Merge branch 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux

Pull turbostat utility updates for v4.18 from Len Brown.

* 'turbostat' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux: (65 commits)
  tools/power turbostat: update version number
  tools/power turbostat: Add Node in output
  tools/power turbostat: add node information into turbostat calculations
  tools/power turbostat: remove num_ from cpu_topology struct
  tools/power turbostat: rename num_cores_per_pkg to num_cores_per_node
  tools/power turbostat: track thread ID in cpu_topology
  tools/power turbostat: Calculate additional node information for a package
  tools/power turbostat: Fix node and siblings lookup data
  tools/power turbostat: set max_num_cpus equal to the cpumask length
  tools/power turbostat: if --num_iterations, print for specific number of iterations
  tools/power turbostat: Add Cannon Lake support
  tools/power turbostat: delete duplicate #defines
  x86: msr-index.h: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: add POLL and POLL% column
  tools/power turbostat: Fix --hide Pk%pc10
  tools/power turbostat: Build-in "Low Power Idle" counters support
  tools/power turbostat: Don't make man pages executable
  tools/power turbostat: remove blank lines
  tools/power turbostat: a small C-states dump readability immprovement
  ...

38 files changed, 894 insertions, 357 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index ca4afd68530c..0d00b6c5370b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14371,6 +14371,15 @@ S:	Maintained
 F:      drivers/tc/
 F:      include/linux/tc.h
 
+TURBOSTAT UTILITY
+M:      "Len Brown" <lenb@kernel.org>
+L:      linux-pm@vger.kernel.org
+B:      https://bugzilla.kernel.org
+Q:      https://patchwork.kernel.org/project/linux-pm/list/
+T:      git git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat
+S:      Supported
+F:      tools/power/x86/turbostat/
+
 TW5864 VIDEO4LINUX DRIVER
 M:      Bluecherry Maintainers <maintainers@bluecherrydvr.com>
 M:      Anton Sviridenko <anton@corp.bluecherry.net>
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 249f38d3388f..b7404f2dcf5b 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -9,6 +9,12 @@ config NDS32
         select CLKSRC_MMIO
         select CLONE_BACKWARDS
         select COMMON_CLK
+        select GENERIC_ASHLDI3
+        select GENERIC_ASHRDI3
+        select GENERIC_LSHRDI3
+        select GENERIC_CMPDI2
+        select GENERIC_MULDI3
+        select GENERIC_UCMPDI2
         select GENERIC_ATOMIC64
         select GENERIC_CPU_DEVICES
         select GENERIC_CLOCKEVENTS
@@ -82,6 +88,7 @@ endmenu
 
 menu "Kernel Features"
 source "kernel/Kconfig.preempt"
+source "kernel/Kconfig.freezer"
 source "mm/Kconfig"
 source "kernel/Kconfig.hz"
 endmenu
diff --git a/arch/nds32/Kconfig.cpu b/arch/nds32/Kconfig.cpu
index ba44cc539da9..b8c8984d1456 100644
--- a/arch/nds32/Kconfig.cpu
+++ b/arch/nds32/Kconfig.cpu
@@ -1,10 +1,11 @@
 comment "Processor Features"
 
 config CPU_BIG_ENDIAN
-        bool "Big endian"
+        def_bool !CPU_LITTLE_ENDIAN
 
 config CPU_LITTLE_ENDIAN
-        def_bool !CPU_BIG_ENDIAN
+        bool "Little endian"
+        default y
 
 config HWZOL
         bool "hardware zero overhead loop support"
diff --git a/arch/nds32/Makefile b/arch/nds32/Makefile
index 91f933d5a962..513bb2e9baf9 100644
--- a/arch/nds32/Makefile
+++ b/arch/nds32/Makefile
@@ -23,9 +23,6 @@ export	TEXTADDR
 # If we have a machine-specific directory, then include it in the build.
 core-y                          += arch/nds32/kernel/ arch/nds32/mm/
 libs-y                          += arch/nds32/lib/
-LIBGCC_PATH                     := \
-  $(shell $(CC) $(KBUILD_CFLAGS) $(KCFLAGS) -print-libgcc-file-name)
-libs-y                          += $(LIBGCC_PATH)
 
 ifneq '$(CONFIG_NDS32_BUILTIN_DTB)' '""'
 BUILTIN_DTB := y
@@ -35,8 +32,12 @@ endif
 
 ifdef CONFIG_CPU_LITTLE_ENDIAN
 KBUILD_CFLAGS   += $(call cc-option, -EL)
+KBUILD_AFLAGS   += $(call cc-option, -EL)
+LDFLAGS         += $(call cc-option, -EL)
 else
 KBUILD_CFLAGS   += $(call cc-option, -EB)
+KBUILD_AFLAGS   += $(call cc-option, -EB)
+LDFLAGS         += $(call cc-option, -EB)
 endif
 
 boot := arch/nds32/boot
diff --git a/arch/nds32/include/asm/Kbuild b/arch/nds32/include/asm/Kbuild
index 06bdf8167f5a..142e612aa639 100644
--- a/arch/nds32/include/asm/Kbuild
+++ b/arch/nds32/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += dma.h
 generic-y += emergency-restart.h
 generic-y += errno.h
 generic-y += exec.h
+generic-y += export.h
 generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ftrace.h
@@ -49,6 +50,7 @@ generic-y += switch_to.h
 generic-y += timex.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += xor.h
 generic-y += unaligned.h
 generic-y += user.h
 generic-y += vga.h
diff --git a/arch/nds32/include/asm/bitfield.h b/arch/nds32/include/asm/bitfield.h
index c73f71d67744..8e84fc385b94 100644
--- a/arch/nds32/include/asm/bitfield.h
+++ b/arch/nds32/include/asm/bitfield.h
@@ -336,7 +336,7 @@
 #define INT_MASK_mskIDIVZE      ( 0x1  << INT_MASK_offIDIVZE )
 #define INT_MASK_mskDSSIM       ( 0x1  << INT_MASK_offDSSIM )
 
-#define INT_MASK_INITAIAL_VAL   0x10003
+#define INT_MASK_INITAIAL_VAL   (INT_MASK_mskDSSIM|INT_MASK_mskIDIVZE)
 
 /******************************************************************************
  * ir15: INT_PEND (Interrupt Pending Register)
@@ -396,6 +396,7 @@
 #define MMU_CTL_D8KB            1
 #define MMU_CTL_UNA             ( 0x1  << MMU_CTL_offUNA )
 
+#define MMU_CTL_CACHEABLE_NON   0
 #define MMU_CTL_CACHEABLE_WB    2
 #define MMU_CTL_CACHEABLE_WT    3
 
diff --git a/arch/nds32/include/asm/cacheflush.h b/arch/nds32/include/asm/cacheflush.h
index 1240f148ec0f..10b48f0d8e85 100644
--- a/arch/nds32/include/asm/cacheflush.h
+++ b/arch/nds32/include/asm/cacheflush.h
@@ -32,6 +32,8 @@ void flush_anon_page(struct vm_area_struct *vma,
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 void flush_kernel_dcache_page(struct page *page);
+void flush_kernel_vmap_range(void *addr, int size);
+void invalidate_kernel_vmap_range(void *addr, int size);
 void flush_icache_range(unsigned long start, unsigned long end);
 void flush_icache_page(struct vm_area_struct *vma, struct page *page);
 #define flush_dcache_mmap_lock(mapping)   xa_lock_irq(&(mapping)->i_pages)
diff --git a/arch/nds32/include/asm/io.h b/arch/nds32/include/asm/io.h
index 966e71b3c960..71cd226d6863 100644
--- a/arch/nds32/include/asm/io.h
+++ b/arch/nds32/include/asm/io.h
@@ -4,6 +4,8 @@
 #ifndef __ASM_NDS32_IO_H
 #define __ASM_NDS32_IO_H
 
+#include <linux/types.h>
+
 extern void iounmap(volatile void __iomem *addr);
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
diff --git a/arch/nds32/include/asm/page.h b/arch/nds32/include/asm/page.h
index e27365c097b6..947f0491c9a7 100644
--- a/arch/nds32/include/asm/page.h
+++ b/arch/nds32/include/asm/page.h
@@ -27,6 +27,9 @@ extern void copy_user_highpage(struct page *to, struct page *from,
                                unsigned long vaddr, struct vm_area_struct *vma);
 extern void clear_user_highpage(struct page *page, unsigned long vaddr);
 
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+                    struct page *to);
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page);
 #define __HAVE_ARCH_COPY_USER_HIGHPAGE
 #define clear_user_highpage     clear_user_highpage
 #else
diff --git a/arch/nds32/include/asm/pgtable.h b/arch/nds32/include/asm/pgtable.h
index 6783937edbeb..d3e19a55cf53 100644
--- a/arch/nds32/include/asm/pgtable.h
+++ b/arch/nds32/include/asm/pgtable.h
@@ -152,6 +152,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define PAGE_CACHE_L1   __pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE)
 #define PAGE_MEMORY     __pgprot(_HAVE_PAGE_L | _PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
 #define PAGE_KERNEL     __pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_E | _PAGE_G | _PAGE_CACHE_SHRD)
+#define PAGE_SHARED     __pgprot(_PAGE_V | _PAGE_M_URW_KRW | _PAGE_D | _PAGE_CACHE_SHRD)
 #define PAGE_DEVICE    __pgprot(_PAGE_V | _PAGE_M_KRW | _PAGE_D | _PAGE_G | _PAGE_C_DEV)
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/nds32/kernel/ex-entry.S b/arch/nds32/kernel/ex-entry.S
index a72e83d804f5..b8ae4e9a6b93 100644
--- a/arch/nds32/kernel/ex-entry.S
+++ b/arch/nds32/kernel/ex-entry.S
@@ -118,7 +118,7 @@ common_exception_handler:
         /* interrupt */
 2:
 #ifdef CONFIG_TRACE_IRQFLAGS
-        jal     arch_trace_hardirqs_off
+        jal     trace_hardirqs_off
 #endif
         move    $r0, $sp
         sethi   $lp, hi20(ret_from_intr)
diff --git a/arch/nds32/kernel/head.S b/arch/nds32/kernel/head.S
index 71f57bd70f3b..c5fdae174ced 100644
--- a/arch/nds32/kernel/head.S
+++ b/arch/nds32/kernel/head.S
@@ -57,14 +57,32 @@ _nodtb:
         isb
         mtsr    $r4, $L1_PPTB       ! load page table pointer\n"
 
-/* set NTC0 cacheable/writeback, mutliple page size in use */
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+        #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_NON
+#else
+        #ifdef CONFIG_CPU_DCACHE_WRITETHROUGH
+                #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WT
+        #else
+                #define MMU_CTL_NTCC MMU_CTL_CACHEABLE_WB
+        #endif
+#endif
+
+/* set NTC cacheability, mutliple page size in use */
         mfsr    $r3, $MMU_CTL
-        li      $r0, #~MMU_CTL_mskNTC0
-        and     $r3, $r3, $r0
+#if CONFIG_MEMORY_START >= 0xc0000000
+        ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC3)
+#elif CONFIG_MEMORY_START >= 0x80000000
+        ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC2)
+#elif CONFIG_MEMORY_START >= 0x40000000
+        ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC1)
+#else
+        ori     $r3, $r3, (MMU_CTL_NTCC << MMU_CTL_offNTC0)
+#endif
+
 #ifdef CONFIG_ANDES_PAGE_SIZE_4KB
-        ori     $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0))
+        ori     $r3, $r3, #(MMU_CTL_mskMPZIU)
 #else
-        ori     $r3, $r3, #(MMU_CTL_mskMPZIU|(MMU_CTL_CACHEABLE_WB << MMU_CTL_offNTC0)|MMU_CTL_D8KB)
+        ori     $r3, $r3, #(MMU_CTL_mskMPZIU|MMU_CTL_D8KB)
 #endif
 #ifdef CONFIG_HW_SUPPORT_UNALIGNMENT_ACCESS
         li      $r0, #MMU_CTL_UNA
diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c
index ba910e9e4ecb..2f5b2ccebe47 100644
--- a/arch/nds32/kernel/setup.c
+++ b/arch/nds32/kernel/setup.c
@@ -293,6 +293,9 @@ void __init setup_arch(char **cmdline_p)
         /* paging_init() sets up the MMU and marks all pages as reserved */
         paging_init();
 
+        /* invalidate all TLB entries because the new mapping is created */
+        __nds32__tlbop_flua();
+
         /* use generic way to parse */
         parse_early_param();
 
diff --git a/arch/nds32/kernel/stacktrace.c b/arch/nds32/kernel/stacktrace.c
index bc70113c0e84..8b231e910ea6 100644
--- a/arch/nds32/kernel/stacktrace.c
+++ b/arch/nds32/kernel/stacktrace.c
@@ -9,6 +9,7 @@ void save_stack_trace(struct stack_trace *trace)
 {
         save_stack_trace_tsk(current, trace);
 }
+EXPORT_SYMBOL_GPL(save_stack_trace);
 
