linux/drivers/char/random.c

1350 lines
39 KiB
C
Raw Normal View History

/*
* random.c -- A strong random number generator
*
* Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
*
* Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999. All
* rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, and the entire permission notice in its entirety,
* including the disclaimer of warranties.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. The name of the author may not be used to endorse or promote
* products derived from this software without specific prior
* written permission.
*
* ALTERNATIVELY, this product may be distributed under the terms of
* the GNU General Public License, in which case the provisions of the GPL are
* required INSTEAD OF the above restrictions. (This clause is
* necessary due to a potential bad interaction between the GPL and
* the restrictions contained in a BSD-style copyright.)
*
* THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
* WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
* OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE, ALL OF
* WHICH ARE HEREBY DISCLAIMED. IN NO EVENT SHALL THE AUTHOR BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT
* OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
* LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE
* USE OF THIS SOFTWARE, EVEN IF NOT ADVISED OF THE POSSIBILITY OF SUCH
* DAMAGE.
*/
/*
* (now, with legal B.S. out of the way.....)
*
* This routine gathers environmental noise from device drivers, etc.,
* and returns good random numbers, suitable for cryptographic use.
* Besides the obvious cryptographic uses, these numbers are also good
* for seeding TCP sequence numbers, and other places where it is
* desirable to have numbers which are not only random, but hard to
* predict by an attacker.
*
* Theory of operation
* ===================
*
* Computers are very predictable devices. Hence it is extremely hard
* to produce truly random numbers on a computer --- as opposed to
* pseudo-random numbers, which can easily generated by using a
* algorithm. Unfortunately, it is very easy for attackers to guess
* the sequence of pseudo-random number generators, and for some
* applications this is not acceptable. So instead, we must try to
* gather "environmental noise" from the computer's environment, which
* must be hard for outside attackers to observe, and use that to
* generate random numbers. In a Unix environment, this is best done
* from inside the kernel.
*
* Sources of randomness from the environment include inter-keyboard
* timings, inter-interrupt timings from some interrupts, and other
* events which are both (a) non-deterministic and (b) hard for an
* outside observer to measure. Randomness from these sources are
* added to an "entropy pool", which is mixed using a CRC-like function.
* This is not cryptographically strong, but it is adequate assuming
* the randomness is not chosen maliciously, and it is fast enough that
* the overhead of doing it on every interrupt is very reasonable.
* As random bytes are mixed into the entropy pool, the routines keep
* an *estimate* of how many bits of randomness have been stored into
* the random number generator's internal state.
*
* When random bytes are desired, they are obtained by taking the SHA
* hash of the contents of the "entropy pool". The SHA hash avoids
* exposing the internal state of the entropy pool. It is believed to
* be computationally infeasible to derive any useful information
* about the input of SHA from its output. Even if it is possible to
* analyze SHA in some clever way, as long as the amount of data
* returned from the generator is less than the inherent entropy in
* the pool, the output data is totally unpredictable. For this
* reason, the routine decreases its internal estimate of how many
* bits of "true randomness" are contained in the entropy pool as it
* outputs random numbers.
*
* If this estimate goes to zero, the routine can still generate
* random numbers; however, an attacker may (at least in theory) be
* able to infer the future output of the generator from prior
* outputs. This requires successful cryptanalysis of SHA, which is
* not believed to be feasible, but there is a remote possibility.
* Nonetheless, these numbers should be useful for the vast majority
* of purposes.
*
* Exported interfaces ---- output
* ===============================
*
* There are three exported interfaces; the first is one designed to
* be used from within the kernel:
*
* void get_random_bytes(void *buf, int nbytes);
*
* This interface will return the requested number of random bytes,
* and place it in the requested buffer.
*
* The two other interfaces are two character devices /dev/random and
* /dev/urandom. /dev/random is suitable for use when very high
* quality randomness is desired (for example, for key generation or
* one-time pads), as it will only return a maximum of the number of
* bits of randomness (as estimated by the random number generator)
* contained in the entropy pool.
*
* The /dev/urandom device does not have this limit, and will return
* as many bytes as are requested. As more and more random bytes are
* requested without giving time for the entropy pool to recharge,
* this will result in random numbers that are merely cryptographically
* strong. For many applications, however, this is acceptable.
*
* Exported interfaces ---- input
* ==============================
*
* The current exported interfaces for gathering environmental noise
* from the devices are:
*
* void add_input_randomness(unsigned int type, unsigned int code,
* unsigned int value);
* void add_interrupt_randomness(int irq);
* void add_disk_randomness(struct gendisk *disk);
*
* add_input_randomness() uses the input layer interrupt timing, as well as
* the event type information from the hardware.
*
* add_interrupt_randomness() uses the inter-interrupt timing as random
* inputs to the entropy pool. Note that not all interrupts are good
* sources of randomness! For example, the timer interrupts is not a
* good choice, because the periodicity of the interrupts is too
* regular, and hence predictable to an attacker. Network Interface
* Controller interrupts are a better measure, since the timing of the
* NIC interrupts are more unpredictable.
*
* add_disk_randomness() uses what amounts to the seek time of block
* layer request events, on a per-disk_devt basis, as input to the
* entropy pool. Note that high-speed solid state drives with very low
* seek times do not make for good sources of entropy, as their seek
* times are usually fairly consistent.
*
* All of these routines try to estimate how many bits of randomness a
* particular randomness source. They do this by keeping track of the
* first and second order deltas of the event timings.
*
* Ensuring unpredictability at system startup
* ============================================
*
* When any operating system starts up, it will go through a sequence
* of actions that are fairly predictable by an adversary, especially
* if the start-up does not involve interaction with a human operator.
* This reduces the actual number of bits of unpredictability in the
* entropy pool below the value in entropy_count. In order to
* counteract this effect, it helps to carry information in the
* entropy pool across shut-downs and start-ups. To do this, put the
* following lines an appropriate script which is run during the boot
* sequence:
*
* echo "Initializing random number generator..."
