-/*****************************************************************************\
+/*
* Copyright (C) 2007-2010 Lawrence Livermore National Security, LLC.
* Copyright (C) 2007 The Regents of the University of California.
* Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
*
* You should have received a copy of the GNU General Public License along
* with the SPL. If not, see <http://www.gnu.org/licenses/>.
- *****************************************************************************
+ *
* Solaris Porting Layer (SPL) Generic Implementation.
-\*****************************************************************************/
+ */
#include <sys/sysmacros.h>
#include <sys/systeminfo.h>
#include <sys/kstat.h>
#include <sys/file.h>
#include <linux/ctype.h>
+#include <sys/disp.h>
+#include <sys/random.h>
+#include <sys/strings.h>
#include <linux/kmod.h>
-#include <linux/math64_compat.h>
-#include <linux/proc_compat.h>
+#include "zfs_gitrev.h"
-char spl_version[32] = "SPL v" SPL_META_VERSION "-" SPL_META_RELEASE;
-EXPORT_SYMBOL(spl_version);
+char spl_gitrev[64] = ZFS_META_GITREV;
+/* BEGIN CSTYLED */
unsigned long spl_hostid = 0;
EXPORT_SYMBOL(spl_hostid);
+/* BEGIN CSTYLED */
module_param(spl_hostid, ulong, 0644);
MODULE_PARM_DESC(spl_hostid, "The system hostid.");
+/* END CSTYLED */
-proc_t p0 = { 0 };
+proc_t p0;
EXPORT_SYMBOL(p0);
+/*
+ * Xorshift Pseudo Random Number Generator based on work by Sebastiano Vigna
+ *
+ * "Further scramblings of Marsaglia's xorshift generators"
+ * http://vigna.di.unimi.it/ftp/papers/xorshiftplus.pdf
+ *
+ * random_get_pseudo_bytes() is an API function on Illumos whose sole purpose
+ * is to provide bytes containing random numbers. It is mapped to /dev/urandom
+ * on Illumos, which uses a "FIPS 186-2 algorithm". No user of the SPL's
+ * random_get_pseudo_bytes() needs bytes that are of cryptographic quality, so
+ * we can implement it using a fast PRNG that we seed using Linux' actual
+ * equivalent to random_get_pseudo_bytes(). We do this by providing each CPU
+ * with an independent seed so that all calls to random_get_pseudo_bytes() are
+ * free of atomic instructions.
+ *
+ * A consequence of using a fast PRNG is that using random_get_pseudo_bytes()
+ * to generate words larger than 128 bits will paradoxically be limited to
+ * `2^128 - 1` possibilities. This is because we have a sequence of `2^128 - 1`
+ * 128-bit words and selecting the first will implicitly select the second. If
+ * a caller finds this behavior undesireable, random_get_bytes() should be used
+ * instead.
+ *
+ * XXX: Linux interrupt handlers that trigger within the critical section
+ * formed by `s[1] = xp[1];` and `xp[0] = s[0];` and call this function will
+ * see the same numbers. Nothing in the code currently calls this in an
+ * interrupt handler, so this is considered to be okay. If that becomes a
+ * problem, we could create a set of per-cpu variables for interrupt handlers
+ * and use them when in_interrupt() from linux/preempt_mask.h evaluates to
+ * true.