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
@@ -45,3 +46,4 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
                 fpn = (unsigned long *)fpp;
         }
 }
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/nds32/kernel/vdso.c b/arch/nds32/kernel/vdso.c
index f1198d7a5654..016f15891f6d 100644
--- a/arch/nds32/kernel/vdso.c
+++ b/arch/nds32/kernel/vdso.c
@@ -23,7 +23,7 @@
 #include <asm/vdso_timer_info.h>
 #include <asm/cache_info.h>
 extern struct cache_info L1_cache_info[2];
-extern char vdso_start, vdso_end;
+extern char vdso_start[], vdso_end[];
 static unsigned long vdso_pages __ro_after_init;
 static unsigned long timer_mapping_base;
 
@@ -66,16 +66,16 @@ static int __init vdso_init(void)
         int i;
         struct page **vdso_pagelist;
 
-        if (memcmp(&vdso_start, "\177ELF", 4)) {
+        if (memcmp(vdso_start, "\177ELF", 4)) {
                 pr_err("vDSO is not a valid ELF object!\n");
                 return -EINVAL;
         }
         /* Creat a timer io mapping to get clock cycles counter */
         get_timer_node_info();
 
-        vdso_pages = (&vdso_end - &vdso_start) >> PAGE_SHIFT;
+        vdso_pages = (vdso_end - vdso_start) >> PAGE_SHIFT;
         pr_info("vdso: %ld pages (%ld code @ %p, %ld data @ %p)\n",
-                vdso_pages + 1, vdso_pages, &vdso_start, 1L, vdso_data);
+                vdso_pages + 1, vdso_pages, vdso_start, 1L, vdso_data);
 
         /* Allocate the vDSO pagelist */
         vdso_pagelist = kcalloc(vdso_pages, sizeof(struct page *), GFP_KERNEL);
@@ -83,7 +83,7 @@ static int __init vdso_init(void)
                 return -ENOMEM;
 
         for (i = 0; i < vdso_pages; i++)
-                vdso_pagelist[i] = virt_to_page(&vdso_start + i * PAGE_SIZE);
+                vdso_pagelist[i] = virt_to_page(vdso_start + i * PAGE_SIZE);
         vdso_spec[1].pages = &vdso_pagelist[0];
 
         return 0;
diff --git a/arch/nds32/lib/copy_page.S b/arch/nds32/lib/copy_page.S
index 4a2ff85f17ee..f8701ed161a8 100644
--- a/arch/nds32/lib/copy_page.S
+++ b/arch/nds32/lib/copy_page.S
@@ -2,6 +2,7 @@
 // Copyright (C) 2005-2017 Andes Technology Corporation
 
 #include <linux/linkage.h>
+#include <asm/export.h>
 #include <asm/page.h>
 
         .text
@@ -16,6 +17,7 @@ ENTRY(copy_page)
         popm    $r2, $r10
         ret
 ENDPROC(copy_page)
+EXPORT_SYMBOL(copy_page)
 
 ENTRY(clear_page)
         pushm   $r1, $r9
@@ -35,3 +37,4 @@ ENTRY(clear_page)
         popm    $r1, $r9
         ret
 ENDPROC(clear_page)
+EXPORT_SYMBOL(clear_page)
diff --git a/arch/nds32/mm/alignment.c b/arch/nds32/mm/alignment.c
index b96a01b10ca7..e1aed9dc692d 100644
--- a/arch/nds32/mm/alignment.c
+++ b/arch/nds32/mm/alignment.c
@@ -19,7 +19,7 @@
 #define RA(inst)        (((inst) >> 15) & 0x1FUL)
 #define RB(inst)        (((inst) >> 10) & 0x1FUL)
 #define SV(inst)        (((inst) >> 8) & 0x3UL)
-#define IMM(inst)       (((inst) >> 0) & 0x3FFFUL)
+#define IMM(inst)       (((inst) >> 0) & 0x7FFFUL)
 
 #define RA3(inst)       (((inst) >> 3) & 0x7UL)
 #define RT3(inst)       (((inst) >> 6) & 0x7UL)
@@ -28,6 +28,9 @@
 #define RA5(inst)       (((inst) >> 0) & 0x1FUL)
 #define RT4(inst)       (((inst) >> 5) & 0xFUL)
 
+#define GET_IMMSVAL(imm_value) \
+        (((imm_value >> 14) & 0x1) ? (imm_value - 0x8000) : imm_value)
+
 #define __get8_data(val,addr,err)       \
         __asm__(                                        \
         "1:     lbi.bi  %1, [%2], #1\n"                 \
@@ -467,7 +470,7 @@ static inline int do_32(unsigned long inst, struct pt_regs *regs)
         }
 
         if (imm)
-                shift = IMM(inst) * len;
+                shift = GET_IMMSVAL(IMM(inst)) * len;
         else
                 shift = *idx_to_addr(regs, RB(inst)) << SV(inst);
 
@@ -552,7 +555,7 @@ static struct ctl_table alignment_tbl[3] = {
 
 static struct ctl_table nds32_sysctl_table[2] = {
         {
-         .procname = "unaligned_acess",
+         .procname = "unaligned_access",
          .mode = 0555,
          .child = alignment_tbl},
         {}
diff --git a/arch/nds32/mm/cacheflush.c b/arch/nds32/mm/cacheflush.c
index 6eb786a399a2..ce8fd34497bf 100644
--- a/arch/nds32/mm/cacheflush.c
+++ b/arch/nds32/mm/cacheflush.c
@@ -147,6 +147,25 @@ void flush_cache_vunmap(unsigned long start, unsigned long end)
         cpu_icache_inval_all();
 }
 
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+                    struct page *to)
+{
+        cpu_dcache_wbinval_page((unsigned long)vaddr);
+        cpu_icache_inval_page((unsigned long)vaddr);
+        copy_page(vto, vfrom);
+        cpu_dcache_wbinval_page((unsigned long)vto);
+        cpu_icache_inval_page((unsigned long)vto);
+}
+
+void clear_user_page(void *addr, unsigned long vaddr, struct page *page)
+{
+        cpu_dcache_wbinval_page((unsigned long)vaddr);
+        cpu_icache_inval_page((unsigned long)vaddr);
+        clear_page(addr);
+        cpu_dcache_wbinval_page((unsigned long)addr);
+        cpu_icache_inval_page((unsigned long)addr);
+}
+
 void copy_user_highpage(struct page *to, struct page *from,
                         unsigned long vaddr, struct vm_area_struct *vma)
 {
@@ -156,11 +175,9 @@ void copy_user_highpage(struct page *to, struct page *from,
         pto = page_to_phys(to);
         pfrom = page_to_phys(from);
 
+        local_irq_save(flags);
         if (aliasing(vaddr, (unsigned long)kfrom))
                 cpu_dcache_wb_page((unsigned long)kfrom);
-        if (aliasing(vaddr, (unsigned long)kto))
-                cpu_dcache_inval_page((unsigned long)kto);
-        local_irq_save(flags);
         vto = kremap0(vaddr, pto);
         vfrom = kremap1(vaddr, pfrom);
         copy_page((void *)vto, (void *)vfrom);
@@ -198,21 +215,25 @@ void flush_dcache_page(struct page *page)
         if (mapping && !mapping_mapped(mapping))
                 set_bit(PG_dcache_dirty, &page->flags);
         else {
-                int i, pc;
-                unsigned long vto, kaddr, flags;
+                unsigned long kaddr, flags;
+
                 kaddr = (unsigned long)page_address(page);
-                cpu_dcache_wbinval_page(kaddr);
-                pc = CACHE_SET(DCACHE) * CACHE_LINE_SIZE(DCACHE) / PAGE_SIZE;
                 local_irq_save(flags);
-                for (i = 0; i < pc; i++) {
-                        vto =
-                            kremap0(kaddr + i * PAGE_SIZE, page_to_phys(page));
-                        cpu_dcache_wbinval_page(vto);
-                        kunmap01(vto);
+                cpu_dcache_wbinval_page(kaddr);
+                if (mapping) {
+                        unsigned long vaddr, kto;
+
+                        vaddr = page->index << PAGE_SHIFT;
+                        if (aliasing(vaddr, kaddr)) {
+                                kto = kremap0(vaddr, page_to_phys(page));
+                                cpu_dcache_wbinval_page(kto);
+                                kunmap01(kto);
+                        }
                 }
                 local_irq_restore(flags);
         }
 }
+EXPORT_SYMBOL(flush_dcache_page);
 
 void copy_to_user_page(struct vm_area_struct *vma, struct page *page,
                        unsigned long vaddr, void *dst, void *src, int len)
@@ -251,7 +272,7 @@ void copy_from_user_page(struct vm_area_struct *vma, struct page *page,
 void flush_anon_page(struct vm_area_struct *vma,
                      struct page *page, unsigned long vaddr)
 {
-        unsigned long flags;
+        unsigned long kaddr, flags, ktmp;
         if (!PageAnon(page))
                 return;
 
@@ -261,7 +282,12 @@ void flush_anon_page(struct vm_area_struct *vma,
         local_irq_save(flags);
         if (vma->vm_flags & VM_EXEC)
                 cpu_icache_inval_page(vaddr & PAGE_MASK);
-        cpu_dcache_wbinval_page((unsigned long)page_address(page));
+        kaddr = (unsigned long)page_address(page);
+        if (aliasing(vaddr, kaddr)) {
+                ktmp = kremap0(vaddr, page_to_phys(page));
+                cpu_dcache_wbinval_page(ktmp);
+                kunmap01(ktmp);
+        }
         local_irq_restore(flags);
 }
 
@@ -272,6 +298,25 @@ void flush_kernel_dcache_page(struct page *page)
         cpu_dcache_wbinval_page((unsigned long)page_address(page));
         local_irq_restore(flags);
 }
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+void flush_kernel_vmap_range(void *addr, int size)
+{
+        unsigned long flags;
+        local_irq_save(flags);
+        cpu_dcache_wb_range((unsigned long)addr, (unsigned long)addr +  size);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(flush_kernel_vmap_range);
+
+void invalidate_kernel_vmap_range(void *addr, int size)
+{
+        unsigned long flags;
+        local_irq_save(flags);
+        cpu_dcache_inval_range((unsigned long)addr, (unsigned long)addr + size);
+        local_irq_restore(flags);
+}
+EXPORT_SYMBOL(invalidate_kernel_vmap_range);
 
 void flush_icache_range(unsigned long start, unsigned long end)
 {
@@ -283,6 +328,7 @@ void flush_icache_range(unsigned long start, unsigned long end)
         cpu_cache_wbinval_range(start, end, 1);
         local_irq_restore(flags);
 }
+EXPORT_SYMBOL(flush_icache_range);
 
 void flush_icache_page(struct vm_area_struct *vma, struct page *page)
 {
diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c
index 93ee0160720b..c713d2ad55dc 100644
--- a/arch/nds32/mm/init.c
+++ b/arch/nds32/mm/init.c
@@ -30,6 +30,7 @@ extern unsigned long phys_initrd_size;
  * zero-initialized data and COW.
  */
 struct page *empty_zero_page;
+EXPORT_SYMBOL(empty_zero_page);
 
 static void __init zone_sizes_init(void)
 {
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index e9525bc1b4a6..1ace023cbdce 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
-KBUILD_CFLAGS += -c -MD -Os -m64
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index fda2114197b3..68b2c3150de1 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -62,8 +62,8 @@
 #define NHM_C3_AUTO_DEMOTE              (1UL << 25)
 #define NHM_C1_AUTO_DEMOTE              (1UL << 26)
 #define ATM_LNC_C6_AUTO_DEMOTE          (1UL << 25)
-#define SNB_C1_AUTO_UNDEMOTE            (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE            (1UL << 28)
+#define SNB_C3_AUTO_UNDEMOTE            (1UL << 27)
+#define SNB_C1_AUTO_UNDEMOTE            (1UL << 28)
 
 #define MSR_MTRRcap                     0x000000fe
 
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index d4a81be0d7d2..b6be62025325 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -152,8 +152,8 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
                EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
         writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
 
-        memset(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
-               EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+        memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
+                  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
 
         eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
                               EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
diff --git a/drivers/input/mouse/elan_i2c_smbus.c b/drivers/input/mouse/elan_i2c_smbus.c
index 29f99529b187..cfcb32559925 100644
--- a/drivers/input/mouse/elan_i2c_smbus.c
+++ b/drivers/input/mouse/elan_i2c_smbus.c
@@ -130,7 +130,7 @@ static int elan_smbus_get_baseline_data(struct i2c_client *client,
                                         bool max_baseline, u8 *value)
 {
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client,
                                           max_baseline ?
@@ -149,7 +149,7 @@ static int elan_smbus_get_version(struct i2c_client *client,
                                   bool iap, u8 *version)
 {
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client,
                                           iap ? ETP_SMBUS_IAP_VERSION_CMD :
@@ -170,7 +170,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
                                      u8 *clickpad)
 {
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client,
                                           ETP_SMBUS_SM_VERSION_CMD, val);
@@ -188,7 +188,7 @@ static int elan_smbus_get_sm_version(struct i2c_client *client,
 static int elan_smbus_get_product_id(struct i2c_client *client, u16 *id)
 {
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client,
                                           ETP_SMBUS_UNIQUEID_CMD, val);
@@ -205,7 +205,7 @@ static int elan_smbus_get_checksum(struct i2c_client *client,
                                    bool iap, u16 *csum)
 {
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client,
                                           iap ? ETP_SMBUS_FW_CHECKSUM_CMD :
@@ -226,7 +226,7 @@ static int elan_smbus_get_max(struct i2c_client *client,
 {
         int ret;
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RANGE_CMD, val);
         if (ret != 3) {
@@ -246,7 +246,7 @@ static int elan_smbus_get_resolution(struct i2c_client *client,
 {
         int ret;
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         ret = i2c_smbus_read_block_data(client, ETP_SMBUS_RESOLUTION_CMD, val);
         if (ret != 3) {
@@ -267,7 +267,7 @@ static int elan_smbus_get_num_traces(struct i2c_client *client,
 {
         int ret;
         int error;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         ret = i2c_smbus_read_block_data(client, ETP_SMBUS_XY_TRACENUM_CMD, val);
         if (ret != 3) {
@@ -294,7 +294,7 @@ static int elan_smbus_iap_get_mode(struct i2c_client *client,
 {
         int error;
         u16 constant;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         error = i2c_smbus_read_block_data(client, ETP_SMBUS_IAP_CTRL_CMD, val);
         if (error < 0) {
@@ -345,7 +345,7 @@ static int elan_smbus_prepare_fw_update(struct i2c_client *client)
         int len;
         int error;
         enum tp_mode mode;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
         u8 cmd[4] = {0x0F, 0x78, 0x00, 0x06};
         u16 password;
 