* random_seed=/var/run/random-seed
* # Carry a random seed from start-up to start-up
* # Load and then save the whole entropy pool
* if [ -f $random_seed ]; then
* cat $random_seed >/dev/urandom
* else
* touch $random_seed
* fi
* chmod 600 $random_seed
* dd if=/dev/urandom of=$random_seed count=1 bs=512
*
* and the following lines in an appropriate script which is run as
* the system is shutdown:
*
* # Carry a random seed from shut-down to start-up
* # Save the whole entropy pool
* echo "Saving random seed..."
* random_seed=/var/run/random-seed
* touch $random_seed
* chmod 600 $random_seed
* dd if=/dev/urandom of=$random_seed count=1 bs=512
*
* For example, on most modern systems using the System V init
* scripts, such code fragments would be found in
* /etc/rc.d/init.d/random. On older Linux systems, the correct script
* location might be in /etc/rcb.d/rc.local or /etc/rc.d/rc.0.
*
* Effectively, these commands cause the contents of the entropy pool
* to be saved at shut-down time and reloaded into the entropy pool at
* start-up. (The 'dd' in the addition to the bootup script is to
* make sure that /etc/random-seed is different for every start-up,
* even if the system crashes without executing rc.0.) Even with
* complete knowledge of the start-up activities, predicting the state
* of the entropy pool requires knowledge of the previous history of
* the system.
*
* Configuring the /dev/random driver under Linux
* ==============================================
*
* The /dev/random driver under Linux uses minor numbers 8 and 9 of
* the /dev/mem major number (#1). So if your system does not have
* /dev/random and /dev/urandom created already, they can be created
* by using the commands:
*
* mknod /dev/random c 1 8
* mknod /dev/urandom c 1 9
*
* Acknowledgements:
* =================
*
* Ideas for constructing this random number generator were derived
* from Pretty Good Privacy's random number generator, and from private
* discussions with Phil Karn. Colin Plumb provided a faster random
* number generator, which speed up the mixing function of the entropy
* pool, taken from PGPfone. Dale Worley has also contributed many
* useful ideas and suggestions to improve this driver.
*
* Any flaws in the design are solely my responsibility, and should
* not be attributed to the Phil, Colin, or any of authors of PGP.
*
* Further background information on this topic may be obtained from
* RFC 1750, "Randomness Recommendations for Security", by Donald
* Eastlake, Steve Crocker, and Jeff Schiller.
*/
#include <linux/utsname.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/major.h>
#include <linux/string.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/random.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/interrupt.h>
2008-07-24 04:28:13 +00:00
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/cryptohash.h>
#include <linux/fips.h>
#ifdef CONFIG_GENERIC_HARDIRQS
# include <linux/irq.h>
#endif
#include <asm/processor.h>
#include <asm/uaccess.h>
#include <asm/irq.h>
#include <asm/io.h>
/*
* Configuration information
*/
#define INPUT_POOL_WORDS 128
#define OUTPUT_POOL_WORDS 32
#define SEC_XFER_SIZE 512
#define EXTRACT_SIZE 10
/*
* The minimum number of bits of entropy before we wake up a read on
* /dev/random. Should be enough to do a significant reseed.
*/
static int random_read_wakeup_thresh = 64;
/*
* If the entropy count falls under this number of bits, then we
* should wake up processes which are selecting or polling on write
* access to /dev/random.
*/
static int random_write_wakeup_thresh = 128;
/*
* When the input pool goes over trickle_thresh, start dropping most
* samples to avoid wasting CPU time and reduce lock contention.
*/
static int trickle_thresh __read_mostly = INPUT_POOL_WORDS * 28;
static DEFINE_PER_CPU(int, trickle_count);
/*
* A pool of size .poolwords is stirred with a primitive polynomial
* of degree .poolwords over GF(2). The taps for various sizes are
* defined below. They are chosen to be evenly spaced (minimum RMS
* distance from evenly spaced; the numbers in the comments are a
* scaled squared error sum) except for the last tap, which is 1 to
* get the twisting happening as fast as possible.
*/
static struct poolinfo {
int poolwords;
int tap1, tap2, tap3, tap4, tap5;
} poolinfo_table[] = {
/* x^128 + x^103 + x^76 + x^51 +x^25 + x + 1 -- 105 */
{ 128, 103, 76, 51, 25, 1 },
/* x^32 + x^26 + x^20 + x^14 + x^7 + x + 1 -- 15 */
{ 32, 26, 20, 14, 7, 1 },
#if 0
/* x^2048 + x^1638 + x^1231 + x^819 + x^411 + x + 1 -- 115 */
{ 2048, 1638, 1231, 819, 411, 1 },
/* x^1024 + x^817 + x^615 + x^412 + x^204 + x + 1 -- 290 */
{ 1024, 817, 615, 412, 204, 1 },
/* x^1024 + x^819 + x^616 + x^410 + x^207 + x^2 + 1 -- 115 */
{ 1024, 819, 616, 410, 207, 2 },
/* x^512 + x^411 + x^308 + x^208 + x^104 + x + 1 -- 225 */
{ 512, 411, 308, 208, 104, 1 },
/* x^512 + x^409 + x^307 + x^206 + x^102 + x^2 + 1 -- 95 */
{ 512, 409, 307, 206, 102, 2 },
/* x^512 + x^409 + x^309 + x^205 + x^103 + x^2 + 1 -- 95 */
{ 512, 409, 309, 205, 103, 2 },
/* x^256 + x^205 + x^155 + x^101 + x^52 + x + 1 -- 125 */
{ 256, 205, 155, 101, 52, 1 },
/* x^128 + x^103 + x^78 + x^51 + x^27 + x^2 + 1 -- 70 */
{ 128, 103, 78, 51, 27, 2 },
/* x^64 + x^52 + x^39 + x^26 + x^14 + x + 1 -- 15 */
{ 64, 52, 39, 26, 14, 1 },
#endif
};
#define POOLBITS poolwords*32
#define POOLBYTES poolwords*4
/*
* For the purposes of better mixing, we use the CRC-32 polynomial as
* well to make a twisted Generalized Feedback Shift Reigster
*
* (See M. Matsumoto & Y. Kurita, 1992. Twisted GFSR generators. ACM
* Transactions on Modeling and Computer Simulation 2(3):179-194.
