/mm/fault.c

@@ -112,8 +112,11 @@ void do_page_fault(struct pt_regs *regs)
 	 */
 	fault = handle_mm_fault(vma, address, flags, regs);
 
-	if (fault_signal_pending(fault, regs))
+	if (fault_signal_pending(fault, regs)) {
+		if (!user_mode(regs))
+			goto bad_page_fault;
 		return;
+	}
 
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)