Merge tag 'loongarch-kvm-6.10' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.10

1. Add ParaVirt IPI support.
2. Add software breakpoint support.
3. Add mmio trace events support.

61 files changed, 778 insertions, 386 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 4fff6ed46e90..928820e61cb5 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -62,6 +62,7 @@ config X86
 	select ACPI_HOTPLUG_CPU			if ACPI_PROCESSOR && HOTPLUG_CPU
 	select ARCH_32BIT_OFF_T			if X86_32
 	select ARCH_CLOCKSOURCE_INIT
+	select ARCH_CONFIGURES_CPU_MITIGATIONS
 	select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE
 	select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION
 	select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64
@@ -2488,17 +2489,21 @@ config PREFIX_SYMBOLS
 	def_bool y
 	depends on CALL_PADDING && !CFI_CLANG
 
-menuconfig SPECULATION_MITIGATIONS
-	bool "Mitigations for speculative execution vulnerabilities"
+menuconfig CPU_MITIGATIONS
+	bool "Mitigations for CPU vulnerabilities"
 	default y
 	help
-	  Say Y here to enable options which enable mitigations for
-	  speculative execution hardware vulnerabilities.
+	  Say Y here to enable options which enable mitigations for hardware
+	  vulnerabilities (usually related to speculative execution).
+	  Mitigations can be disabled or restricted to SMT systems at runtime
+	  via the "mitigations" kernel parameter.
 
-	  If you say N, all mitigations will be disabled. You really
-	  should know what you are doing to say so.
+	  If you say N, all mitigations will be disabled.  This CANNOT be
+	  overridden at runtime.
 
-if SPECULATION_MITIGATIONS
+	  Say 'Y', unless you really know what you are doing.
+
+if CPU_MITIGATIONS
 
 config MITIGATION_PAGE_TABLE_ISOLATION
 	bool "Remove the kernel mapping in user mode"
@@ -2633,6 +2638,16 @@ config MITIGATION_RFDS
 	  stored in floating point, vector and integer registers.
 	  See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst>
 
+config MITIGATION_SPECTRE_BHI
+	bool "Mitigate Spectre-BHB (Branch History Injection)"
+	depends on CPU_SUP_INTEL
+	default y
+	help
+	  Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks
+	  where the branch history buffer is poisoned to speculatively steer
+	  indirect branches.
+	  See <file:Documentation/admin-guide/hw-vuln/spectre.rst>
+
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 6356060caaf3..51cc9c7cb9bd 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
 
 	if (likely(unr < NR_syscalls)) {
 		unr = array_index_nospec(unr, NR_syscalls);
-		regs->ax = sys_call_table[unr](regs);
+		regs->ax = x64_sys_call(regs, unr);
 		return true;
 	}
 	return false;
@@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr)
 
 	if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) {
 		xnr = array_index_nospec(xnr, X32_NR_syscalls);
-		regs->ax = x32_sys_call_table[xnr](regs);
+		regs->ax = x32_sys_call(regs, xnr);
 		return true;
 	}
 	return false;
@@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr)
 
 	if (likely(unr < IA32_NR_syscalls)) {
 		unr = array_index_nospec(unr, IA32_NR_syscalls);
-		regs->ax = ia32_sys_call_table[unr](regs);
+		regs->ax = ia32_sys_call(regs, unr);
 	} else if (nr != -1) {
 		regs->ax = __ia32_sys_ni_syscall(regs);
 	}
@@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void)
 }
 
 /**
- * int80_emulation - 32-bit legacy syscall entry
+ * do_int80_emulation - 32-bit legacy syscall C entry from asm
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in
@@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void)
  *   eax:				system call number
  *   ebx, ecx, edx, esi, edi, ebp:	arg1 - arg 6
  */
-DEFINE_IDTENTRY_RAW(int80_emulation)
+__visible noinstr void do_int80_emulation(struct pt_regs *regs)
 {
 	int nr;
 
