diff --git a/.gitignore b/.gitignore index 6437e14db07b..1ccfbfbe70ff 100644 --- a/.gitignore +++ b/.gitignore @@ -136,7 +136,6 @@ GTAGS # id-utils files ID -*.orig *~ \#*# diff --git a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 index f6c035752639..bc9bb4d83427 100644 --- a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 +++ b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 @@ -3,7 +3,7 @@ KernelVersion: Contact: linux-iio@vger.kernel.org Description: Reading this returns the valid values that can be written to the - on_altvoltage0_mode attribute: + filter_mode attribute: - auto -> Adjust bandpass filter to track changes in input clock rate. - manual -> disable/unregister the clock rate notifier / input clock tracking. diff --git a/Documentation/accounting/delay-accounting.rst b/Documentation/accounting/delay-accounting.rst index 7103b62ba6d7..79f537c9f160 100644 --- a/Documentation/accounting/delay-accounting.rst +++ b/Documentation/accounting/delay-accounting.rst @@ -109,17 +109,17 @@ Get sum of delays, since system boot, for all pids with tgid 5:: CPU count real total virtual total delay total delay average 8 7000000 6872122 3382277 0.423ms IO count delay total delay average - 0 0 0ms + 0 0 0.000ms SWAP count delay total delay average - 0 0 0ms + 0 0 0.000ms RECLAIM count delay total delay average - 0 0 0ms + 0 0 0.000ms THRASHING count delay total delay average - 0 0 0ms + 0 0 0.000ms COMPACT count delay total delay average - 0 0 0ms - WPCOPY count delay total delay average - 0 0 0ms + 0 0 0.000ms + WPCOPY count delay total delay average + 0 0 0.000ms Get IO accounting for pid 1, it works only with -p:: diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst index 3766bf8a1c20..1cd09795f143 100644 --- a/Documentation/admin-guide/cifs/usage.rst +++ b/Documentation/admin-guide/cifs/usage.rst @@ -722,40 +722,26 @@ Configuration pseudo-files: ======================= ======================================================= SecurityFlags Flags which control security negotiation and also packet signing. Authentication (may/must) - flags (e.g. for NTLM and/or NTLMv2) may be combined with + flags (e.g. for NTLMv2) may be combined with the signing flags. Specifying two different password hashing mechanisms (as "must use") on the other hand does not make much sense. Default flags are:: - 0x07007 + 0x00C5 - (NTLM, NTLMv2 and packet signing allowed). The maximum - allowable flags if you want to allow mounts to servers - using weaker password hashes is 0x37037 (lanman, - plaintext, ntlm, ntlmv2, signing allowed). Some - SecurityFlags require the corresponding menuconfig - options to be enabled. Enabling plaintext - authentication currently requires also enabling - lanman authentication in the security flags - because the cifs module only supports sending - laintext passwords using the older lanman dialect - form of the session setup SMB. (e.g. for authentication - using plain text passwords, set the SecurityFlags - to 0x30030):: + (NTLMv2 and packet signing allowed). Some SecurityFlags + may require enabling a corresponding menuconfig option. may use packet signing 0x00001 must use packet signing 0x01001 - may use NTLM (most common password hash) 0x00002 - must use NTLM 0x02002 may use NTLMv2 0x00004 must use NTLMv2 0x04004 - may use Kerberos security 0x00008 - must use Kerberos 0x08008 - may use lanman (weak) password hash 0x00010 - must use lanman password hash 0x10010 - may use plaintext passwords 0x00020 - must use plaintext passwords 0x20020 - (reserved for future packet encryption) 0x00040 + may use Kerberos security (krb5) 0x00008 + must use Kerberos 0x08008 + may use NTLMSSP 0x00080 + must use NTLMSSP 0x80080 + seal (packet encryption) 0x00040 + must seal 0x40040 cifsFYI If set to non-zero value, additional debug information will be logged to the system error log. This field diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index e6f0570cf490..18c8fc60db93 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -637,12 +637,6 @@ loops can be debugged more effectively on production systems. - clocksource.max_cswd_read_retries= [KNL] - Number of clocksource_watchdog() retries due to - external delays before the clock will be marked - unstable. Defaults to two retries, that is, - three attempts to read the clock under test. - clocksource.verify_n_cpus= [KNL] Limit the number of CPUs checked for clocksources marked with CLOCK_SOURCE_VERIFY_PERCPU that @@ -4546,6 +4540,16 @@ printk.time= Show timing data prefixed to each printk message line Format: (1/Y/y=enable, 0/N/n=disable) + proc_mem.force_override= [KNL] + Format: {always | ptrace | never} + Traditionally /proc/pid/mem allows memory permissions to be + overridden without restrictions. This option may be set to + restrict that. Can be one of: + - 'always': traditional behavior always allows mem overrides. + - 'ptrace': only allow mem overrides for active ptracers. + - 'never': never allow mem overrides. + If not specified, default is the CONFIG_PROC_MEM_* choice. + processor.max_cstate= [HW,ACPI] Limit processor to maximum C-state max_cstate=9 overrides any DMI blacklist limit. @@ -4556,11 +4560,9 @@ profile= [KNL] Enable kernel profiling via /proc/profile Format: [,] - Param: : "schedule", "sleep", or "kvm" + Param: : "schedule" or "kvm" [defaults to kernel profiling] Param: "schedule" - profile schedule points. - Param: "sleep" - profile D-state sleeping (millisecs). - Requires CONFIG_SCHEDSTATS Param: "kvm" - profile VM exits. Param: - step/bucket size as a power of 2 for statistical time based profiling. diff --git a/Documentation/arm64/silicon-errata.rst b/Documentation/arm64/silicon-errata.rst index 27135b9c07ac..e7b50babd0d5 100644 --- a/Documentation/arm64/silicon-errata.rst +++ b/Documentation/arm64/silicon-errata.rst @@ -109,8 +109,16 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A76 | #1463225 | ARM64_ERRATUM_1463225 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A76 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A77 | #3324348 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A78C | #3324346,3324347| ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2051678 | ARM64_ERRATUM_2051678 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A510 | #2077057 | ARM64_ERRATUM_2077057 | @@ -125,22 +133,54 @@ stable kernels. +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A715 | #3456084 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1 | #3324344 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X1C | #3324346 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Cortex-X925 | #3324334 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1349291 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N1 | #3324349 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2139208 | ARM64_ERRATUM_2139208 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2067961 | ARM64_ERRATUM_2067961 | +----------------+-----------------+-----------------+-----------------------------+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 | +----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-N3 | #3456111 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ +| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 | ++----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-500 | #841119,826419 | N/A | +----------------+-----------------+-----------------+-----------------------------+ | ARM | MMU-600 | #1076982,1209401| N/A | diff --git a/Documentation/bpf/map_lpm_trie.rst b/Documentation/bpf/map_lpm_trie.rst new file mode 100644 index 000000000000..b4fce3f7c98f --- /dev/null +++ b/Documentation/bpf/map_lpm_trie.rst @@ -0,0 +1,181 @@ +.. SPDX-License-Identifier: GPL-2.0-only +.. Copyright (C) 2022 Red Hat, Inc. + +===================== +BPF_MAP_TYPE_LPM_TRIE +===================== + +.. note:: + - ``BPF_MAP_TYPE_LPM_TRIE`` was introduced in kernel version 4.11 + +``BPF_MAP_TYPE_LPM_TRIE`` provides a longest prefix match algorithm that +can be used to match IP addresses to a stored set of prefixes. +Internally, data is stored in an unbalanced trie of nodes that uses +``prefixlen,data`` pairs as its keys. The ``data`` is interpreted in +network byte order, i.e. big endian, so ``data[0]`` stores the most +significant byte. + +LPM tries may be created with a maximum prefix length that is a multiple +of 8, in the range from 8 to 2048. The key used for lookup and update +operations is a ``struct bpf_lpm_trie_key_u8``, extended by +``max_prefixlen/8`` bytes. + +- For IPv4 addresses the data length is 4 bytes +- For IPv6 addresses the data length is 16 bytes + +The value type stored in the LPM trie can be any user defined type. + +.. note:: + When creating a map of type ``BPF_MAP_TYPE_LPM_TRIE`` you must set the + ``BPF_F_NO_PREALLOC`` flag. + +Usage +===== + +Kernel BPF +---------- + +.. c:function:: + void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + +The longest prefix entry for a given data value can be found using the +``bpf_map_lookup_elem()`` helper. This helper returns a pointer to the +value associated with the longest matching ``key``, or ``NULL`` if no +entry was found. + +The ``key`` should have ``prefixlen`` set to ``max_prefixlen`` when +performing longest prefix lookups. For example, when searching for the +longest prefix match for an IPv4 address, ``prefixlen`` should be set to +``32``. + +.. c:function:: + long bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + +Prefix entries can be added or updated using the ``bpf_map_update_elem()`` +helper. This helper replaces existing elements atomically. + +``bpf_map_update_elem()`` returns ``0`` on success, or negative error in +case of failure. + + .. note:: + The flags parameter must be one of BPF_ANY, BPF_NOEXIST or BPF_EXIST, + but the value is ignored, giving BPF_ANY semantics. + +.. c:function:: + long bpf_map_delete_elem(struct bpf_map *map, const void *key) + +Prefix entries can be deleted using the ``bpf_map_delete_elem()`` +helper. This helper will return 0 on success, or negative error in case +of failure. + +Userspace +--------- + +Access from userspace uses libbpf APIs with the same names as above, with +the map identified by ``fd``. + +.. c:function:: + int bpf_map_get_next_key (int fd, const void *cur_key, void *next_key) + +A userspace program can iterate through the entries in an LPM trie using +libbpf's ``bpf_map_get_next_key()`` function. The first key can be +fetched by calling ``bpf_map_get_next_key()`` with ``cur_key`` set to +``NULL``. Subsequent calls will fetch the next key that follows the +current key. ``bpf_map_get_next_key()`` returns ``0`` on success, +``-ENOENT`` if ``cur_key`` is the last key in the trie, or negative +error in case of failure. + +``bpf_map_get_next_key()`` will iterate through the LPM trie elements +from leftmost leaf first. This means that iteration will return more +specific keys before less specific ones. + +Examples +======== + +Please see ``tools/testing/selftests/bpf/test_lpm_map.c`` for examples +of LPM trie usage from userspace. The code snippets below demonstrate +API usage. + +Kernel BPF +---------- + +The following BPF code snippet shows how to declare a new LPM trie for IPv4 +address prefixes: + +.. code-block:: c + + #include + #include + + struct ipv4_lpm_key { + __u32 prefixlen; + __u32 data; + }; + + struct { + __uint(type, BPF_MAP_TYPE_LPM_TRIE); + __type(key, struct ipv4_lpm_key); + __type(value, __u32); + __uint(map_flags, BPF_F_NO_PREALLOC); + __uint(max_entries, 255); + } ipv4_lpm_map SEC(".maps"); + +The following BPF code snippet shows how to lookup by IPv4 address: + +.. code-block:: c + + void *lookup(__u32 ipaddr) + { + struct ipv4_lpm_key key = { + .prefixlen = 32, + .data = ipaddr + }; + + return bpf_map_lookup_elem(&ipv4_lpm_map, &key); + } + +Userspace +--------- + +The following snippet shows how to insert an IPv4 prefix entry into an +LPM trie: + +.. code-block:: c + + int add_prefix_entry(int lpm_fd, __u32 addr, __u32 prefixlen, struct value *value) + { + struct ipv4_lpm_key ipv4_key = { + .prefixlen = prefixlen, + .data = addr + }; + return bpf_map_update_elem(lpm_fd, &ipv4_key, value, BPF_ANY); + } + +The following snippet shows a userspace program walking through the entries +of an LPM trie: + + +.. code-block:: c + + #include + #include + + void iterate_lpm_trie(int map_fd) + { + struct ipv4_lpm_key *cur_key = NULL; + struct ipv4_lpm_key next_key; + struct value value; + int err; + + for (;;) { + err = bpf_map_get_next_key(map_fd, cur_key, &next_key); + if (err) + break; + + bpf_map_lookup_elem(map_fd, &next_key, &value); + + /* Use key and value here */ + + cur_key = &next_key; + } + } diff --git a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml index 9790f75fc669..fe5145d3b73c 100644 --- a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml +++ b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml @@ -23,7 +23,6 @@ properties: - ak8963 - ak09911 - ak09912 - - ak09916 deprecated: true reg: diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml index f46c66bc6b2d..fe02773a490a 100644 --- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml +++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.yaml @@ -102,21 +102,21 @@ properties: default: 2 interrupts: - anyOf: - - minItems: 1 - items: - - description: TX interrupt - - description: RX interrupt - - items: - - description: common/combined interrupt + minItems: 1 + maxItems: 2 interrupt-names: oneOf: - - minItems: 1 + - description: TX interrupt + const: tx + - description: RX interrupt + const: rx + - description: TX and RX interrupts items: - const: tx - const: rx - - const: common + - description: Common/combined interrupt + const: common fck_parent: $ref: /schemas/types.yaml#/definitions/string diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml index 8d2c6d74b605..bc9ccdfd3a27 100644 --- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml +++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml @@ -49,7 +49,10 @@ properties: to take when the temperature crosses those thresholds. patternProperties: - "^[a-zA-Z][a-zA-Z0-9\\-]{1,12}-thermal$": + # Node name is limited in size due to Linux kernel requirements - 19 + # characters in total (see THERMAL_NAME_LENGTH, including terminating NUL + # byte): + "^[a-zA-Z][a-zA-Z0-9\\-]{1,10}-thermal$": type: object description: Each thermal zone node contains information about how frequently it diff --git a/Documentation/driver-api/ipmi.rst b/Documentation/driver-api/ipmi.rst index e224e47b6b09..dfa021eacd63 100644 --- a/Documentation/driver-api/ipmi.rst +++ b/Documentation/driver-api/ipmi.rst @@ -540,7 +540,7 @@ at module load time (for a module) with:: alerts_broken The addresses are normal I2C addresses. The adapter is the string -name of the adapter, as shown in /sys/class/i2c-adapter/i2c-/name. +name of the adapter, as shown in /sys/bus/i2c/devices/i2c-/name. It is *NOT* i2c- itself. Also, the comparison is done ignoring spaces, so if the name is "This is an I2C chip" you can say adapter_name=ThisisanI2cchip. This is because it's hard to pass in diff --git a/Documentation/filesystems/gfs2-glocks.rst b/Documentation/filesystems/gfs2-glocks.rst index d14f230f0b12..93a690b9bcf2 100644 --- a/Documentation/filesystems/gfs2-glocks.rst +++ b/Documentation/filesystems/gfs2-glocks.rst @@ -20,8 +20,7 @@ The gl_holders list contains all the queued lock requests (not just the holders) associated with the glock. If there are any held locks, then they will be contiguous entries at the head of the list. Locks are granted in strictly the order that they -are queued, except for those marked LM_FLAG_PRIORITY which are -used only during recovery, and even then only for journal locks. +are queued. There are three lock states that users of the glock layer can request, namely shared (SH), deferred (DF) and exclusive (EX). Those translate diff --git a/Documentation/locking/hwspinlock.rst b/Documentation/locking/hwspinlock.rst index 6f03713b7003..2ffaa3cbd63f 100644 --- a/Documentation/locking/hwspinlock.rst +++ b/Documentation/locking/hwspinlock.rst @@ -85,6 +85,17 @@ is already free). Should be called from a process context (might sleep). +:: + + int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id); + +After verifying the owner of the hwspinlock, release a previously acquired +hwspinlock; returns 0 on success, or an appropriate error code on failure +(e.g. -EOPNOTSUPP if the bust operation is not defined for the specific +hwspinlock). + +Should be called from a process context (might sleep). + :: int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout); diff --git a/Documentation/networking/driver.rst b/Documentation/networking/driver.rst index 64f7236ff10b..870f933e4a1a 100644 --- a/Documentation/networking/driver.rst +++ b/Documentation/networking/driver.rst @@ -4,15 +4,19 @@ Softnet Driver Issues ===================== -Transmit path guidelines: +Transmit path guidelines +======================== -1) The ndo_start_xmit method must not return NETDEV_TX_BUSY under - any normal circumstances. It is considered a hard error unless - there is no way your device can tell ahead of time when its - transmit function will become busy. +Stop queues in advance +---------------------- - Instead it must maintain the queue properly. For example, - for a driver implementing scatter-gather this means:: +The ndo_start_xmit method must not return NETDEV_TX_BUSY under +any normal circumstances. It is considered a hard error unless +there is no way your device can tell ahead of time when its +transmit function will become busy. + +Instead it must maintain the queue properly. For example, +for a driver implementing scatter-gather this means:: static netdev_tx_t drv_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) @@ -42,56 +46,79 @@ Transmit path guidelines: return NETDEV_TX_OK; } - And then at the end of your TX reclamation event handling:: +And then at the end of your TX reclamation event handling:: if (netif_queue_stopped(dp->dev) && TX_BUFFS_AVAIL(dp) > (MAX_SKB_FRAGS + 1)) netif_wake_queue(dp->dev); - For a non-scatter-gather supporting card, the three tests simply become:: +For a non-scatter-gather supporting card, the three tests simply become:: /* This is a hard error log it. */ if (TX_BUFFS_AVAIL(dp) <= 0) - and:: +and:: if (TX_BUFFS_AVAIL(dp) == 0) - and:: +and:: if (netif_queue_stopped(dp->dev) && TX_BUFFS_AVAIL(dp) > 0) netif_wake_queue(dp->dev); -2) An ndo_start_xmit method must not modify the shared parts of a - cloned SKB. +Lockless queue stop / wake helper macros +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -3) Do not forget that once you return NETDEV_TX_OK from your - ndo_start_xmit method, it is your driver's responsibility to free - up the SKB and in some finite amount of time. +.. kernel-doc:: include/net/netdev_queues.h + :doc: Lockless queue stopping / waking helpers. - For example, this means that it is not allowed for your TX - mitigation scheme to let TX packets "hang out" in the TX - ring unreclaimed forever if no new TX packets are sent. - This error can deadlock sockets waiting for send buffer room - to be freed up. +No exclusive ownership +---------------------- - If you return NETDEV_TX_BUSY from the ndo_start_xmit method, you - must not keep any reference to that SKB and you must not attempt - to free it up. +An ndo_start_xmit method must not modify the shared parts of a +cloned SKB. -Probing guidelines: +Timely completions +------------------ -1) Any hardware layer address you obtain for your device should - be verified. For example, for ethernet check it with - linux/etherdevice.h:is_valid_ether_addr() +Do not forget that once you return NETDEV_TX_OK from your +ndo_start_xmit method, it is your driver's responsibility to free +up the SKB and in some finite amount of time. -Close/stop guidelines: +For example, this means that it is not allowed for your TX +mitigation scheme to let TX packets "hang out" in the TX +ring unreclaimed forever if no new TX packets are sent. +This error can deadlock sockets waiting for send buffer room +to be freed up. -1) After the ndo_stop routine has been called, the hardware must - not receive or transmit any data. All in flight packets must - be aborted. If necessary, poll or wait for completion of - any reset commands. +If you return NETDEV_TX_BUSY from the ndo_start_xmit method, you +must not keep any reference to that SKB and you must not attempt +to free it up. -2) The ndo_stop routine will be called by unregister_netdevice - if device is still UP. +Probing guidelines +================== + +Address validation +------------------ + +Any hardware layer address you obtain for your device should +be verified. For example, for ethernet check it with +linux/etherdevice.h:is_valid_ether_addr() + +Close/stop guidelines +===================== + +Quiescence +---------- + +After the ndo_stop routine has been called, the hardware must +not receive or transmit any data. All in flight packets must +be aborted. If necessary, poll or wait for completion of +any reset commands. + +Auto-close +---------- + +The ndo_stop routine will be called by unregister_netdevice +if device is still UP. diff --git a/Documentation/translations/zh_CN/accounting/delay-accounting.rst b/Documentation/translations/zh_CN/accounting/delay-accounting.rst index f1849411018e..7b8693ccf80a 100644 --- a/Documentation/translations/zh_CN/accounting/delay-accounting.rst +++ b/Documentation/translations/zh_CN/accounting/delay-accounting.rst @@ -17,8 +17,9 @@ a) 等待一个CPU（任务为可运行） b) 完成由该任务发起的块I/O同步请求 c) 页面交换 d) 内存回收 -e) 页缓存抖动 +e) 抖动 f) 直接规整 +g) 写保护复制 并将这些统计信息通过taskstats接口提供给用户空间。 @@ -42,7 +43,7 @@ f) 直接规整 include/uapi/linux/taskstats.h 其描述了延时计数相关字段。系统通常以计数器形式返回 CPU、同步块 I/O、交换、内存 -回收、页缓存抖动、直接规整等的累积延时。 +回收、页缓存抖动、直接规整、写保护复制等的累积延时。 取任务某计数器两个连续读数的差值，将得到任务在该时间间隔内等待对应资源的总延时。 @@ -91,15 +92,17 @@ getdelays命令的一般格式:: CPU count real total virtual total delay total delay average 8 7000000 6872122 3382277 0.423ms IO count delay total delay average - 0 0 0ms + 0 0 0.000ms SWAP count delay total delay average - 0 0 0ms + 0 0 0.000ms RECLAIM count delay total delay average - 0 0 0ms + 0 0 0.000ms THRASHING count delay total delay average - 0 0 0ms + 0 0 0.000ms COMPACT count delay total delay average - 0 0 0ms + 0 0 0.000ms + WPCOPY count delay total delay average + 0 0 0ms 获取pid为1的IO计数，它只和-p一起使用:: # ./getdelays -i -p 1 diff --git a/Makefile b/Makefile index c12da8fcb089..1982ced2f43a 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 1 -SUBLEVEL = 99 +SUBLEVEL = 115 EXTRAVERSION = NAME = Curry Ramen diff --git a/arch/arm/boot/dts/bcm2837-rpi-cm3-io3.dts b/arch/arm/boot/dts/bcm2837-rpi-cm3-io3.dts index cf84e69fced8..4b2f63e0ae7c 100644 --- a/arch/arm/boot/dts/bcm2837-rpi-cm3-io3.dts +++ b/arch/arm/boot/dts/bcm2837-rpi-cm3-io3.dts @@ -76,7 +76,7 @@ }; &hdmi { - hpd-gpios = <&expgpio 1 GPIO_ACTIVE_LOW>; + hpd-gpios = <&expgpio 0 GPIO_ACTIVE_LOW>; power-domains = <&power RPI_POWER_DOMAIN_HDMI>; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi index 4d6a0c3e8455..ff062f4fd726 100644 --- a/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6q-kontron-samx6i.dtsi @@ -5,31 +5,8 @@ #include "imx6q.dtsi" #include "imx6qdl-kontron-samx6i.dtsi" -#include / { model = "Kontron SMARC sAMX6i Quad/Dual"; compatible = "kontron,imx6q-samx6i", "fsl,imx6q"; }; - -/* Quad/Dual SoMs have 3 chip-select signals */ -&ecspi4 { - cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>, - <&gpio3 25 GPIO_ACTIVE_LOW>; -}; - -&pinctrl_ecspi4 { - fsl,pins = < - MX6QDL_PAD_EIM_D21__ECSPI4_SCLK 0x100b1 - MX6QDL_PAD_EIM_D28__ECSPI4_MOSI 0x100b1 - MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1 - - /* SPI4_IMX_CS2# - connected to internal flash */ - MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 - /* SPI4_IMX_CS0# - connected to SMARC SPI0_CS0# */ - MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 - /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ - MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 - >; -}; diff --git a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi index 85aeebc9485d..668d33d1ff0c 100644 --- a/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi +++ b/arch/arm/boot/dts/imx6qdl-kontron-samx6i.dtsi @@ -244,7 +244,8 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_ecspi4>; cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>, - <&gpio3 29 GPIO_ACTIVE_LOW>; + <&gpio3 29 GPIO_ACTIVE_LOW>, + <&gpio3 25 GPIO_ACTIVE_LOW>; status = "okay"; /* default boot source: workaround #1 for errata ERR006282 */ @@ -259,7 +260,7 @@ &fec { pinctrl-names = "default"; pinctrl-0 = <&pinctrl_enet>; - phy-mode = "rgmii"; + phy-connection-type = "rgmii-id"; phy-handle = <ðphy>; mdio { @@ -269,7 +270,7 @@ ethphy: ethernet-phy@1 { compatible = "ethernet-phy-ieee802.3-c22"; reg = <1>; - reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>; + reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>; reset-assert-us = <1000>; }; }; @@ -464,6 +465,8 @@ MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0 /* SPI_IMX_CS0# - connected to SMARC SPI0_CS0# */ MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0 + /* SPI4_CS3# - connected to SMARC SPI0_CS1# */ + MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0 >; }; @@ -516,7 +519,7 @@ MX6QDL_PAD_ENET_MDIO__ENET_MDIO 0x1b0b0 MX6QDL_PAD_ENET_MDC__ENET_MDC 0x1b0b0 MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK 0x1b0b0 - MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25 0x1b0b0 /* RST_GBE0_PHY# */ + MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x1b0b0 /* RST_GBE0_PHY# */ >; }; @@ -729,7 +732,7 @@ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_pcie>; wake-up-gpio = <&gpio6 18 GPIO_ACTIVE_HIGH>; - reset-gpio = <&gpio3 13 GPIO_ACTIVE_HIGH>; + reset-gpio = <&gpio3 13 GPIO_ACTIVE_LOW>; }; /* LCD_BKLT_PWM */ @@ -817,5 +820,6 @@ /* CPLD is feeded by watchdog (hardwired) */ pinctrl-names = "default"; pinctrl-0 = <&pinctrl_wdog1>; + fsl,ext-reset-output; status = "okay"; }; diff --git a/arch/arm/boot/dts/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/imx7d-zii-rmu2.dts index 1c9f25848bf7..5b43d1d3d46d 100644 --- a/arch/arm/boot/dts/imx7d-zii-rmu2.dts +++ b/arch/arm/boot/dts/imx7d-zii-rmu2.dts @@ -350,7 +350,7 @@ &iomuxc_lpsr { pinctrl_enet1_phy_interrupt: enet1phyinterruptgrp { - fsl,phy = < + fsl,pins = < MX7D_PAD_LPSR_GPIO1_IO02__GPIO1_IO2 0x08 >; }; diff --git a/arch/arm/boot/dts/sam9x60.dtsi b/arch/arm/boot/dts/sam9x60.dtsi index 37a5d96aaf64..d3d49c6144bf 100644 --- a/arch/arm/boot/dts/sam9x60.dtsi +++ b/arch/arm/boot/dts/sam9x60.dtsi @@ -690,7 +690,7 @@ compatible = "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt"; reg = <0xfffffe20 0x20>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; pit: timer@fffffe40 { @@ -716,7 +716,7 @@ compatible = "microchip,sam9x60-rtc", "atmel,at91sam9x5-rtc"; reg = <0xfffffea8 0x100>; interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; watchdog: watchdog@ffffff80 { diff --git a/arch/arm/boot/dts/sama7g5.dtsi b/arch/arm/boot/dts/sama7g5.dtsi index 7bd8ae8e8d38..9cc0e86544ad 100644 --- a/arch/arm/boot/dts/sama7g5.dtsi +++ b/arch/arm/boot/dts/sama7g5.dtsi @@ -221,7 +221,7 @@ compatible = "microchip,sama7g5-rtt", "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt"; reg = <0xe001d020 0x30>; interrupts = ; - clocks = <&clk32k 0>; + clocks = <&clk32k 1>; }; clk32k: clock-controller@e001d050 { diff --git a/arch/arm/crypto/aes-ce-glue.c b/arch/arm/crypto/aes-ce-glue.c index b668c97663ec..f5b66f4cf45d 100644 --- a/arch/arm/crypto/aes-ce-glue.c +++ b/arch/arm/crypto/aes-ce-glue.c @@ -711,7 +711,7 @@ static int __init aes_init(void) algname = aes_algs[i].base.cra_name + 2; drvname = aes_algs[i].base.cra_driver_name + 2; basename = aes_algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto unregister_simds; diff --git a/arch/arm/crypto/aes-neonbs-glue.c b/arch/arm/crypto/aes-neonbs-glue.c index f00f042ef357..0ca94b90bc4e 100644 --- a/arch/arm/crypto/aes-neonbs-glue.c +++ b/arch/arm/crypto/aes-neonbs-glue.c @@ -539,7 +539,7 @@ static int __init aes_init(void) algname = aes_algs[i].base.cra_name + 2; drvname = aes_algs[i].base.cra_driver_name + 2; basename = aes_algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(aes_algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto unregister_simds; diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h index 2fcbec9c306c..d80a70dfac5c 100644 --- a/arch/arm/include/asm/uaccess.h +++ b/arch/arm/include/asm/uaccess.h @@ -109,16 +109,6 @@ extern int __get_user_64t_1(void *); extern int __get_user_64t_2(void *); extern int __get_user_64t_4(void *); -#define __GUP_CLOBBER_1 "lr", "cc" -#ifdef CONFIG_CPU_USE_DOMAINS -#define __GUP_CLOBBER_2 "ip", "lr", "cc" -#else -#define __GUP_CLOBBER_2 "lr", "cc" -#endif -#define __GUP_CLOBBER_4 "lr", "cc" -#define __GUP_CLOBBER_32t_8 "lr", "cc" -#define __GUP_CLOBBER_8 "lr", "cc" - #define __get_user_x(__r2, __p, __e, __l, __s) \ __asm__ __volatile__ ( \ __asmeq("%0", "r0") __asmeq("%1", "r2") \ @@ -126,7 +116,7 @@ extern int __get_user_64t_4(void *); "bl __get_user_" #__s \ : "=&r" (__e), "=r" (__r2) \ : "0" (__p), "r" (__l) \ - : __GUP_CLOBBER_##__s) + : "ip", "lr", "cc") /* narrowing a double-word get into a single 32bit word register: */ #ifdef __ARMEB__ @@ -148,7 +138,7 @@ extern int __get_user_64t_4(void *); "bl __get_user_64t_" #__s \ : "=&r" (__e), "=r" (__r2) \ : "0" (__p), "r" (__l) \ - : __GUP_CLOBBER_##__s) + : "ip", "lr", "cc") #else #define __get_user_x_64t __get_user_x #endif diff --git a/arch/arm/mach-davinci/pm.c b/arch/arm/mach-davinci/pm.c index 8aa39db095d7..2c5155bd376b 100644 --- a/arch/arm/mach-davinci/pm.c +++ b/arch/arm/mach-davinci/pm.c @@ -61,7 +61,7 @@ static void davinci_pm_suspend(void) /* Configure sleep count in deep sleep register */ val = __raw_readl(pm_config.deepsleep_reg); - val &= ~DEEPSLEEP_SLEEPCOUNT_MASK, + val &= ~DEEPSLEEP_SLEEPCOUNT_MASK; val |= pm_config.sleepcount; __raw_writel(val, pm_config.deepsleep_reg); diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c index 85a496ddc619..e9f72a529b50 100644 --- a/arch/arm/mach-ep93xx/clock.c +++ b/arch/arm/mach-ep93xx/clock.c @@ -359,7 +359,7 @@ static unsigned long ep93xx_div_recalc_rate(struct clk_hw *hw, u32 val = __raw_readl(psc->reg); u8 index = (val & psc->mask) >> psc->shift; - if (index > psc->num_div) + if (index >= psc->num_div) return 0; return DIV_ROUND_UP_ULL(parent_rate, psc->div[index]); diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c index 937f56bbaf6c..effd28294da0 100644 --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -512,10 +512,8 @@ static struct ads7846_platform_data spitz_ads7846_info = { static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 6, "BL_CONT", GPIO_ACTIVE_LOW), + GPIO_LOOKUP("sharp-scoop.1", 7, "BL_ON", GPIO_ACTIVE_HIGH), { }, }, }; @@ -523,10 +521,8 @@ static struct gpiod_lookup_table spitz_lcdcon_gpio_table = { static struct gpiod_lookup_table akita_lcdcon_gpio_table = { .dev_id = "spi2.1", .table = { - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_CONT, - "BL_CONT", GPIO_ACTIVE_LOW), - GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_ON, - "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 3, "BL_ON", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 4, "BL_CONT", GPIO_ACTIVE_LOW), { }, }, }; @@ -953,12 +949,9 @@ static inline void spitz_i2c_init(void) {} static struct gpiod_lookup_table spitz_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.1", SPITZ_GPIO_MIC_BIAS - SPITZ_SCP2_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.1", 8, "mic", GPIO_ACTIVE_HIGH), { }, }, }; @@ -966,12 +959,9 @@ static struct gpiod_lookup_table spitz_audio_gpio_table = { static struct gpiod_lookup_table akita_audio_gpio_table = { .dev_id = "spitz-audio", .table = { - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE, - "mute-l", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE, - "mute-r", GPIO_ACTIVE_HIGH), - GPIO_LOOKUP("i2c-max7310", AKITA_GPIO_MIC_BIAS - AKITA_IOEXP_GPIO_BASE, - "mic", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH), + GPIO_LOOKUP("i2c-max7310", 2, "mic", GPIO_ACTIVE_HIGH), { }, }, }; diff --git a/arch/arm/mach-versatile/platsmp-realview.c b/arch/arm/mach-versatile/platsmp-realview.c index 5d363385c801..059d796b26bc 100644 --- a/arch/arm/mach-versatile/platsmp-realview.c +++ b/arch/arm/mach-versatile/platsmp-realview.c @@ -66,6 +66,7 @@ static void __init realview_smp_prepare_cpus(unsigned int max_cpus) return; } map = syscon_node_to_regmap(np); + of_node_put(np); if (IS_ERR(map)) { pr_err("PLATSMP: No syscon regmap\n"); return; diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 044b98a62f7b..1a62ef142a98 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1000,6 +1000,46 @@ config ARM64_ERRATUM_2966298 If unsure, say Y. +config ARM64_ERRATUM_3194386 + bool "Cortex-*/Neoverse-*: workaround for MSR SSBS not self-synchronizing" + default y + help + This option adds the workaround for the following errata: + + * ARM Cortex-A76 erratum 3324349 + * ARM Cortex-A77 erratum 3324348 + * ARM Cortex-A78 erratum 3324344 + * ARM Cortex-A78C erratum 3324346 + * ARM Cortex-A78C erratum 3324347 + * ARM Cortex-A710 erratam 3324338 + * ARM Cortex-A715 errartum 3456084 + * ARM Cortex-A720 erratum 3456091 + * ARM Cortex-A725 erratum 3456106 + * ARM Cortex-X1 erratum 3324344 + * ARM Cortex-X1C erratum 3324346 + * ARM Cortex-X2 erratum 3324338 + * ARM Cortex-X3 erratum 3324335 + * ARM Cortex-X4 erratum 3194386 + * ARM Cortex-X925 erratum 3324334 + * ARM Neoverse-N1 erratum 3324349 + * ARM Neoverse N2 erratum 3324339 + * ARM Neoverse-N3 erratum 3456111 + * ARM Neoverse-V1 erratum 3324341 + * ARM Neoverse V2 erratum 3324336 + * ARM Neoverse-V3 erratum 3312417 + + On affected cores "MSR SSBS, #0" instructions may not affect + subsequent speculative instructions, which may permit unexepected + speculative store bypassing. + + Work around this problem by placing a Speculation Barrier (SB) or + Instruction Synchronization Barrier (ISB) after kernel changes to + SSBS. The presence of the SSBS special-purpose register is hidden + from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such that userspace + will use the PR_SPEC_STORE_BYPASS prctl to change SSBS. + + If unsure, say Y. + config CAVIUM_ERRATUM_22375 bool "Cavium erratum 22375, 24313" default y diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index 99fa774f41fb..29a7cdc1d384 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -10,7 +10,7 @@ # # Copyright (C) 1995-2001 by Russell King -LDFLAGS_vmlinux :=--no-undefined -X +LDFLAGS_vmlinux :=--no-undefined -X --pic-veneer ifeq ($(CONFIG_RELOCATABLE), y) # Pass --no-apply-dynamic-relocs to restore pre-binutils-2.27 behaviour diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi index 7c029f552a23..256c46771db7 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi @@ -311,8 +311,8 @@ <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi index 350022935052..a689bd14ece9 100644 --- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi @@ -323,8 +323,8 @@ <&reset RESET_HDMI_SYSTEM_RESET>, <&reset RESET_HDMI_TX>; reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy"; - clocks = <&clkc CLKID_HDMI_PCLK>, - <&clkc CLKID_CLK81>, + clocks = <&clkc CLKID_HDMI>, + <&clkc CLKID_HDMI_PCLK>, <&clkc CLKID_GCLK_VENCI_INT0>; clock-names = "isfr", "iahb", "venci"; }; diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi index 80737731af3f..8bc4ef9d8a61 100644 --- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi +++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi @@ -337,7 +337,7 @@ }; spdifin: audio-controller@400 { - compatible = "amlogic,g12a-spdifin", + compatible = "amlogic,sm1-spdifin", "amlogic,axg-spdifin"; reg = <0x0 0x400 0x0 0x30>; #sound-dai-cells = <0>; @@ -351,7 +351,7 @@ }; spdifout_a: audio-controller@480 { - compatible = "amlogic,g12a-spdifout", + compatible = "amlogic,sm1-spdifout", "amlogic,axg-spdifout"; reg = <0x0 0x480 0x0 0x50>; #sound-dai-cells = <0>; diff --git a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts index 5db9a81ac7bb..06791d4f99b8 100644 --- a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts +++ b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts @@ -31,7 +31,7 @@ device_type = "memory"; reg = <0x0 0x80000000 0x3da00000>, <0x0 0xc0000000 0x40000000>, - <0x8 0x80000000 0x40000000>; + <0x8 0x80000000 0x80000000>; }; gpio-keys { diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts index b1ddc491d293..9c9431455f85 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts @@ -286,8 +286,8 @@ /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts index 527dcb279ba5..f4bb9c6521c6 100644 --- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts +++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts @@ -244,8 +244,8 @@ /* eMMC is shared pin with parallel NAND */ emmc_pins_default: emmc-pins-default { mux { - function = "emmc", "emmc_rst"; - groups = "emmc"; + function = "emmc"; + groups = "emmc", "emmc_rst"; }; /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7", diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi index 3d95625f1b0b..d7fc924a9d0e 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi @@ -168,21 +168,24 @@ vdd18-supply = <&pp1800_mipibrdg>; vdd33-supply = <&vddio_mipibrdg>; - #address-cells = <1>; - #size-cells = <0>; - port@0 { - reg = <0>; + ports { + #address-cells = <1>; + #size-cells = <0>; - anx7625_in: endpoint { - remote-endpoint = <&dsi_out>; + port@0 { + reg = <0>; + + anx7625_in: endpoint { + remote-endpoint = <&dsi_out>; + }; }; - }; - port@1 { - reg = <1>; + port@1 { + reg = <1>; - anx7625_out: endpoint { - remote-endpoint = <&panel_in>; + anx7625_out: endpoint { + remote-endpoint = <&panel_in>; + }; }; }; }; diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi index 1db97d94658b..03ccdbb1c5ed 100644 --- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi @@ -767,7 +767,6 @@ }; pins-rts { pinmux = ; - output-enable; }; pins-cts { pinmux = ; @@ -786,7 +785,6 @@ }; pins-rts { pinmux = ; - output-enable; }; pins-cts { pinmux = ; diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi index 9180a73db066..39e4f6a560f9 100644 --- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi +++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi @@ -922,6 +922,7 @@ usb2-lpm-disable; vusb33-supply = <&mt6359_vusb_ldo_reg>; vbus-supply = <&usb_vbus>; + mediatek,u3p-dis-msk = <1>; }; #include diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi index 1533c61cb106..3a943912b090 100644 --- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi @@ -760,6 +760,7 @@ clocks = <&xo>; clock-names = "ref"; tx-fifo-resize; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi index 3d8e5ba51ce0..2f53c099634b 100644 --- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi +++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi @@ -593,6 +593,7 @@ interrupts = ; phys = <&qusb_phy_0>, <&usb0_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; @@ -635,6 +636,7 @@ interrupts = ; phys = <&qusb_phy_1>, <&usb1_ssphy>; phy-names = "usb2-phy", "usb3-phy"; + snps,parkmode-disable-ss-quirk; snps,is-utmi-l1-suspend; snps,hird-threshold = /bits/ 8 <0x0>; snps,dis_u2_susphy_quirk; diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi index 77819186086a..de320bebe412 100644 --- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi @@ -368,7 +368,6 @@ &hsusb_phy1 { status = "okay"; - extcon = <&typec>; vdda-pll-supply = <&vreg_l12a_1p8>; vdda-phy-dpdm-supply = <&vreg_l24a_3p075>; diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi index 789121171a11..3b9a4bf89701 100644 --- a/arch/arm64/boot/dts/qcom/msm8996.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi @@ -2016,7 +2016,7 @@ <&gcc GCC_UFS_RX_SYMBOL_0_CLK>; freq-table-hz = <100000000 200000000>, - <0 0>, + <100000000 200000000>, <0 0>, <0 0>, <0 0>, @@ -3004,6 +3004,7 @@ snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; snps,is-utmi-l1-suspend; + snps,parkmode-disable-ss-quirk; tx-fifo-resize; }; }; diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi index 7a41250539ff..4de9ff045ff5 100644 --- a/arch/arm64/boot/dts/qcom/msm8998.dtsi +++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi @@ -1457,7 +1457,6 @@ * SoC VDDMX RPM Power Domain in the Adreno driver. */ power-domains = <&gpucc GPU_GX_GDSC>; - status = "disabled"; }; gpucc: clock-controller@5065000 { @@ -2030,7 +2029,8 @@ interrupts = ; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; - phys = <&qusb2phy>, <&usb1_ssphy>; + snps,parkmode-disable-ss-quirk; + phys = <&qusb2phy>, <&usb3phy>; phy-names = "usb2-phy", "usb3-phy"; snps,has-lpm-erratum; snps,hird-threshold = /bits/ 8 <0x10>; @@ -2039,33 +2039,26 @@ usb3phy: phy@c010000 { compatible = "qcom,msm8998-qmp-usb3-phy"; - reg = <0x0c010000 0x18c>; - status = "disabled"; - #address-cells = <1>; - #size-cells = <1>; - ranges; + reg = <0x0c010000 0x1000>; clocks = <&gcc GCC_USB3_PHY_AUX_CLK>, + <&gcc GCC_USB3_CLKREF_CLK>, <&gcc GCC_USB_PHY_CFG_AHB2PHY_CLK>, - <&gcc GCC_USB3_CLKREF_CLK>; - clock-names = "aux", "cfg_ahb", "ref"; + <&gcc GCC_USB3_PHY_PIPE_CLK>; + clock-names = "aux", + "ref", + "cfg_ahb", + "pipe"; + clock-output-names = "usb3_phy_pipe_clk_src"; + #clock-cells = <0>; + #phy-cells = <0>; resets = <&gcc GCC_USB3_PHY_BCR>, <&gcc GCC_USB3PHY_PHY_BCR>; - reset-names = "phy", "common"; + reset-names = "phy", + "phy_phy"; - usb1_ssphy: phy@c010200 { - reg = <0xc010200 0x128>, - <0xc010400 0x200>, - <0xc010c00 0x20c>, - <0xc010600 0x128>, - <0xc010800 0x200>; - #phy-cells = <0>; - #clock-cells = <0>; - clocks = <&gcc GCC_USB3_PHY_PIPE_CLK>; - clock-names = "pipe0"; - clock-output-names = "usb3_phy_pipe_clk_src"; - }; + status = "disabled"; }; qusb2phy: phy@c012000 { diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi index 2430549265d3..75ddebebb8fc 100644 --- a/arch/arm64/boot/dts/qcom/sdm630.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi @@ -1243,6 +1243,7 @@ interrupts = ; snps,dis_u2_susphy_quirk; snps,dis_enblslpm_quirk; + snps,parkmode-disable-ss-quirk; /* * SDM630 technically supports USB3 but I diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi index 95c515da9f2e..71644b9b8866 100644 --- a/arch/arm64/boot/dts/qcom/sdm845.dtsi +++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi @@ -2537,6 +2537,8 @@ clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi index 9da373090593..ba078099b805 100644 --- a/arch/arm64/boot/dts/qcom/sm6350.dtsi +++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi @@ -830,6 +830,8 @@ clocks = <&gcc GCC_UFS_MEM_CLKREF_CLK>, <&gcc GCC_UFS_PHY_PHY_AUX_CLK>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; @@ -893,6 +895,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "adsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; @@ -1000,6 +1003,7 @@ compatible = "qcom,fastrpc"; qcom,glink-channels = "fastrpcglink-apps-dsp"; label = "cdsp"; + qcom,non-secure-domain; #address-cells = <1>; #size-cells = <0>; diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi index 3d02adbc0b62..c9780b2afd2f 100644 --- a/arch/arm64/boot/dts/qcom/sm8250.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi @@ -2182,6 +2182,8 @@ reset-names = "ufsphy"; status = "disabled"; + power-domains = <&gcc UFS_PHY_GDSC>; + ufs_mem_phy_lanes: phy@1d87400 { reg = <0 0x01d87400 0 0x16c>, <0 0x01d87600 0 0x200>, diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi index 128542582b3d..aa0977af9411 100644 --- a/arch/arm64/boot/dts/qcom/sm8450.dtsi +++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi @@ -3153,6 +3153,8 @@ <&gcc GCC_UFS_PHY_PHY_AUX_CLK>, <&gcc GCC_UFS_0_CLKREF_EN>; + power-domains = <&gcc UFS_PHY_GDSC>; + resets = <&ufs_mem_hc 0>; reset-names = "ufsphy"; status = "disabled"; diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi index b677ef6705d9..158c99b1a7b7 100644 --- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi @@ -2209,8 +2209,7 @@ interrupt-controller; reg = <0x0 0xf1000000 0 0x20000>, <0x0 0xf1060000 0 0x110000>; - interrupts = ; + interrupts = ; }; fcpvd0: fcp@fea10000 { @@ -2857,9 +2856,12 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi index 4092c0016035..140c4672ff5b 100644 --- a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi @@ -935,8 +935,7 @@ interrupt-controller; reg = <0x0 0xf1000000 0 0x20000>, <0x0 0xf1060000 0 0x110000>; - interrupts = ; + interrupts = ; }; prr: chipid@fff00044 { @@ -991,10 +990,13 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(8) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; ufs30_clk: ufs30-clk { diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi index 868d1a3cbdf6..3de3ea0073c3 100644 --- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi +++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi @@ -18,12 +18,80 @@ #address-cells = <1>; #size-cells = <0>; + cpu-map { + cluster0 { + core0 { + cpu = <&a76_0>; + }; + core1 { + cpu = <&a76_1>; + }; + }; + + cluster1 { + core0 { + cpu = <&a76_2>; + }; + core1 { + cpu = <&a76_3>; + }; + }; + }; + a76_0: cpu@0 { compatible = "arm,cortex-a76"; reg = <0>; device_type = "cpu"; power-domains = <&sysc R8A779G0_PD_A1E0D0C0>; + next-level-cache = <&L3_CA76_0>; + enable-method = "psci"; }; + + a76_1: cpu@100 { + compatible = "arm,cortex-a76"; + reg = <0x100>; + device_type = "cpu"; + power-domains = <&sysc R8A779G0_PD_A1E0D0C1>; + next-level-cache = <&L3_CA76_0>; + enable-method = "psci"; + }; + + a76_2: cpu@10000 { + compatible = "arm,cortex-a76"; + reg = <0x10000>; + device_type = "cpu"; + power-domains = <&sysc R8A779G0_PD_A1E0D1C0>; + next-level-cache = <&L3_CA76_1>; + enable-method = "psci"; + }; + + a76_3: cpu@10100 { + compatible = "arm,cortex-a76"; + reg = <0x10100>; + device_type = "cpu"; + power-domains = <&sysc R8A779G0_PD_A1E0D1C1>; + next-level-cache = <&L3_CA76_1>; + enable-method = "psci"; + }; + + L3_CA76_0: cache-controller-0 { + compatible = "cache"; + power-domains = <&sysc R8A779G0_PD_A2E0D0>; + cache-unified; + cache-level = <3>; + }; + + L3_CA76_1: cache-controller-1 { + compatible = "cache"; + power-domains = <&sysc R8A779G0_PD_A2E0D1>; + cache-unified; + cache-level = <3>; + }; + }; + + psci { + compatible = "arm,psci-1.0", "arm,psci-0.2"; + method = "smc"; }; extal_clk: extal { @@ -482,8 +550,7 @@ interrupt-controller; reg = <0x0 0xf1000000 0 0x20000>, <0x0 0xf1060000 0 0x110000>; - interrupts = ; + interrupts = ; }; prr: chipid@fff00044 { @@ -494,9 +561,12 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi index 011d4c88f4ed..1276a9487bfb 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi @@ -41,10 +41,13 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; @@ -132,8 +135,8 @@ #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi index d26488b5a82d..d65f8840ccd8 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi @@ -788,8 +788,8 @@ #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; @@ -1091,9 +1091,12 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g044c1.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044c1.dtsi index 1d57df706939..56a979e82c4f 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044c1.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044c1.dtsi @@ -15,13 +15,6 @@ /delete-node/ cpu-map; /delete-node/ cpu@100; }; - - timer { - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; - }; }; &soc { diff --git a/arch/arm64/boot/dts/renesas/r9a07g044l1.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044l1.dtsi index 9d89d4590358..9cf27ca9f1d2 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g044l1.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g044l1.dtsi @@ -15,11 +15,4 @@ /delete-node/ cpu-map; /delete-node/ cpu@100; }; - - timer { - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; - }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi index b3d37ca942ee..7a50d1432cc0 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi @@ -794,8 +794,8 @@ #interrupt-cells = <3>; #address-cells = <0>; interrupt-controller; - reg = <0x0 0x11900000 0 0x40000>, - <0x0 0x11940000 0 0x60000>; + reg = <0x0 0x11900000 0 0x20000>, + <0x0 0x11940000 0 0x40000>; interrupts = ; }; @@ -1097,9 +1097,12 @@ timer { compatible = "arm,armv8-timer"; - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>; + interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>, + <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>; + interrupt-names = "sec-phys", "phys", "virt", "hyp-phys", + "hyp-virt"; }; }; diff --git a/arch/arm64/boot/dts/renesas/r9a07g054l1.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054l1.dtsi index c448cc6634c1..d85a6ac0f024 100644 --- a/arch/arm64/boot/dts/renesas/r9a07g054l1.dtsi +++ b/arch/arm64/boot/dts/renesas/r9a07g054l1.dtsi @@ -15,11 +15,4 @@ /delete-node/ cpu-map; /delete-node/ cpu@100; }; - - timer { - interrupts-extended = <&gic GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>, - <&gic GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>; - }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts index edc8d2e3980d..bc9e98fe0f01 100644 --- a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts +++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts @@ -17,6 +17,7 @@ ethernet0 = &gmac; mmc0 = &emmc; mmc1 = &sdmmc; + mmc2 = &sdio; }; chosen { @@ -145,11 +146,25 @@ &gmac { clock_in_out = "output"; + phy-handle = <&rtl8201f>; phy-supply = <&vcc_io>; - snps,reset-gpio = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; - snps,reset-active-low; - snps,reset-delays-us = <0 50000 50000>; status = "okay"; + + mdio { + compatible = "snps,dwmac-mdio"; + #address-cells = <1>; + #size-cells = <0>; + + rtl8201f: ethernet-phy@1 { + compatible = "ethernet-phy-ieee802.3-c22"; + reg = <1>; + pinctrl-names = "default"; + pinctrl-0 = <&mac_rst>; + reset-assert-us = <20000>; + reset-deassert-us = <50000>; + reset-gpios = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>; + }; + }; }; &i2c1 { @@ -160,6 +175,26 @@ pinctrl-names = "default"; pinctrl-0 = <&rtc_32k>; + bluetooth { + bt_reg_on: bt-reg-on { + rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>; + }; + + bt_wake_host: bt-wake-host { + rockchip,pins = <4 RK_PB4 RK_FUNC_GPIO &pcfg_pull_down>; + }; + + host_wake_bt: host-wake-bt { + rockchip,pins = <4 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + + gmac { + mac_rst: mac-rst { + rockchip,pins = <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_none>; + }; + }; + leds { green_led: green-led { rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>; @@ -203,15 +238,31 @@ cap-sd-highspeed; cap-sdio-irq; keep-power-in-suspend; - max-frequency = <1000000>; + max-frequency = <100000000>; mmc-pwrseq = <&sdio_pwrseq>; + no-mmc; + no-sd; non-removable; - sd-uhs-sdr104; + sd-uhs-sdr50; + vmmc-supply = <&vcc_io>; + vqmmc-supply = <&vcc_1v8>; status = "okay"; + + rtl8723ds: wifi@1 { + reg = <1>; + interrupt-parent = <&gpio0>; + interrupts = ; + interrupt-names = "host-wake"; + pinctrl-names = "default"; + pinctrl-0 = <&wifi_host_wake>; + }; }; &sdmmc { + cap-mmc-highspeed; cap-sd-highspeed; + disable-wp; + vmmc-supply = <&vcc_io>; status = "okay"; }; @@ -230,16 +281,22 @@ }; &uart0 { + pinctrl-names = "default"; + pinctrl-0 = <&uart0_xfer>; status = "okay"; }; &uart4 { + uart-has-rtscts; status = "okay"; bluetooth { - compatible = "realtek,rtl8723bs-bt"; - device-wake-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; + compatible = "realtek,rtl8723ds-bt"; + device-wake-gpios = <&gpio4 RK_PB2 GPIO_ACTIVE_HIGH>; + enable-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>; host-wake-gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>; + pinctrl-names = "default"; + pinctrl-0 = <&bt_reg_on &bt_wake_host &host_wake_bt>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts index d9905a08c6ce..66443d52cd34 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts +++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts @@ -332,7 +332,7 @@ pmic { pmic_int_l: pmic-int-l { - rockchip,pins = <2 RK_PA6 RK_FUNC_GPIO &pcfg_pull_up>; + rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi index b9440b310520..cb37bb359519 100644 --- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi @@ -1316,8 +1316,8 @@ <0>, <24000000>, <24000000>, <24000000>, <15000000>, <15000000>, - <100000000>, <100000000>, - <100000000>, <100000000>, + <300000000>, <100000000>, + <400000000>, <100000000>, <50000000>, <100000000>, <100000000>, <100000000>, <50000000>, <50000000>, diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts index a51e8d0493ca..3d7b82e921f6 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts +++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts @@ -32,12 +32,12 @@ backlight: edp-backlight { compatible = "pwm-backlight"; power-supply = <&vcc_12v>; - pwms = <&pwm0 0 740740 0>; + pwms = <&pwm0 0 125000 0>; }; bat: battery { compatible = "simple-battery"; - charge-full-design-microamp-hours = <9800000>; + charge-full-design-microamp-hours = <10000000>; voltage-max-design-microvolt = <4350000>; voltage-min-design-microvolt = <3000000>; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi index 937a15005eb0..e089e0c26a72 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi @@ -119,6 +119,22 @@ drive-impedance-ohm = <33>; }; +&gpio3 { + /* + * The Qseven BIOS_DISABLE signal on the RK3399-Q7 keeps the on-module + * eMMC and SPI flash powered-down initially (in fact it keeps the + * reset signal asserted). BIOS_DISABLE_OVERRIDE pin allows to override + * that signal so that eMMC and SPI can be used regardless of the state + * of the signal. + */ + bios-disable-override-hog { + gpios = ; + gpio-hog; + line-name = "bios_disable_override"; + output-high; + }; +}; + &gmac { assigned-clocks = <&cru SCLK_RMII_SRC>; assigned-clock-parents = <&clkin_gmac>; @@ -374,6 +390,7 @@ &i2s0 { pinctrl-0 = <&i2s0_2ch_bus>; + pinctrl-1 = <&i2s0_2ch_bus_bclk_off>; rockchip,playback-channels = <2>; rockchip,capture-channels = <2>; status = "okay"; @@ -382,8 +399,8 @@ /* * As Q7 does not specify neither a global nor a RX clock for I2S these * signals are not used. Furthermore I2S0_LRCK_RX is used as GPIO. - * Therefore we have to redefine the i2s0_2ch_bus definition to prevent - * conflicts. + * Therefore we have to redefine the i2s0_2ch_bus and i2s0_2ch_bus_bclk_off + * definitions to prevent conflicts. */ &i2s0_2ch_bus { rockchip,pins = @@ -393,6 +410,14 @@ <3 RK_PD7 1 &pcfg_pull_none>; }; +&i2s0_2ch_bus_bclk_off { + rockchip,pins = + <3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>, + <3 RK_PD2 1 &pcfg_pull_none>, + <3 RK_PD3 1 &pcfg_pull_none>, + <3 RK_PD7 1 &pcfg_pull_none>; +}; + &io_domains { status = "okay"; bt656-supply = <&vcc_1v8>; @@ -408,9 +433,14 @@ &pinctrl { pinctrl-names = "default"; - pinctrl-0 = <&q7_thermal_pin>; + pinctrl-0 = <&q7_thermal_pin &bios_disable_override_hog_pin>; gpios { + bios_disable_override_hog_pin: bios-disable-override-hog-pin { + rockchip,pins = + <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>; + }; + q7_thermal_pin: q7-thermal-pin { rockchip,pins = <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts index 674792567fa6..4fc8354e069a 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts @@ -478,7 +478,7 @@ }; codec { - mic-in-differential; + rockchip,mic-in-differential; }; }; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts index bab46db2b18c..478620c78259 100644 --- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts +++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts @@ -481,10 +481,6 @@ }; }; }; - - codec { - mic-in-differential; - }; }; }; diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts index 80358cba6954..f4a76926c4e6 100644 --- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts +++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts @@ -111,7 +111,7 @@ no-map; }; - c66_1_dma_memory_region: c66-dma-memory@a6000000 { + c66_0_dma_memory_region: c66-dma-memory@a6000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa6000000 0x00 0x100000>; no-map; @@ -123,7 +123,7 @@ no-map; }; - c66_0_dma_memory_region: c66-dma-memory@a7000000 { + c66_1_dma_memory_region: c66-dma-memory@a7000000 { compatible = "shared-dma-pool"; reg = <0x00 0xa7000000 0x00 0x100000>; no-map; diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h index bd68e1b7f29f..702587fda70c 100644 --- a/arch/arm64/include/asm/acpi.h +++ b/arch/arm64/include/asm/acpi.h @@ -97,6 +97,18 @@ static inline u32 get_acpi_id_for_cpu(unsigned int cpu) return acpi_cpu_get_madt_gicc(cpu)->uid; } +static inline int get_cpu_for_acpi_id(u32 uid) +{ + int cpu; + + for (cpu = 0; cpu < nr_cpu_ids; cpu++) + if (acpi_cpu_get_madt_gicc(cpu) && + uid == get_acpi_id_for_cpu(cpu)) + return cpu; + + return -EINVAL; +} + static inline void arch_fix_phys_package_id(int num, u32 slot) { } void __init acpi_init_cpus(void); int apei_claim_sea(struct pt_regs *regs); diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h index 2cfc4245d2e2..e22ec44d50f5 100644 --- a/arch/arm64/include/asm/barrier.h +++ b/arch/arm64/include/asm/barrier.h @@ -38,6 +38,10 @@ */ #define dgh() asm volatile("hint #6" : : : "memory") +#define spec_bar() asm volatile(ALTERNATIVE("dsb nsh\nisb\n", \ + SB_BARRIER_INSN"nop\n", \ + ARM64_HAS_SB)) + #ifdef CONFIG_ARM64_PSEUDO_NMI #define pmr_sync() \ do { \ diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index af3a678a76b3..8efc3302bf96 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -82,9 +82,19 @@ #define ARM_CPU_PART_CORTEX_A510 0xD46 #define ARM_CPU_PART_CORTEX_A520 0xD80 #define ARM_CPU_PART_CORTEX_A710 0xD47 +#define ARM_CPU_PART_CORTEX_A715 0xD4D #define ARM_CPU_PART_CORTEX_X2 0xD48 #define ARM_CPU_PART_NEOVERSE_N2 0xD49 #define ARM_CPU_PART_CORTEX_A78C 0xD4B +#define ARM_CPU_PART_CORTEX_X1C 0xD4C +#define ARM_CPU_PART_CORTEX_X3 0xD4E +#define ARM_CPU_PART_NEOVERSE_V2 0xD4F +#define ARM_CPU_PART_CORTEX_A720 0xD81 +#define ARM_CPU_PART_CORTEX_X4 0xD82 +#define ARM_CPU_PART_NEOVERSE_V3 0xD84 +#define ARM_CPU_PART_CORTEX_X925 0xD85 +#define ARM_CPU_PART_CORTEX_A725 0xD87 +#define ARM_CPU_PART_NEOVERSE_N3 0xD8E #define APM_CPU_PART_XGENE 0x000 #define APM_CPU_VAR_POTENZA 0x00 @@ -148,9 +158,19 @@ #define MIDR_CORTEX_A510 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A510) #define MIDR_CORTEX_A520 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A520) #define MIDR_CORTEX_A710 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A710) +#define MIDR_CORTEX_A715 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A715) #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2) #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2) #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C) +#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C) +#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3) +#define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2) +#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720) +#define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4) +#define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3) +#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925) +#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725) +#define MIDR_NEOVERSE_N3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N3) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h index b5bd3c38a01b..e714d7770999 100644 --- a/arch/arm64/include/asm/jump_label.h +++ b/arch/arm64/include/asm/jump_label.h @@ -13,6 +13,7 @@ #include #include +#define HAVE_JUMP_LABEL_BATCH #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE static __always_inline bool arch_static_branch(struct static_key *key, diff --git a/arch/arm64/include/asm/uprobes.h b/arch/arm64/include/asm/uprobes.h index 315eef654e39..014b02897f8e 100644 --- a/arch/arm64/include/asm/uprobes.h +++ b/arch/arm64/include/asm/uprobes.h @@ -10,21 +10,19 @@ #include #include -#define MAX_UINSN_BYTES AARCH64_INSN_SIZE - -#define UPROBE_SWBP_INSN BRK64_OPCODE_UPROBES +#define UPROBE_SWBP_INSN cpu_to_le32(BRK64_OPCODE_UPROBES) #define UPROBE_SWBP_INSN_SIZE AARCH64_INSN_SIZE -#define UPROBE_XOL_SLOT_BYTES MAX_UINSN_BYTES +#define UPROBE_XOL_SLOT_BYTES AARCH64_INSN_SIZE -typedef u32 uprobe_opcode_t; +typedef __le32 uprobe_opcode_t; struct arch_uprobe_task { }; struct arch_uprobe { union { - u8 insn[MAX_UINSN_BYTES]; - u8 ixol[MAX_UINSN_BYTES]; + __le32 insn; + __le32 ixol; }; struct arch_probe_insn api; bool simulate; diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index e51535a5f939..2465f291c7e1 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -27,24 +27,13 @@ #include -static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE }; +static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE }; int __init acpi_numa_get_nid(unsigned int cpu) { return acpi_early_node_map[cpu]; } -static inline int get_cpu_for_acpi_id(u32 uid) -{ - int cpu; - - for (cpu = 0; cpu < nr_cpu_ids; cpu++) - if (uid == get_acpi_id_for_cpu(cpu)) - return cpu; - - return -EINVAL; -} - static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header, const unsigned long end) { diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 74584597bfb8..78aea409b092 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -435,6 +435,32 @@ static struct midr_range broken_aarch32_aes[] = { }; #endif /* CONFIG_ARM64_WORKAROUND_TRBE_WRITE_OUT_OF_RANGE */ +#ifdef CONFIG_ARM64_ERRATUM_3194386 +static const struct midr_range erratum_spec_ssbs_list[] = { + MIDR_ALL_VERSIONS(MIDR_CORTEX_A76), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A77), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A710), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A715), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A720), + MIDR_ALL_VERSIONS(MIDR_CORTEX_A725), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X2), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X3), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X4), + MIDR_ALL_VERSIONS(MIDR_CORTEX_X925), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N3), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2), + MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3), + {} +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -726,6 +752,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .cpu_enable = cpu_clear_bf16_from_user_emulation, }, #endif +#ifdef CONFIG_ARM64_ERRATUM_3194386 + { + .desc = "SSBS not fully self-synchronizing", + .