diff options
Diffstat (limited to 'drivers/hv')
| -rw-r--r-- | drivers/hv/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/hv/Makefile | 2 | ||||
| -rw-r--r-- | drivers/hv/channel.c | 29 | ||||
| -rw-r--r-- | drivers/hv/channel_mgmt.c | 15 | ||||
| -rw-r--r-- | drivers/hv/connection.c | 29 | ||||
| -rw-r--r-- | drivers/hv/hv.c | 36 | ||||
| -rw-r--r-- | drivers/hv/hv_common.c | 105 | ||||
| -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 | ||||
| -rw-r--r-- | drivers/hv/vmbus_drv.c | 99 |
11 files changed, 214 insertions, 546 deletions
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index 00242107d62e..862c47b191af 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -16,6 +16,7 @@ config HYPERV config HYPERV_VTL_MODE bool "Enable Linux to boot in VTL context" depends on X86_64 && HYPERV + depends on SMP default n help Virtual Secure Mode (VSM) is a set of hypervisor capabilities and diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile index d76df5c8c2a9..b992c0ed182b 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.c b/drivers/hv/channel.c index adbf674355b2..fb8cd8469328 100644 --- a/drivers/hv/channel.c +++ b/drivers/hv/channel.c @@ -153,7 +153,9 @@ void vmbus_free_ring(struct vmbus_channel *channel) hv_ringbuffer_cleanup(&channel->inbound); if (channel->ringbuffer_page) { - __free_pages(channel->ringbuffer_page, + /* In a CoCo VM leak the memory if it didn't get re-encrypted */ + if (!channel->ringbuffer_gpadlhandle.decrypted) + __free_pages(channel->ringbuffer_page, get_order(channel->ringbuffer_pagecount << PAGE_SHIFT)); channel->ringbuffer_page = NULL; @@ -436,9 +438,18 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel, (atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1); ret = create_gpadl_header(type, kbuffer, size, send_offset, &msginfo); - if (ret) + if (ret) { + gpadl->decrypted = false; return ret; + } + /* + * Set the "decrypted" flag to true for the set_memory_decrypted() + * success case. In the failure case, the encryption state of the + * memory is unknown. Leave "decrypted" as true to ensure the + * memory will be leaked instead of going back on the free list. + */ + gpadl->decrypted = true; ret = set_memory_decrypted((unsigned long)kbuffer, PFN_UP(size)); if (ret) { @@ -527,9 +538,15 @@ cleanup: kfree(msginfo); - if (ret) - set_memory_encrypted((unsigned long)kbuffer, - PFN_UP(size)); + if (ret) { + /* + * If set_memory_encrypted() fails, the decrypted flag is + * left as true so the memory is leaked instead of being + * put back on the free list. + */ + if (!set_memory_encrypted((unsigned long)kbuffer, PFN_UP(size))) + gpadl->decrypted = false; + } return ret; } @@ -850,6 +867,8 @@ post_msg_err: if (ret) pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret); + gpadl->decrypted = ret; + return ret; } EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl); diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 2f4d09ce027a..3c6011a48dab 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/connection.c b/drivers/hv/connection.c index 3cabeeabb1ca..f001ae880e1d 100644 --- a/drivers/hv/connection.c +++ b/drivers/hv/connection.c @@ -237,8 +237,17 @@ int vmbus_connect(void) vmbus_connection.monitor_pages[0], 1); ret |= set_memory_decrypted((unsigned long) vmbus_connection.monitor_pages[1], 1); - if (ret) + if (ret) { + /* + * If set_memory_decrypted() fails, the encryption state + * of the memory is unknown. So leak the memory instead + * of risking returning decrypted memory to the free list. + * For simplicity, always handle both pages the same. + */ + vmbus_connection.monitor_pages[0] = NULL; + vmbus_connection.monitor_pages[1] = NULL; goto cleanup; + } /* * Set_memory_decrypted() will change the memory contents if @@ -337,13 +346,19 @@ void vmbus_disconnect(void) vmbus_connection.int_page = NULL; } - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[0], 1); - set_memory_encrypted((unsigned long)vmbus_connection.monitor_pages[1], 1); + if (vmbus_connection.monitor_pages[0]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[0], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); + vmbus_connection.monitor_pages[0] = NULL; + } - hv_free_hyperv_page(vmbus_connection.monitor_pages[0]); - hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); - vmbus_connection.monitor_pages[0] = NULL; - vmbus_connection.monitor_pages[1] = NULL; + if (vmbus_connection.monitor_pages[1]) { + if (!set_memory_encrypted( + (unsigned long)vmbus_connection.monitor_pages[1], 1)) + hv_free_hyperv_page(vmbus_connection.monitor_pages[1]); + vmbus_connection.monitor_pages[1] = NULL; + } } /* diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c index 51e5018ac9b2..a8ad728354cb 100644 --- a/drivers/hv/hv.c +++ b/drivers/hv/hv.c @@ -270,7 +270,7 @@ void hv_synic_enable_regs(unsigned int cpu) union hv_synic_scontrol sctrl; /* Setup the Synic's message page */ - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP); + simp.as_uint64 = hv_get_msr(HV_MSR_SIMP); simp.simp_enabled = 1; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -286,10 +286,10 @@ void hv_synic_enable_regs(unsigned int cpu) >> HV_HYP_PAGE_SHIFT; } - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64); + hv_set_msr(HV_MSR_SIMP, simp.as_uint64); /* Setup the Synic's event page */ - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP); + siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP); siefp.siefp_enabled = 1; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -305,13 +305,12 @@ void hv_synic_enable_regs(unsigned int cpu) >> HV_HYP_PAGE_SHIFT; } - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64); + hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64); /* Setup the shared SINT. */ if (vmbus_irq != -1) enable_percpu_irq(vmbus_irq, 0); - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 + - VMBUS_MESSAGE_SINT); + shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT); shared_sint.vector = vmbus_interrupt; shared_sint.masked = false; @@ -326,14 +325,13 @@ void hv_synic_enable_regs(unsigned int cpu) #else shared_sint.auto_eoi = 0; #endif - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT, - shared_sint.as_uint64); + hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64); /* Enable the global synic bit */ - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL); + sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL); sctrl.enable = 1; - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64); + hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64); } int hv_synic_init(unsigned int cpu) @@ -357,17 +355,15 @@ void hv_synic_disable_regs(unsigned int cpu) union hv_synic_siefp siefp; union hv_synic_scontrol sctrl; - shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 + - VMBUS_MESSAGE_SINT); + shared_sint.as_uint64 = hv_get_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT); shared_sint.masked = 1; /* Need to correctly cleanup in the case of SMP!!! */ /* Disable the interrupt */ - hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT, - shared_sint.as_uint64); + hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64); - simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP); + simp.as_uint64 = hv_get_msr(HV_MSR_SIMP); /* * In Isolation VM, sim and sief pages are allocated by * paravisor. These pages also will be used by kdump @@ -382,9 +378,9 @@ void hv_synic_disable_regs(unsigned int cpu) simp.base_simp_gpa = 0; } - hv_set_register(HV_REGISTER_SIMP, simp.as_uint64); + hv_set_msr(HV_MSR_SIMP, simp.as_uint64); - siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP); + siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP); siefp.siefp_enabled = 0; if (ms_hyperv.paravisor_present || hv_root_partition) { @@ -394,12 +390,12 @@ void hv_synic_disable_regs(unsigned int cpu) siefp.base_siefp_gpa = 0; } - hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64); + hv_set_msr(HV_MSR_SIEFP, siefp.as_uint64); /* Disable the global synic bit */ - sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL); + sctrl.as_uint64 = hv_get_msr(HV_MSR_SCONTROL); sctrl.enable = 0; - hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64); + hv_set_msr(HV_MSR_SCONTROL, sctrl.as_uint64); if (vmbus_irq != -1) disable_percpu_irq(vmbus_irq); diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c index 0285a74363b3..9c452bfbd571 100644 --- a/drivers/hv/hv_common.c +++ b/drivers/hv/hv_common.c @@ -20,8 +20,11 @@ #include <linux/sched/task_stack.h> #include <linux/panic_notifier.h> #include <linux/ptrace.h> +#include <linux/random.h> +#include <linux/efi.h> #include <linux/kdebug.h> #include <linux/kmsg_dump.