treewide: refresh kmalloc_obj() conversionsgrafted

This is another run of the Coccinelle script for converting kmalloc()
family of allocations to kmalloc_obj() via the existing rules in
scripts/coccinelle/api/kmalloc_objs.cocci

This catches both the set of kmalloc() uses added since the first
kmalloc_obj() conversions in v7.0 and adds a large group missed in the
first pass due to Coccinelle not interacting well with the cleanup.h
scoped_...() family of macros[1]. I worked around this with spatch's
"--macro-file" argument to a file with all the scoped_...() macros mapped
to Coccinelle's YACFE_ITERATOR[2] as that was the closest viable control
flow indicator I could find.

Build tested allmodconfig on x86, arm64, arm, loongarch, mips, powerpc,
riscv, and s390 with no new warnings.

Link: https://lore.kernel.org/lkml/202609021314.8A9C0B8@keescook/ [1]
Link: https://github.com/coccinelle/coccinelle/blob/master/standard.h [2]
Signed-off-by: Kees Cook <kees+treewide@kernel.org>

1 files changed, 208 insertions, 0 deletions

diff --git a/arch/arm/mm/cache-xsc3l2.c b/arch/arm/mm/cache-xsc3l2.c
new file mode 100644
index 000000000..d20d7af02
--- /dev/null
+++ b/arch/arm/mm/cache-xsc3l2.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * arch/arm/mm/cache-xsc3l2.c - XScale3 L2 cache controller support
+ *
+ * Copyright (C) 2007 ARM Limited
+ */
+#include <linux/init.h>
+#include <linux/highmem.h>
+#include <asm/cp15.h>
+#include <asm/cputype.h>
+#include <asm/cacheflush.h>
+
+#define CR_L2	(1 << 26)
+
+#define CACHE_LINE_SIZE		32
+#define CACHE_LINE_SHIFT	5
+#define CACHE_WAY_PER_SET	8
+
+#define CACHE_WAY_SIZE(l2ctype)	(8192 << (((l2ctype) >> 8) & 0xf))
+#define CACHE_SET_SIZE(l2ctype)	(CACHE_WAY_SIZE(l2ctype) >> CACHE_LINE_SHIFT)
+
+static inline int xsc3_l2_present(void)
+{
+	unsigned long l2ctype;
+
+	__asm__("mrc p15, 1, %0, c0, c0, 1" : "=r" (l2ctype));
+
+	return !!(l2ctype & 0xf8);
+}
+
+static inline void xsc3_l2_clean_mva(unsigned long addr)
+{
+	__asm__("mcr p15, 1, %0, c7, c11, 1" : : "r" (addr));
+}
+
+static inline void xsc3_l2_inv_mva(unsigned long addr)
+{
+	__asm__("mcr p15, 1, %0, c7, c7, 1" : : "r" (addr));
+}
+
+static inline void xsc3_l2_inv_all(void)
+{
+	unsigned long l2ctype, set_way;
+	int set, way;
+
+	__asm__("mrc p15, 1, %0, c0, c0, 1" : "=r" (l2ctype));
+
+	for (set = 0; set < CACHE_SET_SIZE(l2ctype); set++) {
+		for (way = 0; way < CACHE_WAY_PER_SET; way++) {
+			set_way = (way << 29) | (set << 5);
+			__asm__("mcr p15, 1, %0, c7, c11, 2" : : "r"(set_way));
+		}
+	}
+
+	dsb();
+}
+
+static inline void l2_unmap_va(unsigned long va)
+{
+#ifdef CONFIG_HIGHMEM
+	if (va != -1)
+		kunmap_atomic((void *)va);
+#endif
+}
+
+static inline unsigned long l2_map_va(unsigned long pa, unsigned long prev_va)
+{
+#ifdef CONFIG_HIGHMEM
+	unsigned long va = prev_va & PAGE_MASK;
+	unsigned long pa_offset = pa << (32 - PAGE_SHIFT);
+	if (unlikely(pa_offset < (prev_va << (32 - PAGE_SHIFT)))) {
