Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/…

…linux/kernel/git/tip/tip

Pull perf updates from Thomas Gleixner:
 "Kernel:
   - Improve kallsyms coverage
   - Add x86 entry trampolines to kcore
   - Fix ARM SPE handling
   - Correct PPC event post processing

  Tools:
   - Make the build system more robust
   - Small fixes and enhancements all over the place
   - Update kernel ABI header copies
   - Preparatory work for converting libtraceevnt to a shared library
   - License cleanups"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (100 commits)
  tools arch: Update arch/x86/lib/memcpy_64.S copy used in 'perf bench mem memcpy'
  tools arch x86: Update tools's copy of cpufeatures.h
  perf python: Fix pyrf_evlist__read_on_cpu() interface
  perf mmap: Store real cpu number in 'struct perf_mmap'
  perf tools: Remove ext from struct kmod_path
  perf tools: Add gzip_is_compressed function
  perf tools: Add lzma_is_compressed function
  perf tools: Add is_compressed callback to compressions array
  perf tools: Move the temp file processing into decompress_kmodule
  perf tools: Use compression id in decompress_kmodule()
  perf tools: Store compression id into struct dso
  perf tools: Add compression id into 'struct kmod_path'
  perf tools: Make is_supported_compression() static
  perf tools: Make decompress_to_file() function static
  perf tools: Get rid of dso__needs_decompress() call in __open_dso()
  perf tools: Get rid of dso__needs_decompress() call in symbol__disassemble()
  perf tools: Get rid of dso__needs_decompress() call in read_object_code()
  tools lib traceevent: Change to SPDX License format
  perf llvm: Allow passing options to llc in addition to clang
  perf parser: Improve error message for PMU address filters
  ...

arch/x86/mm/cpu_entry_area.c

@@ -2,6 +2,8 @@
 
 #include <linux/spinlock.h>
 #include <linux/percpu.h>
+#include <linux/kallsyms.h>
+#include <linux/kcore.h>
 
 #include <asm/cpu_entry_area.h>
 #include <asm/pgtable.h>
@@ -13,6 +15,7 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage)
 #ifdef CONFIG_X86_64
 static DEFINE_PER_CPU_PAGE_ALIGNED(char, exception_stacks
 	[(N_EXCEPTION_STACKS - 1) * EXCEPTION_STKSZ + DEBUG_STKSZ]);
+static DEFINE_PER_CPU(struct kcore_list, kcore_entry_trampoline);
 #endif
 
 struct cpu_entry_area *get_cpu_entry_area(int cpu)
@@ -146,10 +149,40 @@ static void __init setup_cpu_entry_area(int cpu)
 
 	cea_set_pte(&get_cpu_entry_area(cpu)->entry_trampoline,
 		     __pa_symbol(_entry_trampoline), PAGE_KERNEL_RX);
+	/*
+	 * The cpu_entry_area alias addresses are not in the kernel binary
+	 * so they do not show up in /proc/kcore normally.  This adds entries
+	 * for them manually.
+	 */
+	kclist_add_remap(&per_cpu(kcore_entry_trampoline, cpu),
+			 _entry_trampoline,
+			 &get_cpu_entry_area(cpu)->entry_trampoline, PAGE_SIZE);
 #endif
 	percpu_setup_debug_store(cpu);
 }
 
+#ifdef CONFIG_X86_64
+int arch_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
+		     char *name)
+{
+	unsigned int cpu, ncpu = 0;
+
+	if (symnum >= num_possible_cpus())
+		return -EINVAL;
+
+	for_each_possible_cpu(cpu) {
+		if (ncpu++ >= symnum)
+			break;
+	}
+
+	*value = (unsigned long)&get_cpu_entry_area(cpu)->entry_trampoline;
+	*type = 't';
+	strlcpy(name, "__entry_SYSCALL_64_trampoline", KSYM_NAME_LEN);
+
+	return 0;
+}
+#endif
+
 static __init void setup_cpu_entry_area_ptes(void)
 {
 #ifdef CONFIG_X86_32

fs/proc/kcore.c

@@ -359,8 +359,11 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 			phdr->p_type = PT_LOAD;
 			phdr->p_flags = PF_R | PF_W | PF_X;
 			phdr->p_offset = kc_vaddr_to_offset(m->addr) + data_offset;
-			phdr->p_vaddr = (size_t)m->addr;
-			if (m->type == KCORE_RAM)
+			if (m->type == KCORE_REMAP)
+				phdr->p_vaddr = (size_t)m->vaddr;
+			else
+				phdr->p_vaddr = (size_t)m->addr;
+			if (m->type == KCORE_RAM || m->type == KCORE_REMAP)
 				phdr->p_paddr = __pa(m->addr);
 			else if (m->type == KCORE_TEXT)
 				phdr->p_paddr = __pa_symbol(m->addr);

include/linux/kcore.h

@@ -12,11 +12,13 @@ enum kcore_type {
 	KCORE_VMEMMAP,
 	KCORE_USER,
 	KCORE_OTHER,
+	KCORE_REMAP,
 };
 
 struct kcore_list {
 	struct list_head list;
 	unsigned long addr;
+	unsigned long vaddr;
 	size_t size;
 	int type;
 };
@@ -36,11 +38,22 @@ struct vmcoredd_node {
 
