OpenCloudOS-Kernel/drivers/crypto/padlock-aes.c

548 lines
15 KiB
C
Raw Normal View History

/*
* Cryptographic API.
*
* Support for VIA PadLock hardware crypto engine.
*
* Copyright (c) 2004 Michal Ludvig <michal@logix.cz>
*
*/
#include <crypto/algapi.h>
#include <crypto/aes.h>
#include <crypto/padlock.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/percpu.h>
#include <linux/smp.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/cpu_device_id.h>
#include <asm/byteorder.h>
#include <asm/processor.h>
#include <asm/fpu/api.h>
/*
* Number of data blocks actually fetched for each xcrypt insn.
* Processors with prefetch errata will fetch extra blocks.
*/
static unsigned int ecb_fetch_blocks = 2;
#define MAX_ECB_FETCH_BLOCKS (8)
#define ecb_fetch_bytes (ecb_fetch_blocks * AES_BLOCK_SIZE)
static unsigned int cbc_fetch_blocks = 1;
#define MAX_CBC_FETCH_BLOCKS (4)
#define cbc_fetch_bytes (cbc_fetch_blocks * AES_BLOCK_SIZE)
/* Control word. */
struct cword {
unsigned int __attribute__ ((__packed__))
rounds:4,
algo:3,
keygen:1,
interm:1,
encdec:1,
ksize:2;
} __attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
/* Whenever making any changes to the following
* structure *make sure* you keep E, d_data
* and cword aligned on 16 Bytes boundaries and
* the Hardware can access 16 * 16 bytes of E and d_data
* (only the first 15 * 16 bytes matter but the HW reads
* more).
*/
struct aes_ctx {
u32 E[AES_MAX_KEYLENGTH_U32]
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
u32 d_data[AES_MAX_KEYLENGTH_U32]
__attribute__ ((__aligned__(PADLOCK_ALIGNMENT)));
struct {
struct cword encrypt;
struct cword decrypt;
} cword;
u32 *D;
};
static DEFINE_PER_CPU(struct cword *, paes_last_cword);
/* Tells whether the ACE is capable to generate
the extended key for a given key_len. */
static inline int
aes_hw_extkey_available(uint8_t key_len)
{
/* TODO: We should check the actual CPU model/stepping
as it's possible that the capability will be
added in the next CPU revisions. */
if (key_len == 16)
return 1;
return 0;
}
static inline struct aes_ctx *aes_ctx_common(void *ctx)
{
unsigned long addr = (unsigned long)ctx;
unsigned long align = PADLOCK_ALIGNMENT;
if (align <= crypto_tfm_ctx_alignment())
align = 1;
return (struct aes_ctx *)ALIGN(addr, align);
}
static inline struct aes_ctx *aes_ctx(struct crypto_tfm *tfm)
{
return aes_ctx_common(crypto_tfm_ctx(tfm));
}
static inline struct aes_ctx *blk_aes_ctx(struct crypto_blkcipher *tfm)
{
return aes_ctx_common(crypto_blkcipher_ctx(tfm));
}
static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key,
unsigned int key_len)
{
struct aes_ctx *ctx = aes_ctx(tfm);
const __le32 *key = (const __le32 *)in_key;
u32 *flags = &tfm->crt_flags;
struct crypto_aes_ctx gen_aes;
int cpu;
if (key_len % 8) {
*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
}
/*
* If the hardware is capable of generating the extended key
* itself we must supply the plain key for both encryption
* and decryption.
