Merge tag 'kvm-riscv-fixes-6.6-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv fixes for 6.6, take #1

- Fix KVM_GET_REG_LIST API for ISA_EXT registers
- Fix reading ISA_EXT register of a missing extension
- Fix ISA_EXT register handling in get-reg-list test
- Fix filtering of AIA registers in get-reg-list test

11 files changed, 97 insertions, 60 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 982b777eadc7..66bfabae8814 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1945,6 +1945,7 @@ config EFI
 	select UCS2_STRING
 	select EFI_RUNTIME_WRAPPERS
 	select ARCH_USE_MEMREMAP_PROT
+	select EFI_RUNTIME_MAP if KEXEC_CORE
 	help
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
@@ -2020,7 +2021,6 @@ config EFI_MAX_FAKE_MEM
 config EFI_RUNTIME_MAP
 	bool "Export EFI runtime maps to sysfs" if EXPERT
 	depends on EFI
-	default KEXEC_CORE
 	help
 	  Export EFI runtime memory regions to /sys/firmware/efi/runtime-map.
 	  That memory map is required by the 2nd kernel to set up EFI virtual
diff --git a/arch/x86/boot/compressed/ident_map_64.c b/arch/x86/boot/compressed/ident_map_64.c
index bcc956c17872..08f93b0401bb 100644
--- a/arch/x86/boot/compressed/ident_map_64.c
+++ b/arch/x86/boot/compressed/ident_map_64.c
@@ -59,6 +59,14 @@ static void *alloc_pgt_page(void *context)
 		return NULL;
 	}
 
+	/* Consumed more tables than expected? */
+	if (pages->pgt_buf_offset == BOOT_PGT_SIZE_WARN) {
+		debug_putstr("pgt_buf running low in " __FILE__ "\n");
+		debug_putstr("Need to raise BOOT_PGT_SIZE?\n");
+		debug_putaddr(pages->pgt_buf_offset);
+		debug_putaddr(pages->pgt_buf_size);
+	}
+
 	entry = pages->pgt_buf + pages->pgt_buf_offset;
 	pages->pgt_buf_offset += PAGE_SIZE;
 
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 4ae14339cb8c..b3a7cfb0d99e 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -40,23 +40,40 @@
 #ifdef CONFIG_X86_64
 # define BOOT_STACK_SIZE	0x4000
 
+/*
+ * Used by decompressor's startup_32() to allocate page tables for identity
+ * mapping of the 4G of RAM in 4-level paging mode:
+ * - 1 level4 table;
+ * - 1 level3 table;
+ * - 4 level2 table that maps everything with 2M pages;
+ *
+ * The additional level5 table needed for 5-level paging is allocated from
+ * trampoline_32bit memory.
+ */
 # define BOOT_INIT_PGT_SIZE	(6*4096)
-# ifdef CONFIG_RANDOMIZE_BASE
+
 /*
- * Assuming all cross the 512GB boundary:
- * 1 page for level4
- * (2+2)*4 pages for kernel, param, cmd_line, and randomized kernel
- * 2 pages for first 2M (video RAM: CONFIG_X86_VERBOSE_BOOTUP).
- * Total is 19 pages.
+ * Total number of page tables kernel_add_identity_map() can allocate,
+ * including page tables consumed by startup_32().
+ *
+ * Worst-case scenario:
+ *  - 5-level paging needs 1 level5 table;
+ *  - KASLR needs to map kernel, boot_params, cmdline and randomized kernel,
+ *    assuming all of them cross 256T boundary:
+ *    + 4*2 level4 table;
+ *    + 4*2 level3 table;
+ *    + 4*2 level2 table;
+ *  - X86_VERBOSE_BOOTUP needs to map the first 2M (video RAM):
+ *    + 1 level4 table;
+ *    + 1 level3 table;
+ *    + 1 level2 table;
+ * Total: 28 tables
+ *
+ * Add 4 spare table in case decompressor touches anything beyond what is
+ * accounted above. Warn if it happens.
  */
-#  ifdef CONFIG_X86_VERBOSE_BOOTUP
-#   define BOOT_PGT_SIZE	(19*4096)
-#  else /* !CONFIG_X86_VERBOSE_BOOTUP */
-#   define BOOT_PGT_SIZE	(17*4096)
-#  endif
-# else /* !CONFIG_RANDOMIZE_BASE */
-#  define BOOT_PGT_SIZE		BOOT_INIT_PGT_SIZE
-# endif
+# define BOOT_PGT_SIZE_WARN	(28*4096)
+# define BOOT_PGT_SIZE		(32*4096)
 
