e49140120c
Wolfgang Walter reported this oops on his via C3 using padlock for AES-encryption: ################################################################## BUG: unable to handle kernel NULL pointer dereference at 000001f0 IP: [<c01028c5>] __switch_to+0x30/0x117 *pde = 00000000 Oops: 0002 [#1] PREEMPT Modules linked in: Pid: 2071, comm: sleep Not tainted (2.6.26 #11) EIP: 0060:[<c01028c5>] EFLAGS: 00010002 CPU: 0 EIP is at __switch_to+0x30/0x117 EAX: 00000000 EBX: c0493300 ECX: dc48dd00 EDX: c0493300 ESI: dc48dd00 EDI: c0493530 EBP: c04cff8c ESP: c04cff7c DS: 007b ES: 007b FS: 0000 GS: 0033 SS: 0068 Process sleep (pid: 2071, ti=c04ce000 task=dc48dd00 task.ti=d2fe6000) Stack: dc48df30 c0493300 00000000 00000000 d2fe7f44 c03b5b43 c04cffc8 00000046 c0131856 0000005a dc472d3c c0493300 c0493470 d983ae00 00002696 00000000 c0239f54 00000000 c04c4000 c04cffd8 c01025fe c04f3740 00049800 c04cffe0 Call Trace: [<c03b5b43>] ? schedule+0x285/0x2ff [<c0131856>] ? pm_qos_requirement+0x3c/0x53 [<c0239f54>] ? acpi_processor_idle+0x0/0x434 [<c01025fe>] ? cpu_idle+0x73/0x7f [<c03a4dcd>] ? rest_init+0x61/0x63 ======================= Wolfgang also found out that adding kernel_fpu_begin() and kernel_fpu_end() around the padlock instructions fix the oops. Suresh wrote: These padlock instructions though don't use/touch SSE registers, but it behaves similar to other SSE instructions. For example, it might cause DNA faults when cr0.ts is set. While this is a spurious DNA trap, it might cause oops with the recent fpu code changes. This is the code sequence that is probably causing this problem: a) new app is getting exec'd and it is somewhere in between start_thread() and flush_old_exec() in the load_xyz_binary() b) At pont "a", task's fpu state (like TS_USEDFPU, used_math() etc) is cleared. c) Now we get an interrupt/softirq which starts using these encrypt/decrypt routines in the network stack. This generates a math fault (as cr0.ts is '1') which sets TS_USEDFPU and restores the math that is in the task's xstate. d) Return to exec code path, which does start_thread() which does free_thread_xstate() and sets xstate pointer to NULL while the TS_USEDFPU is still set. e) At the next context switch from the new exec'd task to another task, we have a scenarios where TS_USEDFPU is set but xstate pointer is null. This can cause an oops during unlazy_fpu() in __switch_to() Now: 1) This should happen with or with out pre-emption. Viro also encountered similar problem with out CONFIG_PREEMPT. 2) kernel_fpu_begin() and kernel_fpu_end() will fix this problem, because kernel_fpu_begin() will manually do a clts() and won't run in to the situation of setting TS_USEDFPU in step "c" above. 3) This was working before the fpu changes, because its a spurious math fault which doesn't corrupt any fpu/sse registers and the task's math state was always in an allocated state. With out the recent lazy fpu allocation changes, while we don't see oops, there is a possible race still present in older kernels(for example, while kernel is using kernel_fpu_begin() in some optimized clear/copy page and an interrupt/softirq happens which uses these padlock instructions generating DNA fault). This is the failing scenario that existed even before the lazy fpu allocation changes: 0. CPU's TS flag is set 1. kernel using FPU in some optimized copy routine and while doing kernel_fpu_begin() takes an interrupt just before doing clts() 2. Takes an interrupt and ipsec uses padlock instruction. And we take a DNA fault as TS flag is still set. 3. We handle the DNA fault and set TS_USEDFPU and clear cr0.ts 4. We complete the padlock routine 5. Go back to step-1, which resumes clts() in kernel_fpu_begin(), finishes the optimized copy routine and does kernel_fpu_end(). At this point, we have cr0.ts again set to '1' but the task's TS_USEFPU is stilll set and not cleared. 6. Now kernel resumes its user operation. And at the next context switch, kernel sees it has do a FP save as TS_USEDFPU is still set and then will do a unlazy_fpu() in __switch_to(). unlazy_fpu() will take a DNA fault, as cr0.ts is '1' and now, because we are in __switch_to(), math_state_restore() will get confused and will restore the next task's FP state and will save it in prev tasks's FP state. Remember, in __switch_to() we are already on the stack of the next task but take a DNA fault for the prev task. This causes the fpu leakage. Fix the padlock instruction usage by calling them inside the context of new routines irq_ts_save/restore(), which clear/restore cr0.ts manually in the interrupt context. This will not generate spurious DNA in the context of the interrupt which will fix the oops encountered and the possible FPU leakage issue. Reported-and-bisected-by: Wolfgang Walter <wolfgang.walter@stwm.de> Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
210 lines
5.3 KiB
C
210 lines
5.3 KiB
C
/*
|
|
* RNG driver for VIA RNGs
|
|
*
|
|
* Copyright 2005 (c) MontaVista Software, Inc.