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS, + ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list), + }, +#endif #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD { .desc = "ARM erratum 2966298", diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 770a31c6ed81..840cc48b5147 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -2084,6 +2084,17 @@ static void cpu_enable_mte(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_MTE */ +static void user_feature_fixup(void) +{ + if (cpus_have_cap(ARM64_WORKAROUND_SPECULATIVE_SSBS)) { + struct arm64_ftr_reg *regp; + + regp = get_arm64_ftr_reg(SYS_ID_AA64PFR1_EL1); + if (regp) + regp->user_mask &= ~ID_AA64PFR1_EL1_SSBS_MASK; + } +} + static void elf_hwcap_fixup(void) { #ifdef CONFIG_ARM64_ERRATUM_1742098 @@ -3284,6 +3295,7 @@ void __init setup_cpu_features(void) u32 cwg; setup_system_capabilities(); + user_feature_fixup(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) { diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c index faf88ec9c48e..f63ea915d6ad 100644 --- a/arch/arm64/kernel/jump_label.c +++ b/arch/arm64/kernel/jump_label.c @@ -7,11 +7,12 @@ */ #include #include +#include #include #include -void arch_jump_label_transform(struct jump_entry *entry, - enum jump_label_type type) +bool arch_jump_label_transform_queue(struct jump_entry *entry, + enum jump_label_type type) { void *addr = (void *)jump_entry_code(entry); u32 insn; @@ -25,4 +26,10 @@ void arch_jump_label_transform(struct jump_entry *entry, } aarch64_insn_patch_text_nosync(addr, insn); + return true; +} + +void arch_jump_label_transform_apply(void) +{ + kick_all_cpus_sync(); } diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c index 104101f633b1..492e50a6ddbf 100644 --- a/arch/arm64/kernel/probes/decode-insn.c +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -99,10 +99,6 @@ arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api) aarch64_insn_is_blr(insn) || aarch64_insn_is_ret(insn)) { api->handler = simulate_br_blr_ret; - } else if (aarch64_insn_is_ldr_lit(insn)) { - api->handler = simulate_ldr_literal; - } else if (aarch64_insn_is_ldrsw_lit(insn)) { - api->handler = simulate_ldrsw_literal; } else { /* * Instruction cannot be stepped out-of-line and we don't @@ -140,6 +136,17 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) probe_opcode_t insn = le32_to_cpu(*addr); probe_opcode_t *scan_end = NULL; unsigned long size = 0, offset = 0; + struct arch_probe_insn *api = &asi->api; + + if (aarch64_insn_is_ldr_lit(insn)) { + api->handler = simulate_ldr_literal; + decoded = INSN_GOOD_NO_SLOT; + } else if (aarch64_insn_is_ldrsw_lit(insn)) { + api->handler = simulate_ldrsw_literal; + decoded = INSN_GOOD_NO_SLOT; + } else { + decoded = arm_probe_decode_insn(insn, &asi->api); + } /* * If there's a symbol defined in front of and near enough to @@ -157,7 +164,6 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) else scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; } - decoded = arm_probe_decode_insn(insn, &asi->api); if (decoded != INSN_REJECTED && scan_end) if (is_probed_address_atomic(addr - 1, scan_end)) diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c index 22d0b3252476..b65334ab79d2 100644 --- a/arch/arm64/kernel/probes/simulate-insn.c +++ b/arch/arm64/kernel/probes/simulate-insn.c @@ -171,17 +171,15 @@ simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs) void __kprobes simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) { - u64 *load_addr; + unsigned long load_addr; int xn = opcode & 0x1f; - int disp; - disp = ldr_displacement(opcode); - load_addr = (u64 *) (addr + disp); + load_addr = addr + ldr_displacement(opcode); if (opcode & (1 << 30)) /* x0-x30 */ - set_x_reg(regs, xn, *load_addr); + set_x_reg(regs, xn, READ_ONCE(*(u64 *)load_addr)); else /* w0-w30 */ - set_w_reg(regs, xn, *load_addr); + set_w_reg(regs, xn, READ_ONCE(*(u32 *)load_addr)); instruction_pointer_set(regs, instruction_pointer(regs) + 4); } @@ -189,14 +187,12 @@ simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) void __kprobes simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs) { - s32 *load_addr; + unsigned long load_addr; int xn = opcode & 0x1f; - int disp; - disp = ldr_displacement(opcode); - load_addr = (s32 *) (addr + disp); + load_addr = addr + ldr_displacement(opcode); - set_x_reg(regs, xn, *load_addr); + set_x_reg(regs, xn, READ_ONCE(*(s32 *)load_addr)); instruction_pointer_set(regs, instruction_pointer(regs) + 4); } diff --git a/arch/arm64/kernel/probes/uprobes.c b/arch/arm64/kernel/probes/uprobes.c index d49aef2657cd..a2f137a595fc 100644 --- a/arch/arm64/kernel/probes/uprobes.c +++ b/arch/arm64/kernel/probes/uprobes.c @@ -42,7 +42,7 @@ int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE)) return -EINVAL; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); switch (arm_probe_decode_insn(insn, &auprobe->api)) { case INSN_REJECTED: @@ -108,7 +108,7 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) if (!auprobe->simulate) return false; - insn = *(probe_opcode_t *)(&auprobe->insn[0]); + insn = le32_to_cpu(auprobe->insn); addr = instruction_pointer(regs); if (auprobe->api.handler) diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c index bfce41c2a53b..2df5e43ae4d1 100644 --- a/arch/arm64/kernel/proton-pack.c +++ b/arch/arm64/kernel/proton-pack.c @@ -570,6 +570,18 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void) /* SCTLR_EL1.DSSBS was initialised to 0 during boot */ set_pstate_ssbs(0); + + /* + * SSBS is self-synchronizing and is intended to affect subsequent + * speculative instructions, but some CPUs can speculate with a stale + * value of SSBS. + * + * Mitigate this with an unconditional speculation barrier, as CPUs + * could mis-speculate branches and bypass a conditional barrier. + */ + if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386)) + spec_bar(); + return SPECTRE_MITIGATED; } diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index fea3223704b6..44c4d79bd914 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -360,9 +360,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p) smp_init_cpus(); smp_build_mpidr_hash(); - /* Init percpu seeds for random tags after cpus are set up. */ - kasan_init_sw_tags(); - #ifdef CONFIG_ARM64_SW_TTBR0_PAN /* * Make sure init_thread_info.ttbr0 always generates translation diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index be6f9aca4cd4..ebe51af62469 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -468,6 +468,8 @@ void __init smp_prepare_boot_cpu(void) init_gic_priority_masking(); kasan_init_hw_tags(); + /* Init percpu seeds for random tags after cpus are set up. */ + kasan_init_sw_tags(); } /* diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index de94515fb17c..cf7e10587fb0 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -750,6 +750,9 @@ static int kvm_vcpu_suspend(struct kvm_vcpu *vcpu) static int check_vcpu_requests(struct kvm_vcpu *vcpu) { if (kvm_request_pending(vcpu)) { + if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) + return -EIO; + if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) kvm_vcpu_sleep(vcpu); diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c index ae5f6b5ac80f..f0167dc7438f 100644 --- a/arch/arm64/kvm/hyp/pgtable.c +++ b/arch/arm64/kvm/hyp/pgtable.c @@ -475,7 +475,7 @@ static int hyp_unmap_walker(u64 addr, u64 end, u32 level, kvm_pte_t *ptep, kvm_clear_pte(ptep); dsb(ishst); - __tlbi_level(vae2is, __TLBI_VADDR(addr, 0), level); + __tlbi_level(vae2is, __TLBI_VADDR(addr, 0), 0); } else { if (end - addr < granule) return -EINVAL; @@ -699,8 +699,14 @@ static void stage2_put_pte(kvm_pte_t *ptep, struct kvm_s2_mmu *mmu, u64 addr, * Clear the existing PTE, and perform break-before-make with * TLB maintenance if it was valid. */ - if (kvm_pte_valid(*ptep)) { + kvm_pte_t pte = *ptep; + + if (kvm_pte_valid(pte)) { kvm_clear_pte(ptep); + + if (kvm_pte_table(pte, level)) + level = 0; + kvm_call_hyp(__kvm_tlb_flush_vmid_ipa, mmu, addr, level); } diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 457e74f1f671..974b94ad7952 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -30,6 +30,7 @@ #include #include "sys_regs.h" +#include "vgic/vgic.h" #include "trace.h" @@ -200,6 +201,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu, { bool g1; + if (!kvm_has_gicv3(vcpu->kvm)) { + kvm_inject_undefined(vcpu); + return false; + } + if (!p->is_write) return read_from_write_only(vcpu, p, r); diff --git a/arch/arm64/kvm/vgic/vgic-init.c b/arch/arm64/kvm/vgic/vgic-init.c index 39c24e5ea8cd..059d00c17d26 100644 --- a/arch/arm64/kvm/vgic/vgic-init.c +++ b/arch/arm64/kvm/vgic/vgic-init.c @@ -494,10 +494,10 @@ int kvm_vgic_map_resources(struct kvm *kvm) out: mutex_unlock(&kvm->arch.config_lock); out_slots: - mutex_unlock(&kvm->slots_lock); - if (ret) - kvm_vgic_destroy(kvm); + kvm_vm_dead(kvm); + + mutex_unlock(&kvm->slots_lock); return ret; } diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h index 5fb0bfc07d85..bc898229167b 100644 --- a/arch/arm64/kvm/vgic/vgic.h +++ b/arch/arm64/kvm/vgic/vgic.h @@ -334,4 +334,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm); void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val); int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq); +static inline bool kvm_has_gicv3(struct kvm *kvm) +{ + return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) && + irqchip_in_kernel(kvm) && + kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3); +} + #endif diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps index 2dc7ddee5f04..f5c9a4f5f722 100644 --- a/arch/arm64/tools/cpucaps +++ b/arch/arm64/tools/cpucaps @@ -86,4 +86,5 @@ WORKAROUND_NVIDIA_CARMEL_CNP WORKAROUND_QCOM_FALKOR_E1003 WORKAROUND_REPEAT_TLBI WORKAROUND_SPECULATIVE_AT +WORKAROUND_SPECULATIVE_SSBS WORKAROUND_SPECULATIVE_UNPRIV_LOAD diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig index fa3171f56327..f4ba3638b76a 100644 --- a/arch/loongarch/Kconfig +++ b/arch/loongarch/Kconfig @@ -78,6 +78,7 @@ config LOONGARCH select GENERIC_SCHED_CLOCK select GENERIC_SMP_IDLE_THREAD select GENERIC_TIME_VSYSCALL + select GENERIC_VDSO_TIME_NS select GPIOLIB select HAVE_ARCH_AUDITSYSCALL select HAVE_ARCH_MMAP_RND_BITS if MMU diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig index 3540e9c0a631..15b7420c868b 100644 --- a/arch/loongarch/configs/loongson3_defconfig +++ b/arch/loongarch/configs/loongson3_defconfig @@ -82,7 +82,6 @@ CONFIG_ZSWAP=y CONFIG_ZSWAP_COMPRESSOR_DEFAULT_ZSTD=y CONFIG_ZPOOL=y CONFIG_ZBUD=y -CONFIG_Z3FOLD=y CONFIG_ZSMALLOC=m CONFIG_NET=y CONFIG_PACKET=y diff --git a/arch/loongarch/include/asm/bootinfo.h b/arch/loongarch/include/asm/bootinfo.h index ed0910e8b856..e703615ca706 100644 --- a/arch/loongarch/include/asm/bootinfo.h +++ b/arch/loongarch/include/asm/bootinfo.h @@ -25,6 +25,10 @@ struct loongson_board_info { const char *board_vendor; }; +/* + * The "core" of cores_per_node and cores_per_package stands for a + * logical core, which means in a SMT system it stands for a thread. + */ struct loongson_system_configuration { int nr_cpus; int nr_nodes; diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h deleted file mode 100644 index 75ccd808a2af..000000000000 --- a/arch/loongarch/include/asm/dma-direct.h +++ /dev/null @@ -1,11 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Copyright (C) 2020-2022 Loongson Technology Corporation Limited - */ -#ifndef _LOONGARCH_DMA_DIRECT_H -#define _LOONGARCH_DMA_DIRECT_H - -dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr); -phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr); - -#endif /* _LOONGARCH_DMA_DIRECT_H */ diff --git a/arch/loongarch/include/asm/hw_irq.h b/arch/loongarch/include/asm/hw_irq.h index af4f4e8fbd85..8156ffb67415 100644 --- a/arch/loongarch/include/asm/hw_irq.h +++ b/arch/loongarch/include/asm/hw_irq.h @@ -9,6 +9,8 @@ extern atomic_t irq_err_count; +#define ARCH_IRQ_INIT_FLAGS IRQ_NOPROBE + /* * interrupt-retrigger: NOP for now. This may not be appropriate for all * machines, we'll see ... diff --git a/arch/loongarch/include/asm/page.h b/arch/loongarch/include/asm/page.h index 53f284a96182..bbac81dd7378 100644 --- a/arch/loongarch/include/asm/page.h +++ b/arch/loongarch/include/asm/page.h @@ -81,6 +81,7 @@ typedef struct { unsigned long pgprot; } pgprot_t; #define __va(x) ((void *)((unsigned long)(x) + PAGE_OFFSET - PHYS_OFFSET)) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) +#define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) #ifdef CONFIG_FLATMEM diff --git a/arch/loongarch/include/asm/vdso/gettimeofday.h b/arch/loongarch/include/asm/vdso/gettimeofday.h index 7b2cd37641e2..89e6b222c2f2 100644 --- a/arch/loongarch/include/asm/vdso/gettimeofday.h +++ b/arch/loongarch/include/asm/vdso/gettimeofday.h @@ -91,9 +91,16 @@ static inline bool loongarch_vdso_hres_capable(void) static __always_inline const struct vdso_data *__arch_get_vdso_data(void) { - return get_vdso_data(); + return (const struct vdso_data *)get_vdso_data(); } +#ifdef CONFIG_TIME_NS +static __always_inline +const struct vdso_data *__arch_get_timens_vdso_data(const struct vdso_data *vd) +{ + return (const struct vdso_data *)(get_vdso_data() + VVAR_TIMENS_PAGE_OFFSET * PAGE_SIZE); +} +#endif #endif /* !__ASSEMBLY__ */ #endif /* __ASM_VDSO_GETTIMEOFDAY_H */ diff --git a/arch/loongarch/include/asm/vdso/vdso.h b/arch/loongarch/include/asm/vdso/vdso.h index 3b55d32a0619..5a12309d9fb5 100644 --- a/arch/loongarch/include/asm/vdso/vdso.h +++ b/arch/loongarch/include/asm/vdso/vdso.h @@ -16,10 +16,33 @@ struct vdso_pcpu_data { struct loongarch_vdso_data { struct vdso_pcpu_data pdata[NR_CPUS]; - struct vdso_data data[CS_BASES]; /* Arch-independent data */ }; -#define VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data)) +/* + * The layout of vvar: + * + * high + * +---------------------+--------------------------+ + * | loongarch vdso data | LOONGARCH_VDSO_DATA_SIZE | + * +---------------------+--------------------------+ + * | time-ns vdso data | PAGE_SIZE | + * +---------------------+--------------------------+ + * | generic vdso data | PAGE_SIZE | + * +---------------------+--------------------------+ + * low + */ +#define LOONGARCH_VDSO_DATA_SIZE PAGE_ALIGN(sizeof(struct loongarch_vdso_data)) +#define LOONGARCH_VDSO_DATA_PAGES (LOONGARCH_VDSO_DATA_SIZE >> PAGE_SHIFT) + +enum vvar_pages { + VVAR_GENERIC_PAGE_OFFSET, + VVAR_TIMENS_PAGE_OFFSET, + VVAR_LOONGARCH_PAGES_START, + VVAR_LOONGARCH_PAGES_END = VVAR_LOONGARCH_PAGES_START + LOONGARCH_VDSO_DATA_PAGES - 1, + VVAR_NR_PAGES, +}; + +#define VVAR_SIZE (VVAR_NR_PAGES << PAGE_SHIFT) static inline unsigned long get_vdso_base(void) { @@ -34,10 +57,9 @@ static inline unsigned long get_vdso_base(void) return addr; } -static inline const struct vdso_data *get_vdso_data(void) +static inline unsigned long get_vdso_data(void) { - return (const struct vdso_data *)(get_vdso_base() - - VDSO_DATA_SIZE + SMP_CACHE_BYTES * NR_CPUS); + return get_vdso_base() - VVAR_SIZE; } #endif /* __ASSEMBLY__ */ diff --git a/arch/loongarch/include/uapi/asm/unistd.h b/arch/loongarch/include/uapi/asm/unistd.h index fcb668984f03..b344b1f91715 100644 --- a/arch/loongarch/include/uapi/asm/unistd.h +++ b/arch/loongarch/include/uapi/asm/unistd.h @@ -1,4 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#define __ARCH_WANT_NEW_STAT #define __ARCH_WANT_SYS_CLONE #define __ARCH_WANT_SYS_CLONE3 diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c index 0524bf1169b7..4496649c9e68 100644 --- a/arch/loongarch/kernel/irq.c +++ b/arch/loongarch/kernel/irq.c @@ -122,9 +122,6 @@ void __init init_IRQ(void) panic("IPI IRQ request failed\n"); #endif - for (i = 0; i < NR_IRQS; i++) - irq_set_noprobe(i); - for_each_possible_cpu(i) { page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order); diff --git a/arch/loongarch/kernel/process.c b/arch/loongarch/kernel/process.c index 1259bc312979..4561bc81c063 100644 --- a/arch/loongarch/kernel/process.c +++ b/arch/loongarch/kernel/process.c @@ -271,13 +271,15 @@ unsigned long stack_top(void) { unsigned long top = TASK_SIZE & PAGE_MASK; - /* Space for the VDSO & data page */ - top -= PAGE_ALIGN(current->thread.vdso->size); - top -= PAGE_SIZE; + if (current->thread.vdso) { + /* Space for the VDSO & data page */ + top -= PAGE_ALIGN(current->thread.vdso->size); + top -= VVAR_SIZE; - /* Space to randomize the VDSO base */ - if (current->flags & PF_RANDOMIZE) - top -= VDSO_RANDOMIZE_SIZE; + /* Space to randomize the VDSO base */ + if (current->flags & PF_RANDOMIZE) + top -= VDSO_RANDOMIZE_SIZE; + } return top; } diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c index ae436def7ee9..b00e885d9845 100644 --- a/arch/loongarch/kernel/setup.c +++ b/arch/loongarch/kernel/setup.c @@ -49,6 +49,7 @@ #define SMBIOS_FREQHIGH_OFFSET 0x17 #define SMBIOS_FREQLOW_MASK 0xFF #define SMBIOS_CORE_PACKAGE_OFFSET 0x23 +#define SMBIOS_THREAD_PACKAGE_OFFSET 0x25 #define LOONGSON_EFI_ENABLE (1 << 3) struct screen_info screen_info __section(".data"); @@ -115,7 +116,7 @@ static void __init parse_cpu_table(const struct dmi_header *dm) cpu_clock_freq = freq_temp * 1000000; loongson_sysconf.cpuname = (void *)dmi_string_parse(dm, dmi_data[16]); - loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_CORE_PACKAGE_OFFSET); + loongson_sysconf.cores_per_package = *(dmi_data + SMBIOS_THREAD_PACKAGE_OFFSET); pr_info("CpuClock = %llu\n", cpu_clock_freq); } diff --git a/arch/loongarch/kernel/vdso.c b/arch/loongarch/kernel/vdso.c index 8c9826062652..59aa9dd466e8 100644 --- a/arch/loongarch/kernel/vdso.c +++ b/arch/loongarch/kernel/vdso.c @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -26,12 +27,17 @@ extern char vdso_start[], vdso_end[]; /* Kernel-provided data used by the VDSO. */ static union { - u8 page[VDSO_DATA_SIZE]; + u8 page[PAGE_SIZE]; + struct vdso_data data[CS_BASES]; +} generic_vdso_data __page_aligned_data; + +static union { + u8 page[LOONGARCH_VDSO_DATA_SIZE]; struct loongarch_vdso_data vdata; } loongarch_vdso_data __page_aligned_data; static struct page *vdso_pages[] = { NULL }; -struct vdso_data *vdso_data = loongarch_vdso_data.vdata.data; +struct vdso_data *vdso_data = generic_vdso_data.data; struct vdso_pcpu_data *vdso_pdata = loongarch_vdso_data.vdata.pdata; static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struct *new_vma) @@ -41,6 +47,43 @@ static int vdso_mremap(const struct vm_special_mapping *sm, struct vm_area_struc return 0; } +static vm_fault_t vvar_fault(const struct vm_special_mapping *sm, + struct vm_area_struct *vma, struct vm_fault *vmf) +{ + unsigned long pfn; + struct page *timens_page = find_timens_vvar_page(vma); + + switch (vmf->pgoff) { + case VVAR_GENERIC_PAGE_OFFSET: + if (!timens_page) + pfn = sym_to_pfn(vdso_data); + else + pfn = page_to_pfn(timens_page); + break; +#ifdef CONFIG_TIME_NS + case VVAR_TIMENS_PAGE_OFFSET: + /* + * If a task belongs to a time namespace then a namespace specific + * VVAR is mapped with the VVAR_GENERIC_PAGE_OFFSET and the real + * VVAR page is mapped with the VVAR_TIMENS_PAGE_OFFSET offset. + * See also the comment near timens_setup_vdso_data(). + */ + if (!timens_page) + return VM_FAULT_SIGBUS; + else + pfn = sym_to_pfn(vdso_data); + break; +#endif /* CONFIG_TIME_NS */ + case VVAR_LOONGARCH_PAGES_START ... VVAR_LOONGARCH_PAGES_END: + pfn = sym_to_pfn(&loongarch_vdso_data) + vmf->pgoff - VVAR_LOONGARCH_PAGES_START; + break; + default: + return VM_FAULT_SIGBUS; + } + + return vmf_insert_pfn(vma, vmf->address, pfn); +} + struct loongarch_vdso_info vdso_info = { .vdso = vdso_start, .size = PAGE_SIZE, @@ -51,6 +94,7 @@ struct loongarch_vdso_info vdso_info = { }, .data_mapping = { .name = "[vvar]", + .fault = vvar_fault, }, .offset_sigreturn = vdso_offset_sigreturn, }; @@ -73,6 +117,37 @@ static int __init init_vdso(void) } subsys_initcall(init_vdso); +#ifdef CONFIG_TIME_NS +struct vdso_data *arch_get_vdso_data(void *vvar_page) +{ + return (struct vdso_data *)(vvar_page); +} + +/* + * The vvar mapping contains data for a specific time namespace, so when a + * task changes namespace we must unmap its vvar data for the old namespace. + * Subsequent faults will map in data for the new namespace. + * + * For more details see timens_setup_vdso_data(). + */ +int vdso_join_timens(struct task_struct *task, struct time_namespace *ns) +{ + struct mm_struct *mm = task->mm; + struct vm_area_struct *vma; + + VMA_ITERATOR(vmi, mm, 0); + + mmap_read_lock(mm); + for_each_vma(vmi, vma) { + if (vma_is_special_mapping(vma, &vdso_info.data_mapping)) + zap_vma_pages(vma); + } + mmap_read_unlock(mm); + + return 0; +} +#endif + static unsigned long vdso_base(void) { unsigned long base = STACK_TOP; @@ -88,7 +163,7 @@ static unsigned long vdso_base(void) int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) { int ret; - unsigned long vvar_size, size, data_addr, vdso_addr; + unsigned long size, data_addr, vdso_addr; struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct loongarch_vdso_info *info = current->thread.vdso; @@ -100,32 +175,23 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) * Determine total area size. This includes the VDSO data itself * and the data pages. */ - vvar_size = VDSO_DATA_SIZE; - size = vvar_size + info->size; + size = VVAR_SIZE + info->size; data_addr = get_unmapped_area(NULL, vdso_base(), size, 0, 0); if (IS_ERR_VALUE(data_addr)) { ret = data_addr; goto out; } - vdso_addr = data_addr + VDSO_DATA_SIZE; - vma = _install_special_mapping(mm, data_addr, vvar_size, - VM_READ | VM_MAYREAD, + vma = _install_special_mapping(mm, data_addr, VVAR_SIZE, + VM_READ | VM_MAYREAD | VM_PFNMAP, &info->data_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto out; } - /* Map VDSO data page. */ - ret = remap_pfn_range(vma, data_addr, - virt_to_phys(&loongarch_vdso_data) >> PAGE_SHIFT, - vvar_size, PAGE_READONLY); - if (ret) - goto out; - - /* Map VDSO code page. */ + vdso_addr = data_addr + VVAR_SIZE; vma = _install_special_mapping(mm, vdso_addr, info->size, VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, &info->code_mapping); diff --git a/arch/loongarch/pci/acpi.c b/arch/loongarch/pci/acpi.c index 8235ec92b41f..debd79f71286 100644 --- a/arch/loongarch/pci/acpi.c +++ b/arch/loongarch/pci/acpi.c @@ -222,6 +222,7 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) if (bus) { memcpy(bus->sysdata, info->cfg, sizeof(struct pci_config_window)); kfree(info); + kfree(root_ops); } else { struct pci_bus *child; diff --git a/arch/loongarch/vdso/vgetcpu.c b/arch/loongarch/vdso/vgetcpu.c index e02e775f5360..9e445be39763 100644 --- a/arch/loongarch/vdso/vgetcpu.c +++ b/arch/loongarch/vdso/vgetcpu.c @@ -21,7 +21,7 @@ static __always_inline int read_cpu_id(void) static __always_inline const struct vdso_pcpu_data *get_pcpu_data(void) { - return (struct vdso_pcpu_data *)(get_vdso_base() - VDSO_DATA_SIZE); + return (struct vdso_pcpu_data *)(get_vdso_data() + VVAR_LOONGARCH_PAGES_START * PAGE_SIZE); } extern diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c index 3137b45750df..b7cb28f5ee29 100644 --- a/arch/m68k/amiga/config.c +++ b/arch/m68k/amiga/config.c @@ -180,6 +180,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record) dev->slotsize = be16_to_cpu(cd->cd_SlotSize); dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr); dev->boardsize = be32_to_cpu(cd->cd_BoardSize); + + /* CS-LAB Warp 1260 workaround */ + if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) && + dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) { + + /* turn off all interrupts */ + pr_info("Warp 1260 card detected: applying interrupt storm workaround\n"); + *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff; + } } else pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n"); #endif /* CONFIG_ZORRO */ diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c index 56f02ea2c248..715d1e0d973e 100644 --- a/arch/m68k/atari/ataints.c +++ b/arch/m68k/atari/ataints.c @@ -302,11 +302,7 @@ void __init atari_init_IRQ(void) if (ATARIHW_PRESENT(SCU)) { /* init the SCU if present */ - tt_scu.sys_mask = 0x10; /* enable VBL (for the cursor) and - * disable HSYNC interrupts (who - * needs them?) MFP and SCC are - * enabled in VME mask - */ + tt_scu.sys_mask = 0x0; /* disable all interrupts */ tt_scu.vme_mask = 0x60; /* enable MFP and SCC ints */ } else { /* If no SCU and no Hades, the HSYNC interrupt needs to be diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h index 6cf464cdab06..694a44a5c3b0 100644 --- a/arch/m68k/include/asm/cmpxchg.h +++ b/arch/m68k/include/asm/cmpxchg.h @@ -32,7 +32,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz x = tmp; break; default: - tmp = __invalid_xchg_size(x, ptr, size); + x = __invalid_xchg_size(x, ptr, size); break; } diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c index 2cb4a61bcfac..81347e7704c5 100644 --- a/arch/m68k/kernel/process.c +++ b/arch/m68k/kernel/process.c @@ -115,7 +115,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs) { /* regs will be equal to current_pt_regs() */ struct kernel_clone_args args = { - .flags = regs->d1 & ~CSIGNAL, + .flags = (u32)(regs->d1) & ~CSIGNAL, .pidfd = (int __user *)regs->d3, .child_tid = (int __user *)regs->d4, .parent_tid = (int __user *)regs->d3, diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 353fabdfcbc5..2a3248194d50 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -193,11 +193,6 @@ asmlinkage void __init mmu_init(void) { unsigned int kstart, ksize; - if (!memblock.reserved.cnt) { - pr_emerg("Error memory count\n"); - machine_restart(NULL); - } - if ((u32) memblock.memory.regions[0].size < 0x400000) { pr_emerg("Memory must be greater than 4MB\n"); machine_restart(NULL); diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi index c16b521308cb..cc7747c5f21f 100644 --- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi +++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi @@ -23,14 +23,6 @@ }; }; - memory@200000 { - compatible = "memory"; - device_type = "memory"; - reg = <0x00000000 0x00200000 0x00000000 0x0ee00000>, /* 238 MB at 2 MB */ - <0x00000000 0x20000000 0x00000000 0x1f000000>, /* 496 MB at 512 MB */ - <0x00000001 0x10000000 0x00000001 0xb0000000>; /* 6912 MB at 4352MB */ - }; - cpu_clk: cpu_clk { #clock-cells = <0>; compatible = "fixed-clock"; @@ -52,6 +44,13 @@ 0 0x40000000 0 0x40000000 0 0x40000000 0xfe 0x00000000 0xfe 0x00000000 0 0x40000000>; + isa@18000000 { + compatible = "isa"; + #size-cells = <1>; + #address-cells = <2>; + ranges = <1 0x0 0x0 0x18000000 0x4000>; + }; + pm: reset-controller@1fe07000 { compatible = "loongson,ls2k-pm"; reg = <0 0x1fe07000 0 0x422>; @@ -97,12 +96,19 @@ <0x00000000>; /* int3 */ }; + rtc0: rtc@1fe07800 { + compatible = "loongson,ls2k1000-rtc"; + reg = <0 0x1fe07800 0 0x78>; + interrupt-parent = <&liointc1>; + interrupts = <8 IRQ_TYPE_LEVEL_HIGH>; + }; + uart0: serial@1fe00000 { compatible = "ns16550a"; reg = <0 0x1fe00000 0 0x8>; clock-frequency = <125000000>; interrupt-parent = <&liointc0>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; no-loopback-test; }; @@ -111,7 +117,6 @@ device_type = "pci"; #address-cells = <3>; #size-cells = <2>; - #interrupt-cells = <2>; reg = <0 0x1a000000 0 0x02000000>, <0xfe 0x00000000 0 0x20000000>; @@ -126,11 +131,12 @@ "pciclass0c03"; reg = <0x1800 0x0 0x0 0x0 0x0>; - interrupts = <12 IRQ_TYPE_LEVEL_LOW>, - <13 IRQ_TYPE_LEVEL_LOW>; + interrupts = <12 IRQ_TYPE_LEVEL_HIGH>, + <13 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; mdio { #address-cells = <1>; #size-cells = <0>; @@ -149,11 +155,12 @@ "loongson, pci-gmac"; reg = <0x1900 0x0 0x0 0x0 0x0>; - interrupts = <14 IRQ_TYPE_LEVEL_LOW>, - <15 IRQ_TYPE_LEVEL_LOW>; + interrupts = <14 IRQ_TYPE_LEVEL_HIGH>, + <15 IRQ_TYPE_LEVEL_HIGH>; interrupt-names = "macirq", "eth_lpi"; interrupt-parent = <&liointc0>; - phy-mode = "rgmii"; + phy-mode = "rgmii-id"; + phy-handle = <&phy1>; mdio { #address-cells = <1>; #size-cells = <0>; @@ -171,7 +178,7 @@ "pciclass0c03"; reg = <0x2100 0x0 0x0 0x0 0x0>; - interrupts = <18 IRQ_TYPE_LEVEL_LOW>; + interrupts = <18 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -182,7 +189,7 @@ "pciclass0c03"; reg = <0x2200 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; }; @@ -193,97 +200,121 @@ "pciclass0106"; reg = <0x4000 0x0 0x0 0x0 0x0>; - interrupts = <19 IRQ_TYPE_LEVEL_LOW>; + interrupts = <19 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc0>; }; - pci_bridge@9,0 { + pcie@9,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x4800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <0 IRQ_TYPE_LEVEL_LOW>; + interrupts = <0 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@a,0 { + pcie@a,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <1 IRQ_TYPE_LEVEL_LOW>; + interrupts = <1 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@b,0 { + pcie@b,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x5800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <2 IRQ_TYPE_LEVEL_LOW>; + interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@c,0 { + pcie@c,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x6000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <3 IRQ_TYPE_LEVEL_LOW>; + interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@d,0 { + pcie@d,0 { compatible = "pci0014,7a19.0", "pci0014,7a19", "pciclass060400", "pciclass0604"; reg = <0x6800 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <4 IRQ_TYPE_LEVEL_LOW>; + interrupts = <4 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; - pci_bridge@e,0 { + pcie@e,0 { compatible = "pci0014,7a09.0", "pci0014,7a09", "pciclass060400", "pciclass0604"; reg = <0x7000 0x0 0x0 0x0 0x0>; + #address-cells = <3>; + #size-cells = <2>; + device_type = "pci"; #interrupt-cells = <1>; - interrupts = <5 IRQ_TYPE_LEVEL_LOW>; + interrupts = <5 IRQ_TYPE_LEVEL_HIGH>; interrupt-parent = <&liointc1>; interrupt-map-mask = <0 0 0 0>; - interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_LOW>; + interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>; + ranges; external-facing; }; diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h index e007edd6b60a..9218b3ae3383 100644 --- a/arch/mips/include/asm/mach-loongson64/boot_param.h +++ b/arch/mips/include/asm/mach-loongson64/boot_param.h @@ -42,12 +42,14 @@ enum loongson_cpu_type { Legacy_1B = 0x5, Legacy_2G = 0x6, Legacy_2H = 0x7, + Legacy_2K = 0x8, Loongson_1A = 0x100, Loongson_1B = 0x101, Loongson_2E = 0x200, Loongson_2F = 0x201, Loongson_2G = 0x202, Loongson_2H = 0x203, + Loongson_2K = 0x204, Loongson_3A = 0x300, Loongson_3B = 0x301 }; diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h index 23c67c0871b1..696b40beb774 100644 --- a/arch/mips/include/asm/mips-cm.h +++ b/arch/mips/include/asm/mips-cm.h @@ -228,6 +228,10 @@ GCR_ACCESSOR_RO(32, 0x0d0, gic_status) GCR_ACCESSOR_RO(32, 0x0f0, cpc_status) #define CM_GCR_CPC_STATUS_EX BIT(0) +/* GCR_ACCESS - Controls core/IOCU access to GCRs */ +GCR_ACCESSOR_RW(32, 0x120, access_cm3) +#define CM_GCR_ACCESS_ACCESSEN GENMASK(7, 0) + /* GCR_L2_CONFIG - Indicates L2 cache configuration when Config5.L2C=1 */ GCR_ACCESSOR_RW(32, 0x130, l2_config) #define CM_GCR_L2_CONFIG_BYPASS BIT(20) diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c index 32ec67c9ab67..77028aa8c107 100644 --- a/arch/mips/kernel/cevt-r4k.c +++ b/arch/mips/kernel/cevt-r4k.c @@ -303,13 +303,6 @@ int r4k_clockevent_init(void) if (!c0_compare_int_usable()) return -ENXIO; - /* - * With vectored interrupts things are getting platform specific. - * get_c0_compare_int is a hook to allow a platform to return the - * interrupt number of its liking. - */ - irq = get_c0_compare_int(); - cd = &per_cpu(mips_clockevent_device, cpu); cd->name = "MIPS"; @@ -320,7 +313,6 @@ int r4k_clockevent_init(void) min_delta = calculate_min_delta(); cd->rating = 300; - cd->irq = irq; cd->cpumask = cpumask_of(cpu); cd->set_next_event = mips_next_event; cd->event_handler = mips_event_handler; @@ -332,6 +324,13 @@ int r4k_clockevent_init(void) cp0_timer_irq_installed = 1; + /* + * With vectored interrupts things are getting platform specific. + * get_c0_compare_int is a hook to allow a platform to return the + * interrupt number of its liking. + */ + irq = get_c0_compare_int(); + if (request_irq(irq, c0_compare_interrupt, flags, "timer", c0_compare_interrupt)) pr_err("Failed to request irq %d (timer)\n", irq); diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c index 482af80b8179..fdf00c228b67 100644 --- a/arch/mips/kernel/cpu-probe.c +++ b/arch/mips/kernel/cpu-probe.c @@ -1723,12 +1723,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu) c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM | MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2); c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */ + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; case PRID_IMP_LOONGSON_64G: __cpu_name[cpu] = "ICT Loongson-3"; set_elf_platform(cpu, "loongson3a"); set_isa(c, MIPS_CPU_ISA_M64R2); decode_cpucfg(c); + change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER, + LOONGSON_CONF6_INTIMER); break; default: panic("Unknown Loongson Processor ID!"); diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c index bcd6a944b839..739997e6fd65 100644 --- a/arch/mips/kernel/smp-cps.c +++ b/arch/mips/kernel/smp-cps.c @@ -230,7 +230,10 @@ static void boot_core(unsigned int core, unsigned int vpe_id) write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB); /* Ensure the core can access the GCRs */ - set_gcr_access(1 << core); + if (mips_cm_revision() < CM_REV_CM3) + set_gcr_access(1 << core); + else + set_gcr_access_cm3(1 << core); if (mips_cpc_present()) { /* Reset the core */ diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 7ab572040f53..20a6434f5636 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -27,7 +27,7 @@ 17 o32 break sys_ni_syscall # 18 was sys_stat 18 o32 unused18 sys_ni_syscall -19 o32 lseek sys_lseek +19 o32 lseek sys_lseek compat_sys_lseek 20 o32 getpid sys_getpid 21 o32 mount sys_mount 22 o32 umount sys_oldumount diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c index ef3750a6ffac..09ff05269861 100644 --- a/arch/mips/loongson64/env.c +++ b/arch/mips/loongson64/env.c @@ -88,6 +88,12 @@ void __init prom_lefi_init_env(void) cpu_clock_freq = ecpu->cpu_clock_freq; loongson_sysconf.cputype = ecpu->cputype; switch (ecpu->cputype) { + case Legacy_2K: + case Loongson_2K: + smp_group[0] = 0x900000001fe11000; + loongson_sysconf.cores_per_node = 2; + loongson_sysconf.cores_per_package = 2; + break; case Legacy_3A: case Loongson_3A: loongson_sysconf.cores_per_node = 4; @@ -221,6 +227,8 @@ void __init prom_lefi_init_env(void) default: break; } + } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64R) { + loongson_fdt_blob = __dtb_loongson64_2core_2k1000_begin; } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G) { if (loongson_sysconf.bridgetype == LS7A) loongson_fdt_blob = __dtb_loongson64g_4core_ls7a_begin; diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c index e420800043b0..2a8e4cd72605 100644 --- a/arch/mips/loongson64/reset.c +++ b/arch/mips/loongson64/reset.c @@ -11,6 +11,7 @@ #include #include #include +#include #include #include @@ -21,36 +22,21 @@ #include #include -static void loongson_restart(char *command) +static int firmware_restart(struct sys_off_data *unusedd) { void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr; fw_restart(); - while (1) { - if (cpu_wait) - cpu_wait(); - } + return NOTIFY_DONE; } -static void loongson_poweroff(void) +static int firmware_poweroff(struct sys_off_data *unused) { void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr; fw_poweroff(); - while (1) { - if (cpu_wait) - cpu_wait(); - } -} - -static void loongson_halt(void) -{ - pr_notice("\n\n** You can safely turn off the power now **\n\n"); - while (1) { - if (cpu_wait) - cpu_wait(); - } + return NOTIFY_DONE; } #ifdef CONFIG_KEXEC @@ -154,9 +140,17 @@ static void loongson_crash_shutdown(struct pt_regs *regs) static int __init mips_reboot_setup(void) { - _machine_restart = loongson_restart; - _machine_halt = loongson_halt; - pm_power_off = loongson_poweroff; + if (loongson_sysconf.restart_addr) { + register_sys_off_handler(SYS_OFF_MODE_RESTART, + SYS_OFF_PRIO_FIRMWARE, + firmware_restart, NULL); + } + + if (loongson_sysconf.poweroff_addr) { + register_sys_off_handler(SYS_OFF_MODE_POWER_OFF, + SYS_OFF_PRIO_FIRMWARE, + firmware_poweroff, NULL); + } #ifdef CONFIG_KEXEC kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL); diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c index 660e1de4412a..52dc95995783 100644 --- a/arch/mips/loongson64/smp.c +++ b/arch/mips/loongson64/smp.c @@ -479,12 +479,25 @@ static void loongson3_smp_finish(void) static void __init loongson3_smp_setup(void) { int i = 0, num = 0; /* i: physical id, num: logical id */ + int max_cpus = 0; init_cpu_possible(cpu_none_mask); + for (i = 0; i < ARRAY_SIZE(smp_group); i++) { + if (!smp_group[i]) + break; + max_cpus += loongson_sysconf.cores_per_node; + } + + if (max_cpus < loongson_sysconf.nr_cpus) { + pr_err("SMP Groups are less than the number of CPUs\n"); + loongson_sysconf.nr_cpus = max_cpus ? max_cpus : 1; + } + /* For unified kernel, NR_CPUS is the maximum possible value, * loongson_sysconf.nr_cpus is the really present value */ + i = 0; while (i < loongson_sysconf.nr_cpus) { if (loongson_sysconf.reserved_cpus_mask & (1< +#include #include diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index 0cd04d936a7a..f2fe45d3094d 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -270,6 +270,9 @@ void calibrate_delay(void) void __init setup_arch(char **cmdline_p) { + /* setup memblock allocator */ + setup_memory(); + unflatten_and_copy_device_tree(); setup_cpuinfo(); @@ -293,9 +296,6 @@ void __init setup_arch(char **cmdline_p) } #endif - /* setup memblock allocator */ - setup_memory(); - /* paging_init() sets up the MMU and marks all pages as reserved */ paging_init(); diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 5762633ea95e..3341d4a42199 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -75,6 +75,7 @@ config PARISC select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS select TRACE_IRQFLAGS_SUPPORT select HAVE_FUNCTION_DESCRIPTORS if 64BIT + select PCI_MSI_ARCH_FALLBACKS if PCI_MSI help The PA-RISC microprocessor is designed by Hewlett-Packard and used diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S index 335887673c65..1ff54f4dbedb 100644 --- a/arch/parisc/kernel/entry.S +++ b/arch/parisc/kernel/entry.S @@ -1038,8 +1038,7 @@ ENTRY_CFI(intr_save) /* for os_hpmc */ STREG %r16, PT_ISR(%r29) STREG %r17, PT_IOR(%r29) -#if 0 && defined(CONFIG_64BIT) - /* Revisit when we have 64-bit code above 4Gb */ +#if defined(CONFIG_64BIT) b,n intr_save2 skip_save_ior: @@ -1047,8 +1046,7 @@ skip_save_ior: * need to adjust iasq/iaoq here in the same way we adjusted isr/ior * above. */ - extrd,u,* %r8,PSW_W_BIT,1,%r1 - cmpib,COND(=),n 1,%r1,intr_save2 + bb,COND(>=),n %r8,PSW_W_BIT,intr_save2 LDREG PT_IASQ0(%r29), %r16 LDREG PT_IAOQ0(%r29), %r17 /* adjust iasq/iaoq */ diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c index 9ddb2e397058..b481cde6bfb6 100644 --- a/arch/parisc/kernel/irq.c +++ b/arch/parisc/kernel/irq.c @@ -501,7 +501,7 @@ void do_cpu_irq_mask(struct pt_regs *regs) old_regs = set_irq_regs(regs); local_irq_disable(); - irq_enter(); + irq_enter_rcu(); eirr_val = mfctl(23) & cpu_eiem & per_cpu(local_ack_eiem, cpu); if (!eirr_val) @@ -536,7 +536,7 @@ void do_cpu_irq_mask(struct pt_regs *regs) #endif /* CONFIG_IRQSTACKS */ out: - irq_exit(); + irq_exit_rcu(); set_irq_regs(old_regs); return; diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S index 1373e5129868..f0f49ca70362 100644 --- a/arch/parisc/kernel/syscall.S +++ b/arch/parisc/kernel/syscall.S @@ -232,10 +232,10 @@ linux_gateway_entry: #ifdef CONFIG_64BIT ldil L%sys_call_table, %r1 - or,= %r2,%r2,%r2 - addil L%(sys_call_table64-sys_call_table), %r1 + or,ev %r2,%r2,%r2 + ldil L%sys_call_table64, %r1 ldo R%sys_call_table(%r1), %r19 - or,= %r2,%r2,%r2 + or,ev %r2,%r2,%r2 ldo R%sys_call_table64(%r1), %r19 #else load32 sys_call_table, %r19 @@ -368,10 +368,10 @@ tracesys_next: extrd,u %r19,63,1,%r2 /* W hidden in bottom bit */ ldil L%sys_call_table, %r1 - or,= %r2,%r2,%r2 - addil L%(sys_call_table64-sys_call_table), %r1 + or,ev %r2,%r2,%r2 + ldil L%sys_call_table64, %r1 ldo R%sys_call_table(%r1), %r19 - or,= %r2,%r2,%r2 + or,ev %r2,%r2,%r2 ldo R%sys_call_table64(%r1), %r19 #else load32 sys_call_table, %r19 @@ -1310,6 +1310,8 @@ ENTRY(sys_call_table) END(sys_call_table) #ifdef CONFIG_64BIT +#undef __SYSCALL_WITH_COMPAT +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) .align 8 ENTRY(sys_call_table64) #include /* 64-bit syscalls */ diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 6050e6e10d32..46ae22cd8bcc 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -1,6 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 source "arch/powerpc/platforms/Kconfig.cputype" +config CC_HAS_ELFV2 + def_bool PPC64 && $(cc-option, -mabi=elfv2) + +config CC_HAS_PREFIXED + def_bool PPC64 && $(cc-option, -mcpu=power10 -mprefixed) + config 32BIT bool default y if PPC32 @@ -583,6 +589,23 @@ config KEXEC_FILE config ARCH_HAS_KEXEC_PURGATORY def_bool KEXEC_FILE +config PPC64_BIG_ENDIAN_ELF_ABI_V2 + bool "Build big-endian kernel using ELF ABI V2 (EXPERIMENTAL)" + depends on PPC64 && CPU_BIG_ENDIAN + depends on CC_HAS_ELFV2 + depends on LD_VERSION >= 22400 || LLD_VERSION >= 150000 + help + This builds the kernel image using the "Power Architecture 64-Bit ELF + V2 ABI Specification", which has a reduced stack overhead and faster + function calls. This internal kernel ABI option does not affect + userspace compatibility. + + The V2 ABI is standard for 64-bit little-endian, but for big-endian + it is less well tested by kernel and toolchain. However some distros + build userspace this way, and it can produce a functioning kernel. + + This requires GCC and binutils 2.24 or newer. + config RELOCATABLE bool "Build a relocatable kernel" depends on PPC64 || (FLATMEM && (44x || PPC_85xx)) diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile index 487e4967b60d..d7332c6afeaa 100644 --- a/arch/powerpc/Makefile +++ b/arch/powerpc/Makefile @@ -176,7 +176,11 @@ ifdef CONFIG_476FPE_ERR46 endif # No prefix or pcrel +ifdef CONFIG_PPC_KERNEL_PREFIXED +KBUILD_CFLAGS += $(call cc-option,-mprefixed) +else KBUILD_CFLAGS += $(call cc-option,-mno-prefixed) +endif KBUILD_CFLAGS += $(call cc-option,-mno-pcrel) # No AltiVec or VSX or MMA instructions when building kernel diff --git a/arch/powerpc/boot/simple_alloc.c b/arch/powerpc/boot/simple_alloc.c index 267d6524caac..d07796fdf91a 100644 --- a/arch/powerpc/boot/simple_alloc.c +++ b/arch/powerpc/boot/simple_alloc.c @@ -112,8 +112,11 @@ static void *simple_realloc(void *ptr, unsigned long size) return ptr; new = simple_malloc(size); - memcpy(new, ptr, p->size); - simple_free(ptr); + if (new) { + memcpy(new, ptr, p->size); + simple_free(ptr); + } + return new; } diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config index 524db76f47b7..8aff83217397 100644 --- a/arch/powerpc/configs/85xx-hw.config +++ b/arch/powerpc/configs/85xx-hw.config @@ -24,6 +24,7 @@ CONFIG_FS_ENET=y CONFIG_FSL_CORENET_CF=y CONFIG_FSL_DMA=y CONFIG_FSL_HV_MANAGER=y +CONFIG_FSL_IFC=y CONFIG_FSL_PQ_MDIO=y CONFIG_FSL_RIO=y CONFIG_FSL_XGMAC_MDIO=y @@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m CONFIG_MARVELL_PHY=y CONFIG_MDIO_BUS_MUX_GPIO=y CONFIG_MDIO_BUS_MUX_MMIOREG=y +CONFIG_MEMORY=y CONFIG_MMC_SDHCI_OF_ESDHC=y CONFIG_MMC_SDHCI_PLTFM=y CONFIG_MMC_SDHCI=y diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h index 2bc53c646ccd..83848b534cb1 100644 --- a/arch/powerpc/include/asm/asm-compat.h +++ b/arch/powerpc/include/asm/asm-compat.h @@ -39,6 +39,12 @@ #define STDX_BE stringify_in_c(stdbrx) #endif +#ifdef CONFIG_CC_IS_CLANG +#define DS_FORM_CONSTRAINT "Z<>" +#else +#define DS_FORM_CONSTRAINT "YZ<>" +#endif + #else /* 32-bit */ /* operations for longs and pointers */ diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h index 486ab7889121..33742fec25c1 100644 --- a/arch/powerpc/include/asm/atomic.h +++ b/arch/powerpc/include/asm/atomic.h @@ -11,6 +11,7 @@ #include #include #include +#include /* * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with @@ -27,14 +28,22 @@ static __inline__ int arch_atomic_read(const atomic_t *v) { int t; - __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("lwz %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("lwz%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); return t; } static __inline__ void arch_atomic_set(atomic_t *v, int i) { - __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("stw %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("stw%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); } #define ATOMIC_OP(op, asm_op, suffix, sign, ...) \ @@ -226,14 +235,22 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v) { s64 t; - __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter)); + else + __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter)); return t; } static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i) { - __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i)); + /* -mprefixed can generate offsets beyond range, fall back hack */ + if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED)) + __asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter)); + else + __asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i)); } #define ATOMIC64_OP(op, asm_op) \ diff --git a/arch/powerpc/include/asm/io.h b/arch/powerpc/include/asm/io.h index 6d3ce049babd..6010e966b149 100644 --- a/arch/powerpc/include/asm/io.h +++ b/arch/powerpc/include/asm/io.h @@ -97,6 +97,42 @@ extern bool isa_io_special; * */ +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define DEF_MMIO_IN_X(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0,%1;twi 0,%0,0;isync" \ + : "=r" (ret) : "r" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_X(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0,%0" \ + : : "r" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} + +#define DEF_MMIO_IN_D(name, size, insn) \ +static inline u##size name(const volatile u##size __iomem *addr) \ +{ \ + u##size ret; \ + __asm__ __volatile__("sync;"#insn" %0,0(%1);twi 0,%0,0;isync"\ + : "=r" (ret) : "b" (addr) : "memory"); \ + return ret; \ +} + +#define DEF_MMIO_OUT_D(name, size, insn) \ +static inline void name(volatile u##size __iomem *addr, u##size val) \ +{ \ + __asm__ __volatile__("sync;"#insn" %1,0(%0)" \ + : : "b" (addr), "r" (val) : "memory"); \ + mmiowb_set_pending(); \ +} +#else #define DEF_MMIO_IN_X(name, size, insn) \ static inline u##size name(const volatile u##size __iomem *addr) \ { \ @@ -130,6 +166,7 @@ static inline void name(volatile u##size __iomem *addr, u##size val) \ : "=m<>" (*addr) : "r" (val) : "memory"); \ mmiowb_set_pending(); \ } +#endif DEF_MMIO_IN_D(in_8, 8, lbz); DEF_MMIO_OUT_D(out_8, 8, stb); diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h index a1ddba01e7d1..f2db1b443920 100644 --- a/arch/powerpc/include/asm/kexec.h +++ b/arch/powerpc/include/asm/kexec.h @@ -181,6 +181,10 @@ static inline void crash_send_ipi(void (*crash_ipi_callback)(struct pt_regs *)) #endif /* CONFIG_KEXEC_CORE */ +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +int update_cpus_node(void *fdt); +#endif + #ifdef CONFIG_PPC_BOOK3S_64 #include #endif diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h index e43a418d3ccd..9b5ba73d33d6 100644 --- a/arch/powerpc/include/asm/nohash/mmu-e500.h +++ b/arch/powerpc/include/asm/nohash/mmu-e500.h @@ -303,8 +303,7 @@ extern unsigned long linear_map_top; extern int book3e_htw_mode; #define PPC_HTW_NONE 0 -#define PPC_HTW_IBM 1 -#define PPC_HTW_E6500 2 +#define PPC_HTW_E6500 1 /* * 64-bit booke platforms don't load the tlb in the tlb miss handler code. diff --git a/arch/powerpc/platforms/pseries/plpks.h b/arch/powerpc/include/asm/plpks.h similarity index 61% rename from arch/powerpc/platforms/pseries/plpks.h rename to arch/powerpc/include/asm/plpks.h index 07278a990c2d..9e2219b0202d 100644 --- a/arch/powerpc/platforms/pseries/plpks.h +++ b/arch/powerpc/include/asm/plpks.h @@ -6,8 +6,10 @@ * Platform keystore for pseries LPAR(PLPKS). */ -#ifndef _PSERIES_PLPKS_H -#define _PSERIES_PLPKS_H +#ifndef _ASM_POWERPC_PLPKS_H +#define _ASM_POWERPC_PLPKS_H + +#ifdef CONFIG_PSERIES_PLPKS #include #include @@ -93,4 +95,69 @@ int plpks_read_fw_var(struct plpks_var *var); */ int plpks_read_bootloader_var(struct plpks_var *var); -#endif +/** + * Returns if PKS is available on this LPAR. + */ +bool plpks_is_available(void); + +/** + * Returns version of the Platform KeyStore. + */ +u8 plpks_get_version(void); + +/** + * Returns hypervisor storage overhead per object, not including the size of + * the object or label. Only valid for config version >= 2 + */ +u16 plpks_get_objoverhead(void); + +/** + * Returns maximum password size. Must be >= 32 bytes + */ +u16 plpks_get_maxpwsize(void); + +/** + * Returns maximum object size supported by Platform KeyStore. + */ +u16 plpks_get_maxobjectsize(void); + +/** + * Returns maximum object label size supported by Platform KeyStore. + */ +u16 plpks_get_maxobjectlabelsize(void); + +/** + * Returns total size of the configured Platform KeyStore. + */ +u32 plpks_get_totalsize(void); + +/** + * Returns used space from the total size of the Platform KeyStore. + */ +u32 plpks_get_usedspace(void); + +/** + * Returns bitmask of policies supported by the hypervisor. + */ +u32 plpks_get_supportedpolicies(void); + +/** + * Returns maximum byte size of a single object supported by the hypervisor. + * Only valid for config version >= 3 + */ +u32 plpks_get_maxlargeobjectsize(void); + +/** + * Returns bitmask of signature algorithms supported for signed updates. + * Only valid for config version >= 3 + */ +u64 plpks_get_signedupdatealgorithms(void); + +/** + * Returns the length of the PLPKS password in bytes. + */ +u16 plpks_get_passwordlen(void); + +#endif // CONFIG_PSERIES_PLPKS + +#endif // _ASM_POWERPC_PLPKS_H diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h index 661046150e49..63e7c3107cc8 100644 --- a/arch/powerpc/include/asm/uaccess.h +++ b/arch/powerpc/include/asm/uaccess.h @@ -6,6 +6,7 @@ #include #include #include +#include #ifdef __powerpc64__ /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */ @@ -71,19 +72,25 @@ __pu_failed: \ * because we do not write to any memory gcc knows about, so there * are no aliasing issues. */ +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __put_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: " op " %0,0(%1) # put_user\n" \ + EX_TABLE(1b, %l2) \ + : \ + : "r" (x), "b" (addr) \ + : \ + : label) +#else #define __put_user_asm_goto(x, addr, label, op) \ asm goto( \ "1: " op "%U1%X1 %0,%1 # put_user\n" \ EX_TABLE(1b, %l2) \ : \ - : "r" (x), "m<>" (*addr) \ + : "r" (x), "m<>" (*addr) \ : \ : label) - -#ifdef CONFIG_CC_IS_CLANG -#define DS_FORM_CONSTRAINT "Z<>" -#else -#define DS_FORM_CONSTRAINT "YZ<>" #endif #ifdef __powerpc64__ @@ -142,14 +149,26 @@ do { \ #ifdef CONFIG_CC_HAS_ASM_GOTO_OUTPUT +/* -mprefixed can generate offsets beyond range, fall back hack */ +#ifdef CONFIG_PPC_KERNEL_PREFIXED +#define __get_user_asm_goto(x, addr, label, op) \ + asm_volatile_goto( \ + "1: "op" %0,0(%1) # get_user\n" \ + EX_TABLE(1b, %l2) \ + : "=r" (x) \ + : "b" (addr) \ + : \ + : label) +#else #define __get_user_asm_goto(x, addr, label, op) \ asm_goto_output( \ "1: "op"%U1%X1 %0, %1 # get_user\n" \ EX_TABLE(1b, %l2) \ : "=r" (x) \ - : "m<>" (*addr) \ + : "m<>" (*addr) \ : \ : label) +#endif #ifdef __powerpc64__ #define __get_user_asm2_goto(x, addr, label) \ diff --git a/arch/powerpc/include/asm/vdso_datapage.h b/arch/powerpc/include/asm/vdso_datapage.h index a585c8e538ff..939daf6b695e 100644 --- a/arch/powerpc/include/asm/vdso_datapage.h +++ b/arch/powerpc/include/asm/vdso_datapage.h @@ -111,6 +111,21 @@ extern struct vdso_arch_data *vdso_data; addi \ptr, \ptr, (_vdso_datapage - 999b)@l .endm +#include +#include + +.macro get_realdatapage ptr scratch + get_datapage \ptr +#ifdef CONFIG_TIME_NS + lwz \scratch, VDSO_CLOCKMODE_OFFSET(\ptr) + xoris \scratch, \scratch, VDSO_CLOCKMODE_TIMENS@h + xori \scratch, \scratch, VDSO_CLOCKMODE_TIMENS@l + cntlzw \scratch, \scratch + rlwinm \scratch, \scratch, PAGE_SHIFT - 5, 1 << PAGE_SHIFT + add \ptr, \ptr, \scratch +#endif +.endm + #endif /* __ASSEMBLY__ */ #endif /* __KERNEL__ */ diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c index 4ce2a4aa3985..65d79dd0c92c 100644 --- a/arch/powerpc/kernel/asm-offsets.c +++ b/arch/powerpc/kernel/asm-offsets.c @@ -347,6 +347,8 @@ int main(void) #else OFFSET(CFG_SYSCALL_MAP32, vdso_arch_data, syscall_map); #endif + OFFSET(VDSO_CLOCKMODE_OFFSET, vdso_arch_data, data[0].clock_mode); + DEFINE(VDSO_CLOCKMODE_TIMENS, VDSO_CLOCKMODE_TIMENS); #ifdef CONFIG_BUG DEFINE(BUG_ENTRY_SIZE, sizeof(struct bug_entry)); diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c index d2873d17d2b1..e4624d789629 100644 --- a/arch/powerpc/kernel/eeh_pe.c +++ b/arch/powerpc/kernel/eeh_pe.c @@ -850,6 +850,7 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) { struct eeh_dev *edev; struct pci_dev *pdev; + struct pci_bus *bus = NULL; if (pe->type & EEH_PE_PHB) return pe->phb->bus; @@ -860,9 +861,11 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe) /* Retrieve the parent PCI bus of first (top) PCI device */ edev = list_first_entry_or_null(&pe->edevs, struct eeh_dev, entry); + pci_lock_rescan_remove(); pdev = eeh_dev_to_pci_dev(edev); if (pdev) - return pdev->bus; + bus = pdev->bus; + pci_unlock_rescan_remove(); - return NULL; + return bus; } diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S index 0b05f2be66b9..f267e1587a9b 100644 --- a/arch/powerpc/kernel/head_8xx.S +++ b/arch/powerpc/kernel/head_8xx.S @@ -40,12 +40,12 @@ #include "head_32.h" .macro compare_to_kernel_boundary scratch, addr -#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000 +#if CONFIG_TASK_SIZE <= 0x80000000 && MODULES_VADDR >= 0x80000000 /* By simply checking Address >= 0x80000000, we know if its a kernel address */ not. \scratch, \addr #else rlwinm \scratch, \addr, 16, 0xfff8 - cmpli cr0, \scratch, PAGE_OFFSET@h + cmpli cr0, \scratch, TASK_SIZE@h #endif .endm @@ -403,7 +403,7 @@ FixupDAR:/* Entry point for dcbx workaround. */ mfspr r10, SPRN_SRR0 mtspr SPRN_MD_EPN, r10 rlwinm r11, r10, 16, 0xfff8 - cmpli cr1, r11, PAGE_OFFSET@h + cmpli cr1, r11, TASK_SIZE@h mfspr r11, SPRN_M_TWB /* Get level 1 table */ blt+ cr1, 3f diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index 9531ab90feb8..e5b90d67cd53 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -324,6 +324,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, void *data) { const char *type = of_get_flat_dt_prop(node, "device_type", NULL); + const __be32 *cpu_version = NULL; const __be32 *prop; const __be32 *intserv; int i, nthreads; @@ -404,7 +405,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node, prop = of_get_flat_dt_prop(node, "cpu-version", NULL); if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) { identify_cpu(0, be32_to_cpup(prop)); - seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop)); + cpu_version = prop; } check_cpu_feature_properties(node); @@ -415,6 +416,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node, } identical_pvr_fixup(node); + + // We can now add the CPU name & PVR to the hardware description + seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); + if (cpu_version) + seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(cpu_version)); + init_mmu_slb_size(node); #ifdef CONFIG_PPC64 @@ -852,9 +859,6 @@ void __init early_init_devtree(void *params) dt_cpu_ftrs_scan(); - // We can now add the CPU name & PVR to the hardware description - seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR)); - /* Retrieve CPU related informations from the flat tree * (altivec support, boot CPU ID, ...) */ diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 59b4ac57bfaf..56f6b958926d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -948,6 +948,7 @@ void __init setup_arch(char **cmdline_p) mem_topology_setup(); /* Set max_mapnr before paging_init() */ set_max_mapnr(max_pfn); + high_memory = (void *)__va(max_low_pfn * PAGE_SIZE); /* * Release secondary cpus out of their spinloops at 0x60 now that diff --git a/arch/powerpc/kernel/trace/ftrace.c b/arch/powerpc/kernel/trace/ftrace.c index 7b85c3b460a3..72864fb7a6cc 100644 --- a/arch/powerpc/kernel/trace/ftrace.c +++ b/arch/powerpc/kernel/trace/ftrace.c @@ -194,6 +194,8 @@ __ftrace_make_nop(struct module *mod, * get corrupted. * * Use a b +8 to jump over the load. + * XXX: could make PCREL depend on MPROFILE_KERNEL + * XXX: check PCREL && MPROFILE_KERNEL calling sequence */ if (IS_ENABLED(CONFIG_MPROFILE_KERNEL) || IS_ENABLED(CONFIG_PPC32)) pop = ppc_inst(PPC_RAW_NOP()); diff --git a/arch/powerpc/kernel/vdso/cacheflush.S b/arch/powerpc/kernel/vdso/cacheflush.S index 0085ae464dac..3b2479bd2f9a 100644 --- a/arch/powerpc/kernel/vdso/cacheflush.S +++ b/arch/powerpc/kernel/vdso/cacheflush.S @@ -30,7 +30,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_COHERENT_ICACHE) #ifdef CONFIG_PPC64 mflr r12 .cfi_register lr,r12 - get_datapage r10 + get_realdatapage r10, r11 mtlr r12 .cfi_restore lr #endif diff --git a/arch/powerpc/kernel/vdso/datapage.S b/arch/powerpc/kernel/vdso/datapage.S index db8e167f0166..2b19b6201a33 100644 --- a/arch/powerpc/kernel/vdso/datapage.S +++ b/arch/powerpc/kernel/vdso/datapage.S @@ -28,7 +28,7 @@ V_FUNCTION_BEGIN(__kernel_get_syscall_map) mflr r12 .cfi_register lr,r12 mr. r4,r3 - get_datapage r3 + get_realdatapage r3, r11 mtlr r12 #ifdef __powerpc64__ addi r3,r3,CFG_SYSCALL_MAP64 @@ -52,7 +52,7 @@ V_FUNCTION_BEGIN(__kernel_get_tbfreq) .cfi_startproc mflr r12 .cfi_register lr,r12 - get_datapage r3 + get_realdatapage r3, r11 #ifndef __powerpc64__ lwz r4,(CFG_TB_TICKS_PER_SEC + 4)(r3) #endif diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c index e465e4487737..653b3c8c6a53 100644 --- a/arch/powerpc/kexec/core_64.c +++ b/arch/powerpc/kexec/core_64.