Hopefully last target-arm queue before softfreeze; this one's largest part is the remainder of the SVE patches, but there are a selection of other minor things too. thanks -- PMM The following changes since commit 109b25045b3651f9c5d02c3766c0b3ff63e6d193: Merge remote-tracking branch 'remotes/bonzini/tags/for-upstream' into staging (2018-06-29 12:30:29 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180629 for you to fetch changes up to 802abf4024d23e48d45373ac3f2b580124b54b47: target/arm: Add ID_ISAR6 (2018-06-29 15:30:54 +0100) ---------------------------------------------------------------- target-arm queue: * last of the SVE patches; SVE is now enabled for aarch64 linux-user * sd: Don't trace SDRequest crc field (coverity bugfix) * target/arm: Mark PMINTENSET accesses as possibly doing IO * clean up v7VE feature bit handling * i.mx7d: minor cleanups * target/arm: support reading of CNT[VCT|FRQ]_EL0 from user-space * target/arm: Implement ARMv8.2-DotProd * virt: add addresses to dt node names (which stops dtc from complaining that they're not correctly named) * cleanups: replace error_setg(&error_fatal) by error_report() + exit() ---------------------------------------------------------------- Aaron Lindsay (3): target/arm: Add ARM_FEATURE_V7VE for v7 Virtualization Extensions target/arm: Remove redundant DIV detection for KVM target/arm: Mark PMINTENSET accesses as possibly doing IO Alex Bennée (1): target/arm: support reading of CNT[VCT|FRQ]_EL0 from user-space Eric Auger (3): device_tree: Add qemu_fdt_node_unit_path hw/arm/virt: Silence dtc /intc warnings hw/arm/virt: Silence dtc /memory warning Jean-Christophe Dubois (3): i.mx7d: Remove unused header files i.mx7d: Change SRC unimplemented device name from sdma to src i.mx7d: Change IRQ number type from hwaddr to int Peter Maydell (1): sd: Don't trace SDRequest crc field Philippe Mathieu-Daudé (4): hw/block/fdc: Replace error_setg(&error_abort) by assert() hw/arm/sysbus-fdt: Replace error_setg(&error_fatal) by error_report() + exit() device_tree: Replace error_setg(&error_fatal) by error_report() + exit() sdcard: Use the ldst API Richard Henderson (40): target/arm: Implement SVE Memory Contiguous Load Group target/arm: Implement SVE Contiguous Load, first-fault and no-fault target/arm: Implement SVE Memory Contiguous Store Group target/arm: Implement SVE load and broadcast quadword target/arm: Implement SVE integer convert to floating-point target/arm: Implement SVE floating-point arithmetic (predicated) target/arm: Implement SVE FP Multiply-Add Group target/arm: Implement SVE Floating Point Accumulating Reduction Group target/arm: Implement SVE load and broadcast element target/arm: Implement SVE store vector/predicate register target/arm: Implement SVE scatter stores target/arm: Implement SVE prefetches target/arm: Implement SVE gather loads target/arm: Implement SVE first-fault gather loads target/arm: Implement SVE scatter store vector immediate target/arm: Implement SVE floating-point compare vectors target/arm: Implement SVE floating-point arithmetic with immediate target/arm: Implement SVE Floating Point Multiply Indexed Group target/arm: Implement SVE FP Fast Reduction Group target/arm: Implement SVE Floating Point Unary Operations - Unpredicated Group target/arm: Implement SVE FP Compare with Zero Group target/arm: Implement SVE floating-point trig multiply-add coefficient target/arm: Implement SVE floating-point convert precision target/arm: Implement SVE floating-point convert to integer target/arm: Implement SVE floating-point round to integral value target/arm: Implement SVE floating-point unary operations target/arm: Implement SVE MOVPRFX target/arm: Implement SVE floating-point complex add target/arm: Implement SVE fp complex multiply add target/arm: Pass index to AdvSIMD FCMLA (indexed) target/arm: Implement SVE fp complex multiply add (indexed) target/arm: Implement SVE dot product (vectors) target/arm: Implement SVE dot product (indexed) target/arm: Enable SVE for aarch64-linux-user target/arm: Implement ARMv8.2-DotProd target/arm: Fix SVE signed division vs x86 overflow exception target/arm: Fix SVE system register access checks target/arm: Prune a57 features from max target/arm: Prune a15 features from max target/arm: Add ID_ISAR6 include/sysemu/device_tree.h | 16 + target/arm/cpu.h | 3 + target/arm/helper-sve.h | 682 +++++++++++++++ target/arm/helper.h | 44 +- device_tree.c | 78 +- hw/arm/boot.c | 41 +- hw/arm/fsl-imx7.c | 8 +- hw/arm/mcimx7d-sabre.c | 2 - hw/arm/sysbus-fdt.c | 53 +- hw/arm/virt.c | 70 +- hw/block/fdc.c | 9 +- hw/sd/bcm2835_sdhost.c | 13 +- hw/sd/core.c | 2 +- hw/sd/milkymist-memcard.c | 3 +- hw/sd/omap_mmc.c | 6 +- hw/sd/pl181.c | 11 +- hw/sd/sdhci.c | 15 +- hw/sd/ssi-sd.c | 6 +- linux-user/elfload.c | 2 + target/arm/cpu.c | 36 +- target/arm/cpu64.c | 13 +- target/arm/helper.c | 44 +- target/arm/kvm32.c | 27 +- target/arm/sve_helper.c | 1875 +++++++++++++++++++++++++++++++++++++++++- target/arm/translate-a64.c | 62 +- target/arm/translate-sve.c | 1688 ++++++++++++++++++++++++++++++++++++- target/arm/translate.c | 102 ++- target/arm/vec_helper.c | 311 ++++++- hw/sd/trace-events | 2 +- target/arm/sve.decode | 427 ++++++++++ 30 files changed, 5394 insertions(+), 257 deletions(-) From: Philippe Mathieu-Daudé <f4bug@amsat.org> Use assert() instead of error_setg(&error_abort), as suggested by the "qapi/error.h" documentation: Please don't error_setg(&error_fatal, ...), use error_report() and exit(), because that's more obvious. Likewise, don't error_setg(&error_abort, ...), use assert(). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: John Snow <jsnow@redhat.com> Message-id: 20180625165749.3910-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/fdc.c | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) diff --git a/hw/block/fdc.c b/hw/block/fdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/fdc.c +++ b/hw/block/fdc.c @@ -XXX,XX +XXX,XX @@ static int pick_geometry(FDrive *drv) nb_sectors, FloppyDriveType_str(parse->drive)); } + assert(type_match != -1 && "misconfigured fd_format"); match = type_match; } - - /* No match of any kind found -- fd_format is misconfigured, abort. */ - if (match == -1) { - error_setg(&error_abort, "No candidate geometries present in table " - " for floppy drive type '%s'", - FloppyDriveType_str(drv->drive)); - } - parse = &(fd_formats[match]); out: -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Use error_report() + exit() instead of error_setg(&error_fatal), as suggested by the "qapi/error.h" documentation: Please don't error_setg(&error_fatal, ...), use error_report() and exit(), because that's more obvious. This fixes CID 1352173: "Passing null pointer dt_name to qemu_fdt_node_path, which dereferences it." And this also fixes: hw/arm/sysbus-fdt.c:322:9: warning: Array access (from variable 'node_path') results in a null pointer dereference if (node_path[1]) { ^~~~~~~~~~~~ Fixes: Coverity CID 1352173 (Dereference after null check) Suggested-by: Eric Blake <eblake@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 20180625165749.3910-3-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sysbus-fdt.c | 53 +++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 23 deletions(-) diff --git a/hw/arm/sysbus-fdt.c b/hw/arm/sysbus-fdt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sysbus-fdt.c +++ b/hw/arm/sysbus-fdt.c @@ -XXX,XX +XXX,XX @@ static void copy_properties_from_host(HostProperty *props, int nb_props, r = qemu_fdt_getprop(host_fdt, node_path, props[i].name, &prop_len, - props[i].optional ? &err : &error_fatal); + &err); if (r) { qemu_fdt_setprop(guest_fdt, nodename, props[i].name, r, prop_len); } else { - if (prop_len != -FDT_ERR_NOTFOUND) { - /* optional property not returned although property exists */ - error_report_err(err); - } else { + if (props[i].optional && prop_len == -FDT_ERR_NOTFOUND) { + /* optional property does not exist */ error_free(err); + } else { + error_report_err(err); + } + if (!props[i].optional) { + /* mandatory property not found: bail out */ + exit(1); } } } @@ -XXX,XX +XXX,XX @@ static void fdt_build_clock_node(void *host_fdt, void *guest_fdt, node_offset = fdt_node_offset_by_phandle(host_fdt, host_phandle); if (node_offset <= 0) { - error_setg(&error_fatal, - "not able to locate clock handle %d in host device tree", - host_phandle); + error_report("not able to locate clock handle %d in host device tree", + host_phandle); + exit(1); } node_path = g_malloc(path_len); while ((ret = fdt_get_path(host_fdt, node_offset, node_path, path_len)) @@ -XXX,XX +XXX,XX @@ static void fdt_build_clock_node(void *host_fdt, void *guest_fdt, node_path = g_realloc(node_path, path_len); } if (ret < 0) { - error_setg(&error_fatal, - "not able to retrieve node path for clock handle %d", - host_phandle); + error_report("not able to retrieve node path for clock handle %d", + host_phandle); + exit(1); } r = qemu_fdt_getprop(host_fdt, node_path, "compatible", &prop_len, &error_fatal); if (strcmp(r, "fixed-clock")) { - error_setg(&error_fatal, - "clock handle %d is not a fixed clock", host_phandle); + error_report("clock handle %d is not a fixed clock", host_phandle); + exit(1); } nodename = strrchr(node_path, '/'); @@ -XXX,XX +XXX,XX @@ static int add_amd_xgbe_fdt_node(SysBusDevice *sbdev, void *opaque) dt_name = sysfs_to_dt_name(vbasedev->name); if (!dt_name) { - error_setg(&error_fatal, "%s incorrect sysfs device name %s", - __func__, vbasedev->name); + error_report("%s incorrect sysfs device name %s", + __func__, vbasedev->name); + exit(1); } node_path = qemu_fdt_node_path(host_fdt, dt_name, vdev->compat, &error_fatal); if (!node_path || !node_path[0]) { - error_setg(&error_fatal, "%s unable to retrieve node path for %s/%s", - __func__, dt_name, vdev->compat); + error_report("%s unable to retrieve node path for %s/%s", + __func__, dt_name, vdev->compat); + exit(1); } if (node_path[1]) { - error_setg(&error_fatal, "%s more than one node matching %s/%s!", - __func__, dt_name, vdev->compat); + error_report("%s more than one node matching %s/%s!", + __func__, dt_name, vdev->compat); + exit(1); } g_free(dt_name); if (vbasedev->num_regions != 5) { - error_setg(&error_fatal, "%s Does the host dt node combine XGBE/PHY?", - __func__); + error_report("%s Does the host dt node combine XGBE/PHY?", __func__); + exit(1); } /* generate nodes for DMA_CLK and PTP_CLK */ r = qemu_fdt_getprop(host_fdt, node_path[0], "clocks", &prop_len, &error_fatal); if (prop_len != 8) { - error_setg(&error_fatal, "%s clocks property should contain 2 handles", - __func__); + error_report("%s clocks property should contain 2 handles", __func__); + exit(1); } host_clock_phandles = (uint32_t *)r; guest_clock_phandles[0] = qemu_fdt_alloc_phandle(guest_fdt); -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Use error_report() + exit() instead of error_setg(&error_fatal), as suggested by the "qapi/error.h" documentation: Please don't error_setg(&error_fatal, ...), use error_report() and exit(), because that's more obvious. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Markus Armbruster <armbru@redhat.com> Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Message-id: 20180625165749.3910-4-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- device_tree.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ static void read_fstree(void *fdt, const char *dirname) const char *parent_node; if (strstr(dirname, root_dir) != dirname) { - error_setg(&error_fatal, "%s: %s must be searched within %s", - __func__, dirname, root_dir); + error_report("%s: %s must be searched within %s", + __func__, dirname, root_dir); + exit(1); } parent_node = &dirname[strlen(SYSFS_DT_BASEDIR)]; d = opendir(dirname); if (!d) { - error_setg(&error_fatal, "%s cannot open %s", __func__, dirname); - return; + error_report("%s cannot open %s", __func__, dirname); + exit(1); } while ((de = readdir(d)) != NULL) { @@ -XXX,XX +XXX,XX @@ static void read_fstree(void *fdt, const char *dirname) tmpnam = g_strdup_printf("%s/%s", dirname, de->d_name); if (lstat(tmpnam, &st) < 0) { - error_setg(&error_fatal, "%s cannot lstat %s", __func__, tmpnam); + error_report("%s cannot lstat %s", __func__, tmpnam); + exit(1); } if (S_ISREG(st.st_mode)) { @@ -XXX,XX +XXX,XX @@ static void read_fstree(void *fdt, const char *dirname) gsize len; if (!g_file_get_contents(tmpnam, &val, &len, NULL)) { - error_setg(&error_fatal, "%s not able to extract info from %s", - __func__, tmpnam); + error_report("%s not able to extract info from %s", + __func__, tmpnam); + exit(1); } if (strlen(parent_node) > 0) { @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void) host_fdt = create_device_tree(&host_fdt_size); read_fstree(host_fdt, SYSFS_DT_BASEDIR); if (fdt_check_header(host_fdt)) { - error_setg(&error_fatal, - "%s host device tree extracted into memory is invalid", - __func__); + error_report("%s host device tree extracted into memory is invalid", + __func__); + exit(1); } return host_fdt; } -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> This helper allows to retrieve the paths of nodes whose name match node-name or node-name@unit-address patterns. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 1530044492-24921-2-git-send-email-eric.auger@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/device_tree.h | 16 +++++++++++ device_tree.c | 55 ++++++++++++++++++++++++++++++++++++ 2 files changed, 71 insertions(+) diff --git a/include/sysemu/device_tree.h b/include/sysemu/device_tree.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/device_tree.h +++ b/include/sysemu/device_tree.h @@ -XXX,XX +XXX,XX @@ void *load_device_tree_from_sysfs(void); char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, Error **errp); +/** + * qemu_fdt_node_unit_path: return the paths of nodes matching a given + * node-name, ie. node-name and node-name@unit-address + * @fdt: pointer to the dt blob + * @name: node name + * @errp: handle to an error object + * + * returns a newly allocated NULL-terminated array of node paths. + * Use g_strfreev() to free it. If one or more nodes were found, the + * array contains the path of each node and the last element equals to + * NULL. If there is no error but no matching node was found, the + * returned array contains a single element equal to NULL. If an error + * was encountered when parsing the blob, the function returns NULL + */ +char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp); + int qemu_fdt_setprop(void *fdt, const char *node_path, const char *property, const void *val, int size); int qemu_fdt_setprop_cell(void *fdt, const char *node_path, diff --git a/device_tree.c b/device_tree.c index XXXXXXX..XXXXXXX 100644 --- a/device_tree.c +++ b/device_tree.c @@ -XXX,XX +XXX,XX @@ static int findnode_nofail(void *fdt, const char *node_path) return offset; } +char **qemu_fdt_node_unit_path(void *fdt, const char *name, Error **errp) +{ + char *prefix = g_strdup_printf("%s@", name); + unsigned int path_len = 16, n = 0; + GSList *path_list = NULL, *iter; + const char *iter_name; + int offset, len, ret; + char **path_array; + + offset = fdt_next_node(fdt, -1, NULL); + + while (offset >= 0) { + iter_name = fdt_get_name(fdt, offset, &len); + if (!iter_name) { + offset = len; + break; + } + if (!strcmp(iter_name, name) || g_str_has_prefix(iter_name, prefix)) { + char *path; + + path = g_malloc(path_len); + while ((ret = fdt_get_path(fdt, offset, path, path_len)) + == -FDT_ERR_NOSPACE) { + path_len += 16; + path = g_realloc(path, path_len); + } + path_list = g_slist_prepend(path_list, path); + n++; + } + offset = fdt_next_node(fdt, offset, NULL); + } + g_free(prefix); + + if (offset < 0 && offset != -FDT_ERR_NOTFOUND) { + error_setg(errp, "%s: abort parsing dt for %s node units: %s", + __func__, name, fdt_strerror(offset)); + for (iter = path_list; iter; iter = iter->next) { + g_free(iter->data); + } + g_slist_free(path_list); + return NULL; + } + + path_array = g_new(char *, n + 1); + path_array[n--] = NULL; + + for (iter = path_list; iter; iter = iter->next) { + path_array[n--] = iter->data; + } + + g_slist_free(path_list); + + return path_array; +} + char **qemu_fdt_node_path(void *fdt, const char *name, char *compat, Error **errp) { -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> When running dtc on the guest /proc/device-tree we get the following warnings: "Warning (unit_address_vs_reg): Node <name> has a reg or ranges property, but no unit name", with name: /intc, /intc/its, /intc/v2m. Nodes should have a name in the form <name>[@<unit-address>] where unit-address is the primary address used to access the device, listed in the node's reg property. This fix seems to make dtc happy. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1530044492-24921-3-git-send-email-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 63 +++++++++++++++++++++++++++++++-------------------- 1 file changed, 39 insertions(+), 24 deletions(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_cpu_nodes(const VirtMachineState *vms) static void fdt_add_its_gic_node(VirtMachineState *vms) { + char *nodename; + vms->msi_phandle = qemu_fdt_alloc_phandle(vms->fdt); - qemu_fdt_add_subnode(vms->fdt, "/intc/its"); - qemu_fdt_setprop_string(vms->fdt, "/intc/its", "compatible", + nodename = g_strdup_printf("/intc/its@%" PRIx64, + vms->memmap[VIRT_GIC_ITS].base); + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "arm,gic-v3-its"); - qemu_fdt_setprop(vms->fdt, "/intc/its", "msi-controller", NULL, 0); - qemu_fdt_setprop_sized_cells(vms->fdt, "/intc/its", "reg", + qemu_fdt_setprop(vms->fdt, nodename, "msi-controller", NULL, 0); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, vms->memmap[VIRT_GIC_ITS].base, 2, vms->memmap[VIRT_GIC_ITS].size); - qemu_fdt_setprop_cell(vms->fdt, "/intc/its", "phandle", vms->msi_phandle); + qemu_fdt_setprop_cell(vms->fdt, nodename, "phandle", vms->msi_phandle); + g_free(nodename); } static void fdt_add_v2m_gic_node(VirtMachineState *vms) { + char *nodename; + + nodename = g_strdup_printf("/intc/v2m@%" PRIx64, + vms->memmap[VIRT_GIC_V2M].base); vms->msi_phandle = qemu_fdt_alloc_phandle(vms->fdt); - qemu_fdt_add_subnode(vms->fdt, "/intc/v2m"); - qemu_fdt_setprop_string(vms->fdt, "/intc/v2m", "compatible", + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "arm,gic-v2m-frame"); - qemu_fdt_setprop(vms->fdt, "/intc/v2m", "msi-controller", NULL, 0); - qemu_fdt_setprop_sized_cells(vms->fdt, "/intc/v2m", "reg", + qemu_fdt_setprop(vms->fdt, nodename, "msi-controller", NULL, 0); + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, vms->memmap[VIRT_GIC_V2M].base, 2, vms->memmap[VIRT_GIC_V2M].size); - qemu_fdt_setprop_cell(vms->fdt, "/intc/v2m", "phandle", vms->msi_phandle); + qemu_fdt_setprop_cell(vms->fdt, nodename, "phandle", vms->msi_phandle); + g_free(nodename); } static void fdt_add_gic_node(VirtMachineState *vms) { + char *nodename; + vms->gic_phandle = qemu_fdt_alloc_phandle(vms->fdt); qemu_fdt_setprop_cell(vms->fdt, "/", "interrupt-parent", vms->gic_phandle); - qemu_fdt_add_subnode(vms->fdt, "/intc"); - qemu_fdt_setprop_cell(vms->fdt, "/intc", "#interrupt-cells", 3); - qemu_fdt_setprop(vms->fdt, "/intc", "interrupt-controller", NULL, 0); - qemu_fdt_setprop_cell(vms->fdt, "/intc", "#address-cells", 0x2); - qemu_fdt_setprop_cell(vms->fdt, "/intc", "#size-cells", 0x2); - qemu_fdt_setprop(vms->fdt, "/intc", "ranges", NULL, 0); + nodename = g_strdup_printf("/intc@%" PRIx64, + vms->memmap[VIRT_GIC_DIST].base); + qemu_fdt_add_subnode(vms->fdt, nodename); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#interrupt-cells", 3); + qemu_fdt_setprop(vms->fdt, nodename, "interrupt-controller", NULL, 0); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#address-cells", 0x2); + qemu_fdt_setprop_cell(vms->fdt, nodename, "#size-cells", 0x2); + qemu_fdt_setprop(vms->fdt, nodename, "ranges", NULL, 0); if (vms->gic_version == 3) { int nb_redist_regions = virt_gicv3_redist_region_count(vms); - qemu_fdt_setprop_string(vms->fdt, "/intc", "compatible", + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "arm,gic-v3"); - qemu_fdt_setprop_cell(vms->fdt, "/intc", + qemu_fdt_setprop_cell(vms->fdt, nodename, "#redistributor-regions", nb_redist_regions); if (nb_redist_regions == 1) { - qemu_fdt_setprop_sized_cells(vms->fdt, "/intc", "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, vms->memmap[VIRT_GIC_DIST].base, 2, vms->memmap[VIRT_GIC_DIST].size, 2, vms->memmap[VIRT_GIC_REDIST].base, 2, vms->memmap[VIRT_GIC_REDIST].size); } else { - qemu_fdt_setprop_sized_cells(vms->fdt, "/intc", "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, vms->memmap[VIRT_GIC_DIST].base, 2, vms->memmap[VIRT_GIC_DIST].size, 2, vms->memmap[VIRT_GIC_REDIST].base, @@ -XXX,XX +XXX,XX @@ static void fdt_add_gic_node(VirtMachineState *vms) } if (vms->virt) { - qemu_fdt_setprop_cells(vms->fdt, "/intc", "interrupts", + qemu_fdt_setprop_cells(vms->fdt, nodename, "interrupts", GIC_FDT_IRQ_TYPE_PPI, ARCH_GICV3_MAINT_IRQ, GIC_FDT_IRQ_FLAGS_LEVEL_HI); } } else { /* 'cortex-a15-gic' means 'GIC v2' */ - qemu_fdt_setprop_string(vms->fdt, "/intc", "compatible", + qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", "arm,cortex-a15-gic"); - qemu_fdt_setprop_sized_cells(vms->fdt, "/intc", "reg", + qemu_fdt_setprop_sized_cells(vms->fdt, nodename, "reg", 2, vms->memmap[VIRT_GIC_DIST].base, 2, vms->memmap[VIRT_GIC_DIST].size, 2, vms->memmap[VIRT_GIC_CPU].base, 2, vms->memmap[VIRT_GIC_CPU].size); } - qemu_fdt_setprop_cell(vms->fdt, "/intc", "phandle", vms->gic_phandle); + qemu_fdt_setprop_cell(vms->fdt, nodename, "phandle", vms->gic_phandle); + g_free(nodename); } static void fdt_add_pmu_nodes(const VirtMachineState *vms) -- 2.17.1 From: Eric Auger <eric.auger@redhat.com> When running dtc on the guest /proc/device-tree we get the following warning: Warning (unit_address_vs_reg): Node /memory has a reg or ranges property, but no unit name". Let's fix that by adding the unit address to the node name. We also don't create the /memory node anymore in create_fdt(). We directly create it in load_dtb. /chosen still needs to be created in create_fdt as the uart needs it. In case the user provided his own dtb, we nop all memory nodes found in root and create new one(s). Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 1530044492-24921-4-git-send-email-eric.auger@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 41 +++++++++++++++++++++++------------------ hw/arm/virt.c | 7 +------ 2 files changed, 24 insertions(+), 24 deletions(-) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, hwaddr addr_limit, AddressSpace *as) { void *fdt = NULL; - int size, rc; + int size, rc, n = 0; uint32_t acells, scells; char *nodename; unsigned int i; hwaddr mem_base, mem_len; + char **node_path; + Error *err = NULL; if (binfo->dtb_filename) { char *filename; @@ -XXX,XX +XXX,XX @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, goto fail; } + /* nop all root nodes matching /memory or /memory@unit-address */ + node_path = qemu_fdt_node_unit_path(fdt, "memory", &err); + if (err) { + error_report_err(err); + goto fail; + } + while (node_path[n]) { + if (g_str_has_prefix(node_path[n], "/memory")) { + qemu_fdt_nop_node(fdt, node_path[n]); + } + n++; + } + g_strfreev(node_path); + if (nb_numa_nodes > 0) { - /* - * Turn the /memory node created before into a NOP node, then create - * /memory@addr nodes for all numa nodes respectively. - */ - qemu_fdt_nop_node(fdt, "/memory"); mem_base = binfo->loader_start; for (i = 0; i < nb_numa_nodes; i++) { mem_len = numa_info[i].node_mem; @@ -XXX,XX +XXX,XX @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, g_free(nodename); } } else { - Error *err = NULL; + nodename = g_strdup_printf("/memory@%" PRIx64, binfo->loader_start); + qemu_fdt_add_subnode(fdt, nodename); + qemu_fdt_setprop_string(fdt, nodename, "device_type", "memory"); - rc = fdt_path_offset(fdt, "/memory"); - if (rc < 0) { - qemu_fdt_add_subnode(fdt, "/memory"); - } - - if (!qemu_fdt_getprop(fdt, "/memory", "device_type", NULL, &err)) { - qemu_fdt_setprop_string(fdt, "/memory", "device_type", "memory"); - } - - rc = qemu_fdt_setprop_sized_cells(fdt, "/memory", "reg", + rc = qemu_fdt_setprop_sized_cells(fdt, nodename, "reg", acells, binfo->loader_start, scells, binfo->ram_size); if (rc < 0) { - fprintf(stderr, "couldn't set /memory/reg\n"); + fprintf(stderr, "couldn't set %s reg\n", nodename); goto fail; } + g_free(nodename); } rc = fdt_path_offset(fdt, "/chosen"); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void create_fdt(VirtMachineState *vms) qemu_fdt_setprop_cell(fdt, "/", "#address-cells", 0x2); qemu_fdt_setprop_cell(fdt, "/", "#size-cells", 0x2); - /* - * /chosen and /memory nodes must exist for load_dtb - * to fill in necessary properties later - */ + /* /chosen must exist for load_dtb to fill in necessary properties later */ qemu_fdt_add_subnode(fdt, "/chosen"); - qemu_fdt_add_subnode(fdt, "/memory"); - qemu_fdt_setprop_string(fdt, "/memory", "device_type", "memory"); /* Clock node, for the benefit of the UART. The kernel device tree * binding documentation claims the PL011 node clock properties are -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 35 +++++++++ target/arm/sve_helper.c | 153 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 121 +++++++++++++++++++++++++++++ target/arm/sve.decode | 34 +++++++++ 4 files changed, 343 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ld1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ld1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } + +/* + * Load contiguous data, protected by a governing predicate. + */ +#define DO_LD1(NAME, FN, TYPEE, TYPEM, H) \ +static void do_##NAME(CPUARMState *env, void *vd, void *vg, \ + target_ulong addr, intptr_t oprsz, \ + uintptr_t ra) \ +{ \ + intptr_t i = 0; \ + do { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m = 0; \ + if (pg & 1) { \ + m = FN(env, addr, ra); \ + } \ + *(TYPEE *)(vd + H(i)) = m; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += sizeof(TYPEM); \ + } while (i & 15); \ + } while (i < oprsz); \ +} \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + do_##NAME(env, &env->vfp.zregs[simd_data(desc)], vg, \ + addr, simd_oprsz(desc), GETPC()); \ +} + +#define DO_LD2(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m1 = 0, m2 = 0; \ + if (pg & 1) { \ + m1 = FN(env, addr, ra); \ + m2 = FN(env, addr + sizeof(TYPEM), ra); \ + } \ + *(TYPEE *)(d1 + H(i)) = m1; \ + *(TYPEE *)(d2 + H(i)) = m2; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 2 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +#define DO_LD3(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m1 = 0, m2 = 0, m3 = 0; \ + if (pg & 1) { \ + m1 = FN(env, addr, ra); \ + m2 = FN(env, addr + sizeof(TYPEM), ra); \ + m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ + } \ + *(TYPEE *)(d1 + H(i)) = m1; \ + *(TYPEE *)(d2 + H(i)) = m2; \ + *(TYPEE *)(d3 + H(i)) = m3; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 3 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +#define DO_LD4(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ + void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m1 = 0, m2 = 0, m3 = 0, m4 = 0; \ + if (pg & 1) { \ + m1 = FN(env, addr, ra); \ + m2 = FN(env, addr + sizeof(TYPEM), ra); \ + m3 = FN(env, addr + 2 * sizeof(TYPEM), ra); \ + m4 = FN(env, addr + 3 * sizeof(TYPEM), ra); \ + } \ + *(TYPEE *)(d1 + H(i)) = m1; \ + *(TYPEE *)(d2 + H(i)) = m2; \ + *(TYPEE *)(d3 + H(i)) = m3; \ + *(TYPEE *)(d4 + H(i)) = m4; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 4 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +DO_LD1(sve_ld1bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) +DO_LD1(sve_ld1bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) +DO_LD1(sve_ld1bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) +DO_LD1(sve_ld1bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) +DO_LD1(sve_ld1bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) +DO_LD1(sve_ld1bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) + +DO_LD1(sve_ld1hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) +DO_LD1(sve_ld1hss_r, cpu_ldsw_data_ra, uint32_t, int8_t, H1_4) +DO_LD1(sve_ld1hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) +DO_LD1(sve_ld1hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) + +DO_LD1(sve_ld1sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) +DO_LD1(sve_ld1sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) + +DO_LD1(sve_ld1bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) +DO_LD2(sve_ld2bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) +DO_LD3(sve_ld3bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) +DO_LD4(sve_ld4bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) + +DO_LD1(sve_ld1hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) +DO_LD2(sve_ld2hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) +DO_LD3(sve_ld3hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) +DO_LD4(sve_ld4hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) + +DO_LD1(sve_ld1ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +DO_LD2(sve_ld2ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +DO_LD3(sve_ld3ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +DO_LD4(sve_ld4ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) + +DO_LD1(sve_ld1dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) +DO_LD2(sve_ld2dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) +DO_LD3(sve_ld3dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) +DO_LD4(sve_ld4dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) + +#undef DO_LD1 +#undef DO_LD2 +#undef DO_LD3 +#undef DO_LD4 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ typedef void gen_helper_gvec_flags_3(TCGv_i32, TCGv_ptr, TCGv_ptr, typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void gen_helper_gvec_mem(TCGv_env, TCGv_ptr, TCGv_i64, TCGv_i32); + /* * Helpers for extracting complex instruction fields. */ @@ -XXX,XX +XXX,XX @@ static inline int expand_imm_sh8u(int x) return (uint8_t)x << (x & 0x100 ? 8 : 0); } +/* Convert a 2-bit memory size (msz) to a 4-bit data type (dtype) + * with unsigned data. C.f. SVE Memory Contiguous Load Group. + */ +static inline int msz_dtype(int msz) +{ + static const uint8_t dtype[4] = { 0, 5, 10, 15 }; + return dtype[msz]; +} + /* * Include the generated decoder. */ @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a, uint32_t insn) } return true; } + +/* + *** SVE Memory - Contiguous Load Group + */ + +/* The memory mode of the dtype. */ +static const TCGMemOp dtype_mop[16] = { + MO_UB, MO_UB, MO_UB, MO_UB, + MO_SL, MO_UW, MO_UW, MO_UW, + MO_SW, MO_SW, MO_UL, MO_UL, + MO_SB, MO_SB, MO_SB, MO_Q +}; + +#define dtype_msz(x) (dtype_mop[x] & MO_SIZE) + +/* The vector element size of dtype. */ +static const uint8_t dtype_esz[16] = { + 0, 1, 2, 3, + 3, 1, 2, 3, + 3, 2, 2, 3, + 3, 2, 1, 3 +}; + +static void do_mem_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, + gen_helper_gvec_mem *fn) +{ + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr t_pg; + TCGv_i32 desc; + + /* For e.g. LD4, there are not enough arguments to pass all 4 + * registers as pointers, so encode the regno into the data field. + * For consistency, do this even for LD1. + */ + desc = tcg_const_i32(simd_desc(vsz, vsz, zt)); + t_pg = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + fn(cpu_env, t_pg, addr, desc); + + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i32(desc); +} + +static void do_ld_zpa(DisasContext *s, int zt, int pg, + TCGv_i64 addr, int dtype, int nreg) +{ + static gen_helper_gvec_mem * const fns[16][4] = { + { gen_helper_sve_ld1bb_r, gen_helper_sve_ld2bb_r, + gen_helper_sve_ld3bb_r, gen_helper_sve_ld4bb_r }, + { gen_helper_sve_ld1bhu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1sds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hh_r, gen_helper_sve_ld2hh_r, + gen_helper_sve_ld3hh_r, gen_helper_sve_ld4hh_r }, + { gen_helper_sve_ld1hsu_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1hds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1hss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1ss_r, gen_helper_sve_ld2ss_r, + gen_helper_sve_ld3ss_r, gen_helper_sve_ld4ss_r }, + { gen_helper_sve_ld1sdu_r, NULL, NULL, NULL }, + + { gen_helper_sve_ld1bds_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bss_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1bhs_r, NULL, NULL, NULL }, + { gen_helper_sve_ld1dd_r, gen_helper_sve_ld2dd_r, + gen_helper_sve_ld3dd_r, gen_helper_sve_ld4dd_r }, + }; + gen_helper_gvec_mem *fn = fns[dtype][nreg]; + + /* While there are holes in the table, they are not + * accessible via the instruction encoding. + */ + assert(fn != NULL); + do_mem_zpa(s, zt, pg, addr, fn); +} + +static bool trans_LD_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) +{ + if (a->rm == 31) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_muli_i64(addr, cpu_reg(s, a->rm), + (a->nreg + 1) << dtype_msz(a->dtype)); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + do_ld_zpa(s, a->rd, a->pg, addr, a->dtype, a->nreg); + } + return true; +} + +static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) +{ + if (sve_access_check(s)) { + int vsz = vec_full_reg_size(s); + int elements = vsz >> dtype_esz[a->dtype]; + TCGv_i64 addr = new_tmp_a64(s); + + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), + (a->imm * elements * (a->nreg + 1)) + << dtype_msz(a->dtype)); + do_ld_zpa(s, a->rd, a->pg, addr, a->dtype, a->nreg); + } + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ # Unsigned 8-bit immediate, optionally shifted left by 8. %sh8_i8u 5:9 !function=expand_imm_sh8u +# Unsigned load of msz into esz=2, represented as a dtype. +%msz_dtype 23:2 !function=msz_dtype + # Either a copy of rd (at bit 0), or a different source # as propagated via the MOVPRFX instruction. %reg_movprfx 0:5 @@ -XXX,XX +XXX,XX @@ &incdec2_cnt rd rn pat esz imm d u &incdec_pred rd pg esz d u &incdec2_pred rd rn pg esz d u +&rprr_load rd pg rn rm dtype nreg +&rpri_load rd pg rn imm dtype nreg ########################################################################### # Named instruction formats. These are generally used to @@ -XXX,XX +XXX,XX @@ @incdec2_pred ........ esz:2 .... .. ..... .. pg:4 rd:5 \ &incdec2_pred rn=%reg_movprfx +# Loads; user must fill in NREG. +@rprr_load_dt ....... dtype:4 rm:5 ... pg:3 rn:5 rd:5 &rprr_load +@rpri_load_dt ....... dtype:4 . imm:s4 ... pg:3 rn:5 rd:5 &rpri_load + +@rprr_load_msz ....... .... rm:5 ... pg:3 rn:5 rd:5 \ + &rprr_load dtype=%msz_dtype +@rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \ + &rpri_load dtype=%msz_dtype + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ LDR_pri 10000101 10 ...... 000 ... ..... 0 .... @pd_rn_i9 # SVE load vector register LDR_zri 10000101 10 ...... 010 ... ..... ..... @rd_rn_i9 + +### SVE Memory Contiguous Load Group + +# SVE contiguous load (scalar plus scalar) +LD_zprr 1010010 .... ..... 010 ... ..... ..... @rprr_load_dt nreg=0 + +# SVE contiguous load (scalar plus immediate) +LD_zpri 1010010 .... 0.... 101 ... ..... ..... @rpri_load_dt nreg=0 + +# SVE contiguous non-temporal load (scalar plus scalar) +# LDNT1B, LDNT1H, LDNT1W, LDNT1D +# SVE load multiple structures (scalar plus scalar) +# LD2B, LD2H, LD2W, LD2D; etc. +LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz + +# SVE contiguous non-temporal load (scalar plus immediate) +# LDNT1B, LDNT1H, LDNT1W, LDNT1D +# SVE load multiple structures (scalar plus immediate) +# LD2B, LD2H, LD2W, LD2D; etc. +LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 40 ++++++++++ target/arm/sve_helper.c | 157 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 69 ++++++++++++++++ target/arm/sve.decode | 6 ++ 4 files changed, 272 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ld1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldff1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldff1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bhu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bhs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1bds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hsu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1hds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_ldnf1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_ldnf1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LD4(sve_ld4dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) #undef DO_LD2 #undef DO_LD3 #undef DO_LD4 + +/* + * Load contiguous data, first-fault and no-fault. + */ + +#ifdef CONFIG_USER_ONLY + +/* Fault on byte I. All bits in FFR from I are cleared. The vector + * result from I is CONSTRAINED UNPREDICTABLE; we choose the MERGE + * option, which leaves subsequent data unchanged. + */ +static void record_fault(CPUARMState *env, uintptr_t i, uintptr_t oprsz) +{ + uint64_t *ffr = env->vfp.pregs[FFR_PRED_NUM].p; + + if (i & 63) { + ffr[i / 64] &= MAKE_64BIT_MASK(0, i & 63); + i = ROUND_UP(i, 64); + } + for (; i < oprsz; i += 64) { + ffr[i / 64] = 0; + } +} + +/* Hold the mmap lock during the operation so that there is no race + * between page_check_range and the load operation. We expect the + * usual case to have no faults at all, so we check the whole range + * first and if successful defer to the normal load operation. + * + * TODO: Change mmap_lock to a rwlock so that multiple readers + * can run simultaneously. This will probably help other uses + * within QEMU as well. + */ +#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ +static void do_sve_ldff1##PART(CPUARMState *env, void *vd, void *vg, \ + target_ulong addr, intptr_t oprsz, \ + bool first, uintptr_t ra) \ +{ \ + intptr_t i = 0; \ + do { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m = 0; \ + if (pg & 1) { \ + if (!first && \ + unlikely(page_check_range(addr, sizeof(TYPEM), \ + PAGE_READ))) { \ + record_fault(env, i, oprsz); \ + return; \ + } \ + m = FN(env, addr, ra); \ + first = false; \ + } \ + *(TYPEE *)(vd + H(i)) = m; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += sizeof(TYPEM); \ + } while (i & 15); \ + } while (i < oprsz); \ +} \ +void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc); \ + unsigned rd = simd_data(desc); \ + void *vd = &env->vfp.zregs[rd]; \ + mmap_lock(); \ + if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ + do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ + } else { \ + do_sve_ldff1##PART(env, vd, vg, addr, oprsz, true, GETPC()); \ + } \ + mmap_unlock(); \ +} + +/* No-fault loads are like first-fault loads without the + * first faulting special case. + */ +#define DO_LDNF1(PART) \ +void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t oprsz = simd_oprsz(desc); \ + unsigned rd = simd_data(desc); \ + void *vd = &env->vfp.zregs[rd]; \ + mmap_lock(); \ + if (likely(page_check_range(addr, oprsz, PAGE_READ) == 0)) { \ + do_sve_ld1##PART(env, vd, vg, addr, oprsz, GETPC()); \ + } else { \ + do_sve_ldff1##PART(env, vd, vg, addr, oprsz, false, GETPC()); \ + } \ + mmap_unlock(); \ +} + +#else + +/* TODO: System mode is not yet supported. + * This would probably use tlb_vaddr_to_host. + */ +#define DO_LDFF1(PART, FN, TYPEE, TYPEM, H) \ +void HELPER(sve_ldff1##PART)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + g_assert_not_reached(); \ +} + +#define DO_LDNF1(PART) \ +void HELPER(sve_ldnf1##PART)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + g_assert_not_reached(); \ +} + +#endif + +DO_LDFF1(bb_r, cpu_ldub_data_ra, uint8_t, uint8_t, H1) +DO_LDFF1(bhu_r, cpu_ldub_data_ra, uint16_t, uint8_t, H1_2) +DO_LDFF1(bhs_r, cpu_ldsb_data_ra, uint16_t, int8_t, H1_2) +DO_LDFF1(bsu_r, cpu_ldub_data_ra, uint32_t, uint8_t, H1_4) +DO_LDFF1(bss_r, cpu_ldsb_data_ra, uint32_t, int8_t, H1_4) +DO_LDFF1(bdu_r, cpu_ldub_data_ra, uint64_t, uint8_t, ) +DO_LDFF1(bds_r, cpu_ldsb_data_ra, uint64_t, int8_t, ) + +DO_LDFF1(hh_r, cpu_lduw_data_ra, uint16_t, uint16_t, H1_2) +DO_LDFF1(hsu_r, cpu_lduw_data_ra, uint32_t, uint16_t, H1_4) +DO_LDFF1(hss_r, cpu_ldsw_data_ra, uint32_t, int8_t, H1_4) +DO_LDFF1(hdu_r, cpu_lduw_data_ra, uint64_t, uint16_t, ) +DO_LDFF1(hds_r, cpu_ldsw_data_ra, uint64_t, int16_t, ) + +DO_LDFF1(ss_r, cpu_ldl_data_ra, uint32_t, uint32_t, H1_4) +DO_LDFF1(sdu_r, cpu_ldl_data_ra, uint64_t, uint32_t, ) +DO_LDFF1(sds_r, cpu_ldl_data_ra, uint64_t, int32_t, ) + +DO_LDFF1(dd_r, cpu_ldq_data_ra, uint64_t, uint64_t, ) + +#undef DO_LDFF1 + +DO_LDNF1(bb_r) +DO_LDNF1(bhu_r) +DO_LDNF1(bhs_r) +DO_LDNF1(bsu_r) +DO_LDNF1(bss_r) +DO_LDNF1(bdu_r) +DO_LDNF1(bds_r) + +DO_LDNF1(hh_r) +DO_LDNF1(hsu_r) +DO_LDNF1(hss_r) +DO_LDNF1(hdu_r) +DO_LDNF1(hds_r) + +DO_LDNF1(ss_r) +DO_LDNF1(sdu_r) +DO_LDNF1(sds_r) + +DO_LDNF1(dd_r) + +#undef DO_LDNF1 diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) } return true; } + +static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) +{ + static gen_helper_gvec_mem * const fns[16] = { + gen_helper_sve_ldff1bb_r, + gen_helper_sve_ldff1bhu_r, + gen_helper_sve_ldff1bsu_r, + gen_helper_sve_ldff1bdu_r, + + gen_helper_sve_ldff1sds_r, + gen_helper_sve_ldff1hh_r, + gen_helper_sve_ldff1hsu_r, + gen_helper_sve_ldff1hdu_r, + + gen_helper_sve_ldff1hds_r, + gen_helper_sve_ldff1hss_r, + gen_helper_sve_ldff1ss_r, + gen_helper_sve_ldff1sdu_r, + + gen_helper_sve_ldff1bds_r, + gen_helper_sve_ldff1bss_r, + gen_helper_sve_ldff1bhs_r, + gen_helper_sve_ldff1dd_r, + }; + + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + } + return true; +} + +static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) +{ + static gen_helper_gvec_mem * const fns[16] = { + gen_helper_sve_ldnf1bb_r, + gen_helper_sve_ldnf1bhu_r, + gen_helper_sve_ldnf1bsu_r, + gen_helper_sve_ldnf1bdu_r, + + gen_helper_sve_ldnf1sds_r, + gen_helper_sve_ldnf1hh_r, + gen_helper_sve_ldnf1hsu_r, + gen_helper_sve_ldnf1hdu_r, + + gen_helper_sve_ldnf1hds_r, + gen_helper_sve_ldnf1hss_r, + gen_helper_sve_ldnf1ss_r, + gen_helper_sve_ldnf1sdu_r, + + gen_helper_sve_ldnf1bds_r, + gen_helper_sve_ldnf1bss_r, + gen_helper_sve_ldnf1bhs_r, + gen_helper_sve_ldnf1dd_r, + }; + + if (sve_access_check(s)) { + int vsz = vec_full_reg_size(s); + int elements = vsz >> dtype_esz[a->dtype]; + int off = (a->imm * elements) << dtype_msz(a->dtype); + TCGv_i64 addr = new_tmp_a64(s); + + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), off); + do_mem_zpa(s, a->rd, a->pg, addr, fns[a->dtype]); + } + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LDR_zri 10000101 10 ...... 010 ... ..... ..... @rd_rn_i9 # SVE contiguous load (scalar plus scalar) LD_zprr 1010010 .... ..... 010 ... ..... ..... @rprr_load_dt nreg=0 +# SVE contiguous first-fault load (scalar plus scalar) +LDFF1_zprr 1010010 .... ..... 011 ... ..... ..... @rprr_load_dt nreg=0 + # SVE contiguous load (scalar plus immediate) LD_zpri 1010010 .... 0.... 101 ... ..... ..... @rpri_load_dt nreg=0 +# SVE contiguous non-fault load (scalar plus immediate) +LDNF1_zpri 1010010 .... 1.... 101 ... ..... ..... @rpri_load_dt nreg=0 + # SVE contiguous non-temporal load (scalar plus scalar) # LDNT1B, LDNT1H, LDNT1W, LDNT1D # SVE load multiple structures (scalar plus scalar) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 29 +++++ target/arm/sve_helper.c | 211 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 65 ++++++++++++ target/arm/sve.decode | 38 +++++++ 4 files changed, 343 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_ldnf1sdu_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1sds_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ldnf1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4hh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4ss_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st2dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st3dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st4dd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1bh_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1bs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1bd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1hs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDNF1(sds_r) DO_LDNF1(dd_r) #undef DO_LDNF1 + +/* + * Store contiguous data, protected by a governing predicate. + */ +#define DO_ST1(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *vd = &env->vfp.zregs[rd]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + TYPEM m = *(TYPEE *)(vd + H(i)); \ + FN(env, addr, m, ra); \ + } \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +#define DO_ST1_D(NAME, FN, TYPEM) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc) / 8; \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + uint64_t *d = &env->vfp.zregs[rd].d[0]; \ + uint8_t *pg = vg; \ + for (i = 0; i < oprsz; i += 1) { \ + if (pg[H1(i)] & 1) { \ + FN(env, addr, d[i], ra); \ + } \ + addr += sizeof(TYPEM); \ + } \ +} + +#define DO_ST2(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ + TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ + FN(env, addr, m1, ra); \ + FN(env, addr + sizeof(TYPEM), m2, ra); \ + } \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 2 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +#define DO_ST3(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ + TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ + TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ + FN(env, addr, m1, ra); \ + FN(env, addr + sizeof(TYPEM), m2, ra); \ + FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ + } \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 3 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +#define DO_ST4(NAME, FN, TYPEE, TYPEM, H) \ +void HELPER(NAME)(CPUARMState *env, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + intptr_t ra = GETPC(); \ + unsigned rd = simd_data(desc); \ + void *d1 = &env->vfp.zregs[rd]; \ + void *d2 = &env->vfp.zregs[(rd + 1) & 31]; \ + void *d3 = &env->vfp.zregs[(rd + 2) & 31]; \ + void *d4 = &env->vfp.zregs[(rd + 3) & 31]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + TYPEM m1 = *(TYPEE *)(d1 + H(i)); \ + TYPEM m2 = *(TYPEE *)(d2 + H(i)); \ + TYPEM m3 = *(TYPEE *)(d3 + H(i)); \ + TYPEM m4 = *(TYPEE *)(d4 + H(i)); \ + FN(env, addr, m1, ra); \ + FN(env, addr + sizeof(TYPEM), m2, ra); \ + FN(env, addr + 2 * sizeof(TYPEM), m3, ra); \ + FN(env, addr + 3 * sizeof(TYPEM), m4, ra); \ + } \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + addr += 4 * sizeof(TYPEM); \ + } while (i & 15); \ + } \ +} + +DO_ST1(sve_st1bh_r, cpu_stb_data_ra, uint16_t, uint8_t, H1_2) +DO_ST1(sve_st1bs_r, cpu_stb_data_ra, uint32_t, uint8_t, H1_4) +DO_ST1_D(sve_st1bd_r, cpu_stb_data_ra, uint8_t) + +DO_ST1(sve_st1hs_r, cpu_stw_data_ra, uint32_t, uint16_t, H1_4) +DO_ST1_D(sve_st1hd_r, cpu_stw_data_ra, uint16_t) + +DO_ST1_D(sve_st1sd_r, cpu_stl_data_ra, uint32_t) + +DO_ST1(sve_st1bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) +DO_ST2(sve_st2bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) +DO_ST3(sve_st3bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) +DO_ST4(sve_st4bb_r, cpu_stb_data_ra, uint8_t, uint8_t, H1) + +DO_ST1(sve_st1hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) +DO_ST2(sve_st2hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) +DO_ST3(sve_st3hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) +DO_ST4(sve_st4hh_r, cpu_stw_data_ra, uint16_t, uint16_t, H1_2) + +DO_ST1(sve_st1ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) +DO_ST2(sve_st2ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) +DO_ST3(sve_st3ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) +DO_ST4(sve_st4ss_r, cpu_stl_data_ra, uint32_t, uint32_t, H1_4) + +DO_ST1_D(sve_st1dd_r, cpu_stq_data_ra, uint64_t) + +void HELPER(sve_st2dd_r)(CPUARMState *env, void *vg, + target_ulong addr, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc) / 8; + intptr_t ra = GETPC(); + unsigned rd = simd_data(desc); + uint64_t *d1 = &env->vfp.zregs[rd].d[0]; + uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; + uint8_t *pg = vg; + + for (i = 0; i < oprsz; i += 1) { + if (pg[H1(i)] & 1) { + cpu_stq_data_ra(env, addr, d1[i], ra); + cpu_stq_data_ra(env, addr + 8, d2[i], ra); + } + addr += 2 * 8; + } +} + +void HELPER(sve_st3dd_r)(CPUARMState *env, void *vg, + target_ulong addr, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc) / 8; + intptr_t ra = GETPC(); + unsigned rd = simd_data(desc); + uint64_t *d1 = &env->vfp.zregs[rd].d[0]; + uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; + uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; + uint8_t *pg = vg; + + for (i = 0; i < oprsz; i += 1) { + if (pg[H1(i)] & 1) { + cpu_stq_data_ra(env, addr, d1[i], ra); + cpu_stq_data_ra(env, addr + 8, d2[i], ra); + cpu_stq_data_ra(env, addr + 16, d3[i], ra); + } + addr += 3 * 8; + } +} + +void HELPER(sve_st4dd_r)(CPUARMState *env, void *vg, + target_ulong addr, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc) / 8; + intptr_t ra = GETPC(); + unsigned rd = simd_data(desc); + uint64_t *d1 = &env->vfp.zregs[rd].d[0]; + uint64_t *d2 = &env->vfp.zregs[(rd + 1) & 31].d[0]; + uint64_t *d3 = &env->vfp.zregs[(rd + 2) & 31].d[0]; + uint64_t *d4 = &env->vfp.zregs[(rd + 3) & 31].d[0]; + uint8_t *pg = vg; + + for (i = 0; i < oprsz; i += 1) { + if (pg[H1(i)] & 1) { + cpu_stq_data_ra(env, addr, d1[i], ra); + cpu_stq_data_ra(env, addr + 8, d2[i], ra); + cpu_stq_data_ra(env, addr + 16, d3[i], ra); + cpu_stq_data_ra(env, addr + 24, d4[i], ra); + } + addr += 4 * 8; + } +} diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) } return true; } + +static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, + int msz, int esz, int nreg) +{ + static gen_helper_gvec_mem * const fn_single[4][4] = { + { gen_helper_sve_st1bb_r, gen_helper_sve_st1bh_r, + gen_helper_sve_st1bs_r, gen_helper_sve_st1bd_r }, + { NULL, gen_helper_sve_st1hh_r, + gen_helper_sve_st1hs_r, gen_helper_sve_st1hd_r }, + { NULL, NULL, + gen_helper_sve_st1ss_r, gen_helper_sve_st1sd_r }, + { NULL, NULL, NULL, gen_helper_sve_st1dd_r }, + }; + static gen_helper_gvec_mem * const fn_multiple[3][4] = { + { gen_helper_sve_st2bb_r, gen_helper_sve_st2hh_r, + gen_helper_sve_st2ss_r, gen_helper_sve_st2dd_r }, + { gen_helper_sve_st3bb_r, gen_helper_sve_st3hh_r, + gen_helper_sve_st3ss_r, gen_helper_sve_st3dd_r }, + { gen_helper_sve_st4bb_r, gen_helper_sve_st4hh_r, + gen_helper_sve_st4ss_r, gen_helper_sve_st4dd_r }, + }; + gen_helper_gvec_mem *fn; + + if (nreg == 0) { + /* ST1 */ + fn = fn_single[msz][esz]; + } else { + /* ST2, ST3, ST4 -- msz == esz, enforced by encoding */ + assert(msz == esz); + fn = fn_multiple[nreg - 1][msz]; + } + assert(fn != NULL); + do_mem_zpa(s, zt, pg, addr, fn); +} + +static bool trans_ST_zprr(DisasContext *s, arg_rprr_store *a, uint32_t insn) +{ + if (a->rm == 31 || a->msz > a->esz) { + return false; + } + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_muli_i64(addr, cpu_reg(s, a->rm), (a->nreg + 1) << a->msz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + do_st_zpa(s, a->rd, a->pg, addr, a->msz, a->esz, a->nreg); + } + return true; +} + +static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a, uint32_t insn) +{ + if (a->msz > a->esz) { + return false; + } + if (sve_access_check(s)) { + int vsz = vec_full_reg_size(s); + int elements = vsz >> a->esz; + TCGv_i64 addr = new_tmp_a64(s); + + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), + (a->imm * elements * (a->nreg + 1)) << a->msz); + do_st_zpa(s, a->rd, a->pg, addr, a->msz, a->esz, a->nreg); + } + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ %imm7_22_16 22:2 16:5 %imm8_16_10 16:5 10:3 %imm9_16_10 16:s6 10:3 +%size_23 23:2 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -XXX,XX +XXX,XX @@ &incdec2_pred rd rn pg esz d u &rprr_load rd pg rn rm dtype nreg &rpri_load rd pg rn imm dtype nreg +&rprr_store rd pg rn rm msz esz nreg +&rpri_store rd pg rn imm msz esz nreg ########################################################################### # Named instruction formats. These are generally used to @@ -XXX,XX +XXX,XX @@ @rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \ &rpri_load dtype=%msz_dtype +# Stores; user must fill in ESZ, MSZ, NREG as needed. +@rprr_store ....... .. .. rm:5 ... pg:3 rn:5 rd:5 &rprr_store +@rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store +@rprr_store_esz_n0 ....... .. esz:2 rm:5 ... pg:3 rn:5 rd:5 \ + &rprr_store nreg=0 + ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz # SVE load multiple structures (scalar plus immediate) # LD2B, LD2H, LD2W, LD2D; etc. LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz + +### SVE Memory Store Group + +# SVE contiguous store (scalar plus immediate) +# ST1B, ST1H, ST1W, ST1D; require msz <= esz +ST_zpri 1110010 .. esz:2 0.... 111 ... ..... ..... \ + @rpri_store_msz nreg=0 + +# SVE contiguous store (scalar plus scalar) +# ST1B, ST1H, ST1W, ST1D; require msz <= esz +# Enumerate msz lest we conflict with STR_zri. +ST_zprr 1110010 00 .. ..... 010 ... ..... ..... \ + @rprr_store_esz_n0 msz=0 +ST_zprr 1110010 01 .. ..... 010 ... ..... ..... \ + @rprr_store_esz_n0 msz=1 +ST_zprr 1110010 10 .. ..... 010 ... ..... ..... \ + @rprr_store_esz_n0 msz=2 +ST_zprr 1110010 11 11 ..... 010 ... ..... ..... \ + @rprr_store msz=3 esz=3 nreg=0 + +# SVE contiguous non-temporal store (scalar plus immediate) (nreg == 0) +# SVE store multiple structures (scalar plus immediate) (nreg != 0) +ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \ + @rpri_store_msz esz=%size_23 + +# SVE contiguous non-temporal store (scalar plus scalar) (nreg == 0) +# SVE store multiple structures (scalar plus scalar) (nreg != 0) +ST_zprr 1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \ + @rprr_store esz=%size_23 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 52 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 9 +++++++ 2 files changed, 61 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) return true; } +static void do_ldrq(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz) +{ + static gen_helper_gvec_mem * const fns[4] = { + gen_helper_sve_ld1bb_r, gen_helper_sve_ld1hh_r, + gen_helper_sve_ld1ss_r, gen_helper_sve_ld1dd_r, + }; + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr t_pg; + TCGv_i32 desc; + + /* Load the first quadword using the normal predicated load helpers. */ + desc = tcg_const_i32(simd_desc(16, 16, zt)); + t_pg = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + fns[msz](cpu_env, t_pg, addr, desc); + + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i32(desc); + + /* Replicate that first quadword. */ + if (vsz > 16) { + unsigned dofs = vec_full_reg_offset(s, zt); + tcg_gen_gvec_dup_mem(4, dofs + 16, dofs, vsz - 16, vsz - 16); + } +} + +static bool trans_LD1RQ_zprr(DisasContext *s, arg_rprr_load *a, uint32_t insn) +{ + if (a->rm == 31) { + return false; + } + if (sve_access_check(s)) { + int msz = dtype_msz(a->dtype); + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), msz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + do_ldrq(s, a->rd, a->pg, addr, msz); + } + return true; +} + +static bool trans_LD1RQ_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) +{ + if (sve_access_check(s)) { + TCGv_i64 addr = new_tmp_a64(s); + tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 16); + do_ldrq(s, a->rd, a->pg, addr, dtype_msz(a->dtype)); + } + return true; +} + static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD_zprr 1010010 .. nreg:2 ..... 110 ... ..... ..... @rprr_load_msz # LD2B, LD2H, LD2W, LD2D; etc. LD_zpri 1010010 .. nreg:2 0.... 111 ... ..... ..... @rpri_load_msz +# SVE load and broadcast quadword (scalar plus scalar) +LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \ + @rprr_load_msz nreg=0 + +# SVE load and broadcast quadword (scalar plus immediate) +# LD1RQB, LD1RQH, LD1RQS, LD1RQD +LD1RQ_zpri 1010010 .. 00 0.... 001 ... ..... ..... \ + @rpri_load_msz nreg=0 + ### SVE Memory Store Group # SVE contiguous store (scalar plus immediate) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> [PMM: fixed typo] Message-id: 20180627043328.11531-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 30 +++++++++++++ target/arm/sve_helper.c | 38 ++++++++++++++++ target/arm/translate-sve.c | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 22 ++++++++++ 4 files changed, 180 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_dh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_ss, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_scvt_dd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_ucvt_hh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_sh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_dh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_ss, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +/* Fully general two-operand expander, controlled by a predicate, + * With the extra float_status parameter. + */ +#define DO_ZPZ_FP(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPE); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + *(TYPE *)(vd + H(i)) = OP(nn, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16) +DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16) +DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32) +DO_ZPZ_FP(sve_scvt_sd, uint64_t, , int32_to_float64) +DO_ZPZ_FP(sve_scvt_dh, uint64_t, , int64_to_float16) +DO_ZPZ_FP(sve_scvt_ds, uint64_t, , int64_to_float32) +DO_ZPZ_FP(sve_scvt_dd, uint64_t, , int64_to_float64) + +DO_ZPZ_FP(sve_ucvt_hh, uint16_t, H1_2, uint16_to_float16) +DO_ZPZ_FP(sve_ucvt_sh, uint32_t, H1_4, uint32_to_float16) +DO_ZPZ_FP(sve_ucvt_ss, uint32_t, H1_4, uint32_to_float32) +DO_ZPZ_FP(sve_ucvt_sd, uint64_t, , uint32_to_float64) +DO_ZPZ_FP(sve_ucvt_dh, uint64_t, , uint64_to_float16) +DO_ZPZ_FP(sve_ucvt_ds, uint64_t, , uint64_to_float32) +DO_ZPZ_FP(sve_ucvt_dd, uint64_t, , uint64_to_float64) + +#undef DO_ZPZ_FP + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FP3(FRSQRTS, rsqrts) #undef DO_FP3 + +/* + *** SVE Floating Point Unary Operations Predicated Group + */ + +static bool do_zpz_ptr(DisasContext *s, int rd, int rn, int pg, + bool is_fp16, gen_helper_gvec_3_ptr *fn) +{ + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(is_fp16); + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + pred_full_reg_offset(s, pg), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); +} + +static bool trans_SCVTF_sh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_sh); +} + +static bool trans_SCVTF_dh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_dh); +} + +static bool trans_SCVTF_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ss); +} + +static bool trans_SCVTF_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ds); +} + +static bool trans_SCVTF_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_sd); +} + +static bool trans_SCVTF_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_dd); +} + +static bool trans_UCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_hh); +} + +static bool trans_UCVTF_sh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_sh); +} + +static bool trans_UCVTF_dh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_dh); +} + +static bool trans_UCVTF_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ss); +} + +static bool trans_UCVTF_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ds); +} + +static bool trans_UCVTF_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_sd); +} + +static bool trans_UCVTF_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_dd); +} + /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz @rd_pg4_pn ........ esz:2 ... ... .. pg:4 . rn:4 rd:5 &rpr_esz +# One register operand, with governing predicate, no vector element size +@rd_pg_rn_e0 ........ .. ... ... ... pg:3 rn:5 rd:5 &rpr_esz esz=0 + # Two register operands with a 6-bit signed immediate. @rd_rn_i6 ........ ... rn:5 ..... imm:s6 rd:5 &rri @@ -XXX,XX +XXX,XX @@ FTSMUL 01100101 .. 0 ..... 000 011 ..... ..... @rd_rn_rm FRECPS 01100101 .. 0 ..... 000 110 ..... ..... @rd_rn_rm FRSQRTS 01100101 .. 0 ..... 000 111 ..... ..... @rd_rn_rm +### SVE FP Unary Operations Predicated Group + +# SVE integer convert to floating-point +SCVTF_hh 01100101 01 010 01 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_sh 01100101 01 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_dh 01100101 01 010 11 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_ss 01100101 10 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_sd 01100101 11 010 00 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_ds 01100101 11 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 +SCVTF_dd 01100101 11 010 11 0 101 ... ..... ..... @rd_pg_rn_e0 + +UCVTF_hh 01100101 01 010 01 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_sh 01100101 01 010 10 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_dh 01100101 01 010 11 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_ss 01100101 10 010 10 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_sd 01100101 11 010 00 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_ds 01100101 11 010 10 1 101 ... ..... ..... @rd_pg_rn_e0 +UCVTF_dd 01100101 11 010 11 1 101 ... ..... ..... @rd_pg_rn_e0 + ### SVE Memory - 32-bit Gather and Unsized Contiguous Group # SVE load predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 77 +++++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 89 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 46 ++++++++++++++++++++ target/arm/sve.decode | 17 ++++++++ 4 files changed, 229 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fsub_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsub_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsub_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmul_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmul_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmul_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fdiv_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fdiv_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fdiv_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmin_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmin_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmin_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmax_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmax_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmax_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fminnum_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fminnum_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fminnum_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmaxnum_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxnum_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxnum_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fabd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fabd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fabd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fscalbn_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fscalbn_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fscalbn_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmulx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmulx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmulx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +/* Fully general three-operand expander, controlled by a predicate, + * With the extra float_status parameter. + */ +#define DO_ZPZZ_FP(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPE); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + TYPE mm = *(TYPE *)(vm + H(i)); \ + *(TYPE *)(vd + H(i)) = OP(nn, mm, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_ZPZZ_FP(sve_fadd_h, uint16_t, H1_2, float16_add) +DO_ZPZZ_FP(sve_fadd_s, uint32_t, H1_4, float32_add) +DO_ZPZZ_FP(sve_fadd_d, uint64_t, , float64_add) + +DO_ZPZZ_FP(sve_fsub_h, uint16_t, H1_2, float16_sub) +DO_ZPZZ_FP(sve_fsub_s, uint32_t, H1_4, float32_sub) +DO_ZPZZ_FP(sve_fsub_d, uint64_t, , float64_sub) + +DO_ZPZZ_FP(sve_fmul_h, uint16_t, H1_2, float16_mul) +DO_ZPZZ_FP(sve_fmul_s, uint32_t, H1_4, float32_mul) +DO_ZPZZ_FP(sve_fmul_d, uint64_t, , float64_mul) + +DO_ZPZZ_FP(sve_fdiv_h, uint16_t, H1_2, float16_div) +DO_ZPZZ_FP(sve_fdiv_s, uint32_t, H1_4, float32_div) +DO_ZPZZ_FP(sve_fdiv_d, uint64_t, , float64_div) + +DO_ZPZZ_FP(sve_fmin_h, uint16_t, H1_2, float16_min) +DO_ZPZZ_FP(sve_fmin_s, uint32_t, H1_4, float32_min) +DO_ZPZZ_FP(sve_fmin_d, uint64_t, , float64_min) + +DO_ZPZZ_FP(sve_fmax_h, uint16_t, H1_2, float16_max) +DO_ZPZZ_FP(sve_fmax_s, uint32_t, H1_4, float32_max) +DO_ZPZZ_FP(sve_fmax_d, uint64_t, , float64_max) + +DO_ZPZZ_FP(sve_fminnum_h, uint16_t, H1_2, float16_minnum) +DO_ZPZZ_FP(sve_fminnum_s, uint32_t, H1_4, float32_minnum) +DO_ZPZZ_FP(sve_fminnum_d, uint64_t, , float64_minnum) + +DO_ZPZZ_FP(sve_fmaxnum_h, uint16_t, H1_2, float16_maxnum) +DO_ZPZZ_FP(sve_fmaxnum_s, uint32_t, H1_4, float32_maxnum) +DO_ZPZZ_FP(sve_fmaxnum_d, uint64_t, , float64_maxnum) + +static inline float16 abd_h(float16 a, float16 b, float_status *s) +{ + return float16_abs(float16_sub(a, b, s)); +} + +static inline float32 abd_s(float32 a, float32 b, float_status *s) +{ + return float32_abs(float32_sub(a, b, s)); +} + +static inline float64 abd_d(float64 a, float64 b, float_status *s) +{ + return float64_abs(float64_sub(a, b, s)); +} + +DO_ZPZZ_FP(sve_fabd_h, uint16_t, H1_2, abd_h) +DO_ZPZZ_FP(sve_fabd_s, uint32_t, H1_4, abd_s) +DO_ZPZZ_FP(sve_fabd_d, uint64_t, , abd_d) + +static inline float64 scalbn_d(float64 a, int64_t b, float_status *s) +{ + int b_int = MIN(MAX(b, INT_MIN), INT_MAX); + return float64_scalbn(a, b_int, s); +} + +DO_ZPZZ_FP(sve_fscalbn_h, int16_t, H1_2, float16_scalbn) +DO_ZPZZ_FP(sve_fscalbn_s, int32_t, H1_4, float32_scalbn) +DO_ZPZZ_FP(sve_fscalbn_d, int64_t, , scalbn_d) + +DO_ZPZZ_FP(sve_fmulx_h, uint16_t, H1_2, helper_advsimd_mulxh) +DO_ZPZZ_FP(sve_fmulx_s, uint32_t, H1_4, helper_vfp_mulxs) +DO_ZPZZ_FP(sve_fmulx_d, uint64_t, , helper_vfp_mulxd) + +#undef DO_ZPZZ_FP + /* Fully general two-operand expander, controlled by a predicate, * With the extra float_status parameter. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FP3(FRSQRTS, rsqrts) #undef DO_FP3 +/* + *** SVE Floating Point Arithmetic - Predicated Group + */ + +static bool do_zpzz_fp(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +#define DO_FP3(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a, uint32_t insn) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[4] = { \ + NULL, gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, gen_helper_sve_##name##_d \ + }; \ + return do_zpzz_fp(s, a, fns[a->esz]); \ +} + +DO_FP3(FADD_zpzz, fadd) +DO_FP3(FSUB_zpzz, fsub) +DO_FP3(FMUL_zpzz, fmul) +DO_FP3(FMIN_zpzz, fmin) +DO_FP3(FMAX_zpzz, fmax) +DO_FP3(FMINNM_zpzz, fminnum) +DO_FP3(FMAXNM_zpzz, fmaxnum) +DO_FP3(FABD, fabd) +DO_FP3(FSCALE, fscalbn) +DO_FP3(FDIV, fdiv) +DO_FP3(FMULX, fmulx) + +#undef DO_FP3 /* *** SVE Floating Point Unary Operations Predicated Group diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FTSMUL 01100101 .. 0 ..... 000 011 ..... ..... @rd_rn_rm FRECPS 01100101 .. 0 ..... 000 110 ..... ..... @rd_rn_rm FRSQRTS 01100101 .. 0 ..... 000 111 ..... ..... @rd_rn_rm +### SVE FP Arithmetic Predicated Group + +# SVE floating-point arithmetic (predicated) +FADD_zpzz 01100101 .. 00 0000 100 ... ..... ..... @rdn_pg_rm +FSUB_zpzz 01100101 .. 00 0001 100 ... ..... ..... @rdn_pg_rm +FMUL_zpzz 01100101 .. 00 0010 100 ... ..... ..... @rdn_pg_rm +FSUB_zpzz 01100101 .. 00 0011 100 ... ..... ..... @rdm_pg_rn # FSUBR +FMAXNM_zpzz 01100101 .. 00 0100 100 ... ..... ..... @rdn_pg_rm +FMINNM_zpzz 01100101 .. 00 0101 100 ... ..... ..... @rdn_pg_rm +FMAX_zpzz 01100101 .. 00 0110 100 ... ..... ..... @rdn_pg_rm +FMIN_zpzz 01100101 .. 00 0111 100 ... ..... ..... @rdn_pg_rm +FABD 01100101 .. 00 1000 100 ... ..... ..... @rdn_pg_rm +FSCALE 01100101 .. 00 1001 100 ... ..... ..... @rdn_pg_rm +FMULX 01100101 .. 00 1010 100 ... ..... ..... @rdn_pg_rm +FDIV 01100101 .. 00 1100 100 ... ..... ..... @rdm_pg_rn # FDIVR +FDIV 01100101 .. 00 1101 100 ... ..... ..... @rdn_pg_rm + ### SVE FP Unary Operations Predicated Group # SVE integer convert to floating-point -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 16 ++++ target/arm/sve_helper.c | 158 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 49 ++++++++++++ target/arm/sve.decode | 18 +++++ 4 files changed, 241 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_FP(sve_ucvt_dd, uint64_t, , uint64_to_float64) #undef DO_ZPZ_FP +/* 4-operand predicated multiply-add. This requires 7 operands to pass + * "properly", so we need to encode some of the registers into DESC. + */ +QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 20 > 32); + +static void do_fmla_zpzzz_h(CPUARMState *env, void *vg, uint32_t desc, + uint16_t neg1, uint16_t neg3) +{ + intptr_t i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + i -= 2; + if (likely((pg >> (i & 63)) & 1)) { + float16 e1, e2, e3, r; + + e1 = *(uint16_t *)(vn + H1_2(i)) ^ neg1; + e2 = *(uint16_t *)(vm + H1_2(i)); + e3 = *(uint16_t *)(va + H1_2(i)) ^ neg3; + r = float16_muladd(e1, e2, e3, 0, &env->vfp.fp_status); + *(uint16_t *)(vd + H1_2(i)) = r; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_h(env, vg, desc, 0, 0); +} + +void HELPER(sve_fmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0); +} + +void HELPER(sve_fnmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_h(env, vg, desc, 0x8000, 0x8000); +} + +void HELPER(sve_fnmls_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_h(env, vg, desc, 0, 0x8000); +} + +static void do_fmla_zpzzz_s(CPUARMState *env, void *vg, uint32_t desc, + uint32_t neg1, uint32_t neg3) +{ + intptr_t i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + i -= 4; + if (likely((pg >> (i & 63)) & 1)) { + float32 e1, e2, e3, r; + + e1 = *(uint32_t *)(vn + H1_4(i)) ^ neg1; + e2 = *(uint32_t *)(vm + H1_4(i)); + e3 = *(uint32_t *)(va + H1_4(i)) ^ neg3; + r = float32_muladd(e1, e2, e3, 0, &env->vfp.fp_status); + *(uint32_t *)(vd + H1_4(i)) = r; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_s(env, vg, desc, 0, 0); +} + +void HELPER(sve_fmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0); +} + +void HELPER(sve_fnmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_s(env, vg, desc, 0x80000000, 0x80000000); +} + +void HELPER(sve_fnmls_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_s(env, vg, desc, 0, 0x80000000); +} + +static void do_fmla_zpzzz_d(CPUARMState *env, void *vg, uint32_t desc, + uint64_t neg1, uint64_t neg3) +{ + intptr_t i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + i -= 8; + if (likely((pg >> (i & 63)) & 1)) { + float64 e1, e2, e3, r; + + e1 = *(uint64_t *)(vn + i) ^ neg1; + e2 = *(uint64_t *)(vm + i); + e3 = *(uint64_t *)(va + i) ^ neg3; + r = float64_muladd(e1, e2, e3, 0, &env->vfp.fp_status); + *(uint64_t *)(vd + i) = r; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_d(env, vg, desc, 0, 0); +} + +void HELPER(sve_fmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, 0); +} + +void HELPER(sve_fnmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_d(env, vg, desc, INT64_MIN, INT64_MIN); +} + +void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) +{ + do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN); +} + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FP3(FMULX, fmulx) #undef DO_FP3 +typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32); + +static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn) +{ + if (fn == NULL) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = vec_full_reg_size(s); + unsigned desc; + TCGv_i32 t_desc; + TCGv_ptr pg = tcg_temp_new_ptr(); + + /* We would need 7 operands to pass these arguments "properly". + * So we encode all the register numbers into the descriptor. + */ + desc = deposit32(a->rd, 5, 5, a->rn); + desc = deposit32(desc, 10, 5, a->rm); + desc = deposit32(desc, 15, 5, a->ra); + desc = simd_desc(vsz, vsz, desc); + + t_desc = tcg_const_i32(desc); + tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg)); + fn(cpu_env, pg, t_desc); + tcg_temp_free_i32(t_desc); + tcg_temp_free_ptr(pg); + return true; +} + +#define DO_FMLA(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rprrr_esz *a, uint32_t insn) \ +{ \ + static gen_helper_sve_fmla * const fns[4] = { \ + NULL, gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, gen_helper_sve_##name##_d \ + }; \ + return do_fmla(s, a, fns[a->esz]); \ +} + +DO_FMLA(FMLA_zpzzz, fmla_zpzzz) +DO_FMLA(FMLS_zpzzz, fmls_zpzzz) +DO_FMLA(FNMLA_zpzzz, fnmla_zpzzz) +DO_FMLA(FNMLS_zpzzz, fnmls_zpzzz) + +#undef DO_FMLA + /* *** SVE Floating Point Unary Operations Predicated Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rprrr_esz ra=%reg_movprfx @rdn_pg_ra_rm ........ esz:2 . rm:5 ... pg:3 ra:5 rd:5 \ &rprrr_esz rn=%reg_movprfx +@rdn_pg_rm_ra ........ esz:2 . ra:5 ... pg:3 rm:5 rd:5 \ + &rprrr_esz rn=%reg_movprfx # One register operand, with governing predicate, vector element size @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz @@ -XXX,XX +XXX,XX @@ FMULX 01100101 .. 00 1010 100 ... ..... ..... @rdn_pg_rm FDIV 01100101 .. 00 1100 100 ... ..... ..... @rdm_pg_rn # FDIVR FDIV 01100101 .. 00 1101 100 ... ..... ..... @rdn_pg_rm +### SVE FP Multiply-Add Group + +# SVE floating-point multiply-accumulate writing addend +FMLA_zpzzz 01100101 .. 1 ..... 000 ... ..... ..... @rda_pg_rn_rm +FMLS_zpzzz 01100101 .. 1 ..... 001 ... ..... ..... @rda_pg_rn_rm +FNMLA_zpzzz 01100101 .. 1 ..... 010 ... ..... ..... @rda_pg_rn_rm +FNMLS_zpzzz 01100101 .. 1 ..... 011 ... ..... ..... @rda_pg_rn_rm + +# SVE floating-point multiply-accumulate writing multiplicand +# Alter the operand extraction order and reuse the helpers from above. +# FMAD, FMSB, FNMAD, FNMS +FMLA_zpzzz 01100101 .. 1 ..... 100 ... ..... ..... @rdn_pg_rm_ra +FMLS_zpzzz 01100101 .. 1 ..... 101 ... ..... ..... @rdn_pg_rm_ra +FNMLA_zpzzz 01100101 .. 1 ..... 110 ... ..... ..... @rdn_pg_rm_ra +FNMLS_zpzzz 01100101 .. 1 ..... 111 ... ..... ..... @rdn_pg_rm_ra + ### SVE FP Unary Operations Predicated Group # SVE integer convert to floating-point -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 7 +++++ target/arm/sve_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 45 ++++++++++++++++++++++++++++++ target/arm/sve.decode | 5 ++++ 4 files changed, 113 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG, + i64, i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, + i64, i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fadda_d, TCG_CALL_NO_RWG, + i64, i64, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +uint64_t HELPER(sve_fadda_h)(uint64_t nn, void *vm, void *vg, + void *status, uint32_t desc) +{ + intptr_t i = 0, opr_sz = simd_oprsz(desc); + float16 result = nn; + + do { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + float16 mm = *(float16 *)(vm + H1_2(i)); + result = float16_add(result, mm, status); + } + i += sizeof(float16), pg >>= sizeof(float16); + } while (i & 15); + } while (i < opr_sz); + + return result; +} + +uint64_t HELPER(sve_fadda_s)(uint64_t nn, void *vm, void *vg, + void *status, uint32_t desc) +{ + intptr_t i = 0, opr_sz = simd_oprsz(desc); + float32 result = nn; + + do { + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); + do { + if (pg & 1) { + float32 mm = *(float32 *)(vm + H1_2(i)); + result = float32_add(result, mm, status); + } + i += sizeof(float32), pg >>= sizeof(float32); + } while (i & 15); + } while (i < opr_sz); + + return result; +} + +uint64_t HELPER(sve_fadda_d)(uint64_t nn, void *vm, void *vg, + void *status, uint32_t desc) +{ + intptr_t i = 0, opr_sz = simd_oprsz(desc) / 8; + uint64_t *m = vm; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i++) { + if (pg[H1(i)] & 1) { + nn = float64_add(nn, m[i], status); + } + } + + return nn; +} + /* Fully general three-operand expander, controlled by a predicate, * With the extra float_status parameter. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI +/* + *** SVE Floating Point Accumulating Reduction Group + */ + +static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a, uint32_t insn) +{ + typedef void fadda_fn(TCGv_i64, TCGv_i64, TCGv_ptr, + TCGv_ptr, TCGv_ptr, TCGv_i32); + static fadda_fn * const fns[3] = { + gen_helper_sve_fadda_h, + gen_helper_sve_fadda_s, + gen_helper_sve_fadda_d, + }; + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr t_rm, t_pg, t_fpst; + TCGv_i64 t_val; + TCGv_i32 t_desc; + + if (a->esz == 0) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + t_val = load_esz(cpu_env, vec_reg_offset(s, a->rn, 0, a->esz), a->esz); + t_rm = tcg_temp_new_ptr(); + t_pg = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_rm, cpu_env, vec_full_reg_offset(s, a->rm)); + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, a->pg)); + t_fpst = get_fpstatus_ptr(a->esz == MO_16); + t_desc = tcg_const_i32(simd_desc(vsz, vsz, 0)); + + fns[a->esz - 1](t_val, t_val, t_rm, t_pg, t_fpst, t_desc); + + tcg_temp_free_i32(t_desc); + tcg_temp_free_ptr(t_fpst); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_ptr(t_rm); + + write_fp_dreg(s, a->rd, t_val); + tcg_temp_free_i64(t_val); + return true; +} + /* *** SVE Floating Point Arithmetic - Unpredicated Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s +### SVE FP Accumulating Reduction Group + +# SVE floating-point serial reduction (predicated) +FADDA 01100101 .. 011 000 001 ... ..... ..... @rdn_pg_rm + ### SVE Floating Point Arithmetic - Unpredicated Group # SVE floating-point arithmetic (unpredicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 5 +++ target/arm/sve_helper.c | 41 +++++++++++++++++++++++++ target/arm/translate-sve.c | 62 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 5 +++ 4 files changed, 113 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_clr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_clr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(sve_clr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_movz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_asr_zpzi_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_asr_zpzi_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_asr_zpzi_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_clr_d)(void *vd, void *vg, uint32_t desc) } } +/* Copy Zn into Zd, and store zero into inactive elements. */ +void HELPER(sve_movz_b)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_b(pg[H1(i)]); + } +} + +void HELPER(sve_movz_h)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_h(pg[H1(i)]); + } +} + +void HELPER(sve_movz_s)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[i] & expand_pred_s(pg[H1(i)]); + } +} + +void HELPER(sve_movz_d)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + for (i = 0; i < opr_sz; i += 1) { + d[i] = n[1] & -(uint64_t)(pg[H1(i)] & 1); + } +} + /* Three-operand expander, immediate operand, controlled by a predicate. */ #define DO_ZPZI(NAME, TYPE, H, OP) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_clr_zp(DisasContext *s, int rd, int pg, int esz) return true; } +/* Copy Zn into Zd, storing zeros into inactive elements. */ +static void do_movz_zpz(DisasContext *s, int rd, int rn, int pg, int esz) +{ + static gen_helper_gvec_3 * const fns[4] = { + gen_helper_sve_movz_b, gen_helper_sve_movz_h, + gen_helper_sve_movz_s, gen_helper_sve_movz_d, + }; + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + pred_full_reg_offset(s, pg), + vsz, vsz, 0, fns[esz]); +} + static bool do_zpzi_ool(DisasContext *s, arg_rpri_esz *a, gen_helper_gvec_3 *fn) { @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RQ_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) return true; } +/* Load and broadcast element. */ +static bool trans_LD1R_zpri(DisasContext *s, arg_rpri_load *a, uint32_t insn) +{ + if (!sve_access_check(s)) { + return true; + } + + unsigned vsz = vec_full_reg_size(s); + unsigned psz = pred_full_reg_size(s); + unsigned esz = dtype_esz[a->dtype]; + TCGLabel *over = gen_new_label(); + TCGv_i64 temp; + + /* If the guarding predicate has no bits set, no load occurs. */ + if (psz <= 8) { + /* Reduce the pred_esz_masks value simply to reduce the + * size of the code generated here. + */ + uint64_t psz_mask = MAKE_64BIT_MASK(0, psz * 8); + temp = tcg_temp_new_i64(); + tcg_gen_ld_i64(temp, cpu_env, pred_full_reg_offset(s, a->pg)); + tcg_gen_andi_i64(temp, temp, pred_esz_masks[esz] & psz_mask); + tcg_gen_brcondi_i64(TCG_COND_EQ, temp, 0, over); + tcg_temp_free_i64(temp); + } else { + TCGv_i32 t32 = tcg_temp_new_i32(); + find_last_active(s, t32, esz, a->pg); + tcg_gen_brcondi_i32(TCG_COND_LT, t32, 0, over); + tcg_temp_free_i32(t32); + } + + /* Load the data. */ + temp = tcg_temp_new_i64(); + tcg_gen_addi_i64(temp, cpu_reg_sp(s, a->rn), a->imm << esz); + tcg_gen_qemu_ld_i64(temp, temp, get_mem_index(s), + s->be_data | dtype_mop[a->dtype]); + + /* Broadcast to *all* elements. */ + tcg_gen_gvec_dup_i64(esz, vec_full_reg_offset(s, a->rd), + vsz, vsz, temp); + tcg_temp_free_i64(temp); + + /* Zero the inactive elements. */ + gen_set_label(over); + do_movz_zpz(s, a->rd, a->rd, a->pg, esz); + return true; +} + static void do_st_zpa(DisasContext *s, int zt, int pg, TCGv_i64 addr, int msz, int esz, int nreg) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ %imm8_16_10 16:5 10:3 %imm9_16_10 16:s6 10:3 %size_23 23:2 +%dtype_23_13 23:2 13:2 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -XXX,XX +XXX,XX @@ LDR_pri 10000101 10 ...... 000 ... ..... 0 .... @pd_rn_i9 # SVE load vector register LDR_zri 10000101 10 ...... 010 ... ..... ..... @rd_rn_i9 +# SVE load and broadcast element +LD1R_zpri 1000010 .. 1 imm:6 1.. pg:3 rn:5 rd:5 \ + &rpri_load dtype=%dtype_23_13 nreg=0 + ### SVE Memory Contiguous Load Group # SVE contiguous load (scalar plus scalar) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 103 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 6 +++ 2 files changed, 109 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, uint32_t len, tcg_temp_free_i64(t0); } +/* Similarly for stores. */ +static void do_str(DisasContext *s, uint32_t vofs, uint32_t len, + int rn, int imm) +{ + uint32_t len_align = QEMU_ALIGN_DOWN(len, 8); + uint32_t len_remain = len % 8; + uint32_t nparts = len / 8 + ctpop8(len_remain); + int midx = get_mem_index(s); + TCGv_i64 addr, t0; + + addr = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + + /* Note that unpredicated load/store of vector/predicate registers + * are defined as a stream of bytes, which equates to little-endian + * operations on larger quantities. There is no nice way to force + * a little-endian store for aarch64_be-linux-user out of line. + * + * Attempt to keep code expansion to a minimum by limiting the + * amount of unrolling done. + */ + if (nparts <= 4) { + int i; + + for (i = 0; i < len_align; i += 8) { + tcg_gen_ld_i64(t0, cpu_env, vofs + i); + tcg_gen_addi_i64(addr, cpu_reg_sp(s, rn), imm + i); + tcg_gen_qemu_st_i64(t0, addr, midx, MO_LEQ); + } + } else { + TCGLabel *loop = gen_new_label(); + TCGv_ptr t2, i = tcg_const_local_ptr(0); + + gen_set_label(loop); + + t2 = tcg_temp_new_ptr(); + tcg_gen_add_ptr(t2, cpu_env, i); + tcg_gen_ld_i64(t0, t2, vofs); + + /* Minimize the number of local temps that must be re-read from + * the stack each iteration. Instead, re-compute values other + * than the loop counter. + */ + tcg_gen_addi_ptr(t2, i, imm); + tcg_gen_extu_ptr_i64(addr, t2); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, rn)); + tcg_temp_free_ptr(t2); + + tcg_gen_qemu_st_i64(t0, addr, midx, MO_LEQ); + + tcg_gen_addi_ptr(i, i, 8); + + tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); + tcg_temp_free_ptr(i); + } + + /* Predicate register stores can be any multiple of 2. */ + if (len_remain) { + tcg_gen_ld_i64(t0, cpu_env, vofs + len_align); + tcg_gen_addi_i64(addr, cpu_reg_sp(s, rn), imm + len_align); + + switch (len_remain) { + case 2: + case 4: + case 8: + tcg_gen_qemu_st_i64(t0, addr, midx, MO_LE | ctz32(len_remain)); + break; + + case 6: + tcg_gen_qemu_st_i64(t0, addr, midx, MO_LEUL); + tcg_gen_addi_i64(addr, addr, 4); + tcg_gen_shri_i64(t0, t0, 32); + tcg_gen_qemu_st_i64(t0, addr, midx, MO_LEUW); + break; + + default: + g_assert_not_reached(); + } + } + tcg_temp_free_i64(addr); + tcg_temp_free_i64(t0); +} + static bool trans_LDR_zri(DisasContext *s, arg_rri *a, uint32_t insn) { if (sve_access_check(s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a, uint32_t insn) return true; } +static bool trans_STR_zri(DisasContext *s, arg_rri *a, uint32_t insn) +{ + if (sve_access_check(s)) { + int size = vec_full_reg_size(s); + int off = vec_full_reg_offset(s, a->rd); + do_str(s, off, size, a->rn, a->imm * size); + } + return true; +} + +static bool trans_STR_pri(DisasContext *s, arg_rri *a, uint32_t insn) +{ + if (sve_access_check(s)) { + int size = pred_full_reg_size(s); + int off = pred_full_reg_offset(s, a->rd); + do_str(s, off, size, a->rn, a->imm * size); + } + return true; +} + /* *** SVE Memory - Contiguous Load Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD1RQ_zpri 1010010 .. 00 0.... 001 ... ..... ..... \ ### SVE Memory Store Group +# SVE store predicate register +STR_pri 1110010 11 0. ..... 000 ... ..... 0 .... @pd_rn_i9 + +# SVE store vector register +STR_zri 1110010 11 0. ..... 010 ... ..... ..... @rd_rn_i9 + # SVE contiguous store (scalar plus immediate) # ST1B, ST1H, ST1W, ST1D; require msz <= esz ST_zpri 1110010 .. esz:2 0.... 111 ... ..... ..... \ -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 41 +++++++++++++++++++++ target/arm/sve_helper.c | 61 +++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 75 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 39 ++++++++++++++++++++ 4 files changed, 216 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st1hs_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_stbs_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sths_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stss_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_stbd_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_stbd_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_stbd_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_sthd_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stsd_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_stdd_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_st4dd_r)(CPUARMState *env, void *vg, addr += 4 * 8; } } + +/* Stores with a vector index. */ + +#define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + unsigned scale = simd_data(desc); \ + uintptr_t ra = GETPC(); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (likely(pg & 1)) { \ + target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ + uint32_t d = *(uint32_t *)(vd + H1_4(i)); \ + FN(env, base + (off << scale), d, ra); \ + } \ + i += sizeof(uint32_t), pg >>= sizeof(uint32_t); \ + } while (i & 15); \ + } \ +} + +#define DO_ST1_ZPZ_D(NAME, TYPEI, FN) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc) / 8; \ + unsigned scale = simd_data(desc); \ + uintptr_t ra = GETPC(); \ + uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ + for (i = 0; i < oprsz; i++) { \ + if (likely(pg[H1(i)] & 1)) { \ + target_ulong off = (target_ulong)(TYPEI)m[i] << scale; \ + FN(env, base + off, d[i], ra); \ + } \ + } \ +} + +DO_ST1_ZPZ_S(sve_stbs_zsu, uint32_t, cpu_stb_data_ra) +DO_ST1_ZPZ_S(sve_sths_zsu, uint32_t, cpu_stw_data_ra) +DO_ST1_ZPZ_S(sve_stss_zsu, uint32_t, cpu_stl_data_ra) + +DO_ST1_ZPZ_S(sve_stbs_zss, int32_t, cpu_stb_data_ra) +DO_ST1_ZPZ_S(sve_sths_zss, int32_t, cpu_stw_data_ra) +DO_ST1_ZPZ_S(sve_stss_zss, int32_t, cpu_stl_data_ra) + +DO_ST1_ZPZ_D(sve_stbd_zsu, uint32_t, cpu_stb_data_ra) +DO_ST1_ZPZ_D(sve_sthd_zsu, uint32_t, cpu_stw_data_ra) +DO_ST1_ZPZ_D(sve_stsd_zsu, uint32_t, cpu_stl_data_ra) +DO_ST1_ZPZ_D(sve_stdd_zsu, uint32_t, cpu_stq_data_ra) + +DO_ST1_ZPZ_D(sve_stbd_zss, int32_t, cpu_stb_data_ra) +DO_ST1_ZPZ_D(sve_sthd_zss, int32_t, cpu_stw_data_ra) +DO_ST1_ZPZ_D(sve_stsd_zss, int32_t, cpu_stl_data_ra) +DO_ST1_ZPZ_D(sve_stdd_zss, int32_t, cpu_stq_data_ra) + +DO_ST1_ZPZ_D(sve_stbd_zd, uint64_t, cpu_stb_data_ra) +DO_ST1_ZPZ_D(sve_sthd_zd, uint64_t, cpu_stw_data_ra) +DO_ST1_ZPZ_D(sve_stsd_zd, uint64_t, cpu_stl_data_ra) +DO_ST1_ZPZ_D(sve_stdd_zd, uint64_t, cpu_stq_data_ra) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ typedef void gen_helper_gvec_flags_4(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void gen_helper_gvec_mem(TCGv_env, TCGv_ptr, TCGv_i64, TCGv_i32); +typedef void gen_helper_gvec_mem_scatter(TCGv_env, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i64, TCGv_i32); /* * Helpers for extracting complex instruction fields. @@ -XXX,XX +XXX,XX @@ static bool trans_ST_zpri(DisasContext *s, arg_rpri_store *a, uint32_t insn) } return true; } + +/* + *** SVE gather loads / scatter stores + */ + +static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale, + TCGv_i64 scalar, gen_helper_gvec_mem_scatter *fn) +{ + unsigned vsz = vec_full_reg_size(s); + TCGv_i32 desc = tcg_const_i32(simd_desc(vsz, vsz, scale)); + TCGv_ptr t_zm = tcg_temp_new_ptr(); + TCGv_ptr t_pg = tcg_temp_new_ptr(); + TCGv_ptr t_zt = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + tcg_gen_addi_ptr(t_zm, cpu_env, vec_full_reg_offset(s, zm)); + tcg_gen_addi_ptr(t_zt, cpu_env, vec_full_reg_offset(s, zt)); + fn(cpu_env, t_zt, t_pg, t_zm, scalar, desc); + + tcg_temp_free_ptr(t_zt); + tcg_temp_free_ptr(t_zm); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i32(desc); +} + +static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) +{ + /* Indexed by [xs][msz]. */ + static gen_helper_gvec_mem_scatter * const fn32[2][3] = { + { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_zsu, + gen_helper_sve_stss_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_zss, + gen_helper_sve_stss_zss, }, + }; + /* Note that we overload xs=2 to indicate 64-bit offset. */ + static gen_helper_gvec_mem_scatter * const fn64[3][4] = { + { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_zsu, + gen_helper_sve_stsd_zsu, + gen_helper_sve_stdd_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_zss, + gen_helper_sve_stsd_zss, + gen_helper_sve_stdd_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_zd, + gen_helper_sve_stsd_zd, + gen_helper_sve_stdd_zd, }, + }; + gen_helper_gvec_mem_scatter *fn; + + if (a->esz < a->msz || (a->msz == 0 && a->scale)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + switch (a->esz) { + case MO_32: + fn = fn32[a->xs][a->msz]; + break; + case MO_64: + fn = fn64[a->xs][a->msz]; + break; + default: + g_assert_not_reached(); + } + do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, + cpu_reg_sp(s, a->rn), fn); + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rpri_load rd pg rn imm dtype nreg &rprr_store rd pg rn rm msz esz nreg &rpri_store rd pg rn imm msz esz nreg +&rprr_scatter_store rd pg rn rm esz msz xs scale ########################################################################### # Named instruction formats. These are generally used to @@ -XXX,XX +XXX,XX @@ @rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store @rprr_store_esz_n0 ....... .. esz:2 rm:5 ... pg:3 rn:5 rd:5 \ &rprr_store nreg=0 +@rprr_scatter_store ....... msz:2 .. rm:5 ... pg:3 rn:5 rd:5 \ + &rprr_scatter_store ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ ST_zpri 1110010 .. nreg:2 1.... 111 ... ..... ..... \ # SVE store multiple structures (scalar plus scalar) (nreg != 0) ST_zprr 1110010 msz:2 nreg:2 ..... 011 ... ..... ..... \ @rprr_store esz=%size_23 + +# SVE 32-bit scatter store (scalar plus 32-bit scaled offsets) +# Require msz > 0 && msz <= esz. +ST1_zprz 1110010 .. 11 ..... 100 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=2 scale=1 +ST1_zprz 1110010 .. 11 ..... 110 ... ..... ..... \ + @rprr_scatter_store xs=1 esz=2 scale=1 + +# SVE 32-bit scatter store (scalar plus 32-bit unscaled offsets) +# Require msz <= esz. +ST1_zprz 1110010 .. 10 ..... 100 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=2 scale=0 +ST1_zprz 1110010 .. 10 ..... 110 ... ..... ..... \ + @rprr_scatter_store xs=1 esz=2 scale=0 + +# SVE 64-bit scatter store (scalar plus 64-bit scaled offset) +# Require msz > 0 +ST1_zprz 1110010 .. 01 ..... 101 ... ..... ..... \ + @rprr_scatter_store xs=2 esz=3 scale=1 + +# SVE 64-bit scatter store (scalar plus 64-bit unscaled offset) +ST1_zprz 1110010 .. 00 ..... 101 ... ..... ..... \ + @rprr_scatter_store xs=2 esz=3 scale=0 + +# SVE 64-bit scatter store (scalar plus unpacked 32-bit scaled offset) +# Require msz > 0 +ST1_zprz 1110010 .. 01 ..... 100 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=3 scale=1 +ST1_zprz 1110010 .. 01 ..... 110 ... ..... ..... \ + @rprr_scatter_store xs=1 esz=3 scale=1 + +# SVE 64-bit scatter store (scalar plus unpacked 32-bit unscaled offset) +ST1_zprz 1110010 .. 00 ..... 100 ... ..... ..... \ + @rprr_scatter_store xs=0 esz=3 scale=0 +ST1_zprz 1110010 .. 00 ..... 110 ... ..... ..... \ + @rprr_scatter_store xs=1 esz=3 scale=0 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 21 +++++++++++++++++++++ target/arm/sve.decode | 23 +++++++++++++++++++++++ 2 files changed, 44 insertions(+) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) cpu_reg_sp(s, a->rn), fn); return true; } + +/* + * Prefetches + */ + +static bool trans_PRF(DisasContext *s, arg_PRF *a, uint32_t insn) +{ + /* Prefetch is a nop within QEMU. */ + sve_access_check(s); + return true; +} + +static bool trans_PRF_rr(DisasContext *s, arg_PRF_rr *a, uint32_t insn) +{ + if (a->rm == 31) { + return false; + } + /* Prefetch is a nop within QEMU. */ + sve_access_check(s); + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD1RQ_zprr 1010010 .. 00 ..... 000 ... ..... ..... \ LD1RQ_zpri 1010010 .. 00 0.... 001 ... ..... ..... \ @rpri_load_msz nreg=0 +# SVE 32-bit gather prefetch (scalar plus 32-bit scaled offsets) +PRF 1000010 00 -1 ----- 0-- --- ----- 0 ---- + +# SVE 32-bit gather prefetch (vector plus immediate) +PRF 1000010 -- 00 ----- 111 --- ----- 0 ---- + +# SVE contiguous prefetch (scalar plus immediate) +PRF 1000010 11 1- ----- 0-- --- ----- 0 ---- + +# SVE contiguous prefetch (scalar plus scalar) +PRF_rr 1000010 -- 00 rm:5 110 --- ----- 0 ---- + +### SVE Memory 64-bit Gather Group + +# SVE 64-bit gather prefetch (scalar plus 64-bit scaled offsets) +PRF 1100010 00 11 ----- 1-- --- ----- 0 ---- + +# SVE 64-bit gather prefetch (scalar plus unpacked 32-bit scaled offsets) +PRF 1100010 00 -1 ----- 0-- --- ----- 0 ---- + +# SVE 64-bit gather prefetch (vector plus immediate) +PRF 1100010 -- 00 ----- 111 --- ----- 0 ---- + ### SVE Memory Store Group # SVE store predicate register -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 67 +++++++++++++++++++++++++ target/arm/sve_helper.c | 77 ++++++++++++++++++++++++++++ target/arm/translate-sve.c | 100 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 57 +++++++++++++++++++++ 4 files changed, 301 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_st1hd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_st1sd_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbsu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhsu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldssu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbss_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldbsu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhsu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldssu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbss_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhss_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldbdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldddu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldbdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldddu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldbdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldddu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldbds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldhds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldsds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_st4dd_r)(CPUARMState *env, void *vg, } } +/* Loads with a vector index. */ + +#define DO_LD1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + unsigned scale = simd_data(desc); \ + uintptr_t ra = GETPC(); \ + for (i = 0; i < oprsz; i++) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m = 0; \ + if (pg & 1) { \ + target_ulong off = *(TYPEI *)(vm + H1_4(i)); \ + m = FN(env, base + (off << scale), ra); \ + } \ + *(uint32_t *)(vd + H1_4(i)) = m; \ + i += 4, pg >>= 4; \ + } while (i & 15); \ + } \ +} + +#define DO_LD1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc) / 8; \ + unsigned scale = simd_data(desc); \ + uintptr_t ra = GETPC(); \ + uint64_t *d = vd, *m = vm; uint8_t *pg = vg; \ + for (i = 0; i < oprsz; i++) { \ + TYPEM mm = 0; \ + if (pg[H1(i)] & 1) { \ + target_ulong off = (TYPEI)m[i]; \ + mm = FN(env, base + (off << scale), ra); \ + } \ + d[i] = mm; \ + } \ +} + +DO_LD1_ZPZ_S(sve_ldbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_S(sve_ldhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_S(sve_ldssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) +DO_LD1_ZPZ_S(sve_ldbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_S(sve_ldhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) + +DO_LD1_ZPZ_S(sve_ldbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_S(sve_ldhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_S(sve_ldssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) +DO_LD1_ZPZ_S(sve_ldbss_zss, int32_t, int8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_S(sve_ldhss_zss, int32_t, int16_t, cpu_lduw_data_ra) + +DO_LD1_ZPZ_D(sve_ldbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) +DO_LD1_ZPZ_D(sve_ldddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) +DO_LD1_ZPZ_D(sve_ldbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) + +DO_LD1_ZPZ_D(sve_ldbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) +DO_LD1_ZPZ_D(sve_ldddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) +DO_LD1_ZPZ_D(sve_ldbds_zss, int32_t, int8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhds_zss, int32_t, int16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsds_zss, int32_t, int32_t, cpu_ldl_data_ra) + +DO_LD1_ZPZ_D(sve_ldbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) +DO_LD1_ZPZ_D(sve_ldddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) +DO_LD1_ZPZ_D(sve_ldbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) +DO_LD1_ZPZ_D(sve_ldhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) +DO_LD1_ZPZ_D(sve_ldsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) + /* Stores with a vector index. */ #define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static void do_mem_zpz(DisasContext *s, int zt, int pg, int zm, int scale, tcg_temp_free_i32(desc); } +/* Indexed by [ff][xs][u][msz]. */ +static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][3] = { + { { { gen_helper_sve_ldbss_zsu, + gen_helper_sve_ldhss_zsu, + NULL, }, + { gen_helper_sve_ldbsu_zsu, + gen_helper_sve_ldhsu_zsu, + gen_helper_sve_ldssu_zsu, } }, + { { gen_helper_sve_ldbss_zss, + gen_helper_sve_ldhss_zss, + NULL, }, + { gen_helper_sve_ldbsu_zss, + gen_helper_sve_ldhsu_zss, + gen_helper_sve_ldssu_zss, } } }, + /* TODO fill in first-fault handlers */ +}; + +/* Note that we overload xs=2 to indicate 64-bit offset. */ +static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][3][2][4] = { + { { { gen_helper_sve_ldbds_zsu, + gen_helper_sve_ldhds_zsu, + gen_helper_sve_ldsds_zsu, + NULL, }, + { gen_helper_sve_ldbdu_zsu, + gen_helper_sve_ldhdu_zsu, + gen_helper_sve_ldsdu_zsu, + gen_helper_sve_ldddu_zsu, } }, + { { gen_helper_sve_ldbds_zss, + gen_helper_sve_ldhds_zss, + gen_helper_sve_ldsds_zss, + NULL, }, + { gen_helper_sve_ldbdu_zss, + gen_helper_sve_ldhdu_zss, + gen_helper_sve_ldsdu_zss, + gen_helper_sve_ldddu_zss, } }, + { { gen_helper_sve_ldbds_zd, + gen_helper_sve_ldhds_zd, + gen_helper_sve_ldsds_zd, + NULL, }, + { gen_helper_sve_ldbdu_zd, + gen_helper_sve_ldhdu_zd, + gen_helper_sve_ldsdu_zd, + gen_helper_sve_ldddu_zd, } } }, + /* TODO fill in first-fault handlers */ +}; + +static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) +{ + gen_helper_gvec_mem_scatter *fn = NULL; + + if (!sve_access_check(s)) { + return true; + } + + switch (a->esz) { + case MO_32: + fn = gather_load_fn32[a->ff][a->xs][a->u][a->msz]; + break; + case MO_64: + fn = gather_load_fn64[a->ff][a->xs][a->u][a->msz]; + break; + } + assert(fn != NULL); + + do_mem_zpz(s, a->rd, a->pg, a->rm, a->scale * a->msz, + cpu_reg_sp(s, a->rn), fn); + return true; +} + +static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) +{ + gen_helper_gvec_mem_scatter *fn = NULL; + TCGv_i64 imm; + + if (a->esz < a->msz || (a->esz == a->msz && !a->u)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + switch (a->esz) { + case MO_32: + fn = gather_load_fn32[a->ff][0][a->u][a->msz]; + break; + case MO_64: + fn = gather_load_fn64[a->ff][2][a->u][a->msz]; + break; + } + assert(fn != NULL); + + /* Treat LD1_zpiz (zn[x] + imm) the same way as LD1_zprz (rn + zm[x]) + * by loading the immediate into the scalar parameter. + */ + imm = tcg_const_i64(a->imm << a->msz); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + tcg_temp_free_i64(imm); + return true; +} + static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) { /* Indexed by [xs][msz]. */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rpri_load rd pg rn imm dtype nreg &rprr_store rd pg rn rm msz esz nreg &rpri_store rd pg rn imm msz esz nreg +&rprr_gather_load rd pg rn rm esz msz u ff xs scale +&rpri_gather_load rd pg rn imm esz msz u ff &rprr_scatter_store rd pg rn rm esz msz xs scale ########################################################################### @@ -XXX,XX +XXX,XX @@ @rpri_load_msz ....... .... . imm:s4 ... pg:3 rn:5 rd:5 \ &rpri_load dtype=%msz_dtype +# Gather Loads. +@rprr_g_load_u ....... .. . . rm:5 . u:1 ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=2 +@rprr_g_load_xs_u ....... .. xs:1 . rm:5 . u:1 ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load +@rprr_g_load_xs_u_sc ....... .. xs:1 scale:1 rm:5 . u:1 ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load +@rprr_g_load_xs_sc ....... .. xs:1 scale:1 rm:5 . . ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load +@rprr_g_load_u_sc ....... .. . scale:1 rm:5 . u:1 ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=2 +@rprr_g_load_sc ....... .. . scale:1 rm:5 . . ff:1 pg:3 rn:5 rd:5 \ + &rprr_gather_load xs=2 +@rpri_g_load ....... msz:2 .. imm:5 . u:1 ff:1 pg:3 rn:5 rd:5 \ + &rpri_gather_load + # Stores; user must fill in ESZ, MSZ, NREG as needed. @rprr_store ....... .. .. rm:5 ... pg:3 rn:5 rd:5 &rprr_store @rpri_store_msz ....... msz:2 .. . imm:s4 ... pg:3 rn:5 rd:5 &rpri_store @@ -XXX,XX +XXX,XX @@ LDR_zri 10000101 10 ...... 010 ... ..... ..... @rd_rn_i9 LD1R_zpri 1000010 .. 1 imm:6 1.. pg:3 rn:5 rd:5 \ &rpri_load dtype=%dtype_23_13 nreg=0 +# SVE 32-bit gather load (scalar plus 32-bit unscaled offsets) +# SVE 32-bit gather load (scalar plus 32-bit scaled offsets) +LD1_zprz 1000010 00 .0 ..... 0.. ... ..... ..... \ + @rprr_g_load_xs_u esz=2 msz=0 scale=0 +LD1_zprz 1000010 01 .. ..... 0.. ... ..... ..... \ + @rprr_g_load_xs_u_sc esz=2 msz=1 +LD1_zprz 1000010 10 .. ..... 01. ... ..... ..... \ + @rprr_g_load_xs_sc esz=2 msz=2 u=1 + +# SVE 32-bit gather load (vector plus immediate) +LD1_zpiz 1000010 .. 01 ..... 1.. ... ..... ..... \ + @rpri_g_load esz=2 + ### SVE Memory Contiguous Load Group # SVE contiguous load (scalar plus scalar) @@ -XXX,XX +XXX,XX @@ PRF_rr 1000010 -- 00 rm:5 110 --- ----- 0 ---- ### SVE Memory 64-bit Gather Group +# SVE 64-bit gather load (scalar plus 32-bit unpacked unscaled offsets) +# SVE 64-bit gather load (scalar plus 32-bit unpacked scaled offsets) +LD1_zprz 1100010 00 .0 ..... 0.. ... ..... ..... \ + @rprr_g_load_xs_u esz=3 msz=0 scale=0 +LD1_zprz 1100010 01 .. ..... 0.. ... ..... ..... \ + @rprr_g_load_xs_u_sc esz=3 msz=1 +LD1_zprz 1100010 10 .. ..... 0.. ... ..... ..... \ + @rprr_g_load_xs_u_sc esz=3 msz=2 +LD1_zprz 1100010 11 .. ..... 01. ... ..... ..... \ + @rprr_g_load_xs_sc esz=3 msz=3 u=1 + +# SVE 64-bit gather load (scalar plus 64-bit unscaled offsets) +# SVE 64-bit gather load (scalar plus 64-bit scaled offsets) +LD1_zprz 1100010 00 10 ..... 1.. ... ..... ..... \ + @rprr_g_load_u esz=3 msz=0 scale=0 +LD1_zprz 1100010 01 1. ..... 1.. ... ..... ..... \ + @rprr_g_load_u_sc esz=3 msz=1 +LD1_zprz 1100010 10 1. ..... 1.. ... ..... ..... \ + @rprr_g_load_u_sc esz=3 msz=2 +LD1_zprz 1100010 11 1. ..... 11. ... ..... ..... \ + @rprr_g_load_sc esz=3 msz=3 u=1 + +# SVE 64-bit gather load (vector plus immediate) +LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ + @rpri_g_load esz=3 + # SVE 64-bit gather prefetch (scalar plus 64-bit scaled offsets) PRF 1100010 00 11 ----- 1-- --- ----- 0 ---- -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 67 +++++++++++++++++++++++++++++ target/arm/sve_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 40 ++++++++++++++++- 3 files changed, 193 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_ldhds_zd, TCG_CALL_NO_WG, DEF_HELPER_FLAGS_6(sve_ldsds_zd, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbsu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhsu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffssu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbss_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldffbsu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhsu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffssu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbss_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhss_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldffbdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffddu_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_zsu, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldffbdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffddu_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_zss, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_6(sve_ldffbdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsdu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffddu_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffbds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffhds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_6(sve_ldffsds_zd, TCG_CALL_NO_WG, + void, env, ptr, ptr, ptr, tl, i32) + DEF_HELPER_FLAGS_6(sve_stbs_zsu, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_6(sve_sths_zsu, TCG_CALL_NO_WG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LD1_ZPZ_D(sve_ldbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) DO_LD1_ZPZ_D(sve_ldhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) DO_LD1_ZPZ_D(sve_ldsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) +/* First fault loads with a vector index. */ + +#ifdef CONFIG_USER_ONLY + +#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + unsigned scale = simd_data(desc); \ + uintptr_t ra = GETPC(); \ + bool first = true; \ + mmap_lock(); \ + for (i = 0; i < oprsz; i++) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPEM m = 0; \ + if (pg & 1) { \ + target_ulong off = *(TYPEI *)(vm + H(i)); \ + target_ulong addr = base + (off << scale); \ + if (!first && \ + page_check_range(addr, sizeof(TYPEM), PAGE_READ)) { \ + record_fault(env, i, oprsz); \ + goto exit; \ + } \ + m = FN(env, addr, ra); \ + first = false; \ + } \ + *(TYPEE *)(vd + H(i)) = m; \ + i += sizeof(TYPEE), pg >>= sizeof(TYPEE); \ + } while (i & 15); \ + } \ + exit: \ + mmap_unlock(); \ +} + +#else + +#define DO_LDFF1_ZPZ(NAME, TYPEE, TYPEI, TYPEM, FN, H) \ +void HELPER(NAME)(CPUARMState *env, void *vd, void *vg, void *vm, \ + target_ulong base, uint32_t desc) \ +{ \ + g_assert_not_reached(); \ +} + +#endif + +#define DO_LDFF1_ZPZ_S(NAME, TYPEI, TYPEM, FN) \ + DO_LDFF1_ZPZ(NAME, uint32_t, TYPEI, TYPEM, FN, H1_4) +#define DO_LDFF1_ZPZ_D(NAME, TYPEI, TYPEM, FN) \ + DO_LDFF1_ZPZ(NAME, uint64_t, TYPEI, TYPEM, FN, ) + +DO_LDFF1_ZPZ_S(sve_ldffbsu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffhsu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffssu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffbss_zsu, uint32_t, int8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffhss_zsu, uint32_t, int16_t, cpu_lduw_data_ra) + +DO_LDFF1_ZPZ_S(sve_ldffbsu_zss, int32_t, uint8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffhsu_zss, int32_t, uint16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffssu_zss, int32_t, uint32_t, cpu_ldl_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffbss_zss, int32_t, int8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_S(sve_ldffhss_zss, int32_t, int16_t, cpu_lduw_data_ra) + +DO_LDFF1_ZPZ_D(sve_ldffbdu_zsu, uint32_t, uint8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhdu_zsu, uint32_t, uint16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsdu_zsu, uint32_t, uint32_t, cpu_ldl_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffddu_zsu, uint32_t, uint64_t, cpu_ldq_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffbds_zsu, uint32_t, int8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhds_zsu, uint32_t, int16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsds_zsu, uint32_t, int32_t, cpu_ldl_data_ra) + +DO_LDFF1_ZPZ_D(sve_ldffbdu_zss, int32_t, uint8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhdu_zss, int32_t, uint16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsdu_zss, int32_t, uint32_t, cpu_ldl_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffddu_zss, int32_t, uint64_t, cpu_ldq_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffbds_zss, int32_t, int8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhds_zss, int32_t, int16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsds_zss, int32_t, int32_t, cpu_ldl_data_ra) + +DO_LDFF1_ZPZ_D(sve_ldffbdu_zd, uint64_t, uint8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhdu_zd, uint64_t, uint16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsdu_zd, uint64_t, uint32_t, cpu_ldl_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffddu_zd, uint64_t, uint64_t, cpu_ldq_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffbds_zd, uint64_t, int8_t, cpu_ldub_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffhds_zd, uint64_t, int16_t, cpu_lduw_data_ra) +DO_LDFF1_ZPZ_D(sve_ldffsds_zd, uint64_t, int32_t, cpu_ldl_data_ra) + /* Stores with a vector index. */ #define DO_ST1_ZPZ_S(NAME, TYPEI, FN) \ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn32[2][2][2][3] = { { gen_helper_sve_ldbsu_zss, gen_helper_sve_ldhsu_zss, gen_helper_sve_ldssu_zss, } } }, - /* TODO fill in first-fault handlers */ + + { { { gen_helper_sve_ldffbss_zsu, + gen_helper_sve_ldffhss_zsu, + NULL, }, + { gen_helper_sve_ldffbsu_zsu, + gen_helper_sve_ldffhsu_zsu, + gen_helper_sve_ldffssu_zsu, } }, + { { gen_helper_sve_ldffbss_zss, + gen_helper_sve_ldffhss_zss, + NULL, }, + { gen_helper_sve_ldffbsu_zss, + gen_helper_sve_ldffhsu_zss, + gen_helper_sve_ldffssu_zss, } } } }; /* Note that we overload xs=2 to indicate 64-bit offset. */ @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_mem_scatter * const gather_load_fn64[2][3][2][4] = { gen_helper_sve_ldhdu_zd, gen_helper_sve_ldsdu_zd, gen_helper_sve_ldddu_zd, } } }, - /* TODO fill in first-fault handlers */ + + { { { gen_helper_sve_ldffbds_zsu, + gen_helper_sve_ldffhds_zsu, + gen_helper_sve_ldffsds_zsu, + NULL, }, + { gen_helper_sve_ldffbdu_zsu, + gen_helper_sve_ldffhdu_zsu, + gen_helper_sve_ldffsdu_zsu, + gen_helper_sve_ldffddu_zsu, } }, + { { gen_helper_sve_ldffbds_zss, + gen_helper_sve_ldffhds_zss, + gen_helper_sve_ldffsds_zss, + NULL, }, + { gen_helper_sve_ldffbdu_zss, + gen_helper_sve_ldffhdu_zss, + gen_helper_sve_ldffsdu_zss, + gen_helper_sve_ldffddu_zss, } }, + { { gen_helper_sve_ldffbds_zd, + gen_helper_sve_ldffhds_zd, + gen_helper_sve_ldffsds_zd, + NULL, }, + { gen_helper_sve_ldffbdu_zd, + gen_helper_sve_ldffhdu_zd, + gen_helper_sve_ldffsdu_zd, + gen_helper_sve_ldffddu_zd, } } } }; static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a, uint32_t insn) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 85 ++++++++++++++++++++++++++------------ target/arm/sve.decode | 11 +++++ 2 files changed, 70 insertions(+), 26 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a, uint32_t insn) return true; } +/* Indexed by [xs][msz]. */ +static gen_helper_gvec_mem_scatter * const scatter_store_fn32[2][3] = { + { gen_helper_sve_stbs_zsu, + gen_helper_sve_sths_zsu, + gen_helper_sve_stss_zsu, }, + { gen_helper_sve_stbs_zss, + gen_helper_sve_sths_zss, + gen_helper_sve_stss_zss, }, +}; + +/* Note that we overload xs=2 to indicate 64-bit offset. */ +static gen_helper_gvec_mem_scatter * const scatter_store_fn64[3][4] = { + { gen_helper_sve_stbd_zsu, + gen_helper_sve_sthd_zsu, + gen_helper_sve_stsd_zsu, + gen_helper_sve_stdd_zsu, }, + { gen_helper_sve_stbd_zss, + gen_helper_sve_sthd_zss, + gen_helper_sve_stsd_zss, + gen_helper_sve_stdd_zss, }, + { gen_helper_sve_stbd_zd, + gen_helper_sve_sthd_zd, + gen_helper_sve_stsd_zd, + gen_helper_sve_stdd_zd, }, +}; + static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) { - /* Indexed by [xs][msz]. */ - static gen_helper_gvec_mem_scatter * const fn32[2][3] = { - { gen_helper_sve_stbs_zsu, - gen_helper_sve_sths_zsu, - gen_helper_sve_stss_zsu, }, - { gen_helper_sve_stbs_zss, - gen_helper_sve_sths_zss, - gen_helper_sve_stss_zss, }, - }; - /* Note that we overload xs=2 to indicate 64-bit offset. */ - static gen_helper_gvec_mem_scatter * const fn64[3][4] = { - { gen_helper_sve_stbd_zsu, - gen_helper_sve_sthd_zsu, - gen_helper_sve_stsd_zsu, - gen_helper_sve_stdd_zsu, }, - { gen_helper_sve_stbd_zss, - gen_helper_sve_sthd_zss, - gen_helper_sve_stsd_zss, - gen_helper_sve_stdd_zss, }, - { gen_helper_sve_stbd_zd, - gen_helper_sve_sthd_zd, - gen_helper_sve_stsd_zd, - gen_helper_sve_stdd_zd, }, - }; gen_helper_gvec_mem_scatter *fn; if (a->esz < a->msz || (a->msz == 0 && a->scale)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) } switch (a->esz) { case MO_32: - fn = fn32[a->xs][a->msz]; + fn = scatter_store_fn32[a->xs][a->msz]; break; case MO_64: - fn = fn64[a->xs][a->msz]; + fn = scatter_store_fn64[a->xs][a->msz]; break; default: g_assert_not_reached(); @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a, uint32_t insn) return true; } +static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a, uint32_t insn) +{ + gen_helper_gvec_mem_scatter *fn = NULL; + TCGv_i64 imm; + + if (a->esz < a->msz) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + switch (a->esz) { + case MO_32: + fn = scatter_store_fn32[0][a->msz]; + break; + case MO_64: + fn = scatter_store_fn64[2][a->msz]; + break; + } + assert(fn != NULL); + + /* Treat ST1_zpiz (zn[x] + imm) the same way as ST1_zprz (rn + zm[x]) + * by loading the immediate into the scalar parameter. + */ + imm = tcg_const_i64(a->imm << a->msz); + do_mem_zpz(s, a->rd, a->pg, a->rn, 0, imm, fn); + tcg_temp_free_i64(imm); + return true; +} + /* * Prefetches */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ &rprr_gather_load rd pg rn rm esz msz u ff xs scale &rpri_gather_load rd pg rn imm esz msz u ff &rprr_scatter_store rd pg rn rm esz msz xs scale +&rpri_scatter_store rd pg rn imm esz msz ########################################################################### # Named instruction formats. These are generally used to @@ -XXX,XX +XXX,XX @@ &rprr_store nreg=0 @rprr_scatter_store ....... msz:2 .. rm:5 ... pg:3 rn:5 rd:5 \ &rprr_scatter_store +@rpri_scatter_store ....... msz:2 .. imm:5 ... pg:3 rn:5 rd:5 \ + &rpri_scatter_store ########################################################################### # Instruction patterns. Grouped according to the SVE encodingindex.xhtml. @@ -XXX,XX +XXX,XX @@ ST1_zprz 1110010 .. 01 ..... 101 ... ..... ..... \ ST1_zprz 1110010 .. 00 ..... 101 ... ..... ..... \ @rprr_scatter_store xs=2 esz=3 scale=0 +# SVE 64-bit scatter store (vector plus immediate) +ST1_zpiz 1110010 .. 10 ..... 101 ... ..... ..... \ + @rpri_scatter_store esz=3 + +# SVE 32-bit scatter store (vector plus immediate) +ST1_zpiz 1110010 .. 11 ..... 101 ... ..... ..... \ + @rpri_scatter_store esz=2 + # SVE 64-bit scatter store (scalar plus unpacked 32-bit scaled offset) # Require msz > 0 ST1_zprz 1110010 .. 01 ..... 