diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/Makefile | 2 | ||||
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 15 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 37 | ||||
| -rw-r--r-- | drivers/hv/hv_balloon.c | 190 | ||||
| -rw-r--r-- | drivers/hv/hv_common.c | 6 | ||||
| -rw-r--r-- | drivers/hv/hv_fcopy.c | 427 | ||||
| -rw-r--r-- | drivers/hv/hv_util.c | 12 | ||||
| -rw-r--r-- | drivers/hv/hyperv_vmbus.h | 5 |
8 files changed, 117 insertions, 577 deletions
diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile index d76df5c8c2..b992c0ed18 100644 --- a/drivers/hv/Makefile +++ b/drivers/hv/Makefile @@ -10,7 +10,7 @@ hv_vmbus-y := vmbus_drv.o \ hv.o connection.o channel.o \ channel_mgmt.o ring_buffer.o hv_trace.o hv_vmbus-$(CONFIG_HYPERV_TESTING) += hv_debugfs.o -hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o hv_utils_transport.o +hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_utils_transport.o # Code that must be built-in obj-$(subst m,y,$(CONFIG_HYPERV)) += hv_common.o diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 2f4d09ce02..3c6011a48d 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -120,7 +120,9 @@ const struct vmbus_device vmbus_devs[] = { }, /* File copy */ - { .dev_type = HV_FCOPY, + /* fcopy always uses 16KB ring buffer size and is working well for last many years */ + { .pref_ring_size = 0x4000, + .dev_type = HV_FCOPY, HV_FCOPY_GUID, .perf_device = false, .allowed_in_isolated = false, @@ -140,12 +142,19 @@ const struct vmbus_device vmbus_devs[] = { .allowed_in_isolated = false, }, - /* Unknown GUID */ - { .dev_type = HV_UNKNOWN, + /* + * Unknown GUID + * 64 KB ring buffer + 4 KB header should be sufficient size for any Hyper-V device apart + * from HV_NIC and HV_SCSI. This case avoid the fallback for unknown devices to allocate + * much bigger (2 MB) of ring size. + */ + { .pref_ring_size = 0x11000, + .dev_type = HV_UNKNOWN, .perf_device = false, .allowed_in_isolated = false, }, }; +EXPORT_SYMBOL_GPL(vmbus_devs); static const struct { guid_t guid; diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index a8ad728354..e0d676c74f 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -45,8 +45,8 @@ int hv_init(void) * This involves a hypercall. */ int hv_post_message(union hv_connection_id connection_id, - enum hv_message_type message_type, - void *payload, size_t payload_size) + enum hv_message_type message_type, + void *payload, size_t payload_size) { struct hv_input_post_message *aligned_msg; unsigned long flags; @@ -86,7 +86,7 @@ int hv_post_message(union hv_connection_id connection_id, status = HV_STATUS_INVALID_PARAMETER; } else { status = hv_do_hypercall(HVCALL_POST_MESSAGE, - aligned_msg, NULL); + aligned_msg, NULL); } local_irq_restore(flags); @@ -111,7 +111,7 @@ int hv_synic_alloc(void) hv_context.hv_numa_map = kcalloc(nr_node_ids, sizeof(struct cpumask), GFP_KERNEL); - if (hv_context.hv_numa_map == NULL) { + if (!hv_context.hv_numa_map) { pr_err("Unable to allocate NUMA map\n"); goto err; } @@ -120,11 +120,11 @@ int hv_synic_alloc(void) hv_cpu = per_cpu_ptr(hv_context.cpu_context, cpu); tasklet_init(&hv_cpu->msg_dpc, - vmbus_on_msg_dpc, (unsigned long) hv_cpu); + vmbus_on_msg_dpc, (unsigned long)hv_cpu); if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->post_msg_page == NULL) { + if (!hv_cpu->post_msg_page) { pr_err("Unable to allocate post msg page\n"); goto err; } @@ -147,14 +147,14 @@ int hv_synic_alloc(void) if (!ms_hyperv.paravisor_present && !hv_root_partition) { hv_cpu->synic_message_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_message_page == NULL) { + if (!hv_cpu->synic_message_page) { pr_err("Unable to allocate SYNIC message page\n"); goto err; } hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC); - if (hv_cpu->synic_event_page == NULL) { + if (!hv_cpu->synic_event_page) { pr_err("Unable to allocate SYNIC event page\n"); free_page((unsigned long)hv_cpu->synic_message_page); @@ -203,14 +203,13 @@ err: return ret; } - void hv_synic_free(void) { int cpu, ret; for_each_present_cpu(cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); /* It's better to leak the page if the encryption fails. */ if (ms_hyperv.paravisor_present && hv_isolation_type_tdx()) { @@ -262,8 +261,8 @@ void hv_synic_free(void) */ void hv_synic_enable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_simp simp; union hv_synic_siefp siefp; union hv_synic_sint shared_sint; @@ -277,8 +276,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_message_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_message_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_message_page) pr_err("Fail to map synic message page.