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 The following changes since commit 3db29dcac23da85486704ef9e7a8e7217f7829cd: Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2023-01-12 13:51:36 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230113 for you to fetch changes up to 08899b5c68a55a3780d707e2464073c8f2670d31: target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled (2023-01-13 13:19:36 +0000) ---------------------------------------------------------------- target-arm queue: hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 board cubieboard: Support booting from an SD card image with u-boot on it target/arm: Fix sve_probe_page target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled various code cleanups ---------------------------------------------------------------- Evgeny Iakovlev (1): target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled Felipe Balbi (2): hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 Philippe Mathieu-Daudé (27): hw/arm/pxa2xx: Simplify pxa255_init() hw/arm/pxa2xx: Simplify pxa270_init() hw/arm/collie: Use the IEC binary prefix definitions hw/arm/collie: Simplify flash creation using for() loop hw/arm/gumstix: Improve documentation hw/arm/gumstix: Use the IEC binary prefix definitions hw/arm/mainstone: Use the IEC binary prefix definitions hw/arm/musicpal: Use the IEC binary prefix definitions hw/arm/omap_sx1: Remove unused 'total_ram' definitions hw/arm/omap_sx1: Use the IEC binary prefix definitions hw/arm/z2: Use the IEC binary prefix definitions hw/arm/vexpress: Remove dead code in vexpress_common_init() hw/arm: Remove unreachable code calling pflash_cfi01_register() hw/arm/pxa: Avoid forward-declaring PXA2xxI2CState hw/gpio/omap_gpio: Add local variable to avoid embedded cast hw/arm/omap: Drop useless casts from void * to pointer hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP1_GPIO type name hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP2_GPIO type name hw/intc/omap_intc: Use CamelCase for TYPE_OMAP_INTC type name hw/arm/stellaris: Drop useless casts from void * to pointer hw/arm/stellaris: Use CamelCase for STELLARIS_ADC type name hw/arm/bcm2836: Remove definitions generated by OBJECT_DECLARE_TYPE() hw/arm/npcm7xx: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/misc/sbsa_ec: Rename TYPE_SBSA_EC -> TYPE_SBSA_SECURE_EC hw/misc/sbsa_ec: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/intc/xilinx_intc: Use 'XpsIntc' typedef instead of 'struct xlx_pic' hw/timer/xilinx_timer: Use XpsTimerState instead of 'struct timerblock' Richard Henderson (1): target/arm: Fix sve_probe_page Strahinja Jankovic (7): hw/misc: Allwinner-A10 Clock Controller Module Emulation hw/misc: Allwinner A10 DRAM Controller Emulation {hw/i2c,docs/system/arm}: Allwinner TWI/I2C Emulation hw/misc: AXP209 PMU Emulation hw/arm: Add AXP209 to Cubieboard hw/arm: Allwinner A10 enable SPL load from MMC tests/avocado: Add SD boot test to Cubieboard docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + include/hw/adc/npcm7xx_adc.h | 7 +- include/hw/arm/allwinner-a10.h | 27 ++ include/hw/arm/allwinner-h3.h | 3 + include/hw/arm/npcm7xx.h | 18 +- include/hw/arm/omap.h | 24 +- include/hw/arm/pxa.h | 11 +- include/hw/arm/stm32f405_soc.h | 5 +- include/hw/i2c/allwinner-i2c.h | 55 ++++ include/hw/i2c/npcm7xx_smbus.h | 7 +- include/hw/misc/allwinner-a10-ccm.h | 67 +++++ include/hw/misc/allwinner-a10-dramc.h | 68 +++++ include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +- include/hw/misc/npcm7xx_mft.h | 7 +- include/hw/misc/npcm7xx_pwm.h | 3 +- include/hw/misc/npcm7xx_rng.h | 6 +- include/hw/net/npcm7xx_emc.h | 5 +- include/hw/sd/npcm7xx_sdhci.h | 4 +- hw/arm/allwinner-a10.c | 40 +++ hw/arm/allwinner-h3.c | 11 +- hw/arm/bcm2836.c | 9 +- hw/arm/collie.c | 25 +- hw/arm/cubieboard.c | 11 + hw/arm/gumstix.c | 45 ++-- hw/arm/mainstone.c | 37 ++- hw/arm/musicpal.c | 9 +- hw/arm/olimex-stm32-h405.c | 69 +++++ hw/arm/omap1.c | 115 ++++---- hw/arm/omap2.c | 40 ++- hw/arm/omap_sx1.c | 53 ++-- hw/arm/palm.c | 2 +- hw/arm/pxa2xx.c | 8 +- hw/arm/spitz.c | 6 +- hw/arm/stellaris.c | 73 +++-- hw/arm/stm32f405_soc.c | 8 + hw/arm/tosa.c | 2 +- hw/arm/versatilepb.c | 6 +- hw/arm/vexpress.c | 10 +- hw/arm/z2.c | 16 +- hw/char/omap_uart.c | 7 +- hw/display/omap_dss.c | 15 +- hw/display/omap_lcdc.c | 9 +- hw/dma/omap_dma.c | 15 +- hw/gpio/omap_gpio.c | 48 ++-- hw/i2c/allwinner-i2c.c | 459 ++++++++++++++++++++++++++++++++ hw/intc/omap_intc.c | 38 +-- hw/intc/xilinx_intc.c | 28 +- hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++ hw/misc/allwinner-a10-dramc.c | 179 +++++++++++++ hw/misc/axp209.c | 238 +++++++++++++++++ hw/misc/omap_gpmc.c | 12 +- hw/misc/omap_l4.c | 7 +- hw/misc/omap_sdrc.c | 7 +- hw/misc/omap_tap.c | 5 +- hw/misc/sbsa_ec.c | 12 +- hw/sd/omap_mmc.c | 9 +- hw/ssi/omap_spi.c | 7 +- hw/timer/omap_gptimer.c | 22 +- hw/timer/omap_synctimer.c | 4 +- hw/timer/xilinx_timer.c | 27 +- target/arm/helper.c | 3 + target/arm/sve_helper.c | 14 +- MAINTAINERS | 8 + hw/arm/Kconfig | 9 + hw/arm/meson.build | 1 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + hw/misc/Kconfig | 10 + hw/misc/meson.build | 3 + hw/misc/trace-events | 5 + tests/avocado/boot_linux_console.py | 47 ++++ 76 files changed, 1951 insertions(+), 455 deletions(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/arm/olimex-stm32-h405.c create mode 100644 hw/i2c/allwinner-i2c.c create mode 100644 hw/misc/allwinner-a10-ccm.c create mode 100644 hw/misc/allwinner-a10-dramc.c create mode 100644 hw/misc/axp209.c From: Felipe Balbi <balbi@kernel.org> STM32F405 has 128K of SRAM and another 64K of CCM (Core-coupled Memory) at a different base address. Correctly describe the memory layout to give existing FW images a chance to run unmodified. Reviewed-by: Alistair Francis <alistair@alistair23.me> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Felipe Balbi <balbi@kernel.org> Message-id: 20221230145733.200496-2-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/stm32f405_soc.h | 5 ++++- hw/arm/stm32f405_soc.c | 8 ++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/stm32f405_soc.h b/include/hw/arm/stm32f405_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f405_soc.h +++ b/include/hw/arm/stm32f405_soc.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(STM32F405State, STM32F405_SOC) #define FLASH_BASE_ADDRESS 0x08000000 #define FLASH_SIZE (1024 * 1024) #define SRAM_BASE_ADDRESS 0x20000000 -#define SRAM_SIZE (192 * 1024) +#define SRAM_SIZE (128 * 1024) +#define CCM_BASE_ADDRESS 0x10000000 +#define CCM_SIZE (64 * 1024) struct STM32F405State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ struct STM32F405State { STM32F2XXADCState adc[STM_NUM_ADCS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; + MemoryRegion ccm; MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) } memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); + memory_region_init_ram(&s->ccm, NULL, "STM32F405.ccm", CCM_SIZE, + &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + memory_region_add_subregion(system_memory, CCM_BASE_ADDRESS, &s->ccm); + armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); -- 2.34.1 From: Felipe Balbi <balbi@kernel.org> Olimex makes a series of low-cost STM32 boards. This commit introduces the minimum setup to support SMT32-H405. See [1] for details [1] https://www.olimex.com/Products/ARM/ST/STM32-H405/ Signed-off-by: Felipe Balbi <balbi@kernel.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20221230145733.200496-3-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + hw/arm/olimex-stm32-h405.c | 69 +++++++++++++++++++++++++ MAINTAINERS | 6 +++ hw/arm/Kconfig | 4 ++ hw/arm/meson.build | 1 + 6 files changed, 82 insertions(+) create mode 100644 hw/arm/olimex-stm32-h405.c diff --git a/docs/system/arm/stm32.rst b/docs/system/arm/stm32.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/stm32.rst +++ b/docs/system/arm/stm32.rst @@ -XXX,XX +XXX,XX @@ The STM32F4 series is based on ARM Cortex-M4F core. This series is pin-to-pin compatible with STM32F2 series. The following machines are based on this chip : - ``netduinoplus2`` Netduino Plus 2 board with STM32F405RGT6 microcontroller +- ``olimex-stm32-h405`` Olimex STM32 H405 board with STM32F405RGT6 microcontroller There are many other STM32 series that are currently not supported by QEMU. diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ CONFIG_COLLIE=y CONFIG_ASPEED_SOC=y CONFIG_NETDUINO2=y CONFIG_NETDUINOPLUS2=y +CONFIG_OLIMEX_STM32_H405=y CONFIG_MPS2=y CONFIG_RASPI=y CONFIG_DIGIC=y diff --git a/hw/arm/olimex-stm32-h405.c b/hw/arm/olimex-stm32-h405.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/olimex-stm32-h405.c @@ -XXX,XX +XXX,XX @@ +/* + * ST STM32VLDISCOVERY machine + * Olimex STM32-H405 machine + * + * Copyright (c) 2022 Felipe Balbi <balbi@kernel.org> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" +#include "qemu/error-report.h" +#include "hw/arm/stm32f405_soc.h" +#include "hw/arm/boot.h" + +/* olimex-stm32-h405 implementation is derived from netduinoplus2 */ + +/* Main SYSCLK frequency in Hz (168MHz) */ +#define SYSCLK_FRQ 168000000ULL + +static void olimex_stm32_h405_init(MachineState *machine) +{ + DeviceState *dev; + Clock *sysclk; + + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + + dev = qdev_new(TYPE_STM32F405_SOC); + qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); + qdev_connect_clock_in(dev, "sysclk", sysclk); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + + armv7m_load_kernel(ARM_CPU(first_cpu), + machine->kernel_filename, + 0, FLASH_SIZE); +} + +static void olimex_stm32_h405_machine_init(MachineClass *mc) +{ + mc->desc = "Olimex STM32-H405 (Cortex-M4)"; + mc->init = olimex_stm32_h405_init; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); + + /* SRAM pre-allocated as part of the SoC instantiation */ + mc->default_ram_size = 0; +} + +DEFINE_MACHINE("olimex-stm32-h405", olimex_stm32_h405_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/arm/netduinoplus2.c +Olimex STM32 H405 +M: Felipe Balbi <balbi@kernel.org> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/olimex-stm32-h405.c + SmartFusion2 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> 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 NETDUINOPLUS2 bool select STM32F405_SOC +config OLIMEX_STM32_H405 + bool + select STM32F405_SOC + config NSERIES bool select OMAP diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) +arm_ss.add(when: 'CONFIG_OLIMEX_STM32_H405', if_true: files('olimex-stm32-h405.c')) arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several Clock Controller Module (CCM) registers are read, most important are PLL and Tuning, as well as divisor registers. This patch adds these registers and initializes reset values from user's guide. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-2-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-ccm.h | 67 +++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 305 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 hw/misc/allwinner-a10-ccm.c 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/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/misc/allwinner-a10-ccm.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { /*< public >*/ ARMCPU cpu; + AwA10ClockCtlState ccm; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-ccm.h b/include/hw/misc/allwinner-a10-ccm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-ccm.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * 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_A10_CCM_H +#define HW_MISC_ALLWINNER_A10_CCM_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCM device */ +#define AW_A10_CCM_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_A10_CCM_REGS_NUM (AW_A10_CCM_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_CCM "allwinner-a10-ccm" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10ClockCtlState, AW_A10_CCM) + +/** @} */ + +/** + * Allwinner A10 CCM object instance state. + */ +struct AwA10ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_CCM_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_H3_CCU_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/usb/hcd-ohci.h" #define AW_A10_MMC0_BASE 0x01c0f000 +#define AW_A10_CCM_BASE 0x01c20000 #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) object_initialize_child(obj, "timer", &s->timer, TYPE_AW_A10_PIT); + object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), 0x00000000, &s->sram_a); create_unimplemented_device("a10-sram-ctrl", 0x01c00000, 4 * KiB); + /* Clock Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-ccm.c b/hw/misc/allwinner-a10-ccm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-ccm.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * 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-a10-ccm.h" + +/* CCM register offsets */ +enum { + REG_PLL1_CFG = 0x0000, /* PLL1 Control */ + REG_PLL1_TUN = 0x0004, /* PLL1 Tuning */ + REG_PLL2_CFG = 0x0008, /* PLL2 Control */ + REG_PLL2_TUN = 0x000C, /* PLL2 Tuning */ + REG_PLL3_CFG = 0x0010, /* PLL3 Control */ + REG_PLL4_CFG = 0x0018, /* PLL4 Control */ + REG_PLL5_CFG = 0x0020, /* PLL5 Control */ + REG_PLL5_TUN = 0x0024, /* PLL5 Tuning */ + REG_PLL6_CFG = 0x0028, /* PLL6 Control */ + REG_PLL6_TUN = 0x002C, /* PLL6 Tuning */ + REG_PLL7_CFG = 0x0030, /* PLL7 Control */ + REG_PLL1_TUN2 = 0x0038, /* PLL1 Tuning2 */ + REG_PLL5_TUN2 = 0x003C, /* PLL5 Tuning2 */ + REG_PLL8_CFG = 0x0040, /* PLL8 Control */ + REG_OSC24M_CFG = 0x0050, /* OSC24M Control */ + REG_CPU_AHB_APB0_CFG = 0x0054, /* CPU, AHB and APB0 Divide Ratio */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCM register reset values */ +enum { + REG_PLL1_CFG_RST = 0x21005000, + REG_PLL1_TUN_RST = 0x0A101000, + REG_PLL2_CFG_RST = 0x08100010, + REG_PLL2_TUN_RST = 0x00000000, + REG_PLL3_CFG_RST = 0x0010D063, + REG_PLL4_CFG_RST = 0x21009911, + REG_PLL5_CFG_RST = 0x11049280, + REG_PLL5_TUN_RST = 0x14888000, + REG_PLL6_CFG_RST = 0x21009911, + REG_PLL6_TUN_RST = 0x00000000, + REG_PLL7_CFG_RST = 0x0010D063, + REG_PLL1_TUN2_RST = 0x00000000, + REG_PLL5_TUN2_RST = 0x00000000, + REG_PLL8_CFG_RST = 0x21009911, + REG_OSC24M_CFG_RST = 0x00138013, + REG_CPU_AHB_APB0_CFG_RST = 0x00010010, +}; + +static uint64_t allwinner_a10_ccm_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_ccm_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_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_a10_ccm_ops = { + .read = allwinner_a10_ccm_read, + .write = allwinner_a10_ccm_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_ccm_reset_enter(Object *obj, ResetType type) +{ + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL1_CFG)] = REG_PLL1_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN)] = REG_PLL1_TUN_RST; + s->regs[REG_INDEX(REG_PLL2_CFG)] = REG_PLL2_CFG_RST; + s->regs[REG_INDEX(REG_PLL2_TUN)] = REG_PLL2_TUN_RST; + s->regs[REG_INDEX(REG_PLL3_CFG)] = REG_PLL3_CFG_RST; + s->regs[REG_INDEX(REG_PLL4_CFG)] = REG_PLL4_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_CFG)] = REG_PLL5_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_TUN)] = REG_PLL5_TUN_RST; + s->regs[REG_INDEX(REG_PLL6_CFG)] = REG_PLL6_CFG_RST; + s->regs[REG_INDEX(REG_PLL6_TUN)] = REG_PLL6_TUN_RST; + s->regs[REG_INDEX(REG_PLL7_CFG)] = REG_PLL7_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN2)] = REG_PLL1_TUN2_RST; + s->regs[REG_INDEX(REG_PLL5_TUN2)] = REG_PLL5_TUN2_RST; + s->regs[REG_INDEX(REG_PLL8_CFG)] = REG_PLL8_CFG_RST; + s->regs[REG_INDEX(REG_OSC24M_CFG)] = REG_OSC24M_CFG_RST; + s->regs[REG_INDEX(REG_CPU_AHB_APB0_CFG)] = REG_CPU_AHB_APB0_CFG_RST; +} + +static void allwinner_a10_ccm_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_ccm_ops, s, + TYPE_AW_A10_CCM, AW_A10_CCM_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_ccm_vmstate = { + .name = "allwinner-a10-ccm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10ClockCtlState, AW_A10_CCM_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_ccm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_ccm_reset_enter; + dc->vmsd = &allwinner_a10_ccm_vmstate; +} + +static const TypeInfo allwinner_a10_ccm_info = { + .name = TYPE_AW_A10_CCM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_ccm_init, + .instance_size = sizeof(AwA10ClockCtlState), + .class_init = allwinner_a10_ccm_class_init, +}; + +static void allwinner_a10_ccm_register(void) +{ + type_register_static(&allwinner_a10_ccm_info); +} + +type_init(allwinner_a10_ccm_register) 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 AHCI select ALLWINNER_A10_PIT select ALLWINNER_A10_PIC + select ALLWINNER_A10_CCM select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config VIRT_CTRL config LASI bool +config ALLWINNER_A10_CCM + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several DRAM Controller registers are used. Most important registers are those related to DRAM initialization and calibration, where SPL initiates process and waits until certain bit is set/cleared. This patch adds these registers, initializes reset values from user's guide and updates state of registers as SPL expects it. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-3-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-dramc.h | 68 ++++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-dramc.c | 179 ++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 261 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/misc/allwinner-a10-dramc.c 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/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" +#include "hw/misc/allwinner-a10-dramc.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { ARMCPU cpu; AwA10ClockCtlState ccm; + AwA10DramControllerState dramc; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-dramc.h b/include/hw/misc/allwinner-a10-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * 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_A10_DRAMC_H +#define HW_MISC_ALLWINNER_A10_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/register.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by DRAMC device */ +#define AW_A10_DRAMC_IOSIZE (0x1000) + +/** Total number of known registers */ +#define AW_A10_DRAMC_REGS_NUM (AW_A10_DRAMC_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_DRAMC "allwinner-a10-dramc" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10DramControllerState, AW_A10_DRAMC) + +/** @} */ + +/** + * Allwinner A10 DRAMC object instance state. + */ +struct AwA10DramControllerState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_DRAMC_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_A10_DRAMC_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_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 #define AW_A10_PIC_REG_BASE 0x01c20400 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "dramc", &s->dramc, TYPE_AW_A10_DRAMC); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* DRAM Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->dramc), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, AW_A10_DRAMC_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-dramc.c b/hw/misc/allwinner-a10-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * 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-a10-dramc.h" + +/* DRAMC register offsets */ +enum { + REG_SDR_CCR = 0x0000, + REG_SDR_ZQCR0 = 0x00a8, + REG_SDR_ZQSR = 0x00b0 +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMC register flags */ +enum { + REG_SDR_CCR_DATA_TRAINING = (1 << 30), + REG_SDR_CCR_DRAM_INIT = (1 << 31), +}; +enum { + REG_SDR_ZQSR_ZCAL = (1 << 31), +}; + +/* DRAMC register reset values */ +enum { + REG_SDR_CCR_RESET = 0x80020000, + REG_SDR_ZQCR0_RESET = 0x07b00000, + REG_SDR_ZQSR_RESET = 0x80000000 +}; + +static uint64_t allwinner_a10_dramc_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + case REG_SDR_ZQCR0: + case REG_SDR_ZQSR: + break; + case 0x2e4 ... AW_A10_DRAMC_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_dramc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + if (val & REG_SDR_CCR_DRAM_INIT) { + /* Clear DRAM_INIT to indicate process is done. */ + val &= ~REG_SDR_CCR_DRAM_INIT; + } + if (val & REG_SDR_CCR_DATA_TRAINING) { + /* Clear DATA_TRAINING to indicate process is done. */ + val &= ~REG_SDR_CCR_DATA_TRAINING; + } + break; + case REG_SDR_ZQCR0: + /* Set ZCAL in ZQSR to indicate calibration is done. */ + s->regs[REG_INDEX(REG_SDR_ZQSR)] |= REG_SDR_ZQSR_ZCAL; + break; + case 0x2e4 ... AW_A10_DRAMC_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_a10_dramc_ops = { + .read = allwinner_a10_dramc_read, + .write = allwinner_a10_dramc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_dramc_reset_enter(Object *obj, ResetType type) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_SDR_CCR)] = REG_SDR_CCR_RESET; + s->regs[REG_INDEX(REG_SDR_ZQCR0)] = REG_SDR_ZQCR0_RESET; + s->regs[REG_INDEX(REG_SDR_ZQSR)] = REG_SDR_ZQSR_RESET; +} + +static void allwinner_a10_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_dramc_ops, s, + TYPE_AW_A10_DRAMC, AW_A10_DRAMC_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_dramc_vmstate = { + .name = "allwinner-a10-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10DramControllerState, + AW_A10_DRAMC_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_dramc_reset_enter; + dc->vmsd = &allwinner_a10_dramc_vmstate; +} + +static const TypeInfo allwinner_a10_dramc_info = { + .name = TYPE_AW_A10_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_dramc_init, + .instance_size = sizeof(AwA10DramControllerState), + .class_init = allwinner_a10_dramc_class_init, +}; + +static void allwinner_a10_dramc_register(void) +{ + type_register_static(&allwinner_a10_dramc_info); +} + +type_init(allwinner_a10_dramc_register) 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 ALLWINNER_A10_PIT select ALLWINNER_A10_PIC select ALLWINNER_A10_CCM + select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config LASI config ALLWINNER_A10_CCM bool +config ALLWINNER_A10_DRAMC + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_DRAMC', if_true: files('allwinner-a10-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch implements Allwinner TWI/I2C controller emulation. Only master-mode functionality is implemented. The SPL boot for Cubieboard expects AXP209 PMIC on TWI0/I2C0 bus, so this is first part enabling the TWI/I2C bus operation. Since both Allwinner A10 and H3 use the same module, it is added for both boards. Docs are also updated for Cubieboard and Orangepi-PC board to indicate I2C availability. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-4-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/i2c/allwinner-i2c.h | 55 ++++ hw/arm/allwinner-a10.c | 8 + hw/arm/allwinner-h3.c | 11 +- hw/i2c/allwinner-i2c.c | 459 +++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 2 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + 12 files changed, 551 insertions(+), 1 deletion(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 hw/i2c/allwinner-i2c.c diff --git a/docs/system/arm/cubieboard.rst b/docs/system/arm/cubieboard.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/cubieboard.rst +++ b/docs/system/arm/cubieboard.rst @@ -XXX,XX +XXX,XX @@ Emulated devices: - SDHCI - USB controller - SATA controller +- TWI (I2C) controller diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/orangepi.rst +++ b/docs/system/arm/orangepi.rst @@ -XXX,XX +XXX,XX @@ The Orange Pi PC machine supports the following devices: * Clock Control Unit * System Control module * Security Identifier device + * TWI (I2C) Limitations """"""""""" 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/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; AwSdHostState mmc0; + AWI2CState i2c0; AwRtcState rtc; MemoryRegion sram_a; EHCISysBusState ehci[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/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_DEV_UART2, AW_H3_DEV_UART3, AW_H3_DEV_EMAC, + AW_H3_DEV_TWI0, AW_H3_DEV_DRAMCOM, AW_H3_DEV_DRAMCTL, AW_H3_DEV_DRAMPHY, @@ -XXX,XX +XXX,XX @@ struct AwH3State { AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; + AWI2CState i2c0; AwSun8iEmacState emac; AwRtcState rtc; GICState gic; diff --git a/include/hw/i2c/allwinner-i2c.h b/include/hw/i2c/allwinner-i2c.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/i2c/allwinner-i2c.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface registers definition + * + * Copyright (C) 2022 Strahinja Jankovic. <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * 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 ALLWINNER_I2C_H +#define ALLWINNER_I2C_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_AW_I2C "allwinner.i2c" +OBJECT_DECLARE_SIMPLE_TYPE(AWI2CState, AW_I2C) + +#define AW_I2C_MEM_SIZE 0x24 + +struct AWI2CState { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + I2CBus *bus; + qemu_irq irq; + + uint8_t addr; + uint8_t xaddr; + uint8_t data; + uint8_t cntr; + uint8_t stat; + uint8_t ccr; + uint8_t srst; + uint8_t efr; + uint8_t lcr; +}; + +#endif /* ALLWINNER_I2C_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_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 #define AW_A10_RTC_BASE 0x01c20d00 +#define AW_A10_I2C0_BASE 0x01c2ac00 static void aw_a10_init(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); + object_initialize_child(obj, "i2c0", &s->i2c0, TYPE_AW_I2C); + if (machine_usb(current_machine)) { int i; @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) /* RTC */ sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->rtc), 0, AW_A10_RTC_BASE, 10); + + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, AW_A10_I2C0_BASE); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, qdev_get_gpio_in(dev, 7)); } 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_DEV_UART1] = 0x01c28400, [AW_H3_DEV_UART2] = 0x01c28800, [AW_H3_DEV_UART3] = 0x01c28c00, + [AW_H3_DEV_TWI0] = 0x01c2ac00, [AW_H3_DEV_EMAC] = 0x01c30000, [AW_H3_DEV_DRAMCOM] = 0x01c62000, [AW_H3_DEV_DRAMCTL] = 0x01c63000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "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 }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART1 = 1, AW_H3_GIC_SPI_UART2 = 2, AW_H3_GIC_SPI_UART3 = 3, + AW_H3_GIC_SPI_TWI0 = 6, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, AW_H3_GIC_SPI_MMC0 = 60, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "ram-size"); object_initialize_child(obj, "rtc", &s->rtc, TYPE_AW_RTC_SUN6I); + + object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, s->memmap[AW_H3_DEV_RTC]); + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, s->memmap[AW_H3_DEV_TWI0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI0)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * 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/>. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "hw/i2c/allwinner-i2c.h" +#include "hw/irq.h" +#include "migration/vmstate.h" +#include "hw/i2c/i2c.h" +#include "qemu/log.h" +#include "trace.h" +#include "qemu/module.h" + +/* Allwinner I2C memory map */ +#define TWI_ADDR_REG 0x00 /* slave address register */ +#define TWI_XADDR_REG 0x04 /* extended slave address register */ +#define TWI_DATA_REG 0x08 /* data register */ +#define TWI_CNTR_REG 0x0c /* control register */ +#define TWI_STAT_REG 0x10 /* status register */ +#define TWI_CCR_REG 0x14 /* clock control register */ +#define TWI_SRST_REG 0x18 /* software reset register */ +#define TWI_EFR_REG 0x1c /* enhance feature register */ +#define TWI_LCR_REG 0x20 /* line control register */ + +/* Used only in slave mode, do not set */ +#define TWI_ADDR_RESET 0 +#define TWI_XADDR_RESET 0 + +/* Data register */ +#define TWI_DATA_MASK 0xFF +#define TWI_DATA_RESET 0 + +/* Control register */ +#define TWI_CNTR_INT_EN (1 << 7) +#define TWI_CNTR_BUS_EN (1 << 6) +#define TWI_CNTR_M_STA (1 << 5) +#define TWI_CNTR_M_STP (1 << 4) +#define TWI_CNTR_INT_FLAG (1 << 3) +#define TWI_CNTR_A_ACK (1 << 2) +#define TWI_CNTR_MASK 0xFC +#define TWI_CNTR_RESET 0 + +/* Status register */ +#define TWI_STAT_MASK 0xF8 +#define TWI_STAT_RESET 0xF8 + +/* Clock register */ +#define TWI_CCR_CLK_M_MASK 0x78 +#define TWI_CCR_CLK_N_MASK 0x07 +#define TWI_CCR_MASK 0x7F +#define TWI_CCR_RESET 0 + +/* Soft reset */ +#define TWI_SRST_MASK 0x01 +#define TWI_SRST_RESET 0 + +/* Enhance feature */ +#define TWI_EFR_MASK 0x03 +#define TWI_EFR_RESET 0 + +/* Line control */ +#define TWI_LCR_SCL_STATE (1 << 5) +#define TWI_LCR_SDA_STATE (1 << 4) +#define TWI_LCR_SCL_CTL (1 << 3) +#define TWI_LCR_SCL_CTL_EN (1 << 2) +#define TWI_LCR_SDA_CTL (1 << 1) +#define TWI_LCR_SDA_CTL_EN (1 << 0) +#define TWI_LCR_MASK 0x3F +#define TWI_LCR_RESET 0x3A + +/* Status value in STAT register is shifted by 3 bits */ +#define TWI_STAT_SHIFT 3 +#define STAT_FROM_STA(x) ((x) << TWI_STAT_SHIFT) +#define STAT_TO_STA(x) ((x) >> TWI_STAT_SHIFT) + +enum { + STAT_BUS_ERROR = 0, + /* Master mode */ + STAT_M_STA_TX, + STAT_M_RSTA_TX, + STAT_M_ADDR_WR_ACK, + STAT_M_ADDR_WR_NACK, + STAT_M_DATA_TX_ACK, + STAT_M_DATA_TX_NACK, + STAT_M_ARB_LOST, + STAT_M_ADDR_RD_ACK, + STAT_M_ADDR_RD_NACK, + STAT_M_DATA_RX_ACK, + STAT_M_DATA_RX_NACK, + /* Slave mode */ + STAT_S_ADDR_WR_ACK, + STAT_S_ARB_LOST_AW_ACK, + STAT_S_GCA_ACK, + STAT_S_ARB_LOST_GCA_ACK, + STAT_S_DATA_RX_SA_ACK, + STAT_S_DATA_RX_SA_NACK, + STAT_S_DATA_RX_GCA_ACK, + STAT_S_DATA_RX_GCA_NACK, + STAT_S_STP_RSTA, + STAT_S_ADDR_RD_ACK, + STAT_S_ARB_LOST_AR_ACK, + STAT_S_DATA_TX_ACK, + STAT_S_DATA_TX_NACK, + STAT_S_LB_TX_ACK, + /* Master mode, 10-bit */ + STAT_M_2ND_ADDR_WR_ACK, + STAT_M_2ND_ADDR_WR_NACK, + /* Idle */ + STAT_IDLE = 0x1f +} TWI_STAT_STA; + +static const char *allwinner_i2c_get_regname(unsigned offset) +{ + switch (offset) { + case TWI_ADDR_REG: + return "ADDR"; + case TWI_XADDR_REG: + return "XADDR"; + case TWI_DATA_REG: + return "DATA"; + case TWI_CNTR_REG: + return "CNTR"; + case TWI_STAT_REG: + return "STAT"; + case TWI_CCR_REG: + return "CCR"; + case TWI_SRST_REG: + return "SRST"; + case TWI_EFR_REG: + return "EFR"; + case TWI_LCR_REG: + return "LCR"; + default: + return "[?]"; + } +} + +static inline bool allwinner_i2c_is_reset(AWI2CState *s) +{ + return s->srst & TWI_SRST_MASK; +} + +static inline bool allwinner_i2c_bus_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_BUS_EN; +} + +static