tools lib: Adopt list_sort() from the kernel sources

Add list_sort.[ch] from the main kernel tree. The linux/bug.h #include
is removed due to conflicting definitions. Add check-headers and modify
perf build accordingly.

MANIFEST and python-ext-sources fixes suggested by Arnaldo.

Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Antonov <alexander.antonov@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andrew Kilroy <andrew.kilroy@arm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Denys Zagorui <dzagorui@cisco.com>
Cc: Fabian Hemmer <copy@copy.sh>
Cc: Felix Fietkau <nbd@nbd.name>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jacob Keller <jacob.e.keller@intel.com>
Cc: Jiapeng Chong <jiapeng.chong@linux.alibaba.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joakim Zhang <qiangqing.zhang@nxp.com>
Cc: John Garry <john.garry@huawei.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Kees Kook <keescook@chromium.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Nicholas Fraser <nfraser@codeweavers.com>
Cc: Nick Desaulniers <ndesaulniers@google.com>
Cc: Paul Clarke <pc@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Riccardo Mancini <rickyman7@gmail.com>
Cc: Sami Tolvanen <samitolvanen@google.com>
Cc: ShihCheng Tu <mrtoastcheng@gmail.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Sumanth Korikkar <sumanthk@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Wan Jiabing <wanjiabing@vivo.com>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Link: https://lore.kernel.org/r/20211015172132.1162559-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/include/linux/list_sort.h

@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LIST_SORT_H
+#define _LINUX_LIST_SORT_H
+
+#include <linux/types.h>
+
+struct list_head;
+
+typedef int __attribute__((nonnull(2,3))) (*list_cmp_func_t)(void *,
+		const struct list_head *, const struct list_head *);
+
+__attribute__((nonnull(2,3)))
+void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp);
+#endif