\n"); } else { @@ -296,8 +295,8 @@ void hv_synic_enable_regs(unsigned int cpu) /* Mask out vTOM bit. ioremap_cache() maps decrypted */ u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) & ~ms_hyperv.shared_gpa_boundary; - hv_cpu->synic_event_page - = (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); + hv_cpu->synic_event_page = + (void *)ioremap_cache(base, HV_HYP_PAGE_SIZE); if (!hv_cpu->synic_event_page) pr_err("Fail to map synic event page.\n"); } else { @@ -348,8 +347,8 @@ int hv_synic_init(unsigned int cpu) */ void hv_synic_disable_regs(unsigned int cpu) { - struct hv_per_cpu_context *hv_cpu - = per_cpu_ptr(hv_context.cpu_context, cpu); + struct hv_per_cpu_context *hv_cpu = + per_cpu_ptr(hv_context.cpu_context, cpu); union hv_synic_sint shared_sint; union hv_synic_simp simp; union hv_synic_siefp siefp; diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c index e000fa3b9f..0e7427c2ba 100644 --- a/drivers/hv/hv_balloon.c +++ b/drivers/hv/hv_balloon.c @@ -25,6 +25,7 @@ #include <linux/notifier.h> #include <linux/percpu_counter.h> #include <linux/page_reporting.h> +#include <linux/sizes.h> #include <linux/hyperv.h> #include <asm/hyperv-tlfs.h> @@ -41,8 +42,6 @@ * Begin protocol definitions. */ - - /* * Protocol versions. The low word is the minor version, the high word the major * version. @@ -71,8 +70,6 @@ enum { DYNMEM_PROTOCOL_VERSION_CURRENT = DYNMEM_PROTOCOL_VERSION_WIN10 }; - - /* * Message Types */ @@ -101,7 +98,6 @@ enum dm_message_type { DM_VERSION_1_MAX = 12 }; - /* * Structures defining the dynamic memory management * protocol. @@ -115,7 +111,6 @@ union dm_version { __u32 version; } __packed; - union dm_caps { struct { __u64 balloon:1; @@ -148,8 +143,6 @@ union dm_mem_page_range { __u64 page_range; } __packed; - - /* * The header for all dynamic memory messages: * @@ -174,7 +167,6 @@ struct dm_message { __u8 data[]; /* enclosed message */ } __packed; - /* * Specific message types supporting the dynamic memory protocol. */ @@ -271,7 +263,6 @@ struct dm_status { __u32 io_diff; } __packed; - /* * Message to ask the guest to allocate memory - balloon up message. * This message is sent from the host to the guest. The guest may not be @@ -286,14 +277,13 @@ struct dm_balloon { __u32 reservedz; } __packed; - /* * Balloon response message; this message is sent from the guest * to the host in response to the balloon message. * * reservedz: Reserved; must be set to zero. * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * range_count: The number of ranges in the range array. * @@ -314,7 +304,7 @@ struct dm_balloon_response { * to the guest to give guest more memory. * * more_pages: If FALSE, this is the last message of the transaction. - * if TRUE there will atleast one more message from the guest. + * if TRUE there will be at least one more message from the guest. * * reservedz: Reserved; must be set to zero. * @@ -342,7 +332,6 @@ struct dm_unballoon_response { struct dm_header hdr; } __packed; - /* * Hot add request message. Message sent from the host to the guest. * @@ -390,7 +379,6 @@ enum dm_info_type { MAX_INFO_TYPE }; - /* * Header for the information message. */ @@ -425,11 +413,11 @@ struct dm_info_msg { * The range start_pfn : end_pfn specifies the range * that the host has asked us to hot add. The range * start_pfn : ha_end_pfn specifies the range that we have - * currently hot added. We hot add in multiples of 128M - * chunks; it is possible that we may not be able to bring - * online all the pages in the region. The range + * currently hot added. We hot add in chunks equal to the + * memory block size; it is possible that we may not be able + * to bring online all the pages in the region. The range * covered_start_pfn:covered_end_pfn defines the pages that can - * be brough online. + * be brought online. */ struct hv_hotadd_state { @@ -480,10 +468,10 @@ static unsigned long last_post_time; static int hv_hypercall_multi_failure; -module_param(hot_add, bool, (S_IRUGO | S_IWUSR)); +module_param(hot_add, bool, 0644); MODULE_PARM_DESC(hot_add, "If set attempt memory hot_add"); -module_param(pressure_report_delay, uint, (S_IRUGO | S_IWUSR)); +module_param(pressure_report_delay, uint, 0644); MODULE_PARM_DESC(pressure_report_delay, "Delay in secs in reporting pressure"); static atomic_t trans_id = ATOMIC_INIT(0); @@ -502,11 +490,13 @@ enum hv_dm_state { DM_INIT_ERROR }; - static __u8 recv_buffer[HV_HYP_PAGE_SIZE]; static __u8 balloon_up_send_buffer[HV_HYP_PAGE_SIZE]; + +static unsigned long ha_pages_in_chunk; +#define HA_BYTES_IN_CHUNK (ha_pages_in_chunk << PAGE_SHIFT) + #define PAGES_IN_2M (2 * 1024 * 1024 / PAGE_SIZE) -#define HA_CHUNK (128 * 1024 * 1024 / PAGE_SIZE) struct hv_dynmem_device { struct hv_device *dev; @@ -595,12 +585,12 @@ static inline bool has_pfn_is_backed(struct hv_hotadd_state *has, struct hv_hotadd_gap *gap; /* The page is not backed. */ - if ((pfn < has->covered_start_pfn) || (pfn >= has->covered_end_pfn)) + if (pfn < has->covered_start_pfn || pfn >= has->covered_end_pfn) return false; /* Check for gaps. */ list_for_each_entry(gap, &has->gap_list, list) { - if ((pfn >= gap->start_pfn) && (pfn < gap->end_pfn)) + if (pfn >= gap->start_pfn && pfn < gap->end_pfn) return false; } @@ -724,28 +714,21 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, unsigned long processed_pfn; unsigned long total_pfn = pfn_count; - for (i = 0; i < (size/HA_CHUNK); i++) { - start_pfn = start + (i * HA_CHUNK); + for (i = 0; i < (size/ha_pages_in_chunk); i++) { + start_pfn = start + (i * ha_pages_in_chunk); scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn += HA_CHUNK; - - if (total_pfn > HA_CHUNK) { - processed_pfn = HA_CHUNK; - total_pfn -= HA_CHUNK; - } else { - processed_pfn = total_pfn; - total_pfn = 0; - } - - has->covered_end_pfn += processed_pfn; + has->ha_end_pfn += ha_pages_in_chunk; + processed_pfn = umin(total_pfn, ha_pages_in_chunk); + total_pfn -= processed_pfn; + has->covered_end_pfn += processed_pfn; } reinit_completion(&dm_device.ol_waitevent); nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn)); ret = add_memory(nid, PFN_PHYS((start_pfn)), - (HA_CHUNK << PAGE_SHIFT), MHP_MERGE_RESOURCE); + HA_BYTES_IN_CHUNK, MHP_MERGE_RESOURCE); if (ret) { pr_err("hot_add memory failed error is %d\n", ret); @@ -760,7 +743,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size, do_hot_add = false; } scoped_guard(spinlock_irqsave, &dm_device.ha_lock) { - has->ha_end_pfn -= HA_CHUNK; + has->ha_end_pfn -= ha_pages_in_chunk; has->covered_end_pfn -= processed_pfn; } break; @@ -787,8 +770,8 @@ static void hv_online_page(struct page *pg, unsigned int order) guard(spinlock_irqsave)(&dm_device.ha_lock); list_for_each_entry(has, &dm_device.ha_region_list, list) { /* The page belongs to a different HAS. */ - if ((pfn < has->start_pfn) || - (pfn + (1UL << order) > has->end_pfn)) + if (pfn < has->start_pfn || + (pfn + (1UL << order) > has->end_pfn)) continue; hv_bring_pgs_online(has, pfn, 1UL << order); @@ -800,7 +783,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) { struct hv_hotadd_state *has; struct hv_hotadd_gap *gap; - unsigned long residual, new_inc; + unsigned long residual; int ret = 0; guard(spinlock_irqsave)(&dm_device.ha_lock); @@ -836,15 +819,9 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) * our current limit; extend it. */ if ((start_pfn + pfn_cnt) > has->end_pfn) { + /* Extend the region by multiples of ha_pages_in_chunk */ residual = (start_pfn + pfn_cnt - has->end_pfn); - /* - * Extend the region by multiples of HA_CHUNK. - */ - new_inc = (residual / HA_CHUNK) * HA_CHUNK; - if (residual % HA_CHUNK) - new_inc += HA_CHUNK; - - has->end_pfn += new_inc; + has->end_pfn += ALIGN(residual, ha_pages_in_chunk); } ret = 1; @@ -855,7 +832,7 @@ static int pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt) } static unsigned long handle_pg_range(unsigned long pg_start, - unsigned long pg_count) + unsigned long pg_count) { unsigned long start_pfn = pg_start; unsigned long pfn_cnt = pg_count; @@ -866,7 +843,7 @@ static unsigned long handle_pg_range(unsigned long pg_start, unsigned long res = 0, flags; pr_debug("Hot adding %lu pages starting at pfn 0x%lx.\n", pg_count, - pg_start); + pg_start); spin_lock_irqsave(&dm_device.ha_lock, flags); list_for_each_entry(has, &dm_device.ha_region_list, list) { @@ -902,22 +879,19 @@ static unsigned long handle_pg_range(unsigned long pg_start, if (start_pfn > has->start_pfn && online_section_nr(pfn_to_section_nr(start_pfn))) hv_bring_pgs_online(has, start_pfn, pgs_ol); - } - if ((has->ha_end_pfn < has->end_pfn) && (pfn_cnt > 0)) { + if (has->ha_end_pfn < has->end_pfn && pfn_cnt > 0) { /* * We have some residual hot add range * that needs to be hot added; hot add * it now. Hot add a multiple of - * HA_CHUNK that fully covers the pages + * ha_pages_in_chunk that fully covers the pages * we have. */ size = (has->end_pfn - has->ha_end_pfn); if (pfn_cnt <= size) { - size = ((pfn_cnt / HA_CHUNK) * HA_CHUNK); - if (pfn_cnt % HA_CHUNK) - size += HA_CHUNK; + size = ALIGN(pfn_cnt, ha_pages_in_chunk); } else { pfn_cnt = size; } @@ -1010,10 +984,7 @@ static void hot_add_req(struct work_struct *dummy) rg_start = dm->ha_wrk.ha_region_range.finfo.start_page; rg_sz = dm->ha_wrk.ha_region_range.finfo.page_cnt; - if ((rg_start == 0) && (!dm->host_specified_ha_region)) { - unsigned long region_size; - unsigned long region_start; - + if (rg_start == 0 && !dm->host_specified_ha_region) { /* * The host has not specified the hot-add region. * Based on the hot-add page range being specified, @@ -1021,19 +992,13 @@ static void hot_add_req(struct work_struct *dummy) * that need to be hot-added while ensuring the alignment * and size requirements of Linux as it relates to hot-add. */ - region_size = (pfn_cnt / HA_CHUNK) * HA_CHUNK; - if (pfn_cnt % HA_CHUNK) - region_size += HA_CHUNK; - - region_start = (pg_start / HA_CHUNK) * HA_CHUNK; - - rg_start = region_start; - rg_sz = region_size; + rg_start = ALIGN_DOWN(pg_start, ha_pages_in_chunk); + rg_sz = ALIGN(pfn_cnt, ha_pages_in_chunk); } if (do_hot_add) resp.page_count = process_hot_add(pg_start, pfn_cnt, - rg_start, rg_sz); + rg_start, rg_sz); dm->num_pages_added += resp.page_count; #endif @@ -1211,11 +1176,10 @@ static void post_status(struct hv_dynmem_device *dm) sizeof(struct dm_status), (unsigned long)NULL, VM_PKT_DATA_INBAND, 0); - } static void free_balloon_pages(struct hv_dynmem_device *dm, - union dm_mem_page_range *range_array) + union dm_mem_page_range *range_array) { int num_pages = range_array->finfo.page_cnt; __u64 start_frame = range_array->finfo.start_page; @@ -1231,8 +1195,6 @@ static void free_balloon_pages(struct hv_dynmem_device *dm, } } - - static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, unsigned int num_pages, struct dm_balloon_response *bl_resp, @@ -1278,7 +1240,6 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm, page_to_pfn(pg); bl_resp->range_array[i].finfo.page_cnt = alloc_unit; bl_resp->hdr.size += sizeof(union dm_mem_page_range); - } return i * alloc_unit; @@ -1332,7 +1293,7 @@ static void balloon_up(struct work_struct *dummy) if (num_ballooned == 0 || num_ballooned == num_pages) { pr_debug("Ballooned %u out of %u requested pages.\n", - num_pages, dm_device.balloon_wrk.num_pages); + num_pages, dm_device.balloon_wrk.num_pages); bl_resp->more_pages = 0; done = true; @@ -1366,16 +1327,15 @@ static void balloon_up(struct work_struct *dummy) for (i = 0; i < bl_resp->range_count; i++) free_balloon_pages(&dm_device, - &bl_resp->range_array[i]); + &bl_resp->range_array[i]); done = true; } } - } static void balloon_down(struct hv_dynmem_device *dm, - struct dm_unballoon_request *req) + struct dm_unballoon_request *req) { union dm_mem_page_range *range_array = req->range_array; int range_count = req->range_count; @@ -1389,7 +1349,7 @@ static void balloon_down(struct hv_dynmem_device *dm, } pr_debug("Freed %u ballooned pages.\n", - prev_pages_ballooned - dm->num_pages_ballooned); + prev_pages_ballooned - dm->num_pages_ballooned); if (req->more_pages == 1) return; @@ -1414,8 +1374,7 @@ static int dm_thread_func(void *dm_dev) struct hv_dynmem_device *dm = dm_dev; while (!kthread_should_stop()) { - wait_for_completion_interruptible_timeout( - &dm_device.config_event, 1*HZ); + wait_for_completion_interruptible_timeout(&dm_device.config_event, 1 * HZ); /* * The host expects us to post information on the memory * pressure every second. @@ -1439,9 +1398,8 @@ static int dm_thread_func(void *dm_dev) return 0; } - static void version_resp(struct hv_dynmem_device *dm, - struct dm_version_response *vresp) + struct dm_version_response *vresp) { struct dm_version_request version_req; int ret; @@ -1502,7 +1460,7 @@ version_error: } static void cap_resp(struct hv_dynmem_device *dm, - struct dm_capabilities_resp_msg *cap_resp) + struct dm_capabilities_resp_msg *cap_resp) { if (!cap_resp->is_accepted) { pr_err("Capabilities not accepted by host\n"); @@ -1535,7 +1493,7 @@ static void balloon_onchannelcallback(void *context) switch (dm_hdr->type) { case DM_VERSION_RESPONSE: version_resp(dm, - (struct dm_version_response *)dm_msg); + (struct dm_version_response *)dm_msg); break; case DM_CAPABILITIES_RESPONSE: @@ -1565,7 +1523,7 @@ static void balloon_onchannelcallback(void *context) dm->state = DM_BALLOON_DOWN; balloon_down(dm, - (struct dm_unballoon_request *)recv_buffer); + (struct dm_unballoon_request *)recv_buffer); break; case DM_MEM_HOT_ADD_REQUEST: @@ -1603,17 +1561,15 @@ static void balloon_onchannelcallback(void *context) default: pr_warn_ratelimited("Unhandled message: type: %d\n", dm_hdr->type); - } } - } #define HV_LARGE_REPORTING_ORDER 9 #define HV_LARGE_REPORTING_LEN (HV_HYP_PAGE_SIZE << \ HV_LARGE_REPORTING_ORDER) static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, - struct scatterlist *sgl, unsigned int nents) + struct scatterlist *sgl, unsigned int nents) { unsigned long