@@ -419,7 +419,7 @@ static int elan_smbus_write_fw_block(struct i2c_client *client,
         struct device *dev = &client->dev;
         int error;
         u16 result;
-        u8 val[3];
+        u8 val[I2C_SMBUS_BLOCK_MAX] = {0};
 
         /*
          * Due to the limitation of smbus protocol limiting
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 60f2c463d1cc..a9591d278145 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -172,6 +172,12 @@ static const char * const smbus_pnp_ids[] = {
         "LEN0048", /* X1 Carbon 3 */
         "LEN0046", /* X250 */
         "LEN004a", /* W541 */
+        "LEN0071", /* T480 */
+        "LEN0072", /* X1 Carbon Gen 5 (2017) - Elan/ALPS trackpoint */
+        "LEN0073", /* X1 Carbon G5 (Elantech) */
+        "LEN0092", /* X1 Carbon 6 */
+        "LEN0096", /* X280 */
+        "LEN0097", /* X280 -> ALPS trackpoint */
         "LEN200f", /* T450s */
         NULL
 };
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 99b857e5a7a9..b9ca782fe82d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1447,8 +1447,8 @@ static void __nvme_revalidate_disk(struct gendisk *disk, struct nvme_id_ns *id)
         if (ns->lba_shift == 0)
                 ns->lba_shift = 9;
         ns->noiob = le16_to_cpu(id->noiob);
-        ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
         ns->ms = le16_to_cpu(id->lbaf[id->flbas & NVME_NS_FLBAS_LBA_MASK].ms);
+        ns->ext = ns->ms && (id->flbas & NVME_NS_FLBAS_META_EXT);
         /* the PI implementation requires metadata equal t10 pi tuple size */
         if (ns->ms == sizeof(struct t10_pi_tuple))
                 ns->pi_type = id->dps & NVME_NS_DPS_PI_MASK;
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index a32c5c00e0e7..ffffb9909ae1 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -163,6 +163,16 @@ MODULE_LICENSE("GPL");
 
 static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
 
+static bool ashs_present(void)
+{
+        int i = 0;
+        while (ashs_ids[i]) {
+                if (acpi_dev_found(ashs_ids[i++]))
+                        return true;
+        }
+        return false;
+}
+
 struct bios_args {
         u32 arg0;
         u32 arg1;
@@ -1025,6 +1035,9 @@ static int asus_new_rfkill(struct asus_wmi *asus,
 
 static void asus_wmi_rfkill_exit(struct asus_wmi *asus)
 {
+        if (asus->driver->wlan_ctrl_by_user && ashs_present())
+                return;
+
         asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P5");
         asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P6");
         asus_unregister_rfkill_notifier(asus, "\\_SB.PCI0.P0P7");
@@ -2121,16 +2134,6 @@ static int asus_wmi_fan_init(struct asus_wmi *asus)
         return 0;
 }
 
-static bool ashs_present(void)
-{
-        int i = 0;
-        while (ashs_ids[i]) {
-                if (acpi_dev_found(ashs_ids[i++]))
-                        return true;
-        }
-        return false;
-}
-
 /*
  * WMI Driver
  */
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 04143c08bd6e..02c03e418c27 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3034,7 +3034,8 @@ static blk_status_t do_dasd_request(struct blk_mq_hw_ctx *hctx,
         cqr->callback_data = req;
         cqr->status = DASD_CQR_FILLED;
         cqr->dq = dq;
-        req->completion_data = cqr;
+        *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req)) = cqr;
+
         blk_mq_start_request(req);
         spin_lock(&block->queue_lock);
         list_add_tail(&cqr->blocklist, &block->ccw_queue);
@@ -3058,12 +3059,13 @@ out:
  */
 enum blk_eh_timer_return dasd_times_out(struct request *req, bool reserved)
 {
-        struct dasd_ccw_req *cqr = req->completion_data;
         struct dasd_block *block = req->q->queuedata;
         struct dasd_device *device;
+        struct dasd_ccw_req *cqr;
         unsigned long flags;
         int rc = 0;
 
+        cqr = *((struct dasd_ccw_req **) blk_mq_rq_to_pdu(req));
         if (!cqr)
                 return BLK_EH_NOT_HANDLED;
 
@@ -3169,6 +3171,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
         int rc;
 
         block->tag_set.ops = &dasd_mq_ops;
+        block->tag_set.cmd_size = sizeof(struct dasd_ccw_req *);
         block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
         block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
         block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 1992b0ffa543..81dfedb7879f 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -372,18 +372,14 @@ int afs_permission(struct inode *inode, int mask)
                mask, access, S_ISDIR(inode->i_mode) ? "dir" : "file");
 
         if (S_ISDIR(inode->i_mode)) {
-                if (mask & MAY_EXEC) {
+                if (mask & (MAY_EXEC | MAY_READ | MAY_CHDIR)) {
                         if (!(access & AFS_ACE_LOOKUP))
                                 goto permission_denied;
-                } else if (mask & MAY_READ) {
-                        if (!(access & AFS_ACE_LOOKUP))
-                                goto permission_denied;
-                } else if (mask & MAY_WRITE) {
+                }
+                if (mask & MAY_WRITE) {
                         if (!(access & (AFS_ACE_DELETE | /* rmdir, unlink, rename from */
                                         AFS_ACE_INSERT))) /* create, mkdir, symlink, rename to */
                                 goto permission_denied;
-                } else {
-                        BUG();
                 }
         } else {
                 if (!(access & AFS_ACE_LOOKUP))
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 1ed7e2fd2f35..c3b740813fc7 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -23,7 +23,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
         struct afs_uvldbentry__xdr *uvldb;
         struct afs_vldb_entry *entry;
         bool new_only = false;
-        u32 tmp, nr_servers;
+        u32 tmp, nr_servers, vlflags;
         int i, ret;
 
         _enter("");
@@ -55,6 +55,7 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
                         new_only = true;
         }
 
+        vlflags = ntohl(uvldb->flags);
         for (i = 0; i < nr_servers; i++) {
                 struct afs_uuid__xdr *xdr;
                 struct afs_uuid *uuid;
@@ -64,12 +65,13 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
                 if (tmp & AFS_VLSF_DONTUSE ||
                     (new_only && !(tmp & AFS_VLSF_NEWREPSITE)))
                         continue;
-                if (tmp & AFS_VLSF_RWVOL)
+                if (tmp & AFS_VLSF_RWVOL) {
                         entry->fs_mask[i] |= AFS_VOL_VTM_RW;
+                        if (vlflags & AFS_VLF_BACKEXISTS)
+                                entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
+                }
                 if (tmp & AFS_VLSF_ROVOL)
                         entry->fs_mask[i] |= AFS_VOL_VTM_RO;
-                if (tmp & AFS_VLSF_BACKVOL)
-                        entry->fs_mask[i] |= AFS_VOL_VTM_BAK;
                 if (!entry->fs_mask[i])
                         continue;
 
@@ -89,15 +91,14 @@ static int afs_deliver_vl_get_entry_by_name_u(struct afs_call *call)
         for (i = 0; i < AFS_MAXTYPES; i++)
                 entry->vid[i] = ntohl(uvldb->volumeId[i]);
 
-        tmp = ntohl(uvldb->flags);
-        if (tmp & AFS_VLF_RWEXISTS)
+        if (vlflags & AFS_VLF_RWEXISTS)
                 __set_bit(AFS_VLDB_HAS_RW, &entry->flags);
-        if (tmp & AFS_VLF_ROEXISTS)
+        if (vlflags & AFS_VLF_ROEXISTS)
                 __set_bit(AFS_VLDB_HAS_RO, &entry->flags);
-        if (tmp & AFS_VLF_BACKEXISTS)
+        if (vlflags & AFS_VLF_BACKEXISTS)
                 __set_bit(AFS_VLDB_HAS_BAK, &entry->flags);
 
-        if (!(tmp & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
+        if (!(vlflags & (AFS_VLF_RWEXISTS | AFS_VLF_ROEXISTS | AFS_VLF_BACKEXISTS))) {
                 entry->error = -ENOMEDIUM;
                 __set_bit(AFS_VLDB_QUERY_ERROR, &entry->flags);
         }
diff --git a/fs/inode.c b/fs/inode.c
index 13ceb98c3bd3..3b55391072f3 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -178,6 +178,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
         mapping->a_ops = &empty_aops;
         mapping->host = inode;
         mapping->flags = 0;
+        mapping->wb_err = 0;
         atomic_set(&mapping->i_mmap_writable, 0);
         mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE);
         mapping->private_data = NULL;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 414d7210b2ec..bcd93031d042 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -893,7 +893,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
 #ifdef CONFIG_TRACER_SNAPSHOT
-static void tracing_snapshot_instance(struct trace_array *tr)
+void tracing_snapshot_instance(struct trace_array *tr)
 {
         struct tracer *tracer = tr->current_trace;
         unsigned long flags;
@@ -949,7 +949,7 @@ static int resize_buffer_duplicate_size(struct trace_buffer *trace_buf,
                                         struct trace_buffer *size_buf, int cpu_id);
 static void set_buffer_entries(struct trace_buffer *buf, unsigned long val);
 
-static int alloc_snapshot(struct trace_array *tr)
+int tracing_alloc_snapshot_instance(struct trace_array *tr)
 {
         int ret;
 
@@ -995,7 +995,7 @@ int tracing_alloc_snapshot(void)
         struct trace_array *tr = &global_trace;
         int ret;
 
-        ret = alloc_snapshot(tr);
+        ret = tracing_alloc_snapshot_instance(tr);
         WARN_ON(ret < 0);
 
         return ret;
@@ -5408,7 +5408,7 @@ static int tracing_set_tracer(struct trace_array *tr, const char *buf)
 
 #ifdef CONFIG_TRACER_MAX_TRACE
         if (t->use_max_tr && !had_max_tr) {
-                ret = alloc_snapshot(tr);
+                ret = tracing_alloc_snapshot_instance(tr);
                 if (ret < 0)
                         goto out;
         }
@@ -6451,7 +6451,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
                 }
 #endif
                 if (!tr->allocated_snapshot) {
-                        ret = alloc_snapshot(tr);
+                        ret = tracing_alloc_snapshot_instance(tr);
                         if (ret < 0)
                                 break;
                 }
@@ -7179,7 +7179,7 @@ ftrace_trace_snapshot_callback(struct trace_array *tr, struct ftrace_hash *hash,
                 return ret;
 
  out_reg:
-        ret = alloc_snapshot(tr);
+        ret = tracing_alloc_snapshot_instance(tr);
         if (ret < 0)
                 goto out;
 
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6fb46a06c9dc..507954b4e058 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -1817,6 +1817,17 @@ static inline void __init trace_event_init(void) { }
 static inline void trace_event_eval_update(struct trace_eval_map **map, int len) { }
 #endif
 
+#ifdef CONFIG_TRACER_SNAPSHOT
+void tracing_snapshot_instance(struct trace_array *tr);
+int tracing_alloc_snapshot_instance(struct trace_array *tr);
+#else
+static inline void tracing_snapshot_instance(struct trace_array *tr) { }
+static inline int tracing_alloc_snapshot_instance(struct trace_array *tr)
+{
+        return 0;
+}
+#endif
+
 extern struct trace_iterator *tracepoint_print_iter;
 
 #endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d251cabcf69a..8b5bdcf64871 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -483,9 +483,10 @@ clear_event_triggers(struct trace_array *tr)
         struct trace_event_file *file;
 
         list_for_each_entry(file, &tr->events, list) {
-                struct event_trigger_data *data;
-                list_for_each_entry_rcu(data, &file->triggers, list) {
+                struct event_trigger_data *data, *n;
+                list_for_each_entry_safe(data, n, &file->triggers, list) {
                         trace_event_trigger_enable_disable(file, 0);
+                        list_del_rcu(&data->list);
                         if (data->ops->free)
                                 data->ops->free(data->ops, data);
                 }
@@ -642,6 +643,7 @@ event_trigger_callback(struct event_command *cmd_ops,
         trigger_data->count = -1;
         trigger_data->ops = trigger_ops;
         trigger_data->cmd_ops = cmd_ops;
+        trigger_data->private_data = file;
         INIT_LIST_HEAD(&trigger_data->list);
         INIT_LIST_HEAD(&trigger_data->named_list);
 