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include @@ -31,6 +32,7 @@ #include #include #include +#include int machine_kexec_prepare(struct kimage *image) { @@ -431,3 +433,113 @@ static int __init export_htab_values(void) } late_initcall(export_htab_values); #endif /* CONFIG_PPC_64S_HASH_MMU */ + +#if defined(CONFIG_KEXEC_FILE) || defined(CONFIG_CRASH_DUMP) +/** + * add_node_props - Reads node properties from device node structure and add + * them to fdt. + * @fdt: Flattened device tree of the kernel + * @node_offset: offset of the node to add a property at + * @dn: device node pointer + * + * Returns 0 on success, negative errno on error. + */ +static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) +{ + int ret = 0; + struct property *pp; + + if (!dn) + return -EINVAL; + + for_each_property_of_node(dn, pp) { + ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); + if (ret < 0) { + pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); + return ret; + } + } + return ret; +} + +/** + * update_cpus_node - Update cpus node of flattened device tree using of_root + * device node. + * @fdt: Flattened device tree of the kernel. + * + * Returns 0 on success, negative errno on error. + * + * Note: expecting no subnodes under /cpus/ with device_type == "cpu". + * If this changes, update this function to include them. + */ +int update_cpus_node(void *fdt) +{ + int prev_node_offset; + const char *device_type; + const struct fdt_property *prop; + struct device_node *cpus_node, *dn; + int cpus_offset, cpus_subnode_offset, ret = 0; + + cpus_offset = fdt_path_offset(fdt, "/cpus"); + if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { + pr_err("Malformed device tree: error reading /cpus node: %s\n", + fdt_strerror(cpus_offset)); + return cpus_offset; + } + + prev_node_offset = cpus_offset; + /* Delete sub-nodes of /cpus node with device_type == "cpu" */ + for (cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); cpus_subnode_offset >= 0;) { + /* Ignore nodes that do not have a device_type property or device_type != "cpu" */ + prop = fdt_get_property(fdt, cpus_subnode_offset, "device_type", NULL); + if (!prop || strcmp(prop->data, "cpu")) { + prev_node_offset = cpus_subnode_offset; + goto next_node; + } + + ret = fdt_del_node(fdt, cpus_subnode_offset); + if (ret < 0) { + pr_err("Failed to delete a cpus sub-node: %s\n", fdt_strerror(ret)); + return ret; + } +next_node: + if (prev_node_offset == cpus_offset) + cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); + else + cpus_subnode_offset = fdt_next_subnode(fdt, prev_node_offset); + } + + cpus_node = of_find_node_by_path("/cpus"); + /* Fail here to avoid kexec/kdump kernel boot hung */ + if (!cpus_node) { + pr_err("No /cpus node found\n"); + return -EINVAL; + } + + /* Add all /cpus sub-nodes of device_type == "cpu" to FDT */ + for_each_child_of_node(cpus_node, dn) { + /* Ignore device nodes that do not have a device_type property + * or device_type != "cpu". + */ + device_type = of_get_property(dn, "device_type", NULL); + if (!device_type || strcmp(device_type, "cpu")) + continue; + + cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); + if (cpus_subnode_offset < 0) { + pr_err("Unable to add %s subnode: %s\n", dn->full_name, + fdt_strerror(cpus_subnode_offset)); + ret = cpus_subnode_offset; + goto out; + } + + ret = add_node_props(fdt, cpus_subnode_offset, dn); + if (ret < 0) + goto out; + } +out: + of_node_put(cpus_node); + of_node_put(dn); + return ret; +} +#endif /* CONFIG_KEXEC_FILE || CONFIG_CRASH_DUMP */ diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c index 349a781cea0b..180c1dfe4aa7 100644 --- a/arch/powerpc/kexec/file_load_64.c +++ b/arch/powerpc/kexec/file_load_64.c @@ -952,93 +952,6 @@ unsigned int kexec_extra_fdt_size_ppc64(struct kimage *image) return (unsigned int)(usm_entries * sizeof(u64)); } -/** - * add_node_props - Reads node properties from device node structure and add - * them to fdt. - * @fdt: Flattened device tree of the kernel - * @node_offset: offset of the node to add a property at - * @dn: device node pointer - * - * Returns 0 on success, negative errno on error. - */ -static int add_node_props(void *fdt, int node_offset, const struct device_node *dn) -{ - int ret = 0; - struct property *pp; - - if (!dn) - return -EINVAL; - - for_each_property_of_node(dn, pp) { - ret = fdt_setprop(fdt, node_offset, pp->name, pp->value, pp->length); - if (ret < 0) { - pr_err("Unable to add %s property: %s\n", pp->name, fdt_strerror(ret)); - return ret; - } - } - return ret; -} - -/** - * update_cpus_node - Update cpus node of flattened device tree using of_root - * device node. - * @fdt: Flattened device tree of the kernel. - * - * Returns 0 on success, negative errno on error. - */ -static int update_cpus_node(void *fdt) -{ - struct device_node *cpus_node, *dn; - int cpus_offset, cpus_subnode_offset, ret = 0; - - cpus_offset = fdt_path_offset(fdt, "/cpus"); - if (cpus_offset < 0 && cpus_offset != -FDT_ERR_NOTFOUND) { - pr_err("Malformed device tree: error reading /cpus node: %s\n", - fdt_strerror(cpus_offset)); - return cpus_offset; - } - - if (cpus_offset > 0) { - ret = fdt_del_node(fdt, cpus_offset); - if (ret < 0) { - pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret)); - return -EINVAL; - } - } - - /* Add cpus node to fdt */ - cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus"); - if (cpus_offset < 0) { - pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset)); - return -EINVAL; - } - - /* Add cpus node properties */ - cpus_node = of_find_node_by_path("/cpus"); - ret = add_node_props(fdt, cpus_offset, cpus_node); - of_node_put(cpus_node); - if (ret < 0) - return ret; - - /* Loop through all subnodes of cpus and add them to fdt */ - for_each_node_by_type(dn, "cpu") { - cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name); - if (cpus_subnode_offset < 0) { - pr_err("Unable to add %s subnode: %s\n", dn->full_name, - fdt_strerror(cpus_subnode_offset)); - ret = cpus_subnode_offset; - goto out; - } - - ret = add_node_props(fdt, cpus_subnode_offset, dn); - if (ret < 0) - goto out; - } -out: - of_node_put(dn); - return ret; -} - static int copy_property(void *fdt, int node_offset, const struct device_node *dn, const char *propname) { diff --git a/arch/powerpc/kvm/book3s_64_vio.c b/arch/powerpc/kvm/book3s_64_vio.c index 40864373ef87..549e33d4ecd6 100644 --- a/arch/powerpc/kvm/book3s_64_vio.c +++ b/arch/powerpc/kvm/book3s_64_vio.c @@ -129,14 +129,16 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, } rcu_read_unlock(); - fdput(f); - - if (!found) + if (!found) { + fdput(f); return -EINVAL; + } table_group = iommu_group_get_iommudata(grp); - if (WARN_ON(!table_group)) + if (WARN_ON(!table_group)) { + fdput(f); return -EFAULT; + } for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) { struct iommu_table *tbltmp = table_group->tables[i]; @@ -157,8 +159,10 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, break; } } - if (!tbl) + if (!tbl) { + fdput(f); return -EINVAL; + } rcu_read_lock(); list_for_each_entry_rcu(stit, &stt->iommu_tables, next) { @@ -169,6 +173,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, /* stit is being destroyed */ iommu_tce_table_put(tbl); rcu_read_unlock(); + fdput(f); return -ENOTTY; } /* @@ -176,6 +181,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, * its KVM reference counter and can return. */ rcu_read_unlock(); + fdput(f); return 0; } rcu_read_unlock(); @@ -183,6 +189,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, stit = kzalloc(sizeof(*stit), GFP_KERNEL); if (!stit) { iommu_tce_table_put(tbl); + fdput(f); return -ENOMEM; } @@ -191,6 +198,7 @@ extern long kvm_spapr_tce_attach_iommu_group(struct kvm *kvm, int tablefd, list_add_rcu(&stit->next, &stt->iommu_tables); + fdput(f); return 0; } diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c index b850b0efa201..98ac5d39ad9c 100644 --- a/arch/powerpc/kvm/powerpc.c +++ b/arch/powerpc/kvm/powerpc.c @@ -1998,8 +1998,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu, break; r = -ENXIO; - if (!xive_enabled()) + if (!xive_enabled()) { + fdput(f); break; + } r = -EPERM; dev = kvm_device_from_filp(f.file); diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index c7599b173709..40f4a31f001c 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -287,8 +287,6 @@ void __init mem_init(void) swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags); #endif - high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - kasan_late_init(); memblock_free_all(); diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c index dbbfe897455d..52f24fda2d5f 100644 --- a/arch/powerpc/mm/nohash/8xx.c +++ b/arch/powerpc/mm/nohash/8xx.c @@ -147,11 +147,11 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top) mmu_mapin_immr(); - mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true); + mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_X, true); if (debug_pagealloc_enabled_or_kfence()) { top = boundary; } else { - mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_TEXT, true); + mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_X, true); mmu_mapin_ram_chunk(einittext8, top, PAGE_KERNEL, true); } diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile index f3894e79d5f7..24b445a5fcac 100644 --- a/arch/powerpc/mm/nohash/Makefile +++ b/arch/powerpc/mm/nohash/Makefile @@ -3,7 +3,7 @@ ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC) obj-y += mmu_context.o tlb.o tlb_low.o kup.o -obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o +obj-$(CONFIG_PPC_BOOK3E_64) += tlb_64e.o tlb_low_64e.o book3e_pgtable.o obj-$(CONFIG_40x) += 40x.o obj-$(CONFIG_44x) += 44x.o obj-$(CONFIG_PPC_8xx) += 8xx.o diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c index 2c15c86c7015..c0b643d30fcc 100644 --- a/arch/powerpc/mm/nohash/tlb.c +++ b/arch/powerpc/mm/nohash/tlb.c @@ -110,28 +110,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = { }; #endif -/* The variables below are currently only used on 64-bit Book3E - * though this will probably be made common with other nohash - * implementations at some point - */ -#ifdef CONFIG_PPC64 - -int mmu_pte_psize; /* Page size used for PTE pages */ -int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ -int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ -unsigned long linear_map_top; /* Top of linear mapping */ - - -/* - * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug - * exceptions. This is used for bolted and e6500 TLB miss handlers which - * do not modify this SPRG in the TLB miss code; for other TLB miss handlers, - * this is set to zero. - */ -int extlb_level_exc; - -#endif /* CONFIG_PPC64 */ - #ifdef CONFIG_PPC_E500 /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */ DEFINE_PER_CPU(int, next_tlbcam_idx); @@ -361,381 +339,7 @@ void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm(tlb->mm); } -/* - * Below are functions specific to the 64-bit variant of Book3E though that - * may change in the future - */ - -#ifdef CONFIG_PPC64 - -/* - * Handling of virtual linear page tables or indirect TLB entries - * flushing when PTE pages are freed - */ -void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) -{ - int tsize = mmu_psize_defs[mmu_pte_psize].enc; - - if (book3e_htw_mode != PPC_HTW_NONE) { - unsigned long start = address & PMD_MASK; - unsigned long end = address + PMD_SIZE; - unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; - - /* This isn't the most optimal, ideally we would factor out the - * while preempt & CPU mask mucking around, or even the IPI but - * it will do for now - */ - while (start < end) { - __flush_tlb_page(tlb->mm, start, tsize, 1); - start += size; - } - } else { - unsigned long rmask = 0xf000000000000000ul; - unsigned long rid = (address & rmask) | 0x1000000000000000ul; - unsigned long vpte = address & ~rmask; - - vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful; - vpte |= rid; - __flush_tlb_page(tlb->mm, vpte, tsize, 0); - } -} - -static void __init setup_page_sizes(void) -{ - unsigned int tlb0cfg; - unsigned int tlb0ps; - unsigned int eptcfg; - int i, psize; - -#ifdef CONFIG_PPC_E500 - unsigned int mmucfg = mfspr(SPRN_MMUCFG); - int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); - - if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) { - unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG); - unsigned int min_pg, max_pg; - - min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT; - max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT; - - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def; - unsigned int shift; - - def = &mmu_psize_defs[psize]; - shift = def->shift; - - if (shift == 0 || shift & 1) - continue; - - /* adjust to be in terms of 4^shift Kb */ - shift = (shift - 10) >> 1; - - if ((shift >= min_pg) && (shift <= max_pg)) - def->flags |= MMU_PAGE_SIZE_DIRECT; - } - - goto out; - } - - if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { - u32 tlb1cfg, tlb1ps; - - tlb0cfg = mfspr(SPRN_TLB0CFG); - tlb1cfg = mfspr(SPRN_TLB1CFG); - tlb1ps = mfspr(SPRN_TLB1PS); - eptcfg = mfspr(SPRN_EPTCFG); - - if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) - book3e_htw_mode = PPC_HTW_E6500; - - /* - * We expect 4K subpage size and unrestricted indirect size. - * The lack of a restriction on indirect size is a Freescale - * extension, indicated by PSn = 0 but SPSn != 0. - */ - if (eptcfg != 2) - book3e_htw_mode = PPC_HTW_NONE; - - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (!def->shift) - continue; - - if (tlb1ps & (1U << (def->shift - 10))) { - def->flags |= MMU_PAGE_SIZE_DIRECT; - - if (book3e_htw_mode && psize == MMU_PAGE_2M) - def->flags |= MMU_PAGE_SIZE_INDIRECT; - } - } - - goto out; - } -#endif - - tlb0cfg = mfspr(SPRN_TLB0CFG); - tlb0ps = mfspr(SPRN_TLB0PS); - eptcfg = mfspr(SPRN_EPTCFG); - - /* Look for supported direct sizes */ - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (tlb0ps & (1U << (def->shift - 10))) - def->flags |= MMU_PAGE_SIZE_DIRECT; - } - - /* Indirect page sizes supported ? */ - if ((tlb0cfg & TLBnCFG_IND) == 0 || - (tlb0cfg & TLBnCFG_PT) == 0) - goto out; - - book3e_htw_mode = PPC_HTW_IBM; - - /* Now, we only deal with one IND page size for each - * direct size. Hopefully all implementations today are - * unambiguous, but we might want to be careful in the - * future. - */ - for (i = 0; i < 3; i++) { - unsigned int ps, sps; - - sps = eptcfg & 0x1f; - eptcfg >>= 5; - ps = eptcfg & 0x1f; - eptcfg >>= 5; - if (!ps || !sps) - continue; - for (psize = 0; psize < MMU_PAGE_COUNT; psize++) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - - if (ps == (def->shift - 10)) - def->flags |= MMU_PAGE_SIZE_INDIRECT; - if (sps == (def->shift - 10)) - def->ind = ps + 10; - } - } - -out: - /* Cleanup array and print summary */ - pr_info("MMU: Supported page sizes\n"); - for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { - struct mmu_psize_def *def = &mmu_psize_defs[psize]; - const char *__page_type_names[] = { - "unsupported", - "direct", - "indirect", - "direct & indirect" - }; - if (def->flags == 0) { - def->shift = 0; - continue; - } - pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10), - __page_type_names[def->flags & 0x3]); - } -} - -static void __init setup_mmu_htw(void) -{ - /* - * If we want to use HW tablewalk, enable it by patching the TLB miss - * handlers to branch to the one dedicated to it. - */ - - switch (book3e_htw_mode) { - case PPC_HTW_IBM: - patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e); - break; -#ifdef CONFIG_PPC_E500 - case PPC_HTW_E6500: - extlb_level_exc = EX_TLB_SIZE; - patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); - patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); - break; -#endif - } - pr_info("MMU: Book3E HW tablewalk %s\n", - book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); -} - -/* - * Early initialization of the MMU TLB code - */ -static void early_init_this_mmu(void) -{ - unsigned int mas4; - - /* Set MAS4 based on page table setting */ - - mas4 = 0x4 << MAS4_WIMGED_SHIFT; - switch (book3e_htw_mode) { - case PPC_HTW_E6500: - mas4 |= MAS4_INDD; - mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; - mas4 |= MAS4_TLBSELD(1); - mmu_pte_psize = MMU_PAGE_2M; - break; - - case PPC_HTW_IBM: - mas4 |= MAS4_INDD; - mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT; - mmu_pte_psize = MMU_PAGE_1M; - break; - - case PPC_HTW_NONE: - mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; - mmu_pte_psize = mmu_virtual_psize; - break; - } - mtspr(SPRN_MAS4, mas4); - -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - unsigned int num_cams; - bool map = true; - - /* use a quarter of the TLBCAM for bolted linear map */ - num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; - - /* - * Only do the mapping once per core, or else the - * transient mapping would cause problems. - */ -#ifdef CONFIG_SMP - if (hweight32(get_tensr()) > 1) - map = false; -#endif - - if (map) - linear_map_top = map_mem_in_cams(linear_map_top, - num_cams, false, true); - } -#endif - - /* A sync won't hurt us after mucking around with - * the MMU configuration - */ - mb(); -} - -static void __init early_init_mmu_global(void) -{ - /* XXX This should be decided at runtime based on supported - * page sizes in the TLB, but for now let's assume 16M is - * always there and a good fit (which it probably is) - * - * Freescale booke only supports 4K pages in TLB0, so use that. - */ - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) - mmu_vmemmap_psize = MMU_PAGE_4K; - else - mmu_vmemmap_psize = MMU_PAGE_16M; - - /* XXX This code only checks for TLB 0 capabilities and doesn't - * check what page size combos are supported by the HW. It - * also doesn't handle the case where a separate array holds - * the IND entries from the array loaded by the PT. - */ - /* Look for supported page sizes */ - setup_page_sizes(); - - /* Look for HW tablewalk support */ - setup_mmu_htw(); - -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - if (book3e_htw_mode == PPC_HTW_NONE) { - extlb_level_exc = EX_TLB_SIZE; - patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); - patch_exception(0x1e0, - exc_instruction_tlb_miss_bolted_book3e); - } - } -#endif - - /* Set the global containing the top of the linear mapping - * for use by the TLB miss code - */ - linear_map_top = memblock_end_of_DRAM(); - - ioremap_bot = IOREMAP_BASE; -} - -static void __init early_mmu_set_memory_limit(void) -{ -#ifdef CONFIG_PPC_E500 - if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - /* - * Limit memory so we dont have linear faults. - * Unlike memblock_set_current_limit, which limits - * memory available during early boot, this permanently - * reduces the memory available to Linux. We need to - * do this because highmem is not supported on 64-bit. - */ - memblock_enforce_memory_limit(linear_map_top); - } -#endif - - memblock_set_current_limit(linear_map_top); -} - -/* boot cpu only */ -void __init early_init_mmu(void) -{ - early_init_mmu_global(); - early_init_this_mmu(); - early_mmu_set_memory_limit(); -} - -void early_init_mmu_secondary(void) -{ - early_init_this_mmu(); -} - -void setup_initial_memory_limit(phys_addr_t first_memblock_base, - phys_addr_t first_memblock_size) -{ - /* On non-FSL Embedded 64-bit, we adjust the RMA size to match - * the bolted TLB entry. We know for now that only 1G - * entries are supported though that may eventually - * change. - * - * on FSL Embedded 64-bit, usually all RAM is bolted, but with - * unusual memory sizes it's possible for some RAM to not be mapped - * (such RAM is not used at all by Linux, since we don't support - * highmem on 64-bit). We limit ppc64_rma_size to what would be - * mappable if this memblock is the only one. Additional memblocks - * can only increase, not decrease, the amount that ends up getting - * mapped. We still limit max to 1G even if we'll eventually map - * more. This is due to what the early init code is set up to do. - * - * We crop it to the size of the first MEMBLOCK to - * avoid going over total available memory just in case... - */ -#ifdef CONFIG_PPC_E500 - if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { - unsigned long linear_sz; - unsigned int num_cams; - - /* use a quarter of the TLBCAM for bolted linear map */ - num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; - - linear_sz = map_mem_in_cams(first_memblock_size, num_cams, - true, true); - - ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); - } else -#endif - ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); - - /* Finally limit subsequent allocations */ - memblock_set_current_limit(first_memblock_base + ppc64_rma_size); -} -#else /* ! CONFIG_PPC64 */ +#ifndef CONFIG_PPC64 void __init early_init_mmu(void) { #ifdef CONFIG_PPC_47x diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c new file mode 100644 index 000000000000..b6af3ec4d001 --- /dev/null +++ b/arch/powerpc/mm/nohash/tlb_64e.c @@ -0,0 +1,361 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2008,2009 Ben Herrenschmidt + * IBM Corp. + * + * Derived from arch/ppc/mm/init.c: + * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org) + * + * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au) + * and Cort Dougan (PReP) (cort@cs.nmt.edu) + * Copyright (C) 1996 Paul Mackerras + * + * Derived from "arch/i386/mm/init.c" + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include + +/* The variables below are currently only used on 64-bit Book3E + * though this will probably be made common with other nohash + * implementations at some point + */ +static int mmu_pte_psize; /* Page size used for PTE pages */ +int mmu_vmemmap_psize; /* Page size used for the virtual mem map */ +int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */ +unsigned long linear_map_top; /* Top of linear mapping */ + + +/* + * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug + * exceptions. This is used for bolted and e6500 TLB miss handlers which + * do not modify this SPRG in the TLB miss code; for other TLB miss handlers, + * this is set to zero. + */ +int extlb_level_exc; + +/* + * Handling of virtual linear page tables or indirect TLB entries + * flushing when PTE pages are freed + */ +void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address) +{ + int tsize = mmu_psize_defs[mmu_pte_psize].enc; + + if (book3e_htw_mode != PPC_HTW_NONE) { + unsigned long start = address & PMD_MASK; + unsigned long end = address + PMD_SIZE; + unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift; + + /* This isn't the most optimal, ideally we would factor out the + * while preempt & CPU mask mucking around, or even the IPI but + * it will do for now + */ + while (start < end) { + __flush_tlb_page(tlb->mm, start, tsize, 1); + start += size; + } + } else { + unsigned long rmask = 0xf000000000000000ul; + unsigned long rid = (address & rmask) | 0x1000000000000000ul; + unsigned long vpte = address & ~rmask; + + vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful; + vpte |= rid; + __flush_tlb_page(tlb->mm, vpte, tsize, 0); + } +} + +static void __init setup_page_sizes(void) +{ + unsigned int tlb0cfg; + unsigned int eptcfg; + int psize; + +#ifdef CONFIG_PPC_E500 + unsigned int mmucfg = mfspr(SPRN_MMUCFG); + int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E); + + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) { + unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG); + unsigned int min_pg, max_pg; + + min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT; + max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def; + unsigned int shift; + + def = &mmu_psize_defs[psize]; + shift = def->shift; + + if (shift == 0 || shift & 1) + continue; + + /* adjust to be in terms of 4^shift Kb */ + shift = (shift - 10) >> 1; + + if ((shift >= min_pg) && (shift <= max_pg)) + def->flags |= MMU_PAGE_SIZE_DIRECT; + } + + goto out; + } + + if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) { + u32 tlb1cfg, tlb1ps; + + tlb0cfg = mfspr(SPRN_TLB0CFG); + tlb1cfg = mfspr(SPRN_TLB1CFG); + tlb1ps = mfspr(SPRN_TLB1PS); + eptcfg = mfspr(SPRN_EPTCFG); + + if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT)) + book3e_htw_mode = PPC_HTW_E6500; + + /* + * We expect 4K subpage size and unrestricted indirect size. + * The lack of a restriction on indirect size is a Freescale + * extension, indicated by PSn = 0 but SPSn != 0. + */ + if (eptcfg != 2) + book3e_htw_mode = PPC_HTW_NONE; + + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def = &mmu_psize_defs[psize]; + + if (!def->shift) + continue; + + if (tlb1ps & (1U << (def->shift - 10))) { + def->flags |= MMU_PAGE_SIZE_DIRECT; + + if (book3e_htw_mode && psize == MMU_PAGE_2M) + def->flags |= MMU_PAGE_SIZE_INDIRECT; + } + } + + goto out; + } +#endif +out: + /* Cleanup array and print summary */ + pr_info("MMU: Supported page sizes\n"); + for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) { + struct mmu_psize_def *def = &mmu_psize_defs[psize]; + const char *__page_type_names[] = { + "unsupported", + "direct", + "indirect", + "direct & indirect" + }; + if (def->flags == 0) { + def->shift = 0; + continue; + } + pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10), + __page_type_names[def->flags & 0x3]); + } +} + +static void __init setup_mmu_htw(void) +{ + /* + * If we want to use HW tablewalk, enable it by patching the TLB miss + * handlers to branch to the one dedicated to it. + */ + + switch (book3e_htw_mode) { +#ifdef CONFIG_PPC_E500 + case PPC_HTW_E6500: + extlb_level_exc = EX_TLB_SIZE; + patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e); + patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e); + break; +#endif + } + pr_info("MMU: Book3E HW tablewalk %s\n", + book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported"); +} + +/* + * Early initialization of the MMU TLB code + */ +static void early_init_this_mmu(void) +{ + unsigned int mas4; + + /* Set MAS4 based on page table setting */ + + mas4 = 0x4 << MAS4_WIMGED_SHIFT; + switch (book3e_htw_mode) { + case PPC_HTW_E6500: + mas4 |= MAS4_INDD; + mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT; + mas4 |= MAS4_TLBSELD(1); + mmu_pte_psize = MMU_PAGE_2M; + break; + + case PPC_HTW_NONE: + mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT; + mmu_pte_psize = mmu_virtual_psize; + break; + } + mtspr(SPRN_MAS4, mas4); + +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + unsigned int num_cams; + bool map = true; + + /* use a quarter of the TLBCAM for bolted linear map */ + num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; + + /* + * Only do the mapping once per core, or else the + * transient mapping would cause problems. + */ +#ifdef CONFIG_SMP + if (hweight32(get_tensr()) > 1) + map = false; +#endif + + if (map) + linear_map_top = map_mem_in_cams(linear_map_top, + num_cams, false, true); + } +#endif + + /* A sync won't hurt us after mucking around with + * the MMU configuration + */ + mb(); +} + +static void __init early_init_mmu_global(void) +{ + /* XXX This should be decided at runtime based on supported + * page sizes in the TLB, but for now let's assume 16M is + * always there and a good fit (which it probably is) + * + * Freescale booke only supports 4K pages in TLB0, so use that. + */ + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) + mmu_vmemmap_psize = MMU_PAGE_4K; + else + mmu_vmemmap_psize = MMU_PAGE_16M; + + /* XXX This code only checks for TLB 0 capabilities and doesn't + * check what page size combos are supported by the HW. It + * also doesn't handle the case where a separate array holds + * the IND entries from the array loaded by the PT. + */ + /* Look for supported page sizes */ + setup_page_sizes(); + + /* Look for HW tablewalk support */ + setup_mmu_htw(); + +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + if (book3e_htw_mode == PPC_HTW_NONE) { + extlb_level_exc = EX_TLB_SIZE; + patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e); + patch_exception(0x1e0, + exc_instruction_tlb_miss_bolted_book3e); + } + } +#endif + + /* Set the global containing the top of the linear mapping + * for use by the TLB miss code + */ + linear_map_top = memblock_end_of_DRAM(); + + ioremap_bot = IOREMAP_BASE; +} + +static void __init early_mmu_set_memory_limit(void) +{ +#ifdef CONFIG_PPC_E500 + if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + /* + * Limit memory so we dont have linear faults. + * Unlike memblock_set_current_limit, which limits + * memory available during early boot, this permanently + * reduces the memory available to Linux. We need to + * do this because highmem is not supported on 64-bit. + */ + memblock_enforce_memory_limit(linear_map_top); + } +#endif + + memblock_set_current_limit(linear_map_top); +} + +/* boot cpu only */ +void __init early_init_mmu(void) +{ + early_init_mmu_global(); + early_init_this_mmu(); + early_mmu_set_memory_limit(); +} + +void early_init_mmu_secondary(void) +{ + early_init_this_mmu(); +} + +void setup_initial_memory_limit(phys_addr_t first_memblock_base, + phys_addr_t first_memblock_size) +{ + /* On non-FSL Embedded 64-bit, we adjust the RMA size to match + * the bolted TLB entry. We know for now that only 1G + * entries are supported though that may eventually + * change. + * + * on FSL Embedded 64-bit, usually all RAM is bolted, but with + * unusual memory sizes it's possible for some RAM to not be mapped + * (such RAM is not used at all by Linux, since we don't support + * highmem on 64-bit). We limit ppc64_rma_size to what would be + * mappable if this memblock is the only one. Additional memblocks + * can only increase, not decrease, the amount that ends up getting + * mapped. We still limit max to 1G even if we'll eventually map + * more. This is due to what the early init code is set up to do. + * + * We crop it to the size of the first MEMBLOCK to + * avoid going over total available memory just in case... + */ +#ifdef CONFIG_PPC_E500 + if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) { + unsigned long linear_sz; + unsigned int num_cams; + + /* use a quarter of the TLBCAM for bolted linear map */ + num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4; + + linear_sz = map_mem_in_cams(first_memblock_size, num_cams, + true, true); + + ppc64_rma_size = min_t(u64, linear_sz, 0x40000000); + } else +#endif + ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000); + + /* Finally limit subsequent allocations */ + memblock_set_current_limit(first_memblock_base + ppc64_rma_size); +} diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S index 76cf456d7976..d831a111eaba 100644 --- a/arch/powerpc/mm/nohash/tlb_low_64e.S +++ b/arch/powerpc/mm/nohash/tlb_low_64e.S @@ -893,201 +893,6 @@ virt_page_table_tlb_miss_whacko_fault: TLB_MISS_EPILOG_ERROR b exc_data_storage_book3e - -/************************************************************** - * * - * TLB miss handling for Book3E with hw page table support * - * * - **************************************************************/ - - -/* Data TLB miss */ - START_EXCEPTION(data_tlb_miss_htw) - TLB_MISS_PROLOG - - /* Now we handle the fault proper. We only save DEAR in normal - * fault case since that's the only interesting values here. - * We could probably also optimize by not saving SRR0/1 in the - * linear mapping case but I'll leave that for later - */ - mfspr r14,SPRN_ESR - mfspr r16,SPRN_DEAR /* get faulting address */ - srdi r11,r16,44 /* get region */ - xoris r11,r11,0xc - cmpldi cr0,r11,0 /* linear mapping ? */ - beq tlb_load_linear /* yes -> go to linear map load */ - cmpldi cr1,r11,1 /* vmalloc mapping ? */ - - /* We do the user/kernel test for the PID here along with the RW test - */ - srdi. r11,r16,60 /* Check for user region */ - ld r15,PACAPGD(r13) /* Load user pgdir */ - beq htw_tlb_miss - - /* XXX replace the RMW cycles with immediate loads + writes */ -1: mfspr r10,SPRN_MAS1 - rlwinm r10,r10,0,16,1 /* Clear TID */ - mtspr SPRN_MAS1,r10 - ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ - beq+ cr1,htw_tlb_miss - - /* We got a crappy address, just fault with whatever DEAR and ESR - * are here - */ - TLB_MISS_EPILOG_ERROR - b exc_data_storage_book3e - -/* Instruction TLB miss */ - START_EXCEPTION(instruction_tlb_miss_htw) - TLB_MISS_PROLOG - - /* If we take a recursive fault, the second level handler may need - * to know whether we are handling a data or instruction fault in - * order to get to the right store fault handler. We provide that - * info by keeping a crazy value for ESR in r14 - */ - li r14,-1 /* store to exception frame is done later */ - - /* Now we handle the fault proper. We only save DEAR in the non - * linear mapping case since we know the linear mapping case will - * not re-enter. We could indeed optimize and also not save SRR0/1 - * in the linear mapping case but I'll leave that for later - * - * Faulting address is SRR0 which is already in r16 - */ - srdi r11,r16,44 /* get region */ - xoris r11,r11,0xc - cmpldi cr0,r11,0 /* linear mapping ? */ - beq tlb_load_linear /* yes -> go to linear map load */ - cmpldi cr1,r11,1 /* vmalloc mapping ? */ - - /* We do the user/kernel test for the PID here along with the RW test - */ - srdi. r11,r16,60 /* Check for user region */ - ld r15,PACAPGD(r13) /* Load user pgdir */ - beq htw_tlb_miss - - /* XXX replace the RMW cycles with immediate loads + writes */ -1: mfspr r10,SPRN_MAS1 - rlwinm r10,r10,0,16,1 /* Clear TID */ - mtspr SPRN_MAS1,r10 - ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */ - beq+ htw_tlb_miss - - /* We got a crappy address, just fault */ - TLB_MISS_EPILOG_ERROR - b exc_instruction_storage_book3e - - -/* - * This is the guts of the second-level TLB miss handler for direct - * misses. We are entered with: - * - * r16 = virtual page table faulting address - * r15 = PGD pointer - * r14 = ESR - * r13 = PACA - * r12 = TLB exception frame in PACA - * r11 = crap (free to use) - * r10 = crap (free to use) - * - * It can be re-entered by the linear mapping miss handler. However, to - * avoid too much complication, it will save/restore things for us - */ -htw_tlb_miss: -#ifdef CONFIG_PPC_KUAP - mfspr r10,SPRN_MAS1 - rlwinm. r10,r10,0,0x3fff0000 - beq- htw_tlb_miss_fault /* KUAP fault */ -#endif - /* Search if we already have a TLB entry for that virtual address, and - * if we do, bail out. - * - * MAS1:IND should be already set based on MAS4 - */ - PPC_TLBSRX_DOT(0,R16) - beq htw_tlb_miss_done - - /* Now, we need to walk the page tables. First check if we are in - * range. - */ - rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4 - bne- htw_tlb_miss_fault - - /* Get the PGD pointer */ - cmpldi cr0,r15,0 - beq- htw_tlb_miss_fault - - /* Get to PGD entry */ - rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Get to PUD entry */ - rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Get to PMD entry */ - rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3 - clrrdi r10,r11,3 - ldx r15,r10,r15 - cmpdi cr0,r15,0 - bge htw_tlb_miss_fault - - /* Ok, we're all right, we can now create an indirect entry for - * a 1M or 256M page. - * - * The last trick is now that because we use "half" pages for - * the HTW (1M IND is 2K and 256M IND is 32K) we need to account - * for an added LSB bit to the RPN. For 64K pages, there is no - * problem as we already use 32K arrays (half PTE pages), but for - * 4K page we need to extract a bit from the virtual address and - * insert it into the "PA52" bit of the RPN. - */ - rlwimi r15,r16,32-9,20,20 - /* Now we build the MAS: - * - * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG - * MAS 1 : Almost fully setup - * - PID already updated by caller if necessary - * - TSIZE for now is base ind page size always - * MAS 2 : Use defaults - * MAS 3+7 : Needs to be done - */ - ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT) - - srdi r16,r10,32 - mtspr SPRN_MAS3,r10 - mtspr SPRN_MAS7,r16 - - tlbwe - -htw_tlb_miss_done: - /* We don't bother with restoring DEAR or ESR since we know we are - * level 0 and just going back to userland. They are only needed - * if you are going to take an access fault - */ - TLB_MISS_EPILOG_SUCCESS - rfi - -htw_tlb_miss_fault: - /* We need to check if it was an instruction miss. We know this - * though because r14 would contain -1 - */ - cmpdi cr0,r14,-1 - beq 1f - mtspr SPRN_DEAR,r16 - mtspr SPRN_ESR,r14 - TLB_MISS_EPILOG_ERROR - b exc_data_storage_book3e -1: TLB_MISS_EPILOG_ERROR - b exc_instruction_storage_book3e - /* * This is the guts of "any" level TLB miss handler for kernel linear * mapping misses. We are entered with: diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype index 54d655a647ce..8f3db6677457 100644 --- a/arch/powerpc/platforms/Kconfig.cputype +++ b/arch/powerpc/platforms/Kconfig.cputype @@ -176,6 +176,7 @@ config POWER10_CPU bool "POWER10" depends on PPC_BOOK3S_64 select ARCH_HAS_FAST_MULTIPLIER + select PPC_HAVE_PREFIXED_SUPPORT config E5500_CPU bool "Freescale e5500" @@ -449,6 +450,22 @@ config PPC_RADIX_MMU_DEFAULT If you're unsure, say Y. +config PPC_KERNEL_PREFIXED + depends on PPC_HAVE_PREFIXED_SUPPORT + depends on CC_HAS_PREFIXED + default n + bool "Build Kernel with Prefixed Instructions" + help + POWER10 and later CPUs support prefixed instructions, 8 byte + instructions that include large immediate, pc relative addressing, + and various floating point, vector, MMA. + + This option builds the kernel with prefixed instructions, and + allows a pc relative addressing option to be selected. + + Kernel support for prefixed instructions in applications and guests + is not affected by this option. + config PPC_KUEP bool "Kernel Userspace Execution Prevention" if !40x default y if !40x @@ -485,6 +502,9 @@ config PPC_MMU_NOHASH config PPC_HAVE_PMU_SUPPORT bool +config PPC_HAVE_PREFIXED_SUPPORT + bool + config PMU_SYSFS bool "Create PMU SPRs sysfs file" default n @@ -585,10 +605,10 @@ config CPU_LITTLE_ENDIAN endchoice config PPC64_ELF_ABI_V1 - def_bool PPC64 && CPU_BIG_ENDIAN + def_bool PPC64 && (CPU_BIG_ENDIAN && !PPC64_BIG_ENDIAN_ELF_ABI_V2) config PPC64_ELF_ABI_V2 - def_bool PPC64 && CPU_LITTLE_ENDIAN + def_bool PPC64 && !PPC64_ELF_ABI_V1 config PPC64_BOOT_WRAPPER def_bool n diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index 498d6efcb5ae..a78f5e1685d2 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -343,23 +343,6 @@ int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog) { int rc; - /* pseries error logs are in BE format, convert to cpu type */ - switch (hp_elog->id_type) { - case PSERIES_HP_ELOG_ID_DRC_COUNT: - hp_elog->_drc_u.drc_count = - be32_to_cpu(hp_elog->_drc_u.drc_count); - break; - case PSERIES_HP_ELOG_ID_DRC_INDEX: - hp_elog->_drc_u.drc_index = - be32_to_cpu(hp_elog->_drc_u.drc_index); - break; - case PSERIES_HP_ELOG_ID_DRC_IC: - hp_elog->_drc_u.ic.count = - be32_to_cpu(hp_elog->_drc_u.ic.count); - hp_elog->_drc_u.ic.index = - be32_to_cpu(hp_elog->_drc_u.ic.index); - } - switch (hp_elog->resource) { case PSERIES_HP_ELOG_RESOURCE_MEM: rc = dlpar_memory(hp_elog); diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index e0a7ac5db15d..12a6d154f4b4 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -748,7 +748,7 @@ int dlpar_cpu(struct pseries_hp_errorlog *hp_elog) u32 drc_index; int rc; - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); lock_device_hotplug(); diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 051a777ba1b2..dbb25d347fce 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -876,16 +876,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_ACTION_ADD: switch (hp_elog->id_type) { case PSERIES_HP_ELOG_ID_DRC_COUNT: - count = hp_elog->_drc_u.drc_count; + count = be32_to_cpu(hp_elog->_drc_u.drc_count); rc = dlpar_memory_add_by_count(count); break; case PSERIES_HP_ELOG_ID_DRC_INDEX: - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); rc = dlpar_memory_add_by_index(drc_index); break; case PSERIES_HP_ELOG_ID_DRC_IC: - count = hp_elog->_drc_u.ic.count; - drc_index = hp_elog->_drc_u.ic.index; + count = be32_to_cpu(hp_elog->_drc_u.ic.count); + drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index); rc = dlpar_memory_add_by_ic(count, drc_index); break; default: @@ -897,16 +897,16 @@ int dlpar_memory(struct pseries_hp_errorlog *hp_elog) case PSERIES_HP_ELOG_ACTION_REMOVE: switch (hp_elog->id_type) { case PSERIES_HP_ELOG_ID_DRC_COUNT: - count = hp_elog->_drc_u.drc_count; + count = be32_to_cpu(hp_elog->_drc_u.drc_count); rc = dlpar_memory_remove_by_count(count); break; case PSERIES_HP_ELOG_ID_DRC_INDEX: - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); rc = dlpar_memory_remove_by_index(drc_index); break; case PSERIES_HP_ELOG_ID_DRC_IC: - count = hp_elog->_drc_u.ic.count; - drc_index = hp_elog->_drc_u.ic.index; + count = be32_to_cpu(hp_elog->_drc_u.ic.count); + drc_index = be32_to_cpu(hp_elog->_drc_u.ic.index); rc = dlpar_memory_remove_by_ic(count, drc_index); break; default: diff --git a/arch/powerpc/platforms/pseries/plpks.c b/arch/powerpc/platforms/pseries/plpks.c index 25f95440a773..d1eb6f0433fe 100644 --- a/arch/powerpc/platforms/pseries/plpks.c +++ b/arch/powerpc/platforms/pseries/plpks.c @@ -18,15 +18,23 @@ #include #include #include - -#include "plpks.h" +#include +#include static u8 *ospassword; static u16 ospasswordlength; // Retrieved with H_PKS_GET_CONFIG +static u8 version; +static u16 objoverhead; static u16 maxpwsize; static u16 maxobjsize; +static s16 maxobjlabelsize; +static u32 totalsize; +static u32 usedspace; +static u32 supportedpolicies; +static u32 maxlargeobjectsize; +static u64 signedupdatealgorithms; struct plpks_auth { u8 version; @@ -113,7 +121,8 @@ static int plpks_gen_password(void) u8 *password, consumer = PLPKS_OS_OWNER; int rc; - password = kzalloc(maxpwsize, GFP_KERNEL); + // The password must not cross a page boundary, so we align to the next power of 2 + password = kzalloc(roundup_pow_of_two(maxpwsize), GFP_KERNEL); if (!password) return -ENOMEM; @@ -149,7 +158,9 @@ static struct plpks_auth *construct_auth(u8 consumer) if (consumer > PLPKS_OS_OWNER) return ERR_PTR(-EINVAL); - auth = kzalloc(struct_size(auth, password, maxpwsize), GFP_KERNEL); + // The auth structure must not cross a page boundary and must be + // 16 byte aligned. We align to the next largest power of 2 + auth = kzalloc(roundup_pow_of_two(struct_size(auth, password, maxpwsize)), GFP_KERNEL); if (!auth) return ERR_PTR(-ENOMEM); @@ -183,7 +194,8 @@ static struct label *construct_label(char *component, u8 varos, u8 *name, if (component && slen > sizeof(label->attr.prefix)) return ERR_PTR(-EINVAL); - label = kzalloc(sizeof(*label), GFP_KERNEL); + // The label structure must not cross a page boundary, so we align to the next power of 2 + label = kzalloc(roundup_pow_of_two(sizeof(*label)), GFP_KERNEL); if (!label) return ERR_PTR(-ENOMEM); @@ -203,32 +215,157 @@ static struct label *construct_label(char *component, u8 varos, u8 *name, static int _plpks_get_config(void) { unsigned long retbuf[PLPAR_HCALL_BUFSIZE] = { 0 }; - struct { + struct config { u8 version; u8 flags; - __be32 rsvd0; + __be16 rsvd0; + __be16 objoverhead; __be16 maxpwsize; __be16 maxobjlabelsize; __be16 maxobjsize; __be32 totalsize; __be32 usedspace; __be32 supportedpolicies; - __be64 rsvd1; - } __packed config; + __be32 maxlargeobjectsize; + __be64 signedupdatealgorithms; + u8 rsvd1[476]; + } __packed * config; size_t size; + int rc = 0; + + size = sizeof(*config); + + // Config struct must not cross a page boundary. So long as the struct + // size is a power of 2, this should be fine as alignment is guaranteed + config = kzalloc(size, GFP_KERNEL); + if (!config) { + rc = -ENOMEM; + goto err; + } + + rc = plpar_hcall(H_PKS_GET_CONFIG, retbuf, virt_to_phys(config), size); + + if (rc != H_SUCCESS) { + rc = pseries_status_to_err(rc); + goto err; + } + + version = config->version; + objoverhead = be16_to_cpu(config->objoverhead); + maxpwsize = be16_to_cpu(config->maxpwsize); + maxobjsize = be16_to_cpu(config->maxobjsize); + maxobjlabelsize = be16_to_cpu(config->maxobjlabelsize); + totalsize = be32_to_cpu(config->totalsize); + usedspace = be32_to_cpu(config->usedspace); + supportedpolicies = be32_to_cpu(config->supportedpolicies); + maxlargeobjectsize = be32_to_cpu(config->maxlargeobjectsize); + signedupdatealgorithms = be64_to_cpu(config->signedupdatealgorithms); + + // Validate that the numbers we get back match the requirements of the spec + if (maxpwsize < 32) { + pr_err("Invalid Max Password Size received from hypervisor (%d < 32)\n", maxpwsize); + rc = -EIO; + goto err; + } + + if (maxobjlabelsize < 255) { + pr_err("Invalid Max Object Label Size received from hypervisor (%d < 255)\n", + maxobjlabelsize); + rc = -EIO; + goto err; + } + + if (totalsize < 4096) { + pr_err("Invalid Total Size received from hypervisor (%d < 4096)\n", totalsize); + rc = -EIO; + goto err; + } + + if (version >= 3 && maxlargeobjectsize >= 65536 && maxobjsize != 0xFFFF) { + pr_err("Invalid Max Object Size (0x%x != 0xFFFF)\n", maxobjsize); + rc = -EIO; + goto err; + } + +err: + kfree(config); + return rc; +} + +u8 plpks_get_version(void) +{ + return version; +} + +u16 plpks_get_objoverhead(void) +{ + return objoverhead; +} + +u16 plpks_get_maxpwsize(void) +{ + return maxpwsize; +} + +u16 plpks_get_maxobjectsize(void) +{ + return maxobjsize; +} + +u16 plpks_get_maxobjectlabelsize(void) +{ + return maxobjlabelsize; +} + +u32 plpks_get_totalsize(void) +{ + return totalsize; +} + +u32 plpks_get_usedspace(void) +{ + // Unlike other config values, usedspace regularly changes as objects + // are updated, so we need to refresh. + int rc = _plpks_get_config(); + if (rc) { + pr_err("Couldn't get config, rc: %d\n", rc); + return 0; + } + return usedspace; +} + +u32 plpks_get_supportedpolicies(void) +{ + return supportedpolicies; +} + +u32 plpks_get_maxlargeobjectsize(void) +{ + return maxlargeobjectsize; +} + +u64 plpks_get_signedupdatealgorithms(void) +{ + return signedupdatealgorithms; +} + +u16 plpks_get_passwordlen(void) +{ + return ospasswordlength; +} + +bool plpks_is_available(void) +{ int rc; - size = sizeof(config); + if (!firmware_has_feature(FW_FEATURE_LPAR)) + return false; - rc = plpar_hcall(H_PKS_GET_CONFIG, retbuf, virt_to_phys(&config), size); + rc = _plpks_get_config(); + if (rc) + return false; - if (rc != H_SUCCESS) - return pseries_status_to_err(rc); - - maxpwsize = be16_to_cpu(config.maxpwsize); - maxobjsize = be16_to_cpu(config.maxobjsize); - - return 0; + return true; } static int plpks_confirm_object_flushed(struct label *label, diff --git a/arch/powerpc/platforms/pseries/pmem.c b/arch/powerpc/platforms/pseries/pmem.c index 3c290b9ed01b..0f1d45f32e4a 100644 --- a/arch/powerpc/platforms/pseries/pmem.c +++ b/arch/powerpc/platforms/pseries/pmem.c @@ -121,7 +121,7 @@ int dlpar_hp_pmem(struct pseries_hp_errorlog *hp_elog) return -EINVAL; } - drc_index = hp_elog->_drc_u.drc_index; + drc_index = be32_to_cpu(hp_elog->_drc_u.drc_index); lock_device_hotplug(); diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c index df0772619200..c2e6b3a0469d 100644 --- a/arch/powerpc/platforms/pseries/setup.c +++ b/arch/powerpc/platforms/pseries/setup.c @@ -342,8 +342,8 @@ static int alloc_dispatch_log_kmem_cache(void) { void (*ctor)(void *) = get_dtl_cache_ctor(); - dtl_cache = kmem_cache_create("dtl", DISPATCH_LOG_BYTES, - DISPATCH_LOG_BYTES, 0, ctor); + dtl_cache = kmem_cache_create_usercopy("dtl", DISPATCH_LOG_BYTES, + DISPATCH_LOG_BYTES, 0, 0, DISPATCH_LOG_BYTES, ctor); if (!dtl_cache) { pr_warn("Failed to create dispatch trace log buffer cache\n"); pr_warn("Stolen time statistics will be unreliable\n"); diff --git a/arch/powerpc/sysdev/xics/icp-native.c b/arch/powerpc/sysdev/xics/icp-native.c index edc17b6b1cc2..9b2238d73003 100644 --- a/arch/powerpc/sysdev/xics/icp-native.c +++ b/arch/powerpc/sysdev/xics/icp-native.c @@ -236,6 +236,8 @@ static int __init icp_native_map_one_cpu(int hw_id, unsigned long addr, rname = kasprintf(GFP_KERNEL, "CPU %d [0x%x] Interrupt Presentation", cpu, hw_id); + if (!rname) + return -ENOMEM; if (!request_mem_region(addr, size, rname)) { pr_warn("icp_native: Could not reserve ICP MMIO for CPU %d, interrupt server #0x%x\n", cpu, hw_id); diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c index 75fa98221d48..af105e1bc3fc 100644 --- a/arch/powerpc/xmon/ppc-dis.c +++ b/arch/powerpc/xmon/ppc-dis.c @@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr) bool insn_is_short; ppc_cpu_t dialect; - dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON - | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC; + dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON; - if (cpu_has_feature(CPU_FTRS_POWER5)) - dialect |= PPC_OPCODE_POWER5; + if (IS_ENABLED(CONFIG_PPC64)) + dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL | + PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 | + PPC_OPCODE_POWER9; - if (cpu_has_feature(CPU_FTRS_CELL)) - dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_TM)) + dialect |= PPC_OPCODE_HTM; - if (cpu_has_feature(CPU_FTRS_POWER6)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC); + if (cpu_has_feature(CPU_FTR_ALTIVEC)) + dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2; - if (cpu_has_feature(CPU_FTRS_POWER7)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER8)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX); - - if (cpu_has_feature(CPU_FTRS_POWER9)) - dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 - | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM - | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 - | PPC_OPCODE_VSX | PPC_OPCODE_VSX3); + if (cpu_has_feature(CPU_FTR_VSX)) + dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3; /* Get the major opcode of the insn. */ opcode = NULL; diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index d702359f8ab5..b133efc13466 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -216,6 +216,11 @@ config GENERIC_HWEIGHT config FIX_EARLYCON_MEM def_bool MMU +config ILLEGAL_POINTER_VALUE + hex + default 0 if 32BIT + default 0xdead000000000000 if 64BIT + config PGTABLE_LEVELS int default 5 if 64BIT diff --git a/arch/riscv/include/asm/sparsemem.h b/arch/riscv/include/asm/sparsemem.h index 63acaecc3374..2f901a410586 100644 --- a/arch/riscv/include/asm/sparsemem.h +++ b/arch/riscv/include/asm/sparsemem.h @@ -7,7 +7,7 @@ #ifdef CONFIG_64BIT #define MAX_PHYSMEM_BITS 56 #else -#define MAX_PHYSMEM_BITS 34 +#define MAX_PHYSMEM_BITS 32 #endif /* CONFIG_64BIT */ #define SECTION_SIZE_BITS 27 #endif /* CONFIG_SPARSEMEM */ diff --git a/arch/riscv/kernel/elf_kexec.c b/arch/riscv/kernel/elf_kexec.c index b3b96ff46d19..88721bea81fc 100644 --- a/arch/riscv/kernel/elf_kexec.c +++ b/arch/riscv/kernel/elf_kexec.c @@ -444,6 +444,12 @@ int arch_kexec_apply_relocations_add(struct purgatory_info *pi, *(u32 *)loc = CLEAN_IMM(CJTYPE, *(u32 *)loc) | ENCODE_CJTYPE_IMM(val - addr); break; + case R_RISCV_ADD16: + *(u16 *)loc += val; + break; + case R_RISCV_SUB16: + *(u16 *)loc -= val; + break; case R_RISCV_ADD32: *(u32 *)loc += val; break; diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S index 4bf6c449d78b..1a017ad53343 100644 --- a/arch/riscv/kernel/head.S +++ b/arch/riscv/kernel/head.S @@ -307,6 +307,9 @@ clear_bss_done: #else mv a0, s1 #endif /* CONFIG_BUILTIN_DTB */ + /* Set trap vector to spin forever to help debug */ + la a3, .Lsecondary_park + csrw CSR_TVEC, a3 call setup_vm #ifdef CONFIG_MMU la a0, early_pg_dir diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c index 3348a61de7d9..2932791e9388 100644 --- a/arch/riscv/kernel/perf_callchain.c +++ b/arch/riscv/kernel/perf_callchain.c @@ -62,7 +62,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry, perf_callchain_store(entry, regs->epc); fp = user_backtrace(entry, fp, regs->ra); - while (fp && !(fp & 0x3) && entry->nr < entry->max_stack) + while (fp && !(fp & 0x7) && entry->nr < entry->max_stack) fp = user_backtrace(entry, fp, 0); } diff --git a/arch/riscv/kernel/stacktrace.c b/arch/riscv/kernel/stacktrace.c index 0d3f00eb0bae..10e311b2759d 100644 --- a/arch/riscv/kernel/stacktrace.c +++ b/arch/riscv/kernel/stacktrace.c @@ -32,6 +32,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, bool (*fn)(void *, unsigned long), void *arg) { unsigned long fp, sp, pc; + int graph_idx = 0; int level = 0; if (regs) { @@ -68,7 +69,7 @@ void notrace walk_stackframe(struct task_struct *task, struct pt_regs *regs, pc = regs->ra; } else { fp = frame->fp; - pc = ftrace_graph_ret_addr(current, NULL, frame->ra, + pc = ftrace_graph_ret_addr(current, &graph_idx, frame->ra, &frame->ra); if (pc == (unsigned long)ret_from_exception) { if (unlikely(!__kernel_text_address(pc) || !fn(arg, pc))) diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c index f96991d230bf..bc575f692150 100644 --- a/arch/riscv/kvm/vcpu_sbi.c +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -67,8 +67,8 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run) run->riscv_sbi.args[3] = cp->a3; run->riscv_sbi.args[4] = cp->a4; run->riscv_sbi.args[5] = cp->a5; - run->riscv_sbi.ret[0] = cp->a0; - run->riscv_sbi.ret[1] = cp->a1; + run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED; + run->riscv_sbi.ret[1] = 0; } void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu, diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index 274bc6dd839f..05d7d3647964 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -60,26 +60,27 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr) static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault) { + if (!user_mode(regs)) { + no_context(regs, addr); + return; + } + if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return the userspace * (which will retry the fault, or kill us if we got oom-killed). */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } pagefault_out_of_memory(); return; } else if (fault & VM_FAULT_SIGBUS) { /* Kernel mode? Handle exceptions or die */ - if (!user_mode(regs)) { - no_context(regs, addr); - return; - } do_trap(regs, SIGBUS, BUS_ADRERR, addr); return; + } else if (fault & VM_FAULT_SIGSEGV) { + do_trap(regs, SIGSEGV, SEGV_MAPERR, addr); + return; } + BUG(); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 7ba5c244f3a0..ba2210b553f9 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -816,7 +816,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir, PMD_SIZE, PAGE_KERNEL_EXEC); /* Map the data in RAM */ - end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size; + end_va = kernel_map.virt_addr + kernel_map.size; for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE) create_pgd_mapping(pgdir, va, kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)), @@ -947,7 +947,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa) phys_ram_base = CONFIG_PHYS_RAM_BASE; kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE; - kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata); + kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start); kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom; #else diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c index 4c4ac563326b..66ee5f00ec54 100644 --- a/arch/riscv/net/bpf_jit_comp64.c +++ b/arch/riscv/net/bpf_jit_comp64.c @@ -542,8 +542,8 @@ static void emit_atomic(u8 rd, u8 rs, s16 off, s32 imm, bool is64, rv_lr_w(r0, 0, rd, 0, 0), ctx); jmp_offset = ninsns_rvoff(8); emit(rv_bne(RV_REG_T2, r0, jmp_offset >> 1), ctx); - emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 0) : - rv_sc_w(RV_REG_T3, rs, rd, 0, 0), ctx); + emit(is64 ? rv_sc_d(RV_REG_T3, rs, rd, 0, 1) : + rv_sc_w(RV_REG_T3, rs, rd, 0, 1), ctx); jmp_offset = ninsns_rvoff(-6); emit(rv_bne(RV_REG_T3, 0, jmp_offset >> 1), ctx); emit(rv_fence(0x3, 0x3), ctx); diff --git a/arch/s390/include/asm/facility.h b/arch/s390/include/asm/facility.h index 94b6919026df..953d42205ea8 100644 --- a/arch/s390/include/asm/facility.h +++ b/arch/s390/include/asm/facility.h @@ -60,8 +60,10 @@ static inline int test_facility(unsigned long nr) unsigned long facilities_als[] = { FACILITIES_ALS }; if (__builtin_constant_p(nr) && nr < sizeof(facilities_als) * 8) { - if (__test_facility(nr, &facilities_als)) - return 1; + if (__test_facility(nr, &facilities_als)) { + if (!__is_defined(__DECOMPRESSOR)) + return 1; + } } return __test_facility(nr, &stfle_fac_list); } diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h index b9da71632827..ea340b901839 100644 --- a/arch/s390/include/asm/perf_event.h +++ b/arch/s390/include/asm/perf_event.h @@ -75,6 +75,7 @@ struct perf_sf_sde_regs { #define SAMPLE_FREQ_MODE(hwc) (SAMPL_FLAGS(hwc) & PERF_CPUM_SF_FREQ_MODE) #define perf_arch_fetch_caller_regs(regs, __ip) do { \ + (regs)->psw.mask = 0; \ (regs)->psw.addr = (__ip); \ (regs)->gprs[15] = (unsigned long)__builtin_frame_address(0) - \ offsetof(struct stack_frame, back_chain); \ diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h index c907f747d2a0..26861b09293f 100644 --- a/arch/s390/include/asm/processor.h +++ b/arch/s390/include/asm/processor.h @@ -250,8 +250,8 @@ static inline void __load_psw(psw_t psw) */ static __always_inline void __load_psw_mask(unsigned long mask) { + psw_t psw __uninitialized; unsigned long addr; - psw_t psw; psw.mask = mask; diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h index be3ef9dd6972..6abcb46a8dfe 100644 --- a/arch/s390/include/asm/uv.h +++ b/arch/s390/include/asm/uv.h @@ -387,7 +387,10 @@ static inline int share(unsigned long addr, u16 cmd) if (!uv_call(0, (u64)&uvcb)) return 0; - return -EINVAL; + pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n", + uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare", + uvcb.header.rc, uvcb.header.rrc); + panic("System security cannot be guaranteed unless the system panics now.