 #else /* !CONFIG_X86_64 */
 # define BOOT_STACK_SIZE	0x1000
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index b0994ae3bc23..c4555b269a1b 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -91,19 +91,6 @@ static inline void efi_fpu_end(void)
 
 #ifdef CONFIG_X86_32
 #define EFI_X86_KERNEL_ALLOC_LIMIT		(SZ_512M - 1)
-
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-})
-
-#define arch_efi_call_virt_teardown()					\
-({									\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #else /* !CONFIG_X86_32 */
 #define EFI_X86_KERNEL_ALLOC_LIMIT		EFI_ALLOC_LIMIT
 
@@ -116,14 +103,6 @@ extern bool efi_disable_ibt_for_runtime;
 	__efi_call(__VA_ARGS__);					\
 })
 
-#define arch_efi_call_virt_setup()					\
-({									\
-	efi_sync_low_kernel_mappings();					\
-	efi_fpu_begin();						\
-	firmware_restrict_branch_speculation_start();			\
-	efi_enter_mm();							\
-})
-
 #undef arch_efi_call_virt
 #define arch_efi_call_virt(p, f, args...) ({				\
 	u64 ret, ibt = ibt_save(efi_disable_ibt_for_runtime);		\
@@ -132,13 +111,6 @@ extern bool efi_disable_ibt_for_runtime;
 	ret;								\
 })
 
-#define arch_efi_call_virt_teardown()					\
-({									\
-	efi_leave_mm();							\
-	firmware_restrict_branch_speculation_end();			\
-	efi_fpu_end();							\
-})
-
 #ifdef CONFIG_KASAN
 /*
  * CONFIG_KASAN may redefine memset to __memset.  __memset function is present
@@ -168,8 +140,8 @@ extern void efi_delete_dummy_variable(void);
 extern void efi_crash_gracefully_on_page_fault(unsigned long phys_addr);
 extern void efi_free_boot_services(void);
 
-void efi_enter_mm(void);
-void efi_leave_mm(void);
+void arch_efi_call_virt_setup(void);
+void arch_efi_call_virt_teardown(void);
 
 /* kexec external ABI */
 struct efi_setup_data {
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 97a3de7892d3..5ff49fd67732 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -8,6 +8,14 @@
 #undef notrace
 #define notrace __attribute__((no_instrument_function))
 
+#ifdef CONFIG_64BIT
+/*
+ * The generic version tends to create spurious ENDBR instructions under
+ * certain conditions.
+ */
+#define _THIS_IP_ ({ unsigned long __here; asm ("lea 0(%%rip), %0" : "=r" (__here)); __here; })
+#endif
+
 #ifdef CONFIG_X86_32
 #define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
 #endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d9f5d7492f83..205cee567629 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -1533,7 +1533,7 @@ static void __init build_socket_tables(void)
 {
 	struct uv_gam_range_entry *gre = uv_gre_table;
 	int nums, numn, nump;
-	int cpu, i, lnid;
+	int i, lnid, apicid;
 	int minsock = _min_socket;
 	int maxsock = _max_socket;
 	int minpnode = _min_pnode;
@@ -1584,15 +1584,14 @@ static void __init build_socket_tables(void)
 
 	/* Set socket -> node values: */
 	lnid = NUMA_NO_NODE;
-	for_each_possible_cpu(cpu) {
-		int nid = cpu_to_node(cpu);
-		int apicid, sockid;
+	for (apicid = 0; apicid < ARRAY_SIZE(__apicid_to_node); apicid++) {
+		int nid = __apicid_to_node[apicid];
+		int sockid;
 
-		if (lnid == nid)
+		if ((nid == NUMA_NO_NODE) || (lnid == nid))
 			continue;
 		lnid = nid;
 
-		apicid = per_cpu(x86_cpu_to_apicid, cpu);
 		sockid = apicid >> uv_cpuid.socketid_shift;
 
 		if (_socket_to_node[sockid - minsock] == SOCK_EMPTY)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 4e45ff44aa07..48e040618731 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -579,7 +579,6 @@ static bool match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 }
 