@@ -1053,7 +1055,12 @@ static void
 snapshot_trigger(struct event_trigger_data *data, void *rec,
                  struct ring_buffer_event *event)
 {
-        tracing_snapshot();
+        struct trace_event_file *file = data->private_data;
+
+        if (file)
+                tracing_snapshot_instance(file->tr);
+        else
+                tracing_snapshot();
 }
 
 static void
@@ -1076,7 +1083,7 @@ register_snapshot_trigger(char *glob, struct event_trigger_ops *ops,
 {
         int ret = register_trigger(glob, ops, data, file);
 
-        if (ret > 0 && tracing_alloc_snapshot() != 0) {
+        if (ret > 0 && tracing_alloc_snapshot_instance(file->tr) != 0) {
                 unregister_trigger(glob, ops, data, file);
                 ret = 0;
         }
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 8057e19dc15f..3ce225e3f142 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -1494,7 +1494,7 @@ static int security_context_to_sid_core(struct selinux_state *state,
                                       scontext_len, &context, def_sid);
         if (rc == -EINVAL && force) {
                 context.str = str;
-                context.len = scontext_len;
+                context.len = strlen(str) + 1;
                 str = NULL;
         } else if (rc)
                 goto out_unlock;
diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile
index a9bc914a8fe8..2ab25aa38263 100644
--- a/tools/power/x86/turbostat/Makefile
+++ b/tools/power/x86/turbostat/Makefile
@@ -25,4 +25,4 @@ install : turbostat
         install -d  $(DESTDIR)$(PREFIX)/bin
         install $(BUILD_OUTPUT)/turbostat $(DESTDIR)$(PREFIX)/bin/turbostat
         install -d  $(DESTDIR)$(PREFIX)/share/man/man8
-        install turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
+        install -m 644 turbostat.8 $(DESTDIR)$(PREFIX)/share/man/man8
diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8
index ccf2a69365cc..ca9ef7017624 100644
--- a/tools/power/x86/turbostat/turbostat.8
+++ b/tools/power/x86/turbostat/turbostat.8
@@ -54,9 +54,12 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--cpu cpu-set\fP limit output to system summary plus the specified cpu-set.  If cpu-set is the string "core", then the system summary plus the first CPU in each core are printed -- eg. subsequent HT siblings are not printed.  Or if cpu-set is the string "package", then the system summary plus the first CPU in each package is printed.  Otherwise, the system summary plus the specified set of CPUs are printed.  The cpu-set is ordered from low to high, comma delimited with ".." and "-" permitted to denote a range. eg. 1,2,8,14..17,21-44
 .PP
-\fB--hide column\fP do not show the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
+\fB--hide column\fP do not show the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--hide sysfs" to hide the sysfs statistics columns as a group.
 .PP
-\fB--show column\fP show only the specified columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
+\fB--enable column\fP show the specified built-in columns, which are otherwise disabled, by default.  Currently the only built-in counters disabled by default are "usec" and "Time_Of_Day_Seconds".
+The column name "all" can be used to enable all disabled-by-default built-in counters.
+.PP
+\fB--show column\fP show only the specified built-in columns.  May be invoked multiple times, or with a comma-separated list of column names.  Use "--show sysfs" to show the sysfs statistics columns as a group.
 .PP
 \fB--Dump\fP displays the raw counter values.
 .PP
@@ -64,6 +67,8 @@ name as necessary to disambiguate it from others is necessary.  Note that option
 .PP
 \fB--interval seconds\fP overrides the default 5.0 second measurement interval.
 .PP
+\fB--num_iterations num\fP number of the measurement iterations.
+.PP
 \fB--out output_file\fP turbostat output is written to the specified output_file.
 The file is truncated if it already exists, and it is created if it does not exist.
 .PP
@@ -86,6 +91,8 @@ displays the statistics gathered since it was forked.
 The system configuration dump (if --quiet is not used) is followed by statistics.  The first row of the statistics labels the content of each column (below).  The second row of statistics is the system summary line.  The system summary line has a '-' in the columns for the Package, Core, and CPU.  The contents of the system summary line depends on the type of column.  Columns that count items (eg. IRQ) show the sum across all CPUs in the system.  Columns that show a percentage show the average across all CPUs in the system.  Columns that dump raw MSR values simply show 0 in the summary.  After the system summary row, each row describes a specific Package/Core/CPU.  Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system.
 .SH COLUMN DESCRIPTIONS
 .nf
+\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any.  This counter is disabled by default, and is enabled with "--enable usec", or --debug.  On the summary row, usec refers to the total elapsed time to collect the counters on all cpus.
+\fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected.  This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug".  On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU.
 \fBCore\fP processor core number.  Note that multiple CPUs per core indicate support for Intel(R) Hyper-Threading Technology (HT).
 \fBCPU\fP Linux CPU (logical processor) number.  Yes, it is okay that on many systems the CPUs are not listed in numerical order -- for efficiency reasons, turbostat runs in topology order, so HT siblings appear together.
 \fBPackage\fP processor package number -- not present on systems with a single processor package.
@@ -262,6 +269,21 @@ CPU	  PRF_CTRL
 
 .fi
 
+.SH INPUT
+
+For interval-mode, turbostat will immediately end the current interval
+when it sees a newline on standard input.
+turbostat will then start the next interval.
+Control-C will be send a SIGINT to turbostat,
+which will immediately abort the program with no further processing.
+.SH SIGNALS
+
+SIGINT will interrupt interval-mode.
+The end-of-interval data will be collected and displayed before turbostat exits.
+
+SIGUSR1 will end current interval,
+end-of-interval data will be collected and displayed before turbostat
+starts a new interval.
 .SH NOTES
 
 .B "turbostat "
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index bd9c6b31a504..d6cff3070ebd 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -29,6 +29,7 @@
 #include <sys/types.h>
 #include <sys/wait.h>
 #include <sys/stat.h>
+#include <sys/select.h>
 #include <sys/resource.h>
 #include <fcntl.h>
 #include <signal.h>
@@ -47,9 +48,13 @@
 char *proc_stat = "/proc/stat";
 FILE *outf;
 int *fd_percpu;
+struct timeval interval_tv = {5, 0};
 struct timespec interval_ts = {5, 0};
+struct timespec one_msec = {0, 1000000};
+unsigned int num_iterations;
 unsigned int debug;
 unsigned int quiet;
+unsigned int shown;
 unsigned int sums_need_wide_columns;
 unsigned int rapl_joules;
 unsigned int summary_only;
@@ -58,6 +63,7 @@ unsigned int dump_only;
 unsigned int do_snb_cstates;
 unsigned int do_knl_cstates;
 unsigned int do_slm_cstates;
+unsigned int do_cnl_cstates;
 unsigned int use_c1_residency_msr;
 unsigned int has_aperf;
 unsigned int has_epb;
@@ -80,6 +86,8 @@ unsigned int do_rapl;
 unsigned int do_dts;
 unsigned int do_ptm;
 unsigned long long  gfx_cur_rc6_ms;
+unsigned long long cpuidle_cur_cpu_lpi_us;
+unsigned long long cpuidle_cur_sys_lpi_us;
 unsigned int gfx_cur_mhz;
 unsigned int tcc_activation_temp;
 unsigned int tcc_activation_temp_override;
@@ -87,6 +95,7 @@ double rapl_power_units, rapl_time_units;
 double rapl_dram_energy_units, rapl_energy_units;
 double rapl_joule_counter_range;
 unsigned int do_core_perf_limit_reasons;
+unsigned int has_automatic_cstate_conversion;
 unsigned int do_gfx_perf_limit_reasons;
 unsigned int do_ring_perf_limit_reasons;
 unsigned int crystal_hz;
@@ -147,7 +156,9 @@ char *progname;
 #define CPU_SUBSET_MAXCPUS      1024    /* need to use before probe... */
 cpu_set_t *cpu_present_set, *cpu_affinity_set, *cpu_subset;
 size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size;
-#define MAX_ADDED_COUNTERS 16
+#define MAX_ADDED_COUNTERS 8
+#define MAX_ADDED_THREAD_COUNTERS 24
+#define BITMASK_SIZE 32
 
 struct thread_data {
         struct timeval tv_begin;
@@ -162,7 +173,7 @@ struct thread_data {
         unsigned int flags;
 #define CPU_IS_FIRST_THREAD_IN_CORE     0x2
 #define CPU_IS_FIRST_CORE_IN_PACKAGE    0x4
-        unsigned long long counter[MAX_ADDED_COUNTERS];
+        unsigned long long counter[MAX_ADDED_THREAD_COUNTERS];
 } *thread_even, *thread_odd;
 
 struct core_data {
@@ -183,6 +194,8 @@ struct pkg_data {
         unsigned long long pc8;
         unsigned long long pc9;
         unsigned long long pc10;
+        unsigned long long cpu_lpi;
+        unsigned long long sys_lpi;
         unsigned long long pkg_wtd_core_c0;
         unsigned long long pkg_any_core_c0;
         unsigned long long pkg_any_gfxe_c0;
@@ -203,12 +216,21 @@ struct pkg_data {
 #define ODD_COUNTERS thread_odd, core_odd, package_odd
 #define EVEN_COUNTERS thread_even, core_even, package_even
 
-#define GET_THREAD(thread_base, thread_no, core_no, pkg_no) \
-        (thread_base + (pkg_no) * topo.num_cores_per_pkg * \
-                topo.num_threads_per_core + \
-                (core_no) * topo.num_threads_per_core + (thread_no))
-#define GET_CORE(core_base, core_no, pkg_no) \
-        (core_base + (pkg_no) * topo.num_cores_per_pkg + (core_no))
+#define GET_THREAD(thread_base, thread_no, core_no, node_no, pkg_no)          \
+        ((thread_base) +                                                      \
+         ((pkg_no) *                                                          \
+          topo.nodes_per_pkg * topo.cores_per_node * topo.threads_per_core) + \
+         ((node_no) * topo.cores_per_node * topo.threads_per_core) +          \
+         ((core_no) * topo.threads_per_core) +                                \
+         (thread_no))
+
+#define GET_CORE(core_base, core_no, node_no, pkg_no)                   \
+        ((core_base) +                                                  \
+         ((pkg_no) *  topo.nodes_per_pkg * topo.cores_per_node) +       \
+         ((node_no) * topo.cores_per_node) +                            \
+         (core_no))
+
+
 #define GET_PKG(pkg_base, pkg_no) (pkg_base + pkg_no)
 
 enum counter_scope {SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE};
@@ -244,14 +266,25 @@ struct system_summary {
         struct pkg_data packages;
 } average;
 
+struct cpu_topology {
+        int physical_package_id;
+        int logical_cpu_id;
+        int physical_node_id;
+        int logical_node_id;    /* 0-based count within the package */
+        int physical_core_id;
+        int thread_id;
+        cpu_set_t *put_ids; /* Processing Unit/Thread IDs */
+} *cpus;
 
 struct topo_params {
         int num_packages;
         int num_cpus;
         int num_cores;
         int max_cpu_num;
-        int num_cores_per_pkg;
-        int num_threads_per_core;
+        int max_node_num;
+        int nodes_per_pkg;
+        int cores_per_node;
+        int threads_per_core;
 } topo;
 
 struct timeval tv_even, tv_odd, tv_delta;
@@ -273,27 +306,33 @@ int cpu_is_not_present(int cpu)
 int for_all_cpus(int (func)(struct thread_data *, struct core_data *, struct pkg_data *),
         struct thread_data *thread_base, struct core_data *core_base, struct pkg_data *pkg_base)
 {
-        int retval, pkg_no, core_no, thread_no;
+        int retval, pkg_no, core_no, thread_no, node_no;
 
         for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-                for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
-                        for (thread_no = 0; thread_no <
-                                topo.num_threads_per_core; ++thread_no) {
-                                struct thread_data *t;
-                                struct core_data *c;
-                                struct pkg_data *p;
-
-                                t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
-
-                                if (cpu_is_not_present(t->cpu_id))
-                                        continue;
-
-                                c = GET_CORE(core_base, core_no, pkg_no);
-                                p = GET_PKG(pkg_base, pkg_no);
-
-                                retval = func(t, c, p);
-                                if (retval)
-                                        return retval;
+                for (core_no = 0; core_no < topo.cores_per_node; ++core_no) {
+                        for (node_no = 0; node_no < topo.nodes_per_pkg;
+                             node_no++) {
+                                for (thread_no = 0; thread_no <
+                                        topo.threads_per_core; ++thread_no) {
+                                        struct thread_data *t;
+                                        struct core_data *c;
+                                        struct pkg_data *p;
+
+                                        t = GET_THREAD(thread_base, thread_no,
+                                                       core_no, node_no,
+                                                       pkg_no);
+
+                                        if (cpu_is_not_present(t->cpu_id))
+                                                continue;
+
+                                        c = GET_CORE(core_base, core_no,
+                                                     node_no, pkg_no);
+                                        p = GET_PKG(pkg_base, pkg_no);
+
+                                        retval = func(t, c, p);
+                                        if (retval)
+                                                return retval;
+                                }
                         }
                 }
         }
@@ -346,6 +385,8 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr)
  * Thus, strings that are proper sub-sets must follow their more specific peers.
  */
 struct msr_counter bic[] = {
+        { 0x0, "usec" },
+        { 0x0, "Time_Of_Day_Seconds" },
         { 0x0, "Package" },
         { 0x0, "Avg_MHz" },
         { 0x0, "Bzy_MHz" },
@@ -369,7 +410,9 @@ struct msr_counter bic[] = {
         { 0x0, "Pkg%pc7" },
         { 0x0, "Pkg%pc8" },
         { 0x0, "Pkg%pc9" },
-        { 0x0, "Pkg%pc10" },
+        { 0x0, "Pk%pc10" },
+        { 0x0, "CPU%LPI" },
+        { 0x0, "SYS%LPI" },
         { 0x0, "PkgWatt" },
         { 0x0, "CorWatt" },
         { 0x0, "GFXWatt" },
@@ -389,62 +432,72 @@ struct msr_counter bic[] = {
         { 0x0, "Any%C0" },
         { 0x0, "GFX%C0" },
         { 0x0, "CPUGFX%" },
+        { 0x0, "Node%" },
 };
 