 #ifdef CONFIG_PROC_KCORE
 void __init kclist_add(struct kcore_list *, void *, size_t, int type);
+static inline
+void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
+{
+	m->vaddr = (unsigned long)vaddr;
+	kclist_add(m, addr, sz, KCORE_REMAP);
+}
 #else
 static inline
 void kclist_add(struct kcore_list *new, void *addr, size_t size, int type)
 {
 }
+
+static inline
+void kclist_add_remap(struct kcore_list *m, void *addr, void *vaddr, size_t sz)
+{
+}
 #endif
 
 #endif /* _LINUX_KCORE_H */

kernel/kallsyms.c

@@ -432,6 +432,7 @@ int sprint_backtrace(char *buffer, unsigned long address)
 /* To avoid using get_symbol_offset for every symbol, we carry prefix along. */
 struct kallsym_iter {
 	loff_t pos;
+	loff_t pos_arch_end;
 	loff_t pos_mod_end;
 	loff_t pos_ftrace_mod_end;
 	unsigned long value;
@@ -443,9 +444,29 @@ struct kallsym_iter {
 	int show_value;
 };
 
+int __weak arch_get_kallsym(unsigned int symnum, unsigned long *value,
+			    char *type, char *name)
+{
+	return -EINVAL;
+}
+
+static int get_ksymbol_arch(struct kallsym_iter *iter)
+{
+	int ret = arch_get_kallsym(iter->pos - kallsyms_num_syms,
+				   &iter->value, &iter->type,
+				   iter->name);
+
+	if (ret < 0) {
+		iter->pos_arch_end = iter->pos;
+		return 0;
+	}
+
+	return 1;
+}
+
 static int get_ksymbol_mod(struct kallsym_iter *iter)
 {
-	int ret = module_get_kallsym(iter->pos - kallsyms_num_syms,
+	int ret = module_get_kallsym(iter->pos - iter->pos_arch_end,
 				     &iter->value, &iter->type,
 				     iter->name, iter->module_name,
 				     &iter->exported);
@@ -501,32 +522,34 @@ static void reset_iter(struct kallsym_iter *iter, loff_t new_pos)
 	iter->nameoff = get_symbol_offset(new_pos);
 	iter->pos = new_pos;
 	if (new_pos == 0) {
+		iter->pos_arch_end = 0;
 		iter->pos_mod_end = 0;
 		iter->pos_ftrace_mod_end = 0;
 	}
 }
 
+/*
+ * The end position (last + 1) of each additional kallsyms section is recorded
+ * in iter->pos_..._end as each section is added, and so can be used to
+ * determine which get_ksymbol_...() function to call next.
+ */
 static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 {
 	iter->pos = pos;
 
-	if (iter->pos_ftrace_mod_end > 0 &&
-	    iter->pos_ftrace_mod_end < iter->pos)
-		return get_ksymbol_bpf(iter);
+	if ((!iter->pos_arch_end || iter->pos_arch_end > pos) &&
+	    get_ksymbol_arch(iter))
+		return 1;
 
-	if (iter->pos_mod_end > 0 &&
-	    iter->pos_mod_end < iter->pos) {
-		if (!get_ksymbol_ftrace_mod(iter))
-			return get_ksymbol_bpf(iter);
+	if ((!iter->pos_mod_end || iter->pos_mod_end > pos) &&
+	    get_ksymbol_mod(iter))
 		return 1;
-	}
 
-	if (!get_ksymbol_mod(iter)) {
-		if (!get_ksymbol_ftrace_mod(iter))
-			return get_ksymbol_bpf(iter);
-	}
+	if ((!iter->pos_ftrace_mod_end || iter->pos_ftrace_mod_end > pos) &&
+	    get_ksymbol_ftrace_mod(iter))
+		return 1;
 
-	return 1;
+	return get_ksymbol_bpf(iter);
 }
 
 /* Returns false if pos at or past end of file. */

tools/arch/x86/include/asm/cpufeatures.h

@@ -220,6 +220,7 @@
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
 #define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
+#define X86_FEATURE_IBRS_ENHANCED	( 7*32+30) /* Enhanced IBRS */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -230,7 +231,7 @@
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
-
+#define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/

tools/arch/x86/lib/memcpy_64.S

@@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe)
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
-	xorq %rax, %rax
+	xorl %eax, %eax
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)

tools/lib/lockdep/Makefile

@@ -129,12 +129,12 @@ $(OUTPUT)liblockdep.a: $(LIB_IN)
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
-	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+	--regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/'
 
 TAGS:	force
 	$(RM) TAGS
 	find . -name '*.[ch]' | xargs etags \
-	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+	--regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/'
 
 define do_install
 	$(print_install)				\

tools/lib/traceevent/Makefile

@@ -233,12 +233,12 @@ endef
 tags:	force
 	$(RM) tags
 	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
-	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+	--regex-c++='/_PE\(([^,)]*).*/TEP_ERRNO__\1/'
 
 TAGS:	force
 	$(RM) TAGS
 	find . -name '*.[ch]' | xargs etags \
-	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+	--regex='/_PE(\([^,)]*\).*/TEP_ERRNO__\1/'
 
 define do_install_mkdir
 	if [ ! -d '$(DESTDIR_SQ)$1' ]; then		\