100 ... ..... ..... \ -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 49 ++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 62 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 40 ++++++++++++++++++++++++ target/arm/sve.decode | 11 +++++++ 4 files changed, 162 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmge_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmge_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmge_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmgt_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmgt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmgt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmeq_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmeq_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmeq_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmne_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmne_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmne_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fcmuo_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmuo_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcmuo_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_facge_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facge_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facge_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_facgt_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fnmls_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) do_fmla_zpzzz_d(env, vg, desc, 0, INT64_MIN); } +/* Two operand floating-point comparison controlled by a predicate. + * Unlike the integer version, we are not allowed to optimistically + * compare operands, since the comparison may have side effects wrt + * the FPSR. + */ +#define DO_FPCMP_PPZZ(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc), j = (i - 1) >> 6; \ + uint64_t *d = vd, *g = vg; \ + do { \ + uint64_t out = 0, pg = g[j]; \ + do { \ + i -= sizeof(TYPE), out <<= sizeof(TYPE); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + TYPE mm = *(TYPE *)(vm + H(i)); \ + out |= OP(TYPE, nn, mm, status); \ + } \ + } while (i & 63); \ + d[j--] = out; \ + } while (i > 0); \ +} + +#define DO_FPCMP_PPZZ_H(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_h, float16, H1_2, OP) +#define DO_FPCMP_PPZZ_S(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_s, float32, H1_4, OP) +#define DO_FPCMP_PPZZ_D(NAME, OP) \ + DO_FPCMP_PPZZ(NAME##_d, float64, , OP) + +#define DO_FPCMP_PPZZ_ALL(NAME, OP) \ + DO_FPCMP_PPZZ_H(NAME, OP) \ + DO_FPCMP_PPZZ_S(NAME, OP) \ + DO_FPCMP_PPZZ_D(NAME, OP) + +#define DO_FCMGE(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) <= 0 +#define DO_FCMGT(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) < 0 +#define DO_FCMEQ(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) == 0 +#define DO_FCMNE(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) != 0 +#define DO_FCMUO(TYPE, X, Y, ST) \ + TYPE##_compare_quiet(X, Y, ST) == float_relation_unordered +#define DO_FACGE(TYPE, X, Y, ST) \ + TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) <= 0 +#define DO_FACGT(TYPE, X, Y, ST) \ + TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) < 0 + +DO_FPCMP_PPZZ_ALL(sve_fcmge, DO_FCMGE) +DO_FPCMP_PPZZ_ALL(sve_fcmgt, DO_FCMGT) +DO_FPCMP_PPZZ_ALL(sve_fcmeq, DO_FCMEQ) +DO_FPCMP_PPZZ_ALL(sve_fcmne, DO_FCMNE) +DO_FPCMP_PPZZ_ALL(sve_fcmuo, DO_FCMUO) +DO_FPCMP_PPZZ_ALL(sve_facge, DO_FACGE) +DO_FPCMP_PPZZ_ALL(sve_facgt, DO_FACGT) + +#undef DO_FPCMP_PPZZ_ALL +#undef DO_FPCMP_PPZZ_D +#undef DO_FPCMP_PPZZ_S +#undef DO_FPCMP_PPZZ_H +#undef DO_FPCMP_PPZZ + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FP3(FMULX, fmulx) #undef DO_FP3 +static bool do_fp_cmp(DisasContext *s, arg_rprr_esz *a, + gen_helper_gvec_4_ptr *fn) +{ + if (fn == NULL) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_4_ptr(pred_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); + } + return true; +} + +#define DO_FPCMP(NAME, name) \ +static bool trans_##NAME##_ppzz(DisasContext *s, arg_rprr_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_gvec_4_ptr * const fns[4] = { \ + NULL, gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, gen_helper_sve_##name##_d \ + }; \ + return do_fp_cmp(s, a, fns[a->esz]); \ +} + +DO_FPCMP(FCMGE, fcmge) +DO_FPCMP(FCMGT, fcmgt) +DO_FPCMP(FCMEQ, fcmeq) +DO_FPCMP(FCMNE, fcmne) +DO_FPCMP(FCMUO, fcmuo) +DO_FPCMP(FACGE, facge) +DO_FPCMP(FACGT, facgt) + +#undef DO_FPCMP + typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32); static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UXTH 00000100 .. 010 011 101 ... ..... ..... @rd_pg_rn SXTW 00000100 .. 010 100 101 ... ..... ..... @rd_pg_rn UXTW 00000100 .. 010 101 101 ... ..... ..... @rd_pg_rn +### SVE Floating Point Compare - Vectors Group + +# SVE floating-point compare vectors +FCMGE_ppzz 01100101 .. 0 ..... 010 ... ..... 0 .... @pd_pg_rn_rm +FCMGT_ppzz 01100101 .. 0 ..... 010 ... ..... 1 .... @pd_pg_rn_rm +FCMEQ_ppzz 01100101 .. 0 ..... 011 ... ..... 0 .... @pd_pg_rn_rm +FCMNE_ppzz 01100101 .. 0 ..... 011 ... ..... 1 .... @pd_pg_rn_rm +FCMUO_ppzz 01100101 .. 0 ..... 110 ... ..... 0 .... @pd_pg_rn_rm +FACGE_ppzz 01100101 .. 0 ..... 110 ... ..... 1 .... @pd_pg_rn_rm +FACGT_ppzz 01100101 .. 0 ..... 111 ... ..... 1 .... @pd_pg_rn_rm + ### SVE Integer Multiply-Add Group # SVE integer multiply-add writing addend (predicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 56 ++++++++++++++++++++++++++++ target/arm/sve_helper.c | 69 +++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 75 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 14 +++++++ 4 files changed, 214 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_fmulx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(sve_fmulx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadds_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadds_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fadds_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fsubs_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsubs_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsubs_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmuls_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmuls_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmuls_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fsubrs_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsubrs_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fsubrs_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmaxnms_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxnms_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxnms_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fminnms_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fminnms_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fminnms_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmaxs_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxs_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmaxs_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + +DEF_HELPER_FLAGS_6(sve_fmins_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmins_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fmins_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, i64, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(sve_fmulx_d, uint64_t, , helper_vfp_mulxd) #undef DO_ZPZZ_FP +/* Three-operand expander, with one scalar operand, controlled by + * a predicate, with the extra float_status parameter. + */ +#define DO_ZPZS_FP(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, uint64_t scalar, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc); \ + uint64_t *g = vg; \ + TYPE mm = scalar; \ + do { \ + uint64_t pg = g[(i - 1) >> 6]; \ + do { \ + i -= sizeof(TYPE); \ + if (likely((pg >> (i & 63)) & 1)) { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + *(TYPE *)(vd + H(i)) = OP(nn, mm, status); \ + } \ + } while (i & 63); \ + } while (i != 0); \ +} + +DO_ZPZS_FP(sve_fadds_h, float16, H1_2, float16_add) +DO_ZPZS_FP(sve_fadds_s, float32, H1_4, float32_add) +DO_ZPZS_FP(sve_fadds_d, float64, , float64_add) + +DO_ZPZS_FP(sve_fsubs_h, float16, H1_2, float16_sub) +DO_ZPZS_FP(sve_fsubs_s, float32, H1_4, float32_sub) +DO_ZPZS_FP(sve_fsubs_d, float64, , float64_sub) + +DO_ZPZS_FP(sve_fmuls_h, float16, H1_2, float16_mul) +DO_ZPZS_FP(sve_fmuls_s, float32, H1_4, float32_mul) +DO_ZPZS_FP(sve_fmuls_d, float64, , float64_mul) + +static inline float16 subr_h(float16 a, float16 b, float_status *s) +{ + return float16_sub(b, a, s); +} + +static inline float32 subr_s(float32 a, float32 b, float_status *s) +{ + return float32_sub(b, a, s); +} + +static inline float64 subr_d(float64 a, float64 b, float_status *s) +{ + return float64_sub(b, a, s); +} + +DO_ZPZS_FP(sve_fsubrs_h, float16, H1_2, subr_h) +DO_ZPZS_FP(sve_fsubrs_s, float32, H1_4, subr_s) +DO_ZPZS_FP(sve_fsubrs_d, float64, , subr_d) + +DO_ZPZS_FP(sve_fmaxnms_h, float16, H1_2, float16_maxnum) +DO_ZPZS_FP(sve_fmaxnms_s, float32, H1_4, float32_maxnum) +DO_ZPZS_FP(sve_fmaxnms_d, float64, , float64_maxnum) + +DO_ZPZS_FP(sve_fminnms_h, float16, H1_2, float16_minnum) +DO_ZPZS_FP(sve_fminnms_s, float32, H1_4, float32_minnum) +DO_ZPZS_FP(sve_fminnms_d, float64, , float64_minnum) + +DO_ZPZS_FP(sve_fmaxs_h, float16, H1_2, float16_max) +DO_ZPZS_FP(sve_fmaxs_s, float32, H1_4, float32_max) +DO_ZPZS_FP(sve_fmaxs_d, float64, , float64_max) + +DO_ZPZS_FP(sve_fmins_h, float16, H1_2, float16_min) +DO_ZPZS_FP(sve_fmins_s, float32, H1_4, float32_min) +DO_ZPZS_FP(sve_fmins_d, float64, , float64_min) + /* Fully general two-operand expander, controlled by a predicate, * With the extra float_status parameter. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ #include "exec/log.h" #include "trace-tcg.h" #include "translate-a64.h" +#include "fpu/softfloat.h" typedef void GVecGen2sFn(unsigned, uint32_t, uint32_t, @@ -XXX,XX +XXX,XX @@ DO_FP3(FMULX, fmulx) #undef DO_FP3 +typedef void gen_helper_sve_fp2scalar(TCGv_ptr, TCGv_ptr, TCGv_ptr, + TCGv_i64, TCGv_ptr, TCGv_i32); + +static void do_fp_scalar(DisasContext *s, int zd, int zn, int pg, bool is_fp16, + TCGv_i64 scalar, gen_helper_sve_fp2scalar *fn) +{ + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr t_zd, t_zn, t_pg, status; + TCGv_i32 desc; + + t_zd = tcg_temp_new_ptr(); + t_zn = tcg_temp_new_ptr(); + t_pg = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(t_zd, cpu_env, vec_full_reg_offset(s, zd)); + tcg_gen_addi_ptr(t_zn, cpu_env, vec_full_reg_offset(s, zn)); + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, pg)); + + status = get_fpstatus_ptr(is_fp16); + desc = tcg_const_i32(simd_desc(vsz, vsz, 0)); + fn(t_zd, t_zn, t_pg, scalar, status, desc); + + tcg_temp_free_i32(desc); + tcg_temp_free_ptr(status); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_ptr(t_zn); + tcg_temp_free_ptr(t_zd); +} + +static void do_fp_imm(DisasContext *s, arg_rpri_esz *a, uint64_t imm, + gen_helper_sve_fp2scalar *fn) +{ + TCGv_i64 temp = tcg_const_i64(imm); + do_fp_scalar(s, a->rd, a->rn, a->pg, a->esz == MO_16, temp, fn); + tcg_temp_free_i64(temp); +} + +#define DO_FP_IMM(NAME, name, const0, const1) \ +static bool trans_##NAME##_zpzi(DisasContext *s, arg_rpri_esz *a, \ + uint32_t insn) \ +{ \ + static gen_helper_sve_fp2scalar * const fns[3] = { \ + gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, \ + gen_helper_sve_##name##_d \ + }; \ + static uint64_t const val[3][2] = { \ + { float16_##const0, float16_##const1 }, \ + { float32_##const0, float32_##const1 }, \ + { float64_##const0, float64_##const1 }, \ + }; \ + if (a->esz == 0) { \ + return false; \ + } \ + if (sve_access_check(s)) { \ + do_fp_imm(s, a, val[a->esz - 1][a->imm], fns[a->esz - 1]); \ + } \ + return true; \ +} + +#define float16_two make_float16(0x4000) +#define float32_two make_float32(0x40000000) +#define float64_two make_float64(0x4000000000000000ULL) + +DO_FP_IMM(FADD, fadds, half, one) +DO_FP_IMM(FSUB, fsubs, half, one) +DO_FP_IMM(FMUL, fmuls, half, two) +DO_FP_IMM(FSUBR, fsubrs, half, one) +DO_FP_IMM(FMAXNM, fmaxnms, zero, one) +DO_FP_IMM(FMINNM, fminnms, zero, one) +DO_FP_IMM(FMAX, fmaxs, zero, one) +DO_FP_IMM(FMIN, fmins, zero, one) + +#undef DO_FP_IMM + static bool do_fp_cmp(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4_ptr *fn) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ @rdn_pg4 ........ esz:2 .. pg:4 ... ........ rd:5 \ &rpri_esz rn=%reg_movprfx +# Two register operand, one one-bit floating-point operand. +@rdn_i1 ........ esz:2 ......... pg:3 .... imm:1 rd:5 \ + &rpri_esz rn=%reg_movprfx + # Two register operand, one encoded bitmask. @rdn_dbm ........ .. .... dbm:13 rd:5 \ &rr_dbm rn=%reg_movprfx @@ -XXX,XX +XXX,XX @@ FMULX 01100101 .. 00 1010 100 ... ..... ..... @rdn_pg_rm FDIV 01100101 .. 00 1100 100 ... ..... ..... @rdm_pg_rn # FDIVR FDIV 01100101 .. 00 1101 100 ... ..... ..... @rdn_pg_rm +# SVE floating-point arithmetic with immediate (predicated) +FADD_zpzi 01100101 .. 011 000 100 ... 0000 . ..... @rdn_i1 +FSUB_zpzi 01100101 .. 011 001 100 ... 0000 . ..... @rdn_i1 +FMUL_zpzi 01100101 .. 011 010 100 ... 0000 . ..... @rdn_i1 +FSUBR_zpzi 01100101 .. 011 011 100 ... 0000 . ..... @rdn_i1 +FMAXNM_zpzi 01100101 .. 011 100 100 ... 0000 . ..... @rdn_i1 +FMINNM_zpzi 01100101 .. 011 101 100 ... 0000 . ..... @rdn_i1 +FMAX_zpzi 01100101 .. 011 110 100 ... 0000 . ..... @rdn_i1 +FMIN_zpzi 01100101 .. 011 111 100 ... 0000 . ..... @rdn_i1 + ### SVE FP Multiply-Add Group # SVE floating-point multiply-accumulate writing addend -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 14 +++++++++++ target/arm/translate-sve.c | 50 ++++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 48 ++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 19 +++++++++++++++ 4 files changed, 131 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI +/* + *** SVE Floating Point Multiply-Add Indexed Group + */ + +static bool trans_FMLA_zzxz(DisasContext *s, arg_FMLA_zzxz *a, uint32_t insn) +{ + static gen_helper_gvec_4_ptr * const fns[3] = { + gen_helper_gvec_fmla_idx_h, + gen_helper_gvec_fmla_idx_s, + gen_helper_gvec_fmla_idx_d, + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vec_full_reg_offset(s, a->ra), + status, vsz, vsz, (a->index << 1) | a->sub, + fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + +/* + *** SVE Floating Point Multiply Indexed Group + */ + +static bool trans_FMUL_zzx(DisasContext *s, arg_FMUL_zzx *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] = { + gen_helper_gvec_fmul_idx_h, + gen_helper_gvec_fmul_idx_s, + gen_helper_gvec_fmul_idx_d, + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + status, vsz, vsz, a->index, fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64) #endif #undef DO_3OP + +/* For the indexed ops, SVE applies the index per 128-bit vector segment. + * For AdvSIMD, there is of course only one such vector segment. + */ + +#define DO_MUL_IDX(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t idx = simd_data(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ + TYPE mm = m[H(i + idx)]; \ + for (j = 0; j < segment; j++) { \ + d[i + j] = TYPE##_mul(n[i + j], mm, stat); \ + } \ + } \ +} + +DO_MUL_IDX(gvec_fmul_idx_h, float16, H2) +DO_MUL_IDX(gvec_fmul_idx_s, float32, H4) +DO_MUL_IDX(gvec_fmul_idx_d, float64, ) + +#undef DO_MUL_IDX + +#define DO_FMLA_IDX(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ + void *stat, uint32_t desc) \ +{ \ + intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1); \ + intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1); \ + TYPE *d = vd, *n = vn, *m = vm, *a = va; \ + op1_neg <<= (8 * sizeof(TYPE) - 1); \ + for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ + TYPE mm = m[H(i + idx)]; \ + for (j = 0; j < segment; j++) { \ + d[i + j] = TYPE##_muladd(n[i + j] ^ op1_neg, \ + mm, a[i + j], 0, stat); \ + } \ + } \ +} + +DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2) +DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4) +DO_FMLA_IDX(gvec_fmla_idx_d, float64, ) + +#undef DO_FMLA_IDX diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ %imm9_16_10 16:s6 10:3 %size_23 23:2 %dtype_23_13 23:2 13:2 +%index3_22_19 22:1 19:2 # A combination of tsz:imm3 -- extract esize. %tszimm_esz 22:2 5:5 !function=tszimm_esz @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s +### SVE FP Multiply-Add Indexed Group + +# SVE floating-point multiply-add (indexed) +FMLA_zzxz 01100100 0.1 .. rm:3 00000 sub:1 rn:5 rd:5 \ + ra=%reg_movprfx index=%index3_22_19 esz=1 +FMLA_zzxz 01100100 101 index:2 rm:3 00000 sub:1 rn:5 rd:5 \ + ra=%reg_movprfx esz=2 +FMLA_zzxz 01100100 111 index:1 rm:4 00000 sub:1 rn:5 rd:5 \ + ra=%reg_movprfx esz=3 + +### SVE FP Multiply Indexed Group + +# SVE floating-point multiply (indexed) +FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \ + index=%index3_22_19 esz=1 +FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=2 +FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3 + ### SVE FP Accumulating Reduction Group # SVE floating-point serial reduction (predicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 35 ++++++++++++++++++++++ target/arm/sve_helper.c | 61 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 57 +++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 8 +++++ 4 files changed, 161 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_faddv_h, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_faddv_s, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_faddv_d, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_fmaxnmv_h, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fmaxnmv_s, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fmaxnmv_d, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_fminnmv_h, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fminnmv_s, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fminnmv_d, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_fmaxv_h, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fmaxv_s, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fmaxv_d, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(sve_fminv_h, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fminv_s, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sve_fminv_d, TCG_CALL_NO_RWG, + i64, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG, i64, i64, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc) return predtest_ones(d, oprsz, esz_mask); } +/* Recursive reduction on a function; + * C.f. the ARM ARM function ReducePredicated. + * + * While it would be possible to write this without the DATA temporary, + * it is much simpler to process the predicate register this way. + * The recursion is bounded to depth 7 (128 fp16 elements), so there's + * little to gain with a more complex non-recursive form. + */ +#define DO_REDUCE(NAME, TYPE, H, FUNC, IDENT) \ +static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \ +{ \ + if (n == 1) { \ + return *data; \ + } else { \ + uintptr_t half = n / 2; \ + TYPE lo = NAME##_reduce(data, status, half); \ + TYPE hi = NAME##_reduce(data + half, status, half); \ + return TYPE##_##FUNC(lo, hi, status); \ + } \ +} \ +uint64_t HELPER(NAME)(void *vn, void *vg, void *vs, uint32_t desc) \ +{ \ + uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_maxsz(desc); \ + TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + *(TYPE *)((void *)data + i) = (pg & 1 ? nn : IDENT); \ + i += sizeof(TYPE), pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ + for (; i < maxsz; i += sizeof(TYPE)) { \ + *(TYPE *)((void *)data + i) = IDENT; \ + } \ + return NAME##_reduce(data, vs, maxsz / sizeof(TYPE)); \ +} + +DO_REDUCE(sve_faddv_h, float16, H1_2, add, float16_zero) +DO_REDUCE(sve_faddv_s, float32, H1_4, add, float32_zero) +DO_REDUCE(sve_faddv_d, float64, , add, float64_zero) + +/* Identity is floatN_default_nan, without the function call. */ +DO_REDUCE(sve_fminnmv_h, float16, H1_2, minnum, 0x7E00) +DO_REDUCE(sve_fminnmv_s, float32, H1_4, minnum, 0x7FC00000) +DO_REDUCE(sve_fminnmv_d, float64, , minnum, 0x7FF8000000000000ULL) + +DO_REDUCE(sve_fmaxnmv_h, float16, H1_2, maxnum, 0x7E00) +DO_REDUCE(sve_fmaxnmv_s, float32, H1_4, maxnum, 0x7FC00000) +DO_REDUCE(sve_fmaxnmv_d, float64, , maxnum, 0x7FF8000000000000ULL) + +DO_REDUCE(sve_fminv_h, float16, H1_2, min, float16_infinity) +DO_REDUCE(sve_fminv_s, float32, H1_4, min, float32_infinity) +DO_REDUCE(sve_fminv_d, float64, , min, float64_infinity) + +DO_REDUCE(sve_fmaxv_h, float16, H1_2, max, float16_chs(float16_infinity)) +DO_REDUCE(sve_fmaxv_s, float32, H1_4, max, float32_chs(float32_infinity)) +DO_REDUCE(sve_fmaxv_d, float64, , max, float64_chs(float64_infinity)) + +#undef DO_REDUCE + uint64_t HELPER(sve_fadda_h)(uint64_t nn, void *vm, void *vg, void *status, uint32_t desc) { diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FMUL_zzx(DisasContext *s, arg_FMUL_zzx *a, uint32_t insn) return true; } +/* + *** SVE Floating Point Fast Reduction Group + */ + +typedef void gen_helper_fp_reduce(TCGv_i64, TCGv_ptr, TCGv_ptr, + TCGv_ptr, TCGv_i32); + +static void do_reduce(DisasContext *s, arg_rpr_esz *a, + gen_helper_fp_reduce *fn) +{ + unsigned vsz = vec_full_reg_size(s); + unsigned p2vsz = pow2ceil(vsz); + TCGv_i32 t_desc = tcg_const_i32(simd_desc(vsz, p2vsz, 0)); + TCGv_ptr t_zn, t_pg, status; + TCGv_i64 temp; + + temp = tcg_temp_new_i64(); + t_zn = tcg_temp_new_ptr(); + t_pg = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(t_zn, cpu_env, vec_full_reg_offset(s, a->rn)); + tcg_gen_addi_ptr(t_pg, cpu_env, pred_full_reg_offset(s, a->pg)); + status = get_fpstatus_ptr(a->esz == MO_16); + + fn(temp, t_zn, t_pg, status, t_desc); + tcg_temp_free_ptr(t_zn); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_ptr(status); + tcg_temp_free_i32(t_desc); + + write_fp_dreg(s, a->rd, temp); + tcg_temp_free_i64(temp); +} + +#define DO_VPZ(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a, uint32_t insn) \ +{ \ + static gen_helper_fp_reduce * const fns[3] = { \ + gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, \ + gen_helper_sve_##name##_d, \ + }; \ + if (a->esz == 0) { \ + return false; \ + } \ + if (sve_access_check(s)) { \ + do_reduce(s, a, fns[a->esz - 1]); \ + } \ + return true; \ +} + +DO_VPZ(FADDV, faddv) +DO_VPZ(FMINNMV, fminnmv) +DO_VPZ(FMAXNMV, fmaxnmv) +DO_VPZ(FMINV, fminv) +DO_VPZ(FMAXV, fmaxv) + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FMUL_zzx 01100100 0.1 .. rm:3 001000 rn:5 rd:5 \ FMUL_zzx 01100100 101 index:2 rm:3 001000 rn:5 rd:5 esz=2 FMUL_zzx 01100100 111 index:1 rm:4 001000 rn:5 rd:5 esz=3 +### SVE FP Fast Reduction Group + +FADDV 01100101 .. 000 000 001 ... ..... ..... @rd_pg_rn +FMAXNMV 01100101 .. 000 100 001 ... ..... ..... @rd_pg_rn +FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn +FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn +FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn + ### SVE FP Accumulating Reduction Group # SVE floating-point serial reduction (predicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 8 +++++++ target/arm/translate-sve.c | 47 ++++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 20 ++++++++++++++++ target/arm/sve.decode | 5 ++++ 4 files changed, 80 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_VPZ(FMAXNMV, fmaxnmv) DO_VPZ(FMINV, fminv) DO_VPZ(FMAXV, fmaxv) +/* + *** SVE Floating Point Unary Operations - Unpredicated Group + */ + +static void do_zz_fp(DisasContext *s, arg_rr_esz *a, gen_helper_gvec_2_ptr *fn) +{ + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); +} + +static bool trans_FRECPE(DisasContext *s, arg_rr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_2_ptr * const fns[3] = { + gen_helper_gvec_frecpe_h, + gen_helper_gvec_frecpe_s, + gen_helper_gvec_frecpe_d, + }; + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + do_zz_fp(s, a, fns[a->esz - 1]); + } + return true; +} + +static bool trans_FRSQRTE(DisasContext *s, arg_rr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_2_ptr * const fns[3] = { + gen_helper_gvec_frsqrte_h, + gen_helper_gvec_frsqrte_s, + gen_helper_gvec_frsqrte_d, + }; + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + do_zz_fp(s, a, fns[a->esz - 1]); + } + return true; +} + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +#define DO_2OP(NAME, FUNC, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], stat); \ + } \ +} + +DO_2OP(gvec_frecpe_h, helper_recpe_f16, float16) +DO_2OP(gvec_frecpe_s, helper_recpe_f32, float32) +DO_2OP(gvec_frecpe_d, helper_recpe_f64, float64) + +DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) +DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) +DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) + +#undef DO_2OP + /* Floating-point trigonometric starting value. * See the ARM ARM pseudocode function FPTrigSMul. */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FMINNMV 01100101 .. 000 101 001 ... ..... ..... @rd_pg_rn FMAXV 01100101 .. 000 110 001 ... ..... ..... @rd_pg_rn FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn +## SVE Floating Point Unary Operations - Unpredicated Group + +FRECPE 01100101 .. 001 110 001100 ..... ..... @rd_rn +FRSQRTE 01100101 .. 001 111 001100 ..... ..... @rd_rn + ### SVE FP Accumulating Reduction Group # SVE floating-point serial reduction (predicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 42 +++++++++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 43 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 43 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 10 +++++++++ 4 files changed, 138 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_fadda_d, TCG_CALL_NO_RWG, i64, i64, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmge0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmge0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmge0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcmgt0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmgt0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmgt0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcmlt0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmlt0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmlt0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcmle0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmle0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmle0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcmeq0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmeq0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmeq0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcmne0_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmne0_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcmne0_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(sve_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ #define DO_FCMGE(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) <= 0 #define DO_FCMGT(TYPE, X, Y, ST) TYPE##_compare(Y, X, ST) < 0 +#define DO_FCMLE(TYPE, X, Y, ST) TYPE##_compare(X, Y, ST) <= 0 +#define DO_FCMLT(TYPE, X, Y, ST) TYPE##_compare(X, Y, ST) < 0 #define DO_FCMEQ(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) == 0 #define DO_FCMNE(TYPE, X, Y, ST) TYPE##_compare_quiet(X, Y, ST) != 0 #define DO_FCMUO(TYPE, X, Y, ST) \ @@ -XXX,XX +XXX,XX @@ DO_FPCMP_PPZZ_ALL(sve_facgt, DO_FACGT) #undef DO_FPCMP_PPZZ_H #undef DO_FPCMP_PPZZ +/* One operand floating-point comparison against zero, controlled + * by a predicate. + */ +#define DO_FPCMP_PPZ0(NAME, TYPE, H, OP) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, \ + void *status, uint32_t desc) \ +{ \ + intptr_t i = simd_oprsz(desc), j = (i - 1) >> 6; \ + uint64_t *d = vd, *g = vg; \ + do { \ + uint64_t out = 0, pg = g[j]; \ + do { \ + i -= sizeof(TYPE), out <<= sizeof(TYPE); \ + if ((pg >> (i & 63)) & 1) { \ + TYPE nn = *(TYPE *)(vn + H(i)); \ + out |= OP(TYPE, nn, 0, status); \ + } \ + } while (i & 63); \ + d[j--] = out; \ + } while (i > 0); \ +} + +#define DO_FPCMP_PPZ0_H(NAME, OP) \ + DO_FPCMP_PPZ0(NAME##_h, float16, H1_2, OP) +#define DO_FPCMP_PPZ0_S(NAME, OP) \ + DO_FPCMP_PPZ0(NAME##_s, float32, H1_4, OP) +#define DO_FPCMP_PPZ0_D(NAME, OP) \ + DO_FPCMP_PPZ0(NAME##_d, float64, , OP) + +#define DO_FPCMP_PPZ0_ALL(NAME, OP) \ + DO_FPCMP_PPZ0_H(NAME, OP) \ + DO_FPCMP_PPZ0_S(NAME, OP) \ + DO_FPCMP_PPZ0_D(NAME, OP) + +DO_FPCMP_PPZ0_ALL(sve_fcmge0, DO_FCMGE) +DO_FPCMP_PPZ0_ALL(sve_fcmgt0, DO_FCMGT) +DO_FPCMP_PPZ0_ALL(sve_fcmle0, DO_FCMLE) +DO_FPCMP_PPZ0_ALL(sve_fcmlt0, DO_FCMLT) +DO_FPCMP_PPZ0_ALL(sve_fcmeq0, DO_FCMEQ) +DO_FPCMP_PPZ0_ALL(sve_fcmne0, DO_FCMNE) + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FRSQRTE(DisasContext *s, arg_rr_esz *a, uint32_t insn) return true; } +/* + *** SVE Floating Point Compare with Zero Group + */ + +static void do_ppz_fp(DisasContext *s, arg_rpr_esz *a, + gen_helper_gvec_3_ptr *fn) +{ + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + + tcg_gen_gvec_3_ptr(pred_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, fn); + tcg_temp_free_ptr(status); +} + +#define DO_PPZ(NAME, name) \ +static bool trans_##NAME(DisasContext *s, arg_rpr_esz *a, uint32_t insn) \ +{ \ + static gen_helper_gvec_3_ptr * const fns[3] = { \ + gen_helper_sve_##name##_h, \ + gen_helper_sve_##name##_s, \ + gen_helper_sve_##name##_d, \ + }; \ + if (a->esz == 0) { \ + return false; \ + } \ + if (sve_access_check(s)) { \ + do_ppz_fp(s, a, fns[a->esz - 1]); \ + } \ + return true; \ +} + +DO_PPZ(FCMGE_ppz0, fcmge0) +DO_PPZ(FCMGT_ppz0, fcmgt0) +DO_PPZ(FCMLE_ppz0, fcmle0) +DO_PPZ(FCMLT_ppz0, fcmlt0) +DO_PPZ(FCMEQ_ppz0, fcmeq0) +DO_PPZ(FCMNE_ppz0, fcmne0) + +#undef DO_PPZ + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ # One register operand, with governing predicate, vector element size @rd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 rd:5 &rpr_esz @rd_pg4_pn ........ esz:2 ... ... .. pg:4 . rn:4 rd:5 &rpr_esz +@pd_pg_rn ........ esz:2 ... ... ... pg:3 rn:5 . rd:4 &rpr_esz # One register operand, with governing predicate, no vector element size @rd_pg_rn_e0 ........ .. ... ... ... pg:3 rn:5 rd:5 &rpr_esz esz=0 @@ -XXX,XX +XXX,XX @@ FMINV 01100101 .. 000 111 001 ... ..... ..... @rd_pg_rn FRECPE 01100101 .. 001 110 001100 ..... ..... @rd_rn FRSQRTE 01100101 .. 001 111 001100 ..... ..... @rd_rn +### SVE FP Compare with Zero Group + +FCMGE_ppz0 01100101 .. 0100 00 001 ... ..... 0 .... @pd_pg_rn +FCMGT_ppz0 01100101 .. 0100 00 001 ... ..... 1 .... @pd_pg_rn +FCMLT_ppz0 01100101 .. 0100 01 001 ... ..... 0 .... @pd_pg_rn +FCMLE_ppz0 01100101 .. 0100 01 001 ... ..... 1 .... @pd_pg_rn +FCMEQ_ppz0 01100101 .. 0100 10 001 ... ..... 0 .... @pd_pg_rn +FCMNE_ppz0 01100101 .. 0100 11 001 ... ..... 0 .... @pd_pg_rn + ### SVE FP Accumulating Reduction Group # SVE floating-point serial reduction (predicated) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 4 +++ target/arm/sve_helper.c | 70 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 27 +++++++++++++++ target/arm/sve.decode | 3 ++ 4 files changed, 104 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_FPCMP_PPZ0_ALL(sve_fcmlt0, DO_FCMLT) DO_FPCMP_PPZ0_ALL(sve_fcmeq0, DO_FCMEQ) DO_FPCMP_PPZ0_ALL(sve_fcmne0, DO_FCMNE) +/* FP Trig Multiply-Add. */ + +void HELPER(sve_ftmad_h)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +{ + static const float16 coeff[16] = { + 0x3c00, 0xb155, 0x2030, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + 0x3c00, 0xb800, 0x293a, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, + }; + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(float16); + intptr_t x = simd_data(desc); + float16 *d = vd, *n = vn, *m = vm; + for (i = 0; i < opr_sz; i++) { + float16 mm = m[i]; + intptr_t xx = x; + if (float16_is_neg(mm)) { + mm = float16_abs(mm); + xx += 8; + } + d[i] = float16_muladd(n[i], mm, coeff[xx], 0, vs); + } +} + +void HELPER(sve_ftmad_s)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +{ + static const float32 coeff[16] = { + 0x3f800000, 0xbe2aaaab, 0x3c088886, 0xb95008b9, + 0x36369d6d, 0x00000000, 0x00000000, 0x00000000, + 0x3f800000, 0xbf000000, 0x3d2aaaa6, 0xbab60705, + 0x37cd37cc, 0x00000000, 0x00000000, 0x00000000, + }; + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(float32); + intptr_t x = simd_data(desc); + float32 *d = vd, *n = vn, *m = vm; + for (i = 0; i < opr_sz; i++) { + float32 mm = m[i]; + intptr_t xx = x; + if (float32_is_neg(mm)) { + mm = float32_abs(mm); + xx += 8; + } + d[i] = float32_muladd(n[i], mm, coeff[xx], 0, vs); + } +} + +void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +{ + static const float64 coeff[16] = { + 0x3ff0000000000000ull, 0xbfc5555555555543ull, + 0x3f8111111110f30cull, 0xbf2a01a019b92fc6ull, + 0x3ec71de351f3d22bull, 0xbe5ae5e2b60f7b91ull, + 0x3de5d8408868552full, 0x0000000000000000ull, + 0x3ff0000000000000ull, 0xbfe0000000000000ull, + 0x3fa5555555555536ull, 0xbf56c16c16c13a0bull, + 0x3efa01a019b1e8d8ull, 0xbe927e4f7282f468ull, + 0x3e21ee96d2641b13ull, 0xbda8f76380fbb401ull, + }; + intptr_t i, opr_sz = simd_oprsz(desc) / sizeof(float64); + intptr_t x = simd_data(desc); + float64 *d = vd, *n = vn, *m = vm; + for (i = 0; i < opr_sz; i++) { + float64 mm = m[i]; + intptr_t xx = x; + if (float64_is_neg(mm)) { + mm = float64_abs(mm); + xx += 8; + } + d[i] = float64_muladd(n[i], mm, coeff[xx], 0, vs); + } +} + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_PPZ(FCMNE_ppz0, fcmne0) #undef DO_PPZ +/* + *** SVE floating-point trig multiply-add coefficient + */ + +static bool trans_FTMAD(DisasContext *s, arg_FTMAD *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] = { + gen_helper_sve_ftmad_h, + gen_helper_sve_ftmad_s, + gen_helper_sve_ftmad_d, + }; + + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + status, vsz, vsz, a->imm, fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + /* *** SVE Floating Point Accumulating Reduction Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FMINNM_zpzi 01100101 .. 011 101 100 ... 0000 . ..... @rdn_i1 FMAX_zpzi 01100101 .. 011 110 100 ... 0000 . ..... @rdn_i1 FMIN_zpzi 01100101 .. 011 111 100 ... 0000 . ..... @rdn_i1 +# SVE floating-point trig multiply-add coefficient +FTMAD 01100101 esz:2 010 imm:3 100000 rm:5 rd:5 rn=%reg_movprfx + ### SVE FP Multiply-Add Group # SVE floating-point multiply-accumulate writing addend -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 13 +++++++++ target/arm/sve_helper.c | 55 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 30 +++++++++++++++++++++ target/arm/sve.decode | 8 ++++++ 4 files changed, 106 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_fmins_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(sve_fmins_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i64, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_sh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_dh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_hs, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_hd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvt_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ } while (i != 0); \ } +/* SVE fp16 conversions always use IEEE mode. Like AdvSIMD, they ignore + * FZ16. When converting from fp16, this affects flushing input denormals; + * when converting to fp16, this affects flushing output denormals. + */ +static inline float32 sve_f16_to_f32(float16 f, float_status *fpst) +{ + flag save = get_flush_inputs_to_zero(fpst); + float32 ret; + + set_flush_inputs_to_zero(false, fpst); + ret = float16_to_float32(f, true, fpst); + set_flush_inputs_to_zero(save, fpst); + return ret; +} + +static inline float64 sve_f16_to_f64(float16 f, float_status *fpst) +{ + flag save = get_flush_inputs_to_zero(fpst); + float64 ret; + + set_flush_inputs_to_zero(false, fpst); + ret = float16_to_float64(f, true, fpst); + set_flush_inputs_to_zero(save, fpst); + return ret; +} + +static inline float16 sve_f32_to_f16(float32 f, float_status *fpst) +{ + flag save = get_flush_to_zero(fpst); + float16 ret; + + set_flush_to_zero(false, fpst); + ret = float32_to_float16(f, true, fpst); + set_flush_to_zero(save, fpst); + return ret; +} + +static inline float16 sve_f64_to_f16(float64 f, float_status *fpst) +{ + flag save = get_flush_to_zero(fpst); + float16 ret; + + set_flush_to_zero(false, fpst); + ret = float64_to_float16(f, true, fpst); + set_flush_to_zero(save, fpst); + return ret; +} + +DO_ZPZ_FP(sve_fcvt_sh, uint32_t, H1_4, sve_f32_to_f16) +DO_ZPZ_FP(sve_fcvt_hs, uint32_t, H1_4, sve_f16_to_f32) +DO_ZPZ_FP(sve_fcvt_dh, uint64_t, , sve_f64_to_f16) +DO_ZPZ_FP(sve_fcvt_hd, uint64_t, , sve_f16_to_f64) +DO_ZPZ_FP(sve_fcvt_ds, uint64_t, , float64_to_float32) +DO_ZPZ_FP(sve_fcvt_sd, uint64_t, , float32_to_float64) + DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16) DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16) DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zpz_ptr(DisasContext *s, int rd, int rn, int pg, return true; } +static bool trans_FCVT_sh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvt_sh); +} + +static bool trans_FCVT_hs(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hs); +} + +static bool trans_FCVT_dh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvt_dh); +} + +static bool trans_FCVT_hd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_hd); +} + +static bool trans_FCVT_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_ds); +} + +static bool trans_FCVT_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_sd); +} + static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) { return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FNMLS_zpzzz 01100101 .. 1 ..... 111 ... ..... ..... @rdn_pg_rm_ra ### SVE FP Unary Operations Predicated Group +# SVE floating-point convert precision +FCVT_sh 01100101 10 0010 00 101 ... ..... ..... @rd_pg_rn_e0 +FCVT_hs 01100101 10 0010 01 101 ... ..... ..... @rd_pg_rn_e0 +FCVT_dh 01100101 11 0010 00 101 ... ..... ..... @rd_pg_rn_e0 +FCVT_hd 01100101 11 0010 01 101 ... ..... ..... @rd_pg_rn_e0 +FCVT_ds 01100101 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 +FCVT_sd 01100101 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 + # SVE integer convert to floating-point SCVTF_hh 01100101 01 010 01 0 101 ... ..... ..... @rd_pg_rn_e0 SCVTF_sh 01100101 01 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 30 +++++++++++++ target/arm/helper.h | 12 +++--- target/arm/helper.c | 2 +- target/arm/sve_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 70 ++++++++++++++++++++++++++++++ target/arm/sve.decode | 16 +++++++ 6 files changed, 211 insertions(+), 7 deletions(-) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_fcvt_hd, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_fcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_hh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_hs, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_ss, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_hd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzs_dd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fcvtzu_hh, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_hs, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_ss, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_ds, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_hd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_sd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fcvtzu_dd, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(vfp_touid, i32, f64, ptr) DEF_HELPER_2(vfp_touizh, i32, f16, ptr) DEF_HELPER_2(vfp_touizs, i32, f32, ptr) DEF_HELPER_2(vfp_touizd, i32, f64, ptr) -DEF_HELPER_2(vfp_tosih, i32, f16, ptr) -DEF_HELPER_2(vfp_tosis, i32, f32, ptr) -DEF_HELPER_2(vfp_tosid, i32, f64, ptr) -DEF_HELPER_2(vfp_tosizh, i32, f16, ptr) -DEF_HELPER_2(vfp_tosizs, i32, f32, ptr) -DEF_HELPER_2(vfp_tosizd, i32, f64, ptr) +DEF_HELPER_2(vfp_tosih, s32, f16, ptr) +DEF_HELPER_2(vfp_tosis, s32, f32, ptr) +DEF_HELPER_2(vfp_tosid, s32, f64, ptr) +DEF_HELPER_2(vfp_tosizh, s32, f16, ptr) +DEF_HELPER_2(vfp_tosizs, s32, f32, ptr) +DEF_HELPER_2(vfp_tosizd, s32, f64, ptr) DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, ptr) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ ftype HELPER(name)(uint32_t x, void *fpstp) \ } #define CONV_FTOI(name, ftype, fsz, sign, round) \ -uint32_t HELPER(name)(ftype x, void *fpstp) \ +sign##int32_t HELPER(name)(ftype x, void *fpstp) \ { \ float_status *fpst = fpstp; \ if (float##fsz##_is_any_nan(x)) { \ diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ static inline float16 sve_f64_to_f16(float64 f, float_status *fpst) return ret; } +static inline int16_t vfp_float16_to_int16_rtz(float16 f, float_status *s) +{ + if (float16_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float16_to_int16_round_to_zero(f, s); +} + +static inline int64_t vfp_float16_to_int64_rtz(float16 f, float_status *s) +{ + if (float16_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float16_to_int64_round_to_zero(f, s); +} + +static inline int64_t vfp_float32_to_int64_rtz(float32 f, float_status *s) +{ + if (float32_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float32_to_int64_round_to_zero(f, s); +} + +static inline int64_t vfp_float64_to_int64_rtz(float64 f, float_status *s) +{ + if (float64_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float64_to_int64_round_to_zero(f, s); +} + +static inline uint16_t vfp_float16_to_uint16_rtz(float16 f, float_status *s) +{ + if (float16_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float16_to_uint16_round_to_zero(f, s); +} + +static inline uint64_t vfp_float16_to_uint64_rtz(float16 f, float_status *s) +{ + if (float16_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float16_to_uint64_round_to_zero(f, s); +} + +static inline uint64_t vfp_float32_to_uint64_rtz(float32 f, float_status *s) +{ + if (float32_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float32_to_uint64_round_to_zero(f, s); +} + +static inline uint64_t vfp_float64_to_uint64_rtz(float64 f, float_status *s) +{ + if (float64_is_any_nan(f)) { + float_raise(float_flag_invalid, s); + return 0; + } + return float64_to_uint64_round_to_zero(f, s); +} + DO_ZPZ_FP(sve_fcvt_sh, uint32_t, H1_4, sve_f32_to_f16) DO_ZPZ_FP(sve_fcvt_hs, uint32_t, H1_4, sve_f16_to_f32) DO_ZPZ_FP(sve_fcvt_dh, uint64_t, , sve_f64_to_f16) @@ -XXX,XX +XXX,XX @@ DO_ZPZ_FP(sve_fcvt_hd, uint64_t, , sve_f16_to_f64) DO_ZPZ_FP(sve_fcvt_ds, uint64_t, , float64_to_float32) DO_ZPZ_FP(sve_fcvt_sd, uint64_t, , float32_to_float64) +DO_ZPZ_FP(sve_fcvtzs_hh, uint16_t, H1_2, vfp_float16_to_int16_rtz) +DO_ZPZ_FP(sve_fcvtzs_hs, uint32_t, H1_4, helper_vfp_tosizh) +DO_ZPZ_FP(sve_fcvtzs_ss, uint32_t, H1_4, helper_vfp_tosizs) +DO_ZPZ_FP(sve_fcvtzs_hd, uint64_t, , vfp_float16_to_int64_rtz) +DO_ZPZ_FP(sve_fcvtzs_sd, uint64_t, , vfp_float32_to_int64_rtz) +DO_ZPZ_FP(sve_fcvtzs_ds, uint64_t, , helper_vfp_tosizd) +DO_ZPZ_FP(sve_fcvtzs_dd, uint64_t, , vfp_float64_to_int64_rtz) + +DO_ZPZ_FP(sve_fcvtzu_hh, uint16_t, H1_2, vfp_float16_to_uint16_rtz) +DO_ZPZ_FP(sve_fcvtzu_hs, uint32_t, H1_4, helper_vfp_touizh) +DO_ZPZ_FP(sve_fcvtzu_ss, uint32_t, H1_4, helper_vfp_touizs) +DO_ZPZ_FP(sve_fcvtzu_hd, uint64_t, , vfp_float16_to_uint64_rtz) +DO_ZPZ_FP(sve_fcvtzu_sd, uint64_t, , vfp_float32_to_uint64_rtz) +DO_ZPZ_FP(sve_fcvtzu_ds, uint64_t, , helper_vfp_touizd) +DO_ZPZ_FP(sve_fcvtzu_dd, uint64_t, , vfp_float64_to_uint64_rtz) + DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16) DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16) DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvt_sd); } +static bool trans_FCVTZS_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hh); +} + +static bool trans_FCVTZU_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hh); +} + +static bool trans_FCVTZS_hs(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hs); +} + +static bool trans_FCVTZU_hs(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hs); +} + +static bool trans_FCVTZS_hd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzs_hd); +} + +static bool trans_FCVTZU_hd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_fcvtzu_hd); +} + +static bool trans_FCVTZS_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_ss); +} + +static bool trans_FCVTZU_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_ss); +} + +static bool trans_FCVTZS_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_sd); +} + +static bool trans_FCVTZU_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_sd); +} + +static bool trans_FCVTZS_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_ds); +} + +static bool trans_FCVTZU_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_ds); +} + +static bool trans_FCVTZS_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzs_dd); +} + +static bool trans_FCVTZU_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_dd); +} + static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) { return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FCVT_hd 01100101 11 0010 01 101 ... ..... ..... @rd_pg_rn_e0 FCVT_ds 01100101 11 0010 10 101 ... ..... ..... @rd_pg_rn_e0 FCVT_sd 01100101 11 0010 11 101 ... ..... ..... @rd_pg_rn_e0 +# SVE floating-point convert to integer +FCVTZS_hh 01100101 01 011 01 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_hh 01100101 01 011 01 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_hs 01100101 01 011 10 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_hs 01100101 01 011 10 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_hd 01100101 01 011 11 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_hd 01100101 01 011 11 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_ss 01100101 10 011 10 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_ss 01100101 10 011 10 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_ds 01100101 11 011 00 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_ds 01100101 11 011 00 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_sd 01100101 11 011 10 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_sd 01100101 11 011 10 1 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZS_dd 01100101 11 011 11 0 101 ... ..... ..... @rd_pg_rn_e0 +FCVTZU_dd 01100101 11 011 11 1 101 ... ..... ..... @rd_pg_rn_e0 + # SVE integer convert to floating-point SCVTF_hh 01100101 01 010 01 0 101 ... ..... ..... @rd_pg_rn_e0 SCVTF_sh 01100101 01 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 +++++++ target/arm/sve_helper.c | 8 ++++ target/arm/translate-sve.c | 77 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 9 +++++ 4 files changed, 108 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_fcvtzu_sd, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_fcvtzu_dd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frint_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frint_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frint_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_frintx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frintx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frintx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_FP(sve_fcvtzu_sd, uint64_t, , vfp_float32_to_uint64_rtz) DO_ZPZ_FP(sve_fcvtzu_ds, uint64_t, , helper_vfp_touizd) DO_ZPZ_FP(sve_fcvtzu_dd, uint64_t, , vfp_float64_to_uint64_rtz) +DO_ZPZ_FP(sve_frint_h, uint16_t, H1_2, helper_advsimd_rinth) +DO_ZPZ_FP(sve_frint_s, uint32_t, H1_4, helper_rints) +DO_ZPZ_FP(sve_frint_d, uint64_t, , helper_rintd) + +DO_ZPZ_FP(sve_frintx_h, uint16_t, H1_2, float16_round_to_int) +DO_ZPZ_FP(sve_frintx_s, uint32_t, H1_4, float32_round_to_int) +DO_ZPZ_FP(sve_frintx_d, uint64_t, , float64_round_to_int) + DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16) DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16) DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTZU_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_fcvtzu_dd); } +static gen_helper_gvec_3_ptr * const frint_fns[3] = { + gen_helper_sve_frint_h, + gen_helper_sve_frint_s, + gen_helper_sve_frint_d +}; + +static bool trans_FRINTI(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + if (a->esz == 0) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, + frint_fns[a->esz - 1]); +} + +static bool trans_FRINTX(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] = { + gen_helper_sve_frintx_h, + gen_helper_sve_frintx_s, + gen_helper_sve_frintx_d + }; + if (a->esz == 0) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); +} + +static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, int mode) +{ + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_i32 tmode = tcg_const_i32(mode); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + + gen_helper_set_rmode(tmode, tmode, status); + + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, 0, frint_fns[a->esz - 1]); + + gen_helper_set_rmode(tmode, tmode, status); + tcg_temp_free_i32(tmode); + tcg_temp_free_ptr(status); + } + return true; +} + +static bool trans_FRINTN(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_frint_mode(s, a, float_round_nearest_even); +} + +static bool trans_FRINTP(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_frint_mode(s, a, float_round_up); +} + +static bool trans_FRINTM(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_frint_mode(s, a, float_round_down); +} + +static bool trans_FRINTZ(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_frint_mode(s, a, float_round_to_zero); +} + +static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + return do_frint_mode(s, a, float_round_ties_away); +} + static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) { return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FCVTZU_sd 01100101 11 011 10 1 101 ... ..... ..... @rd_pg_rn_e0 FCVTZS_dd 01100101 11 011 11 0 101 ... ..... ..... @rd_pg_rn_e0 FCVTZU_dd 01100101 11 011 11 1 101 ... ..... ..... @rd_pg_rn_e0 +# SVE floating-point round to integral value +FRINTN 01100101 .. 000 000 101 ... ..... ..... @rd_pg_rn +FRINTP 01100101 .. 000 001 101 ... ..... ..... @rd_pg_rn +FRINTM 01100101 .. 000 010 101 ... ..... ..... @rd_pg_rn +FRINTZ 01100101 .. 000 011 101 ... ..... ..... @rd_pg_rn +FRINTA 01100101 .. 000 100 101 ... ..... ..... @rd_pg_rn +FRINTX 01100101 .. 000 110 101 ... ..... ..... @rd_pg_rn +FRINTI 01100101 .. 000 111 101 ... ..... ..... @rd_pg_rn + # SVE integer convert to floating-point SCVTF_hh 01100101 01 010 01 0 101 ... ..... ..... @rd_pg_rn_e0 SCVTF_sh 01100101 01 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 14 ++++++++++++++ target/arm/sve_helper.c | 8 ++++++++ target/arm/translate-sve.c | 26 ++++++++++++++++++++++++++ target/arm/sve.decode | 4 ++++ 4 files changed, 52 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_frintx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve_frintx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frecpx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frecpx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_frecpx_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sve_fsqrt_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fsqrt_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_fsqrt_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_FP(sve_frintx_h, uint16_t, H1_2, float16_round_to_int) DO_ZPZ_FP(sve_frintx_s, uint32_t, H1_4, float32_round_to_int) DO_ZPZ_FP(sve_frintx_d, uint64_t, , float64_round_to_int) +DO_ZPZ_FP(sve_frecpx_h, uint16_t, H1_2, helper_frecpx_f16) +DO_ZPZ_FP(sve_frecpx_s, uint32_t, H1_4, helper_frecpx_f32) +DO_ZPZ_FP(sve_frecpx_d, uint64_t, , helper_frecpx_f64) + +DO_ZPZ_FP(sve_fsqrt_h, uint16_t, H1_2, float16_sqrt) +DO_ZPZ_FP(sve_fsqrt_s, uint32_t, H1_4, float32_sqrt) +DO_ZPZ_FP(sve_fsqrt_d, uint64_t, , float64_sqrt) + DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16) DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16) DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FRINTA(DisasContext *s, arg_rpr_esz *a, uint32_t insn) return do_frint_mode(s, a, float_round_ties_away); } +static bool trans_FRECPX(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] = { + gen_helper_sve_frecpx_h, + gen_helper_sve_frecpx_s, + gen_helper_sve_frecpx_d + }; + if (a->esz == 0) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); +} + +static bool trans_FSQRT(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[3] = { + gen_helper_sve_fsqrt_h, + gen_helper_sve_fsqrt_s, + gen_helper_sve_fsqrt_d + }; + if (a->esz == 0) { + return false; + } + return do_zpz_ptr(s, a->rd, a->rn, a->pg, a->esz == MO_16, fns[a->esz - 1]); +} + static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn) { return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh); diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FRINTA 01100101 .. 000 100 101 ... ..... ..... @rd_pg_rn FRINTX 01100101 .. 000 110 101 ... ..... ..... @rd_pg_rn FRINTI 01100101 .. 000 111 101 ... ..... ..... @rd_pg_rn +# SVE floating-point unary operations +FRECPX 01100101 .. 001 100 101 ... ..... ..... @rd_pg_rn +FSQRT 01100101 .. 001 101 101 ... ..... ..... @rd_pg_rn + # SVE integer convert to floating-point SCVTF_hh 01100101 01 010 01 0 101 ... ..... ..... @rd_pg_rn_e0 SCVTF_sh 01100101 01 010 10 0 101 ... ..... ..... @rd_pg_rn_e0 -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 60 +++++++++++++++++++++++++++++++++++++- target/arm/sve.decode | 7 +++++ 2 files changed, 66 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_zpzz_ool(DisasContext *s, arg_rprr_esz *a, gen_helper_gvec_4 *fn) return true; } +/* Select active elememnts from Zn and inactive elements from Zm, + * storing the result in Zd. + */ +static void do_sel_z(DisasContext *s, int rd, int rn, int rm, int pg, int esz) +{ + static gen_helper_gvec_4 * const fns[4] = { + gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, + gen_helper_sve_sel_zpzz_s, gen_helper_sve_sel_zpzz_d + }; + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_4_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + pred_full_reg_offset(s, pg), + vsz, vsz, 0, fns[esz]); +} + #define DO_ZPZZ(NAME, name) \ static bool trans_##NAME##_zpzz(DisasContext *s, arg_rprr_esz *a, \ uint32_t insn) \ @@ -XXX,XX +XXX,XX @@ static bool trans_UDIV_zpzz(DisasContext *s, arg_rprr_esz *a, uint32_t insn) return do_zpzz_ool(s, a, fns[a->esz]); } -DO_ZPZZ(SEL, sel) +static bool trans_SEL_zpzz(DisasContext *s, arg_rprr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_sel_z(s, a->rd, a->rn, a->rm, a->pg, a->esz); + } + return true; +} #undef DO_ZPZZ @@ -XXX,XX +XXX,XX @@ static bool trans_PRF_rr(DisasContext *s, arg_PRF_rr *a, uint32_t insn) sve_access_check(s); return true; } + +/* + * Move Prefix + * + * TODO: The implementation so far could handle predicated merging movprfx. + * The helper functions as written take an extra source register to + * use in the operation, but the result is only written when predication + * succeeds. For unpredicated movprfx, we need to rearrange the helpers + * to allow the final write back to the destination to be unconditional. + * For predicated zeroing movprfx, we need to rearrange the helpers to + * allow the final write back to zero inactives. + * + * In the meantime, just emit the moves. + */ + +static bool trans_MOVPRFX(DisasContext *s, arg_MOVPRFX *a, uint32_t insn) +{ + return do_mov_z(s, a->rd, a->rn); +} + +static bool trans_MOVPRFX_m(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_sel_z(s, a->rd, a->rn, a->rd, a->pg, a->esz); + } + return true; +} + +static bool trans_MOVPRFX_z(DisasContext *s, arg_rpr_esz *a, uint32_t insn) +{ + if (sve_access_check(s)) { + do_movz_zpz(s, a->rd, a->rn, a->pg, a->esz); + } + return true; +} diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ ORV 00000100 .. 011 000 001 ... ..... ..... @rd_pg_rn EORV 00000100 .. 011 001 001 ... ..... ..... @rd_pg_rn ANDV 00000100 .. 011 010 001 ... ..... ..... @rd_pg_rn +# SVE constructive prefix (predicated) +MOVPRFX_z 00000100 .. 010 000 001 ... ..... ..... @rd_pg_rn +MOVPRFX_m 00000100 .. 010 001 001 ... ..... ..... @rd_pg_rn + # SVE integer add reduction (predicated) # Note that saddv requires size != 3. UADDV 00000100 .. 000 001 001 ... ..... ..... @rd_pg_rn @@ -XXX,XX +XXX,XX @@ ADR_p64 00000100 11 1 ..... 1010 .. ..... ..... @rd_rn_msz_rm ### SVE Integer Misc - Unpredicated Group +# SVE constructive prefix (unpredicated) +MOVPRFX 00000100 00 1 00000 101111 rn:5 rd:5 + # SVE floating-point exponential accelerator # Note esz != 0 FEXPA 00000100 .. 