 
 
 #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter))
-#define BIC_Package     (1ULL << 0)
-#define BIC_Avg_MHz     (1ULL << 1)
-#define BIC_Bzy_MHz     (1ULL << 2)
-#define BIC_TSC_MHz     (1ULL << 3)
-#define BIC_IRQ         (1ULL << 4)
-#define BIC_SMI         (1ULL << 5)
-#define BIC_Busy        (1ULL << 6)
-#define BIC_CPU_c1      (1ULL << 7)
-#define BIC_CPU_c3      (1ULL << 8)
-#define BIC_CPU_c6      (1ULL << 9)
-#define BIC_CPU_c7      (1ULL << 10)
-#define BIC_ThreadC     (1ULL << 11)
-#define BIC_CoreTmp     (1ULL << 12)
-#define BIC_CoreCnt     (1ULL << 13)
-#define BIC_PkgTmp      (1ULL << 14)
-#define BIC_GFX_rc6     (1ULL << 15)
-#define BIC_GFXMHz      (1ULL << 16)
-#define BIC_Pkgpc2      (1ULL << 17)
-#define BIC_Pkgpc3      (1ULL << 18)
-#define BIC_Pkgpc6      (1ULL << 19)
-#define BIC_Pkgpc7      (1ULL << 20)
-#define BIC_Pkgpc8      (1ULL << 21)
-#define BIC_Pkgpc9      (1ULL << 22)
-#define BIC_Pkgpc10     (1ULL << 23)
-#define BIC_PkgWatt     (1ULL << 24)
-#define BIC_CorWatt     (1ULL << 25)
-#define BIC_GFXWatt     (1ULL << 26)
-#define BIC_PkgCnt      (1ULL << 27)
-#define BIC_RAMWatt     (1ULL << 28)
-#define BIC_PKG__       (1ULL << 29)
-#define BIC_RAM__       (1ULL << 30)
-#define BIC_Pkg_J       (1ULL << 31)
-#define BIC_Cor_J       (1ULL << 32)
-#define BIC_GFX_J       (1ULL << 33)
-#define BIC_RAM_J       (1ULL << 34)
-#define BIC_Core        (1ULL << 35)
-#define BIC_CPU         (1ULL << 36)
-#define BIC_Mod_c6      (1ULL << 37)
-#define BIC_sysfs       (1ULL << 38)
-#define BIC_Totl_c0     (1ULL << 39)
-#define BIC_Any_c0      (1ULL << 40)
-#define BIC_GFX_c0      (1ULL << 41)
-#define BIC_CPUGFX      (1ULL << 42)
-
-unsigned long long bic_enabled = 0xFFFFFFFFFFFFFFFFULL;
-unsigned long long bic_present = BIC_sysfs;
+#define BIC_USEC        (1ULL << 0)
+#define BIC_TOD         (1ULL << 1)
+#define BIC_Package     (1ULL << 2)
+#define BIC_Avg_MHz     (1ULL << 3)
+#define BIC_Bzy_MHz     (1ULL << 4)
+#define BIC_TSC_MHz     (1ULL << 5)
+#define BIC_IRQ         (1ULL << 6)
+#define BIC_SMI         (1ULL << 7)
+#define BIC_Busy        (1ULL << 8)
+#define BIC_CPU_c1      (1ULL << 9)
+#define BIC_CPU_c3      (1ULL << 10)
+#define BIC_CPU_c6      (1ULL << 11)
+#define BIC_CPU_c7      (1ULL << 12)
+#define BIC_ThreadC     (1ULL << 13)
+#define BIC_CoreTmp     (1ULL << 14)
+#define BIC_CoreCnt     (1ULL << 15)
+#define BIC_PkgTmp      (1ULL << 16)
+#define BIC_GFX_rc6     (1ULL << 17)
+#define BIC_GFXMHz      (1ULL << 18)
+#define BIC_Pkgpc2      (1ULL << 19)
+#define BIC_Pkgpc3      (1ULL << 20)
+#define BIC_Pkgpc6      (1ULL << 21)
+#define BIC_Pkgpc7      (1ULL << 22)
+#define BIC_Pkgpc8      (1ULL << 23)
+#define BIC_Pkgpc9      (1ULL << 24)
+#define BIC_Pkgpc10     (1ULL << 25)
+#define BIC_CPU_LPI     (1ULL << 26)
+#define BIC_SYS_LPI     (1ULL << 27)
+#define BIC_PkgWatt     (1ULL << 26)
+#define BIC_CorWatt     (1ULL << 27)
+#define BIC_GFXWatt     (1ULL << 28)
+#define BIC_PkgCnt      (1ULL << 29)
+#define BIC_RAMWatt     (1ULL << 30)
+#define BIC_PKG__       (1ULL << 31)
+#define BIC_RAM__       (1ULL << 32)
+#define BIC_Pkg_J       (1ULL << 33)
+#define BIC_Cor_J       (1ULL << 34)
+#define BIC_GFX_J       (1ULL << 35)
+#define BIC_RAM_J       (1ULL << 36)
+#define BIC_Core        (1ULL << 37)
+#define BIC_CPU         (1ULL << 38)
+#define BIC_Mod_c6      (1ULL << 39)
+#define BIC_sysfs       (1ULL << 40)
+#define BIC_Totl_c0     (1ULL << 41)
+#define BIC_Any_c0      (1ULL << 42)
+#define BIC_GFX_c0      (1ULL << 43)
+#define BIC_CPUGFX      (1ULL << 44)
+#define BIC_Node        (1ULL << 45)
+
+#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD)
+
+unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT);
+unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs;
 
 #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME)
+#define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME)
 #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT)
 #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT)
 
+
 #define MAX_DEFERRED 16
 char *deferred_skip_names[MAX_DEFERRED];
 int deferred_skip_index;
@@ -469,9 +522,10 @@ void help(void)
         "--cpu  cpu-set limit output to summary plus cpu-set:\n"
         "               {core | package | j,k,l..m,n-p }\n"
         "--quiet        skip decoding system configuration header\n"
-        "--interval sec Override default 5-second measurement interval\n"
+        "--interval sec.subsec  Override default 5-second measurement interval\n"
         "--help         print this help message\n"
         "--list         list column headers only\n"
+        "--num_iterations num   number of the measurement iterations\n"
         "--out file     create or truncate \"file\" for all output\n"
         "--version      print version information\n"
         "\n"
@@ -496,6 +550,9 @@ unsigned long long bic_lookup(char *name_list, enum show_hide_mode mode)
                 if (comma)
                         *comma = '\0';
 
+                if (!strcmp(name_list, "all"))
+                        return ~0;
+
                 for (i = 0; i < MAX_BIC; ++i) {
                         if (!strcmp(name_list, bic[i].name)) {
                                 retval |= (1ULL << i);
@@ -532,10 +589,14 @@ void print_header(char *delim)
         struct msr_counter *mp;
         int printed = 0;
 
-        if (debug)
-                outp += sprintf(outp, "usec %s", delim);
+        if (DO_BIC(BIC_USEC))
+                outp += sprintf(outp, "%susec", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_TOD))
+                outp += sprintf(outp, "%sTime_Of_Day_Seconds", (printed++ ? delim : ""));
         if (DO_BIC(BIC_Package))
                 outp += sprintf(outp, "%sPackage", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_Node))
+                outp += sprintf(outp, "%sNode", (printed++ ? delim : ""));
         if (DO_BIC(BIC_Core))
                 outp += sprintf(outp, "%sCore", (printed++ ? delim : ""));
         if (DO_BIC(BIC_CPU))
@@ -576,7 +637,7 @@ void print_header(char *delim)
 
         if (DO_BIC(BIC_CPU_c1))
                 outp += sprintf(outp, "%sCPU%%c1", (printed++ ? delim : ""));
-        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
                 outp += sprintf(outp, "%sCPU%%c3", (printed++ ? delim : ""));
         if (DO_BIC(BIC_CPU_c6))
                 outp += sprintf(outp, "%sCPU%%c6", (printed++ ? delim : ""));
@@ -635,6 +696,10 @@ void print_header(char *delim)
                 outp += sprintf(outp, "%sPkg%%pc9", (printed++ ? delim : ""));
         if (DO_BIC(BIC_Pkgpc10))
                 outp += sprintf(outp, "%sPk%%pc10", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_CPU_LPI))
+                outp += sprintf(outp, "%sCPU%%LPI", (printed++ ? delim : ""));
+        if (DO_BIC(BIC_SYS_LPI))
+                outp += sprintf(outp, "%sSYS%%LPI", (printed++ ? delim : ""));
 
         if (do_rapl && !rapl_joules) {
                 if (DO_BIC(BIC_PkgWatt))
@@ -739,6 +804,9 @@ int dump_counters(struct thread_data *t, struct core_data *c,
                 outp += sprintf(outp, "pc8: %016llX\n", p->pc8);
                 outp += sprintf(outp, "pc9: %016llX\n", p->pc9);
                 outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+                outp += sprintf(outp, "pc10: %016llX\n", p->pc10);
+                outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi);
+                outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi);
                 outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg);
                 outp += sprintf(outp, "Joules COR: %0X\n", p->energy_cores);
                 outp += sprintf(outp, "Joules GFX: %0X\n", p->energy_gfx);
@@ -786,7 +854,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
                 (cpu_subset && !CPU_ISSET_S(t->cpu_id, cpu_subset_size, cpu_subset)))
                 return 0;
 
-        if (debug) {
+        if (DO_BIC(BIC_USEC)) {
                 /* on each row, print how many usec each timestamp took to gather */
                 struct timeval tv;
 
@@ -794,6 +862,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
                 outp += sprintf(outp, "%5ld\t", tv.tv_sec * 1000000 + tv.tv_usec);
         }
 
+        /* Time_Of_Day_Seconds: on each row, print sec.usec last timestamp taken */
+        if (DO_BIC(BIC_TOD))
+                outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec);
+
         interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0;
 
         tsc = t->tsc * tsc_tweak;
@@ -802,6 +874,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
         if (t == &average.threads) {
                 if (DO_BIC(BIC_Package))
                         outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
+                if (DO_BIC(BIC_Node))
+                        outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
                 if (DO_BIC(BIC_Core))
                         outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
                 if (DO_BIC(BIC_CPU))
@@ -813,6 +887,15 @@ int format_counters(struct thread_data *t, struct core_data *c,
                         else
                                 outp += sprintf(outp, "%s-", (printed++ ? delim : ""));
                 }
+                if (DO_BIC(BIC_Node)) {
+                        if (t)
+                                outp += sprintf(outp, "%s%d",
+                                                (printed++ ? delim : ""),
+                                              cpus[t->cpu_id].physical_node_id);
+                        else
+                                outp += sprintf(outp, "%s-",
+                                                (printed++ ? delim : ""));
+                }
                 if (DO_BIC(BIC_Core)) {
                         if (c)
                                 outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), c->core_id);
@@ -882,7 +965,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
         if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
                 goto done;
 
-        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates)
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates)
                 outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c3/tsc);
         if (DO_BIC(BIC_CPU_c6))
                 outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * c->c6/tsc);
@@ -959,6 +1042,11 @@ int format_counters(struct thread_data *t, struct core_data *c,
         if (DO_BIC(BIC_Pkgpc10))
                 outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->pc10/tsc);
 
