Merge tag 'loongarch-fixes-6.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson

Pull LoongArch fixes from Huacai Chen:
 "Fix a lot of build warnings for LTO-enabled objtool check, increase
  COMMAND_LINE_SIZE up to 4096, rename a missing GCC_PLUGIN_STACKLEAK to
  KSTACK_ERASE, and fix some bugs about arch timer, module loading, LBT
  and KVM"

* tag 'loongarch-fixes-6.17-1' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson:
  LoongArch: KVM: Add address alignment check in pch_pic register access
  LoongArch: KVM: Use kvm_get_vcpu_by_id() instead of kvm_get_vcpu()
  LoongArch: KVM: Fix stack protector issue in send_ipi_data()
  LoongArch: KVM: Make function kvm_own_lbt() robust
  LoongArch: Rename GCC_PLUGIN_STACKLEAK to KSTACK_ERASE
  LoongArch: Save LBT before FPU in setup_sigcontext()
  LoongArch: Optimize module load time by optimizing PLT/GOT counting
  LoongArch: Add cpuhotplug hooks to fix high cpu usage of vCPU threads
  LoongArch: Increase COMMAND_LINE_SIZE up to 4096
  LoongArch: Pass annotate-tablejump option if LTO is enabled
  objtool/LoongArch: Get table size correctly if LTO is enabled
diff --git a/arch/loongarch/Makefile b/arch/loongarch/Makefile
index b0703a4..a3a9759 100644
--- a/arch/loongarch/Makefile
+++ b/arch/loongarch/Makefile
@@ -102,7 +102,13 @@
 
 ifdef CONFIG_OBJTOOL
 ifdef CONFIG_CC_HAS_ANNOTATE_TABLEJUMP
+# The annotate-tablejump option can not be passed to LLVM backend when LTO is enabled.
+# Ensure it is aware of linker with LTO, '--loongarch-annotate-tablejump' also needs to
+# be passed via '-mllvm' to ld.lld.
 KBUILD_CFLAGS			+= -mannotate-tablejump
+ifdef CONFIG_LTO_CLANG
+KBUILD_LDFLAGS			+= -mllvm --loongarch-annotate-tablejump
+endif
 else
 KBUILD_CFLAGS			+= -fno-jump-tables # keep compatibility with older compilers
 endif
diff --git a/arch/loongarch/include/asm/stackframe.h b/arch/loongarch/include/asm/stackframe.h
index 3eda298..5cb568a 100644
--- a/arch/loongarch/include/asm/stackframe.h
+++ b/arch/loongarch/include/asm/stackframe.h
@@ -58,7 +58,7 @@
 	.endm
 
 	.macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	bl	stackleak_erase_on_task_stack
 #endif
 	.endm
diff --git a/arch/loongarch/include/uapi/asm/setup.h b/arch/loongarch/include/uapi/asm/setup.h
new file mode 100644
index 0000000..d46363c
--- /dev/null
+++ b/arch/loongarch/include/uapi/asm/setup.h
@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+
+#ifndef _UAPI_ASM_LOONGARCH_SETUP_H
+#define _UAPI_ASM_LOONGARCH_SETUP_H
+
+#define COMMAND_LINE_SIZE	4096
+
+#endif /* _UAPI_ASM_LOONGARCH_SETUP_H */
diff --git a/arch/loongarch/kernel/module-sections.c b/arch/loongarch/kernel/module-sections.c
index e2f30ff..a43ba7f9 100644
--- a/arch/loongarch/kernel/module-sections.c
+++ b/arch/loongarch/kernel/module-sections.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/moduleloader.h>
 #include <linux/ftrace.h>
+#include <linux/sort.h>
 
 Elf_Addr module_emit_got_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr val)
 {
@@ -61,39 +62,38 @@ Elf_Addr module_emit_plt_entry(struct module *mod, Elf_Shdr *sechdrs, Elf_Addr v
 	return (Elf_Addr)&plt[nr];
 }
 
-static int is_rela_equal(const Elf_Rela *x, const Elf_Rela *y)
+#define cmp_3way(a, b)  ((a) < (b) ? -1 : (a) > (b))
+
+static int compare_rela(const void *x, const void *y)
 {
-	return x->r_info == y->r_info && x->r_addend == y->r_addend;
-}
+	int ret;
+	const Elf_Rela *rela_x = x, *rela_y = y;
 
-static bool duplicate_rela(const Elf_Rela *rela, int idx)
-{
-	int i;
+	ret = cmp_3way(rela_x->r_info, rela_y->r_info);
+	if (ret == 0)
+		ret = cmp_3way(rela_x->r_addend, rela_y->r_addend);
 