flags; struct hv_memory_hint *hint; @@ -1648,7 +1604,7 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, */ /* page reporting for pages 2MB or higher */ - if (order >= HV_LARGE_REPORTING_ORDER ) { + if (order >= HV_LARGE_REPORTING_ORDER) { range->page.largepage = 1; range->page_size = HV_GPA_PAGE_RANGE_PAGE_SIZE_2MB; range->base_large_pfn = page_to_hvpfn( @@ -1662,23 +1618,21 @@ static int hv_free_page_report(struct page_reporting_dev_info *pr_dev_info, range->page.additional_pages = (sg->length / HV_HYP_PAGE_SIZE) - 1; } - } status = hv_do_rep_hypercall(HV_EXT_CALL_MEMORY_HEAT_HINT, nents, 0, hint, NULL); local_irq_restore(flags); if (!hv_result_success(status)) { - pr_err("Cold memory discard hypercall failed with status %llx\n", - status); + status); if (hv_hypercall_multi_failure > 0) hv_hypercall_multi_failure++; if (hv_result(status) == HV_STATUS_INVALID_PARAMETER) { pr_err("Underlying Hyper-V does not support order less than 9. Hypercall failed\n"); pr_err("Defaulting to page_reporting_order %d\n", - pageblock_order); + pageblock_order); page_reporting_order = pageblock_order; hv_hypercall_multi_failure++; return -EINVAL; @@ -1712,7 +1666,7 @@ static void enable_page_reporting(void) pr_err("Failed to enable cold memory discard: %d\n", ret); } else { pr_info("Cold memory discard hint enabled with order %d\n", - page_reporting_order); + page_reporting_order); } } @@ -1795,7 +1749,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1831,10 +1785,13 @@ static int balloon_connect_vsp(struct hv_device *dev) cap_msg.caps.cap_bits.hot_add = hot_add_enabled(); /* - * Specify our alignment requirements as it relates - * memory hot-add. Specify 128MB alignment. + * Specify our alignment requirements for memory hot-add. The value is + * the log base 2 of the number of megabytes in a chunk. For example, + * with 256 MiB chunks, the value is 8. The number of MiB in a chunk + * must be a power of 2. */ - cap_msg.caps.cap_bits.hot_add_alignment = 7; + cap_msg.caps.cap_bits.hot_add_alignment = + ilog2(HA_BYTES_IN_CHUNK / SZ_1M); /* * Currently the host does not use these @@ -1850,7 +1807,7 @@ static int balloon_connect_vsp(struct hv_device *dev) if (ret) goto out; - t = wait_for_completion_timeout(&dm_device.host_event, 5*HZ); + t = wait_for_completion_timeout(&dm_device.host_event, 5 * HZ); if (t == 0) { ret = -ETIMEDOUT; goto out; @@ -1891,8 +1848,8 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) char *sname; seq_printf(f, "%-22s: %u.%u\n", "host_version", - DYNMEM_MAJOR_VERSION(dm->version), - DYNMEM_MINOR_VERSION(dm->version)); + DYNMEM_MAJOR_VERSION(dm->version), + DYNMEM_MINOR_VERSION(dm->version)); seq_printf(f, "%-22s:", "capabilities"); if (ballooning_enabled()) @@ -1941,10 +1898,10 @@ static int hv_balloon_debug_show(struct seq_file *f, void *offset) seq_printf(f, "%-22s: %u\n", "pages_ballooned", dm->num_pages_ballooned); seq_printf(f, "%-22s: %lu\n", "total_pages_committed", - get_pages_committed(dm)); + get_pages_committed(dm)); seq_printf(f, "%-22s: %llu\n", "max_dynamic_page_count", - dm->max_dynamic_page_count); + dm->max_dynamic_page_count); return 0; } @@ -1954,7 +1911,7 @@ DEFINE_SHOW_ATTRIBUTE(hv_balloon_debug); static void hv_balloon_debugfs_init(struct hv_dynmem_device *b) { debugfs_create_file("hv-balloon", 0444, NULL, b, - &hv_balloon_debug_fops); + &hv_balloon_debug_fops); } static void hv_balloon_debugfs_exit(struct hv_dynmem_device *b) @@ -1984,8 +1941,23 @@ static int balloon_probe(struct hv_device *dev, hot_add = false; #ifdef CONFIG_MEMORY_HOTPLUG + /* + * Hot-add must operate in chunks that are of size equal to the + * memory block size because that's what the core add_memory() + * interface requires. The Hyper-V interface requires that the memory + * block size be a power of 2, which is guaranteed by the check in + * memory_dev_init(). + */ + ha_pages_in_chunk = memory_block_size_bytes() / PAGE_SIZE; do_hot_add = hot_add; #else + /* + * Without MEMORY_HOTPLUG, the guest returns a failure status for all + * hot add requests from Hyper-V, and the chunk size is used only to + * specify alignment to Hyper-V as required by the host/guest protocol. + * Somewhat arbitrarily, use 128 MiB. + */ + ha_pages_in_chunk = SZ_128M / PAGE_SIZE; do_hot_add = false; #endif dm_device.dev = dev; @@ -2097,7 +2069,6 @@ static int balloon_suspend(struct hv_device *hv_dev) tasklet_enable(&hv_dev->channel->callback_event); return 0; - } static int balloon_resume(struct hv_device *dev) @@ -2156,7 +2127,6 @@ static struct hv_driver balloon_drv = { static int __init init_balloon_drv(void) { - return vmbus_driver_register(&balloon_drv); } diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index