* UCRL-CODE-235197
*
* This file is part of the SPL, Solaris Porting Layer.
- * For details, see <http://github.com/behlendorf/spl/>.
+ * For details, see <http://zfsonlinux.org/>.
*
* The SPL is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
#include <sys/sysmacros.h>
#include <sys/systeminfo.h>
#include <sys/vmsystm.h>
-#include <sys/vnode.h>
+#include <sys/kobj.h>
#include <sys/kmem.h>
+#include <sys/kmem_cache.h>
+#include <sys/vmem.h>
#include <sys/mutex.h>
#include <sys/rwlock.h>
#include <sys/taskq.h>
+#include <sys/tsd.h>
+#include <sys/zmod.h>
#include <sys/debug.h>
#include <sys/proc.h>
#include <sys/kstat.h>
-#include <sys/utsname.h>
#include <sys/file.h>
+#include <linux/ctype.h>
+#include <sys/disp.h>
+#include <sys/random.h>
#include <linux/kmod.h>
+#include <linux/math64_compat.h>
#include <linux/proc_compat.h>
-#ifdef DEBUG_SUBSYSTEM
-#undef DEBUG_SUBSYSTEM
-#endif
-
-#define DEBUG_SUBSYSTEM S_GENERIC
-
-char spl_version[16] = "SPL v" SPL_META_VERSION;
+char spl_version[32] = "SPL v" SPL_META_VERSION "-" SPL_META_RELEASE;
EXPORT_SYMBOL(spl_version);
-long spl_hostid = 0;
+unsigned long spl_hostid = 0;
EXPORT_SYMBOL(spl_hostid);
+module_param(spl_hostid, ulong, 0644);
+MODULE_PARM_DESC(spl_hostid, "The system hostid.");
-char hw_serial[HW_HOSTID_LEN] = "<none>";
-EXPORT_SYMBOL(hw_serial);
-
-proc_t p0 = { 0 };
+proc_t p0;
EXPORT_SYMBOL(p0);
-#ifndef HAVE_KALLSYMS_LOOKUP_NAME
-kallsyms_lookup_name_t spl_kallsyms_lookup_name_fn = SYMBOL_POISON;
-#endif
+/*
+ * 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
-highbit(unsigned long i)
+random_get_pseudo_bytes(uint8_t *ptr, size_t len)
{
- register int h = 1;
- ENTRY;
-
- if (i == 0)
- RETURN(0);
-#if BITS_PER_LONG == 64
- if (i & 0xffffffff00000000ul) {
- h += 32; i >>= 32;
- }
-#endif
- if (i & 0xffff0000) {
- h += 16; i >>= 16;
- }
- if (i & 0xff00) {
- h += 8; i >>= 8;
- }
- if (i & 0xf0) {
- h += 4; i >>= 4;
- }
- if (i & 0xc) {
- h += 2; i >>= 2;
- }
- if (i & 0x2) {
- h += 1;
- }
- RETURN(h);
+ 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(highbit);
+
+
+EXPORT_SYMBOL(random_get_pseudo_bytes);
#if BITS_PER_LONG == 32
/*
q0 = q0 - 1; // too small by 1.
if ((u - q0 * v) >= v)
q0 = q0 + 1; // Now q0 is correct.
-
+
return q0;
}
}
}
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.