+ */
+static DEFINE_PER_CPU(uint64_t[2], spl_pseudo_entropy);
+
+/*
+ * spl_rand_next()/spl_rand_jump() are copied from the following CC-0 licensed
+ * file:
+ *
+ * http://xorshift.di.unimi.it/xorshift128plus.c
+ */
+
+static inline uint64_t
+spl_rand_next(uint64_t *s)
+{
+ uint64_t s1 = s[0];
+ const uint64_t s0 = s[1];
+ s[0] = s0;
+ s1 ^= s1 << 23; // a
+ s[1] = s1 ^ s0 ^ (s1 >> 18) ^ (s0 >> 5); // b, c
+ return (s[1] + s0);
+}
+
+static inline void
+spl_rand_jump(uint64_t *s)
+{
+ static const uint64_t JUMP[] =
+ { 0x8a5cd789635d2dff, 0x121fd2155c472f96 };
+
+ uint64_t s0 = 0;
+ uint64_t s1 = 0;
+ int i, b;
+ for (i = 0; i < sizeof (JUMP) / sizeof (*JUMP); i++)
+ for (b = 0; b < 64; b++) {
+ if (JUMP[i] & 1ULL << b) {
+ s0 ^= s[0];
+ s1 ^= s[1];
+ }
+ (void) spl_rand_next(s);
+ }
+
+ s[0] = s0;
+ s[1] = s1;
+}
+
+int
+random_get_pseudo_bytes(uint8_t *ptr, size_t len)
+{
+ uint64_t *xp, s[2];
+
+ ASSERT(ptr);
+
+ xp = get_cpu_var(spl_pseudo_entropy);
+
+ s[0] = xp[0];
+ s[1] = xp[1];
+
+ while (len) {
+ union {
+ uint64_t ui64;
+ uint8_t byte[sizeof (uint64_t)];
+ }entropy;
+ int i = MIN(len, sizeof (uint64_t));
+
+ len -= i;
+ entropy.ui64 = spl_rand_next(s);
+
+ while (i--)
+ *ptr++ = entropy.byte[i];
+ }
+
+ xp[0] = s[0];
+ xp[1] = s[1];
+
+ put_cpu_var(spl_pseudo_entropy);
+
+ return (0);
+}
+
+
+EXPORT_SYMBOL(random_get_pseudo_bytes);
+
#if BITS_PER_LONG == 32
/*
* Support 64/64 => 64 division on a 32-bit platform. While the kernel
* Calculate number of leading of zeros for a 64-bit value.
*/
static int
-nlz64(uint64_t x) {
+nlz64(uint64_t x)
+{
register int n = 0;
if (x == 0)
- return 64;
+ return (64);
- if (x <= 0x00000000FFFFFFFFULL) {n = n + 32; x = x << 32;}
- if (x <= 0x0000FFFFFFFFFFFFULL) {n = n + 16; x = x << 16;}
- if (x <= 0x00FFFFFFFFFFFFFFULL) {n = n + 8; x = x << 8;}
- if (x <= 0x0FFFFFFFFFFFFFFFULL) {n = n + 4; x = x << 4;}
- if (x <= 0x3FFFFFFFFFFFFFFFULL) {n = n + 2; x = x << 2;}
- if (x <= 0x7FFFFFFFFFFFFFFFULL) {n = n + 1;}
+ if (x <= 0x00000000FFFFFFFFULL) { n = n + 32; x = x << 32; }
+ if (x <= 0x0000FFFFFFFFFFFFULL) { n = n + 16; x = x << 16; }
+ if (x <= 0x00FFFFFFFFFFFFFFULL) { n = n + 8; x = x << 8; }
+ if (x <= 0x0FFFFFFFFFFFFFFFULL) { n = n + 4; x = x << 4; }
+ if (x <= 0x3FFFFFFFFFFFFFFFULL) { n = n + 2; x = x << 2; }
+ if (x <= 0x7FFFFFFFFFFFFFFFULL) { n = n + 1; }
- return n;
+ return (n);
}
/*
__div_u64(uint64_t u, uint32_t v)
{
(void) do_div(u, v);
- return u;
+ return (u);
}
/*
if (v >> 32 == 0) { // If v < 2**32:
if (u >> 32 < v) { // If u/v cannot overflow,
- return __div_u64(u, v); // just do one division.
+ return (__div_u64(u, v)); // just do one division.
} else { // If u/v would overflow:
u1 = u >> 32; // Break u into two halves.
u0 = u & 0xFFFFFFFF;
k = u1 - q1 * v; // First remainder, < v.
u0 += (k << 32);
q0 = __div_u64(u0, v); // Seconds quotient digit.
- return (q1 << 32) + q0;
+ return ((q1 << 32) + q0);
}
} else { // If v >= 2**32:
n = nlz64(v); // 0 <= n <= 31.
if ((u - q0 * v) >= v)
q0 = q0 + 1; // Now q0 is correct.
- return q0;
+ return (q0);
}
}
EXPORT_SYMBOL(__udivdi3);
+/* BEGIN CSTYLED */
+#ifndef abs64
+#define abs64(x) ({ uint64_t t = (x) >> 63; ((x) ^ t) - t; })
+#endif
+/* END CSTYLED */
+
/*
* Implementation of 64-bit signed division for 32-bit machines.