tools/lib/list_sort.c

@@ -0,0 +1,252 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/string.h>
+#include <linux/list_sort.h>
+#include <linux/list.h>
+
+/*
+ * Returns a list organized in an intermediate format suited
+ * to chaining of merge() calls: null-terminated, no reserved or
+ * sentinel head node, "prev" links not maintained.
+ */
+__attribute__((nonnull(2,3,4)))
+static struct list_head *merge(void *priv, list_cmp_func_t cmp,
+				struct list_head *a, struct list_head *b)
+{
+	struct list_head *head, **tail = &head;
+
+	for (;;) {
+		/* if equal, take 'a' -- important for sort stability */
+		if (cmp(priv, a, b) <= 0) {
+			*tail = a;
+			tail = &a->next;
+			a = a->next;
+			if (!a) {
+				*tail = b;
+				break;
+			}
+		} else {
+			*tail = b;
+			tail = &b->next;
+			b = b->next;
+			if (!b) {
+				*tail = a;
+				break;
+			}
+		}
+	}
+	return head;
+}
+
+/*
+ * Combine final list merge with restoration of standard doubly-linked
+ * list structure.  This approach duplicates code from merge(), but
+ * runs faster than the tidier alternatives of either a separate final
+ * prev-link restoration pass, or maintaining the prev links
+ * throughout.
+ */
+__attribute__((nonnull(2,3,4,5)))
+static void merge_final(void *priv, list_cmp_func_t cmp, struct list_head *head,
+			struct list_head *a, struct list_head *b)
+{
+	struct list_head *tail = head;
+	u8 count = 0;
+
+	for (;;) {
+		/* if equal, take 'a' -- important for sort stability */
+		if (cmp(priv, a, b) <= 0) {
+			tail->next = a;
+			a->prev = tail;
+			tail = a;
+			a = a->next;
+			if (!a)
+				break;
+		} else {
+			tail->next = b;
+			b->prev = tail;
+			tail = b;
+			b = b->next;
+			if (!b) {
+				b = a;
+				break;
+			}
+		}
+	}
+
+	/* Finish linking remainder of list b on to tail */
+	tail->next = b;
+	do {
+		/*
+		 * If the merge is highly unbalanced (e.g. the input is
+		 * already sorted), this loop may run many iterations.
+		 * Continue callbacks to the client even though no
+		 * element comparison is needed, so the client's cmp()
+		 * routine can invoke cond_resched() periodically.
+		 */
+		if (unlikely(!++count))
+			cmp(priv, b, b);
+		b->prev = tail;
+		tail = b;
+		b = b->next;
+	} while (b);
+
+	/* And the final links to make a circular doubly-linked list */
+	tail->next = head;
+	head->prev = tail;
+}
+
+/**
+ * list_sort - sort a list
+ * @priv: private data, opaque to list_sort(), passed to @cmp
+ * @head: the list to sort
+ * @cmp: the elements comparison function
+ *
+ * The comparison function @cmp must return > 0 if @a should sort after
+ * @b ("@a > @b" if you want an ascending sort), and <= 0 if @a should
+ * sort before @b *or* their original order should be preserved.  It is
+ * always called with the element that came first in the input in @a,
+ * and list_sort is a stable sort, so it is not necessary to distinguish
+ * the @a < @b and @a == @b cases.
+ *
+ * This is compatible with two styles of @cmp function:
+ * - The traditional style which returns <0 / =0 / >0, or
+ * - Returning a boolean 0/1.
+ * The latter offers a chance to save a few cycles in the comparison
+ * (which is used by e.g. plug_ctx_cmp() in block/blk-mq.c).
+ *
+ * A good way to write a multi-word comparison is::
+ *
+ *	if (a->high != b->high)
+ *		return a->high > b->high;
+ *	if (a->middle != b->middle)
+ *		return a->middle > b->middle;
+ *	return a->low > b->low;
+ *
+ *
+ * This mergesort is as eager as possible while always performing at least
+ * 2:1 balanced merges.  Given two pending sublists of size 2^k, they are
+ * merged to a size-2^(k+1) list as soon as we have 2^k following elements.
+ *
+ * Thus, it will avoid cache thrashing as long as 3*2^k elements can
+ * fit into the cache.  Not quite as good as a fully-eager bottom-up
+ * mergesort, but it does use 0.2*n fewer comparisons, so is faster in
+ * the common case that everything fits into L1.
+ *
+ *
+ * The merging is controlled by "count", the number of elements in the
+ * pending lists.  This is beautifully simple code, but rather subtle.
+ *
+ * Each time we increment "count", we set one bit (bit k) and clear
+ * bits k-1 .. 0.  Each time this happens (except the very first time
+ * for each bit, when count increments to 2^k), we merge two lists of
+ * size 2^k into one list of size 2^(k+1).
+ *
+ * This merge happens exactly when the count reaches an odd multiple of
+ * 2^k, which is when we have 2^k elements pending in smaller lists,
+ * so it's safe to merge away two lists of size 2^k.
+ *
+ * After this happens twice, we have created two lists of size 2^(k+1),
+ * which will be merged into a list of size 2^(k+2) before we create
+ * a third list of size 2^(k+1), so there are never more than two pending.
+ *
+ * The number of pending lists of size 2^k is determined by the
+ * state of bit k of "count" plus two extra pieces of information:
+ *
+ * - The state of bit k-1 (when k == 0, consider bit -1 always set), and
+ * - Whether the higher-order bits are zero or non-zero (i.e.
+ *   is count >= 2^(k+1)).
+ *
+ * There are six states we distinguish.  "x" represents some arbitrary
+ * bits, and "y" represents some arbitrary non-zero bits:
+ * 0:  00x: 0 pending of size 2^k;           x pending of sizes < 2^k
+ * 1:  01x: 0 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * 2: x10x: 0 pending of size 2^k; 2^k     + x pending of sizes < 2^k
+ * 3: x11x: 1 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * 4: y00x: 1 pending of size 2^k; 2^k     + x pending of sizes < 2^k
+ * 5: y01x: 2 pending of size 2^k; 2^(k-1) + x pending of sizes < 2^k
+ * (merge and loop back to state 2)
+ *
+ * We gain lists of size 2^k in the 2->3 and 4->5 transitions (because
+ * bit k-1 is set while the more significant bits are non-zero) and
+ * merge them away in the 5->2 transition.  Note in particular that just
+ * before the 5->2 transition, all lower-order bits are 11 (state 3),
+ * so there is one list of each smaller size.
+ *
+ * When we reach the end of the input, we merge all the pending
+ * lists, from smallest to largest.  If you work through cases 2 to
+ * 5 above, you can see that the number of elements we merge with a list
+ * of size 2^k varies from 2^(k-1) (cases 3 and 5 when x == 0) to
+ * 2^(k+1) - 1 (second merge of case 5 when x == 2^(k-1) - 1).
+ */
+__attribute__((nonnull(2,3)))
+void list_sort(void *priv, struct list_head *head, list_cmp_func_t cmp)
+{
+	struct list_head *list = head->next, *pending = NULL;
+	size_t count = 0;	/* Count of pending */
+
+	if (list == head->prev)	/* Zero or one elements */
+		return;
+
+	/* Convert to a null-terminated singly-linked list. */
+	head->prev->next = NULL;
+
+	/*
+	 * Data structure invariants:
+	 * - All lists are singly linked and null-terminated; prev
+	 *   pointers are not maintained.
+	 * - pending is a prev-linked "list of lists" of sorted
+	 *   sublists awaiting further merging.
+	 * - Each of the sorted sublists is power-of-two in size.
+	 * - Sublists are sorted by size and age, smallest & newest at front.
+	 * - There are zero to two sublists of each size.
+	 * - A pair of pending sublists are merged as soon as the number
+	 *   of following pending elements equals their size (i.e.
+	 *   each time count reaches an odd multiple of that size).
+	 *   That ensures each later final merge will be at worst 2:1.
+	 * - Each round consists of:
+	 *   - Merging the two sublists selected by the highest bit
+	 *     which flips when count is incremented, and
+	 *   - Adding an element from the input as a size-1 sublist.
+	 */
+	do {
+		size_t bits;
+		struct list_head **tail = &pending;
+
+		/* Find the least-significant clear bit in count */
+		for (bits = count; bits & 1; bits >>= 1)
+			tail = &(*tail)->prev;
+		/* Do the indicated merge */
+		if (likely(bits)) {
+			struct list_head *a = *tail, *b = a->prev;
+
+			a = merge(priv, cmp, b, a);
+			/* Install the merged result in place of the inputs */
+			a->prev = b->prev;
+			*tail = a;
+		}
+
+		/* Move one element from input list to pending */
+		list->prev = pending;
+		pending = list;
+		list = list->next;
+		pending->next = NULL;
+		count++;
+	} while (list);
+
+	/* End of input; merge together all the pending lists. */
+	list = pending;
+	pending = pending->prev;
+	for (;;) {
+		struct list_head *next = pending->prev;
+
+		if (!next)
+			break;
+		list = merge(priv, cmp, pending, list);
+		pending = next;
+	}
+	/* The final merge, rebuilding prev links */
+	merge_final(priv, cmp, head, pending, list);
+}
+EXPORT_SYMBOL(list_sort);