+ *
+ * Run-time ABI for the ARM Architecture (page 20). A pair of (unsigned)
+ * long longs is returned in {{r0, r1}, {r2,r3}}, the quotient in {r0, r1},
+ * and the remainder in {r2, r3}. The return type is specifically left
+ * set to 'void' to ensure the compiler does not overwrite these registers
+ * during the return. All results are in registers as per ABI
+ */
+void
+__aeabi_uldivmod(uint64_t u, uint64_t v)
+{
+ uint64_t res;
+ uint64_t mod;
+
+ res = __udivdi3(u, v);
+ mod = __umoddi3(u, v);
+ {
+ register uint32_t r0 asm("r0") = (res & 0xFFFFFFFF);
+ register uint32_t r1 asm("r1") = (res >> 32);
+ register uint32_t r2 asm("r2") = (mod & 0xFFFFFFFF);
+ register uint32_t r3 asm("r3") = (mod >> 32);
+
+ asm volatile(""
+ : "+r"(r0), "+r"(r1), "+r"(r2),"+r"(r3) /* output */
+ : "r"(r0), "r"(r1), "r"(r2), "r"(r3)); /* input */
+
+ return; /* r0; */
+ }
+}
+EXPORT_SYMBOL(__aeabi_uldivmod);
+
+void
+__aeabi_ldivmod(int64_t u, int64_t v)
+{
+ int64_t res;
+ uint64_t mod;
+
+ res = __divdi3(u, v);
+ mod = __umoddi3(u, v);
+ {
+ register uint32_t r0 asm("r0") = (res & 0xFFFFFFFF);
+ register uint32_t r1 asm("r1") = (res >> 32);
+ register uint32_t r2 asm("r2") = (mod & 0xFFFFFFFF);
+ register uint32_t r3 asm("r3") = (mod >> 32);
+
+ asm volatile(""
+ : "+r"(r0), "+r"(r1), "+r"(r2),"+r"(r3) /* output */
+ : "r"(r0), "r"(r1), "r"(r2), "r"(r3)); /* input */
+
+ return; /* r0; */
+ }
+}
+EXPORT_SYMBOL(__aeabi_ldivmod);
+#endif /* __arm || __arm__ */
#endif /* BITS_PER_LONG */
/* NOTE: The strtoxx behavior is solely based on my reading of the Solaris
}
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 SBUG() immediately so we know about it.
+ * Read the unique system identifier from the /etc/hostid file.
+ *
+ * The behavior of /usr/bin/hostid on Linux systems with the
+ * regular eglibc and coreutils is:
+ *
+ * 1. Generate the value if the /etc/hostid file does not exist
+ * or if the /etc/hostid file is less than four bytes in size.
+ *
+ * 2. If the /etc/hostid file is at least 4 bytes, then return
+ * the first four bytes [0..3] in native endian order.
+ *
+ * 3. Always ignore bytes [4..] if they exist in the file.
+ *
+ * Only the first four bytes are significant, even on systems that
+ * have a 64-bit word size.
+ *
+ * See:
+ *
+ * eglibc: sysdeps/unix/sysv/linux/gethostid.c
+ * coreutils: src/hostid.c
+ *
+ * Notes:
+ *
+ * The /etc/hostid file on Solaris is a text file that often reads:
+ *
+ * # DO NOT EDIT
+ * "0123456789"
+ *
+ * Directly copying this file to Linux results in a constant
+ * hostid of 4f442023 because the default comment constitutes
+ * the first four bytes of the file.
+ *
*/
-void
-__put_task_struct(struct task_struct *t)
-{
- SBUG();
-}
-EXPORT_SYMBOL(__put_task_struct);
-#endif /* HAVE_PUT_TASK_STRUCT */
-struct new_utsname *__utsname(void)
-{
-#ifdef HAVE_INIT_UTSNAME
- return init_utsname();
-#else
- return &system_utsname;
-#endif
-}
-EXPORT_SYMBOL(__utsname);
+char *spl_hostid_path = HW_HOSTID_PATH;
+module_param(spl_hostid_path, charp, 0444);
+MODULE_PARM_DESC(spl_hostid_path, "The system hostid file (/etc/hostid)");
static int
-set_hostid(void)
+hostid_read(uint32_t *hostid)
{
- char sh_path[] = "/bin/sh";
- char *argv[] = { sh_path,
- "-c",
- "/usr/bin/hostid >/proc/sys/kernel/spl/hostid",
- NULL };
- char *envp[] = { "HOME=/",
- "TERM=linux",
- "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
- NULL };
- int rc;
-
- /* Doing address resolution in the kernel is tricky and just
- * not a good idea in general. So to set the proper 'hw_serial'
- * use the usermodehelper support to ask '/bin/sh' to run
- * '/usr/bin/hostid' and redirect the result to /proc/sys/spl/hostid
- * for us to use. It's a horrific solution but it will do for now.
