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, 214 insertions, 0 deletions

diff --git a/arch/mips/cavium-octeon/csrc-octeon.c b/arch/mips/cavium-octeon/csrc-octeon.c
new file mode 100644
index 000000000..af62a210a
--- /dev/null
+++ b/arch/mips/cavium-octeon/csrc-octeon.c
@@ -0,0 +1,214 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2007 by Ralf Baechle
+ * Copyright (C) 2009, 2012 Cavium, Inc.
+ */
+#include <linux/clocksource.h>
+#include <linux/sched/clock.h>
+#include <linux/export.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+
+#include <asm/cpu-info.h>
+#include <asm/cpu-type.h>
+#include <asm/time.h>
+
+#include <asm/octeon/octeon.h>
+#include <asm/octeon/cvmx-ipd-defs.h>
+#include <asm/octeon/cvmx-mio-defs.h>
+#include <asm/octeon/cvmx-rst-defs.h>
+#include <asm/octeon/cvmx-fpa-defs.h>
+
+static u64 f;
+static u64 rdiv;
+static u64 sdiv;
+static u64 octeon_udelay_factor;
+static u64 octeon_ndelay_factor;
+
+void __init octeon_setup_delays(void)
+{
+	octeon_udelay_factor = octeon_get_clock_rate() / 1000000;
+	/*
+	 * For __ndelay we divide by 2^16, so the factor is multiplied
+	 * by the same amount.
+	 */
+	octeon_ndelay_factor = (octeon_udelay_factor * 0x10000ull) / 1000ull;
+
+	preset_lpj = octeon_get_clock_rate() / HZ;
+
+	if (current_cpu_type() == CPU_CAVIUM_OCTEON2) {
+		union cvmx_mio_rst_boot rst_boot;
+
+		rst_boot.u64 = cvmx_read_csr(CVMX_MIO_RST_BOOT);
+		rdiv = rst_boot.s.c_mul;	/* CPU clock */
+		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
+		f = (0x8000000000000000ull / sdiv) * 2;
+	} else if (current_cpu_type() == CPU_CAVIUM_OCTEON3) {
+		union cvmx_rst_boot rst_boot;
+
+		rst_boot.u64 = cvmx_read_csr(CVMX_RST_BOOT);
+		rdiv = rst_boot.s.c_mul;	/* CPU clock */
+		sdiv = rst_boot.s.pnr_mul;	/* I/O clock */
+		f = (0x8000000000000000ull / sdiv) * 2;
+	}
+
+}
+
+/*
+ * Set the current core's cvmcount counter to the value of the
+ * IPD_CLK_COUNT.  We do this on all cores as they are brought
+ * on-line.  This allows for a read from a local cpu register to
+ * access a synchronized counter.
+ *
+ * On CPU_CAVIUM_OCTEON2 the IPD_CLK_COUNT is scaled by rdiv/sdiv.
+ */
+void octeon_init_cvmcount(void)
+{
+	u64 clk_reg;
+	unsigned long flags;
+	unsigned loops = 2;
+
+	clk_reg = octeon_has_feature(OCTEON_FEATURE_FPA3) ?
+		CVMX_FPA_CLK_COUNT : CVMX_IPD_CLK_COUNT;
+
+	/* Clobber loops so GCC will not unroll the following while loop. */
+	asm("" : "+r" (loops));
+
+	local_irq_save(flags);
+	/*
+	 * Loop several times so we are executing from the cache,
+	 * which should give more deterministic timing.
+	 */
+	while (loops--) {
+		u64 clk_count = cvmx_read_csr(clk_reg);
+		if (rdiv != 0) {
+			clk_count *= rdiv;
+			if (f != 0) {
+				asm("dmultu\t%[cnt],%[f]\n\t"
+				    "mfhi\t%[cnt]"
+				    : [cnt] "+r" (clk_count)
+				    : [f] "r" (f)
+				    : "hi", "lo");
+			}
+		}
+		write_c0_cvmcount(clk_count);
+	}
+	local_irq_restore(flags);
+}
+
+static u64 octeon_cvmcount_read(struct clocksource *cs)
+{
+	return read_c0_cvmcount();
+}
+
+static struct clocksource clocksource_mips = {
+	.name		= "OCTEON_CVMCOUNT",
+	.read		= octeon_cvmcount_read,
+	.mask		= CLOCKSOURCE_MASK(64),
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+unsigned long long notrace sched_clock(void)
+{
+	/* 64-bit arithmetic can overflow, so use 128-bit.  */
+	u64 t1, t2, t3;
+	unsigned long long rv;
+	u64 mult = clocksource_mips.mult;
+	u64 shift = clocksource_mips.shift;
+	u64 cnt = read_c0_cvmcount();
+
+	asm (
+		"dmultu\t%[cnt],%[mult]\n\t"
+		"nor\t%[t1],$0,%[shift]\n\t"
+		"mfhi\t%[t2]\n\t"
+		"mflo\t%[t3]\n\t"
+		"dsll\t%[t2],%[t2],1\n\t"
+		"dsrlv\t%[rv],%[t3],%[shift]\n\t"
+		"dsllv\t%[t1],%[t2],%[t1]\n\t"
+		"or\t%[rv],%[t1],%[rv]\n\t"
+		: [rv] "=&r" (rv), [t1] "=&r" (t1), [t2] "=&r" (t2), [t3] "=&r" (t3)
+		: [cnt] "r" (cnt), [mult] "r" (mult), [shift] "r" (shift)
+		: "hi", "lo");
+	return rv;
+}
+
+void __init plat_time_init(void)
+{
+	clocksource_mips.rating = 300;
+	clocksource_register_hz(&clocksource_mips, octeon_get_clock_rate());
+}
+
+void __udelay(unsigned long us)
+{
+	u64 cur, end, inc;
+
+	cur = read_c0_cvmcount();
+
+	inc = us * octeon_udelay_factor;
+	end = cur + inc;
+
+	while (end > cur)
+		cur = read_c0_cvmcount();
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	u64 cur, end, inc;
+
+	cur = read_c0_cvmcount();
+
+	inc = ((ns * octeon_ndelay_factor) >> 16);
+	end = cur + inc;
+
+	while (end > cur)
+		cur = read_c0_cvmcount();
+}
+EXPORT_SYMBOL(__ndelay);
+
+void __delay(unsigned long loops)
+{
+	u64 cur, end;
+
+	cur = read_c0_cvmcount();
+	end = cur + loops;
+
+	while (end > cur)
+		cur = read_c0_cvmcount();
+}
+EXPORT_SYMBOL(__delay);
+
+
+/**
+ * octeon_io_clk_delay - wait for a given number of io clock cycles to pass.
+ *
+ * We scale the wait by the clock ratio, and then wait for the
+ * corresponding number of core clocks.
+ *
+ * @count: The number of clocks to wait.
+ */
+void octeon_io_clk_delay(unsigned long count)
+{
+	u64 cur, end;
+
+	cur = read_c0_cvmcount();
+	if (rdiv != 0) {
+		end = count * rdiv;
+		if (f != 0) {
+			asm("dmultu\t%[cnt],%[f]\n\t"
+				"mfhi\t%[cnt]"
+				: [cnt] "+r" (end)
+				: [f] "r" (f)
+				: "hi", "lo");
+		}
+		end = cur + end;
+	} else {
+		end = cur + count;
+	}
+	while (end > cur)
+		cur = read_c0_cvmcount();
+}
+EXPORT_SYMBOL(octeon_io_clk_delay);