+        if (DO_BIC(BIC_CPU_LPI))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->cpu_lpi / 1000000.0 / interval_float);
+        if (DO_BIC(BIC_SYS_LPI))
+                outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), 100.0 * p->sys_lpi / 1000000.0 / interval_float);
+
         /*
          * If measurement interval exceeds minimum RAPL Joule Counter range,
          * indicate that results are suspect by printing "**" in fraction place.
@@ -1006,7 +1094,8 @@ int format_counters(struct thread_data *t, struct core_data *c,
         }
 
 done:
-        outp += sprintf(outp, "\n");
+        if (*(outp - 1) != '\n')
+                outp += sprintf(outp, "\n");
 
         return 0;
 }
@@ -1083,6 +1172,8 @@ delta_package(struct pkg_data *new, struct pkg_data *old)
         old->pc8 = new->pc8 - old->pc8;
         old->pc9 = new->pc9 - old->pc9;
         old->pc10 = new->pc10 - old->pc10;
+        old->cpu_lpi = new->cpu_lpi - old->cpu_lpi;
+        old->sys_lpi = new->sys_lpi - old->sys_lpi;
         old->pkg_temp_c = new->pkg_temp_c;
 
         /* flag an error when rc6 counter resets/wraps */
@@ -1140,6 +1231,15 @@ delta_thread(struct thread_data *new, struct thread_data *old,
         int i;
         struct msr_counter *mp;
 
+        /*
+         * the timestamps from start of measurement interval are in "old"
+         * the timestamp from end of measurement interval are in "new"
+         * over-write old w/ new so we can print end of interval values
+         */
+
+        old->tv_begin = new->tv_begin;
+        old->tv_end = new->tv_end;
+
         old->tsc = new->tsc - old->tsc;
 
         /* check for TSC < 1 Mcycles over interval */
@@ -1228,6 +1328,11 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
         int i;
         struct msr_counter  *mp;
 
+        t->tv_begin.tv_sec = 0;
+        t->tv_begin.tv_usec = 0;
+        t->tv_end.tv_sec = 0;
+        t->tv_end.tv_usec = 0;
+
         t->tsc = 0;
         t->aperf = 0;
         t->mperf = 0;
@@ -1260,6 +1365,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
         p->pc8 = 0;
         p->pc9 = 0;
         p->pc10 = 0;
+        p->cpu_lpi = 0;
+        p->sys_lpi = 0;
 
         p->energy_pkg = 0;
         p->energy_dram = 0;
@@ -1286,6 +1393,13 @@ int sum_counters(struct thread_data *t, struct core_data *c,
         int i;
         struct msr_counter *mp;
 
+        /* remember first tv_begin */
+        if (average.threads.tv_begin.tv_sec == 0)
+                average.threads.tv_begin = t->tv_begin;
+
+        /* remember last tv_end */
+        average.threads.tv_end = t->tv_end;
+
         average.threads.tsc += t->tsc;
         average.threads.aperf += t->aperf;
         average.threads.mperf += t->mperf;
@@ -1341,6 +1455,9 @@ int sum_counters(struct thread_data *t, struct core_data *c,
         average.packages.pc9 += p->pc9;
         average.packages.pc10 += p->pc10;
 
+        average.packages.cpu_lpi = p->cpu_lpi;
+        average.packages.sys_lpi = p->sys_lpi;
+
         average.packages.energy_pkg += p->energy_pkg;
         average.packages.energy_dram += p->energy_dram;
         average.packages.energy_cores += p->energy_cores;
@@ -1487,7 +1604,7 @@ int get_mp(int cpu, struct msr_counter *mp, unsigned long long *counterp)
                 if (get_msr(cpu, mp->msr_num, counterp))
                         return -1;
         } else {
-                char path[128];
+                char path[128 + PATH_BYTES];
 
                 if (mp->flags & SYSFS_PERCPU) {
                         sprintf(path, "/sys/devices/system/cpu/cpu%d/%s",
@@ -1603,7 +1720,7 @@ retry:
         if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE))
                 goto done;
 
-        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates) {
+        if (DO_BIC(BIC_CPU_c3) && !do_slm_cstates && !do_knl_cstates && !do_cnl_cstates) {
                 if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3))
                         return -6;
         }
@@ -1684,6 +1801,11 @@ retry:
                 if (get_msr(cpu, MSR_PKG_C10_RESIDENCY, &p->pc10))
                         return -13;
 
+        if (DO_BIC(BIC_CPU_LPI))
+                p->cpu_lpi = cpuidle_cur_cpu_lpi_us;
+        if (DO_BIC(BIC_SYS_LPI))
+                p->sys_lpi = cpuidle_cur_sys_lpi_us;
+
         if (do_rapl & RAPL_PKG) {
                 if (get_msr(cpu, MSR_PKG_ENERGY_STATUS, &msr))
                         return -13;
@@ -1769,7 +1891,7 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCLUNL, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int bxt_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
-int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
+int skx_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
 
 static void
@@ -2071,12 +2193,9 @@ dump_nhm_cst_cfg(void)
 
         get_msr(base_cpu, MSR_PKG_CST_CONFIG_CONTROL, &msr);
 
-#define SNB_C1_AUTO_UNDEMOTE              (1UL << 27)
-#define SNB_C3_AUTO_UNDEMOTE              (1UL << 28)
-
         fprintf(outf, "cpu%d: MSR_PKG_CST_CONFIG_CONTROL: 0x%08llx", base_cpu, msr);
 
-        fprintf(outf, " (%s%s%s%s%slocked: pkg-cstate-limit=%d: %s)\n",
+        fprintf(outf, " (%s%s%s%s%slocked, pkg-cstate-limit=%d (%s)",
                 (msr & SNB_C3_AUTO_UNDEMOTE) ? "UNdemote-C3, " : "",
                 (msr & SNB_C1_AUTO_UNDEMOTE) ? "UNdemote-C1, " : "",
                 (msr & NHM_C3_AUTO_DEMOTE) ? "demote-C3, " : "",
@@ -2084,6 +2203,15 @@ dump_nhm_cst_cfg(void)
                 (msr & (1 << 15)) ? "" : "UN",
                 (unsigned int)msr & 0xF,
                 pkg_cstate_limit_strings[pkg_cstate_limit]);
+
+#define AUTOMATIC_CSTATE_CONVERSION             (1UL << 16)
+        if (has_automatic_cstate_conversion) {
+                fprintf(outf, ", automatic c-state conversion=%s",
+                        (msr & AUTOMATIC_CSTATE_CONVERSION) ? "on" : "off");
+        }
+
+        fprintf(outf, ")\n");
+
         return;
 }
 
@@ -2184,6 +2312,8 @@ void free_fd_percpu(void)
 
 void free_all_buffers(void)
 {
+        int i;
+
         CPU_FREE(cpu_present_set);
         cpu_present_set = NULL;
         cpu_present_setsize = 0;
@@ -2216,6 +2346,12 @@ void free_all_buffers(void)
 
         free(irq_column_2_cpu);
         free(irqs_per_cpu);
+
+        for (i = 0; i <= topo.max_cpu_num; ++i) {
+                if (cpus[i].put_ids)
+                        CPU_FREE(cpus[i].put_ids);
+        }
+        free(cpus);
 }
 
 
@@ -2240,44 +2376,6 @@ int parse_int_file(const char *fmt, ...)
 }
 
 /*
- * get_cpu_position_in_core(cpu)
- * return the position of the CPU among its HT siblings in the core
- * return -1 if the sibling is not in list
- */
-int get_cpu_position_in_core(int cpu)
-{
-        char path[64];
-        FILE *filep;
-        int this_cpu;
-        char character;
-        int i;
-
-        sprintf(path,
-                "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list",
-                cpu);
-        filep = fopen(path, "r");
-        if (filep == NULL) {
-                perror(path);
-                exit(1);
-        }
-
-        for (i = 0; i < topo.num_threads_per_core; i++) {
-                fscanf(filep, "%d", &this_cpu);
-                if (this_cpu == cpu) {
-                        fclose(filep);
-                        return i;
-                }
-
-                /* Account for no separator after last thread*/
-                if (i != (topo.num_threads_per_core - 1))
-                        fscanf(filep, "%c", &character);
-        }
-
-        fclose(filep);
-        return -1;
-}
-
-/*
  * cpu_is_first_core_in_package(cpu)
  * return 1 if given CPU is 1st core in package
  */
@@ -2296,35 +2394,115 @@ int get_core_id(int cpu)
         return parse_int_file("/sys/devices/system/cpu/cpu%d/topology/core_id", cpu);
 }
 
-int get_num_ht_siblings(int cpu)
+void set_node_data(void)
 {
         char path[80];
         FILE *filep;
-        int sib1;
-        int matches = 0;
-        char character;
-        char str[100];
-        char *ch;
+        int pkg, node, cpu;
 
-        sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu);
-        filep = fopen_or_die(path, "r");
+        struct pkg_node_info {
+                int count;
+                int min;
+        } *pni;
 
-        /*
-         * file format:
-         * A ',' separated or '-' separated set of numbers
-         * (eg 1-2 or 1,3,4,5)
-         */
-        fscanf(filep, "%d%c\n", &sib1, &character);
-        fseek(filep, 0, SEEK_SET);
-        fgets(str, 100, filep);
-        ch = strchr(str, character);
-        while (ch != NULL) {
-                matches++;
-                ch = strchr(ch+1, character);
+        pni = calloc(topo.num_packages, sizeof(struct pkg_node_info));
+        if (!pni)
+                err(1, "calloc pkg_node_count");
+
+        for (pkg = 0; pkg < topo.num_packages; pkg++)
+                pni[pkg].min = topo.num_cpus;
+
+        for (node = 0; node <= topo.max_node_num; node++) {
+                /* find the "first" cpu in the node */
+                sprintf(path, "/sys/bus/node/devices/node%d/cpulist", node);
+                filep = fopen(path, "r");
+                if (!filep)
+                        continue;
+                fscanf(filep, "%d", &cpu);
+                fclose(filep);
+
+                pkg = cpus[cpu].physical_package_id;
+                pni[pkg].count++;
+
+                if (node < pni[pkg].min)
+                        pni[pkg].min = node;
         }
 
+        for (pkg = 0; pkg < topo.num_packages; pkg++)
+                if (pni[pkg].count > topo.nodes_per_pkg)
+                        topo.nodes_per_pkg = pni[0].count;
+
+        for (cpu = 0; cpu < topo.num_cpus; cpu++) {
+                pkg = cpus[cpu].physical_package_id;
+                node = cpus[cpu].physical_node_id;
+                cpus[cpu].logical_node_id = node - pni[pkg].min;
+        }
+        free(pni);
+
+}
+
+int get_physical_node_id(struct cpu_topology *thiscpu)
+{
+        char path[80];
+        FILE *filep;
+        int i;
+        int cpu = thiscpu->logical_cpu_id;
+
+        for (i = 0; i <= topo.max_cpu_num; i++) {
+                sprintf(path, "/sys/devices/system/cpu/cpu%d/node%i/cpulist",
+                        cpu, i);
+                filep = fopen(path, "r");
+                if (!filep)
+                        continue;
+                fclose(filep);
+                return i;
+        }
+        return -1;
+}
+
+int get_thread_siblings(struct cpu_topology *thiscpu)
+{
+        char path[80], character;
+        FILE *filep;
+        unsigned long map;
+        int so, shift, sib_core;
+        int cpu = thiscpu->logical_cpu_id;
+        int offset = topo.max_cpu_num + 1;
+        size_t size;
+        int thread_id = 0;
+
+        thiscpu->put_ids = CPU_ALLOC((topo.max_cpu_num + 1));
+        if (thiscpu->thread_id < 0)
+                thiscpu->thread_id = thread_id++;
+        if (!thiscpu->put_ids)
+                return -1;
+
+        size = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
+        CPU_ZERO_S(size, thiscpu->put_ids);
+
+        sprintf(path,
+                "/sys/devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
+        filep = fopen_or_die(path, "r");
+        do {
+                offset -= BITMASK_SIZE;
+                fscanf(filep, "%lx%c", &map, &character);
+                for (shift = 0; shift < BITMASK_SIZE; shift++) {
+                        if ((map >> shift) & 0x1) {
+                                so = shift + offset;
+                                sib_core = get_core_id(so);
+                                if (sib_core == thiscpu->physical_core_id) {
+                                        CPU_SET_S(so, size, thiscpu->put_ids);
+                                        if ((so != cpu) &&
+                                            (cpus[so].thread_id < 0))
+                                                cpus[so].thread_id =
+                                                                    thread_id++;
+                                }
+                        }
+                }
+        } while (!strncmp(&character, ",", 1));
         fclose(filep);
-        return matches+1;
+
+        return CPU_COUNT_S(size, thiscpu->put_ids);
 }
 