* Also see M. Matsumoto & Y. Kurita, 1994. Twisted GFSR generators
* II. ACM Transactions on Mdeling and Computer Simulation 4:254-266)
*
* Thanks to Colin Plumb for suggesting this.
*
* We have not analyzed the resultant polynomial to prove it primitive;
* in fact it almost certainly isn't. Nonetheless, the irreducible factors
* of a random large-degree polynomial over GF(2) are more than large enough
* that periodicity is not a concern.
*
* The input hash is much less sensitive than the output hash. All
* that we want of it is that it be a good non-cryptographic hash;
* i.e. it not produce collisions when fed "random" data of the sort
* we expect to see. As long as the pool state differs for different
* inputs, we have preserved the input entropy and done a good job.
* The fact that an intelligent attacker can construct inputs that
* will produce controlled alterations to the pool's state is not
* important because we don't consider such inputs to contribute any
* randomness. The only property we need with respect to them is that
* the attacker can't increase his/her knowledge of the pool's state.
* Since all additions are reversible (knowing the final state and the
* input, you can reconstruct the initial state), if an attacker has
* any uncertainty about the initial state, he/she can only shuffle
* that uncertainty about, but never cause any collisions (which would
* decrease the uncertainty).
*
* The chosen system lets the state of the pool be (essentially) the input
* modulo the generator polymnomial. Now, for random primitive polynomials,
* this is a universal class of hash functions, meaning that the chance
* of a collision is limited by the attacker's knowledge of the generator
* polynomail, so if it is chosen at random, an attacker can never force
* a collision. Here, we use a fixed polynomial, but we *can* assume that
* ###--> it is unknown to the processes generating the input entropy. <-###
* Because of this important property, this is a good, collision-resistant
* hash; hash collisions will occur no more often than chance.
*/
/*
* Static global variables
*/
static DECLARE_WAIT_QUEUE_HEAD(random_read_wait);
static DECLARE_WAIT_QUEUE_HEAD(random_write_wait);
2008-04-29 08:03:08 +00:00
static struct fasync_struct *fasync;
#if 0
static int debug;
module_param(debug, bool, 0644);
#define DEBUG_ENT(fmt, arg...) do { \
if (debug) \
printk(KERN_DEBUG "random %04d %04d %04d: " \
fmt,\
input_pool.entropy_count,\
blocking_pool.entropy_count,\
nonblocking_pool.entropy_count,\
## arg); } while (0)
#else
#define DEBUG_ENT(fmt, arg...) do {} while (0)
#endif
/**********************************************************************
*
* OS independent entropy store. Here are the functions which handle
* storing entropy in an entropy pool.
*
**********************************************************************/
struct entropy_store;
struct entropy_store {
/* read-only data: */
struct poolinfo *poolinfo;
__u32 *pool;
const char *name;
struct entropy_store *pull;
int limit;
/* read-write data: */
spinlock_t lock;
unsigned add_ptr;
int entropy_count;
int input_rotate;
__u8 last_data[EXTRACT_SIZE];
};
static __u32 input_pool_data[INPUT_POOL_WORDS];
static __u32 blocking_pool_data[OUTPUT_POOL_WORDS];
static __u32 nonblocking_pool_data[OUTPUT_POOL_WORDS];
static struct entropy_store input_pool = {
.poolinfo = &poolinfo_table[0],
.name = "input",
.limit = 1,
.lock = __SPIN_LOCK_UNLOCKED(&input_pool.lock),
.pool = input_pool_data
};
static struct entropy_store blocking_pool = {
.poolinfo = &poolinfo_table[1],
.name = "blocking",
.limit = 1,
.pull = &input_pool,
.lock = __SPIN_LOCK_UNLOCKED(&blocking_pool.lock),
.pool = blocking_pool_data
};
static struct entropy_store nonblocking_pool = {
.poolinfo = &poolinfo_table[1],
.name = "nonblocking",
.pull = &input_pool,
.lock = __SPIN_LOCK_UNLOCKED(&nonblocking_pool.lock),
.pool = nonblocking_pool_data
};
/*
* This function adds bytes into the entropy "pool". It does not
* update the entropy estimate. The caller should call
* credit_entropy_bits if this is appropriate.
*
* The pool is stirred with a primitive polynomial of the appropriate
* degree, and then twisted. We twist by three bits at a time because
* it's cheap to do so and helps slightly in the expected case where
* the entropy is concentrated in the low-order bits.
*/
static void mix_pool_bytes_extract(struct entropy_store *r, const void *in,
int nbytes, __u8 out[64])
{
static __u32 const twist_table[8] = {
0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
unsigned long i, j, tap1, tap2, tap3, tap4, tap5;
int input_rotate;
int wordmask = r->poolinfo->poolwords - 1;
const char *bytes = in;
__u32 w;
unsigned long flags;
/* Taps are constant, so we can load them without holding r->lock. */
tap1 = r->poolinfo->tap1;
tap2 = r->poolinfo->tap2;
tap3 = r->poolinfo->tap3;
tap4 = r->poolinfo->tap4;
tap5 = r->poolinfo->tap5;
spin_lock_irqsave(&r->lock, flags);
input_rotate = r->input_rotate;
i = r->add_ptr;
/* mix one byte at a time to simplify size handling and churn faster */
while (nbytes--) {
w = rol32(*bytes++, input_rotate & 31);
i = (i - 1) & wordmask;
/* XOR in the various taps */
w ^= r->pool[i];
w ^= r->pool[(i + tap1) & wordmask];
w ^= r->pool[(i + tap2) & wordmask];
w ^= r->pool[(i + tap3) & wordmask];
w ^= r->pool[(i + tap4) & wordmask];
w ^= r->pool[(i + tap5) & wordmask];
/* Mix the result back in with a twist */
r->pool[i] = (w >> 3) ^ twist_table[w & 7];
/*
* Normally, we add 7 bits of rotation to the pool.