\n"); } /* diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c index 9693c8630e73..b3cb256ec669 100644 --- a/arch/s390/kernel/early.c +++ b/arch/s390/kernel/early.c @@ -237,15 +237,9 @@ static inline void save_vector_registers(void) #endif } -static inline void setup_control_registers(void) +static inline void setup_low_address_protection(void) { - unsigned long reg; - - __ctl_store(reg, 0, 0); - reg |= CR0_LOW_ADDRESS_PROTECTION; - reg |= CR0_EMERGENCY_SIGNAL_SUBMASK; - reg |= CR0_EXTERNAL_CALL_SUBMASK; - __ctl_load(reg, 0, 0); + __ctl_set_bit(0, 28); } static inline void setup_access_registers(void) @@ -304,7 +298,7 @@ void __init startup_init(void) save_vector_registers(); setup_topology(); sclp_early_detect(); - setup_control_registers(); + setup_low_address_protection(); setup_access_registers(); lockdep_on(); } diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index ce886a03545a..f3b0a106f722 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1432,7 +1432,7 @@ static int aux_output_begin(struct perf_output_handle *handle, unsigned long head, base, offset; struct hws_trailer_entry *te; - if (WARN_ON_ONCE(handle->head & ~PAGE_MASK)) + if (handle->head & ~PAGE_MASK) return -EINVAL; aux->head = handle->head >> PAGE_SHIFT; @@ -1613,7 +1613,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) unsigned long num_sdb; aux = perf_get_aux(handle); - if (WARN_ON_ONCE(!aux)) + if (!aux) return; /* Inform user space new data arrived */ @@ -1635,7 +1635,7 @@ static void hw_collect_aux(struct cpu_hw_sf *cpuhw) __func__); break; } - if (WARN_ON_ONCE(!aux)) + if (!aux) return; /* Update head and alert_mark to new position */ @@ -1870,12 +1870,8 @@ static void cpumsf_pmu_start(struct perf_event *event, int flags) { struct cpu_hw_sf *cpuhw = this_cpu_ptr(&cpu_hw_sf); - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + if (!(event->hw.state & PERF_HES_STOPPED)) return; - - if (flags & PERF_EF_RELOAD) - WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); - perf_pmu_disable(event->pmu); event->hw.state = 0; cpuhw->lsctl.cs = 1; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 0031325ce4bc..436dbf4d743d 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -1007,12 +1007,12 @@ void __init smp_fill_possible_mask(void) void __init smp_prepare_cpus(unsigned int max_cpus) { - /* request the 0x1201 emergency signal external interrupt */ if (register_external_irq(EXT_IRQ_EMERGENCY_SIG, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1201"); - /* request the 0x1202 external call external interrupt */ + ctl_set_bit(0, 14); if (register_external_irq(EXT_IRQ_EXTERNAL_CALL, do_ext_call_interrupt)) panic("Couldn't request external interrupt 0x1202"); + ctl_set_bit(0, 13); } void __init smp_prepare_boot_cpu(void) diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c index 5caa0ed2b594..1ae7a0403804 100644 --- a/arch/s390/kernel/uv.c +++ b/arch/s390/kernel/uv.c @@ -172,36 +172,36 @@ int uv_convert_owned_from_secure(unsigned long paddr) } /* - * Calculate the expected ref_count for a page that would otherwise have no + * Calculate the expected ref_count for a folio that would otherwise have no * further pins. This was cribbed from similar functions in other places in * the kernel, but with some slight modifications. We know that a secure - * page can not be a huge page for example. + * folio can not be a large folio, for example. */ -static int expected_page_refs(struct page *page) +static int expected_folio_refs(struct folio *folio) { int res; - res = page_mapcount(page); - if (PageSwapCache(page)) { + res = folio_mapcount(folio); + if (folio_test_swapcache(folio)) { res++; - } else if (page_mapping(page)) { + } else if (folio_mapping(folio)) { res++; - if (page_has_private(page)) + if (folio->private) res++; } return res; } -static int make_page_secure(struct page *page, struct uv_cb_header *uvcb) +static int make_folio_secure(struct folio *folio, struct uv_cb_header *uvcb) { int expected, cc = 0; - if (PageWriteback(page)) + if (folio_test_writeback(folio)) return -EAGAIN; - expected = expected_page_refs(page); - if (!page_ref_freeze(page, expected)) + expected = expected_folio_refs(folio); + if (!folio_ref_freeze(folio, expected)) return -EBUSY; - set_bit(PG_arch_1, &page->flags); + set_bit(PG_arch_1, &folio->flags); /* * If the UVC does not succeed or fail immediately, we don't want to * loop for long, or we might get stall notifications. @@ -211,9 +211,9 @@ static int make_page_secure(struct page *page, struct uv_cb_header *uvcb) * -EAGAIN and we let the callers deal with it. */ cc = __uv_call(0, (u64)uvcb); - page_ref_unfreeze(page, expected); + folio_ref_unfreeze(folio, expected); /* - * Return -ENXIO if the page was not mapped, -EINVAL for other errors. + * Return -ENXIO if the folio was not mapped, -EINVAL for other errors. * If busy or partially completed, return -EAGAIN. */ if (cc == UVC_CC_OK) @@ -261,7 +261,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb) bool local_drain = false; spinlock_t *ptelock; unsigned long uaddr; - struct page *page; + struct folio *folio; pte_t *ptep; int rc; @@ -288,15 +288,26 @@ again: rc = -ENXIO; ptep = get_locked_pte(gmap->mm, uaddr, &ptelock); if (pte_present(*ptep) && !(pte_val(*ptep) & _PAGE_INVALID) && pte_write(*ptep)) { - page = pte_page(*ptep); + folio = page_folio(pte_page(*ptep)); + rc = -EINVAL; + if (folio_test_large(folio)) + goto unlock; rc = -EAGAIN; - if (trylock_page(page)) { + if (folio_trylock(folio)) { if (should_export_before_import(uvcb, gmap->mm)) - uv_convert_from_secure(page_to_phys(page)); - rc = make_page_secure(page, uvcb); - unlock_page(page); + uv_convert_from_secure(PFN_PHYS(folio_pfn(folio))); + rc = make_folio_secure(folio, uvcb); + folio_unlock(folio); } + + /* + * Once we drop the PTL, the folio may get unmapped and + * freed immediately. We need a temporary reference. + */ + if (rc == -EAGAIN) + folio_get(folio); } +unlock: pte_unmap_unlock(ptep, ptelock); out: mmap_read_unlock(gmap->mm); @@ -306,10 +317,11 @@ out: * If we are here because the UVC returned busy or partial * completion, this is just a useless check, but it is safe. */ - wait_on_page_writeback(page); + folio_wait_writeback(folio); + folio_put(folio); } else if (rc == -EBUSY) { /* - * If we have tried a local drain and the page refcount + * If we have tried a local drain and the folio refcount * still does not match our expected safe value, try with a * system wide drain. This is needed if the pagevecs holding * the page are on a different CPU. @@ -320,7 +332,7 @@ out: return -EAGAIN; } /* - * We are here if the page refcount does not match the + * We are here if the folio refcount does not match the * expected safe value. The main culprits are usually * pagevecs. With lru_add_drain() we drain the pagevecs * on the local CPU so that hopefully the refcount will diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S index 729d4f949cfe..52d6e5d1b453 100644 --- a/arch/s390/kernel/vmlinux.lds.S +++ b/arch/s390/kernel/vmlinux.lds.S @@ -71,6 +71,15 @@ SECTIONS . = ALIGN(PAGE_SIZE); __end_ro_after_init = .; + .data.rel.ro : { + *(.data.rel.ro .data.rel.ro.*) + } + .got : { + __got_start = .; + *(.got) + __got_end = .; + } + RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE) BOOT_DATA_PRESERVED diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c index 3c65b8258ae6..2cc3ec034046 100644 --- a/arch/s390/kvm/diag.c +++ b/arch/s390/kvm/diag.c @@ -77,7 +77,7 @@ static int __diag_page_ref_service(struct kvm_vcpu *vcpu) vcpu->stat.instruction_diagnose_258++; if (vcpu->run->s.regs.gprs[rx] & 7) return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION); - rc = read_guest(vcpu, vcpu->run->s.regs.gprs[rx], rx, &parm, sizeof(parm)); + rc = read_guest_real(vcpu, vcpu->run->s.regs.gprs[rx], &parm, sizeof(parm)); if (rc) return kvm_s390_inject_prog_cond(vcpu, rc); if (parm.parm_version != 2 || parm.parm_len < 5 || parm.code != 0x258) diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c index 3beceff5f1c0..e88803e3f271 100644 --- a/arch/s390/kvm/gaccess.c +++ b/arch/s390/kvm/gaccess.c @@ -1001,6 +1001,8 @@ static int access_guest_page(struct kvm *kvm, enum gacc_mode mode, gpa_t gpa, const gfn_t gfn = gpa_to_gfn(gpa); int rc; + if (!gfn_to_memslot(kvm, gfn)) + return PGM_ADDRESSING; if (mode == GACC_STORE) rc = kvm_write_guest_page(kvm, gfn, data, offset, len); else @@ -1158,6 +1160,8 @@ int access_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, gra += fragment_len; data += fragment_len; } + if (rc > 0) + vcpu->arch.pgm.code = rc; return rc; } diff --git a/arch/s390/kvm/gaccess.h b/arch/s390/kvm/gaccess.h index 9408d6cc8e2c..9b6de683dc5e 100644 --- a/arch/s390/kvm/gaccess.h +++ b/arch/s390/kvm/gaccess.h @@ -402,11 +402,12 @@ int read_guest_abs(struct kvm_vcpu *vcpu, unsigned long gpa, void *data, * @len: number of bytes to copy * * Copy @len bytes from @data (kernel space) to @gra (guest real address). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest low address and key protection are not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying from @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to guest memory. */ @@ -425,11 +426,12 @@ int write_guest_real(struct kvm_vcpu *vcpu, unsigned long gra, void *data, * @len: number of bytes to copy * * Copy @len bytes from @gra (guest real address) to @data (kernel space). - * It is up to the caller to ensure that the entire guest memory range is - * valid memory before calling this function. * Guest key protection is not checked. * - * Returns zero on success or -EFAULT on error. + * Returns zero on success, -EFAULT when copying to @data failed, or + * PGM_ADRESSING in case @gra is outside a memslot. In this case, pgm check info + * is also stored to allow injecting into the guest (if applicable) using + * kvm_s390_inject_prog_cond(). * * If an error occurs data may have been copied partially to kernel space. */ diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c index 9141ed4c52e9..02e030ad38c5 100644 --- a/arch/s390/mm/cmm.c +++ b/arch/s390/mm/cmm.c @@ -95,11 +95,12 @@ static long cmm_alloc_pages(long nr, long *counter, (*counter)++; spin_unlock(&cmm_lock); nr--; + cond_resched(); } return nr; } -static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) +static long __cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) { struct cmm_page_array *pa; unsigned long addr; @@ -123,6 +124,21 @@ static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) return nr; } +static long cmm_free_pages(long nr, long *counter, struct cmm_page_array **list) +{ + long inc = 0; + + while (nr) { + inc = min(256L, nr); + nr -= inc; + inc = __cmm_free_pages(inc, counter, list); + if (inc) + break; + cond_resched(); + } + return nr + inc; +} + static int cmm_oom_notify(struct notifier_block *self, unsigned long dummy, void *parm) { diff --git a/arch/s390/pci/pci_event.c b/arch/s390/pci/pci_event.c index b9324ca2eb94..b3961f1016ea 100644 --- a/arch/s390/pci/pci_event.c +++ b/arch/s390/pci/pci_event.c @@ -272,18 +272,19 @@ static void __zpci_event_error(struct zpci_ccdf_err *ccdf) goto no_pdev; switch (ccdf->pec) { - case 0x003a: /* Service Action or Error Recovery Successful */ + case 0x002a: /* Error event concerns FMB */ + case 0x002b: + case 0x002c: + break; + case 0x0040: /* Service Action or Error Recovery Failed */ + case 0x003b: + zpci_event_io_failure(pdev, pci_channel_io_perm_failure); + break; + default: /* PCI function left in the error state attempt to recover */ ers_res = zpci_event_attempt_error_recovery(pdev); if (ers_res != PCI_ERS_RESULT_RECOVERED) zpci_event_io_failure(pdev, pci_channel_io_perm_failure); break; - default: - /* - * Mark as frozen not permanently failed because the device - * could be subsequently recovered by the platform. - */ - zpci_event_io_failure(pdev, pci_channel_io_frozen); - break; } pci_dev_put(pdev); no_pdev: diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 04c19ab93a32..393bcc2c3dc2 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -268,33 +268,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq, } } -int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs, + unsigned long *bit) { - struct zpci_dev *zdev = to_zpci(pdev); - unsigned int hwirq, msi_vecs, cpu; - unsigned long bit; - struct msi_desc *msi; - struct msi_msg msg; - int cpu_addr; - int rc, irq; - - zdev->aisb = -1UL; - zdev->msi_first_bit = -1U; - if (type == PCI_CAP_ID_MSI && nvec > 1) - return 1; - msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); - if (irq_delivery == DIRECTED) { /* Allocate cpu vector bits */ - bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); - if (bit == -1UL) + *bit = airq_iv_alloc(zpci_ibv[0], msi_vecs); + if (*bit == -1UL) return -EIO; } else { /* Allocate adapter summary indicator bit */ - bit = airq_iv_alloc_bit(zpci_sbv); - if (bit == -1UL) + *bit = airq_iv_alloc_bit(zpci_sbv); + if (*bit == -1UL) return -EIO; - zdev->aisb = bit; + zdev->aisb = *bit; /* Create adapter interrupt vector */ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL); @@ -302,27 +289,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) return -ENOMEM; /* Wire up shortcut pointer */ - zpci_ibv[bit] = zdev->aibv; + zpci_ibv[*bit] = zdev->aibv; /* Each function has its own interrupt vector */ - bit = 0; + *bit = 0; + } + return 0; +} + +int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) +{ + unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu; + struct zpci_dev *zdev = to_zpci(pdev); + struct msi_desc *msi; + struct msi_msg msg; + unsigned long bit; + int cpu_addr; + int rc, irq; + + zdev->aisb = -1UL; + zdev->msi_first_bit = -1U; + + msi_vecs = min_t(unsigned int, nvec, zdev->max_msi); + if (msi_vecs < nvec) { + pr_info("%s requested %d irqs, allocate system limit of %d", + pci_name(pdev), nvec, zdev->max_msi); } - /* Request MSI interrupts */ + rc = __alloc_airq(zdev, msi_vecs, &bit); + if (rc < 0) + return rc; + + /* + * Request MSI interrupts: + * When using MSI, nvec_used interrupt sources and their irq + * descriptors are controlled through one msi descriptor. + * Thus the outer loop over msi descriptors shall run only once, + * while two inner loops iterate over the interrupt vectors. + * When using MSI-X, each interrupt vector/irq descriptor + * is bound to exactly one msi descriptor (nvec_used is one). + * So the inner loops are executed once, while the outer iterates + * over the MSI-X descriptors. + */ hwirq = bit; msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) { - rc = -EIO; if (hwirq - bit >= msi_vecs) break; - irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE, - (irq_delivery == DIRECTED) ? - msi->affinity : NULL); + irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used); + irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE, + (irq_delivery == DIRECTED) ? + msi->affinity : NULL); if (irq < 0) return -ENOMEM; - rc = irq_set_msi_desc(irq, msi); - if (rc) - return rc; - irq_set_chip_and_handler(irq, &zpci_irq_chip, - handle_percpu_irq); + + for (i = 0; i < irqs_per_msi; i++) { + rc = irq_set_msi_desc_off(irq, i, msi); + if (rc) + return rc; + irq_set_chip_and_handler(irq + i, &zpci_irq_chip, + handle_percpu_irq); + } + msg.data = hwirq - bit; if (irq_delivery == DIRECTED) { if (msi->affinity) @@ -335,31 +361,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type) msg.address_lo |= (cpu_addr << 8); for_each_possible_cpu(cpu) { - airq_iv_set_data(zpci_ibv[cpu], hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zpci_ibv[cpu], + hwirq + i, irq + i); } } else { msg.address_lo = zdev->msi_addr & 0xffffffff; - airq_iv_set_data(zdev->aibv, hwirq, irq); + for (i = 0; i < irqs_per_msi; i++) + airq_iv_set_data(zdev->aibv, hwirq + i, irq + i); } msg.address_hi = zdev->msi_addr >> 32; pci_write_msi_msg(irq, &msg); - hwirq++; + hwirq += irqs_per_msi; } zdev->msi_first_bit = bit; - zdev->msi_nr_irqs = msi_vecs; + zdev->msi_nr_irqs = hwirq - bit; rc = zpci_set_irq(zdev); if (rc) return rc; - return (msi_vecs == nvec) ? 0 : msi_vecs; + return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs; } void arch_teardown_msi_irqs(struct pci_dev *pdev) { struct zpci_dev *zdev = to_zpci(pdev); struct msi_desc *msi; + unsigned int i; int rc; /* Disable interrupts */ @@ -369,8 +399,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev) /* Release MSI interrupts */ msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) { - irq_set_msi_desc(msi->irq, NULL); - irq_free_desc(msi->irq); + for (i = 0; i < msi->nvec_used; i++) { + irq_set_msi_desc(msi->irq + i, NULL); + irq_free_desc(msi->irq + i); + } msi->msg.address_lo = 0; msi->msg.address_hi = 0; msi->msg.data = 0; diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h index a67abebd4359..1b86d02a8455 100644 --- a/arch/sparc/include/asm/oplib_64.h +++ b/arch/sparc/include/asm/oplib_64.h @@ -247,6 +247,7 @@ void prom_sun4v_guest_soft_state(void); int prom_ihandle2path(int handle, char *buffer, int bufsize); /* Client interface level routines. */ +void prom_cif_init(void *cif_handler); void p1275_cmd_direct(unsigned long *); #endif /* !(__SPARC64_OPLIB_H) */ diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c index 103aa9104318..f7b8a1a865b8 100644 --- a/arch/sparc/prom/init_64.c +++ b/arch/sparc/prom/init_64.c @@ -26,9 +26,6 @@ phandle prom_chosen_node; * routines in the prom library. * It gets passed the pointer to the PROM vector. */ - -extern void prom_cif_init(void *); - void __init prom_init(void *cif_handler) { phandle node; diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c index 889aa602f8d8..51c3f984bbf7 100644 --- a/arch/sparc/prom/p1275.c +++ b/arch/sparc/prom/p1275.c @@ -49,7 +49,7 @@ void p1275_cmd_direct(unsigned long *args) local_irq_restore(flags); } -void prom_cif_init(void *cif_handler, void *cif_stack) +void prom_cif_init(void *cif_handler) { p1275buf.prom_cif_handler = (void (*)(long *))cif_handler; } diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c index 95ad6b190d1d..6b4faca401ea 100644 --- a/arch/um/drivers/line.c +++ b/arch/um/drivers/line.c @@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init, parse_chan_pair(NULL, line, n, opts, error_out); err = 0; } + *error_out = "configured as 'none'"; } else { char *new = kstrdup(init, GFP_KERNEL); if (!new) { @@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init, } } if (err) { + *error_out = "failed to parse channel pair"; line->init_str = NULL; line->valid = 0; kfree(new); diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c index 13a22a461305..1203f5078cb5 100644 --- a/arch/um/drivers/ubd_kern.c +++ b/arch/um/drivers/ubd_kern.c @@ -456,43 +456,31 @@ static int bulk_req_safe_read( return n; } -/* Called without dev->lock held, and only in interrupt context. */ -static void ubd_handler(void) +static void ubd_end_request(struct io_thread_req *io_req) { - int n; - int count; - - while(1){ - n = bulk_req_safe_read( - thread_fd, - irq_req_buffer, - &irq_remainder, - &irq_remainder_size, - UBD_REQ_BUFFER_SIZE - ); - if (n < 0) { - if(n == -EAGAIN) - break; - printk(KERN_ERR "spurious interrupt in ubd_handler, " - "err = %d\n", -n); - return; - } - for (count = 0; count < n/sizeof(struct io_thread_req *); count++) { - struct io_thread_req *io_req = (*irq_req_buffer)[count]; - - if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) { - blk_queue_max_discard_sectors(io_req->req->q, 0); - blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); - } - blk_mq_end_request(io_req->req, io_req->error); - kfree(io_req); - } + if (io_req->error == BLK_STS_NOTSUPP) { + if (req_op(io_req->req) == REQ_OP_DISCARD) + blk_queue_max_discard_sectors(io_req->req->q, 0); + else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES) + blk_queue_max_write_zeroes_sectors(io_req->req->q, 0); } + blk_mq_end_request(io_req->req, io_req->error); + kfree(io_req); } static irqreturn_t ubd_intr(int irq, void *dev) { - ubd_handler(); + int len, i; + + while ((len = bulk_req_safe_read(thread_fd, irq_req_buffer, + &irq_remainder, &irq_remainder_size, + UBD_REQ_BUFFER_SIZE)) >= 0) { + for (i = 0; i < len / sizeof(struct io_thread_req *); i++) + ubd_end_request((*irq_req_buffer)[i]); + } + + if (len < 0 && len != -EAGAIN) + pr_err("spurious interrupt in %s, err = %d\n", __func__, len); return IRQ_HANDLED; } diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c index 3e270da6b6f6..c8c4ef94c753 100644 --- a/arch/um/kernel/time.c +++ b/arch/um/kernel/time.c @@ -874,9 +874,9 @@ int setup_time_travel_start(char *str) return 1; } -__setup("time-travel-start", setup_time_travel_start); +__setup("time-travel-start=", setup_time_travel_start); __uml_help(setup_time_travel_start, -"time-travel-start=\n" +"time-travel-start=\n" "Configure the UML instance's wall clock to start at this value rather than\n" "the host's wall clock at the time of UML boot.\n"); #endif diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c index 24a403a70a02..850d21e6473e 100644 --- a/arch/um/os-Linux/signal.c +++ b/arch/um/os-Linux/signal.c @@ -8,6 +8,7 @@ #include #include +#include #include #include #include @@ -65,9 +66,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc) int signals_enabled; #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT -static int signals_blocked; -#else -#define signals_blocked 0 +static int signals_blocked, signals_blocked_pending; #endif static unsigned int signals_pending; static unsigned int signals_active = 0; @@ -76,14 +75,27 @@ void sig_handler(int sig, struct siginfo *si, mcontext_t *mc) { int enabled = signals_enabled; - if ((signals_blocked || !enabled) && (sig == SIGIO)) { +#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT + if ((signals_blocked || + __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) && + (sig == SIGIO)) { + /* increment so unblock will do another round */ + __atomic_add_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST); + return; + } +#endif + + if (!enabled && (sig == SIGIO)) { /* * In TT_MODE_EXTERNAL, need to still call time-travel - * handlers unless signals are also blocked for the - * external time message processing. This will mark - * signals_pending by itself (only if necessary.) + * handlers. This will mark signals_pending by itself + * (only if necessary.) + * Note we won't get here if signals are hard-blocked + * (which is handled above), in that case the hard- + * unblock will handle things. */ - if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL) + if (time_travel_mode == TT_MODE_EXTERNAL) sigio_run_timetravel_handlers(); else signals_pending |= SIGIO_MASK; @@ -380,33 +392,99 @@ int um_set_signals_trace(int enable) #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT void mark_sigio_pending(void) { + /* + * It would seem that this should be atomic so + * it isn't a read-modify-write with a signal + * that could happen in the middle, losing the + * value set by the signal. + * + * However, this function is only called when in + * time-travel=ext simulation mode, in which case + * the only signal ever pending is SIGIO, which + * is blocked while this can be called, and the + * timer signal (SIGALRM) cannot happen. + */ signals_pending |= SIGIO_MASK; } void block_signals_hard(void) { - if (signals_blocked) - return; - signals_blocked = 1; + signals_blocked++; barrier(); } void unblock_signals_hard(void) { + static bool unblocking; + if (!signals_blocked) + panic("unblocking signals while not blocked"); + + if (--signals_blocked) return; - /* Must be set to 0 before we check the pending bits etc. */ - signals_blocked = 0; + /* + * Must be set to 0 before we check pending so the + * SIGIO handler will run as normal unless we're still + * going to process signals_blocked_pending. + */ barrier(); - if (signals_pending && signals_enabled) { - /* this is a bit inefficient, but that's not really important */ - block_signals(); - unblock_signals(); - } else if (signals_pending & SIGIO_MASK) { - /* we need to run time-travel handlers even if not enabled */ - sigio_run_timetravel_handlers(); + /* + * Note that block_signals_hard()/unblock_signals_hard() can be called + * within the unblock_signals()/sigio_run_timetravel_handlers() below. + * This would still be prone to race conditions since it's actually a + * call _within_ e.g. vu_req_read_message(), where we observed this + * issue, which loops. Thus, if the inner call handles the recorded + * pending signals, we can get out of the inner call with the real + * signal hander no longer blocked, and still have a race. Thus don't + * handle unblocking in the inner call, if it happens, but only in + * the outermost call - 'unblocking' serves as an ownership for the + * signals_blocked_pending decrement. + */ + if (unblocking) + return; + unblocking = true; + + while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) { + if (signals_enabled) { + /* signals are enabled so we can touch this */ + signals_pending |= SIGIO_MASK; + /* + * this is a bit inefficient, but that's + * not really important + */ + block_signals(); + unblock_signals(); + } else { + /* + * we need to run time-travel handlers even + * if not enabled + */ + sigio_run_timetravel_handlers(); + } + + /* + * The decrement of signals_blocked_pending must be atomic so + * that the signal handler will either happen before or after + * the decrement, not during a read-modify-write: + * - If it happens before, it can increment it and we'll + * decrement it and do another round in the loop. + * - If it happens after it'll see 0 for both signals_blocked + * and signals_blocked_pending and thus run the handler as + * usual (subject to signals_enabled, but that's unrelated.) + * + * Note that a call to unblock_signals_hard() within the calls + * to unblock_signals() or sigio_run_timetravel_handlers() above + * will do nothing due to the 'unblocking' state, so this cannot + * underflow as the only one decrementing will be the outermost + * one. + */ + if (__atomic_sub_fetch(&signals_blocked_pending, 1, + __ATOMIC_SEQ_CST) < 0) + panic("signals_blocked_pending underflow"); } + + unblocking = false; } #endif diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c index 4692450aeb4d..9032fea50219 100644 --- a/arch/x86/coco/tdx/tdx.c +++ b/arch/x86/coco/tdx/tdx.c @@ -12,6 +12,7 @@ #include #include #include +#include /* TDX module Call Leaf IDs */ #define TDX_GET_INFO 1 @@ -328,7 +329,6 @@ static bool mmio_read(int size, unsigned long addr, unsigned long *val) .r12 = size, .r13 = EPT_READ, .r14 = addr, - .r15 = *val, }; if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT)) @@ -372,6 +372,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve) return -EINVAL; } + if (!fault_in_kernel_space(ve->gla)) { + WARN_ONCE(1, "Access to userspace address is not supported"); + return -EINVAL; + } + /* * Reject EPT violation #VEs that split pages. * diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S index 09e99d13fc0b..f4419afc7147 100644 --- a/arch/x86/entry/entry.S +++ b/arch/x86/entry/entry.S @@ -9,6 +9,8 @@ #include #include #include +#include +#include .pushsection .noinstr.text, "ax" @@ -17,6 +19,9 @@ SYM_FUNC_START(entry_ibpb) movl $PRED_CMD_IBPB, %eax xorl %edx, %edx wrmsr + + /* Make sure IBPB clears return stack preductions too. */ + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_BUG_IBPB_NO_RET RET SYM_FUNC_END(entry_ibpb) /* For KVM */ diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index ee5def1060c8..475ce40401ec 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -902,6 +902,8 @@ SYM_FUNC_START(entry_SYSENTER_32) /* Now ready to switch the cr3 */ SWITCH_TO_USER_CR3 scratch_reg=%eax + /* Clobbers ZF */ + CLEAR_CPU_BUFFERS /* * Restore all flags except IF. (We restore IF separately because @@ -912,7 +914,6 @@ SYM_FUNC_START(entry_SYSENTER_32) BUG_IF_WRONG_CR3 no_user_check=1 popfl popl %eax - CLEAR_CPU_BUFFERS /* * Return back to the vDSO, which will pop ecx and edx. @@ -1175,7 +1176,6 @@ SYM_CODE_START(asm_exc_nmi) /* Not on SYSENTER stack. */ call exc_nmi - CLEAR_CPU_BUFFERS jmp .Lnmi_return .Lnmi_from_sysenter_stack: @@ -1196,6 +1196,7 @@ SYM_CODE_START(asm_exc_nmi) CHECK_AND_APPLY_ESPFIX RESTORE_ALL_NMI cr3_reg=%edi pop=4 + CLEAR_CPU_BUFFERS jmp .Lirq_return #ifdef CONFIG_X86_ESPFIX32 @@ -1237,6 +1238,7 @@ SYM_CODE_START(asm_exc_nmi) * 1 - orig_ax */ lss (1+5+6)*4(%esp), %esp # back to espfix stack + CLEAR_CPU_BUFFERS jmp .Lirq_return #endif SYM_CODE_END(asm_exc_nmi) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 6624806e6904..a114338380a6 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -167,22 +167,9 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) jne swapgs_restore_regs_and_return_to_usermode /* - * SYSCALL clears RF when it saves RFLAGS in R11 and SYSRET cannot - * restore RF properly. If the slowpath sets it for whatever reason, we - * need to restore it correctly. - * - * SYSRET can restore TF, but unlike IRET, restoring TF results in a - * trap from userspace immediately after SYSRET. This would cause an - * infinite loop whenever #DB happens with register state that satisfies - * the opportunistic SYSRET conditions. For example, single-stepping - * this user code: - * - * movq $stuck_here, %rcx - * pushfq - * popq %r11 - * stuck_here: - * - * would never get past 'stuck_here'. + * SYSRET cannot restore RF. It can restore TF, but unlike IRET, + * restoring TF results in a trap from userspace immediately after + * SYSRET. */ testq $(X86_EFLAGS_RF|X86_EFLAGS_TF), %r11 jnz swapgs_restore_regs_and_return_to_usermode diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index b14b8cd85eb2..74a2f418e674 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -90,10 +90,6 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) cld - IBRS_ENTER - UNTRAIN_RET - CLEAR_BRANCH_HISTORY - /* * SYSENTER doesn't filter flags, so we need to clear NT and AC * ourselves. To save a few cycles, we can check whether @@ -117,6 +113,16 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) jnz .Lsysenter_fix_flags .Lsysenter_flags_fixed: + /* + * CPU bugs mitigations mechanisms can call other functions. They + * should be invoked after making sure TF is cleared because + * single-step is ignored only for instructions inside the + * entry_SYSENTER_compat function. + */ + IBRS_ENTER + UNTRAIN_RET + CLEAR_BRANCH_HISTORY + movq %rsp, %rdi call do_SYSENTER_32 /* XEN PV guests always use IRET path */ diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 1394312b732a..39f86188be54 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -41,6 +41,8 @@ #include #include #include +#include +#include #include "perf_event.h" @@ -2573,6 +2575,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev, struct device_attribute *attr, const char *buf, size_t count) { + static DEFINE_MUTEX(rdpmc_mutex); unsigned long val; ssize_t ret; @@ -2586,6 +2589,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev, if (x86_pmu.attr_rdpmc_broken) return -ENOTSUPP; + guard(mutex)(&rdpmc_mutex); + if (val != x86_pmu.attr_rdpmc) { /* * Changing into or out of never available or always available, @@ -2838,6 +2843,46 @@ static unsigned long get_segment_base(unsigned int segment) return get_desc_base(desc); } +#ifdef CONFIG_UPROBES +/* + * Heuristic-based check if uprobe is installed at the function entry. + * + * Under assumption of user code being compiled with frame pointers, + * `push %rbp/%ebp` is a good indicator that we indeed are. + * + * Similarly, `endbr64` (assuming 64-bit mode) is also a common pattern. + * If we get this wrong, captured stack trace might have one extra bogus + * entry, but the rest of stack trace will still be meaningful. + */ +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + struct arch_uprobe *auprobe; + + if (!current->utask) + return false; + + auprobe = current->utask->auprobe; + if (!auprobe) + return false; + + /* push %rbp/%ebp */ + if (auprobe->insn[0] == 0x55) + return true; + + /* endbr64 (64-bit only) */ + if (user_64bit_mode(regs) && is_endbr(*(u32 *)auprobe->insn)) + return true; + + return false; +} + +#else +static bool is_uprobe_at_func_entry(struct pt_regs *regs) +{ + return false; +} +#endif /* CONFIG_UPROBES */ + #ifdef CONFIG_IA32_EMULATION #include @@ -2849,6 +2894,7 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent unsigned long ss_base, cs_base; struct stack_frame_ia32 frame; const struct stack_frame_ia32 __user *fp; + u32 ret_addr; if (user_64bit_mode(regs)) return 0; @@ -2858,6 +2904,12 @@ perf_callchain_user32(struct pt_regs *regs, struct perf_callchain_entry_ctx *ent fp = compat_ptr(ss_base + regs->bp); pagefault_disable(); + + /* see perf_callchain_user() below for why we do this */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const u32 __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; @@ -2886,6 +2938,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs { struct stack_frame frame; const struct stack_frame __user *fp; + unsigned long ret_addr; if (perf_guest_state()) { /* TODO: We don't support guest os callchain now */ @@ -2909,6 +2962,19 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs return; pagefault_disable(); + + /* + * If we are called from uprobe handler, and we are indeed at the very + * entry to user function (which is normally a `push %rbp` instruction, + * under assumption of application being compiled with frame pointers), + * we should read return address from *regs->sp before proceeding + * to follow frame pointers, otherwise we'll skip immediate caller + * as %rbp is not yet setup. + */ + if (is_uprobe_at_func_entry(regs) && + !get_user(ret_addr, (const unsigned long __user *)regs->sp)) + perf_callchain_store(entry, ret_addr); + while (entry->nr < entry->max_stack) { if (!valid_user_frame(fp, sizeof(frame))) break; diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 949129443b1c..27968d10dd0b 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -4352,6 +4352,25 @@ static u8 adl_get_hybrid_cpu_type(void) return hybrid_big; } +static inline bool erratum_hsw11(struct perf_event *event) +{ + return (event->hw.config & INTEL_ARCH_EVENT_MASK) == + X86_CONFIG(.event=0xc0, .umask=0x01); +} + +/* + * The HSW11 requires a period larger than 100 which is the same as the BDM11. + * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL. + * + * The message 'interrupt took too long' can be observed on any counter which + * was armed with a period < 32 and two events expired in the same NMI. + * A minimum period of 32 is enforced for the rest of the events. + */ +static void hsw_limit_period(struct perf_event *event, s64 *left) +{ + *left = max(*left, erratum_hsw11(event) ? 128 : 32); +} + /* * Broadwell: * @@ -4369,8 +4388,7 @@ static u8 adl_get_hybrid_cpu_type(void) */ static void bdw_limit_period(struct perf_event *event, s64 *left) { - if ((event->hw.config & INTEL_ARCH_EVENT_MASK) == - X86_CONFIG(.event=0xc0, .umask=0x01)) { + if (erratum_hsw11(event)) { if (*left < 128) *left = 128; *left &= ~0x3fULL; @@ -6180,6 +6198,7 @@ __init int intel_pmu_init(void) x86_pmu.hw_config = hsw_hw_config; x86_pmu.get_event_constraints = hsw_get_event_constraints; + x86_pmu.limit_period = hsw_limit_period; x86_pmu.lbr_double_abort = true; extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? hsw_format_attr : nhm_format_attr; diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c index 551741e79e03..8175bff77efa 100644 --- a/arch/x86/events/intel/cstate.c +++ b/arch/x86/events/intel/cstate.c @@ -80,7 +80,7 @@ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter. * perf code: 0x03 * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL, - * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL + * KBL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter. * perf code: 0x04 @@ -89,8 +89,7 @@ * Scope: Package (physical package) * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter. * perf code: 0x05 - * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL, - * ADL,RPL,MTL + * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL * Scope: Package (physical package) * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter. * perf code: 0x06 @@ -584,9 +583,7 @@ static const struct cstate_model adl_cstates __initconst = { .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) | BIT(PERF_CSTATE_PKG_C3_RES) | BIT(PERF_CSTATE_PKG_C6_RES) | - BIT(PERF_CSTATE_PKG_C7_RES) | BIT(PERF_CSTATE_PKG_C8_RES) | - BIT(PERF_CSTATE_PKG_C9_RES) | BIT(PERF_CSTATE_PKG_C10_RES), }; diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 42a55794004a..4110246aba12 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -877,7 +877,7 @@ static void pt_update_head(struct pt *pt) */ static void *pt_buffer_region(struct pt_buffer *buf) { - return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); + return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT); } /** @@ -989,7 +989,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg) * order allocations, there shouldn't be many of these. */ list_for_each_entry(topa, &buf->tables, list) { - if (topa->offset + topa->size > pg << PAGE_SHIFT) + if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT) goto found; } @@ -1602,6 +1602,7 @@ static void pt_event_stop(struct perf_event *event, int mode) * see comment in intel_pt_interrupt(). */ WRITE_ONCE(pt->handle_nmi, 0); + barrier(); pt_config_stop(event); @@ -1653,11 +1654,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, return 0; /* - * Here, handle_nmi tells us if the tracing is on + * There is no PT interrupt in this mode, so stop the trace and it will + * remain stopped while the buffer is copied. */ - if (READ_ONCE(pt->handle_nmi)) - pt_config_stop(event); - + pt_config_stop(event); pt_read_offset(buf); pt_update_head(pt); @@ -1669,11 +1669,10 @@ static long pt_event_snapshot_aux(struct perf_event *event, ret = perf_output_copy_aux(&pt->handle, handle, from, to); /* - * If the tracing was on when we turned up, restart it. - * Compiler barrier not needed as we couldn't have been - * preempted by anything that touches pt->handle_nmi. + * Here, handle_nmi tells us if the tracing was on. + * If the tracing was on, restart it. */ - if (pt->handle_nmi) + if (READ_ONCE(pt->handle_nmi)) pt_config_start(event); return ret; diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h index 96906a62aacd..f5e46c04c145 100644 --- a/arch/x86/events/intel/pt.h +++ b/arch/x86/events/intel/pt.h @@ -33,8 +33,8 @@ struct topa_entry { u64 rsvd2 : 1; u64 size : 4; u64 rsvd3 : 2; - u64 base : 36; - u64 rsvd4 : 16; + u64 base : 40; + u64 rsvd4 : 12; }; /* TSC to Core Crystal Clock Ratio */ diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c index 9b5859812f4f..d081eb89ba12 100644 --- a/arch/x86/events/intel/uncore_snbep.c +++ b/arch/x86/events/intel/uncore_snbep.c @@ -459,6 +459,7 @@ #define SPR_RAW_EVENT_MASK_EXT 0xffffff /* SPR CHA */ +#define SPR_CHA_EVENT_MASK_EXT 0xffffffff #define SPR_CHA_PMON_CTL_TID_EN (1 << 16) #define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \ SPR_CHA_PMON_CTL_TID_EN) @@ -475,6 +476,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39"); DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55"); +DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63"); DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16"); DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18"); DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19"); @@ -5648,7 +5650,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = { static struct attribute *spr_uncore_cha_formats_attr[] = { &format_attr_event.attr, - &format_attr_umask_ext4.attr, + &format_attr_umask_ext5.attr, &format_attr_tid_en2.attr, &format_attr_edge.attr, &format_attr_inv.attr, @@ -5684,7 +5686,7 @@ ATTRIBUTE_GROUPS(uncore_alias); static struct intel_uncore_type spr_uncore_chabox = { .name = "cha", .event_mask = SPR_CHA_PMON_EVENT_MASK, - .event_mask_ext = SPR_RAW_EVENT_MASK_EXT, + .event_mask_ext = SPR_CHA_EVENT_MASK_EXT, .num_shared_regs = 1, .constraints = skx_uncore_chabox_constraints, .ops = &spr_uncore_chabox_ops, diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index 7ded92672414..91224a926137 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -217,7 +217,7 @@ #define X86_FEATURE_SPEC_STORE_BYPASS_DISABLE ( 7*32+23) /* "" Disable Speculative Store Bypass. */ #define X86_FEATURE_LS_CFG_SSBD ( 7*32+24) /* "" AMD SSBD implementation via LS_CFG MSR */ #define X86_FEATURE_IBRS ( 7*32+25) /* Indirect Branch Restricted Speculation */ -#define X86_FEATURE_IBPB ( 7*32+26) /* Indirect Branch Prediction Barrier */ +#define X86_FEATURE_IBPB ( 7*32+26) /* "ibpb" Indirect Branch Prediction Barrier without a guaranteed RSB flush */ #define X86_FEATURE_STIBP ( 7*32+27) /* Single Thread Indirect Branch Predictors */ #define X86_FEATURE_ZEN (7*32+28) /* "" CPU based on Zen microarchitecture */ #define X86_FEATURE_L1TF_PTEINV ( 7*32+29) /* "" L1TF workaround PTE inversion */ @@ -332,6 +332,7 @@ #define X86_FEATURE_AMD_SSB_NO (13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */ #define X86_FEATURE_CPPC (13*32+27) /* Collaborative Processor Performance Control */ #define X86_FEATURE_BTC_NO (13*32+29) /* "" Not vulnerable to Branch Type Confusion */ +#define X86_FEATURE_AMD_IBPB_RET (13*32+30) /* "" IBPB clears return address predictor */ #define X86_FEATURE_BRS (13*32+31) /* Branch Sampling available */ /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */ @@ -492,4 +493,5 @@ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ #define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ +#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h index eb7cd1139d97..b85af124f899 100644 --- a/arch/x86/include/asm/fpu/types.h +++ b/arch/x86/include/asm/fpu/types.h @@ -577,6 +577,13 @@ struct fpu_state_config { * even without XSAVE support, i.e. legacy features FP + SSE */ u64 legacy_features; + /* + * @independent_features: + * + * Features that are supported by XSAVES, but not managed as part of + * the FPU core, such as LBR + */ + u64 independent_features; }; /* FPU state configuration information */ diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h index 275e7fd20310..a18df4191699 100644 --- a/arch/x86/include/asm/hardirq.h +++ b/arch/x86/include/asm/hardirq.h @@ -62,7 +62,11 @@ extern u64 arch_irq_stat(void); #if IS_ENABLED(CONFIG_KVM_INTEL) -static inline void kvm_set_cpu_l1tf_flush_l1d(void) +/* + * This function is called from noinstr interrupt contexts + * and must be inlined to not get instrumentation. + */ +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1); } @@ -77,7 +81,7 @@ static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void) return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d); } #else /* !IS_ENABLED(CONFIG_KVM_INTEL) */ -static inline void kvm_set_cpu_l1tf_flush_l1d(void) { } +static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { } #endif /* IS_ENABLED(CONFIG_KVM_INTEL) */ #endif /* _ASM_X86_HARDIRQ_H */ diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h index fca710a93eb9..9c04f3c0ff18 100644 --- a/arch/x86/include/asm/idtentry.h +++ b/arch/x86/include/asm/idtentry.h @@ -13,15 +13,18 @@ #include +typedef void (*idtentry_t)(struct pt_regs *regs); + /** * DECLARE_IDTENTRY - Declare functions for simple IDT entry points * No error code pushed by hardware * @vector: Vector number (ignored for C) * @func: Function name of the entry point * - * Declares three functions: + * Declares four functions: * - The ASM entry point: asm_##func * - The XEN PV trap entry point: xen_##func (maybe unused) + * - The C handler called from the FRED event dispatcher (maybe unused) * - The C handler called from the ASM entry point * * Note: This is the C variant of DECLARE_IDTENTRY(). As the name says it @@ -31,6 +34,7 @@ #define DECLARE_IDTENTRY(vector, func) \ asmlinkage void asm_##func(void); \ asmlinkage void xen_asm_##func(void); \ + void fred_##func(struct pt_regs *regs); \ __visible void func(struct pt_regs *regs) /** @@ -137,6 +141,17 @@ static __always_inline void __##func(struct pt_regs *regs, \ #define DEFINE_IDTENTRY_RAW(func) \ __visible noinstr void func(struct pt_regs *regs) +/** + * DEFINE_FREDENTRY_RAW - Emit code for raw FRED entry points + * @func: Function name of the entry point + * + * @func is called from the FRED event dispatcher with interrupts disabled. + * + * See @DEFINE_IDTENTRY_RAW for further details. + */ +#define DEFINE_FREDENTRY_RAW(func) \ +noinstr void fred_##func(struct pt_regs *regs) + /** * DECLARE_IDTENTRY_RAW_ERRORCODE - Declare functions for raw IDT entry points * Error code pushed by hardware @@ -197,8 +212,8 @@ __visible noinstr void func(struct pt_regs *regs, \ irqentry_state_t state = irqentry_enter(regs); \ u32 vector = (u32)(u8)error_code; \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ run_irq_on_irqstack_cond(__##func, regs, vector); \ instrumentation_end(); \ irqentry_exit(regs, state); \ @@ -233,17 +248,27 @@ static noinline void __##func(struct pt_regs *regs, u32 vector) #define DEFINE_IDTENTRY_SYSVEC(func) \ static void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + run_sysvec_on_irqstack_cond(__##func, regs); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - run_sysvec_on_irqstack_cond(__##func, regs); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static noinline void __##func(struct pt_regs *regs) /** @@ -260,19 +285,29 @@ static noinline void __##func(struct pt_regs *regs) #define DEFINE_IDTENTRY_SYSVEC_SIMPLE(func) \ static __always_inline void __##func(struct pt_regs *regs); \ \ +static __always_inline void instr_##func(struct pt_regs *regs) \ +{ \ + __irq_enter_raw(); \ + __##func (regs); \ + __irq_exit_raw(); \ +} \ + \ __visible noinstr void func(struct pt_regs *regs) \ { \ irqentry_state_t state = irqentry_enter(regs); \ \ + kvm_set_cpu_l1tf_flush_l1d(); \ instrumentation_begin(); \ - __irq_enter_raw(); \ - kvm_set_cpu_l1tf_flush_l1d(); \ - __##func (regs); \ - __irq_exit_raw(); \ + instr_##func (regs); \ instrumentation_end(); \ irqentry_exit(regs, state); \ } \ \ +void fred_##func(struct pt_regs *regs) \ +{ \ + instr_##func (regs); \ +} \ + \ static __always_inline void __##func(struct pt_regs *regs) /** @@ -410,15 +445,18 @@ __visible noinstr void func(struct pt_regs *regs, \ /* C-Code mapping */ #define DECLARE_IDTENTRY_NMI DECLARE_IDTENTRY_RAW #define DEFINE_IDTENTRY_NMI DEFINE_IDTENTRY_RAW +#define DEFINE_FREDENTRY_NMI DEFINE_FREDENTRY_RAW #ifdef CONFIG_X86_64 #define DECLARE_IDTENTRY_MCE DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_MCE_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_MCE DEFINE_FREDENTRY_RAW #define DECLARE_IDTENTRY_DEBUG DECLARE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG DEFINE_IDTENTRY_IST #define DEFINE_IDTENTRY_DEBUG_USER DEFINE_IDTENTRY_NOIST +#define DEFINE_FREDENTRY_DEBUG DEFINE_FREDENTRY_RAW #endif #else /* !__ASSEMBLY__ */ @@ -660,23 +698,36 @@ DECLARE_IDTENTRY_SYSVEC(IRQ_MOVE_CLEANUP_VECTOR, sysvec_irq_move_cleanup); DECLARE_IDTENTRY_SYSVEC(REBOOT_VECTOR, sysvec_reboot); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_SINGLE_VECTOR, sysvec_call_function_single); DECLARE_IDTENTRY_SYSVEC(CALL_FUNCTION_VECTOR, sysvec_call_function); +#else +# define fred_sysvec_reschedule_ipi NULL +# define fred_sysvec_reboot NULL +# define fred_sysvec_call_function_single NULL +# define fred_sysvec_call_function NULL #endif #ifdef CONFIG_X86_LOCAL_APIC # ifdef CONFIG_X86_MCE_THRESHOLD DECLARE_IDTENTRY_SYSVEC(THRESHOLD_APIC_VECTOR, sysvec_threshold); +# else +# define fred_sysvec_threshold NULL # endif # ifdef CONFIG_X86_MCE_AMD DECLARE_IDTENTRY_SYSVEC(DEFERRED_ERROR_VECTOR, sysvec_deferred_error); +# else +# define fred_sysvec_deferred_error NULL # endif # ifdef CONFIG_X86_THERMAL_VECTOR DECLARE_IDTENTRY_SYSVEC(THERMAL_APIC_VECTOR, sysvec_thermal); +# else +# define fred_sysvec_thermal NULL # endif # ifdef CONFIG_IRQ_WORK DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); +# else +# define fred_sysvec_irq_work NULL # endif #endif @@ -684,12 +735,16 @@ DECLARE_IDTENTRY_SYSVEC(IRQ_WORK_VECTOR, sysvec_irq_work); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_VECTOR, sysvec_kvm_posted_intr_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_WAKEUP_VECTOR, sysvec_kvm_posted_intr_wakeup_ipi); DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR, sysvec_kvm_posted_intr_nested_ipi); +#else +# define fred_sysvec_kvm_posted_intr_ipi NULL +# define fred_sysvec_kvm_posted_intr_wakeup_ipi NULL +# define fred_sysvec_kvm_posted_intr_nested_ipi NULL #endif #if IS_ENABLED(CONFIG_HYPERV) DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR, sysvec_hyperv_callback); DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR, sysvec_hyperv_reenlightenment); -DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); +DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR, sysvec_hyperv_stimer0); #endif #if IS_ENABLED(CONFIG_ACRN_GUEST) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 887a171488ea..9de3db4a32f8 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1651,7 +1651,7 @@ struct kvm_x86_nested_ops { bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector, u32 error_code); int (*check_events)(struct kvm_vcpu *vcpu); - bool (*has_events)(struct kvm_vcpu *vcpu); + bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection); void (*triple_fault)(struct kvm_vcpu *vcpu); int (*get_state)(struct kvm_vcpu *vcpu, struct kvm_nested_state __user *user_kvm_nested_state, diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h index 198e03e59ca1..554af02a0526 100644 --- a/arch/x86/include/asm/page_64.h +++ b/arch/x86/include/asm/page_64.h @@ -17,6 +17,7 @@ extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; +extern unsigned long physmem_end; static __always_inline unsigned long __phys_addr_nodebug(unsigned long x) { diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h index 04f36063ad54..6c7f7c526450 100644 --- a/arch/x86/include/asm/pgtable_64_types.h +++ b/arch/x86/include/asm/pgtable_64_types.h @@ -139,6 +139,10 @@ extern unsigned int ptrs_per_p4d; # define VMEMMAP_START __VMEMMAP_BASE_L4 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */ +#ifdef CONFIG_RANDOMIZE_MEMORY +# define PHYSMEM_END physmem_end +#endif + /* * End of the region for which vmalloc page tables are pre-allocated. * For non-KMSAN builds, this is the same as VMALLOC_END. diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index 2725a4502321..bad79b82dfa0 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -82,7 +82,12 @@ static inline void syscall_get_arguments(struct task_struct *task, struct pt_regs *regs, unsigned long *args) { - memcpy(args, ®s->bx, 6 * sizeof(args[0])); + args[0] = regs->bx; + args[1] = regs->cx; + args[2] = regs->dx; + args[3] = regs->si; + args[4] = regs->di; + args[5] = regs->bp; } static inline int syscall_get_arch(struct task_struct *task) diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index e1672cc77c65..d00491e610b0 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -503,7 +503,19 @@ static int lapic_timer_shutdown(struct clock_event_device *evt) v = apic_read(APIC_LVTT); v |= (APIC_LVT_MASKED | LOCAL_TIMER_VECTOR); apic_write(APIC_LVTT, v); - apic_write(APIC_TMICT, 0); + + /* + * Setting APIC_LVT_MASKED (above) should be enough to tell + * the hardware that this timer will never fire. But AMD + * erratum 411 and some Intel CPU behavior circa 2024 say + * otherwise. Time for belt and suspenders programming: mask + * the timer _and_ zero the counter registers: + */ + if (v & APIC_LVT_TIMER_TSCDEADLINE) + wrmsrl(MSR_IA32_TSC_DEADLINE, 0); + else + apic_write(APIC_TMICT, 0); + return 0; } diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index efa87b6bb1cd..5e606477960c 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -351,27 +351,26 @@ static void ioapic_mask_entry(int apic, int pin) * shared ISA-space IRQs, so we have to support them. We are super * fast in the common case, and fast for shared ISA-space IRQs. */ -static int __add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) +static bool add_pin_to_irq_node(struct mp_chip_data *data, int node, int apic, int pin) { struct irq_pin_list *entry; - /* don't allow duplicates */ - for_each_irq_pin(entry, data->irq_2_pin) + /* Don't allow duplicates */ + for_each_irq_pin(entry, data->irq_2_pin) { if (entry->apic == apic && entry->pin == pin) - return 0; + return true; + } entry = kzalloc_node(sizeof(struct irq_pin_list), GFP_ATOMIC, node); if (!entry) { - pr_err("can not alloc irq_pin_list (%d,%d,%d)\n", - node, apic, pin); - return -ENOMEM; + pr_err("Cannot allocate irq_pin_list (%d,%d,%d)\n", node, apic, pin); + return false; } + entry->apic = apic; entry->pin = pin; list_add_tail(&entry->list, &data->irq_2_pin); - - return 0; + return true; } static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) @@ -386,13 +385,6 @@ static void __remove_pin_from_irq(struct mp_chip_data *data, int apic, int pin) } } -static void add_pin_to_irq_node(struct mp_chip_data *data, - int node, int apic, int pin) -{ - if (__add_pin_to_irq_node(data, node, apic, pin)) - panic("IO-APIC: failed to add irq-pin. Can not proceed\n"); -} - /* * Reroute an IRQ to a different pin. */ @@ -1001,8 +993,7 @@ static int alloc_isa_irq_from_domain(struct irq_domain *domain, if (irq_data && irq_data->parent_data) { if (!mp_check_pin_attr(irq, info)) return -EBUSY; - if (__add_pin_to_irq_node(irq_data->chip_data, node, ioapic, - info->ioapic.pin)) + if (!add_pin_to_irq_node(irq_data->chip_data, node, ioapic, info->ioapic.pin)) return -ENOMEM; } else { info->flags |= X86_IRQ_ALLOC_LEGACY; @@ -3038,10 +3029,8 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, return -ENOMEM; ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info); - if (ret < 0) { - kfree(data); - return ret; - } + if (ret < 0) + goto free_data; INIT_LIST_HEAD(&data->irq_2_pin); irq_data->hwirq = info->ioapic.pin; @@ -3050,7 +3039,10 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, irq_data->chip_data = data; mp_irqdomain_get_attr(mp_pin_to_gsi(ioapic, pin), data, info); - add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin); + if (!add_pin_to_irq_node(data, ioapic_alloc_attr_node(info), ioapic, pin)) { + ret = -ENOMEM; + goto free_irqs; + } mp_preconfigure_entry(data); mp_register_handler(virq, data->is_level); @@ -3065,6 +3057,12 @@ int mp_irqdomain_alloc(struct irq_domain *domain, unsigned int virq, ioapic, mpc_ioapic_id(ioapic), pin, virq, data->is_level, data->active_low); return 0; + +free_irqs: + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +free_data: + kfree(data); + return ret; } void mp_irqdomain_free(struct irq_domain *domain, unsigned int virq, diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3f38592ec771..fa2045ad408a 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1092,7 +1092,24 @@ do_cmd_auto: case RETBLEED_MITIGATION_IBPB: setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like SRSO has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); + mitigate_smt = true; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); + break; default: @@ -2591,6 +2608,14 @@ static void __init srso_select_mitigation(void) if (has_microcode) { setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB); srso_mitigation = SRSO_MITIGATION_IBPB; + + /* + * IBPB on entry already obviates the need for + * software-based untraining so clear those in case some + * other mitigation like Retbleed has selected them. + */ + setup_clear_cpu_cap(X86_FEATURE_UNRET); + setup_clear_cpu_cap(X86_FEATURE_RETHUNK); } } else { pr_err("WARNING: kernel not compiled with CPU_IBPB_ENTRY.\n"); @@ -2603,6 +2628,13 @@ static void __init srso_select_mitigation(void) if (!boot_cpu_has(X86_FEATURE_ENTRY_IBPB) && has_microcode) { setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT); srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT; + + /* + * There is no need for RSB filling: entry_ibpb() ensures + * all predictions, including the RSB, are invalidated, + * regardless of IBPB implementation. + */ + setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT); } } else { pr_err("WARNING: kernel not compiled with CPU_SRSO.