 /*
@@ -2339,32 +2517,42 @@ int for_all_cpus_2(int (func)(struct thread_data *, struct core_data *,
         struct thread_data *thread_base2, struct core_data *core_base2,
         struct pkg_data *pkg_base2)
 {
-        int retval, pkg_no, core_no, thread_no;
+        int retval, pkg_no, node_no, core_no, thread_no;
 
         for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) {
-                for (core_no = 0; core_no < topo.num_cores_per_pkg; ++core_no) {
-                        for (thread_no = 0; thread_no <
-                                topo.num_threads_per_core; ++thread_no) {
-                                struct thread_data *t, *t2;
-                                struct core_data *c, *c2;
-                                struct pkg_data *p, *p2;
-
-                                t = GET_THREAD(thread_base, thread_no, core_no, pkg_no);
-
-                                if (cpu_is_not_present(t->cpu_id))
-                                        continue;
-
-                                t2 = GET_THREAD(thread_base2, thread_no, core_no, pkg_no);
-
-                                c = GET_CORE(core_base, core_no, pkg_no);
-                                c2 = GET_CORE(core_base2, core_no, pkg_no);
-
-                                p = GET_PKG(pkg_base, pkg_no);
-                                p2 = GET_PKG(pkg_base2, pkg_no);
-
-                                retval = func(t, c, p, t2, c2, p2);
-                                if (retval)
-                                        return retval;
+                for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) {
+                        for (core_no = 0; core_no < topo.cores_per_node;
+                             ++core_no) {
+                                for (thread_no = 0; thread_no <
+                                        topo.threads_per_core; ++thread_no) {
+                                        struct thread_data *t, *t2;
+                                        struct core_data *c, *c2;
+                                        struct pkg_data *p, *p2;
+
+                                        t = GET_THREAD(thread_base, thread_no,
+                                                       core_no, node_no,
+                                                       pkg_no);
+
+                                        if (cpu_is_not_present(t->cpu_id))
+                                                continue;
+
+                                        t2 = GET_THREAD(thread_base2, thread_no,
+                                                        core_no, node_no,
+                                                        pkg_no);
+
+                                        c = GET_CORE(core_base, core_no,
+                                                     node_no, pkg_no);
+                                        c2 = GET_CORE(core_base2, core_no,
+                                                      node_no,
+                                                      pkg_no);
+
+                                        p = GET_PKG(pkg_base, pkg_no);
+                                        p2 = GET_PKG(pkg_base2, pkg_no);
+
+                                        retval = func(t, c, p, t2, c2, p2);
+                                        if (retval)
+                                                return retval;
+                                }
                         }
                 }
         }
@@ -2409,6 +2597,20 @@ void re_initialize(void)
         printf("turbostat: re-initialized with num_cpus %d\n", topo.num_cpus);
 }
 
+void set_max_cpu_num(void)
+{
+        FILE *filep;
+        unsigned long dummy;
+
+        topo.max_cpu_num = 0;
+        filep = fopen_or_die(
+                        "/sys/devices/system/cpu/cpu0/topology/thread_siblings",
+                        "r");
+        while (fscanf(filep, "%lx,", &dummy) == 1)
+                topo.max_cpu_num += BITMASK_SIZE;
+        fclose(filep);
+        topo.max_cpu_num--; /* 0 based */
+}
 
 /*
  * count_cpus()
@@ -2416,10 +2618,7 @@ void re_initialize(void)
  */
 int count_cpus(int cpu)
 {
-        if (topo.max_cpu_num < cpu)
-                topo.max_cpu_num = cpu;
-
-        topo.num_cpus += 1;
+        topo.num_cpus++;
         return 0;
 }
 int mark_cpu_present(int cpu)
@@ -2428,6 +2627,12 @@ int mark_cpu_present(int cpu)
         return 0;
 }
 
+int init_thread_id(int cpu)
+{
+        cpus[cpu].thread_id = -1;
+        return 0;
+}
+
 /*
  * snapshot_proc_interrupts()
  *
@@ -2542,6 +2747,52 @@ int snapshot_gfx_mhz(void)
 }
 
 /*
+ * snapshot_cpu_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_cpu_lpi_us(void)
+{
+        FILE *fp;
+        int retval;
+
+        fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", "r");
+
+        retval = fscanf(fp, "%lld", &cpuidle_cur_cpu_lpi_us);
+        if (retval != 1)
+                err(1, "CPU LPI");
+
+        fclose(fp);
+
+        return 0;
+}
+/*
+ * snapshot_sys_lpi()
+ *
+ * record snapshot of
+ * /sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us
+ *
+ * return 1 if config change requires a restart, else return 0
+ */
+int snapshot_sys_lpi_us(void)
+{
+        FILE *fp;
+        int retval;
+
+        fp = fopen_or_die("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", "r");
+
+        retval = fscanf(fp, "%lld", &cpuidle_cur_sys_lpi_us);
+        if (retval != 1)
+                err(1, "SYS LPI");
+
+        fclose(fp);
+
+        return 0;
+}
+/*
  * snapshot /proc and /sys files
  *
  * return 1 if configuration restart needed, else return 0
@@ -2558,13 +2809,83 @@ int snapshot_proc_sysfs_files(void)
         if (DO_BIC(BIC_GFXMHz))
                 snapshot_gfx_mhz();
 
+        if (DO_BIC(BIC_CPU_LPI))
+                snapshot_cpu_lpi_us();
+
+        if (DO_BIC(BIC_SYS_LPI))
+                snapshot_sys_lpi_us();
+
         return 0;
 }
 
+int exit_requested;
+
+static void signal_handler (int signal)
+{
+        switch (signal) {
+        case SIGINT:
+                exit_requested = 1;
+                if (debug)
+                        fprintf(stderr, " SIGINT\n");
+                break;
+        case SIGUSR1:
+                if (debug > 1)
+                        fprintf(stderr, "SIGUSR1\n");
+                break;
+        }
+        /* make sure this manually-invoked interval is at least 1ms long */
+        nanosleep(&one_msec, NULL);
+}
+
+void setup_signal_handler(void)
+{
+        struct sigaction sa;
+
+        memset(&sa, 0, sizeof(sa));
+
+        sa.sa_handler = &signal_handler;
+
+        if (sigaction(SIGINT, &sa, NULL) < 0)
+                err(1, "sigaction SIGINT");
+        if (sigaction(SIGUSR1, &sa, NULL) < 0)
+                err(1, "sigaction SIGUSR1");
+}
+
+void do_sleep(void)
+{
+        struct timeval select_timeout;
+        fd_set readfds;
+        int retval;
+
+        FD_ZERO(&readfds);
+        FD_SET(0, &readfds);
+
+        if (!isatty(fileno(stdin))) {
+                nanosleep(&interval_ts, NULL);
+                return;
+        }
+
+        select_timeout = interval_tv;
+        retval = select(1, &readfds, NULL, NULL, &select_timeout);
+
+        if (retval == 1) {
+                switch (getc(stdin)) {
+                case 'q':
+                        exit_requested = 1;
+                        break;
+                }
+                /* make sure this manually-invoked interval is at least 1ms long */
+                nanosleep(&one_msec, NULL);
+        }
+}
+
 void turbostat_loop()
 {
         int retval;
         int restarted = 0;
+        int done_iters = 0;
+
+        setup_signal_handler();
 
 restart:
         restarted++;
@@ -2581,6 +2902,7 @@ restart:
                 goto restart;
         }
         restarted = 0;
+        done_iters = 0;
         gettimeofday(&tv_even, (struct timezone *)NULL);
 
         while (1) {
@@ -2588,7 +2910,7 @@ restart:
                         re_initialize();
                         goto restart;
                 }
-                nanosleep(&interval_ts, NULL);
+                do_sleep();
                 if (snapshot_proc_sysfs_files())
                         goto restart;
                 retval = for_all_cpus(get_counters, ODD_COUNTERS);
@@ -2607,7 +2929,11 @@ restart:
                 compute_average(EVEN_COUNTERS);
                 format_all_counters(EVEN_COUNTERS);
                 flush_output_stdout();
-                nanosleep(&interval_ts, NULL);
+                if (exit_requested)
+                        break;
+                if (num_iterations && ++done_iters >= num_iterations)
+                        break;
+                do_sleep();
                 if (snapshot_proc_sysfs_files())
                         goto restart;
                 retval = for_all_cpus(get_counters, EVEN_COUNTERS);
@@ -2626,6 +2952,10 @@ restart:
                 compute_average(ODD_COUNTERS);
                 format_all_counters(ODD_COUNTERS);
                 flush_output_stdout();
+                if (exit_requested)
+                        break;
+                if (num_iterations && ++done_iters >= num_iterations)
+                        break;
         }
 }
 
@@ -2740,6 +3070,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
                 pkg_cstate_limits = hsw_pkg_cstate_limits;
                 has_misc_feature_control = 1;
                 break;
@@ -2945,6 +3276,7 @@ int has_config_tdp(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
         case INTEL_FAM6_SKYLAKE_X:      /* SKX */
 
         case INTEL_FAM6_XEON_PHI_KNL:   /* Knights Landing */
@@ -3399,6 +3731,7 @@ void rapl_probe(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
                 do_rapl = RAPL_PKG | RAPL_CORES | RAPL_CORE_POLICY | RAPL_DRAM | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_GFX | RAPL_PKG_POWER_INFO;
                 BIC_PRESENT(BIC_PKG__);
                 BIC_PRESENT(BIC_RAM__);
@@ -3523,6 +3856,12 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model)
         }
 }
 
+void automatic_cstate_conversion_probe(unsigned int family, unsigned int model)
+{
+        if (is_skx(family, model) || is_bdx(family, model))
+                has_automatic_cstate_conversion = 1;
+}
+
 int print_thermal(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 {
         unsigned long long msr;
@@ -3728,6 +4067,7 @@ int has_snb_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
         case INTEL_FAM6_SKYLAKE_X:      /* SKX */
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
         case INTEL_FAM6_ATOM_GEMINI_LAKE:
@@ -3761,6 +4101,7 @@ int has_hsw_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
         case INTEL_FAM6_ATOM_GOLDMONT:  /* BXT */
         case INTEL_FAM6_ATOM_GEMINI_LAKE:
                 return 1;
@@ -3786,6 +4127,7 @@ int has_skl_msrs(unsigned int family, unsigned int model)
         case INTEL_FAM6_SKYLAKE_DESKTOP:        /* SKL */
         case INTEL_FAM6_KABYLAKE_MOBILE:        /* KBL */
         case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
+        case INTEL_FAM6_CANNONLAKE_MOBILE:      /* CNL */
                 return 1;
         }
         return 0;
@@ -3815,6 +4157,19 @@ int is_knl(unsigned int family, unsigned int model)
         return 0;
 }
 
+int is_cnl(unsigned int family, unsigned int model)
+{
+        if (!genuine_intel)
+                return 0;
+
+        switch (model) {
+        case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */
+                return 1;
+        }
+
+        return 0;
+}
+
 unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
 {
         if (is_knl(family, model))
@@ -3947,7 +4302,7 @@ void decode_misc_enable_msr(void)
                         base_cpu, msr,
                         msr & MSR_IA32_MISC_ENABLE_TM1 ? "" : "No-",
                         msr & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP ? "" : "No-",
-                        msr & MSR_IA32_MISC_ENABLE_MWAIT ? "No-" : "",
+                        msr & MSR_IA32_MISC_ENABLE_MWAIT ? "" : "No-",
                         msr & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE ? "No-" : "",
                         msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ? "No-" : "");
 }
@@ -4152,7 +4507,6 @@ void process_cpuid()
                                 case INTEL_FAM6_KABYLAKE_DESKTOP:       /* KBL */
                                         crystal_hz = 24000000;  /* 24.0 MHz */
                                         break;
-                                case INTEL_FAM6_SKYLAKE_X:      /* SKX */
                                 case INTEL_FAM6_ATOM_DENVERTON: /* DNV */
                                         crystal_hz = 25000000;  /* 25.0 MHz */
                                         break;
@@ -4253,6 +4607,7 @@ void process_cpuid()
         }
         do_slm_cstates = is_slm(family, model);
         do_knl_cstates  = is_knl(family, model);
+        do_cnl_cstates = is_cnl(family, model);
 
         if (!quiet)
                 decode_misc_pwr_mgmt_msr();
@@ -4262,6 +4617,7 @@ void process_cpuid()
 
         rapl_probe(family, model);
         perf_limit_reasons_probe(family, model);
+        automatic_cstate_conversion_probe(family, model);
 
         if (!quiet)
                 dump_cstate_pstate_config_info(family, model);
@@ -4280,6 +4636,16 @@ void process_cpuid()
         if (!access("/sys/class/graphics/fb0/device/drm/card0/gt_cur_freq_mhz", R_OK))
                 BIC_PRESENT(BIC_GFXMHz);
 
+        if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_cpu_residency_us", R_OK))
+                BIC_PRESENT(BIC_CPU_LPI);
+        else
+                BIC_NOT_PRESENT(BIC_CPU_LPI);
+
+        if (!access("/sys/devices/system/cpu/cpuidle/low_power_idle_system_residency_us", R_OK))
+                BIC_PRESENT(BIC_SYS_LPI);
+        else
+                BIC_NOT_PRESENT(BIC_SYS_LPI);
+
         if (!quiet)
                 decode_misc_feature_control();
 
@@ -4310,14 +4676,10 @@ void topology_probe()
         int max_core_id = 0;
         int max_package_id = 0;
         int max_siblings = 0;
-        struct cpu_topology {
-                int core_id;
-                int physical_package_id;
-        } *cpus;
 
         /* Initialize num_cpus, max_cpu_num */
+        set_max_cpu_num();
         topo.num_cpus = 0;
-        topo.max_cpu_num = 0;
         for_all_proc_cpus(count_cpus);
         if (!summary_only && topo.num_cpus > 1)
                 BIC_PRESENT(BIC_CPU);
@@ -4357,6 +4719,7 @@ void topology_probe()
         cpu_affinity_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1));
         CPU_ZERO_S(cpu_affinity_setsize, cpu_affinity_set);
 
+        for_all_proc_cpus(init_thread_id);
 