1 00000 101110 ..... ..... @rd_rn -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 7 +++ target/arm/sve_helper.c | 100 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 24 +++++++++ target/arm/sve.decode | 4 ++ 4 files changed, 135 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sve_fcadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) } } +/* + * FP Complex Add + */ + +void HELPER(sve_fcadd_h)(void *vd, void *vn, void *vm, void *vg, + void *vs, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + uint64_t *g = vg; + float16 neg_imag = float16_set_sign(0, simd_data(desc)); + float16 neg_real = float16_chs(neg_imag); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float16 e0, e1, e2, e3; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float16); + i -= 2 * sizeof(float16); + + e0 = *(float16 *)(vn + H1_2(i)); + e1 = *(float16 *)(vm + H1_2(j)) ^ neg_real; + e2 = *(float16 *)(vn + H1_2(j)); + e3 = *(float16 *)(vm + H1_2(i)) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + *(float16 *)(vd + H1_2(i)) = float16_add(e0, e1, vs); + } + if (likely((pg >> (j & 63)) & 1)) { + *(float16 *)(vd + H1_2(j)) = float16_add(e2, e3, vs); + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fcadd_s)(void *vd, void *vn, void *vm, void *vg, + void *vs, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + uint64_t *g = vg; + float32 neg_imag = float32_set_sign(0, simd_data(desc)); + float32 neg_real = float32_chs(neg_imag); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float32 e0, e1, e2, e3; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float32); + i -= 2 * sizeof(float32); + + e0 = *(float32 *)(vn + H1_2(i)); + e1 = *(float32 *)(vm + H1_2(j)) ^ neg_real; + e2 = *(float32 *)(vn + H1_2(j)); + e3 = *(float32 *)(vm + H1_2(i)) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + *(float32 *)(vd + H1_2(i)) = float32_add(e0, e1, vs); + } + if (likely((pg >> (j & 63)) & 1)) { + *(float32 *)(vd + H1_2(j)) = float32_add(e2, e3, vs); + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg, + void *vs, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + uint64_t *g = vg; + float64 neg_imag = float64_set_sign(0, simd_data(desc)); + float64 neg_real = float64_chs(neg_imag); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float64 e0, e1, e2, e3; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float64); + i -= 2 * sizeof(float64); + + e0 = *(float64 *)(vn + H1_2(i)); + e1 = *(float64 *)(vm + H1_2(j)) ^ neg_real; + e2 = *(float64 *)(vn + H1_2(j)); + e3 = *(float64 *)(vm + H1_2(i)) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + *(float64 *)(vd + H1_2(i)) = float64_add(e0, e1, vs); + } + if (likely((pg >> (j & 63)) & 1)) { + *(float64 *)(vd + H1_2(j)) = float64_add(e2, e3, vs); + } + } while (i & 63); + } while (i != 0); +} + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FPCMP(FACGT, facgt) #undef DO_FPCMP +static bool trans_FCADD(DisasContext *s, arg_FCADD *a, uint32_t insn) +{ + static gen_helper_gvec_4_ptr * const fns[3] = { + gen_helper_sve_fcadd_h, + gen_helper_sve_fcadd_s, + gen_helper_sve_fcadd_d + }; + + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + pred_full_reg_offset(s, a->pg), + status, vsz, vsz, a->rot, fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32); static bool do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s +# SVE floating-point complex add (predicated) +FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ + rn=%reg_movprfx + ### SVE FP Multiply-Add Indexed Group # SVE floating-point multiply-add (indexed) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 4 + target/arm/sve_helper.c | 162 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sve.c | 37 +++++++++ target/arm/sve.decode | 4 + 4 files changed, 207 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32) + DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg, } while (i != 0); } +/* + * FP Complex Multiply + */ + +QEMU_BUILD_BUG_ON(SIMD_DATA_SHIFT + 22 > 32); + +void HELPER(sve_fcmla_zpzzz_h)(CPUARMState *env, void *vg, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2); + bool flip = rot & 1; + float16 neg_imag, neg_real; + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + neg_imag = float16_set_sign(0, (rot & 2) != 0); + neg_real = float16_set_sign(0, rot == 1 || rot == 2); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float16 e1, e2, e3, e4, nr, ni, mr, mi, d; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float16); + i -= 2 * sizeof(float16); + + nr = *(float16 *)(vn + H1_2(i)); + ni = *(float16 *)(vn + H1_2(j)); + mr = *(float16 *)(vm + H1_2(i)); + mi = *(float16 *)(vm + H1_2(j)); + + e2 = (flip ? ni : nr); + e1 = (flip ? mi : mr) ^ neg_real; + e4 = e2; + e3 = (flip ? mr : mi) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + d = *(float16 *)(va + H1_2(i)); + d = float16_muladd(e2, e1, d, 0, &env->vfp.fp_status_f16); + *(float16 *)(vd + H1_2(i)) = d; + } + if (likely((pg >> (j & 63)) & 1)) { + d = *(float16 *)(va + H1_2(j)); + d = float16_muladd(e4, e3, d, 0, &env->vfp.fp_status_f16); + *(float16 *)(vd + H1_2(j)) = d; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fcmla_zpzzz_s)(CPUARMState *env, void *vg, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2); + bool flip = rot & 1; + float32 neg_imag, neg_real; + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + neg_imag = float32_set_sign(0, (rot & 2) != 0); + neg_real = float32_set_sign(0, rot == 1 || rot == 2); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float32 e1, e2, e3, e4, nr, ni, mr, mi, d; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float32); + i -= 2 * sizeof(float32); + + nr = *(float32 *)(vn + H1_2(i)); + ni = *(float32 *)(vn + H1_2(j)); + mr = *(float32 *)(vm + H1_2(i)); + mi = *(float32 *)(vm + H1_2(j)); + + e2 = (flip ? ni : nr); + e1 = (flip ? mi : mr) ^ neg_real; + e4 = e2; + e3 = (flip ? mr : mi) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + d = *(float32 *)(va + H1_2(i)); + d = float32_muladd(e2, e1, d, 0, &env->vfp.fp_status); + *(float32 *)(vd + H1_2(i)) = d; + } + if (likely((pg >> (j & 63)) & 1)) { + d = *(float32 *)(va + H1_2(j)); + d = float32_muladd(e4, e3, d, 0, &env->vfp.fp_status); + *(float32 *)(vd + H1_2(j)) = d; + } + } while (i & 63); + } while (i != 0); +} + +void HELPER(sve_fcmla_zpzzz_d)(CPUARMState *env, void *vg, uint32_t desc) +{ + intptr_t j, i = simd_oprsz(desc); + unsigned rd = extract32(desc, SIMD_DATA_SHIFT, 5); + unsigned rn = extract32(desc, SIMD_DATA_SHIFT + 5, 5); + unsigned rm = extract32(desc, SIMD_DATA_SHIFT + 10, 5); + unsigned ra = extract32(desc, SIMD_DATA_SHIFT + 15, 5); + unsigned rot = extract32(desc, SIMD_DATA_SHIFT + 20, 2); + bool flip = rot & 1; + float64 neg_imag, neg_real; + void *vd = &env->vfp.zregs[rd]; + void *vn = &env->vfp.zregs[rn]; + void *vm = &env->vfp.zregs[rm]; + void *va = &env->vfp.zregs[ra]; + uint64_t *g = vg; + + neg_imag = float64_set_sign(0, (rot & 2) != 0); + neg_real = float64_set_sign(0, rot == 1 || rot == 2); + + do { + uint64_t pg = g[(i - 1) >> 6]; + do { + float64 e1, e2, e3, e4, nr, ni, mr, mi, d; + + /* I holds the real index; J holds the imag index. */ + j = i - sizeof(float64); + i -= 2 * sizeof(float64); + + nr = *(float64 *)(vn + H1_2(i)); + ni = *(float64 *)(vn + H1_2(j)); + mr = *(float64 *)(vm + H1_2(i)); + mi = *(float64 *)(vm + H1_2(j)); + + e2 = (flip ? ni : nr); + e1 = (flip ? mi : mr) ^ neg_real; + e4 = e2; + e3 = (flip ? mr : mi) ^ neg_imag; + + if (likely((pg >> (i & 63)) & 1)) { + d = *(float64 *)(va + H1_2(i)); + d = float64_muladd(e2, e1, d, 0, &env->vfp.fp_status); + *(float64 *)(vd + H1_2(i)) = d; + } + if (likely((pg >> (j & 63)) & 1)) { + d = *(float64 *)(va + H1_2(j)); + d = float64_muladd(e4, e3, d, 0, &env->vfp.fp_status); + *(float64 *)(vd + H1_2(j)) = d; + } + } while (i & 63); + } while (i != 0); +} + /* * Load contiguous data, protected by a governing predicate. */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_FMLA(FNMLS_zpzzz, fnmls_zpzzz) #undef DO_FMLA +static bool trans_FCMLA_zpzzz(DisasContext *s, + arg_FCMLA_zpzzz *a, uint32_t insn) +{ + static gen_helper_sve_fmla * const fns[3] = { + gen_helper_sve_fcmla_zpzzz_h, + gen_helper_sve_fcmla_zpzzz_s, + gen_helper_sve_fcmla_zpzzz_d, + }; + + if (a->esz == 0) { + return false; + } + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + unsigned desc; + TCGv_i32 t_desc; + TCGv_ptr pg = tcg_temp_new_ptr(); + + /* We would need 7 operands to pass these arguments "properly". + * So we encode all the register numbers into the descriptor. + */ + desc = deposit32(a->rd, 5, 5, a->rn); + desc = deposit32(desc, 10, 5, a->rm); + desc = deposit32(desc, 15, 5, a->ra); + desc = deposit32(desc, 20, 2, a->rot); + desc = sextract32(desc, 0, 22); + desc = simd_desc(vsz, vsz, desc); + + t_desc = tcg_const_i32(desc); + tcg_gen_addi_ptr(pg, cpu_env, pred_full_reg_offset(s, a->pg)); + fns[a->esz - 1](cpu_env, pg, t_desc); + tcg_temp_free_i32(t_desc); + tcg_temp_free_ptr(pg); + } + return true; +} + /* *** SVE Floating Point Unary Operations Predicated Group */ diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ rn=%reg_movprfx +# SVE floating-point complex multiply-add (predicated) +FCMLA_zpzzz 01100100 esz:2 0 rm:5 0 rot:2 pg:3 rn:5 rd:5 \ + ra=%reg_movprfx + ### SVE FP Multiply-Add Indexed Group # SVE floating-point multiply-add (indexed) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> For aa64 advsimd, we had been passing the pre-indexed vector. However, sve applies the index to each 128-bit segment, so we need to pass in the index separately. For aa32 advsimd, the fp32 operation always has index 0, but we failed to interpret the fp16 index correctly. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 21 ++++++++++++--------- target/arm/translate.c | 32 +++++++++++++++++++++++--------- target/arm/vec_helper.c | 10 ++++++---- 3 files changed, 41 insertions(+), 22 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ case 0x17: /* FCMLA #270 */ - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_reg_offset(s, rm, index, size), fpst, - is_q ? 16 : 8, vec_full_reg_size(s), - extract32(insn, 13, 2), /* rot */ - size == MO_64 - ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); - tcg_temp_free_ptr(fpst); + { + int rot = extract32(insn, 13, 2); + int data = (index << 2) | rot; + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), fpst, + is_q ? 16 : 8, vec_full_reg_size(s), data, + size == MO_64 + ? gen_helper_gvec_fcmlas_idx + : gen_helper_gvec_fcmlah_idx); + tcg_temp_free_ptr(fpst); + } return; } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) { - int rd, rn, rm, rot, size, opr_sz; + gen_helper_gvec_3_ptr *fn_gvec_ptr; + int rd, rn, rm, opr_sz, data; TCGv_ptr fpst; bool q; q = extract32(insn, 6, 1); VFP_DREG_D(rd, insn); VFP_DREG_N(rn, insn); - VFP_DREG_M(rm, insn); if ((rd | rn) & q) { return 1; } if ((insn & 0xff000f10) == 0xfe000800) { /* VCMLA (indexed) -- 1111 1110 S.RR .... .... 1000 ...0 .... */ - rot = extract32(insn, 20, 2); - size = extract32(insn, 23, 1); - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) - || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { + int rot = extract32(insn, 20, 2); + int size = extract32(insn, 23, 1); + int index; + + if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA)) { return 1; } + if (size == 0) { + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + return 1; + } + /* For fp16, rm is just Vm, and index is M. */ + rm = extract32(insn, 0, 4); + index = extract32(insn, 5, 1); + } else { + /* For fp32, rm is the usual M:Vm, and index is 0. */ + VFP_DREG_M(rm, insn); + index = 0; + } + data = (index << 2) | rot; + fn_gvec_ptr = (size ? gen_helper_gvec_fcmlas_idx + : gen_helper_gvec_fcmlah_idx); } else { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), vfp_reg_offset(1, rn), vfp_reg_offset(1, rm), fpst, - opr_sz, opr_sz, rot, - size ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); + opr_sz, opr_sz, data, fn_gvec_ptr); tcg_temp_free_ptr(fpst); return 0; } diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); + intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; uintptr_t i; - float16 e1 = m[H2(flip)]; - float16 e3 = m[H2(1 - flip)]; + float16 e1 = m[H2(2 * index + flip)]; + float16 e3 = m[H2(2 * index + 1 - flip)]; /* Shift boolean to the sign bit so we can xor to negate. */ neg_real <<= 15; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); + intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; uintptr_t i; - float32 e1 = m[H4(flip)]; - float32 e3 = m[H4(1 - flip)]; + float32 e1 = m[H4(2 * index + flip)]; + float32 e3 = m[H4(2 * index + 1 - flip)]; /* Shift boolean to the sign bit so we can xor to negate. */ neg_real <<= 31; -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Enhance the existing helpers to support SVE, which takes the index from each 128-bit segment. The change has no effect for AdvSIMD, since there is only one such segment. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-sve.c | 23 ++++++++++++++++++ target/arm/vec_helper.c | 50 +++++++++++++++++++++++--------------- target/arm/sve.decode | 6 +++++ 3 files changed, 59 insertions(+), 20 deletions(-) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCMLA_zpzzz(DisasContext *s, return true; } +static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a, uint32_t insn) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_gvec_fcmlah_idx, + gen_helper_gvec_fcmlas_idx, + }; + + tcg_debug_assert(a->esz == 1 || a->esz == 2); + tcg_debug_assert(a->rd == a->ra); + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16); + tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + status, vsz, vsz, + a->index * 4 + a->rot, + fns[a->esz - 1]); + tcg_temp_free_ptr(status); + } + return true; +} + /* *** SVE Floating Point Unary Operations Predicated Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; - uintptr_t i; - float16 e1 = m[H2(2 * index + flip)]; - float16 e3 = m[H2(2 * index + 1 - flip)]; + intptr_t elements = opr_sz / sizeof(float16); + intptr_t eltspersegment = 16 / sizeof(float16); + intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ neg_real <<= 15; neg_imag <<= 15; - e1 ^= neg_real; - e3 ^= neg_imag; - for (i = 0; i < opr_sz / 2; i += 2) { - float16 e2 = n[H2(i + flip)]; - float16 e4 = e2; + for (i = 0; i < elements; i += eltspersegment) { + float16 mr = m[H2(i + 2 * index + 0)]; + float16 mi = m[H2(i + 2 * index + 1)]; + float16 e1 = neg_real ^ (flip ? mi : mr); + float16 e3 = neg_imag ^ (flip ? mr : mi); - d[H2(i)] = float16_muladd(e2, e1, d[H2(i)], 0, fpst); - d[H2(i + 1)] = float16_muladd(e4, e3, d[H2(i + 1)], 0, fpst); + for (j = i; j < i + eltspersegment; j += 2) { + float16 e2 = n[H2(j + flip)]; + float16 e4 = e2; + + d[H2(j)] = float16_muladd(e2, e1, d[H2(j)], 0, fpst); + d[H2(j + 1)] = float16_muladd(e4, e3, d[H2(j + 1)], 0, fpst); + } } clear_tail(d, opr_sz, simd_maxsz(desc)); } @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; - uintptr_t i; - float32 e1 = m[H4(2 * index + flip)]; - float32 e3 = m[H4(2 * index + 1 - flip)]; + intptr_t elements = opr_sz / sizeof(float32); + intptr_t eltspersegment = 16 / sizeof(float32); + intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ neg_real <<= 31; neg_imag <<= 31; - e1 ^= neg_real; - e3 ^= neg_imag; - for (i = 0; i < opr_sz / 4; i += 2) { - float32 e2 = n[H4(i + flip)]; - float32 e4 = e2; + for (i = 0; i < elements; i += eltspersegment) { + float32 mr = m[H4(i + 2 * index + 0)]; + float32 mi = m[H4(i + 2 * index + 1)]; + float32 e1 = neg_real ^ (flip ? mi : mr); + float32 e3 = neg_imag ^ (flip ? mr : mi); - d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst); - d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst); + for (j = i; j < i + eltspersegment; j += 2) { + float32 e2 = n[H4(j + flip)]; + float32 e4 = e2; + + d[H4(j)] = float32_muladd(e2, e1, d[H4(j)], 0, fpst); + d[H4(j + 1)] = float32_muladd(e4, e3, d[H4(j + 1)], 0, fpst); + } } clear_tail(d, opr_sz, simd_maxsz(desc)); } diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ FCMLA_zpzzz 01100100 esz:2 0 rm:5 0 rot:2 pg:3 rn:5 rd:5 \ ra=%reg_movprfx +# SVE floating-point complex multiply-add (indexed) +FCMLA_zzxz 01100100 10 1 index:2 rm:3 0001 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx esz=1 +FCMLA_zzxz 01100100 11 1 index:1 rm:4 0001 rot:2 rn:5 rd:5 \ + ra=%reg_movprfx esz=2 + ### SVE FP Multiply-Add Indexed Group # SVE floating-point multiply-add (indexed) -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-33-richard.henderson@linaro.org [PMM: moved 'ra=%reg_movprfx' here from following patch] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 5 +++ target/arm/translate-sve.c | 17 ++++++++++ target/arm/vec_helper.c | 67 ++++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 3 ++ 4 files changed, 92 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_qrdmlah_s32, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_qrdmlsh_s32, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sdot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_ZZI(UMIN, umin) #undef DO_ZZI +static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[2][2] = { + { gen_helper_gvec_sdot_b, gen_helper_gvec_sdot_h }, + { gen_helper_gvec_udot_b, gen_helper_gvec_udot_h } + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, 0, fns[a->u][a->sz]); + } + return true; +} + /* *** SVE Floating Point Multiply-Add Indexed Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_qrdmlsh_s32)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +/* Integer 8 and 16-bit dot-product. + * + * Note that for the loops herein, host endianness does not matter + * with respect to the ordering of data within the 64-bit lanes. + * All elements are treated equally, no matter where they are. + */ + +void HELPER(gvec_sdot_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd; + int8_t *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] += n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_udot_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd; + uint8_t *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] += n[i * 4 + 0] * m[i * 4 + 0] + + n[i * 4 + 1] * m[i * 4 + 1] + + n[i * 4 + 2] * m[i * 4 + 2] + + n[i * 4 + 3] * m[i * 4 + 3]; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_sdot_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd; + int16_t *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] += (int64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (int64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (int64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (int64_t)n[i * 4 + 3] * m[i * 4 + 3]; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd; + uint16_t *n = vn, *m = vm; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] += (uint64_t)n[i * 4 + 0] * m[i * 4 + 0] + + (uint64_t)n[i * 4 + 1] * m[i * 4 + 1] + + (uint64_t)n[i * 4 + 2] * m[i * 4 + 2] + + (uint64_t)n[i * 4 + 3] * m[i * 4 + 3]; + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, void *vfpst, uint32_t desc) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ UMIN_zzi 00100101 .. 101 011 110 ........ ..... @rdn_i8u # SVE integer multiply immediate (unpredicated) MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s +# SVE integer dot product (unpredicated) +DOT_zzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 ra=%reg_movprfx + # SVE floating-point complex add (predicated) FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ rn=%reg_movprfx -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180627043328.11531-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 5 ++ target/arm/translate-sve.c | 18 ++++++ target/arm/vec_helper.c | 124 +++++++++++++++++++++++++++++++++++++ target/arm/sve.decode | 6 ++ 4 files changed, 153 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_udot_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_sdot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_udot_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_udot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sdot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_udot_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_DOT_zzz(DisasContext *s, arg_DOT_zzz *a, uint32_t insn) return true; } +static bool trans_DOT_zzx(DisasContext *s, arg_DOT_zzx *a, uint32_t insn) +{ + static gen_helper_gvec_3 * const fns[2][2] = { + { gen_helper_gvec_sdot_idx_b, gen_helper_gvec_sdot_idx_h }, + { gen_helper_gvec_udot_idx_b, gen_helper_gvec_udot_idx_h } + }; + + if (sve_access_check(s)) { + unsigned vsz = vec_full_reg_size(s); + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd), + vec_full_reg_offset(s, a->rn), + vec_full_reg_offset(s, a->rm), + vsz, vsz, a->index, fns[a->u][a->sz]); + } + return true; +} + + /* *** SVE Floating Point Multiply-Add Indexed Group */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_udot_h)(void *vd, void *vn, void *vm, uint32_t desc) clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(gvec_sdot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; + intptr_t index = simd_data(desc); + uint32_t *d = vd; + int8_t *n = vn; + int8_t *m_indexed = (int8_t *)vm + index * 4; + + /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. + * Otherwise opr_sz is a multiple of 16. + */ + segend = MIN(4, opr_sz_4); + i = 0; + do { + int8_t m0 = m_indexed[i * 4 + 0]; + int8_t m1 = m_indexed[i * 4 + 1]; + int8_t m2 = m_indexed[i * 4 + 2]; + int8_t m3 = m_indexed[i * 4 + 3]; + + do { + d[i] += n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3; + } while (++i < segend); + segend = i + 4; + } while (i < opr_sz_4); + + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_udot_idx_b)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, segend, opr_sz = simd_oprsz(desc), opr_sz_4 = opr_sz / 4; + intptr_t index = simd_data(desc); + uint32_t *d = vd; + uint8_t *n = vn; + uint8_t *m_indexed = (uint8_t *)vm + index * 4; + + /* Notice the special case of opr_sz == 8, from aa64/aa32 advsimd. + * Otherwise opr_sz is a multiple of 16. + */ + segend = MIN(4, opr_sz_4); + i = 0; + do { + uint8_t m0 = m_indexed[i * 4 + 0]; + uint8_t m1 = m_indexed[i * 4 + 1]; + uint8_t m2 = m_indexed[i * 4 + 2]; + uint8_t m3 = m_indexed[i * 4 + 3]; + + do { + d[i] += n[i * 4 + 0] * m0 + + n[i * 4 + 1] * m1 + + n[i * 4 + 2] * m2 + + n[i * 4 + 3] * m3; + } while (++i < segend); + segend = i + 4; + } while (i < opr_sz_4); + + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_sdot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; + intptr_t index = simd_data(desc); + uint64_t *d = vd; + int16_t *n = vn; + int16_t *m_indexed = (int16_t *)vm + index * 4; + + /* This is supported by SVE only, so opr_sz is always a multiple of 16. + * Process the entire segment all at once, writing back the results + * only after we've consumed all of the inputs. + */ + for (i = 0; i < opr_sz_8 ; i += 2) { + uint64_t d0, d1; + + d0 = n[i * 4 + 0] * (int64_t)m_indexed[i * 4 + 0]; + d0 += n[i * 4 + 1] * (int64_t)m_indexed[i * 4 + 1]; + d0 += n[i * 4 + 2] * (int64_t)m_indexed[i * 4 + 2]; + d0 += n[i * 4 + 3] * (int64_t)m_indexed[i * 4 + 3]; + d1 = n[i * 4 + 4] * (int64_t)m_indexed[i * 4 + 0]; + d1 += n[i * 4 + 5] * (int64_t)m_indexed[i * 4 + 1]; + d1 += n[i * 4 + 6] * (int64_t)m_indexed[i * 4 + 2]; + d1 += n[i * 4 + 7] * (int64_t)m_indexed[i * 4 + 3]; + + d[i + 0] += d0; + d[i + 1] += d1; + } + + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_udot_idx_h)(void *vd, void *vn, void *vm, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc), opr_sz_8 = opr_sz / 8; + intptr_t index = simd_data(desc); + uint64_t *d = vd; + uint16_t *n = vn; + uint16_t *m_indexed = (uint16_t *)vm + index * 4; + + /* This is supported by SVE only, so opr_sz is always a multiple of 16. + * Process the entire segment all at once, writing back the results + * only after we've consumed all of the inputs. + */ + for (i = 0; i < opr_sz_8 ; i += 2) { + uint64_t d0, d1; + + d0 = n[i * 4 + 0] * (uint64_t)m_indexed[i * 4 + 0]; + d0 += n[i * 4 + 1] * (uint64_t)m_indexed[i * 4 + 1]; + d0 += n[i * 4 + 2] * (uint64_t)m_indexed[i * 4 + 2]; + d0 += n[i * 4 + 3] * (uint64_t)m_indexed[i * 4 + 3]; + d1 = n[i * 4 + 4] * (uint64_t)m_indexed[i * 4 + 0]; + d1 += n[i * 4 + 5] * (uint64_t)m_indexed[i * 4 + 1]; + d1 += n[i * 4 + 6] * (uint64_t)m_indexed[i * 4 + 2]; + d1 += n[i * 4 + 7] * (uint64_t)m_indexed[i * 4 + 3]; + + d[i + 0] += d0; + d[i + 1] += d1; + } + + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, void *vfpst, uint32_t desc) { diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ MUL_zzi 00100101 .. 110 000 110 ........ ..... @rdn_i8s # SVE integer dot product (unpredicated) DOT_zzz 01000100 1 sz:1 0 rm:5 00000 u:1 rn:5 rd:5 ra=%reg_movprfx +# SVE integer dot product (indexed) +DOT_zzx 01000100 101 index:2 rm:3 00000 u:1 rn:5 rd:5 \ + sz=0 ra=%reg_movprfx +DOT_zzx 01000100 111 index:1 rm:4 00000 u:1 rn:5 rd:5 \ + sz=1 ra=%reg_movprfx + # SVE floating-point complex add (predicated) FCADD 01100100 esz:2 00000 rot:1 100 pg:3 rm:5 rd:5 \ rn=%reg_movprfx -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Enable ARM_FEATURE_SVE for the generic "max" cpu. Tested-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 1 + target/arm/cpu.c | 7 +++++++ target/arm/cpu64.c | 1 + 3 files changed, 9 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_V8_ATOMICS, ARM_HWCAP_A64_ATOMICS); GET_FEATURE(ARM_FEATURE_V8_RDM, ARM_HWCAP_A64_ASIMDRDM); GET_FEATURE(ARM_FEATURE_V8_FCMA, ARM_HWCAP_A64_FCMA); + GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); #undef GET_FEATURE return hwcaps; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) env->cp15.sctlr_el[1] |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 20, 2, 3); + /* and to the SVE instructions */ + env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 16, 2, 3); + env->cp15.cptr_el[3] |= CPTR_EZ; + /* with maximum vector length */ + env->vfp.zcr_el[1] = ARM_MAX_VQ - 1; + env->vfp.zcr_el[2] = ARM_MAX_VQ - 1; + env->vfp.zcr_el[3] = ARM_MAX_VQ - 1; #else /* Reset into the highest available EL */ if (arm_feature(env, ARM_FEATURE_EL3)) { diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8_RDM); set_feature(&cpu->env, ARM_FEATURE_V8_FP16); set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); + set_feature(&cpu->env, ARM_FEATURE_SVE); /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. */ -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> We've already added the helpers with an SVE patch, all that remains is to wire up the aa64 and aa32 translators. Enable the feature within -cpu max for CONFIG_USER_ONLY. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180627043328.11531-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + linux-user/elfload.c | 1 + target/arm/cpu.c | 1 + target/arm/cpu64.c | 1 + target/arm/translate-a64.c | 36 +++++++++++++++++++ target/arm/translate.c | 74 +++++++++++++++++++++++++++----------- 6 files changed, 93 insertions(+), 21 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V8_SM4, /* implements SM4 part of v8 Crypto Extensions */ ARM_FEATURE_V8_ATOMICS, /* ARMv8.1-Atomics feature */ ARM_FEATURE_V8_RDM, /* implements v8.1 simd round multiply */ + ARM_FEATURE_V8_DOTPROD, /* implements v8.2 simd dot product */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_V8_FCMA, /* has complex number part of v8.3 extensions. */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); GET_FEATURE(ARM_FEATURE_V8_ATOMICS, ARM_HWCAP_A64_ATOMICS); GET_FEATURE(ARM_FEATURE_V8_RDM, ARM_HWCAP_A64_ASIMDRDM); + GET_FEATURE(ARM_FEATURE_V8_DOTPROD, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE(ARM_FEATURE_V8_FCMA, ARM_HWCAP_A64_FCMA); GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); #undef GET_FEATURE diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_V8_RDM); + set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); #endif } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_V8_ATOMICS); set_feature(&cpu->env, ARM_FEATURE_V8_RDM); + set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); set_feature(&cpu->env, ARM_FEATURE_V8_FP16); set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); set_feature(&cpu->env, ARM_FEATURE_SVE); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3(DisasContext *s, bool is_q, int rd, vec_full_reg_size(s), gvec_op); } +/* Expand a 3-operand operation using an out-of-line helper. */ +static void gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd, + int rn, int rm, int data, gen_helper_gvec_3 *fn) +{ + tcg_gen_gvec_3_ool(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + is_q ? 16 : 8, vec_full_reg_size(s), data, fn); +} + /* Expand a 3-operand + env pointer operation using * an out-of-line helper. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } feature = ARM_FEATURE_V8_RDM; break; + case 0x02: /* SDOT (vector) */ + case 0x12: /* UDOT (vector) */ + if (size != MO_32) { + unallocated_encoding(s); + return; + } + feature = ARM_FEATURE_V8_DOTPROD; + break; case 0x8: /* FCMLA, #0 */ case 0x9: /* FCMLA, #90 */ case 0xa: /* FCMLA, #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } return; + case 0x2: /* SDOT / UDOT */ + gen_gvec_op3_ool(s, is_q, rd, rn, rm, 0, + u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); + return; + case 0x8: /* FCMLA, #0 */ case 0x9: /* FCMLA, #90 */ case 0xa: /* FCMLA, #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) return; } break; + case 0x0e: /* SDOT */ + case 0x1e: /* UDOT */ + if (size != MO_32 || !arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + unallocated_encoding(s); + return; + } + break; case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } switch (16 * u + opcode) { + case 0x0e: /* SDOT */ + case 0x1e: /* UDOT */ + gen_gvec_op3_ool(s, is_q, rd, rn, rm, index, + u ? gen_helper_gvec_udot_idx_b + : gen_helper_gvec_sdot_idx_b); + return; case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) */ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) { - gen_helper_gvec_3_ptr *fn_gvec_ptr; - int rd, rn, rm, rot, size, opr_sz; - TCGv_ptr fpst; + gen_helper_gvec_3 *fn_gvec = NULL; + gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; + int rd, rn, rm, opr_sz; + int data = 0; bool q; q = extract32(insn, 6, 1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) if ((insn & 0xfe200f10) == 0xfc200800) { /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */ - size = extract32(insn, 20, 1); - rot = extract32(insn, 23, 2); + int size = extract32(insn, 20, 1); + data = extract32(insn, 23, 2); /* rot */ if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; } else if ((insn & 0xfea00f10) == 0xfc800800) { /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ - size = extract32(insn, 20, 1); - rot = extract32(insn, 24, 1); + int size = extract32(insn, 20, 1); + data = extract32(insn, 24, 1); /* rot */ if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; } fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; + } else if ((insn & 0xfeb00f00) == 0xfc200d00) { + /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ + bool u = extract32(insn, 4, 1); + if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + return 1; + } + fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; } else { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) } opr_sz = (1 + q) * 8; - fpst = get_fpstatus_ptr(1); - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), - vfp_reg_offset(1, rn), - vfp_reg_offset(1, rm), fpst, - opr_sz, opr_sz, rot, fn_gvec_ptr); - tcg_temp_free_ptr(fpst); + if (fn_gvec_ptr) { + TCGv_ptr fpst = get_fpstatus_ptr(1); + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), + vfp_reg_offset(1, rn), + vfp_reg_offset(1, rm), fpst, + opr_sz, opr_sz, data, fn_gvec_ptr); + tcg_temp_free_ptr(fpst); + } else { + tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), + vfp_reg_offset(1, rn), + vfp_reg_offset(1, rm), + opr_sz, opr_sz, data, fn_gvec); + } return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) { - gen_helper_gvec_3_ptr *fn_gvec_ptr; + gen_helper_gvec_3 *fn_gvec = NULL; + gen_helper_gvec_3_ptr *fn_gvec_ptr = NULL; int rd, rn, rm, opr_sz, data; - TCGv_ptr fpst; bool q; q = extract32(insn, 6, 1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) data = (index << 2) | rot; fn_gvec_ptr = (size ? gen_helper_gvec_fcmlas_idx : gen_helper_gvec_fcmlah_idx); + } else if ((insn & 0xffb00f00) == 0xfe200d00) { + /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ + int u = extract32(insn, 4, 1); + if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + return 1; + } + fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; + /* rm is just Vm, and index is M. */ + data = extract32(insn, 5, 1); /* index */ + rm = extract32(insn, 0, 4); } else { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) } opr_sz = (1 + q) * 8; - fpst = get_fpstatus_ptr(1); - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), - vfp_reg_offset(1, rn), - vfp_reg_offset(1, rm), fpst, - opr_sz, opr_sz, data, fn_gvec_ptr); - tcg_temp_free_ptr(fpst); + if (fn_gvec_ptr) { + TCGv_ptr fpst = get_fpstatus_ptr(1); + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), + vfp_reg_offset(1, rn), + vfp_reg_offset(1, rm), fpst, + opr_sz, opr_sz, data, fn_gvec_ptr); + tcg_temp_free_ptr(fpst); + } else { + tcg_gen_gvec_3_ool(vfp_reg_offset(1, rd), + vfp_reg_offset(1, rn), + vfp_reg_offset(1, rm), + opr_sz, opr_sz, data, fn_gvec); + } return 0; } -- 2.17.1 From: Alex Bennée <alex.bennee@linaro.org> Since kernel commit a86bd139f2 (arm64: arch_timer: Enable CNTVCT_EL0 trap..), released in kernel version v4.12, user-space has been able to read these system registers. As we can't use QEMUTimer's in linux-user mode we just directly call cpu_get_clock(). Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180625160009.17437-2-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo generic_timer_cp_reginfo[] = { }; #else -/* In user-mode none of the generic timer registers are accessible, - * and their implementation depends on QEMU_CLOCK_VIRTUAL and qdev gpio outputs, - * so instead just don't register any of them. + +/* In user-mode most of the generic timer registers are inaccessible + * however modern kernels (4.12+) allow access to cntvct_el0 */ + +static uint64_t gt_virt_cnt_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* Currently we have no support for QEMUTimer in linux-user so we + * can't call gt_get_countervalue(env), instead we directly + * call the lower level functions. + */ + return cpu_get_clock() / GTIMER_SCALE; +} + static const ARMCPRegInfo generic_timer_cp_reginfo[] = { + { .name = "CNTFRQ_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 0, + .type = ARM_CP_CONST, .access = PL0_R /* no PL1_RW in linux-user */, + .fieldoffset = offsetof(CPUARMState, cp15.c14_cntfrq), + .resetvalue = NANOSECONDS_PER_SECOND / GTIMER_SCALE, + }, + { .name = "CNTVCT_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 0, .opc2 = 2, + .access = PL0_R, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .readfn = gt_virt_cnt_read, + }, REGINFO_SENTINEL }; -- 2.17.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mcimx7d-sabre.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/mcimx7d-sabre.c b/hw/arm/mcimx7d-sabre.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mcimx7d-sabre.c +++ b/hw/arm/mcimx7d-sabre.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/fsl-imx7.h" #include "hw/boards.h" #include "sysemu/sysemu.h" -#include "sysemu/device_tree.h" #include "qemu/error-report.h" #include "sysemu/qtest.h" -#include "net/net.h" typedef struct { FslIMX7State soc; -- 2.17.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx7.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) /* * SRC */ - create_unimplemented_device("sdma", FSL_IMX7_SRC_ADDR, FSL_IMX7_SRC_SIZE); + create_unimplemented_device("src", FSL_IMX7_SRC_ADDR, FSL_IMX7_SRC_SIZE); /* * Watchdog -- 2.17.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> The qdev_get_gpio_in() function accept an int as second parameter. Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx7.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_ECSPI4_ADDR, }; - static const hwaddr FSL_IMX7_SPIn_IRQ[FSL_IMX7_NUM_ECSPIS] = { + static const int FSL_IMX7_SPIn_IRQ[FSL_IMX7_NUM_ECSPIS] = { FSL_IMX7_ECSPI1_IRQ, FSL_IMX7_ECSPI2_IRQ, FSL_IMX7_ECSPI3_IRQ, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_I2C4_ADDR, }; - static const hwaddr FSL_IMX7_I2Cn_IRQ[FSL_IMX7_NUM_I2CS] = { + static const int FSL_IMX7_I2Cn_IRQ[FSL_IMX7_NUM_I2CS] = { FSL_IMX7_I2C1_IRQ, FSL_IMX7_I2C2_IRQ, FSL_IMX7_I2C3_IRQ, @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_USB3_ADDR, }; - static const hwaddr FSL_IMX7_USBn_IRQ[FSL_IMX7_NUM_USBS] = { + static const int FSL_IMX7_USBn_IRQ[FSL_IMX7_NUM_USBS] = { FSL_IMX7_USB1_IRQ, FSL_IMX7_USB2_IRQ, FSL_IMX7_USB3_IRQ, -- 2.17.1 From: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Message-id: 1529699547-17044-5-git-send-email-alindsay@codeaurora.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/cpu.c | 21 ++++++++++++++------- target/arm/kvm32.c | 8 ++++---- 3 files changed, 19 insertions(+), 11 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ ARM_FEATURE_THUMB2EE, ARM_FEATURE_V7MP, /* v7 Multiprocessing Extensions */ + ARM_FEATURE_V7VE, /* v7 Virtualization Extensions (non-EL2 parts) */ ARM_FEATURE_V4T, ARM_FEATURE_V5, ARM_FEATURE_STRONGARM, diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) /* Some features automatically imply others: */ if (arm_feature(env, ARM_FEATURE_V8)) { - set_feature(env, ARM_FEATURE_V7); + set_feature(env, ARM_FEATURE_V7VE); + } + if (arm_feature(env, ARM_FEATURE_V7VE)) { + /* v7 Virtualization Extensions. In real hardware this implies + * EL2 and also the presence of the Security Extensions. + * For QEMU, for backwards-compatibility we implement some + * CPUs or CPU configs which have no actual EL2 or EL3 but do + * include the various other features that V7VE implies. + * Presence of EL2 itself is ARM_FEATURE_EL2, and of the + * Security Extensions is ARM_FEATURE_EL3. + */ set_feature(env, ARM_FEATURE_ARM_DIV); set_feature(env, ARM_FEATURE_LPAE); + set_feature(env, ARM_FEATURE_V7); } if (arm_feature(env, ARM_FEATURE_V7)) { set_feature(env, ARM_FEATURE_VAPA); @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); cpu->dtb_compatible = "arm,cortex-a7"; - set_feature(&cpu->env, ARM_FEATURE_V7); + set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); - set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_LPAE); set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A7; cpu->midr = 0x410fc075; @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); cpu->dtb_compatible = "arm,cortex-a15"; - set_feature(&cpu->env, ARM_FEATURE_V7); + set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); - set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_LPAE); set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A15; cpu->midr = 0x412fc0f1; diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) /* Now we've retrieved all the register information we can * set the feature bits based on the ID register fields. * We can assume any KVM supporting CPU is at least a v7 - * with VFPv3, LPAE and the generic timers; this in turn implies - * most of the other feature bits, but a few must be tested. + * with VFPv3, virtualization extensions, and the generic + * timers; this in turn implies most of the other feature + * bits, but a few must be tested. */ - set_feature(&features, ARM_FEATURE_V7); + set_feature(&features, ARM_FEATURE_V7VE); set_feature(&features, ARM_FEATURE_VFP3); - set_feature(&features, ARM_FEATURE_LPAE); set_feature(&features, ARM_FEATURE_GENERIC_TIMER); switch (extract32(id_isar0, 24, 4)) { -- 2.17.1 From: Aaron Lindsay <alindsay@codeaurora.org> KVM implies V7VE, which implies ARM_DIV and THUMB_DIV. The conditional detection here is therefore unnecessary. Because V7VE is already unconditionally specified for all KVM hosts, ARM_DIV and THUMB_DIV are already indirectly specified and do not need to be included here at all. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Message-id: 1529699547-17044-6-git-send-email-alindsay@codeaurora.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm32.c | 19 +------------------ 1 file changed, 1 insertion(+), 18 deletions(-) diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) * and then query that CPU for the relevant ID registers. */ int i, ret, fdarray[3]; - uint32_t midr, id_pfr0, id_isar0, mvfr1; + uint32_t midr, id_pfr0, mvfr1; uint64_t features = 0; /* Old kernels may not know about the PREFERRED_TARGET ioctl: however * we know these will only support creating one kind of guest CPU, @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) | ENCODE_CP_REG(15, 0, 0, 0, 1, 0, 0), .addr = (uintptr_t)&id_pfr0, }, - { - .id = KVM_REG_ARM | KVM_REG_SIZE_U32 - | ENCODE_CP_REG(15, 0, 0, 0, 2, 0, 0), - .addr = (uintptr_t)&id_isar0, - }, { .id = KVM_REG_ARM | KVM_REG_SIZE_U32 | KVM_REG_ARM_VFP | KVM_REG_ARM_VFP_MVFR1, @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) set_feature(&features, ARM_FEATURE_VFP3); set_feature(&features, ARM_FEATURE_GENERIC_TIMER); - switch (extract32(id_isar0, 24, 4)) { - case 1: - set_feature(&features, ARM_FEATURE_THUMB_DIV); - break; - case 2: - set_feature(&features, ARM_FEATURE_ARM_DIV); - set_feature(&features, ARM_FEATURE_THUMB_DIV); - break; - default: - break; - } - if (extract32(id_pfr0, 12, 4) == 1) { set_feature(&features, ARM_FEATURE_THUMB2EE); } -- 2.17.1 From: Aaron Lindsay <alindsay@codeaurora.org> This makes it match its AArch64 equivalent, PMINTENSET_EL1 Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Message-id: 1529699547-17044-13-git-send-email-alindsay@codeaurora.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .writefn = pmuserenr_write, .raw_writefn = raw_write }, { .name = "PMINTENSET", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 1, .access = PL1_RW, .accessfn = access_tpm, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pminten), .resetvalue = 0, .writefn = pmintenset_write, .raw_writefn = raw_write }, -- 2.17.1 We don't actually implement SD command CRC checking, because for almost all of our SD controllers the CRC generation is done in hardware, and so modelling CRC generation and checking would be a bit pointless. (The exception is that milkymist-memcard makes the guest software compute the CRC.) As a result almost all of our SD controller models don't bother to set the SDRequest crc field, and the SD card model doesn't check it. So the tracing of it in sdbus_do_command() provokes Coverity warnings about use of uninitialized data. Drop the CRC field from the trace; we can always add it back if and when we do anything useful with the CRC. Fixes Coverity issues 1386072, 1386074, 1386076, 1390571. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180626180324.5537-1-peter.maydell@linaro.org --- hw/sd/core.c | 2 +- hw/sd/trace-events | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/sd/core.c b/hw/sd/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/core.c +++ b/hw/sd/core.c @@ -XXX,XX +XXX,XX @@ int sdbus_do_command(SDBus *sdbus, SDRequest *req, uint8_t *response) { SDState *card = get_card(sdbus); - trace_sdbus_command(sdbus_name(sdbus), req->cmd, req->arg, req->crc); + trace_sdbus_command(sdbus_name(sdbus), req->cmd, req->arg); if (card) { SDCardClass *sc = SD_CARD_GET_CLASS(card); diff --git a/hw/sd/trace-events b/hw/sd/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -XXX,XX +XXX,XX @@ bcm2835_sdhost_edm_change(const char *why, uint32_t edm) "(%s) EDM now 0x%x" bcm2835_sdhost_update_irq(uint32_t irq) "IRQ bits 0x%x\n" # hw/sd/core.c -sdbus_command(const char *bus_name, uint8_t cmd, uint32_t arg, uint8_t crc) "@%s CMD%02d arg 0x%08x crc 0x%02x" +sdbus_command(const char *bus_name, uint8_t cmd, uint32_t arg) "@%s CMD%02d arg 0x%08x" sdbus_read(const char *bus_name, uint8_t value) "@%s value 0x%02x" sdbus_write(const char *bus_name, uint8_t value) "@%s value 0x%02x" sdbus_set_voltage(const char *bus_name, uint16_t millivolts) "@%s %u (mV)" -- 2.17.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The load/store API will ease further code movement. Per the Physical Layer Simplified Spec. "3.6 Bus Protocol": "In the CMD line the Most Significant Bit (MSB) is transmitted first, the Least Significant Bit (LSB) is the last." Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/bcm2835_sdhost.c | 13 +++++-------- hw/sd/milkymist-memcard.c | 3 +-- hw/sd/omap_mmc.c | 6 ++---- hw/sd/pl181.c | 11 ++++------- hw/sd/sdhci.c | 15 +++++---------- hw/sd/ssi-sd.c | 6 ++---- 6 files changed, 19 insertions(+), 35 deletions(-) diff --git a/hw/sd/bcm2835_sdhost.c b/hw/sd/bcm2835_sdhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/bcm2835_sdhost.c +++ b/hw/sd/bcm2835_sdhost.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_send_command(BCM2835SDHostState *s) goto error; } if (!(s->cmd & SDCMD_NO_RESPONSE)) { -#define RWORD(n) (((uint32_t)rsp[n] << 24) | (rsp[n + 1] << 16) \ - | (rsp[n + 2] << 8) | rsp[n + 3]) if (rlen == 0 || (rlen == 4 && (s->cmd & SDCMD_LONG_RESPONSE))) { goto error; } @@ -XXX,XX +XXX,XX @@ static void bcm2835_sdhost_send_command(BCM2835SDHostState *s) goto error; } if (rlen == 4) { - s->rsp[0] = RWORD(0); + s->rsp[0] = ldl_be_p(&rsp[0]); s->rsp[1] = s->rsp[2] = s->rsp[3] = 0; } else { - s->rsp[0] = RWORD(12); - s->rsp[1] = RWORD(8); - s->rsp[2] = RWORD(4); - s->rsp[3] = RWORD(0); + s->rsp[0] = ldl_be_p(&rsp[12]); + s->rsp[1] = ldl_be_p(&rsp[8]); + s->rsp[2] = ldl_be_p(&rsp[4]); + s->rsp[3] = ldl_be_p(&rsp[0]); } -#undef RWORD } /* We never really delay commands, so if this was a 'busywait' command * then we've completed it now and can raise the interrupt. diff --git a/hw/sd/milkymist-memcard.c b/hw/sd/milkymist-memcard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/milkymist-memcard.c +++ b/hw/sd/milkymist-memcard.c @@ -XXX,XX +XXX,XX @@ static void memcard_sd_command(MilkymistMemcardState *s) SDRequest req; req.cmd = s->command[0] & 0x3f; - req.arg = (s->command[1] << 24) | (s->command[2] << 16) - | (s->command[3] << 8) | s->command[4]; + req.arg = ldl_be_p(s->command + 1); req.crc = s->command[5]; s->response[0] = req.cmd; diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ static void omap_mmc_command(struct omap_mmc_s *host, int cmd, int dir, CID_CSD_OVERWRITE; if (host->sdio & (1 << 13)) mask |= AKE_SEQ_ERROR; - rspstatus = (response[0] << 24) | (response[1] << 16) | - (response[2] << 8) | (response[3] << 0); + rspstatus = ldl_be_p(response); break; case sd_r2: @@ -XXX,XX +XXX,XX @@ static void omap_mmc_command(struct omap_mmc_s *host, int cmd, int dir, } rsplen = 4; - rspstatus = (response[0] << 24) | (response[1] << 16) | - (response[2] << 8) | (response[3] << 0); + rspstatus = ldl_be_p(response); if (rspstatus & 0x80000000) host->status &= 0xe000; else diff --git a/hw/sd/pl181.c b/hw/sd/pl181.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/pl181.c +++ b/hw/sd/pl181.c @@ -XXX,XX +XXX,XX @@ static void pl181_send_command(PL181State *s) if (rlen < 0) goto error; if (s->cmd & PL181_CMD_RESPONSE) { -#define RWORD(n) (((uint32_t)response[n] << 24) | (response[n + 1] << 16) \ - | (response[n + 2] << 8) | response[n + 3]) if (rlen == 0 || (rlen == 4 && (s->cmd & PL181_CMD_LONGRESP))) goto error; if (rlen != 4 && rlen != 16) goto error; - s->response[0] = RWORD(0); + s->response[0] = ldl_be_p(&response[0]); if (rlen == 4) { s->response[1] = s->response[2] = s->response[3] = 0; } else { - s->response[1] = RWORD(4); - s->response[2] = RWORD(8); - s->response[3] = RWORD(12) & ~1; + s->response[1] = ldl_be_p(&response[4]); + s->response[2] = ldl_be_p(&response[8]); + s->response[3] = ldl_be_p(&response[12]) & ~1; } DPRINTF("Response received\n"); s->status |= PL181_STATUS_CMDRESPEND; -#undef RWORD } else { DPRINTF("Command sent\n"); s->status |= PL181_STATUS_CMDSENT; diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sdhci.c +++ b/hw/sd/sdhci.c @@ -XXX,XX +XXX,XX @@ static void sdhci_send_command(SDHCIState *s) if (s->cmdreg & SDHC_CMD_RESPONSE) { if (rlen == 4) { - s->rspreg[0] = (response[0] << 24) | (response[1] << 16) | - (response[2] << 8) | response[3]; + s->rspreg[0] = ldl_be_p(response); s->rspreg[1] = s->rspreg[2] = s->rspreg[3] = 0; trace_sdhci_response4(s->rspreg[0]); } else if (rlen == 16) { - s->rspreg[0] = (response[11] << 24) | (response[12] << 16) | - (response[13] << 8) | response[14]; - s->rspreg[1] = (response[7] << 24) | (response[8] << 16) | - (response[9] << 8) | response[10]; - s->rspreg[2] = (response[3] << 24) | (response[4] << 16) | - (response[5] << 8) | response[6]; + s->rspreg[0] = ldl_be_p(&response[11]); + s->rspreg[1] = ldl_be_p(&response[7]); + s->rspreg[2] = ldl_be_p(&response[3]); s->rspreg[3] = (response[0] << 16) | (response[1] << 8) | response[2]; trace_sdhci_response16(s->rspreg[3], s->rspreg[2], @@ -XXX,XX +XXX,XX @@ static void sdhci_end_transfer(SDHCIState *s) trace_sdhci_end_transfer(request.cmd, request.arg); sdbus_do_command(&s->sdbus, &request, response); /* Auto CMD12 response goes to the upper Response register */ - s->rspreg[3] = (response[0] << 24) | (response[1] << 16) | - (response[2] << 8) | response[3]; + s->rspreg[3] = ldl_be_p(response); } s->prnsts &= ~(SDHC_DOING_READ | SDHC_DOING_WRITE | diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/ssi-sd.c +++ b/hw/sd/ssi-sd.c @@ -XXX,XX +XXX,XX @@ static uint32_t ssi_sd_transfer(SSISlave *dev, uint32_t val) uint8_t longresp[16]; /* FIXME: Check CRC. */ request.cmd = s->cmd; - request.arg = (s->cmdarg[0] << 24) | (s->cmdarg[1] << 16) - | (s->cmdarg[2] << 8) | s->cmdarg[3]; + request.arg = ldl_be_p(s->cmdarg); DPRINTF("CMD%d arg 0x%08x\n", s->cmd, request.arg); s->arglen = sdbus_do_command(&s->sdbus, &request, longresp); if (s->arglen <= 0) { @@ -XXX,XX +XXX,XX @@ static uint32_t ssi_sd_transfer(SSISlave *dev, uint32_t val) /* CMD13 returns a 2-byte statuse work. Other commands only return the first byte. */ s->arglen = (s->cmd == 13) ? 2 : 1; - cardstatus = (longresp[0] << 24) | (longresp[1] << 16) - | (longresp[2] << 8) | longresp[3]; + cardstatus = ldl_be_p(longresp); status = 0; if (((cardstatus >> 9) & 0xf) < 4) status |= SSI_SDR_IDLE; -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> We already check for the same condition within the normal integer sdiv and sdiv64 helpers. Use a slightly different formation that does not require deducing the expression type. Fixes: f97cfd596ed Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180629001538.11415-2-richard.henderson@linaro.org [PMM: reworded a comment] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc) \ #define DO_MIN(N, M) ((N) >= (M) ? (M) : (N)) #define DO_ABD(N, M) ((N) >= (M) ? (N) - (M) : (M) - (N)) #define DO_MUL(N, M) (N * M) -#define DO_DIV(N, M) (M ? N / M : 0) + + +/* + * We must avoid the C undefined behaviour cases: division by + * zero and signed division of INT_MIN by -1. Both of these + * have architecturally defined required results for Arm. + * We special case all signed divisions by -1 to avoid having + * to deduce the minimum integer for the type involved. + */ +#define DO_SDIV(N, M) (unlikely(M == 0) ? 0 : unlikely(M == -1) ? -N : N / M) +#define DO_UDIV(N, M) (unlikely(M == 0) ? 0 : N / M) DO_ZPZZ(sve_and_zpzz_b, uint8_t, H1, DO_AND) DO_ZPZZ(sve_and_zpzz_h, uint16_t, H1_2, DO_AND) @@ -XXX,XX +XXX,XX @@ DO_ZPZZ(sve_umulh_zpzz_h, uint16_t, H1_2, do_mulh_h) DO_ZPZZ(sve_umulh_zpzz_s, uint32_t, H1_4, do_mulh_s) DO_ZPZZ_D(sve_umulh_zpzz_d, uint64_t, do_umulh_d) -DO_ZPZZ(sve_sdiv_zpzz_s, int32_t, H1_4, DO_DIV) -DO_ZPZZ_D(sve_sdiv_zpzz_d, int64_t, DO_DIV) +DO_ZPZZ(sve_sdiv_zpzz_s, int32_t, H1_4, DO_SDIV) +DO_ZPZZ_D(sve_sdiv_zpzz_d, int64_t, DO_SDIV) -DO_ZPZZ(sve_udiv_zpzz_s, uint32_t, H1_4, DO_DIV) -DO_ZPZZ_D(sve_udiv_zpzz_d, uint64_t, DO_DIV) +DO_ZPZZ(sve_udiv_zpzz_s, uint32_t, H1_4, DO_UDIV) +DO_ZPZZ_D(sve_udiv_zpzz_d, uint64_t, DO_UDIV) /* Note that all bits of the shift are significant and not modulo the element size. */ -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> Leave ARM_CP_SVE, removing ARM_CP_FPU; the sve_access_check produced by the flag already includes fp_access_check. If we also check ARM_CP_FPU the double fp_access_check asserts. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20180629001538.11415-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 ++++---- target/arm/translate-a64.c | 5 ++--- 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void zcr_write(CPUARMState *env, const ARMCPRegInfo *ri, static const ARMCPRegInfo zcr_el1_reginfo = { .name = "ZCR_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_SVE | ARM_CP_FPU, + .access = PL1_RW, .type = ARM_CP_SVE, .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[1]), .writefn = zcr_write, .raw_writefn = raw_write }; @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo zcr_el1_reginfo = { static const ARMCPRegInfo zcr_el2_reginfo = { .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_SVE | ARM_CP_FPU, + .access = PL2_RW, .type = ARM_CP_SVE, .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[2]), .writefn = zcr_write, .raw_writefn = raw_write }; @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo zcr_el2_reginfo = { static const ARMCPRegInfo zcr_no_el2_reginfo = { .name = "ZCR_EL2", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_SVE | ARM_CP_FPU, + .access = PL2_RW, .type = ARM_CP_SVE, .readfn = arm_cp_read_zero, .writefn = arm_cp_write_ignore }; static const ARMCPRegInfo zcr_el3_reginfo = { .name = "ZCR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 1, .crm = 2, .opc2 = 0, - .access = PL3_RW, .type = ARM_CP_SVE | ARM_CP_FPU, + .access = PL3_RW, .type = ARM_CP_SVE, .fieldoffset = offsetof(CPUARMState, vfp.zcr_el[3]), .writefn = zcr_write, .raw_writefn = raw_write }; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, default: break; } - if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) { - return; - } if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) { return; + } else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) { + return; } if ((tb_cflags(s->base.tb) & CF_USE_ICOUNT) && (ri->type & ARM_CP_IO)) { -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> There is no need to re-set these 9 features already implied by the call to aarch64_a57_initfn. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180629001538.11415-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 9 --------- 1 file changed, 9 deletions(-) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * whereas the architecture requires them to be present in both if * present in either. */ - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_VFP4); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); set_feature(&cpu->env, ARM_FEATURE_V8_SHA512); set_feature(&cpu->env, ARM_FEATURE_V8_SHA3); set_feature(&cpu->env, ARM_FEATURE_V8_SM3); set_feature(&cpu->env, ARM_FEATURE_V8_SM4); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_V8_ATOMICS); set_feature(&cpu->env, ARM_FEATURE_V8_RDM); set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> There is no need to re-set these 3 features already implied by the call to aarch64_a15_initfn. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180629001538.11415-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) * since we don't correctly set the ID registers to advertise them, */ set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_VFP4); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_V8_AES); set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); -- 2.17.1 From: Richard Henderson <richard.henderson@linaro.org> This register was added to aa32 state by ARMv8.2. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180629001538.11415-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/cpu.c | 4 ++++ target/arm/cpu64.c | 2 ++ target/arm/helper.c | 5 ++--- 4 files changed, 9 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { uint32_t id_isar3; uint32_t id_isar4; uint32_t id_isar5; + uint32_t id_isar6; uint64_t id_aa64pfr0; uint64_t id_aa64pfr1; uint64_t id_aa64dfr0; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void cortex_m3_initfn(Object *obj) cpu->id_isar3 = 0x01111110; cpu->id_isar4 = 0x01310102; cpu->id_isar5 = 0x00000000; + cpu->id_isar6 = 0x00000000; } static void cortex_m4_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m4_initfn(Object *obj) cpu->id_isar3 = 0x01111110; cpu->id_isar4 = 0x01310102; cpu->id_isar5 = 0x00000000; + cpu->id_isar6 = 0x00000000; } static void cortex_m33_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m33_initfn(Object *obj) cpu->id_isar3 = 0x01111131; cpu->id_isar4 = 0x01310132; cpu->id_isar5 = 0x00000000; + cpu->id_isar6 = 0x00000000; cpu->clidr = 0x00000000; cpu->ctr = 0x8000c000; } @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) cpu->id_isar3 = 0x01112131; cpu->id_isar4 = 0x0010142; cpu->id_isar5 = 0x0; + cpu->id_isar6 = 0x0; cpu->mp_is_up = true; cpu->pmsav7_dregion = 16; define_arm_cp_regs(cpu, cortexr5_cp_reginfo); diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->id_isar3 = 0x01112131; cpu->id_isar4 = 0x00011142; cpu->id_isar5 = 0x00011121; + cpu->id_isar6 = 0; cpu->id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->pmceid0 = 0x00000000; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->id_isar3 = 0x01112131; cpu->id_isar4 = 0x00011142; cpu->id_isar5 = 0x00011121; + cpu->id_isar6 = 0; cpu->id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->id_aa64isar0 = 0x00011120; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 6, .