* At the beginning of the pool, add an extra 7 bits
* rotation, so that successive passes spread the
* input bits across the pool evenly.
*/
input_rotate += i ? 7 : 14;
}
r->input_rotate = input_rotate;
r->add_ptr = i;
if (out)
for (j = 0; j < 16; j++)
((__u32 *)out)[j] = r->pool[(i - j) & wordmask];
spin_unlock_irqrestore(&r->lock, flags);
}
static void mix_pool_bytes(struct entropy_store *r, const void *in, int bytes)
{
mix_pool_bytes_extract(r, in, bytes, NULL);
}
/*
* Credit (or debit) the entropy store with n bits of entropy
*/
static void credit_entropy_bits(struct entropy_store *r, int nbits)
{
unsigned long flags;
int entropy_count;
if (!nbits)
return;
spin_lock_irqsave(&r->lock, flags);
DEBUG_ENT("added %d entropy credits to %s\n", nbits, r->name);
entropy_count = r->entropy_count;
entropy_count += nbits;
if (entropy_count < 0) {
DEBUG_ENT("negative entropy/overflow\n");
entropy_count = 0;
} else if (entropy_count > r->poolinfo->POOLBITS)
entropy_count = r->poolinfo->POOLBITS;
r->entropy_count = entropy_count;
/* should we wake readers? */
if (r == &input_pool && entropy_count >= random_read_wakeup_thresh) {
wake_up_interruptible(&random_read_wait);
2008-04-29 08:03:08 +00:00
kill_fasync(&fasync, SIGIO, POLL_IN);
}
spin_unlock_irqrestore(&r->lock, flags);
}
/*********************************************************************
*
* Entropy input management
*
*********************************************************************/
/* There is one of these per entropy source */
struct timer_rand_state {
cycles_t last_time;
long last_delta, last_delta2;
unsigned dont_count_entropy:1;
};
#ifndef CONFIG_GENERIC_HARDIRQS
static struct timer_rand_state *irq_timer_state[NR_IRQS];
static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
{
return irq_timer_state[irq];
}
static void set_timer_rand_state(unsigned int irq,
struct timer_rand_state *state)
{
irq_timer_state[irq] = state;
}
#else
static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
{
struct irq_desc *desc;
desc = irq_to_desc(irq);
return desc->timer_rand_state;
}
static void set_timer_rand_state(unsigned int irq,
struct timer_rand_state *state)
{
struct irq_desc *desc;
desc = irq_to_desc(irq);
desc->timer_rand_state = state;
}
#endif
static struct timer_rand_state input_timer_state;
/*
* This function adds entropy to the entropy "pool" by using timing
* delays. It uses the timer_rand_state structure to make an estimate
* of how many bits of entropy this call has added to the pool.
*
* The number "num" is also added to the pool - it should somehow describe
* the type of event which just happened. This is currently 0-255 for
* keyboard scan codes, and 256 upwards for interrupts.
*
*/
static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
{
struct {
cycles_t cycles;
long jiffies;
unsigned num;
} sample;
long delta, delta2, delta3;
preempt_disable();
/* if over the trickle threshold, use only 1 in 4096 samples */
if (input_pool.entropy_count > trickle_thresh &&
((__this_cpu_inc_return(trickle_count) - 1) & 0xfff))
goto out;
sample.jiffies = jiffies;
sample.cycles = get_cycles();
sample.num = num;
mix_pool_bytes(&input_pool, &sample, sizeof(sample));
/*
* Calculate number of bits of randomness we probably added.
* We take into account the first, second and third-order deltas
* in order to make our estimate.
*/
if (!state->dont_count_entropy) {
delta = sample.jiffies - state->last_time;
state->last_time = sample.jiffies;
delta2 = delta - state->last_delta;
state->last_delta = delta;
delta3 = delta2 - state->last_delta2;
state->last_delta2 = delta2;
if (delta < 0)
delta = -delta;
if (delta2 < 0)
delta2 = -delta2;
if (delta3 < 0)
delta3 = -delta3;
if (delta > delta2)
delta = delta2;
if (delta > delta3)
delta = delta3;
/*
* delta is now minimum absolute delta.
* Round down by 1 bit on general principles,
* and limit entropy entimate to 12 bits.
*/
credit_entropy_bits(&input_pool,
min_t(int, fls(delta>>1), 11));
}
out:
preempt_enable();
}
void add_input_randomness(unsigned int type, unsigned int code,
unsigned int value)
{
static unsigned char last_value;
/* ignore autorepeat and the like */
if (value == last_value)
return;
DEBUG_ENT("input event\n");
last_value = value;
add_timer_randomness(&input_timer_state,
(type << 4) ^ code ^ (code >> 4) ^ value);
}
EXPORT_SYMBOL_GPL(add_input_randomness);
void add_interrupt_randomness(int irq)
{
struct timer_rand_state *state;
state = get_timer_rand_state(irq);
if (state == NULL)
return;
DEBUG_ENT("irq event %d\n", irq);
add_timer_randomness(state, 0x100 + irq);
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#ifdef CONFIG_BLOCK
void add_disk_randomness(struct gendisk *disk)
{
if (!disk || !disk->random)
return;
/* first major is 1, so we get >= 0x200 here */
DEBUG_ENT("disk event %d:%d\n",
MAJOR(disk_devt(disk)), MINOR(disk_devt(disk)));
add_timer_randomness(disk->random, 0x100 + disk_devt(disk));
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#endif
/*********************************************************************
*
* Entropy extraction routines
*
*********************************************************************/
static ssize_t extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int min, int rsvd);
/*
* This utility inline function is responsible for transferring entropy
* from the primary pool to the secondary extraction pool. We make
* sure we pull enough for a 'catastrophic reseed'.