@@ -255,6 +255,71 @@ DEFINE_IDTENTRY_RAW(int80_emulation)
 	instrumentation_end();
 	syscall_exit_to_user_mode(regs);
 }
+
+#ifdef CONFIG_X86_FRED
+/*
+ * A FRED-specific INT80 handler is warranted for the follwing reasons:
+ *
+ * 1) As INT instructions and hardware interrupts are separate event
+ *    types, FRED does not preclude the use of vector 0x80 for external
+ *    interrupts. As a result, the FRED setup code does not reserve
+ *    vector 0x80 and calling int80_is_external() is not merely
+ *    suboptimal but actively incorrect: it could cause a system call
+ *    to be incorrectly ignored.
+ *
+ * 2) It is called only for handling vector 0x80 of event type
+ *    EVENT_TYPE_SWINT and will never be called to handle any external
+ *    interrupt (event type EVENT_TYPE_EXTINT).
+ *
+ * 3) FRED has separate entry flows depending on if the event came from
+ *    user space or kernel space, and because the kernel does not use
+ *    INT insns, the FRED kernel entry handler fred_entry_from_kernel()
+ *    falls through to fred_bad_type() if the event type is
+ *    EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling
+ *    an INT insn, it can only be from a user level.
+ *
+ * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will
+ *    likely take a different approach if it is ever needed: it
+ *    probably belongs in either fred_intx()/ fred_other() or
+ *    asm_fred_entrypoint_user(), depending on if this ought to be done
+ *    for all entries from userspace or only system
+ *    calls.
+ *
+ * 5) INT $0x80 is the fast path for 32-bit system calls under FRED.
+ */
+DEFINE_FREDENTRY_RAW(int80_emulation)
+{
+	int nr;
+
+	enter_from_user_mode(regs);
+
+	instrumentation_begin();
+	add_random_kstack_offset();
+
+	/*
+	 * FRED pushed 0 into regs::orig_ax and regs::ax contains the
+	 * syscall number.
+	 *
+	 * User tracing code (ptrace or signal handlers) might assume
+	 * that the regs::orig_ax contains a 32-bit number on invoking
+	 * a 32-bit syscall.
+	 *
+	 * Establish the syscall convention by saving the 32bit truncated
+	 * syscall number in regs::orig_ax and by invalidating regs::ax.
+	 */
+	regs->orig_ax = regs->ax & GENMASK(31, 0);
+	regs->ax = -ENOSYS;
+
+	nr = syscall_32_enter(regs);
+
+	local_irq_enable();
+	nr = syscall_enter_from_user_mode_work(regs, nr);
+	do_syscall_32_irqs_on(regs, nr);
+
+	instrumentation_end();
+	syscall_exit_to_user_mode(regs);
+}
+#endif
 #else /* CONFIG_IA32_EMULATION */
 
 /* Handles int $0x80 on a 32bit kernel */
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8af2a26b24f6..1b5be07f8669 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL)
 	/* clobbers %rax, make sure it is after saving the syscall nr */
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	call	do_syscall_64		/* returns with IRQs disabled */
 
