MFC r282209:

Emulate the 'bit test' instruction.

MFC r282259:
Re-implement RTC current time calculation to eliminate the possibility of
losing time.

MFC r282281:
Advertise the MTRR feature via CPUID and emulate the minimal set of MTRR MSRs.

MFC r282284:
When an instruction cannot be decoded just return to userspace so bhyve(8)
can dump the instruction bytes.

MFC r282287:
Don't require <sys/cpuset.h> to be always included before <machine/vmm.h>.

MFC r282296:
Emulate MSR_SYSCFG which is accessed by Linux on AMD cpus when MTRRs are
enabled.

MFC r282301:
Relax limits when transitioning a vector from the IRR to the ISR and also
when extinguishing it from the ISR in response to an EOI.

MFC r282335:
Advertise an additional memory BAR in the "dummy" device emulation.

MFC r282336:
Emulate machine check related MSRs to allow guest OSes like Windows to boot.

MFC r282351:
Don't advertise the Intel SMX capability to the guest.

MFC r282407:
Emulate the 'CMP r/m8, imm8' instruction.

MFC r282519:
Add macros for AMD-specific bits in MSR_EFER: LMSLE, FFXSR and TCE.

MFC r282520:
Emulate guest writes to EFER_MSR properly.

MFC r282558:
Deprecate the 3-way return values from vm_gla2gpa() and vm_copy_setup().

MFC r282571:
Check 'td_owepreempt' and yield the vcpu thread if it is set.

MFC r282595:
Allow byte reads of AHCI registers.

MFC r282784:
Handling indirect descriptors is a capability of the host and not one that
needs to be negotiated. Use the host capabilities field and not the negotiated
field when verifying that indirect descriptors are supported.

MFC r282788:
Allow configuration of the sector size advertised to the guest.

MFC r282865:
Set the subvendor field in config space to the vendor ID. This is required
by the Windows virtio drivers to correctly match a device.

MFC r282922:
Bump the size of the blockif scatter-gather list to 67.

MFC r283075:
Fix off-by-one in array index bounds check. bhyveload would allow you to
create 33 entries on an array that only has 32 slots

MFC r283168:
Temporarily revert r282922 which bumped the max descriptors.

MFC r283255:
Emulate the "CMP r/m, reg" instruction (opcode 39H).

MFC r283256:
Add an option "--get-vmcs-exit-inst-length" to display the instruction length
of the instruction that caused the VM-exit.

MFC r283264:
Change the header type of the emulated host-bridge from type 1 to type 0.

MFC r283293:
Don't rely on the 'VM-exit instruction length' field in the VMCS to always
have an accurate length on an EPT violation.

MFC r283299:
Remove bogus verification of instruction length after instruction decode.

MFC r283308:
Exceptions don't deliver an error code in real mode.

MFC r283657:
Fix non-deterministic delays when accessing a vcpu that was in "running" or
"sleeping" state.

MFC r283973:
Use tunable 'hw.vmm.svm.features' to disable specific SVM features even
though they might be available in hardware. Use tunable 'hw.vmm.svm.num_asids'
to limit the number of ASIDs used by the hypervisor.

MFC r284046:
Fix regression in 'verify_gla()' with the RIP-relative addressing mode.

MFC r284174:
Support guest writes to the TSC by enabling the "use TSC offsetting"
execution control.

1 files changed, 58 insertions, 16 deletions

diff --git a/usr.sbin/bhyve/block_if.c b/usr.sbin/bhyve/block_if.c
index bcb1617..ef8e11e 100644
--- a/usr.sbin/bhyve/block_if.c
+++ b/usr.sbin/bhyve/block_if.c
@@ -392,16 +392,18 @@ blockif_open(const char *optstr, const char *ident)
 {
 	char tname[MAXCOMLEN + 1];
 	char name[MAXPATHLEN];
-	char *nopt, *xopts;
+	char *nopt, *xopts, *cp;
 	struct blockif_ctxt *bc;
 	struct stat sbuf;
 	struct diocgattr_arg arg;
 	off_t size, psectsz, psectoff;
 	int extra, fd, i, sectsz;
-	int nocache, sync, ro, candelete, geom;
+	int nocache, sync, ro, candelete, geom, ssopt, pssopt;
 
 	pthread_once(&blockif_once, blockif_init);
 
