Merge tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull objtool updates from Thomas Gleixner:

 - Improve retpoline code patching by separating it from alternatives
   which reduces memory footprint and allows to do better optimizations
   in the actual runtime patching.

 - Add proper retpoline support for x86/BPF

 - Address noinstr warnings in x86/kvm, lockdep and paravirtualization
   code

 - Add support to handle pv_opsindirect calls in the noinstr analysis

 - Classify symbols upfront and cache the result to avoid redundant
   str*cmp() invocations.

 - Add a CFI hash to reduce memory consumption which also reduces
   runtime on a allyesconfig by ~50%

 - Adjust XEN code to make objtool handling more robust and as a side
   effect to prevent text fragmentation due to placement of the
   hypercall page.

* tag 'objtool-core-2021-10-31' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  bpf,x86: Respect X86_FEATURE_RETPOLINE*
  bpf,x86: Simplify computing label offsets
  x86,bugs: Unconditionally allow spectre_v2=retpoline,amd
  x86/alternative: Add debug prints to apply_retpolines()
  x86/alternative: Try inline spectre_v2=retpoline,amd
  x86/alternative: Handle Jcc __x86_indirect_thunk_\reg
  x86/alternative: Implement .retpoline_sites support
  x86/retpoline: Create a retpoline thunk array
  x86/retpoline: Move the retpoline thunk declarations to nospec-branch.h
  x86/asm: Fixup odd GEN-for-each-reg.h usage
  x86/asm: Fix register order
  x86/retpoline: Remove unused replacement symbols
  objtool,x86: Replace alternatives with .retpoline_sites
  objtool: Shrink struct instruction
  objtool: Explicitly avoid self modifying code in .altinstr_replacement
  objtool: Classify symbols
  objtool: Support pv_opsindirect calls for noinstr
  x86/xen: Rework the xen_{cpu,irq,mmu}_opsarrays
  x86/xen: Mark xen_force_evtchn_callback() noinstr
  x86/xen: Make irq_disable() noinstr
  ...

5 files changed, 158 insertions, 149 deletions

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index a7b7d674f500..4f63117f09bb 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -283,12 +283,12 @@ static void __init xen_init_capabilities(void)
 	}
 }
 
-static void xen_set_debugreg(int reg, unsigned long val)
+static noinstr void xen_set_debugreg(int reg, unsigned long val)
 {
 	HYPERVISOR_set_debugreg(reg, val);
 }
 
-static unsigned long xen_get_debugreg(int reg)
+static noinstr unsigned long xen_get_debugreg(int reg)
 {
 	return HYPERVISOR_get_debugreg(reg);
 }
@@ -1025,52 +1025,54 @@ static const struct pv_info xen_info __initconst = {
 	.name = "Xen",
 };
 
-static const struct pv_cpu_ops xen_cpu_ops __initconst = {
-	.cpuid = xen_cpuid,
+static const typeof(pv_ops) xen_cpu_ops __initconst = {
+	.cpu = {
+		.cpuid = xen_cpuid,
 
-	.set_debugreg = xen_set_debugreg,
-	.get_debugreg = xen_get_debugreg,
+		.set_debugreg = xen_set_debugreg,
+		.get_debugreg = xen_get_debugreg,
 
-	.read_cr0 = xen_read_cr0,
-	.write_cr0 = xen_write_cr0,
+		.read_cr0 = xen_read_cr0,
+		.write_cr0 = xen_write_cr0,
 
-	.write_cr4 = xen_write_cr4,
+		.write_cr4 = xen_write_cr4,
 
-	.wbinvd = native_wbinvd,
+		.wbinvd = native_wbinvd,
 
-	.read_msr = xen_read_msr,
-	.write_msr = xen_write_msr,
+		.read_msr = xen_read_msr,
+		.write_msr = xen_write_msr,
 
-	.read_msr_safe = xen_read_msr_safe,
-	.write_msr_safe = xen_write_msr_safe,
+		.read_msr_safe = xen_read_msr_safe,
+		.write_msr_safe = xen_write_msr_safe,
 