@@ -1491,3 +1492,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead)
 	call	make_task_dead
 SYM_CODE_END(rewind_stack_and_make_dead)
 .popsection
+
+/*
+ * This sequence executes branches in order to remove user branch information
+ * from the branch history tracker in the Branch Predictor, therefore removing
+ * user influence on subsequent BTB lookups.
+ *
+ * It should be used on parts prior to Alder Lake. Newer parts should use the
+ * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being
+ * virtualized on newer hardware the VMM should protect against BHI attacks by
+ * setting BHI_DIS_S for the guests.
+ *
+ * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging
+ * and not clearing the branch history. The call tree looks like:
+ *
+ * call 1
+ *    call 2
+ *      call 2
+ *        call 2
+ *          call 2
+ * 	      call 2
+ * 	      ret
+ * 	    ret
+ *        ret
+ *      ret
+ *    ret
+ * ret
+ *
+ * This means that the stack is non-constant and ORC can't unwind it with %rsp
+ * alone.  Therefore we unconditionally set up the frame pointer, which allows
+ * ORC to unwind properly.
+ *
+ * The alignment is for performance and not for safety, and may be safely
+ * refactored in the future if needed.
+ */
+SYM_FUNC_START(clear_bhb_loop)
+	push	%rbp
+	mov	%rsp, %rbp
+	movl	$5, %ecx
+	ANNOTATE_INTRA_FUNCTION_CALL
+	call	1f
+	jmp	5f
+	.align 64, 0xcc
+	ANNOTATE_INTRA_FUNCTION_CALL
+1:	call	2f
+	RET
+	.align 64, 0xcc
+2:	movl	$5, %eax
+3:	jmp	4f
+	nop
+4:	sub	$1, %eax
+	jnz	3b
+	sub	$1, %ecx
+	jnz	1b
+	RET
+5:	lfence
+	pop	%rbp
+	RET
+SYM_FUNC_END(clear_bhb_loop)
+EXPORT_SYMBOL_GPL(clear_bhb_loop)
+STACK_FRAME_NON_STANDARD(clear_bhb_loop)
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index eabf48c4d4b4..c779046cc3fe 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL)
 
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT and AC
@@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL)
 
 	IBRS_ENTER
 	UNTRAIN_RET
+	CLEAR_BRANCH_HISTORY
 
 	movq	%rsp, %rdi
 	call	do_fast_syscall_32
@@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
 	int3
 SYM_CODE_END(entry_SYSCALL_compat)
+
+/*
+ * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries
+ * point to C routines, however since this is a system call interface the branch
+ * history needs to be scrubbed to protect against BHI attacks, and that
+ * scrubbing needs to take place in assembly code prior to entering any C
+ * routines.
+ */
+SYM_CODE_START(int80_emulation)
+	ANNOTATE_NOENDBR
+	UNWIND_HINT_FUNC
+	CLEAR_BRANCH_HISTORY
+	jmp do_int80_emulation
+SYM_CODE_END(int80_emulation)
diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c
index ac120cbdaaf2..89c1476fcdd9 100644
--- a/arch/x86/entry/entry_fred.c
+++ b/arch/x86/entry/entry_fred.c
@@ -28,9 +28,9 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code
 	if (regs->fred_cs.sl > 0) {
 		pr_emerg("PANIC: invalid or fatal FRED event; event type %u "
 			 "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
-			 regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+			 regs->fred_ss.type, regs->fred_ss.vector, error_code,
 			 fred_event_data(regs), regs->cs, regs->ip);
-		die("invalid or fatal FRED event", regs, regs->orig_ax);
+		die("invalid or fatal FRED event", regs, error_code);
 		panic("invalid or fatal FRED event");
 	} else {
 		unsigned long flags = oops_begin();
@@ -38,10 +38,10 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code
 
 		pr_alert("BUG: invalid or fatal FRED event; event type %u "
 			 "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n",
-			 regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax,
+			 regs->fred_ss.type, regs->fred_ss.vector, error_code,
 			 fred_event_data(regs), regs->cs, regs->ip);
 
-		if (__die("Invalid or fatal FRED event", regs, regs->orig_ax))
+		if (__die("Invalid or fatal FRED event", regs, error_code))
 			sig = 0;
 
 		oops_end(flags, regs, sig);
@@ -66,7 +66,7 @@ static noinstr void fred_intx(struct pt_regs *regs)
 	/* INT80 */
 	case IA32_SYSCALL_VECTOR:
 		if (ia32_enabled())
-			return int80_emulation(regs);
+			return fred_int80_emulation(regs);
 		fallthrough;
 #endif
 
diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
index 8cfc9bc73e7f..c2235bae17ef 100644
--- a/arch/x86/entry/syscall_32.c
+++ b/arch/x86/entry/syscall_32.c
@@ -18,8 +18,25 @@
 #include <asm/syscalls_32.h>
 #undef __SYSCALL
 