-	for (i = 0; i < idx; i++) {
-		if (is_rela_equal(&rela[i], &rela[idx]))
-			return true;
-	}
-
-	return false;
+	return ret;
 }
 
 static void count_max_entries(Elf_Rela *relas, int num,
 			      unsigned int *plts, unsigned int *gots)
 {
-	unsigned int i, type;
+	unsigned int i;
+
+	sort(relas, num, sizeof(Elf_Rela), compare_rela, NULL);
 
 	for (i = 0; i < num; i++) {
-		type = ELF_R_TYPE(relas[i].r_info);
-		switch (type) {
+		if (i && !compare_rela(&relas[i-1], &relas[i]))
+			continue;
+
+		switch (ELF_R_TYPE(relas[i].r_info)) {
 		case R_LARCH_SOP_PUSH_PLT_PCREL:
 		case R_LARCH_B26:
-			if (!duplicate_rela(relas, i))
-				(*plts)++;
+			(*plts)++;
 			break;
 		case R_LARCH_GOT_PC_HI20:
-			if (!duplicate_rela(relas, i))
-				(*gots)++;
+			(*gots)++;
 			break;
 		default:
 			break; /* Do nothing. */
diff --git a/arch/loongarch/kernel/signal.c b/arch/loongarch/kernel/signal.c
index 4740cb5..c9f7ca7 100644
--- a/arch/loongarch/kernel/signal.c
+++ b/arch/loongarch/kernel/signal.c
@@ -677,6 +677,11 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	for (i = 1; i < 32; i++)
 		err |= __put_user(regs->regs[i], &sc->sc_regs[i]);
 
+#ifdef CONFIG_CPU_HAS_LBT
+	if (extctx->lbt.addr)
+		err |= protected_save_lbt_context(extctx);
+#endif
+
 	if (extctx->lasx.addr)
 		err |= protected_save_lasx_context(extctx);
 	else if (extctx->lsx.addr)
@@ -684,11 +689,6 @@ static int setup_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
 	else if (extctx->fpu.addr)
 		err |= protected_save_fpu_context(extctx);
 
-#ifdef CONFIG_CPU_HAS_LBT
-	if (extctx->lbt.addr)
-		err |= protected_save_lbt_context(extctx);
-#endif
-
 	/* Set the "end" magic */
 	info = (struct sctx_info *)extctx->end.addr;
 	err |= __put_user(0, &info->magic);
diff --git a/arch/loongarch/kernel/time.c b/arch/loongarch/kernel/time.c
index 367906b..f3092f2 100644
--- a/arch/loongarch/kernel/time.c
+++ b/arch/loongarch/kernel/time.c
@@ -5,6 +5,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/clockchips.h>
+#include <linux/cpuhotplug.h>
 #include <linux/delay.h>
 #include <linux/export.h>
 #include <linux/init.h>
@@ -102,6 +103,23 @@ static int constant_timer_next_event(unsigned long delta, struct clock_event_dev
 	return 0;
 }
 
+static int arch_timer_starting(unsigned int cpu)
+{
+	set_csr_ecfg(ECFGF_TIMER);
+
+	return 0;
+}
+
+static int arch_timer_dying(unsigned int cpu)
+{
+	constant_set_state_shutdown(this_cpu_ptr(&constant_clockevent_device));
+
+	/* Clear Timer Interrupt */
+	write_csr_tintclear(CSR_TINTCLR_TI);
+
+	return 0;
+}
+
 static unsigned long get_loops_per_jiffy(void)
 {
 	unsigned long lpj = (unsigned long)const_clock_freq;
@@ -172,6 +190,10 @@ int constant_clockevent_init(void)
 	lpj_fine = get_loops_per_jiffy();
 	pr_info("Constant clock event device register\n");
 
+	cpuhp_setup_state(CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
+			  "clockevents/loongarch/timer:starting",
+			  arch_timer_starting, arch_timer_dying);
+
 	return 0;
 }
 
diff --git a/arch/loongarch/kvm/intc/eiointc.c b/arch/loongarch/kvm/intc/eiointc.c
index a3a12af..026b139 100644
--- a/arch/loongarch/kvm/intc/eiointc.c
+++ b/arch/loongarch/kvm/intc/eiointc.c
@@ -45,7 +45,12 @@ static void eiointc_update_irq(struct loongarch_eiointc *s, int irq, int level)
 	}
 
 	cpu = s->sw_coremap[irq];
-	vcpu = kvm_get_vcpu(s->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(s->kvm, cpu);
+	if (unlikely(vcpu == NULL)) {
+		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
+		return;
+	}
+
 	if (level) {
 		/* if not enable return false */
 		if (!test_bit(irq, (unsigned long *)s->enable.reg_u32))
diff --git a/arch/loongarch/kvm/intc/ipi.c b/arch/loongarch/kvm/intc/ipi.c
index e658d5b..5a8481d 100644
--- a/arch/loongarch/kvm/intc/ipi.c
+++ b/arch/loongarch/kvm/intc/ipi.c
@@ -99,7 +99,7 @@ static void write_mailbox(struct kvm_vcpu *vcpu, int offset, uint64_t data, int
 static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 {
 	int i, idx, ret;
-	uint32_t val = 0, mask = 0;
+	uint64_t val = 0, mask = 0;
 