*/
static void xfer_secondary_pool(struct entropy_store *r, size_t nbytes)
{
__u32 tmp[OUTPUT_POOL_WORDS];
if (r->pull && r->entropy_count < nbytes * 8 &&
r->entropy_count < r->poolinfo->POOLBITS) {
/* If we're limited, always leave two wakeup worth's BITS */
int rsvd = r->limit ? 0 : random_read_wakeup_thresh/4;
int bytes = nbytes;
/* pull at least as many as BYTES as wakeup BITS */
bytes = max_t(int, bytes, random_read_wakeup_thresh / 8);
/* but never more than the buffer size */
bytes = min_t(int, bytes, sizeof(tmp));
DEBUG_ENT("going to reseed %s with %d bits "
"(%d of %d requested)\n",
r->name, bytes * 8, nbytes * 8, r->entropy_count);
bytes = extract_entropy(r->pull, tmp, bytes,
random_read_wakeup_thresh / 8, rsvd);
mix_pool_bytes(r, tmp, bytes);
credit_entropy_bits(r, bytes*8);
}
}
/*
* These functions extracts randomness from the "entropy pool", and
* returns it in a buffer.
*
* The min parameter specifies the minimum amount we can pull before
* failing to avoid races that defeat catastrophic reseeding while the
* reserved parameter indicates how much entropy we must leave in the
* pool after each pull to avoid starving other readers.
*
* Note: extract_entropy() assumes that .poolwords is a multiple of 16 words.
*/
static size_t account(struct entropy_store *r, size_t nbytes, int min,
int reserved)
{
unsigned long flags;
/* Hold lock while accounting */
spin_lock_irqsave(&r->lock, flags);
BUG_ON(r->entropy_count > r->poolinfo->POOLBITS);
DEBUG_ENT("trying to extract %d bits from %s\n",
nbytes * 8, r->name);
/* Can we pull enough? */
if (r->entropy_count / 8 < min + reserved) {
nbytes = 0;
} else {
/* If limited, never pull more than available */
if (r->limit && nbytes + reserved >= r->entropy_count / 8)
nbytes = r->entropy_count/8 - reserved;
if (r->entropy_count / 8 >= nbytes + reserved)
r->entropy_count -= nbytes*8;
else
r->entropy_count = reserved;
2008-04-29 08:03:08 +00:00
if (r->entropy_count < random_write_wakeup_thresh) {
wake_up_interruptible(&random_write_wait);
2008-04-29 08:03:08 +00:00
kill_fasync(&fasync, SIGIO, POLL_OUT);
}
}
DEBUG_ENT("debiting %d entropy credits from %s%s\n",
nbytes * 8, r->name, r->limit ? "" : " (unlimited)");
spin_unlock_irqrestore(&r->lock, flags);
return nbytes;
}
static void extract_buf(struct entropy_store *r, __u8 *out)
{
int i;
__u32 hash[5], workspace[SHA_WORKSPACE_WORDS];
__u8 extract[64];
/* Generate a hash across the pool, 16 words (512 bits) at a time */
sha_init(hash);
for (i = 0; i < r->poolinfo->poolwords; i += 16)
sha_transform(hash, (__u8 *)(r->pool + i), workspace);
/*
* We mix the hash back into the pool to prevent backtracking
* attacks (where the attacker knows the state of the pool
* plus the current outputs, and attempts to find previous
* ouputs), unless the hash function can be inverted. By
* mixing at least a SHA1 worth of hash data back, we make
* brute-forcing the feedback as hard as brute-forcing the
* hash.
*/
mix_pool_bytes_extract(r, hash, sizeof(hash), extract);
/*
* To avoid duplicates, we atomically extract a portion of the
* pool while mixing, and hash one final time.
*/
sha_transform(hash, extract, workspace);
memset(extract, 0, sizeof(extract));
memset(workspace, 0, sizeof(workspace));
/*
* In case the hash function has some recognizable output
* pattern, we fold it in half. Thus, we always feed back
* twice as much data as we output.
*/
hash[0] ^= hash[3];
hash[1] ^= hash[4];
hash[2] ^= rol32(hash[2], 16);
memcpy(out, hash, EXTRACT_SIZE);
memset(hash, 0, sizeof(hash));
}
static ssize_t extract_entropy(struct entropy_store *r, void *buf,
size_t nbytes, int min, int reserved)
{
ssize_t ret = 0, i;
__u8 tmp[EXTRACT_SIZE];
unsigned long flags;
xfer_secondary_pool(r, nbytes);
nbytes = account(r, nbytes, min, reserved);
while (nbytes) {
extract_buf(r, tmp);
if (fips_enabled) {
spin_lock_irqsave(&r->lock, flags);
if (!memcmp(tmp, r->last_data, EXTRACT_SIZE))
panic("Hardware RNG duplicated output!\n");
memcpy(r->last_data, tmp, EXTRACT_SIZE);
spin_unlock_irqrestore(&r->lock, flags);
}
i = min_t(int, nbytes, EXTRACT_SIZE);
memcpy(buf, tmp, i);
nbytes -= i;
buf += i;
ret += i;
}
/* Wipe data just returned from memory */
memset(tmp, 0, sizeof(tmp));
return ret;
}
static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
size_t nbytes)
{
ssize_t ret = 0, i;
__u8 tmp[EXTRACT_SIZE];
xfer_secondary_pool(r, nbytes);
nbytes = account(r, nbytes, 0, 0);
while (nbytes) {
if (need_resched()) {
if (signal_pending(current)) {
if (ret == 0)
ret = -ERESTARTSYS;
break;
}
schedule();
}
extract_buf(r, tmp);
i = min_t(int, nbytes, EXTRACT_SIZE);
if (copy_to_user(buf, tmp, i)) {
ret = -EFAULT;
break;
}
nbytes -= i;
buf += i;
ret += i;
}
/* Wipe data just returned from memory */
memset(tmp, 0, sizeof(tmp));
return ret;
}
/*
* This function is the exported kernel interface. It returns some
* number of good random numbers, suitable for seeding TCP sequence
* numbers, etc.