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/dma-map-ops.h> #include <linux/set_memory.h> @@ -227,19 +230,19 @@ static void hv_kmsg_dump(struct kmsg_dumper *dumper, * contain the size of the panic data in that page. Rest of the * registers are no-op when the NOTIFY_MSG flag is set. */ - hv_set_register(HV_REGISTER_CRASH_P0, 0); - hv_set_register(HV_REGISTER_CRASH_P1, 0); - hv_set_register(HV_REGISTER_CRASH_P2, 0); - hv_set_register(HV_REGISTER_CRASH_P3, virt_to_phys(hv_panic_page)); - hv_set_register(HV_REGISTER_CRASH_P4, bytes_written); + hv_set_msr(HV_MSR_CRASH_P0, 0); + hv_set_msr(HV_MSR_CRASH_P1, 0); + hv_set_msr(HV_MSR_CRASH_P2, 0); + hv_set_msr(HV_MSR_CRASH_P3, virt_to_phys(hv_panic_page)); + hv_set_msr(HV_MSR_CRASH_P4, bytes_written); /* * Let Hyper-V know there is crash data available along with * the panic message. */ - hv_set_register(HV_REGISTER_CRASH_CTL, - (HV_CRASH_CTL_CRASH_NOTIFY | - HV_CRASH_CTL_CRASH_NOTIFY_MSG)); + hv_set_msr(HV_MSR_CRASH_CTL, + (HV_CRASH_CTL_CRASH_NOTIFY | + HV_CRASH_CTL_CRASH_NOTIFY_MSG)); } static struct kmsg_dumper hv_kmsg_dumper = { @@ -278,6 +281,14 @@ static void hv_kmsg_dump_register(void) int __init hv_common_init(void) { int i; + union hv_hypervisor_version_info version; + + /* Get information about the Hyper-V host version */ + if (!hv_get_hypervisor_version(&version)) + pr_info("Hyper-V: Host Build %d.%d.%d.%d-%d-%d\n", + version.major_version, version.minor_version, + version.build_number, version.service_number, + version.service_pack, version.service_branch); if (hv_is_isolation_supported()) sysctl_record_panic_msg = 0; @@ -310,7 +321,7 @@ int __init hv_common_init(void) * Register for panic kmsg callback only if the right * capability is supported by the hypervisor. */ - hyperv_crash_ctl = hv_get_register(HV_REGISTER_CRASH_CTL); + hyperv_crash_ctl = hv_get_msr(HV_MSR_CRASH_CTL); if (hyperv_crash_ctl & HV_CRASH_CTL_CRASH_NOTIFY_MSG) hv_kmsg_dump_register(); @@ -347,6 +358,72 @@ int __init hv_common_init(void) return 0; } +void __init ms_hyperv_late_init(void) +{ + struct acpi_table_header *header; + acpi_status status; + u8 *randomdata; + u32 length, i; + + /* + * Seed the Linux random number generator with entropy provided by + * the Hyper-V host in ACPI table OEM0. + */ + if (!IS_ENABLED(CONFIG_ACPI)) + return; + + status = acpi_get_table("OEM0", 0, &header); + if (ACPI_FAILURE(status) || !header) + return; + + /* + * Since the "OEM0" table name is for OEM specific usage, verify + * that what we're seeing purports to be from Microsoft. + */ + if (strncmp(header->oem_table_id, "MICROSFT", 8)) + goto error; + + /* + * Ensure the length is reasonable. Requiring at least 8 bytes and + * no more than 4K bytes is somewhat arbitrary and just protects + * against a malformed table. Hyper-V currently provides 64 bytes, + * but allow for a change in a later version. + */ + if (header->length < sizeof(*header) + 8 || + header->length > sizeof(*header) + SZ_4K) + goto error; + + length = header->length - sizeof(*header); + randomdata = (u8 *)(header + 1); + + pr_debug("Hyper-V: Seeding rng with %d random bytes from ACPI table OEM0\n", + length); + + add_bootloader_randomness(randomdata, length); + + /* + * To prevent the seed data from being visible in /sys/firmware/acpi, + * zero out the random data in the ACPI table and fixup the checksum. + * The zero'ing is done out of an abundance of caution in avoiding + * potential security risks to the rng. Similarly, reset the table + * length to just the header size so that a subsequent kexec doesn't + * try to use the zero'ed out random data. + */ + for (i = 0; i < length; i++) { + header->checksum += randomdata[i]; + randomdata[i] = 0; + } + + for (i = 0; i < sizeof(header->length); i++) + header->checksum += ((u8 *)&header->length)[i]; + header->length = sizeof(*header); + for (i = 0; i < sizeof(header->length); i++) + header->checksum -= ((u8 *)&header->length)[i]; + +error: + acpi_put_table(header); +} + /* * Hyper-V specific initialization and die code for * individual CPUs that is common across all architectures. @@ -409,7 +486,7 @@ int hv_common_cpu_init(unsigned int cpu) *inputarg = mem; } - msr_vp_index = hv_get_register(HV_REGISTER_VP_INDEX); + msr_vp_index = hv_get_msr(HV_MSR_VP_INDEX); hv_vp_index[cpu] = msr_vp_index; @@ -484,11 +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); @@ -506,7 +579,7 @@ EXPORT_SYMBOL_GPL(hv_is_hibernation_supported); */ static u64 __hv_read_ref_counter(void) { - return hv_get_register(HV_REGISTER_TIME_REF_COUNT); + return hv_get_msr(HV_MSR_TIME_REF_COUNT); } u64 (*hv_read_reference_counter)(void) = __hv_read_ref_counter; diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c deleted file mode 100644 index 922d83eb7ddf..000000000000 --- 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 9c97c4065fe7..c4f525325790 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 f6b1e710f805..76ac5185a01a 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; diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c index 7f7965f3d187..12a707ab73f8 100644 --- a/drivers/hv/vmbus_drv.c +++ b/drivers/hv/vmbus_drv.c @@ -131,7 +131,7 @@ static ssize_t id_show(struct device *dev, struct device_attribute *dev_attr, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->offermsg.child_relid); + return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.child_relid); } static DEVICE_ATTR_RO(id); @@ -142,7 +142,7 @@ static ssize_t state_show(struct device *dev, struct device_attribute *dev_attr, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->state); + return sysfs_emit(buf, "%d\n", hv_dev->channel->state); } static DEVICE_ATTR_RO(state); @@ -153,7 +153,7 @@ static ssize_t monitor_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", hv_dev->channel->offermsg.monitorid); + return sysfs_emit(buf, "%d\n", hv_dev->channel->offermsg.monitorid); } static DEVICE_ATTR_RO(monitor_id); @@ -164,8 +164,8 @@ static ssize_t class_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "{%pUl}\n", - &hv_dev->channel->offermsg.offer.if_type); + return sysfs_emit(buf, "{%pUl}\n", + &hv_dev->channel->offermsg.offer.if_type); } static DEVICE_ATTR_RO(class_id); @@ -176,8 +176,8 @@ static ssize_t device_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "{%pUl}\n", - &hv_dev->channel->offermsg.offer.if_instance); + return sysfs_emit(buf, "{%pUl}\n", + &hv_dev->channel->offermsg.offer.if_instance); } static DEVICE_ATTR_RO(device_id); @@ -186,7 +186,7 @@ static ssize_t modalias_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type); + return sysfs_emit(buf, "vmbus:%*phN\n", UUID_SIZE, &hv_dev->dev_type); } static DEVICE_ATTR_RO(modalias); @@ -199,7 +199,7 @@ static ssize_t numa_node_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu)); + return sysfs_emit(buf, "%d\n", cpu_to_node(hv_dev->channel->target_cpu)); } static DEVICE_ATTR_RO(numa_node); #endif @@ -212,9 +212,8 @@ static ssize_t server_monitor_pending_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_pending(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_pending); @@ -226,9 +225,8 @@ static ssize_t client_monitor_pending_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_pending(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_pending(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_pending); @@ -240,9 +238,8 @@ static ssize_t server_monitor_latency_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_latency(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_latency); @@ -254,9 +251,8 @@ static ssize_t client_monitor_latency_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_latency(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_latency(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_latency); @@ -268,9 +264,8 @@ static ssize_t server_monitor_conn_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_conn_id(hv_dev->channel, - vmbus_connection.monitor_pages[0])); + return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel, + vmbus_connection.monitor_pages[0])); } static DEVICE_ATTR_RO(server_monitor_conn_id); @@ -282,9 +277,8 @@ static ssize_t client_monitor_conn_id_show(struct device *dev, if (!hv_dev->channel) return -ENODEV; - return sprintf(buf, "%d\n", - channel_conn_id(hv_dev->channel, - vmbus_connection.monitor_pages[1])); + return sysfs_emit(buf, "%d\n", channel_conn_id(hv_dev->channel, + vmbus_connection.monitor_pages[1])); } static DEVICE_ATTR_RO(client_monitor_conn_id); @@ -303,7 +297,7 @@ static ssize_t out_intr_mask_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_interrupt_mask); + return sysfs_emit(buf, "%d\n", outbound.current_interrupt_mask); } static DEVICE_ATTR_RO(out_intr_mask); @@ -321,7 +315,7 @@ static ssize_t out_read_index_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_read_index); + return sysfs_emit(buf, "%d\n", outbound.current_read_index); } static DEVICE_ATTR_RO(out_read_index); @@ -340,7 +334,7 @@ static ssize_t out_write_index_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.current_write_index); + return