         /*
          * For online cpus
@@ -4370,26 +4733,45 @@ void topology_probe()
                                 fprintf(outf, "cpu%d NOT PRESENT\n", i);
                         continue;
                 }
-                cpus[i].core_id = get_core_id(i);
-                if (cpus[i].core_id > max_core_id)
-                        max_core_id = cpus[i].core_id;
 
+                cpus[i].logical_cpu_id = i;
+
+                /* get package information */
                 cpus[i].physical_package_id = get_physical_package_id(i);
                 if (cpus[i].physical_package_id > max_package_id)
                         max_package_id = cpus[i].physical_package_id;
 
-                siblings = get_num_ht_siblings(i);
+                /* get numa node information */
+                cpus[i].physical_node_id = get_physical_node_id(&cpus[i]);
+                if (cpus[i].physical_node_id > topo.max_node_num)
+                        topo.max_node_num = cpus[i].physical_node_id;
+
+                /* get core information */
+                cpus[i].physical_core_id = get_core_id(i);
+                if (cpus[i].physical_core_id > max_core_id)
+                        max_core_id = cpus[i].physical_core_id;
+
+                /* get thread information */
+                siblings = get_thread_siblings(&cpus[i]);
                 if (siblings > max_siblings)
                         max_siblings = siblings;
+                if (cpus[i].thread_id != -1)
+                        topo.num_cores++;
+
                 if (debug > 1)
-                        fprintf(outf, "cpu %d pkg %d core %d\n",
-                                i, cpus[i].physical_package_id, cpus[i].core_id);
+                        fprintf(outf,
+                                "cpu %d pkg %d node %d core %d thread %d\n",
+                                i, cpus[i].physical_package_id,
+                                cpus[i].physical_node_id,
+                                cpus[i].physical_core_id,
+                                cpus[i].thread_id);
         }
-        topo.num_cores_per_pkg = max_core_id + 1;
+
+        topo.cores_per_node = max_core_id + 1;
         if (debug > 1)
                 fprintf(outf, "max_core_id %d, sizing for %d cores per package\n",
-                        max_core_id, topo.num_cores_per_pkg);
-        if (!summary_only && topo.num_cores_per_pkg > 1)
+                        max_core_id, topo.cores_per_node);
+        if (!summary_only && topo.cores_per_node > 1)
                 BIC_PRESENT(BIC_Core);
 
         topo.num_packages = max_package_id + 1;
@@ -4399,33 +4781,38 @@ void topology_probe()
         if (!summary_only && topo.num_packages > 1)
                 BIC_PRESENT(BIC_Package);
 
-        topo.num_threads_per_core = max_siblings;
+        set_node_data();
         if (debug > 1)
-                fprintf(outf, "max_siblings %d\n", max_siblings);
+                fprintf(outf, "nodes_per_pkg %d\n", topo.nodes_per_pkg);
+        if (!summary_only && topo.nodes_per_pkg > 1)
+                BIC_PRESENT(BIC_Node);
 
-        free(cpus);
+        topo.threads_per_core = max_siblings;
+        if (debug > 1)
+                fprintf(outf, "max_siblings %d\n", max_siblings);
 }
 
 void
-allocate_counters(struct thread_data **t, struct core_data **c, struct pkg_data **p)
+allocate_counters(struct thread_data **t, struct core_data **c,
+                  struct pkg_data **p)
 {
         int i;
+        int num_cores = topo.cores_per_node * topo.nodes_per_pkg *
+                        topo.num_packages;
+        int num_threads = topo.threads_per_core * num_cores;
 
-        *t = calloc(topo.num_threads_per_core * topo.num_cores_per_pkg *
-                topo.num_packages, sizeof(struct thread_data));
+        *t = calloc(num_threads, sizeof(struct thread_data));
         if (*t == NULL)
                 goto error;
 
-        for (i = 0; i < topo.num_threads_per_core *
-                topo.num_cores_per_pkg * topo.num_packages; i++)
+        for (i = 0; i < num_threads; i++)
                 (*t)[i].cpu_id = -1;
 
-        *c = calloc(topo.num_cores_per_pkg * topo.num_packages,
-                sizeof(struct core_data));
+        *c = calloc(num_cores, sizeof(struct core_data));
         if (*c == NULL)
                 goto error;
 
-        for (i = 0; i < topo.num_cores_per_pkg * topo.num_packages; i++)
+        for (i = 0; i < num_cores; i++)
                 (*c)[i].core_id = -1;
 
         *p = calloc(topo.num_packages, sizeof(struct pkg_data));
@@ -4442,47 +4829,39 @@ error:
 /*
  * init_counter()
  *
- * set cpu_id, core_num, pkg_num
  * set FIRST_THREAD_IN_CORE and FIRST_CORE_IN_PACKAGE
- *
- * increment topo.num_cores when 1st core in pkg seen
  */
 void init_counter(struct thread_data *thread_base, struct core_data *core_base,
-        struct pkg_data *pkg_base, int thread_num, int core_num,
-        int pkg_num, int cpu_id)
+        struct pkg_data *pkg_base, int cpu_id)
 {
+        int pkg_id = cpus[cpu_id].physical_package_id;
+        int node_id = cpus[cpu_id].logical_node_id;
+        int core_id = cpus[cpu_id].physical_core_id;
+        int thread_id = cpus[cpu_id].thread_id;
         struct thread_data *t;
         struct core_data *c;
         struct pkg_data *p;
 
-        t = GET_THREAD(thread_base, thread_num, core_num, pkg_num);
-        c = GET_CORE(core_base, core_num, pkg_num);
-        p = GET_PKG(pkg_base, pkg_num);
+        t = GET_THREAD(thread_base, thread_id, core_id, node_id, pkg_id);
+        c = GET_CORE(core_base, core_id, node_id, pkg_id);
+        p = GET_PKG(pkg_base, pkg_id);
 
         t->cpu_id = cpu_id;
-        if (thread_num == 0) {
+        if (thread_id == 0) {
                 t->flags |= CPU_IS_FIRST_THREAD_IN_CORE;
                 if (cpu_is_first_core_in_package(cpu_id))
                         t->flags |= CPU_IS_FIRST_CORE_IN_PACKAGE;
         }
 
-        c->core_id = core_num;
-        p->package_id = pkg_num;
+        c->core_id = core_id;
+        p->package_id = pkg_id;
 }
 
 
 int initialize_counters(int cpu_id)
 {
-        int my_thread_id, my_core_id, my_package_id;
-
-        my_package_id = get_physical_package_id(cpu_id);
-        my_core_id = get_core_id(cpu_id);
-        my_thread_id = get_cpu_position_in_core(cpu_id);
-        if (!my_thread_id)
-                topo.num_cores++;
-
-        init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
-        init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id);
+        init_counter(EVEN_COUNTERS, cpu_id);
+        init_counter(ODD_COUNTERS, cpu_id);
         return 0;
 }
 
@@ -4630,7 +5009,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-        fprintf(outf, "turbostat version 17.06.23"
+        fprintf(outf, "turbostat version 18.06.01"
                 " - Len Brown <lenb@kernel.org>\n");
 }
 
@@ -4661,7 +5040,7 @@ int add_counter(unsigned int msr_num, char *path, char *name,
                 msrp->next = sys.tp;
                 sys.tp = msrp;
                 sys.added_thread_counters++;
-                if (sys.added_thread_counters > MAX_ADDED_COUNTERS) {
+                if (sys.added_thread_counters > MAX_ADDED_THREAD_COUNTERS) {
                         fprintf(stderr, "exceeded max %d added thread counters\n",
                                 MAX_ADDED_COUNTERS);
                         exit(-1);
@@ -4820,7 +5199,7 @@ void probe_sysfs(void)
         if (!DO_BIC(BIC_sysfs))
                 return;
 
-        for (state = 10; state > 0; --state) {
+        for (state = 10; state >= 0; --state) {
 
                 sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
                         base_cpu, state);
@@ -4847,7 +5226,7 @@ void probe_sysfs(void)
                                 FORMAT_PERCENT, SYSFS_PERCPU);
         }
 
-        for (state = 10; state > 0; --state) {
+        for (state = 10; state >= 0; --state) {
 
                 sprintf(path, "/sys/devices/system/cpu/cpu%d/cpuidle/state%d/name",
                         base_cpu, state);
@@ -4960,34 +5339,6 @@ error:
         exit(-1);
 }
 
-int shown;
-/*
- * parse_show_hide() - process cmdline to set default counter action
- */
-void parse_show_hide(char *optarg, enum show_hide_mode new_mode)
-{
-        /*
-         * --show: show only those specified
-         *  The 1st invocation will clear and replace the enabled mask
-         *  subsequent invocations can add to it.
-         */
-        if (new_mode == SHOW_LIST) {
-                if (shown == 0)
-                        bic_enabled = bic_lookup(optarg, new_mode);
-                else
-                        bic_enabled |= bic_lookup(optarg, new_mode);
-                shown = 1;
-
-                return;
-        }
-
-        /*
-         * --hide: do not show those specified
-         *  multiple invocations simply clear more bits in enabled mask
-         */
-        bic_enabled &= ~bic_lookup(optarg, new_mode);
-
-}
 
 void cmdline(int argc, char **argv)
 {
@@ -4998,7 +5349,9 @@ void cmdline(int argc, char **argv)
                 {"cpu",         required_argument,      0, 'c'},
                 {"Dump",        no_argument,            0, 'D'},
                 {"debug",       no_argument,            0, 'd'},        /* internal, not documented */
+                {"enable",      required_argument,      0, 'e'},
                 {"interval",    required_argument,      0, 'i'},
+                {"num_iterations",      required_argument,      0, 'n'},
                 {"help",        no_argument,            0, 'h'},
                 {"hide",        required_argument,      0, 'H'},        // meh, -h taken by --help
                 {"Joules",      no_argument,            0, 'J'},
@@ -5014,7 +5367,7 @@ void cmdline(int argc, char **argv)
 
         progname = argv[0];
 
-        while ((opt = getopt_long_only(argc, argv, "+C:c:Ddhi:JM:m:o:qST:v",
+        while ((opt = getopt_long_only(argc, argv, "+C:c:Dde:hi:Jn:o:qST:v",
                                 long_options, &option_index)) != -1) {
                 switch (opt) {
                 case 'a':
@@ -5026,11 +5379,20 @@ void cmdline(int argc, char **argv)
                 case 'D':
                         dump_only++;
                         break;
+                case 'e':
+                        /* --enable specified counter */
+                        bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+                        break;
                 case 'd':
                         debug++;
+                        ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
                         break;
                 case 'H':
-                        parse_show_hide(optarg, HIDE_LIST);
+                        /*
+                         * --hide: do not show those specified
+                         *  multiple invocations simply clear more bits in enabled mask
+                         */
+                        bic_enabled &= ~bic_lookup(optarg, HIDE_LIST);
                         break;
                 case 'h':
                 default:
@@ -5046,7 +5408,8 @@ void cmdline(int argc, char **argv)
                                         exit(2);
                                 }
 
-                                interval_ts.tv_sec = interval;
+                                interval_tv.tv_sec = interval_ts.tv_sec = interval;
+                                interval_tv.tv_usec = (interval - interval_tv.tv_sec) * 1000000;
                                 interval_ts.tv_nsec = (interval - interval_ts.tv_sec) * 1000000000;
                         }
                         break;
@@ -5054,6 +5417,7 @@ void cmdline(int argc, char **argv)
                         rapl_joules++;
                         break;
                 case 'l':
+                        ENABLE_BIC(BIC_DISABLED_BY_DEFAULT);
                         list_header_only++;
                         quiet++;
                         break;
@@ -5063,8 +5427,26 @@ void cmdline(int argc, char **argv)
                 case 'q':
                         quiet = 1;
                         break;
+                case 'n':
+                        num_iterations = strtod(optarg, NULL);
+
+                        if (num_iterations <= 0) {
+                                fprintf(outf, "iterations %d should be positive number\n",
+                                        num_iterations);
+                                exit(2);
+                        }
+                        break;
                 case 's':
-                        parse_show_hide(optarg, SHOW_LIST);
+                        /*
+                         * --show: show only those specified
+                         *  The 1st invocation will clear and replace the enabled mask
+                         *  subsequent invocations can add to it.
+                         */
+                        if (shown == 0)
+                                bic_enabled = bic_lookup(optarg, SHOW_LIST);
+                        else
+                                bic_enabled |= bic_lookup(optarg, SHOW_LIST);
+                        shown = 1;
                         break;
                 case 'S':
                         summary_only++;
diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile
index 2447b1bbaacf..f4534fb8b951 100644
--- a/tools/power/x86/x86_energy_perf_policy/Makefile
+++ b/tools/power/x86/x86_energy_perf_policy/Makefile
@@ -24,5 +24,5 @@ install : x86_energy_perf_policy
         install -d  $(DESTDIR)$(PREFIX)/bin
         install $(BUILD_OUTPUT)/x86_energy_perf_policy $(DESTDIR)$(PREFIX)/bin/x86_energy_perf_policy
         install -d  $(DESTDIR)$(PREFIX)/share/man/man8
-        install x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8
+        install -m 644 x86_energy_perf_policy.8 $(DESTDIR)$(PREFIX)/share/man/man8