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
+#ifdef CONFIG_X86_32
 #define __SYSCALL(nr, sym) __ia32_##sym,
-
-__visible const sys_call_ptr_t ia32_sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_32.h>
 };
+#undef __SYSCALL
+#endif
+
+#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+
+long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_32.h>
+	default: return __ia32_sys_ni_syscall(regs);
+	}
+};
diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
index be120eec1fc9..33b3f09e6f15 100644
--- a/arch/x86/entry/syscall_64.c
+++ b/arch/x86/entry/syscall_64.c
@@ -11,8 +11,23 @@
 #include <asm/syscalls_64.h>
 #undef __SYSCALL
 
+/*
+ * The sys_call_table[] is no longer used for system calls, but
+ * kernel/trace/trace_syscalls.c still wants to know the system
+ * call address.
+ */
 #define __SYSCALL(nr, sym) __x64_##sym,
-
-asmlinkage const sys_call_ptr_t sys_call_table[] = {
+const sys_call_ptr_t sys_call_table[] = {
 #include <asm/syscalls_64.h>
 };
+#undef __SYSCALL
+
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+
+long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_64.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
+};
diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
index bdd0e03a1265..03de4a932131 100644
--- a/arch/x86/entry/syscall_x32.c
+++ b/arch/x86/entry/syscall_x32.c
@@ -11,8 +11,12 @@
 #include <asm/syscalls_x32.h>
 #undef __SYSCALL
 
-#define __SYSCALL(nr, sym) __x64_##sym,
+#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
 
-asmlinkage const sys_call_ptr_t x32_sys_call_table[] = {
-#include <asm/syscalls_x32.h>
+long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+{
+	switch (nr) {
+	#include <asm/syscalls_x32.h>
+	default: return __x64_sys_ni_syscall(regs);
+	}
 };
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index a3c0df11d0e6..2fb7d53cf333 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/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. */
+		goto sigsegv;
 	}
 
 	regs->ax = ret;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 09050641ce5d..5b0dd07b1ef1 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags)
 	while (++i < cpuc->n_events) {
 		cpuc->event_list[i-1] = cpuc->event_list[i];
 		cpuc->event_constraint[i-1] = cpuc->event_constraint[i];
+		cpuc->assign[i-1] = cpuc->assign[i];
 	}
 	cpuc->event_constraint[i-1] = NULL;
 	--cpuc->n_events;
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index 78cd5084104e..4367aa77cb8d 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr)
 	lbr->from = x86_pmu.lbr_from;
 	lbr->to = x86_pmu.lbr_to;
 	lbr->info = x86_pmu.lbr_info;
+	lbr->has_callstack = x86_pmu_has_lbr_callstack();
 }
 EXPORT_SYMBOL_GPL(x86_perf_get_lbr);
 
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 5fc45543e955..0569f579338b 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -105,7 +105,7 @@ static bool cpu_is_self(int cpu)
  * IPI implementation on Hyper-V.
  */
 static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
-		bool exclude_self)
+			       bool exclude_self)
 {
 	struct hv_send_ipi_ex *ipi_arg;
 	unsigned long flags;
@@ -132,8 +132,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 	if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) {
 		ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 
-		nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask,
-				exclude_self ? cpu_is_self : NULL);
+		nr_bank = cpumask_to_vpset_skip(&ipi_arg->vp_set, mask,
+						exclude_self ? cpu_is_self : NULL);
 
 		/*
 		 * 'nr_bank <= 0' means some CPUs in cpumask can't be
@@ -147,7 +147,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector,
 	}
 
 	status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank,
-			      ipi_arg, NULL);
+				     ipi_arg, NULL);
 
 ipi_mask_ex_done:
 	local_irq_restore(flags);
@@ -155,7 +155,7 @@ ipi_mask_ex_done:
 }
 
 static bool __send_ipi_mask(const struct cpumask *mask, int vector,
-		bool exclude_self)
+			    bool exclude_self)
 {