+ uint64_t size;
+ struct _buf *file;
+ uint32_t value = 0;
+ int error;
+
+ file = kobj_open_file(spl_hostid_path);
+ if (file == (struct _buf *)-1)
+ return (ENOENT);
+
+ error = kobj_get_filesize(file, &size);
+ if (error) {
+ kobj_close_file(file);
+ return (error);
+ }
+
+ if (size < sizeof(HW_HOSTID_MASK)) {
+ kobj_close_file(file);
+ return (EINVAL);
+ }
+
+ /*
+ * Read directly into the variable like eglibc does.
+ * Short reads are okay; native behavior is preserved.
*/
- rc = call_usermodehelper(sh_path, argv, envp, 1);
- if (rc)
- printk("SPL: Failed user helper '%s %s %s', rc = %d\n",
- argv[0], argv[1], argv[2], rc);
+ error = kobj_read_file(file, (char *)&value, sizeof(value), 0);
+ if (error < 0) {
+ kobj_close_file(file);
+ return (EIO);
+ }
+
+ /* Mask down to 32 bits like coreutils does. */
+ *hostid = (value & HW_HOSTID_MASK);
+ kobj_close_file(file);
- return rc;
+ 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)
{
- unsigned long hostid;
+ uint32_t hostid;
- /* Only the global zone is supported */
- ASSERT(zone == NULL);
+ ASSERT3P(zone, ==, NULL);
- if (ddi_strtoul(hw_serial, NULL, HW_HOSTID_LEN-1, &hostid) != 0)
- return HW_INVALID_HOSTID;
+ if (spl_hostid != 0)
+ return ((uint32_t)(spl_hostid & HW_HOSTID_MASK));
- return (uint32_t)hostid;
+ if (hostid_read(&hostid) == 0)
+ return (hostid);
+
+ return (0);
}
EXPORT_SYMBOL(zone_get_hostid);
-#ifndef HAVE_KALLSYMS_LOOKUP_NAME
-/*
- * Because kallsyms_lookup_name() is no longer exported in the
- * mainline kernel we are forced to resort to somewhat drastic
- * measures. This function replaces the functionality by performing
- * an upcall to user space where /proc/kallsyms is consulted for
- * the requested address.
- */
-#define GET_KALLSYMS_ADDR_CMD \
- "gawk '{ if ( $3 == \"kallsyms_lookup_name\") { print $1 } }' " \
- "/proc/kallsyms >/proc/sys/kernel/spl/kallsyms_lookup_name"
-
static int
-set_kallsyms_lookup_name(void)
+spl_kvmem_init(void)
{
- char sh_path[] = "/bin/sh";
- char *argv[] = { sh_path,
- "-c",
- GET_KALLSYMS_ADDR_CMD,
- NULL };
- char *envp[] = { "HOME=/",
- "TERM=linux",
- "PATH=/sbin:/usr/sbin:/bin:/usr/bin",
- NULL };
- int rc;
-
- rc = call_usermodehelper(sh_path, argv, envp, 1);
+ int rc = 0;
+
+ rc = spl_kmem_init();
if (rc)
- printk("SPL: Failed user helper '%s %s %s', rc = %d\n",
- argv[0], argv[1], argv[2], rc);
+ return (rc);
- return rc;
+ rc = spl_vmem_init();
+ if (rc) {
+ spl_kmem_fini();
+ return (rc);
+ }
+
+ return (rc);
}
-#endif
-static int
-__init spl_init(void)
+/*
+ * 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.", 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)
+{
+ spl_vmem_fini();
+ spl_kmem_fini();
+}
+
+static int __init
+spl_init(void)
{
int rc = 0;
- if ((rc = debug_init()))
- return rc;
+ bzero(&p0, sizeof (proc_t));
+ spl_random_init();
- if ((rc = spl_kmem_init()))