-	.read_pmc = xen_read_pmc,
+		.read_pmc = xen_read_pmc,
 
-	.load_tr_desc = paravirt_nop,
-	.set_ldt = xen_set_ldt,
-	.load_gdt = xen_load_gdt,
-	.load_idt = xen_load_idt,
-	.load_tls = xen_load_tls,
-	.load_gs_index = xen_load_gs_index,
+		.load_tr_desc = paravirt_nop,
+		.set_ldt = xen_set_ldt,
+		.load_gdt = xen_load_gdt,
+		.load_idt = xen_load_idt,
+		.load_tls = xen_load_tls,
+		.load_gs_index = xen_load_gs_index,
 
-	.alloc_ldt = xen_alloc_ldt,
-	.free_ldt = xen_free_ldt,
+		.alloc_ldt = xen_alloc_ldt,
+		.free_ldt = xen_free_ldt,
 
-	.store_tr = xen_store_tr,
+		.store_tr = xen_store_tr,
 
-	.write_ldt_entry = xen_write_ldt_entry,
-	.write_gdt_entry = xen_write_gdt_entry,
-	.write_idt_entry = xen_write_idt_entry,
-	.load_sp0 = xen_load_sp0,
+		.write_ldt_entry = xen_write_ldt_entry,
+		.write_gdt_entry = xen_write_gdt_entry,
+		.write_idt_entry = xen_write_idt_entry,
+		.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
-	.update_io_bitmap = xen_update_io_bitmap,
+		.invalidate_io_bitmap = xen_invalidate_io_bitmap,
+		.update_io_bitmap = xen_update_io_bitmap,
 #endif
-	.io_delay = xen_io_delay,
+		.io_delay = xen_io_delay,
 
-	.start_context_switch = paravirt_start_context_switch,
-	.end_context_switch = xen_end_context_switch,
+		.start_context_switch = paravirt_start_context_switch,
+		.end_context_switch = xen_end_context_switch,
+	},
 };
 
 static void xen_restart(char *msg)
@@ -1211,7 +1213,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
 
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
-	pv_ops.cpu = xen_cpu_ops;
+	pv_ops.cpu = xen_cpu_ops.cpu;
 	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
 
diff --git a/arch/x86/xen/irq.c b/arch/x86/xen/irq.c
index dfa091d79c2e..4fe387e520af 100644
--- a/arch/x86/xen/irq.c
+++ b/arch/x86/xen/irq.c
@@ -19,12 +19,12 @@
  * callback mask. We do this in a very simple manner, by making a call
  * down into Xen. The pending flag will be checked by Xen on return.
  */
-void xen_force_evtchn_callback(void)
+noinstr void xen_force_evtchn_callback(void)
 {
 	(void)HYPERVISOR_xen_version(0, NULL);
 }
 
-asmlinkage __visible unsigned long xen_save_fl(void)
+asmlinkage __visible noinstr unsigned long xen_save_fl(void)
 {
 	struct vcpu_info *vcpu;
 	unsigned long flags;
@@ -40,9 +40,9 @@ asmlinkage __visible unsigned long xen_save_fl(void)
 	*/
 	return (-flags) & X86_EFLAGS_IF;
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_save_fl, ".noinstr.text");
 
-asmlinkage __visible void xen_irq_disable(void)
+asmlinkage __visible noinstr void xen_irq_disable(void)
 {
 	/* There's a one instruction preempt window here.  We need to
 	   make sure we're don't switch CPUs between getting the vcpu
@@ -51,9 +51,9 @@ asmlinkage __visible void xen_irq_disable(void)
 	this_cpu_read(xen_vcpu)->evtchn_upcall_mask = 1;
 	preempt_enable_no_resched();
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_disable, ".noinstr.text");
 
-asmlinkage __visible void xen_irq_enable(void)
+asmlinkage __visible noinstr void xen_irq_enable(void)
 {
 	struct vcpu_info *vcpu;
 