*/
ctx->D = ctx->E;
ctx->E[0] = le32_to_cpu(key[0]);
ctx->E[1] = le32_to_cpu(key[1]);
ctx->E[2] = le32_to_cpu(key[2]);
ctx->E[3] = le32_to_cpu(key[3]);
/* Prepare control words. */
memset(&ctx->cword, 0, sizeof(ctx->cword));
ctx->cword.decrypt.encdec = 1;
ctx->cword.encrypt.rounds = 10 + (key_len - 16) / 4;
ctx->cword.decrypt.rounds = ctx->cword.encrypt.rounds;
ctx->cword.encrypt.ksize = (key_len - 16) / 8;
ctx->cword.decrypt.ksize = ctx->cword.encrypt.ksize;
/* Don't generate extended keys if the hardware can do it. */
if (aes_hw_extkey_available(key_len))
goto ok;
ctx->D = ctx->d_data;
ctx->cword.encrypt.keygen = 1;
ctx->cword.decrypt.keygen = 1;
if (crypto_aes_expand_key(&gen_aes, in_key, key_len)) {
*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
return -EINVAL;
}
memcpy(ctx->E, gen_aes.key_enc, AES_MAX_KEYLENGTH);
memcpy(ctx->D, gen_aes.key_dec, AES_MAX_KEYLENGTH);
ok:
for_each_online_cpu(cpu)
if (&ctx->cword.encrypt == per_cpu(paes_last_cword, cpu) ||
&ctx->cword.decrypt == per_cpu(paes_last_cword, cpu))
per_cpu(paes_last_cword, cpu) = NULL;
return 0;
}
/* ====== Encryption/decryption routines ====== */
/* These are the real call to PadLock. */
static inline void padlock_reset_key(struct cword *cword)
{
int cpu = raw_smp_processor_id();
if (cword != per_cpu(paes_last_cword, cpu))
#ifndef CONFIG_X86_64
asm volatile ("pushfl; popfl");
#else
asm volatile ("pushfq; popfq");
#endif
}
static inline void padlock_store_cword(struct cword *cword)
{
per_cpu(paes_last_cword, raw_smp_processor_id()) = cword;
}
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() 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>
2008-08-13 20:02:26 +08:00
/*
* While the padlock instructions don't use FP/SSE registers, they
* generate a spurious DNA fault when CR0.TS is '1'. Fortunately,
* the kernel doesn't use CR0.TS.
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() 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>
2008-08-13 20:02:26 +08:00
*/
static inline void rep_xcrypt_ecb(const u8 *input, u8 *output, void *key,
struct cword *control_word, int count)
{
asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */
: "+S"(input), "+D"(output)
: "d"(control_word), "b"(key), "c"(count));
}
static inline u8 *rep_xcrypt_cbc(const u8 *input, u8 *output, void *key,
u8 *iv, struct cword *control_word, int count)
{
asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */
: "+S" (input), "+D" (output), "+a" (iv)
: "d" (control_word), "b" (key), "c" (count));
return iv;
}
static void ecb_crypt_copy(const u8 *in, u8 *out, u32 *key,
struct cword *cword, int count)
{
/*
* Padlock prefetches extra data so we must provide mapped input buffers.
* Assume there are at least 16 bytes of stack already in use.
*/
u8 buf[AES_BLOCK_SIZE * (MAX_ECB_FETCH_BLOCKS - 1) + PADLOCK_ALIGNMENT - 1];
u8 *tmp = PTR_ALIGN(&buf[0], PADLOCK_ALIGNMENT);
memcpy(tmp, in, count * AES_BLOCK_SIZE);
rep_xcrypt_ecb(tmp, out, key, cword, count);
}
static u8 *cbc_crypt_copy(const u8 *in, u8 *out, u32 *key,
u8 *iv, struct cword *cword, int count)
{
/*
* Padlock prefetches extra data so we must provide mapped input buffers.
* Assume there are at least 16 bytes of stack already in use.
*/
u8 buf[AES_BLOCK_SIZE * (MAX_CBC_FETCH_BLOCKS - 1) + PADLOCK_ALIGNMENT - 1];
u8 *tmp = PTR_ALIGN(&buf[0], PADLOCK_ALIGNMENT);
memcpy(tmp, in, count * AES_BLOCK_SIZE);
return rep_xcrypt_cbc(tmp, out, key, iv, cword, count);
}
static inline void ecb_crypt(const u8 *in, u8 *out, u32 *key,
struct cword *cword, int count)
{
/* Padlock in ECB mode fetches at least ecb_fetch_bytes of data.
* We could avoid some copying here but it's probably not worth it.
