10 files changed, 283 insertions, 28 deletions

diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c
index a105e6369efc..6b62a6bdd50e 100644
--- a/lib/cpumask_kunit.c
+++ b/lib/cpumask_kunit.c
@@ -152,4 +152,5 @@ static struct kunit_suite test_cpumask_suite = {
 };
 kunit_test_suite(test_cpumask_suite);
 
+MODULE_DESCRIPTION("KUnit tests for cpumask");
 MODULE_LICENSE("GPL");
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 3518e7394eca..ca736166f100 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd)
 	   RUNB) */
 	symCount = symTotal+2;
 	for (j = 0; j < groupCount; j++) {
-		unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1];
+		unsigned char length[MAX_SYMBOLS];
+		unsigned short temp[MAX_HUFCODE_BITS+1];
 		int	minLen,	maxLen, pp;
 		/* Read Huffman code lengths for each symbol.  They're
 		   stored in a way similar to mtf; record a starting
diff --git a/lib/find_bit_benchmark.c b/lib/find_bit_benchmark.c
index d3fb09e6eff1..402e160e7186 100644
--- a/lib/find_bit_benchmark.c
+++ b/lib/find_bit_benchmark.c
@@ -194,4 +194,5 @@ static int __init find_bit_test(void)
 }
 module_init(find_bit_test);
 
+MODULE_DESCRIPTION("Test for find_*_bit functions");
 MODULE_LICENSE("GPL");
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 03b427e2707e..b7f2fa08d9c8 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env)
 		len = strlen(env->envp[i]) + 1;
 
 		if (i != env->envp_idx - 1) {
+			/* @env->envp[] contains pointers to @env->buf[]
+			 * with @env->buflen chars, and we are removing
+			 * variable MODALIAS here pointed by @env->envp[i]
+			 * with length @len as shown below:
+			 *
+			 * 0               @env->buf[]      @env->buflen
+			 * ---------------------------------------------
+			 * ^             ^              ^              ^
+			 * |             |->   @len   <-| target block |
+			 * @env->envp[0] @env->envp[i]  @env->envp[i + 1]
+			 *
+			 * so the "target block" indicated above is moved
+			 * backward by @len, and its right size is
+			 * @env->buflen - (@env->envp[i + 1] - @env->envp[0]).
+			 */
 			memmove(env->envp[i], env->envp[i + 1],
-				env->buflen - len);
+				env->buflen - (env->envp[i + 1] - env->envp[0]));
 
 			for (j = i; j < env->envp_idx - 1; j++)
 				env->envp[j] = env->envp[j + 1] - len;
diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c
index 6dfb8d46a4ff..65a75d58ed9e 100644
--- a/lib/test_bitmap.c
+++ b/lib/test_bitmap.c
@@ -1486,4 +1486,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_bitmap);
 MODULE_AUTHOR("david decotigny <david.decotigny@googlers.com>");
+MODULE_DESCRIPTION("Test cases for bitmap API");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_printf.c b/lib/test_printf.c
index 69b6a5e177f2..965cb6f28527 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -824,4 +824,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_printf);
 MODULE_AUTHOR("Rasmus Villemoes <linux@rasmusvillemoes.dk>");
+MODULE_DESCRIPTION("Test cases for printf facility");
 MODULE_LICENSE("GPL");
diff --git a/lib/test_scanf.c b/lib/test_scanf.c
index a2707af2951a..7257b1768545 100644
--- a/lib/test_scanf.c
+++ b/lib/test_scanf.c
@@ -810,4 +810,5 @@ static void __init selftest(void)
 
 KSTM_MODULE_LOADERS(test_scanf);
 MODULE_AUTHOR("Richard Fitzgerald <rf@opensource.cirrus.com>");
+MODULE_DESCRIPTION("Test cases for sscanf facility");
 MODULE_LICENSE("GPL v2");
diff --git a/lib/usercopy.c b/lib/usercopy.c
index 499a7a7d54db..7b17b83c8042 100644
--- a/lib/usercopy.c
+++ b/lib/usercopy.c
@@ -12,40 +12,18 @@
 