@@ -76,7 +76,7 @@ asmlinkage __visible void xen_irq_enable(void)
 
 	preempt_enable();
 }
-PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable);
+__PV_CALLEE_SAVE_REGS_THUNK(xen_irq_enable, ".noinstr.text");
 
 static void xen_safe_halt(void)
 {
@@ -94,17 +94,20 @@ static void xen_halt(void)
 		xen_safe_halt();
 }
 
-static const struct pv_irq_ops xen_irq_ops __initconst = {
-	.save_fl = PV_CALLEE_SAVE(xen_save_fl),
-	.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
-	.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+static const typeof(pv_ops) xen_irq_ops __initconst = {
+	.irq = {
 
-	.safe_halt = xen_safe_halt,
-	.halt = xen_halt,
+		.save_fl = PV_CALLEE_SAVE(xen_save_fl),
+		.irq_disable = PV_CALLEE_SAVE(xen_irq_disable),
+		.irq_enable = PV_CALLEE_SAVE(xen_irq_enable),
+
+		.safe_halt = xen_safe_halt,
+		.halt = xen_halt,
+	},
 };
 
 void __init xen_init_irq_ops(void)
 {
-	pv_ops.irq = xen_irq_ops;
+	pv_ops.irq = xen_irq_ops.irq;
 	x86_init.irqs.intr_init = xen_init_IRQ;
 }
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 3359c23573c5..1ce436eeda15 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1204,7 +1204,8 @@ static void __init xen_pagetable_init(void)
 	xen_remap_memory();
 	xen_setup_mfn_list_list();
 }
-static void xen_write_cr2(unsigned long cr2)
+
+static noinstr void xen_write_cr2(unsigned long cr2)
 {
 	this_cpu_read(xen_vcpu)->arch.cr2 = cr2;
 }
@@ -2078,67 +2079,69 @@ static void xen_leave_lazy_mmu(void)
 	preempt_enable();
 }
 
-static const struct pv_mmu_ops xen_mmu_ops __initconst = {
-	.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
-	.write_cr2 = xen_write_cr2,
+static const typeof(pv_ops) xen_mmu_ops __initconst = {
+	.mmu = {
+		.read_cr2 = __PV_IS_CALLEE_SAVE(xen_read_cr2),
+		.write_cr2 = xen_write_cr2,
 
-	.read_cr3 = xen_read_cr3,
-	.write_cr3 = xen_write_cr3_init,
+		.read_cr3 = xen_read_cr3,
+		.write_cr3 = xen_write_cr3_init,
 
-	.flush_tlb_user = xen_flush_tlb,
-	.flush_tlb_kernel = xen_flush_tlb,
-	.flush_tlb_one_user = xen_flush_tlb_one_user,
-	.flush_tlb_multi = xen_flush_tlb_multi,
-	.tlb_remove_table = tlb_remove_table,
+		.flush_tlb_user = xen_flush_tlb,
+		.flush_tlb_kernel = xen_flush_tlb,
+		.flush_tlb_one_user = xen_flush_tlb_one_user,
+		.flush_tlb_multi = xen_flush_tlb_multi,
+		.tlb_remove_table = tlb_remove_table,
 
-	.pgd_alloc = xen_pgd_alloc,
-	.pgd_free = xen_pgd_free,
+		.pgd_alloc = xen_pgd_alloc,
+		.pgd_free = xen_pgd_free,
 
-	.alloc_pte = xen_alloc_pte_init,
-	.release_pte = xen_release_pte_init,
-	.alloc_pmd = xen_alloc_pmd_init,
-	.release_pmd = xen_release_pmd_init,
+		.alloc_pte = xen_alloc_pte_init,
+		.release_pte = xen_release_pte_init,
+		.alloc_pmd = xen_alloc_pmd_init,
+		.release_pmd = xen_release_pmd_init,
 
-	.set_pte = xen_set_pte_init,
-	.set_pmd = xen_set_pmd_hyper,
+		.set_pte = xen_set_pte_init,
+		.set_pmd = xen_set_pmd_hyper,
 
