Merge 'x86/alternatives'

Pick up dependent changes.

Signed-off-by: Borislav Petkov <bp@suse.de>

10 files changed, 80 insertions, 177 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 2ddf08351f0b..0704c2a94272 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -35,7 +35,6 @@ KASAN_SANITIZE_sev-es.o					:= n
 KCSAN_SANITIZE := n
 
 OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
-OBJECT_FILES_NON_STANDARD_paravirt_patch.o		:= y
 
 ifdef CONFIG_FRAME_POINTER
 OBJECT_FILES_NON_STANDARD_ftrace_$(BITS).o		:= y
@@ -121,7 +120,7 @@ obj-$(CONFIG_AMD_NB)		+= amd_nb.o
 obj-$(CONFIG_DEBUG_NMI_SELFTEST) += nmi_selftest.o
 
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o kvmclock.o
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ff359b3a30e7..f902f28d9dff 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -28,6 +28,7 @@
 #include <asm/insn.h>
 #include <asm/io.h>
 #include <asm/fixmap.h>
+#include <asm/paravirt.h>
 
 int __read_mostly alternatives_patched;
 
@@ -388,21 +389,31 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
 	 */
 	for (a = start; a < end; a++) {
 		int insn_buff_sz = 0;
+		/* Mask away "NOT" flag bit for feature to test. */
+		u16 feature = a->cpuid & ~ALTINSTR_FLAG_INV;
 
 		instr = (u8 *)&a->instr_offset + a->instr_offset;
 		replacement = (u8 *)&a->repl_offset + a->repl_offset;
 		BUG_ON(a->instrlen > sizeof(insn_buff));
-		BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32);
-		if (!boot_cpu_has(a->cpuid)) {
+		BUG_ON(feature >= (NCAPINTS + NBUGINTS) * 32);
+
+		/*
+		 * Patch if either:
+		 * - feature is present
+		 * - feature not present but ALTINSTR_FLAG_INV is set to mean,
+		 *   patch if feature is *NOT* present.
+		 */
+		if (!boot_cpu_has(feature) == !(a->cpuid & ALTINSTR_FLAG_INV)) {
 			if (a->padlen > 1)
 				optimize_nops(a, instr);
 
 			continue;
 		}
 
-		DPRINTK("feat: %d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
-			a->cpuid >> 5,
-			a->cpuid & 0x1f,
+		DPRINTK("feat: %s%d*32+%d, old: (%pS (%px) len: %d), repl: (%px, len: %d), pad: %d",
+			(a->cpuid & ALTINSTR_FLAG_INV) ? "!" : "",
+			feature >> 5,
+			feature & 0x1f,
 			instr, instr, a->instrlen,
 			replacement, a->replacementlen, a->padlen);
 
@@ -605,7 +616,7 @@ void __init_or_module apply_paravirt(struct paravirt_patch_site *start,
 		BUG_ON(p->len > MAX_PATCH_LEN);
 		/* prep the buffer with the original instructions */
 		memcpy(insn_buff, p->instr, p->len);
-		used = pv_ops.init.patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
+		used = paravirt_patch(p->type, insn_buff, (unsigned long)p->instr, p->len);
 
 		BUG_ON(used > p->len);
 
@@ -723,6 +734,33 @@ void __init alternative_instructions(void)
 	 * patching.
 	 */
 
+	/*
+	 * Paravirt patching and alternative patching can be combined to
+	 * replace a function call with a short direct code sequence (e.g.
+	 * by setting a constant return value instead of doing that in an
+	 * external function).
+	 * In order to make this work the following sequence is required:
+	 * 1. set (artificial) features depending on used paravirt
+	 *    functions which can later influence alternative patching
+	 * 2. apply paravirt patching (generally replacing an indirect
+	 *    function call with a direct one)
+	 * 3. apply alternative patching (e.g. replacing a direct function
+	 *    call with a custom code sequence)
+	 * Doing paravirt patching after alternative patching would clobber
+	 * the optimization of the custom code with a function call again.
+	 */
+	paravirt_set_cap();
+
+	/*
+	 * First patch paravirt functions, such that we overwrite the indirect
+	 * call with the direct call.
+	 */
+	apply_paravirt(__parainstructions, __parainstructions_end);
+
+	/*
+	 * Then patch alternatives, such that those paravirt calls that are in
+	 * alternatives can be overwritten by their immediate fragments.
+	 */
 	apply_alternatives(__alt_instructions, __alt_instructions_end);
 
 #ifdef CONFIG_SMP
@@ -741,8 +779,6 @@ void __init alternative_instructions(void)
 	}
 #endif
 