inline bool allwinner_i2c_interrupt_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_INT_EN; +} + +static void allwinner_i2c_reset_hold(Object *obj) +{ + AWI2CState *s = AW_I2C(obj); + + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + i2c_end_transfer(s->bus); + } + + s->addr = TWI_ADDR_RESET; + s->xaddr = TWI_XADDR_RESET; + s->data = TWI_DATA_RESET; + s->cntr = TWI_CNTR_RESET; + s->stat = TWI_STAT_RESET; + s->ccr = TWI_CCR_RESET; + s->srst = TWI_SRST_RESET; + s->efr = TWI_EFR_RESET; + s->lcr = TWI_LCR_RESET; +} + +static inline void allwinner_i2c_raise_interrupt(AWI2CState *s) +{ + /* + * Raise an interrupt if the device is not reset and it is configured + * to generate some interrupts. + */ + if (!allwinner_i2c_is_reset(s) && allwinner_i2c_bus_is_enabled(s)) { + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + s->cntr |= TWI_CNTR_INT_FLAG; + if (allwinner_i2c_interrupt_is_enabled(s)) { + qemu_irq_raise(s->irq); + } + } + } +} + +static uint64_t allwinner_i2c_read(void *opaque, hwaddr offset, + unsigned size) +{ + uint16_t value; + AWI2CState *s = AW_I2C(opaque); + + switch (offset) { + case TWI_ADDR_REG: + value = s->addr; + break; + case TWI_XADDR_REG: + value = s->xaddr; + break; + case TWI_DATA_REG: + if ((STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK)) { + /* Get the next byte */ + s->data = i2c_recv(s->bus); + + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + value = s->data; + break; + case TWI_CNTR_REG: + value = s->cntr; + break; + case TWI_STAT_REG: + value = s->stat; + /* + * If polling when reading then change state to indicate data + * is available + */ + if (STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) { + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case TWI_CCR_REG: + value = s->ccr; + break; + case TWI_SRST_REG: + value = s->srst; + break; + case TWI_EFR_REG: + value = s->efr; + break; + case TWI_LCR_REG: + value = s->lcr; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + value = 0; + break; + } + + trace_allwinner_i2c_read(allwinner_i2c_get_regname(offset), offset, value); + + return (uint64_t)value; +} + +static void allwinner_i2c_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AWI2CState *s = AW_I2C(opaque); + + value &= 0xff; + + trace_allwinner_i2c_write(allwinner_i2c_get_regname(offset), offset, value); + + switch (offset) { + case TWI_ADDR_REG: + s->addr = (uint8_t)value; + break; + case TWI_XADDR_REG: + s->xaddr = (uint8_t)value; + break; + case TWI_DATA_REG: + /* If the device is in reset or not enabled, nothing to do */ + if (allwinner_i2c_is_reset(s) || (!allwinner_i2c_bus_is_enabled(s))) { + break; + } + + s->data = value & TWI_DATA_MASK; + + switch (STAT_TO_STA(s->stat)) { + case STAT_M_STA_TX: + case STAT_M_RSTA_TX: + /* Send address */ + if (i2c_start_transfer(s->bus, extract32(s->data, 1, 7), + extract32(s->data, 0, 1))) { + /* If non zero is returned, the address is not valid */ + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_NACK); + } else { + /* Determine if read of write */ + if (extract32(s->data, 0, 1)) { + s->stat = STAT_FROM_STA(STAT_M_ADDR_RD_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_ACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case STAT_M_ADDR_WR_ACK: + case STAT_M_DATA_TX_ACK: + if (i2c_send(s->bus, s->data)) { + /* If the target return non zero then end the transfer */ + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_NACK); + i2c_end_transfer(s->bus); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_ACK); + allwinner_i2c_raise_interrupt(s); + } + break; + default: + break; + } + break; + case TWI_CNTR_REG: + if (!allwinner_i2c_is_reset(s)) { + /* Do something only if not in software reset */ + s->cntr = value & TWI_CNTR_MASK; + + /* Check if start condition should be sent */ + if (s->cntr & TWI_CNTR_M_STA) { + /* Update status */ + if (STAT_TO_STA(s->stat) == STAT_IDLE) { + /* Send start condition */ + s->stat = STAT_FROM_STA(STAT_M_STA_TX); + } else { + /* Send repeated start condition */ + s->stat = STAT_FROM_STA(STAT_M_RSTA_TX); + } + /* Clear start condition */ + s->cntr &= ~TWI_CNTR_M_STA; + } + if (s->cntr & TWI_CNTR_M_STP) { + /* Update status */ + i2c_end_transfer(s->bus); + s->stat = STAT_FROM_STA(STAT_IDLE); + s->cntr &= ~TWI_CNTR_M_STP; + } + if ((s->cntr & TWI_CNTR_INT_FLAG) == 0) { + /* Interrupt flag cleared */ + qemu_irq_lower(s->irq); + } + if ((s->cntr & TWI_CNTR_A_ACK) == 0) { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + } else { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } + } + allwinner_i2c_raise_interrupt(s); + + } + break; + case TWI_CCR_REG: + s->ccr = value & TWI_CCR_MASK; + break; + case TWI_SRST_REG: + if (((value & TWI_SRST_MASK) == 0) && (s->srst & TWI_SRST_MASK)) { + /* Perform reset */ + allwinner_i2c_reset_hold(OBJECT(s)); + } + s->srst = value & TWI_SRST_MASK; + break; + case TWI_EFR_REG: + s->efr = value & TWI_EFR_MASK; + break; + case TWI_LCR_REG: + s->lcr = value & TWI_LCR_MASK; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + break; + } +} + +static const MemoryRegionOps allwinner_i2c_ops = { + .read = allwinner_i2c_read, + .write = allwinner_i2c_write, + .valid.min_access_size = 1, + .valid.max_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription allwinner_i2c_vmstate = { + .name = TYPE_AW_I2C, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8(addr, AWI2CState), + VMSTATE_UINT8(xaddr, AWI2CState), + VMSTATE_UINT8(data, AWI2CState), + VMSTATE_UINT8(cntr, AWI2CState), + VMSTATE_UINT8(ccr, AWI2CState), + VMSTATE_UINT8(srst, AWI2CState), + VMSTATE_UINT8(efr, AWI2CState), + VMSTATE_UINT8(lcr, AWI2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_i2c_realize(DeviceState *dev, Error **errp) +{ + AWI2CState *s = AW_I2C(dev); + + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_i2c_ops, s, + TYPE_AW_I2C, AW_I2C_MEM_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); + s->bus = i2c_init_bus(dev, "i2c"); +} + +static void allwinner_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = allwinner_i2c_reset_hold; + dc->vmsd = &allwinner_i2c_vmstate; + dc->realize = allwinner_i2c_realize; + dc->desc = "Allwinner I2C Controller"; +} + +static const TypeInfo allwinner_i2c_type_info = { + .name = TYPE_AW_I2C, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AWI2CState), + .class_init = allwinner_i2c_class_init, +}; + +static void allwinner_i2c_register_types(void) +{ + type_register_static(&allwinner_i2c_type_info); +} + +type_init(allwinner_i2c_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 select ALLWINNER_A10_CCM select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC + select ALLWINNER_I2C select SERIAL select UNIMP @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 bool select ALLWINNER_A10_PIT select ALLWINNER_SUN8I_EMAC + select ALLWINNER_I2C select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/i2c/Kconfig b/hw/i2c/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/Kconfig +++ b/hw/i2c/Kconfig @@ -XXX,XX +XXX,XX @@ config MPC_I2C bool select I2C +config ALLWINNER_I2C + bool + select I2C + config PCA954X bool select I2C diff --git a/hw/i2c/meson.build b/hw/i2c/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/meson.build +++ b/hw/i2c/meson.build @@ -XXX,XX +XXX,XX @@ i2c_ss.add(when: 'CONFIG_BITBANG_I2C', if_true: files('bitbang_i2c.c')) i2c_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_i2c.c')) i2c_ss.add(when: 'CONFIG_IMX_I2C', if_true: files('imx_i2c.c')) i2c_ss.add(when: 'CONFIG_MPC_I2C', if_true: files('mpc_i2c.c')) +i2c_ss.add(when: 'CONFIG_ALLWINNER_I2C', if_true: files('allwinner-i2c.c')) i2c_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('microbit_i2c.c')) i2c_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_smbus.c')) i2c_ss.add(when: 'CONFIG_SMBUS_EEPROM', if_true: files('smbus_eeprom.c')) diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -XXX,XX +XXX,XX @@ i2c_send_async(uint8_t address, uint8_t data) "send_async(addr:0x%02x) data:0x%0 i2c_recv(uint8_t address, uint8_t data) "recv(addr:0x%02x) data:0x%02x" i2c_ack(void) "" +# allwinner_i2c.c + +allwinner_i2c_read(const char* reg_name, uint64_t offset, uint64_t value) "read %s [0x%" PRIx64 "]: -> 0x%" PRIx64 +allwinner_i2c_write(const char* reg_name, uint64_t offset, uint64_t value) "write %s [0x%" PRIx64 "]: <- 0x%" PRIx64 + # aspeed_i2c.c aspeed_i2c_bus_cmd(uint32_t cmd, const char *cmd_flags, uint32_t count, uint32_t intr_status) "handling cmd=0x%x %s count=%d intr=0x%x" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch adds minimal support for AXP-209 PMU. Most important is chip ID since U-Boot SPL expects version 0x1. Besides the chip ID register, reset values for two more registers used by A10 U-Boot SPL are covered. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Message-id: 20221226220303.14420-5-strahinja.p.jankovic@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/axp209.c | 238 +++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + hw/misc/Kconfig | 4 + hw/misc/meson.build | 1 + hw/misc/trace-events | 5 + 5 files changed, 250 insertions(+) create mode 100644 hw/misc/axp209.c diff --git a/hw/misc/axp209.c b/hw/misc/axp209.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/axp209.c @@ -XXX,XX +XXX,XX @@ +/* + * AXP-209 PMU Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "trace.h" +#include "hw/i2c/i2c.h" +#include "migration/vmstate.h" + +#define TYPE_AXP209_PMU "axp209_pmu" + +#define AXP209(obj) \ + OBJECT_CHECK(AXP209I2CState, (obj), TYPE_AXP209_PMU) + +/* registers */ +enum { + REG_POWER_STATUS = 0x0u, + REG_OPERATING_MODE, + REG_OTG_VBUS_STATUS, + REG_CHIP_VERSION, + REG_DATA_CACHE_0, + REG_DATA_CACHE_1, + REG_DATA_CACHE_2, + REG_DATA_CACHE_3, + REG_DATA_CACHE_4, + REG_DATA_CACHE_5, + REG_DATA_CACHE_6, + REG_DATA_CACHE_7, + REG_DATA_CACHE_8, + REG_DATA_CACHE_9, + REG_DATA_CACHE_A, + REG_DATA_CACHE_B, + REG_POWER_OUTPUT_CTRL = 0x12u, + REG_DC_DC2_OUT_V_CTRL = 0x23u, + REG_DC_DC2_DVS_CTRL = 0x25u, + REG_DC_DC3_OUT_V_CTRL = 0x27u, + REG_LDO2_4_OUT_V_CTRL, + REG_LDO3_OUT_V_CTRL, + REG_VBUS_CH_MGMT = 0x30u, + REG_SHUTDOWN_V_CTRL, + REG_SHUTDOWN_CTRL, + REG_CHARGE_CTRL_1, + REG_CHARGE_CTRL_2, + REG_SPARE_CHARGE_CTRL, + REG_PEK_KEY_CTRL, + REG_DC_DC_FREQ_SET, + REG_CHR_TEMP_TH_SET, + REG_CHR_HIGH_TEMP_TH_CTRL, + REG_IPSOUT_WARN_L1, + REG_IPSOUT_WARN_L2, + REG_DISCHR_TEMP_TH_SET, + REG_DISCHR_HIGH_TEMP_TH_CTRL, + REG_IRQ_BANK_1_CTRL = 0x40u, + REG_IRQ_BANK_2_CTRL, + REG_IRQ_BANK_3_CTRL, + REG_IRQ_BANK_4_CTRL, + REG_IRQ_BANK_5_CTRL, + REG_IRQ_BANK_1_STAT = 0x48u, + REG_IRQ_BANK_2_STAT, + REG_IRQ_BANK_3_STAT, + REG_IRQ_BANK_4_STAT, + REG_IRQ_BANK_5_STAT, + REG_ADC_ACIN_V_H = 0x56u, + REG_ADC_ACIN_V_L, + REG_ADC_ACIN_CURR_H, + REG_ADC_ACIN_CURR_L, + REG_ADC_VBUS_V_H, + REG_ADC_VBUS_V_L, + REG_ADC_VBUS_CURR_H, + REG_ADC_VBUS_CURR_L, + REG_ADC_INT_TEMP_H, + REG_ADC_INT_TEMP_L, + REG_ADC_TEMP_SENS_V_H = 0x62u, + REG_ADC_TEMP_SENS_V_L, + REG_ADC_BAT_V_H = 0x78u, + REG_ADC_BAT_V_L, + REG_ADC_BAT_DISCHR_CURR_H, + REG_ADC_BAT_DISCHR_CURR_L, + REG_ADC_BAT_CHR_CURR_H, + REG_ADC_BAT_CHR_CURR_L, + REG_ADC_IPSOUT_V_H, + REG_ADC_IPSOUT_V_L, + REG_DC_DC_MOD_SEL = 0x80u, + REG_ADC_EN_1, + REG_ADC_EN_2, + REG_ADC_SR_CTRL, + REG_ADC_IN_RANGE, + REG_GPIO1_ADC_IRQ_RISING_TH, + REG_GPIO1_ADC_IRQ_FALLING_TH, + REG_TIMER_CTRL = 0x8au, + REG_VBUS_CTRL_MON_SRP, + REG_OVER_TEMP_SHUTDOWN = 0x8fu, + REG_GPIO0_FEAT_SET, + REG_GPIO_OUT_HIGH_SET, + REG_GPIO1_FEAT_SET, + REG_GPIO2_FEAT_SET, + REG_GPIO_SIG_STATE_SET_MON, + REG_GPIO3_SET, + REG_COULOMB_CNTR_CTRL = 0xb8u, + REG_POWER_MEAS_RES, + NR_REGS +}; + +#define AXP209_CHIP_VERSION_ID (0x01) +#define AXP209_DC_DC2_OUT_V_CTRL_RESET (0x16) +#define AXP209_IRQ_BANK_1_CTRL_RESET (0xd8) + +/* A simple I2C slave which returns values of ID or CNT register. */ +typedef struct AXP209I2CState { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + uint8_t regs[NR_REGS]; /* peripheral registers */ + uint8_t ptr; /* current register index */ + uint8_t count; /* counter used for tx/rx */ +} AXP209I2CState; + +/* Reset all counters and load ID register */ +static void axp209_reset_enter(Object *obj, ResetType type) +{ + AXP209I2CState *s = AXP209(obj); + + memset(s->regs, 0, NR_REGS); + s->ptr = 0; + s->count = 0; + s->regs[REG_CHIP_VERSION] = AXP209_CHIP_VERSION_ID; + s->regs[REG_DC_DC2_OUT_V_CTRL] = AXP209_DC_DC2_OUT_V_CTRL_RESET; + s->regs[REG_IRQ_BANK_1_CTRL] = AXP209_IRQ_BANK_1_CTRL_RESET; +} + +/* Handle events from master. */ +static int axp209_event(I2CSlave *i2c, enum i2c_event event) +{ + AXP209I2CState *s = AXP209(i2c); + + s->count = 0; + + return 0; +} + +/* Called when master requests read */ +static uint8_t axp209_rx(I2CSlave *i2c) +{ + AXP209I2CState *s = AXP209(i2c); + uint8_t ret = 0xff; + + if (s->ptr < NR_REGS) { + ret = s->regs[s->ptr++]; + } + + trace_axp209_rx(s->ptr - 1, ret); + + return ret; +} + +/* + * Called when master sends write. + * Update ptr with byte 0, then perform write with second byte. + */ +static int axp209_tx(I2CSlave *i2c, uint8_t data) +{ + AXP209I2CState *s = AXP209(i2c); + + if (s->count == 0) { + /* Store register address */ + s->ptr = data; + s->count++; + trace_axp209_select(data); + } else { + trace_axp209_tx(s->ptr, data); + if (s->ptr == REG_DC_DC2_OUT_V_CTRL) { + s->regs[s->ptr++] = data; + } + } + + return 0; +} + +static const VMStateDescription vmstate_axp209 = { + .name = TYPE_AXP209_PMU, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(regs, AXP209I2CState, NR_REGS), + VMSTATE_UINT8(count, AXP209I2CState), + VMSTATE_UINT8(ptr, AXP209I2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void axp209_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); + + rc->phases.enter = axp209_reset_enter; + dc->vmsd = &vmstate_axp209; + isc->event = axp209_event; + isc->recv = axp209_rx; + isc->send = axp209_tx; +} + +static const TypeInfo axp209_info = { + .name = TYPE_AXP209_PMU, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(AXP209I2CState), + .class_init = axp209_class_init +}; + +static void axp209_register_devices(void) +{ + type_register_static(&axp209_info); +} + +type_init(axp209_register_devices); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ ARM Machines Allwinner-a10 M: Beniamino Galvani <b.galvani@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> +R: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c F: docs/system/arm/cubieboard.rst +F: hw/misc/axp209.c Allwinner-h3 M: Niek Linnenbank <nieklinnenbank@gmail.com> diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10_CCM config ALLWINNER_A10_DRAMC bool +config AXP209_PMU + bool + depends on I2C + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c' softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) +softmmu_ss.add(when: 'CONFIG_AXP209_PMU', if_true: files('axp209.