|
|
*
|
|
* with the majority of the code coming from:
|
|
*
|
|
* Hardware driver for the Intel/AMD/VIA Random Number Generators (RNG)
|
|
* (c) Copyright 2003 Red Hat Inc <jgarzik@redhat.com>
|
|
*
|
|
* derived from
|
|
*
|
|
* Hardware driver for the AMD 768 Random Number Generator (RNG)
|
|
* (c) Copyright 2001 Red Hat Inc <alan@redhat.com>
|
|
*
|
|
* derived from
|
|
*
|
|
* Hardware driver for Intel i810 Random Number Generator (RNG)
|
|
* Copyright 2000,2001 Jeff Garzik <jgarzik@pobox.com>
|
|
* Copyright 2000,2001 Philipp Rumpf <prumpf@mandrakesoft.com>
|
|
*
|
|
* This file is licensed under the terms of the GNU General Public
|
|
* License version 2. This program is licensed "as is" without any
|
|
* warranty of any kind, whether express or implied.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/kernel.h>
|
|
#include <linux/hw_random.h>
|
|
#include <linux/delay.h>
|
|
#include <asm/io.h>
|
|
#include <asm/msr.h>
|
|
#include <asm/cpufeature.h>
|
|
#include <asm/i387.h>
|
|
|
|
|
|
#define PFX KBUILD_MODNAME ": "
|
|
|
|
|
|
enum {
|
|
VIA_STRFILT_CNT_SHIFT = 16,
|
|
VIA_STRFILT_FAIL = (1 << 15),
|
|
VIA_STRFILT_ENABLE = (1 << 14),
|
|
VIA_RAWBITS_ENABLE = (1 << 13),
|
|
VIA_RNG_ENABLE = (1 << 6),
|
|
VIA_NOISESRC1 = (1 << 8),
|
|
VIA_NOISESRC2 = (1 << 9),
|
|
VIA_XSTORE_CNT_MASK = 0x0F,
|
|
|
|
VIA_RNG_CHUNK_8 = 0x00, /* 64 rand bits, 64 stored bits */
|
|
VIA_RNG_CHUNK_4 = 0x01, /* 32 rand bits, 32 stored bits */
|
|
VIA_RNG_CHUNK_4_MASK = 0xFFFFFFFF,
|
|
VIA_RNG_CHUNK_2 = 0x02, /* 16 rand bits, 32 stored bits */
|
|
VIA_RNG_CHUNK_2_MASK = 0xFFFF,
|
|
VIA_RNG_CHUNK_1 = 0x03, /* 8 rand bits, 32 stored bits */
|
|
VIA_RNG_CHUNK_1_MASK = 0xFF,
|
|
};
|
|
|
|
/*
|
|
* Investigate using the 'rep' prefix to obtain 32 bits of random data
|
|
* in one insn. The upside is potentially better performance. The
|
|
* downside is that the instruction becomes no longer atomic. Due to
|
|
* this, just like familiar issues with /dev/random itself, the worst
|
|
* case of a 'rep xstore' could potentially pause a cpu for an
|
|
* unreasonably long time. In practice, this condition would likely
|
|
* only occur when the hardware is failing. (or so we hope :))
|
|
*
|
|
* Another possible performance boost may come from simply buffering
|
|
* until we have 4 bytes, thus returning a u32 at a time,
|
|
* instead of the current u8-at-a-time.
|
|
*
|
|
* Padlock instructions can generate a spurious DNA fault, so
|
|
* we have to call them in the context of irq_ts_save/restore()
|
|
*/
|
|
|
|
static inline u32 xstore(u32 *addr, u32 edx_in)
|
|
{
|
|
u32 eax_out;
|
|
int ts_state;
|
|
|
|
ts_state = irq_ts_save();
|
|
|
|
asm(".byte 0x0F,0xA7,0xC0 /* xstore %%edi (addr=%0) */"
|
|
:"=m"(*addr), "=a"(eax_out)
|
|
:"D"(addr), "d"(edx_in));
|
|
|
|
irq_ts_restore(ts_state);
|
|
return eax_out;
|
|
}
|
|
|
|
static int via_rng_data_present(struct hwrng *rng, int wait)
|
|
{
|
|
u32 bytes_out;
|
|
u32 *via_rng_datum = (u32 *)(&rng->priv);
|
|
int i;
|
|
|
|
/* We choose the recommended 1-byte-per-instruction RNG rate,
|
|
* for greater randomness at the expense of speed. Larger
|
|
* values 2, 4, or 8 bytes-per-instruction yield greater
|
|
* speed at lesser randomness.