dde3f9b687..9c452bfbd5 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -561,11 +561,7 @@ EXPORT_SYMBOL_GPL(hv_query_ext_cap); void hv_setup_dma_ops(struct device *dev, bool coherent) { - /* - * Hyper-V does not offer a vIOMMU in the guest - * VM, so pass 0/NULL for the IOMMU settings - */ - arch_setup_dma_ops(dev, 0, 0, coherent); + arch_setup_dma_ops(dev, coherent); } EXPORT_SYMBOL_GPL(hv_setup_dma_ops); diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c deleted file mode 100644 index 922d83eb7d..0000000000 --- a/drivers/hv/hv_fcopy.c +++ /dev/null @@ -1,427 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * An implementation of file copy service. - * - * Copyright (C) 2014, Microsoft, Inc. - * - * Author : K. Y. Srinivasan <ksrinivasan@novell.com> - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/nls.h> -#include <linux/workqueue.h> -#include <linux/hyperv.h> -#include <linux/sched.h> -#include <asm/hyperv-tlfs.h> - -#include "hyperv_vmbus.h" -#include "hv_utils_transport.h" - -#define WIN8_SRV_MAJOR 1 -#define WIN8_SRV_MINOR 1 -#define WIN8_SRV_VERSION (WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR) - -#define FCOPY_VER_COUNT 1 -static const int fcopy_versions[] = { - WIN8_SRV_VERSION -}; - -#define FW_VER_COUNT 1 -static const int fw_versions[] = { - UTIL_FW_VERSION -}; - -/* - * Global state maintained for transaction that is being processed. - * For a class of integration services, including the "file copy service", - * the specified protocol is a "request/response" protocol which means that - * there can only be single outstanding transaction from the host at any - * given point in time. We use this to simplify memory management in this - * driver - we cache and process only one message at a time. - * - * While the request/response protocol is guaranteed by the host, we further - * ensure this by serializing packet processing in this driver - we do not - * read additional packets from the VMBUs until the current packet is fully - * handled. - */ - -static struct { - int state; /* hvutil_device_state */ - int recv_len; /* number of bytes received. */ - struct hv_fcopy_hdr *fcopy_msg; /* current message */ - struct vmbus_channel *recv_channel; /* chn we got the request */ - u64 recv_req_id; /* request ID. */ -} fcopy_transaction; - -static void fcopy_respond_to_host(int error); -static void fcopy_send_data(struct work_struct *dummy); -static void fcopy_timeout_func(struct work_struct *dummy); -static DECLARE_DELAYED_WORK(fcopy_timeout_work, fcopy_timeout_func); -static DECLARE_WORK(fcopy_send_work, fcopy_send_data); -static const char fcopy_devname[] = "vmbus/hv_fcopy"; -static u8 *recv_buffer; -static struct hvutil_transport *hvt; -/* - * This state maintains the version number registered by the daemon. - */ -static int dm_reg_value; - -static void fcopy_poll_wrapper(void *channel) -{ - /* Transaction is finished, reset the state here to avoid races. */ - fcopy_transaction.state = HVUTIL_READY; - tasklet_schedule(&((struct vmbus_channel *)channel)->callback_event); -} - -static void fcopy_timeout_func(struct work_struct *dummy) -{ - /* - * If the timer fires, the user-mode component has not responded; - * process the pending transaction. - */ - fcopy_respond_to_host(HV_E_FAIL); - hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper); -} - -static void fcopy_register_done(void) -{ - pr_debug("FCP: userspace daemon registered\n"); - hv_poll_channel(fcopy_transaction.recv_channel, fcopy_poll_wrapper); -} - -static int fcopy_handle_handshake(u32 version) -{ - u32 our_ver = FCOPY_CURRENT_VERSION; - - switch (version) { - case FCOPY_VERSION_0: - /* Daemon doesn't expect us to reply */ - dm_reg_value = version; - break; - case FCOPY_VERSION_1: - /* Daemon expects us to reply with our own version */ - if (hvutil_transport_send(hvt, &our_ver, sizeof(our_ver), - fcopy_register_done)) - return -EFAULT; - dm_reg_value = version; - break; - default: - /* - * For now we will fail the registration. - * If and when we have multiple versions to - * deal with, we will be backward compatible. - * We will add this code when needed. - */ - return -EINVAL; - } - pr_debug("FCP: userspace daemon ver. %d connected\n", version); - return 0; -} - -static void fcopy_send_data(struct work_struct *dummy) -{ - struct hv_start_fcopy *smsg_out = NULL; - int operation = fcopy_transaction.fcopy_msg->operation; - struct hv_start_fcopy *smsg_in; - void *out_src; - int rc, out_len; - - /* - * The strings sent from the host are encoded in - * utf16; convert it to utf8 strings. - * The host assures us that