+		/*
+		 * Switching to a new page.  Because cache ops are
+		 * using virtual addresses only, we must put a mapping
+		 * in place for it.
+		 */
+		l2_unmap_va(prev_va);
+		va = (unsigned long)kmap_atomic_pfn(pa >> PAGE_SHIFT);
+	}
+	return va + (pa_offset >> (32 - PAGE_SHIFT));
+#else
+	return __phys_to_virt(pa);
+#endif
+}
+
+static void xsc3_l2_inv_range(unsigned long start, unsigned long end)
+{
+	unsigned long vaddr;
+
+	if (start == 0 && end == -1ul) {
+		xsc3_l2_inv_all();
+		return;
+	}
+
+	vaddr = -1;  /* to force the first mapping */
+
+	/*
+	 * Clean and invalidate partial first cache line.
+	 */
+	if (start & (CACHE_LINE_SIZE - 1)) {
+		vaddr = l2_map_va(start & ~(CACHE_LINE_SIZE - 1), vaddr);
+		xsc3_l2_clean_mva(vaddr);
+		xsc3_l2_inv_mva(vaddr);
+		start = (start | (CACHE_LINE_SIZE - 1)) + 1;
+	}
+
+	/*
+	 * Invalidate all full cache lines between 'start' and 'end'.
+	 */
+	while (start < (end & ~(CACHE_LINE_SIZE - 1))) {
+		vaddr = l2_map_va(start, vaddr);
+		xsc3_l2_inv_mva(vaddr);
+		start += CACHE_LINE_SIZE;
+	}
+
+	/*
+	 * Clean and invalidate partial last cache line.
+	 */
+	if (start < end) {
+		vaddr = l2_map_va(start, vaddr);
+		xsc3_l2_clean_mva(vaddr);
+		xsc3_l2_inv_mva(vaddr);
+	}
+
+	l2_unmap_va(vaddr);
+
+	dsb();
+}
+
+static void xsc3_l2_clean_range(unsigned long start, unsigned long end)
+{
+	unsigned long vaddr;
+
+	vaddr = -1;  /* to force the first mapping */
+
+	start &= ~(CACHE_LINE_SIZE - 1);
+	while (start < end) {
+		vaddr = l2_map_va(start, vaddr);
+		xsc3_l2_clean_mva(vaddr);
+		start += CACHE_LINE_SIZE;
+	}
+
+	l2_unmap_va(vaddr);
+
+	dsb();
+}
+
+/*
+ * optimize L2 flush all operation by set/way format
+ */
+static inline void xsc3_l2_flush_all(void)
+{
+	unsigned long l2ctype, set_way;
+	int set, way;
+
+	__asm__("mrc p15, 1, %0, c0, c0, 1" : "=r" (l2ctype));
+
+	for (set = 0; set < CACHE_SET_SIZE(l2ctype); set++) {
+		for (way = 0; way < CACHE_WAY_PER_SET; way++) {
+			set_way = (way << 29) | (set << 5);
+			__asm__("mcr p15, 1, %0, c7, c15, 2" : : "r"(set_way));
+		}
+	}
+
+	dsb();
+}
+
+static void xsc3_l2_flush_range(unsigned long start, unsigned long end)
+{
+	unsigned long vaddr;
+
+	if (start == 0 && end == -1ul) {
+		xsc3_l2_flush_all();
+		return;
+	}
+
+	vaddr = -1;  /* to force the first mapping */
+
+	start &= ~(CACHE_LINE_SIZE - 1);
+	while (start < end) {
+		vaddr = l2_map_va(start, vaddr);
+		xsc3_l2_clean_mva(vaddr);
+		xsc3_l2_inv_mva(vaddr);
+		start += CACHE_LINE_SIZE;
+	}
+
+	l2_unmap_va(vaddr);
+
+	dsb();
+}
+
+static int __init xsc3_l2_init(void)
+{
+	if (!cpu_is_xsc3() || !xsc3_l2_present())
+		return 0;
+
+	if (get_cr() & CR_L2) {
+		pr_info("XScale3 L2 cache enabled.\n");
+		xsc3_l2_inv_all();
+
+		outer_cache.inv_range = xsc3_l2_inv_range;
+		outer_cache.clean_range = xsc3_l2_clean_range;
+		outer_cache.flush_range = xsc3_l2_flush_range;
+	}
+
+	return 0;
+}
+core_initcall(xsc3_l2_init);