*/
void get_random_bytes(void *buf, int nbytes)
{
extract_entropy(&nonblocking_pool, buf, nbytes, 0, 0);
}
EXPORT_SYMBOL(get_random_bytes);
/*
* init_std_data - initialize pool with system data
*
* @r: pool to initialize
*
* This function clears the pool's entropy count and mixes some system
* data into the pool to prepare it for use. The pool is not cleared
* as that can only decrease the entropy in the pool.
*/
static void init_std_data(struct entropy_store *r)
{
ktime_t now;
unsigned long flags;
spin_lock_irqsave(&r->lock, flags);
r->entropy_count = 0;
spin_unlock_irqrestore(&r->lock, flags);
now = ktime_get_real();
mix_pool_bytes(r, &now, sizeof(now));
mix_pool_bytes(r, utsname(), sizeof(*(utsname())));
}
static int rand_initialize(void)
{
init_std_data(&input_pool);
init_std_data(&blocking_pool);
init_std_data(&nonblocking_pool);
return 0;
}
module_init(rand_initialize);
void rand_initialize_irq(int irq)
{
struct timer_rand_state *state;
state = get_timer_rand_state(irq);
if (state)
return;
/*
* If kzalloc returns null, we just won't use that entropy
* source.
*/
state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
if (state)
set_timer_rand_state(irq, state);
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#ifdef CONFIG_BLOCK
void rand_initialize_disk(struct gendisk *disk)
{
struct timer_rand_state *state;
/*
* If kzalloc returns null, we just won't use that entropy
* source.
*/
state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
if (state)
disk->random = state;
}
[PATCH] BLOCK: Make it possible to disable the block layer [try #6] Make it possible to disable the block layer. Not all embedded devices require it, some can make do with just JFFS2, NFS, ramfs, etc - none of which require the block layer to be present. This patch does the following: (*) Introduces CONFIG_BLOCK to disable the block layer, buffering and blockdev support. (*) Adds dependencies on CONFIG_BLOCK to any configuration item that controls an item that uses the block layer. This includes: (*) Block I/O tracing. (*) Disk partition code. (*) All filesystems that are block based, eg: Ext3, ReiserFS, ISOFS. (*) The SCSI layer. As far as I can tell, even SCSI chardevs use the block layer to do scheduling. Some drivers that use SCSI facilities - such as USB storage - end up disabled indirectly from this. (*) Various block-based device drivers, such as IDE and the old CDROM drivers. (*) MTD blockdev handling and FTL. (*) JFFS - which uses set_bdev_super(), something it could avoid doing by taking a leaf out of JFFS2's book. (*) Makes most of the contents of linux/blkdev.h, linux/buffer_head.h and linux/elevator.h contingent on CONFIG_BLOCK being set. sector_div() is, however, still used in places, and so is still available. (*) Also made contingent are the contents of linux/mpage.h, linux/genhd.h and parts of linux/fs.h. (*) Makes a number of files in fs/ contingent on CONFIG_BLOCK. (*) Makes mm/bounce.c (bounce buffering) contingent on CONFIG_BLOCK. (*) set_page_dirty() doesn't call __set_page_dirty_buffers() if CONFIG_BLOCK is not enabled. (*) fs/no-block.c is created to hold out-of-line stubs and things that are required when CONFIG_BLOCK is not set: (*) Default blockdev file operations (to give error ENODEV on opening). (*) Makes some /proc changes: (*) /proc/devices does not list any blockdevs. (*) /proc/diskstats and /proc/partitions are contingent on CONFIG_BLOCK. (*) Makes some compat ioctl handling contingent on CONFIG_BLOCK. (*) If CONFIG_BLOCK is not defined, makes sys_quotactl() return -ENODEV if given command other than Q_SYNC or if a special device is specified. (*) In init/do_mounts.c, no reference is made to the blockdev routines if CONFIG_BLOCK is not defined. This does not prohibit NFS roots or JFFS2. (*) The bdflush, ioprio_set and ioprio_get syscalls can now be absent (return error ENOSYS by way of cond_syscall if so). (*) The seclvl_bd_claim() and seclvl_bd_release() security calls do nothing if CONFIG_BLOCK is not set, since they can't then happen. Signed-Off-By: David Howells <dhowells@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
2006-09-30 18:45:40 +00:00
#endif
static ssize_t
random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
ssize_t n, retval = 0, count = 0;
if (nbytes == 0)
return 0;
while (nbytes > 0) {
n = nbytes;
if (n > SEC_XFER_SIZE)
n = SEC_XFER_SIZE;
DEBUG_ENT("reading %d bits\n", n*8);
n = extract_entropy_user(&blocking_pool, buf, n);
DEBUG_ENT("read got %d bits (%d still needed)\n",
n*8, (nbytes-n)*8);
if (n == 0) {
if (file->f_flags & O_NONBLOCK) {
retval = -EAGAIN;
break;
}
DEBUG_ENT("sleeping?\n");
wait_event_interruptible(random_read_wait,
input_pool.entropy_count >=
random_read_wakeup_thresh);
DEBUG_ENT("awake\n");
if (signal_pending(current)) {
retval = -ERESTARTSYS;
break;
}
continue;
}
if (n < 0) {
retval = n;
break;
}
count += n;
buf += n;
nbytes -= n;
break; /* This break makes the device work */
/* like a named pipe */
}
return (count ? count : retval);
}
static ssize_t
urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
return extract_entropy_user(&nonblocking_pool, buf, nbytes);
}
static unsigned int
random_poll(struct file *file, poll_table * wait)
{
unsigned int mask;
poll_wait(file, &random_read_wait, wait);
poll_wait(file, &random_write_wait, wait);
mask = 0;
if (input_pool.entropy_count >= random_read_wakeup_thresh)
mask |= POLLIN | POLLRDNORM;
if (input_pool.entropy_count < random_write_wakeup_thresh)
mask |= POLLOUT | POLLWRNORM;
return mask;
}
static int
write_pool(struct entropy_store *r, const char __user *buffer, size_t count)
{
size_t bytes;
__u32 buf[16];
const char __user *p = buffer;
while (count > 0) {
bytes = min(count, sizeof(buf));
if (copy_from_user(&buf, p, bytes))
return -EFAULT;
count -= bytes;
p += bytes;
mix_pool_bytes(r, buf, bytes);
cond_resched();
}
return 0;
}