+	fd = -1;
+	ssopt = 0;
 	nocache = 0;
 	sync = 0;
 	ro = 0;
@@ -410,16 +412,25 @@ blockif_open(const char *optstr, const char *ident)
 	 * The first element in the optstring is always a pathname.
 	 * Optional elements follow
 	 */
-	nopt = strdup(optstr);
-	for (xopts = strtok(nopt, ",");
-	     xopts != NULL;
-	     xopts = strtok(NULL, ",")) {
-		if (!strcmp(xopts, "nocache"))
+	nopt = xopts = strdup(optstr);
+	while (xopts != NULL) {
+		cp = strsep(&xopts, ",");
+		if (cp == nopt)		/* file or device pathname */
+			continue;
+		else if (!strcmp(cp, "nocache"))
 			nocache = 1;
-		else if (!strcmp(xopts, "sync"))
+		else if (!strcmp(cp, "sync") || !strcmp(cp, "direct"))
 			sync = 1;
-		else if (!strcmp(xopts, "ro"))
+		else if (!strcmp(cp, "ro"))
 			ro = 1;
+		else if (sscanf(cp, "sectorsize=%d/%d", &ssopt, &pssopt) == 2)
+			;
+		else if (sscanf(cp, "sectorsize=%d", &ssopt) == 1)
+			pssopt = ssopt;
+		else {
+			fprintf(stderr, "Invalid device option \"%s\"\n", cp);
+			goto err;
+		}
 	}
 
 	extra = 0;
@@ -437,13 +448,12 @@ blockif_open(const char *optstr, const char *ident)
 
 	if (fd < 0) {
 		perror("Could not open backing file");
-		return (NULL);
+		goto err;
 	}
 
         if (fstat(fd, &sbuf) < 0) {
                 perror("Could not stat backing file");
-                close(fd);
-                return (NULL);
+		goto err;
         }
 
         /*
@@ -457,8 +467,7 @@ blockif_open(const char *optstr, const char *ident)
 		if (ioctl(fd, DIOCGMEDIASIZE, &size) < 0 ||
 		    ioctl(fd, DIOCGSECTORSIZE, &sectsz)) {
 			perror("Could not fetch dev blk/sector size");
-			close(fd);
-			return (NULL);
+			goto err;
 		}
 		assert(size != 0);
 		assert(sectsz != 0);
@@ -473,10 +482,39 @@ blockif_open(const char *optstr, const char *ident)
 	} else
 		psectsz = sbuf.st_blksize;
 
+	if (ssopt != 0) {
+		if (!powerof2(ssopt) || !powerof2(pssopt) || ssopt < 512 ||
+		    ssopt > pssopt) {
+			fprintf(stderr, "Invalid sector size %d/%d\n",
+			    ssopt, pssopt);
+			goto err;
+		}
+
+		/*
+		 * Some backend drivers (e.g. cd0, ada0) require that the I/O
+		 * size be a multiple of the device's sector size.
+		 *
+		 * Validate that the emulated sector size complies with this
+		 * requirement.
+		 */
+		if (S_ISCHR(sbuf.st_mode)) {
+			if (ssopt < sectsz || (ssopt % sectsz) != 0) {
+				fprintf(stderr, "Sector size %d incompatible "
+				    "with underlying device sector size %d\n",
+				    ssopt, sectsz);
+				goto err;
+			}
+		}
+
+		sectsz = ssopt;
+		psectsz = pssopt;
+		psectoff = 0;
+	}
+
 	bc = calloc(1, sizeof(struct blockif_ctxt));
 	if (bc == NULL) {
-		close(fd);
-		return (NULL);
+		perror("calloc");
+		goto err;
 	}
 
 	bc->bc_magic = BLOCKIF_SIG;
@@ -506,6 +544,10 @@ blockif_open(const char *optstr, const char *ident)
 	}
 
 	return (bc);
+err:
+	if (fd >= 0)
+		close(fd);
+	return (NULL);
 }
 
 static int