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) softmmu_ss.add(when: 'CONFIG_ECCMEMCTL', if_true: files('eccmemctl.c')) 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_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" avr_power_read(uint8_t value) "power_reduc read value:%u" avr_power_write(uint8_t value) "power_reduc write value:%u" +# axp209.c +axp209_rx(uint8_t reg, uint8_t data) "Read reg 0x%" PRIx8 " : 0x%" PRIx8 +axp209_select(uint8_t reg) "Accessing reg 0x%" PRIx8 +axp209_tx(uint8_t reg, uint8_t data) "Write reg 0x%" PRIx8 " : 0x%" PRIx8 + # 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" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> SPL Boot for Cubieboard expects AXP209 connected to I2C0 bus. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20221226220303.14420-6-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/cubieboard.c | 6 ++++++ hw/arm/Kconfig | 1 + 2 files changed, 7 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 @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" +#include "hw/i2c/i2c.h" static struct arm_boot_info cubieboard_binfo = { .loader_start = AW_A10_SDRAM_BASE, @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) BlockBackend *blk; BusState *bus; DeviceState *carddev; + I2CBus *i2c; /* BIOS is not supported by this board */ if (machine->firmware) { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) exit(1); } + /* Connect AXP 209 */ + i2c = I2C_BUS(qdev_get_child_bus(DEVICE(&a10->i2c0), "i2c")); + i2c_slave_create_simple(i2c, "axp209_pmu", 0x34); + /* Retrieve SD bus */ di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; 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 ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select ALLWINNER_I2C + select AXP209_PMU select SERIAL select UNIMP -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch enables copying of SPL from MMC if `-kernel` parameter is not passed when starting QEMU. SPL is copied to SRAM_A. The approach is reused from Allwinner H3 implementation. Tested with Armbian and custom Yocto image. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-7-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 21 +++++++++++++++++++++ hw/arm/allwinner-a10.c | 18 ++++++++++++++++++ hw/arm/cubieboard.c | 5 +++++ 3 files changed, 44 insertions(+) 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/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" #include "hw/i2c/allwinner-i2c.h" +#include "sysemu/block-backend.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { OHCISysBusState ohci[AW_A10_NUM_USB]; }; +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner A10 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 at offset 8 KiB from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner A10 state object pointer + * @blk: Block backend device object pointer + */ +void allwinner_a10_bootrom_setup(AwA10State *s, BlockBackend *blk); + #endif 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 "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#include "hw/loader.h" +#define AW_A10_SRAM_A_BASE 0x00000000 #define AW_A10_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 @@ -XXX,XX +XXX,XX @@ #define AW_A10_RTC_BASE 0x01c20d00 #define AW_A10_I2C0_BASE 0x01c2ac00 +void allwinner_a10_bootrom_setup(AwA10State *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, rom_size, buffer, 0) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return; + } + + rom_add_blob("allwinner-a10.bootrom", buffer, rom_size, + rom_size, AW_A10_SRAM_A_BASE, + NULL, NULL, NULL, NULL, false); +} + static void aw_a10_init(Object *obj) { AwA10State *s = AW_A10(obj); 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) memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE, machine->ram); + /* Load target kernel or start using BootROM */ + if (!machine->kernel_filename && blk && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + allwinner_a10_bootrom_setup(a10, blk); + } /* TODO create and connect IDE devices for ide_drive_get() */ cubieboard_binfo.ram_size = machine->ram_size; -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> Cubieboard now can boot directly from SD card, without the need to pass `-kernel` parameter. Update Avocado tests to cover this functionality. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-8-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/boot_linux_console.py | 47 +++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_sata(self): 'sda') # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_cubieboard_openwrt_22_03_2(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:cubieboard + :avocado: tags=device:sd + """ + + # This test download a 7.5 MiB compressed image and expand it + # to 126 MiB. + image_url = ('https://downloads.openwrt.org/releases/22.03.2/targets/' + 'sunxi/cortexa8/openwrt-22.03.2-sunxi-cortexa8-' + 'cubietech_a10-cubieboard-ext4-sdcard.img.gz') + image_hash = ('94b5ecbfbc0b3b56276e5146b899eafa' + '2ac5dc2d08733d6705af9f144f39f554') + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash, + algorithm='sha256') + image_path = archive.extract(image_path_gz, self.workdir) + image_pow2ceil_expand(image_path) + + 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 + + 'usbcore.nousb ' + 'noreboot') + + self.wait_for_console_pattern('U-Boot SPL') + + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', '=>') + 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( + 'Please press Enter to activate this console.') + + exec_command_and_wait_for_pattern(self, ' ', 'root@') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun4i/sun5i') + # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_TIMEOUT_EXPECTED'), 'Test might timeout') def test_arm_quanta_gsj(self): """ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Don't dereference CPUTLBEntryFull until we verify that the page is valid. Move the other user-only info field updates after the valid check to match. Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1412 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230104190056.305143-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 14 +++++++++----- 1 file changed, 9 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 @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, #ifdef CONFIG_USER_ONLY flags = probe_access_flags(env, addr, access_type, mmu_idx, nofault, &info->host, retaddr); - memset(&info->attrs, 0, sizeof(info->attrs)); - /* Require both ANON and MTE; see allocation_tag_mem(). */ - info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); #else CPUTLBEntryFull *full; flags = probe_access_full(env, addr, access_type, mmu_idx, nofault, &info->host, &full, retaddr); - info->attrs = full->attrs; - info->tagged = full->pte_attrs == 0xf0; #endif info->flags = flags; @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, return false; } +#ifdef CONFIG_USER_ONLY + memset(&info->attrs, 0, sizeof(info->attrs)); + /* Require both ANON and MTE; see allocation_tag_mem(). */ + info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); +#else + info->attrs = full->attrs; + info->tagged = full->pte_attrs == 0xf0; +#endif + /* Ensure that info->host[] is relative to addr, not addr + mem_off. */ info->host -= mem_off; return true; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa255_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 2 +- hw/arm/gumstix.c | 3 +-- hw/arm/pxa2xx.c | 4 +++- hw/arm/tosa.c | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, const char *revision); -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size); +PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t connex_rom = 0x01000000; uint32_t connex_ram = 0x04000000; - cpu = pxa255_init(address_space_mem, connex_ram); + cpu = pxa255_init(connex_ram); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" +#include "exec/address-spaces.h" #include "cpu.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(MemoryRegion *address_space, } /* Initialise a PXA255 integrated chip (ARM based core). */ -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size) +PXA2xxState *pxa255_init(unsigned int sdram_size) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/tosa.c +++ b/hw/arm/tosa.c @@ -XXX,XX +XXX,XX @@ static void tosa_init(MachineState *machine) TC6393xbState *tmio; DeviceState *scp0, *scp1; - mpu = pxa255_init(address_space_mem, tosa_binfo.ram_size); + mpu = pxa255_init(tosa_binfo.ram_size); memory_region_init_rom(rom, NULL, "tosa.rom", TOSA_ROM, &error_fatal); memory_region_add_subregion(address_space_mem, 0, rom); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa270_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 3 +-- hw/arm/gumstix.c | 3 +-- hw/arm/mainstone.c | 10 ++++------ hw/arm/pxa2xx.c | 4 ++-- hw/arm/spitz.c | 6 ++---- hw/arm/z2.c | 3 +-- 6 files changed, 11 insertions(+), 18 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { # define PA_FMT "0x%08lx" -PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, - const char *revision); +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *revision); PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t verdex_rom = 0x02000000; uint32_t verdex_ram = 0x10000000; - cpu = pxa270_init(address_space_mem, verdex_ram, machine->cpu_type); + cpu = pxa270_init(verdex_ram, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info mainstone_binfo = { .ram_size = 0x04000000, }; -static void mainstone_common_init(MemoryRegion *address_space_mem, - MachineState *machine, +static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { uint32_t sector_len = 256 * 1024; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, mainstone_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0x00000000, rom); /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, static void mainstone_init(MachineState *machine) { - mainstone_common_init(get_system_memory(), machine, mainstone, 0x196); + mainstone_common_init(machine, mainstone, 0x196); } static void mainstone2_machine_init(MachineClass *mc) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_reset(void *opaque, int line, int level) } /* Initialise a PXA270 integrated chip (ARM based core). */ -PXA2xxState *pxa270_init(MemoryRegion *address_space, - unsigned int sdram_size, const char *cpu_type) +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -XXX,XX +XXX,XX @@ static void spitz_common_init(MachineState *machine) SpitzMachineState *sms = SPITZ_MACHINE(machine); enum spitz_model_e model = smc->model; PXA2xxState *mpu; - MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, spitz_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(spitz_binfo.ram_size, machine->cpu_type); sms->mpu = mpu; sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M); memory_region_init_rom(rom, NULL, "spitz.rom", SPITZ_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0, rom); /* Setup peripherals */ spitz_keyboard_register(mpu); diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { static void z2_init(MachineState *machine) { - MemoryRegion *address_space_mem = get_system_memory(); uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) DeviceState *wm; /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, z2_binfo.ram_size, machine->cpu_type); + mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "qom/object.h" +#define RAM_SIZE (512 * MiB) +#define FLASH_SIZE (32 * MiB) +#define FLASH_SECTOR_SIZE (64 * KiB) + struct CollieMachineState { MachineState parent; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(CollieMachineState, COLLIE_MACHINE) static struct arm_boot_info collie_binfo = { .loader_start = SA_SDCS0, - .ram_size = 0x20000000, + .ram_size = RAM_SIZE, }; static void collie_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", 0x02000000, + pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", 0x02000000, + pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); sysbus_create_simple("scoop", 0x40800000, NULL); @@ -XXX,XX +XXX,XX @@ static void collie_machine_class_init(ObjectClass *oc, void *data) mc->init = collie_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("sa1110"); - mc->default_ram_size = 0x20000000; + mc->default_ram_size = RAM_SIZE; mc->default_ram_id = "strongarm.sdram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info collie_binfo = { static void collie_init(MachineState *machine) { - DriveInfo *dinfo; MachineClass *mc = MACHINE_GET_CLASS(machine); CollieMachineState *cms = COLLIE_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); - dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); - - dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + for (unsigned i = 0; i < 2; i++) { + DriveInfo *dinfo = drive_get(IF_PFLASH, 0, i); + pflash_cfi01_register(i ? SA_CS1 : SA_CS0, + i ? "collie.fl2" : "collie.fl1", FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + } sysbus_create_simple("scoop", 0x40800000, NULL); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a comment describing the Connex uses a Numonyx RC28F128J3F75 flash, and the Verdex uses a Micron RC28F256P30TFA. Correct the Verdex machine description (we model the 'Pro' board). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-6-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ * Contributions after 2012-01-13 are licensed under the terms of the * GNU GPL, version 2 or (at your option) any later version. */ - + /* * Example usage: * @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) exit(1); } + /* Numonyx RC28F128J3F75 */ if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) exit(1); } + /* Micron RC28F256P30TFA */ if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); - mc->desc = "Gumstix Verdex (PXA270)"; + mc->desc = "Gumstix Verdex Pro XL6P COMs (PXA270)"; mc->init = verdex_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-7-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "hw/arm/pxa.h" #include "net/net.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "cpu.h" -static const int sector_len = 128 * 1024; +#define CONNEX_FLASH_SIZE (16 * MiB) +#define CONNEX_RAM_SIZE (64 * MiB) + +#define VERDEX_FLASH_SIZE (32 * MiB) +#define VERDEX_RAM_SIZE (256 * MiB) + +#define FLASH_SECTOR_SIZE (128 * KiB) static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t connex_rom = 0x01000000; - uint32_t connex_ram = 0x04000000; - - cpu = pxa255_init(connex_ram); + cpu = pxa255_init(CONNEX_RAM_SIZE); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, + if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t verdex_rom = 0x02000000; - uint32_t verdex_ram = 0x10000000; - - cpu = pxa270_init(verdex_ram, machine->cpu_type); + cpu = pxa270_init(VERDEX_RAM_SIZE, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, + if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mainstone.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ * GNU GPL, version 2 or (at your option) any later version. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/arm/pxa.h" @@ -XXX,XX +XXX,XX @@ static const struct keymap map[0xE0] = { enum mainstone_model_e { mainstone }; -#define MAINSTONE_RAM 0x04000000 -#define MAINSTONE_ROM 0x00800000 -#define MAINSTONE_FLASH 0x02000000 +#define MAINSTONE_RAM_SIZE (64 * MiB) +#define MAINSTONE_ROM_SIZE (8 * MiB) +#define MAINSTONE_FLASH_SIZE (32 * MiB) static struct arm_boot_info mainstone_binfo = { .