-	.ptep_modify_prot_start = xen_ptep_modify_prot_start,
-	.ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
+		.ptep_modify_prot_start = xen_ptep_modify_prot_start,
+		.ptep_modify_prot_commit = xen_ptep_modify_prot_commit,
 
-	.pte_val = PV_CALLEE_SAVE(xen_pte_val),
-	.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
+		.pte_val = PV_CALLEE_SAVE(xen_pte_val),
+		.pgd_val = PV_CALLEE_SAVE(xen_pgd_val),
 
-	.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
-	.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
+		.make_pte = PV_CALLEE_SAVE(xen_make_pte_init),
+		.make_pgd = PV_CALLEE_SAVE(xen_make_pgd),
 
-	.set_pud = xen_set_pud_hyper,
+		.set_pud = xen_set_pud_hyper,
 
-	.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
-	.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
+		.make_pmd = PV_CALLEE_SAVE(xen_make_pmd),
+		.pmd_val = PV_CALLEE_SAVE(xen_pmd_val),
 
-	.pud_val = PV_CALLEE_SAVE(xen_pud_val),
-	.make_pud = PV_CALLEE_SAVE(xen_make_pud),
-	.set_p4d = xen_set_p4d_hyper,
+		.pud_val = PV_CALLEE_SAVE(xen_pud_val),
+		.make_pud = PV_CALLEE_SAVE(xen_make_pud),
+		.set_p4d = xen_set_p4d_hyper,
 
-	.alloc_pud = xen_alloc_pmd_init,
-	.release_pud = xen_release_pmd_init,
+		.alloc_pud = xen_alloc_pmd_init,
+		.release_pud = xen_release_pmd_init,
 
 #if CONFIG_PGTABLE_LEVELS >= 5
-	.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
-	.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
+		.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
+		.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
 #endif
 
-	.activate_mm = xen_activate_mm,
-	.dup_mmap = xen_dup_mmap,
-	.exit_mmap = xen_exit_mmap,
+		.activate_mm = xen_activate_mm,
+		.dup_mmap = xen_dup_mmap,
+		.exit_mmap = xen_exit_mmap,
 
-	.lazy_mode = {
-		.enter = paravirt_enter_lazy_mmu,
-		.leave = xen_leave_lazy_mmu,
-		.flush = paravirt_flush_lazy_mmu,
-	},
+		.lazy_mode = {
+			.enter = paravirt_enter_lazy_mmu,
+			.leave = xen_leave_lazy_mmu,
+			.flush = paravirt_flush_lazy_mmu,
+		},
 
-	.set_fixmap = xen_set_fixmap,
+		.set_fixmap = xen_set_fixmap,
+	},
 };
 
 void __init xen_init_mmu_ops(void)
@@ -2146,7 +2149,7 @@ void __init xen_init_mmu_ops(void)
 	x86_init.paging.pagetable_init = xen_pagetable_init;
 	x86_init.hyper.init_after_bootmem = xen_after_bootmem;
 
-	pv_ops.mmu = xen_mmu_ops;
+	pv_ops.mmu = xen_mmu_ops.mmu;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
 }
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 1e626444712b..220dd9678494 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -21,6 +21,45 @@
 #include <linux/init.h>
 #include <linux/linkage.h>
 
+.pushsection .noinstr.text, "ax"
+/*
+ * Disabling events is simply a matter of making the event mask
+ * non-zero.
+ */
+SYM_FUNC_START(xen_irq_disable_direct)
+	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	ret
+SYM_FUNC_END(xen_irq_disable_direct)
+
+/*
+ * Force an event check by making a hypercall, but preserve regs
+ * before making the call.
+ */
+SYM_FUNC_START(check_events)
+	FRAME_BEGIN
+	push %rax
+	push %rcx
+	push %rdx
+	push %rsi
+	push %rdi
+	push %r8
+	push %r9
+	push %r10
+	push %r11
+	call xen_force_evtchn_callback
+	pop %r11
+	pop %r10
+	pop %r9
+	pop %r8
+	pop %rdi
+	pop %rsi
+	pop %rdx
+	pop %rcx
+	pop %rax
+	FRAME_END
+	ret
+SYM_FUNC_END(check_events)
+
 /*
  * Enable events.  This clears the event mask and tests the pending
  * event status with one and operation.  If there are pending events,
@@ -47,16 +86,6 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	ret
 SYM_FUNC_END(xen_irq_enable_direct)
 
