Use the fpu_kern_enter() interface to properly separate usermode FPU

context from in-kernel execution of padlock instructions and to handle
spurious FPUDNA exceptions that sometime are raised when doing padlock
calculations.

Globally mark crypto(9) kthread as using FPU.

Reviewed by:	pjd
Hardware provided by:	Sentex Communications
Tested by:	  pho
PR:    amd64/135014
MFC after:    1 month

sys/crypto/via/padlock.c

@@ -169,6 +169,7 @@ padlock_newsession(device_t dev, uint32_t *sidp, struct cryptoini *cri)
 	struct padlock_softc *sc = device_get_softc(dev);
 	struct padlock_session *ses = NULL;
 	struct cryptoini *encini, *macini;
+	struct thread *td;
 	int error;
 
 	if (sidp == NULL || cri == NULL)
@@ -236,7 +237,12 @@ padlock_newsession(device_t dev, uint32_t *sidp, struct cryptoini *cri)
 	}
 
 	if (macini != NULL) {
-		error = padlock_hash_setup(ses, macini);
+		td = curthread;
+		error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+		if (error == 0) {
+			error = padlock_hash_setup(ses, macini);
+			fpu_kern_leave(td, &ses->ses_fpu_ctx);
+		}
 		if (error != 0) {
 			padlock_freesession_one(sc, ses, 0);
 			return (error);

sys/crypto/via/padlock.h

@@ -32,6 +32,12 @@
 #include <opencrypto/cryptodev.h>
 #include <crypto/rijndael/rijndael.h>
 
+#if defined(__i386__)
+#include <machine/npx.h>
+#elif defined(__amd64__)
+#include <machine/fpu.h>
+#endif
+
 union padlock_cw {
 	uint64_t raw;
 	struct {
@@ -70,6 +76,7 @@ struct padlock_session {
 	int		ses_used;
 	uint32_t	ses_id;
 	TAILQ_ENTRY(padlock_session) ses_next;
+	struct fpu_kern_ctx ses_fpu_ctx;
 };
 
 #define	PADLOCK_ALIGN(p)	(void *)(roundup2((uintptr_t)(p), 16))

sys/crypto/via/padlock_cipher.c

@@ -53,6 +53,7 @@ __FBSDID("$FreeBSD$");
 #include <sys/module.h>
 #include <sys/malloc.h>
 #include <sys/libkern.h>
+#include <sys/pcpu.h>
 #include <sys/uio.h>
 
 #include <opencrypto/cryptodev.h>
@@ -201,9 +202,10 @@ padlock_cipher_process(struct padlock_session *ses, struct cryptodesc *enccrd,
     struct cryptop *crp)
 {
 	union padlock_cw *cw;
+	struct thread *td;
 	u_char *buf, *abuf;
 	uint32_t *key;
-	int allocated;
+	int allocated, error;
 
 	buf = padlock_cipher_alloc(enccrd, crp, &allocated);
 	if (buf == NULL)
@@ -247,9 +249,16 @@ padlock_cipher_process(struct padlock_session *ses, struct cryptodesc *enccrd,
 		    enccrd->crd_len, abuf);
 	}
 
+	td = curthread;
+	error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+	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 (allocated) {
 		crypto_copyback(crp->crp_flags, crp->crp_buf, enccrd->crd_skip,
 		    enccrd->crd_len, abuf);
@@ -262,9 +271,10 @@ padlock_cipher_process(struct padlock_session *ses, struct cryptodesc *enccrd,
 		    AES_BLOCK_LEN, ses->ses_iv);
 	}
 
+ out:
 	if (allocated) {
 		bzero(buf, enccrd->crd_len + 16);
 		free(buf, M_PADLOCK);
 	}
-	return (0);
+	return (error);
 }

sys/crypto/via/padlock_hash.c

@@ -34,12 +34,14 @@ __FBSDID("$FreeBSD$");
 #include <sys/malloc.h>
 #include <sys/libkern.h>
 #include <sys/endian.h>
+#include <sys/pcpu.h>
 #if defined(__amd64__) || (defined(__i386__) && !defined(PC98))
 #include <machine/cpufunc.h>
 #include <machine/cputypes.h>
 #include <machine/md_var.h>
 #include <machine/specialreg.h>
 #endif
+#include <machine/pcb.h>
 
 #include <opencrypto/cryptodev.h>
 #include <opencrypto/cryptosoft.h> /* for hmac_ipad_buffer and hmac_opad_buffer */
@@ -363,12 +365,18 @@ int
 padlock_hash_process(struct padlock_session *ses, struct cryptodesc *maccrd,
     struct cryptop *crp)
 {
+	struct thread *td;
 	int error;
 
+	td = curthread;
+	error = fpu_kern_enter(td, &ses->ses_fpu_ctx, FPU_KERN_NORMAL);
+	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);
 	return (error);
 }
 

sys/dev/random/nehemiah.c

@@ -35,6 +35,8 @@ __FBSDID("$FreeBSD$");
 #include <sys/selinfo.h>
 #include <sys/systm.h>
 
+#include <machine/pcb.h>
+
 #include <dev/random/randomdev.h>
 
 #define RANDOM_BLOCK_SIZE	256
@@ -82,6 +84,8 @@ static uint8_t out[RANDOM_BLOCK_SIZE+7]	__aligned(16);
 
 static union VIA_ACE_CW acw		__aligned(16);
 
+static struct fpu_kern_ctx fpu_ctx_save;
+
 static struct mtx random_nehemiah_mtx;
 
 /* ARGSUSED */
@@ -142,11 +146,16 @@ random_nehemiah_deinit(void)
 static int
 random_nehemiah_read(void *buf, int c)
 {
-	int i;
+	int i, error;
 	size_t count, ret;
 	uint8_t *p;
 
 	mtx_lock(&random_nehemiah_mtx);
+	error = fpu_kern_enter(curthread, &fpu_ctx_save, FPU_KERN_NORMAL);
+	if (error != 0) {
+		mtx_unlock(&random_nehemiah_mtx);
+		return (0);
+	}
 
 	/* Get a random AES key */
 	count = 0;
@@ -187,6 +196,7 @@ random_nehemiah_read(void *buf, int c)
 	c = MIN(RANDOM_BLOCK_SIZE, c);
 	memcpy(buf, out, (size_t)c);
 
+	fpu_kern_leave(curthread, &fpu_ctx_save);
 	mtx_unlock(&random_nehemiah_mtx);
 	return (c);
 }

sys/opencrypto/crypto.c

@@ -82,6 +82,10 @@ __FBSDID("$FreeBSD$");
 #include <sys/bus.h>
 #include "cryptodev_if.h"
 
+#if defined(__i386__) || defined(__amd64__)
+#include <machine/pcb.h>
+#endif
+
 SDT_PROVIDER_DEFINE(opencrypto);
 
 /*
@@ -1241,6 +1245,10 @@ crypto_proc(void)
 	u_int32_t hid;
 	int result, hint;
 
+#if defined(__i386__) || defined(__amd64__)
+	fpu_kern_thread(FPU_KERN_NORMAL);
+#endif
+
 	CRYPTO_Q_LOCK();
 	for (;;) {
 		/*