the utf16 strings will not exceed - * the max lengths specified. We will however, reserve room - * for the string terminating character - in the utf16s_utf8s() - * function we limit the size of the buffer where the converted - * string is placed to W_MAX_PATH -1 to guarantee - * that the strings can be properly terminated! - */ - - switch (operation) { - case START_FILE_COPY: - out_len = sizeof(struct hv_start_fcopy); - smsg_out = kzalloc(sizeof(*smsg_out), GFP_KERNEL); - if (!smsg_out) - return; - - smsg_out->hdr.operation = operation; - smsg_in = (struct hv_start_fcopy *)fcopy_transaction.fcopy_msg; - - utf16s_to_utf8s((wchar_t *)smsg_in->file_name, W_MAX_PATH, - UTF16_LITTLE_ENDIAN, - (__u8 *)&smsg_out->file_name, W_MAX_PATH - 1); - - utf16s_to_utf8s((wchar_t *)smsg_in->path_name, W_MAX_PATH, - UTF16_LITTLE_ENDIAN, - (__u8 *)&smsg_out->path_name, W_MAX_PATH - 1); - - smsg_out->copy_flags = smsg_in->copy_flags; - smsg_out->file_size = smsg_in->file_size; - out_src = smsg_out; - break; - - case WRITE_TO_FILE: - out_src = fcopy_transaction.fcopy_msg; - out_len = sizeof(struct hv_do_fcopy); - break; - default: - out_src = fcopy_transaction.fcopy_msg; - out_len = fcopy_transaction.recv_len; - break; - } - - fcopy_transaction.state = HVUTIL_USERSPACE_REQ; - rc = hvutil_transport_send(hvt, out_src, out_len, NULL); - if (rc) { - pr_debug("FCP: failed to communicate to the daemon: %d\n", rc); - if (cancel_delayed_work_sync(&fcopy_timeout_work)) { - fcopy_respond_to_host(HV_E_FAIL); - fcopy_transaction.state = HVUTIL_READY; - } - } - kfree(smsg_out); -} - -/* - * Send a response back to the host. - */ - -static void -fcopy_respond_to_host(int error) -{ - struct icmsg_hdr *icmsghdr; - u32 buf_len; - struct vmbus_channel *channel; - u64 req_id; - - /* - * Copy the global state for completing the transaction. Note that - * only one transaction can be active at a time. This is guaranteed - * by the file copy protocol implemented by the host. Furthermore, - * the "transaction active" state we maintain ensures that there can - * only be one active transaction at a time. - */ - - buf_len = fcopy_transaction.recv_len; - channel = fcopy_transaction.recv_channel; - req_id = fcopy_transaction.recv_req_id; - - icmsghdr = (struct icmsg_hdr *) - &recv_buffer[sizeof(struct vmbuspipe_hdr)]; - - if (channel->onchannel_callback == NULL) - /* - * We have raced with util driver being unloaded; - * silently return. - */ - return; - - icmsghdr->status = error; - icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; - vmbus_sendpacket(channel, recv_buffer, buf_len, req_id, - VM_PKT_DATA_INBAND, 0); -} - -void hv_fcopy_onchannelcallback(void *context) -{ - struct vmbus_channel *channel = context; - u32 recvlen; - u64 requestid; - struct hv_fcopy_hdr *fcopy_msg; - struct icmsg_hdr *icmsghdr; - int fcopy_srv_version; - - if (fcopy_transaction.state > HVUTIL_READY) - return; - - if (vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 2, &recvlen, &requestid)) { - pr_err_ratelimited("Fcopy request received. Could not read into recv buf\n"); - return; - } - - if (!recvlen) - return; - - /* Ensure recvlen is big enough to read header data */ - if (recvlen < ICMSG_HDR) { - pr_err_ratelimited("Fcopy request received. Packet length too small: %d\n", - recvlen); - return; - } - - icmsghdr = (struct icmsg_hdr *)&recv_buffer[ - sizeof(struct vmbuspipe_hdr)]; - - if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) { - if (vmbus_prep_negotiate_resp(icmsghdr, - recv_buffer, recvlen, - fw_versions, FW_VER_COUNT, - fcopy_versions, FCOPY_VER_COUNT, - NULL, &fcopy_srv_version)) { - - pr_info("FCopy IC version %d.%d\n", - fcopy_srv_version >> 16, - fcopy_srv_version & 0xFFFF); - } - } else if (icmsghdr->icmsgtype == ICMSGTYPE_FCOPY) { - /* Ensure recvlen is big enough to contain hv_fcopy_hdr */ - if (recvlen < ICMSG_HDR + sizeof(struct hv_fcopy_hdr)) { - pr_err_ratelimited("Invalid Fcopy hdr. Packet length too small: %u\n", - recvlen); - return; - } - fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[ICMSG_HDR]; - - /* - * Stash away this global state for completing the - * transaction; note transactions are serialized. - */ - - fcopy_transaction.recv_len = recvlen; - fcopy_transaction.recv_req_id = requestid; - fcopy_transaction.fcopy_msg = fcopy_msg; - - if (fcopy_transaction.state < HVUTIL_READY) { - /* Userspace is not registered yet */ - fcopy_respond_to_host(HV_E_FAIL); - return; - } - fcopy_transaction.state = HVUTIL_HOSTMSG_RECEIVED; - - /* - * Send the information to the user-level daemon. - */ - schedule_work(&fcopy_send_work); - schedule_delayed_work(&fcopy_timeout_work, - HV_UTIL_TIMEOUT * HZ); - return; - } else { - pr_err_ratelimited("Fcopy request received. Invalid msg type: %d\n", - icmsghdr->icmsgtype); - return; - } - icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE; - vmbus_sendpacket(channel, recv_buffer, recvlen, requestid, - VM_PKT_DATA_INBAND, 0); -} - -/* Callback when data is received from userspace */ -static int fcopy_on_msg(void *msg, int len) -{ - int *val = (int *)msg; - - if (len != sizeof(int)) - return -EINVAL; - - if (fcopy_transaction.state == HVUTIL_DEVICE_INIT) - return fcopy_handle_handshake(*val); - - if (fcopy_transaction.state != HVUTIL_USERSPACE_REQ) - return -EINVAL; - - /* - * Complete the transaction by forwarding the result - * to the host. But first, cancel the timeout. - */ - if (cancel_delayed_work_sync(&fcopy_timeout_work)) { - fcopy_transaction.state = HVUTIL_USERSPACE_RECV; - fcopy_respond_to_host(*val); - hv_poll_channel(fcopy_transaction.recv_channel, - fcopy_poll_wrapper); - } - - return 0; -} - -static void fcopy_on_reset(void) -{ - /* - * The daemon has exited; reset the state. - */ - fcopy_transaction.state = HVUTIL_DEVICE_INIT; - - if (cancel_delayed_work_sync(&fcopy_timeout_work)) - fcopy_respond_to_host(HV_E_FAIL); -} - -int hv_fcopy_init(struct hv_util_service *srv) -{ - recv_buffer = srv->recv_buffer; - fcopy_transaction.recv_channel = srv->channel; - fcopy_transaction.recv_channel->max_pkt_size = HV_HYP_PAGE_SIZE * 2; - - /* - * When this driver loads, the user level daemon that - * processes the host requests may not yet be running. - * Defer processing channel callbacks until the daemon - * has registered. - */ - fcopy_transaction.state = HVUTIL_DEVICE_INIT; - - hvt = hvutil_transport_init(fcopy_devname, 0, 0, - fcopy_on_msg, fcopy_on_reset); - if (!hvt) - return -EFAULT; - - return 0; -} - -static void hv_fcopy_cancel_work(void) -{ - cancel_delayed_work_sync(&fcopy_timeout_work); - cancel_work_sync(&fcopy_send_work); -} - -int hv_fcopy_pre_suspend(void) -{ - struct vmbus_channel *channel = fcopy_transaction.recv_channel; - struct hv_fcopy_hdr *fcopy_msg; - - /* - * Fake a CANCEL_FCOPY message for the user space daemon in case the - * daemon is in the middle of copying some file. It doesn't matter if - * there is already a message pending to be delivered to the user - * space since we force fcopy_transaction.state to be HVUTIL_READY, so - * the user space daemon's write() will fail with EINVAL (see - * fcopy_on_msg()), and the daemon will reset the device by closing - * and re-opening it. - */ - fcopy_msg = kzalloc(sizeof(*fcopy_msg), GFP_KERNEL); - if (!fcopy_msg) - return -ENOMEM; - - tasklet_disable(&channel->callback_event); - - fcopy_msg->operation = CANCEL_FCOPY; - - hv_fcopy_cancel_work(); - - /* We don't care about the return value. */ - hvutil_transport_send(hvt, fcopy_msg, sizeof(*fcopy_msg), NULL); - - kfree(fcopy_msg); - - fcopy_transaction.state = HVUTIL_READY; - - /* tasklet_enable() will be called in hv_fcopy_pre_resume(). */ - return 0; -} - -int hv_fcopy_pre_resume(void) -{ - struct vmbus_channel *channel = fcopy_transaction.recv_channel; - - tasklet_enable(&channel->callback_event); - - return 0; -} - -void hv_fcopy_deinit(void) -{ - fcopy_transaction.state = HVUTIL_DEVICE_DYING; - - hv_fcopy_cancel_work(); - - hvutil_transport_destroy(hvt); -} diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c index 9c97c4065f..c4f5253257 100644 --- a/drivers/hv/hv_util.c +++ b/drivers/hv/hv_util.c @@ -154,14 +154,6 @@ static struct hv_util_service util_vss = { .util_deinit = hv_vss_deinit, }; -static struct hv_util_service util_fcopy = { - .util_cb = hv_fcopy_onchannelcallback, - .util_init = hv_fcopy_init, - .util_pre_suspend = hv_fcopy_pre_suspend, - .util_pre_resume = hv_fcopy_pre_resume, - .util_deinit = hv_fcopy_deinit, -}; - static void perform_shutdown(struct work_struct *dummy) { orderly_poweroff(true); @@ -700,10 +692,6 @@ static const struct hv_vmbus_device_id id_table[] = { { HV_VSS_GUID, .driver_data = (unsigned long)&util_vss }, - /* File copy GUID */ - { HV_FCOPY_GUID, - .driver_data = (unsigned long)&util_fcopy - }, { }, }; diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h index f6b1e710f8..76ac5185a0 100644 --- a/drivers/hv/hyperv_vmbus.h +++ b/drivers/hv/hyperv_vmbus.h @@ -417,6 +417,11 @@ static inline bool hv_is_perf_channel(struct vmbus_channel *channel) return vmbus_devs[channel->device_id].perf_device; } +static inline size_t hv_dev_ring_size(struct vmbus_channel *channel) +{ + return vmbus_devs[channel->device_id].pref_ring_size; +} + static inline bool hv_is_allocated_cpu(unsigned int cpu) { struct vmbus_channel *channel, *sc; |