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = cpu->id_mmfr4 }, - /* 7 is as yet unallocated and must RAZ */ - { .name = "ID_ISAR7_RESERVED", .state = ARM_CP_STATE_BOTH, + { .name = "ID_ISAR6", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 7, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = 0 }, + .resetvalue = cpu->id_isar6 }, REGINFO_SENTINEL }; define_arm_cp_regs(cpu, v6_idregs); -- 2.17.1 arm queue; dunno if this will be the last before softfreeze or not, but anyway probably the last large one. New orangepi-pc board model is the big item here. thanks -- PMM The following changes since commit 67d9ef7d541c3d21a25796c51c26da096a433565: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-docs-20200312' into staging (2020-03-12 15:20:52 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200312 for you to fetch changes up to aca53be34ac3e7cac5f39396a51a338860a5a837: target/arm: kvm: Inject events at the last stage of sync (2020-03-12 16:31:10 +0000) ---------------------------------------------------------------- target-arm queue: * Fix various bugs that might result in an assert() due to incorrect hflags for M-profile CPUs * Fix Aspeed SMC Controller user-mode select handling * Report correct (with-tag) address in fault address register when TBI is enabled * cubieboard: make sure SOC object isn't leaked * fsl-imx25: Wire up eSDHC controllers * fsl-imx25: Wire up USB controllers * New board model: orangepi-pc (OrangePi PC) * ARM/KVM: if user doesn't select GIC version and the host kernel can only provide GICv3, use that, rather than defaulting to "fail because GICv2 isn't possible" * kvm: Only do KVM_SET_VCPU_EVENTS at the last stage of sync ---------------------------------------------------------------- Beata Michalska (1): target/arm: kvm: Inject events at the last stage of sync Cédric Le Goater (2): aspeed/smc: Add some tracing aspeed/smc: Fix User mode select/unselect scheme Eric Auger (6): hw/arm/virt: Document 'max' value in gic-version property description hw/arm/virt: Introduce VirtGICType enum type hw/arm/virt: Introduce finalize_gic_version() target/arm/kvm: Let kvm_arm_vgic_probe() return a bitmap hw/arm/virt: kvm: Restructure finalize_gic_version() hw/arm/virt: kvm: allow gicv3 by default if v2 cannot work Guenter Roeck (2): hw/arm/fsl-imx25: Wire up eSDHC controllers hw/arm/fsl-imx25: Wire up USB controllers Igor Mammedov (1): hw/arm/cubieboard: make sure SOC object isn't leaked Niek Linnenbank (13): hw/arm: add Allwinner H3 System-on-Chip hw/arm: add Xunlong Orange Pi PC machine hw/arm/allwinner-h3: add Clock Control Unit hw/arm/allwinner-h3: add USB host controller hw/arm/allwinner-h3: add System Control module hw/arm/allwinner: add CPU Configuration module hw/arm/allwinner: add Security Identifier device hw/arm/allwinner: add SD/MMC host controller hw/arm/allwinner-h3: add EMAC ethernet device hw/arm/allwinner-h3: add Boot ROM support hw/arm/allwinner-h3: add SDRAM controller device hw/arm/allwinner: add RTC device support docs: add Orange Pi PC document Peter Maydell (4): hw/intc/armv7m_nvic: Rebuild hflags on reset target/arm: Update hflags in trans_CPS_v7m() target/arm: Recalculate hflags correctly after writes to CONTROL target/arm: Fix some comment typos Philippe Mathieu-Daudé (5): tests/boot_linux_console: Add a quick test for the OrangePi PC board tests/boot_linux_console: Add initrd test for the Orange Pi PC board tests/boot_linux_console: Add a SD card test for the OrangePi PC board tests/boot_linux_console: Add a SLOW test booting Ubuntu on OrangePi PC tests/boot_linux_console: Test booting NetBSD via U-Boot on OrangePi PC Richard Henderson (2): target/arm: Check addresses for disabled regimes target/arm: Disable clean_data_tbi for system mode Makefile.objs | 1 + hw/arm/Makefile.objs | 1 + hw/misc/Makefile.objs | 5 + hw/net/Makefile.objs | 1 + hw/rtc/Makefile.objs | 1 + hw/sd/Makefile.objs | 1 + hw/usb/hcd-ehci.h | 1 + include/hw/arm/allwinner-a10.h | 4 + include/hw/arm/allwinner-h3.h | 161 ++++++ include/hw/arm/fsl-imx25.h | 18 + include/hw/arm/virt.h | 12 +- include/hw/misc/allwinner-cpucfg.h | 52 ++ include/hw/misc/allwinner-h3-ccu.h | 66 +++ include/hw/misc/allwinner-h3-dramc.h | 106 ++++ include/hw/misc/allwinner-h3-sysctrl.h | 67 +++ include/hw/misc/allwinner-sid.h | 60 +++ include/hw/net/allwinner-sun8i-emac.h | 99 ++++ include/hw/rtc/allwinner-rtc.h | 134 +++++ include/hw/sd/allwinner-sdhost.h | 135 +++++ target/arm/helper.h | 1 + target/arm/kvm_arm.h | 3 + hw/arm/allwinner-a10.c | 19 + hw/arm/allwinner-h3.c | 465 ++++++++++++++++++ hw/arm/cubieboard.c | 18 + hw/arm/fsl-imx25.c | 56 +++ hw/arm/imx25_pdk.c | 16 + hw/arm/orangepi.c | 130 +++++ hw/arm/virt.c | 145 ++++-- hw/intc/armv7m_nvic.c | 6 + hw/misc/allwinner-cpucfg.c | 282 +++++++++++ hw/misc/allwinner-h3-ccu.c | 242 +++++++++ hw/misc/allwinner-h3-dramc.c | 358 ++++++++++++++ hw/misc/allwinner-h3-sysctrl.c | 140 ++++++ hw/misc/allwinner-sid.c | 168 +++++++ hw/net/allwinner-sun8i-emac.c | 871 +++++++++++++++++++++++++++++++++ hw/rtc/allwinner-rtc.c | 411 ++++++++++++++++ hw/sd/allwinner-sdhost.c | 854 ++++++++++++++++++++++++++++++++ hw/ssi/aspeed_smc.c | 56 ++- hw/usb/hcd-ehci-sysbus.c | 17 + target/arm/helper.c | 49 +- target/arm/kvm.c | 14 +- target/arm/kvm32.c | 15 +- target/arm/kvm64.c | 15 +- target/arm/translate-a64.c | 11 + target/arm/translate.c | 14 +- MAINTAINERS | 9 + default-configs/arm-softmmu.mak | 1 + docs/system/arm/orangepi.rst | 253 ++++++++++ docs/system/target-arm.rst | 2 + hw/arm/Kconfig | 12 + hw/misc/trace-events | 19 + hw/net/Kconfig | 3 + hw/net/trace-events | 10 + hw/rtc/trace-events | 4 + hw/sd/trace-events | 7 + hw/ssi/trace-events | 10 + tests/acceptance/boot_linux_console.py | 230 +++++++++ 57 files changed, 5787 insertions(+), 74 deletions(-) create mode 100644 include/hw/arm/allwinner-h3.h create mode 100644 include/hw/misc/allwinner-cpucfg.h create mode 100644 include/hw/misc/allwinner-h3-ccu.h create mode 100644 include/hw/misc/allwinner-h3-dramc.h create mode 100644 include/hw/misc/allwinner-h3-sysctrl.h create mode 100644 include/hw/misc/allwinner-sid.h create mode 100644 include/hw/net/allwinner-sun8i-emac.h create mode 100644 include/hw/rtc/allwinner-rtc.h create mode 100644 include/hw/sd/allwinner-sdhost.h create mode 100644 hw/arm/allwinner-h3.c create mode 100644 hw/arm/orangepi.c create mode 100644 hw/misc/allwinner-cpucfg.c create mode 100644 hw/misc/allwinner-h3-ccu.c create mode 100644 hw/misc/allwinner-h3-dramc.c create mode 100644 hw/misc/allwinner-h3-sysctrl.c create mode 100644 hw/misc/allwinner-sid.c create mode 100644 hw/net/allwinner-sun8i-emac.c create mode 100644 hw/rtc/allwinner-rtc.c create mode 100644 hw/sd/allwinner-sdhost.c create mode 100644 docs/system/arm/orangepi.rst create mode 100644 hw/ssi/trace-events Some of an M-profile CPU's cached hflags state depends on state that's in our NVIC object. We already do an hflags rebuild when the NVIC registers are written, but we also need to do this on NVIC reset, because there's no guarantee that this will happen before the CPU reset. This fixes an assertion due to mismatched hflags which happens if the CPU is reset from inside a HardFault handler. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-2-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->itns[i] = true; } } + + /* + * We updated state that affects the CPU's MMUidx and thus its hflags; + * and we can't guarantee that we run before the CPU reset function. + */ + arm_rebuild_hflags(&s->cpu->env); } static void nvic_systick_trigger(void *opaque, int n, int level) -- 2.20.1 For M-profile CPUs, the FAULTMASK value affects the CPU's MMU index (it changes the NegPri bit). We update the hflags after calls to the v7m_msr helper in trans_MSR_v7m() but forgot to do so in trans_CPS_v7m(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-3-peter.maydell@linaro.org --- target/arm/translate.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_CPS(DisasContext *s, arg_CPS *a) static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) { - TCGv_i32 tmp, addr; + TCGv_i32 tmp, addr, el; if (!arm_dc_feature(s, ARM_FEATURE_M)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_CPS_v7m(DisasContext *s, arg_CPS_v7m *a) gen_helper_v7m_msr(cpu_env, addr, tmp); tcg_temp_free_i32(addr); } + el = tcg_const_i32(s->current_el); + gen_helper_rebuild_hflags_m32(cpu_env, el); + tcg_temp_free_i32(el); tcg_temp_free_i32(tmp); gen_lookup_tb(s); return true; -- 2.20.1 A write to the CONTROL register can change our current EL (by writing to the nPRIV bit). That means that we can't assume that s->current_el is still valid in trans_MSR_v7m() when we try to rebuild the hflags. Add a new helper rebuild_hflags_m32_newel() which, like the existing rebuild_hflags_a32_newel(), recalculates the current EL from scratch, and use it in trans_MSR_v7m(). This fixes an assertion about an hflags mismatch when the guest changes privilege by writing to CONTROL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-4-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/helper.c | 12 ++++++++++++ target/arm/translate.c | 7 +++---- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(msr_banked, void, env, i32, i32, i32) DEF_HELPER_2(get_user_reg, i32, env, i32) DEF_HELPER_3(set_user_reg, void, env, i32, i32) +DEF_HELPER_FLAGS_1(rebuild_hflags_m32_newel, TCG_CALL_NO_RWG, void, env) DEF_HELPER_FLAGS_2(rebuild_hflags_m32, TCG_CALL_NO_RWG, void, env, int) DEF_HELPER_FLAGS_1(rebuild_hflags_a32_newel, TCG_CALL_NO_RWG, void, env) DEF_HELPER_FLAGS_2(rebuild_hflags_a32, TCG_CALL_NO_RWG, void, env, int) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void arm_rebuild_hflags(CPUARMState *env) env->hflags = rebuild_hflags_internal(env); } +/* + * If we have triggered a EL state change we can't rely on the + * translator having passed it to us, we need to recompute. + */ +void HELPER(rebuild_hflags_m32_newel)(CPUARMState *env) +{ + int el = arm_current_el(env); + int fp_el = fp_exception_el(env, el); + ARMMMUIdx mmu_idx = arm_mmu_idx_el(env, el); + env->hflags = rebuild_hflags_m32(env, fp_el, mmu_idx); +} + void HELPER(rebuild_hflags_m32)(CPUARMState *env, int el) { int fp_el = fp_exception_el(env, el); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_MRS_v7m(DisasContext *s, arg_MRS_v7m *a) static bool trans_MSR_v7m(DisasContext *s, arg_MSR_v7m *a) { - TCGv_i32 addr, reg, el; + TCGv_i32 addr, reg; if (!arm_dc_feature(s, ARM_FEATURE_M)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_MSR_v7m(DisasContext *s, arg_MSR_v7m *a) gen_helper_v7m_msr(cpu_env, addr, reg); tcg_temp_free_i32(addr); tcg_temp_free_i32(reg); - el = tcg_const_i32(s->current_el); - gen_helper_rebuild_hflags_m32(cpu_env, el); - tcg_temp_free_i32(el); + /* If we wrote to CONTROL, the EL might have changed */ + gen_helper_rebuild_hflags_m32_newel(cpu_env); gen_lookup_tb(s); return true; } -- 2.20.1 Fix a couple of comment typos. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200303174950.3298-5-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- target/arm/translate.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(rebuild_hflags_m32)(CPUARMState *env, int el) /* * If we have triggered a EL state change we can't rely on the - * translator having passed it too us, we need to recompute. + * translator having passed it to us, we need to recompute. */ void HELPER(rebuild_hflags_a32_newel)(CPUARMState *env) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_coproc_insn(DisasContext *s, uint32_t insn) if (!isread && !(ri->type & ARM_CP_SUPPRESS_TB_END)) { /* - * A write to any coprocessor regiser that ends a TB + * A write to any coprocessor register that ends a TB * must rebuild the hflags for the next TB. */ TCGv_i32 tcg_el = tcg_const_i32(s->current_el); -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Reviewed-by: Joel Stanley <joel@jms.id.au> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200206112645.21275-2-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- Makefile.objs | 1 + hw/ssi/aspeed_smc.c | 17 +++++++++++++++++ hw/ssi/trace-events | 9 +++++++++ 3 files changed, 27 insertions(+) create mode 100644 hw/ssi/trace-events diff --git a/Makefile.objs b/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/Makefile.objs +++ b/Makefile.objs @@ -XXX,XX +XXX,XX @@ trace-events-subdirs += hw/scsi trace-events-subdirs += hw/sd trace-events-subdirs += hw/sparc trace-events-subdirs += hw/sparc64 +trace-events-subdirs += hw/ssi trace-events-subdirs += hw/timer trace-events-subdirs += hw/tpm trace-events-subdirs += hw/usb diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "exec/address-spaces.h" #include "qemu/units.h" +#include "trace.h" #include "hw/irq.h" #include "hw/qdev-properties.h" @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_set_segment(AspeedSMCState *s, int cs, s->ctrl->reg_to_segment(s, new, &seg); + trace_aspeed_smc_flash_set_segment(cs, new, seg.addr, seg.addr + seg.size); + /* The start address of CS0 is read-only */ if (cs == 0 && seg.addr != s->ctrl->flash_window_base) { qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_smc_flash_read(void *opaque, hwaddr addr, unsigned size) __func__, aspeed_smc_flash_mode(fl)); } + trace_aspeed_smc_flash_read(fl->id, addr, size, ret, + aspeed_smc_flash_mode(fl)); return ret; } @@ -XXX,XX +XXX,XX @@ static bool aspeed_smc_do_snoop(AspeedSMCFlash *fl, uint64_t data, AspeedSMCState *s = fl->controller; uint8_t addr_width = aspeed_smc_flash_is_4byte(fl) ? 4 : 3; + trace_aspeed_smc_do_snoop(fl->id, s->snoop_index, s->snoop_dummies, + (uint8_t) data & 0xff); + if (s->snoop_index == SNOOP_OFF) { return false; /* Do nothing */ @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_flash_write(void *opaque, hwaddr addr, uint64_t data, AspeedSMCState *s = fl->controller; int i; + trace_aspeed_smc_flash_write(fl->id, addr, size, data, + aspeed_smc_flash_mode(fl)); + if (!aspeed_smc_is_writable(fl)) { qemu_log_mask(LOG_GUEST_ERROR, "%s: flash is not writable at 0x%" HWADDR_PRIx "\n", __func__, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t aspeed_smc_read(void *opaque, hwaddr addr, unsigned int size) (s->ctrl->has_dma && addr == R_DMA_CHECKSUM) || (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_slaves) || (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->ctrl->max_slaves)) { + + trace_aspeed_smc_read(addr, size, s->regs[addr]); + return s->regs[addr]; } else { qemu_log_mask(LOG_UNIMP, "%s: not implemented: 0x%" HWADDR_PRIx "\n", @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_dma_checksum(AspeedSMCState *s) __func__, s->regs[R_DMA_FLASH_ADDR]); return; } + trace_aspeed_smc_dma_checksum(s->regs[R_DMA_FLASH_ADDR], data); /* * When the DMA is on-going, the DMA registers are updated @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, addr >>= 2; + trace_aspeed_smc_write(addr, size, data); + if (addr == s->r_conf || (addr >= s->r_timings && addr < s->r_timings + s->ctrl->nregs_timings) || diff --git a/hw/ssi/trace-events b/hw/ssi/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/ssi/trace-events @@ -XXX,XX +XXX,XX @@ +# aspeed_smc.c + +aspeed_smc_flash_set_segment(int cs, uint64_t reg, uint64_t start, uint64_t end) "CS%d segreg=0x%"PRIx64" [ 0x%"PRIx64" - 0x%"PRIx64" ]" +aspeed_smc_flash_read(int cs, uint64_t addr, uint32_t size, uint64_t data, int mode) "CS%d @0x%" PRIx64 " size %u: 0x%" PRIx64" mode:%d" +aspeed_smc_do_snoop(int cs, int index, int dummies, int data) "CS%d index:0x%x dummies:%d data:0x%x" +aspeed_smc_flash_write(int cs, uint64_t addr, uint32_t size, uint64_t data, int mode) "CS%d @0x%" PRIx64 " size %u: 0x%" PRIx64" mode:%d" +aspeed_smc_read(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 +aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 0x%08x" +aspeed_smc_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The Aspeed SMC Controller can operate in different modes : Read, Fast Read, Write and User modes. When the User mode is configured, it selects automatically the SPI slave device until the CE_STOP_ACTIVE bit is set to 1. When any other modes are configured the device is unselected. The HW logic handles the chip select automatically when the flash is accessed through its AHB window. When configuring the CEx Control Register, the User mode logic to select and unselect the slave is incorrect and data corruption can be seen on machines using two chips, witherspoon and romulus. Rework the handler setting the CEx Control Register to fix this issue. Fixes: 7c1c69bca43c ("ast2400: add SMC controllers (FMC and SPI)") Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Message-id: 20200206112645.21275-3-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/ssi/aspeed_smc.c | 39 +++++++++++++++++++++++---------------- hw/ssi/trace-events | 1 + 2 files changed, 24 insertions(+), 16 deletions(-) diff --git a/hw/ssi/aspeed_smc.c b/hw/ssi/aspeed_smc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/aspeed_smc.c +++ b/hw/ssi/aspeed_smc.c @@ -XXX,XX +XXX,XX @@ static inline int aspeed_smc_flash_is_4byte(const AspeedSMCFlash *fl) } } -static inline bool aspeed_smc_is_ce_stop_active(const AspeedSMCFlash *fl) +static void aspeed_smc_flash_do_select(AspeedSMCFlash *fl, bool unselect) { - const AspeedSMCState *s = fl->controller; + AspeedSMCState *s = fl->controller; - return s->regs[s->r_ctrl0 + fl->id] & CTRL_CE_STOP_ACTIVE; + trace_aspeed_smc_flash_select(fl->id, unselect ? "un" : ""); + + qemu_set_irq(s->cs_lines[fl->id], unselect); } static void aspeed_smc_flash_select(AspeedSMCFlash *fl) { - AspeedSMCState *s = fl->controller; - - s->regs[s->r_ctrl0 + fl->id] &= ~CTRL_CE_STOP_ACTIVE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + aspeed_smc_flash_do_select(fl, false); } static void aspeed_smc_flash_unselect(AspeedSMCFlash *fl) { - AspeedSMCState *s = fl->controller; - - s->regs[s->r_ctrl0 + fl->id] |= CTRL_CE_STOP_ACTIVE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + aspeed_smc_flash_do_select(fl, true); } static uint32_t aspeed_smc_check_segment_addr(const AspeedSMCFlash *fl, @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps aspeed_smc_flash_ops = { }, }; -static void aspeed_smc_flash_update_cs(AspeedSMCFlash *fl) +static void aspeed_smc_flash_update_ctrl(AspeedSMCFlash *fl, uint32_t value) { AspeedSMCState *s = fl->controller; + bool unselect; - s->snoop_index = aspeed_smc_is_ce_stop_active(fl) ? SNOOP_OFF : SNOOP_START; + /* User mode selects the CS, other modes unselect */ + unselect = (value & CTRL_CMD_MODE_MASK) != CTRL_USERMODE; - qemu_set_irq(s->cs_lines[fl->id], aspeed_smc_is_ce_stop_active(fl)); + /* A change of CTRL_CE_STOP_ACTIVE from 0 to 1, unselects the CS */ + if (!(s->regs[s->r_ctrl0 + fl->id] & CTRL_CE_STOP_ACTIVE) && + value & CTRL_CE_STOP_ACTIVE) { + unselect = true; + } + + s->regs[s->r_ctrl0 + fl->id] = value; + + s->snoop_index = unselect ? SNOOP_OFF : SNOOP_START; + + aspeed_smc_flash_do_select(fl, unselect); } static void aspeed_smc_reset(DeviceState *d) @@ -XXX,XX +XXX,XX @@ static void aspeed_smc_write(void *opaque, hwaddr addr, uint64_t data, s->regs[addr] = value; } else if (addr >= s->r_ctrl0 && addr < s->r_ctrl0 + s->num_cs) { int cs = addr - s->r_ctrl0; - s->regs[addr] = value; - aspeed_smc_flash_update_cs(&s->flashes[cs]); + aspeed_smc_flash_update_ctrl(&s->flashes[cs], value); } else if (addr >= R_SEG_ADDR0 && addr < R_SEG_ADDR0 + s->ctrl->max_slaves) { int cs = addr - R_SEG_ADDR0; diff --git a/hw/ssi/trace-events b/hw/ssi/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/trace-events +++ b/hw/ssi/trace-events @@ -XXX,XX +XXX,XX @@ aspeed_smc_flash_write(int cs, uint64_t addr, uint32_t size, uint64_t data, int aspeed_smc_read(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 aspeed_smc_dma_checksum(uint32_t addr, uint32_t data) "0x%08x: 0x%08x" aspeed_smc_write(uint64_t addr, uint32_t size, uint64_t data) "@0x%" PRIx64 " size %u: 0x%" PRIx64 +aspeed_smc_flash_select(int cs, const char *prefix) "CS%d %sselect" -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We fail to validate the upper bits of a virtual address on a translation disabled regime, as per AArch64.TranslateAddressS1Off. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200308012946.16303-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 35 ++++++++++++++++++++++++++++++++++- 1 file changed, 34 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ bool get_phys_addr(CPUARMState *env, target_ulong address, /* Definitely a real MMU, not an MPU */ if (regime_translation_disabled(env, mmu_idx)) { - /* MMU disabled. */ + /* + * MMU disabled. S1 addresses within aa64 translation regimes are + * still checked for bounds -- see AArch64.TranslateAddressS1Off. + */ + if (mmu_idx != ARMMMUIdx_Stage2) { + int r_el = regime_el(env, mmu_idx); + if (arm_el_is_aa64(env, r_el)) { + int pamax = arm_pamax(env_archcpu(env)); + uint64_t tcr = env->cp15.tcr_el[r_el].raw_tcr; + int addrtop, tbi; + + tbi = aa64_va_parameter_tbi(tcr, mmu_idx); + if (access_type == MMU_INST_FETCH) { + tbi &= ~aa64_va_parameter_tbid(tcr, mmu_idx); + } + tbi = (tbi >> extract64(address, 55, 1)) & 1; + addrtop = (tbi ? 55 : 63); + + if (extract64(address, pamax, addrtop - pamax + 1) != 0) { + fi->type = ARMFault_AddressSize; + fi->level = 0; + fi->stage2 = false; + return 1; + } + + /* + * When TBI is disabled, we've just validated that all of the + * bits above PAMax are zero, so logically we only need to + * clear the top byte for TBI. But it's clearer to follow + * the pseudocode set of addrdesc.paddress. + */ + address = extract64(address, 0, 52); + } + } *phys_ptr = address; *prot = PAGE_READ | PAGE_WRITE | PAGE_EXEC; *page_size = TARGET_PAGE_SIZE; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We must include the tag in the FAR_ELx register when raising an addressing exception. Which means that we should not clear out the tag during translation. We cannot at present comply with this for user mode, so we retain the clean_data_tbi function for the moment, though it no longer does what it says on the tin for system mode. This function is to be replaced with MTE, so don't worry about the slight misnaming. Buglink: https://bugs.launchpad.net/qemu/+bug/1867072 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200308012946.16303-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) static TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr) { TCGv_i64 clean = new_tmp_a64(s); + /* + * In order to get the correct value in the FAR_ELx register, + * we must present the memory subsystem with the "dirty" address + * including the TBI. In system mode we can make this work via + * the TLB, dropping the TBI during translation. But for user-only + * mode we don't have that option, and must remove the top byte now. + */ +#ifdef CONFIG_USER_ONLY gen_top_byte_ignore(s, clean, addr, s->tbid); +#else + tcg_gen_mov_i64(clean, addr); +#endif return clean; } -- 2.20.1 From: Igor Mammedov <imammedo@redhat.com> SOC object returned by object_new() is leaked in current code. Set SOC parent explicitly to board and then unref to SOC object to make sure that refererence returned by object_new() is taken care of. The SOC object will be kept alive by its parent (machine) and will be automatically freed when MachineState is destroyed. Signed-off-by: Igor Mammedov <imammedo@redhat.com> Reported-by: Andrew Jones <drjones@redhat.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20200303091254.22373-1-imammedo@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/cubieboard.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) } a10 = AW_A10(object_new(TYPE_AW_A10)); + object_property_add_child(OBJECT(machine), "soc", OBJECT(a10), + &error_abort); + object_unref(OBJECT(a10)); object_property_set_int(OBJECT(&a10->emac), 1, "phy-addr", &err); if (err != NULL) { -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Wire up eSDHC controllers in fsl-imx25. For imx25-pdk, connect drives provided on the command line to available eSDHC controllers. This patch enables booting the imx25-pdk emulation from SD card. Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20200310215146.19688-2-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: made commit subject consistent with other patch] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 9 +++++++++ hw/arm/fsl-imx25.c | 32 ++++++++++++++++++++++++++++++++ hw/arm/imx25_pdk.c | 16 ++++++++++++++++ 3 files changed, 57 insertions(+) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx_rngc.h" #include "hw/i2c/imx_i2c.h" #include "hw/gpio/imx_gpio.h" +#include "hw/sd/sdhci.h" #include "exec/memory.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ #define FSL_IMX25_NUM_EPITS 2 #define FSL_IMX25_NUM_I2CS 3 #define FSL_IMX25_NUM_GPIOS 4 +#define FSL_IMX25_NUM_ESDHCS 2 typedef struct FslIMX25State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { IMXRNGCState rngc; IMXI2CState i2c[FSL_IMX25_NUM_I2CS]; IMXGPIOState gpio[FSL_IMX25_NUM_GPIOS]; + SDHCIState esdhc[FSL_IMX25_NUM_ESDHCS]; MemoryRegion rom[2]; MemoryRegion iram; MemoryRegion iram_alias; @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO3_SIZE 0x4000 #define FSL_IMX25_RNGC_ADDR 0x53FB0000 #define FSL_IMX25_RNGC_SIZE 0x4000 +#define FSL_IMX25_ESDHC1_ADDR 0x53FB4000 +#define FSL_IMX25_ESDHC1_SIZE 0x4000 +#define FSL_IMX25_ESDHC2_ADDR 0x53FB8000 +#define FSL_IMX25_ESDHC2_SIZE 0x4000 #define FSL_IMX25_GPIO1_ADDR 0x53FCC000 #define FSL_IMX25_GPIO1_SIZE 0x4000 #define FSL_IMX25_GPIO2_ADDR 0x53FD0000 @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO2_IRQ 51 #define FSL_IMX25_GPIO3_IRQ 16 #define FSL_IMX25_GPIO4_IRQ 23 +#define FSL_IMX25_ESDHC1_IRQ 9 +#define FSL_IMX25_ESDHC2_IRQ 8 #endif /* FSL_IMX25_H */ diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "chardev/char.h" +#define IMX25_ESDHC_CAPABILITIES 0x07e20000 + static void fsl_imx25_init(Object *obj) { FslIMX25State *s = FSL_IMX25(obj); @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_init(Object *obj) sysbus_init_child_obj(obj, "gpio[*]", &s->gpio[i], sizeof(s->gpio[i]), TYPE_IMX_GPIO); } + + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + sysbus_init_child_obj(obj, "sdhc[*]", &s->esdhc[i], sizeof(s->esdhc[i]), + TYPE_IMX_USDHC); + } } static void fsl_imx25_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp) gpio_table[i].irq)); } + /* Initialize all SDHC */ + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } esdhc_table[FSL_IMX25_NUM_ESDHCS] = { + { FSL_IMX25_ESDHC1_ADDR, FSL_IMX25_ESDHC1_IRQ }, + { FSL_IMX25_ESDHC2_ADDR, FSL_IMX25_ESDHC2_IRQ }, + }; + + object_property_set_uint(OBJECT(&s->esdhc[i]), 2, "sd-spec-version", + &err); + object_property_set_uint(OBJECT(&s->esdhc[i]), IMX25_ESDHC_CAPABILITIES, + "capareg", &err); + object_property_set_bool(OBJECT(&s->esdhc[i]), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->esdhc[i]), 0, esdhc_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->esdhc[i]), 0, + qdev_get_gpio_in(DEVICE(&s->avic), + esdhc_table[i].irq)); + } + /* initialize 2 x 16 KB ROM */ memory_region_init_rom(&s->rom[0], NULL, "imx25.rom0", FSL_IMX25_ROM0_SIZE, &err); diff --git a/hw/arm/imx25_pdk.c b/hw/arm/imx25_pdk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx25_pdk.c +++ b/hw/arm/imx25_pdk.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "cpu.h" +#include "hw/qdev-properties.h" #include "hw/arm/fsl-imx25.h" #include "hw/boards.h" #include "qemu/error-report.h" @@ -XXX,XX +XXX,XX @@ static void imx25_pdk_init(MachineState *machine) imx25_pdk_binfo.board_id = 1771, imx25_pdk_binfo.nb_cpus = 1; + for (i = 0; i < FSL_IMX25_NUM_ESDHCS; i++) { + BusState *bus; + DeviceState *carddev; + DriveInfo *di; + BlockBackend *blk; + + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(&s->soc.esdhc[i]), "sd-bus"); + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, + "realized", &error_fatal); + } + /* * We test explicitly for qtest here as it is not done (yet?) in * arm_load_kernel(). Without this the "make check" command would -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> i.MX25 supports two USB controllers. Let's wire them up. With this patch, imx25-pdk can boot from both USB ports. Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20200310215146.19688-3-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx25.h | 9 +++++++++ hw/arm/fsl-imx25.c | 24 ++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/include/hw/arm/fsl-imx25.h b/include/hw/arm/fsl-imx25.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx25.h +++ b/include/hw/arm/fsl-imx25.h @@ -XXX,XX +XXX,XX @@ #include "hw/i2c/imx_i2c.h" #include "hw/gpio/imx_gpio.h" #include "hw/sd/sdhci.h" +#include "hw/usb/chipidea.h" #include "exec/memory.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ #define FSL_IMX25_NUM_I2CS 3 #define FSL_IMX25_NUM_GPIOS 4 #define FSL_IMX25_NUM_ESDHCS 2 +#define FSL_IMX25_NUM_USBS 2 typedef struct FslIMX25State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { IMXI2CState i2c[FSL_IMX25_NUM_I2CS]; IMXGPIOState gpio[FSL_IMX25_NUM_GPIOS]; SDHCIState esdhc[FSL_IMX25_NUM_ESDHCS]; + ChipideaState usb[FSL_IMX25_NUM_USBS]; MemoryRegion rom[2]; MemoryRegion iram; MemoryRegion iram_alias; @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO1_SIZE 0x4000 #define FSL_IMX25_GPIO2_ADDR 0x53FD0000 #define FSL_IMX25_GPIO2_SIZE 0x4000 +#define FSL_IMX25_USB1_ADDR 0x53FF4000 +#define FSL_IMX25_USB1_SIZE 0x0200 +#define FSL_IMX25_USB2_ADDR 0x53FF4400 +#define FSL_IMX25_USB2_SIZE 0x0200 #define FSL_IMX25_AVIC_ADDR 0x68000000 #define FSL_IMX25_AVIC_SIZE 0x4000 #define FSL_IMX25_IRAM_ADDR 0x78000000 @@ -XXX,XX +XXX,XX @@ typedef struct FslIMX25State { #define FSL_IMX25_GPIO4_IRQ 23 #define FSL_IMX25_ESDHC1_IRQ 9 #define FSL_IMX25_ESDHC2_IRQ 8 +#define FSL_IMX25_USB1_IRQ 37 +#define FSL_IMX25_USB2_IRQ 35 #endif /* FSL_IMX25_H */ diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_init(Object *obj) sysbus_init_child_obj(obj, "sdhc[*]", &s->esdhc[i], sizeof(s->esdhc[i]), TYPE_IMX_USDHC); } + + for (i = 0; i < FSL_IMX25_NUM_USBS; i++) { + sysbus_init_child_obj(obj, "usb[*]", &s->usb[i], sizeof(s->usb[i]), + TYPE_CHIPIDEA); + } + } static void fsl_imx25_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp) esdhc_table[i].irq)); } + /* USB */ + for (i = 0; i < FSL_IMX25_NUM_USBS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usb_table[FSL_IMX25_NUM_USBS] = { + { FSL_IMX25_USB1_ADDR, FSL_IMX25_USB1_IRQ }, + { FSL_IMX25_USB2_ADDR, FSL_IMX25_USB2_IRQ }, + }; + + object_property_set_bool(OBJECT(&s->usb[i]), true, "realized", + &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, + qdev_get_gpio_in(DEVICE(&s->avic), + usb_table[i].irq)); + } + /* initialize 2 x 16 KB ROM */ memory_region_init_rom(&s->rom[0], NULL, "imx25.rom0", FSL_IMX25_ROM0_SIZE, &err); -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 is a System on Chip containing four ARM Cortex A7 processor cores. Features and specifications include DDR2/DDR3 memory, SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and various I/O modules. This commit adds support for the Allwinner H3 System on Chip. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-2-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 106 +++++++++++ hw/arm/allwinner-h3.c | 327 ++++++++++++++++++++++++++++++++ MAINTAINERS | 7 + default-configs/arm-softmmu.mak | 1 + hw/arm/Kconfig | 8 + 6 files changed, 450 insertions(+) create mode 100644 include/hw/arm/allwinner-h3.h create mode 100644 hw/arm/allwinner-h3.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_DIGIC) += digic.o obj-$(CONFIG_OMAP) += omap1.o omap2.o obj-$(CONFIG_STRONGARM) += strongarm.o obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o obj-$(CONFIG_STM32F405_SOC) += stm32f405_soc.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System on Chip emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +/* + * The Allwinner H3 is a System on Chip containing four ARM Cortex A7 + * processor cores. Features and specifications include DDR2/DDR3 memory, + * SD/MMC storage cards, 10/100/1000Mbit Ethernet, USB 2.0, HDMI and + * various I/O modules. + * + * This implementation is based on the following datasheet: + * + * https://linux-sunxi.org/File:Allwinner_H3_Datasheet_V1.2.pdf + * + * The latest datasheet and more info can be found on the Linux Sunxi wiki: + * + * https://linux-sunxi.org/H3 + */ + +#ifndef HW_ARM_ALLWINNER_H3_H +#define HW_ARM_ALLWINNER_H3_H + +#include "qom/object.h" +#include "hw/arm/boot.h" +#include "hw/timer/allwinner-a10-pit.h" +#include "hw/intc/arm_gic.h" +#include "target/arm/cpu.h" + +/** + * Allwinner H3 device list + * + * This enumeration is can be used refer to a particular device in the + * Allwinner H3 SoC. For example, the physical memory base address for + * each device can be found in the AwH3State object in the memmap member + * using the device enum value as index. + * + * @see AwH3State + */ +enum { + AW_H3_SRAM_A1, + AW_H3_SRAM_A2, + AW_H3_SRAM_C, + AW_H3_PIT, + AW_H3_UART0, + AW_H3_UART1, + AW_H3_UART2, + AW_H3_UART3, + AW_H3_GIC_DIST, + AW_H3_GIC_CPU, + AW_H3_GIC_HYP, + AW_H3_GIC_VCPU, + AW_H3_SDRAM +}; + +/** Total number of CPU cores in the H3 SoC */ +#define AW_H3_NUM_CPUS (4) + +/** + * Allwinner H3 object model + * @{ + */ + +/** Object type for the Allwinner H3 SoC */ +#define TYPE_AW_H3 "allwinner-h3" + +/** Convert input object to Allwinner H3 state object */ +#define AW_H3(obj) OBJECT_CHECK(AwH3State, (obj), TYPE_AW_H3) + +/** @} */ + +/** + * Allwinner H3 object + * + * This struct contains the state of all the devices + * which are currently emulated by the H3 SoC code. + */ +typedef struct AwH3State { + /*< private >*/ + DeviceState parent_obj; + /*< public >*/ + + ARMCPU cpus[AW_H3_NUM_CPUS]; + const hwaddr *memmap; + AwA10PITState timer; + GICState gic; + MemoryRegion sram_a1; + MemoryRegion sram_a2; + MemoryRegion sram_c; +} AwH3State; + +#endif /* HW_ARM_ALLWINNER_H3_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System on Chip emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "qemu/error-report.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "hw/qdev-core.h" +#include "cpu.h" +#include "hw/sysbus.h" +#include "hw/char/serial.h" +#include "hw/misc/unimp.h" +#include "sysemu/sysemu.h" +#include "hw/arm/allwinner-h3.h" + +/* Memory map */ +const hwaddr allwinner_h3_memmap[] = { + [AW_H3_SRAM_A1] = 0x00000000, + [AW_H3_SRAM_A2] = 0x00044000, + [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_PIT] = 0x01c20c00, + [AW_H3_UART0] = 0x01c28000, + [AW_H3_UART1] = 0x01c28400, + [AW_H3_UART2] = 0x01c28800, + [AW_H3_UART3] = 0x01c28c00, + [AW_H3_GIC_DIST] = 0x01c81000, + [AW_H3_GIC_CPU] = 0x01c82000, + [AW_H3_GIC_HYP] = 0x01c84000, + [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_SDRAM] = 0x40000000 +}; + +/* List of unimplemented devices */ +struct AwH3Unimplemented { + const char *device_name; + hwaddr base; + hwaddr size; +} unimplemented[] = { + { "d-engine", 0x01000000, 4 * MiB }, + { "d-inter", 0x01400000, 128 * KiB }, + { "syscon", 0x01c00000, 4 * KiB }, + { "dma", 0x01c02000, 4 * KiB }, + { "nfdc", 0x01c03000, 4 * KiB }, + { "ts", 0x01c06000, 4 * KiB }, + { "keymem", 0x01c0b000, 4 * KiB }, + { "lcd0", 0x01c0c000, 4 * KiB }, + { "lcd1", 0x01c0d000, 4 * KiB }, + { "ve", 0x01c0e000, 4 * KiB }, + { "mmc0", 0x01c0f000, 4 * KiB }, + { "mmc1", 0x01c10000, 4 * KiB }, + { "mmc2", 0x01c11000, 4 * KiB }, + { "sid", 0x01c14000, 1 * KiB }, + { "crypto", 0x01c15000, 4 * KiB }, + { "msgbox", 0x01c17000, 4 * KiB }, + { "spinlock", 0x01c18000, 4 * KiB }, + { "usb0-otg", 0x01c19000, 4 * KiB }, + { "usb0-phy", 0x01c1a000, 4 * KiB }, + { "usb1-phy", 0x01c1b000, 4 * KiB }, + { "usb2-phy", 0x01c1c000, 4 * KiB }, + { "usb3-phy", 0x01c1d000, 4 * KiB }, + { "smc", 0x01c1e000, 4 * KiB }, + { "ccu", 0x01c20000, 1 * KiB }, + { "pio", 0x01c20800, 1 * KiB }, + { "owa", 0x01c21000, 1 * KiB }, + { "pwm", 0x01c21400, 1 * KiB }, + { "keyadc", 0x01c21800, 1 * KiB }, + { "pcm0", 0x01c22000, 1 * KiB }, + { "pcm1", 0x01c22400, 1 * KiB }, + { "pcm2", 0x01c22800, 1 * KiB }, + { "audio", 0x01c22c00, 2 * KiB }, + { "smta", 0x01c23400, 1 * KiB }, + { "ths", 0x01c25000, 1 * KiB }, + { "uart0", 0x01c28000, 1 * KiB }, + { "uart1", 0x01c28400, 1 * KiB }, + { "uart2", 0x01c28800, 1 * KiB }, + { "uart3", 0x01c28c00, 1 * KiB }, + { "twi0", 0x01c2ac00, 1 * KiB }, + { "twi1", 0x01c2b000, 1 * KiB }, + { "twi2", 0x01c2b400, 1 * KiB }, + { "scr", 0x01c2c400, 1 * KiB }, + { "emac", 0x01c30000, 64 * KiB }, + { "gpu", 0x01c40000, 64 * KiB }, + { "hstmr", 0x01c60000, 4 * KiB }, + { "dramcom", 0x01c62000, 4 * KiB }, + { "dramctl0", 0x01c63000, 4 * KiB }, + { "dramphy0", 0x01c65000, 4 * KiB }, + { "spi0", 0x01c68000, 4 * KiB }, + { "spi1", 0x01c69000, 4 * KiB }, + { "csi", 0x01cb0000, 320 * KiB }, + { "tve", 0x01e00000, 64 * KiB }, + { "hdmi", 0x01ee0000, 128 * KiB }, + { "rtc", 0x01f00000, 1 * KiB }, + { "r_timer", 0x01f00800, 1 * KiB }, + { "r_intc", 0x01f00c00, 1 * KiB }, + { "r_wdog", 0x01f01000, 1 * KiB }, + { "r_prcm", 0x01f01400, 1 * KiB }, + { "r_twd", 0x01f01800, 1 * KiB }, + { "r_cpucfg", 0x01f01c00, 1 * KiB }, + { "r_cir-rx", 0x01f02000, 1 * KiB }, + { "r_twi", 0x01f02400, 1 * KiB }, + { "r_uart", 0x01f02800, 1 * KiB }, + { "r_pio", 0x01f02c00, 1 * KiB }, + { "r_pwm", 0x01f03800, 1 * KiB }, + { "core-dbg", 0x3f500000, 128 * KiB }, + { "tsgen-ro", 0x3f506000, 4 * KiB }, + { "tsgen-ctl", 0x3f507000, 4 * KiB }, + { "ddr-mem", 0x40000000, 2 * GiB }, + { "n-brom", 0xffff0000, 32 * KiB }, + { "s-brom", 0xffff0000, 64 * KiB } +}; + +/* Per Processor Interrupts */ +enum { + AW_H3_GIC_PPI_MAINT = 9, + AW_H3_GIC_PPI_HYPTIMER = 10, + AW_H3_GIC_PPI_VIRTTIMER = 11, + AW_H3_GIC_PPI_SECTIMER = 13, + AW_H3_GIC_PPI_PHYSTIMER = 14 +}; + +/* Shared Processor Interrupts */ +enum { + AW_H3_GIC_SPI_UART0 = 0, + AW_H3_GIC_SPI_UART1 = 1, + AW_H3_GIC_SPI_UART2 = 2, + AW_H3_GIC_SPI_UART3 = 3, + AW_H3_GIC_SPI_TIMER0 = 18, + AW_H3_GIC_SPI_TIMER1 = 19, +}; + +/* Allwinner H3 general constants */ +enum { + AW_H3_GIC_NUM_SPI = 128 +}; + +static void allwinner_h3_init(Object *obj) +{ + AwH3State *s = AW_H3(obj); + + s->memmap = allwinner_h3_memmap; + + for (int i = 0; i < AW_H3_NUM_CPUS; i++) { + object_initialize_child(obj, "cpu[*]", &s->cpus[i], sizeof(s->cpus[i]), + ARM_CPU_TYPE_NAME("cortex-a7"), + &error_abort, NULL); + } + + sysbus_init_child_obj(obj, "gic", &s->gic, sizeof(s->gic), + TYPE_ARM_GIC); + + sysbus_init_child_obj(obj, "timer", &s->timer, sizeof(s->timer), + TYPE_AW_A10_PIT); + object_property_add_alias(obj, "clk0-freq", OBJECT(&s->timer), + "clk0-freq", &error_abort); + object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), + "clk1-freq", &error_abort); +} + +static void allwinner_h3_realize(DeviceState *dev, Error **errp) +{ + AwH3State *s = AW_H3(dev); + unsigned i; + + /* CPUs */ + for (i = 0; i < AW_H3_NUM_CPUS; i++) { + + /* Provide Power State Coordination Interface */ + qdev_prop_set_int32(DEVICE(&s->cpus[i]), "psci-conduit", + QEMU_PSCI_CONDUIT_HVC); + + /* Disable secondary CPUs */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "start-powered-off", + i > 0); + + /* All exception levels required */ + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el3", true); + qdev_prop_set_bit(DEVICE(&s->cpus[i]), "has_el2", true); + + /* Mark realized */ + qdev_init_nofail(DEVICE(&s->cpus[i])); + } + + /* Generic Interrupt Controller */ + qdev_prop_set_uint32(DEVICE(&s->gic), "num-irq", AW_H3_GIC_NUM_SPI + + GIC_INTERNAL); + qdev_prop_set_uint32(DEVICE(&s->gic), "revision", 2); + qdev_prop_set_uint32(DEVICE(&s->gic), "num-cpu", AW_H3_NUM_CPUS); + qdev_prop_set_bit(DEVICE(&s->gic), "has-security-extensions", false); + qdev_prop_set_bit(DEVICE(&s->gic), "has-virtualization-extensions", true); + qdev_init_nofail(DEVICE(&s->gic)); + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 0, s->memmap[AW_H3_GIC_DIST]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 1, s->memmap[AW_H3_GIC_CPU]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 2, s->memmap[AW_H3_GIC_HYP]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gic), 3, s->memmap[AW_H3_GIC_VCPU]); + + /* + * Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, + * and the GIC's IRQ/FIQ/VIRQ/VFIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < AW_H3_NUM_CPUS; i++) { + DeviceState *cpudev = DEVICE(&s->cpus[i]); + int ppibase = AW_H3_GIC_NUM_SPI + i * GIC_INTERNAL + GIC_NR_SGIS; + int irq; + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs used for this board. + */ + const int timer_irq[] = { + [GTIMER_PHYS] = AW_H3_GIC_PPI_PHYSTIMER, + [GTIMER_VIRT] = AW_H3_GIC_PPI_VIRTTIMER, + [GTIMER_HYP] = AW_H3_GIC_PPI_HYPTIMER, + [GTIMER_SEC] = AW_H3_GIC_PPI_SECTIMER, + }; + + /* Connect CPU timer outputs to GIC PPI inputs */ + for (irq = 0; irq < ARRAY_SIZE(timer_irq); irq++) { + qdev_connect_gpio_out(cpudev, irq, + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + timer_irq[irq])); + } + + /* Connect GIC outputs to CPU interrupt inputs */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + AW_H3_NUM_CPUS, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (2 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (3 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + /* GIC maintenance signal */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gic), i + (4 * AW_H3_NUM_CPUS), + qdev_get_gpio_in(DEVICE(&s->gic), + ppibase + AW_H3_GIC_PPI_MAINT)); + } + + /* Timer */ + qdev_init_nofail(DEVICE(&s->timer)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer), 0, s->memmap[AW_H3_PIT]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TIMER0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer), 1, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TIMER1)); + + /* SRAM */ + memory_region_init_ram(&s->sram_a1, OBJECT(dev), "sram A1", + 64 * KiB, &error_abort); + memory_region_init_ram(&s->sram_a2, OBJECT(dev), "sram A2", + 32 * KiB, &error_abort); + memory_region_init_ram(&s->sram_c, OBJECT(dev), "sram C", + 44 * KiB, &error_abort); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_A1], + &s->sram_a1); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_A2], + &s->sram_a2); + memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_C], + &s->sram_c); + + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), + 115200, serial_hd(0), DEVICE_NATIVE_ENDIAN); + /* UART1 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART1], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART1), + 115200, serial_hd(1), DEVICE_NATIVE_ENDIAN); + /* UART2 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART2], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART2), + 115200, serial_hd(2), DEVICE_NATIVE_ENDIAN); + /* UART3 */ + serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART3], 2, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART3), + 115200, serial_hd(3), DEVICE_NATIVE_ENDIAN); + + /* Unimplemented devices */ + for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { + create_unimplemented_device(unimplemented[i].device_name, + unimplemented[i].base, + unimplemented[i].size); + } +} + +static void allwinner_h3_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = allwinner_h3_realize; + /* Reason: uses serial_hd() in realize function */ + dc->user_creatable = false; +} + +static const TypeInfo allwinner_h3_type_info = { + .name = TYPE_AW_H3, + .parent = TYPE_DEVICE, + .instance_size = sizeof(AwH3State), + .instance_init = allwinner_h3_init, + .class_init = allwinner_h3_class_init, +}; + +static void allwinner_h3_register_types(void) +{ + type_register_static(&allwinner_h3_type_info); +} + +type_init(allwinner_h3_register_types) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c +Allwinner-h3 +M: Niek Linnenbank <nieklinnenbank@gmail.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/*/allwinner-h3* +F: include/hw/*/allwinner-h3* + ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_FSL_IMX25=y CONFIG_FSL_IMX7=y CONFIG_FSL_IMX6UL=y CONFIG_SEMIHOSTING=y +CONFIG_ALLWINNER_H3=y diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select SERIAL select UNIMP +config ALLWINNER_H3 + bool + select ALLWINNER_A10_PIT + select SERIAL + select ARM_TIMER + select ARM_GIC + select UNIMP + config RASPI bool select FRAMEBUFFER -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Xunlong Orange Pi PC is an Allwinner H3 System on Chip based embedded computer with mainline support in both U-Boot and Linux. The board comes with a Quad Core Cortex A7 @ 1.3GHz, 1GiB RAM, 100Mbit ethernet, USB, SD/MMC, USB, HDMI and various other I/O. This commit add support for the Xunlong Orange Pi PC machine. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: KONRAD Frederic <frederic.konrad@adacore.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Acked-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20200311221854.30370-3-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Makefile.objs | 2 +- hw/arm/orangepi.c | 92 ++++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 1 + 3 files changed, 94 insertions(+), 1 deletion(-) create mode 100644 hw/arm/orangepi.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_DIGIC) += digic.o obj-$(CONFIG_OMAP) += omap1.o omap2.o obj-$(CONFIG_STRONGARM) += strongarm.o obj-$(CONFIG_ALLWINNER_A10) += allwinner-a10.o cubieboard.o -obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3.o orangepi.o obj-$(CONFIG_RASPI) += bcm2835_peripherals.o bcm2836.o raspi.o obj-$(CONFIG_STM32F205_SOC) += stm32f205_soc.o obj-$(CONFIG_STM32F405_SOC) += stm32f405_soc.o diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ +/* + * Orange Pi emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "exec/address-spaces.h" +#include "qapi/error.h" +#include "cpu.h" +#include "hw/sysbus.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/arm/allwinner-h3.h" +#include "sysemu/sysemu.h" + +static struct arm_boot_info orangepi_binfo = { + .nb_cpus = AW_H3_NUM_CPUS, +}; + +static void orangepi_init(MachineState *machine) +{ + AwH3State *h3; + + /* BIOS is not supported by this board */ + if (bios_name) { + error_report("BIOS not supported for this machine"); + exit(1); + } + + /* This board has fixed size RAM */ + if (machine->ram_size != 1 * GiB) { + error_report("This machine can only be used with 1GiB of RAM"); + exit(1); + } + + /* Only allow Cortex-A7 for this board */ + if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a7")) != 0) { + error_report("This board can only be used with cortex-a7 CPU"); + exit(1); + } + + h3 = AW_H3(object_new(TYPE_AW_H3)); + object_property_add_child(OBJECT(machine), "soc", OBJECT(h3), + &error_abort); + object_unref(OBJECT(h3)); + + /* Setup timer properties */ + object_property_set_int(OBJECT(h3), 32768, "clk0-freq", + &error_abort); + object_property_set_int(OBJECT(h3), 24 * 1000 * 1000, "clk1-freq", + &error_abort); + + /* Mark H3 object realized */ + object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); + + /* SDRAM */ + memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], + machine->ram); + + orangepi_binfo.loader_start = h3->memmap[AW_H3_SDRAM]; + orangepi_binfo.ram_size = machine->ram_size; + arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); +} + +static void orangepi_machine_init(MachineClass *mc) +{ + mc->desc = "Orange Pi PC"; + mc->init = orangepi_init; + mc->min_cpus = AW_H3_NUM_CPUS; + mc->max_cpus = AW_H3_NUM_CPUS; + mc->default_cpus = AW_H3_NUM_CPUS; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a7"); + mc->default_ram_size = 1 * GiB; + mc->default_ram_id = "orangepi.ram"; +} + +DEFINE_MACHINE("orangepi-pc", orangepi_machine_init) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Maintained F: hw/*/allwinner-h3* F: include/hw/*/allwinner-h3* +F: hw/arm/orangepi.c ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Clock Control Unit is responsible for clock signal generation, configuration and distribution in the Allwinner H3 System on Chip. This commit adds support for the Clock Control Unit which emulates a simple read/write register interface. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-4-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-h3-ccu.h | 66 ++++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-h3-ccu.c | 242 +++++++++++++++++++++++++++++ 5 files changed, 320 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-h3-ccu.h create mode 100644 hw/misc/allwinner-h3-ccu.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" +#include "hw/misc/allwinner-h3-ccu.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_CCU, AW_H3_PIT, AW_H3_UART0, AW_H3_UART1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { ARMCPU cpus[AW_H3_NUM_CPUS]; const hwaddr *memmap; AwA10PITState timer; + AwH3ClockCtlState ccu; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-h3-ccu.h b/include/hw/misc/allwinner-h3-ccu.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-ccu.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 Clock Control Unit emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_CCU_H +#define HW_MISC_ALLWINNER_H3_CCU_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCU device */ +#define AW_H3_CCU_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_H3_CCU_REGS_NUM (AW_H3_CCU_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_H3_CCU "allwinner-h3-ccu" +#define AW_H3_CCU(obj) \ + OBJECT_CHECK(AwH3ClockCtlState, (obj), TYPE_AW_H3_CCU) + +/** @} */ + +/** + * Allwinner H3 CCU object instance state. + */ +typedef struct AwH3ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_H3_CCU_REGS_NUM]; + +} AwH3ClockCtlState; + +#endif /* HW_MISC_ALLWINNER_H3_CCU_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_CCU] = 0x01c20000, [AW_H3_PIT] = 0x01c20c00, [AW_H3_UART0] = 0x01c28000, [AW_H3_UART1] = 0x01c28400, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "usb2-phy", 0x01c1c000, 4 * KiB }, { "usb3-phy", 0x01c1d000, 4 * KiB }, { "smc", 0x01c1e000, 4 * KiB }, - { "ccu", 0x01c20000, 1 * KiB }, { "pio", 0x01c20800, 1 * KiB }, { "owa", 0x01c21000, 1 * KiB }, { "pwm", 0x01c21400, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "clk0-freq", &error_abort); object_property_add_alias(obj, "clk1-freq", OBJECT(&s->timer), "clk1-freq", &error_abort); + + sysbus_init_child_obj(obj, "ccu", &s->ccu, sizeof(s->ccu), + TYPE_AW_H3_CCU); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), s->memmap[AW_H3_SRAM_C], &s->sram_c); + /* Clock Control Unit */ + qdev_init_nofail(DEVICE(&s->ccu)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), diff --git a/hw/misc/allwinner-h3-ccu.c b/hw/misc/allwinner-h3-ccu.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-ccu.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 Clock Control Unit emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-h3-ccu.h" + +/* CCU register offsets */ +enum { + REG_PLL_CPUX = 0x0000, /* PLL CPUX Control */ + REG_PLL_AUDIO = 0x0008, /* PLL Audio Control */ + REG_PLL_VIDEO = 0x0010, /* PLL Video Control */ + REG_PLL_VE = 0x0018, /* PLL VE Control */ + REG_PLL_DDR = 0x0020, /* PLL DDR Control */ + REG_PLL_PERIPH0 = 0x0028, /* PLL Peripherals 0 Control */ + REG_PLL_GPU = 0x0038, /* PLL GPU Control */ + REG_PLL_PERIPH1 = 0x0044, /* PLL Peripherals 1 Control */ + REG_PLL_DE = 0x0048, /* PLL Display Engine Control */ + REG_CPUX_AXI = 0x0050, /* CPUX/AXI Configuration */ + REG_APB1 = 0x0054, /* ARM Peripheral Bus 1 Config */ + REG_APB2 = 0x0058, /* ARM Peripheral Bus 2 Config */ + REG_DRAM_CFG = 0x00F4, /* DRAM Configuration */ + REG_MBUS = 0x00FC, /* MBUS Reset */ + REG_PLL_TIME0 = 0x0200, /* PLL Stable Time 0 */ + REG_PLL_TIME1 = 0x0204, /* PLL Stable Time 1 */ + REG_PLL_CPUX_BIAS = 0x0220, /* PLL CPUX Bias */ + REG_PLL_AUDIO_BIAS = 0x0224, /* PLL Audio Bias */ + REG_PLL_VIDEO_BIAS = 0x0228, /* PLL Video Bias */ + REG_PLL_VE_BIAS = 0x022C, /* PLL VE Bias */ + REG_PLL_DDR_BIAS = 0x0230, /* PLL DDR Bias */ + REG_PLL_PERIPH0_BIAS = 0x0234, /* PLL Peripherals 0 Bias */ + REG_PLL_GPU_BIAS = 0x023C, /* PLL GPU Bias */ + REG_PLL_PERIPH1_BIAS = 0x0244, /* PLL Peripherals 1 Bias */ + REG_PLL_DE_BIAS = 0x0248, /* PLL Display Engine Bias */ + REG_PLL_CPUX_TUNING = 0x0250, /* PLL CPUX Tuning */ + REG_PLL_DDR_TUNING = 0x0260, /* PLL DDR Tuning */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCU register flags */ +enum { + REG_DRAM_CFG_UPDATE = (1 << 16), +}; + +enum { + REG_PLL_ENABLE = (1 << 31), + REG_PLL_LOCK = (1 << 28), +}; + + +/* CCU register reset values */ +enum { + REG_PLL_CPUX_RST = 0x00001000, + REG_PLL_AUDIO_RST = 0x00035514, + REG_PLL_VIDEO_RST = 0x03006207, + REG_PLL_VE_RST = 0x03006207, + REG_PLL_DDR_RST = 0x00001000, + REG_PLL_PERIPH0_RST = 0x00041811, + REG_PLL_GPU_RST = 0x03006207, + REG_PLL_PERIPH1_RST = 0x00041811, + REG_PLL_DE_RST = 0x03006207, + REG_CPUX_AXI_RST = 0x00010000, + REG_APB1_RST = 0x00001010, + REG_APB2_RST = 0x01000000, + REG_DRAM_CFG_RST = 0x00000000, + REG_MBUS_RST = 0x80000000, + REG_PLL_TIME0_RST = 0x000000FF, + REG_PLL_TIME1_RST = 0x000000FF, + REG_PLL_CPUX_BIAS_RST = 0x08100200, + REG_PLL_AUDIO_BIAS_RST = 0x10100000, + REG_PLL_VIDEO_BIAS_RST = 0x10100000, + REG_PLL_VE_BIAS_RST = 0x10100000, + REG_PLL_DDR_BIAS_RST = 0x81104000, + REG_PLL_PERIPH0_BIAS_RST = 0x10100010, + REG_PLL_GPU_BIAS_RST = 0x10100000, + REG_PLL_PERIPH1_BIAS_RST = 0x10100010, + REG_PLL_DE_BIAS_RST = 0x10100000, + REG_PLL_CPUX_TUNING_RST = 0x0A101000, + REG_PLL_DDR_TUNING_RST = 0x14880000, +}; + +static uint64_t allwinner_h3_ccu_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3ClockCtlState *s = AW_H3_CCU(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case 0x308 ... AW_H3_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_h3_ccu_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3ClockCtlState *s = AW_H3_CCU(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_DRAM_CFG: /* DRAM Configuration */ + val &= ~REG_DRAM_CFG_UPDATE; + break; + case REG_PLL_CPUX: /* PLL CPUX Control */ + case REG_PLL_AUDIO: /* PLL Audio Control */ + case REG_PLL_VIDEO: /* PLL Video Control */ + case REG_PLL_VE: /* PLL VE Control */ + case REG_PLL_DDR: /* PLL DDR Control */ + case REG_PLL_PERIPH0: /* PLL Peripherals 0 Control */ + case REG_PLL_GPU: /* PLL GPU Control */ + case REG_PLL_PERIPH1: /* PLL Peripherals 1 Control */ + case REG_PLL_DE: /* PLL Display Engine Control */ + if (val & REG_PLL_ENABLE) { + val |= REG_PLL_LOCK; + } + break; + case 0x308 ... AW_H3_CCU_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_h3_ccu_ops = { + .read = allwinner_h3_ccu_read, + .write = allwinner_h3_ccu_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_ccu_reset(DeviceState *dev) +{ + AwH3ClockCtlState *s = AW_H3_CCU(dev); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL_CPUX)] = REG_PLL_CPUX_RST; + s->regs[REG_INDEX(REG_PLL_AUDIO)] = REG_PLL_AUDIO_RST; + s->regs[REG_INDEX(REG_PLL_VIDEO)] = REG_PLL_VIDEO_RST; + s->regs[REG_INDEX(REG_PLL_VE)] = REG_PLL_VE_RST; + s->regs[REG_INDEX(REG_PLL_DDR)] = REG_PLL_DDR_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH0)] = REG_PLL_PERIPH0_RST; + s->regs[REG_INDEX(REG_PLL_GPU)] = REG_PLL_GPU_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH1)] = REG_PLL_PERIPH1_RST; + s->regs[REG_INDEX(REG_PLL_DE)] = REG_PLL_DE_RST; + s->regs[REG_INDEX(REG_CPUX_AXI)] = REG_CPUX_AXI_RST; + s->regs[REG_INDEX(REG_APB1)] = REG_APB1_RST; + s->regs[REG_INDEX(REG_APB2)] = REG_APB2_RST; + s->regs[REG_INDEX(REG_DRAM_CFG)] = REG_DRAM_CFG_RST; + s->regs[REG_INDEX(REG_MBUS)] = REG_MBUS_RST; + s->regs[REG_INDEX(REG_PLL_TIME0)] = REG_PLL_TIME0_RST; + s->regs[REG_INDEX(REG_PLL_TIME1)] = REG_PLL_TIME1_RST; + s->regs[REG_INDEX(REG_PLL_CPUX_BIAS)] = REG_PLL_CPUX_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_AUDIO_BIAS)] = REG_PLL_AUDIO_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_VIDEO_BIAS)] = REG_PLL_VIDEO_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_VE_BIAS)] = REG_PLL_VE_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_DDR_BIAS)] = REG_PLL_DDR_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH0_BIAS)] = REG_PLL_PERIPH0_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_GPU_BIAS)] = REG_PLL_GPU_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_PERIPH1_BIAS)] = REG_PLL_PERIPH1_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_DE_BIAS)] = REG_PLL_DE_BIAS_RST; + s->regs[REG_INDEX(REG_PLL_CPUX_TUNING)] = REG_PLL_CPUX_TUNING_RST; + s->regs[REG_INDEX(REG_PLL_DDR_TUNING)] = REG_PLL_DDR_TUNING_RST; +} + +static void allwinner_h3_ccu_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3ClockCtlState *s = AW_H3_CCU(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_h3_ccu_ops, s, + TYPE_AW_H3_CCU, AW_H3_CCU_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_h3_ccu_vmstate = { + .name = "allwinner-h3-ccu", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwH3ClockCtlState, AW_H3_CCU_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_ccu_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_ccu_reset; + dc->vmsd = &allwinner_h3_ccu_vmstate; +} + +static const TypeInfo allwinner_h3_ccu_info = { + .name = TYPE_AW_H3_CCU, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_ccu_init, + .instance_size = sizeof(AwH3ClockCtlState), + .class_init = allwinner_h3_ccu_class_init, +}; + +static void allwinner_h3_ccu_register(void) +{ + type_register_static(&allwinner_h3_ccu_info); +} + +type_init(allwinner_h3_ccu_register) -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 System on Chip contains multiple USB 2.0 bus connections which provide software access using the Enhanced Host Controller Interface (EHCI) and Open Host Controller Interface (OHCI) interfaces. This commit adds support for both interfaces in the Allwinner H3 System on Chip. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Gerd Hoffmann <kraxel@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-5-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-ehci.h | 1 + include/hw/arm/allwinner-h3.h | 8 +++++++ hw/arm/allwinner-h3.c | 44 +++++++++++++++++++++++++++++++++++ hw/usb/hcd-ehci-sysbus.c | 17 ++++++++++++++ hw/arm/Kconfig | 2 ++ 5 files changed, 72 insertions(+) diff --git a/hw/usb/hcd-ehci.h b/hw/usb/hcd-ehci.h index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ehci.h +++ b/hw/usb/hcd-ehci.h @@ -XXX,XX +XXX,XX @@ typedef struct EHCIPCIState { #define TYPE_SYS_BUS_EHCI "sysbus-ehci-usb" #define TYPE_PLATFORM_EHCI "platform-ehci-usb" #define TYPE_EXYNOS4210_EHCI "exynos4210-ehci-usb" +#define TYPE_AW_H3_EHCI "aw-h3-ehci-usb" #define TYPE_TEGRA2_EHCI "tegra2-ehci-usb" #define TYPE_PPC4xx_EHCI "ppc4xx-ehci-usb" #define TYPE_FUSBH200_EHCI "fusbh200-ehci-usb" diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_EHCI0, + AW_H3_OHCI0, + AW_H3_EHCI1, + AW_H3_OHCI1, + AW_H3_EHCI2, + AW_H3_OHCI2, + AW_H3_EHCI3, + AW_H3_OHCI3, AW_H3_CCU, AW_H3_PIT, AW_H3_UART0, diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/char/serial.h" #include "hw/misc/unimp.h" +#include "hw/usb/hcd-ehci.h" #include "sysemu/sysemu.h" #include "hw/arm/allwinner-h3.h" @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_EHCI0] = 0x01c1a000, + [AW_H3_OHCI0] = 0x01c1a400, + [AW_H3_EHCI1] = 0x01c1b000, + [AW_H3_OHCI1] = 0x01c1b400, + [AW_H3_EHCI2] = 0x01c1c000, + [AW_H3_OHCI2] = 0x01c1c400, + [AW_H3_EHCI3] = 0x01c1d000, + [AW_H3_OHCI3] = 0x01c1d400, [AW_H3_CCU] = 0x01c20000, [AW_H3_PIT] = 0x01c20c00, [AW_H3_UART0] = 0x01c28000, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART3 = 3, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, + AW_H3_GIC_SPI_EHCI0 = 72, + AW_H3_GIC_SPI_OHCI0 = 73, + AW_H3_GIC_SPI_EHCI1 = 74, + AW_H3_GIC_SPI_OHCI1 = 75, + AW_H3_GIC_SPI_EHCI2 = 76, + AW_H3_GIC_SPI_OHCI2 = 77, + AW_H3_GIC_SPI_EHCI3 = 78, + AW_H3_GIC_SPI_OHCI3 = 79, }; /* Allwinner H3 general constants */ @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->ccu)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* Universal Serial Bus */ + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI0)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI1], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI1)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI2], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI2)); + sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI3], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_EHCI3)); + + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI0], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI0)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI1], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI1)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI2], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI2)); + sysbus_create_simple("sysbus-ohci", s->memmap[AW_H3_OHCI3], + qdev_get_gpio_in(DEVICE(&s->gic), + AW_H3_GIC_SPI_OHCI3)); + /* UART0. For future clocktree API: All UARTS are connected to APB2_CLK. */ serial_mm_init(get_system_memory(), s->memmap[AW_H3_UART0], 2, qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART0), diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ehci-sysbus.c +++ b/hw/usb/hcd-ehci-sysbus.