\n"); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index f2bc651c0dcd..7f922a359ccc 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1462,6 +1462,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) boot_cpu_has(X86_FEATURE_HYPERVISOR))) setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_has(c, X86_FEATURE_AMD_IBPB) && !cpu_has(c, X86_FEATURE_AMD_IBPB_RET)) + setup_force_cpu_bug(X86_BUG_IBPB_NO_RET); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index 9b039e9635e4..542b818c0d20 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -324,6 +324,7 @@ static void __init ms_hyperv_init_platform(void) ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) { x86_platform.calibrate_tsc = hv_get_tsc_khz; x86_platform.calibrate_cpu = hv_get_tsc_khz; + setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ); } if (ms_hyperv.priv_high & HV_ISOLATION) { diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c index 2746cac9d8a9..dbebb646c9fc 100644 --- a/arch/x86/kernel/cpu/mtrr/mtrr.c +++ b/arch/x86/kernel/cpu/mtrr/mtrr.c @@ -816,7 +816,7 @@ void mtrr_save_state(void) { int first_cpu; - if (!mtrr_enabled()) + if (!mtrr_enabled() || !mtrr_state.have_fixed) return; first_cpu = cpumask_first(cpu_online_mask); diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c index 3266ea36667c..72c33ec07ba7 100644 --- a/arch/x86/kernel/cpu/resctrl/core.c +++ b/arch/x86/kernel/cpu/resctrl/core.c @@ -174,7 +174,7 @@ static inline bool rdt_get_mb_table(struct rdt_resource *r) return false; } -static bool __get_mem_config_intel(struct rdt_resource *r) +static __init bool __get_mem_config_intel(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; @@ -208,7 +208,7 @@ static bool __get_mem_config_intel(struct rdt_resource *r) return true; } -static bool __rdt_get_mem_config_amd(struct rdt_resource *r) +static __init bool __rdt_get_mem_config_amd(struct rdt_resource *r) { struct rdt_hw_resource *hw_res = resctrl_to_arch_res(r); union cpuid_0x10_3_eax eax; diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c index 84f23327caed..d2cb96738ff6 100644 --- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c +++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c @@ -27,10 +27,10 @@ * hardware. The allocated bandwidth percentage is rounded to the next * control step available on the hardware. */ -static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) +static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r) { - unsigned long bw; int ret; + u32 bw; /* * Only linear delay values is supported for current Intel SKUs. @@ -40,16 +40,21 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r) return false; } - ret = kstrtoul(buf, 10, &bw); + ret = kstrtou32(buf, 10, &bw); if (ret) { - rdt_last_cmd_printf("Non-decimal digit in MB value %s\n", buf); + rdt_last_cmd_printf("Invalid MB value %s\n", buf); return false; } - if ((bw < r->membw.min_bw || bw > r->default_ctrl) && - !is_mba_sc(r)) { - rdt_last_cmd_printf("MB value %ld out of range [%d,%d]\n", bw, - r->membw.min_bw, r->default_ctrl); + /* Nothing else to do if software controller is enabled. */ + if (is_mba_sc(r)) { + *data = bw; + return true; + } + + if (bw < r->membw.min_bw || bw > r->default_ctrl) { + rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n", + bw, r->membw.min_bw, r->default_ctrl); return false; } @@ -63,7 +68,7 @@ int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s, struct resctrl_staged_config *cfg; u32 closid = data->rdtgrp->closid; struct rdt_resource *r = s->res; - unsigned long bw_val; + u32 bw_val; cfg = &d->staged_config[s->conf_type]; if (cfg->have_new_ctrl) { diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c index 0aad028f04d4..c4960b8e5195 100644 --- a/arch/x86/kernel/cpu/sgx/main.c +++ b/arch/x86/kernel/cpu/sgx/main.c @@ -474,24 +474,25 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void) { struct sgx_epc_page *page; int nid_of_current = numa_node_id(); - int nid = nid_of_current; + int nid_start, nid; - if (node_isset(nid_of_current, sgx_numa_mask)) { - page = __sgx_alloc_epc_page_from_node(nid_of_current); - if (page) - return page; - } - - /* Fall back to the non-local NUMA nodes: */ - while (true) { - nid = next_node_in(nid, sgx_numa_mask); - if (nid == nid_of_current) - break; + /* + * Try local node first. If it doesn't have an EPC section, + * fall back to the non-local NUMA nodes. + */ + if (node_isset(nid_of_current, sgx_numa_mask)) + nid_start = nid_of_current; + else + nid_start = next_node_in(nid_of_current, sgx_numa_mask); + nid = nid_start; + do { page = __sgx_alloc_epc_page_from_node(nid); if (page) return page; - } + + nid = next_node_in(nid, sgx_numa_mask); + } while (nid != nid_start); return ERR_PTR(-ENOMEM); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index 5cd51f25f446..c77297fa2dad 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -87,7 +87,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev) ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin); if (ret) - return ret; + return pcibios_err_to_errno(ret); if (!pin) return 0; diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 2aa849705bb6..d18594343745 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -792,6 +792,9 @@ void __init fpu__init_system_xstate(unsigned int legacy_size) goto out_disable; } + fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features & + XFEATURE_MASK_INDEPENDENT; + /* * Clear XSAVE features that are disabled in the normal CPUID. */ diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h index 19ca623ffa2a..544224611e23 100644 --- a/arch/x86/kernel/fpu/xstate.h +++ b/arch/x86/kernel/fpu/xstate.h @@ -64,9 +64,9 @@ static inline u64 xfeatures_mask_supervisor(void) static inline u64 xfeatures_mask_independent(void) { if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) - return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR; + return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR; - return XFEATURE_MASK_INDEPENDENT; + return fpu_kernel_cfg.independent_features; } /* XSAVE/XRSTOR wrapper functions */ diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c index 0611fd83858e..24b6eaacc81e 100644 --- a/arch/x86/kernel/machine_kexec_64.c +++ b/arch/x86/kernel/machine_kexec_64.c @@ -28,6 +28,7 @@ #include #include #include +#include #ifdef CONFIG_ACPI /* @@ -90,6 +91,8 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) { #ifdef CONFIG_EFI unsigned long mstart, mend; + void *kaddr; + int ret; if (!efi_enabled(EFI_BOOT)) return 0; @@ -105,6 +108,30 @@ map_efi_systab(struct x86_mapping_info *info, pgd_t *level4p) if (!mstart) return 0; + ret = kernel_ident_mapping_init(info, level4p, mstart, mend); + if (ret) + return ret; + + kaddr = memremap(mstart, mend - mstart, MEMREMAP_WB); + if (!kaddr) { + pr_err("Could not map UEFI system table\n"); + return -ENOMEM; + } + + mstart = efi_config_table; + + if (efi_enabled(EFI_64BIT)) { + efi_system_table_64_t *stbl = (efi_system_table_64_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_64_t) * stbl->nr_tables; + } else { + efi_system_table_32_t *stbl = (efi_system_table_32_t *)kaddr; + + mend = mstart + sizeof(efi_config_table_32_t) * stbl->nr_tables; + } + + memunmap(kaddr); + return kernel_ident_mapping_init(info, level4p, mstart, mend); #endif return 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 279b5e9be80f..acc83738bf5b 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -991,7 +991,10 @@ unsigned long arch_align_stack(unsigned long sp) unsigned long arch_randomize_brk(struct mm_struct *mm) { - return randomize_page(mm->brk, 0x02000000); + if (mmap_is_ia32()) + return randomize_page(mm->brk, SZ_32M); + + return randomize_page(mm->brk, SZ_1G); } /* diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index c90fef0258c5..246374cb3ed3 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -1843,8 +1843,12 @@ static bool set_target_expiration(struct kvm_lapic *apic, u32 count_reg) if (unlikely(count_reg != APIC_TMICT)) { deadline = tmict_to_ns(apic, kvm_lapic_get_reg(apic, count_reg)); - if (unlikely(deadline <= 0)) - deadline = apic->lapic_timer.period; + if (unlikely(deadline <= 0)) { + if (apic_lvtt_period(apic)) + deadline = apic->lapic_timer.period; + else + deadline = 0; + } else if (unlikely(deadline > apic->lapic_timer.period)) { pr_info_ratelimited( "kvm: vcpu %i: requested lapic timer restore with " @@ -2293,6 +2297,29 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu) } EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi); +#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13)) + +int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) +{ + if (data & X2APIC_ICR_RESERVED_BITS) + return 1; + + /* + * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but + * only AMD requires it to be zero, Intel essentially just ignores the + * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled, + * the CPU performs the reserved bits checks, i.e. the underlying CPU + * behavior will "win". Arbitrarily clear the BUSY bit, as there is no + * sane way to provide consistent behavior with respect to hardware. + */ + data &= ~APIC_ICR_BUSY; + + kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); + kvm_lapic_set_reg64(apic, APIC_ICR, data); + trace_kvm_apic_write(APIC_ICR, data); + return 0; +} + /* emulate APIC access in a trap manner */ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) { @@ -2310,7 +2337,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset) * maybe-unecessary write, and both are in the noise anyways. */ if (apic_x2apic_mode(apic) && offset == APIC_ICR) - kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)); + WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR))); else kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset)); } @@ -2932,16 +2959,6 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr) return 0; } -int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data) -{ - data &= ~APIC_ICR_BUSY; - - kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32)); - kvm_lapic_set_reg64(apic, APIC_ICR, data); - trace_kvm_apic_write(APIC_ICR, data); - return 0; -} - static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data) { u32 low; diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c index 5d4d78c9a787..974f30d38c79 100644 --- a/arch/x86/kvm/svm/nested.c +++ b/arch/x86/kvm/svm/nested.c @@ -62,8 +62,12 @@ static u64 nested_svm_get_tdp_pdptr(struct kvm_vcpu *vcpu, int index) u64 pdpte; int ret; + /* + * Note, nCR3 is "assumed" to be 32-byte aligned, i.e. the CPU ignores + * nCR3[4:0] when loading PDPTEs from memory. + */ ret = kvm_vcpu_read_guest_page(vcpu, gpa_to_gfn(cr3), &pdpte, - offset_in_page(cr3) + index * 8, 8); + (cr3 & GENMASK(11, 5)) + index * 8, 8); if (ret) return 0; return pdpte; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 4a663812562d..a96facc05139 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -2756,6 +2756,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) case MSR_CSTAR: msr_info->data = svm->vmcb01.ptr->save.cstar; break; + case MSR_GS_BASE: + msr_info->data = svm->vmcb01.ptr->save.gs.base; + break; + case MSR_FS_BASE: + msr_info->data = svm->vmcb01.ptr->save.fs.base; + break; case MSR_KERNEL_GS_BASE: msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base; break; @@ -2982,6 +2988,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr) case MSR_CSTAR: svm->vmcb01.ptr->save.cstar = data; break; + case MSR_GS_BASE: + svm->vmcb01.ptr->save.gs.base = data; + break; + case MSR_FS_BASE: + svm->vmcb01.ptr->save.fs.base = data; + break; case MSR_KERNEL_GS_BASE: svm->vmcb01.ptr->save.kernel_gs_base = data; break; @@ -4960,6 +4972,9 @@ static __init void svm_set_cpu_caps(void) /* CPUID 0x8000001F (SME/SEV features) */ sev_set_cpu_caps(); + + /* Don't advertise Bus Lock Detect to guest if SVM support is absent */ + kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT); } static __init int svm_hardware_setup(void) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9d683b6067c7..2283f485a81f 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -3934,7 +3934,7 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu) to_vmx(vcpu)->nested.preemption_timer_expired; } -static bool vmx_has_nested_events(struct kvm_vcpu *vcpu) +static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection) { return nested_vmx_preemption_timer_pending(vcpu) || to_vmx(vcpu)->nested.mtf_pending; diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 10aff2c9a4e4..87abf4eebf8a 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -4980,14 +4980,19 @@ static int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection) return !vmx_nmi_blocked(vcpu); } +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu) +{ + return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || + (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & + (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); +} + bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu) { if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu)) return false; - return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) || - (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & - (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS)); + return __vmx_interrupt_blocked(vcpu); } static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection) diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index e2b04f4c0fef..9e0bb98b116d 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -413,6 +413,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu); void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu); bool vmx_nmi_blocked(struct kvm_vcpu *vcpu); +bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu); bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu); void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 53d83b37db8c..4e778ba6a5d4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5747,7 +5747,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp, if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events))) break; + kvm_vcpu_srcu_read_lock(vcpu); r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events); + kvm_vcpu_srcu_read_unlock(vcpu); break; } case KVM_GET_DEBUGREGS: { @@ -10131,7 +10133,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu, if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, true)) *req_immediate_exit = true; /* @@ -13013,7 +13015,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu) if (is_guest_mode(vcpu) && kvm_x86_ops.nested_ops->has_events && - kvm_x86_ops.nested_ops->has_events(vcpu)) + kvm_x86_ops.nested_ops->has_events(vcpu, false)) return true; if (kvm_xen_has_pending_events(vcpu)) diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c index e0411a3774d4..5eecb45d05d5 100644 --- a/arch/x86/lib/iomem.c +++ b/arch/x86/lib/iomem.c @@ -25,6 +25,9 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n) static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n) { + const void *orig_to = to; + const size_t orig_n = n; + if (unlikely(!n)) return; @@ -39,7 +42,7 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si } rep_movs(to, (const void *)from, n); /* KMSAN must treat values read from devices as initialized. */ - kmsan_unpoison_memory(to, n); + kmsan_unpoison_memory(orig_to, orig_n); } static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n) diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index 055955c9bfcb..7880e2a7ec6a 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -107,6 +107,7 @@ __EXPORT_THUNK(srso_alias_untrain_ret) /* dummy definition for alternatives */ SYM_START(srso_alias_untrain_ret, SYM_L_GLOBAL, SYM_A_NONE) ANNOTATE_UNRET_SAFE + ANNOTATE_NOENDBR ret int3 SYM_FUNC_END(srso_alias_untrain_ret) @@ -261,7 +262,6 @@ SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR ANNOTATE_UNRET_SAFE - ANNOTATE_NOENDBR ret int3 SYM_CODE_END(__x86_return_thunk) diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 913287b9340c..ed861ef33f80 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -262,21 +262,17 @@ static void __init probe_page_size_mask(void) } } -#define INTEL_MATCH(_model) { .vendor = X86_VENDOR_INTEL, \ - .family = 6, \ - .model = _model, \ - } /* * INVLPG may not properly flush Global entries * on these CPUs when PCIDs are enabled. */ static const struct x86_cpu_id invlpg_miss_ids[] = { - INTEL_MATCH(INTEL_FAM6_ALDERLAKE ), - INTEL_MATCH(INTEL_FAM6_ALDERLAKE_L ), - INTEL_MATCH(INTEL_FAM6_ALDERLAKE_N ), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE ), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_P), - INTEL_MATCH(INTEL_FAM6_RAPTORLAKE_S), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE, 0), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 0), + X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_N, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_P, 0), + X86_MATCH_INTEL_FAM6_MODEL(RAPTORLAKE_S, 0), {} }; diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 3f040c6e5d13..6d294d24e488 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -950,8 +950,12 @@ static void update_end_of_memory_vars(u64 start, u64 size) int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages, struct mhp_params *params) { + unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1; int ret; + if (WARN_ON_ONCE(end > PHYSMEM_END)) + return -ERANGE; + ret = __add_pages(nid, start_pfn, nr_pages, params); WARN_ON_ONCE(ret); diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 37db264866b6..230f1dee4f09 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE; */ static __initdata struct kaslr_memory_region { unsigned long *base; + unsigned long *end; unsigned long size_tb; } kaslr_regions[] = { - { &page_offset_base, 0 }, - { &vmalloc_base, 0 }, - { &vmemmap_base, 0 }, + { + .base = &page_offset_base, + .end = &physmem_end, + }, + { + .base = &vmalloc_base, + }, + { + .base = &vmemmap_base, + }, }; +/* The end of the possible address space for physical memory */ +unsigned long physmem_end __ro_after_init; + /* Get size in bytes used by the memory region */ static inline unsigned long get_padding(struct kaslr_memory_region *region) { @@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void) BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE); BUILD_BUG_ON(vaddr_end > __START_KERNEL_map); + /* Preset the end of the possible address space for physical memory */ + physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1); if (!kaslr_memory_enabled()) return; @@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void) vaddr += entropy; *kaslr_regions[i].base = vaddr; - /* - * Jump the region and add a minimum padding based on - * randomization alignment. - */ + /* Calculate the end of the region */ vaddr += get_padding(&kaslr_regions[i]); + /* + * KASLR trims the maximum possible size of the + * direct-map. Update the physmem_end boundary. + * No rounding required as the region starts + * PUD aligned and size is in units of TB. + */ + if (kaslr_regions[i].end) + *kaslr_regions[i].end = __pa_nodebug(vaddr - 1); + + /* Add a minimum padding based on randomization alignment. */ vaddr = round_up(vaddr + 1, PUD_SIZE); remain_entropy -= entropy; } diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c index 78414c6d1b5e..d5f702ea4c78 100644 --- a/arch/x86/mm/pti.c +++ b/arch/x86/mm/pti.c @@ -241,7 +241,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address) * * Returns a pointer to a PTE on success, or NULL on failure. */ -static pte_t *pti_user_pagetable_walk_pte(unsigned long address) +static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text) { gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO); pmd_t *pmd; @@ -251,10 +251,15 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address) if (!pmd) return NULL; - /* We can't do anything sensible if we hit a large mapping. */ + /* Large PMD mapping found */ if (pmd_large(*pmd)) { - WARN_ON(1); - return NULL; + /* Clear the PMD if we hit a large mapping from the first round */ + if (late_text) { + set_pmd(pmd, __pmd(0)); + } else { + WARN_ON_ONCE(1); + return NULL; + } } if (pmd_none(*pmd)) { @@ -283,7 +288,7 @@ static void __init pti_setup_vsyscall(void) if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte)) return; - target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR); + target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false); if (WARN_ON(!target_pte)) return; @@ -301,7 +306,7 @@ enum pti_clone_level { static void pti_clone_pgtable(unsigned long start, unsigned long end, - enum pti_clone_level level) + enum pti_clone_level level, bool late_text) { unsigned long addr; @@ -374,14 +379,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end, */ *target_pmd = *pmd; - addr += PMD_SIZE; + addr = round_up(addr + 1, PMD_SIZE); } else if (level == PTI_CLONE_PTE) { /* Walk the page-table down to the pte level */ pte = pte_offset_kernel(pmd, addr); if (pte_none(*pte)) { - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); continue; } @@ -390,7 +395,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, return; /* Allocate PTE in the user page-table */ - target_pte = pti_user_pagetable_walk_pte(addr); + target_pte = pti_user_pagetable_walk_pte(addr, late_text); if (WARN_ON(!target_pte)) return; @@ -401,7 +406,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end, /* Clone the PTE */ *target_pte = *pte; - addr += PAGE_SIZE; + addr = round_up(addr + 1, PAGE_SIZE); } else { BUG(); @@ -452,7 +457,7 @@ static void __init pti_clone_user_shared(void) phys_addr_t pa = per_cpu_ptr_to_phys((void *)va); pte_t *target_pte; - target_pte = pti_user_pagetable_walk_pte(va); + target_pte = pti_user_pagetable_walk_pte(va, false); if (WARN_ON(!target_pte)) return; @@ -475,7 +480,7 @@ static void __init pti_clone_user_shared(void) start = CPU_ENTRY_AREA_BASE; end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES); - pti_clone_pgtable(start, end, PTI_CLONE_PMD); + pti_clone_pgtable(start, end, PTI_CLONE_PMD, false); } #endif /* CONFIG_X86_64 */ @@ -492,11 +497,11 @@ static void __init pti_setup_espfix64(void) /* * Clone the populated PMDs of the entry text and force it RO. */ -static void pti_clone_entry_text(void) +static void pti_clone_entry_text(bool late) { pti_clone_pgtable((unsigned long) __entry_text_start, (unsigned long) __entry_text_end, - PTI_CLONE_PMD); + PTI_LEVEL_KERNEL_IMAGE, late); } /* @@ -571,7 +576,7 @@ static void pti_clone_kernel_text(void) * pti_set_kernel_image_nonglobal() did to clear the * global bit. */ - pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE); + pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false); /* * pti_clone_pgtable() will set the global bit in any PMDs @@ -638,8 +643,15 @@ void __init pti_init(void) /* Undo all global bits from the init pagetables in head_64.S: */ pti_set_kernel_image_nonglobal(); + /* Replace some of the global bits just for shared entry text: */ - pti_clone_entry_text(); + /* + * This is very early in boot. Device and Late initcalls can do + * modprobe before free_initmem() and mark_readonly(). This + * pti_clone_entry_text() allows those user-mode-helpers to function, + * but notably the text is still RW. + */ + pti_clone_entry_text(false); pti_setup_espfix64(); pti_setup_vsyscall(); } @@ -656,10 +668,11 @@ void pti_finalize(void) if (!boot_cpu_has(X86_FEATURE_PTI)) return; /* - * We need to clone everything (again) that maps parts of the - * kernel image. + * This is after free_initmem() (all initcalls are done) and we've done + * mark_readonly(). Text is now NX which might've split some PMDs + * relative to the early clone. */ - pti_clone_entry_text(); + pti_clone_entry_text(true); pti_clone_kernel_text(); debug_checkwx_user(); diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 7913440c0fd4..92db785a0a8e 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -57,6 +57,56 @@ static bool is_imm8(int value) return value <= 127 && value >= -128; } +/* + * Let us limit the positive offset to be <= 123. + * This is to ensure eventual jit convergence For the following patterns: + * ... + * pass4, final_proglen=4391: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 74 7d je 0x290 + * 213: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 289: 48 85 ff test rdi,rdi + * 28c: 74 17 je 0x2a5 + * 28e: e9 7f ff ff ff jmp 0x212 + * 293: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 2-byte cond jump insn for offset 0x7d (-125) + * and insn at 0x28e is 5-byte jmp insn with offset -129. + * + * pass5, final_proglen=4392: + * ... + * 20e: 48 85 ff test rdi,rdi + * 211: 0f 84 80 00 00 00 je 0x297 + * 217: 48 8b 77 00 mov rsi,QWORD PTR [rdi+0x0] + * ... + * 28d: 48 85 ff test rdi,rdi + * 290: 74 1a je 0x2ac + * 292: eb 84 jmp 0x218 + * 294: bf 03 00 00 00 mov edi,0x3 + * Note that insn at 0x211 is 6-byte cond jump insn now since its offset + * becomes 0x80 based on previous round (0x293 - 0x213 = 0x80). + * At the same time, insn at 0x292 is a 2-byte insn since its offset is + * -124. + * + * pass6 will repeat the same code as in pass4 and this will prevent + * eventual convergence. + * + * To fix this issue, we need to break je (2->6 bytes) <-> jmp (5->2 bytes) + * cycle in the above. In the above example je offset <= 0x7c should work. + * + * For other cases, je <-> je needs offset <= 0x7b to avoid no convergence + * issue. For jmp <-> je and jmp <-> jmp cases, jmp offset <= 0x7c should + * avoid no convergence issue. + * + * Overall, let us limit the positive offset for 8bit cond/uncond jmp insn + * to maximum 123 (0x7b). This way, the jit pass can eventually converge. + */ +static bool is_imm8_jmp_offset(int value) +{ + return value <= 123 && value >= -128; +} + static bool is_simm32(s64 value) { return value == (s64)(s32)value; @@ -1589,7 +1639,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ return -EFAULT; } jmp_offset = addrs[i + insn->off] - addrs[i]; - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To keep the jmp_offset valid, the extra bytes are * padded before the jump insn, so we subtract the @@ -1671,7 +1721,7 @@ emit_cond_jmp: /* Convert BPF opcode to x86 */ break; } emit_jmp: - if (is_imm8(jmp_offset)) { + if (is_imm8_jmp_offset(jmp_offset)) { if (jmp_padding) { /* To avoid breaking jmp_offset, the extra bytes * are padded before the actual jmp insn, so diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c index 8edd62206604..722a33be08a1 100644 --- a/arch/x86/pci/intel_mid_pci.c +++ b/arch/x86/pci/intel_mid_pci.c @@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev) return 0; ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (ret < 0) { + if (ret) { dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret); - return ret; + return pcibios_err_to_errno(ret); } id = x86_match_cpu(intel_mid_cpu_ids); diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c index 5a4ecf0c2ac4..b4621cc95e1f 100644 --- a/arch/x86/pci/xen.c +++ b/arch/x86/pci/xen.c @@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev) u8 gsi; rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi); - if (rc < 0) { + if (rc) { dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n", rc); - return rc; + return pcibios_err_to_errno(rc); } /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/ pirq = gsi; diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c index fdd49d70b437..c81cea208c2c 100644 --- a/arch/x86/platform/intel/iosf_mbi.c +++ b/arch/x86/platform/intel/iosf_mbi.c @@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr) fail_read: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) @@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr) fail_write: dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result); - return result; + return pcibios_err_to_errno(result); } int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 58db86f7b384..a02cc5433889 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -736,7 +736,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, * immediate unmapping. */ map_ops[i].status = GNTST_general_error; - unmap[0].host_addr = map_ops[i].host_addr, + unmap[0].host_addr = map_ops[i].host_addr; unmap[0].handle = map_ops[i].handle; map_ops[i].handle = INVALID_GRANT_HANDLE; if (map_ops[i].flags & GNTMAP_device_map) @@ -746,7 +746,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops, if (kmap_ops) { kmap_ops[i].status = GNTST_general_error; - unmap[1].host_addr = kmap_ops[i].host_addr, + unmap[1].host_addr = kmap_ops[i].host_addr; unmap[1].handle = kmap_ops[i].handle; kmap_ops[i].handle = INVALID_GRANT_HANDLE; if (kmap_ops[i].flags & GNTMAP_device_map) diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 8db26f10fb1d..46a2cb782ab7 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -853,7 +853,7 @@ char * __init xen_memory_setup(void) * to relocating (and even reusing) pages with kernel text or data. */ if (xen_is_e820_reserved(__pa_symbol(_text), - __pa_symbol(__bss_stop) - __pa_symbol(_text))) { + __pa_symbol(_end) - __pa_symbol(_text))) { xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n"); BUG(); } diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 52eb79d60a3f..8e797782cfe3 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -2889,8 +2889,12 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq, struct bfq_queue *in_service_bfqq, *new_bfqq; /* if a merge has already been setup, then proceed with that first */ - if (bfqq->new_bfqq) - return bfqq->new_bfqq; + new_bfqq = bfqq->new_bfqq; + if (new_bfqq) { + while (new_bfqq->new_bfqq) + new_bfqq = new_bfqq->new_bfqq; + return new_bfqq; + } /* * Check delayed stable merge for rotational or non-queueing @@ -3113,10 +3117,12 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq) bfq_put_queue(bfqq); } -static void -bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, - struct bfq_queue *bfqq, struct bfq_queue *new_bfqq) +static struct bfq_queue *bfq_merge_bfqqs(struct bfq_data *bfqd, + struct bfq_io_cq *bic, + struct bfq_queue *bfqq) { + struct bfq_queue *new_bfqq = bfqq->new_bfqq; + bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu", (unsigned long)new_bfqq->pid); /* Save weight raising and idle window of the merged queues */ @@ -3210,6 +3216,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic, bfq_reassign_last_bfqq(bfqq, new_bfqq); bfq_release_process_ref(bfqd, bfqq); + + return new_bfqq; } static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, @@ -3245,14 +3253,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq, * fulfilled, i.e., bic can be redirected to new_bfqq * and bfqq can be put. */ - bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq, - new_bfqq); - /* - * If we get here, bio will be queued into new_queue, - * so use new_bfqq to decide whether bio and rq can be - * merged. - */ - bfqq = new_bfqq; + while (bfqq != new_bfqq) + bfqq = bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq); /* * Change also bqfd->bio_bfqq, as @@ -5612,9 +5614,7 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq, * state before killing it. */ bfqq->bic = bic; - bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq); - - return new_bfqq; + return bfq_merge_bfqqs(bfqd, bic, bfqq); } /* @@ -6062,6 +6062,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) bool waiting, idle_timer_disabled = false; if (new_bfqq) { + struct bfq_queue *old_bfqq = bfqq; /* * Release the request's reference to the old bfqq * and make sure one is taken to the shared queue. @@ -6077,18 +6078,18 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) * then complete the merge and redirect it to * new_bfqq. */ - if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) - bfq_merge_bfqqs(bfqd, RQ_BIC(rq), - bfqq, new_bfqq); + if (bic_to_bfqq(RQ_BIC(rq), 1) == bfqq) { + while (bfqq != new_bfqq) + bfqq = bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq); + } - bfq_clear_bfqq_just_created(bfqq); + bfq_clear_bfqq_just_created(old_bfqq); /* * rq is about to be enqueued into new_bfqq, * release rq reference on bfqq */ - bfq_put_queue(bfqq); + bfq_put_queue(old_bfqq); rq->elv.priv[1] = new_bfqq; - bfqq = new_bfqq; } bfq_update_io_thinktime(bfqd, bfqq); @@ -6624,7 +6625,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq) { bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue"); - if (bfqq_process_refs(bfqq) == 1) { + if (bfqq_process_refs(bfqq) == 1 && !bfqq->new_bfqq) { bfqq->pid = current->pid; bfq_clear_bfqq_coop(bfqq); bfq_clear_bfqq_split_coop(bfqq); @@ -6720,6 +6721,31 @@ static void bfq_prepare_request(struct request *rq) rq->elv.priv[0] = rq->elv.priv[1] = NULL; } +static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq) +{ + struct bfq_queue *new_bfqq = bfqq->new_bfqq; + struct bfq_queue *waker_bfqq = bfqq->waker_bfqq; + + if (!waker_bfqq) + return NULL; + + while (new_bfqq) { + if (new_bfqq == waker_bfqq) { + /* + * If waker_bfqq is in the merge chain, and current + * is the only procress. + */ + if (bfqq_process_refs(waker_bfqq) == 1) + return NULL; + break; + } + + new_bfqq = new_bfqq->new_bfqq; + } + + return waker_bfqq; +} + /* * If needed, init rq, allocate bfq data structures associated with * rq, and increment reference counters in the destination bfq_queue @@ -6780,7 +6806,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) /* If the queue was seeky for too long, break it apart. */ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) && !bic->stably_merged) { - struct bfq_queue *old_bfqq = bfqq; + struct bfq_queue *waker_bfqq = bfq_waker_bfqq(bfqq); /* Update bic before losing reference to bfqq */ if (bfq_bfqq_in_large_burst(bfqq)) @@ -6799,7 +6825,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) bfqq_already_existing = true; if (!bfqq_already_existing) { - bfqq->waker_bfqq = old_bfqq->waker_bfqq; + bfqq->waker_bfqq = waker_bfqq; bfqq->tentative_waker_bfqq = NULL; /* @@ -6809,7 +6835,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) * woken_list of the waker. See * bfq_check_waker for details. */ - if (bfqq->waker_bfqq) + if (waker_bfqq) hlist_add_head(&bfqq->woken_list_node, &bfqq->waker_bfqq->woken_list); } @@ -6831,7 +6857,8 @@ static struct bfq_queue *bfq_init_rq(struct request *rq) * addition, if the queue has also just been split, we have to * resume its state. */ - if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) { + if (likely(bfqq != &bfqd->oom_bfqq) && !bfqq->new_bfqq && + bfqq_process_refs(bfqq) == 1) { bfqq->bic = bic; if (split) { /* diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 4533eb491661..adbc00449a9c 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -199,8 +199,7 @@ bool bio_integrity_prep(struct bio *bio) unsigned long start, end; unsigned int len, nr_pages; unsigned int bytes, offset, i; - unsigned int intervals; - blk_status_t status; + gfp_t gfp = GFP_NOIO; if (!bi) return true; @@ -223,13 +222,19 @@ bool bio_integrity_prep(struct bio *bio) if (!bi->profile->generate_fn || !(bi->flags & BLK_INTEGRITY_GENERATE)) return true; + + /* + * Zero the memory allocated to not leak uninitialized kernel + * memory to disk. For PI this only affects the app tag, but + * for non-integrity metadata it affects the entire metadata + * buffer. + */ + gfp |= __GFP_ZERO; } - intervals = bio_integrity_intervals(bi, bio_sectors(bio)); /* Allocate kernel buffer for protection data */ - len = intervals * bi->tuple_size; - buf = kmalloc(len, GFP_NOIO); - status = BLK_STS_RESOURCE; + len = bio_integrity_bytes(bi, bio_sectors(bio)); + buf = kmalloc(len, gfp); if (unlikely(buf == NULL)) { printk(KERN_ERR "could not allocate integrity buffer\n"); goto err_end_io; @@ -244,7 +249,6 @@ bool bio_integrity_prep(struct bio *bio) if (IS_ERR(bip)) { printk(KERN_ERR "could not allocate data integrity bioset\n"); kfree(buf); - status = BLK_STS_RESOURCE; goto err_end_io; } @@ -272,7 +276,6 @@ bool bio_integrity_prep(struct bio *bio) if (ret == 0) { printk(KERN_ERR "could not attach integrity payload\n"); - status = BLK_STS_RESOURCE; goto err_end_io; } @@ -294,7 +297,7 @@ bool bio_integrity_prep(struct bio *bio) return true; err_end_io: - bio->bi_status = status; + bio->bi_status = BLK_STS_RESOURCE; bio_endio(bio); return false; diff --git a/block/blk-core.c b/block/blk-core.c index a4155f123ab3..94941e3ce219 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -49,6 +49,7 @@ #include "blk-pm.h" #include "blk-cgroup.h" #include "blk-throttle.h" +#include "blk-ioprio.h" struct dentry *blk_debugfs_root; @@ -799,6 +800,14 @@ end_io: } EXPORT_SYMBOL(submit_bio_noacct); +static void bio_set_ioprio(struct bio *bio) +{ + /* Nobody set ioprio so far? Initialize it based on task's nice value */ + if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) + bio->bi_ioprio = get_current_ioprio(); + blkcg_set_ioprio(bio); +} + /** * submit_bio - submit a bio to the block device layer for I/O * @bio: The &struct bio which describes the I/O @@ -824,6 +833,7 @@ void submit_bio(struct bio *bio) count_vm_events(PGPGOUT, bio_sectors(bio)); } + bio_set_ioprio(bio); submit_bio_noacct(bio); } EXPORT_SYMBOL(submit_bio); diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 69eed260a823..5276c556a9df 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -212,61 +212,44 @@ bool blk_integrity_merge_bio(struct request_queue *q, struct request *req, return true; } -struct integrity_sysfs_entry { - struct attribute attr; - ssize_t (*show)(struct blk_integrity *, char *); - ssize_t (*store)(struct blk_integrity *, const char *, size_t); -}; - -static ssize_t integrity_attr_show(struct kobject *kobj, struct attribute *attr, - char *page) +static inline struct blk_integrity *dev_to_bi(struct device *dev) { - struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct blk_integrity *bi = &disk->queue->integrity; - struct integrity_sysfs_entry *entry = - container_of(attr, struct integrity_sysfs_entry, attr); - - return entry->show(bi, page); + return &dev_to_disk(dev)->queue->integrity; } -static ssize_t integrity_attr_store(struct kobject *kobj, - struct attribute *attr, const char *page, - size_t count) +static ssize_t format_show(struct device *dev, struct device_attribute *attr, + char *page) { - struct gendisk *disk = container_of(kobj, struct gendisk, integrity_kobj); - struct blk_integrity *bi = &disk->queue->integrity; - struct integrity_sysfs_entry *entry = - container_of(attr, struct integrity_sysfs_entry, attr); - ssize_t ret = 0; + struct blk_integrity *bi = dev_to_bi(dev); - if (entry->store) - ret = entry->store(bi, page, count); - - return ret; -} - -static ssize_t integrity_format_show(struct blk_integrity *bi, char *page) -{ if (bi->profile && bi->profile->name) - return sprintf(page, "%s\n", bi->profile->name); - else - return sprintf(page, "none\n"); + return sysfs_emit(page, "%s\n", bi->profile->name); + return sysfs_emit(page, "none\n"); } -static ssize_t integrity_tag_size_show(struct blk_integrity *bi, char *page) +static ssize_t tag_size_show(struct device *dev, struct device_attribute *attr, + char *page) { - return sprintf(page, "%u\n", bi->tag_size); + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%u\n", bi->tag_size); } -static ssize_t integrity_interval_show(struct blk_integrity *bi, char *page) +static ssize_t protection_interval_bytes_show(struct device *dev, + struct device_attribute *attr, + char *page) { - return sprintf(page, "%u\n", - bi->interval_exp ? 1 << bi->interval_exp : 0); + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%u\n", + bi->interval_exp ? 1 << bi->interval_exp : 0); } -static ssize_t integrity_verify_store(struct blk_integrity *bi, - const char *page, size_t count) +static ssize_t read_verify_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t count) { + struct blk_integrity *bi = dev_to_bi(dev); char *p = (char *) page; unsigned long val = simple_strtoul(p, &p, 10); @@ -278,14 +261,20 @@ static ssize_t integrity_verify_store(struct blk_integrity *bi, return count; } -static ssize_t integrity_verify_show(struct blk_integrity *bi, char *page) +static ssize_t read_verify_show(struct device *dev, + struct device_attribute *attr, char *page) { - return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_VERIFY) != 0); + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_VERIFY)); } -static ssize_t integrity_generate_store(struct blk_integrity *bi, - const char *page, size_t count) +static ssize_t write_generate_store(struct device *dev, + struct device_attribute *attr, + const char *page, size_t count) { + struct blk_integrity *bi = dev_to_bi(dev); + char *p = (char *) page; unsigned long val = simple_strtoul(p, &p, 10); @@ -297,68 +286,44 @@ static ssize_t integrity_generate_store(struct blk_integrity *bi, return count; } -static ssize_t integrity_generate_show(struct blk_integrity *bi, char *page) +static ssize_t write_generate_show(struct device *dev, + struct device_attribute *attr, char *page) { - return sprintf(page, "%d\n", (bi->flags & BLK_INTEGRITY_GENERATE) != 0); + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%d\n", !!(bi->flags & BLK_INTEGRITY_GENERATE)); } -static ssize_t integrity_device_show(struct blk_integrity *bi, char *page) +static ssize_t device_is_integrity_capable_show(struct device *dev, + struct device_attribute *attr, + char *page) { - return sprintf(page, "%u\n", - (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) != 0); + struct blk_integrity *bi = dev_to_bi(dev); + + return sysfs_emit(page, "%u\n", + !!(bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)); } -static struct integrity_sysfs_entry integrity_format_entry = { - .attr = { .name = "format", .mode = 0444 }, - .show = integrity_format_show, -}; - -static struct integrity_sysfs_entry integrity_tag_size_entry = { - .attr = { .name = "tag_size", .mode = 0444 }, - .show = integrity_tag_size_show, -}; - -static struct integrity_sysfs_entry integrity_interval_entry = { - .attr = { .name = "protection_interval_bytes", .mode = 0444 }, - .show = integrity_interval_show, -}; - -static struct integrity_sysfs_entry integrity_verify_entry = { - .attr = { .name = "read_verify", .mode = 0644 }, - .show = integrity_verify_show, - .store = integrity_verify_store, -}; - -static struct integrity_sysfs_entry integrity_generate_entry = { - .attr = { .name = "write_generate", .mode = 0644 }, - .show = integrity_generate_show, - .store = integrity_generate_store, -}; - -static struct integrity_sysfs_entry integrity_device_entry = { - .attr = { .name = "device_is_integrity_capable", .mode = 0444 }, - .show = integrity_device_show, -}; +static DEVICE_ATTR_RO(format); +static DEVICE_ATTR_RO(tag_size); +static DEVICE_ATTR_RO(protection_interval_bytes); +static DEVICE_ATTR_RW(read_verify); +static DEVICE_ATTR_RW(write_generate); +static DEVICE_ATTR_RO(device_is_integrity_capable); static struct attribute *integrity_attrs[] = { - &integrity_format_entry.attr, - &integrity_tag_size_entry.attr, - &integrity_interval_entry.attr, - &integrity_verify_entry.attr, - &integrity_generate_entry.attr, - &integrity_device_entry.attr, - NULL, -}; -ATTRIBUTE_GROUPS(integrity); - -static const struct sysfs_ops integrity_ops = { - .show = &integrity_attr_show, - .store = &integrity_attr_store, + &dev_attr_format.attr, + &dev_attr_tag_size.attr, + &dev_attr_protection_interval_bytes.attr, + &dev_attr_read_verify.attr, + &dev_attr_write_generate.attr, + &dev_attr_device_is_integrity_capable.attr, + NULL }; -static struct kobj_type integrity_ktype = { - .default_groups = integrity_groups, - .sysfs_ops = &integrity_ops, +const struct attribute_group blk_integrity_attr_group = { + .name = "integrity", + .attrs = integrity_attrs, }; static blk_status_t blk_integrity_nop_fn(struct blk_integrity_iter *iter) @@ -431,27 +396,7 @@ void blk_integrity_unregister(struct gendisk *disk) if (!bi->profile) return; - /* ensure all bios are off the integrity workqueue */ - blk_flush_integrity(); blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue); memset(bi, 0, sizeof(*bi)); } EXPORT_SYMBOL(blk_integrity_unregister); - -int blk_integrity_add(struct gendisk *disk) -{ - int ret; - - ret = kobject_init_and_add(&disk->integrity_kobj, &integrity_ktype, - &disk_to_dev(disk)->kobj, "%s", "integrity"); - if (!ret) - kobject_uevent(&disk->integrity_kobj, KOBJ_ADD); - return ret; -} - -void blk_integrity_del(struct gendisk *disk) -{ - kobject_uevent(&disk->integrity_kobj, KOBJ_REMOVE); - kobject_del(&disk->integrity_kobj); - kobject_put(&disk->integrity_kobj); -} diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 64b594d660b7..772e909e9fbf 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2057,7 +2057,7 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, struct ioc_now *now) { struct ioc_gq *iocg; - u64 dur, usage_pct, nr_cycles; + u64 dur, usage_pct, nr_cycles, nr_cycles_shift; /* if no debtor, reset the cycle */ if (!nr_debtors) { @@ -2119,10 +2119,12 @@ static void ioc_forgive_debts(struct ioc *ioc, u64 usage_us_sum, int nr_debtors, old_debt = iocg->abs_vdebt; old_delay = iocg->delay; + nr_cycles_shift = min_t(u64, nr_cycles, BITS_PER_LONG - 1); if (iocg->abs_vdebt) - iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles ?: 1; + iocg->abs_vdebt = iocg->abs_vdebt >> nr_cycles_shift ?: 1; + if (iocg->delay) - iocg->delay = iocg->delay >> nr_cycles ?: 1; + iocg->delay = iocg->delay >> nr_cycles_shift ?: 1; iocg_kick_waitq(iocg, true, now); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 100889c276c3..dcd620422d01 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -40,6 +40,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; + unsigned long flags; struct blk_mq_tags *tags = hctx->tags; /* @@ -58,11 +59,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) return; } - spin_lock_irq(&tags->lock); + spin_lock_irqsave(&tags->lock, flags); users = tags->active_queues + 1; WRITE_ONCE(tags->active_queues, users); blk_mq_update_wake_batch(tags, users); - spin_unlock_irq(&tags->lock); + spin_unlock_irqrestore(&tags->lock, flags); } /* diff --git a/block/blk-mq.c b/block/blk-mq.c index 3afa5c8d165b..542b28a2e6b0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -42,7 +42,6 @@ #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" -#include "blk-ioprio.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); @@ -439,6 +438,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data, static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) { + void (*limit_depth)(blk_opf_t, struct blk_mq_alloc_data *) = NULL; struct request_queue *q = data->q; u64 alloc_time_ns = 0; struct request *rq; @@ -465,7 +465,7 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data) !blk_op_is_passthrough(data->cmd_flags) && e->type->ops.limit_depth && !(data->flags & BLK_MQ_REQ_RESERVED)) - e->type->ops.limit_depth(data->cmd_flags, data); + limit_depth = e->type->ops.limit_depth; } retry: @@ -477,6 +477,9 @@ retry: if (data->flags & BLK_MQ_REQ_RESERVED) data->rq_flags |= RQF_RESV; + if (limit_depth) + limit_depth(data->cmd_flags, data); + /* * Try batched alloc if we want more than 1 tag. */ @@ -2945,14 +2948,6 @@ static bool blk_mq_can_use_cached_rq(struct request *rq, struct blk_plug *plug, return true; } -static void bio_set_ioprio(struct bio *bio) -{ - /* Nobody set ioprio so far? Initialize it based on task's nice value */ - if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) - bio->bi_ioprio = get_current_ioprio(); - blkcg_set_ioprio(bio); -} - /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. @@ -2976,7 +2971,6 @@ void blk_mq_submit_bio(struct bio *bio) blk_status_t ret; bio = blk_queue_bounce(bio, q); - bio_set_ioprio(bio); if (plug) { rq = rq_list_peek(&plug->cached_rq); diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index 88f0fe7dcf54..a319311d1ced 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -219,8 +219,8 @@ static int rq_qos_wake_function(struct wait_queue_entry *curr, data->got_token = true; smp_wmb(); - list_del_init(&curr->entry); wake_up_process(data->task); + list_del_init_careful(&curr->entry); return 1; } diff --git a/block/blk.h b/block/blk.h index 9b2f53ff4c37..75316eab0247 100644 --- a/block/blk.h +++ b/block/blk.h @@ -212,8 +212,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } -int blk_integrity_add(struct gendisk *disk); -void blk_integrity_del(struct gendisk *); +extern const struct attribute_group blk_integrity_attr_group; #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline bool blk_integrity_merge_rq(struct request_queue *rq, struct request *r1, struct request *r2) @@ -246,13 +245,6 @@ static inline bool bio_integrity_endio(struct bio *bio) static inline void bio_integrity_free(struct bio *bio) { } -static inline int blk_integrity_add(struct gendisk *disk) -{ - return 0; -} -static inline void blk_integrity_del(struct gendisk *disk) -{ -} #endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout); diff --git a/block/genhd.c b/block/genhd.c index f9e3ecd5ba2f..146ce13b192b 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -489,15 +489,11 @@ int __must_check device_add_disk(struct device *parent, struct gendisk *disk, */ pm_runtime_set_memalloc_noio(ddev, true); - ret = blk_integrity_add(disk); - if (ret) - goto out_del_block_link; - disk->part0->bd_holder_dir = kobject_create_and_add("holders", &ddev->kobj); if (!disk->part0->bd_holder_dir) { ret = -ENOMEM; - goto out_del_integrity; + goto out_del_block_link; } disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj); if (!disk->slave_dir) { @@ -564,8 +560,6 @@ out_put_slave_dir: disk->slave_dir = NULL; out_put_holder_dir: kobject_put(disk->part0->bd_holder_dir); -out_del_integrity: - blk_integrity_del(disk); out_del_block_link: if (!sysfs_deprecated) sysfs_remove_link(block_depr, dev_name(ddev)); @@ -624,7 +618,6 @@ void del_gendisk(struct gendisk *disk) if (WARN_ON_ONCE(!disk_live(disk) && !(disk->flags & GENHD_FL_HIDDEN))) return; - blk_integrity_del(disk); disk_del_events(disk); mutex_lock(&disk->open_mutex); @@ -1160,6 +1153,9 @@ static const struct attribute_group *disk_attr_groups[] = { &disk_attr_group, #ifdef CONFIG_BLK_DEV_IO_TRACE &blk_trace_attr_group, +#endif +#ifdef CONFIG_BLK_DEV_INTEGRITY + &blk_integrity_attr_group, #endif NULL }; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index f10c2a0d18d4..ff029e1acc4d 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -597,6 +597,20 @@ unlock: return rq; } +/* + * 'depth' is a number in the range 1..INT_MAX representing a number of + * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since + * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow(). + * Values larger than q->nr_requests have the same effect as q->nr_requests. + */ +static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth) +{ + struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags; + const unsigned int nrr = hctx->queue->nr_requests; + + return ((qdepth << bt->sb.shift) + nrr - 1) / nrr; +} + /* * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). @@ -613,7 +627,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) * Throttle asynchronous requests and writes such that these requests * do not block the allocation of synchronous requests. */ - data->shallow_depth = dd->async_depth; + data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth); } /* Called by blk_mq_update_nr_requests(). */ @@ -623,9 +637,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx) struct deadline_data *dd = q->elevator->elevator_data; struct blk_mq_tags *tags = hctx->sched_tags; - dd->async_depth = max(1UL, 3 * q->nr_requests / 4); + dd->async_depth = q->nr_requests; - sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth); + sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1); } /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */ diff --git a/block/partitions/core.c b/block/partitions/core.c index 3927f4283f6b..e4f6f56cadc4 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -580,9 +580,11 @@ static bool blk_add_partition(struct gendisk *disk, part = add_partition(disk, p, from, size, state->parts[p].flags, &state->parts[p].info); - if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) { - printk(KERN_ERR " %s: p%d could not be added: %ld\n", - disk->disk_name, p, -PTR_ERR(part)); + if (IS_ERR(part)) { + if (PTR_ERR(part) != -ENXIO) { + printk(KERN_ERR " %s: p%d could not be added: %pe\n", + disk->disk_name, p, part); + } return true; } diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c index 41a2f0eb4ce4..3e4f5a361612 100644 --- a/crypto/asymmetric_keys/asymmetric_type.c +++ b/crypto/asymmetric_keys/asymmetric_type.c @@ -61,17 +61,18 @@ struct key *find_asymmetric_key(struct key *keyring, char *req, *p; int len; - WARN_ON(!id_0 && !id_1 && !id_2); - if (id_0) { lookup = id_0->data; len = id_0->len; } else if (id_1) { lookup = id_1->data; len = id_1->len; - } else { + } else if (id_2) { lookup = id_2->data; len = id_2->len; + } else { + WARN_ON(1); + return ERR_PTR(-EINVAL); } /* Construct an identifier "id:". */ diff --git a/crypto/simd.c b/crypto/simd.c index edaa479a1ec5..d109866641a2 100644 --- a/crypto/simd.c +++ b/crypto/simd.c @@ -136,27 +136,19 @@ static int simd_skcipher_init(struct crypto_skcipher *tfm) return 0; } -struct simd_skcipher_alg *simd_skcipher_create_compat(const char *algname, +struct simd_skcipher_alg *simd_skcipher_create_compat(struct skcipher_alg *ialg, + const char *algname, const char *drvname, const char *basename) { struct simd_skcipher_alg *salg; - struct crypto_skcipher *tfm; - struct skcipher_alg *ialg; struct skcipher_alg *alg; int err; - tfm = crypto_alloc_skcipher(basename, CRYPTO_ALG_INTERNAL, - CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return ERR_CAST(tfm); - - ialg = crypto_skcipher_alg(tfm); - salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); - goto out_put_tfm; + goto out; } salg->ialg_name = basename; @@ -195,30 +187,16 @@ struct simd_skcipher_alg *simd_skcipher_create_compat(const char *algname, if (err) goto out_free_salg; -out_put_tfm: - crypto_free_skcipher(tfm); +out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); - goto out_put_tfm; + goto out; } EXPORT_SYMBOL_GPL(simd_skcipher_create_compat); -struct simd_skcipher_alg *simd_skcipher_create(const char *algname, - const char *basename) -{ - char drvname[CRYPTO_MAX_ALG_NAME]; - - if (snprintf(drvname, CRYPTO_MAX_ALG_NAME, "simd-%s", basename) >= - CRYPTO_MAX_ALG_NAME) - return ERR_PTR(-ENAMETOOLONG); - - return simd_skcipher_create_compat(algname, drvname, basename); -} -EXPORT_SYMBOL_GPL(simd_skcipher_create); - void simd_skcipher_free(struct simd_skcipher_alg *salg) { crypto_unregister_skcipher(&salg->alg); @@ -246,7 +224,7 @@ int simd_register_skciphers_compat(struct skcipher_alg *algs, int count, algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; - simd = simd_skcipher_create_compat(algname, drvname, basename); + simd = simd_skcipher_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; @@ -383,27 +361,19 @@ static int simd_aead_init(struct crypto_aead *tfm) return 0; } -struct simd_aead_alg *simd_aead_create_compat(const char *algname, - const char *drvname, - const char *basename) +static struct simd_aead_alg *simd_aead_create_compat(struct aead_alg *ialg, + const char *algname, + const char *drvname, + const char *basename) { struct simd_aead_alg *salg; - struct crypto_aead *tfm; - struct aead_alg *ialg; struct aead_alg *alg; int err; - tfm = crypto_alloc_aead(basename, CRYPTO_ALG_INTERNAL, - CRYPTO_ALG_INTERNAL | CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) - return ERR_CAST(tfm); - - ialg = crypto_aead_alg(tfm); - salg = kzalloc(sizeof(*salg), GFP_KERNEL); if (!salg) { salg = ERR_PTR(-ENOMEM); - goto out_put_tfm; + goto out; } salg->ialg_name = basename; @@ -442,36 +412,20 @@ struct simd_aead_alg *simd_aead_create_compat(const char *algname, if (err) goto out_free_salg; -out_put_tfm: - crypto_free_aead(tfm); +out: return salg; out_free_salg: kfree(salg); salg = ERR_PTR(err); - goto out_put_tfm; + goto out; } -EXPORT_SYMBOL_GPL(simd_aead_create_compat); -struct simd_aead_alg *simd_aead_create(const char *algname, - const char *basename) -{ - char drvname[CRYPTO_MAX_ALG_NAME]; - - if (snprintf(drvname, CRYPTO_MAX_ALG_NAME, "simd-%s", basename) >= - CRYPTO_MAX_ALG_NAME) - return ERR_PTR(-ENAMETOOLONG); - - return simd_aead_create_compat(algname, drvname, basename); -} -EXPORT_SYMBOL_GPL(simd_aead_create); - -void simd_aead_free(struct simd_aead_alg *salg) +static void simd_aead_free(struct simd_aead_alg *salg) { crypto_unregister_aead(&salg->alg); kfree(salg); } -EXPORT_SYMBOL_GPL(simd_aead_free); int simd_register_aeads_compat(struct aead_alg *algs, int count, struct simd_aead_alg **simd_algs) @@ -493,7 +447,7 @@ int simd_register_aeads_compat(struct aead_alg *algs, int count, algname = algs[i].base.cra_name + 2; drvname = algs[i].base.cra_driver_name + 2; basename = algs[i].base.cra_driver_name; - simd = simd_aead_create_compat(algname, drvname, basename); + simd = simd_aead_create_compat(algs + i, algname, drvname, basename); err = PTR_ERR(simd); if (IS_ERR(simd)) goto err_unregister; diff --git a/crypto/xor.c b/crypto/xor.c index 8e72e5d5db0d..56aa3169e871 100644 --- a/crypto/xor.c +++ b/crypto/xor.c @@ -83,33 +83,30 @@ static void __init do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2) { int speed; - int i, j; - ktime_t min, start, diff; + unsigned long reps; + ktime_t min, start, t0; tmpl->next = template_list; template_list = tmpl; preempt_disable(); - min = (ktime_t)S64_MAX; - for (i = 0; i < 3; i++) { - start = ktime_get(); - for (j = 0; j < REPS; j++) { - mb(); /* prevent loop optimization */ - tmpl->do_2(BENCH_SIZE, b1, b2); - mb(); - } - diff = ktime_sub(ktime_get(), start); - if (diff < min) - min = diff; - } + reps = 0; + t0 = ktime_get(); + /* delay start until time has advanced */ + while ((start = ktime_get()) == t0) + cpu_relax(); + do { + mb(); /* prevent loop optimization */ + tmpl->do_2(BENCH_SIZE, b1, b2); + mb(); + } while (reps++ < REPS || (t0 = ktime_get()) == start); + min = ktime_sub(t0, start); preempt_enable(); // bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s] - if (!min) - min = 1; - speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); + speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min); tmpl->speed = speed; pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed); diff --git a/drivers/acpi/acpi_pad.c b/drivers/acpi/acpi_pad.c index ec0e22a1e25d..bfb8ad1e2e85 100644 --- a/drivers/acpi/acpi_pad.c +++ b/drivers/acpi/acpi_pad.c @@ -130,8 +130,10 @@ static void exit_round_robin(unsigned int tsk_index) { struct cpumask *pad_busy_cpus = to_cpumask(pad_busy_cpus_bits); - cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus); - tsk_in_cpu[tsk_index] = -1; + if (tsk_in_cpu[tsk_index] != -1) { + cpumask_clear_cpu(tsk_in_cpu[tsk_index], pad_busy_cpus); + tsk_in_cpu[tsk_index] = -1; + } } static unsigned int idle_pct = 5; /* percentage */ diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c index 6737b1cbf6d6..8bd5c4fa91f2 100644 --- a/drivers/acpi/acpi_processor.c +++ b/drivers/acpi/acpi_processor.c @@ -373,7 +373,7 @@ static int acpi_processor_add(struct acpi_device *device, result = acpi_processor_get_info(device); if (result) /* Processor is not physically present or unavailable */ - return 0; + goto err_clear_driver_data; BUG_ON(pr->id >= nr_cpu_ids); @@ -388,7 +388,7 @@ static int acpi_processor_add(struct acpi_device *device, "BIOS reported wrong ACPI id %d for the processor\n", pr->id); /* Give up, but do not abort the namespace scan. */ - goto err; + goto err_clear_driver_data; } /* * processor_device_array is not cleared on errors to allow buggy BIOS @@ -400,12 +400,12 @@ static int acpi_processor_add(struct acpi_device *device, dev = get_cpu_device(pr->id); if (!dev) { result = -ENODEV; - goto err; + goto err_clear_per_cpu; } result = acpi_bind_one(dev, device); if (result) - goto err; + goto err_clear_per_cpu; pr->dev = dev; @@ -416,10 +416,11 @@ static int acpi_processor_add(struct acpi_device *device, dev_err(dev, "Processor driver could not be attached\n"); acpi_unbind_one(dev); - err: - free_cpumask_var(pr->throttling.shared_cpu_map); - device->driver_data = NULL; + err_clear_per_cpu: per_cpu(processors, pr->id) = NULL; + err_clear_driver_data: + device->driver_data = NULL; + free_cpumask_var(pr->throttling.shared_cpu_map); err_free_pr: kfree(pr); return result; diff --git a/drivers/acpi/acpica/dbconvert.c b/drivers/acpi/acpica/dbconvert.c index 2b84ac093698..8dbab6932049 100644 --- a/drivers/acpi/acpica/dbconvert.c +++ b/drivers/acpi/acpica/dbconvert.c @@ -174,6 +174,8 @@ acpi_status acpi_db_convert_to_package(char *string, union acpi_object *object) elements = ACPI_ALLOCATE_ZEROED(DB_DEFAULT_PKG_ELEMENTS * sizeof(union acpi_object)); + if (!elements) + return (AE_NO_MEMORY); this = string; for (i = 0; i < (DB_DEFAULT_PKG_ELEMENTS - 1); i++) { diff --git a/drivers/acpi/acpica/exprep.c b/drivers/acpi/acpica/exprep.c index 08f06797386a..4daef7530d91 100644 --- a/drivers/acpi/acpica/exprep.c +++ b/drivers/acpi/acpica/exprep.c @@ -437,6 +437,9 @@ acpi_status acpi_ex_prep_field_value(struct acpi_create_field_info *info) if (info->connection_node) { second_desc = info->connection_node->object; + if (second_desc == NULL) { + break; + } if (!