- GOTO(out1, rc);
+ if ((rc = spl_kvmem_init()))
+ goto out1;
if ((rc = spl_mutex_init()))
- GOTO(out2, rc);
+ goto out2;
if ((rc = spl_rw_init()))
- GOTO(out3, rc);
+ goto out3;
+
+ if ((rc = spl_tsd_init()))
+ goto out4;
if ((rc = spl_taskq_init()))
- GOTO(out4, rc);
+ goto out5;
- if ((rc = vn_init()))
- GOTO(out5, rc);
+ if ((rc = spl_kmem_cache_init()))
+ goto out6;
- if ((rc = proc_init()))
- GOTO(out6, rc);
+ if ((rc = spl_vn_init()))
+ goto out7;
- if ((rc = kstat_init()))
- GOTO(out7, rc);
+ if ((rc = spl_proc_init()))
+ goto out8;
- if ((rc = set_hostid()))
- GOTO(out8, rc = -EADDRNOTAVAIL);
+ if ((rc = spl_kstat_init()))
+ goto out9;
-#ifndef HAVE_KALLSYMS_LOOKUP_NAME
- if ((rc = set_kallsyms_lookup_name()))
- GOTO(out8, rc = -EADDRNOTAVAIL);
-#endif /* HAVE_KALLSYMS_LOOKUP_NAME */
+ if ((rc = spl_zlib_init()))
+ goto out10;
- if ((rc = spl_kmem_init_kallsyms_lookup()))
- GOTO(out8, rc);
+ printk(KERN_NOTICE "SPL: Loaded module v%s-%s%s\n", SPL_META_VERSION,
+ SPL_META_RELEASE, SPL_DEBUG_STR);
+ return (rc);
- printk("SPL: Loaded Solaris Porting Layer v%s\n", SPL_META_VERSION);
- RETURN(rc);
+out10:
+ spl_kstat_fini();
+out9:
+ spl_proc_fini();
out8:
- kstat_fini();
+ spl_vn_fini();
out7:
- proc_fini();
+ spl_kmem_cache_fini();
out6:
- vn_fini();
-out5:
spl_taskq_fini();
+out5:
+ spl_tsd_fini();
out4:
spl_rw_fini();
out3:
spl_mutex_fini();
out2:
- spl_kmem_fini();
+ spl_kvmem_fini();
out1:
- debug_fini();
+ 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);
- printk("SPL: Failed to Load Solaris Porting Layer v%s, "
- "rc = %d\n", SPL_META_VERSION, rc);
- return rc;
+ return (rc);
}
-static void
+static void __exit
spl_fini(void)
{
- ENTRY;
-
- printk("SPL: Unloaded Solaris Porting Layer v%s\n", SPL_META_VERSION);
- kstat_fini();
- proc_fini();
- vn_fini();
+ 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();
+ spl_vn_fini();
+ spl_kmem_cache_fini();
spl_taskq_fini();
+ spl_tsd_fini();
spl_rw_fini();
spl_mutex_fini();
- spl_kmem_fini();
- debug_fini();
-}
-
-/* Called when a dependent module is loaded */
-void
-spl_setup(void)
-{
- int rc;
-
- /*
- * At module load time the pwd is set to '/' on a Solaris system.
- * On a Linux system will be set to whatever directory the caller
- * was in when executing insmod/modprobe.
- */
- rc = vn_set_pwd("/");
- if (rc)
- printk("SPL: Warning unable to set pwd to '/': %d\n", rc);
-}
-EXPORT_SYMBOL(spl_setup);
-
-/* Called when a dependent module is unloaded */
-void
-spl_cleanup(void)
-{
+ spl_kvmem_fini();
}
-EXPORT_SYMBOL(spl_cleanup);
module_init(spl_init);
module_exit(spl_fini);
-MODULE_AUTHOR("Lawrence Livermore National Labs");
MODULE_DESCRIPTION("Solaris Porting Layer");
-MODULE_LICENSE("GPL");
+MODULE_AUTHOR(SPL_META_AUTHOR);
+MODULE_LICENSE(SPL_META_LICENSE);
+MODULE_VERSION(SPL_META_VERSION "-" SPL_META_RELEASE);
projects / mirror_spl-debian.git / blobdiff