-
-/*
- * Disabling events is simply a matter of making the event mask
- * non-zero.
- */
-SYM_FUNC_START(xen_irq_disable_direct)
-	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
-	ret
-SYM_FUNC_END(xen_irq_disable_direct)
-
 /*
  * (xen_)save_fl is used to get the current interrupt enable status.
  * Callers expect the status to be in X86_EFLAGS_IF, and other bits
@@ -73,35 +102,6 @@ SYM_FUNC_START(xen_save_fl_direct)
 	ret
 SYM_FUNC_END(xen_save_fl_direct)
 
-/*
- * Force an event check by making a hypercall, but preserve regs
- * before making the call.
- */
-SYM_FUNC_START(check_events)
-	FRAME_BEGIN
-	push %rax
-	push %rcx
-	push %rdx
-	push %rsi
-	push %rdi
-	push %r8
-	push %r9
-	push %r10
-	push %r11
-	call xen_force_evtchn_callback
-	pop %r11
-	pop %r10
-	pop %r9
-	pop %r8
-	pop %rdi
-	pop %rsi
-	pop %rdx
-	pop %rcx
-	pop %rax
-	FRAME_END
-	ret
-SYM_FUNC_END(check_events)
-
 SYM_FUNC_START(xen_read_cr2)
 	FRAME_BEGIN
 	_ASM_MOV PER_CPU_VAR(xen_vcpu), %_ASM_AX
@@ -116,6 +116,7 @@ SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_END
 	ret
 SYM_FUNC_END(xen_read_cr2_direct);
+.popsection
 
 .macro xen_pv_trap name
 SYM_CODE_START(xen_\name)
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index cb6538ae2fe0..9e27b86a0c31 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -20,6 +20,23 @@
 #include <xen/interface/xen-mca.h>
 #include <asm/xen/interface.h>
 
+.pushsection .noinstr.text, "ax"
+	.balign PAGE_SIZE
+SYM_CODE_START(hypercall_page)
+	.rept (PAGE_SIZE / 32)
+		UNWIND_HINT_FUNC
+		.skip 31, 0x90
+		ret
+	.endr
+
+#define HYPERCALL(n) \
+	.equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
+	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
+#include <asm/xen-hypercalls.h>
+#undef HYPERCALL
+SYM_CODE_END(hypercall_page)
+.popsection
+
 #ifdef CONFIG_XEN_PV
 	__INIT
 SYM_CODE_START(startup_xen)
@@ -64,23 +81,6 @@ SYM_CODE_END(asm_cpu_bringup_and_idle)
 #endif
 #endif
 
-.pushsection .text
-	.balign PAGE_SIZE
-SYM_CODE_START(hypercall_page)
-	.rept (PAGE_SIZE / 32)
-		UNWIND_HINT_FUNC
-		.skip 31, 0x90
-		ret
-	.endr
-
-#define HYPERCALL(n) \
-	.equ xen_hypercall_##n, hypercall_page + __HYPERVISOR_##n * 32; \
-	.type xen_hypercall_##n, @function; .size xen_hypercall_##n, 32
-#include <asm/xen-hypercalls.h>
-#undef HYPERCALL
-SYM_CODE_END(hypercall_page)
-.popsection
-
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_OS,       .asciz "linux")
 	ELFNOTE(Xen, XEN_ELFNOTE_GUEST_VERSION,  .asciz "2.6")
 	ELFNOTE(Xen, XEN_ELFNOTE_XEN_VERSION,    .asciz "xen-3.0")