(second_desc->common.flags & AOPOBJ_DATA_VALID)) { status = acpi_ds_get_buffer_arguments(second_desc); diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c index 7b5470f404f3..104e6e96c31e 100644 --- a/drivers/acpi/acpica/exsystem.c +++ b/drivers/acpi/acpica/exsystem.c @@ -133,14 +133,15 @@ acpi_status acpi_ex_system_do_stall(u32 how_long_us) * (ACPI specifies 100 usec as max, but this gives some slack in * order to support existing BIOSs) */ - ACPI_ERROR((AE_INFO, - "Time parameter is too large (%u)", how_long_us)); + ACPI_ERROR_ONCE((AE_INFO, + "Time parameter is too large (%u)", + how_long_us)); status = AE_AML_OPERAND_VALUE; } else { if (how_long_us > 100) { - ACPI_WARNING((AE_INFO, - "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.", - how_long_us)); + ACPI_WARNING_ONCE((AE_INFO, + "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.", + how_long_us)); } acpi_os_stall(how_long_us); } diff --git a/drivers/acpi/acpica/psargs.c b/drivers/acpi/acpica/psargs.c index f7ec5606098c..418d56203e27 100644 --- a/drivers/acpi/acpica/psargs.c +++ b/drivers/acpi/acpica/psargs.c @@ -25,6 +25,8 @@ acpi_ps_get_next_package_length(struct acpi_parse_state *parser_state); static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state *parser_state); +static void acpi_ps_free_field_list(union acpi_parse_object *start); + /******************************************************************************* * * FUNCTION: acpi_ps_get_next_package_length @@ -683,6 +685,39 @@ static union acpi_parse_object *acpi_ps_get_next_field(struct acpi_parse_state return_PTR(field); } +/******************************************************************************* + * + * FUNCTION: acpi_ps_free_field_list + * + * PARAMETERS: start - First Op in field list + * + * RETURN: None. + * + * DESCRIPTION: Free all Op objects inside a field list. + * + ******************************************************************************/ + +static void acpi_ps_free_field_list(union acpi_parse_object *start) +{ + union acpi_parse_object *cur = start; + union acpi_parse_object *next; + union acpi_parse_object *arg; + + while (cur) { + next = cur->common.next; + + /* AML_INT_CONNECTION_OP can have a single argument */ + + arg = acpi_ps_get_arg(cur, 0); + if (arg) { + acpi_ps_free_op(arg); + } + + acpi_ps_free_op(cur); + cur = next; + } +} + /******************************************************************************* * * FUNCTION: acpi_ps_get_next_arg @@ -751,6 +786,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, while (parser_state->aml < parser_state->pkg_end) { field = acpi_ps_get_next_field(parser_state); if (!field) { + if (arg) { + acpi_ps_free_field_list(arg); + } + return_ACPI_STATUS(AE_NO_MEMORY); } @@ -820,6 +859,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, acpi_ps_get_next_namepath(walk_state, parser_state, arg, ACPI_NOT_METHOD_CALL); + if (ACPI_FAILURE(status)) { + acpi_ps_free_op(arg); + return_ACPI_STATUS(status); + } } else { /* Single complex argument, nothing returned */ @@ -854,6 +897,10 @@ acpi_ps_get_next_arg(struct acpi_walk_state *walk_state, acpi_ps_get_next_namepath(walk_state, parser_state, arg, ACPI_POSSIBLE_METHOD_CALL); + if (ACPI_FAILURE(status)) { + acpi_ps_free_op(arg); + return_ACPI_STATUS(status); + } if (arg->common.aml_opcode == AML_INT_METHODCALL_OP) { diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c index 084f156bdfbc..5a4e02266241 100644 --- a/drivers/acpi/battery.c +++ b/drivers/acpi/battery.c @@ -667,12 +667,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* * The Battery Hooking API * @@ -686,27 +692,34 @@ static LIST_HEAD(acpi_battery_list); static LIST_HEAD(battery_hook_list); static DEFINE_MUTEX(hook_mutex); -static void __battery_hook_unregister(struct acpi_battery_hook *hook, int lock) +static void battery_hook_unregister_unlocked(struct acpi_battery_hook *hook) { struct acpi_battery *battery; + /* * In order to remove a hook, we first need to * de-register all the batteries that are registered. */ - if (lock) - mutex_lock(&hook_mutex); list_for_each_entry(battery, &acpi_battery_list, list) { hook->remove_battery(battery->bat); } - list_del(&hook->list); - if (lock) - mutex_unlock(&hook_mutex); + list_del_init(&hook->list); + pr_info("extension unregistered: %s\n", hook->name); } void battery_hook_unregister(struct acpi_battery_hook *hook) { - __battery_hook_unregister(hook, 1); + mutex_lock(&hook_mutex); + /* + * Ignore already unregistered battery hooks. This might happen + * if a battery hook was previously unloaded due to an error when + * adding a new battery. + */ + if (!list_empty(&hook->list)) + battery_hook_unregister_unlocked(hook); + + mutex_unlock(&hook_mutex); } EXPORT_SYMBOL_GPL(battery_hook_unregister); @@ -715,7 +728,6 @@ void battery_hook_register(struct acpi_battery_hook *hook) struct acpi_battery *battery; mutex_lock(&hook_mutex); - INIT_LIST_HEAD(&hook->list); list_add(&hook->list, &battery_hook_list); /* * Now that the driver is registered, we need @@ -732,7 +744,7 @@ void battery_hook_register(struct acpi_battery_hook *hook) * hooks. */ pr_err("extension failed to load: %s", hook->name); - __battery_hook_unregister(hook, 0); + battery_hook_unregister_unlocked(hook); goto end; } } @@ -769,7 +781,7 @@ static void battery_hook_add_battery(struct acpi_battery *battery) */ pr_err("error in extension, unloading: %s", hook_node->name); - __battery_hook_unregister(hook_node, 0); + battery_hook_unregister_unlocked(hook_node); } } mutex_unlock(&hook_mutex); @@ -802,14 +814,17 @@ static void __exit battery_hook_exit(void) * need to remove the hooks. */ list_for_each_entry_safe(hook, ptr, &battery_hook_list, list) { - __battery_hook_unregister(hook, 1); + battery_hook_unregister(hook); } mutex_destroy(&hook_mutex); } static int sysfs_add_battery(struct acpi_battery *battery) { - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; bool full_cap_broken = false; if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) && @@ -854,7 +869,7 @@ static int sysfs_add_battery(struct acpi_battery *battery) return result; } battery_hook_add_battery(battery); - return device_create_file(&battery->bat->dev, &alarm_attr); + return 0; } static void sysfs_remove_battery(struct acpi_battery *battery) @@ -865,7 +880,6 @@ static void sysfs_remove_battery(struct acpi_battery *battery) return; } battery_hook_remove_battery(battery); - device_remove_file(&battery->bat->dev, &alarm_attr); power_supply_unregister(battery->bat); battery->bat = NULL; mutex_unlock(&battery->sysfs_lock); diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c index 1f9b9a4c38c7..000a7a7e5d49 100644 --- a/drivers/acpi/button.c +++ b/drivers/acpi/button.c @@ -121,6 +121,17 @@ static const struct dmi_system_id dmi_lid_quirks[] = { }, .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, }, + { + /* + * Samsung galaxybook2 ,initial _LID device notification returns + * lid closed. + */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), + DMI_MATCH(DMI_PRODUCT_NAME, "750XED"), + }, + .driver_data = (void *)(long)ACPI_BUTTON_LID_INIT_OPEN, + }, {} }; diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 49339f37d940..3d9326172af4 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -39,6 +39,9 @@ #include #include #include +#include +#include +#include #include @@ -167,8 +170,11 @@ show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time); #define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width) /* Shift and apply the mask for CPC reads/writes */ -#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \ +#define MASK_VAL_READ(reg, val) (((val) >> (reg)->bit_offset) & \ GENMASK(((reg)->bit_width) - 1, 0)) +#define MASK_VAL_WRITE(reg, prev_val, val) \ + ((((val) & GENMASK(((reg)->bit_width) - 1, 0)) << (reg)->bit_offset) | \ + ((prev_val) & ~(GENMASK(((reg)->bit_width) - 1, 0) << (reg)->bit_offset))) \ static ssize_t show_feedback_ctrs(struct kobject *kobj, struct kobj_attribute *attr, char *buf) @@ -851,6 +857,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) /* Store CPU Logical ID */ cpc_ptr->cpu_id = pr->id; + spin_lock_init(&cpc_ptr->rmw_lock); /* Parse PSD data for this CPU */ ret = acpi_get_psd(cpc_ptr, handle); @@ -1056,7 +1063,7 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val) } if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) - *val = MASK_VAL(reg, *val); + *val = MASK_VAL_READ(reg, *val); return 0; } @@ -1065,9 +1072,11 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) { int ret_val = 0; int size; + u64 prev_val; void __iomem *vaddr = NULL; int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu); struct cpc_reg *reg = ®_res->cpc_entry.reg; + struct cpc_desc *cpc_desc; size = GET_BIT_WIDTH(reg); @@ -1100,8 +1109,34 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) return acpi_os_write_memory((acpi_physical_address)reg->address, val, size); - if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) - val = MASK_VAL(reg, val); + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) { + cpc_desc = per_cpu(cpc_desc_ptr, cpu); + if (!cpc_desc) { + pr_debug("No CPC descriptor for CPU:%d\n", cpu); + return -ENODEV; + } + + spin_lock(&cpc_desc->rmw_lock); + switch (size) { + case 8: + prev_val = readb_relaxed(vaddr); + break; + case 16: + prev_val = readw_relaxed(vaddr); + break; + case 32: + prev_val = readl_relaxed(vaddr); + break; + case 64: + prev_val = readq_relaxed(vaddr); + break; + default: + spin_unlock(&cpc_desc->rmw_lock); + return -EFAULT; + } + val = MASK_VAL_WRITE(reg, prev_val, val); + val |= prev_val; + } switch (size) { case 8: @@ -1128,6 +1163,9 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val) break; } + if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) + spin_unlock(&cpc_desc->rmw_lock); + return ret_val; } @@ -1629,3 +1667,116 @@ unsigned int cppc_get_transition_latency(int cpu_num) return latency_ns; } EXPORT_SYMBOL_GPL(cppc_get_transition_latency); + +/* Minimum struct length needed for the DMI processor entry we want */ +#define DMI_ENTRY_PROCESSOR_MIN_LENGTH 48 + +/* Offset in the DMI processor structure for the max frequency */ +#define DMI_PROCESSOR_MAX_SPEED 0x14 + +/* Callback function used to retrieve the max frequency from DMI */ +static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) +{ + const u8 *dmi_data = (const u8 *)dm; + u16 *mhz = (u16 *)private; + + if (dm->type == DMI_ENTRY_PROCESSOR && + dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) { + u16 val = (u16)get_unaligned((const u16 *) + (dmi_data + DMI_PROCESSOR_MAX_SPEED)); + *mhz = val > *mhz ? val : *mhz; + } +} + +/* Look up the max frequency in DMI */ +static u64 cppc_get_dmi_max_khz(void) +{ + u16 mhz = 0; + + dmi_walk(cppc_find_dmi_mhz, &mhz); + + /* + * Real stupid fallback value, just in case there is no + * actual value set. + */ + mhz = mhz ? mhz : 1; + + return KHZ_PER_MHZ * mhz; +} + +/* + * If CPPC lowest_freq and nominal_freq registers are exposed then we can + * use them to convert perf to freq and vice versa. The conversion is + * extrapolated as an affine function passing by the 2 points: + * - (Low perf, Low freq) + * - (Nominal perf, Nominal freq) + */ +unsigned int cppc_perf_to_khz(struct cppc_perf_caps *caps, unsigned int perf) +{ + s64 retval, offset = 0; + static u64 max_khz; + u64 mul, div; + + if (caps->lowest_freq && caps->nominal_freq) { + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_freq; + div = caps->nominal_perf; + } else { + mul = caps->nominal_freq - caps->lowest_freq; + div = caps->nominal_perf - caps->lowest_perf; + } + mul *= KHZ_PER_MHZ; + offset = caps->nominal_freq * KHZ_PER_MHZ - + div64_u64(caps->nominal_perf * mul, div); + } else { + if (!max_khz) + max_khz = cppc_get_dmi_max_khz(); + mul = max_khz; + div = caps->highest_perf; + } + + retval = offset + div64_u64(perf * mul, div); + if (retval >= 0) + return retval; + return 0; +} +EXPORT_SYMBOL_GPL(cppc_perf_to_khz); + +unsigned int cppc_khz_to_perf(struct cppc_perf_caps *caps, unsigned int freq) +{ + s64 retval, offset = 0; + static u64 max_khz; + u64 mul, div; + + if (caps->lowest_freq && caps->nominal_freq) { + /* Avoid special case when nominal_freq is equal to lowest_freq */ + if (caps->lowest_freq == caps->nominal_freq) { + mul = caps->nominal_perf; + div = caps->nominal_freq; + } else { + mul = caps->nominal_perf - caps->lowest_perf; + div = caps->nominal_freq - caps->lowest_freq; + } + /* + * We don't need to convert to kHz for computing offset and can + * directly use nominal_freq and lowest_freq as the div64_u64 + * will remove the frequency unit. + */ + offset = caps->nominal_perf - + div64_u64(caps->nominal_freq * mul, div); + /* But we need it for computing the perf level. */ + div *= KHZ_PER_MHZ; + } else { + if (!max_khz) + max_khz = cppc_get_dmi_max_khz(); + mul = caps->highest_perf; + div = max_khz; + } + + retval = offset + div64_u64(freq * mul, div); + if (retval >= 0) + return retval; + return 0; +} +EXPORT_SYMBOL_GPL(cppc_khz_to_perf); diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c index c727fb320eee..a8b4e2bed598 100644 --- a/drivers/acpi/device_sysfs.c +++ b/drivers/acpi/device_sysfs.c @@ -544,8 +544,9 @@ int acpi_device_setup_files(struct acpi_device *dev) * If device has _STR, 'description' file is created */ if (acpi_has_method(dev->handle, "_STR")) { - status = acpi_evaluate_object(dev->handle, "_STR", - NULL, &buffer); + status = acpi_evaluate_object_typed(dev->handle, "_STR", + NULL, &buffer, + ACPI_TYPE_BUFFER); if (ACPI_FAILURE(status)) buffer.pointer = NULL; dev->pnp.str_obj = buffer.pointer; diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 77d1f2cb89ef..63803091f8b1 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -797,6 +797,9 @@ static int acpi_ec_transaction_unlocked(struct acpi_ec *ec, unsigned long tmp; int ret = 0; + if (t->rdata) + memset(t->rdata, 0, t->rlen); + /* start transaction */ spin_lock_irqsave(&ec->lock, tmp); /* Enable GPE for command processing (IBF=0/OBF=1) */ @@ -833,8 +836,6 @@ static int acpi_ec_transaction(struct acpi_ec *ec, struct transaction *t) if (!ec || (!t) || (t->wlen && !t->wdata) || (t->rlen && !t->rdata)) return -EINVAL; - if (t->rdata) - memset(t->rdata, 0, t->rlen); mutex_lock(&ec->mutex); if (ec->global_lock) { @@ -861,7 +862,7 @@ static int acpi_ec_burst_enable(struct acpi_ec *ec) .wdata = NULL, .rdata = &d, .wlen = 0, .rlen = 1}; - return acpi_ec_transaction(ec, &t); + return acpi_ec_transaction_unlocked(ec, &t); } static int acpi_ec_burst_disable(struct acpi_ec *ec) @@ -871,7 +872,7 @@ static int acpi_ec_burst_disable(struct acpi_ec *ec) .wlen = 0, .rlen = 0}; return (acpi_ec_read_status(ec) & ACPI_EC_FLAG_BURST) ? - acpi_ec_transaction(ec, &t) : 0; + acpi_ec_transaction_unlocked(ec, &t) : 0; } static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) @@ -887,6 +888,19 @@ static int acpi_ec_read(struct acpi_ec *ec, u8 address, u8 *data) return result; } +static int acpi_ec_read_unlocked(struct acpi_ec *ec, u8 address, u8 *data) +{ + int result; + u8 d; + struct transaction t = {.command = ACPI_EC_COMMAND_READ, + .wdata = &address, .rdata = &d, + .wlen = 1, .rlen = 1}; + + result = acpi_ec_transaction_unlocked(ec, &t); + *data = d; + return result; +} + static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) { u8 wdata[2] = { address, data }; @@ -897,6 +911,16 @@ static int acpi_ec_write(struct acpi_ec *ec, u8 address, u8 data) return acpi_ec_transaction(ec, &t); } +static int acpi_ec_write_unlocked(struct acpi_ec *ec, u8 address, u8 data) +{ + u8 wdata[2] = { address, data }; + struct transaction t = {.command = ACPI_EC_COMMAND_WRITE, + .wdata = wdata, .rdata = NULL, + .wlen = 2, .rlen = 0}; + + return acpi_ec_transaction_unlocked(ec, &t); +} + int ec_read(u8 addr, u8 *val) { int err; @@ -1304,6 +1328,7 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, struct acpi_ec *ec = handler_context; int result = 0, i, bytes = bits / 8; u8 *value = (u8 *)value64; + u32 glk; if ((address > 0xFF) || !value || !handler_context) return AE_BAD_PARAMETER; @@ -1311,17 +1336,38 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, if (function != ACPI_READ && function != ACPI_WRITE) return AE_BAD_PARAMETER; + mutex_lock(&ec->mutex); + + if (ec->global_lock) { + acpi_status status; + + status = acpi_acquire_global_lock(ACPI_EC_UDELAY_GLK, &glk); + if (ACPI_FAILURE(status)) { + result = -ENODEV; + goto unlock; + } + } + if (ec->busy_polling || bits > 8) acpi_ec_burst_enable(ec); - for (i = 0; i < bytes; ++i, ++address, ++value) + for (i = 0; i < bytes; ++i, ++address, ++value) { result = (function == ACPI_READ) ? - acpi_ec_read(ec, address, value) : - acpi_ec_write(ec, address, *value); + acpi_ec_read_unlocked(ec, address, value) : + acpi_ec_write_unlocked(ec, address, *value); + if (result < 0) + break; + } if (ec->busy_polling || bits > 8) acpi_ec_burst_disable(ec); + if (ec->global_lock) + acpi_release_global_lock(glk); + +unlock: + mutex_unlock(&ec->mutex); + switch (result) { case -EINVAL: return AE_BAD_PARAMETER; @@ -1329,8 +1375,10 @@ acpi_ec_space_handler(u32 function, acpi_physical_address address, return AE_NOT_FOUND; case -ETIME: return AE_TIME; - default: + case 0: return AE_OK; + default: + return AE_ERROR; } } diff --git a/drivers/acpi/pmic/tps68470_pmic.c b/drivers/acpi/pmic/tps68470_pmic.c index ebd03e472955..0d1a82eeb4b0 100644 --- a/drivers/acpi/pmic/tps68470_pmic.c +++ b/drivers/acpi/pmic/tps68470_pmic.c @@ -376,10 +376,8 @@ static int tps68470_pmic_opregion_probe(struct platform_device *pdev) struct tps68470_pmic_opregion *opregion; acpi_status status; - if (!dev || !tps68470_regmap) { - dev_warn(dev, "dev or regmap is NULL\n"); - return -EINVAL; - } + if (!tps68470_regmap) + return dev_err_probe(dev, -EINVAL, "regmap is missing\n"); if (!handle) { dev_warn(dev, "acpi handle is NULL\n"); diff --git a/drivers/acpi/prmt.c b/drivers/acpi/prmt.c index 3d4c4620f9f9..dd0261fd12d6 100644 --- a/drivers/acpi/prmt.c +++ b/drivers/acpi/prmt.c @@ -52,7 +52,7 @@ struct prm_context_buffer { static LIST_HEAD(prm_module_list); struct prm_handler_info { - guid_t guid; + efi_guid_t guid; void *handler_addr; u64 static_data_buffer_addr; u64 acpi_param_buffer_addr; @@ -72,17 +72,21 @@ struct prm_module_info { struct prm_handler_info handlers[]; }; -static u64 efi_pa_va_lookup(u64 pa) +static u64 efi_pa_va_lookup(efi_guid_t *guid, u64 pa) { efi_memory_desc_t *md; u64 pa_offset = pa & ~PAGE_MASK; u64 page = pa & PAGE_MASK; for_each_efi_memory_desc(md) { - if (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages) + if ((md->attribute & EFI_MEMORY_RUNTIME) && + (md->phys_addr < pa && pa < md->phys_addr + PAGE_SIZE * md->num_pages)) { return pa_offset + md->virt_addr + page - md->phys_addr; + } } + pr_warn("Failed to find VA for GUID: %pUL, PA: 0x%llx", guid, pa); + return 0; } @@ -148,9 +152,15 @@ acpi_parse_prmt(union acpi_subtable_headers *header, const unsigned long end) th = &tm->handlers[cur_handler]; guid_copy(&th->guid, (guid_t *)handler_info->handler_guid); - th->handler_addr = (void *)efi_pa_va_lookup(handler_info->handler_address); - th->static_data_buffer_addr = efi_pa_va_lookup(handler_info->static_data_buffer_address); - th->acpi_param_buffer_addr = efi_pa_va_lookup(handler_info->acpi_param_buffer_address); + th->handler_addr = + (void *)efi_pa_va_lookup(&th->guid, handler_info->handler_address); + + th->static_data_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->static_data_buffer_address); + + th->acpi_param_buffer_addr = + efi_pa_va_lookup(&th->guid, handler_info->acpi_param_buffer_address); + } while (++cur_handler < tm->handler_count && (handler_info = get_next_handler(handler_info))); return 0; @@ -253,6 +263,13 @@ static acpi_status acpi_platformrt_space_handler(u32 function, if (!handler || !module) goto invalid_guid; + if (!handler->handler_addr || + !handler->static_data_buffer_addr || + !handler->acpi_param_buffer_addr) { + buffer->prm_status = PRM_HANDLER_ERROR; + return AE_OK; + } + ACPI_COPY_NAMESEG(context.signature, "PRMC"); context.revision = 0x0; context.reserved = 0x0; diff --git a/drivers/acpi/processor_idle.c b/drivers/acpi/processor_idle.c index 6f613eef2887..18f4334a9691 100644 --- a/drivers/acpi/processor_idle.c +++ b/drivers/acpi/processor_idle.c @@ -16,7 +16,6 @@ #include #include #include /* need_resched() */ -#include #include #include #include @@ -388,25 +387,24 @@ static void acpi_processor_power_verify_c3(struct acpi_processor *pr, return; } -static int acpi_cst_latency_cmp(const void *a, const void *b) +static void acpi_cst_latency_sort(struct acpi_processor_cx *states, size_t length) { - const struct acpi_processor_cx *x = a, *y = b; + int i, j, k; - if (!(x->valid && y->valid)) - return 0; - if (x->latency > y->latency) - return 1; - if (x->latency < y->latency) - return -1; - return 0; -} -static void acpi_cst_latency_swap(void *a, void *b, int n) -{ - struct acpi_processor_cx *x = a, *y = b; + for (i = 1; i < length; i++) { + if (!states[i].valid) + continue; - if (!(x->valid && y->valid)) - return; - swap(x->latency, y->latency); + for (j = i - 1, k = i; j >= 0; j--) { + if (!states[j].valid) + continue; + + if (states[j].latency > states[k].latency) + swap(states[j].latency, states[k].latency); + + k = j; + } + } } static int acpi_processor_power_verify(struct acpi_processor *pr) @@ -451,10 +449,7 @@ static int acpi_processor_power_verify(struct acpi_processor *pr) if (buggy_latency) { pr_notice("FW issue: working around C-state latencies out of order\n"); - sort(&pr->power.states[1], max_cstate, - sizeof(struct acpi_processor_cx), - acpi_cst_latency_cmp, - acpi_cst_latency_swap); + acpi_cst_latency_sort(&pr->power.states[1], max_cstate); } lapic_timer_propagate_broadcast(pr); diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c index d34812db1b67..d57bc814dec4 100644 --- a/drivers/acpi/resource.c +++ b/drivers/acpi/resource.c @@ -439,6 +439,13 @@ static const struct dmi_system_id asus_laptop[] = { DMI_MATCH(DMI_BOARD_NAME, "S5602ZA"), }, }, + { + /* Asus Vivobook X1704VAP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "X1704VAP"), + }, + }, { .ident = "Asus ExpertBook B1402CBA", .matches = { @@ -495,6 +502,13 @@ static const struct dmi_system_id tongfang_gm_rg[] = { DMI_MATCH(DMI_BOARD_NAME, "GMxRGxx"), }, }, + { + /* LG Electronics 16T90SP */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LG Electronics"), + DMI_MATCH(DMI_BOARD_NAME, "16T90SP"), + }, + }, { } }; @@ -506,12 +520,25 @@ static const struct dmi_system_id maingear_laptop[] = { DMI_MATCH(DMI_PRODUCT_NAME, "MG-VCP2-15A3070T"), } }, + { + /* Asus ExpertBook B2502CVA */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."), + DMI_MATCH(DMI_BOARD_NAME, "B2502CVA"), + }, + }, { /* TongFang GMxXGxx/TUXEDO Polaris 15 Gen5 AMD */ .matches = { DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"), }, }, + { + /* TongFang GMxXGxX/TUXEDO Polaris 15 Gen5 AMD */ + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "GMxXGxX"), + }, + }, { /* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */ .matches = { diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c index e6a01a8df1b8..7c0eba1a37d8 100644 --- a/drivers/acpi/sbs.c +++ b/drivers/acpi/sbs.c @@ -77,7 +77,6 @@ struct acpi_battery { u16 spec; u8 id; u8 present:1; - u8 have_sysfs_alarm:1; }; #define to_acpi_battery(x) power_supply_get_drvdata(x) @@ -462,12 +461,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev, return count; } -static const struct device_attribute alarm_attr = { +static struct device_attribute alarm_attr = { .attr = {.name = "alarm", .mode = 0644}, .show = acpi_battery_alarm_show, .store = acpi_battery_alarm_store, }; +static struct attribute *acpi_battery_attrs[] = { + &alarm_attr.attr, + NULL +}; +ATTRIBUTE_GROUPS(acpi_battery); + /* -------------------------------------------------------------------------- Driver Interface -------------------------------------------------------------------------- */ @@ -509,7 +514,10 @@ static int acpi_battery_read(struct acpi_battery *battery) static int acpi_battery_add(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - struct power_supply_config psy_cfg = { .drv_data = battery, }; + struct power_supply_config psy_cfg = { + .drv_data = battery, + .attr_grp = acpi_battery_groups, + }; int result; battery->id = id; @@ -539,10 +547,6 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id) goto end; } - result = device_create_file(&battery->bat->dev, &alarm_attr); - if (result) - goto end; - battery->have_sysfs_alarm = 1; end: pr_info("%s [%s]: Battery Slot [%s] (battery %s)\n", ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device), @@ -554,11 +558,8 @@ static void acpi_battery_remove(struct acpi_sbs *sbs, int id) { struct acpi_battery *battery = &sbs->battery[id]; - if (battery->bat) { - if (battery->have_sysfs_alarm) - device_remove_file(&battery->bat->dev, &alarm_attr); + if (battery->bat) power_supply_unregister(battery->bat); - } } static int acpi_charger_add(struct acpi_sbs *sbs) diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c index 60b0128a10e8..f7a2ab62c6c2 100644 --- a/drivers/acpi/video_detect.c +++ b/drivers/acpi/video_detect.c @@ -258,6 +258,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = { DMI_MATCH(DMI_PRODUCT_NAME, "PCG-FRV35"), }, }, + { + .callback = video_detect_force_vendor, + /* Panasonic Toughbook CF-18 */ + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Matsushita Electric Industrial"), + DMI_MATCH(DMI_PRODUCT_NAME, "CF-18"), + }, + }, /* * Toshiba models with Transflective display, these need to use diff --git a/drivers/android/binder.c b/drivers/android/binder.c index 46111f8c12e6..931aa2609f3b 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -569,9 +569,7 @@ static bool binder_has_work(struct binder_thread *thread, bool do_proc_work) static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread) { return !thread->transaction_stack && - binder_worklist_empty_ilocked(&thread->todo) && - (thread->looper & (BINDER_LOOPER_STATE_ENTERED | - BINDER_LOOPER_STATE_REGISTERED)); + binder_worklist_empty_ilocked(&thread->todo); } static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc, @@ -3331,6 +3329,7 @@ static void binder_transaction(struct binder_proc *proc, */ copy_size = object_offset - user_offset; if (copy_size && (user_offset > object_offset || + object_offset > tr->data_size || binder_alloc_copy_user_to_buffer( &target_proc->alloc, t->buffer, user_offset, diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 5a13630034ef..14bcfebf20b8 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -5471,6 +5471,9 @@ static void ata_host_release(struct kref *kref) for (i = 0; i < host->n_ports; i++) { struct ata_port *ap = host->ports[i]; + if (!ap) + continue; + kfree(ap->pmp_link); kfree(ap->slave_link); kfree(ap); @@ -5529,8 +5532,10 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports) } dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL); - if (!dr) + if (!dr) { + kfree(host); goto err_out; + } devres_add(dev, dr); dev_set_drvdata(dev, host); diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c index b8034d194078..3f327ba759fd 100644 --- a/drivers/ata/libata-eh.c +++ b/drivers/ata/libata-eh.c @@ -3946,10 +3946,20 @@ static void ata_eh_handle_port_suspend(struct ata_port *ap) WARN_ON(ap->pflags & ATA_PFLAG_SUSPENDED); - /* Set all devices attached to the port in standby mode */ - ata_for_each_link(link, ap, HOST_FIRST) { - ata_for_each_dev(dev, link, ENABLED) - ata_dev_power_set_standby(dev); + /* + * We will reach this point for all of the PM events: + * PM_EVENT_SUSPEND (if runtime pm, PM_EVENT_AUTO will also be set) + * PM_EVENT_FREEZE, and PM_EVENT_HIBERNATE. + * + * We do not want to perform disk spin down for PM_EVENT_FREEZE. + * (Spin down will be performed by the subsequent PM_EVENT_HIBERNATE.) + */ + if (!(ap->pm_mesg.event & PM_EVENT_FREEZE)) { + /* Set all devices attached to the port in standby mode */ + ata_for_each_link(link, ap, HOST_FIRST) { + ata_for_each_dev(dev, link, ENABLED) + ata_dev_power_set_standby(dev); + } } /* diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 65fde5717928..0e71b8763c4c 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -902,7 +902,15 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc) } else { /* * ATA PASS-THROUGH INFORMATION AVAILABLE - * Always in descriptor format sense. + * + * Note: we are supposed to call ata_scsi_set_sense(), which + * respects the D_SENSE bit, instead of unconditionally + * generating the sense data in descriptor format. However, + * because hdparm, hddtemp, and udisks incorrectly assume sense + * data in descriptor format, without even looking at the + * RESPONSE CODE field in the returned sense data (to see which + * format the returned sense data is in), we are stuck with + * being bug compatible with older kernels. */ scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D); } diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c index 9ccaac9e2bc3..f19ede2965a1 100644 --- a/drivers/ata/pata_macio.c +++ b/drivers/ata/pata_macio.c @@ -540,7 +540,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) while (sg_len) { /* table overflow should never happen */ - BUG_ON (pi++ >= MAX_DCMDS); + if (WARN_ON_ONCE(pi >= MAX_DCMDS)) + return AC_ERR_SYSTEM; len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG; table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE); @@ -552,11 +553,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc) addr += len; sg_len -= len; ++table; + ++pi; } } /* Should never happen according to Tejun */ - BUG_ON(!pi); + if (WARN_ON_ONCE(!pi)) + return AC_ERR_SYSTEM; /* Convert the last command to an input/output */ table--; diff --git a/drivers/ata/pata_serverworks.c b/drivers/ata/pata_serverworks.c index c0bc4af0d196..804c74ce3c1d 100644 --- a/drivers/ata/pata_serverworks.c +++ b/drivers/ata/pata_serverworks.c @@ -46,10 +46,11 @@ #define SVWKS_CSB5_REVISION_NEW 0x92 /* min PCI_REVISION_ID for UDMA5 (A2.0) */ #define SVWKS_CSB6_REVISION 0xa0 /* min PCI_REVISION_ID for UDMA4 (A1.0) */ -/* Seagate Barracuda ATA IV Family drives in UDMA mode 5 - * can overrun their FIFOs when used with the CSB5 */ - -static const char *csb_bad_ata100[] = { +/* + * Seagate Barracuda ATA IV Family drives in UDMA mode 5 + * can overrun their FIFOs when used with the CSB5. + */ +static const char * const csb_bad_ata100[] = { "ST320011A", "ST340016A", "ST360021A", @@ -163,10 +164,11 @@ static unsigned int serverworks_osb4_filter(struct ata_device *adev, unsigned in * @adev: ATA device * @mask: Mask of proposed modes * - * Check the blacklist and disable UDMA5 if matched + * Check the list of devices with broken UDMA5 and + * disable UDMA5 if matched. */ - -static unsigned int serverworks_csb_filter(struct ata_device *adev, unsigned int mask) +static unsigned int serverworks_csb_filter(struct ata_device *adev, + unsigned int mask) { const char *p; char model_num[ATA_ID_PROD_LEN + 1]; diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index 3b989a52879d..f412b8d71252 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -128,7 +128,7 @@ static const struct pci_device_id sil_pci_tbl[] = { static const struct sil_drivelist { const char *product; unsigned int quirk; -} sil_blacklist [] = { +} sil_quirks[] = { { "ST320012AS", SIL_QUIRK_MOD15WRITE }, { "ST330013AS", SIL_QUIRK_MOD15WRITE }, { "ST340017AS", SIL_QUIRK_MOD15WRITE }, @@ -600,8 +600,8 @@ static void sil_thaw(struct ata_port *ap) * list, and apply the fixups to only the specific * devices/hosts/firmwares that need it. * - * 20040111 - Seagate drives affected by the Mod15Write bug are blacklisted - * The Maxtor quirk is in the blacklist, but I'm keeping the original + * 20040111 - Seagate drives affected by the Mod15Write bug are quirked + * The Maxtor quirk is in sil_quirks, but I'm keeping the original * pessimistic fix for the following reasons... * - There seems to be less info on it, only one device gleaned off the * Windows driver, maybe only one is affected. More info would be greatly @@ -620,9 +620,9 @@ static void sil_dev_config(struct ata_device *dev) ata_id_c_string(dev->id, model_num, ATA_ID_PROD, sizeof(model_num)); - for (n = 0; sil_blacklist[n].product; n++) - if (!strcmp(sil_blacklist[n].product, model_num)) { - quirks = sil_blacklist[n].quirk; + for (n = 0; sil_quirks[n].product; n++) + if (!strcmp(sil_quirks[n].product, model_num)) { + quirks = sil_quirks[n].quirk; break; } diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c index 2daf50d4cd47..7810f974b2ca 100644 --- a/drivers/atm/idt77252.c +++ b/drivers/atm/idt77252.c @@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) rpp->len += skb->len; if (stat & SAR_RSQE_EPDU) { + unsigned int len, truesize; unsigned char *l1l2; - unsigned int len; l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6); @@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe) ATM_SKB(skb)->vcc = vcc; __net_timestamp(skb); + truesize = skb->truesize; vcc->push(vcc, skb); atomic_inc(&vcc->stats->rx); - if (skb->truesize > SAR_FB_SIZE_3) + if (truesize > SAR_FB_SIZE_3) add_rx_skb(card, 3, SAR_FB_SIZE_3, 1); - else if (skb->truesize > SAR_FB_SIZE_2) + else if (truesize > SAR_FB_SIZE_2) add_rx_skb(card, 2, SAR_FB_SIZE_2, 1); - else if (skb->truesize > SAR_FB_SIZE_1) + else if (truesize > SAR_FB_SIZE_1) add_rx_skb(card, 1, SAR_FB_SIZE_1, 1); else add_rx_skb(card, 0, SAR_FB_SIZE_0, 1); diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c index 02425991c159..57b4efff344e 100644 --- a/drivers/auxdisplay/ht16k33.c +++ b/drivers/auxdisplay/ht16k33.c @@ -507,6 +507,7 @@ static int ht16k33_led_probe(struct device *dev, struct led_classdev *led, led->max_brightness = MAX_BRIGHTNESS; err = devm_led_classdev_register_ext(dev, led, &init_data); + fwnode_handle_put(init_data.fwnode); if (err) dev_err(dev, "Failed to register LED\n"); diff --git a/drivers/base/bus.c b/drivers/base/bus.c index 7ca47e5b3c1f..339a9edcde5f 100644 --- a/drivers/base/bus.c +++ b/drivers/base/bus.c @@ -104,7 +104,8 @@ static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for reading a bus attribute without show() */ + ssize_t ret = -EIO; if (bus_attr->show) ret = bus_attr->show(subsys_priv->bus, buf); @@ -116,7 +117,8 @@ static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); - ssize_t ret = 0; + /* return -EIO for writing a bus attribute without store() */ + ssize_t ret = -EIO; if (bus_attr->store) ret = bus_attr->store(subsys_priv->bus, buf, count); diff --git a/drivers/base/core.c b/drivers/base/core.c index 30204e62497c..1de19cecaa62 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -2558,6 +2559,7 @@ static const char *dev_uevent_name(struct kobject *kobj) static int dev_uevent(struct kobject *kobj, struct kobj_uevent_env *env) { struct device *dev = kobj_to_dev(kobj); + struct device_driver *driver; int retval = 0; /* add device node properties if present */ @@ -2586,8 +2588,12 @@ static int dev_uevent(struct kobject *kobj, struct kobj_uevent_env *env) if (dev->type && dev->type->name) add_uevent_var(env, "DEVTYPE=%s", dev->type->name); - if (dev->driver) - add_uevent_var(env, "DRIVER=%s", dev->driver->name); + /* Synchronize with module_remove_driver() */ + rcu_read_lock(); + driver = READ_ONCE(dev->driver); + if (driver) + add_uevent_var(env, "DRIVER=%s", driver->name); + rcu_read_unlock(); /* Add common DT information about the device */ of_device_uevent(dev, env); @@ -2657,11 +2663,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr, if (!env) return -ENOMEM; - /* Synchronize with really_probe() */ - device_lock(dev); /* let the kset specific function add its keys */ retval = kset->uevent_ops->uevent(&dev->kobj, env); - device_unlock(dev); if (retval) goto out; diff --git a/drivers/base/devres.c b/drivers/base/devres.c index 4ab2b50ee38f..35d1e2864696 100644 --- a/drivers/base/devres.c +++ b/drivers/base/devres.c @@ -564,6 +564,7 @@ void * devres_open_group(struct device *dev, void *id, gfp_t gfp) grp->id = grp; if (id) grp->id = id; + grp->color = 0; spin_lock_irqsave(&dev->devres_lock, flags); add_dr(dev, &grp->node[0]); @@ -892,9 +893,12 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp) /* * Otherwise: allocate new, larger chunk. We need to allocate before * taking the lock as most probably the caller uses GFP_KERNEL. + * alloc_dr() will call check_dr_size() to reserve extra memory + * for struct devres automatically, so size @new_size user request + * is delivered to it directly as devm_kmalloc() does. */ new_dr = alloc_dr(devm_kmalloc_release, - total_new_size, gfp, dev_to_node(dev)); + new_size, gfp, dev_to_node(dev)); if (!new_dr) return NULL; @@ -1218,7 +1222,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu); */ void devm_free_percpu(struct device *dev, void __percpu *pdata) { - WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match, + /* + * Use devres_release() to prevent memory leakage as + * devm_free_pages() does. + */ + WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match, (__force void *)pdata)); } EXPORT_SYMBOL_GPL(devm_free_percpu); diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c index 7c3590fd97c2..cfface4f4c1e 100644 --- a/drivers/base/firmware_loader/main.c +++ b/drivers/base/firmware_loader/main.c @@ -791,6 +791,26 @@ static void fw_abort_batch_reqs(struct firmware *fw) mutex_unlock(&fw_lock); } +/* + * Reject firmware file names with ".." path components. + * There are drivers that construct firmware file names from device-supplied + * strings, and we don't want some device to be able to tell us "I would like to + * be sent my firmware from ../../../etc/shadow, please". + * + * Search for ".." surrounded by either '/' or start/end of string. + * + * This intentionally only looks at the firmware name, not at the firmware base + * directory or at symlink contents. + */ +static bool name_contains_dotdot(const char *name) +{ + size_t name_len = strlen(name); + + return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 || + strstr(name, "/../") != NULL || + (name_len >= 3 && strcmp(name+name_len-3, "/..") == 0); +} + /* called from request_firmware() and request_firmware_work_func() */ static int _request_firmware(const struct firmware **firmware_p, const char *name, @@ -811,6 +831,14 @@ _request_firmware(const struct firmware **firmware_p, const char *name, goto out; } + if (name_contains_dotdot(name)) { + dev_warn(device, + "Firmware load for '%s' refused, path contains '..' component\n", + name); + ret = -EINVAL; + goto out; + } + ret = _request_firmware_prepare(&fw, name, device, buf, size, offset, opt_flags); if (ret <= 0) /* error or already assigned */ @@ -886,6 +914,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name, * @name will be used as $FIRMWARE in the uevent environment and * should be distinctive enough not to be confused with any other * firmware image for this or any other device. + * It must not contain any ".." path components - "foo/bar..bin" is + * allowed, but "foo/../bar.bin" is not. * * Caller must hold the reference count of @device. * diff --git a/drivers/base/module.c b/drivers/base/module.c index 46ad4d636731..851cc5367c04 100644 --- a/drivers/base/module.c +++ b/drivers/base/module.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "base.h" static char *make_driver_name(struct device_driver *drv) @@ -77,6 +78,9 @@ void module_remove_driver(struct device_driver *drv) if (!drv) return; + /* Synchronize with dev_uevent() */ + synchronize_rcu(); + sysfs_remove_link(&drv->p->kobj, "module"); if (drv->owner) diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index d238b47f74c3..e01bb359034b 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -3119,7 +3119,7 @@ static int genpd_summary_one(struct seq_file *s, else snprintf(state, sizeof(state), "%s", status_lookup[genpd->status]); - seq_printf(s, "%-30s %-50s %u", genpd->name, state, genpd->performance_state); + seq_printf(s, "%-30s %-49s %u", genpd->name, state, genpd->performance_state); /* * Modifications on the list require holding locks on both diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c index 37ab23a9d034..7f14c5ed1e22 100644 --- a/drivers/base/regmap/regmap-spi.c +++ b/drivers/base/regmap/regmap-spi.c @@ -122,8 +122,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi, return ERR_PTR(-ENOMEM); max_msg_size = spi_max_message_size(spi); - reg_reserve_size = config->reg_bits / BITS_PER_BYTE - + config->pad_bits / BITS_PER_BYTE; + reg_reserve_size = (config->reg_bits + config->pad_bits) / BITS_PER_BYTE; if (max_size + reg_reserve_size > max_msg_size) max_size -= reg_reserve_size; diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c index cc9077b588d7..d1f4ddc57645 100644 --- a/drivers/block/aoe/aoecmd.c +++ b/drivers/block/aoe/aoecmd.c @@ -361,6 +361,7 @@ ata_rw_frameinit(struct frame *f) } ah->cmdstat = ATA_CMD_PIO_READ | writebit | extbit; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; } @@ -401,6 +402,8 @@ aoecmd_ata_rw(struct aoedev *d) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } return 1; } @@ -483,10 +486,13 @@ resend(struct aoedev *d, struct frame *f) memcpy(h->dst, t->addr, sizeof h->dst); memcpy(h->src, t->ifp->nd->dev_addr, sizeof h->src); + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; skb = skb_clone(skb, GFP_ATOMIC); - if (skb == NULL) + if (skb == NULL) { + dev_put(t->ifp->nd); return; + } f->sent = ktime_get(); __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); @@ -617,6 +623,8 @@ probe(struct aoetgt *t) __skb_queue_head_init(&queue); __skb_queue_tail(&queue, skb); aoenet_xmit(&queue); + } else { + dev_put(f->t->ifp->nd); } } @@ -1395,6 +1403,7 @@ aoecmd_ata_id(struct aoedev *d) ah->cmdstat = ATA_CMD_ID_ATA; ah->lba3 = 0xa0; + dev_hold(t->ifp->nd); skb->dev = t->ifp->nd; d->rttavg = RTTAVG_INIT; @@ -1404,6 +1413,8 @@ aoecmd_ata_id(struct aoedev *d) skb = skb_clone(skb, GFP_ATOMIC); if (skb) f->sent = ktime_get(); + else + dev_put(t->ifp->nd); return skb; } diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 590d1b50ab5d..b84d079d80b2 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -3380,10 +3380,12 @@ void drbd_uuid_new_current(struct drbd_device *device) __must_hold(local) void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local) { unsigned long flags; - if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) - return; - spin_lock_irqsave(&device->ldev->md.uuid_lock, flags); + if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) { + spin_unlock_irqrestore(&device->ldev->md.uuid_lock, flags); + return; + } + if (val == 0) { drbd_uuid_move_history(device); device->ldev->md.uuid[UI_HISTORY_START] = device->ldev->md.uuid[UI_BITMAP]; diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c index 3f7bf9f2d874..0ba4955d3d7f 100644 --- a/drivers/block/drbd/drbd_state.c +++ b/drivers/block/drbd/drbd_state.c @@ -876,7 +876,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns) ns.disk == D_OUTDATED) rv = SS_CONNECTED_OUTDATES; - else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && + else if (nc && (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && (nc->verify_alg[0] == 0)) rv = SS_NO_VERIFY_ALG; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 12ff6f58b8a9..041d307a2f28 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -211,13 +211,10 @@ static void __loop_update_dio(struct loop_device *lo, bool dio) if (lo->lo_state == Lo_bound) blk_mq_freeze_queue(lo->lo_queue); lo->use_dio = use_dio; - if (use_dio) { - blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue); + if (use_dio) lo->lo_flags |= LO_FLAGS_DIRECT_IO; - } else { - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); + else lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; - } if (lo->lo_state == Lo_bound) blk_mq_unfreeze_queue(lo->lo_queue); } @@ -2034,14 +2031,6 @@ static int loop_add(int i) blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS); - /* - * By default, we do buffer IO, so it doesn't make sense to enable - * merge because the I/O submitted to backing file is handled page by - * page. For directio mode, merge does help to dispatch bigger request - * to underlayer disk. We will enable merge once directio is enabled. - */ - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue); - /* * Disable partition scanning by default. The in-kernel partition * scanning can be requested individually per-device during its diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 5c4be8dda253..1f3cd5de4117 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -181,6 +181,17 @@ static void nbd_requeue_cmd(struct nbd_cmd *cmd) { struct request *req = blk_mq_rq_from_pdu(cmd); + lockdep_assert_held(&cmd->lock); + + /* + * Clear INFLIGHT flag so that this cmd won't be completed in + * normal completion path + * + * INFLIGHT flag will be set when the cmd is queued to nbd next + * time. + */ + __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags); + if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags)) blk_mq_requeue_request(req, true); } @@ -445,8 +456,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req) nbd_mark_nsock_dead(nbd, nsock, 1); mutex_unlock(&nsock->tx_lock); } - mutex_unlock(&cmd->lock); nbd_requeue_cmd(cmd); + mutex_unlock(&cmd->lock); nbd_config_put(nbd); return BLK_EH_DONE; } diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c index 220cedda2ca7..4d78b5583dc6 100644 --- a/drivers/block/null_blk/main.c +++ b/drivers/block/null_blk/main.c @@ -1958,8 +1958,8 @@ static int null_validate_conf(struct nullb_device *dev) return -EINVAL; } - dev->blocksize = round_down(dev->blocksize, 512); - dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096); + if (blk_validate_block_size(dev->blocksize)) + return -EINVAL; if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) { if (dev->submit_queues != nr_online_nodes) diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c index f58ca9ce3503..4f8efc829a59 100644 --- a/drivers/block/rbd.c +++ b/drivers/block/rbd.c @@ -362,7 +362,7 @@ enum rbd_watch_state { enum rbd_lock_state { RBD_LOCK_STATE_UNLOCKED, RBD_LOCK_STATE_LOCKED, - RBD_LOCK_STATE_RELEASING, + RBD_LOCK_STATE_QUIESCING, }; /* WatchNotify::ClientId */ @@ -422,7 +422,7 @@ struct rbd_device { struct list_head running_list; struct completion acquire_wait; int acquire_err; - struct completion releasing_wait; + struct completion quiescing_wait; spinlock_t object_map_lock; u8 *object_map; @@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev) lockdep_assert_held(&rbd_dev->lock_rwsem); return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED || - rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING; + rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING; } static bool rbd_is_lock_owner(struct rbd_device *rbd_dev) @@ -3458,13 +3458,14 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req) lockdep_assert_held(&rbd_dev->lock_rwsem); spin_lock(&rbd_dev->lock_lists_lock); if (!list_empty(&img_req->lock_item)) { + rbd_assert(!list_empty(&rbd_dev->running_list)); list_del_init(&img_req->lock_item); - need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING && + need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING && list_empty(&rbd_dev->running_list)); } spin_unlock(&rbd_dev->lock_lists_lock); if (need_wakeup) - complete(&rbd_dev->releasing_wait); + complete(&rbd_dev->quiescing_wait); } static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) @@ -3477,11 +3478,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req) if (rbd_lock_add_request(img_req)) return 1; - if (rbd_dev->opts->exclusive) { - WARN_ON(1); /* lock got released? */ - return -EROFS; - } - /* * Note the use of mod_delayed_work() in rbd_acquire_lock() * and cancel_delayed_work() in wake_lock_waiters(). @@ -4182,16 +4178,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev) /* * Ensure that all in-flight IO is flushed. */ - rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING; - rbd_assert(!completion_done(&rbd_dev->releasing_wait)); + rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING; + rbd_assert(!completion_done(&rbd_dev->quiescing_wait)); if (list_empty(&rbd_dev->running_list)) return true; up_write(&rbd_dev->lock_rwsem); - wait_for_completion(&rbd_dev->releasing_wait); + wait_for_completion(&rbd_dev->quiescing_wait); down_write(&rbd_dev->lock_rwsem); - if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING) + if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING) return false; rbd_assert(list_empty(&rbd_dev->running_list)); @@ -4602,6 +4598,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev) rbd_warn(rbd_dev, "failed to update lock cookie: %d", ret); + if (rbd_dev->opts->exclusive) + rbd_warn(rbd_dev, + "temporarily releasing lock on exclusive mapping"); + /* * Lock cookie cannot be updated on older OSDs, so do * a manual release and queue an acquire. @@ -5383,7 +5383,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec) INIT_LIST_HEAD(&rbd_dev->acquiring_list); INIT_LIST_HEAD(&rbd_dev->running_list); init_completion(&rbd_dev->acquire_wait); - init_completion(&rbd_dev->releasing_wait); + init_completion(&rbd_dev->quiescing_wait); spin_lock_init(&rbd_dev->object_map_lock); @@ -6589,11 +6589,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev) if (ret) return ret; - /* - * The lock may have been released by now, unless automatic lock - * transitions are disabled. - */ - rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev)); return 0; } diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index 3fa74051f31b..bfd643856f64 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -1915,6 +1915,8 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub, mutex_lock(&ub->mutex); if (!ublk_can_use_recovery(ub)) goto out_unlock; + if (!ub->nr_queues_ready) + goto out_unlock; /* * START_RECOVERY is only allowd after: * diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c index ba057ebfda5c..981b43f79e4a 100644 --- a/drivers/bluetooth/btmrvl_sdio.c +++ b/drivers/bluetooth/btmrvl_sdio.c @@ -92,7 +92,7 @@ static int btmrvl_sdio_probe_of(struct device *dev, } else { ret = devm_request_irq(dev, cfg->irq_bt, btmrvl_wake_irq_bt, - 0, "bt_wake", card); + IRQF_NO_AUTOEN, "bt_wake", card); if (ret) { dev_err(dev, "Failed to request irq_bt %d (%d)\n", @@ -101,7 +101,6 @@ static int btmrvl_sdio_probe_of(struct device *dev, /* Configure wakeup (enabled by default) */ device_init_wakeup(dev, true); - disable_irq(cfg->irq_bt); } } diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 6a772b955d69..0b915f2c7607 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -531,6 +531,8 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3592), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe122), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek 8852BE Bluetooth devices */ { USB_DEVICE(0x0cb8, 0xc559), .driver_info = BTUSB_REALTEK | @@ -545,6 +547,10 @@ static const struct usb_device_id blacklist_table[] = { BTUSB_WIDEBAND_SPEECH }, { USB_DEVICE(0x13d3, 0x3571), .driver_info = BTUSB_REALTEK | BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x13d3, 0x3591), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, + { USB_DEVICE(0x0489, 0xe125), .driver_info = BTUSB_REALTEK | + BTUSB_WIDEBAND_SPEECH }, /* Realtek Bluetooth devices */ { USB_VENDOR_AND_INTERFACE_INFO(0x0bda, 0xe0, 0x01, 0x01), @@ -1185,7 +1191,15 @@ static int btusb_submit_intr_urb(struct hci_dev *hdev, gfp_t mem_flags) if (!urb) return -ENOMEM; - size = le16_to_cpu(data->intr_ep->wMaxPacketSize); + if (le16_to_cpu(data->udev->descriptor.idVendor) == 0x0a12 && + le16_to_cpu(data->udev->descriptor.idProduct) == 0x0001) + /* Fake CSR devices don't seem to support sort-transter */ + size = le16_to_cpu(data->intr_ep->wMaxPacketSize); + else + /* Use maximum HCI Event size so the USB stack handles + * ZPL/short-transfer automatically. + */ + size = HCI_MAX_EVENT_SIZE; buf = kmalloc(size, mem_flags); if (!buf) { diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c index f0a5c755ca95..60d22bbde8fa 100644 --- a/drivers/bluetooth/hci_ldisc.c +++ b/drivers/bluetooth/hci_ldisc.c @@ -775,7 +775,8 @@ static int hci_uart_tty_ioctl(struct tty_struct *tty, unsigned int cmd, break; case HCIUARTGETPROTO: - if (test_bit(HCI_UART_PROTO_SET, &hu->flags)) + if (test_bit(HCI_UART_PROTO_SET, &hu->flags) && + test_bit(HCI_UART_PROTO_READY, &hu->flags)) err = hu->proto->id; else err = -EUNATCH; diff --git a/drivers/bus/arm-integrator-lm.c b/drivers/bus/arm-integrator-lm.c index 2344d560b144..ab5fad8aaa99 100644 --- a/drivers/bus/arm-integrator-lm.c +++ b/drivers/bus/arm-integrator-lm.c @@ -85,6 +85,7 @@ static int integrator_ap_lm_probe(struct platform_device *pdev) return -ENODEV; } map = syscon_node_to_regmap(syscon); + of_node_put(syscon); if (IS_ERR(map)) { dev_err(dev, "could not find Integrator/AP system controller\n"); diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c index caa4ce28cf9e..e01754af576b 100644 --- a/drivers/bus/mhi/host/pci_generic.c +++ b/drivers/bus/mhi/host/pci_generic.c @@ -538,6 +538,15 @@ static const struct mhi_pci_dev_info mhi_telit_fn990_info = { .mru_default = 32768, }; +static const struct mhi_pci_dev_info mhi_telit_fe990a_info = { + .name = "telit-fe990a", + .config = &modem_telit_fn990_config, + .bar_num = MHI_PCI_DEFAULT_BAR_NUM, + .dma_data_width = 32, + .sideband_wake = false, + .mru_default = 32768, +}; + /* Keep the list sorted based on the PID. New VID should be added as the last entry */ static const struct pci_device_id mhi_pci_id_table[] = { { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0304), @@ -553,6 +562,9 @@ static const struct pci_device_id mhi_pci_id_table[] = { /* Telit FN990 */ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2010), .driver_data = (kernel_ulong_t) &mhi_telit_fn990_info }, + /* Telit FE990A */ + { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2015), + .driver_data = (kernel_ulong_t) &mhi_telit_fe990a_info }, { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0308), .driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info }, { PCI_DEVICE(0x1eac, 0x1001), /* EM120R-GL (sdx24) */ diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c index ee71376f174b..3bc1d9243dbd 100644 --- a/drivers/char/hpet.c +++ b/drivers/char/hpet.c @@ -289,8 +289,13 @@ hpet_read(struct file *file, char __user *buf, size_t count, loff_t * ppos) if (!devp->hd_ireqfreq) return -EIO; - if (count < sizeof(unsigned long)) - return -EINVAL; + if (in_compat_syscall()) { + if (count < sizeof(compat_ulong_t)) + return -EINVAL; + } else { + if (count < sizeof(unsigned long)) + return -EINVAL; + } add_wait_queue(&devp->hd_waitqueue, &wait); @@ -314,9 +319,16 @@ hpet_read(struct file *file, char __user *buf, size_t count, loff_t * ppos) schedule(); } - retval = put_user(data, (unsigned long __user *)buf); - if (!retval) - retval = sizeof(unsigned long); + if (in_compat_syscall()) { + retval = put_user(data, (compat_ulong_t __user *)buf); + if (!retval) + retval = sizeof(compat_ulong_t); + } else { + retval = put_user(data, (unsigned long __user *)buf); + if (!retval) + retval = sizeof(unsigned long); + } + out: __set_current_state(TASK_RUNNING); remove_wait_queue(&devp->hd_waitqueue, &wait); @@ -671,12 +683,24 @@ struct compat_hpet_info { unsigned short hi_timer; }; +/* 32-bit types would lead to different command codes which should be + * translated into 64-bit ones before passed to hpet_ioctl_common + */ +#define COMPAT_HPET_INFO _IOR('h', 0x03, struct compat_hpet_info) +#define COMPAT_HPET_IRQFREQ _IOW('h', 0x6, compat_ulong_t) + static long hpet_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct hpet_info info; int err; + if (cmd == COMPAT_HPET_INFO) + cmd = HPET_INFO; + + if (cmd == COMPAT_HPET_IRQFREQ) + cmd = HPET_IRQFREQ; + mutex_lock(&hpet_mutex); err = hpet_ioctl_common(file->private_data, cmd, arg, &info); mutex_unlock(&hpet_mutex); diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c index 0555e3838bce..5229da114377 100644 --- a/drivers/char/hw_random/amd-rng.c +++ b/drivers/char/hw_random/amd-rng.c @@ -142,8 +142,10 @@ static int __init amd_rng_mod_init(void) found: err = pci_read_config_dword(pdev, 0x58, &pmbase); - if (err) + if (err) { + err = pcibios_err_to_errno(err); goto put_dev; + } pmbase &= 0x0000FF00; if (pmbase == 0) { diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c index 634eab4776f3..373bb0ad528a 100644 --- a/drivers/char/hw_random/bcm2835-rng.c +++ b/drivers/char/hw_random/bcm2835-rng.c @@ -95,8 +95,10 @@ static int bcm2835_rng_init(struct hwrng *rng) return ret; ret = reset_control_reset(priv->reset); - if (ret) + if (ret) { + clk_disable_unprepare(priv->clk); return ret; + } if (priv->mask_interrupts) { /* mask the interrupt */ diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c index 302ffa354c2f..2ab38a92778d 100644 --- a/drivers/char/hw_random/cctrng.c +++ b/drivers/char/hw_random/cctrng.c @@ -665,6 +665,7 @@ static int __maybe_unused cctrng_resume(struct device *dev) /* wait for Cryptocell reset completion */ if (!cctrng_wait_for_reset_completion(drvdata)) { dev_err(dev, "Cryptocell reset not completed"); + clk_disable_unprepare(drvdata->clk); return -EBUSY; } diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c index 6c00ea008555..3e00506543b6 100644 --- a/drivers/char/hw_random/mtk-rng.c +++ b/drivers/char/hw_random/mtk-rng.c @@ -142,7 +142,7 @@ static int mtk_rng_probe(struct platform_device *pdev) dev_set_drvdata(&pdev->dev, priv); pm_runtime_set_autosuspend_delay(&pdev->dev, RNG_AUTOSUSPEND_TIMEOUT); pm_runtime_use_autosuspend(&pdev->dev); - pm_runtime_enable(&pdev->dev); + devm_pm_runtime_enable(&pdev->dev); dev_info(&pdev->dev, "registered RNG driver\n"); diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c index 8512ec76d526..4a6186f9f889 100644 --- a/drivers/char/tpm/eventlog/common.c +++ b/drivers/char/tpm/eventlog/common.c @@ -47,6 +47,8 @@ static int tpm_bios_measurements_open(struct inode *inode, if (!err) { seq = file->private_data; seq->private = chip; + } else { + put_device(&chip->dev); } return err; diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c index 30b4c288c1bb..c3fbbf4d3db7 100644 --- a/drivers/char/tpm/tpm-dev-common.c +++ b/drivers/char/tpm/tpm-dev-common.c @@ -47,6 +47,8 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space, if (!ret) ret = tpm2_commit_space(chip, space, buf, &len); + else + tpm2_flush_space(chip); out_rc: return ret ? ret : len; diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c index ffb35f0154c1..c57404c6b98c 100644 --- a/drivers/char/tpm/tpm2-space.c +++ b/drivers/char/tpm/tpm2-space.c @@ -166,6 +166,9 @@ void tpm2_flush_space(struct tpm_chip *chip) struct tpm_space *space = &chip->work_space; int i; + if (!space) + return; + for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++) if (space->context_tbl[i] && ~space->context_tbl[i]) tpm2_flush_context(chip, space->context_tbl[i]); diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c index 9fa3c76a267f..899036ce3802 100644 --- a/drivers/char/virtio_console.c +++ b/drivers/char/virtio_console.c @@ -2055,25 +2055,27 @@ static int virtcons_probe(struct virtio_device *vdev) multiport = true; } - err = init_vqs(portdev); - if (err < 0) { - dev_err(&vdev->dev, "Error %d initializing vqs\n", err); - goto free_chrdev; - } - spin_lock_init(&portdev->ports_lock); INIT_LIST_HEAD(&portdev->ports); INIT_LIST_HEAD(&portdev->list); - virtio_device_ready(portdev->vdev); - INIT_WORK(&portdev->config_work, &config_work_handler); INIT_WORK(&portdev->control_work, &control_work_handler); if (multiport) { spin_lock_init(&portdev->c_ivq_lock); spin_lock_init(&portdev->c_ovq_lock); + } + err = init_vqs(portdev); + if (err < 0) { + dev_err(&vdev->dev, "Error %d initializing vqs\n", err); + goto free_chrdev; + } + + virtio_device_ready(portdev->vdev); + + if (multiport) { err = fill_queue(portdev->c_ivq, &portdev->c_ivq_lock); if (err < 0) { dev_err(&vdev->dev, diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c index 39bcbfd908b4..3a2a0fb3d928 100644 --- a/drivers/char/xillybus/xillyusb.c +++ b/drivers/char/xillybus/xillyusb.c @@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2"); static const char xillyname[] = "xillyusb"; static unsigned int fifo_buf_order; +static struct workqueue_struct *wakeup_wq; #define USB_VENDOR_ID_XILINX 0x03fd #define USB_VENDOR_ID_ALTERA 0x09fb @@ -561,10 +562,6 @@ static void cleanup_dev(struct kref *kref) * errors if executed. The mechanism relies on that xdev->error is assigned * a non-zero value by report_io_error() prior to queueing wakeup_all(), * which prevents bulk_in_work() from calling process_bulk_in(). - * - * The fact that wakeup_all() and bulk_in_work() are queued on the same - * workqueue makes their concurrent execution very unlikely, however the - * kernel's API doesn't seem to ensure this strictly. */ static void wakeup_all(struct work_struct *work) @@ -619,7 +616,7 @@ static void report_io_error(struct xillyusb_dev *xdev, if (do_once) { kref_get(&xdev->kref); /* xdev is used by work item */ - queue_work(xdev->workq, &xdev->wakeup_workitem); + queue_work(wakeup_wq, &xdev->wakeup_workitem); } } @@ -1892,6 +1889,13 @@ static const struct file_operations xillyusb_fops = { static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev) { + struct usb_device *udev = xdev->udev; + + /* Verify that device has the two fundamental bulk in/out endpoints */ + if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) || + usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM))) + return -ENODEV; + xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT, bulk_out_work, 1, 2); if (!xdev->msg_ep) @@ -1921,14 +1925,15 @@ static int setup_channels(struct xillyusb_dev *xdev, __le16 *chandesc, int num_channels) { - struct xillyusb_channel *chan; + struct usb_device *udev = xdev->udev; + struct xillyusb_channel *chan, *new_channels; int i; chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL); if (!chan) return -ENOMEM; - xdev->channels = chan; + new_channels = chan; for (i = 0; i < num_channels; i++, chan++) { unsigned int in_desc = le16_to_cpu(*chandesc++); @@ -1957,6 +1962,15 @@ static int setup_channels(struct xillyusb_dev *xdev, */ if ((out_desc & 0x80) && i < 14) { /* Entry is valid */ + if (usb_pipe_type_check(udev, + usb_sndbulkpipe(udev, i + 2))) { + dev_err(xdev->dev, + "Missing BULK OUT endpoint %d\n", + i + 2); + kfree(new_channels); + return -ENODEV; + } + chan->writable = 1; chan->out_synchronous = !!