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo ehci_exynos4210_type_info = { .class_init = ehci_exynos4210_class_init, }; +static void ehci_aw_h3_class_init(ObjectClass *oc, void *data) +{ + SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); + DeviceClass *dc = DEVICE_CLASS(oc); + + sec->capsbase = 0x0; + sec->opregbase = 0x10; + set_bit(DEVICE_CATEGORY_USB, dc->categories); +} + +static const TypeInfo ehci_aw_h3_type_info = { + .name = TYPE_AW_H3_EHCI, + .parent = TYPE_SYS_BUS_EHCI, + .class_init = ehci_aw_h3_class_init, +}; + static void ehci_tegra2_class_init(ObjectClass *oc, void *data) { SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void ehci_sysbus_register_types(void) type_register_static(&ehci_type_info); type_register_static(&ehci_platform_type_info); type_register_static(&ehci_exynos4210_type_info); + type_register_static(&ehci_aw_h3_type_info); type_register_static(&ehci_tegra2_type_info); type_register_static(&ehci_ppc4xx_type_info); type_register_static(&ehci_fusbh200_type_info); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 select ARM_TIMER select ARM_GIC select UNIMP + select USB_OHCI + select USB_EHCI_SYSBUS config RASPI bool -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner H3 System on Chip has an System Control module that provides system wide generic controls and device information. This commit adds support for the Allwinner H3 System Control module. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-6-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-h3-sysctrl.h | 67 ++++++++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-h3-sysctrl.c | 140 +++++++++++++++++++++++++ 5 files changed, 219 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-h3-sysctrl.h create mode 100644 hw/misc/allwinner-h3-sysctrl.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" +#include "hw/misc/allwinner-h3-sysctrl.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A1, AW_H3_SRAM_A2, AW_H3_SRAM_C, + AW_H3_SYSCTRL, AW_H3_EHCI0, AW_H3_OHCI0, AW_H3_EHCI1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { const hwaddr *memmap; AwA10PITState timer; AwH3ClockCtlState ccu; + AwH3SysCtrlState sysctrl; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-h3-sysctrl.h b/include/hw/misc/allwinner-h3-sysctrl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-sysctrl.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System Control emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_SYSCTRL_H +#define HW_MISC_ALLWINNER_H3_SYSCTRL_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Highest register address used by System Control device */ +#define AW_H3_SYSCTRL_REGS_MAXADDR (0x30) + +/** Total number of known registers */ +#define AW_H3_SYSCTRL_REGS_NUM ((AW_H3_SYSCTRL_REGS_MAXADDR / \ + sizeof(uint32_t)) + 1) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_H3_SYSCTRL "allwinner-h3-sysctrl" +#define AW_H3_SYSCTRL(obj) \ + OBJECT_CHECK(AwH3SysCtrlState, (obj), TYPE_AW_H3_SYSCTRL) + +/** @} */ + +/** + * Allwinner H3 System Control object instance state + */ +typedef struct AwH3SysCtrlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_H3_SYSCTRL_REGS_NUM]; + +} AwH3SysCtrlState; + +#endif /* HW_MISC_ALLWINNER_H3_SYSCTRL_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A1] = 0x00000000, [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, + [AW_H3_SYSCTRL] = 0x01c00000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, [AW_H3_EHCI1] = 0x01c1b000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { } unimplemented[] = { { "d-engine", 0x01000000, 4 * MiB }, { "d-inter", 0x01400000, 128 * KiB }, - { "syscon", 0x01c00000, 4 * KiB }, { "dma", 0x01c02000, 4 * KiB }, { "nfdc", 0x01c03000, 4 * KiB }, { "ts", 0x01c06000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "ccu", &s->ccu, sizeof(s->ccu), TYPE_AW_H3_CCU); + + sysbus_init_child_obj(obj, "sysctrl", &s->sysctrl, sizeof(s->sysctrl), + TYPE_AW_H3_SYSCTRL); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->ccu)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccu), 0, s->memmap[AW_H3_CCU]); + /* System Control */ + qdev_init_nofail(DEVICE(&s->sysctrl)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sysctrl), 0, s->memmap[AW_H3_SYSCTRL]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/misc/allwinner-h3-sysctrl.c b/hw/misc/allwinner-h3-sysctrl.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-sysctrl.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 System Control emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-h3-sysctrl.h" + +/* System Control register offsets */ +enum { + REG_VER = 0x24, /* Version */ + REG_EMAC_PHY_CLK = 0x30, /* EMAC PHY Clock */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* System Control register reset values */ +enum { + REG_VER_RST = 0x0, + REG_EMAC_PHY_CLK_RST = 0x58000, +}; + +static uint64_t allwinner_h3_sysctrl_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3SysCtrlState *s = AW_H3_SYSCTRL(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_SYSCTRL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_h3_sysctrl_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3SysCtrlState *s = AW_H3_SYSCTRL(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_SYSCTRL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_VER: /* Version */ + break; + default: + s->regs[idx] = (uint32_t) val; + break; + } +} + +static const MemoryRegionOps allwinner_h3_sysctrl_ops = { + .read = allwinner_h3_sysctrl_read, + .write = allwinner_h3_sysctrl_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_sysctrl_reset(DeviceState *dev) +{ + AwH3SysCtrlState *s = AW_H3_SYSCTRL(dev); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_VER)] = REG_VER_RST; + s->regs[REG_INDEX(REG_EMAC_PHY_CLK)] = REG_EMAC_PHY_CLK_RST; +} + +static void allwinner_h3_sysctrl_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3SysCtrlState *s = AW_H3_SYSCTRL(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_h3_sysctrl_ops, s, + TYPE_AW_H3_SYSCTRL, 4 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_h3_sysctrl_vmstate = { + .name = "allwinner-h3-sysctrl", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwH3SysCtrlState, AW_H3_SYSCTRL_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_sysctrl_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_sysctrl_reset; + dc->vmsd = &allwinner_h3_sysctrl_vmstate; +} + +static const TypeInfo allwinner_h3_sysctrl_info = { + .name = TYPE_AW_H3_SYSCTRL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_sysctrl_init, + .instance_size = sizeof(AwH3SysCtrlState), + .class_init = allwinner_h3_sysctrl_class_init, +}; + +static void allwinner_h3_sysctrl_register(void) +{ + type_register_static(&allwinner_h3_sysctrl_info); +} + +type_init(allwinner_h3_sysctrl_register) -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Various Allwinner System on Chip designs contain multiple processors that can be configured and reset using the generic CPU Configuration module interface. This commit adds support for the Allwinner CPU configuration interface which emulates the following features: * CPU reset * CPU status Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-7-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-cpucfg.h | 52 ++++++ hw/arm/allwinner-h3.c | 9 +- hw/misc/allwinner-cpucfg.c | 282 +++++++++++++++++++++++++++++ hw/misc/trace-events | 5 + 6 files changed, 351 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-cpucfg.h create mode 100644 hw/misc/allwinner-cpucfg.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_MACIO) += macio/ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o +obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" +#include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_CPU, AW_H3_GIC_HYP, AW_H3_GIC_VCPU, + AW_H3_CPUCFG, AW_H3_SDRAM }; @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { const hwaddr *memmap; AwA10PITState timer; AwH3ClockCtlState ccu; + AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; GICState gic; MemoryRegion sram_a1; diff --git a/include/hw/misc/allwinner-cpucfg.h b/include/hw/misc/allwinner-cpucfg.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-cpucfg.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner CPU Configuration Module emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_CPUCFG_H +#define HW_MISC_ALLWINNER_CPUCFG_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_CPUCFG "allwinner-cpucfg" +#define AW_CPUCFG(obj) \ + OBJECT_CHECK(AwCpuCfgState, (obj), TYPE_AW_CPUCFG) + +/** @} */ + +/** + * Allwinner CPU Configuration Module instance state + */ +typedef struct AwCpuCfgState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + MemoryRegion iomem; + uint32_t gen_ctrl; + uint32_t super_standby; + uint32_t entry_addr; + +} AwCpuCfgState; + +#endif /* HW_MISC_ALLWINNER_CPUCFG_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_CPUCFG] = 0x01f01c00, [AW_H3_SDRAM] = 0x40000000 }; @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "r_wdog", 0x01f01000, 1 * KiB }, { "r_prcm", 0x01f01400, 1 * KiB }, { "r_twd", 0x01f01800, 1 * KiB }, - { "r_cpucfg", 0x01f01c00, 1 * KiB }, { "r_cir-rx", 0x01f02000, 1 * KiB }, { "r_twi", 0x01f02400, 1 * KiB }, { "r_uart", 0x01f02800, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "sysctrl", &s->sysctrl, sizeof(s->sysctrl), TYPE_AW_H3_SYSCTRL); + + sysbus_init_child_obj(obj, "cpucfg", &s->cpucfg, sizeof(s->cpucfg), + TYPE_AW_CPUCFG); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->sysctrl)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->sysctrl), 0, s->memmap[AW_H3_SYSCTRL]); + /* CPU Configuration */ + qdev_init_nofail(DEVICE(&s->cpucfg)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->cpucfg), 0, s->memmap[AW_H3_CPUCFG]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/misc/allwinner-cpucfg.c b/hw/misc/allwinner-cpucfg.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-cpucfg.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner CPU Configuration Module emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/error-report.h" +#include "qemu/timer.h" +#include "hw/core/cpu.h" +#include "target/arm/arm-powerctl.h" +#include "target/arm/cpu.h" +#include "hw/misc/allwinner-cpucfg.h" +#include "trace.h" + +/* CPUCFG register offsets */ +enum { + REG_CPUS_RST_CTRL = 0x0000, /* CPUs Reset Control */ + REG_CPU0_RST_CTRL = 0x0040, /* CPU#0 Reset Control */ + REG_CPU0_CTRL = 0x0044, /* CPU#0 Control */ + REG_CPU0_STATUS = 0x0048, /* CPU#0 Status */ + REG_CPU1_RST_CTRL = 0x0080, /* CPU#1 Reset Control */ + REG_CPU1_CTRL = 0x0084, /* CPU#1 Control */ + REG_CPU1_STATUS = 0x0088, /* CPU#1 Status */ + REG_CPU2_RST_CTRL = 0x00C0, /* CPU#2 Reset Control */ + REG_CPU2_CTRL = 0x00C4, /* CPU#2 Control */ + REG_CPU2_STATUS = 0x00C8, /* CPU#2 Status */ + REG_CPU3_RST_CTRL = 0x0100, /* CPU#3 Reset Control */ + REG_CPU3_CTRL = 0x0104, /* CPU#3 Control */ + REG_CPU3_STATUS = 0x0108, /* CPU#3 Status */ + REG_CPU_SYS_RST = 0x0140, /* CPU System Reset */ + REG_CLK_GATING = 0x0144, /* CPU Clock Gating */ + REG_GEN_CTRL = 0x0184, /* General Control */ + REG_SUPER_STANDBY = 0x01A0, /* Super Standby Flag */ + REG_ENTRY_ADDR = 0x01A4, /* Reset Entry Address */ + REG_DBG_EXTERN = 0x01E4, /* Debug External */ + REG_CNT64_CTRL = 0x0280, /* 64-bit Counter Control */ + REG_CNT64_LOW = 0x0284, /* 64-bit Counter Low */ + REG_CNT64_HIGH = 0x0288, /* 64-bit Counter High */ +}; + +/* CPUCFG register flags */ +enum { + CPUX_RESET_RELEASED = ((1 << 1) | (1 << 0)), + CPUX_STATUS_SMP = (1 << 0), + CPU_SYS_RESET_RELEASED = (1 << 0), + CLK_GATING_ENABLE = ((1 << 8) | 0xF), +}; + +/* CPUCFG register reset values */ +enum { + REG_CLK_GATING_RST = 0x0000010F, + REG_GEN_CTRL_RST = 0x00000020, + REG_SUPER_STANDBY_RST = 0x0, + REG_CNT64_CTRL_RST = 0x0, +}; + +/* CPUCFG constants */ +enum { + CPU_EXCEPTION_LEVEL_ON_RESET = 3, /* EL3 */ +}; + +static void allwinner_cpucfg_cpu_reset(AwCpuCfgState *s, uint8_t cpu_id) +{ + int ret; + + trace_allwinner_cpucfg_cpu_reset(cpu_id, s->entry_addr); + + ARMCPU *target_cpu = ARM_CPU(arm_get_cpu_by_id(cpu_id)); + if (!target_cpu) { + /* + * Called with a bogus value for cpu_id. Guest error will + * already have been logged, we can simply return here. + */ + return; + } + bool target_aa64 = arm_feature(&target_cpu->env, ARM_FEATURE_AARCH64); + + ret = arm_set_cpu_on(cpu_id, s->entry_addr, 0, + CPU_EXCEPTION_LEVEL_ON_RESET, target_aa64); + if (ret != QEMU_ARM_POWERCTL_RET_SUCCESS) { + error_report("%s: failed to bring up CPU %d: err %d", + __func__, cpu_id, ret); + return; + } +} + +static uint64_t allwinner_cpucfg_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwCpuCfgState *s = AW_CPUCFG(opaque); + uint64_t val = 0; + + switch (offset) { + case REG_CPUS_RST_CTRL: /* CPUs Reset Control */ + case REG_CPU_SYS_RST: /* CPU System Reset */ + val = CPU_SYS_RESET_RELEASED; + break; + case REG_CPU0_RST_CTRL: /* CPU#0 Reset Control */ + case REG_CPU1_RST_CTRL: /* CPU#1 Reset Control */ + case REG_CPU2_RST_CTRL: /* CPU#2 Reset Control */ + case REG_CPU3_RST_CTRL: /* CPU#3 Reset Control */ + val = CPUX_RESET_RELEASED; + break; + case REG_CPU0_CTRL: /* CPU#0 Control */ + case REG_CPU1_CTRL: /* CPU#1 Control */ + case REG_CPU2_CTRL: /* CPU#2 Control */ + case REG_CPU3_CTRL: /* CPU#3 Control */ + val = 0; + break; + case REG_CPU0_STATUS: /* CPU#0 Status */ + case REG_CPU1_STATUS: /* CPU#1 Status */ + case REG_CPU2_STATUS: /* CPU#2 Status */ + case REG_CPU3_STATUS: /* CPU#3 Status */ + val = CPUX_STATUS_SMP; + break; + case REG_CLK_GATING: /* CPU Clock Gating */ + val = CLK_GATING_ENABLE; + break; + case REG_GEN_CTRL: /* General Control */ + val = s->gen_ctrl; + break; + case REG_SUPER_STANDBY: /* Super Standby Flag */ + val = s->super_standby; + break; + case REG_ENTRY_ADDR: /* Reset Entry Address */ + val = s->entry_addr; + break; + case REG_DBG_EXTERN: /* Debug External */ + case REG_CNT64_CTRL: /* 64-bit Counter Control */ + case REG_CNT64_LOW: /* 64-bit Counter Low */ + case REG_CNT64_HIGH: /* 64-bit Counter High */ + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register at 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + trace_allwinner_cpucfg_read(offset, val, size); + + return val; +} + +static void allwinner_cpucfg_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwCpuCfgState *s = AW_CPUCFG(opaque); + + trace_allwinner_cpucfg_write(offset, val, size); + + switch (offset) { + case REG_CPUS_RST_CTRL: /* CPUs Reset Control */ + case REG_CPU_SYS_RST: /* CPU System Reset */ + break; + case REG_CPU0_RST_CTRL: /* CPU#0 Reset Control */ + case REG_CPU1_RST_CTRL: /* CPU#1 Reset Control */ + case REG_CPU2_RST_CTRL: /* CPU#2 Reset Control */ + case REG_CPU3_RST_CTRL: /* CPU#3 Reset Control */ + if (val) { + allwinner_cpucfg_cpu_reset(s, (offset - REG_CPU0_RST_CTRL) >> 6); + } + break; + case REG_CPU0_CTRL: /* CPU#0 Control */ + case REG_CPU1_CTRL: /* CPU#1 Control */ + case REG_CPU2_CTRL: /* CPU#2 Control */ + case REG_CPU3_CTRL: /* CPU#3 Control */ + case REG_CPU0_STATUS: /* CPU#0 Status */ + case REG_CPU1_STATUS: /* CPU#1 Status */ + case REG_CPU2_STATUS: /* CPU#2 Status */ + case REG_CPU3_STATUS: /* CPU#3 Status */ + case REG_CLK_GATING: /* CPU Clock Gating */ + break; + case REG_GEN_CTRL: /* General Control */ + s->gen_ctrl = val; + break; + case REG_SUPER_STANDBY: /* Super Standby Flag */ + s->super_standby = val; + break; + case REG_ENTRY_ADDR: /* Reset Entry Address */ + s->entry_addr = val; + break; + case REG_DBG_EXTERN: /* Debug External */ + case REG_CNT64_CTRL: /* 64-bit Counter Control */ + case REG_CNT64_LOW: /* 64-bit Counter Low */ + case REG_CNT64_HIGH: /* 64-bit Counter High */ + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register at 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } +} + +static const MemoryRegionOps allwinner_cpucfg_ops = { + .read = allwinner_cpucfg_read, + .write = allwinner_cpucfg_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_cpucfg_reset(DeviceState *dev) +{ + AwCpuCfgState *s = AW_CPUCFG(dev); + + /* Set default values for registers */ + s->gen_ctrl = REG_GEN_CTRL_RST; + s->super_standby = REG_SUPER_STANDBY_RST; + s->entry_addr = 0; +} + +static void allwinner_cpucfg_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwCpuCfgState *s = AW_CPUCFG(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_cpucfg_ops, s, + TYPE_AW_CPUCFG, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_cpucfg_vmstate = { + .name = "allwinner-cpucfg", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(gen_ctrl, AwCpuCfgState), + VMSTATE_UINT32(super_standby, AwCpuCfgState), + VMSTATE_UINT32(entry_addr, AwCpuCfgState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_cpucfg_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_cpucfg_reset; + dc->vmsd = &allwinner_cpucfg_vmstate; +} + +static const TypeInfo allwinner_cpucfg_info = { + .name = TYPE_AW_CPUCFG, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_cpucfg_init, + .instance_size = sizeof(AwCpuCfgState), + .class_init = allwinner_cpucfg_class_init, +}; + +static void allwinner_cpucfg_register(void) +{ + type_register_static(&allwinner_cpucfg_info); +} + +type_init(allwinner_cpucfg_register) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-cpucfg.c +allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_addr 0x%" PRIu32 +allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Security Identifier device found in various Allwinner System on Chip designs gives applications a per-board unique identifier. This commit adds support for the Allwinner Security Identifier using a 128-bit UUID value as input. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-8-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/misc/allwinner-sid.h | 60 ++++++++++++ hw/arm/allwinner-h3.c | 11 ++- hw/arm/orangepi.c | 8 ++ hw/misc/allwinner-sid.c | 168 ++++++++++++++++++++++++++++++++ hw/misc/trace-events | 4 + 7 files changed, 254 insertions(+), 1 deletion(-) create mode 100644 include/hw/misc/allwinner-sid.h create mode 100644 hw/misc/allwinner-sid.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sid.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o common-obj-$(CONFIG_NSERIES) += cbus.o common-obj-$(CONFIG_ECCMEMCTL) += eccmemctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-h3-ccu.h" #include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" +#include "hw/misc/allwinner-sid.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A2, AW_H3_SRAM_C, AW_H3_SYSCTRL, + AW_H3_SID, AW_H3_EHCI0, AW_H3_OHCI0, AW_H3_EHCI1, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwH3ClockCtlState ccu; AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; + AwSidState sid; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/misc/allwinner-sid.h b/include/hw/misc/allwinner-sid.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-sid.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Security ID emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_SID_H +#define HW_MISC_ALLWINNER_SID_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "qemu/uuid.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_SID "allwinner-sid" +#define AW_SID(obj) \ + OBJECT_CHECK(AwSidState, (obj), TYPE_AW_SID) + +/** @} */ + +/** + * Allwinner Security ID object instance state + */ +typedef struct AwSidState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Control register defines how and what to read */ + uint32_t control; + + /** RdKey register contains the data retrieved by the device */ + uint32_t rdkey; + + /** Stores the emulated device identifier */ + QemuUUID identifier; + +} AwSidState; + +#endif /* HW_MISC_ALLWINNER_SID_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, [AW_H3_SYSCTRL] = 0x01c00000, + [AW_H3_SID] = 0x01c14000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, [AW_H3_EHCI1] = 0x01c1b000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "mmc0", 0x01c0f000, 4 * KiB }, { "mmc1", 0x01c10000, 4 * KiB }, { "mmc2", 0x01c11000, 4 * KiB }, - { "sid", 0x01c14000, 1 * KiB }, { "crypto", 0x01c15000, 4 * KiB }, { "msgbox", 0x01c17000, 4 * KiB }, { "spinlock", 0x01c18000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "cpucfg", &s->cpucfg, sizeof(s->cpucfg), TYPE_AW_CPUCFG); + + sysbus_init_child_obj(obj, "sid", &s->sid, sizeof(s->sid), + TYPE_AW_SID); + object_property_add_alias(obj, "identifier", OBJECT(&s->sid), + "identifier", &error_abort); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->cpucfg)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->cpucfg), 0, s->memmap[AW_H3_CPUCFG]); + /* Security Identifier */ + qdev_init_nofail(DEVICE(&s->sid)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->sid), 0, s->memmap[AW_H3_SID]); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) object_property_set_int(OBJECT(h3), 24 * 1000 * 1000, "clk1-freq", &error_abort); + /* Setup SID properties. Currently using a default fixed SID identifier. */ + if (qemu_uuid_is_null(&h3->sid.identifier)) { + qdev_prop_set_string(DEVICE(h3), "identifier", + "02c00081-1111-2222-3333-000044556677"); + } else if (ldl_be_p(&h3->sid.identifier.data[0]) != 0x02c00081) { + warn_report("Security Identifier value does not include H3 prefix"); + } + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/misc/allwinner-sid.c b/hw/misc/allwinner-sid.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-sid.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Security ID emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/guest-random.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/misc/allwinner-sid.h" +#include "trace.h" + +/* SID register offsets */ +enum { + REG_PRCTL = 0x40, /* Control */ + REG_RDKEY = 0x60, /* Read Key */ +}; + +/* SID register flags */ +enum { + REG_PRCTL_WRITE = 0x0002, /* Unknown write flag */ + REG_PRCTL_OP_LOCK = 0xAC00, /* Lock operation */ +}; + +static uint64_t allwinner_sid_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwSidState *s = AW_SID(opaque); + uint64_t val = 0; + + switch (offset) { + case REG_PRCTL: /* Control */ + val = s->control; + break; + case REG_RDKEY: /* Read Key */ + val = s->rdkey; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_sid_read(offset, val, size); + + return val; +} + +static void allwinner_sid_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwSidState *s = AW_SID(opaque); + + trace_allwinner_sid_write(offset, val, size); + + switch (offset) { + case REG_PRCTL: /* Control */ + s->control = val; + + if ((s->control & REG_PRCTL_OP_LOCK) && + (s->control & REG_PRCTL_WRITE)) { + uint32_t id = s->control >> 16; + + if (id <= sizeof(QemuUUID) - sizeof(s->rdkey)) { + s->rdkey = ldl_be_p(&s->identifier.data[id]); + } + } + s->control &= ~REG_PRCTL_WRITE; + break; + case REG_RDKEY: /* Read Key */ + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } +} + +static const MemoryRegionOps allwinner_sid_ops = { + .read = allwinner_sid_read, + .write = allwinner_sid_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_sid_reset(DeviceState *dev) +{ + AwSidState *s = AW_SID(dev); + + /* Set default values for registers */ + s->control = 0; + s->rdkey = 0; +} + +static void allwinner_sid_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwSidState *s = AW_SID(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_sid_ops, s, + TYPE_AW_SID, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static Property allwinner_sid_properties[] = { + DEFINE_PROP_UUID_NODEFAULT("identifier", AwSidState, identifier), + DEFINE_PROP_END_OF_LIST() +}; + +static const VMStateDescription allwinner_sid_vmstate = { + .name = "allwinner-sid", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(control, AwSidState), + VMSTATE_UINT32(rdkey, AwSidState), + VMSTATE_UINT8_ARRAY_V(identifier.data, AwSidState, sizeof(QemuUUID), 1), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sid_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_sid_reset; + dc->vmsd = &allwinner_sid_vmstate; + device_class_set_props(dc, allwinner_sid_properties); +} + +static const TypeInfo allwinner_sid_info = { + .name = TYPE_AW_SID, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_sid_init, + .instance_size = sizeof(AwSidState), + .class_init = allwinner_sid_class_init, +}; + +static void allwinner_sid_register(void) +{ + type_register_static(&allwinner_sid_info); +} + +type_init(allwinner_sid_register) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_ad allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-sid.c +allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner System on Chip families sun4i and above contain an integrated storage controller for Secure Digital (SD) and Multi Media Card (MMC) interfaces. This commit adds support for the Allwinner SD/MMC storage controller with the following emulated features: * DMA transfers * Direct FIFO I/O * Short/Long format command responses * Auto-Stop command (CMD12) * Insert & remove card detection The following boards are extended with the SD host controller: * Cubieboard (hw/arm/cubieboard.c) * Orange Pi PC (hw/arm/orangepi.c) Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20200311221854.30370-9-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/Makefile.objs | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/sd/allwinner-sdhost.h | 135 +++++ hw/arm/allwinner-a10.c | 11 + hw/arm/allwinner-h3.c | 15 +- hw/arm/cubieboard.c | 15 + hw/arm/orangepi.c | 16 + hw/sd/allwinner-sdhost.c | 854 +++++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/sd/trace-events | 7 + 11 files changed, 1059 insertions(+), 1 deletion(-) create mode 100644 include/hw/sd/allwinner-sdhost.h create mode 100644 hw/sd/allwinner-sdhost.c diff --git a/hw/sd/Makefile.objs b/hw/sd/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/Makefile.objs +++ b/hw/sd/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SD) += sd.o core.o sdmmc-internal.o common-obj-$(CONFIG_SDHCI) += sdhci.o common-obj-$(CONFIG_SDHCI_PCI) += sdhci-pci.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sdhost.o common-obj-$(CONFIG_MILKYMIST) += milkymist-memcard.o common-obj-$(CONFIG_OMAP) += omap_mmc.o common-obj-$(CONFIG_PXA2XX) += pxa2xx_mmci.o diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/allwinner-a10-pit.h" #include "hw/intc/allwinner-a10-pic.h" #include "hw/net/allwinner_emac.h" +#include "hw/sd/allwinner-sdhost.h" #include "hw/ide/ahci.h" #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" @@ -XXX,XX +XXX,XX @@ typedef struct AwA10State { AwA10PICState intc; AwEmacState emac; AllwinnerAHCIState sata; + AwSdHostState mmc0; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; OHCISysBusState ohci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-cpucfg.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" +#include "hw/sd/allwinner-sdhost.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_SRAM_A2, AW_H3_SRAM_C, AW_H3_SYSCTRL, + AW_H3_MMC0, AW_H3_SID, AW_H3_EHCI0, AW_H3_OHCI0, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwCpuCfgState cpucfg; AwH3SysCtrlState sysctrl; AwSidState sid; + AwSdHostState mmc0; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/sd/allwinner-sdhost.h b/include/hw/sd/allwinner-sdhost.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/sd/allwinner-sdhost.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner (sun4i and above) SD Host Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_SD_ALLWINNER_SDHOST_H +#define HW_SD_ALLWINNER_SDHOST_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/sd/sd.h" + +/** + * Object model types + * @{ + */ + +/** Generic Allwinner SD Host Controller (abstract) */ +#define TYPE_AW_SDHOST "allwinner-sdhost" + +/** Allwinner sun4i family (A10, A12) */ +#define TYPE_AW_SDHOST_SUN4I TYPE_AW_SDHOST "-sun4i" + +/** Allwinner sun5i family and newer (A13, H2+, H3, etc) */ +#define TYPE_AW_SDHOST_SUN5I TYPE_AW_SDHOST "-sun5i" + +/** @} */ + +/** + * Object model macros + * @{ + */ + +#define AW_SDHOST(obj) \ + OBJECT_CHECK(AwSdHostState, (obj), TYPE_AW_SDHOST) +#define AW_SDHOST_CLASS(klass) \ + OBJECT_CLASS_CHECK(AwSdHostClass, (klass), TYPE_AW_SDHOST) +#define AW_SDHOST_GET_CLASS(obj) \ + OBJECT_GET_CLASS(AwSdHostClass, (obj), TYPE_AW_SDHOST) + +/** @} */ + +/** + * Allwinner SD Host Controller object instance state. + */ +typedef struct AwSdHostState { + /*< private >*/ + SysBusDevice busdev; + /*< public >*/ + + /** Secure Digital (SD) bus, which connects to SD card (if present) */ + SDBus sdbus; + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Interrupt output signal to notify CPU */ + qemu_irq irq; + + /** Number of bytes left in current DMA transfer */ + uint32_t transfer_cnt; + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t global_ctl; /**< Global Control */ + uint32_t clock_ctl; /**< Clock Control */ + uint32_t timeout; /**< Timeout */ + uint32_t bus_width; /**< Bus Width */ + uint32_t block_size; /**< Block Size */ + uint32_t byte_count; /**< Byte Count */ + + uint32_t command; /**< Command */ + uint32_t command_arg; /**< Command Argument */ + uint32_t response[4]; /**< Command Response */ + + uint32_t irq_mask; /**< Interrupt Mask */ + uint32_t irq_status; /**< Raw Interrupt Status */ + uint32_t status; /**< Status */ + + uint32_t fifo_wlevel; /**< FIFO Water Level */ + uint32_t fifo_func_sel; /**< FIFO Function Select */ + uint32_t debug_enable; /**< Debug Enable */ + uint32_t auto12_arg; /**< Auto Command 12 Argument */ + uint32_t newtiming_set; /**< SD New Timing Set */ + uint32_t newtiming_debug; /**< SD New Timing Debug */ + uint32_t hardware_rst; /**< Hardware Reset */ + uint32_t dmac; /**< Internal DMA Controller Control */ + uint32_t desc_base; /**< Descriptor List Base Address */ + uint32_t dmac_status; /**< Internal DMA Controller Status */ + uint32_t dmac_irq; /**< Internal DMA Controller IRQ Enable */ + uint32_t card_threshold; /**< Card Threshold Control */ + uint32_t startbit_detect; /**< eMMC DDR Start Bit Detection Control */ + uint32_t response_crc; /**< Response CRC */ + uint32_t data_crc[8]; /**< Data CRC */ + uint32_t status_crc; /**< Status CRC */ + + /** @} */ + +} AwSdHostState; + +/** + * Allwinner SD Host Controller class-level struct. + * + * This struct is filled by each sunxi device specific code + * such that the generic code can use this struct to support + * all devices. + */ +typedef struct AwSdHostClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + /** Maximum buffer size in bytes per DMA descriptor */ + size_t max_desc_size; + +} AwSdHostClass; + +#endif /* HW_SD_ALLWINNER_SDHOST_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_PIC_REG_BASE 0x01c20400 #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) sizeof(s->ohci[i]), TYPE_SYSBUS_OHCI); } } + + sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), + TYPE_AW_SDHOST_SUN4I); } static void aw_a10_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(dev, 64 + i)); } } + + /* SD/MMC */ + qdev_init_nofail(DEVICE(&s->mmc0)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mmc0), 0, AW_A10_MMC0_BASE); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, qdev_get_gpio_in(dev, 32)); + object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), + "sd-bus", &error_abort); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_SRAM_A2] = 0x00044000, [AW_H3_SRAM_C] = 0x00010000, [AW_H3_SYSCTRL] = 0x01c00000, + [AW_H3_MMC0] = 0x01c0f000, [AW_H3_SID] = 0x01c14000, [AW_H3_EHCI0] = 0x01c1a000, [AW_H3_OHCI0] = 0x01c1a400, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "lcd0", 0x01c0c000, 4 * KiB }, { "lcd1", 0x01c0d000, 4 * KiB }, { "ve", 0x01c0e000, 4 * KiB }, - { "mmc0", 0x01c0f000, 4 * KiB }, { "mmc1", 0x01c10000, 4 * KiB }, { "mmc2", 0x01c11000, 4 * KiB }, { "crypto", 0x01c15000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART3 = 3, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, + AW_H3_GIC_SPI_MMC0 = 60, AW_H3_GIC_SPI_EHCI0 = 72, AW_H3_GIC_SPI_OHCI0 = 73, AW_H3_GIC_SPI_EHCI1 = 74, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) TYPE_AW_SID); object_property_add_alias(obj, "identifier", OBJECT(&s->sid), "identifier", &error_abort); + + sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), + TYPE_AW_SDHOST_SUN5I); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_init_nofail(DEVICE(&s->sid)); sysbus_mmio_map(SYS_BUS_DEVICE(&s->sid), 0, s->memmap[AW_H3_SID]); + /* SD/MMC */ + qdev_init_nofail(DEVICE(&s->mmc0)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->mmc0), 0, s->memmap[AW_H3_MMC0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_MMC0)); + + object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), + "sd-bus", &error_abort); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "hw/sysbus.h" #include "hw/boards.h" +#include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" static struct arm_boot_info cubieboard_binfo = { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) { AwA10State *a10; Error *err = NULL; + DriveInfo *di; + BlockBackend *blk; + BusState *bus; + DeviceState *carddev; /* BIOS is not supported by this board */ if (bios_name) { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) exit(1); } + /* Retrieve SD bus */ + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(a10), "sd-bus"); + + /* Plug in SD card */ + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal); + memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE, machine->ram); diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info orangepi_binfo = { static void orangepi_init(MachineState *machine) { AwH3State *h3; + DriveInfo *di; + BlockBackend *blk; + BusState *bus; + DeviceState *carddev; /* BIOS is not supported by this board */ if (bios_name) { @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); + /* Retrieve SD bus */ + di = drive_get_next(IF_SD); + blk = di ? blk_by_legacy_dinfo(di) : NULL; + bus = qdev_get_child_bus(DEVICE(h3), "sd-bus"); + + /* Plug in SD card */ + carddev = qdev_create(bus, TYPE_SD_CARD); + qdev_prop_set_drive(carddev, "drive", blk, &error_fatal); + object_property_set_bool(OBJECT(carddev), true, "realized", &error_fatal); + /* SDRAM */ memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], machine->ram); @@ -XXX,XX +XXX,XX @@ static void orangepi_machine_init(MachineClass *mc) { mc->desc = "Orange Pi PC"; mc->init = orangepi_init; + mc->block_default_type = IF_SD; + mc->units_per_default_bus = 1; mc->min_cpus = AW_H3_NUM_CPUS; mc->max_cpus = AW_H3_NUM_CPUS; mc->default_cpus = AW_H3_NUM_CPUS; diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner (sun4i and above) SD Host Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "sysemu/blockdev.h" +#include "hw/irq.h" +#include "hw/sd/allwinner-sdhost.h" +#include "migration/vmstate.h" +#include "trace.h" + +#define TYPE_AW_SDHOST_BUS "allwinner-sdhost-bus" +#define AW_SDHOST_BUS(obj) \ + OBJECT_CHECK(SDBus, (obj), TYPE_AW_SDHOST_BUS) + +/* SD Host register offsets */ +enum { + REG_SD_GCTL = 0x00, /* Global Control */ + REG_SD_CKCR = 0x04, /* Clock Control */ + REG_SD_TMOR = 0x08, /* Timeout */ + REG_SD_BWDR = 0x0C, /* Bus Width */ + REG_SD_BKSR = 0x10, /* Block Size */ + REG_SD_BYCR = 0x14, /* Byte Count */ + REG_SD_CMDR = 0x18, /* Command */ + REG_SD_CAGR = 0x1C, /* Command Argument */ + REG_SD_RESP0 = 0x20, /* Response Zero */ + REG_SD_RESP1 = 0x24, /* Response One */ + REG_SD_RESP2 = 0x28, /* Response Two */ + REG_SD_RESP3 = 0x2C, /* Response Three */ + REG_SD_IMKR = 0x30, /* Interrupt Mask */ + REG_SD_MISR = 0x34, /* Masked Interrupt Status */ + REG_SD_RISR = 0x38, /* Raw Interrupt Status */ + REG_SD_STAR = 0x3C, /* Status */ + REG_SD_FWLR = 0x40, /* FIFO Water Level */ + REG_SD_FUNS = 0x44, /* FIFO Function Select */ + REG_SD_DBGC = 0x50, /* Debug Enable */ + REG_SD_A12A = 0x58, /* Auto command 12 argument */ + REG_SD_NTSR = 0x5C, /* SD NewTiming Set */ + REG_SD_SDBG = 0x60, /* SD newTiming Set Debug */ + REG_SD_HWRST = 0x78, /* Hardware Reset Register */ + REG_SD_DMAC = 0x80, /* Internal DMA Controller Control */ + REG_SD_DLBA = 0x84, /* Descriptor List Base Address */ + REG_SD_IDST = 0x88, /* Internal DMA Controller Status */ + REG_SD_IDIE = 0x8C, /* Internal DMA Controller IRQ Enable */ + REG_SD_THLDC = 0x100, /* Card Threshold Control */ + REG_SD_DSBD = 0x10C, /* eMMC DDR Start Bit Detection Control */ + REG_SD_RES_CRC = 0x110, /* Response CRC from card/eMMC */ + REG_SD_DATA7_CRC = 0x114, /* CRC Data 7 from card/eMMC */ + REG_SD_DATA6_CRC = 0x118, /* CRC Data 6 from card/eMMC */ + REG_SD_DATA5_CRC = 0x11C, /* CRC Data 5 from card/eMMC */ + REG_SD_DATA4_CRC = 0x120, /* CRC Data 4 from card/eMMC */ + REG_SD_DATA3_CRC = 0x124, /* CRC Data 3 from card/eMMC */ + REG_SD_DATA2_CRC = 0x128, /* CRC Data 2 from card/eMMC */ + REG_SD_DATA1_CRC = 0x12C, /* CRC Data 1 from card/eMMC */ + REG_SD_DATA0_CRC = 0x130, /* CRC Data 0 from card/eMMC */ + REG_SD_CRC_STA = 0x134, /* CRC status from card/eMMC during write */ + REG_SD_FIFO = 0x200, /* Read/Write FIFO */ +}; + +/* SD Host register flags */ +enum { + SD_GCTL_FIFO_AC_MOD = (1 << 31), + SD_GCTL_DDR_MOD_SEL = (1 << 10), + SD_GCTL_CD_DBC_ENB = (1 << 8), + SD_GCTL_DMA_ENB = (1 << 5), + SD_GCTL_INT_ENB = (1 << 4), + SD_GCTL_DMA_RST = (1 << 2), + SD_GCTL_FIFO_RST = (1 << 1), + SD_GCTL_SOFT_RST = (1 << 0), +}; + +enum { + SD_CMDR_LOAD = (1 << 31), + SD_CMDR_CLKCHANGE = (1 << 21), + SD_CMDR_WRITE = (1 << 10), + SD_CMDR_AUTOSTOP = (1 << 12), + SD_CMDR_DATA = (1 << 9), + SD_CMDR_RESPONSE_LONG = (1 << 7), + SD_CMDR_RESPONSE = (1 << 6), + SD_CMDR_CMDID_MASK = (0x3f), +}; + +enum { + SD_RISR_CARD_REMOVE = (1 << 31), + SD_RISR_CARD_INSERT = (1 << 30), + SD_RISR_SDIO_INTR = (1 << 16), + SD_RISR_AUTOCMD_DONE = (1 << 14), + SD_RISR_DATA_COMPLETE = (1 << 3), + SD_RISR_CMD_COMPLETE = (1 << 2), + SD_RISR_NO_RESPONSE = (1 << 1), +}; + +enum { + SD_STAR_CARD_PRESENT = (1 << 8), +}; + +enum { + SD_IDST_INT_SUMMARY = (1 << 8), + SD_IDST_RECEIVE_IRQ = (1 << 1), + SD_IDST_TRANSMIT_IRQ = (1 << 0), + SD_IDST_IRQ_MASK = (1 << 1) | (1 << 0) | (1 << 8), + SD_IDST_WR_MASK = (0x3ff), +}; + +/* SD Host register reset values */ +enum { + REG_SD_GCTL_RST = 0x00000300, + REG_SD_CKCR_RST = 0x0, + REG_SD_TMOR_RST = 0xFFFFFF40, + REG_SD_BWDR_RST = 0x0, + REG_SD_BKSR_RST = 0x00000200, + REG_SD_BYCR_RST = 0x00000200, + REG_SD_CMDR_RST = 0x0, + REG_SD_CAGR_RST = 0x0, + REG_SD_RESP_RST = 0x0, + REG_SD_IMKR_RST = 0x0, + REG_SD_MISR_RST = 0x0, + REG_SD_RISR_RST = 0x0, + REG_SD_STAR_RST = 0x00000100, + REG_SD_FWLR_RST = 0x000F0000, + REG_SD_FUNS_RST = 0x0, + REG_SD_DBGC_RST = 0x0, + REG_SD_A12A_RST = 0x0000FFFF, + REG_SD_NTSR_RST = 0x00000001, + REG_SD_SDBG_RST = 0x0, + REG_SD_HWRST_RST = 0x00000001, + REG_SD_DMAC_RST = 0x0, + REG_SD_DLBA_RST = 0x0, + REG_SD_IDST_RST = 0x0, + REG_SD_IDIE_RST = 0x0, + REG_SD_THLDC_RST = 0x0, + REG_SD_DSBD_RST = 0x0, + REG_SD_RES_CRC_RST = 0x0, + REG_SD_DATA_CRC_RST = 0x0, + REG_SD_CRC_STA_RST = 0x0, + REG_SD_FIFO_RST = 0x0, +}; + +/* Data transfer descriptor for DMA */ +typedef struct TransferDescriptor { + uint32_t status; /* Status flags */ + uint32_t size; /* Data buffer size */ + uint32_t addr; /* Data buffer address */ + uint32_t next; /* Physical address of next descriptor */ +} TransferDescriptor; + +/* Data transfer descriptor flags */ +enum { + DESC_STATUS_HOLD = (1 << 31), /* Set when descriptor is in use by DMA */ + DESC_STATUS_ERROR = (1 << 30), /* Set when DMA transfer error occurred */ + DESC_STATUS_CHAIN = (1 << 4), /* Indicates chained descriptor. */ + DESC_STATUS_FIRST = (1 << 3), /* Set on the first descriptor */ + DESC_STATUS_LAST = (1 << 2), /* Set on the last descriptor */ + DESC_STATUS_NOIRQ = (1 << 1), /* Skip raising interrupt after transfer */ + DESC_SIZE_MASK = (0xfffffffc) +}; + +static void allwinner_sdhost_update_irq(AwSdHostState *s) +{ + uint32_t irq; + + if (s->global_ctl & SD_GCTL_INT_ENB) { + irq = s->irq_status & s->irq_mask; + } else { + irq = 0; + } + + trace_allwinner_sdhost_update_irq(irq); + qemu_set_irq(s->irq, irq); +} + +static void allwinner_sdhost_update_transfer_cnt(AwSdHostState *s, + uint32_t bytes) +{ + if (s->transfer_cnt > bytes) { + s->transfer_cnt -= bytes; + } else { + s->transfer_cnt = 0; + } + + if (!s->transfer_cnt) { + s->irq_status |= SD_RISR_DATA_COMPLETE; + } +} + +static void allwinner_sdhost_set_inserted(DeviceState *dev, bool inserted) +{ + AwSdHostState *s = AW_SDHOST(dev); + + trace_allwinner_sdhost_set_inserted(inserted); + + if (inserted) { + s->irq_status |= SD_RISR_CARD_INSERT; + s->irq_status &= ~SD_RISR_CARD_REMOVE; + s->status |= SD_STAR_CARD_PRESENT; + } else { + s->irq_status &= ~SD_RISR_CARD_INSERT; + s->irq_status |= SD_RISR_CARD_REMOVE; + s->status &= ~SD_STAR_CARD_PRESENT; + } + + allwinner_sdhost_update_irq(s); +} + +static void allwinner_sdhost_send_command(AwSdHostState *s) +{ + SDRequest request; + uint8_t resp[16]; + int rlen; + + /* Auto clear load flag */ + s->command &= ~SD_CMDR_LOAD; + + /* Clock change does not actually interact with the SD bus */ + if (!(s->command & SD_CMDR_CLKCHANGE)) { + + /* Prepare request */ + request.cmd = s->command & SD_CMDR_CMDID_MASK; + request.arg = s->command_arg; + + /* Send request to SD bus */ + rlen = sdbus_do_command(&s->sdbus, &request, resp); + if (rlen < 0) { + goto error; + } + + /* If the command has a response, store it in the response registers */ + if ((s->command & SD_CMDR_RESPONSE)) { + if (rlen == 4 && !(s->command & SD_CMDR_RESPONSE_LONG)) { + s->response[0] = ldl_be_p(&resp[0]); + s->response[1] = s->response[2] = s->response[3] = 0; + + } else if (rlen == 16 && (s->command & SD_CMDR_RESPONSE_LONG)) { + s->response[0] = ldl_be_p(&resp[12]); + s->response[1] = ldl_be_p(&resp[8]); + s->response[2] = ldl_be_p(&resp[4]); + s->response[3] = ldl_be_p(&resp[0]); + } else { + goto error; + } + } + } + + /* Set interrupt status bits */ + s->irq_status |= SD_RISR_CMD_COMPLETE; + return; + +error: + s->irq_status |= SD_RISR_NO_RESPONSE; +} + +static void allwinner_sdhost_auto_stop(AwSdHostState *s) +{ + /* + * The stop command (CMD12) ensures the SD bus + * returns to the transfer state. + */ + if ((s->command & SD_CMDR_AUTOSTOP) && (s->transfer_cnt == 0)) { + /* First save current command registers */ + uint32_t saved_cmd = s->command; + uint32_t saved_arg = s->command_arg; + + /* Prepare stop command (CMD12) */ + s->command &= ~SD_CMDR_CMDID_MASK; + s->command |= 12; /* CMD12 */ + s->command_arg = 0; + + /* Put the command on SD bus */ + allwinner_sdhost_send_command(s); + + /* Restore command values */ + s->command = saved_cmd; + s->command_arg = saved_arg; + + /* Set IRQ status bit for automatic stop done */ + s->irq_status |= SD_RISR_AUTOCMD_DONE; + } +} + +static uint32_t allwinner_sdhost_process_desc(AwSdHostState *s, + hwaddr desc_addr, + TransferDescriptor *desc, + bool is_write, uint32_t max_bytes) +{ + AwSdHostClass *klass = AW_SDHOST_GET_CLASS(s); + uint32_t num_done = 0; + uint32_t num_bytes = max_bytes; + uint8_t buf[1024]; + + /* Read descriptor */ + cpu_physical_memory_read(desc_addr, desc, sizeof(*desc)); + if (desc->size == 0) { + desc->size = klass->max_desc_size; + } else if (desc->size > klass->max_desc_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: DMA descriptor buffer size " + " is out-of-bounds: %" PRIu32 " > %zu", + __func__, desc->size, klass->max_desc_size); + desc->size = klass->max_desc_size; + } + if (desc->size < num_bytes) { + num_bytes = desc->size; + } + + trace_allwinner_sdhost_process_desc(desc_addr, desc->size, + is_write, max_bytes); + + while (num_done < num_bytes) { + /* Try to completely fill the local buffer */ + uint32_t buf_bytes = num_bytes - num_done; + if (buf_bytes > sizeof(buf)) { + buf_bytes = sizeof(buf); + } + + /* Write to SD bus */ + if (is_write) { + cpu_physical_memory_read((desc->addr & DESC_SIZE_MASK) + num_done, + buf, buf_bytes); + + for (uint32_t i = 0; i < buf_bytes; i++) { + sdbus_write_data(&s->sdbus, buf[i]); + } + + /* Read from SD bus */ + } else { + for (uint32_t i = 0; i < buf_bytes; i++) { + buf[i] = sdbus_read_data(&s->sdbus); + } + cpu_physical_memory_write((desc->addr & DESC_SIZE_MASK) + num_done, + buf, buf_bytes); + } + num_done += buf_bytes; + } + + /* Clear hold flag and flush descriptor */ + desc->status &= ~DESC_STATUS_HOLD; + cpu_physical_memory_write(desc_addr, desc, sizeof(*desc)); + + return num_done; +} + +static void allwinner_sdhost_dma(AwSdHostState *s) +{ + TransferDescriptor desc; + hwaddr desc_addr = s->desc_base; + bool is_write = (s->command & SD_CMDR_WRITE); + uint32_t bytes_done = 0; + + /* Check if DMA can be performed */ + if (s->byte_count == 0 || s->block_size == 0 || + !(s->global_ctl & SD_GCTL_DMA_ENB)) { + return; + } + + /* + * For read operations, data must be available on the SD bus + * If not, it is an error and we should not act at all + */ + if (!is_write && !sdbus_data_ready(&s->sdbus)) { + return; + } + + /* Process the DMA descriptors until all data is copied */ + while (s->byte_count > 0) { + bytes_done = allwinner_sdhost_process_desc(s, desc_addr, &desc, + is_write, s->byte_count); + allwinner_sdhost_update_transfer_cnt(s, bytes_done); + + if (bytes_done <= s->byte_count) { + s->byte_count -= bytes_done; + } else { + s->byte_count = 0; + } + + if (desc.status & DESC_STATUS_LAST) { + break; + } else { + desc_addr = desc.next; + } + } + + /* Raise IRQ to signal DMA is completed */ + s->irq_status |= SD_RISR_DATA_COMPLETE | SD_RISR_SDIO_INTR; + + /* Update DMAC bits */ + s->dmac_status |= SD_IDST_INT_SUMMARY; + + if (is_write) { + s->dmac_status |= SD_IDST_TRANSMIT_IRQ; + } else { + s->dmac_status |= SD_IDST_RECEIVE_IRQ; + } +} + +static uint64_t allwinner_sdhost_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwSdHostState *s = AW_SDHOST(opaque); + uint32_t res = 0; + + switch (offset) { + case REG_SD_GCTL: /* Global Control */ + res = s->global_ctl; + break; + case REG_SD_CKCR: /* Clock Control */ + res = s->clock_ctl; + break; + case REG_SD_TMOR: /* Timeout */ + res = s->timeout; + break; + case REG_SD_BWDR: /* Bus Width */ + res = s->bus_width; + break; + case REG_SD_BKSR: /* Block Size */ + res = s->block_size; + break; + case REG_SD_BYCR: /* Byte Count */ + res = s->byte_count; + break; + case REG_SD_CMDR: /* Command */ + res = s->command; + break; + case REG_SD_CAGR: /* Command Argument */ + res = s->command_arg; + break; + case REG_SD_RESP0: /* Response Zero */ + res = s->response[0]; + break; + case REG_SD_RESP1: /* Response One */ + res = s->response[1]; + break; + case REG_SD_RESP2: /* Response Two */ + res = s->response[2]; + break; + case REG_SD_RESP3: /* Response Three */ + res = s->response[3]; + break; + case REG_SD_IMKR: /* Interrupt Mask */ + res = s->irq_mask; + break; + case REG_SD_MISR: /* Masked Interrupt Status */ + res = s->irq_status & s->irq_mask; + break; + case REG_SD_RISR: /* Raw Interrupt Status */ + res = s->irq_status; + break; + case REG_SD_STAR: /* Status */ + res = s->status; + break; + case REG_SD_FWLR: /* FIFO Water Level */ + res = s->fifo_wlevel; + break; + case REG_SD_FUNS: /* FIFO Function Select */ + res = s->fifo_func_sel; + break; + case REG_SD_DBGC: /* Debug Enable */ + res = s->debug_enable; + break; + case REG_SD_A12A: /* Auto command 12 argument */ + res = s->auto12_arg; + break; + case REG_SD_NTSR: /* SD NewTiming Set */ + res = s->newtiming_set; + break; + case REG_SD_SDBG: /* SD newTiming Set Debug */ + res = s->newtiming_debug; + break; + case REG_SD_HWRST: /* Hardware Reset Register */ + res = s->hardware_rst; + break; + case REG_SD_DMAC: /* Internal DMA Controller Control */ + res = s->dmac; + break; + case REG_SD_DLBA: /* Descriptor List Base Address */ + res = s->desc_base; + break; + case REG_SD_IDST: /* Internal DMA Controller Status */ + res = s->dmac_status; + break; + case REG_SD_IDIE: /* Internal DMA Controller Interrupt Enable */ + res = s->dmac_irq; + break; + case REG_SD_THLDC: /* Card Threshold Control */ + res = s->card_threshold; + break; + case REG_SD_DSBD: /* eMMC DDR Start Bit Detection Control */ + res = s->startbit_detect; + break; + case REG_SD_RES_CRC: /* Response CRC from card/eMMC */ + res = s->response_crc; + break; + case REG_SD_DATA7_CRC: /* CRC Data 7 from card/eMMC */ + case REG_SD_DATA6_CRC: /* CRC Data 6 from card/eMMC */ + case REG_SD_DATA5_CRC: /* CRC Data 5 from card/eMMC */ + case REG_SD_DATA4_CRC: /* CRC Data 4 from card/eMMC */ + case REG_SD_DATA3_CRC: /* CRC Data 3 from card/eMMC */ + case REG_SD_DATA2_CRC: /* CRC Data 2 from card/eMMC */ + case REG_SD_DATA1_CRC: /* CRC Data 1 from card/eMMC */ + case REG_SD_DATA0_CRC: /* CRC Data 0 from card/eMMC */ + res = s->data_crc[((offset - REG_SD_DATA7_CRC) / sizeof(uint32_t))]; + break; + case REG_SD_CRC_STA: /* CRC status from card/eMMC in write operation */ + res = s->status_crc; + break; + case REG_SD_FIFO: /* Read/Write FIFO */ + if (sdbus_data_ready(&s->sdbus)) { + res = sdbus_read_data(&s->sdbus); + res |= sdbus_read_data(&s->sdbus) << 8; + res |= sdbus_read_data(&s->sdbus) << 16; + res |= sdbus_read_data(&s->sdbus) << 24; + allwinner_sdhost_update_transfer_cnt(s, sizeof(uint32_t)); + allwinner_sdhost_auto_stop(s); + allwinner_sdhost_update_irq(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no data ready on SD bus\n", + __func__); + } + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" + HWADDR_PRIx"\n", __func__, offset); + res = 0; + break; + } + + trace_allwinner_sdhost_read(offset, res, size); + return res; +} + +static void allwinner_sdhost_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AwSdHostState *s = AW_SDHOST(opaque); + + trace_allwinner_sdhost_write(offset, value, size); + + switch (offset) { + case REG_SD_GCTL: /* Global Control */ + s->global_ctl = value; + s->global_ctl &= ~(SD_GCTL_DMA_RST | SD_GCTL_FIFO_RST | + SD_GCTL_SOFT_RST); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_CKCR: /* Clock Control */ + s->clock_ctl = value; + break; + case REG_SD_TMOR: /* Timeout */ + s->timeout = value; + break; + case REG_SD_BWDR: /* Bus Width */ + s->bus_width = value; + break; + case REG_SD_BKSR: /* Block Size */ + s->block_size = value; + break; + case REG_SD_BYCR: /* Byte Count */ + s->byte_count = value; + s->transfer_cnt = value; + break; + case REG_SD_CMDR: /* Command */ + s->command = value; + if (value & SD_CMDR_LOAD) { + allwinner_sdhost_send_command(s); + allwinner_sdhost_dma(s); + allwinner_sdhost_auto_stop(s); + } + allwinner_sdhost_update_irq(s); + break; + case REG_SD_CAGR: /* Command Argument */ + s->command_arg = value; + break; + case REG_SD_RESP0: /* Response Zero */ + s->response[0] = value; + break; + case REG_SD_RESP1: /* Response One */ + s->response[1] = value; + break; + case REG_SD_RESP2: /* Response Two */ + s->response[2] = value; + break; + case REG_SD_RESP3: /* Response Three */ + s->response[3] = value; + break; + case REG_SD_IMKR: /* Interrupt Mask */ + s->irq_mask = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_MISR: /* Masked Interrupt Status */ + case REG_SD_RISR: /* Raw Interrupt Status */ + s->irq_status &= ~value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_STAR: /* Status */ + s->status &= ~value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_FWLR: /* FIFO Water Level */ + s->fifo_wlevel = value; + break; + case REG_SD_FUNS: /* FIFO Function Select */ + s->fifo_func_sel = value; + break; + case REG_SD_DBGC: /* Debug Enable */ + s->debug_enable = value; + break; + case REG_SD_A12A: /* Auto command 12 argument */ + s->auto12_arg = value; + break; + case REG_SD_NTSR: /* SD NewTiming Set */ + s->newtiming_set = value; + break; + case REG_SD_SDBG: /* SD newTiming Set Debug */ + s->newtiming_debug = value; + break; + case REG_SD_HWRST: /* Hardware Reset Register */ + s->hardware_rst = value; + break; + case REG_SD_DMAC: /* Internal DMA Controller Control */ + s->dmac = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_DLBA: /* Descriptor List Base Address */ + s->desc_base = value; + break; + case REG_SD_IDST: /* Internal DMA Controller Status */ + s->dmac_status &= (~SD_IDST_WR_MASK) | (~value & SD_IDST_WR_MASK); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_IDIE: /* Internal DMA Controller Interrupt Enable */ + s->dmac_irq = value; + allwinner_sdhost_update_irq(s); + break; + case REG_SD_THLDC: /* Card Threshold Control */ + s->card_threshold = value; + break; + case REG_SD_DSBD: /* eMMC DDR Start Bit Detection Control */ + s->startbit_detect = value; + break; + case REG_SD_FIFO: /* Read/Write FIFO */ + sdbus_write_data(&s->sdbus, value & 0xff); + sdbus_write_data(&s->sdbus, (value >> 8) & 0xff); + sdbus_write_data(&s->sdbus, (value >> 16) & 0xff); + sdbus_write_data(&s->sdbus, (value >> 24) & 0xff); + allwinner_sdhost_update_transfer_cnt(s, sizeof(uint32_t)); + allwinner_sdhost_auto_stop(s); + allwinner_sdhost_update_irq(s); + break; + case REG_SD_RES_CRC: /* Response CRC from card/eMMC */ + case REG_SD_DATA7_CRC: /* CRC Data 7 from card/eMMC */ + case REG_SD_DATA6_CRC: /* CRC Data 6 from card/eMMC */ + case REG_SD_DATA5_CRC: /* CRC Data 5 from card/eMMC */ + case REG_SD_DATA4_CRC: /* CRC Data 4 from card/eMMC */ + case REG_SD_DATA3_CRC: /* CRC Data 3 from card/eMMC */ + case REG_SD_DATA2_CRC: /* CRC Data 2 from card/eMMC */ + case REG_SD_DATA1_CRC: /* CRC Data 1 from card/eMMC */ + case REG_SD_DATA0_CRC: /* CRC Data 0 from card/eMMC */ + case REG_SD_CRC_STA: /* CRC status from card/eMMC in write operation */ + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset %" + HWADDR_PRIx"\n", __func__, offset); + break; + } +} + +static const MemoryRegionOps allwinner_sdhost_ops = { + .read = allwinner_sdhost_read, + .write = allwinner_sdhost_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const VMStateDescription vmstate_allwinner_sdhost = { + .name = "allwinner-sdhost", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(global_ctl, AwSdHostState), + VMSTATE_UINT32(clock_ctl, AwSdHostState), + VMSTATE_UINT32(timeout, AwSdHostState), + VMSTATE_UINT32(bus_width, AwSdHostState), + VMSTATE_UINT32(block_size, AwSdHostState), + VMSTATE_UINT32(byte_count, AwSdHostState), + VMSTATE_UINT32(transfer_cnt, AwSdHostState), + VMSTATE_UINT32(command, AwSdHostState), + VMSTATE_UINT32(command_arg, AwSdHostState), + VMSTATE_UINT32_ARRAY(response, AwSdHostState, 4), + VMSTATE_UINT32(irq_mask, AwSdHostState), + VMSTATE_UINT32(irq_status, AwSdHostState), + VMSTATE_UINT32(status, AwSdHostState), + VMSTATE_UINT32(fifo_wlevel, AwSdHostState), + VMSTATE_UINT32(fifo_func_sel, AwSdHostState), + VMSTATE_UINT32(debug_enable, AwSdHostState), + VMSTATE_UINT32(auto12_arg, AwSdHostState), + VMSTATE_UINT32(newtiming_set, AwSdHostState), + VMSTATE_UINT32(newtiming_debug, AwSdHostState), + VMSTATE_UINT32(hardware_rst, AwSdHostState), + VMSTATE_UINT32(dmac, AwSdHostState), + VMSTATE_UINT32(desc_base, AwSdHostState), + VMSTATE_UINT32(dmac_status, AwSdHostState), + VMSTATE_UINT32(dmac_irq, AwSdHostState), + VMSTATE_UINT32(card_threshold, AwSdHostState), + VMSTATE_UINT32(startbit_detect, AwSdHostState), + VMSTATE_UINT32(response_crc, AwSdHostState), + VMSTATE_UINT32_ARRAY(data_crc, AwSdHostState, 8), + VMSTATE_UINT32(status_crc, AwSdHostState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sdhost_init(Object *obj) +{ + AwSdHostState *s = AW_SDHOST(obj); + + qbus_create_inplace(&s->sdbus, sizeof(s->sdbus), + TYPE_AW_SDHOST_BUS, DEVICE(s), "sd-bus"); + + memory_region_init_io(&s->iomem, obj, &allwinner_sdhost_ops, s, + TYPE_AW_SDHOST, 4 * KiB); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(s), &s->irq); +} + +static void allwinner_sdhost_reset(DeviceState *dev) +{ + AwSdHostState *s = AW_SDHOST(dev); + + s->global_ctl = REG_SD_GCTL_RST; + s->clock_ctl = REG_SD_CKCR_RST; + s->timeout = REG_SD_TMOR_RST; + s->bus_width = REG_SD_BWDR_RST; + s->block_size = REG_SD_BKSR_RST; + s->byte_count = REG_SD_BYCR_RST; + s->transfer_cnt = 0; + + s->command = REG_SD_CMDR_RST; + s->command_arg = REG_SD_CAGR_RST; + + for (int i = 0; i < ARRAY_SIZE(s->response); i++) { + s->response[i] = REG_SD_RESP_RST; + } + + s->irq_mask = REG_SD_IMKR_RST; + s->irq_status = REG_SD_RISR_RST; + s->status = REG_SD_STAR_RST; + + s->fifo_wlevel = REG_SD_FWLR_RST; + s->fifo_func_sel = REG_SD_FUNS_RST; + s->debug_enable = REG_SD_DBGC_RST; + s->auto12_arg = REG_SD_A12A_RST; + s->newtiming_set = REG_SD_NTSR_RST; + s->newtiming_debug = REG_SD_SDBG_RST; + s->hardware_rst = REG_SD_HWRST_RST; + s->dmac = REG_SD_DMAC_RST; + s->desc_base = REG_SD_DLBA_RST; + s->dmac_status = REG_SD_IDST_RST; + s->dmac_irq = REG_SD_IDIE_RST; + s->card_threshold = REG_SD_THLDC_RST; + s->startbit_detect = REG_SD_DSBD_RST; + s->response_crc = REG_SD_RES_CRC_RST; + + for (int i = 0; i < ARRAY_SIZE(s->data_crc); i++) { + s->data_crc[i] = REG_SD_DATA_CRC_RST; + } + + s->status_crc = REG_SD_CRC_STA_RST; +} + +static void allwinner_sdhost_bus_class_init(ObjectClass *klass, void *data) +{ + SDBusClass *sbc = SD_BUS_CLASS(klass); + + sbc->set_inserted = allwinner_sdhost_set_inserted; +} + +static void allwinner_sdhost_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_sdhost_reset; + dc->vmsd = &vmstate_allwinner_sdhost; +} + +static void allwinner_sdhost_sun4i_class_init(ObjectClass *klass, void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 8 * KiB; +} + +static void allwinner_sdhost_sun5i_class_init(ObjectClass *klass, void *data) +{ + AwSdHostClass *sc = AW_SDHOST_CLASS(klass); + sc->max_desc_size = 64 * KiB; +} + +static TypeInfo allwinner_sdhost_info = { + .name = TYPE_AW_SDHOST, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_sdhost_init, + .instance_size = sizeof(AwSdHostState), + .class_init = allwinner_sdhost_class_init, + .class_size = sizeof(AwSdHostClass), + .abstract = true, +}; + +static const TypeInfo allwinner_sdhost_sun4i_info = { + .name = TYPE_AW_SDHOST_SUN4I, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun4i_class_init, +}; + +static const TypeInfo allwinner_sdhost_sun5i_info = { + .name = TYPE_AW_SDHOST_SUN5I, + .parent = TYPE_AW_SDHOST, + .class_init = allwinner_sdhost_sun5i_class_init, +}; + +static const TypeInfo allwinner_sdhost_bus_info = { + .name = TYPE_AW_SDHOST_BUS, + .parent = TYPE_SD_BUS, + .instance_size = sizeof(SDBus), + .class_init = allwinner_sdhost_bus_class_init, +}; + +static void allwinner_sdhost_register_types(void) +{ + type_register_static(&allwinner_sdhost_info); + type_register_static(&allwinner_sdhost_sun4i_info); + type_register_static(&allwinner_sdhost_sun5i_info); + type_register_static(&allwinner_sdhost_bus_info); +} + +type_init(allwinner_sdhost_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 select UNIMP select USB_OHCI select USB_EHCI_SYSBUS + select SD config RASPI bool diff --git a/hw/sd/trace-events b/hw/sd/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/trace-events +++ b/hw/sd/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-sdhost.c +allwinner_sdhost_set_inserted(bool inserted) "inserted %u" +allwinner_sdhost_process_desc(uint64_t desc_addr, uint32_t desc_size, bool is_write, uint32_t max_bytes) "desc_addr 0x%" PRIx64 " desc_size %" PRIu32 " is_write %u max_bytes %" PRIu32 +allwinner_sdhost_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sdhost_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_sdhost_update_irq(uint32_t irq) "IRQ bits 0x%" PRIx32 + # bcm2835_sdhost.c bcm2835_sdhost_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" bcm2835_sdhost_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %u" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Allwinner Sun8i System on Chip family includes an Ethernet MAC (EMAC) which provides 10M/100M/1000M Ethernet connectivity. This commit adds support for the Allwinner EMAC from the Sun8i family (H2+, H3, A33, etc), including emulation for the following functionality: * DMA transfers * MII interface * Transmit CRC calculation Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-10-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 3 + include/hw/net/allwinner-sun8i-emac.h | 99 +++ hw/arm/allwinner-h3.c | 16 +- hw/arm/orangepi.c | 3 + hw/net/allwinner-sun8i-emac.c | 871 ++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/net/Kconfig | 3 + hw/net/trace-events | 10 + 9 files changed, 1006 insertions(+), 1 deletion(-) create mode 100644 include/hw/net/allwinner-sun8i-emac.h create mode 100644 hw/net/allwinner-sun8i-emac.c diff --git a/hw/net/Makefile.objs b/hw/net/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Makefile.objs +++ b/hw/net/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_XGMAC) += xgmac.o common-obj-$(CONFIG_MIPSNET) += mipsnet.o common-obj-$(CONFIG_XILINX_AXI) += xilinx_axienet.o common-obj-$(CONFIG_ALLWINNER_EMAC) += allwinner_emac.o +common-obj-$(CONFIG_ALLWINNER_SUN8I_EMAC) += allwinner-sun8i-emac.o common-obj-$(CONFIG_IMX_FEC) += imx_fec.o common-obj-$(CONFIG_CADENCE) += cadence_gem.