Re: Call for testers: FPU changes

[Kostik Belousov]

On Tue, Nov 16, 2010 at 08:46:23PM -0500, Mike Tancsa wrote:
> On 11/16/2010 5:19 PM, Kostik Belousov wrote:
> > Would your conclusion be that the patch seems to increase the throughput
> > of the aesni(4) ?
> > 
> > I think that on small-sized blocks, when using aesni(4), the dominating
> > factor is the copying/copyout of the data to/from the kernel address
> > space. Still would be interesting to compare the full output
> > of "openssl speed" on aesni(4) with and without the patch I posted.
> 
> Hi,
>       There does seem to be some improvement on large blocks.  But there are
> some freakishly fast times. On other sizes, there is no difference in
> speed it would seem
> 
> I did 20 runs. Updated stats at http://www.tancsa.com/fpu.html

Thank you. Indeed, I think that the test units are too small so that
random system events can cause the variation. Nonetheless, patch seems
to help, so I committed it.

Meantime, the similar change may be beneficial for padlock(4) too.
f you are going to test it, please note that most likely, openssl padlock
engine does not use padlock(4), I do not know for sure.

diff --git a/sys/crypto/via/padlock.c b/sys/crypto/via/padlock.c
index 77e059b..ba63093 100644
--- a/sys/crypto/via/padlock.c
+++ b/sys/crypto/via/padlock.c
@@ -170,7 +170,7 @@ padlock_newsession(device_t dev, uint32_t *sidp, struct 
cryptoini *cri)
        struct padlock_session *ses = NULL;
        struct cryptoini *encini, *macini;
        struct thread *td;
-       int error;
+       int error, saved_ctx;
 
        if (sidp == NULL || cri == NULL)
                return (EINVAL);
@@ -238,10 +238,18 @@ padlock_newsession(device_t dev, uint32_t *sidp, struct 
cryptoini *cri)
 
        if (macini != NULL) {
                td = curthread;
-               error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+               if (!is_fpu_kern_thread(0)) {
+                       error = fpu_kern_enter(td, &ses->ses_fpu_ctx,
+                           FPU_KERN_NORMAL);
+                       saved_ctx = 1;
+               } else {
+                       error = 0;
+                       saved_ctx = 0;
+               }
                if (error == 0) {
                        error = padlock_hash_setup(ses, macini);
-                       fpu_kern_leave(td, &ses->ses_fpu_ctx);
+                       if (saved_ctx)
+                               fpu_kern_leave(td, &ses->ses_fpu_ctx);
                }
                if (error != 0) {
                        padlock_freesession_one(sc, ses, 0);
diff --git a/sys/crypto/via/padlock_cipher.c b/sys/crypto/via/padlock_cipher.c
index 0ae26c8..1456ddf 100644
--- a/sys/crypto/via/padlock_cipher.c
+++ b/sys/crypto/via/padlock_cipher.c
@@ -205,7 +205,7 @@ padlock_cipher_process(struct padlock_session *ses, struct 
cryptodesc *enccrd,
        struct thread *td;
        u_char *buf, *abuf;
        uint32_t *key;
-       int allocated, error;
+       int allocated, error, saved_ctx;
 
        buf = padlock_cipher_alloc(enccrd, crp, &allocated);
        if (buf == NULL)
@@ -250,14 +250,21 @@ padlock_cipher_process(struct padlock_session *ses, 
struct cryptodesc *enccrd,
        }
 
        td = curthread;
-       error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+       if (!is_fpu_kern_thread(0)) {
+               error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+               saved_ctx = 1;
+       } else {
+               error = 0;
+               saved_ctx = 0;
+       }
        if (error != 0)
                goto out;
 
        padlock_cbc(abuf, abuf, enccrd->crd_len / AES_BLOCK_LEN, key, cw,
            ses->ses_iv);
 
-       fpu_kern_leave(td, &ses->ses_fpu_ctx);
+       if (saved_ctx)
+               fpu_kern_leave(td, &ses->ses_fpu_ctx);
 
        if (allocated) {
                crypto_copyback(crp->crp_flags, crp->crp_buf, enccrd->crd_skip,
diff --git a/sys/crypto/via/padlock_hash.c b/sys/crypto/via/padlock_hash.c
index 58c58b2..0fe182b 100644
--- a/sys/crypto/via/padlock_hash.c
+++ b/sys/crypto/via/padlock_hash.c
@@ -366,17 +366,24 @@ padlock_hash_process(struct padlock_session *ses, struct 
cryptodesc *maccrd,
     struct cryptop *crp)
 {
        struct thread *td;
-       int error;
+       int error, saved_ctx;
 
        td = curthread;
-       error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+       if (!is_fpu_kern_thread(0)) {
+               error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+               saved_ctx = 1;
+       } else {
+               error = 0;
+               saved_ctx = 0;
+       }
        if (error != 0)
                return (error);
        if ((maccrd->crd_flags & CRD_F_KEY_EXPLICIT) != 0)
                padlock_hash_key_setup(ses, maccrd->crd_key, maccrd->crd_klen);
 
        error = padlock_authcompute(ses, maccrd, crp->crp_buf, crp->crp_flags);
-       fpu_kern_leave(td, &ses->ses_fpu_ctx);
+       if (saved_ctx)
+               fpu_kern_leave(td, &ses->ses_fpu_ctx);
        return (error);
 }
 

pgpIvqSGwXYtX.pgp
Description: PGP signature