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = 0x04000000, + .ram_size = MAINSTONE_RAM_SIZE, }; +#define FLASH_SECTOR_SIZE (256 * KiB) + static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { - uint32_t sector_len = 256 * 1024; hwaddr mainstone_flash_base[] = { MST_FLASH_0, MST_FLASH_1 }; PXA2xxState *mpu; DeviceState *mst_irq; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* Setup CPU & memory */ mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); - memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, + memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM_SIZE, &error_fatal); memory_region_add_subregion(get_system_memory(), 0x00000000, rom); @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, dinfo = drive_get(IF_PFLASH, 0, i); if (!pflash_cfi01_register(mainstone_flash_base[i], i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH, + MAINSTONE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/musicpal.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "cpu.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo musicpal_key_info = { .class_init = musicpal_key_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static struct arm_boot_info musicpal_binfo = { .loader_start = 0x0, .board_id = 0x20e, @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) BlockBackend *blk = blk_by_legacy_dinfo(dinfo); flash_size = blk_getlength(blk); - if (flash_size != 8*1024*1024 && flash_size != 16*1024*1024 && - flash_size != 32*1024*1024) { + if (flash_size != 8 * MiB && flash_size != 16 * MiB && + flash_size != 32 * MiB) { error_report("Invalid flash image size"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) */ pflash_cfi02_register(0x100000000ULL - MP_FLASH_SIZE_MAX, "musicpal.flash", flash_size, - blk, 0x10000, + blk, FLASH_SECTOR_SIZE, MP_FLASH_SIZE_MAX / flash_size, 2, 0x00BF, 0x236D, 0x0000, 0x0000, 0x5555, 0x2AAA, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The total_ram_v1/total_ram_v2 definitions were never used. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { #define flash0_size (16 * 1024 * 1024) #define flash1_size ( 8 * 1024 * 1024) #define flash2_size (32 * 1024 * 1024) -#define total_ram_v1 (sdram_size + flash0_size + flash1_size + OMAP15XX_SRAM_SIZE) -#define total_ram_v2 (sdram_size + flash2_size + OMAP15XX_SRAM_SIZE) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "ui/console.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -#define sdram_size 0x02000000 -#define sector_size (128 * 1024) -#define flash0_size (16 * 1024 * 1024) -#define flash1_size ( 8 * 1024 * 1024) -#define flash2_size (32 * 1024 * 1024) +#define SDRAM_SIZE (32 * MiB) +#define SECTOR_SIZE (128 * KiB) +#define FLASH0_SIZE (16 * MiB) +#define FLASH1_SIZE (8 * MiB) +#define FLASH2_SIZE (32 * MiB) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, - .ram_size = sdram_size, + .ram_size = SDRAM_SIZE, .board_id = 0x265, }; @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) static uint32_t cs3val = 0x00001139; DriveInfo *dinfo; int fl_idx; - uint32_t flash_size = flash0_size; + uint32_t flash_size = FLASH0_SIZE; if (machine->ram_size != mc->default_ram_size) { char *sz = size_to_str(mc->default_ram_size); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) } if (version == 2) { - flash_size = flash2_size; + flash_size = FLASH2_SIZE; } memory_region_add_subregion(address_space, OMAP_EMIFF_BASE, machine->ram); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) if (!pflash_cfi01_register(OMAP_CS0_BASE, "omap_sx1.flash0-1", flash_size, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) (dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { MemoryRegion *flash_1 = g_new(MemoryRegion, 1); memory_region_init_rom(flash_1, NULL, "omap_sx1.flash1-0", - flash1_size, &error_fatal); + FLASH1_SIZE, &error_fatal); memory_region_add_subregion(address_space, OMAP_CS1_BASE, flash_1); memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, - "sx1.cs1", OMAP_CS1_SIZE - flash1_size); + "sx1.cs1", OMAP_CS1_SIZE - FLASH1_SIZE); memory_region_add_subregion(address_space, - OMAP_CS1_BASE + flash1_size, &cs[1]); + OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", flash1_size, + "omap_sx1.flash1-1", FLASH1_SIZE, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v2_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v2; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v1_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v1; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/z2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "hw/arm/pxa.h" #include "hw/arm/boot.h" #include "hw/i2c/i2c.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { .class_init = aer915_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static void z2_init(MachineState *machine) { - uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; void *z2_lcd; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Upon introduction in commit b8433303fb ("Set proper device-width for vexpress flash"), ve_pflash_cfi01_register() was calling qdev_init_nofail() which can not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/vexpress.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); pflash0 = ve_pflash_cfi01_register(map[VE_NORFLASH0], "vexpress.flash0", dinfo); - if (!pflash0) { - error_report("vexpress: error registering flash 0"); - exit(1); - } if (map[VE_NORFLASHALIAS] != -1) { /* Map flash 0 as an alias into low memory */ @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) } dinfo = drive_get(IF_PFLASH, 0, 1); - if (!ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", - dinfo)) { - error_report("vexpress: error registering flash 1"); - exit(1); - } + ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", dinfo); sram_size = 0x2000000; memory_region_init_ram(sram, NULL, "vexpress.sram", sram_size, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since its QOM'ification in commit 368a354f02 ("pflash_cfi0x: QOMified") the pflash_cfi01_register() function does not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 18 ++++++------------ hw/arm/mainstone.c | 13 +++++-------- hw/arm/omap_sx1.c | 22 ++++++++-------------- hw/arm/versatilepb.c | 6 ++---- hw/arm/z2.c | 9 +++------ 5 files changed, 24 insertions(+), 44 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 36 */ smc91c111_init(&nd_table[0], 0x04000300, @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 99 */ smc91c111_init(&nd_table[0], 0x04000300, diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { dinfo = drive_get(IF_PFLASH, 0, i); - if (!pflash_cfi01_register(mainstone_flash_base[i], - i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(mainstone_flash_base[i], + i ? "mainstone.flash1" : "mainstone.flash0", + MAINSTONE_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); } mst_irq = sysbus_create_simple("mainstone-fpga", MST_FPGA_PHYS, diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) fl_idx = 0; if ((dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { - if (!pflash_cfi01_register(OMAP_CS0_BASE, - "omap_sx1.flash0-1", flash_size, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS0_BASE, + "omap_sx1.flash0-1", flash_size, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) memory_region_add_subregion(address_space, OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); - if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", FLASH1_SIZE, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS1_BASE, + "omap_sx1.flash1-1", FLASH1_SIZE, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } else { memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -XXX,XX +XXX,XX @@ static void versatile_init(MachineState *machine, int board_id) /* 0x34000000 NOR Flash */ dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", + pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", VERSATILE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, VERSATILE_FLASH_SECT_SIZE, - 4, 0x0089, 0x0018, 0x0000, 0x0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory.\n"); - } + 4, 0x0089, 0x0018, 0x0000, 0x0, 0); versatile_binfo.ram_size = machine->ram_size; versatile_binfo.board_id = board_id; diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); /* setup keypad */ pxa27x_register_keypad(mpu->kp, map, 0x100); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> To avoid forward-declaring PXA2xxI2CState, declare PXA2XX_I2C before its use in pxa2xx_i2c_init() prototype. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ void pxa27x_register_keypad(PXA2xxKeyPadState *kp, const struct keymap *map, int size); /* pxa2xx.c */ -typedef struct PXA2xxI2CState PXA2xxI2CState; +#define TYPE_PXA2XX_I2C "pxa2xx_i2c" +OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) + PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, qemu_irq irq, uint32_t page_size); I2CBus *pxa2xx_i2c_bus(PXA2xxI2CState *s); -#define TYPE_PXA2XX_I2C "pxa2xx_i2c" typedef struct PXA2xxI2SState PXA2xxI2SState; -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) #define TYPE_PXA2XX_FIR "pxa2xx-fir" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxFIrState, PXA2XX_FIR) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add a local 'struct omap_gpif_s *' variable to improve readability. (This also eases next commit conversion). Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/omap_gpio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpio_s *s = &((struct omap_gpif_s *) opaque)->omap1; + struct omap_gpif_s *p = opaque; + struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; if (level) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap1.c | 115 ++++++++++++++++++-------------------- hw/arm/omap2.c | 40 ++++++------- hw/arm/omap_sx1.c | 2 +- hw/arm/palm.c | 2 +- hw/char/omap_uart.c | 7 +-- hw/display/omap_dss.c | 15 +++-- hw/display/omap_lcdc.c | 9 ++- hw/dma/omap_dma.c | 15 +++-- hw/gpio/omap_gpio.c | 15 +++-- hw/intc/omap_intc.c | 12 ++-- hw/misc/omap_gpmc.c | 12 ++-- hw/misc/omap_l4.c | 7 +-- hw/misc/omap_sdrc.c | 7 +-- hw/misc/omap_tap.c | 5 +- hw/sd/omap_mmc.c | 9 ++- hw/ssi/omap_spi.c | 7 +-- hw/timer/omap_gptimer.c | 22 ++++---- hw/timer/omap_synctimer.c | 4 +- 18 files changed, 142 insertions(+), 163 deletions(-) diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap1.c +++ b/hw/arm/omap1.c @@ -XXX,XX +XXX,XX @@ static void omap_timer_fire(void *opaque) static void omap_timer_tick(void *opaque) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); omap_timer_fire(timer); @@ -XXX,XX +XXX,XX @@ static void omap_timer_tick(void *opaque) static void omap_timer_clk_update(void *opaque, int line, int on) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ static void omap_timer_clk_setup(struct omap_mpu_timer_s *timer) static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, static void omap_mpu_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_watchdog_timer_s { static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, static void omap_wd_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_32khz_timer_s { static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, static void omap_os_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static struct omap_32khz_timer_s *omap_os_timer_init(MemoryRegion *memory, static uint64_t omap_ulpd_pm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_ulpd_req_update(struct omap_mpu_state_s *s, static void omap_ulpd_pm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; int64_t now, ticks; int div, mult; static const int bypass_div[4] = { 1, 2, 4, 4 }; @@ -XXX,XX +XXX,XX @@ static void omap_ulpd_pm_init(MemoryRegion *system_memory, static uint64_t omap_pin_cfg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_pin_modconf1_update(struct omap_mpu_state_s *s, static void omap_pin_cfg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t diff; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_pin_cfg_init(MemoryRegion *system_memory, static uint64_t omap_id_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static void omap_id_init(MemoryRegion *memory, struct omap_mpu_state_s *mpu) static uint64_t omap_mpui_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpui_read(void *opaque, hwaddr addr, static void omap_mpui_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_tipb_bridge_s { static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, static void omap_tipb_bridge_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static struct omap_tipb_bridge_s *omap_tipb_bridge_init( static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, static void omap_tcmi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct dpll_ctl_s { static uint64_t omap_dpll_read(void *opaque, hwaddr addr, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dpll_read(void *opaque, hwaddr addr, static void omap_dpll_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; uint16_t diff; static const int bypass_div[4] = { 1, 2, 4, 4 }; int div, mult; @@ -XXX,XX +XXX,XX @@ static struct dpll_ctl_s *omap_dpll_init(MemoryRegion *memory, static uint64_t omap_clkm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_clkm_ckout1_update(struct omap_mpu_state_s *s, static void omap_clkm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; omap_clk clk; static const char *clkschemename[8] = { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_clkm_ops = { static uint64_t omap_clkdsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; CPUState *cpu = CPU(s->cpu); if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_clkdsp_idlect2_update(struct omap_mpu_state_s *s, static void omap_clkdsp_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; if (size != 2) { @@ -XXX,XX +XXX,XX @@ struct omap_mpuio_s { static void omap_mpuio_set(void *opaque, int line, int level) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; uint16_t prev = s->inputs; if (level) @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_kbd_update(struct omap_mpuio_s *s) static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, static void omap_mpuio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_reset(struct omap_mpuio_s *s) static void omap_mpuio_onoff(void *opaque, int line, int on) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; s->clk = on; if (on) @@ -XXX,XX +XXX,XX @@ static void omap_uwire_transfer_start(struct omap_uwire_s *s) } } -static uint64_t omap_uwire_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uwire_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uwire_read(void *opaque, hwaddr addr, static void omap_uwire_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_update(struct omap_pwl_s *s) } } -static uint64_t omap_pwl_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwl_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwl_read(void *opaque, hwaddr addr, static void omap_pwl_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_reset(struct omap_pwl_s *s) static void omap_pwl_clk_update(void *opaque, int line, int on) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; s->clk = on; omap_pwl_update(s); @@ -XXX,XX +XXX,XX @@ struct omap_pwt_s { omap_clk clk; }; -static uint64_t omap_pwt_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwt_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwt_read(void *opaque, hwaddr addr, static void