Kernel/linux-stable
1
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git synced 2025-01-06 13:16:22 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
4ad10a5f5f
linux-stable/include/vdso/datapage.h
Jason A. Donenfeld 4ad10a5f5f random: introduce generic vDSO getrandom() implementation 
Provide a generic C vDSO getrandom() implementation, which operates on
an opaque state returned by vgetrandom_alloc() and produces random bytes
the same way as getrandom(). This has the following API signature:

  ssize_t vgetrandom(void *buffer, size_t len, unsigned int flags,
                     void *opaque_state, size_t opaque_len);

The return value and the first three arguments are the same as ordinary
getrandom(), while the last two arguments are a pointer to the opaque
allocated state and its size. Were all five arguments passed to the
getrandom() syscall, nothing different would happen, and the functions
would have the exact same behavior.

The actual vDSO RNG algorithm implemented is the same one implemented by
drivers/char/random.c, using the same fast-erasure techniques as that.
Should the in-kernel implementation change, so too will the vDSO one.

It requires an implementation of ChaCha20 that does not use any stack,
in order to maintain forward secrecy if a multi-threaded program forks
(though this does not account for a similar issue with SA_SIGINFO
copying registers to the stack), so this is left as an
architecture-specific fill-in. Stack-less ChaCha20 is an easy algorithm
to implement on a variety of architectures, so this shouldn't be too
onerous.

Initially, the state is keyless, and so the first call makes a
getrandom() syscall to generate that key, and then uses it for
subsequent calls. By keeping track of a generation counter, it knows
when its key is invalidated and it should fetch a new one using the
syscall. Later, more than just a generation counter might be used.

Since MADV_WIPEONFORK is set on the opaque state, the key and related
state is wiped during a fork(), so secrets don't roll over into new
processes, and the same state doesn't accidentally generate the same
random stream. The generation counter, as well, is always >0, so that
the 0 counter is a useful indication of a fork() or otherwise
uninitialized state.

If the kernel RNG is not yet initialized, then the vDSO always calls the
syscall, because that behavior cannot be emulated in userspace, but
fortunately that state is short lived and only during early boot. If it
has been initialized, then there is no need to inspect the `flags`
argument, because the behavior does not change post-initialization
regardless of the `flags` value.

Since the opaque state passed to it is mutated, vDSO getrandom() is not
reentrant, when used with the same opaque state, which libc should be
mindful of.

The function works over an opaque per-thread state of a particular size,
which must be marked VM_WIPEONFORK, VM_DONTDUMP, VM_NORESERVE, and
VM_DROPPABLE for proper operation. Over time, the nuances of these
allocations may change or grow or even differ based on architectural
features.

The opaque state passed to vDSO getrandom() must be allocated using the
mmap_flags and mmap_prot parameters provided by the vgetrandom_opaque_params
struct, which also contains the size of each state. That struct can be
obtained with a call to vgetrandom(NULL, 0, 0, &params, ~0UL). Then,
libc can call mmap(2) and slice up the returned array into a state per
each thread, while ensuring that no single state straddles a page
boundary. Libc is expected to allocate a chunk of these on first use,
and then dole them out to threads as they're created, allocating more
when needed.

vDSO getrandom() provides the ability for userspace to generate random
bytes quickly and safely, and is intended to be integrated into libc's
thread management. As an illustrative example, the introduced code in
the vdso_test_getrandom self test later in this series might be used to
do the same outside of libc. In a libc the various pthread-isms are
expected to be elided into libc internals.

Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
2024-07-19 20:22:12 +02:00

166 lines
4.7 KiB
C
Raw Blame History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __VDSO_DATAPAGE_H
#define __VDSO_DATAPAGE_H
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
#include <uapi/linux/time.h>
#include <uapi/linux/types.h>
#include <uapi/asm-generic/errno-base.h>
#include <vdso/bits.h>
#include <vdso/clocksource.h>
#include <vdso/ktime.h>
#include <vdso/limits.h>
#include <vdso/math64.h>
#include <vdso/processor.h>
#include <vdso/time.h>
#include <vdso/time32.h>
#include <vdso/time64.h>
#ifdef CONFIG_ARCH_HAS_VDSO_DATA
#include <asm/vdso/data.h>
#else
struct arch_vdso_data {};
#endif
#define VDSO_BASES (CLOCK_TAI + 1)
#define VDSO_HRES (BIT(CLOCK_REALTIME) | \
BIT(CLOCK_MONOTONIC) | \
BIT(CLOCK_BOOTTIME) | \
BIT(CLOCK_TAI))
#define VDSO_COARSE (BIT(CLOCK_REALTIME_COARSE) | \
BIT(CLOCK_MONOTONIC_COARSE))
#define VDSO_RAW (BIT(CLOCK_MONOTONIC_RAW))
#define CS_HRES_COARSE 0
#define CS_RAW 1
#define CS_BASES (CS_RAW + 1)
/**
* struct vdso_timestamp - basetime per clock_id
* @sec: seconds
* @nsec: nanoseconds
*
* There is one vdso_timestamp object in vvar for each vDSO-accelerated
* clock_id. For high-resolution clocks, this encodes the time
* corresponding to vdso_data.cycle_last. For coarse clocks this encodes
* the actual time.
*
* To be noticed that for highres clocks nsec is left-shifted by
* vdso_data.cs[x].shift.
*/
struct vdso_timestamp {
u64 sec;
u64 nsec;
};
/**
* struct vdso_data - vdso datapage representation
* @seq: timebase sequence counter
* @clock_mode: clock mode
* @cycle_last: timebase at clocksource init
* @max_cycles: maximum cycles which won't overflow 64bit multiplication
* @mask: clocksource mask
* @mult: clocksource multiplier
* @shift: clocksource shift
* @basetime[clock_id]: basetime per clock_id
* @offset[clock_id]: time namespace offset per clock_id
* @tz_minuteswest: minutes west of Greenwich
* @tz_dsttime: type of DST correction
* @hrtimer_res: hrtimer resolution
* @__unused: unused
* @arch_data: architecture specific data (optional, defaults
* to an empty struct)
*
* vdso_data will be accessed by 64 bit and compat code at the same time
* so we should be careful before modifying this structure.
*
* @basetime is used to store the base time for the system wide time getter
* VVAR page.
*
* @offset is used by the special time namespace VVAR pages which are
* installed instead of the real VVAR page. These namespace pages must set
* @seq to 1 and @clock_mode to VDSO_CLOCKMODE_TIMENS to force the code into
* the time namespace slow path. The namespace aware functions retrieve the
* real system wide VVAR page, read host time and add the per clock offset.
* For clocks which are not affected by time namespace adjustment the
* offset must be zero.
*/
struct vdso_data {
u32 seq;
s32 clock_mode;
u64 cycle_last;
#ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT
u64 max_cycles;
#endif
u64 mask;
u32 mult;
u32 shift;
union {
struct vdso_timestamp basetime[VDSO_BASES];
struct timens_offset offset[VDSO_BASES];
};
s32 tz_minuteswest;
s32 tz_dsttime;
u32 hrtimer_res;
u32 __unused;
struct arch_vdso_data arch_data;
};
/**
* struct vdso_rng_data - vdso RNG state information
* @generation: counter representing the number of RNG reseeds
* @is_ready: boolean signaling whether the RNG is initialized
*/
struct vdso_rng_data {
u64 generation;
u8 is_ready;
};
/*
* We use the hidden visibility to prevent the compiler from generating a GOT
* relocation. Not only is going through a GOT useless (the entry couldn't and
* must not be overridden by another library), it does not even work: the linker
* cannot generate an absolute address to the data page.
*
* With the hidden visibility, the compiler simply generates a PC-relative
* relocation, and this is what we need.
*/
extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
extern struct vdso_rng_data _vdso_rng_data __attribute__((visibility("hidden")));
/**
* union vdso_data_store - Generic vDSO data page
*/
union vdso_data_store {
struct vdso_data data[CS_BASES];
u8 page[1U << CONFIG_PAGE_SHIFT];
};
/*
* The generic vDSO implementation requires that gettimeofday.h
* provides:
* - __arch_get_vdso_data(): to get the vdso datapage.
* - __arch_get_hw_counter(): to get the hw counter based on the
* clock_mode.
* - gettimeofday_fallback(): fallback for gettimeofday.
* - clock_gettime_fallback(): fallback for clock_gettime.
* - clock_getres_fallback(): fallback for clock_getres.
*/
#ifdef ENABLE_COMPAT_VDSO
#include <asm/vdso/compat_gettimeofday.h>
#else
#include <asm/vdso/gettimeofday.h>
#endif /* ENABLE_COMPAT_VDSO */
#endif /* !__ASSEMBLY__ */
#endif /* __VDSO_DATAPAGE_H */
Reference in New Issue View Git Blame Copy Permalink