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" +#include "hw/net/allwinner-sun8i-emac.h" #include "target/arm/cpu.h" /** @@ -XXX,XX +XXX,XX @@ enum { AW_H3_UART1, AW_H3_UART2, AW_H3_UART3, + AW_H3_EMAC, AW_H3_GIC_DIST, AW_H3_GIC_CPU, AW_H3_GIC_HYP, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; + AwSun8iEmacState emac; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/net/allwinner-sun8i-emac.h b/include/hw/net/allwinner-sun8i-emac.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/allwinner-sun8i-emac.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Sun8i Ethernet MAC emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_NET_ALLWINNER_SUN8I_EMAC_H +#define HW_NET_ALLWINNER_SUN8I_EMAC_H + +#include "qom/object.h" +#include "net/net.h" +#include "hw/sysbus.h" + +/** + * Object model + * @{ + */ + +#define TYPE_AW_SUN8I_EMAC "allwinner-sun8i-emac" +#define AW_SUN8I_EMAC(obj) \ + OBJECT_CHECK(AwSun8iEmacState, (obj), TYPE_AW_SUN8I_EMAC) + +/** @} */ + +/** + * Allwinner Sun8i EMAC object instance state + */ +typedef struct AwSun8iEmacState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Interrupt output signal to notify CPU */ + qemu_irq irq; + + /** Generic Network Interface Controller (NIC) for networking API */ + NICState *nic; + + /** Generic Network Interface Controller (NIC) configuration */ + NICConf conf; + + /** + * @name Media Independent Interface (MII) + * @{ + */ + + uint8_t mii_phy_addr; /**< PHY address */ + uint32_t mii_cr; /**< Control */ + uint32_t mii_st; /**< Status */ + uint32_t mii_adv; /**< Advertised Abilities */ + + /** @} */ + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t basic_ctl0; /**< Basic Control 0 */ + uint32_t basic_ctl1; /**< Basic Control 1 */ + uint32_t int_en; /**< Interrupt Enable */ + uint32_t int_sta; /**< Interrupt Status */ + uint32_t frm_flt; /**< Receive Frame Filter */ + + uint32_t rx_ctl0; /**< Receive Control 0 */ + uint32_t rx_ctl1; /**< Receive Control 1 */ + uint32_t rx_desc_head; /**< Receive Descriptor List Address */ + uint32_t rx_desc_curr; /**< Current Receive Descriptor Address */ + + uint32_t tx_ctl0; /**< Transmit Control 0 */ + uint32_t tx_ctl1; /**< Transmit Control 1 */ + uint32_t tx_desc_head; /**< Transmit Descriptor List Address */ + uint32_t tx_desc_curr; /**< Current Transmit Descriptor Address */ + uint32_t tx_flowctl; /**< Transmit Flow Control */ + + uint32_t mii_cmd; /**< Management Interface Command */ + uint32_t mii_data; /**< Management Interface Data */ + + /** @} */ + +} AwSun8iEmacState; + +#endif /* HW_NET_ALLWINNER_SUN8I_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_UART1] = 0x01c28400, [AW_H3_UART2] = 0x01c28800, [AW_H3_UART3] = 0x01c28c00, + [AW_H3_EMAC] = 0x01c30000, [AW_H3_GIC_DIST] = 0x01c81000, [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "twi1", 0x01c2b000, 1 * KiB }, { "twi2", 0x01c2b400, 1 * KiB }, { "scr", 0x01c2c400, 1 * KiB }, - { "emac", 0x01c30000, 64 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, { "dramcom", 0x01c62000, 4 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_OHCI2 = 77, AW_H3_GIC_SPI_EHCI3 = 78, AW_H3_GIC_SPI_OHCI3 = 79, + AW_H3_GIC_SPI_EMAC = 82 }; /* Allwinner H3 general constants */ @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), TYPE_AW_SDHOST_SUN5I); + + sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), + TYPE_AW_SUN8I_EMAC); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), "sd-bus", &error_abort); + /* EMAC */ + if (nd_table[0].used) { + qemu_check_nic_model(&nd_table[0], TYPE_AW_SUN8I_EMAC); + qdev_set_nic_properties(DEVICE(&s->emac), &nd_table[0]); + } + qdev_init_nofail(DEVICE(&s->emac)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->emac), 0, s->memmap[AW_H3_EMAC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->emac), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_EMAC)); + /* Universal Serial Bus */ sysbus_create_simple(TYPE_AW_H3_EHCI, s->memmap[AW_H3_EHCI0], qdev_get_gpio_in(DEVICE(&s->gic), diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) warn_report("Security Identifier value does not include H3 prefix"); } + /* Setup EMAC properties */ + object_property_set_int(OBJECT(&h3->emac), 1, "phy-addr", &error_abort); + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/allwinner-sun8i-emac.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Sun8i Ethernet MAC emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "net/net.h" +#include "hw/irq.h" +#include "hw/qdev-properties.h" +#include "qemu/log.h" +#include "trace.h" +#include "net/checksum.h" +#include "qemu/module.h" +#include "exec/cpu-common.h" +#include "hw/net/allwinner-sun8i-emac.h" + +/* EMAC register offsets */ +enum { + REG_BASIC_CTL_0 = 0x0000, /* Basic Control 0 */ + REG_BASIC_CTL_1 = 0x0004, /* Basic Control 1 */ + REG_INT_STA = 0x0008, /* Interrupt Status */ + REG_INT_EN = 0x000C, /* Interrupt Enable */ + REG_TX_CTL_0 = 0x0010, /* Transmit Control 0 */ + REG_TX_CTL_1 = 0x0014, /* Transmit Control 1 */ + REG_TX_FLOW_CTL = 0x001C, /* Transmit Flow Control */ + REG_TX_DMA_DESC_LIST = 0x0020, /* Transmit Descriptor List Address */ + REG_RX_CTL_0 = 0x0024, /* Receive Control 0 */ + REG_RX_CTL_1 = 0x0028, /* Receive Control 1 */ + REG_RX_DMA_DESC_LIST = 0x0034, /* Receive Descriptor List Address */ + REG_FRM_FLT = 0x0038, /* Receive Frame Filter */ + REG_RX_HASH_0 = 0x0040, /* Receive Hash Table 0 */ + REG_RX_HASH_1 = 0x0044, /* Receive Hash Table 1 */ + REG_MII_CMD = 0x0048, /* Management Interface Command */ + REG_MII_DATA = 0x004C, /* Management Interface Data */ + REG_ADDR_HIGH = 0x0050, /* MAC Address High */ + REG_ADDR_LOW = 0x0054, /* MAC Address Low */ + REG_TX_DMA_STA = 0x00B0, /* Transmit DMA Status */ + REG_TX_CUR_DESC = 0x00B4, /* Transmit Current Descriptor */ + REG_TX_CUR_BUF = 0x00B8, /* Transmit Current Buffer */ + REG_RX_DMA_STA = 0x00C0, /* Receive DMA Status */ + REG_RX_CUR_DESC = 0x00C4, /* Receive Current Descriptor */ + REG_RX_CUR_BUF = 0x00C8, /* Receive Current Buffer */ + REG_RGMII_STA = 0x00D0, /* RGMII Status */ +}; + +/* EMAC register flags */ +enum { + BASIC_CTL0_100Mbps = (0b11 << 2), + BASIC_CTL0_FD = (1 << 0), + BASIC_CTL1_SOFTRST = (1 << 0), +}; + +enum { + INT_STA_RGMII_LINK = (1 << 16), + INT_STA_RX_EARLY = (1 << 13), + INT_STA_RX_OVERFLOW = (1 << 12), + INT_STA_RX_TIMEOUT = (1 << 11), + INT_STA_RX_DMA_STOP = (1 << 10), + INT_STA_RX_BUF_UA = (1 << 9), + INT_STA_RX = (1 << 8), + INT_STA_TX_EARLY = (1 << 5), + INT_STA_TX_UNDERFLOW = (1 << 4), + INT_STA_TX_TIMEOUT = (1 << 3), + INT_STA_TX_BUF_UA = (1 << 2), + INT_STA_TX_DMA_STOP = (1 << 1), + INT_STA_TX = (1 << 0), +}; + +enum { + INT_EN_RX_EARLY = (1 << 13), + INT_EN_RX_OVERFLOW = (1 << 12), + INT_EN_RX_TIMEOUT = (1 << 11), + INT_EN_RX_DMA_STOP = (1 << 10), + INT_EN_RX_BUF_UA = (1 << 9), + INT_EN_RX = (1 << 8), + INT_EN_TX_EARLY = (1 << 5), + INT_EN_TX_UNDERFLOW = (1 << 4), + INT_EN_TX_TIMEOUT = (1 << 3), + INT_EN_TX_BUF_UA = (1 << 2), + INT_EN_TX_DMA_STOP = (1 << 1), + INT_EN_TX = (1 << 0), +}; + +enum { + TX_CTL0_TX_EN = (1 << 31), + TX_CTL1_TX_DMA_START = (1 << 31), + TX_CTL1_TX_DMA_EN = (1 << 30), + TX_CTL1_TX_FLUSH = (1 << 0), +}; + +enum { + RX_CTL0_RX_EN = (1 << 31), + RX_CTL0_STRIP_FCS = (1 << 28), + RX_CTL0_CRC_IPV4 = (1 << 27), +}; + +enum { + RX_CTL1_RX_DMA_START = (1 << 31), + RX_CTL1_RX_DMA_EN = (1 << 30), + RX_CTL1_RX_MD = (1 << 1), +}; + +enum { + RX_FRM_FLT_DIS_ADDR = (1 << 31), +}; + +enum { + MII_CMD_PHY_ADDR_SHIFT = (12), + MII_CMD_PHY_ADDR_MASK = (0xf000), + MII_CMD_PHY_REG_SHIFT = (4), + MII_CMD_PHY_REG_MASK = (0xf0), + MII_CMD_PHY_RW = (1 << 1), + MII_CMD_PHY_BUSY = (1 << 0), +}; + +enum { + TX_DMA_STA_STOP = (0b000), + TX_DMA_STA_RUN_FETCH = (0b001), + TX_DMA_STA_WAIT_STA = (0b010), +}; + +enum { + RX_DMA_STA_STOP = (0b000), + RX_DMA_STA_RUN_FETCH = (0b001), + RX_DMA_STA_WAIT_FRM = (0b011), +}; + +/* EMAC register reset values */ +enum { + REG_BASIC_CTL_1_RST = 0x08000000, +}; + +/* EMAC constants */ +enum { + AW_SUN8I_EMAC_MIN_PKT_SZ = 64 +}; + +/* Transmit/receive frame descriptor */ +typedef struct FrameDescriptor { + uint32_t status; + uint32_t status2; + uint32_t addr; + uint32_t next; +} FrameDescriptor; + +/* Frame descriptor flags */ +enum { + DESC_STATUS_CTL = (1 << 31), + DESC_STATUS2_BUF_SIZE_MASK = (0x7ff), +}; + +/* Transmit frame descriptor flags */ +enum { + TX_DESC_STATUS_LENGTH_ERR = (1 << 14), + TX_DESC_STATUS2_FIRST_DESC = (1 << 29), + TX_DESC_STATUS2_LAST_DESC = (1 << 30), + TX_DESC_STATUS2_CHECKSUM_MASK = (0x3 << 27), +}; + +/* Receive frame descriptor flags */ +enum { + RX_DESC_STATUS_FIRST_DESC = (1 << 9), + RX_DESC_STATUS_LAST_DESC = (1 << 8), + RX_DESC_STATUS_FRM_LEN_MASK = (0x3fff0000), + RX_DESC_STATUS_FRM_LEN_SHIFT = (16), + RX_DESC_STATUS_NO_BUF = (1 << 14), + RX_DESC_STATUS_HEADER_ERR = (1 << 7), + RX_DESC_STATUS_LENGTH_ERR = (1 << 4), + RX_DESC_STATUS_CRC_ERR = (1 << 1), + RX_DESC_STATUS_PAYLOAD_ERR = (1 << 0), + RX_DESC_STATUS2_RX_INT_CTL = (1 << 31), +}; + +/* MII register offsets */ +enum { + MII_REG_CR = (0x0), /* Control */ + MII_REG_ST = (0x1), /* Status */ + MII_REG_ID_HIGH = (0x2), /* Identifier High */ + MII_REG_ID_LOW = (0x3), /* Identifier Low */ + MII_REG_ADV = (0x4), /* Advertised abilities */ + MII_REG_LPA = (0x5), /* Link partner abilities */ +}; + +/* MII register flags */ +enum { + MII_REG_CR_RESET = (1 << 15), + MII_REG_CR_POWERDOWN = (1 << 11), + MII_REG_CR_10Mbit = (0), + MII_REG_CR_100Mbit = (1 << 13), + MII_REG_CR_1000Mbit = (1 << 6), + MII_REG_CR_AUTO_NEG = (1 << 12), + MII_REG_CR_AUTO_NEG_RESTART = (1 << 9), + MII_REG_CR_FULLDUPLEX = (1 << 8), +}; + +enum { + MII_REG_ST_100BASE_T4 = (1 << 15), + MII_REG_ST_100BASE_X_FD = (1 << 14), + MII_REG_ST_100BASE_X_HD = (1 << 13), + MII_REG_ST_10_FD = (1 << 12), + MII_REG_ST_10_HD = (1 << 11), + MII_REG_ST_100BASE_T2_FD = (1 << 10), + MII_REG_ST_100BASE_T2_HD = (1 << 9), + MII_REG_ST_AUTONEG_COMPLETE = (1 << 5), + MII_REG_ST_AUTONEG_AVAIL = (1 << 3), + MII_REG_ST_LINK_UP = (1 << 2), +}; + +enum { + MII_REG_LPA_10_HD = (1 << 5), + MII_REG_LPA_10_FD = (1 << 6), + MII_REG_LPA_100_HD = (1 << 7), + MII_REG_LPA_100_FD = (1 << 8), + MII_REG_LPA_PAUSE = (1 << 10), + MII_REG_LPA_ASYMPAUSE = (1 << 11), +}; + +/* MII constants */ +enum { + MII_PHY_ID_HIGH = 0x0044, + MII_PHY_ID_LOW = 0x1400, +}; + +static void allwinner_sun8i_emac_mii_set_link(AwSun8iEmacState *s, + bool link_active) +{ + if (link_active) { + s->mii_st |= MII_REG_ST_LINK_UP; + } else { + s->mii_st &= ~MII_REG_ST_LINK_UP; + } +} + +static void allwinner_sun8i_emac_mii_reset(AwSun8iEmacState *s, + bool link_active) +{ + s->mii_cr = MII_REG_CR_100Mbit | MII_REG_CR_AUTO_NEG | + MII_REG_CR_FULLDUPLEX; + s->mii_st = MII_REG_ST_100BASE_T4 | MII_REG_ST_100BASE_X_FD | + MII_REG_ST_100BASE_X_HD | MII_REG_ST_10_FD | MII_REG_ST_10_HD | + MII_REG_ST_100BASE_T2_FD | MII_REG_ST_100BASE_T2_HD | + MII_REG_ST_AUTONEG_COMPLETE | MII_REG_ST_AUTONEG_AVAIL; + s->mii_adv = 0; + + allwinner_sun8i_emac_mii_set_link(s, link_active); +} + +static void allwinner_sun8i_emac_mii_cmd(AwSun8iEmacState *s) +{ + uint8_t addr, reg; + + addr = (s->mii_cmd & MII_CMD_PHY_ADDR_MASK) >> MII_CMD_PHY_ADDR_SHIFT; + reg = (s->mii_cmd & MII_CMD_PHY_REG_MASK) >> MII_CMD_PHY_REG_SHIFT; + + if (addr != s->mii_phy_addr) { + return; + } + + /* Read or write a PHY register? */ + if (s->mii_cmd & MII_CMD_PHY_RW) { + trace_allwinner_sun8i_emac_mii_write_reg(reg, s->mii_data); + + switch (reg) { + case MII_REG_CR: + if (s->mii_data & MII_REG_CR_RESET) { + allwinner_sun8i_emac_mii_reset(s, s->mii_st & + MII_REG_ST_LINK_UP); + } else { + s->mii_cr = s->mii_data & ~(MII_REG_CR_RESET | + MII_REG_CR_AUTO_NEG_RESTART); + } + break; + case MII_REG_ADV: + s->mii_adv = s->mii_data; + break; + case MII_REG_ID_HIGH: + case MII_REG_ID_LOW: + case MII_REG_LPA: + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: write access to " + "unknown MII register 0x%x\n", reg); + break; + } + } else { + switch (reg) { + case MII_REG_CR: + s->mii_data = s->mii_cr; + break; + case MII_REG_ST: + s->mii_data = s->mii_st; + break; + case MII_REG_ID_HIGH: + s->mii_data = MII_PHY_ID_HIGH; + break; + case MII_REG_ID_LOW: + s->mii_data = MII_PHY_ID_LOW; + break; + case MII_REG_ADV: + s->mii_data = s->mii_adv; + break; + case MII_REG_LPA: + s->mii_data = MII_REG_LPA_10_HD | MII_REG_LPA_10_FD | + MII_REG_LPA_100_HD | MII_REG_LPA_100_FD | + MII_REG_LPA_PAUSE | MII_REG_LPA_ASYMPAUSE; + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: read access to " + "unknown MII register 0x%x\n", reg); + s->mii_data = 0; + break; + } + + trace_allwinner_sun8i_emac_mii_read_reg(reg, s->mii_data); + } +} + +static void allwinner_sun8i_emac_update_irq(AwSun8iEmacState *s) +{ + qemu_set_irq(s->irq, (s->int_sta & s->int_en) != 0); +} + +static uint32_t allwinner_sun8i_emac_next_desc(FrameDescriptor *desc, + size_t min_size) +{ + uint32_t paddr = desc->next; + + cpu_physical_memory_read(paddr, desc, sizeof(*desc)); + + if ((desc->status & DESC_STATUS_CTL) && + (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { + return paddr; + } else { + return 0; + } +} + +static uint32_t allwinner_sun8i_emac_get_desc(FrameDescriptor *desc, + uint32_t start_addr, + size_t min_size) +{ + uint32_t desc_addr = start_addr; + + /* Note that the list is a cycle. Last entry points back to the head. */ + while (desc_addr != 0) { + cpu_physical_memory_read(desc_addr, desc, sizeof(*desc)); + + if ((desc->status & DESC_STATUS_CTL) && + (desc->status2 & DESC_STATUS2_BUF_SIZE_MASK) >= min_size) { + return desc_addr; + } else if (desc->next == start_addr) { + break; + } else { + desc_addr = desc->next; + } + } + + return 0; +} + +static uint32_t allwinner_sun8i_emac_rx_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + size_t min_size) +{ + return allwinner_sun8i_emac_get_desc(desc, s->rx_desc_curr, min_size); +} + +static uint32_t allwinner_sun8i_emac_tx_desc(AwSun8iEmacState *s, + FrameDescriptor *desc, + size_t min_size) +{ + return allwinner_sun8i_emac_get_desc(desc, s->tx_desc_head, min_size); +} + +static void allwinner_sun8i_emac_flush_desc(FrameDescriptor *desc, + uint32_t phys_addr) +{ + cpu_physical_memory_write(phys_addr, desc, sizeof(*desc)); +} + +static int allwinner_sun8i_emac_can_receive(NetClientState *nc) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + FrameDescriptor desc; + + return (s->rx_ctl0 & RX_CTL0_RX_EN) && + (allwinner_sun8i_emac_rx_desc(s, &desc, 0) != 0); +} + +static ssize_t allwinner_sun8i_emac_receive(NetClientState *nc, + const uint8_t *buf, + size_t size) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + FrameDescriptor desc; + size_t bytes_left = size; + size_t desc_bytes = 0; + size_t pad_fcs_size = 4; + size_t padding = 0; + + if (!(s->rx_ctl0 & RX_CTL0_RX_EN)) { + return -1; + } + + s->rx_desc_curr = allwinner_sun8i_emac_rx_desc(s, &desc, + AW_SUN8I_EMAC_MIN_PKT_SZ); + if (!s->rx_desc_curr) { + s->int_sta |= INT_STA_RX_BUF_UA; + } + + /* Keep filling RX descriptors until the whole frame is written */ + while (s->rx_desc_curr && bytes_left > 0) { + desc.status &= ~DESC_STATUS_CTL; + desc.status &= ~RX_DESC_STATUS_FRM_LEN_MASK; + + if (bytes_left == size) { + desc.status |= RX_DESC_STATUS_FIRST_DESC; + } + + if ((desc.status2 & DESC_STATUS2_BUF_SIZE_MASK) < + (bytes_left + pad_fcs_size)) { + desc_bytes = desc.status2 & DESC_STATUS2_BUF_SIZE_MASK; + desc.status |= desc_bytes << RX_DESC_STATUS_FRM_LEN_SHIFT; + } else { + padding = pad_fcs_size; + if (bytes_left < AW_SUN8I_EMAC_MIN_PKT_SZ) { + padding += (AW_SUN8I_EMAC_MIN_PKT_SZ - bytes_left); + } + + desc_bytes = (bytes_left); + desc.status |= RX_DESC_STATUS_LAST_DESC; + desc.status |= (bytes_left + padding) + << RX_DESC_STATUS_FRM_LEN_SHIFT; + } + + cpu_physical_memory_write(desc.addr, buf, desc_bytes); + allwinner_sun8i_emac_flush_desc(&desc, s->rx_desc_curr); + trace_allwinner_sun8i_emac_receive(s->rx_desc_curr, desc.addr, + desc_bytes); + + /* Check if frame needs to raise the receive interrupt */ + if (!(desc.status2 & RX_DESC_STATUS2_RX_INT_CTL)) { + s->int_sta |= INT_STA_RX; + } + + /* Increment variables */ + buf += desc_bytes; + bytes_left -= desc_bytes; + + /* Move to the next descriptor */ + s->rx_desc_curr = allwinner_sun8i_emac_next_desc(&desc, 64); + if (!s->rx_desc_curr) { + /* Not enough buffer space available */ + s->int_sta |= INT_STA_RX_BUF_UA; + s->rx_desc_curr = s->rx_desc_head; + break; + } + } + + /* Report receive DMA is finished */ + s->rx_ctl1 &= ~RX_CTL1_RX_DMA_START; + allwinner_sun8i_emac_update_irq(s); + + return size; +} + +static void allwinner_sun8i_emac_transmit(AwSun8iEmacState *s) +{ + NetClientState *nc = qemu_get_queue(s->nic); + FrameDescriptor desc; + size_t bytes = 0; + size_t packet_bytes = 0; + size_t transmitted = 0; + static uint8_t packet_buf[2048]; + + s->tx_desc_curr = allwinner_sun8i_emac_tx_desc(s, &desc, 0); + + /* Read all transmit descriptors */ + while (s->tx_desc_curr != 0) { + + /* Read from physical memory into packet buffer */ + bytes = desc.status2 & DESC_STATUS2_BUF_SIZE_MASK; + if (bytes + packet_bytes > sizeof(packet_buf)) { + desc.status |= TX_DESC_STATUS_LENGTH_ERR; + break; + } + cpu_physical_memory_read(desc.addr, packet_buf + packet_bytes, bytes); + packet_bytes += bytes; + desc.status &= ~DESC_STATUS_CTL; + allwinner_sun8i_emac_flush_desc(&desc, s->tx_desc_curr); + + /* After the last descriptor, send the packet */ + if (desc.status2 & TX_DESC_STATUS2_LAST_DESC) { + if (desc.status2 & TX_DESC_STATUS2_CHECKSUM_MASK) { + net_checksum_calculate(packet_buf, packet_bytes); + } + + qemu_send_packet(nc, packet_buf, packet_bytes); + trace_allwinner_sun8i_emac_transmit(s->tx_desc_curr, desc.addr, + bytes); + + packet_bytes = 0; + transmitted++; + } + s->tx_desc_curr = allwinner_sun8i_emac_next_desc(&desc, 0); + } + + /* Raise transmit completed interrupt */ + if (transmitted > 0) { + s->int_sta |= INT_STA_TX; + s->tx_ctl1 &= ~TX_CTL1_TX_DMA_START; + allwinner_sun8i_emac_update_irq(s); + } +} + +static void allwinner_sun8i_emac_reset(DeviceState *dev) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(dev); + NetClientState *nc = qemu_get_queue(s->nic); + + trace_allwinner_sun8i_emac_reset(); + + s->mii_cmd = 0; + s->mii_data = 0; + s->basic_ctl0 = 0; + s->basic_ctl1 = REG_BASIC_CTL_1_RST; + s->int_en = 0; + s->int_sta = 0; + s->frm_flt = 0; + s->rx_ctl0 = 0; + s->rx_ctl1 = RX_CTL1_RX_MD; + s->rx_desc_head = 0; + s->rx_desc_curr = 0; + s->tx_ctl0 = 0; + s->tx_ctl1 = 0; + s->tx_desc_head = 0; + s->tx_desc_curr = 0; + s->tx_flowctl = 0; + + allwinner_sun8i_emac_mii_reset(s, !nc->link_down); +} + +static uint64_t allwinner_sun8i_emac_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(opaque); + uint64_t value = 0; + FrameDescriptor desc; + + switch (offset) { + case REG_BASIC_CTL_0: /* Basic Control 0 */ + value = s->basic_ctl0; + break; + case REG_BASIC_CTL_1: /* Basic Control 1 */ + value = s->basic_ctl1; + break; + case REG_INT_STA: /* Interrupt Status */ + value = s->int_sta; + break; + case REG_INT_EN: /* Interupt Enable */ + value = s->int_en; + break; + case REG_TX_CTL_0: /* Transmit Control 0 */ + value = s->tx_ctl0; + break; + case REG_TX_CTL_1: /* Transmit Control 1 */ + value = s->tx_ctl1; + break; + case REG_TX_FLOW_CTL: /* Transmit Flow Control */ + value = s->tx_flowctl; + break; + case REG_TX_DMA_DESC_LIST: /* Transmit Descriptor List Address */ + value = s->tx_desc_head; + break; + case REG_RX_CTL_0: /* Receive Control 0 */ + value = s->rx_ctl0; + break; + case REG_RX_CTL_1: /* Receive Control 1 */ + value = s->rx_ctl1; + break; + case REG_RX_DMA_DESC_LIST: /* Receive Descriptor List Address */ + value = s->rx_desc_head; + break; + case REG_FRM_FLT: /* Receive Frame Filter */ + value = s->frm_flt; + break; + case REG_RX_HASH_0: /* Receive Hash Table 0 */ + case REG_RX_HASH_1: /* Receive Hash Table 1 */ + break; + case REG_MII_CMD: /* Management Interface Command */ + value = s->mii_cmd; + break; + case REG_MII_DATA: /* Management Interface Data */ + value = s->mii_data; + break; + case REG_ADDR_HIGH: /* MAC Address High */ + value = *(((uint32_t *) (s->conf.macaddr.a)) + 1); + break; + case REG_ADDR_LOW: /* MAC Address Low */ + value = *(uint32_t *) (s->conf.macaddr.a); + break; + case REG_TX_DMA_STA: /* Transmit DMA Status */ + break; + case REG_TX_CUR_DESC: /* Transmit Current Descriptor */ + value = s->tx_desc_curr; + break; + case REG_TX_CUR_BUF: /* Transmit Current Buffer */ + if (s->tx_desc_curr != 0) { + cpu_physical_memory_read(s->tx_desc_curr, &desc, sizeof(desc)); + value = desc.addr; + } else { + value = 0; + } + break; + case REG_RX_DMA_STA: /* Receive DMA Status */ + break; + case REG_RX_CUR_DESC: /* Receive Current Descriptor */ + value = s->rx_desc_curr; + break; + case REG_RX_CUR_BUF: /* Receive Current Buffer */ + if (s->rx_desc_curr != 0) { + cpu_physical_memory_read(s->rx_desc_curr, &desc, sizeof(desc)); + value = desc.addr; + } else { + value = 0; + } + break; + case REG_RGMII_STA: /* RGMII Status */ + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: read access to unknown " + "EMAC register 0x" TARGET_FMT_plx "\n", + offset); + } + + trace_allwinner_sun8i_emac_read(offset, value); + return value; +} + +static void allwinner_sun8i_emac_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(opaque); + NetClientState *nc = qemu_get_queue(s->nic); + + trace_allwinner_sun8i_emac_write(offset, value); + + switch (offset) { + case REG_BASIC_CTL_0: /* Basic Control 0 */ + s->basic_ctl0 = value; + break; + case REG_BASIC_CTL_1: /* Basic Control 1 */ + if (value & BASIC_CTL1_SOFTRST) { + allwinner_sun8i_emac_reset(DEVICE(s)); + value &= ~BASIC_CTL1_SOFTRST; + } + s->basic_ctl1 = value; + if (allwinner_sun8i_emac_can_receive(nc)) { + qemu_flush_queued_packets(nc); + } + break; + case REG_INT_STA: /* Interrupt Status */ + s->int_sta &= ~value; + allwinner_sun8i_emac_update_irq(s); + break; + case REG_INT_EN: /* Interrupt Enable */ + s->int_en = value; + allwinner_sun8i_emac_update_irq(s); + break; + case REG_TX_CTL_0: /* Transmit Control 0 */ + s->tx_ctl0 = value; + break; + case REG_TX_CTL_1: /* Transmit Control 1 */ + s->tx_ctl1 = value; + if (value & TX_CTL1_TX_DMA_EN) { + allwinner_sun8i_emac_transmit(s); + } + break; + case REG_TX_FLOW_CTL: /* Transmit Flow Control */ + s->tx_flowctl = value; + break; + case REG_TX_DMA_DESC_LIST: /* Transmit Descriptor List Address */ + s->tx_desc_head = value; + s->tx_desc_curr = value; + break; + case REG_RX_CTL_0: /* Receive Control 0 */ + s->rx_ctl0 = value; + break; + case REG_RX_CTL_1: /* Receive Control 1 */ + s->rx_ctl1 = value | RX_CTL1_RX_MD; + if ((value & RX_CTL1_RX_DMA_EN) && + allwinner_sun8i_emac_can_receive(nc)) { + qemu_flush_queued_packets(nc); + } + break; + case REG_RX_DMA_DESC_LIST: /* Receive Descriptor List Address */ + s->rx_desc_head = value; + s->rx_desc_curr = value; + break; + case REG_FRM_FLT: /* Receive Frame Filter */ + s->frm_flt = value; + break; + case REG_RX_HASH_0: /* Receive Hash Table 0 */ + case REG_RX_HASH_1: /* Receive Hash Table 1 */ + break; + case REG_MII_CMD: /* Management Interface Command */ + s->mii_cmd = value & ~MII_CMD_PHY_BUSY; + allwinner_sun8i_emac_mii_cmd(s); + break; + case REG_MII_DATA: /* Management Interface Data */ + s->mii_data = value; + break; + case REG_ADDR_HIGH: /* MAC Address High */ + s->conf.macaddr.a[4] = (value & 0xff); + s->conf.macaddr.a[5] = (value & 0xff00) >> 8; + break; + case REG_ADDR_LOW: /* MAC Address Low */ + s->conf.macaddr.a[0] = (value & 0xff); + s->conf.macaddr.a[1] = (value & 0xff00) >> 8; + s->conf.macaddr.a[2] = (value & 0xff0000) >> 16; + s->conf.macaddr.a[3] = (value & 0xff000000) >> 24; + break; + case REG_TX_DMA_STA: /* Transmit DMA Status */ + case REG_TX_CUR_DESC: /* Transmit Current Descriptor */ + case REG_TX_CUR_BUF: /* Transmit Current Buffer */ + case REG_RX_DMA_STA: /* Receive DMA Status */ + case REG_RX_CUR_DESC: /* Receive Current Descriptor */ + case REG_RX_CUR_BUF: /* Receive Current Buffer */ + case REG_RGMII_STA: /* RGMII Status */ + break; + default: + qemu_log_mask(LOG_UNIMP, "allwinner-h3-emac: write access to unknown " + "EMAC register 0x" TARGET_FMT_plx "\n", + offset); + } +} + +static void allwinner_sun8i_emac_set_link(NetClientState *nc) +{ + AwSun8iEmacState *s = qemu_get_nic_opaque(nc); + + trace_allwinner_sun8i_emac_set_link(!nc->link_down); + allwinner_sun8i_emac_mii_set_link(s, !nc->link_down); +} + +static const MemoryRegionOps allwinner_sun8i_emac_mem_ops = { + .read = allwinner_sun8i_emac_read, + .write = allwinner_sun8i_emac_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static NetClientInfo net_allwinner_sun8i_emac_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = allwinner_sun8i_emac_can_receive, + .receive = allwinner_sun8i_emac_receive, + .link_status_changed = allwinner_sun8i_emac_set_link, +}; + +static void allwinner_sun8i_emac_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwSun8iEmacState *s = AW_SUN8I_EMAC(obj); + + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_sun8i_emac_mem_ops, + s, TYPE_AW_SUN8I_EMAC, 64 * KiB); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(sbd, &s->irq); +} + +static void allwinner_sun8i_emac_realize(DeviceState *dev, Error **errp) +{ + AwSun8iEmacState *s = AW_SUN8I_EMAC(dev); + + qemu_macaddr_default_if_unset(&s->conf.macaddr); + s->nic = qemu_new_nic(&net_allwinner_sun8i_emac_info, &s->conf, + object_get_typename(OBJECT(dev)), dev->id, s); + qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); +} + +static Property allwinner_sun8i_emac_properties[] = { + DEFINE_NIC_PROPERTIES(AwSun8iEmacState, conf), + DEFINE_PROP_UINT8("phy-addr", AwSun8iEmacState, mii_phy_addr, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static int allwinner_sun8i_emac_post_load(void *opaque, int version_id) +{ + AwSun8iEmacState *s = opaque; + + allwinner_sun8i_emac_set_link(qemu_get_queue(s->nic)); + + return 0; +} + +static const VMStateDescription vmstate_aw_emac = { + .name = "allwinner-sun8i-emac", + .version_id = 1, + .minimum_version_id = 1, + .post_load = allwinner_sun8i_emac_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT8(mii_phy_addr, AwSun8iEmacState), + VMSTATE_UINT32(mii_cmd, AwSun8iEmacState), + VMSTATE_UINT32(mii_data, AwSun8iEmacState), + VMSTATE_UINT32(mii_cr, AwSun8iEmacState), + VMSTATE_UINT32(mii_st, AwSun8iEmacState), + VMSTATE_UINT32(mii_adv, AwSun8iEmacState), + VMSTATE_UINT32(basic_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(basic_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(int_en, AwSun8iEmacState), + VMSTATE_UINT32(int_sta, AwSun8iEmacState), + VMSTATE_UINT32(frm_flt, AwSun8iEmacState), + VMSTATE_UINT32(rx_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(rx_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(rx_desc_head, AwSun8iEmacState), + VMSTATE_UINT32(rx_desc_curr, AwSun8iEmacState), + VMSTATE_UINT32(tx_ctl0, AwSun8iEmacState), + VMSTATE_UINT32(tx_ctl1, AwSun8iEmacState), + VMSTATE_UINT32(tx_desc_head, AwSun8iEmacState), + VMSTATE_UINT32(tx_desc_curr, AwSun8iEmacState), + VMSTATE_UINT32(tx_flowctl, AwSun8iEmacState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_sun8i_emac_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = allwinner_sun8i_emac_realize; + dc->reset = allwinner_sun8i_emac_reset; + dc->vmsd = &vmstate_aw_emac; + device_class_set_props(dc, allwinner_sun8i_emac_properties); +} + +static const TypeInfo allwinner_sun8i_emac_info = { + .name = TYPE_AW_SUN8I_EMAC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AwSun8iEmacState), + .instance_init = allwinner_sun8i_emac_init, + .class_init = allwinner_sun8i_emac_class_init, +}; + +static void allwinner_sun8i_emac_register_types(void) +{ + type_register_static(&allwinner_sun8i_emac_info); +} + +type_init(allwinner_sun8i_emac_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 config ALLWINNER_H3 bool select ALLWINNER_A10_PIT + select ALLWINNER_SUN8I_EMAC select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config MIPSNET config ALLWINNER_EMAC bool +config ALLWINNER_SUN8I_EMAC + bool + config IMX_FEC bool diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-sun8i-emac.c +allwinner_sun8i_emac_mii_write_reg(uint32_t reg, uint32_t value) "MII write: reg=0x%" PRIx32 " value=0x%" PRIx32 +allwinner_sun8i_emac_mii_read_reg(uint32_t reg, uint32_t value) "MII read: reg=0x%" PRIx32 " value=0x%" PRIx32 +allwinner_sun8i_emac_receive(uint32_t desc, uint32_t paddr, uint32_t bytes) "RX packet: desc=0x%" PRIx32 " paddr=0x%" PRIx32 " bytes=%" PRIu32 +allwinner_sun8i_emac_transmit(uint32_t desc, uint32_t paddr, uint32_t bytes) "TX packet: desc=0x%" PRIx32 " paddr=0x%" PRIx32 " bytes=%" PRIu32 +allwinner_sun8i_emac_reset(void) "HW reset" +allwinner_sun8i_emac_set_link(bool active) "Set link: active=%u" +allwinner_sun8i_emac_read(uint64_t offset, uint64_t val) "MMIO read: offset=0x%" PRIx64 " value=0x%" PRIx64 +allwinner_sun8i_emac_write(uint64_t offset, uint64_t val) "MMIO write: offset=0x%" PRIx64 " value=0x%" PRIx64 + # etraxfs_eth.c mdio_phy_read(int regnum, uint16_t value) "read phy_reg:%d value:0x%04x" mdio_phy_write(int regnum, uint16_t value) "write phy_reg:%d value:0x%04x" -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> A real Allwinner H3 SoC contains a Boot ROM which is the first code that runs right after the SoC is powered on. The Boot ROM is responsible for loading user code (e.g. a bootloader) from any of the supported external devices and writing the downloaded code to internal SRAM. After loading the SoC begins executing the code written to SRAM. This commits adds emulation of the Boot ROM firmware setup functionality by loading user code from SD card in the A1 SRAM. While the A1 SRAM is 64KiB, we limit the size to 32KiB because the real H3 Boot ROM also rejects sizes larger than 32KiB. For reference, this behaviour is documented by the Linux Sunxi project wiki at: https://linux-sunxi.org/BROM#U-Boot_SPL_limitations Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-11-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-h3.h | 21 +++++++++++++++++++++ hw/arm/allwinner-h3.c | 17 +++++++++++++++++ hw/arm/orangepi.c | 5 +++++ 3 files changed, 43 insertions(+) diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" #include "target/arm/cpu.h" +#include "sysemu/block-backend.h" /** * Allwinner H3 device list @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { MemoryRegion sram_c; } AwH3State; +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner H3 SoC contains a Boot ROM + * which is the first code that runs right after + * the SoC is powered on. The Boot ROM is responsible + * for loading user code (e.g. a bootloader) from any + * of the supported external devices and writing the + * downloaded code to internal SRAM. After loading the SoC + * begins executing the code written to SRAM. + * + * This function emulates the Boot ROM by copying 32 KiB + * of data from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner H3 state object pointer + * @blk: Block backend device object pointer + */ +void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk); + #endif /* HW_ARM_ALLWINNER_H3_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/serial.h" #include "hw/misc/unimp.h" #include "hw/usb/hcd-ehci.h" +#include "hw/loader.h" #include "sysemu/sysemu.h" #include "hw/arm/allwinner-h3.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_NUM_SPI = 128 }; +void allwinner_h3_bootrom_setup(AwH3State *s, BlockBackend *blk) +{ + const int64_t rom_size = 32 * KiB; + g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); + + if (blk_pread(blk, 8 * KiB, buffer, rom_size) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return; + } + + rom_add_blob("allwinner-h3.bootrom", buffer, rom_size, + rom_size, s->memmap[AW_H3_SRAM_A1], + NULL, NULL, NULL, NULL, false); +} + static void allwinner_h3_init(Object *obj) { AwH3State *s = AW_H3(obj); diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), h3->memmap[AW_H3_SDRAM], machine->ram); + /* Load target kernel or start using BootROM */ + if (!machine->kernel_filename && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + allwinner_h3_bootrom_setup(h3, blk); + } orangepi_binfo.loader_start = h3->memmap[AW_H3_SDRAM]; orangepi_binfo.ram_size = machine->ram_size; arm_load_kernel(ARM_CPU(first_cpu), machine, &orangepi_binfo); -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> In the Allwinner H3 SoC the SDRAM controller is responsible for interfacing with the external Synchronous Dynamic Random Access Memory (SDRAM). Types of memory that the SDRAM controller supports are DDR2/DDR3 and capacities of up to 2GiB. This commit adds emulation support of the Allwinner H3 SDRAM controller. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-12-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/Makefile.objs | 1 + include/hw/arm/allwinner-h3.h | 5 + include/hw/misc/allwinner-h3-dramc.h | 106 ++++++++ hw/arm/allwinner-h3.c | 19 +- hw/arm/orangepi.c | 6 + hw/misc/allwinner-h3-dramc.c | 358 +++++++++++++++++++++++++++ hw/misc/trace-events | 10 + 7 files changed, 502 insertions(+), 3 deletions(-) create mode 100644 include/hw/misc/allwinner-h3-dramc.h create mode 100644 hw/misc/allwinner-h3-dramc.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_IVSHMEM_DEVICE) += ivshmem.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-ccu.o obj-$(CONFIG_ALLWINNER_H3) += allwinner-cpucfg.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-dramc.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-h3-sysctrl.o common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-sid.o common-obj-$(CONFIG_REALVIEW) += arm_sysctl.o diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/misc/allwinner-h3-ccu.h" #include "hw/misc/allwinner-cpucfg.h" +#include "hw/misc/allwinner-h3-dramc.h" #include "hw/misc/allwinner-h3-sysctrl.h" #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_UART2, AW_H3_UART3, AW_H3_EMAC, + AW_H3_DRAMCOM, + AW_H3_DRAMCTL, + AW_H3_DRAMPHY, AW_H3_GIC_DIST, AW_H3_GIC_CPU, AW_H3_GIC_HYP, @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwA10PITState timer; AwH3ClockCtlState ccu; AwCpuCfgState cpucfg; + AwH3DramCtlState dramc; AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; diff --git a/include/hw/misc/allwinner-h3-dramc.h b/include/hw/misc/allwinner-h3-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-h3-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 SDRAM Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_H3_DRAMC_H +#define HW_MISC_ALLWINNER_H3_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "exec/hwaddr.h" + +/** + * Constants + * @{ + */ + +/** Highest register address used by DRAMCOM module */ +#define AW_H3_DRAMCOM_REGS_MAXADDR (0x804) + +/** Total number of known DRAMCOM registers */ +#define AW_H3_DRAMCOM_REGS_NUM (AW_H3_DRAMCOM_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMCTL module */ +#define AW_H3_DRAMCTL_REGS_MAXADDR (0x88c) + +/** Total number of known DRAMCTL registers */ +#define AW_H3_DRAMCTL_REGS_NUM (AW_H3_DRAMCTL_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** Highest register address used by DRAMPHY module */ +#define AW_H3_DRAMPHY_REGS_MAXADDR (0x4) + +/** Total number of known DRAMPHY registers */ +#define AW_H3_DRAMPHY_REGS_NUM (AW_H3_DRAMPHY_REGS_MAXADDR / \ + sizeof(uint32_t)) + +/** @} */ + +/** + * Object model + * @{ + */ + +#define TYPE_AW_H3_DRAMC "allwinner-h3-dramc" +#define AW_H3_DRAMC(obj) \ + OBJECT_CHECK(AwH3DramCtlState, (obj), TYPE_AW_H3_DRAMC) + +/** @} */ + +/** + * Allwinner H3 SDRAM Controller object instance state. + */ +typedef struct AwH3DramCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Physical base address for start of RAM */ + hwaddr ram_addr; + + /** Total RAM size in megabytes */ + uint32_t ram_size; + + /** + * @name Memory Regions + * @{ + */ + + MemoryRegion row_mirror; /**< Simulates rows for RAM size detection */ + MemoryRegion row_mirror_alias; /**< Alias of the row which is mirrored */ + MemoryRegion dramcom_iomem; /**< DRAMCOM module I/O registers */ + MemoryRegion dramctl_iomem; /**< DRAMCTL module I/O registers */ + MemoryRegion dramphy_iomem; /**< DRAMPHY module I/O registers */ + + /** @} */ + + /** + * @name Hardware Registers + * @{ + */ + + uint32_t dramcom[AW_H3_DRAMCOM_REGS_NUM]; /**< Array of DRAMCOM registers */ + uint32_t dramctl[AW_H3_DRAMCTL_REGS_NUM]; /**< Array of DRAMCTL registers */ + uint32_t dramphy[AW_H3_DRAMPHY_REGS_NUM] ;/**< Array of DRAMPHY registers */ + + /** @} */ + +} AwH3DramCtlState; + +#endif /* HW_MISC_ALLWINNER_H3_DRAMC_H */ diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_UART2] = 0x01c28800, [AW_H3_UART3] = 0x01c28c00, [AW_H3_EMAC] = 0x01c30000, + [AW_H3_DRAMCOM] = 0x01c62000, + [AW_H3_DRAMCTL] = 0x01c63000, + [AW_H3_DRAMPHY] = 0x01c65000, [AW_H3_GIC_DIST] = 0x01c81000, [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "scr", 0x01c2c400, 1 * KiB }, { "gpu", 0x01c40000, 64 * KiB }, { "hstmr", 0x01c60000, 4 * KiB }, - { "dramcom", 0x01c62000, 4 * KiB }, - { "dramctl0", 0x01c63000, 4 * KiB }, - { "dramphy0", 0x01c65000, 4 * KiB }, { "spi0", 0x01c68000, 4 * KiB }, { "spi1", 0x01c69000, 4 * KiB }, { "csi", 0x01cb0000, 320 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) sysbus_init_child_obj(obj, "emac", &s->emac, sizeof(s->emac), TYPE_AW_SUN8I_EMAC); + + sysbus_init_child_obj(obj, "dramc", &s->dramc, sizeof(s->dramc), + TYPE_AW_H3_DRAMC); + object_property_add_alias(obj, "ram-addr", OBJECT(&s->dramc), + "ram-addr", &error_abort); + object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), + "ram-size", &error_abort); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_UART3), 115200, serial_hd(3), DEVICE_NATIVE_ENDIAN); + /* DRAMC */ + qdev_init_nofail(DEVICE(&s->dramc)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, s->memmap[AW_H3_DRAMCOM]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 1, s->memmap[AW_H3_DRAMCTL]); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, s->memmap[AW_H3_DRAMPHY]); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/arm/orangepi.c b/hw/arm/orangepi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/orangepi.c +++ b/hw/arm/orangepi.c @@ -XXX,XX +XXX,XX @@ static void orangepi_init(MachineState *machine) /* Setup EMAC properties */ object_property_set_int(OBJECT(&h3->emac), 1, "phy-addr", &error_abort); + /* DRAMC */ + object_property_set_uint(OBJECT(h3), h3->memmap[AW_H3_SDRAM], + "ram-addr", &error_abort); + object_property_set_int(OBJECT(h3), machine->ram_size / MiB, "ram-size", + &error_abort); + /* Mark H3 object realized */ object_property_set_bool(OBJECT(h3), true, "realized", &error_abort); diff --git a/hw/misc/allwinner-h3-dramc.c b/hw/misc/allwinner-h3-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-h3-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner H3 SDRAM Controller emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "qemu/error-report.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "exec/address-spaces.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" +#include "hw/misc/allwinner-h3-dramc.h" +#include "trace.h" + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMCOM register offsets */ +enum { + REG_DRAMCOM_CR = 0x0000, /* Control Register */ +}; + +/* DRAMCTL register offsets */ +enum { + REG_DRAMCTL_PIR = 0x0000, /* PHY Initialization Register */ + REG_DRAMCTL_PGSR = 0x0010, /* PHY General Status Register */ + REG_DRAMCTL_STATR = 0x0018, /* Status Register */ +}; + +/* DRAMCTL register flags */ +enum { + REG_DRAMCTL_PGSR_INITDONE = (1 << 0), +}; + +enum { + REG_DRAMCTL_STATR_ACTIVE = (1 << 0), +}; + +static void allwinner_h3_dramc_map_rows(AwH3DramCtlState *s, uint8_t row_bits, + uint8_t bank_bits, uint16_t page_size) +{ + /* + * This function simulates row addressing behavior when bootloader + * software attempts to detect the amount of available SDRAM. In U-Boot + * the controller is configured with the widest row addressing available. + * Then a pattern is written to RAM at an offset on the row boundary size. + * If the value read back equals the value read back from the + * start of RAM, the bootloader knows the amount of row bits. + * + * This function inserts a mirrored memory region when the configured row + * bits are not matching the actual emulated memory, to simulate the + * same behavior on hardware as expected by the bootloader. + */ + uint8_t row_bits_actual = 0; + + /* Calculate the actual row bits using the ram_size property */ + for (uint8_t i = 8; i < 12; i++) { + if (1 << i == s->ram_size) { + row_bits_actual = i + 3; + break; + } + } + + if (s->ram_size == (1 << (row_bits - 3))) { + /* When row bits is the expected value, remove the mirror */ + memory_region_set_enabled(&s->row_mirror_alias, false); + trace_allwinner_h3_dramc_rowmirror_disable(); + + } else if (row_bits_actual) { + /* Row bits not matching ram_size, install the rows mirror */ + hwaddr row_mirror = s->ram_addr + ((1 << (row_bits_actual + + bank_bits)) * page_size); + + memory_region_set_enabled(&s->row_mirror_alias, true); + memory_region_set_address(&s->row_mirror_alias, row_mirror); + + trace_allwinner_h3_dramc_rowmirror_enable(row_mirror); + } +} + +static uint64_t allwinner_h3_dramcom_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramcom_read(offset, s->dramcom[idx], size); + + return s->dramcom[idx]; +} + +static void allwinner_h3_dramcom_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramcom_write(offset, val, size); + + if (idx >= AW_H3_DRAMCOM_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCOM_CR: /* Control Register */ + allwinner_h3_dramc_map_rows(s, ((val >> 4) & 0xf) + 1, + ((val >> 2) & 0x1) + 2, + 1 << (((val >> 8) & 0xf) + 3)); + break; + default: + break; + }; + + s->dramcom[idx] = (uint32_t) val; +} + +static uint64_t allwinner_h3_dramctl_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramctl_read(offset, s->dramctl[idx], size); + + return s->dramctl[idx]; +} + +static void allwinner_h3_dramctl_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramctl_write(offset, val, size); + + if (idx >= AW_H3_DRAMCTL_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + switch (offset) { + case REG_DRAMCTL_PIR: /* PHY Initialization Register */ + s->dramctl[REG_INDEX(REG_DRAMCTL_PGSR)] |= REG_DRAMCTL_PGSR_INITDONE; + s->dramctl[REG_INDEX(REG_DRAMCTL_STATR)] |= REG_DRAMCTL_STATR_ACTIVE; + break; + default: + break; + } + + s->dramctl[idx] = (uint32_t) val; +} + +static uint64_t allwinner_h3_dramphy_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + if (idx >= AW_H3_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + trace_allwinner_h3_dramphy_read(offset, s->dramphy[idx], size); + + return s->dramphy[idx]; +} + +static void allwinner_h3_dramphy_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + trace_allwinner_h3_dramphy_write(offset, val, size); + + if (idx >= AW_H3_DRAMPHY_REGS_NUM) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + s->dramphy[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_h3_dramcom_ops = { + .read = allwinner_h3_dramcom_read, + .write = allwinner_h3_dramcom_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_h3_dramctl_ops = { + .read = allwinner_h3_dramctl_read, + .write = allwinner_h3_dramctl_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static const MemoryRegionOps allwinner_h3_dramphy_ops = { + .read = allwinner_h3_dramphy_read, + .write = allwinner_h3_dramphy_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_h3_dramc_reset(DeviceState *dev) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(dev); + + /* Set default values for registers */ + memset(&s->dramcom, 0, sizeof(s->dramcom)); + memset(&s->dramctl, 0, sizeof(s->dramctl)); + memset(&s->dramphy, 0, sizeof(s->dramphy)); +} + +static void allwinner_h3_dramc_realize(DeviceState *dev, Error **errp) +{ + AwH3DramCtlState *s = AW_H3_DRAMC(dev); + + /* Only power of 2 RAM sizes from 256MiB up to 2048MiB are supported */ + for (uint8_t i = 8; i < 13; i++) { + if (1 << i == s->ram_size) { + break; + } else if (i == 12) { + error_report("%s: ram-size %u MiB is not supported", + __func__, s->ram_size); + exit(1); + } + } + + /* Setup row mirror mappings */ + memory_region_init_ram(&s->row_mirror, OBJECT(s), + "allwinner-h3-dramc.row-mirror", + 4 * KiB, &error_abort); + memory_region_add_subregion_overlap(get_system_memory(), s->ram_addr, + &s->row_mirror, 10); + + memory_region_init_alias(&s->row_mirror_alias, OBJECT(s), + "allwinner-h3-dramc.row-mirror-alias", + &s->row_mirror, 0, 4 * KiB); + memory_region_add_subregion_overlap(get_system_memory(), + s->ram_addr + 1 * MiB, + &s->row_mirror_alias, 10); + memory_region_set_enabled(&s->row_mirror_alias, false); +} + +static void allwinner_h3_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwH3DramCtlState *s = AW_H3_DRAMC(obj); + + /* DRAMCOM registers */ + memory_region_init_io(&s->dramcom_iomem, OBJECT(s), + &allwinner_h3_dramcom_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramcom_iomem); + + /* DRAMCTL registers */ + memory_region_init_io(&s->dramctl_iomem, OBJECT(s), + &allwinner_h3_dramctl_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramctl_iomem); + + /* DRAMPHY registers */ + memory_region_init_io(&s->dramphy_iomem, OBJECT(s), + &allwinner_h3_dramphy_ops, s, + TYPE_AW_H3_DRAMC, 4 * KiB); + sysbus_init_mmio(sbd, &s->dramphy_iomem); +} + +static Property allwinner_h3_dramc_properties[] = { + DEFINE_PROP_UINT64("ram-addr", AwH3DramCtlState, ram_addr, 0x0), + DEFINE_PROP_UINT32("ram-size", AwH3DramCtlState, ram_size, 256 * MiB), + DEFINE_PROP_END_OF_LIST() +}; + +static const VMStateDescription allwinner_h3_dramc_vmstate = { + .name = "allwinner-h3-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(dramcom, AwH3DramCtlState, AW_H3_DRAMCOM_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramctl, AwH3DramCtlState, AW_H3_DRAMCTL_REGS_NUM), + VMSTATE_UINT32_ARRAY(dramphy, AwH3DramCtlState, AW_H3_DRAMPHY_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_h3_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_h3_dramc_reset; + dc->vmsd = &allwinner_h3_dramc_vmstate; + dc->realize = allwinner_h3_dramc_realize; + device_class_set_props(dc, allwinner_h3_dramc_properties); +} + +static const TypeInfo allwinner_h3_dramc_info = { + .name = TYPE_AW_H3_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_h3_dramc_init, + .instance_size = sizeof(AwH3DramCtlState), + .class_init = allwinner_h3_dramc_class_init, +}; + +static void allwinner_h3_dramc_register(void) +{ + type_register_static(&allwinner_h3_dramc_info); +} + +type_init(allwinner_h3_dramc_register) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_cpucfg_cpu_reset(uint8_t cpu_id, uint32_t reset_addr) "id %u, reset_ad allwinner_cpucfg_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_cpucfg_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +# allwinner-h3-dramc.c +allwinner_h3_dramc_rowmirror_disable(void) "Disable row mirror" +allwinner_h3_dramc_rowmirror_enable(uint64_t addr) "Enable row mirror: addr 0x%" PRIx64 +allwinner_h3_dramcom_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramcom_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramctl_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramctl_write(uint64_t offset, uint64_t data, unsigned size) "Write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramphy_read(uint64_t offset, uint64_t data, unsigned size) "Read: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 +allwinner_h3_dramphy_write(uint64_t offset, uint64_t data, unsigned size) "write: offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 + # allwinner-sid.c allwinner_sid_read(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" PRIx64 " data 0x%" PRIx64 " size %" PRIu32 -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> Allwinner System-on-Chips usually contain a Real Time Clock (RTC) for non-volatile system date and time keeping. This commit adds a generic Allwinner RTC device that supports the RTC devices found in Allwinner SoC family sun4i (A10), sun7i (A20) and sun6i and newer (A31, H2+, H3, etc). The following RTC functionality and features are implemented: * Year-Month-Day read/write * Hour-Minute-Second read/write * General Purpose storage The following boards are extended with the RTC device: * Cubieboard (hw/arm/cubieboard.c) * Orange Pi PC (hw/arm/orangepi.c) Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-13-nieklinnenbank@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/rtc/Makefile.objs | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/rtc/allwinner-rtc.h | 134 +++++++++++ hw/arm/allwinner-a10.c | 8 + hw/arm/allwinner-h3.c | 9 +- hw/rtc/allwinner-rtc.c | 411 +++++++++++++++++++++++++++++++++ hw/rtc/trace-events | 4 + 8 files changed, 571 insertions(+), 1 deletion(-) create mode 100644 include/hw/rtc/allwinner-rtc.h create mode 100644 hw/rtc/allwinner-rtc.c diff --git a/hw/rtc/Makefile.objs b/hw/rtc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/Makefile.objs +++ b/hw/rtc/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_MC146818RTC) += mc146818rtc.o common-obj-$(CONFIG_SUN4V_RTC) += sun4v-rtc.o common-obj-$(CONFIG_ASPEED_SOC) += aspeed_rtc.o common-obj-$(CONFIG_GOLDFISH_RTC) += goldfish_rtc.o +common-obj-$(CONFIG_ALLWINNER_H3) += allwinner-rtc.o diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/ide/ahci.h" #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" +#include "hw/rtc/allwinner-rtc.h" #include "target/arm/cpu.h" @@ -XXX,XX +XXX,XX @@ typedef struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; AwSdHostState mmc0; + AwRtcState rtc; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; OHCISysBusState ohci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-sid.h" #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" +#include "hw/rtc/allwinner-rtc.