 /* out-of-line parts */
 
-#ifndef INLINE_COPY_FROM_USER
+#if !defined(INLINE_COPY_FROM_USER) || defined(CONFIG_RUST)
 unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
 {
-	unsigned long res = n;
-	might_fault();
-	if (!should_fail_usercopy() && likely(access_ok(from, n))) {
-		/*
-		 * Ensure that bad access_ok() speculation will not
-		 * lead to nasty side effects *after* the copy is
-		 * finished:
-		 */
-		barrier_nospec();
-		instrument_copy_from_user_before(to, from, n);
-		res = raw_copy_from_user(to, from, n);
-		instrument_copy_from_user_after(to, from, n, res);
-	}
-	if (unlikely(res))
-		memset(to + (n - res), 0, res);
-	return res;
+	return _inline_copy_from_user(to, from, n);
 }
 EXPORT_SYMBOL(_copy_from_user);
 #endif
 
-#ifndef INLINE_COPY_TO_USER
+#if !defined(INLINE_COPY_TO_USER) || defined(CONFIG_RUST)
 unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
 {
-	might_fault();
-	if (should_fail_usercopy())
-		return n;
-	if (likely(access_ok(to, n))) {
-		instrument_copy_to_user(to, from, n);
-		n = raw_copy_to_user(to, from, n);
-	}
-	return n;
+	return _inline_copy_to_user(to, from, n);
 }
 EXPORT_SYMBOL(_copy_to_user);
 #endif
diff --git a/lib/vdso/Kconfig b/lib/vdso/Kconfig
index c46c2300517c..82fe827af542 100644
--- a/lib/vdso/Kconfig
+++ b/lib/vdso/Kconfig
@@ -38,3 +38,8 @@ config GENERIC_VDSO_OVERFLOW_PROTECT
 	  in the hotpath.
 