omap_pwt_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_rtc_alarm_update(struct omap_rtc_s *s) printf("%s: conversion failed\n", __func__); } -static uint64_t omap_rtc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rtc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint8_t i; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rtc_read(void *opaque, hwaddr addr, static void omap_rtc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; struct tm new_tm; time_t ti[2]; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_rx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_source_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->rx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_tx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_sink_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->tx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_req_update(struct omap_mcbsp_s *s) static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, static void omap_mcbsp_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; switch (offset) { @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_writeh(void *opaque, hwaddr addr, static void omap_mcbsp_writew(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (offset == 0x04) { /* DXR */ @@ -XXX,XX +XXX,XX @@ static struct omap_mcbsp_s *omap_mcbsp_init(MemoryRegion *system_memory, static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->rx_rate) { s->rx_req = s->codec->in.len; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) static void omap_mcbsp_i2s_start(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->tx_rate) { s->tx_req = s->codec->out.size; @@ -XXX,XX +XXX,XX @@ static void omap_lpg_reset(struct omap_lpg_s *s) omap_lpg_update(s); } -static uint64_t omap_lpg_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lpg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lpg_read(void *opaque, hwaddr addr, static void omap_lpg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_lpg_ops = { static void omap_lpg_clk_update(void *opaque, int line, int on) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; s->clk = on; omap_lpg_update(s); @@ -XXX,XX +XXX,XX @@ static void omap_setup_mpui_io(MemoryRegion *system_memory, /* General chip reset */ static void omap1_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_mpu_timer_reset(mpu->timer[0]); @@ -XXX,XX +XXX,XX @@ static void omap_setup_dsp_mapping(MemoryRegion *system_memory, void omap_mpu_wakeup(void *opaque, int irq, int req) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; CPUState *cpu = CPU(mpu->cpu); if (cpu->halted) { diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap2.c +++ b/hw/arm/omap2.c @@ -XXX,XX +XXX,XX @@ static inline void omap_eac_out_empty(struct omap_eac_s *s) static void omap_eac_in_cb(void *opaque, int avail_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.rxavail = avail_b >> 2; omap_eac_in_refill(s); @@ -XXX,XX +XXX,XX @@ static void omap_eac_in_cb(void *opaque, int avail_b) static void omap_eac_out_cb(void *opaque, int free_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.txavail = free_b >> 2; if (s->codec.txlen) @@ -XXX,XX +XXX,XX @@ static void omap_eac_reset(struct omap_eac_s *s) omap_eac_interrupt_update(s); } -static uint64_t omap_eac_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_eac_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; uint32_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_eac_read(void *opaque, hwaddr addr, static void omap_eac_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_sti_reset(struct omap_sti_s *s) static uint64_t omap_sti_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_read(void *opaque, hwaddr addr, static void omap_sti_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_sti_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, unsigned size) { OMAP_BAD_REG(addr); return 0; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, static void omap_sti_fifo_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; int ch = addr >> 6; uint8_t byte = value; @@ -XXX,XX +XXX,XX @@ static void omap_prcm_int_update(struct omap_prcm_s *s, int dom) static uint64_t omap_prcm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_prcm_dpll_update(struct omap_prcm_s *s) static void omap_prcm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_sysctl_s { static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int value; @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) return 0; } -static void omap_sysctl_write8(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write8(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int prev_value; @@ -XXX,XX +XXX,XX @@ static void omap_sysctl_write8(void *opaque, hwaddr addr, } } -static void omap_sysctl_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static struct omap_sysctl_s *omap_sysctl_init(struct omap_target_agent_s *ta, /* General chip reset */ static void omap2_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_prcm_reset(mpu->prcm); diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static uint64_t static_read(void *opaque, hwaddr offset, unsigned size) { - uint32_t *val = (uint32_t *) opaque; + uint32_t *val = opaque; uint32_t mask = (4 / size) - 1; return *val >> ((offset & mask) << 3); diff --git a/hw/arm/palm.c b/hw/arm/palm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/palm.c +++ b/hw/arm/palm.c @@ -XXX,XX +XXX,XX @@ static struct { static void palmte_button_event(void *opaque, int keycode) { - struct omap_mpu_state_s *cpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *cpu = opaque; if (palmte_keymap[keycode & 0x7f].row != -1) omap_mpuio_key(cpu->mpuio, diff --git a/hw/char/omap_uart.c b/hw/char/omap_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/omap_uart.c +++ b/hw/char/omap_uart.c @@ -XXX,XX +XXX,XX @@ struct omap_uart_s *omap_uart_init(hwaddr base, return s; } -static uint64_t omap_uart_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uart_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { return omap_badwidth_read8(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uart_read(void *opaque, hwaddr addr, static void omap_uart_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { omap_badwidth_write8(opaque, addr, value); diff --git a/hw/display/omap_dss.c b/hw/display/omap_dss.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_dss.c +++ b/hw/display/omap_dss.c @@ -XXX,XX +XXX,XX @@ void omap_dss_reset(struct omap_dss_s *s) static uint64_t omap_diss_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_diss_read(void *opaque, hwaddr addr, static void omap_diss_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_diss_ops = { static uint64_t omap_disc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_disc_read(void *opaque, hwaddr addr, static void omap_disc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_rfbi_transfer_start(struct omap_dss_s *s) omap_dispc_interrupt_update(s); } -static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, static void omap_rfbi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, static void omap_update_display(void *opaque) { - struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *omap_lcd = opaque; DisplaySurface *surface; drawfn draw_line; int size, height, first, last; @@ -XXX,XX +XXX,XX @@ static void omap_lcd_update(struct omap_lcd_panel_s *s) { } } -static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, static void omap_lcdc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ static int omap_dma_sys_read(struct omap_dma_s *s, int offset, return 0; } -static uint64_t omap_dma_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_dma_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma_read(void *opaque, hwaddr addr, static void omap_dma_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_dma_ops = { static void omap_dma_request(void *opaque, int drq, int req) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; /* The request pins are level triggered in QEMU. */ if (req) { if (~s->dma->drqbmp & (1ULL << drq)) { @@ -XXX,XX +XXX,XX @@ static void omap_dma_request(void *opaque, int drq, int req) /* XXX: this won't be needed once soc_dma knows about clocks. */ static void omap_dma_clk_update(void *opaque, int line, int on) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int i; s->dma->freq = omap_clk_getrate(s->clk); @@ -XXX,XX +XXX,XX @@ static void omap_dma_interrupts_4_update(struct omap_dma_s *s) static uint64_t omap_dma4_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int irqn = 0, chnum; struct omap_dma_channel_s *ch; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma4_read(void *opaque, hwaddr addr, static void omap_dma4_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int chnum, irqn = 0; struct omap_dma_channel_s *ch; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ static void omap_gpio_set(void *opaque, int line, int level) static uint64_t omap_gpio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpio_read(void *opaque, hwaddr addr, static void omap_gpio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_module_reset(struct omap2_gpio_s *s) static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; switch (addr) { case 0x00: /* GPIO_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) static void omap2_gpio_module_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; uint32_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) s->gpo = 0; } -static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; diff --git a/hw/misc/omap_gpmc.c b/hw/misc/omap_gpmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_gpmc.c +++ b/hw/misc/omap_gpmc.c @@ -XXX,XX +XXX,XX @@ static void omap_gpmc_dma_update(struct omap_gpmc_s *s, int value) static uint64_t omap_nand_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; uint64_t v; nand_setpins(f->dev, 0, 0, 0, 1, 0); switch (omap_gpmc_devsize(f)) { @@ -XXX,XX +XXX,XX @@ static void omap_nand_setio(DeviceState *dev, uint64_t value, static void omap_nand_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; nand_setpins(f->dev, 0, 0, 0, 1, 0); omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); } @@ -XXX,XX +XXX,XX @@ static void fill_prefetch_fifo(struct omap_gpmc_s *s) static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; uint32_t data; if (s->prefetch.config1 & 1) { /* The TRM doesn't define the behaviour if you read from the @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, static void omap_gpmc_prefetch_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs = prefetch_cs(s->prefetch.config1); if ((s->prefetch.config1 & 1) == 0) { /* The TRM doesn't define the behaviour of writing to the @@ -XXX,XX +XXX,XX @@ static int gpmc_wordaccess_only(hwaddr addr) static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, static void omap_gpmc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; diff --git a/hw/misc/omap_l4.c b/hw/misc/omap_l4.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_l4.c +++ b/hw/misc/omap_l4.c @@ -XXX,XX +XXX,XX @@ hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, return ta->start[region].size; } -static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, static void omap_l4ta_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_sdrc.c b/hw/misc/omap_sdrc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_sdrc.c +++ b/hw/misc/omap_sdrc.c @@ -XXX,XX +XXX,XX @@ void omap_sdrc_reset(struct omap_sdrc_s *s) s->config = 0x10; } -static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, static void omap_sdrc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_tap.c b/hw/misc/omap_tap.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_tap.c +++ b/hw/misc/omap_tap.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/omap.h" /* TEST-Chip-level TAP */ -static uint64_t omap_tap_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_tap_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); 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 @@ void omap_mmc_reset(struct omap_mmc_s *host) device_cold_reset(DEVICE(host->card)); } -static uint64_t omap_mmc_read(void *opaque, hwaddr offset, - unsigned size) +static uint64_t omap_mmc_read(void *opaque, hwaddr offset, unsigned size) { uint16_t i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, offset); @@ -XXX,XX +XXX,XX @@ static void omap_mmc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { int i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, offset, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_mmc_ops = { static void omap_mmc_cover_cb(void *opaque, int line, int level) { - struct omap_mmc_s *host = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *host = opaque; if (!host->cdet_state && level) { host->status |= 0x0002; diff --git a/hw/ssi/omap_spi.c b/hw/ssi/omap_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/omap_spi.c +++ b/hw/ssi/omap_spi.c @@ -XXX,XX +XXX,XX @@ void omap_mcspi_reset(struct omap_mcspi_s *s) omap_mcspi_interrupt_update(s); } -static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; uint32_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, static void omap_mcspi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; if (size != 4) { diff --git a/hw/timer/omap_gptimer.c b/hw/timer/omap_gptimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_gptimer.c +++ b/hw/timer/omap_gptimer.c @@ -XXX,XX +XXX,XX @@ static inline void omap_gp_timer_trigger(struct omap_gp_timer_s *timer) static void omap_gp_timer_tick(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (!timer->ar) { timer->st = 0; @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_tick(void *opaque) static void omap_gp_timer_match(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (timer->trigger == gpt_trigger_both) omap_gp_timer_trigger(timer); @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_match(void *opaque) static void omap_gp_timer_input(void *opaque, int line, int on) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; int trigger; switch (s->capture) { @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_input(void *opaque, int line, int on) static void omap_gp_timer_clk_update(void *opaque, int line, int on) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; omap_gp_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ void omap_gp_timer_reset(struct omap_gp_timer_s *s) static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; uint32_t ret; if (addr & 2) @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) } } -static void omap_gp_timer_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_write(void *opaque, hwaddr addr, } } -static void omap_gp_timer_writeh(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; if (addr & 2) omap_gp_timer_write(opaque, addr, (value << 16) | s->writeh); diff --git a/hw/timer/omap_synctimer.c b/hw/timer/omap_synctimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_synctimer.c +++ b/hw/timer/omap_synctimer.c @@ -XXX,XX +XXX,XX @@ void omap_synctimer_reset(struct omap_synctimer_s *s) static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; switch (addr) { case 0x00: /* 32KSYNCNT_REV */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) static uint32_t omap_synctimer_readh(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; uint32_t ret; if (addr & 2) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_gpif_s -> Omap1GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 6 +++--- hw/gpio/omap_gpio.