(out_desc & 0x40); chan->out_seekable = !!(out_desc & 0x20); @@ -1966,6 +1980,7 @@ static int setup_channels(struct xillyusb_dev *xdev, } } + xdev->channels = new_channels; return 0; } @@ -2082,9 +2097,11 @@ static int xillyusb_discovery(struct usb_interface *interface) * just after responding with the IDT, there is no reason for any * work item to be running now. To be sure that xdev->channels * is updated on anything that might run in parallel, flush the - * workqueue, which rarely does anything. + * device's workqueue and the wakeup work item. This rarely + * does anything. */ flush_workqueue(xdev->workq); + flush_work(&xdev->wakeup_workitem); xdev->num_channels = num_channels; @@ -2242,6 +2259,10 @@ static int __init xillyusb_init(void) { int rc = 0; + wakeup_wq = alloc_workqueue(xillyname, 0, 0); + if (!wakeup_wq) + return -ENOMEM; + if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT) fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT; else @@ -2249,12 +2270,17 @@ static int __init xillyusb_init(void) rc = usb_register(&xillyusb_driver); + if (rc) + destroy_workqueue(wakeup_wq); + return rc; } static void __exit xillyusb_exit(void) { usb_deregister(&xillyusb_driver); + + destroy_workqueue(wakeup_wq); } module_init(xillyusb_init); diff --git a/drivers/clk/bcm/clk-bcm53573-ilp.c b/drivers/clk/bcm/clk-bcm53573-ilp.c index 84f2af736ee8..83ef41d618be 100644 --- a/drivers/clk/bcm/clk-bcm53573-ilp.c +++ b/drivers/clk/bcm/clk-bcm53573-ilp.c @@ -112,7 +112,7 @@ static void bcm53573_ilp_init(struct device_node *np) goto err_free_ilp; } - ilp->regmap = syscon_node_to_regmap(of_get_parent(np)); + ilp->regmap = syscon_node_to_regmap(np->parent); if (IS_ERR(ilp->regmap)) { err = PTR_ERR(ilp->regmap); goto err_free_ilp; diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c index 29f0126cbd05..d22fae24a3da 100644 --- a/drivers/clk/clk-en7523.c +++ b/drivers/clk/clk-en7523.c @@ -41,6 +41,7 @@ struct en_clk_desc { u8 div_shift; u16 div_val0; u8 div_step; + u8 div_offset; }; struct en_clk_gate { @@ -68,6 +69,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_EMI, .name = "emi", @@ -81,6 +83,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_BUS, .name = "bus", @@ -94,6 +97,7 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_SLIC, .name = "slic", @@ -134,13 +138,14 @@ static const struct en_clk_desc en7523_base_clks[] = { .div_bits = 3, .div_shift = 0, .div_step = 1, + .div_offset = 1, }, { .id = EN7523_CLK_CRYPTO, .name = "crypto", .base_reg = REG_CRYPTO_CLKSRC, .base_bits = 1, - .base_shift = 8, + .base_shift = 0, .base_values = emi_base, .n_base_values = ARRAY_SIZE(emi_base), } @@ -185,7 +190,7 @@ static u32 en7523_get_div(void __iomem *base, int i) if (!val && desc->div_val0) return desc->div_val0; - return (val + 1) * desc->div_step; + return (val + desc->div_offset) * desc->div_step; } static int en7523_pci_is_enabled(struct clk_hw *hw) diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c index 4103d605e804..6faa4372ed65 100644 --- a/drivers/clk/davinci/da8xx-cfgchip.c +++ b/drivers/clk/davinci/da8xx-cfgchip.c @@ -505,7 +505,7 @@ da8xx_cfgchip_register_usb0_clk48(struct device *dev, const char * const parent_names[] = { "usb_refclkin", "pll0_auxclk" }; struct clk *fck_clk; struct da8xx_usb0_clk48 *usb0; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; fck_clk = devm_clk_get(dev, "fck"); @@ -579,7 +579,7 @@ da8xx_cfgchip_register_usb1_clk48(struct device *dev, { const char * const parent_names[] = { "usb0_clk48", "usb_refclkin" }; struct da8xx_usb1_clk48 *usb1; - struct clk_init_data init; + struct clk_init_data init = {}; int ret; usb1 = devm_kzalloc(dev, sizeof(*usb1), GFP_KERNEL); diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c index 4eedd45dbaa8..5429b76f4f72 100644 --- a/drivers/clk/imx/clk-composite-7ulp.c +++ b/drivers/clk/imx/clk-composite-7ulp.c @@ -14,6 +14,7 @@ #include "../clk-fractional-divider.h" #include "clk.h" +#define PCG_PR_MASK BIT(31) #define PCG_PCS_SHIFT 24 #define PCG_PCS_MASK 0x7 #define PCG_CGC_SHIFT 30 @@ -80,6 +81,12 @@ static struct clk_hw *imx_ulp_clk_hw_composite(const char *name, struct clk_hw *hw; u32 val; + val = readl(reg); + if (!(val & PCG_PR_MASK)) { + pr_info("PCC PR is 0 for clk:%s, bypass\n", name); + return 0; + } + if (mux_present) { mux = kzalloc(sizeof(*mux), GFP_KERNEL); if (!mux) diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c index 3e9a092e136c..4f5536163d65 100644 --- a/drivers/clk/imx/clk-composite-8m.c +++ b/drivers/clk/imx/clk-composite-8m.c @@ -173,6 +173,34 @@ static const struct clk_ops imx8m_clk_composite_mux_ops = { .determine_rate = imx8m_clk_composite_mux_determine_rate, }; +static int imx8m_clk_composite_gate_enable(struct clk_hw *hw) +{ + struct clk_gate *gate = to_clk_gate(hw); + unsigned long flags; + u32 val; + + spin_lock_irqsave(gate->lock, flags); + + val = readl(gate->reg); + val |= BIT(gate->bit_idx); + writel(val, gate->reg); + + spin_unlock_irqrestore(gate->lock, flags); + + return 0; +} + +static void imx8m_clk_composite_gate_disable(struct clk_hw *hw) +{ + /* composite clk requires the disable hook */ +} + +static const struct clk_ops imx8m_clk_composite_gate_ops = { + .enable = imx8m_clk_composite_gate_enable, + .disable = imx8m_clk_composite_gate_disable, + .is_enabled = clk_gate_is_enabled, +}; + struct clk_hw *__imx8m_clk_hw_composite(const char *name, const char * const *parent_names, int num_parents, void __iomem *reg, @@ -186,10 +214,11 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, struct clk_mux *mux = NULL; const struct clk_ops *divider_ops; const struct clk_ops *mux_ops; + const struct clk_ops *gate_ops; mux = kzalloc(sizeof(*mux), GFP_KERNEL); if (!mux) - goto fail; + return ERR_CAST(hw); mux_hw = &mux->hw; mux->reg = reg; @@ -199,7 +228,7 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, div = kzalloc(sizeof(*div), GFP_KERNEL); if (!div) - goto fail; + goto free_mux; div_hw = &div->hw; div->reg = reg; @@ -226,28 +255,32 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name, div->flags = CLK_DIVIDER_ROUND_CLOSEST; /* skip registering the gate ops if M4 is enabled */ - if (!mcore_booted) { - gate = kzalloc(sizeof(*gate), GFP_KERNEL); - if (!gate) - goto fail; + gate = kzalloc(sizeof(*gate), GFP_KERNEL); + if (!gate) + goto free_div; - gate_hw = &gate->hw; - gate->reg = reg; - gate->bit_idx = PCG_CGC_SHIFT; - gate->lock = &imx_ccm_lock; - } + gate_hw = &gate->hw; + gate->reg = reg; + gate->bit_idx = PCG_CGC_SHIFT; + gate->lock = &imx_ccm_lock; + if (!mcore_booted) + gate_ops = &clk_gate_ops; + else + gate_ops = &imx8m_clk_composite_gate_ops; hw = clk_hw_register_composite(NULL, name, parent_names, num_parents, mux_hw, mux_ops, div_hw, - divider_ops, gate_hw, &clk_gate_ops, flags); + divider_ops, gate_hw, gate_ops, flags); if (IS_ERR(hw)) - goto fail; + goto free_gate; return hw; -fail: +free_gate: kfree(gate); +free_div: kfree(div); +free_mux: kfree(mux); return ERR_CAST(hw); } diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c index f6674110a88e..421a78e295ee 100644 --- a/drivers/clk/imx/clk-fracn-gppll.c +++ b/drivers/clk/imx/clk-fracn-gppll.c @@ -53,11 +53,22 @@ .odiv = (_odiv), \ } +#define PLL_FRACN_GP_INTEGER(_rate, _mfi, _rdiv, _odiv) \ + { \ + .rate = (_rate), \ + .mfi = (_mfi), \ + .mfn = 0, \ + .mfd = 0, \ + .rdiv = (_rdiv), \ + .odiv = (_odiv), \ + } + struct clk_fracn_gppll { struct clk_hw hw; void __iomem *base; const struct imx_fracn_gppll_rate_table *rate_table; int rate_count; + u32 flags; }; /* @@ -83,6 +94,24 @@ struct imx_fracn_gppll_clk imx_fracn_gppll = { }; EXPORT_SYMBOL_GPL(imx_fracn_gppll); +/* + * Fvco = (Fref / rdiv) * MFI + * Fout = Fvco / odiv + * The (Fref / rdiv) should be in range 20MHz to 40MHz + * The Fvco should be in range 2.5Ghz to 5Ghz + */ +static const struct imx_fracn_gppll_rate_table int_tbl[] = { + PLL_FRACN_GP_INTEGER(1700000000U, 141, 1, 2), + PLL_FRACN_GP_INTEGER(1400000000U, 175, 1, 3), + PLL_FRACN_GP_INTEGER(900000000U, 150, 1, 4), +}; + +struct imx_fracn_gppll_clk imx_fracn_gppll_integer = { + .rate_table = int_tbl, + .rate_count = ARRAY_SIZE(int_tbl), +}; +EXPORT_SYMBOL_GPL(imx_fracn_gppll_integer); + static inline struct clk_fracn_gppll *to_clk_fracn_gppll(struct clk_hw *hw) { return container_of(hw, struct clk_fracn_gppll, hw); @@ -169,9 +198,15 @@ static unsigned long clk_fracn_gppll_recalc_rate(struct clk_hw *hw, unsigned lon break; } - /* Fvco = Fref * (MFI + MFN / MFD) */ - fvco = fvco * mfi * mfd + fvco * mfn; - do_div(fvco, mfd * rdiv * odiv); + if (pll->flags & CLK_FRACN_GPPLL_INTEGER) { + /* Fvco = (Fref / rdiv) * MFI */ + fvco = fvco * mfi; + do_div(fvco, rdiv * odiv); + } else { + /* Fvco = (Fref / rdiv) * (MFI + MFN / MFD) */ + fvco = fvco * mfi * mfd + fvco * mfn; + do_div(fvco, mfd * rdiv * odiv); + } return (unsigned long)fvco; } @@ -215,8 +250,10 @@ static int clk_fracn_gppll_set_rate(struct clk_hw *hw, unsigned long drate, pll_div = FIELD_PREP(PLL_RDIV_MASK, rate->rdiv) | rate->odiv | FIELD_PREP(PLL_MFI_MASK, rate->mfi); writel_relaxed(pll_div, pll->base + PLL_DIV); - writel_relaxed(rate->mfd, pll->base + PLL_DENOMINATOR); - writel_relaxed(FIELD_PREP(PLL_MFN_MASK, rate->mfn), pll->base + PLL_NUMERATOR); + if (pll->flags & CLK_FRACN_GPPLL_FRACN) { + writel_relaxed(rate->mfd, pll->base + PLL_DENOMINATOR); + writel_relaxed(FIELD_PREP(PLL_MFN_MASK, rate->mfn), pll->base + PLL_NUMERATOR); + } /* Wait for 5us according to fracn mode pll doc */ udelay(5); @@ -252,6 +289,10 @@ static int clk_fracn_gppll_prepare(struct clk_hw *hw) if (val & POWERUP_MASK) return 0; + if (pll->flags & CLK_FRACN_GPPLL_FRACN) + writel_relaxed(readl_relaxed(pll->base + PLL_NUMERATOR), + pll->base + PLL_NUMERATOR); + val |= CLKMUX_BYPASS; writel_relaxed(val, pll->base + PLL_CTRL); @@ -300,8 +341,10 @@ static const struct clk_ops clk_fracn_gppll_ops = { .set_rate = clk_fracn_gppll_set_rate, }; -struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, - const struct imx_fracn_gppll_clk *pll_clk) +static struct clk_hw *_imx_clk_fracn_gppll(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk, + u32 pll_flags) { struct clk_fracn_gppll *pll; struct clk_hw *hw; @@ -322,6 +365,7 @@ struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, vo pll->hw.init = &init; pll->rate_table = pll_clk->rate_table; pll->rate_count = pll_clk->rate_count; + pll->flags = pll_flags; hw = &pll->hw; @@ -334,4 +378,18 @@ struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, vo return hw; } + +struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk) +{ + return _imx_clk_fracn_gppll(name, parent_name, base, pll_clk, CLK_FRACN_GPPLL_FRACN); +} EXPORT_SYMBOL_GPL(imx_clk_fracn_gppll); + +struct clk_hw *imx_clk_fracn_gppll_integer(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk) +{ + return _imx_clk_fracn_gppll(name, parent_name, base, pll_clk, CLK_FRACN_GPPLL_INTEGER); +} +EXPORT_SYMBOL_GPL(imx_clk_fracn_gppll_integer); diff --git a/drivers/clk/imx/clk-imx7d.c b/drivers/clk/imx/clk-imx7d.c index cbf8131c63f7..f26b85e8f329 100644 --- a/drivers/clk/imx/clk-imx7d.c +++ b/drivers/clk/imx/clk-imx7d.c @@ -498,9 +498,9 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node) hws[IMX7D_ENET_AXI_ROOT_SRC] = imx_clk_hw_mux2_flags("enet_axi_src", base + 0x8900, 24, 3, enet_axi_sel, ARRAY_SIZE(enet_axi_sel), CLK_SET_PARENT_GATE); hws[IMX7D_NAND_USDHC_BUS_ROOT_SRC] = imx_clk_hw_mux2_flags("nand_usdhc_src", base + 0x8980, 24, 3, nand_usdhc_bus_sel, ARRAY_SIZE(nand_usdhc_bus_sel), CLK_SET_PARENT_GATE); hws[IMX7D_DRAM_PHYM_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_phym_src", base + 0x9800, 24, 1, dram_phym_sel, ARRAY_SIZE(dram_phym_sel), CLK_SET_PARENT_GATE); - hws[IMX7D_DRAM_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel), CLK_SET_PARENT_GATE); + hws[IMX7D_DRAM_ROOT_SRC] = imx_clk_hw_mux2("dram_src", base + 0x9880, 24, 1, dram_sel, ARRAY_SIZE(dram_sel)); hws[IMX7D_DRAM_PHYM_ALT_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_phym_alt_src", base + 0xa000, 24, 3, dram_phym_alt_sel, ARRAY_SIZE(dram_phym_alt_sel), CLK_SET_PARENT_GATE); - hws[IMX7D_DRAM_ALT_ROOT_SRC] = imx_clk_hw_mux2_flags("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel), CLK_SET_PARENT_GATE); + hws[IMX7D_DRAM_ALT_ROOT_SRC] = imx_clk_hw_mux2("dram_alt_src", base + 0xa080, 24, 3, dram_alt_sel, ARRAY_SIZE(dram_alt_sel)); hws[IMX7D_USB_HSIC_ROOT_SRC] = imx_clk_hw_mux2_flags("usb_hsic_src", base + 0xa100, 24, 3, usb_hsic_sel, ARRAY_SIZE(usb_hsic_sel), CLK_SET_PARENT_GATE); hws[IMX7D_PCIE_CTRL_ROOT_SRC] = imx_clk_hw_mux2_flags("pcie_ctrl_src", base + 0xa180, 24, 3, pcie_ctrl_sel, ARRAY_SIZE(pcie_ctrl_sel), CLK_SET_PARENT_GATE); hws[IMX7D_PCIE_PHY_ROOT_SRC] = imx_clk_hw_mux2_flags("pcie_phy_src", base + 0xa200, 24, 3, pcie_phy_sel, ARRAY_SIZE(pcie_phy_sel), CLK_SET_PARENT_GATE); diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c index 3d0d8f2c02dc..2de49bbc40f3 100644 --- a/drivers/clk/imx/clk-imx8mp.c +++ b/drivers/clk/imx/clk-imx8mp.c @@ -550,8 +550,8 @@ static int imx8mp_clocks_probe(struct platform_device *pdev) hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1); - hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000); - hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080); + hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_fw_managed_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000); + hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_fw_managed_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080); hws[IMX8MP_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mp_vpu_g1_sels, ccm_base + 0xa100); hws[IMX8MP_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mp_vpu_g2_sels, ccm_base + 0xa180); hws[IMX8MP_CLK_CAN1] = imx8m_clk_hw_composite("can1", imx8mp_can1_sels, ccm_base + 0xa200); diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c index 1066ea16de62..28265e28856c 100644 --- a/drivers/clk/imx/clk-imx8qxp.c +++ b/drivers/clk/imx/clk-imx8qxp.c @@ -166,8 +166,8 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("pwm_clk", IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER); imx_clk_scu("elcdif_pll", IMX_SC_R_ELCDIF_PLL, IMX_SC_PM_CLK_PLL); imx_clk_scu2("lcd_clk", lcd_sels, ARRAY_SIZE(lcd_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER); - imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0); imx_clk_scu("lcd_pxl_bypass_div_clk", IMX_SC_R_LCD_0, IMX_SC_PM_CLK_BYPASS); + imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0); /* Audio SS */ imx_clk_scu("audio_pll0_clk", IMX_SC_R_AUDIO_PLL_0, IMX_SC_PM_CLK_PLL); @@ -200,18 +200,18 @@ static int imx8qxp_clk_probe(struct platform_device *pdev) imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC); /* Display controller SS */ - imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); - imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc0_pll0_clk", IMX_SC_R_DC_0_PLL_0, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc0_pll1_clk", IMX_SC_R_DC_0_PLL_1, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc0_bypass0_clk", IMX_SC_R_DC_0_VIDEO0, IMX_SC_PM_CLK_BYPASS); + imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0); + imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc0_bypass1_clk", IMX_SC_R_DC_0_VIDEO1, IMX_SC_PM_CLK_BYPASS); - imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0); - imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc1_pll0_clk", IMX_SC_R_DC_1_PLL_0, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc1_pll1_clk", IMX_SC_R_DC_1_PLL_1, IMX_SC_PM_CLK_PLL); imx_clk_scu("dc1_bypass0_clk", IMX_SC_R_DC_1_VIDEO0, IMX_SC_PM_CLK_BYPASS); + imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0); + imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1); imx_clk_scu("dc1_bypass1_clk", IMX_SC_R_DC_1_VIDEO1, IMX_SC_PM_CLK_BYPASS); /* MIPI-LVDS SS */ diff --git a/drivers/clk/imx/clk.h b/drivers/clk/imx/clk.h index fb59131395f0..ef090fa3327a 100644 --- a/drivers/clk/imx/clk.h +++ b/drivers/clk/imx/clk.h @@ -74,6 +74,9 @@ extern struct imx_pll14xx_clk imx_1416x_pll; extern struct imx_pll14xx_clk imx_1443x_pll; extern struct imx_pll14xx_clk imx_1443x_dram_pll; +#define CLK_FRACN_GPPLL_INTEGER BIT(0) +#define CLK_FRACN_GPPLL_FRACN BIT(1) + /* NOTE: Rate table should be kept sorted in descending order. */ struct imx_fracn_gppll_rate_table { unsigned int rate; @@ -92,8 +95,12 @@ struct imx_fracn_gppll_clk { struct clk_hw *imx_clk_fracn_gppll(const char *name, const char *parent_name, void __iomem *base, const struct imx_fracn_gppll_clk *pll_clk); +struct clk_hw *imx_clk_fracn_gppll_integer(const char *name, const char *parent_name, + void __iomem *base, + const struct imx_fracn_gppll_clk *pll_clk); extern struct imx_fracn_gppll_clk imx_fracn_gppll; +extern struct imx_fracn_gppll_clk imx_fracn_gppll_integer; #define imx_clk_cpu(name, parent_name, div, mux, pll, step) \ to_clk(imx_clk_hw_cpu(name, parent_name, div, mux, pll, step)) diff --git a/drivers/clk/qcom/camcc-sc7280.c b/drivers/clk/qcom/camcc-sc7280.c index ec163ea769f5..932096a972bc 100644 --- a/drivers/clk/qcom/camcc-sc7280.c +++ b/drivers/clk/qcom/camcc-sc7280.c @@ -2260,6 +2260,7 @@ static struct gdsc cam_cc_bps_gdsc = { .name = "cam_cc_bps_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = HW_CTRL | RETAIN_FF_ENABLE, }; @@ -2269,6 +2270,7 @@ static struct gdsc cam_cc_ife_0_gdsc = { .name = "cam_cc_ife_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2278,6 +2280,7 @@ static struct gdsc cam_cc_ife_1_gdsc = { .name = "cam_cc_ife_1_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2287,6 +2290,7 @@ static struct gdsc cam_cc_ife_2_gdsc = { .name = "cam_cc_ife_2_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = RETAIN_FF_ENABLE, }; @@ -2296,6 +2300,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = { .name = "cam_cc_ipe_0_gdsc", }, .pwrsts = PWRSTS_OFF_ON, + .parent = &cam_cc_titan_top_gdsc.pd, .flags = HW_CTRL | RETAIN_FF_ENABLE, }; diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c index 1973d79c9465..8780fd107472 100644 --- a/drivers/clk/qcom/clk-alpha-pll.c +++ b/drivers/clk/qcom/clk-alpha-pll.c @@ -40,7 +40,7 @@ #define PLL_USER_CTL(p) ((p)->offset + (p)->regs[PLL_OFF_USER_CTL]) # define PLL_POST_DIV_SHIFT 8 -# define PLL_POST_DIV_MASK(p) GENMASK((p)->width, 0) +# define PLL_POST_DIV_MASK(p) GENMASK((p)->width - 1, 0) # define PLL_ALPHA_EN BIT(24) # define PLL_ALPHA_MODE BIT(25) # define PLL_VCO_SHIFT 20 @@ -1421,8 +1421,8 @@ clk_trion_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate, } return regmap_update_bits(regmap, PLL_USER_CTL(pll), - PLL_POST_DIV_MASK(pll) << PLL_POST_DIV_SHIFT, - val << PLL_POST_DIV_SHIFT); + PLL_POST_DIV_MASK(pll) << pll->post_div_shift, + val << pll->post_div_shift); } const struct clk_ops clk_alpha_pll_postdiv_trion_ops = { @@ -1581,7 +1581,7 @@ static int __alpha_pll_trion_set_rate(struct clk_hw *hw, unsigned long rate, if (ret < 0) return ret; - regmap_write(pll->clkr.regmap, PLL_L_VAL(pll), l); + regmap_update_bits(pll->clkr.regmap, PLL_L_VAL(pll), LUCID_EVO_PLL_L_VAL_MASK, l); regmap_write(pll->clkr.regmap, PLL_ALPHA_VAL(pll), a); /* Latch the PLL input */ @@ -1700,6 +1700,58 @@ const struct clk_ops clk_alpha_pll_agera_ops = { }; EXPORT_SYMBOL_GPL(clk_alpha_pll_agera_ops); +/** + * clk_lucid_5lpe_pll_configure - configure the lucid 5lpe pll + * + * @pll: clk alpha pll + * @regmap: register map + * @config: configuration to apply for pll + */ +void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config) +{ + /* + * If the bootloader left the PLL enabled it's likely that there are + * RCGs that will lock up if we disable the PLL below. + */ + if (trion_pll_is_enabled(pll, regmap)) { + pr_debug("Lucid 5LPE PLL is already enabled, skipping configuration\n"); + return; + } + + clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l); + regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL); + clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll), + config->config_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll), + config->config_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U1(pll), + config->config_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll), + config->user_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll), + config->user_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U1(pll), + config->user_ctl_hi1_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll), + config->test_ctl_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll), + config->test_ctl_hi_val); + clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U1(pll), + config->test_ctl_hi1_val); + + /* Disable PLL output */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0); + + /* Set operation mode to OFF */ + regmap_write(regmap, PLL_OPMODE(pll), PLL_STANDBY); + + /* Place the PLL in STANDBY mode */ + regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N); +} +EXPORT_SYMBOL_GPL(clk_lucid_5lpe_pll_configure); + static int alpha_pll_lucid_5lpe_enable(struct clk_hw *hw) { struct clk_alpha_pll *pll = to_clk_alpha_pll(hw); diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h index f9524b3fce6b..e0c5f2f855ad 100644 --- a/drivers/clk/qcom/clk-alpha-pll.h +++ b/drivers/clk/qcom/clk-alpha-pll.h @@ -178,6 +178,8 @@ void clk_agera_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, void clk_zonda_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); +void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, + const struct alpha_pll_config *config); void clk_lucid_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, const struct alpha_pll_config *config); void clk_rivian_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap, diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h index 17a58119165e..55b3a2c3afed 100644 --- a/drivers/clk/qcom/clk-branch.h +++ b/drivers/clk/qcom/clk-branch.h @@ -37,6 +37,32 @@ struct clk_branch { struct clk_regmap clkr; }; +/* Branch clock common bits for HLOS-owned clocks */ +#define CBCR_FORCE_MEM_CORE_ON BIT(14) +#define CBCR_FORCE_MEM_PERIPH_ON BIT(13) +#define CBCR_FORCE_MEM_PERIPH_OFF BIT(12) + +static inline void qcom_branch_set_force_mem_core(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_CORE_ON, + on ? CBCR_FORCE_MEM_CORE_ON : 0); +} + +static inline void qcom_branch_set_force_periph_on(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_PERIPH_ON, + on ? CBCR_FORCE_MEM_PERIPH_ON : 0); +} + +static inline void qcom_branch_set_force_periph_off(struct regmap *regmap, + struct clk_branch clk, bool on) +{ + regmap_update_bits(regmap, clk.halt_reg, CBCR_FORCE_MEM_PERIPH_OFF, + on ? CBCR_FORCE_MEM_PERIPH_OFF : 0); +} + extern const struct clk_ops clk_branch_ops; extern const struct clk_ops clk_branch2_ops; extern const struct clk_ops clk_branch_simple_ops; diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c index dc797bd137ca..e46bb60dcda4 100644 --- a/drivers/clk/qcom/clk-rcg2.c +++ b/drivers/clk/qcom/clk-rcg2.c @@ -1136,7 +1136,39 @@ clk_rcg2_shared_recalc_rate(struct clk_hw *hw, unsigned long parent_rate) return clk_rcg2_recalc_rate(hw, parent_rate); } +static int clk_rcg2_shared_init(struct clk_hw *hw) +{ + /* + * This does a few things: + * + * 1. Sets rcg->parked_cfg to reflect the value at probe so that the + * proper parent is reported from clk_rcg2_shared_get_parent(). + * + * 2. Clears the force enable bit of the RCG because we rely on child + * clks (branches) to turn the RCG on/off with a hardware feedback + * mechanism and only set the force enable bit in the RCG when we + * want to make sure the clk stays on for parent switches or + * parking. + * + * 3. Parks shared RCGs on the safe source at registration because we + * can't be certain that the parent clk will stay on during boot, + * especially if the parent is shared. If this RCG is enabled at + * boot, and the parent is turned off, the RCG will get stuck on. A + * GDSC can wedge if is turned on and the RCG is stuck on because + * the GDSC's controller will hang waiting for the clk status to + * toggle on when it never does. + * + * The safest option here is to "park" the RCG at init so that the clk + * can never get stuck on or off. This ensures the GDSC can't get + * wedged. + */ + clk_rcg2_shared_disable(hw); + + return 0; +} + const struct clk_ops clk_rcg2_shared_ops = { + .init = clk_rcg2_shared_init, .enable = clk_rcg2_shared_enable, .disable = clk_rcg2_shared_disable, .get_parent = clk_rcg2_shared_get_parent, diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c index 0471bab82464..60819a39702d 100644 --- a/drivers/clk/qcom/clk-rpmh.c +++ b/drivers/clk/qcom/clk-rpmh.c @@ -266,6 +266,8 @@ static int clk_rpmh_bcm_send_cmd(struct clk_rpmh *c, bool enable) cmd_state = 0; } + cmd_state = min(cmd_state, BCM_TCS_CMD_VOTE_MASK); + if (c->last_sent_aggr_state != cmd_state) { cmd.addr = c->res_addr; cmd.data = BCM_TCS_CMD(1, enable, 0, cmd_state); diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c index 709076f0f9d7..dcd76977a73b 100644 --- a/drivers/clk/qcom/dispcc-sm8250.c +++ b/drivers/clk/qcom/dispcc-sm8250.c @@ -837,6 +837,7 @@ static struct clk_branch disp_cc_mdss_dp_link1_intf_clk = { &disp_cc_mdss_dp_link1_div_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -872,6 +873,7 @@ static struct clk_branch disp_cc_mdss_dp_link_intf_clk = { &disp_cc_mdss_dp_link_div_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -997,6 +999,7 @@ static struct clk_branch disp_cc_mdss_mdp_lut_clk = { &disp_cc_mdss_mdp_clk_src.clkr.hw, }, .num_parents = 1, + .flags = CLK_SET_RATE_PARENT, .ops = &clk_branch2_ops, }, }, @@ -1332,8 +1335,13 @@ static int disp_cc_sm8250_probe(struct platform_device *pdev) disp_cc_pll1.vco_table = lucid_5lpe_vco; } - clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); - clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + if (of_device_is_compatible(pdev->dev.of_node, "qcom,sm8350-dispcc")) { + clk_lucid_5lpe_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); + clk_lucid_5lpe_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + } else { + clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config); + clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config); + } /* Enable clock gating for MDP clocks */ regmap_update_bits(regmap, 0x8000, 0x10, 0x10); diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c index 46d41ebce2b0..2067e39840cb 100644 --- a/drivers/clk/qcom/gcc-sc7280.c +++ b/drivers/clk/qcom/gcc-sc7280.c @@ -3469,6 +3469,9 @@ static int gcc_sc7280_probe(struct platform_device *pdev) regmap_update_bits(regmap, 0x71004, BIT(0), BIT(0)); regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13)); + /* FORCE_MEM_CORE_ON for ufs phy ice core clocks */ + qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_ice_core_clk, true); + ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks, ARRAY_SIZE(gcc_dfs_clocks)); if (ret) diff --git a/drivers/clk/qcom/gcc-sc8180x.c b/drivers/clk/qcom/gcc-sc8180x.c index c41b9f010585..ba004281f294 100644 --- a/drivers/clk/qcom/gcc-sc8180x.c +++ b/drivers/clk/qcom/gcc-sc8180x.c @@ -143,6 +143,23 @@ static struct clk_alpha_pll gpll7 = { }, }; +static struct clk_alpha_pll gpll9 = { + .offset = 0x1c000, + .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_TRION], + .clkr = { + .enable_reg = 0x52000, + .enable_mask = BIT(9), + .hw.init = &(const struct clk_init_data) { + .name = "gpll9", + .parent_data = &(const struct clk_parent_data) { + .fw_name = "bi_tcxo", + }, + .num_parents = 1, + .ops = &clk_alpha_pll_fixed_trion_ops, + }, + }, +}; + static const struct parent_map gcc_parent_map_0[] = { { P_BI_TCXO, 0 }, { P_GPLL0_OUT_MAIN, 1 }, @@ -242,7 +259,7 @@ static const struct parent_map gcc_parent_map_7[] = { static const struct clk_parent_data gcc_parents_7[] = { { .fw_name = "bi_tcxo", }, { .hw = &gpll0.clkr.hw }, - { .name = "gppl9" }, + { .hw = &gpll9.clkr.hw }, { .hw = &gpll4.clkr.hw }, { .hw = &gpll0_out_even.clkr.hw }, }; @@ -261,28 +278,6 @@ static const struct clk_parent_data gcc_parents_8[] = { { .hw = &gpll0_out_even.clkr.hw }, }; -static const struct freq_tbl ftbl_gcc_cpuss_ahb_clk_src[] = { - F(19200000, P_BI_TCXO, 1, 0, 0), - F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), - F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), - { } -}; - -static struct clk_rcg2 gcc_cpuss_ahb_clk_src = { - .cmd_rcgr = 0x48014, - .mnd_width = 0, - .hid_width = 5, - .parent_map = gcc_parent_map_0, - .freq_tbl = ftbl_gcc_cpuss_ahb_clk_src, - .clkr.hw.init = &(struct clk_init_data){ - .name = "gcc_cpuss_ahb_clk_src", - .parent_data = gcc_parents_0, - .num_parents = ARRAY_SIZE(gcc_parents_0), - .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, - }, -}; - static const struct freq_tbl ftbl_gcc_emac_ptp_clk_src[] = { F(19200000, P_BI_TCXO, 1, 0, 0), F(50000000, P_GPLL0_OUT_EVEN, 6, 0, 0), @@ -917,7 +912,7 @@ static const struct freq_tbl ftbl_gcc_sdcc2_apps_clk_src[] = { F(25000000, P_GPLL0_OUT_MAIN, 12, 1, 2), F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), - F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0), + F(202000000, P_GPLL9_OUT_MAIN, 4, 0, 0), { } }; @@ -940,9 +935,8 @@ static const struct freq_tbl ftbl_gcc_sdcc4_apps_clk_src[] = { F(400000, P_BI_TCXO, 12, 1, 4), F(9600000, P_BI_TCXO, 2, 0, 0), F(19200000, P_BI_TCXO, 1, 0, 0), - F(37500000, P_GPLL0_OUT_MAIN, 16, 0, 0), F(50000000, P_GPLL0_OUT_MAIN, 12, 0, 0), - F(75000000, P_GPLL0_OUT_MAIN, 8, 0, 0), + F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0), { } }; @@ -1600,25 +1594,6 @@ static struct clk_branch gcc_cfg_noc_usb3_sec_axi_clk = { }, }; -/* For CPUSS functionality the AHB clock needs to be left enabled */ -static struct clk_branch gcc_cpuss_ahb_clk = { - .halt_reg = 0x48000, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x52004, - .enable_mask = BIT(21), - .hw.init = &(struct clk_init_data){ - .name = "gcc_cpuss_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ - &gcc_cpuss_ahb_clk_src.clkr.hw - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_cpuss_rbcpr_clk = { .halt_reg = 0x48008, .halt_check = BRANCH_HALT, @@ -3151,25 +3126,6 @@ static struct clk_branch gcc_sdcc4_apps_clk = { }, }; -/* For CPUSS functionality the SYS NOC clock needs to be left enabled */ -static struct clk_branch gcc_sys_noc_cpuss_ahb_clk = { - .halt_reg = 0x4819c, - .halt_check = BRANCH_HALT_VOTED, - .clkr = { - .enable_reg = 0x52004, - .enable_mask = BIT(0), - .hw.init = &(struct clk_init_data){ - .name = "gcc_sys_noc_cpuss_ahb_clk", - .parent_hws = (const struct clk_hw *[]){ - &gcc_cpuss_ahb_clk_src.clkr.hw - }, - .num_parents = 1, - .flags = CLK_IS_CRITICAL | CLK_SET_RATE_PARENT, - .ops = &clk_branch2_ops, - }, - }, -}; - static struct clk_branch gcc_tsif_ahb_clk = { .halt_reg = 0x36004, .halt_check = BRANCH_HALT, @@ -4259,8 +4215,6 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GCC_CFG_NOC_USB3_MP_AXI_CLK] = &gcc_cfg_noc_usb3_mp_axi_clk.clkr, [GCC_CFG_NOC_USB3_PRIM_AXI_CLK] = &gcc_cfg_noc_usb3_prim_axi_clk.clkr, [GCC_CFG_NOC_USB3_SEC_AXI_CLK] = &gcc_cfg_noc_usb3_sec_axi_clk.clkr, - [GCC_CPUSS_AHB_CLK] = &gcc_cpuss_ahb_clk.clkr, - [GCC_CPUSS_AHB_CLK_SRC] = &gcc_cpuss_ahb_clk_src.clkr, [GCC_CPUSS_RBCPR_CLK] = &gcc_cpuss_rbcpr_clk.clkr, [GCC_DDRSS_GPU_AXI_CLK] = &gcc_ddrss_gpu_axi_clk.clkr, [GCC_DISP_HF_AXI_CLK] = &gcc_disp_hf_axi_clk.clkr, @@ -4397,7 +4351,6 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GCC_SDCC4_AHB_CLK] = &gcc_sdcc4_ahb_clk.clkr, [GCC_SDCC4_APPS_CLK] = &gcc_sdcc4_apps_clk.clkr, [GCC_SDCC4_APPS_CLK_SRC] = &gcc_sdcc4_apps_clk_src.clkr, - [GCC_SYS_NOC_CPUSS_AHB_CLK] = &gcc_sys_noc_cpuss_ahb_clk.clkr, [GCC_TSIF_AHB_CLK] = &gcc_tsif_ahb_clk.clkr, [GCC_TSIF_INACTIVITY_TIMERS_CLK] = &gcc_tsif_inactivity_timers_clk.clkr, [GCC_TSIF_REF_CLK] = &gcc_tsif_ref_clk.clkr, @@ -4484,6 +4437,7 @@ static struct clk_regmap *gcc_sc8180x_clocks[] = { [GPLL1] = &gpll1.clkr, [GPLL4] = &gpll4.clkr, [GPLL7] = &gpll7.clkr, + [GPLL9] = &gpll9.clkr, }; static const struct qcom_reset_map gcc_sc8180x_resets[] = { diff --git a/drivers/clk/qcom/gcc-sm8250.c b/drivers/clk/qcom/gcc-sm8250.c index 30bd56146107..3f78ed8b770b 100644 --- a/drivers/clk/qcom/gcc-sm8250.c +++ b/drivers/clk/qcom/gcc-sm8250.c @@ -3228,7 +3228,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_1_gdsc = { @@ -3236,7 +3236,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_2_gdsc = { @@ -3244,7 +3244,7 @@ static struct gdsc pcie_2_gdsc = { .pd = { .name = "pcie_2_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc ufs_card_gdsc = { diff --git a/drivers/clk/qcom/gcc-sm8450.c b/drivers/clk/qcom/gcc-sm8450.c index 59c567e76d65..6997f9bf4a87 100644 --- a/drivers/clk/qcom/gcc-sm8450.c +++ b/drivers/clk/qcom/gcc-sm8450.c @@ -2934,7 +2934,7 @@ static struct gdsc pcie_0_gdsc = { .pd = { .name = "pcie_0_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc pcie_1_gdsc = { @@ -2942,7 +2942,7 @@ static struct gdsc pcie_1_gdsc = { .pd = { .name = "pcie_1_gdsc", }, - .pwrsts = PWRSTS_OFF_ON, + .pwrsts = PWRSTS_RET_ON, }; static struct gdsc ufs_phy_gdsc = { diff --git a/drivers/clk/qcom/gpucc-sm8350.c b/drivers/clk/qcom/gpucc-sm8350.c index 5367ce654ac9..cc9fcbc88465 100644 --- a/drivers/clk/qcom/gpucc-sm8350.c +++ b/drivers/clk/qcom/gpucc-sm8350.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved. * Copyright (c) 2022, Linaro Limited + * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved. */ #include @@ -147,7 +148,7 @@ static struct clk_rcg2 gpu_cc_gmu_clk_src = { .parent_data = gpu_cc_parent_data_0, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; @@ -169,7 +170,7 @@ static struct clk_rcg2 gpu_cc_hub_clk_src = { .parent_data = gpu_cc_parent_data_1, .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1), .flags = CLK_SET_RATE_PARENT, - .ops = &clk_rcg2_ops, + .ops = &clk_rcg2_shared_ops, }, }; diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c index 04e75861eb18..4a07f99dbd48 100644 --- a/drivers/clk/rockchip/clk-rk3228.c +++ b/drivers/clk/rockchip/clk-rk3228.c @@ -410,7 +410,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = { RK2928_CLKSEL_CON(29), 0, 3, DFLAGS), DIV(0, "sclk_vop_pre", "sclk_vop_src", 0, RK2928_CLKSEL_CON(27), 8, 8, DFLAGS), - MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, 0, + MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT, RK2928_CLKSEL_CON(27), 1, 1, MFLAGS), FACTOR(0, "xin12m", "xin24m", 0, 1, 2), diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c index 6151a157def0..c716d4177e59 100644 --- a/drivers/clk/rockchip/clk.c +++ b/drivers/clk/rockchip/clk.c @@ -488,12 +488,13 @@ void rockchip_clk_register_branches(struct rockchip_clk_provider *ctx, struct rockchip_clk_branch *list, unsigned int nr_clk) { - struct clk *clk = NULL; + struct clk *clk; unsigned int idx; unsigned long flags; for (idx = 0; idx < nr_clk; idx++, list++) { flags = list->flags; + clk = NULL; /* catch simple muxes */ switch (list->branch_type) { diff --git a/drivers/clk/samsung/clk-exynos7885.c b/drivers/clk/samsung/clk-exynos7885.c index 0d2a950ed184..0f71fa6e8878 100644 --- a/drivers/clk/samsung/clk-exynos7885.c +++ b/drivers/clk/samsung/clk-exynos7885.c @@ -17,6 +17,12 @@ #include "clk.h" #include "clk-exynos-arm64.h" +/* NOTE: Must be equal to the last clock ID increased by one */ +#define CLKS_NR_TOP (CLK_GOUT_FSYS_USB30DRD + 1) +#define CLKS_NR_CORE (CLK_GOUT_TREX_P_CORE_PCLK_P_CORE + 1) +#define CLKS_NR_PERI (CLK_GOUT_WDT1_PCLK + 1) +#define CLKS_NR_FSYS (CLK_MOUT_FSYS_USB30DRD_USER + 1) + /* ---- CMU_TOP ------------------------------------------------------------- */ /* Register Offset definitions for CMU_TOP (0x12060000) */ @@ -334,7 +340,7 @@ static const struct samsung_cmu_info top_cmu_info __initconst = { .nr_div_clks = ARRAY_SIZE(top_div_clks), .gate_clks = top_gate_clks, .nr_gate_clks = ARRAY_SIZE(top_gate_clks), - .nr_clk_ids = TOP_NR_CLK, + .nr_clk_ids = CLKS_NR_TOP, .clk_regs = top_clk_regs, .nr_clk_regs = ARRAY_SIZE(top_clk_regs), }; @@ -553,7 +559,7 @@ static const struct samsung_cmu_info peri_cmu_info __initconst = { .nr_mux_clks = ARRAY_SIZE(peri_mux_clks), .gate_clks = peri_gate_clks, .nr_gate_clks = ARRAY_SIZE(peri_gate_clks), - .nr_clk_ids = PERI_NR_CLK, + .nr_clk_ids = CLKS_NR_PERI, .clk_regs = peri_clk_regs, .nr_clk_regs = ARRAY_SIZE(peri_clk_regs), .clk_name = "dout_peri_bus", @@ -662,7 +668,7 @@ static const struct samsung_cmu_info core_cmu_info __initconst = { .nr_div_clks = ARRAY_SIZE(core_div_clks), .gate_clks = core_gate_clks, .nr_gate_clks = ARRAY_SIZE(core_gate_clks), - .nr_clk_ids = CORE_NR_CLK, + .nr_clk_ids = CLKS_NR_CORE, .clk_regs = core_clk_regs, .nr_clk_regs = ARRAY_SIZE(core_clk_regs), .clk_name = "dout_core_bus", @@ -744,7 +750,7 @@ static const struct samsung_cmu_info fsys_cmu_info __initconst = { .nr_mux_clks = ARRAY_SIZE(fsys_mux_clks), .gate_clks = fsys_gate_clks, .nr_gate_clks = ARRAY_SIZE(fsys_gate_clks), - .nr_clk_ids = FSYS_NR_CLK, + .nr_clk_ids = CLKS_NR_FSYS, .clk_regs = fsys_clk_regs, .nr_clk_regs = ARRAY_SIZE(fsys_clk_regs), .clk_name = "dout_fsys_bus", diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c index 1c576599f6db..32b8adfa8bbf 100644 --- a/drivers/clk/ti/clk-dra7-atl.c +++ b/drivers/clk/ti/clk-dra7-atl.c @@ -250,6 +250,7 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev) } clk = of_clk_get_from_provider(&clkspec); + of_node_put(clkspec.np); if (IS_ERR(clk)) { pr_err("%s: failed to get atl clock %d from provider\n", __func__, i); diff --git a/drivers/clk/visconti/pll.c b/drivers/clk/visconti/pll.c index 1f3234f22667..e9cd80e085dc 100644 --- a/drivers/clk/visconti/pll.c +++ b/drivers/clk/visconti/pll.c @@ -329,12 +329,12 @@ struct visconti_pll_provider * __init visconti_init_pll(struct device_node *np, if (!ctx) return ERR_PTR(-ENOMEM); - for (i = 0; i < nr_plls; ++i) - ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); - ctx->node = np; ctx->reg_base = base; ctx->clk_data.num = nr_plls; + for (i = 0; i < nr_plls; ++i) + ctx->clk_data.hws[i] = ERR_PTR(-ENOENT); + return ctx; } diff --git a/drivers/clocksource/arm_global_timer.c b/drivers/clocksource/arm_global_timer.c index e1c773bb5535..22a58d35a41f 100644 --- a/drivers/clocksource/arm_global_timer.c +++ b/drivers/clocksource/arm_global_timer.c @@ -290,18 +290,17 @@ static int gt_clk_rate_change_cb(struct notifier_block *nb, switch (event) { case PRE_RATE_CHANGE: { - int psv; + unsigned long psv; - psv = DIV_ROUND_CLOSEST(ndata->new_rate, - gt_target_rate); - - if (abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR) + psv = DIV_ROUND_CLOSEST(ndata->new_rate, gt_target_rate); + if (!psv || + abs(gt_target_rate - (ndata->new_rate / psv)) > MAX_F_ERR) return NOTIFY_BAD; psv--; /* prescaler within legal range? */ - if (psv < 0 || psv > GT_CONTROL_PRESCALER_MAX) + if (psv > GT_CONTROL_PRESCALER_MAX) return NOTIFY_BAD; /* diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c index 7b952aa52c0b..7a2b83157bf5 100644 --- a/drivers/clocksource/sh_cmt.c +++ b/drivers/clocksource/sh_cmt.c @@ -529,6 +529,7 @@ static void sh_cmt_set_next(struct sh_cmt_channel *ch, unsigned long delta) static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) { struct sh_cmt_channel *ch = dev_id; + unsigned long flags; /* clear flags */ sh_cmt_write_cmcsr(ch, sh_cmt_read_cmcsr(ch) & @@ -559,6 +560,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_SKIPEVENT; + raw_spin_lock_irqsave(&ch->lock, flags); + if (ch->flags & FLAG_REPROGRAM) { ch->flags &= ~FLAG_REPROGRAM; sh_cmt_clock_event_program_verify(ch, 1); @@ -571,6 +574,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id) ch->flags &= ~FLAG_IRQCONTEXT; + raw_spin_unlock_irqrestore(&ch->lock, flags); + return IRQ_HANDLED; } @@ -781,12 +786,18 @@ static int sh_cmt_clock_event_next(unsigned long delta, struct clock_event_device *ced) { struct sh_cmt_channel *ch = ced_to_sh_cmt(ced); + unsigned long flags; BUG_ON(!clockevent_state_oneshot(ced)); + + raw_spin_lock_irqsave(&ch->lock, flags); + if (likely(ch->flags & FLAG_IRQCONTEXT)) ch->next_match_value = delta - 1; else - sh_cmt_set_next(ch, delta - 1); + __sh_cmt_set_next(ch, delta - 1); + + raw_spin_unlock_irqrestore(&ch->lock, flags); return 0; } diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c index bd64a8a8427f..92c025b70eb6 100644 --- a/drivers/clocksource/timer-imx-tpm.c +++ b/drivers/clocksource/timer-imx-tpm.c @@ -83,20 +83,28 @@ static u64 notrace tpm_read_sched_clock(void) static int tpm_set_next_event(unsigned long delta, struct clock_event_device *evt) { - unsigned long next, now; + unsigned long next, prev, now; - next = tpm_read_counter(); - next += delta; + prev = tpm_read_counter(); + next = prev + delta; writel(next, timer_base + TPM_C0V); now = tpm_read_counter(); + /* + * Need to wait CNT increase at least 1 cycle to make sure + * the C0V has been updated into HW. + */ + if ((next & 0xffffffff) != readl(timer_base + TPM_C0V)) + while (now == tpm_read_counter()) + ; + /* * NOTE: We observed in a very small probability, the bus fabric * contention between GPU and A7 may results a few cycles delay * of writing CNT registers which may cause the min_delta event got * missed, so we need add a ETIME check here in case it happened. */ - return (int)(next - now) <= 0 ? -ETIME : 0; + return (now - prev) >= delta ? -ETIME : 0; } static int tpm_set_state_oneshot(struct clock_event_device *evt) diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c index c3f54d9912be..420202bf76e4 100644 --- a/drivers/clocksource/timer-of.c +++ b/drivers/clocksource/timer-of.c @@ -25,10 +25,7 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) struct clock_event_device *clkevt = &to->clkevt; - if (of_irq->percpu) - free_percpu_irq(of_irq->irq, clkevt); - else - free_irq(of_irq->irq, clkevt); + free_irq(of_irq->irq, clkevt); } /** @@ -42,9 +39,6 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq) * - Get interrupt number by name * - Get interrupt number by index * - * When the interrupt is per CPU, 'request_percpu_irq()' is called, - * otherwise 'request_irq()' is used. - * * Returns 0 on success, < 0 otherwise */ static __init int timer_of_irq_init(struct device_node *np, @@ -69,12 +63,9 @@ static __init int timer_of_irq_init(struct device_node *np, return -EINVAL; } - ret = of_irq->percpu ? - request_percpu_irq(of_irq->irq, of_irq->handler, - np->full_name, clkevt) : - request_irq(of_irq->irq, of_irq->handler, - of_irq->flags ? of_irq->flags : IRQF_TIMER, - np->full_name, clkevt); + ret = request_irq(of_irq->irq, of_irq->handler, + of_irq->flags ? of_irq->flags : IRQF_TIMER, + np->full_name, clkevt); if (ret) { pr_err("Failed to request irq %d for %pOF\n", of_irq->irq, np); return ret; diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h index a5478f3e8589..01a2c6b7db06 100644 --- a/drivers/clocksource/timer-of.h +++ b/drivers/clocksource/timer-of.h @@ -11,7 +11,6 @@ struct of_timer_irq { int irq; int index; - int percpu; const char *name; unsigned long flags; irq_handler_t handler; diff --git a/drivers/clocksource/timer-qcom.c b/drivers/clocksource/timer-qcom.c index b4afe3a67583..eac4c95c6127 100644 --- a/drivers/clocksource/timer-qcom.c +++ b/drivers/clocksource/timer-qcom.c @@ -233,6 +233,7 @@ static int __init msm_dt_timer_init(struct device_node *np) } if (of_property_read_u32(np, "clock-frequency", &freq)) { + iounmap(cpu0_base); pr_err("Unknown frequency\n"); return -EINVAL; } @@ -243,7 +244,11 @@ static int __init msm_dt_timer_init(struct device_node *np) freq /= 4; writel_relaxed(DGT_CLK_CTL_DIV_4, source_base + DGT_CLK_CTL); - return msm_timer_init(freq, 32, irq, !!percpu_offset); + ret = msm_timer_init(freq, 32, irq, !!percpu_offset); + if (ret) + iounmap(cpu0_base); + + return ret; } TIMER_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init); TIMER_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init); diff --git a/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c b/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c index d55521b5bdcb..892a66b2cea6 100644 --- a/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c +++ b/drivers/comedi/drivers/ni_routing/tools/convert_c_to_py.c @@ -140,6 +140,11 @@ int main(void) { FILE *fp = fopen("ni_values.py", "w"); + if (fp == NULL) { + fprintf(stderr, "Could not open file!"); + return -1; + } + /* write route register values */ fprintf(fp, "ni_route_values = {\n"); for (int i = 0; ni_all_route_values[i]; ++i) diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c index 8791a88c7741..0050242d382e 100644 --- a/drivers/cpufreq/cppc_cpufreq.c +++ b/drivers/cpufreq/cppc_cpufreq.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include @@ -27,12 +26,6 @@ #include -/* Minimum struct length needed for the DMI processor entry we want */ -#define DMI_ENTRY_PROCESSOR_MIN_LENGTH 48 - -/* Offset in the DMI processor structure for the max frequency */ -#define DMI_PROCESSOR_MAX_SPEED 0x14 - /* * This list contains information parsed from per CPU ACPI _CPC and _PSD * structures: e.g. the highest and lowest supported performance, capabilities, @@ -288,97 +281,9 @@ static inline void cppc_freq_invariance_exit(void) } #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */ -/* Callback function used to retrieve the max frequency from DMI */ -static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private) -{ - const u8 *dmi_data = (const u8 *)dm; - u16 *mhz = (u16 *)private; - - if (dm->type == DMI_ENTRY_PROCESSOR && - dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) { - u16 val = (u16)get_unaligned((const u16 *) - (dmi_data + DMI_PROCESSOR_MAX_SPEED)); - *mhz = val > *mhz ? val : *mhz; - } -} - -/* Look up the max frequency in DMI */ -static u64 cppc_get_dmi_max_khz(void) -{ - u16 mhz = 0; - - dmi_walk(cppc_find_dmi_mhz, &mhz); - - /* - * Real stupid fallback value, just in case there is no - * actual value set. - */ - mhz = mhz ? mhz : 1; - - return (1000 * mhz); -} - -/* - * If CPPC lowest_freq and nominal_freq registers are exposed then we can - * use them to convert perf to freq and vice versa. The conversion is - * extrapolated as an affine function passing by the 2 points: - * - (Low perf, Low freq) - * - (Nominal perf, Nominal perf) - */ -static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data, - unsigned int perf) -{ - struct cppc_perf_caps *caps = &cpu_data->perf_caps; - s64 retval, offset = 0; - static u64 max_khz; - u64 mul, div; - - if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_freq - caps->lowest_freq; - div = caps->nominal_perf - caps->lowest_perf; - offset = caps->nominal_freq - div64_u64(caps->nominal_perf * mul, div); - } else { - if (!max_khz) - max_khz = cppc_get_dmi_max_khz(); - mul = max_khz; - div = caps->highest_perf; - } - - retval = offset + div64_u64(perf * mul, div); - if (retval >= 0) - return retval; - return 0; -} - -static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data, - unsigned int freq) -{ - struct cppc_perf_caps *caps = &cpu_data->perf_caps; - s64 retval, offset = 0; - static u64 max_khz; - u64 mul, div; - - if (caps->lowest_freq && caps->nominal_freq) { - mul = caps->nominal_perf - caps->lowest_perf; - div = caps->nominal_freq - caps->lowest_freq; - offset = caps->nominal_perf - div64_u64(caps->nominal_freq * mul, div); - } else { - if (!max_khz) - max_khz = cppc_get_dmi_max_khz(); - mul = caps->highest_perf; - div = max_khz; - } - - retval = offset + div64_u64(freq * mul, div); - if (retval >= 0) - return retval; - return 0; -} - static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation) - { struct cppc_cpudata *cpu_data = policy->driver_data; unsigned int cpu = policy->cpu; @@ -386,7 +291,7 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy, u32 desired_perf; int ret = 0; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); /* Return if it is exactly the same perf */ if (desired_perf == cpu_data->perf_ctrls.desired_perf) return ret; @@ -414,7 +319,7 @@ static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy, u32 desired_perf; int ret; - desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq); + desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq); cpu_data->perf_ctrls.desired_perf = desired_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -527,7 +432,7 @@ static int cppc_get_cpu_power(struct device *cpu_dev, min_step = min_cap / CPPC_EM_CAP_STEP; max_step = max_cap / CPPC_EM_CAP_STEP; - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + perf_prev = cppc_khz_to_perf(perf_caps, *KHz); step = perf_prev / perf_step; if (step > max_step) @@ -547,8 +452,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, perf = step * perf_step; } - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; /* @@ -558,8 +463,8 @@ static int cppc_get_cpu_power(struct device *cpu_dev, */ while ((*KHz == prev_freq) || (step_check != step)) { perf++; - *KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf); - perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz); + *KHz = cppc_perf_to_khz(perf_caps, perf); + perf_check = cppc_khz_to_perf(perf_caps, *KHz); step_check = perf_check / perf_step; } @@ -588,7 +493,7 @@ static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz, perf_caps = &cpu_data->perf_caps; max_cap = arch_scale_cpu_capacity(cpu_dev->id); - perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz); + perf_prev = cppc_khz_to_perf(perf_caps, KHz); perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap; step = perf_prev / perf_step; @@ -676,10 +581,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu) goto free_mask; } - /* Convert the lowest and nominal freq from MHz to KHz */ - cpu_data->perf_caps.lowest_freq *= 1000; - cpu_data->perf_caps.nominal_freq *= 1000; - list_add(&cpu_data->node, &cpu_data_list); return cpu_data; @@ -721,20 +622,16 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) * Set min to lowest nonlinear perf to avoid any efficiency penalty (see * Section 8.4.7.1.1.5 of ACPI 6.1 spec) */ - policy->min = cppc_cpufreq_perf_to_khz(cpu_data, - caps->lowest_nonlinear_perf); - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); /* * Set cpuinfo.min_freq to Lowest to make the full range of performance * available if userspace wants to use any perf between lowest & lowest * nonlinear perf */ - policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data, - caps->lowest_perf); - policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf); + policy->cpuinfo.max_freq = cppc_perf_to_khz(caps, caps->nominal_perf); policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu); policy->shared_type = cpu_data->shared_type; @@ -770,7 +667,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy) boost_supported = true; /* Set policy->cur to max now. The governors will adjust later. */ - policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf); + policy->cur = cppc_perf_to_khz(caps, caps->highest_perf); cpu_data->perf_ctrls.desired_perf = caps->highest_perf; ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls); @@ -865,7 +762,7 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu) delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0, &fb_ctrs_t1); - return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf); } static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) @@ -880,11 +777,9 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state) } if (state) - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->highest_perf); + policy->max = cppc_perf_to_khz(caps, caps->highest_perf); else - policy->max = cppc_cpufreq_perf_to_khz(cpu_data, - caps->nominal_perf); + policy->max = cppc_perf_to_khz(caps, caps->nominal_perf); policy->cpuinfo.max_freq = policy->max; ret = freq_qos_update_request(policy->max_freq_req, policy->max); @@ -944,7 +839,7 @@ static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu) if (ret < 0) return -EIO; - return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf); + return cppc_perf_to_khz(&cpu_data->perf_caps, desired_perf); } static void cppc_check_hisi_workaround(void) diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 4abda800c632..d471d74df3bb 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -1596,7 +1596,7 @@ static void intel_pstate_notify_work(struct work_struct *work) wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_STATUS, 0); } -static DEFINE_SPINLOCK(hwp_notify_lock); +static DEFINE_RAW_SPINLOCK(hwp_notify_lock); static cpumask_t hwp_intr_enable_mask; void notify_hwp_interrupt(void) @@ -1613,7 +1613,7 @@ void notify_hwp_interrupt(void) if (!(value & 0x01)) return; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (!cpumask_test_cpu(this_cpu, &hwp_intr_enable_mask)) goto ack_intr; @@ -1637,13 +1637,13 @@ void notify_hwp_interrupt(void) schedule_delayed_work(&cpudata->hwp_notify_work, msecs_to_jiffies(10)); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); return; ack_intr: wrmsrl_safe(MSR_HWP_STATUS, 0); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) @@ -1656,10 +1656,10 @@ static void intel_pstate_disable_hwp_interrupt(struct cpudata *cpudata) /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00); - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); if (cpumask_test_and_clear_cpu(cpudata->cpu, &hwp_intr_enable_mask)) cancel_delayed_work(&cpudata->hwp_notify_work); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); } static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) @@ -1668,10 +1668,10 @@ static void intel_pstate_enable_hwp_interrupt(struct cpudata *cpudata) if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY)) { unsigned long flags; - spin_lock_irqsave(&hwp_notify_lock, flags); + raw_spin_lock_irqsave(&hwp_notify_lock, flags); INIT_DELAYED_WORK(&cpudata->hwp_notify_work, intel_pstate_notify_work); cpumask_set_cpu(cpudata->cpu, &hwp_intr_enable_mask); - spin_unlock_irqrestore(&hwp_notify_lock, flags); + raw_spin_unlock_irqrestore(&hwp_notify_lock, flags); /* wrmsrl_on_cpu has to be outside spinlock as this can result in IPC */ wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x01); @@ -3101,10 +3101,10 @@ static void intel_pstate_driver_cleanup(void) if (intel_pstate_driver == &intel_pstate) intel_pstate_clear_update_util_hook(cpu); - spin_lock(&hwp_notify_lock); + raw_spin_lock(&hwp_notify_lock); kfree(all_cpu_data[cpu]); WRITE_ONCE(all_cpu_data[cpu], NULL); - spin_unlock(&hwp_notify_lock); + raw_spin_unlock(&hwp_notify_lock); } } cpus_read_unlock(); diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c index cb03bfb0435e..2edb66097cdb 100644 --- a/drivers/cpufreq/qcom-cpufreq-nvmem.c +++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c @@ -53,10 +53,14 @@ struct qcom_cpufreq_match_data { const char **genpd_names; }; +struct qcom_cpufreq_drv_cpu { + int opp_token; +}; + struct qcom_cpufreq_drv { - int *opp_tokens; u32 versions; const struct qcom_cpufreq_match_data *data; + struct qcom_cpufreq_drv_cpu cpus[]; }; static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev; @@ -284,42 +288,39 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) return -ENOENT; } - drv = kzalloc(sizeof(*drv), GFP_KERNEL); - if (!drv) + drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()), + GFP_KERNEL); + if (!drv) { + of_node_put(np); return -ENOMEM; + } match = pdev->dev.platform_data; drv->data = match->data; if (!drv->data) { - ret = -ENODEV; - goto free_drv; + of_node_put(np); + return -ENODEV; } if (drv->data->get_version) { speedbin_nvmem = of_nvmem_cell_get(np, NULL); if (IS_ERR(speedbin_nvmem)) { - ret = dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), - "Could not get nvmem cell\n"); - goto free_drv; + of_node_put(np); + return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem), + "Could not get nvmem cell\n"); } ret = drv->data->get_version(cpu_dev, speedbin_nvmem, &pvs_name, drv); if (ret) { + of_node_put(np); nvmem_cell_put(speedbin_nvmem); - goto free_drv; + return ret; } nvmem_cell_put(speedbin_nvmem); } of_node_put(np); - drv->opp_tokens = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tokens), - GFP_KERNEL); - if (!drv->opp_tokens) { - ret = -ENOMEM; - goto free_drv; - } - for_each_possible_cpu(cpu) { struct dev_pm_opp_config config = { .supported_hw = NULL, @@ -345,9 +346,9 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) } if (config.supported_hw || config.genpd_names) { - drv->opp_tokens[cpu] = dev_pm_opp_set_config(cpu_dev, &config); - if (drv->opp_tokens[cpu] < 0) { - ret = drv->opp_tokens[cpu]; + drv->cpus[cpu].opp_token = dev_pm_opp_set_config(cpu_dev, &config); + if (drv->cpus[cpu].opp_token < 0) { + ret = drv->cpus[cpu].opp_token; dev_err(cpu_dev, "Failed to set OPP config\n"); goto free_opp; } @@ -366,15 +367,11 @@ static int qcom_cpufreq_probe(struct platform_device *pdev) free_opp: for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - kfree(drv->opp_tokens); -free_drv: - kfree(drv); - + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); return ret; } -static int qcom_cpufreq_remove(struct platform_device *pdev) +static void qcom_cpufreq_remove(struct platform_device *pdev) { struct qcom_cpufreq_drv *drv = platform_get_drvdata(pdev); unsigned int cpu; @@ -382,17 +379,12 @@ static int qcom_cpufreq_remove(struct platform_device *pdev) platform_device_unregister(cpufreq_dt_pdev); for_each_possible_cpu(cpu) - dev_pm_opp_clear_config(drv->opp_tokens[cpu]); - - kfree(drv->opp_tokens); - kfree(drv); - - return 0; + dev_pm_opp_clear_config(drv->cpus[cpu].opp_token); } static struct platform_driver qcom_cpufreq_driver = { .probe = qcom_cpufreq_probe, - .remove = qcom_cpufreq_remove, + .remove_new = qcom_cpufreq_remove, .driver = { .name = "qcom-cpufreq-nvmem", }, diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c index 028df8a5f537..079940c69ee0 100644 --- a/drivers/cpufreq/scmi-cpufreq.c +++ b/drivers/cpufreq/scmi-cpufreq.c @@ -62,9 +62,9 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy, unsigned int target_freq) { struct scmi_data *priv = policy->driver_data; + unsigned long freq = target_freq; - if (!perf_ops->freq_set(ph, priv->domain_id, - target_freq * 1000, true)) + if (!perf_ops->freq_set(ph, priv->domain_id, freq * 1000, true)) return target_freq; return 0; diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c index 61ef653bcf56..9e3c7478fc20 100644 --- a/drivers/cpufreq/ti-cpufreq.c +++ b/drivers/cpufreq/ti-cpufreq.c @@ -53,6 +53,9 @@ struct ti_cpufreq_soc_data { unsigned long efuse_shift; unsigned long rev_offset; bool multi_regulator; +/* Backward compatibility hack: Might have missing syscon */ +#define TI_QUIRK_SYSCON_MAY_BE_MISSING 0x1 + u8 quirks; }; struct ti_cpufreq_data { @@ -155,6 +158,7 @@ static struct ti_cpufreq_soc_data omap34xx_soc_data = { .efuse_mask = BIT(3), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -182,6 +186,7 @@ static struct ti_cpufreq_soc_data omap36xx_soc_data = { .efuse_mask = BIT(9), .