 
-#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_CLUSTER) || defined(CONFIG_SCHED_MC)
 static inline int x86_sched_itmt_flags(void)
 {
 	return sysctl_sched_itmt_enabled ? SD_ASYM_PACKING : 0;
@@ -603,7 +602,14 @@ static int x86_cluster_flags(void)
 	return cpu_cluster_flags() | x86_sched_itmt_flags();
 }
 #endif
-#endif
+
+static int x86_die_flags(void)
+{
+	if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+	       return x86_sched_itmt_flags();
+
+	return 0;
+}
 
 /*
  * Set if a package/die has multiple NUMA nodes inside.
@@ -640,7 +646,7 @@ static void __init build_sched_topology(void)
 	 */
 	if (!x86_has_numa_in_package) {
 		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, SD_INIT_NAME(DIE)
+			cpu_cpu_mask, x86_die_flags, SD_INIT_NAME(DIE)
 		};
 	}
 
diff --git a/arch/x86/lib/putuser.S b/arch/x86/lib/putuser.S
index 1451e0c4ae22..235bbda6fc82 100644
--- a/arch/x86/lib/putuser.S
+++ b/arch/x86/lib/putuser.S
@@ -56,7 +56,6 @@ SYM_FUNC_END(__put_user_1)
 EXPORT_SYMBOL(__put_user_1)
 
 SYM_FUNC_START(__put_user_nocheck_1)
-	ENDBR
 	ASM_STAC
 2:	movb %al,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -76,7 +75,6 @@ SYM_FUNC_END(__put_user_2)
 EXPORT_SYMBOL(__put_user_2)
 
 SYM_FUNC_START(__put_user_nocheck_2)
-	ENDBR
 	ASM_STAC
 4:	movw %ax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -96,7 +94,6 @@ SYM_FUNC_END(__put_user_4)
 EXPORT_SYMBOL(__put_user_4)
 
 SYM_FUNC_START(__put_user_nocheck_4)
-	ENDBR
 	ASM_STAC
 6:	movl %eax,(%_ASM_CX)
 	xor %ecx,%ecx
@@ -119,7 +116,6 @@ SYM_FUNC_END(__put_user_8)
 EXPORT_SYMBOL(__put_user_8)
 
 SYM_FUNC_START(__put_user_nocheck_8)
-	ENDBR
 	ASM_STAC
 9:	mov %_ASM_AX,(%_ASM_CX)
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/platform/efi/efi_32.c b/arch/x86/platform/efi/efi_32.c
index e06a199423c0..b2cc7b4552a1 100644
--- a/arch/x86/platform/efi/efi_32.c
+++ b/arch/x86/platform/efi/efi_32.c
@@ -140,3 +140,15 @@ void __init efi_runtime_update_mappings(void)
 		}
 	}
 }
+
+void arch_efi_call_virt_setup(void)
+{
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77f7ac3668cb..91d31ac422d6 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -474,19 +474,34 @@ void __init efi_dump_pagetable(void)
  * can not change under us.
  * It should be ensured that there are no concurrent calls to this function.
  */
-void efi_enter_mm(void)
+static void efi_enter_mm(void)
 {
 	efi_prev_mm = current->active_mm;
 	current->active_mm = &efi_mm;
 	switch_mm(efi_prev_mm, &efi_mm, NULL);
 }
 
-void efi_leave_mm(void)
+static void efi_leave_mm(void)
 {
 	current->active_mm = efi_prev_mm;
 	switch_mm(&efi_mm, efi_prev_mm, NULL);
 }
 
+void arch_efi_call_virt_setup(void)
+{
+	efi_sync_low_kernel_mappings();
+	efi_fpu_begin();
+	firmware_restrict_branch_speculation_start();
+	efi_enter_mm();
+}
+
+void arch_efi_call_virt_teardown(void)
+{
+	efi_leave_mm();
+	firmware_restrict_branch_speculation_end();
+	efi_fpu_end();
+}
+
 static DEFINE_SPINLOCK(efi_runtime_lock);
 
 /*
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index c2a29be35c01..08aa0f25f12a 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -19,6 +19,10 @@ CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
 # optimization flags.
 KBUILD_CFLAGS := $(filter-out -fprofile-sample-use=% -fprofile-use=%,$(KBUILD_CFLAGS))
 
+# When LTO is enabled, llvm emits many text sections, which is not supported
+# by kexec. Remove -flto=* flags.
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+
 # When linking purgatory.ro with -r unresolved symbols are not checked,
 # also link a purgatory.chk binary without -r to check for unresolved symbols.
 PURGATORY_LDFLAGS := -e purgatory_start -z nodefaultlib