-	apply_paravirt(__parainstructions, __parainstructions_end);
-
 	restart_nmi();
 	alternatives_patched = 1;
 }
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 60b9f42ce3c1..ecd3fd6993d1 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -61,13 +61,6 @@ static void __used common(void)
 	OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe_ia32, uc.uc_mcontext);
 #endif
 
-#ifdef CONFIG_PARAVIRT_XXL
-	BLANK();
-	OFFSET(PV_IRQ_irq_disable, paravirt_patch_template, irq.irq_disable);
-	OFFSET(PV_IRQ_irq_enable, paravirt_patch_template, irq.irq_enable);
-	OFFSET(PV_CPU_iret, paravirt_patch_template, cpu.iret);
-#endif
-
 #ifdef CONFIG_XEN
 	BLANK();
 	OFFSET(XEN_vcpu_info_mask, vcpu_info, evtchn_upcall_mask);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index c6ede3b3d302..84fb8e3f3d1b 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -27,6 +27,7 @@
 #include <linux/clocksource.h>
 #include <linux/cpu.h>
 #include <linux/reboot.h>
+#include <linux/static_call.h>
 #include <asm/div64.h>
 #include <asm/x86_init.h>
 #include <asm/hypervisor.h>
@@ -336,11 +337,11 @@ static void __init vmware_paravirt_ops_setup(void)
 	vmware_cyc2ns_setup();
 
 	if (vmw_sched_clock)
-		pv_ops.time.sched_clock = vmware_sched_clock;
+		paravirt_set_sched_clock(vmware_sched_clock);
 
 	if (vmware_is_stealclock_available()) {
 		has_steal_clock = true;
-		pv_ops.time.steal_clock = vmware_steal_clock;
+		static_call_update(pv_steal_clock, vmware_steal_clock);
 
 		/* We use reboot notifier only to disable steal clock */
 		register_reboot_notifier(&vmware_pv_reboot_nb);
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5e78e01ca3b4..351ba99f6009 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -650,7 +650,7 @@ static void __init kvm_guest_init(void)
 
 	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
 		has_steal_clock = 1;
-		pv_ops.time.steal_clock = kvm_steal_clock;
+		static_call_update(pv_steal_clock, kvm_steal_clock);
 	}
 
 	if (pv_tlb_flush_supported()) {
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1fc0962c89c0..d37ed4e1d033 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -106,7 +106,7 @@ static inline void kvm_sched_clock_init(bool stable)
 	if (!stable)
 		clear_sched_clock_stable();
 	kvm_sched_clock_offset = kvm_clock_read();
-	pv_ops.time.sched_clock = kvm_sched_clock_read;
+	paravirt_set_sched_clock(kvm_sched_clock_read);
 
 	pr_info("kvm-clock: using sched offset of %llu cycles",
 		kvm_sched_clock_offset);
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 4f75d0cf6305..9e1ea99ad9df 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/arch/x86/kernel/paravirt-spinlocks.c
@@ -32,3 +32,12 @@ bool pv_is_native_vcpu_is_preempted(void)
 	return pv_ops.lock.vcpu_is_preempted.func ==
 		__raw_callee_save___native_vcpu_is_preempted;
 }
+
+void __init paravirt_set_cap(void)
+{
+	if (!pv_is_native_spin_unlock())
+		setup_force_cpu_cap(X86_FEATURE_PVUNLOCK);
+
+	if (!pv_is_native_vcpu_is_preempted())
+		setup_force_cpu_cap(X86_FEATURE_VCPUPREEMPT);
+}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index c60222ab8ab9..d0730264786b 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -14,6 +14,7 @@
 #include <linux/highmem.h>
 #include <linux/kprobes.h>
 #include <linux/pgtable.h>
+#include <linux/static_call.h>
 
 #include <asm/bug.h>
 #include <asm/paravirt.h>
@@ -52,7 +53,10 @@ void __init default_banner(void)
 }
 
 /* Undefined instruction for dealing with missing ops pointers. */
-static const unsigned char ud2a[] = { 0x0f, 0x0b };
+static void paravirt_BUG(void)
+{
+	BUG();
+}
 
 struct branch {
 	unsigned char opcode;
@@ -85,25 +89,6 @@ u64 notrace _paravirt_ident_64(u64 x)
 {
 	return x;
 }
-
-static unsigned paravirt_patch_jmp(void *insn_buff, const void *target,
-				   unsigned long addr, unsigned len)
-{
-	struct branch *b = insn_buff;
-	unsigned long delta = (unsigned long)target - (addr+5);
-
-	if (len < 5) {
-#ifdef CONFIG_RETPOLINE
-		WARN_ONCE(1, "Failing to patch indirect JMP in %ps\n", (void *)addr);
-#endif
-		return len;	/* call too long for patch site */
-	}
-
-	b->opcode = 0xe9;	/* jmp */
-	b->delta = delta;
-
-	return 5;
-}
 #endif
 
 DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
@@ -114,8 +99,8 @@ void __init native_pv_lock_init(void)
 		static_branch_disable(&virt_spin_lock_key);
 }
 
-unsigned paravirt_patch_default(u8 type, void *insn_buff,
-				unsigned long addr, unsigned len)
+unsigned int paravirt_patch(u8 type, void *insn_buff, unsigned long addr,
+			    unsigned int len)
 {
 	/*
 	 * Neat trick to map patch type back to the call within the
@@ -125,20 +110,10 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	unsigned ret;
 
 	if (opfunc == NULL)
-		/* If there's no function, patch it with a ud2a (BUG) */
-		ret = paravirt_patch_insns(insn_buff, len, ud2a, ud2a+sizeof(ud2a));
+		/* If there's no function, patch it with paravirt_BUG() */
+		ret = paravirt_patch_call(insn_buff, paravirt_BUG, addr, len);
 	else if (opfunc == _paravirt_nop)
 		ret = 0;
-
-#ifdef CONFIG_PARAVIRT_XXL
-	/* identity functions just return their single argument */
-	else if (opfunc == _paravirt_ident_64)
-		ret = paravirt_patch_ident_64(insn_buff, len);
-
-	else if (type == PARAVIRT_PATCH(cpu.iret))
-		/* If operation requires a jmp, then jmp */
-		ret = paravirt_patch_jmp(insn_buff, opfunc, addr, len);
-#endif
 	else
 		/* Otherwise call the function. */
 		ret = paravirt_patch_call(insn_buff, opfunc, addr, len);
@@ -146,19 +121,6 @@ unsigned paravirt_patch_default(u8 type, void *insn_buff,
 	return ret;
 }
 
-unsigned paravirt_patch_insns(void *insn_buff, unsigned len,
-			      const char *start, const char *end)
-{
-	unsigned insn_len = end - start;
-
-	/* Alternative instruction is too large for the patch site and we cannot continue: */
-	BUG_ON(insn_len > len || start == NULL);
-
-	memcpy(insn_buff, start, insn_len);
-
-	return insn_len;
-}
-
 struct static_key paravirt_steal_enabled;
 struct static_key paravirt_steal_rq_enabled;
 
@@ -167,6 +129,14 @@ static u64 native_steal_clock(int cpu)
 	return 0;
 }
 
+DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock);
+DEFINE_STATIC_CALL(pv_sched_clock, native_sched_clock);
+
+void paravirt_set_sched_clock(u64 (*func)(void))
+{
+	static_call_update(pv_sched_clock, func);
+}
+
 /* These are in entry.S */
 extern void native_iret(void);
 
@@ -269,13 +239,6 @@ struct pv_info pv_info = {
 #define PTE_IDENT	__PV_IS_CALLEE_SAVE(_paravirt_ident_64)
 
 struct paravirt_patch_template pv_ops = {
-	/* Init ops. */
-	.init.patch		= native_patch,
-
-	/* Time ops. */
-	.time.sched_clock	= native_sched_clock,
-	.time.steal_clock	= native_steal_clock,
-
 	/* Cpu ops. */
 	.cpu.io_delay		= native_io_delay,
 
@@ -308,8 +271,6 @@ struct paravirt_patch_template pv_ops = {
 
 	.cpu.load_sp0		= native_load_sp0,
 
-	.cpu.iret		= native_iret,
-
 #ifdef CONFIG_X86_IOPL_IOPERM
 	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
 	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
@@ -414,6 +375,8 @@ struct paravirt_patch_template pv_ops = {
 NOKPROBE_SYMBOL(native_get_debugreg);
 NOKPROBE_SYMBOL(native_set_debugreg);
 NOKPROBE_SYMBOL(native_load_idt);
+
+void (*paravirt_iret)(void) = native_iret;
 #endif
 
