bpf: mark a NULL kfunc argument precisegrafted

check_kfunc_arg() allows bpf_register_is_null() for nullable arguments
w/o marking the underlying scalar register precise. Hence a checkpoint
created on such a path would prune against arbitrary scalar value.

Fixes: 3bda08b63670 ("bpf: Allow NULL buffers in bpf_dynptr_slice(_rw)")
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20260904-register-is-null-precise-fixes-v1-5-0f5a360ff15d@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 68 insertions, 0 deletions

diff --git a/arch/mips/lib/delay.c b/arch/mips/lib/delay.c
new file mode 100644
index 000000000..ccdb1fc1e
--- /dev/null
+++ b/arch/mips/lib/delay.c
@@ -0,0 +1,68 @@
+/*
+ * 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) 1994 by Waldorf Electronics
+ * Copyright (C) 1995 - 2000, 01, 03 by Ralf Baechle
+ * Copyright (C) 1999, 2000 Silicon Graphics, Inc.
+ * Copyright (C) 2007, 2014 Maciej W. Rozycki
+ */
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/param.h>
+#include <linux/smp.h>
+#include <linux/stringify.h>
+
+#include <asm/asm.h>
+#include <asm/compiler.h>
+
+#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
+#define GCC_DADDI_IMM_ASM() "I"
+#else
+#define GCC_DADDI_IMM_ASM() "r"
+#endif
+
+#ifndef CONFIG_HAVE_PLAT_DELAY
+
+void __delay(unsigned long loops)
+{
+	__asm__ __volatile__ (
+	"	.set	noreorder				\n"
+	"	.align	3					\n"
+	"1:	bnez	%0, 1b					\n"
+	"	 " __stringify(LONG_SUBU) "	%0, %1		\n"
+	"	.set	reorder					\n"
+	: "=r" (loops)
+	: GCC_DADDI_IMM_ASM() (1), "0" (loops));
+}
+EXPORT_SYMBOL(__delay);
+
+/*
+ * Division by multiplication: you don't have to worry about
+ * loss of precision.
+ *
+ * Use only for very small delays ( < 1 msec).	Should probably use a
+ * lookup table, really, as the multiplications take much too long with
+ * short delays.  This is a "reasonable" implementation, though (and the
+ * first constant multiplications gets optimized away if the delay is
+ * a constant)
+ */
+
+void __udelay(unsigned long us)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((us * 0x000010c7ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__udelay);
+
+void __ndelay(unsigned long ns)
+{
+	unsigned int lpj = raw_current_cpu_data.udelay_val;
+
+	__delay((ns * 0x00000005ull * HZ * lpj) >> 32);
+}
+EXPORT_SYMBOL(__ndelay);
+
+#endif