static ssize_t random_write(struct file *file, const char __user *buffer,
size_t count, loff_t *ppos)
{
size_t ret;
ret = write_pool(&blocking_pool, buffer, count);
if (ret)
return ret;
ret = write_pool(&nonblocking_pool, buffer, count);
if (ret)
return ret;
return (ssize_t)count;
}
static long random_ioctl(struct file *f, unsigned int cmd, unsigned long arg)
{
int size, ent_count;
int __user *p = (int __user *)arg;
int retval;
switch (cmd) {
case RNDGETENTCNT:
/* inherently racy, no point locking */
if (put_user(input_pool.entropy_count, p))
return -EFAULT;
return 0;
case RNDADDTOENTCNT:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p))
return -EFAULT;
credit_entropy_bits(&input_pool, ent_count);
return 0;
case RNDADDENTROPY:
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
if (get_user(ent_count, p++))
return -EFAULT;
if (ent_count < 0)
return -EINVAL;
if (get_user(size, p++))
return -EFAULT;
retval = write_pool(&input_pool, (const char __user *)p,
size);
if (retval < 0)
return retval;
credit_entropy_bits(&input_pool, ent_count);
return 0;
case RNDZAPENTCNT:
case RNDCLEARPOOL:
/* Clear the entropy pool counters. */
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
rand_initialize();
return 0;
default:
return -EINVAL;
}
}
2008-04-29 08:03:08 +00:00
static int random_fasync(int fd, struct file *filp, int on)
{
return fasync_helper(fd, filp, on, &fasync);
}
const struct file_operations random_fops = {
.read = random_read,
.write = random_write,
.poll = random_poll,
.unlocked_ioctl = random_ioctl,
2008-04-29 08:03:08 +00:00
.fasync = random_fasync,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 16:52:59 +00:00
.llseek = noop_llseek,
};
const struct file_operations urandom_fops = {
.read = urandom_read,
.write = random_write,
.unlocked_ioctl = random_ioctl,
2008-04-29 08:03:08 +00:00
.fasync = random_fasync,
llseek: automatically add .llseek fop All file_operations should get a .llseek operation so we can make nonseekable_open the default for future file operations without a .llseek pointer. The three cases that we can automatically detect are no_llseek, seq_lseek and default_llseek. For cases where we can we can automatically prove that the file offset is always ignored, we use noop_llseek, which maintains the current behavior of not returning an error from a seek. New drivers should normally not use noop_llseek but instead use no_llseek and call nonseekable_open at open time. Existing drivers can be converted to do the same when the maintainer knows for certain that no user code relies on calling seek on the device file. The generated code is often incorrectly indented and right now contains comments that clarify for each added line why a specific variant was chosen. In the version that gets submitted upstream, the comments will be gone and I will manually fix the indentation, because there does not seem to be a way to do that using coccinelle. Some amount of new code is currently sitting in linux-next that should get the same modifications, which I will do at the end of the merge window. Many thanks to Julia Lawall for helping me learn to write a semantic patch that does all this. ===== begin semantic patch ===== // This adds an llseek= method to all file operations, // as a preparation for making no_llseek the default. // // The rules are // - use no_llseek explicitly if we do nonseekable_open // - use seq_lseek for sequential files // - use default_llseek if we know we access f_pos // - use noop_llseek if we know we don't access f_pos, // but we still want to allow users to call lseek // @ open1 exists @ identifier nested_open; @@ nested_open(...) { <+... nonseekable_open(...) ...+> } @ open exists@ identifier open_f; identifier i, f; identifier open1.nested_open; @@ int open_f(struct inode *i, struct file *f) { <+... ( nonseekable_open(...) | nested_open(...) ) ...+> } @ read disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ read_no_fpos disable optional_qualifier exists @ identifier read_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off) { ... when != off } @ write @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; expression E; identifier func; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { <+... ( *off = E | *off += E | func(..., off, ...) | E = *off ) ...+> } @ write_no_fpos @ identifier write_f; identifier f, p, s, off; type ssize_t, size_t, loff_t; @@ ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off) { ... when != off } @ fops0 @ identifier fops; @@ struct file_operations fops = { ... }; @ has_llseek depends on fops0 @ identifier fops0.fops; identifier llseek_f; @@ struct file_operations fops = { ... .llseek = llseek_f, ... }; @ has_read depends on fops0 @ identifier fops0.fops; identifier read_f; @@ struct file_operations fops = { ... .read = read_f, ... }; @ has_write depends on fops0 @ identifier fops0.fops; identifier write_f; @@ struct file_operations fops = { ... .write = write_f, ... }; @ has_open depends on fops0 @ identifier fops0.fops; identifier open_f; @@ struct file_operations fops = { ... .open = open_f, ... }; // use no_llseek if we call nonseekable_open //////////////////////////////////////////// @ nonseekable1 depends on !has_llseek && has_open @ identifier fops0.fops; identifier nso ~= "nonseekable_open"; @@ struct file_operations fops = { ... .open = nso, ... +.llseek = no_llseek, /* nonseekable */ }; @ nonseekable2 depends on !has_llseek @ identifier fops0.fops; identifier open.open_f; @@ struct file_operations fops = { ... .open = open_f, ... +.llseek = no_llseek, /* open uses nonseekable */ }; // use seq_lseek for sequential files ///////////////////////////////////// @ seq depends on !has_llseek @ identifier fops0.fops; identifier sr ~= "seq_read"; @@ struct file_operations fops = { ... .read = sr, ... +.llseek = seq_lseek, /* we have seq_read */ }; // use