*/
if (unlikely(offset_in_page(in) + ecb_fetch_bytes > PAGE_SIZE)) {
ecb_crypt_copy(in, out, key, cword, count);
return;
}
rep_xcrypt_ecb(in, out, key, cword, count);
}
static inline u8 *cbc_crypt(const u8 *in, u8 *out, u32 *key,
u8 *iv, struct cword *cword, int count)
{
/* Padlock in CBC mode fetches at least cbc_fetch_bytes of data. */
if (unlikely(offset_in_page(in) + cbc_fetch_bytes > PAGE_SIZE))
return cbc_crypt_copy(in, out, key, iv, cword, count);
return rep_xcrypt_cbc(in, out, key, iv, cword, count);
}
static inline void padlock_xcrypt_ecb(const u8 *input, u8 *output, void *key,
void *control_word, u32 count)
{
u32 initial = count & (ecb_fetch_blocks - 1);
if (count < ecb_fetch_blocks) {
ecb_crypt(input, output, key, control_word, count);
return;
}
if (initial)
asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */
: "+S"(input), "+D"(output)
: "d"(control_word), "b"(key), "c"(initial));
asm volatile (".byte 0xf3,0x0f,0xa7,0xc8" /* rep xcryptecb */
: "+S"(input), "+D"(output)
: "d"(control_word), "b"(key), "c"(count - initial));
}
static inline u8 *padlock_xcrypt_cbc(const u8 *input, u8 *output, void *key,
u8 *iv, void *control_word, u32 count)
{
u32 initial = count & (cbc_fetch_blocks - 1);
if (count < cbc_fetch_blocks)
return cbc_crypt(input, output, key, iv, control_word, count);
if (initial)
asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */
: "+S" (input), "+D" (output), "+a" (iv)
: "d" (control_word), "b" (key), "c" (initial));
asm volatile (".byte 0xf3,0x0f,0xa7,0xd0" /* rep xcryptcbc */
: "+S" (input), "+D" (output), "+a" (iv)
: "d" (control_word), "b" (key), "c" (count-initial));
return iv;
}
static void aes_encrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct aes_ctx *ctx = aes_ctx(tfm);
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() 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>
2008-08-13 20:02:26 +08:00
padlock_reset_key(&ctx->cword.encrypt);
ecb_crypt(in, out, ctx->E, &ctx->cword.encrypt, 1);
padlock_store_cword(&ctx->cword.encrypt);
}
static void aes_decrypt(struct crypto_tfm *tfm, u8 *out, const u8 *in)
{
struct aes_ctx *ctx = aes_ctx(tfm);
crypto: padlock - fix VIA PadLock instruction usage with irq_ts_save/restore() 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>
2008-08-13 20:02:26 +08:00
padlock_reset_key(&ctx->cword.encrypt);
ecb_crypt(in, out, ctx->D, &ctx->cword.decrypt, 1);
padlock_store_cword(&ctx->cword.encrypt);
}
static struct crypto_alg aes_alg = {
.cra_name = "aes",
.cra_driver_name = "aes-padlock",
.cra_priority = PADLOCK_CRA_PRIORITY,
.cra_flags = CRYPTO_ALG_TYPE_CIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct aes_ctx),
.cra_alignmask = PADLOCK_ALIGNMENT - 1,
.cra_module = THIS_MODULE,
.cra_u = {
.cipher = {
.cia_min_keysize = AES_MIN_KEY_SIZE,
.cia_max_keysize = AES_MAX_KEY_SIZE,
.cia_setkey = aes_set_key,
.cia_encrypt = aes_encrypt,
.cia_decrypt = aes_decrypt,
}
}
};
static int ecb_aes_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
padlock_reset_key(&ctx->cword.encrypt);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while ((nbytes = walk.nbytes)) {
padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr,
ctx->E, &ctx->cword.encrypt,
nbytes / AES_BLOCK_SIZE);
nbytes &= AES_BLOCK_SIZE - 1;
err = blkcipher_walk_done(desc, &walk, nbytes);
}
padlock_store_cword(&ctx->cword.encrypt);
return err;
}
static int ecb_aes_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
padlock_reset_key(&ctx->cword.decrypt);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while ((nbytes = walk.nbytes)) {
padlock_xcrypt_ecb(walk.src.virt.addr, walk.dst.virt.addr,
ctx->D, &ctx->cword.decrypt,
nbytes / AES_BLOCK_SIZE);
nbytes &= AES_BLOCK_SIZE - 1;