 endif
+
+config VDSO_GETRANDOM
+	bool
+	help
+	  Selected by architectures that support vDSO getrandom().
diff --git a/lib/vdso/getrandom.c b/lib/vdso/getrandom.c
new file mode 100644
index 000000000000..b230f0b10832
--- /dev/null
+++ b/lib/vdso/getrandom.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022-2024 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#include <linux/cache.h>
+#include <linux/kernel.h>
+#include <linux/time64.h>
+#include <vdso/datapage.h>
+#include <vdso/getrandom.h>
+#include <asm/vdso/getrandom.h>
+#include <asm/vdso/vsyscall.h>
+#include <asm/unaligned.h>
+#include <uapi/linux/mman.h>
+
+#define MEMCPY_AND_ZERO_SRC(type, dst, src, len) do {				\
+	while (len >= sizeof(type)) {						\
+		__put_unaligned_t(type, __get_unaligned_t(type, src), dst);	\
+		__put_unaligned_t(type, 0, src);				\
+		dst += sizeof(type);						\
+		src += sizeof(type);						\
+		len -= sizeof(type);						\
+	}									\
+} while (0)
+
+static void memcpy_and_zero_src(void *dst, void *src, size_t len)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+		if (IS_ENABLED(CONFIG_64BIT))
+			MEMCPY_AND_ZERO_SRC(u64, dst, src, len);
+		MEMCPY_AND_ZERO_SRC(u32, dst, src, len);
+		MEMCPY_AND_ZERO_SRC(u16, dst, src, len);
+	}
+	MEMCPY_AND_ZERO_SRC(u8, dst, src, len);
+}
+
+/**
+ * __cvdso_getrandom_data - Generic vDSO implementation of getrandom() syscall.
+ * @rng_info:		Describes state of kernel RNG, memory shared with kernel.
+ * @buffer:		Destination buffer to fill with random bytes.
+ * @len:		Size of @buffer in bytes.
+ * @flags:		Zero or more GRND_* flags.
+ * @opaque_state:	Pointer to an opaque state area.
+ * @opaque_len:		Length of opaque state area.
+ *
+ * This implements a "fast key erasure" RNG using ChaCha20, in the same way that the kernel's
+ * getrandom() syscall does. It periodically reseeds its key from the kernel's RNG, at the same
+ * schedule that the kernel's RNG is reseeded. If the kernel's RNG is not ready, then this always
+ * calls into the syscall.
+ *
+ * If @buffer, @len, and @flags are 0, and @opaque_len is ~0UL, then @opaque_state is populated
+ * with a struct vgetrandom_opaque_params and the function returns 0; if it does not return 0,
+ * this function should not be used.
+ *
+ * @opaque_state *must* be allocated by calling mmap(2) using the mmap_prot and mmap_flags fields
+ * from the struct vgetrandom_opaque_params, and states must not straddle pages. Unless external
+ * locking is used, one state must be allocated per thread, as it is not safe to call this function
+ * concurrently with the same @opaque_state. However, it is safe to call this using the same
+ * @opaque_state that is shared between main code and signal handling code, within the same thread.
+ *
+ * Returns:	The number of random bytes written to @buffer, or a negative value indicating an error.
+ */
+static __always_inline ssize_t
+__cvdso_getrandom_data(const struct vdso_rng_data *rng_info, void *buffer, size_t len,
+		       unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	ssize_t ret = min_t(size_t, INT_MAX & PAGE_MASK /* = MAX_RW_COUNT */, len);
+	struct vgetrandom_state *state = opaque_state;
+	size_t batch_len, nblocks, orig_len = len;
+	bool in_use, have_retried = false;
+	unsigned long current_generation;
+	void *orig_buffer = buffer;
+	u32 counter[2] = { 0 };
+
+	if (unlikely(opaque_len == ~0UL && !buffer && !len && !flags)) {
+		*(struct vgetrandom_opaque_params *)opaque_state = (struct vgetrandom_opaque_params) {
+			.size_of_opaque_state = sizeof(*state),
+			.mmap_prot = PROT_READ | PROT_WRITE,
+			.mmap_flags = MAP_DROPPABLE | MAP_ANONYMOUS
+		};
+		return 0;
+	}
+
+	/* The state must not straddle a page, since pages can be zeroed at any time. */
+	if (unlikely(((unsigned long)opaque_state & ~PAGE_MASK) + sizeof(*state) > PAGE_SIZE))
+		return -EFAULT;
+
+	/* If the caller passes the wrong size, which might happen due to CRIU, fallback. */
+	if (unlikely(opaque_len != sizeof(*state)))
+		goto fallback_syscall;
+
+	/*
+	 * If the kernel's RNG is not yet ready, then it's not possible to provide random bytes from
+	 * userspace, because A) the various @flags require this to block, or not, depending on
+	 * various factors unavailable to userspace, and B) the kernel's behavior before the RNG is
+	 * ready is to reseed from the entropy pool at every invocation.
+	 */
+	if (unlikely(!READ_ONCE(rng_info->is_ready)))
+		goto fallback_syscall;
+
+	/*
+	 * This condition is checked after @rng_info->is_ready, because before the kernel's RNG is
+	 * initialized, the @flags parameter may require this to block or return an error, even when
+	 * len is zero.
+	 */
+	if (unlikely(!len))
+		return 0;
+
+	/*
+	 * @state->in_use is basic reentrancy protection against this running in a signal handler
+	 * with the same @opaque_state, but obviously not atomic wrt multiple CPUs or more than one
+	 * level of reentrancy. If a signal interrupts this after reading @state->in_use, but before