*/
int64_t q, t;
q = __udivdi3(abs64(u), abs64(v));
t = (u ^ v) >> 63; // If u, v have different
- return (q ^ t) - t; // signs, negate q.
+ return ((q ^ t) - t); // signs, negate q.
}
EXPORT_SYMBOL(__divdi3);
}
EXPORT_SYMBOL(__umoddi3);
+/*
+ * Implementation of 64-bit unsigned division/modulo for 32-bit machines.
+ */
+uint64_t
+__udivmoddi4(uint64_t n, uint64_t d, uint64_t *r)
+{
+ uint64_t q = __udivdi3(n, d);
+ if (r)
+ *r = n - d * q;
+ return (q);
+}
+EXPORT_SYMBOL(__udivmoddi4);
+
+/*
+ * Implementation of 64-bit signed division/modulo for 32-bit machines.
+ */
+int64_t
+__divmoddi4(int64_t n, int64_t d, int64_t *r)
+{
+ int64_t q, rr;
+ boolean_t nn = B_FALSE;
+ boolean_t nd = B_FALSE;
+ if (n < 0) {
+ nn = B_TRUE;
+ n = -n;
+ }
+ if (d < 0) {
+ nd = B_TRUE;
+ d = -d;
+ }
+
+ q = __udivmoddi4(n, d, (uint64_t *)&rr);
+
+ if (nn != nd)
+ q = -q;
+ if (nn)
+ rr = -rr;
+ if (r)
+ *r = rr;
+ return (q);
+}
+EXPORT_SYMBOL(__divmoddi4);
+
#if defined(__arm) || defined(__arm__)
/*
* Implementation of 64-bit (un)signed division for 32-bit arm machines.
register uint32_t r2 asm("r2") = (mod & 0xFFFFFFFF);
register uint32_t r3 asm("r3") = (mod >> 32);
+ /* BEGIN CSTYLED */
asm volatile(""
: "+r"(r0), "+r"(r1), "+r"(r2),"+r"(r3) /* output */
: "r"(r0), "r"(r1), "r"(r2), "r"(r3)); /* input */
+ /* END CSTYLED */
return; /* r0; */
}
register uint32_t r2 asm("r2") = (mod & 0xFFFFFFFF);
register uint32_t r3 asm("r3") = (mod >> 32);
+ /* BEGIN CSTYLED */
asm volatile(""
: "+r"(r0), "+r"(r1), "+r"(r2),"+r"(r3) /* output */
: "r"(r0), "r"(r1), "r"(r2), "r"(r3)); /* input */
+ /* END CSTYLED */
return; /* r0; */
}
#endif /* __arm || __arm__ */
#endif /* BITS_PER_LONG */
-/* NOTE: The strtoxx behavior is solely based on my reading of the Solaris
+/*
+ * NOTE: The strtoxx behavior is solely based on my reading of the Solaris
* ddi_strtol(9F) man page. I have not verified the behavior of these
* functions against their Solaris counterparts. It is possible that I
* may have misinterpreted the man page or the man page is incorrect.