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_i2c_set_fclk(OMAPI2CState *i2c, omap_clk clk); /* omap_gpio.c */ #define TYPE_OMAP1_GPIO "omap-gpio" -DECLARE_INSTANCE_CHECKER(struct omap_gpif_s, OMAP1_GPIO, +typedef struct Omap1GpioState Omap1GpioState; +DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap_gpif_s omap_gpif; typedef struct omap2_gpif_s omap2_gpif; /* TODO: clock framework (see above) */ -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk); +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpio_s { uint16_t pins; }; -struct omap_gpif_s { +struct Omap1GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpif_s *p = opaque; + Omap1GpioState *p = opaque; struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpio_module_ops = { static void omap_gpif_reset(DeviceState *dev) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); omap_gpio_reset(&s->omap1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpif_top_ops = { static void omap_gpio_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_gpif_s *s = OMAP1_GPIO(obj); + Omap1GpioState *s = OMAP1_GPIO(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); qdev_init_gpio_in(dev, omap_gpio_set, 16); @@ -XXX,XX +XXX,XX @@ static void omap_gpio_init(Object *obj) static void omap_gpio_realize(DeviceState *dev, Error **errp) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); if (!s->clk) { error_setg(errp, "omap-gpio: clk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_realize(DeviceState *dev, Error **errp) } } -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk) +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk) { gpio->clk = clk; } static Property omap_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap1GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap_gpio_info = { .name = TYPE_OMAP1_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap_gpif_s), + .instance_size = sizeof(Omap1GpioState), .instance_init = omap_gpio_init, .class_init = omap_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap2_gpif_s -> Omap2GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/gpio/omap_gpio.c | 20 ++++++++++---------- 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" -DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, +typedef struct Omap2GpioState Omap2GpioState; +DECLARE_INSTANCE_CHECKER(Omap2GpioState, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap2_gpif_s omap2_gpif; - /* TODO: clock framework (see above) */ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk); +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk); /* OMAP2 l4 Interconnect */ struct omap_l4_s; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap2_gpio_s { uint8_t delay; }; -struct omap2_gpif_s { +struct Omap2GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ static inline void omap2_gpio_module_int(struct omap2_gpio_s *s, int line) static void omap2_gpio_set(void *opaque, int line, int level) { - struct omap2_gpif_s *p = opaque; + Omap2GpioState *p = opaque; struct omap2_gpio_s *s = &p->modules[line >> 5]; line &= 31; @@ -XXX,XX +XXX,XX @@ static void omap_gpif_reset(DeviceState *dev) static void omap2_gpif_reset(DeviceState *dev) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); int i; for (i = 0; i < s->modulecount; i++) { @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static void omap_gpio_realize(DeviceState *dev, Error **errp) static void omap2_gpio_realize(DeviceState *dev, Error **errp) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); SysBusDevice *sbd = SYS_BUS_DEVICE(dev); int i; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_gpio_info = { .class_init = omap_gpio_class_init, }; -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk) +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk) { gpio->iclk = clk; } -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk) +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk) { assert(i <= 5); gpio->fclk[i] = clk; } static Property omap2_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap2_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap2GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap2_gpio_info = { .name = TYPE_OMAP2_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap2_gpif_s), + .instance_size = sizeof(Omap2GpioState), .class_init = omap2_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_intr_handler_s -> OMAPIntcState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/intc/omap_intc.c | 38 +++++++++++++++++++------------------- 2 files changed, 23 insertions(+), 24 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_clk_reparent(omap_clk clk, omap_clk parent); /* omap_intc.c */ #define TYPE_OMAP_INTC "common-omap-intc" -typedef struct omap_intr_handler_s omap_intr_handler; -DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, - TYPE_OMAP_INTC) +typedef struct OMAPIntcState OMAPIntcState; +DECLARE_INSTANCE_CHECKER(OMAPIntcState, OMAP_INTC, TYPE_OMAP_INTC) /* @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, * (ie the struct omap_mpu_state_s*) to do the clockname to pointer * translation.) */ -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk); -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk); +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk); +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk); /* omap_i2c.c */ #define TYPE_OMAP_I2C "omap_i2c" diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_bank_s { unsigned char priority[32]; }; -struct omap_intr_handler_s { +struct OMAPIntcState { SysBusDevice parent_obj; qemu_irq *pins; @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_s { struct omap_intr_handler_bank_s bank[3]; }; -static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) +static void omap_inth_sir_update(OMAPIntcState *s, int is_fiq) { int i, j, sir_intr, p_intr, p; uint32_t level; @@ -XXX,XX +XXX,XX @@ static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) s->sir_intr[is_fiq] = sir_intr; } -static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) +static inline void omap_inth_update(OMAPIntcState *s, int is_fiq) { int i; uint32_t has_intr = 0; @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_inth_mem_ops = { static void omap_inth_reset(DeviceState *dev) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); int i; for (i = 0; i < s->nbanks; ++i){ @@ -XXX,XX +XXX,XX @@ static void omap_inth_reset(DeviceState *dev) static void omap_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->nbanks = 1; @@ -XXX,XX +XXX,XX @@ static void omap_intc_init(Object *obj) static void omap_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap-intc: clk not connected"); } } -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk) { intc->iclk = clk; } -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk) { intc->fclk = clk; } static Property omap_intc_properties[] = { - DEFINE_PROP_UINT32("size", struct omap_intr_handler_s, size, 0x100), + DEFINE_PROP_UINT32("size", OMAPIntcState, size, 0x100), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_inth_mem_ops = { static void omap2_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->level_only = 1; @@ -XXX,XX +XXX,XX @@ static void omap2_intc_init(Object *obj) static void omap2_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap2-intc: iclk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_intc_realize(DeviceState *dev, Error **errp) } static Property omap2_intc_properties[] = { - DEFINE_PROP_UINT8("revision", struct omap_intr_handler_s, + DEFINE_PROP_UINT8("revision", OMAPIntcState, revision, 0x21), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap2_intc_info = { static const TypeInfo omap_intc_type_info = { .name = TYPE_OMAP_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(omap_intr_handler), + .instance_size = sizeof(OMAPIntcState), .abstract = true, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename stellaris_adc_state -> StellarisADCState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 73 +++++++++++++++++++++++----------------------- 1 file changed, 36 insertions(+), 37 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_init(Object *obj) #define STELLARIS_ADC_FIFO_FULL 0x1000 #define TYPE_STELLARIS_ADC "stellaris-adc" -typedef struct StellarisADCState stellaris_adc_state; -DECLARE_INSTANCE_CHECKER(stellaris_adc_state, STELLARIS_ADC, - TYPE_STELLARIS_ADC) +typedef struct StellarisADCState StellarisADCState; +DECLARE_INSTANCE_CHECKER(StellarisADCState, STELLARIS_ADC, TYPE_STELLARIS_ADC) struct StellarisADCState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct StellarisADCState { qemu_irq irq[4]; }; -static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) +static uint32_t stellaris_adc_fifo_read(StellarisADCState *s, int n) { int tail; @@ -XXX,XX +XXX,XX @@ static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) return s->fifo[n].data[tail]; } -static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, +static void stellaris_adc_fifo_write(StellarisADCState *s, int n, uint32_t value) { int head; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, s->fifo[n].state |= STELLARIS_ADC_FIFO_FULL; } -static void stellaris_adc_update(stellaris_adc_state *s) +static void stellaris_adc_update(StellarisADCState *s) { int level; int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_trigger(void *opaque, int irq, int level) } } -static void stellaris_adc_reset(stellaris_adc_state *s) +static void stellaris_adc_reset(StellarisADCState *s) { int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_UINT32(actss, stellaris_adc_state), - VMSTATE_UINT32(ris, stellaris_adc_state), - VMSTATE_UINT32(im, stellaris_adc_state), - VMSTATE_UINT32(emux, stellaris_adc_state), - VMSTATE_UINT32(ostat, stellaris_adc_state), - VMSTATE_UINT32(ustat, stellaris_adc_state), - VMSTATE_UINT32(sspri, stellaris_adc_state), - VMSTATE_UINT32(sac, stellaris_adc_state), - VMSTATE_UINT32(fifo[0].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[0].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[0], stellaris_adc_state), - VMSTATE_UINT32(ssctl[0], stellaris_adc_state), - VMSTATE_UINT32(fifo[1].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[1].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[1], stellaris_adc_state), - VMSTATE_UINT32(ssctl[1], stellaris_adc_state), - VMSTATE_UINT32(fifo[2].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[2].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[2], stellaris_adc_state), - VMSTATE_UINT32(ssctl[2], stellaris_adc_state), - VMSTATE_UINT32(fifo[3].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[3].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[3], stellaris_adc_state), - VMSTATE_UINT32(ssctl[3], stellaris_adc_state), - VMSTATE_UINT32(noise, stellaris_adc_state), + VMSTATE_UINT32(actss, StellarisADCState), + VMSTATE_UINT32(ris, StellarisADCState), + VMSTATE_UINT32(im, StellarisADCState), + VMSTATE_UINT32(emux, StellarisADCState), + VMSTATE_UINT32(ostat, StellarisADCState), + VMSTATE_UINT32(ustat, StellarisADCState), + VMSTATE_UINT32(sspri, StellarisADCState), + VMSTATE_UINT32(sac, StellarisADCState), + VMSTATE_UINT32(fifo[0].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[0].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[0], StellarisADCState), + VMSTATE_UINT32(ssctl[0], StellarisADCState), + VMSTATE_UINT32(fifo[1].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[1].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[1], StellarisADCState), + VMSTATE_UINT32(ssctl[1], StellarisADCState), + VMSTATE_UINT32(fifo[2].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[2].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[2], StellarisADCState), + VMSTATE_UINT32(ssctl[2], StellarisADCState), + VMSTATE_UINT32(fifo[3].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[3].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[3], StellarisADCState), + VMSTATE_UINT32(ssctl[3], StellarisADCState), + VMSTATE_UINT32(noise, StellarisADCState), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { static void stellaris_adc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - stellaris_adc_state *s = STELLARIS_ADC(obj); + StellarisADCState *s = STELLARIS_ADC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_class_init(ObjectClass *klass, void *data) static const TypeInfo stellaris_adc_info = { .name = TYPE_STELLARIS_ADC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(stellaris_adc_state), + .instance_size = sizeof(StellarisADCState), .instance_init = stellaris_adc_init, .class_init = stellaris_adc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The typedef and definitions are generated by the OBJECT_DECLARE_TYPE macro in "hw/arm/bcm2836.h": 20 #define TYPE_BCM283X "bcm283x" 21 OBJECT_DECLARE_TYPE(BCM283XState, BCM283XClass, BCM283X) The script ran in commit a489d1951c ("Use OBJECT_DECLARE_TYPE when possible") missed them because they are declared in a different file unit. Remove them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bcm2836.