[PATCH v8 1/3] random: add vgetrandom_alloc() syscall

@@ -17287,6 +17287,7 @@ T:	git https://git.kernel.org/pub/scm/linux/kernel/git/crng/random.git
 S:	Maintained
 F:	drivers/char/random.c
 F:	drivers/virt/vmgenid.c
+F:	include/vdso/getrandom.h
 
 RAPIDIO SUBSYSTEM
 M:	Matt Porter <mporter@kernel.crashing.org>

@@ -8,6 +8,7 @@
  * into roughly six sections, each with a section header:
  *
  *   - Initialization and readiness waiting.
+ *   - vDSO support helpers.
  *   - Fast key erasure RNG, the "crng".
  *   - Entropy accumulation and extraction routines.
  *   - Entropy collection routines.

@@ -39,6 +40,7 @@
 #include <linux/blkdev.h>
 #include <linux/interrupt.h>
 #include <linux/mm.h>
+#include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/spinlock.h>
 #include <linux/kthread.h>

@@ -55,6 +57,9 @@
 #include <linux/siphash.h>
 #include <crypto/chacha.h>
 #include <crypto/blake2s.h>
+#ifdef CONFIG_VGETRANDOM_ALLOC_SYSCALL
+#include <vdso/getrandom.h>
+#endif
 #include <asm/processor.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>

@@ -167,6 +172,76 @@ int __cold execute_with_initialized_rng(struct notifier_block *nb)
 				__func__, (void *)_RET_IP_, crng_init)
 
 
+
+/********************************************************************
+ *
+ * vDSO support helpers.
+ *
+ * The actual vDSO function is defined over in lib/vdso/getrandom.c,
+ * but this section contains the kernel-mode helpers to support that.
+ *
+ ********************************************************************/
+
+#ifdef CONFIG_VGETRANDOM_ALLOC_SYSCALL
+/**
+ * vgetrandom_alloc - allocate opaque states for use with vDSO getrandom().
+ *
+ * @num: on input, a pointer to a suggested hint of how many states to
+ * allocate, and on output the number of states actually allocated.
+ *
+ * @size_per_each: the size of each state allocated, so that the caller can
+ * split up the returned allocation into individual states.
+ *
+ * @flags: currently always zero.
+ *
+ * The getrandom() vDSO function in userspace requires an opaque state, which
+ * this function allocates by mapping a certain number of special pages into
+ * the calling process. It takes a hint as to the number of opaque states
+ * desired, and provides the caller with the number of opaque states actually
+ * allocated, the size of each one in bytes, and the address of the first
+ * state.
+
+ * Returns a pointer to the first state in the allocation.
+ *
+ */
+SYSCALL_DEFINE3(vgetrandom_alloc, unsigned int __user *, num,
+		unsigned int __user *, size_per_each, unsigned int, flags)
+{
+	const size_t state_size = sizeof(struct vgetrandom_state);
+	size_t alloc_size, num_states;
+	unsigned long pages_addr;
+	unsigned int num_hint;
+	int ret;
+
+	if (flags)
+		return -EINVAL;
+
+	if (get_user(num_hint, num))
+		return -EFAULT;
+
+	num_states = clamp_t(size_t, num_hint, 1, (SIZE_MAX & PAGE_MASK) / state_size);
+	alloc_size = PAGE_ALIGN(num_states * state_size);
+
+	if (put_user(alloc_size / state_size, num) || put_user(state_size, size_per_each))
+		return -EFAULT;
+
+	pages_addr = vm_mmap(NULL, 0, alloc_size, PROT_READ | PROT_WRITE,
+			     MAP_PRIVATE | MAP_ANONYMOUS | MAP_LOCKED, 0);
+	if (IS_ERR_VALUE(pages_addr))
+		return pages_addr;
+
+	ret = do_madvise(current->mm, pages_addr, alloc_size, MADV_WIPEONFORK);
+	if (ret < 0)
+		goto err_unmap;
+
+	return pages_addr;
+
+err_unmap:
+	vm_munmap(pages_addr, alloc_size);
+	return ret;
+}
+#endif
+
 /*********************************************************************
  *
  * Fast key erasure RNG, the "crng".

@@ -886,8 +886,13 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 
+#ifdef __ARCH_WANT_VGETRANDOM_ALLOC
+#define __NR_vgetrandom_alloc 451
+__SYSCALL(__NR_vgetrandom_alloc, sys_vgetrandom_alloc)
+#endif
+
 #undef __NR_syscalls
-#define __NR_syscalls 451
+#define __NR_syscalls 452
 
 /*
  * 32 bit systems traditionally used different

@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ */
+
+#ifndef _VDSO_GETRANDOM_H
+#define _VDSO_GETRANDOM_H
+
+#include <crypto/chacha.h>
+
+struct vgetrandom_state {
+	union {
+		struct {
+			u8 batch[CHACHA_BLOCK_SIZE * 3 / 2];
+			u32 key[CHACHA_KEY_SIZE / sizeof(u32)];
+		};
+		u8 batch_key[CHACHA_BLOCK_SIZE * 2];
+	};
+	unsigned long generation;
+	u8 pos;
+	bool in_use;
+};
+
+#endif /* _VDSO_GETRANDOM_H */

@@ -360,6 +360,9 @@ COND_SYSCALL(pkey_free);
 /* memfd_secret */
 COND_SYSCALL(memfd_secret);
 
+/* random */
+COND_SYSCALL(vgetrandom_alloc);
+
 /*
  * Architecture specific weak syscall entries.
  */

@@ -31,3 +31,10 @@ config GENERIC_VDSO_TIME_NS
 	  VDSO
 
 endif
+
+config VGETRANDOM_ALLOC_SYSCALL
+	bool
+	select ADVISE_SYSCALLS
+	help
+	  Selected by the getrandom() vDSO function, which requires this
+	  for state allocation.

@@ -44,6 +44,10 @@ cat << EOF
 #define __IGNORE_memfd_secret
 #endif
 
+#ifndef __ARCH_WANT_VGETRANDOM_ALLOC
+#define __IGNORE_vgetrandom_alloc
+#endif
+
 /* Missing flags argument */
 #define __IGNORE_renameat	/* renameat2 */
 

@@ -886,8 +886,13 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv)
 #define __NR_set_mempolicy_home_node 450
 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node)
 
+#ifdef __ARCH_WANT_VGETRANDOM_ALLOC
+#define __NR_vgetrandom_alloc 451
+__SYSCALL(__NR_vgetrandom_alloc, sys_vgetrandom_alloc)
+#endif
+
 #undef __NR_syscalls
-#define __NR_syscalls 451
+#define __NR_syscalls 452
 
 /*
  * 32 bit systems traditionally used different