int ddi_strtoull(const char *, char **, int, unsigned long long *);
int ddi_strtoll(const char *, char **, int, long long *);
-#define define_ddi_strtoux(type, valtype) \
+#define define_ddi_strtoux(type, valtype) \
int ddi_strtou##type(const char *str, char **endptr, \
- int base, valtype *result) \
+ int base, valtype *result) \
{ \
valtype last_value, value = 0; \
char *ptr = (char *)str; \
int flag = 1, digit; \
\
if (strlen(ptr) == 0) \
- return EINVAL; \
+ return (EINVAL); \
\
/* Auto-detect base based on prefix */ \
if (!base) { \
if (str[0] == '0') { \
- if (tolower(str[1])=='x' && isxdigit(str[2])) { \
+ if (tolower(str[1]) == 'x' && isxdigit(str[2])) { \
base = 16; /* hex */ \
ptr += 2; \
} else if (str[1] >= '0' && str[1] < 8) { \
base = 8; /* octal */ \
ptr += 1; \
} else { \
- return EINVAL; \
+ return (EINVAL); \
} \
} else { \
base = 10; /* decimal */ \
last_value = value; \
value = value * base + digit; \
if (last_value > value) /* Overflow */ \
- return ERANGE; \
+ return (ERANGE); \
\
flag = 1; \
ptr++; \
if (endptr) \
*endptr = (char *)(flag ? ptr : str); \
\
- return 0; \
+ return (0); \
} \
-#define define_ddi_strtox(type, valtype) \
+#define define_ddi_strtox(type, valtype) \
int ddi_strto##type(const char *str, char **endptr, \
- int base, valtype *result) \
+ int base, valtype *result) \
{ \
int rc; \
\
rc = ddi_strtou##type(str, endptr, base, result); \
} \
\
- return rc; \
+ return (rc); \
}
define_ddi_strtoux(l, unsigned long)
/* Fake ioctl() issued by kernel, 'from' is a kernel address */
if (flags & FKIOCTL) {
memcpy(to, from, len);
- return 0;
+ return (0);
}
- return copyin(from, to, len);
+ return (copyin(from, to, len));
}
EXPORT_SYMBOL(ddi_copyin);
/* Fake ioctl() issued by kernel, 'from' is a kernel address */
if (flags & FKIOCTL) {
memcpy(to, from, len);
- return 0;
+ return (0);
}
- return copyout(from, to, len);
+ return (copyout(from, to, len));
}
EXPORT_SYMBOL(ddi_copyout);
-#ifndef HAVE_PUT_TASK_STRUCT
-/*
- * This is only a stub function which should never be used. The SPL should
- * never be putting away the last reference on a task structure so this will
- * not be called. However, we still need to define it so the module does not
- * have undefined symbol at load time. That all said if this impossible
- * thing does somehow happen PANIC immediately so we know about it.
- */
-void
-__put_task_struct(struct task_struct *t)
-{
- PANIC("Unexpectly put last reference on task %d\n", (int)t->pid);
-}
-EXPORT_SYMBOL(__put_task_struct);
-#endif /* HAVE_PUT_TASK_STRUCT */
-
/*
* Read the unique system identifier from the /etc/hostid file.
*
MODULE_PARM_DESC(spl_hostid_path, "The system hostid file (/etc/hostid)");
static int
-hostid_read(void)
+hostid_read(uint32_t *hostid)
{
- int result;
uint64_t size;
struct _buf *file;
- uint32_t hostid = 0;
+ uint32_t value = 0;
+ int error;
file = kobj_open_file(spl_hostid_path);
-
if (file == (struct _buf *)-1)
- return -1;
-
- result = kobj_get_filesize(file, &size);
+ return (ENOENT);
- if (result != 0) {
- printk(KERN_WARNING
- "SPL: kobj_get_filesize returned %i on %s\n",
- result, spl_hostid_path);
+ error = kobj_get_filesize(file, &size);
+ if (error) {
kobj_close_file(file);
- return -2;
+ return (error);
}
- if (size < sizeof(HW_HOSTID_MASK)) {
- printk(KERN_WARNING
- "SPL: Ignoring the %s file because it is %llu bytes; "
- "expecting %lu bytes instead.\n", spl_hostid_path,
- size, (unsigned long)sizeof(HW_HOSTID_MASK));
+ if (size < sizeof (HW_HOSTID_MASK)) {
kobj_close_file(file);
- return -3;
+ return (EINVAL);
}
- /* Read directly into the variable like eglibc does. */
- /* Short reads are okay; native behavior is preserved. */
- result = kobj_read_file(file, (char *)&hostid, sizeof(hostid), 0);
-
- if (result < 0) {
- printk(KERN_WARNING
- "SPL: kobj_read_file returned %i on %s\n",
- result, spl_hostid_path);
+ /*
+ * Read directly into the variable like eglibc does.
+ * Short reads are okay; native behavior is preserved.
+ */
+ error = kobj_read_file(file, (char *)&value, sizeof (value), 0);
+ if (error < 0) {
kobj_close_file(file);
- return -4;
+ return (EIO);
}
/* Mask down to 32 bits like coreutils does. */
- spl_hostid = hostid & HW_HOSTID_MASK;
+ *hostid = (value & HW_HOSTID_MASK);
kobj_close_file(file);
- return 0;
+
+ return (0);
}
+/*
+ * Return the system hostid. Preferentially use the spl_hostid module option
+ * when set, otherwise use the value in the /etc/hostid file.