+	 * writing @state->in_use, there is still no race, because the signal handler will run to
+	 * its completion before returning execution.
+	 */
+	in_use = READ_ONCE(state->in_use);
+	if (unlikely(in_use))
+		/* The syscall simply fills the buffer and does not touch @state, so fallback. */
+		goto fallback_syscall;
+	WRITE_ONCE(state->in_use, true);
+
+retry_generation:
+	/*
+	 * @rng_info->generation must always be read here, as it serializes @state->key with the
+	 * kernel's RNG reseeding schedule.
+	 */
+	current_generation = READ_ONCE(rng_info->generation);
+
+	/*
+	 * If @state->generation doesn't match the kernel RNG's generation, then it means the
+	 * kernel's RNG has reseeded, and so @state->key is reseeded as well.
+	 */
+	if (unlikely(state->generation != current_generation)) {
+		/*
+		 * Write the generation before filling the key, in case of fork. If there is a fork
+		 * just after this line, the parent and child will get different random bytes from
+		 * the syscall, which is good. However, were this line to occur after the getrandom
+		 * syscall, then both child and parent could have the same bytes and the same
+		 * generation counter, so the fork would not be detected. Therefore, write
+		 * @state->generation before the call to the getrandom syscall.
+		 */
+		WRITE_ONCE(state->generation, current_generation);
+
+		/*
+		 * Prevent the syscall from being reordered wrt current_generation. Pairs with the
+		 * smp_store_release(&_vdso_rng_data.generation) in random.c.
+		 */
+		smp_rmb();
+
+		/* Reseed @state->key using fresh bytes from the kernel. */
+		if (getrandom_syscall(state->key, sizeof(state->key), 0) != sizeof(state->key)) {
+			/*
+			 * If the syscall failed to refresh the key, then @state->key is now
+			 * invalid, so invalidate the generation so that it is not used again, and
+			 * fallback to using the syscall entirely.
+			 */
+			WRITE_ONCE(state->generation, 0);
+
+			/*
+			 * Set @state->in_use to false only after the last write to @state in the
+			 * line above.
+			 */
+			WRITE_ONCE(state->in_use, false);
+
+			goto fallback_syscall;
+		}
+
+		/*
+		 * Set @state->pos to beyond the end of the batch, so that the batch is refilled
+		 * using the new key.
+		 */
+		state->pos = sizeof(state->batch);
+	}
+
+	/* Set len to the total amount of bytes that this function is allowed to read, ret. */
+	len = ret;
+more_batch:
+	/*
+	 * First use bytes out of @state->batch, which may have been filled by the last call to this
+	 * function.
+	 */
+	batch_len = min_t(size_t, sizeof(state->batch) - state->pos, len);
+	if (batch_len) {
+		/* Zeroing at the same time as memcpying helps preserve forward secrecy. */
+		memcpy_and_zero_src(buffer, state->batch + state->pos, batch_len);
+		state->pos += batch_len;
+		buffer += batch_len;
+		len -= batch_len;
+	}
+
+	if (!len) {
+		/* Prevent the loop from being reordered wrt ->generation. */
+		barrier();
+
+		/*
+		 * Since @rng_info->generation will never be 0, re-read @state->generation, rather
+		 * than using the local current_generation variable, to learn whether a fork
+		 * occurred or if @state was zeroed due to memory pressure. Primarily, though, this
+		 * indicates whether the kernel's RNG has reseeded, in which case generate a new key
+		 * and start over.
+		 */
+		if (unlikely(READ_ONCE(state->generation) != READ_ONCE(rng_info->generation))) {
+			/*
+			 * Prevent this from looping forever in case of low memory or racing with a
+			 * user force-reseeding the kernel's RNG using the ioctl.
+			 */
+			if (have_retried) {
+				WRITE_ONCE(state->in_use, false);
+				goto fallback_syscall;
+			}
+
+			have_retried = true;
+			buffer = orig_buffer;
+			goto retry_generation;
+		}
+
+		/*
+		 * Set @state->in_use to false only when there will be no more reads or writes of
+		 * @state.
+		 */
+		WRITE_ONCE(state->in_use, false);
+		return ret;
+	}
+
+	/* Generate blocks of RNG output directly into @buffer while there's enough room left. */
+	nblocks = len / CHACHA_BLOCK_SIZE;
+	if (nblocks) {
+		__arch_chacha20_blocks_nostack(buffer, state->key, counter, nblocks);
+		buffer += nblocks * CHACHA_BLOCK_SIZE;
+		len -= nblocks * CHACHA_BLOCK_SIZE;
+	}
+
+	BUILD_BUG_ON(sizeof(state->batch_key) % CHACHA_BLOCK_SIZE != 0);
+
+	/* Refill the batch and overwrite the key, in order to preserve forward secrecy. */
+	__arch_chacha20_blocks_nostack(state->batch_key, state->key, counter,
+				       sizeof(state->batch_key) / CHACHA_BLOCK_SIZE);
+
+	/* Since the batch was just refilled, set the position back to 0 to indicate a full batch. */
+	state->pos = 0;
+	goto more_batch;
+
+fallback_syscall:
+	return getrandom_syscall(orig_buffer, orig_len, flags);
+}
+
+static __always_inline ssize_t
+__cvdso_getrandom(void *buffer, size_t len, unsigned int flags, void *opaque_state, size_t opaque_len)
+{
+	return __cvdso_getrandom_data(__arch_get_vdso_rng_data(), buffer, len, flags, opaque_state, opaque_len);
+}