err = blkcipher_walk_done(desc, &walk, nbytes);
}
padlock_store_cword(&ctx->cword.encrypt);
return err;
}
static struct crypto_alg ecb_aes_alg = {
.cra_name = "ecb(aes)",
.cra_driver_name = "ecb-aes-padlock",
.cra_priority = PADLOCK_COMPOSITE_PRIORITY,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct aes_ctx),
.cra_alignmask = PADLOCK_ALIGNMENT - 1,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_u = {
.blkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.setkey = aes_set_key,
.encrypt = ecb_aes_encrypt,
.decrypt = ecb_aes_decrypt,
}
}
};
static int cbc_aes_encrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
padlock_reset_key(&ctx->cword.encrypt);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while ((nbytes = walk.nbytes)) {
u8 *iv = padlock_xcrypt_cbc(walk.src.virt.addr,
walk.dst.virt.addr, ctx->E,
walk.iv, &ctx->cword.encrypt,
nbytes / AES_BLOCK_SIZE);
memcpy(walk.iv, iv, AES_BLOCK_SIZE);
nbytes &= AES_BLOCK_SIZE - 1;
err = blkcipher_walk_done(desc, &walk, nbytes);
}
padlock_store_cword(&ctx->cword.decrypt);
return err;
}
static int cbc_aes_decrypt(struct blkcipher_desc *desc,
struct scatterlist *dst, struct scatterlist *src,
unsigned int nbytes)
{
struct aes_ctx *ctx = blk_aes_ctx(desc->tfm);
struct blkcipher_walk walk;
int err;
padlock_reset_key(&ctx->cword.encrypt);
blkcipher_walk_init(&walk, dst, src, nbytes);
err = blkcipher_walk_virt(desc, &walk);
while ((nbytes = walk.nbytes)) {
padlock_xcrypt_cbc(walk.src.virt.addr, walk.dst.virt.addr,
ctx->D, walk.iv, &ctx->cword.decrypt,
nbytes / AES_BLOCK_SIZE);
nbytes &= AES_BLOCK_SIZE - 1;
err = blkcipher_walk_done(desc, &walk, nbytes);
}
padlock_store_cword(&ctx->cword.encrypt);
return err;
}
static struct crypto_alg cbc_aes_alg = {
.cra_name = "cbc(aes)",
.cra_driver_name = "cbc-aes-padlock",
.cra_priority = PADLOCK_COMPOSITE_PRIORITY,
.cra_flags = CRYPTO_ALG_TYPE_BLKCIPHER,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct aes_ctx),
.cra_alignmask = PADLOCK_ALIGNMENT - 1,
.cra_type = &crypto_blkcipher_type,
.cra_module = THIS_MODULE,
.cra_u = {
.blkcipher = {
.min_keysize = AES_MIN_KEY_SIZE,
.max_keysize = AES_MAX_KEY_SIZE,
.ivsize = AES_BLOCK_SIZE,
.setkey = aes_set_key,
.encrypt = cbc_aes_encrypt,
.decrypt = cbc_aes_decrypt,
}
}
};
static const struct x86_cpu_id padlock_cpu_id[] = {
X86_FEATURE_MATCH(X86_FEATURE_XCRYPT),
{}
};
MODULE_DEVICE_TABLE(x86cpu, padlock_cpu_id);
static int __init padlock_init(void)
{
int ret;
struct cpuinfo_x86 *c = &cpu_data(0);
if (!x86_match_cpu(padlock_cpu_id))
return -ENODEV;
if (!boot_cpu_has(X86_FEATURE_XCRYPT_EN)) {
printk(KERN_NOTICE PFX "VIA PadLock detected, but not enabled. Hmm, strange...\n");
return -ENODEV;
}
if ((ret = crypto_register_alg(&aes_alg)))
goto aes_err;
if ((ret = crypto_register_alg(&ecb_aes_alg)))
goto ecb_aes_err;
if ((ret = crypto_register_alg(&cbc_aes_alg)))
goto cbc_aes_err;
printk(KERN_NOTICE PFX "Using VIA PadLock ACE for AES algorithm.\n");
if (c->x86 == 6 && c->x86_model == 15 && c->x86_stepping == 2) {
ecb_fetch_blocks = MAX_ECB_FETCH_BLOCKS;
cbc_fetch_blocks = MAX_CBC_FETCH_BLOCKS;
printk(KERN_NOTICE PFX "VIA Nano stepping 2 detected: enabling workaround.\n");
}
out:
return ret;
cbc_aes_err:
crypto_unregister_alg(&ecb_aes_alg);
ecb_aes_err:
crypto_unregister_alg(&aes_alg);
aes_err:
printk(KERN_ERR PFX "VIA PadLock AES initialization failed.\n");
goto out;
}
static void __exit padlock_fini(void)
{
crypto_unregister_alg(&cbc_aes_alg);
crypto_unregister_alg(&ecb_aes_alg);
crypto_unregister_alg(&aes_alg);
}
module_init(padlock_init);
module_exit(padlock_fini);
MODULE_DESCRIPTION("VIA PadLock AES algorithm support");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Michal Ludvig");
MODULE_ALIAS_CRYPTO("aes");