 	/*
 	 * Bit 27-30 is mask for byte writing.
@@ -108,7 +108,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	if ((data >> 27) & 0xf) {
 		/* Read the old val */
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+		ret = kvm_io_bus_read(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		if (unlikely(ret)) {
 			kvm_err("%s: : read data from addr %llx failed\n", __func__, addr);
@@ -124,7 +124,7 @@ static int send_ipi_data(struct kvm_vcpu *vcpu, gpa_t addr, uint64_t data)
 	}
 	val |= ((uint32_t)(data >> 32) & ~mask);
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
-	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, sizeof(val), &val);
+	ret = kvm_io_bus_write(vcpu, KVM_IOCSR_BUS, addr, 4, &val);
 	srcu_read_unlock(&vcpu->kvm->srcu, idx);
 	if (unlikely(ret))
 		kvm_err("%s: : write data to addr %llx failed\n", __func__, addr);
@@ -298,7 +298,7 @@ static int kvm_ipi_regs_access(struct kvm_device *dev,
 	cpu = (attr->attr >> 16) & 0x3ff;
 	addr = attr->attr & 0xff;
 
-	vcpu = kvm_get_vcpu(dev->kvm, cpu);
+	vcpu = kvm_get_vcpu_by_id(dev->kvm, cpu);
 	if (unlikely(vcpu == NULL)) {
 		kvm_err("%s: invalid target cpu: %d\n", __func__, cpu);
 		return -EINVAL;
diff --git a/arch/loongarch/kvm/intc/pch_pic.c b/arch/loongarch/kvm/intc/pch_pic.c
index 6f00ffe..119290b 100644
--- a/arch/loongarch/kvm/intc/pch_pic.c
+++ b/arch/loongarch/kvm/intc/pch_pic.c
@@ -195,6 +195,11 @@ static int kvm_pch_pic_read(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic reading */
 	vcpu->stat.pch_pic_read_exits++;
 	ret = loongarch_pch_pic_read(s, addr, len, val);
@@ -302,6 +307,11 @@ static int kvm_pch_pic_write(struct kvm_vcpu *vcpu,
 		return -EINVAL;
 	}
 
+	if (addr & (len - 1)) {
+		kvm_err("%s: pch pic not aligned addr %llx len %d\n", __func__, addr, len);
+		return -EINVAL;
+	}
+
 	/* statistics of pch pic writing */
 	vcpu->stat.pch_pic_write_exits++;
 	ret = loongarch_pch_pic_write(s, addr, len, val);
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index d1b8c50..ce47815 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -1283,9 +1283,11 @@ int kvm_own_lbt(struct kvm_vcpu *vcpu)
 		return -EINVAL;
 
 	preempt_disable();
-	set_csr_euen(CSR_EUEN_LBTEN);
-	_restore_lbt(&vcpu->arch.lbt);
-	vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	if (!(vcpu->arch.aux_inuse & KVM_LARCH_LBT)) {
+		set_csr_euen(CSR_EUEN_LBTEN);
+		_restore_lbt(&vcpu->arch.lbt);
+		vcpu->arch.aux_inuse |= KVM_LARCH_LBT;
+	}
 	preempt_enable();
 
 	return 0;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index edfa61d..62cd7b3 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -168,6 +168,7 @@ enum cpuhp_state {
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
+	CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
 	CPUHP_AP_REALTEK_TIMER_STARTING,
diff --git a/tools/objtool/arch/loongarch/special.c b/tools/objtool/arch/loongarch/special.c
index e39f86d..a80b75f 100644
--- a/tools/objtool/arch/loongarch/special.c
+++ b/tools/objtool/arch/loongarch/special.c
@@ -27,6 +27,7 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	struct table_info *next_table;
 	unsigned long tmp_insn_offset;
 	unsigned long tmp_rodata_offset;
+	bool is_valid_list = false;
 
 	rsec = find_section_by_name(file->elf, ".rela.discard.tablejump_annotate");
 	if (!rsec)
@@ -35,6 +36,12 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 	INIT_LIST_HEAD(&table_list);
 
 	for_each_reloc(rsec, reloc) {
+		if (reloc->sym->sec->rodata)
+			continue;
+
+		if (strcmp(insn->sec->name, reloc->sym->sec->name))
+			continue;
+
 		orig_table = malloc(sizeof(struct table_info));
 		if (!orig_table) {
 			WARN("malloc failed");
@@ -49,6 +56,22 @@ static void get_rodata_table_size_by_table_annotate(struct objtool_file *file,
 
 		if (reloc_idx(reloc) + 1 == sec_num_entries(rsec))
 			break;
+
+		if (strcmp(insn->sec->name, (reloc + 1)->sym->sec->name)) {
+			list_for_each_entry(orig_table, &table_list, jump_info) {
+				if (orig_table->insn_offset == insn->offset) {
+					is_valid_list = true;
+					break;
+				}
+			}
+
+			if (!is_valid_list) {
+				list_del_init(&table_list);
+				continue;
+			}
+
+			break;
+		}
 	}
 
 	list_for_each_entry(orig_table, &table_list, jump_info) {