 EXPORT_SYMBOL(pv_ops);
diff --git a/arch/x86/kernel/paravirt_patch.c b/arch/x86/kernel/paravirt_patch.c
deleted file mode 100644
index abd27ec67397..000000000000
--- a/arch/x86/kernel/paravirt_patch.c
+++ /dev/null
@@ -1,99 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/stringify.h>
-
-#include <asm/paravirt.h>
-#include <asm/asm-offsets.h>
-
-#define PSTART(d, m)							\
-	patch_data_##d.m
-
-#define PEND(d, m)							\
-	(PSTART(d, m) + sizeof(patch_data_##d.m))
-
-#define PATCH(d, m, insn_buff, len)						\
-	paravirt_patch_insns(insn_buff, len, PSTART(d, m), PEND(d, m))
-
-#define PATCH_CASE(ops, m, data, insn_buff, len)				\
-	case PARAVIRT_PATCH(ops.m):					\
-		return PATCH(data, ops##_##m, insn_buff, len)
-
-#ifdef CONFIG_PARAVIRT_XXL
-struct patch_xxl {
-	const unsigned char	irq_irq_disable[1];
-	const unsigned char	irq_irq_enable[1];
-	const unsigned char	irq_save_fl[2];
-	const unsigned char	mmu_read_cr2[3];
-	const unsigned char	mmu_read_cr3[3];
-	const unsigned char	mmu_write_cr3[3];
-	const unsigned char	cpu_wbinvd[2];
-	const unsigned char	mov64[3];
-};
-
-static const struct patch_xxl patch_data_xxl = {
-	.irq_irq_disable	= { 0xfa },		// cli
-	.irq_irq_enable		= { 0xfb },		// sti
-	.irq_save_fl		= { 0x9c, 0x58 },	// pushf; pop %[re]ax
-	.mmu_read_cr2		= { 0x0f, 0x20, 0xd0 },	// mov %cr2, %[re]ax
-	.mmu_read_cr3		= { 0x0f, 0x20, 0xd8 },	// mov %cr3, %[re]ax
-	.mmu_write_cr3		= { 0x0f, 0x22, 0xdf },	// mov %rdi, %cr3
-	.cpu_wbinvd		= { 0x0f, 0x09 },	// wbinvd
-	.mov64			= { 0x48, 0x89, 0xf8 },	// mov %rdi, %rax
-};
-
-unsigned int paravirt_patch_ident_64(void *insn_buff, unsigned int len)
-{
-	return PATCH(xxl, mov64, insn_buff, len);
-}
-# endif /* CONFIG_PARAVIRT_XXL */
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-struct patch_lock {
-	unsigned char queued_spin_unlock[3];
-	unsigned char vcpu_is_preempted[2];
-};
-
-static const struct patch_lock patch_data_lock = {
-	.vcpu_is_preempted	= { 0x31, 0xc0 },	// xor %eax, %eax
-
-# ifdef CONFIG_X86_64
-	.queued_spin_unlock	= { 0xc6, 0x07, 0x00 },	// movb $0, (%rdi)
-# else
-	.queued_spin_unlock	= { 0xc6, 0x00, 0x00 },	// movb $0, (%eax)
-# endif
-};
-#endif /* CONFIG_PARAVIRT_SPINLOCKS */
-
-unsigned int native_patch(u8 type, void *insn_buff, unsigned long addr,
-			  unsigned int len)
-{
-	switch (type) {
-
-#ifdef CONFIG_PARAVIRT_XXL
-	PATCH_CASE(irq, save_fl, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_enable, xxl, insn_buff, len);
-	PATCH_CASE(irq, irq_disable, xxl, insn_buff, len);
-
-	PATCH_CASE(mmu, read_cr2, xxl, insn_buff, len);
-	PATCH_CASE(mmu, read_cr3, xxl, insn_buff, len);
-	PATCH_CASE(mmu, write_cr3, xxl, insn_buff, len);
-
-	PATCH_CASE(cpu, wbinvd, xxl, insn_buff, len);
-#endif
-
-#ifdef CONFIG_PARAVIRT_SPINLOCKS
-	case PARAVIRT_PATCH(lock.queued_spin_unlock):
-		if (pv_is_native_spin_unlock())
-			return PATCH(lock, queued_spin_unlock, insn_buff, len);
-		break;
-
-	case PARAVIRT_PATCH(lock.vcpu_is_preempted):
-		if (pv_is_native_vcpu_is_preempted())
-			return PATCH(lock, vcpu_is_preempted, insn_buff, len);
-		break;
-#endif
-	default:
-		break;
-	}
-
-	return paravirt_patch_default(type, insn_buff, addr, len);
-}
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index f70dffc2771f..9f592923f956 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 #include <linux/timex.h>
 #include <linux/static_key.h>
+#include <linux/static_call.h>
 
 #include <asm/hpet.h>
 #include <asm/timer.h>
@@ -254,7 +255,7 @@ unsigned long long sched_clock(void)
 
 bool using_native_sched_clock(void)
 {
-	return pv_ops.time.sched_clock == native_sched_clock;
+	return static_call_query(pv_sched_clock) == native_sched_clock;
 }
 #else
 unsigned long long