sysfs_emit(buf, "%d\n", outbound.current_write_index); } static DEVICE_ATTR_RO(out_write_index); @@ -359,7 +353,7 @@ static ssize_t out_read_bytes_avail_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.bytes_avail_toread); + return sysfs_emit(buf, "%d\n", outbound.bytes_avail_toread); } static DEVICE_ATTR_RO(out_read_bytes_avail); @@ -378,7 +372,7 @@ static ssize_t out_write_bytes_avail_show(struct device *dev, &outbound); if (ret < 0) return ret; - return sprintf(buf, "%d\n", outbound.bytes_avail_towrite); + return sysfs_emit(buf, "%d\n", outbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(out_write_bytes_avail); @@ -396,7 +390,7 @@ static ssize_t in_intr_mask_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_interrupt_mask); + return sysfs_emit(buf, "%d\n", inbound.current_interrupt_mask); } static DEVICE_ATTR_RO(in_intr_mask); @@ -414,7 +408,7 @@ static ssize_t in_read_index_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_read_index); + return sysfs_emit(buf, "%d\n", inbound.current_read_index); } static DEVICE_ATTR_RO(in_read_index); @@ -432,7 +426,7 @@ static ssize_t in_write_index_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.current_write_index); + return sysfs_emit(buf, "%d\n", inbound.current_write_index); } static DEVICE_ATTR_RO(in_write_index); @@ -451,7 +445,7 @@ static ssize_t in_read_bytes_avail_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.bytes_avail_toread); + return sysfs_emit(buf, "%d\n", inbound.bytes_avail_toread); } static DEVICE_ATTR_RO(in_read_bytes_avail); @@ -470,7 +464,7 @@ static ssize_t in_write_bytes_avail_show(struct device *dev, if (ret < 0) return ret; - return sprintf(buf, "%d\n", inbound.bytes_avail_towrite); + return sysfs_emit(buf, "%d\n", inbound.bytes_avail_towrite); } static DEVICE_ATTR_RO(in_write_bytes_avail); @@ -480,7 +474,7 @@ static ssize_t channel_vp_mapping_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); struct vmbus_channel *channel = hv_dev->channel, *cur_sc; - int buf_size = PAGE_SIZE, n_written, tot_written; + int n_written; struct list_head *cur; if (!channel) @@ -488,25 +482,21 @@ static ssize_t channel_vp_mapping_show(struct device *dev, mutex_lock(&vmbus_connection.channel_mutex); - tot_written = snprintf(buf, buf_size, "%u:%u\n", - channel->offermsg.child_relid, channel->target_cpu); + n_written = sysfs_emit(buf, "%u:%u\n", + channel->offermsg.child_relid, + channel->target_cpu); list_for_each(cur, &channel->sc_list) { - if (tot_written >= buf_size - 1) - break; cur_sc = list_entry(cur, struct vmbus_channel, sc_list); - n_written = scnprintf(buf + tot_written, - buf_size - tot_written, - "%u:%u\n", - cur_sc->offermsg.child_relid, - cur_sc->target_cpu); - tot_written += n_written; + n_written += sysfs_emit_at(buf, n_written, "%u:%u\n", + cur_sc->offermsg.child_relid, + cur_sc->target_cpu); } mutex_unlock(&vmbus_connection.channel_mutex); - return tot_written; + return n_written; } static DEVICE_ATTR_RO(channel_vp_mapping); @@ -516,7 +506,7 @@ static ssize_t vendor_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "0x%x\n", hv_dev->vendor_id); + return sysfs_emit(buf, "0x%x\n", hv_dev->vendor_id); } static DEVICE_ATTR_RO(vendor); @@ -526,7 +516,7 @@ static ssize_t device_show(struct device *dev, { struct hv_device *hv_dev = device_to_hv_device(dev); - return sprintf(buf, "0x%x\n", hv_dev->device_id); + return sysfs_emit(buf, "0x%x\n", hv_dev->device_id); } static DEVICE_ATTR_RO(device); @@ -551,7 +541,7 @@ static ssize_t driver_override_show(struct device *dev, ssize_t len; device_lock(dev); - len = snprintf(buf, PAGE_SIZE, "%s\n", hv_dev->driver_override); + len = sysfs_emit(buf, "%s\n", hv_dev->driver_override); device_unlock(dev); return len; @@ -2359,10 +2349,9 @@ static int vmbus_platform_driver_probe(struct platform_device *pdev) return vmbus_acpi_add(pdev); } -static int vmbus_platform_driver_remove(struct platform_device *pdev) +static void vmbus_platform_driver_remove(struct platform_device *pdev) { vmbus_mmio_remove(); - return 0; } #ifdef CONFIG_PM_SLEEP @@ -2542,7 +2531,7 @@ static const struct dev_pm_ops vmbus_bus_pm = { static struct platform_driver vmbus_platform_driver = { .probe = vmbus_platform_driver_probe, - .remove = vmbus_platform_driver_remove, + .remove_new = vmbus_platform_driver_remove, .driver = { .name = "vmbus", .acpi_match_table = ACPI_PTR(vmbus_acpi_device_ids), |