tools/perf/MANIFEST

@@ -17,6 +17,7 @@ tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/find_bit.c
 tools/lib/bitmap.c
+tools/lib/list_sort.c
 tools/lib/str_error_r.c
 tools/lib/vsprintf.c
 tools/lib/zalloc.c

tools/perf/check-headers.sh

@@ -26,6 +26,7 @@ include/vdso/bits.h
 include/linux/const.h
 include/vdso/const.h
 include/linux/hash.h
+include/linux/list-sort.h
 include/uapi/linux/hw_breakpoint.h
 arch/x86/include/asm/disabled-features.h
 arch/x86/include/asm/required-features.h
@@ -150,6 +151,7 @@ check include/uapi/linux/mman.h       '-I "^#include <\(uapi/\)*asm/mman.h>"'
 check include/linux/build_bug.h       '-I "^#\(ifndef\|endif\)\( \/\/\)* static_assert$"'
 check include/linux/ctype.h	      '-I "isdigit("'
 check lib/ctype.c		      '-I "^EXPORT_SYMBOL" -I "^#include <linux/export.h>" -B'
+check lib/list_sort.c		      '-I "^#include <linux/bug.h>"'
 
 # diff non-symmetric files
 check_2 tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl

tools/perf/util/Build

@@ -138,6 +138,7 @@ perf-y += expr.o
 perf-y += branch.o
 perf-y += mem2node.o
 perf-y += clockid.o
+perf-y += list_sort.o
 
 perf-$(CONFIG_LIBBPF) += bpf-loader.o
 perf-$(CONFIG_LIBBPF) += bpf_map.o
@@ -315,3 +316,7 @@ $(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+$(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE
+	$(call rule_mkdir)
+	$(call if_changed_dep,cc_o_c)

tools/perf/util/python-ext-sources

@@ -18,6 +18,7 @@ util/mmap.c
 util/namespaces.c
 ../lib/bitmap.c
 ../lib/find_bit.c
+../lib/list_sort.c
 ../lib/hweight.c
 ../lib/string.c
 ../lib/vsprintf.c