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_CPU, AW_H3_GIC_HYP, AW_H3_GIC_VCPU, + AW_H3_RTC, AW_H3_CPUCFG, AW_H3_SDRAM }; @@ -XXX,XX +XXX,XX @@ typedef struct AwH3State { AwSidState sid; AwSdHostState mmc0; AwSun8iEmacState emac; + AwRtcState rtc; GICState gic; MemoryRegion sram_a1; MemoryRegion sram_a2; diff --git a/include/hw/rtc/allwinner-rtc.h b/include/hw/rtc/allwinner-rtc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/rtc/allwinner-rtc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Real Time Clock emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_RTC_H +#define HW_MISC_ALLWINNER_RTC_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * Constants + * @{ + */ + +/** Highest register address used by RTC device */ +#define AW_RTC_REGS_MAXADDR (0x200) + +/** Total number of known registers */ +#define AW_RTC_REGS_NUM (AW_RTC_REGS_MAXADDR / sizeof(uint32_t)) + +/** @} */ + +/** + * Object model types + * @{ + */ + +/** Generic Allwinner RTC device (abstract) */ +#define TYPE_AW_RTC "allwinner-rtc" + +/** Allwinner RTC sun4i family (A10, A12) */ +#define TYPE_AW_RTC_SUN4I TYPE_AW_RTC "-sun4i" + +/** Allwinner RTC sun6i family and newer (A31, H2+, H3, etc) */ +#define TYPE_AW_RTC_SUN6I TYPE_AW_RTC "-sun6i" + +/** Allwinner RTC sun7i family (A20) */ +#define TYPE_AW_RTC_SUN7I TYPE_AW_RTC "-sun7i" + +/** @} */ + +/** + * Object model macros + * @{ + */ + +#define AW_RTC(obj) \ + OBJECT_CHECK(AwRtcState, (obj), TYPE_AW_RTC) +#define AW_RTC_CLASS(klass) \ + OBJECT_CLASS_CHECK(AwRtcClass, (klass), TYPE_AW_RTC) +#define AW_RTC_GET_CLASS(obj) \ + OBJECT_GET_CLASS(AwRtcClass, (obj), TYPE_AW_RTC) + +/** @} */ + +/** + * Allwinner RTC per-object instance state. + */ +typedef struct AwRtcState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** + * Actual year represented by the device when year counter is zero + * + * Can be overridden by the user using the corresponding 'base-year' + * property. The base year used by the target OS driver can vary, for + * example the Linux driver for sun6i uses 1970 while NetBSD uses 2000. + */ + int base_year; + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_RTC_REGS_NUM]; + +} AwRtcState; + +/** + * Allwinner RTC class-level struct. + * + * This struct is filled by each sunxi device specific code + * such that the generic code can use this struct to support + * all devices. + */ +typedef struct AwRtcClass { + /*< private >*/ + SysBusDeviceClass parent_class; + /*< public >*/ + + /** Defines device specific register map */ + const uint8_t *regmap; + + /** Size of the regmap in bytes */ + size_t regmap_size; + + /** + * Read device specific register + * + * @offset: register offset to read + * @return true if register read successful, false otherwise + */ + bool (*read)(AwRtcState *s, uint32_t offset); + + /** + * Write device specific register + * + * @offset: register offset to write + * @data: value to set in register + * @return true if register write successful, false otherwise + */ + bool (*write)(AwRtcState *s, uint32_t offset, uint32_t data); + +} AwRtcClass; + +#endif /* HW_MISC_ALLWINNER_RTC_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #define AW_A10_EHCI_BASE 0x01c14000 #define AW_A10_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 +#define AW_A10_RTC_BASE 0x01c20d00 static void aw_a10_init(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) sysbus_init_child_obj(obj, "mmc0", &s->mmc0, sizeof(s->mmc0), TYPE_AW_SDHOST_SUN4I); + + sysbus_init_child_obj(obj, "rtc", &s->rtc, sizeof(s->rtc), + TYPE_AW_RTC_SUN4I); } static void aw_a10_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->mmc0), 0, qdev_get_gpio_in(dev, 32)); object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->mmc0), "sd-bus", &error_abort); + + /* RTC */ + qdev_init_nofail(DEVICE(&s->rtc)); + sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->rtc), 0, AW_A10_RTC_BASE, 10); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_GIC_CPU] = 0x01c82000, [AW_H3_GIC_HYP] = 0x01c84000, [AW_H3_GIC_VCPU] = 0x01c86000, + [AW_H3_RTC] = 0x01f00000, [AW_H3_CPUCFG] = 0x01f01c00, [AW_H3_SDRAM] = 0x40000000 }; @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "csi", 0x01cb0000, 320 * KiB }, { "tve", 0x01e00000, 64 * KiB }, { "hdmi", 0x01ee0000, 128 * KiB }, - { "rtc", 0x01f00000, 1 * KiB }, { "r_timer", 0x01f00800, 1 * KiB }, { "r_intc", 0x01f00c00, 1 * KiB }, { "r_wdog", 0x01f01000, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "ram-addr", &error_abort); object_property_add_alias(obj, "ram-size", OBJECT(&s->dramc), "ram-size", &error_abort); + + sysbus_init_child_obj(obj, "rtc", &s->rtc, sizeof(s->rtc), + TYPE_AW_RTC_SUN6I); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 1, s->memmap[AW_H3_DRAMCTL]); sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 2, s->memmap[AW_H3_DRAMPHY]); + /* RTC */ + qdev_init_nofail(DEVICE(&s->rtc)); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, s->memmap[AW_H3_RTC]); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/rtc/allwinner-rtc.c b/hw/rtc/allwinner-rtc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/rtc/allwinner-rtc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner Real Time Clock emulation + * + * Copyright (C) 2019 Niek Linnenbank <nieklinnenbank@gmail.com> + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu-common.h" +#include "hw/qdev-properties.h" +#include "hw/rtc/allwinner-rtc.h" +#include "trace.h" + +/* RTC registers */ +enum { + REG_LOSC = 1, /* Low Oscillator Control */ + REG_YYMMDD, /* RTC Year-Month-Day */ + REG_HHMMSS, /* RTC Hour-Minute-Second */ + REG_ALARM1_WKHHMMSS, /* Alarm1 Week Hour-Minute-Second */ + REG_ALARM1_EN, /* Alarm1 Enable */ + REG_ALARM1_IRQ_EN, /* Alarm1 IRQ Enable */ + REG_ALARM1_IRQ_STA, /* Alarm1 IRQ Status */ + REG_GP0, /* General Purpose Register 0 */ + REG_GP1, /* General Purpose Register 1 */ + REG_GP2, /* General Purpose Register 2 */ + REG_GP3, /* General Purpose Register 3 */ + + /* sun4i registers */ + REG_ALARM1_DDHHMMSS, /* Alarm1 Day Hour-Minute-Second */ + REG_CPUCFG, /* CPU Configuration Register */ + + /* sun6i registers */ + REG_LOSC_AUTOSTA, /* LOSC Auto Switch Status */ + REG_INT_OSC_PRE, /* Internal OSC Clock Prescaler */ + REG_ALARM0_COUNTER, /* Alarm0 Counter */ + REG_ALARM0_CUR_VLU, /* Alarm0 Counter Current Value */ + REG_ALARM0_ENABLE, /* Alarm0 Enable */ + REG_ALARM0_IRQ_EN, /* Alarm0 IRQ Enable */ + REG_ALARM0_IRQ_STA, /* Alarm0 IRQ Status */ + REG_ALARM_CONFIG, /* Alarm Config */ + REG_LOSC_OUT_GATING, /* LOSC Output Gating Register */ + REG_GP4, /* General Purpose Register 4 */ + REG_GP5, /* General Purpose Register 5 */ + REG_GP6, /* General Purpose Register 6 */ + REG_GP7, /* General Purpose Register 7 */ + REG_RTC_DBG, /* RTC Debug Register */ + REG_GPL_HOLD_OUT, /* GPL Hold Output Register */ + REG_VDD_RTC, /* VDD RTC Regulate Register */ + REG_IC_CHARA, /* IC Characteristics Register */ +}; + +/* RTC register flags */ +enum { + REG_LOSC_YMD = (1 << 7), + REG_LOSC_HMS = (1 << 8), +}; + +/* RTC sun4i register map (offset to name) */ +const uint8_t allwinner_rtc_sun4i_regmap[] = { + [0x0000] = REG_LOSC, + [0x0004] = REG_YYMMDD, + [0x0008] = REG_HHMMSS, + [0x000C] = REG_ALARM1_DDHHMMSS, + [0x0010] = REG_ALARM1_WKHHMMSS, + [0x0014] = REG_ALARM1_EN, + [0x0018] = REG_ALARM1_IRQ_EN, + [0x001C] = REG_ALARM1_IRQ_STA, + [0x0020] = REG_GP0, + [0x0024] = REG_GP1, + [0x0028] = REG_GP2, + [0x002C] = REG_GP3, + [0x003C] = REG_CPUCFG, +}; + +/* RTC sun6i register map (offset to name) */ +const uint8_t allwinner_rtc_sun6i_regmap[] = { + [0x0000] = REG_LOSC, + [0x0004] = REG_LOSC_AUTOSTA, + [0x0008] = REG_INT_OSC_PRE, + [0x0010] = REG_YYMMDD, + [0x0014] = REG_HHMMSS, + [0x0020] = REG_ALARM0_COUNTER, + [0x0024] = REG_ALARM0_CUR_VLU, + [0x0028] = REG_ALARM0_ENABLE, + [0x002C] = REG_ALARM0_IRQ_EN, + [0x0030] = REG_ALARM0_IRQ_STA, + [0x0040] = REG_ALARM1_WKHHMMSS, + [0x0044] = REG_ALARM1_EN, + [0x0048] = REG_ALARM1_IRQ_EN, + [0x004C] = REG_ALARM1_IRQ_STA, + [0x0050] = REG_ALARM_CONFIG, + [0x0060] = REG_LOSC_OUT_GATING, + [0x0100] = REG_GP0, + [0x0104] = REG_GP1, + [0x0108] = REG_GP2, + [0x010C] = REG_GP3, + [0x0110] = REG_GP4, + [0x0114] = REG_GP5, + [0x0118] = REG_GP6, + [0x011C] = REG_GP7, + [0x0170] = REG_RTC_DBG, + [0x0180] = REG_GPL_HOLD_OUT, + [0x0190] = REG_VDD_RTC, + [0x01F0] = REG_IC_CHARA, +}; + +static bool allwinner_rtc_sun4i_read(AwRtcState *s, uint32_t offset) +{ + /* no sun4i specific registers currently implemented */ + return false; +} + +static bool allwinner_rtc_sun4i_write(AwRtcState *s, uint32_t offset, + uint32_t data) +{ + /* no sun4i specific registers currently implemented */ + return false; +} + +static bool allwinner_rtc_sun6i_read(AwRtcState *s, uint32_t offset) +{ + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + switch (c->regmap[offset]) { + case REG_GP4: /* General Purpose Register 4 */ + case REG_GP5: /* General Purpose Register 5 */ + case REG_GP6: /* General Purpose Register 6 */ + case REG_GP7: /* General Purpose Register 7 */ + return true; + default: + break; + } + return false; +} + +static bool allwinner_rtc_sun6i_write(AwRtcState *s, uint32_t offset, + uint32_t data) +{ + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + switch (c->regmap[offset]) { + case REG_GP4: /* General Purpose Register 4 */ + case REG_GP5: /* General Purpose Register 5 */ + case REG_GP6: /* General Purpose Register 6 */ + case REG_GP7: /* General Purpose Register 7 */ + return true; + default: + break; + } + return false; +} + +static uint64_t allwinner_rtc_read(void *opaque, hwaddr offset, + unsigned size) +{ + AwRtcState *s = AW_RTC(opaque); + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + uint64_t val = 0; + + if (offset >= c->regmap_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + if (!c->regmap[offset]) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid register 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + switch (c->regmap[offset]) { + case REG_LOSC: /* Low Oscillator Control */ + val = s->regs[REG_LOSC]; + s->regs[REG_LOSC] &= ~(REG_LOSC_YMD | REG_LOSC_HMS); + break; + case REG_YYMMDD: /* RTC Year-Month-Day */ + case REG_HHMMSS: /* RTC Hour-Minute-Second */ + case REG_GP0: /* General Purpose Register 0 */ + case REG_GP1: /* General Purpose Register 1 */ + case REG_GP2: /* General Purpose Register 2 */ + case REG_GP3: /* General Purpose Register 3 */ + val = s->regs[c->regmap[offset]]; + break; + default: + if (!c->read(s, offset)) { + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register 0x%04x\n", + __func__, (uint32_t)offset); + } + val = s->regs[c->regmap[offset]]; + break; + } + + trace_allwinner_rtc_read(offset, val); + return val; +} + +static void allwinner_rtc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwRtcState *s = AW_RTC(opaque); + const AwRtcClass *c = AW_RTC_GET_CLASS(s); + + if (offset >= c->regmap_size) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + if (!c->regmap[offset]) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid register 0x%04x\n", + __func__, (uint32_t)offset); + return; + } + + trace_allwinner_rtc_write(offset, val); + + switch (c->regmap[offset]) { + case REG_YYMMDD: /* RTC Year-Month-Day */ + s->regs[REG_YYMMDD] = val; + s->regs[REG_LOSC] |= REG_LOSC_YMD; + break; + case REG_HHMMSS: /* RTC Hour-Minute-Second */ + s->regs[REG_HHMMSS] = val; + s->regs[REG_LOSC] |= REG_LOSC_HMS; + break; + case REG_GP0: /* General Purpose Register 0 */ + case REG_GP1: /* General Purpose Register 1 */ + case REG_GP2: /* General Purpose Register 2 */ + case REG_GP3: /* General Purpose Register 3 */ + s->regs[c->regmap[offset]] = val; + break; + default: + if (!c->write(s, offset, val)) { + qemu_log_mask(LOG_UNIMP, "%s: unimplemented register 0x%04x\n", + __func__, (uint32_t)offset); + } + break; + } +} + +static const MemoryRegionOps allwinner_rtc_ops = { + .read = allwinner_rtc_read, + .write = allwinner_rtc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_rtc_reset(DeviceState *dev) +{ + AwRtcState *s = AW_RTC(dev); + struct tm now; + + /* Clear registers */ + memset(s->regs, 0, sizeof(s->regs)); + + /* Get current datetime */ + qemu_get_timedate(&now, 0); + + /* Set RTC with current datetime */ + if (s->base_year > 1900) { + s->regs[REG_YYMMDD] = ((now.tm_year + 1900 - s->base_year) << 16) | + ((now.tm_mon + 1) << 8) | + now.tm_mday; + s->regs[REG_HHMMSS] = (((now.tm_wday + 6) % 7) << 29) | + (now.tm_hour << 16) | + (now.tm_min << 8) | + now.tm_sec; + } +} + +static void allwinner_rtc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwRtcState *s = AW_RTC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_rtc_ops, s, + TYPE_AW_RTC, 1 * KiB); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_rtc_vmstate = { + .name = "allwinner-rtc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwRtcState, AW_RTC_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static Property allwinner_rtc_properties[] = { + DEFINE_PROP_INT32("base-year", AwRtcState, base_year, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void allwinner_rtc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = allwinner_rtc_reset; + dc->vmsd = &allwinner_rtc_vmstate; + device_class_set_props(dc, allwinner_rtc_properties); +} + +static void allwinner_rtc_sun4i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 2010; +} + +static void allwinner_rtc_sun4i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + + arc->regmap = allwinner_rtc_sun4i_regmap; + arc->regmap_size = sizeof(allwinner_rtc_sun4i_regmap); + arc->read = allwinner_rtc_sun4i_read; + arc->write = allwinner_rtc_sun4i_write; +} + +static void allwinner_rtc_sun6i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 1970; +} + +static void allwinner_rtc_sun6i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + + arc->regmap = allwinner_rtc_sun6i_regmap; + arc->regmap_size = sizeof(allwinner_rtc_sun6i_regmap); + arc->read = allwinner_rtc_sun6i_read; + arc->write = allwinner_rtc_sun6i_write; +} + +static void allwinner_rtc_sun7i_init(Object *obj) +{ + AwRtcState *s = AW_RTC(obj); + s->base_year = 1970; +} + +static void allwinner_rtc_sun7i_class_init(ObjectClass *klass, void *data) +{ + AwRtcClass *arc = AW_RTC_CLASS(klass); + allwinner_rtc_sun4i_class_init(klass, arc); +} + +static const TypeInfo allwinner_rtc_info = { + .name = TYPE_AW_RTC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_rtc_init, + .instance_size = sizeof(AwRtcState), + .class_init = allwinner_rtc_class_init, + .class_size = sizeof(AwRtcClass), + .abstract = true, +}; + +static const TypeInfo allwinner_rtc_sun4i_info = { + .name = TYPE_AW_RTC_SUN4I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun4i_class_init, + .instance_init = allwinner_rtc_sun4i_init, +}; + +static const TypeInfo allwinner_rtc_sun6i_info = { + .name = TYPE_AW_RTC_SUN6I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun6i_class_init, + .instance_init = allwinner_rtc_sun6i_init, +}; + +static const TypeInfo allwinner_rtc_sun7i_info = { + .name = TYPE_AW_RTC_SUN7I, + .parent = TYPE_AW_RTC, + .class_init = allwinner_rtc_sun7i_class_init, + .instance_init = allwinner_rtc_sun7i_init, +}; + +static void allwinner_rtc_register(void) +{ + type_register_static(&allwinner_rtc_info); + type_register_static(&allwinner_rtc_sun4i_info); + type_register_static(&allwinner_rtc_sun6i_info); + type_register_static(&allwinner_rtc_sun7i_info); +} + +type_init(allwinner_rtc_register) diff --git a/hw/rtc/trace-events b/hw/rtc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/rtc/trace-events +++ b/hw/rtc/trace-events @@ -XXX,XX +XXX,XX @@ # See docs/devel/tracing.txt for syntax documentation. +# allwinner-rtc.c +allwinner_rtc_read(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 +allwinner_rtc_write(uint64_t addr, uint64_t value) "addr 0x%" PRIx64 " value 0x%" PRIx64 + # sun4v-rtc.c sun4v_rtc_read(uint64_t addr, uint64_t value) "read: addr 0x%" PRIx64 " value 0x%" PRIx64 sun4v_rtc_write(uint64_t addr, uint64_t value) "write: addr 0x%" PRIx64 " value 0x%" PRIx64 -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots a Linux kernel on a OrangePi PC board and verify the serial output is working. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ make check-venv $ ./tests/venv/bin/avocado --show=console,app run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py JOB ID : 2e4d15eceb13c33672af406f08171e6e9de1414a JOB LOG : ~/job-results/job-2019-12-17T05.46-2e4d15e/job.log (1/1) tests/acceptance/boot_linux_console.py:BootLinuxConsole.test_arm_orangepi: console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC console: Memory policy: Data cache writealloc console: OF: reserved mem: failed to allocate memory for node 'cma@4a000000' console: cma: Failed to reserve 128 MiB console: psci: probing for conduit method from DT. console: psci: PSCIv0.2 detected in firmware. console: psci: Using standard PSCI v0.2 function IDs console: psci: Trusted OS migration not required console: random: get_random_bytes called from start_kernel+0x8d/0x3c2 with crng_init=0 console: percpu: Embedded 18 pages/cpu @(ptrval) s41228 r8192 d24308 u73728 console: Built 1 zonelists, mobility grouping on. Total pages: 32480 console: Kernel command line: printk.time=0 console=ttyS0,115200 PASS (8.59 s) JOB TIME : 8.81 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-14-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 25 +++++++++++++++++++++++++ 1 file changed, 25 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + def test_arm_orangepi(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200n8 ' + 'earlycon=uart,mmio32,0x1c28000') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-append', kernel_command_line) + self.vm.launch() + console_pattern = 'Kernel command line: %s' % kernel_command_line + self.wait_for_console_pattern(console_pattern) + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots a Linux kernel on a OrangePi PC board and verify the serial output is working. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The cpio image used comes from the linux-build-test project: https://github.com/groeck/linux-build-test If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ avocado --show=console run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC [...] console: Trying to unpack rootfs image as initramfs... console: Freeing initrd memory: 3256K console: Freeing unused kernel memory: 1024K console: Run /init as init process console: mount: mounting devtmpfs on /dev failed: Device or resource busy console: Starting logging: OK console: Initializing random number generator... random: dd: uninitialized urandom read (512 bytes read) console: done. console: Starting network: OK console: Found console ttyS0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: Boot successful. console: cat /proc/cpuinfo console: / # cat /proc/cpuinfo console: processor : 0 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 [...] console: processor : 3 console: model name : ARMv7 Processor rev 5 (v7l) console: BogoMIPS : 125.00 console: Features : half thumb fastmult vfp edsp neon vfpv3 tls vfpv4 idiva idivt vfpd32 lpae evtstrm console: CPU implementer : 0x41 console: CPU architecture: 7 console: CPU variant : 0x0 console: CPU part : 0xc07 console: CPU revision : 5 console: Hardware : Allwinner sun8i Family console: Revision : 0000 console: Serial : 0000000000000000 console: cat /proc/iomem console: / # cat /proc/iomem console: 01000000-010fffff : clock@1000000 console: 01c00000-01c00fff : system-control@1c00000 console: 01c02000-01c02fff : dma-controller@1c02000 [...] console: reboot console: / # reboot console: / # Found console ttyS0 console: Stopping network: OK console: hrtimer: interrupt took 21852064 ns console: Saving random seed... random: dd: uninitialized urandom read (512 bytes read) console: done. console: Stopping logging: OK console: umount: devtmpfs busy - remounted read-only console: umount: can't unmount /: Invalid argument console: The system is going down NOW! console: Sent SIGTERM to all processes console: Sent SIGKILL to all processes console: Requesting system reboot console: reboot: Restarting system PASS (48.32 s) JOB TIME : 49.16 s Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-15-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 40 ++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): console_pattern = 'Kernel command line: %s' % kernel_command_line self.wait_for_console_pattern(console_pattern) + def test_arm_orangepi_initrd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + initrd_url = ('https://github.com/groeck/linux-build-test/raw/' + '2eb0a73b5d5a28df3170c546ddaaa9757e1e0848/rootfs/' + 'arm/rootfs-armv7a.cpio.gz') + initrd_hash = '604b2e45cdf35045846b8bbfbf2129b1891bdc9c' + initrd_path_gz = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + initrd_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.gzip_uncompress(initrd_path_gz, initrd_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'panic=-1 noreboot') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-initrd', initrd_path, + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + self.wait_for_console_pattern('Boot successful.') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/iomem', + 'system-control@1c00000') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The SD image is from the kernelci.org project: https://kernelci.org/faq/#the-code If ARM is a target being built, "make check-acceptance" will automatically include this test by the use of the "arch:arm" tags. Alternatively, this test can be run using: $ avocado --show=console run -t machine:orangepi-pc tests/acceptance/boot_linux_console.py console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 4.20.7-sunxi (root@armbian.com) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #5.75 SMP Fri Feb 8 09:02:10 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d [...] console: sunxi-wdt 1c20ca0.watchdog: Watchdog enabled (timeout=16 sec, nowayout=0) console: sunxi-mmc 1c0f000.mmc: Linked as a consumer to regulator.2 console: sunxi-mmc 1c0f000.mmc: Got CD GPIO console: ledtrig-cpu: registered to indicate activity on CPUs console: hidraw: raw HID events driver (C) Jiri Kosina console: usbcore: registered new interface driver usbhid console: usbhid: USB HID core driver console: Initializing XFRM netlink socket console: sunxi-mmc 1c0f000.mmc: initialized, max. request size: 16384 KB console: NET: Registered protocol family 10 console: mmc0: host does not support reading read-only switch, assuming write-enable console: mmc0: Problem switching card into high-speed mode! console: mmc0: new SD card at address 4567 console: mmcblk0: mmc0:4567 QEMU! 60.0 MiB [...] console: EXT4-fs (mmcblk0): mounting ext2 file system using the ext4 subsystem console: EXT4-fs (mmcblk0): mounted filesystem without journal. Opts: (null) console: VFS: Mounted root (ext2 filesystem) on device 179:0. console: Run /sbin/init as init process console: EXT4-fs (mmcblk0): re-mounted. Opts: block_validity,barrier,user_xattr,acl console: Starting syslogd: OK console: Starting klogd: OK console: Populating /dev using udev: udevd[203]: starting version 3.2.7 console: /bin/sh: can't access tty; job control turned off console: cat /proc/partitions console: / # cat /proc/partitions console: major minor #blocks name console: 1 0 4096 ram0 console: 1 1 4096 ram1 console: 1 2 4096 ram2 console: 1 3 4096 ram3 console: 179 0 61440 mmcblk0 console: reboot console: / # reboot console: umount: devtmpfs busy - remounted read-only console: EXT4-fs (mmcblk0): re-mounted. Opts: (null) console: The system is going down NOW! console: Sent SIGTERM to all processes console: Sent SIGKILL to all processes console: Requesting system reboot console: reboot: Restarting system JOB TIME : 68.64 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-16-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] [NL: extend test with ethernet device checks] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 47 ++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + def test_arm_orangepi_sd(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + deb_url = ('https://apt.armbian.com/pool/main/l/' + 'linux-4.20.7-sunxi/linux-image-dev-sunxi_5.75_armhf.deb') + deb_hash = '1334c29c44d984ffa05ed10de8c3361f33d78315' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + kernel_path = self.extract_from_deb(deb_path, + '/boot/vmlinuz-4.20.7-sunxi') + dtb_path = '/usr/lib/linux-image-dev-sunxi/sun8i-h3-orangepi-pc.dtb' + dtb_path = self.extract_from_deb(deb_path, dtb_path) + rootfs_url = ('http://storage.kernelci.org/images/rootfs/buildroot/' + 'kci-2019.02/armel/base/rootfs.ext2.xz') + rootfs_hash = '692510cb625efda31640d1de0a8d60e26040f061' + rootfs_path_xz = self.fetch_asset(rootfs_url, asset_hash=rootfs_hash) + rootfs_path = os.path.join(self.workdir, 'rootfs.cpio') + archive.lzma_uncompress(rootfs_path_xz, rootfs_path) + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'root=/dev/mmcblk0 rootwait rw ' + 'panic=-1 noreboot') + self.vm.add_args('-kernel', kernel_path, + '-dtb', dtb_path, + '-drive', 'file=' + rootfs_path + ',if=sd,format=raw', + '-append', kernel_command_line, + '-no-reboot') + self.vm.launch() + shell_ready = "/bin/sh: can't access tty; job control turned off" + self.wait_for_console_pattern(shell_ready) + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun8i Family') + exec_command_and_wait_for_pattern(self, 'cat /proc/partitions', + 'mmcblk0') + exec_command_and_wait_for_pattern(self, 'ifconfig eth0 up', + 'eth0: Link is Up') + exec_command_and_wait_for_pattern(self, 'udhcpc eth0', + 'udhcpc: lease of 10.0.2.15 obtained') + exec_command_and_wait_for_pattern(self, 'ping -c 3 10.0.2.2', + '3 packets transmitted, 3 packets received, 0% packet loss') + exec_command_and_wait_for_pattern(self, 'reboot', + 'reboot: Restarting system') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots Ubuntu Bionic on a OrangePi PC board. As it requires 1GB of storage, and is slow, this test is disabled on automatic CI testing. It is useful for workstation testing. Currently Avocado timeouts too quickly, so we can't run userland commands. The kernel image and DeviceTree blob are built by the Armbian project (based on Debian): https://www.armbian.com/orange-pi-pc/ The Ubuntu image is downloaded from: https://dl.armbian.com/orangepipc/Bionic_current This test can be run using: $ AVOCADO_ALLOW_LARGE_STORAGE=yes \ avocado --show=app,console run -t machine:orangepi-pc \ tests/acceptance/boot_linux_console.py console: U-Boot SPL 2019.04-armbian (Nov 18 2019 - 23:08:35 +0100) console: DRAM: 1024 MiB console: Failed to set core voltage! Can't set CPU frequency console: Trying to boot from MMC1 console: U-Boot 2019.04-armbian (Nov 18 2019 - 23:08:35 +0100) Allwinner Technology console: CPU: Allwinner H3 (SUN8I 0000) console: Model: Xunlong Orange Pi PC console: DRAM: 1 GiB console: MMC: mmc@1c0f000: 0 [...] console: Uncompressing Linux... done, booting the kernel. console: Booting Linux on physical CPU 0x0 console: Linux version 5.3.9-sunxi (root@builder) (gcc version 8.3.0 (GNU Toolchain for the A-profile Architecture 8.3-2019.03 (arm-rel-8.36))) #19.11.3 SMP Mon Nov 18 18:49:43 CET 2019 console: CPU: ARMv7 Processor [410fc075] revision 5 (ARMv7), cr=50c5387d console: CPU: div instructions available: patching division code console: CPU: PIPT / VIPT nonaliasing data cache, VIPT aliasing instruction cache console: OF: fdt: Machine model: Xunlong Orange Pi PC [...] console: EXT4-fs (mmcblk0p1): mounted filesystem with writeback data mode. Opts: (null) console: done. console: Begin: Running /scripts/local-bottom ... done. console: Begin: Running /scripts/init-bottom ... done. console: systemd[1]: systemd 237 running in system mode. (...) console: systemd[1]: Detected architecture arm. console: Welcome to Ubuntu 18.04.3 LTS! console: systemd[1]: Set hostname to <orangepipc>. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-17-nieklinnenbank@gmail.com [NL: rename in commit message Raspbian to Armbian, remove vm.set_machine()] [NL: changed test to boot from SD card via BootROM, added check for 7z] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 48 ++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ from avocado_qemu import exec_command_and_wait_for_pattern from avocado_qemu import wait_for_console_pattern from avocado.utils import process from avocado.utils import archive +from avocado.utils.path import find_command, CmdNotFoundError +P7ZIP_AVAILABLE = True +try: + find_command('7z') +except CmdNotFoundError: + P7ZIP_AVAILABLE = False class BootLinuxConsole(Test): """ @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): exec_command_and_wait_for_pattern(self, 'reboot', 'reboot: Restarting system') + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + @skipUnless(P7ZIP_AVAILABLE, '7z not installed') + def test_arm_orangepi_bionic(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + + # This test download a 196MB compressed image and expand it to 932MB... + image_url = ('https://dl.armbian.com/orangepipc/archive/' + 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.7z') + image_hash = '196a8ffb72b0123d92cea4a070894813d305c71e' + image_path_7z = self.fetch_asset(image_url, asset_hash=image_hash) + image_name = 'Armbian_19.11.3_Orangepipc_bionic_current_5.3.9.img' + image_path = os.path.join(self.workdir, image_name) + process.run("7z e -o%s %s" % (self.workdir, image_path_7z)) + + self.vm.set_console() + self.vm.add_args('-drive', 'file=' + image_path + ',if=sd,format=raw', + '-nic', 'user', + '-no-reboot') + self.vm.launch() + + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyS0,115200 ' + 'loglevel=7 ' + 'nosmp ' + 'systemd.default_timeout_start_sec=9000 ' + 'systemd.mask=armbian-zram-config.service ' + 'systemd.mask=armbian-ramlog.service') + + self.wait_for_console_pattern('U-Boot SPL') + self.wait_for_console_pattern('Autoboot in ') + exec_command_and_wait_for_pattern(self, ' ', '=>') + exec_command_and_wait_for_pattern(self, "setenv extraargs '" + + kernel_command_line + "'", '=>') + exec_command_and_wait_for_pattern(self, 'boot', 'Starting kernel ...'); + + self.wait_for_console_pattern('systemd[1]: Set hostname ' + + 'to <orangepipc>') + self.wait_for_console_pattern('Starting Load Kernel Modules...') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> This test boots U-Boot then NetBSD (stored on a SD card) on a OrangePi PC board. As it requires ~1.3GB of storage, it is disabled by default. U-Boot is built by the Debian project [1], and the SD card image is provided by the NetBSD organization [2]. Once the compressed SD card image is downloaded (304MB) and extracted, this test is fast: $ AVOCADO_ALLOW_LARGE_STORAGE=yes \ avocado --show=app,console run -t machine:orangepi-pc \ tests/acceptance/boot_linux_console.py console: U-Boot SPL 2020.01+dfsg-1 (Jan 08 2020 - 08:19:44 +0000) console: DRAM: 1024 MiB console: U-Boot 2020.01+dfsg-1 (Jan 08 2020 - 08:19:44 +0000) Allwinner Technology console: CPU: Allwinner H3 (SUN8I 0000) console: scanning bus usb@1c1b000 for devices... 1 USB Device(s) found console: scanning bus usb@1c1d000 for devices... 1 USB Device(s) found console: scanning usb for storage devices... 0 Storage Device(s) found console: Hit any key to stop autoboot: 0 console: => setenv bootargs root=ld0a console: => setenv kernel netbsd-GENERIC.ub console: => setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb console: => boot console: ## Booting kernel from Legacy Image at 42000000 ... console: Image Name: NetBSD/earmv7hf 9.0_RC1 console: Image Type: ARM Linux Kernel Image (no loading done) (uncompressed) console: XIP Kernel Image (no loading done) console: Loading Device Tree to 49ff6000, end 49fffe01 ... OK console: Starting kernel ... console: [ 1.0000000] NetBSD/evbarm (fdt) booting ... console: [ 1.0000000] NetBSD 9.0 (GENERIC) #0: Fri Feb 14 00:06:28 UTC 2020 console: [ 1.0000000] mkrepro@mkrepro.NetBSD.org:/usr/src/sys/arch/evbarm/compile/GENERIC console: [ 1.0000000] total memory = 1024 MB console: [ 1.0000000] avail memory = 1003 MB console: [ 1.0000000] armfdt0 (root) console: [ 1.0000000] simplebus0 at armfdt0: Xunlong Orange Pi PC console: [ 1.0000000] cpu0 at cpus0: Cortex-A7 r0p5 (Cortex V7A core) console: [ 1.0000000] cpu0: DC enabled IC enabled WB enabled LABT branch prediction enabled console: [ 1.0000000] cpu0: 32KB/64B 2-way L1 VIPT Instruction cache console: [ 1.0000000] cpu0: 32KB/64B 2-way write-back-locking-C L1 PIPT Data cache console: [ 1.0000000] cpu0: 2304KB/64B 16-way write-through L2 PIPT Unified cache console: [ 1.0000000] vfp0 at cpu0: NEON MPE (VFP 3.0+), rounding, NaN propagation, denormals ... console: [ 2.3812082] sdmmc0: SD card status: 4-bit, C0 console: [ 2.3812082] ld0 at sdmmc0: <0xaa:0x5859:QEMU!:0x01:0xdeadbeef:0x062> console: [ 2.4012856] ld0: 1226 MB, 622 cyl, 64 head, 63 sec, 512 bytes/sect x 2511872 sectors console: [ 2.5321222] ld0: 4-bit width, High-Speed/SDR25, 50.000 MHz console: [ 3.1068718] WARNING: 4 errors while detecting hardware; check system log. console: [ 3.1179868] boot device: ld0 console: [ 3.1470623] root on ld0a dumps on ld0b console: [ 3.2464436] root file system type: ffs console: [ 3.2897123] kern.module.path=/stand/evbarm/9.0/modules console: Mon Feb 17 20:33:35 UTC 2020 console: Starting root file system check: PASS (35.96 s) RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 JOB TIME : 36.09 s Note, this test only took ~65 seconds to run on Travis-CI, see: [3]. This test is based on a description from Niek Linnenbank from [4]. [1] https://wiki.debian.org/InstallingDebianOn/Allwinner#Creating_a_bootable_SD_Card_with_u-boot [2] https://wiki.netbsd.org/ports/evbarm/allwinner/ [3] https://travis-ci.org/philmd/qemu/jobs/638823612#L3778 [4] https://www.mail-archive.com/qemu-devel@nongnu.org/msg669347.html Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-18-nieklinnenbank@gmail.com [NL: changed test to use NetBSD 9.0 final release and -global allwinner-rtc.base-year] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/boot_linux_console.py | 70 ++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ import shutil from avocado import skipUnless from avocado_qemu import Test from avocado_qemu import exec_command_and_wait_for_pattern +from avocado_qemu import interrupt_interactive_console_until_pattern from avocado_qemu import wait_for_console_pattern from avocado.utils import process from avocado.utils import archive @@ -XXX,XX +XXX,XX @@ class BootLinuxConsole(Test): 'to <orangepipc>') self.wait_for_console_pattern('Starting Load Kernel Modules...') + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_orangepi_uboot_netbsd9(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:orangepi-pc + """ + # This test download a 304MB compressed image and expand it to 1.3GB... + deb_url = ('http://snapshot.debian.org/archive/debian/' + '20200108T145233Z/pool/main/u/u-boot/' + 'u-boot-sunxi_2020.01%2Bdfsg-1_armhf.deb') + deb_hash = 'f67f404a80753ca3d1258f13e38f2b060e13db99' + deb_path = self.fetch_asset(deb_url, asset_hash=deb_hash) + # We use the common OrangePi PC 'plus' build of U-Boot for our secondary + # program loader (SPL). We will then set the path to the more specific + # OrangePi "PC" device tree blob with 'setenv fdtfile' in U-Boot prompt, + # before to boot NetBSD. + uboot_path = '/usr/lib/u-boot/orangepi_plus/u-boot-sunxi-with-spl.bin' + uboot_path = self.extract_from_deb(deb_path, uboot_path) + image_url = ('https://cdn.netbsd.org/pub/NetBSD/NetBSD-9.0/' + 'evbarm-earmv7hf/binary/gzimg/armv7.img.gz') + image_hash = '2babb29d36d8360adcb39c09e31060945259917a' + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash) + image_path = os.path.join(self.workdir, 'armv7.img') + image_drive_args = 'if=sd,format=raw,snapshot=on,file=' + image_path + archive.gzip_uncompress(image_path_gz, image_path) + + # dd if=u-boot-sunxi-with-spl.bin of=armv7.img bs=1K seek=8 conv=notrunc + with open(uboot_path, 'rb') as f_in: + with open(image_path, 'r+b') as f_out: + f_out.seek(8 * 1024) + shutil.copyfileobj(f_in, f_out) + + # Extend image, to avoid that NetBSD thinks the partition + # inside the image is larger than device size itself + f_out.seek(0, 2) + f_out.seek(64 * 1024 * 1024, 1) + f_out.write(bytearray([0x00])) + + self.vm.set_console() + self.vm.add_args('-nic', 'user', + '-drive', image_drive_args, + '-global', 'allwinner-rtc.base-year=2000', + '-no-reboot') + self.vm.launch() + wait_for_console_pattern(self, 'U-Boot 2020.01+dfsg-1') + interrupt_interactive_console_until_pattern(self, + 'Hit any key to stop autoboot:', + 'switch to partitions #0, OK') + + exec_command_and_wait_for_pattern(self, '', '=>') + cmd = 'setenv bootargs root=ld0a' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = 'setenv kernel netbsd-GENERIC.ub' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = 'setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb' + exec_command_and_wait_for_pattern(self, cmd, '=>') + cmd = ("setenv bootcmd 'fatload mmc 0:1 ${kernel_addr_r} ${kernel}; " + "fatload mmc 0:1 ${fdt_addr_r} ${fdtfile}; " + "fdt addr ${fdt_addr_r}; " + "bootm ${kernel_addr_r} - ${fdt_addr_r}'") + exec_command_and_wait_for_pattern(self, cmd, '=>') + + exec_command_and_wait_for_pattern(self, 'boot', + 'Booting kernel from Legacy Image') + wait_for_console_pattern(self, 'Starting kernel ...') + wait_for_console_pattern(self, 'NetBSD 9.0 (GENERIC)') + # Wait for user-space + wait_for_console_pattern(self, 'Starting root file system check') + def test_s390x_s390_ccw_virtio(self): """ :avocado: tags=arch:s390x -- 2.20.1 From: Niek Linnenbank <nieklinnenbank@gmail.com> The Xunlong Orange Pi PC machine is a functional ARM machine based on the Allwinner H3 System-on-Chip. It supports mainline Linux, U-Boot, NetBSD and is covered by acceptance tests. This commit adds a documentation text file with a description of the machine and instructions for the user. Signed-off-by: Niek Linnenbank <nieklinnenbank@gmail.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20200311221854.30370-19-nieklinnenbank@gmail.com [PMM: moved file into docs/system/arm to match the reorg of the arm target part of the docs; tweaked heading to match other boards] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + docs/system/arm/orangepi.rst | 253 +++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 2 + 3 files changed, 256 insertions(+) create mode 100644 docs/system/arm/orangepi.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/*/allwinner-h3* F: include/hw/*/allwinner-h3* F: hw/arm/orangepi.c +F: docs/system/orangepi.rst ARM PrimeCell and CMSDK devices M: Peter Maydell <peter.maydell@linaro.org> diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/orangepi.rst @@ -XXX,XX +XXX,XX @@ +Orange Pi PC (``orangepi-pc``) +^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ + +The Xunlong Orange Pi PC is an Allwinner H3 System on Chip +based embedded computer with mainline support in both U-Boot +and Linux. The board comes with a Quad Core Cortex-A7 @ 1.3GHz, +1GiB RAM, 100Mbit ethernet, USB, SD/MMC, USB, HDMI and +various other I/O. + +Supported devices +""""""""""""""""" + +The Orange Pi PC machine supports the following devices: + + * SMP (Quad Core Cortex-A7) + * Generic Interrupt Controller configuration + * SRAM mappings + * SDRAM controller + * Real Time Clock + * Timer device (re-used from Allwinner A10) + * UART + * SD/MMC storage controller + * EMAC ethernet + * USB 2.0 interfaces + * Clock Control Unit + * System Control module + * Security Identifier device + +Limitations +""""""""""" + +Currently, Orange Pi PC does *not* support the following features: + +- Graphical output via HDMI, GPU and/or the Display Engine +- Audio output +- Hardware Watchdog + +Also see the 'unimplemented' array in the Allwinner H3 SoC module +for a complete list of unimplemented I/O devices: ``./hw/arm/allwinner-h3.c`` + +Boot options +"""""""""""" + +The Orange Pi PC machine can start using the standard -kernel functionality +for loading a Linux kernel or ELF executable. Additionally, the Orange Pi PC +machine can also emulate the BootROM which is present on an actual Allwinner H3 +based SoC, which loads the bootloader from a SD card, specified via the -sd argument +to qemu-system-arm. + +Machine-specific options +"""""""""""""""""""""""" + +The following machine-specific options are supported: + +- allwinner-rtc.base-year=YYYY + + The Allwinner RTC device is automatically created by the Orange Pi PC machine + and uses a default base year value which can be overridden using the 'base-year' property. + The base year is the actual represented year when the RTC year value is zero. + This option can be used in case the target operating system driver uses a different + base year value. The minimum value for the base year is 1900. + +- allwinner-sid.identifier=abcd1122-a000-b000-c000-12345678ffff + + The Security Identifier value can be read by the guest. + For example, U-Boot uses it to determine a unique MAC address. + +The above machine-specific options can be specified in qemu-system-arm +via the '-global' argument, for example: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -sd mycard.img \ + -global allwinner-rtc.base-year=2000 + +Running mainline Linux +"""""""""""""""""""""" + +Mainline Linux kernels from 4.19 up to latest master are known to work. +To build a Linux mainline kernel that can be booted by the Orange Pi PC machine, +simply configure the kernel using the sunxi_defconfig configuration: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make mrproper + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make sunxi_defconfig + +To be able to use USB storage, you need to manually enable the corresponding +configuration item. Start the kconfig configuration tool: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make menuconfig + +Navigate to the following item, enable it and save your configuration: + + Device Drivers > USB support > USB Mass Storage support + +Build the Linux kernel with: + +.. code-block:: bash + + $ ARCH=arm CROSS_COMPILE=arm-linux-gnueabi- make + +To boot the newly build linux kernel in QEMU with the Orange Pi PC machine, use: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/linux/arch/arm/boot/zImage \ + -append 'console=ttyS0,115200' \ + -dtb /path/to/linux/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dtb + +Orange Pi PC images +""""""""""""""""""" + +Note that the mainline kernel does not have a root filesystem. You may provide it +with an official Orange Pi PC image from the official website: + + http://www.orangepi.org/downloadresources/ + +Another possibility is to run an Armbian image for Orange Pi PC which +can be downloaded from: + + https://www.armbian.com/orange-pi-pc/ + +Alternatively, you can also choose to build you own image with buildroot +using the orangepi_pc_defconfig. Also see https://buildroot.org for more information. + +You can choose to attach the selected image either as an SD card or as USB mass storage. +For example, to boot using the Orange Pi PC Debian image on SD card, simply add the -sd +argument and provide the proper root= kernel parameter: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/linux/arch/arm/boot/zImage \ + -append 'console=ttyS0,115200 root=/dev/mmcblk0p2' \ + -dtb /path/to/linux/arch/arm/boot/dts/sun8i-h3-orangepi-pc.dtb \ + -sd OrangePi_pc_debian_stretch_server_linux5.3.5_v1.0.img + +To attach the image as an USB mass storage device to the machine, +simply append to the command: + +.. code-block:: bash + + -drive if=none,id=stick,file=myimage.img \ + -device usb-storage,bus=usb-bus.0,drive=stick + +Instead of providing a custom Linux kernel via the -kernel command you may also +choose to let the Orange Pi PC machine load the bootloader from SD card, just like +a real board would do using the BootROM. Simply pass the selected image via the -sd +argument and remove the -kernel, -append, -dbt and -initrd arguments: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -sd Armbian_19.11.3_Orangepipc_buster_current_5.3.9.img + +Note that both the official Orange Pi PC images and Armbian images start +a lot of userland programs via systemd. Depending on the host hardware and OS, +they may be slow to emulate, especially due to emulating the 4 cores. +To help reduce the performance slow down due to emulating the 4 cores, you can +give the following kernel parameters via U-Boot (or via -append): + +.. code-block:: bash + + => setenv extraargs 'systemd.default_timeout_start_sec=9000 loglevel=7 nosmp console=ttyS0,115200' + +Running U-Boot +"""""""""""""" + +U-Boot mainline can be build and configured using the orangepi_pc_defconfig +using similar commands as describe above for Linux. Note that it is recommended +for development/testing to select the following configuration setting in U-Boot: + + Device Tree Control > Provider for DTB for DT Control > Embedded DTB + +To start U-Boot using the Orange Pi PC machine, provide the +u-boot binary to the -kernel argument: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -kernel /path/to/uboot/u-boot -sd disk.img + +Use the following U-boot commands to load and boot a Linux kernel from SD card: + +.. code-block:: bash + + => setenv bootargs console=ttyS0,115200 + => ext2load mmc 0 0x42000000 zImage + => ext2load mmc 0 0x43000000 sun8i-h3-orangepi-pc.dtb + => bootz 0x42000000 - 0x43000000 + +Running NetBSD +"""""""""""""" + +The NetBSD operating system also includes support for Allwinner H3 based boards, +including the Orange Pi PC. NetBSD 9.0 is known to work best for the Orange Pi PC +board and provides a fully working system with serial console, networking and storage. +For the Orange Pi PC machine, get the 'evbarm-earmv7hf' based image from: + + https://cdn.netbsd.org/pub/NetBSD/NetBSD-9.0/evbarm-earmv7hf/binary/gzimg/armv7.img.gz + +The image requires manually installing U-Boot in the image. Build U-Boot with +the orangepi_pc_defconfig configuration as described in the previous section. +Next, unzip the NetBSD image and write the U-Boot binary including SPL using: + +.. code-block:: bash + + $ gunzip armv7.img.gz + $ dd if=/path/to/u-boot-sunxi-with-spl.bin of=armv7.img bs=1024 seek=8 conv=notrunc + +Finally, before starting the machine the SD image must be extended such +that the NetBSD kernel will not conclude the NetBSD partition is larger than +the emulated SD card: + +.. code-block:: bash + + $ dd if=/dev/zero bs=1M count=64 >> armv7.img + +Start the machine using the following command: + +.. code-block:: bash + + $ qemu-system-arm -M orangepi-pc -nic user -nographic \ + -sd armv7.img -global allwinner-rtc.base-year=2000 + +At the U-Boot stage, interrupt the automatic boot process by pressing a key +and set the following environment variables before booting: + +.. code-block:: bash + + => setenv bootargs root=ld0a + => setenv kernel netbsd-GENERIC.ub + => setenv fdtfile dtb/sun8i-h3-orangepi-pc.dtb + => setenv bootcmd 'fatload mmc 0:1 ${kernel_addr_r} ${kernel}; fatload mmc 0:1 ${fdt_addr_r} ${fdtfile}; fdt addr ${fdt_addr_r}; bootm ${kernel_addr_r} - ${fdt_addr_r}' + +Optionally you may save the environment variables to SD card with 'saveenv'. +To continue booting simply give the 'boot' command and NetBSD boots. + +Orange Pi PC acceptance tests +""""""""""""""""""""""""""""" + +The Orange Pi PC machine has several acceptance tests included. +To run the whole set of tests, build QEMU from source and simply +provide the following command: + +.. code-block:: bash + + $ AVOCADO_ALLOW_LARGE_STORAGE=yes avocado --show=app,console run \ + -t machine:orangepi-pc tests/acceptance/boot_linux_console.py diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running ``qemu-system-aarch64 --machine help``. .. toctree:: + :maxdepth: 1 arm/integratorcp arm/versatile @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/stellaris arm/musicpal arm/sx1 + arm/orangepi Arm CPU features ================ -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Mention 'max' value in the gic-version property description. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-2-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", "Set GIC version. " - "Valid values are 2, 3 and host", NULL); + "Valid values are 2, 3, host and max", + NULL); vms->highmem_ecam = !vmc->no_highmem_ecam; -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> We plan to introduce yet another value for the gic version (nosel). As we already use exotic values such as 0 and -1, let's introduce a dedicated enum type and let vms->gic_version take this type. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-3-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 11 +++++++++-- hw/arm/virt.c | 30 +++++++++++++++--------------- 2 files changed, 24 insertions(+), 17 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef enum VirtIOMMUType { VIRT_IOMMU_VIRTIO, } VirtIOMMUType; +typedef enum VirtGICType { + VIRT_GIC_VERSION_MAX, + VIRT_GIC_VERSION_HOST, + VIRT_GIC_VERSION_2, + VIRT_GIC_VERSION_3, +} VirtGICType; + typedef struct MemMapEntry { hwaddr base; hwaddr size; @@ -XXX,XX +XXX,XX @@ typedef struct { bool highmem_ecam; bool its; bool virt; - int32_t gic_version; + VirtGICType gic_version; VirtIOMMUType iommu; uint16_t virtio_iommu_bdf; struct arm_boot_info bootinfo; @@ -XXX,XX +XXX,XX @@ static inline int virt_gicv3_redist_region_count(VirtMachineState *vms) uint32_t redist0_capacity = vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; - assert(vms->gic_version == 3); + assert(vms->gic_version == VIRT_GIC_VERSION_3); return vms->smp_cpus > redist0_capacity ? 2 : 1; } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void fdt_add_timer_nodes(const VirtMachineState *vms) irqflags = GIC_FDT_IRQ_FLAGS_EDGE_LO_HI; } - if (vms->gic_version == 2) { + if (vms->gic_version == VIRT_GIC_VERSION_2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, (1 << vms->smp_cpus) - 1); @@ -XXX,XX +XXX,XX @@ static void fdt_add_gic_node(VirtMachineState *vms) qemu_fdt_setprop_cell(vms->fdt, nodename, "#address-cells", 0x2); qemu_fdt_setprop_cell(vms->fdt, nodename, "#size-cells", 0x2); qemu_fdt_setprop(vms->fdt, nodename, "ranges", NULL, 0); - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { int nb_redist_regions = virt_gicv3_redist_region_count(vms); qemu_fdt_setprop_string(vms->fdt, nodename, "compatible", @@ -XXX,XX +XXX,XX @@ static void fdt_add_pmu_nodes(const VirtMachineState *vms) } } - if (vms->gic_version == 2) { + if (vms->gic_version == VIRT_GIC_VERSION_2) { irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START, GIC_FDT_IRQ_PPI_CPU_WIDTH, (1 << vms->smp_cpus) - 1); @@ -XXX,XX +XXX,XX @@ static uint64_t virt_cpu_mp_affinity(VirtMachineState *vms, int idx) * purposes are to make TCG consistent (with 64-bit KVM hosts) * and to improve SGI efficiency. */ - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { clustersz = GICV3_TARGETLIST_BITS; } else { clustersz = GIC_TARGETLIST_BITS; @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* We can probe only here because during property set * KVM is not available yet */ - if (vms->gic_version <= 0) { - /* "host" or "max" */ + if (vms->gic_version == VIRT_GIC_VERSION_HOST || + vms->gic_version == VIRT_GIC_VERSION_MAX) { if (!kvm_enabled()) { - if (vms->gic_version == 0) { + if (vms->gic_version == VIRT_GIC_VERSION_HOST) { error_report("gic-version=host requires KVM"); exit(1); } else { /* "max": currently means 3 for TCG */ - vms->gic_version = 3; + vms->gic_version = VIRT_GIC_VERSION_3; } } else { vms->gic_version = kvm_arm_vgic_probe(); @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* The maximum number of CPUs depends on the GIC version, or on how * many redistributors we can fit into the memory map. */ - if (vms->gic_version == 3) { + if (vms->gic_version == VIRT_GIC_VERSION_3) { virt_max_cpus = vms->memmap[VIRT_GIC_REDIST].size / GICV3_REDIST_SIZE; virt_max_cpus += @@ -XXX,XX +XXX,XX @@ static void virt_set_its(Object *obj, bool value, Error **errp) static char *virt_get_gic_version(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); - const char *val = vms->gic_version == 3 ? "3" : "2"; + const char *val = vms->gic_version == VIRT_GIC_VERSION_3 ? "3" : "2"; return g_strdup(val); } @@ -XXX,XX +XXX,XX @@ static void virt_set_gic_version(Object *obj, const char *value, Error **errp) VirtMachineState *vms = VIRT_MACHINE(obj); if (!strcmp(value, "3")) { - vms->gic_version = 3; + vms->gic_version = VIRT_GIC_VERSION_3; } else if (!strcmp(value, "2")) { - vms->gic_version = 2; + vms->gic_version = VIRT_GIC_VERSION_2; } else if (!strcmp(value, "host")) { - vms->gic_version = 0; /* Will probe later */ + vms->gic_version = VIRT_GIC_VERSION_HOST; /* Will probe later */ } else if (!strcmp(value, "max")) { - vms->gic_version = -1; /* Will probe later */ + vms->gic_version = VIRT_GIC_VERSION_MAX; /* Will probe later */ } else { error_setg(errp, "Invalid gic-version value"); error_append_hint(errp, "Valid values are 3, 2, host, max.\n"); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "physical address space above 32 bits", NULL); /* Default GIC type is v2 */ - vms->gic_version = 2; + vms->gic_version = VIRT_GIC_VERSION_2; object_property_add_str(obj, "gic-version", virt_get_gic_version, virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Let's move the code which freezes which gic-version to be applied in a dedicated function. We also now set by default the VIRT_GIC_VERSION_NO_SET. This eventually turns into the legacy v2 choice in the finalize() function. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-4-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 1 + hw/arm/virt.c | 54 ++++++++++++++++++++++++++----------------- 2 files changed, 34 insertions(+), 21 deletions(-) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef enum VirtGICType { VIRT_GIC_VERSION_HOST, VIRT_GIC_VERSION_2, VIRT_GIC_VERSION_3, + VIRT_GIC_VERSION_NOSEL, } VirtGICType; typedef struct MemMapEntry { diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) } } +/* + * finalize_gic_version - Determines the final gic_version + * according to the gic-version property + * + * Default GIC type is v2 + */ +static void finalize_gic_version(VirtMachineState *vms) +{ + if (vms->gic_version == VIRT_GIC_VERSION_HOST || + vms->gic_version == VIRT_GIC_VERSION_MAX) { + if (!kvm_enabled()) { + if (vms->gic_version == VIRT_GIC_VERSION_HOST) { + error_report("gic-version=host requires KVM"); + exit(1); + } else { + /* "max": currently means 3 for TCG */ + vms->gic_version = VIRT_GIC_VERSION_3; + } + } else { + vms->gic_version = kvm_arm_vgic_probe(); + if (!vms->gic_version) { + error_report( + "Unable to determine GIC version supported by host"); + exit(1); + } + } + } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { + vms->gic_version = VIRT_GIC_VERSION_2; + } +} + static void machvirt_init(MachineState *machine) { VirtMachineState *vms = VIRT_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) /* We can probe only here because during property set * KVM is not available yet */ - if (vms->gic_version == VIRT_GIC_VERSION_HOST || - vms->gic_version == VIRT_GIC_VERSION_MAX) { - if (!kvm_enabled()) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST) { - error_report("gic-version=host requires KVM"); - exit(1); - } else { - /* "max": currently means 3 for TCG */ - vms->gic_version = VIRT_GIC_VERSION_3; - } - } else { - vms->gic_version = kvm_arm_vgic_probe(); - if (!vms->gic_version) { - error_report( - "Unable to determine GIC version supported by host"); - exit(1); - } - } - } + finalize_gic_version(vms); if (!cpu_type_valid(machine->cpu_type)) { error_report("mach-virt: CPU type %s not supported", machine->cpu_type); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "Set on/off to enable/disable using " "physical address space above 32 bits", NULL); - /* Default GIC type is v2 */ - vms->gic_version = VIRT_GIC_VERSION_2; + vms->gic_version = VIRT_GIC_VERSION_NOSEL; object_property_add_str(obj, "gic-version", virt_get_gic_version, virt_set_gic_version, NULL); object_property_set_description(obj, "gic-version", -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Convert kvm_arm_vgic_probe() so that it returns a bitmap of supported in-kernel emulation VGIC versions instead of the max version: at the moment values can be v2 and v3. This allows to expose the case where the host GICv3 also supports GICv2 emulation. This will be useful to choose the default version in KVM accelerated mode. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200311131618.7187-5-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm_arm.h | 3 +++ hw/arm/virt.c | 11 +++++++++-- target/arm/kvm.c | 14 ++++++++------ 3 files changed, 20 insertions(+), 8 deletions(-) diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ #include "exec/memory.h" #include "qemu/error-report.h" +#define KVM_ARM_VGIC_V2 (1 << 0) +#define KVM_ARM_VGIC_V3 (1 << 1) + /** * kvm_arm_vcpu_init: * @cs: CPUState diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) vms->gic_version = VIRT_GIC_VERSION_3; } } else { - vms->gic_version = kvm_arm_vgic_probe(); - if (!vms->gic_version) { + int probe_bitmap = kvm_arm_vgic_probe(); + + if (!probe_bitmap) { error_report( "Unable to determine GIC version supported by host"); exit(1); + } else { + if (probe_bitmap & KVM_ARM_VGIC_V3) { + vms->gic_version = VIRT_GIC_VERSION_3; + } else { + vms->gic_version = VIRT_GIC_VERSION_2; + } } } } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_irqchip_create(KVMState *s) int kvm_arm_vgic_probe(void) { + int val = 0; + if (kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V3, true) == 0) { - return 3; - } else if (kvm_create_device(kvm_state, - KVM_DEV_TYPE_ARM_VGIC_V2, true) == 0) { - return 2; - } else { - return 0; + val |= KVM_ARM_VGIC_V3; } + if (kvm_create_device(kvm_state, + KVM_DEV_TYPE_ARM_VGIC_V2, true) == 0) { + val |= KVM_ARM_VGIC_V2; + } + return val; } int kvm_arm_set_irq(int cpu, int irqtype, int irq, int level) -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Restructure the finalize_gic_version with switch cases and clearly separate the following cases: - KVM mode / in-kernel irqchip - KVM mode / userspace irqchip - TCG mode In KVM mode / in-kernel irqchip , we explictly check whether the chosen version is supported by the host. If the end-user explicitly sets v2/v3 and this is not supported by the host, then the user gets an explicit error message. Note that for old kernels where the CREATE_DEVICE ioctl doesn't exist then we will now fail if the user specifically asked for gicv2, where previously we (probably) would have succeeded. In KVM mode / userspace irqchip we immediatly output an error in case the end-user explicitly selected v3. Also we warn the end-user about the unexpected usage of gic-version=host in that case as only userspace GICv2 is supported. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-6-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 88 +++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 67 insertions(+), 21 deletions(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) */ static void finalize_gic_version(VirtMachineState *vms) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST || - vms->gic_version == VIRT_GIC_VERSION_MAX) { - if (!kvm_enabled()) { - if (vms->gic_version == VIRT_GIC_VERSION_HOST) { - error_report("gic-version=host requires KVM"); - exit(1); - } else { - /* "max": currently means 3 for TCG */ - vms->gic_version = VIRT_GIC_VERSION_3; - } - } else { - int probe_bitmap = kvm_arm_vgic_probe(); + if (kvm_enabled()) { + int probe_bitmap; - if (!probe_bitmap) { + if (!kvm_irqchip_in_kernel()) { + switch (vms->gic_version) { + case VIRT_GIC_VERSION_HOST: + warn_report( + "gic-version=host not relevant with kernel-irqchip=off " + "as only userspace GICv2 is supported. Using v2 ..."); + return; + case VIRT_GIC_VERSION_MAX: + case VIRT_GIC_VERSION_NOSEL: + vms->gic_version = VIRT_GIC_VERSION_2; + return; + case VIRT_GIC_VERSION_2: + return; + case VIRT_GIC_VERSION_3: error_report( - "Unable to determine GIC version supported by host"); + "gic-version=3 is not supported with kernel-irqchip=off"); exit(1); - } else { - if (probe_bitmap & KVM_ARM_VGIC_V3) { - vms->gic_version = VIRT_GIC_VERSION_3; - } else { - vms->gic_version = VIRT_GIC_VERSION_2; - } } } - } else if (vms->gic_version == VIRT_GIC_VERSION_NOSEL) { + + probe_bitmap = kvm_arm_vgic_probe(); + if (!probe_bitmap) { + error_report("Unable to determine GIC version supported by host"); + exit(1); + } + + switch (vms->gic_version) { + case VIRT_GIC_VERSION_HOST: + case VIRT_GIC_VERSION_MAX: + if (probe_bitmap & KVM_ARM_VGIC_V3) { + vms->gic_version = VIRT_GIC_VERSION_3; + } else { + vms->gic_version = VIRT_GIC_VERSION_2; + } + return; + case VIRT_GIC_VERSION_NOSEL: + vms->gic_version = VIRT_GIC_VERSION_2; + break; + case VIRT_GIC_VERSION_2: + case VIRT_GIC_VERSION_3: + break; + } + + /* Check chosen version is effectively supported by the host */ + if (vms->gic_version == VIRT_GIC_VERSION_2 && + !(probe_bitmap & KVM_ARM_VGIC_V2)) { + error_report("host does not support in-kernel GICv2 emulation"); + exit(1); + } else if (vms->gic_version == VIRT_GIC_VERSION_3 && + !(probe_bitmap & KVM_ARM_VGIC_V3)) { + error_report("host does not support in-kernel GICv3 emulation"); + exit(1); + } + return; + } + + /* TCG mode */ + switch (vms->gic_version) { + case VIRT_GIC_VERSION_NOSEL: vms->gic_version = VIRT_GIC_VERSION_2; + break; + case VIRT_GIC_VERSION_MAX: + vms->gic_version = VIRT_GIC_VERSION_3; + break; + case VIRT_GIC_VERSION_HOST: + error_report("gic-version=host requires KVM"); + exit(1); + case VIRT_GIC_VERSION_2: + case VIRT_GIC_VERSION_3: + break; } } -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> At the moment if the end-user does not specify the gic-version along with KVM acceleration, v2 is set by default. However most of the systems now have GICv3 and sometimes they do not support GICv2 compatibility. This patch keeps the default v2 selection in all cases except in the KVM accelerated mode when either - the host does not support GICv2 in-kernel emulation or - number of VCPUS exceeds 8. Those cases did not work anyway so we do not break any compatibility. Now we get v3 selected in such a case. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reported-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200311131618.7187-7-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_memmap(VirtMachineState *vms) */ static void finalize_gic_version(VirtMachineState *vms) { + unsigned int max_cpus = MACHINE(vms)->smp.max_cpus; + if (kvm_enabled()) { int probe_bitmap; @@ -XXX,XX +XXX,XX @@ static void finalize_gic_version(VirtMachineState *vms) } return; case VIRT_GIC_VERSION_NOSEL: - vms->gic_version = VIRT_GIC_VERSION_2; + if ((probe_bitmap & KVM_ARM_VGIC_V2) && max_cpus <= GIC_NCPU) { + vms->gic_version = VIRT_GIC_VERSION_2; + } else if (probe_bitmap & KVM_ARM_VGIC_V3) { + /* + * in case the host does not support v2 in-kernel emulation or + * the end-user requested more than 8 VCPUs we now default + * to v3. In any case defaulting to v2 would be broken. + */ + vms->gic_version = VIRT_GIC_VERSION_3; + } else if (max_cpus > GIC_NCPU) { + error_report("host only supports in-kernel GICv2 emulation " + "but more than 8 vcpus are requested"); + exit(1); + } break; case VIRT_GIC_VERSION_2: case VIRT_GIC_VERSION_3: -- 2.20.1 From: Beata Michalska <beata.michalska@linaro.org> KVM_SET_VCPU_EVENTS might actually lead to vcpu registers being modified. As such this should be the last step of sync to avoid potential overwriting of whatever changes KVM might have done. Signed-off-by: Beata Michalska <beata.michalska@linaro.org> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200312003401.29017-2-beata.michalska@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm32.c | 15 ++++++++++----- target/arm/kvm64.c | 15 ++++++++++----- 2 files changed, 20 insertions(+), 10 deletions(-) diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - ret = kvm_put_vcpu_events(cpu); - if (ret) { - return ret; - } - write_cpustate_to_list(cpu, true); if (!write_list_to_kvmstate(cpu, level)) { return EINVAL; } + /* + * Setting VCPU events should be triggered after syncing the registers + * to avoid overwriting potential changes made by KVM upon calling + * KVM_SET_VCPU_EVENTS ioctl + */ + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + kvm_arm_sync_mpstate_to_kvm(cpu); return ret; diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - ret = kvm_put_vcpu_events(cpu); - if (ret) { - return ret; - } - write_cpustate_to_list(cpu, true); if (!write_list_to_kvmstate(cpu, level)) { return -EINVAL; } + /* + * Setting VCPU events should be triggered after syncing the registers + * to avoid overwriting potential changes made by KVM upon calling + * KVM_SET_VCPU_EVENTS ioctl + */ + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + kvm_arm_sync_mpstate_to_kvm(cpu); return ret; -- 2.20.1