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/raspi_platform.h" #include "hw/sysbus.h" -typedef struct BCM283XClass { +struct BCM283XClass { /*< private >*/ DeviceClass parent_class; /*< public >*/ @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XClass { hwaddr peri_base; /* Peripheral base address seen by the CPU */ hwaddr ctrl_base; /* Interrupt controller and mailboxes etc. */ int clusterid; -} BCM283XClass; - -#define BCM283X_CLASS(klass) \ - OBJECT_CLASS_CHECK(BCM283XClass, (klass), TYPE_BCM283X) -#define BCM283X_GET_CLASS(obj) \ - OBJECT_GET_CLASS(BCM283XClass, (obj), TYPE_BCM283X) +}; static Property bcm2836_enabled_cores_property = DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> NPCM7XX models have been commited after the conversion from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible"). Manually convert them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/adc/npcm7xx_adc.h | 7 +++---- include/hw/arm/npcm7xx.h | 18 ++++++------------ include/hw/i2c/npcm7xx_smbus.h | 7 +++---- include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +++--- include/hw/misc/npcm7xx_mft.h | 7 +++---- include/hw/misc/npcm7xx_pwm.h | 3 +-- include/hw/misc/npcm7xx_rng.h | 6 +++--- include/hw/net/npcm7xx_emc.h | 5 +---- include/hw/sd/npcm7xx_sdhci.h | 4 ++-- 10 files changed, 26 insertions(+), 39 deletions(-) diff --git a/include/hw/adc/npcm7xx_adc.h b/include/hw/adc/npcm7xx_adc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/adc/npcm7xx_adc.h +++ b/include/hw/adc/npcm7xx_adc.h @@ -XXX,XX +XXX,XX @@ * @iref: The internal reference voltage, initialized at launch time. * @rv: The calibrated output values of 0.5V and 1.5V for the ADC. */ -typedef struct { +struct NPCM7xxADCState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct { uint32_t iref; uint16_t calibration_r_values[NPCM7XX_ADC_NUM_CALIB]; -} NPCM7xxADCState; +}; #define TYPE_NPCM7XX_ADC "npcm7xx-adc" -#define NPCM7XX_ADC(obj) \ - OBJECT_CHECK(NPCM7xxADCState, (obj), TYPE_NPCM7XX_ADC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxADCState, NPCM7XX_ADC) #endif /* NPCM7XX_ADC_H */ diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_NR_PWM_MODULES 2 -typedef struct NPCM7xxMachine { +struct NPCM7xxMachine { MachineState parent; /* * PWM fan splitter. each splitter connects to one PWM output and @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachine { */ SplitIRQ fan_splitter[NPCM7XX_NR_PWM_MODULES * NPCM7XX_PWM_PER_MODULE]; -} NPCM7xxMachine; +}; #define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") -#define NPCM7XX_MACHINE(obj) \ - OBJECT_CHECK(NPCM7xxMachine, (obj), TYPE_NPCM7XX_MACHINE) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMachine, NPCM7XX_MACHINE) typedef struct NPCM7xxMachineClass { MachineClass parent; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachineClass { #define NPCM7XX_MACHINE_GET_CLASS(obj) \ OBJECT_GET_CLASS(NPCM7xxMachineClass, (obj), TYPE_NPCM7XX_MACHINE) -typedef struct NPCM7xxState { +struct NPCM7xxState { DeviceState parent; ARMCPU cpu[NPCM7XX_MAX_NUM_CPUS]; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxFIUState fiu[2]; NPCM7xxEMCState emc[2]; NPCM7xxSDHCIState mmc; -} NPCM7xxState; +}; #define TYPE_NPCM7XX "npcm7xx" -#define NPCM7XX(obj) OBJECT_CHECK(NPCM7xxState, (obj), TYPE_NPCM7XX) +OBJECT_DECLARE_TYPE(NPCM7xxState, NPCM7xxClass, NPCM7XX) #define TYPE_NPCM730 "npcm730" #define TYPE_NPCM750 "npcm750" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxClass { uint32_t num_cpus; } NPCM7xxClass; -#define NPCM7XX_CLASS(klass) \ - OBJECT_CLASS_CHECK(NPCM7xxClass, (klass), TYPE_NPCM7XX) -#define NPCM7XX_GET_CLASS(obj) \ - OBJECT_GET_CLASS(NPCM7xxClass, (obj), TYPE_NPCM7XX) - /** * npcm7xx_load_kernel - Loads memory with everything needed to boot * @machine - The machine containing the SoC to be booted. diff --git a/include/hw/i2c/npcm7xx_smbus.h b/include/hw/i2c/npcm7xx_smbus.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/npcm7xx_smbus.h +++ b/include/hw/i2c/npcm7xx_smbus.h @@ -XXX,XX +XXX,XX @@ typedef enum NPCM7xxSMBusStatus { * @rx_cur: The current position of rx_fifo. * @status: The current status of the SMBus. */ -typedef struct NPCM7xxSMBusState { +struct NPCM7xxSMBusState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSMBusState { uint8_t rx_cur; NPCM7xxSMBusStatus status; -} NPCM7xxSMBusState; +}; #define TYPE_NPCM7XX_SMBUS "npcm7xx-smbus" -#define NPCM7XX_SMBUS(obj) OBJECT_CHECK(NPCM7xxSMBusState, (obj), \ - TYPE_NPCM7XX_SMBUS) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxSMBusState, NPCM7XX_SMBUS) #endif /* NPCM7XX_SMBUS_H */ diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_clk.h +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxCLKState { }; #define TYPE_NPCM7XX_CLK "npcm7xx-clk" -#define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxCLKState, NPCM7XX_CLK) #endif /* NPCM7XX_CLK_H */ diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_gcr.h +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ */ #define NPCM7XX_GCR_NR_REGS (0x148 / sizeof(uint32_t)) -typedef struct NPCM7xxGCRState { +struct NPCM7xxGCRState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxGCRState { uint32_t reset_pwron; uint32_t reset_mdlr; uint32_t reset_intcr3; -} NPCM7xxGCRState; +}; #define TYPE_NPCM7XX_GCR "npcm7xx-gcr" -#define NPCM7XX_GCR(obj) OBJECT_CHECK(NPCM7xxGCRState, (obj), TYPE_NPCM7XX_GCR) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxGCRState, NPCM7XX_GCR) #endif /* NPCM7XX_GCR_H */ diff --git a/include/hw/misc/npcm7xx_mft.h b/include/hw/misc/npcm7xx_mft.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_mft.h +++ b/include/hw/misc/npcm7xx_mft.h @@ -XXX,XX +XXX,XX @@ * @max_rpm: The maximum rpm for fans. Order: A0, B0, A1, B1. * @duty: The duty cycles for fans, relative to NPCM7XX_PWM_MAX_DUTY. */ -typedef struct NPCM7xxMFTState { +struct NPCM7xxMFTState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMFTState { uint32_t max_rpm[NPCM7XX_MFT_FANIN_COUNT]; uint32_t duty[NPCM7XX_MFT_FANIN_COUNT]; -} NPCM7xxMFTState; +}; #define TYPE_NPCM7XX_MFT "npcm7xx-mft" -#define NPCM7XX_MFT(obj) \ - OBJECT_CHECK(NPCM7xxMFTState, (obj), TYPE_NPCM7XX_MFT) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMFTState, NPCM7XX_MFT) #endif /* NPCM7XX_MFT_H */ diff --git a/include/hw/misc/npcm7xx_pwm.h b/include/hw/misc/npcm7xx_pwm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_pwm.h +++ b/include/hw/misc/npcm7xx_pwm.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxPWMState { }; #define TYPE_NPCM7XX_PWM "npcm7xx-pwm" -#define NPCM7XX_PWM(obj) \ - OBJECT_CHECK(NPCM7xxPWMState, (obj), TYPE_NPCM7XX_PWM) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxPWMState, NPCM7XX_PWM) #endif /* NPCM7XX_PWM_H */ diff --git a/include/hw/misc/npcm7xx_rng.h b/include/hw/misc/npcm7xx_rng.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_rng.h +++ b/include/hw/misc/npcm7xx_rng.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" -typedef struct NPCM7xxRNGState { +struct NPCM7xxRNGState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRNGState { uint8_t rngcs; uint8_t rngd; uint8_t rngmode; -} NPCM7xxRNGState; +}; #define TYPE_NPCM7XX_RNG "npcm7xx-rng" -#define NPCM7XX_RNG(obj) OBJECT_CHECK(NPCM7xxRNGState, (obj), TYPE_NPCM7XX_RNG) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxRNGState, NPCM7XX_RNG) #endif /* NPCM7XX_RNG_H */ diff --git a/include/hw/net/npcm7xx_emc.h b/include/hw/net/npcm7xx_emc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/npcm7xx_emc.h +++ b/include/hw/net/npcm7xx_emc.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxEMCState { bool rx_active; }; -typedef struct NPCM7xxEMCState NPCM7xxEMCState; - #define TYPE_NPCM7XX_EMC "npcm7xx-emc" -#define NPCM7XX_EMC(obj) \ - OBJECT_CHECK(NPCM7xxEMCState, (obj), TYPE_NPCM7XX_EMC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxEMCState, NPCM7XX_EMC) #endif /* NPCM7XX_EMC_H */ diff --git a/include/hw/sd/npcm7xx_sdhci.h b/include/hw/sd/npcm7xx_sdhci.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/npcm7xx_sdhci.h +++ b/include/hw/sd/npcm7xx_sdhci.h @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRegs { uint32_t boottoctrl; } NPCM7xxRegisters; -typedef struct NPCM7xxSDHCIState { +struct NPCM7xxSDHCIState { SysBusDevice parent; MemoryRegion container; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSDHCIState { NPCM7xxRegisters regs; SDHCIState sdhci; -} NPCM7xxSDHCIState; +}; #endif /* NPCM7XX_SDHCI_H */ -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The structure is named SECUREECState. Rename the type accordingly. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "sysemu/runstate.h" -typedef struct { +typedef struct SECUREECState { SysBusDevice parent_obj; MemoryRegion iomem; } SECUREECState; -#define TYPE_SBSA_EC "sbsa-ec" -#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC) +#define TYPE_SBSA_SECURE_EC "sbsa-ec" +#define SBSA_SECURE_EC(obj) \ + OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, @@ -XXX,XX +XXX,XX @@ static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size) } static void sbsa_ec_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) + uint64_t value, unsigned size) { if (offset == 0) { /* PSCI machine power command register */ switch (value) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps sbsa_ec_ops = { static void sbsa_ec_init(Object *obj) { - SECUREECState *s = SECURE_EC(obj); + SECUREECState *s = SBSA_SECURE_EC(obj); SysBusDevice *dev = SYS_BUS_DEVICE(obj); memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec", @@ -XXX,XX +XXX,XX @@ static void sbsa_ec_class_init(ObjectClass *klass, void *data) } static const TypeInfo sbsa_ec_info = { - .name = TYPE_SBSA_EC, + .name = TYPE_SBSA_SECURE_EC, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(SECUREECState), .instance_init = sbsa_ec_init, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This model was merged few days before the QOM cleanup from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible") was pulled and merged. Manually adapt. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ typedef struct SECUREECState { } SECUREECState; #define TYPE_SBSA_SECURE_EC "sbsa-ec" -#define SBSA_SECURE_EC(obj) \ - OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) +OBJECT_DECLARE_SIMPLE_TYPE(SECUREECState, SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/intc/xilinx_intc.c:45:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/xilinx_intc.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/hw/intc/xilinx_intc.c b/hw/intc/xilinx_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/xilinx_intc.c +++ b/hw/intc/xilinx_intc.c @@ -XXX,XX +XXX,XX @@ #define R_MAX 8 #define TYPE_XILINX_INTC "xlnx.xps-intc" -DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, - TYPE_XILINX_INTC) +typedef struct XpsIntc XpsIntc; +DECLARE_INSTANCE_CHECKER(XpsIntc, XILINX_INTC, TYPE_XILINX_INTC) -struct xlx_pic +struct XpsIntc { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct xlx_pic uint32_t irq_pin_state; }; -static void update_irq(struct xlx_pic *p) +static void update_irq(XpsIntc *p) { uint32_t i; @@ -XXX,XX +XXX,XX @@ static void update_irq(struct xlx_pic *p) qemu_set_irq(p->parent_irq, (p->regs[R_MER] & 1) && p->regs[R_IPR]); } -static uint64_t -pic_read(void *opaque, hwaddr addr, unsigned int size) +static uint64_t pic_read(void *opaque, hwaddr addr, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t r = 0; addr >>= 2; @@ -XXX,XX +XXX,XX @@ pic_read(void *opaque, hwaddr addr, unsigned int size) return r; } -static void -pic_write(void *opaque, hwaddr addr, - uint64_t val64, unsigned int size) +static void pic_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t value = val64; addr >>= 2; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps pic_ops = { static void irq_handler(void *opaque, int irq, int level) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; /* edge triggered interrupt */ if (p->c_kind_of_intr & (1 << irq) && p->regs[R_MER] & 2) { @@ -XXX,XX +XXX,XX @@ static void irq_handler(void *opaque, int irq, int level) static void xilinx_intc_init(Object *obj) { - struct xlx_pic *p = XILINX_INTC(obj); + XpsIntc *p = XILINX_INTC(obj); qdev_init_gpio_in(DEVICE(obj), irq_handler, 32); sysbus_init_irq(SYS_BUS_DEVICE(obj), &p->parent_irq); @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_init(Object *obj) } static Property xilinx_intc_properties[] = { - DEFINE_PROP_UINT32("kind-of-intr", struct xlx_pic, c_kind_of_intr, 0), + DEFINE_PROP_UINT32("kind-of-intr", XpsIntc, c_kind_of_intr, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_intc_info = { .name = TYPE_XILINX_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct xlx_pic), + .instance_size = sizeof(XpsIntc), .instance_init = xilinx_intc_init, .class_init = xilinx_intc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/timer/xilinx_timer.c:65:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-15-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/xilinx_timer.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/hw/timer/xilinx_timer.c b/hw/timer/xilinx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/xilinx_timer.c +++ b/hw/timer/xilinx_timer.c @@ -XXX,XX +XXX,XX @@ struct xlx_timer }; #define TYPE_XILINX_TIMER "xlnx.xps-timer" -DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, - TYPE_XILINX_TIMER) +typedef struct XpsTimerState XpsTimerState; +DECLARE_INSTANCE_CHECKER(XpsTimerState, XILINX_TIMER, TYPE_XILINX_TIMER) -struct timerblock +struct XpsTimerState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct timerblock struct xlx_timer *timers; }; -static inline unsigned int num_timers(struct timerblock *t) +static inline unsigned int num_timers(XpsTimerState *t) { return 2 - t->one_timer_only; } @@ -XXX,XX +XXX,XX @@ static inline unsigned int timer_from_addr(hwaddr addr) return addr >> 2; } -static void timer_update_irq(struct timerblock *t) +static void timer_update_irq(XpsTimerState *t) { unsigned int i, irq = 0; uint32_t csr; @@ -XXX,XX +XXX,XX @@ static void timer_update_irq(struct timerblock *t) static uint64_t timer_read(void *opaque, hwaddr addr, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; uint32_t r = 0; unsigned int timer; @@ -XXX,XX +XXX,XX @@ static void timer_write(void *opaque, hwaddr addr, uint64_t val64, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; unsigned int timer; uint32_t value = val64; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps timer_ops = { static void timer_hit(void *opaque) { struct xlx_timer *xt = opaque; - struct timerblock *t = xt->parent; + XpsTimerState *t = xt->parent; D(fprintf(stderr, "%s %d\n", __func__, xt->nr)); xt->regs[R_TCSR] |= TCSR_TINT; @@ -XXX,XX +XXX,XX @@ static void timer_hit(void *opaque) static void xilinx_timer_realize(DeviceState *dev, Error **errp) { - struct timerblock *t = XILINX_TIMER(dev); + XpsTimerState *t = XILINX_TIMER(dev); unsigned int i; /* Init all the ptimers. */ @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_realize(DeviceState *dev, Error **errp) static void xilinx_timer_init(Object *obj) { - struct timerblock *t = XILINX_TIMER(obj); + XpsTimerState *t = XILINX_TIMER(obj); /* All timers share a single irq line. */ sysbus_init_irq(SYS_BUS_DEVICE(obj), &t->irq); } static Property xilinx_timer_properties[] = { - DEFINE_PROP_UINT32("clock-frequency", struct timerblock, freq_hz, - 62 * 1000000), - DEFINE_PROP_UINT8("one-timer-only", struct timerblock, one_timer_only, 0), + DEFINE_PROP_UINT32("clock-frequency", XpsTimerState, freq_hz, 62 * 1000000), + DEFINE_PROP_UINT8("one-timer-only", XpsTimerState, one_timer_only, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_timer_info = { .name = TYPE_XILINX_TIMER, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct timerblock), + .instance_size = sizeof(XpsTimerState), .instance_init = xilinx_timer_init, .class_init = xilinx_timer_class_init, }; -- 2.34.1 From: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> ARM trusted firmware, when built with FEAT_HCX support, sets SCR_EL3.HXEn bit to allow EL2 to modify HCRX_EL2 register without trapping it in EL3. Qemu uses a valid mask to clear unsupported SCR_EL3 bits when emulating SCR_EL3 write, and that mask doesn't include SCR_EL3.HXEn bit even if FEAT_HCX is enabled and exposed to the guest. As a result EL3 writes of that bit are ignored. Cc: qemu-stable@nongnu.org Signed-off-by: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> Message-id: 20230105221251.17896-4-eiakovlev@linux.microsoft.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 +++ 1 file changed, 3 insertions(+) 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 scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) if (cpu_isar_feature(aa64_sme, cpu)) { valid_mask |= SCR_ENTP2; } + if (cpu_isar_feature(aa64_hcx, cpu)) { + valid_mask |= SCR_HXEN; + } } else { valid_mask &= ~(SCR_RW | SCR_ST); if (cpu_isar_feature(aa32_ras, cpu)) { -- 2.34.1