default_llseek if there is a readdir /////////////////////////////////////////// @ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier readdir_e; @@ // any other fop is used that changes pos struct file_operations fops = { ... .readdir = readdir_e, ... +.llseek = default_llseek, /* readdir is present */ }; // use default_llseek if at least one of read/write touches f_pos ///////////////////////////////////////////////////////////////// @ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read.read_f; @@ // read fops use offset struct file_operations fops = { ... .read = read_f, ... +.llseek = default_llseek, /* read accesses f_pos */ }; @ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, ... + .llseek = default_llseek, /* write accesses f_pos */ }; // Use noop_llseek if neither read nor write accesses f_pos /////////////////////////////////////////////////////////// @ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; identifier write_no_fpos.write_f; @@ // write fops use offset struct file_operations fops = { ... .write = write_f, .read = read_f, ... +.llseek = noop_llseek, /* read and write both use no f_pos */ }; @ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier write_no_fpos.write_f; @@ struct file_operations fops = { ... .write = write_f, ... +.llseek = noop_llseek, /* write uses no f_pos */ }; @ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; identifier read_no_fpos.read_f; @@ struct file_operations fops = { ... .read = read_f, ... +.llseek = noop_llseek, /* read uses no f_pos */ }; @ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @ identifier fops0.fops; @@ struct file_operations fops = { ... +.llseek = noop_llseek, /* no read or write fn */ }; ===== End semantic patch ===== Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Julia Lawall <julia@diku.dk> Cc: Christoph Hellwig <hch@infradead.org>
2010-08-15 16:52:59 +00:00
.llseek = noop_llseek,
};
/***************************************************************
* Random UUID interface
*
* Used here for a Boot ID, but can be useful for other kernel
* drivers.
***************************************************************/
/*
* Generate random UUID
*/
void generate_random_uuid(unsigned char uuid_out[16])
{
get_random_bytes(uuid_out, 16);
/* Set UUID version to 4 --- truly random generation */
uuid_out[6] = (uuid_out[6] & 0x0F) | 0x40;
/* Set the UUID variant to DCE */
uuid_out[8] = (uuid_out[8] & 0x3F) | 0x80;
}
EXPORT_SYMBOL(generate_random_uuid);
/********************************************************************
*
* Sysctl interface
*
********************************************************************/
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
static int min_read_thresh = 8, min_write_thresh;
static int max_read_thresh = INPUT_POOL_WORDS * 32;
static int max_write_thresh = INPUT_POOL_WORDS * 32;
static char sysctl_bootid[16];
/*
* These functions is used to return both the bootid UUID, and random
* UUID. The difference is in whether table->data is NULL; if it is,
* then a new UUID is generated and returned to the user.
*
* If the user accesses this via the proc interface, it will be returned
* as an ASCII string in the standard UUID format. If accesses via the
* sysctl system call, it is returned as 16 bytes of binary data.
*/
static int proc_do_uuid(ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
ctl_table fake_table;
unsigned char buf[64], tmp_uuid[16], *uuid;
uuid = table->data;
if (!uuid) {
uuid = tmp_uuid;
uuid[8] = 0;
}
if (uuid[8] == 0)
generate_random_uuid(uuid);
sprintf(buf, "%pU", uuid);
fake_table.data = buf;
fake_table.maxlen = sizeof(buf);
return proc_dostring(&fake_table, write, buffer, lenp, ppos);
}
static int sysctl_poolsize = INPUT_POOL_WORDS * 32;
ctl_table random_table[] = {
{
.procname = "poolsize",
.data = &sysctl_poolsize,
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
},
{
.procname = "entropy_avail",
.maxlen = sizeof(int),
.mode = 0444,
.proc_handler = proc_dointvec,
.data = &input_pool.entropy_count,
},
{
.procname = "read_wakeup_threshold",
.data = &random_read_wakeup_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_read_thresh,
.extra2 = &max_read_thresh,
},
{
.procname = "write_wakeup_threshold",
.data = &random_write_wakeup_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_write_thresh,
.extra2 = &max_write_thresh,
},
{
.procname = "boot_id",
.data = &sysctl_bootid,
.maxlen = 16,
.mode = 0444,
.proc_handler = proc_do_uuid,
},
{
.procname = "uuid",
.maxlen = 16,
.mode = 0444,
.proc_handler = proc_do_uuid,
},
{ }
};
#endif /* CONFIG_SYSCTL */
static u32 random_int_secret[MD5_MESSAGE_BYTES / 4] ____cacheline_aligned;
static int __init random_int_secret_init(void)
{
get_random_bytes(random_int_secret, sizeof(random_int_secret));
return 0;
}
late_initcall(random_int_secret_init);
/*
* Get a random word for internal kernel use only. Similar to urandom but
* with the goal of minimal entropy pool depletion. As a result, the random
* value is not cryptographically secure but for several uses the cost of
* depleting entropy is too high
*/
DEFINE_PER_CPU(__u32 [MD5_DIGEST_WORDS], get_random_int_hash);
unsigned int get_random_int(void)
{
__u32 *hash = get_cpu_var(get_random_int_hash);
unsigned int ret;
hash[0] += current->pid + jiffies + get_cycles();
md5_transform(hash, random_int_secret);
ret = hash[0];
put_cpu_var(get_random_int_hash);
return ret;
}
/*
* randomize_range() returns a start address such that
*
* [...... <range> .....]
* start end
*
* a <range> with size "len" starting at the return value is inside in the
* area defined by [start, end], but is otherwise randomized.
*/
unsigned long
randomize_range(unsigned long start, unsigned long end, unsigned long len)
{
unsigned long range = end - len - start;
if (end <= start + len)
return 0;
return PAGE_ALIGN(get_random_int() % range + start);
}