+ */
uint32_t
zone_get_hostid(void *zone)
{
- static int first = 1;
-
- /* Only the global zone is supported */
- ASSERT(zone == NULL);
+ uint32_t hostid;
- if (first) {
- first = 0;
+ ASSERT3P(zone, ==, NULL);
- spl_hostid &= HW_HOSTID_MASK;
- /*
- * Get the hostid if it was not passed as a module parameter.
- * Try reading the /etc/hostid file directly.
- */
- if (spl_hostid == 0 && hostid_read())
- spl_hostid = 0;
+ if (spl_hostid != 0)
+ return ((uint32_t)(spl_hostid & HW_HOSTID_MASK));
+ if (hostid_read(&hostid) == 0)
+ return (hostid);
- printk(KERN_NOTICE "SPL: using hostid 0x%08x\n",
- (unsigned int) spl_hostid);
- }
-
- return spl_hostid;
+ return (0);
}
EXPORT_SYMBOL(zone_get_hostid);
return (rc);
}
+/*
+ * We initialize the random number generator with 128 bits of entropy from the
+ * system random number generator. In the improbable case that we have a zero
+ * seed, we fallback to the system jiffies, unless it is also zero, in which
+ * situation we use a preprogrammed seed. We step forward by 2^64 iterations to
+ * initialize each of the per-cpu seeds so that the sequences generated on each
+ * CPU are guaranteed to never overlap in practice.
+ */
+static void __init
+spl_random_init(void)
+{
+ uint64_t s[2];
+ int i;
+
+ get_random_bytes(s, sizeof (s));
+
+ if (s[0] == 0 && s[1] == 0) {
+ if (jiffies != 0) {
+ s[0] = jiffies;
+ s[1] = ~0 - jiffies;
+ } else {
+ (void) memcpy(s, "improbable seed", sizeof (s));
+ }
+ printk("SPL: get_random_bytes() returned 0 "
+ "when generating random seed. Setting initial seed to "
+ "0x%016llx%016llx.\n", cpu_to_be64(s[0]),
+ cpu_to_be64(s[1]));
+ }
+
+ for_each_possible_cpu(i) {
+ uint64_t *wordp = per_cpu(spl_pseudo_entropy, i);
+
+ spl_rand_jump(s);
+
+ wordp[0] = s[0];
+ wordp[1] = s[1];
+ }
+}
+
static void
spl_kvmem_fini(void)
{
{
int rc = 0;
+ bzero(&p0, sizeof (proc_t));
+ spl_random_init();
+
if ((rc = spl_kvmem_init()))
goto out1;
if ((rc = spl_zlib_init()))
goto out10;
- printk(KERN_NOTICE "SPL: Loaded module v%s-%s%s\n", SPL_META_VERSION,
- SPL_META_RELEASE, SPL_DEBUG_STR);
return (rc);
out10:
out2:
spl_kvmem_fini();
out1:
- printk(KERN_NOTICE "SPL: Failed to Load Solaris Porting Layer "
- "v%s-%s%s, rc = %d\n", SPL_META_VERSION, SPL_META_RELEASE,
- SPL_DEBUG_STR, rc);
-
return (rc);
}
static void __exit
spl_fini(void)
{
- printk(KERN_NOTICE "SPL: Unloaded module v%s-%s%s\n",
- SPL_META_VERSION, SPL_META_RELEASE, SPL_DEBUG_STR);
spl_zlib_fini();
spl_kstat_fini();
spl_proc_fini();
module_exit(spl_fini);
MODULE_DESCRIPTION("Solaris Porting Layer");
-MODULE_AUTHOR(SPL_META_AUTHOR);
-MODULE_LICENSE(SPL_META_LICENSE);
-MODULE_VERSION(SPL_META_VERSION "-" SPL_META_RELEASE);
+MODULE_AUTHOR(ZFS_META_AUTHOR);
+MODULE_LICENSE("GPL");
+MODULE_VERSION(ZFS_META_VERSION "-" ZFS_META_RELEASE);