|
|
*
|
|
* If you change this to another VIA_CHUNK_n, you must also
|
|
* change the ->n_bytes values in rng_vendor_ops[] tables.
|
|
* VIA_CHUNK_8 requires further code changes.
|
|
*
|
|
* A copy of MSR_VIA_RNG is placed in eax_out when xstore
|
|
* completes.
|
|
*/
|
|
|
|
for (i = 0; i < 20; i++) {
|
|
*via_rng_datum = 0; /* paranoia, not really necessary */
|
|
bytes_out = xstore(via_rng_datum, VIA_RNG_CHUNK_1);
|
|
bytes_out &= VIA_XSTORE_CNT_MASK;
|
|
if (bytes_out || !wait)
|
|
break;
|
|
udelay(10);
|
|
}
|
|
return bytes_out ? 1 : 0;
|
|
}
|
|
|
|
static int via_rng_data_read(struct hwrng *rng, u32 *data)
|
|
{
|
|
u32 via_rng_datum = (u32)rng->priv;
|
|
|
|
*data = via_rng_datum;
|
|
|
|
return 1;
|
|
}
|
|
|
|
static int via_rng_init(struct hwrng *rng)
|
|
{
|
|
struct cpuinfo_x86 *c = &cpu_data(0);
|
|
u32 lo, hi, old_lo;
|
|
|
|
/* Control the RNG via MSR. Tread lightly and pay very close
|
|
* close attention to values written, as the reserved fields
|
|
* are documented to be "undefined and unpredictable"; but it
|
|
* does not say to write them as zero, so I make a guess that
|
|
* we restore the values we find in the register.
|
|
*/
|
|
rdmsr(MSR_VIA_RNG, lo, hi);
|
|
|
|
old_lo = lo;
|
|
lo &= ~(0x7f << VIA_STRFILT_CNT_SHIFT);
|
|
lo &= ~VIA_XSTORE_CNT_MASK;
|
|
lo &= ~(VIA_STRFILT_ENABLE | VIA_STRFILT_FAIL | VIA_RAWBITS_ENABLE);
|
|
lo |= VIA_RNG_ENABLE;
|
|
lo |= VIA_NOISESRC1;
|
|
|
|
/* Enable secondary noise source on CPUs where it is present. */
|
|
|
|
/* Nehemiah stepping 8 and higher */
|
|
if ((c->x86_model == 9) && (c->x86_mask > 7))
|
|
lo |= VIA_NOISESRC2;
|
|
|
|
/* Esther */
|
|
if (c->x86_model >= 10)
|
|
lo |= VIA_NOISESRC2;
|
|
|
|
if (lo != old_lo)
|
|
wrmsr(MSR_VIA_RNG, lo, hi);
|
|
|
|
/* perhaps-unnecessary sanity check; remove after testing if
|
|
unneeded */
|
|
rdmsr(MSR_VIA_RNG, lo, hi);
|
|
if ((lo & VIA_RNG_ENABLE) == 0) {
|
|
printk(KERN_ERR PFX "cannot enable VIA C3 RNG, aborting\n");
|
|
return -ENODEV;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
|
|
static struct hwrng via_rng = {
|
|
.name = "via",
|
|
.init = via_rng_init,
|
|
.data_present = via_rng_data_present,
|
|
.data_read = via_rng_data_read,
|
|
};
|
|
|
|
|
|
static int __init mod_init(void)
|
|
{
|
|
int err;
|
|
|
|
if (!cpu_has_xstore)
|
|
return -ENODEV;
|
|
printk(KERN_INFO "VIA RNG detected\n");
|
|
err = hwrng_register(&via_rng);
|
|
if (err) {
|
|
printk(KERN_ERR PFX "RNG registering failed (%d)\n",
|
|
err);
|
|
goto out;
|
|
}
|
|
out:
|
|
return err;
|
|
}
|
|
|
|
static void __exit mod_exit(void)
|
|
{
|
|
hwrng_unregister(&via_rng);
|
|
}
|
|
|
|
module_init(mod_init);
|
|
module_exit(mod_exit);
|
|
|
|
MODULE_DESCRIPTION("H/W RNG driver for VIA chipsets");
|
|
MODULE_LICENSE("GPL");
|