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = true, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; /* @@ -196,6 +201,7 @@ static struct ti_cpufreq_soc_data am3517_soc_data = { .efuse_mask = 0, .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE, .multi_regulator = false, + .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING, }; @@ -215,7 +221,7 @@ static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data, ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset, &efuse); - if (ret == -EIO) { + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->efuse_offset, 4); @@ -256,7 +262,7 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data, ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset, &revision); - if (ret == -EIO) { + if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) { /* not a syscon register! */ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE + opp_data->soc_data->rev_offset, 4); @@ -381,7 +387,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev) ret = dev_pm_opp_set_config(opp_data->cpu_dev, &config); if (ret < 0) { - dev_err(opp_data->cpu_dev, "Failed to set OPP config\n"); + dev_err_probe(opp_data->cpu_dev, ret, "Failed to set OPP config\n"); goto fail_put_node; } diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c index bbfb0f288dc3..06e7a4d2b20d 100644 --- a/drivers/crypto/ccp/sev-dev.c +++ b/drivers/crypto/ccp/sev-dev.c @@ -1362,6 +1362,8 @@ void sev_pci_init(void) return; err: + sev_dev_destroy(psp_master); + psp_master->sev_data = NULL; } diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c index 269df4ec148b..e9abb66773fe 100644 --- a/drivers/crypto/hisilicon/hpre/hpre_main.c +++ b/drivers/crypto/hisilicon/hpre/hpre_main.c @@ -14,9 +14,7 @@ #include #include "hpre.h" -#define HPRE_QM_ABNML_INT_MASK 0x100004 #define HPRE_CTRL_CNT_CLR_CE_BIT BIT(0) -#define HPRE_COMM_CNT_CLR_CE 0x0 #define HPRE_CTRL_CNT_CLR_CE 0x301000 #define HPRE_FSM_MAX_CNT 0x301008 #define HPRE_VFG_AXQOS 0x30100c @@ -43,7 +41,6 @@ #define HPRE_HAC_INT_SET 0x301500 #define HPRE_RNG_TIMEOUT_NUM 0x301A34 #define HPRE_CORE_INT_ENABLE 0 -#define HPRE_CORE_INT_DISABLE GENMASK(21, 0) #define HPRE_RDCHN_INI_ST 0x301a00 #define HPRE_CLSTR_BASE 0x302000 #define HPRE_CORE_EN_OFFSET 0x04 @@ -67,7 +64,6 @@ #define HPRE_CLSTR_ADDR_INTRVL 0x1000 #define HPRE_CLUSTER_INQURY 0x100 #define HPRE_CLSTR_ADDR_INQRY_RSLT 0x104 -#define HPRE_TIMEOUT_ABNML_BIT 6 #define HPRE_PASID_EN_BIT 9 #define HPRE_REG_RD_INTVRL_US 10 #define HPRE_REG_RD_TMOUT_US 1000 @@ -203,9 +199,9 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = { {HPRE_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC37, 0x6C37}, {HPRE_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C37}, {HPRE_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8}, - {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xFFFFFE}, - {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFFFE}, - {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFFFE}, + {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0x1FFFC3E}, + {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFC3E}, + {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFC3E}, {HPRE_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x1, 0x1}, {HPRE_CLUSTER_NUM_CAP, 0x313c, 20, GENMASK(3, 0), 0x0, 0x4, 0x1}, {HPRE_CORE_TYPE_NUM_CAP, 0x313c, 16, GENMASK(3, 0), 0x0, 0x2, 0x2}, @@ -283,6 +279,9 @@ static const struct hpre_hw_error hpre_hw_errors[] = { }, { .int_msk = BIT(23), .msg = "sva_fsm_timeout_int_set" + }, { + .int_msk = BIT(24), + .msg = "sva_int_set" }, { /* sentinel */ } @@ -355,6 +354,8 @@ static struct dfx_diff_registers hpre_diff_regs[] = { }, }; +static const struct hisi_qm_err_ini hpre_err_ini; + bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg) { u32 cap_val; @@ -651,11 +652,6 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) writel(HPRE_QM_USR_CFG_MASK, qm->io_base + QM_AWUSER_M_CFG_ENABLE); writel_relaxed(HPRE_QM_AXI_CFG_MASK, qm->io_base + QM_AXI_M_CFG); - /* HPRE need more time, we close this interrupt */ - val = readl_relaxed(qm->io_base + HPRE_QM_ABNML_INT_MASK); - val |= BIT(HPRE_TIMEOUT_ABNML_BIT); - writel_relaxed(val, qm->io_base + HPRE_QM_ABNML_INT_MASK); - if (qm->ver >= QM_HW_V3) writel(HPRE_RSA_ENB | HPRE_ECC_ENB, qm->io_base + HPRE_TYPES_ENB); @@ -664,9 +660,7 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm) writel(HPRE_QM_VFG_AX_MASK, qm->io_base + HPRE_VFG_AXCACHE); writel(0x0, qm->io_base + HPRE_BD_ENDIAN); - writel(0x0, qm->io_base + HPRE_INT_MASK); writel(0x0, qm->io_base + HPRE_POISON_BYPASS); - writel(0x0, qm->io_base + HPRE_COMM_CNT_CLR_CE); writel(0x0, qm->io_base + HPRE_ECC_BYPASS); writel(HPRE_BD_USR_MASK, qm->io_base + HPRE_BD_ARUSR_CFG); @@ -756,7 +750,7 @@ static void hpre_hw_error_disable(struct hisi_qm *qm) static void hpre_hw_error_enable(struct hisi_qm *qm) { - u32 ce, nfe; + u32 ce, nfe, err_en; ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CE_MASK_CAP, qm->cap_ver); nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver); @@ -773,7 +767,8 @@ static void hpre_hw_error_enable(struct hisi_qm *qm) hpre_master_ooo_ctrl(qm, true); /* enable hpre hw error interrupts */ - writel(HPRE_CORE_INT_ENABLE, qm->io_base + HPRE_INT_MASK); + err_en = ce | nfe | HPRE_HAC_RAS_FE_ENABLE; + writel(~err_en, qm->io_base + HPRE_INT_MASK); } static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file) @@ -1159,6 +1154,7 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &hpre_devices; + qm->err_ini = &hpre_err_ini; if (pf_q_num_flag) set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } @@ -1348,8 +1344,6 @@ static int hpre_pf_probe_init(struct hpre *hpre) hpre_open_sva_prefetch(qm); - qm->err_ini = &hpre_err_ini; - qm->err_ini->err_info_init(qm); hisi_qm_dev_err_init(qm); ret = hpre_show_last_regs_init(qm); if (ret) @@ -1378,6 +1372,18 @@ static int hpre_probe_init(struct hpre *hpre) return 0; } +static void hpre_probe_uninit(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + hpre_cnt_regs_clear(qm); + qm->debug.curr_qm_qp_num = 0; + hpre_show_last_regs_uninit(qm); + hpre_close_sva_prefetch(qm); + hisi_qm_dev_err_uninit(qm); +} + static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_qm *qm; @@ -1403,7 +1409,7 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_qm_start(qm); if (ret) - goto err_with_err_init; + goto err_with_probe_init; ret = hpre_debugfs_init(qm); if (ret) @@ -1440,9 +1446,8 @@ err_with_qm_start: hpre_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); -err_with_err_init: - hpre_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); +err_with_probe_init: + hpre_probe_uninit(qm); err_with_qm_init: hisi_qm_uninit(qm); @@ -1463,13 +1468,7 @@ static void hpre_remove(struct pci_dev *pdev) hpre_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); - if (qm->fun_type == QM_HW_PF) { - hpre_cnt_regs_clear(qm); - qm->debug.curr_qm_qp_num = 0; - hpre_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); - } - + hpre_probe_uninit(qm); hisi_qm_uninit(qm); } diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 5539be1bfb40..df14727f6e71 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -118,7 +118,7 @@ #define QM_SQC_VFT_BASE_SHIFT_V2 28 #define QM_SQC_VFT_BASE_MASK_V2 GENMASK(15, 0) #define QM_SQC_VFT_NUM_SHIFT_V2 45 -#define QM_SQC_VFT_NUM_MASK_v2 GENMASK(9, 0) +#define QM_SQC_VFT_NUM_MASK_V2 GENMASK(9, 0) #define QM_ABNORMAL_INT_SOURCE 0x100000 #define QM_ABNORMAL_INT_MASK 0x100004 @@ -240,23 +240,23 @@ #define QM_DEV_ALG_MAX_LEN 256 #define QM_MK_CQC_DW3_V1(hop_num, pg_sz, buf_sz, cqe_sz) \ - (((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \ - ((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \ - ((buf_sz) << QM_CQ_BUF_SIZE_SHIFT) | \ + (((hop_num) << QM_CQ_HOP_NUM_SHIFT) | \ + ((pg_sz) << QM_CQ_PAGE_SIZE_SHIFT) | \ + ((buf_sz) << QM_CQ_BUF_SIZE_SHIFT) | \ ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) #define QM_MK_CQC_DW3_V2(cqe_sz, cq_depth) \ ((((u32)cq_depth) - 1) | ((cqe_sz) << QM_CQ_CQE_SIZE_SHIFT)) #define QM_MK_SQC_W13(priority, orders, alg_type) \ - (((priority) << QM_SQ_PRIORITY_SHIFT) | \ - ((orders) << QM_SQ_ORDERS_SHIFT) | \ + (((priority) << QM_SQ_PRIORITY_SHIFT) | \ + ((orders) << QM_SQ_ORDERS_SHIFT) | \ (((alg_type) & QM_SQ_TYPE_MASK) << QM_SQ_TYPE_SHIFT)) #define QM_MK_SQC_DW3_V1(hop_num, pg_sz, buf_sz, sqe_sz) \ - (((hop_num) << QM_SQ_HOP_NUM_SHIFT) | \ - ((pg_sz) << QM_SQ_PAGE_SIZE_SHIFT) | \ - ((buf_sz) << QM_SQ_BUF_SIZE_SHIFT) | \ + (((hop_num) << QM_SQ_HOP_NUM_SHIFT) | \ + ((pg_sz) << QM_SQ_PAGE_SIZE_SHIFT) | \ + ((buf_sz) << QM_SQ_BUF_SIZE_SHIFT) | \ ((u32)ilog2(sqe_sz) << QM_SQ_SQE_SIZE_SHIFT)) #define QM_MK_SQC_DW3_V2(sqe_sz, sq_depth) \ @@ -454,6 +454,7 @@ static struct qm_typical_qos_table shaper_cbs_s[] = { }; static void qm_irqs_unregister(struct hisi_qm *qm); +static int qm_reset_device(struct hisi_qm *qm); static bool qm_avail_state(struct hisi_qm *qm, enum qm_state new) { @@ -720,7 +721,7 @@ static void qm_db_v2(struct hisi_qm *qm, u16 qn, u8 cmd, u16 index, u8 priority) doorbell = qn | ((u64)cmd << QM_DB_CMD_SHIFT_V2) | ((u64)randata << QM_DB_RAND_SHIFT_V2) | - ((u64)index << QM_DB_INDEX_SHIFT_V2) | + ((u64)index << QM_DB_INDEX_SHIFT_V2) | ((u64)priority << QM_DB_PRIORITY_SHIFT_V2); writeq(doorbell, io_base); @@ -1354,7 +1355,7 @@ static int qm_get_vft_v2(struct hisi_qm *qm, u32 *base, u32 *number) sqc_vft = readl(qm->io_base + QM_MB_CMD_DATA_ADDR_L) | ((u64)readl(qm->io_base + QM_MB_CMD_DATA_ADDR_H) << 32); *base = QM_SQC_VFT_BASE_MASK_V2 & (sqc_vft >> QM_SQC_VFT_BASE_SHIFT_V2); - *number = (QM_SQC_VFT_NUM_MASK_v2 & + *number = (QM_SQC_VFT_NUM_MASK_V2 & (sqc_vft >> QM_SQC_VFT_NUM_SHIFT_V2)) + 1; return 0; @@ -3123,7 +3124,6 @@ static int qm_stop_started_qp(struct hisi_qm *qm) return 0; } - /** * qm_clear_queues() - Clear all queues memory in a qm. * @qm: The qm in which the queues will be cleared. @@ -3609,7 +3609,7 @@ static ssize_t qm_algqos_read(struct file *filp, char __user *buf, qos_val = ir / QM_QOS_RATE; ret = scnprintf(tbuf, QM_DBG_READ_LEN, "%u\n", qos_val); - ret = simple_read_from_buffer(buf, count, pos, tbuf, ret); + ret = simple_read_from_buffer(buf, count, pos, tbuf, ret); err_get_status: clear_bit(QM_RESETTING, &qm->misc_ctl); @@ -4017,6 +4017,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set) return -ETIMEDOUT; } +static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +{ + u32 nfe_enb = 0; + + /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ + if (qm->ver >= QM_HW_V3) + return; + + if (!qm->err_status.is_dev_ecc_mbit && + qm->err_status.is_qm_ecc_mbit && + qm->err_ini->close_axi_master_ooo) { + qm->err_ini->close_axi_master_ooo(qm); + } else if (qm->err_status.is_dev_ecc_mbit && + !qm->err_status.is_qm_ecc_mbit && + !qm->err_ini->close_axi_master_ooo) { + nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); + writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, + qm->io_base + QM_RAS_NFE_ENABLE); + writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); + } +} + static int qm_vf_reset_prepare(struct hisi_qm *qm, enum qm_stop_reason stop_reason) { @@ -4081,6 +4103,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return ret; } + qm_dev_ecc_mbit_handle(qm); + /* PF obtains the information of VF by querying the register. */ qm_cmd_uninit(qm); @@ -4105,36 +4129,26 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm) return 0; } -static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm) +static int qm_master_ooo_check(struct hisi_qm *qm) { - u32 nfe_enb = 0; + u32 val; + int ret; - /* Kunpeng930 hardware automatically close master ooo when NFE occurs */ - if (qm->ver >= QM_HW_V3) - return; + /* Check the ooo register of the device before resetting the device. */ + writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL); + ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, + val, (val == ACC_MASTER_TRANS_RETURN_RW), + POLL_PERIOD, POLL_TIMEOUT); + if (ret) + pci_warn(qm->pdev, "Bus lock! Please reset system.\n"); - if (!qm->err_status.is_dev_ecc_mbit && - qm->err_status.is_qm_ecc_mbit && - qm->err_ini->close_axi_master_ooo) { - - qm->err_ini->close_axi_master_ooo(qm); - - } else if (qm->err_status.is_dev_ecc_mbit && - !qm->err_status.is_qm_ecc_mbit && - !qm->err_ini->close_axi_master_ooo) { - - nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE); - writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE, - qm->io_base + QM_RAS_NFE_ENABLE); - writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET); - } + return ret; } -static int qm_soft_reset(struct hisi_qm *qm) +static int qm_soft_reset_prepare(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; int ret; - u32 val; /* Ensure all doorbells and mailboxes received by QM */ ret = qm_check_req_recv(qm); @@ -4155,30 +4169,23 @@ static int qm_soft_reset(struct hisi_qm *qm) return ret; } - qm_dev_ecc_mbit_handle(qm); - - /* OOO register set and check */ - writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, - qm->io_base + ACC_MASTER_GLOBAL_CTRL); - - /* If bus lock, reset chip */ - ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, - val, - (val == ACC_MASTER_TRANS_RETURN_RW), - POLL_PERIOD, POLL_TIMEOUT); - if (ret) { - pci_emerg(pdev, "Bus lock! Please reset system.\n"); + ret = qm_master_ooo_check(qm); + if (ret) return ret; - } if (qm->err_ini->close_sva_prefetch) qm->err_ini->close_sva_prefetch(qm); ret = qm_set_pf_mse(qm, false); - if (ret) { + if (ret) pci_err(pdev, "Fails to disable pf MSE bit.\n"); - return ret; - } + + return ret; +} + +static int qm_reset_device(struct hisi_qm *qm) +{ + struct pci_dev *pdev = qm->pdev; /* The reset related sub-control registers are not in PCI BAR */ if (ACPI_HANDLE(&pdev->dev)) { @@ -4197,12 +4204,23 @@ static int qm_soft_reset(struct hisi_qm *qm) pci_err(pdev, "Reset step %llu failed!\n", value); return -EIO; } - } else { - pci_err(pdev, "No reset method!\n"); - return -EINVAL; + + return 0; } - return 0; + pci_err(pdev, "No reset method!\n"); + return -EINVAL; +} + +static int qm_soft_reset(struct hisi_qm *qm) +{ + int ret; + + ret = qm_soft_reset_prepare(qm); + if (ret) + return ret; + + return qm_reset_device(qm); } static int qm_vf_reset_done(struct hisi_qm *qm) @@ -4566,7 +4584,6 @@ static irqreturn_t qm_abnormal_irq(int irq, void *data) return IRQ_HANDLED; } - /** * hisi_qm_dev_shutdown() - Shutdown device. * @pdev: The device will be shutdown. @@ -5165,6 +5182,35 @@ err_request_mem_regions: return ret; } +static int qm_clear_device(struct hisi_qm *qm) +{ + acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev); + int ret; + + if (qm->fun_type == QM_HW_VF) + return 0; + + /* Device does not support reset, return */ + if (!qm->err_ini->err_info_init) + return 0; + qm->err_ini->err_info_init(qm); + + if (!handle) + return 0; + + /* No reset method, return */ + if (!acpi_has_method(handle, qm->err_info.acpi_rst)) + return 0; + + ret = qm_master_ooo_check(qm); + if (ret) { + writel(0x0, qm->io_base + ACC_MASTER_GLOBAL_CTRL); + return ret; + } + + return qm_reset_device(qm); +} + static int hisi_qm_pci_init(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; @@ -5194,8 +5240,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm) goto err_get_pci_res; } + ret = qm_clear_device(qm); + if (ret) + goto err_free_vectors; + return 0; +err_free_vectors: + pci_free_irq_vectors(pdev); err_get_pci_res: qm_put_pci_res(qm); err_disable_pcidev: @@ -5462,7 +5514,6 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm) { struct pci_dev *pdev = qm->pdev; int ret; - u32 val; ret = qm->ops->set_msi(qm, false); if (ret) { @@ -5470,18 +5521,9 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm) return ret; } - /* shutdown OOO register */ - writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, - qm->io_base + ACC_MASTER_GLOBAL_CTRL); - - ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN, - val, - (val == ACC_MASTER_TRANS_RETURN_RW), - POLL_PERIOD, POLL_TIMEOUT); - if (ret) { - pci_emerg(pdev, "Bus lock! Please reset system.\n"); + ret = qm_master_ooo_check(qm); + if (ret) return ret; - } ret = qm_set_pf_mse(qm, false); if (ret) diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c index 4bab5000a13e..d2ead648767b 100644 --- a/drivers/crypto/hisilicon/sec2/sec_main.c +++ b/drivers/crypto/hisilicon/sec2/sec_main.c @@ -1063,9 +1063,6 @@ static int sec_pf_probe_init(struct sec_dev *sec) struct hisi_qm *qm = &sec->qm; int ret; - qm->err_ini = &sec_err_ini; - qm->err_ini->err_info_init(qm); - ret = sec_set_user_domain_and_cache(qm); if (ret) return ret; @@ -1120,6 +1117,7 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &sec_devices; + qm->err_ini = &sec_err_ini; if (pf_q_num_flag) set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) { @@ -1184,6 +1182,12 @@ static int sec_probe_init(struct sec_dev *sec) static void sec_probe_uninit(struct hisi_qm *qm) { + if (qm->fun_type == QM_HW_VF) + return; + + sec_debug_regs_clear(qm); + sec_show_last_regs_uninit(qm); + sec_close_sva_prefetch(qm); hisi_qm_dev_err_uninit(qm); } @@ -1276,7 +1280,6 @@ err_qm_stop: sec_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); err_probe_uninit: - sec_show_last_regs_uninit(qm); sec_probe_uninit(qm); err_qm_uninit: sec_qm_uninit(qm); @@ -1298,11 +1301,6 @@ static void sec_remove(struct pci_dev *pdev) sec_debugfs_exit(qm); (void)hisi_qm_stop(qm, QM_NORMAL); - - if (qm->fun_type == QM_HW_PF) - sec_debug_regs_clear(qm); - sec_show_last_regs_uninit(qm); - sec_probe_uninit(qm); sec_qm_uninit(qm); diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c index 0974b0041405..09586a837b1e 100644 --- a/drivers/crypto/hisilicon/sgl.c +++ b/drivers/crypto/hisilicon/sgl.c @@ -249,7 +249,6 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, dev_err(dev, "Get SGL error!\n"); dma_unmap_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL); return ERR_PTR(-ENOMEM); - } curr_hw_sgl->entry_length_in_sgl = cpu_to_le16(pool->sge_nr); curr_hw_sge = curr_hw_sgl->sge_entries; diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c index 9e3f5bca27de..a8d5d105b354 100644 --- a/drivers/crypto/hisilicon/zip/zip_main.c +++ b/drivers/crypto/hisilicon/zip/zip_main.c @@ -1151,8 +1151,6 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip) hisi_zip->ctrl = ctrl; ctrl->hisi_zip = hisi_zip; - qm->err_ini = &hisi_zip_err_ini; - qm->err_ini->err_info_init(qm); ret = hisi_zip_set_user_domain_and_cache(qm); if (ret) @@ -1213,6 +1211,7 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev) qm->qp_num = pf_q_num; qm->debug.curr_qm_qp_num = pf_q_num; qm->qm_list = &zip_devices; + qm->err_ini = &hisi_zip_err_ini; if (pf_q_num_flag) set_bit(QM_MODULE_PARAM, &qm->misc_ctl); } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) { @@ -1279,6 +1278,16 @@ static int hisi_zip_probe_init(struct hisi_zip *hisi_zip) return 0; } +static void hisi_zip_probe_uninit(struct hisi_qm *qm) +{ + if (qm->fun_type == QM_HW_VF) + return; + + hisi_zip_show_last_regs_uninit(qm); + hisi_zip_close_sva_prefetch(qm); + hisi_qm_dev_err_uninit(qm); +} + static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct hisi_zip *hisi_zip; @@ -1305,7 +1314,7 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id) ret = hisi_qm_start(qm); if (ret) - goto err_dev_err_uninit; + goto err_probe_uninit; ret = hisi_zip_debugfs_init(qm); if (ret) @@ -1342,9 +1351,8 @@ err_qm_stop: hisi_zip_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); -err_dev_err_uninit: - hisi_zip_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); +err_probe_uninit: + hisi_zip_probe_uninit(qm); err_qm_uninit: hisi_zip_qm_uninit(qm); @@ -1365,8 +1373,7 @@ static void hisi_zip_remove(struct pci_dev *pdev) hisi_zip_debugfs_exit(qm); hisi_qm_stop(qm, QM_NORMAL); - hisi_zip_show_last_regs_uninit(qm); - hisi_qm_dev_err_uninit(qm); + hisi_zip_probe_uninit(qm); hisi_zip_qm_uninit(qm); } diff --git a/drivers/crypto/qat/qat_common/adf_cfg.c b/drivers/crypto/qat/qat_common/adf_cfg.c index 1931e5b37f2b..368d14d81503 100644 --- a/drivers/crypto/qat/qat_common/adf_cfg.c +++ b/drivers/crypto/qat/qat_common/adf_cfg.c @@ -276,17 +276,19 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev, * 3. if the key exists with the same value, then return without doing * anything (the newly created key_val is freed). */ + down_write(&cfg->lock); if (!adf_cfg_key_val_get(accel_dev, section_name, key, temp_val)) { if (strncmp(temp_val, key_val->val, sizeof(temp_val))) { adf_cfg_keyval_remove(key, section); } else { kfree(key_val); - return 0; + goto out; } } - down_write(&cfg->lock); adf_cfg_keyval_add(key_val, section); + +out: up_write(&cfg->lock); return 0; } diff --git a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c index 70ef11963938..43af81fcab86 100644 --- a/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c +++ b/drivers/crypto/qat/qat_common/adf_gen2_pfvf.c @@ -100,7 +100,9 @@ static u32 adf_gen2_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); - errmsk3 &= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); + /* Update only section of errmsk3 related to VF2PF */ + errmsk3 &= ~ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK); + errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); /* Return the sources of the (new) interrupt(s) */ diff --git a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c index cb3bdd3618fb..85295c7ee0e0 100644 --- a/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c +++ b/drivers/crypto/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c @@ -180,8 +180,12 @@ static u32 disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr) ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); - errmsk3 &= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); - errmsk5 &= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); + /* Update only section of errmsk3 and errmsk5 related to VF2PF */ + errmsk3 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK); + errmsk5 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK); + + errmsk3 |= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled); + errmsk5 |= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3); ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5); diff --git a/drivers/crypto/vmx/Makefile b/drivers/crypto/vmx/Makefile index 2560cfea1dec..e33c7238e7f8 100644 --- a/drivers/crypto/vmx/Makefile +++ b/drivers/crypto/vmx/Makefile @@ -2,8 +2,18 @@ obj-$(CONFIG_CRYPTO_DEV_VMX_ENCRYPT) += vmx-crypto.o vmx-crypto-objs := vmx.o aesp8-ppc.o ghashp8-ppc.o aes.o aes_cbc.o aes_ctr.o aes_xts.o ghash.o +ifeq ($(CONFIG_CPU_LITTLE_ENDIAN),y) +override flavour := linux-ppc64le +else +ifdef CONFIG_PPC64_ELF_ABI_V2 +override flavour := linux-ppc64-elfv2 +else +override flavour := linux-ppc64 +endif +endif + quiet_cmd_perl = PERL $@ - cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@ + cmd_perl = $(PERL) $< $(flavour) > $@ targets += aesp8-ppc.S ghashp8-ppc.S diff --git a/drivers/crypto/vmx/ppc-xlate.pl b/drivers/crypto/vmx/ppc-xlate.pl index 36db2ef09e5b..b583898c11ae 100644 --- a/drivers/crypto/vmx/ppc-xlate.pl +++ b/drivers/crypto/vmx/ppc-xlate.pl @@ -9,6 +9,8 @@ open STDOUT,">$output" || die "can't open $output: $!"; my %GLOBALS; my $dotinlocallabels=($flavour=~/linux/)?1:0; +my $elfv2abi=(($flavour =~ /linux-ppc64le/) or ($flavour =~ /linux-ppc64-elfv2/))?1:0; +my $dotfunctions=($elfv2abi=~1)?0:1; ################################################################ # directives which need special treatment on different platforms @@ -40,7 +42,7 @@ my $globl = sub { }; my $text = sub { my $ret = ($flavour =~ /aix/) ? ".csect\t.text[PR],7" : ".text"; - $ret = ".abiversion 2\n".$ret if ($flavour =~ /linux.*64le/); + $ret = ".abiversion 2\n".$ret if ($elfv2abi); $ret; }; my $machine = sub { @@ -56,8 +58,8 @@ my $size = sub { if ($flavour =~ /linux/) { shift; my $name = shift; $name =~ s|^[\.\_]||; - my $ret = ".size $name,.-".($flavour=~/64$/?".":"").$name; - $ret .= "\n.size .$name,.-.$name" if ($flavour=~/64$/); + my $ret = ".size $name,.-".($dotfunctions?".":"").$name; + $ret .= "\n.size .$name,.-.$name" if ($dotfunctions); $ret; } else @@ -142,7 +144,7 @@ my $vmr = sub { # Some ABIs specify vrsave, special-purpose register #256, as reserved # for system use. -my $no_vrsave = ($flavour =~ /linux-ppc64le/); +my $no_vrsave = ($elfv2abi); my $mtspr = sub { my ($f,$idx,$ra) = @_; if ($idx == 256 && $no_vrsave) { diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c index 5584af15300a..8d92a24fd73d 100644 --- a/drivers/cxl/core/pci.c +++ b/drivers/cxl/core/pci.c @@ -211,11 +211,10 @@ int cxl_await_media_ready(struct cxl_dev_state *cxlds) } EXPORT_SYMBOL_NS_GPL(cxl_await_media_ready, CXL); -static int wait_for_valid(struct cxl_dev_state *cxlds) +static int wait_for_valid(struct pci_dev *pdev, int d) { - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - int d = cxlds->cxl_dvsec, rc; u32 val; + int rc; /* * Memory_Info_Valid: When set, indicates that the CXL Range 1 Size high @@ -404,20 +403,11 @@ static bool __cxl_hdm_decode_init(struct cxl_dev_state *cxlds, return true; } -/** - * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint - * @cxlds: Device state - * @cxlhdm: Mapped HDM decoder Capability - * - * Try to enable the endpoint's HDM Decoder Capability - */ -int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) +static int cxl_dvsec_rr_decode(struct device *dev, int d, + struct cxl_endpoint_dvsec_info *info) { - struct pci_dev *pdev = to_pci_dev(cxlds->dev); - struct cxl_endpoint_dvsec_info info = { 0 }; + struct pci_dev *pdev = to_pci_dev(dev); int hdm_count, rc, i, ranges = 0; - struct device *dev = &pdev->dev; - int d = cxlds->cxl_dvsec; u16 cap, ctrl; if (!d) { @@ -448,7 +438,7 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) if (!hdm_count || hdm_count > 2) return -EINVAL; - rc = wait_for_valid(cxlds); + rc = wait_for_valid(pdev, d); if (rc) { dev_dbg(dev, "Failure awaiting MEM_INFO_VALID (%d)\n", rc); return rc; @@ -459,9 +449,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) * disabled, and they will remain moot after the HDM Decoder * capability is enabled. */ - info.mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl); - if (!info.mem_enabled) - goto hdm_init; + info->mem_enabled = FIELD_GET(CXL_DVSEC_MEM_ENABLE, ctrl); + if (!info->mem_enabled) + return 0; for (i = 0; i < hdm_count; i++) { u64 base, size; @@ -480,6 +470,9 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) return rc; size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK; + if (!size) { + continue; + } rc = pci_read_config_dword( pdev, d + CXL_DVSEC_RANGE_BASE_HIGH(i), &temp); @@ -495,22 +488,39 @@ int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK; - info.dvsec_range[i] = (struct range) { + info->dvsec_range[ranges++] = (struct range) { .start = base, .end = base + size - 1 }; - - if (size) - ranges++; } - info.ranges = ranges; + info->ranges = ranges; + + return 0; +} + +/** + * cxl_hdm_decode_init() - Setup HDM decoding for the endpoint + * @cxlds: Device state + * @cxlhdm: Mapped HDM decoder Capability + * + * Try to enable the endpoint's HDM Decoder Capability + */ +int cxl_hdm_decode_init(struct cxl_dev_state *cxlds, struct cxl_hdm *cxlhdm) +{ + struct cxl_endpoint_dvsec_info info = { 0 }; + struct device *dev = cxlds->dev; + int d = cxlds->cxl_dvsec; + int rc; + + rc = cxl_dvsec_rr_decode(dev, d, &info); + if (rc < 0) + return rc; /* * If DVSEC ranges are being used instead of HDM decoder registers there * is no use in trying to manage those. */ -hdm_init: if (!__cxl_hdm_decode_init(cxlds, cxlhdm, &info)) { dev_err(dev, "Legacy range registers configuration prevents HDM operation.\n"); diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index b58a5b782e5d..0be48441d0f2 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -293,7 +293,7 @@ enum cxl_opcode { 0x3b, 0x3f, 0x17) #define DEFINE_CXL_VENDOR_DEBUG_UUID \ - UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ + UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \ 0x40, 0x3d, 0x86) struct cxl_mbox_get_supported_logs { diff --git a/drivers/dax/device.c b/drivers/dax/device.c index 5494d745ced5..b10761b8c35a 100644 --- a/drivers/dax/device.c +++ b/drivers/dax/device.c @@ -86,7 +86,7 @@ static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn, nr_pages = 1; pgoff = linear_page_index(vmf->vma, - ALIGN(vmf->address, fault_size)); + ALIGN_DOWN(vmf->address, fault_size)); for (i = 0; i < nr_pages; i++) { struct page *page = pfn_to_page(pfn_t_to_pfn(pfn) + i); diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c index 28fb04eccdd0..ec2a2a1560a4 100644 --- a/drivers/dma-buf/heaps/cma_heap.c +++ b/drivers/dma-buf/heaps/cma_heap.c @@ -165,7 +165,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; struct cma_heap_buffer *buffer = vma->vm_private_data; - if (vmf->pgoff > buffer->pagecount) + if (vmf->pgoff >= buffer->pagecount) return VM_FAULT_SIGBUS; vmf->page = buffer->pages[vmf->pgoff]; diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c index 4153c2edb049..711e3756a39a 100644 --- a/drivers/dma/altera-msgdma.c +++ b/drivers/dma/altera-msgdma.c @@ -233,7 +233,7 @@ static void msgdma_free_descriptor(struct msgdma_device *mdev, struct msgdma_sw_desc *child, *next; mdev->desc_free_cnt++; - list_add_tail(&desc->node, &mdev->free_list); + list_move_tail(&desc->node, &mdev->free_list); list_for_each_entry_safe(child, next, &desc->tx_list, node) { mdev->desc_free_cnt++; list_move_tail(&child->node, &mdev->free_list); @@ -583,17 +583,16 @@ static void msgdma_issue_pending(struct dma_chan *chan) static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev) { struct msgdma_sw_desc *desc, *next; + unsigned long irqflags; list_for_each_entry_safe(desc, next, &mdev->done_list, node) { struct dmaengine_desc_callback cb; - list_del(&desc->node); - dmaengine_desc_get_callback(&desc->async_tx, &cb); if (dmaengine_desc_callback_valid(&cb)) { - spin_unlock(&mdev->lock); + spin_unlock_irqrestore(&mdev->lock, irqflags); dmaengine_desc_callback_invoke(&cb, NULL); - spin_lock(&mdev->lock); + spin_lock_irqsave(&mdev->lock, irqflags); } /* Run any dependencies, then free the descriptor */ diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c index 97ba3bfc10b1..66c98676e66a 100644 --- a/drivers/dma/dw/core.c +++ b/drivers/dma/dw/core.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -621,12 +622,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, struct dw_desc *prev; struct dw_desc *first; u32 ctllo, ctlhi; - u8 m_master = dwc->dws.m_master; - u8 lms = DWC_LLP_LMS(m_master); + u8 lms = DWC_LLP_LMS(dwc->dws.m_master); dma_addr_t reg; unsigned int reg_width; unsigned int mem_width; - unsigned int data_width = dw->pdata->data_width[m_master]; unsigned int i; struct scatterlist *sg; size_t total_len = 0; @@ -660,7 +659,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl, mem = sg_dma_address(sg); len = sg_dma_len(sg); - mem_width = __ffs(data_width | mem | len); + mem_width = __ffs(sconfig->src_addr_width | mem | len); slave_sg_todev_fill_desc: desc = dwc_desc_get(dwc); @@ -720,7 +719,7 @@ slave_sg_fromdev_fill_desc: lli_write(desc, sar, reg); lli_write(desc, dar, mem); lli_write(desc, ctlhi, ctlhi); - mem_width = __ffs(data_width | mem); + mem_width = __ffs(sconfig->dst_addr_width | mem); lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width)); desc->len = dlen; @@ -780,17 +779,93 @@ bool dw_dma_filter(struct dma_chan *chan, void *param) } EXPORT_SYMBOL_GPL(dw_dma_filter); +static int dwc_verify_p_buswidth(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); + u32 reg_width, max_width; + + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) + reg_width = dwc->dma_sconfig.dst_addr_width; + else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) + reg_width = dwc->dma_sconfig.src_addr_width; + else /* DMA_MEM_TO_MEM */ + return 0; + + max_width = dw->pdata->data_width[dwc->dws.p_master]; + + /* Fall-back to 1-byte transfer width if undefined */ + if (reg_width == DMA_SLAVE_BUSWIDTH_UNDEFINED) + reg_width = DMA_SLAVE_BUSWIDTH_1_BYTE; + else if (!is_power_of_2(reg_width) || reg_width > max_width) + return -EINVAL; + else /* bus width is valid */ + return 0; + + /* Update undefined addr width value */ + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) + dwc->dma_sconfig.dst_addr_width = reg_width; + else /* DMA_DEV_TO_MEM */ + dwc->dma_sconfig.src_addr_width = reg_width; + + return 0; +} + +static int dwc_verify_m_buswidth(struct dma_chan *chan) +{ + struct dw_dma_chan *dwc = to_dw_dma_chan(chan); + struct dw_dma *dw = to_dw_dma(chan->device); + u32 reg_width, reg_burst, mem_width; + + mem_width = dw->pdata->data_width[dwc->dws.m_master]; + + /* + * It's possible to have a data portion locked in the DMA FIFO in case + * of the channel suspension. Subsequent channel disabling will cause + * that data silent loss. In order to prevent that maintain the src and + * dst transfer widths coherency by means of the relation: + * (CTLx.SRC_TR_WIDTH * CTLx.SRC_MSIZE >= CTLx.DST_TR_WIDTH) + * Look for the details in the commit message that brings this change. + * + * Note the DMA configs utilized in the calculations below must have + * been verified to have correct values by this method call. + */ + if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) { + reg_width = dwc->dma_sconfig.dst_addr_width; + if (mem_width < reg_width) + return -EINVAL; + + dwc->dma_sconfig.src_addr_width = mem_width; + } else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) { + reg_width = dwc->dma_sconfig.src_addr_width; + reg_burst = rounddown_pow_of_two(dwc->dma_sconfig.src_maxburst); + + dwc->dma_sconfig.dst_addr_width = min(mem_width, reg_width * reg_burst); + } + + return 0; +} + static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig) { struct dw_dma_chan *dwc = to_dw_dma_chan(chan); struct dw_dma *dw = to_dw_dma(chan->device); + int ret; memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig)); dwc->dma_sconfig.src_maxburst = - clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst); + clamp(dwc->dma_sconfig.src_maxburst, 1U, dwc->max_burst); dwc->dma_sconfig.dst_maxburst = - clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst); + clamp(dwc->dma_sconfig.dst_maxburst, 1U, dwc->max_burst); + + ret = dwc_verify_p_buswidth(chan); + if (ret) + return ret; + + ret = dwc_verify_m_buswidth(chan); + if (ret) + return ret; dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst); dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst); diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 82e7acfda6ed..e323e1a5f20f 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4423,7 +4423,9 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud) ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2); break; case DMA_TYPE_BCDMA: - ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2); + ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2) + + BCDMA_CAP3_HBCHAN_CNT(cap3) + + BCDMA_CAP3_UBCHAN_CNT(cap3); ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2); ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2); ud->rflow_cnt = ud->rchan_cnt; diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile index ed6d0b7e07b3..85174e25d62a 100644 --- a/drivers/edac/Makefile +++ b/drivers/edac/Makefile @@ -54,11 +54,13 @@ obj-$(CONFIG_EDAC_MPC85XX) += mpc85xx_edac_mod.o layerscape_edac_mod-y := fsl_ddr_edac.o layerscape_edac.o obj-$(CONFIG_EDAC_LAYERSCAPE) += layerscape_edac_mod.o -skx_edac-y := skx_common.o skx_base.o -obj-$(CONFIG_EDAC_SKX) += skx_edac.o +skx_edac_common-y := skx_common.o -i10nm_edac-y := skx_common.o i10nm_base.o -obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o +skx_edac-y := skx_base.o +obj-$(CONFIG_EDAC_SKX) += skx_edac.o skx_edac_common.o + +i10nm_edac-y := i10nm_base.o +obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o obj-$(CONFIG_EDAC_CELL) += cell_edac.o obj-$(CONFIG_EDAC_PPC4XX) += ppc4xx_edac.o diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c index c46880a934da..74c5aad1f608 100644 --- a/drivers/edac/igen6_edac.c +++ b/drivers/edac/igen6_edac.c @@ -245,7 +245,7 @@ static u64 ehl_err_addr_to_imc_addr(u64 eaddr, int mc) if (igen6_tom <= _4GB) return eaddr + igen6_tolud - _4GB; - if (eaddr < _4GB) + if (eaddr >= igen6_tom) return eaddr + igen6_tolud - igen6_tom; return eaddr; diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c index f0f8e98f6efb..e218909f9f9e 100644 --- a/drivers/edac/skx_common.c +++ b/drivers/edac/skx_common.c @@ -48,7 +48,7 @@ static u64 skx_tolm, skx_tohm; static LIST_HEAD(dev_edac_list); static bool skx_mem_cfg_2lm; -int __init skx_adxl_get(void) +int skx_adxl_get(void) { const char * const *names; int i, j; @@ -110,12 +110,14 @@ err: return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_adxl_get); -void __exit skx_adxl_put(void) +void skx_adxl_put(void) { kfree(adxl_values); kfree(adxl_msg); } +EXPORT_SYMBOL_GPL(skx_adxl_put); static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem) { @@ -187,12 +189,14 @@ void skx_set_mem_cfg(bool mem_cfg_2lm) { skx_mem_cfg_2lm = mem_cfg_2lm; } +EXPORT_SYMBOL_GPL(skx_set_mem_cfg); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log) { driver_decode = decode; skx_show_retry_rd_err_log = show_retry_log; } +EXPORT_SYMBOL_GPL(skx_set_decode); int skx_get_src_id(struct skx_dev *d, int off, u8 *id) { @@ -206,6 +210,7 @@ int skx_get_src_id(struct skx_dev *d, int off, u8 *id) *id = GET_BITFIELD(reg, 12, 14); return 0; } +EXPORT_SYMBOL_GPL(skx_get_src_id); int skx_get_node_id(struct skx_dev *d, u8 *id) { @@ -219,6 +224,7 @@ int skx_get_node_id(struct skx_dev *d, u8 *id) *id = GET_BITFIELD(reg, 0, 2); return 0; } +EXPORT_SYMBOL_GPL(skx_get_node_id); static int get_width(u32 mtr) { @@ -284,6 +290,7 @@ int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list) *list = &dev_edac_list; return ndev; } +EXPORT_SYMBOL_GPL(skx_get_all_bus_mappings); int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm) { @@ -323,6 +330,7 @@ fail: pci_dev_put(pdev); return -ENODEV; } +EXPORT_SYMBOL_GPL(skx_get_hi_lo); static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add, int minval, int maxval, const char *name) @@ -394,6 +402,7 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm, return 1; } +EXPORT_SYMBOL_GPL(skx_get_dimm_info); int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc, int chan, int dimmno, const char *mod_str) @@ -442,6 +451,7 @@ unknown_size: return (size == 0 || size == ~0ull) ? 0 : 1; } +EXPORT_SYMBOL_GPL(skx_get_nvdimm_info); int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev, const char *ctl_name, const char *mod_str, @@ -512,6 +522,7 @@ fail0: imc->mci = NULL; return rc; } +EXPORT_SYMBOL_GPL(skx_register_mci); static void skx_unregister_mci(struct skx_imc *imc) { @@ -694,6 +705,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val, mce->kflags |= MCE_HANDLED_EDAC; return NOTIFY_DONE; } +EXPORT_SYMBOL_GPL(skx_mce_check_error); void skx_remove(void) { @@ -731,3 +743,8 @@ void skx_remove(void) kfree(d); } } +EXPORT_SYMBOL_GPL(skx_remove); + +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Tony Luck"); +MODULE_DESCRIPTION("MC Driver for Intel server processors"); diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h index 0cbadd3d2cd3..c0c174c101d2 100644 --- a/drivers/edac/skx_common.h +++ b/drivers/edac/skx_common.h @@ -178,8 +178,8 @@ typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci, typedef bool (*skx_decode_f)(struct decoded_addr *res); typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len, bool scrub_err); -int __init skx_adxl_get(void); -void __exit skx_adxl_put(void); +int skx_adxl_get(void); +void skx_adxl_put(void); void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log); void skx_set_mem_cfg(bool mem_cfg_2lm); diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c index f7d37c282819..e7c18bb61f81 100644 --- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -9,6 +9,8 @@ #include #include #include +#include +#include #include #include #include @@ -300,6 +302,7 @@ struct synps_ecc_status { /** * struct synps_edac_priv - DDR memory controller private instance data. * @baseaddr: Base address of the DDR controller. + * @reglock: Concurrent CSRs access lock. * @message: Buffer for framing the event specific info. * @stat: ECC status information. * @p_data: Platform data. @@ -314,6 +317,7 @@ struct synps_ecc_status { */ struct synps_edac_priv { void __iomem *baseaddr; + spinlock_t reglock; char message[SYNPS_EDAC_MSG_SIZE]; struct synps_ecc_status stat; const struct synps_platform_data *p_data; @@ -335,6 +339,7 @@ struct synps_edac_priv { * @get_mtype: Get mtype. * @get_dtype: Get dtype. * @get_ecc_state: Get ECC state. + * @get_mem_info: Get EDAC memory info * @quirks: To differentiate IPs. */ struct synps_platform_data { @@ -342,6 +347,9 @@ struct synps_platform_data { enum mem_type (*get_mtype)(const void __iomem *base); enum dev_type (*get_dtype)(const void __iomem *base); bool (*get_ecc_state)(void __iomem *base); +#ifdef CONFIG_EDAC_DEBUG + u64 (*get_mem_info)(struct synps_edac_priv *priv); +#endif int quirks; }; @@ -400,6 +408,25 @@ out: return 0; } +#ifdef CONFIG_EDAC_DEBUG +/** + * zynqmp_get_mem_info - Get the current memory info. + * @priv: DDR memory controller private instance data. + * + * Return: host interface address. + */ +static u64 zynqmp_get_mem_info(struct synps_edac_priv *priv) +{ + u64 hif_addr = 0, linear_addr; + + linear_addr = priv->poison_addr; + if (linear_addr >= SZ_32G) + linear_addr = linear_addr - SZ_32G + SZ_2G; + hif_addr = linear_addr >> 3; + return hif_addr; +} +#endif + /** * zynqmp_get_error_info - Get the current ECC error info. * @priv: DDR memory controller private instance data. @@ -409,7 +436,8 @@ out: static int zynqmp_get_error_info(struct synps_edac_priv *priv) { struct synps_ecc_status *p; - u32 regval, clearval = 0; + u32 regval, clearval; + unsigned long flags; void __iomem *base; base = priv->baseaddr; @@ -453,10 +481,14 @@ ue_err: p->ueinfo.blknr = (regval & ECC_CEADDR1_BLKNR_MASK); p->ueinfo.data = readl(base + ECC_UESYND0_OFST); out: - clearval = ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT; - clearval |= ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT; + spin_lock_irqsave(&priv->reglock, flags); + + clearval = readl(base + ECC_CLR_OFST) | + ECC_CTRL_CLR_CE_ERR | ECC_CTRL_CLR_CE_ERRCNT | + ECC_CTRL_CLR_UE_ERR | ECC_CTRL_CLR_UE_ERRCNT; writel(clearval, base + ECC_CLR_OFST); - writel(0x0, base + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); return 0; } @@ -516,24 +548,41 @@ static void handle_error(struct mem_ctl_info *mci, struct synps_ecc_status *p) static void enable_intr(struct synps_edac_priv *priv) { + unsigned long flags; + /* Enable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(DDR_UE_MASK | DDR_CE_MASK, - priv->baseaddr + ECC_CLR_OFST); - else + if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) { writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, priv->baseaddr + DDR_QOS_IRQ_EN_OFST); + return; + } + + spin_lock_irqsave(&priv->reglock, flags); + + writel(DDR_UE_MASK | DDR_CE_MASK, + priv->baseaddr + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); } static void disable_intr(struct synps_edac_priv *priv) { + unsigned long flags; + /* Disable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(0x0, priv->baseaddr + ECC_CLR_OFST); - else + if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) { writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, priv->baseaddr + DDR_QOS_IRQ_DB_OFST); + + return; + } + + spin_lock_irqsave(&priv->reglock, flags); + + writel(0, priv->baseaddr + ECC_CLR_OFST); + + spin_unlock_irqrestore(&priv->reglock, flags); } /** @@ -577,8 +626,6 @@ static irqreturn_t intr_handler(int irq, void *dev_id) /* v3.0 of the controller does not have this register */ if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) writel(regval, priv->baseaddr + DDR_QOS_IRQ_STAT_OFST); - else - enable_intr(priv); return IRQ_HANDLED; } @@ -900,6 +947,9 @@ static const struct synps_platform_data zynqmp_edac_def = { .get_mtype = zynqmp_get_mtype, .get_dtype = zynqmp_get_dtype, .get_ecc_state = zynqmp_get_ecc_state, +#ifdef CONFIG_EDAC_DEBUG + .get_mem_info = zynqmp_get_mem_info, +#endif .quirks = (DDR_ECC_INTR_SUPPORT #ifdef CONFIG_EDAC_DEBUG | DDR_ECC_DATA_POISON_SUPPORT @@ -953,10 +1003,16 @@ MODULE_DEVICE_TABLE(of, synps_edac_match); static void ddr_poison_setup(struct synps_edac_priv *priv) { int col = 0, row = 0, bank = 0, bankgrp = 0, rank = 0, regval; + const struct synps_platform_data *p_data; int index; ulong hif_addr = 0; - hif_addr = priv->poison_addr >> 3; + p_data = priv->p_data; + + if (p_data->get_mem_info) + hif_addr = p_data->get_mem_info(priv); + else + hif_addr = priv->poison_addr >> 3; for (index = 0; index < DDR_MAX_ROW_SHIFT; index++) { if (priv->row_shift[index]) @@ -1360,6 +1416,7 @@ static int mc_probe(struct platform_device *pdev) priv = mci->pvt_info; priv->baseaddr = baseaddr; priv->p_data = p_data; + spin_lock_init(&priv->reglock); mc_init(mci, pdev); diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c index 2a7aeab40e54..f5f6ec83d3e1 100644 --- a/drivers/firmware/arm_scmi/optee.c +++ b/drivers/firmware/arm_scmi/optee.c @@ -467,6 +467,13 @@ static int scmi_optee_chan_free(int id, void *p, void *data) struct scmi_chan_info *cinfo = p; struct scmi_optee_channel *channel = cinfo->transport_info; + /* + * Different protocols might share the same chan info, so a previous + * call might have already freed the structure. + */ + if (!channel) + return 0; + mutex_lock(&scmi_optee_private->mu); list_del(&channel->link); mutex_unlock(&scmi_optee_private->mu); diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c index 64ed9d3f5d5d..cf4f4da0cb87 100644 --- a/drivers/firmware/cirrus/cs_dsp.c +++ b/drivers/firmware/cirrus/cs_dsp.c @@ -490,7 +490,7 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp) { cs_dsp_debugfs_clear(dsp); debugfs_remove_recursive(dsp->debugfs_root); - dsp->debugfs_root = NULL; + dsp->debugfs_root = ERR_PTR(-ENODEV); } EXPORT_SYMBOL_GPL(cs_dsp_cleanup_debugfs); #else @@ -764,6 +764,9 @@ int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, lockdep_assert_held(&ctl->dsp->pwr_lock); + if (ctl->flags && !(ctl->flags & WMFW_CTL_FLAG_WRITEABLE)) + return -EPERM; + if (len + off * sizeof(u32) > ctl->len) return -EINVAL; @@ -1014,9 +1017,16 @@ struct cs_dsp_coeff_parsed_coeff { int len; }; -static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) +static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, unsigned int avail, + const u8 **str) { - int length; + int length, total_field_len; + + /* String fields are at least one __le32 */ + if (sizeof(__le32) > avail) { + *pos = NULL; + return 0; + } switch (bytes) { case 1: @@ -1029,10 +1039,16 @@ static int cs_dsp_coeff_parse_string(int bytes, const u8 **pos, const u8 **str) return 0; } + total_field_len = ((length + bytes) + 3) & ~0x03; + if ((unsigned int)total_field_len > avail) { + *pos = NULL; + return 0; + } + if (str) *str = *pos + bytes; - *pos += ((length + bytes) + 3) & ~0x03; + *pos += total_field_len; return length; } @@ -1057,71 +1073,134 @@ static int cs_dsp_coeff_parse_int(int bytes, const u8 **pos) return val; } -static inline void cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_alg *blk) +static int cs_dsp_coeff_parse_alg(struct cs_dsp *dsp, + const struct wmfw_region *region, + struct cs_dsp_coeff_parsed_alg *blk) { const struct wmfw_adsp_alg_data *raw; + unsigned int data_len = le32_to_cpu(region->len); + unsigned int pos; + const u8 *tmp; + + raw = (const struct wmfw_adsp_alg_data *)region->data; switch (dsp->fw_ver) { case 0: case 1: - raw = (const struct wmfw_adsp_alg_data *)*data; - *data = raw->data; + if (sizeof(*raw) > data_len) + return -EOVERFLOW; blk->id = le32_to_cpu(raw->id); blk->name = raw->name; - blk->name_len = strlen(raw->name); + blk->name_len = strnlen(raw->name, ARRAY_SIZE(raw->name)); blk->ncoeff = le32_to_cpu(raw->ncoeff); + + pos = sizeof(*raw); break; default: - blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), data); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), data, + if (sizeof(raw->id) > data_len) + return -EOVERFLOW; + + tmp = region->data; + blk->id = cs_dsp_coeff_parse_int(sizeof(raw->id), &tmp); + pos = tmp - region->data; + + tmp = ®ion->data[pos]; + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, &blk->name); - cs_dsp_coeff_parse_string(sizeof(u16), data, NULL); - blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), data); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u16), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + if (sizeof(raw->ncoeff) > (data_len - pos)) + return -EOVERFLOW; + + blk->ncoeff = cs_dsp_coeff_parse_int(sizeof(raw->ncoeff), &tmp); + pos += sizeof(raw->ncoeff); break; } + if ((int)blk->ncoeff < 0) + return -EOVERFLOW; + cs_dsp_dbg(dsp, "Algorithm ID: %#x\n", blk->id); cs_dsp_dbg(dsp, "Algorithm name: %.*s\n", blk->name_len, blk->name); cs_dsp_dbg(dsp, "# of coefficient descriptors: %#x\n", blk->ncoeff); + + return pos; } -static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, - struct cs_dsp_coeff_parsed_coeff *blk) +static int cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, + const struct wmfw_region *region, + unsigned int pos, + struct cs_dsp_coeff_parsed_coeff *blk) { const struct wmfw_adsp_coeff_data *raw; + unsigned int data_len = le32_to_cpu(region->len); + unsigned int blk_len, blk_end_pos; const u8 *tmp; - int length; + + raw = (const struct wmfw_adsp_coeff_data *)®ion->data[pos]; + if (sizeof(raw->hdr) > (data_len - pos)) + return -EOVERFLOW; + + blk_len = le32_to_cpu(raw->hdr.size); + if (blk_len > S32_MAX) + return -EOVERFLOW; + + if (blk_len > (data_len - pos - sizeof(raw->hdr))) + return -EOVERFLOW; + + blk_end_pos = pos + sizeof(raw->hdr) + blk_len; + + blk->offset = le16_to_cpu(raw->hdr.offset); + blk->mem_type = le16_to_cpu(raw->hdr.type); switch (dsp->fw_ver) { case 0: case 1: - raw = (const struct wmfw_adsp_coeff_data *)*data; - *data = *data + sizeof(raw->hdr) + le32_to_cpu(raw->hdr.size); + if (sizeof(*raw) > (data_len - pos)) + return -EOVERFLOW; - blk->offset = le16_to_cpu(raw->hdr.offset); - blk->mem_type = le16_to_cpu(raw->hdr.type); blk->name = raw->name; - blk->name_len = strlen(raw->name); + blk->name_len = strnlen(raw->name, ARRAY_SIZE(raw->name)); blk->ctl_type = le16_to_cpu(raw->ctl_type); blk->flags = le16_to_cpu(raw->flags); blk->len = le32_to_cpu(raw->len); break; default: - tmp = *data; - blk->offset = cs_dsp_coeff_parse_int(sizeof(raw->hdr.offset), &tmp); - blk->mem_type = cs_dsp_coeff_parse_int(sizeof(raw->hdr.type), &tmp); - length = cs_dsp_coeff_parse_int(sizeof(raw->hdr.size), &tmp); - blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, + pos += sizeof(raw->hdr); + tmp = ®ion->data[pos]; + blk->name_len = cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, &blk->name); - cs_dsp_coeff_parse_string(sizeof(u8), &tmp, NULL); - cs_dsp_coeff_parse_string(sizeof(u16), &tmp, NULL); - blk->ctl_type = cs_dsp_coeff_parse_int(sizeof(raw->ctl_type), &tmp); - blk->flags = cs_dsp_coeff_parse_int(sizeof(raw->flags), &tmp); - blk->len = cs_dsp_coeff_parse_int(sizeof(raw->len), &tmp); + if (!tmp) + return -EOVERFLOW; - *data = *data + sizeof(raw->hdr) + length; + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u8), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + cs_dsp_coeff_parse_string(sizeof(u16), &tmp, data_len - pos, NULL); + if (!tmp) + return -EOVERFLOW; + + pos = tmp - region->data; + if (sizeof(raw->ctl_type) + sizeof(raw->flags) + sizeof(raw->len) > + (data_len - pos)) + return -EOVERFLOW; + + blk->ctl_type = cs_dsp_coeff_parse_int(sizeof(raw->ctl_type), &tmp); + pos += sizeof(raw->ctl_type); + blk->flags = cs_dsp_coeff_parse_int(sizeof(raw->flags), &tmp); + pos += sizeof(raw->flags); + blk->len = cs_dsp_coeff_parse_int(sizeof(raw->len), &tmp); break; } @@ -1131,6 +1210,8 @@ static inline void cs_dsp_coeff_parse_coeff(struct cs_dsp *dsp, const u8 **data, cs_dsp_dbg(dsp, "\tCoefficient flags: %#x\n", blk->flags); cs_dsp_dbg(dsp, "\tALSA control type: %#x\n", blk->ctl_type); cs_dsp_dbg(dsp, "\tALSA control len: %#x\n", blk->len); + + return blk_end_pos; } static int cs_dsp_check_coeff_flags(struct cs_dsp *dsp, @@ -1154,12 +1235,16 @@ static int cs_dsp_parse_coeff(struct cs_dsp *dsp, struct cs_dsp_alg_region alg_region = {}; struct cs_dsp_coeff_parsed_alg alg_blk; struct cs_dsp_coeff_parsed_coeff coeff_blk; - const u8 *data = region->data; - int i, ret; + int i, pos, ret; + + pos = cs_dsp_coeff_parse_alg(dsp, region, &alg_blk); + if (pos < 0) + return pos; - cs_dsp_coeff_parse_alg(dsp, &data, &alg_blk); for (i = 0; i < alg_blk.ncoeff; i++) { - cs_dsp_coeff_parse_coeff(dsp, &data, &coeff_blk); + pos = cs_dsp_coeff_parse_coeff(dsp, region, pos, &coeff_blk); + if (pos < 0) + return pos; switch (coeff_blk.ctl_type) { case WMFW_CTL_TYPE_BYTES: @@ -1228,6 +1313,10 @@ static unsigned int cs_dsp_adsp1_parse_sizes(struct cs_dsp *dsp, const struct wmfw_adsp1_sizes *adsp1_sizes; adsp1_sizes = (void *)&firmware->data[pos]; + if (sizeof(*adsp1_sizes) > firmware->size - pos) { + cs_dsp_err(dsp, "%s: file truncated\n", file); + return 0; + } cs_dsp_dbg(dsp, "%s: %d DM, %d PM, %d ZM\n", file, le32_to_cpu(adsp1_sizes->dm), le32_to_cpu(adsp1_sizes->pm), @@ -1244,6 +1333,10 @@ static unsigned int cs_dsp_adsp2_parse_sizes(struct cs_dsp *dsp, const struct wmfw_adsp2_sizes *adsp2_sizes; adsp2_sizes = (void *)&firmware->data[pos]; + if (sizeof(*adsp2_sizes) > firmware->size - pos) { + cs_dsp_err(dsp, "%s: file truncated\n", file); + return 0; + } cs_dsp_dbg(dsp, "%s: %d XM, %d YM %d PM, %d ZM\n", file, le32_to_cpu(adsp2_sizes->xm), le32_to_cpu(adsp2_sizes->ym), @@ -1283,7 +1376,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, struct regmap *regmap = dsp->regmap; unsigned int pos = 0; const struct wmfw_header *header; - const struct wmfw_adsp1_sizes *adsp1_sizes; const struct wmfw_footer *footer; const struct wmfw_region *region; const struct cs_dsp_region *mem; @@ -1296,10 +1388,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, ret = -EINVAL; - pos = sizeof(*header) + sizeof(*adsp1_sizes) + sizeof(*footer); - if (pos >= firmware->size) { - cs_dsp_err(dsp, "%s: file too short, %zu bytes\n", - file, firmware->size); + if (sizeof(*header) >= firmware->size) { + ret = -EOVERFLOW; goto out_fw; } @@ -1327,22 +1417,36 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, pos = sizeof(*header); pos = dsp->ops->parse_sizes(dsp, file, pos, firmware); + if ((pos == 0) || (sizeof(*footer) > firmware->size - pos)) { + ret = -EOVERFLOW; + goto out_fw; + } footer = (void *)&firmware->data[pos]; pos += sizeof(*footer); if (le32_to_cpu(header->len) != pos) { - cs_dsp_err(dsp, "%s: unexpected header length %d\n", - file, le32_to_cpu(header->len)); + ret = -EOVERFLOW; goto out_fw; } cs_dsp_dbg(dsp, "%s: timestamp %llu\n", file, le64_to_cpu(footer->timestamp)); - while (pos < firmware->size && - sizeof(*region) < firmware->size - pos) { + while (pos < firmware->size) { + /* Is there enough data for a complete block header? */ + if (sizeof(*region) > firmware->size - pos) { + ret = -EOVERFLOW; + goto out_fw; + } + region = (void *)&(firmware->data[pos]); + + if (le32_to_cpu(region->len) > firmware->size - pos - sizeof(*region)) { + ret = -EOVERFLOW; + goto out_fw; + } + region_name = "Unknown"; reg = 0; text = NULL; @@ -1399,16 +1503,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware, regions, le32_to_cpu(region->len), offset, region_name); - if (le32_to_cpu(region->len) > - firmware->size - pos - sizeof(*region)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, regions, region_name, - le32_to_cpu(region->len), firmware->size); - ret = -EINVAL; - goto out_fw; - } - if (text) { memcpy(text, region->data, le32_to_cpu(region->len)); cs_dsp_info(dsp, "%s: %s\n", file, text); @@ -1459,6 +1553,9 @@ out_fw: cs_dsp_buf_free(&buf_list); kfree(text); + if (ret == -EOVERFLOW) + cs_dsp_err(dsp, "%s: file content overflows file data\n", file); + return ret; } @@ -2026,10 +2123,20 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware pos = le32_to_cpu(hdr->len); blocks = 0; - while (pos < firmware->size && - sizeof(*blk) < firmware->size - pos) { + while (pos < firmware->size) { + /* Is there enough data for a complete block header? */ + if (sizeof(*blk) > firmware->size - pos) { + ret = -EOVERFLOW; + goto out_fw; + } + blk = (void *)(&firmware->data[pos]); + if (le32_to_cpu(blk->len) > firmware->size - pos - sizeof(*blk)) { + ret = -EOVERFLOW; + goto out_fw; + } + type = le16_to_cpu(blk->type); offset = le16_to_cpu(blk->offset); version = le32_to_cpu(blk->ver) >> 8; @@ -2125,17 +2232,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware } if (reg) { - if (le32_to_cpu(blk->len) > - firmware->size - pos - sizeof(*blk)) { - cs_dsp_err(dsp, - "%s.%d: %s region len %d bytes exceeds file length %zu\n", - file, blocks, region_name, - le32_to_cpu(blk->len), - firmware->size); - ret = -EINVAL; - goto out_fw; - } - buf = cs_dsp_buf_alloc(blk->data, le32_to_cpu(blk->len), &buf_list); @@ -2175,6 +2271,10 @@ out_fw: regmap_async_complete(regmap); cs_dsp_buf_free(&buf_list); kfree(text); + + if (ret == -EOVERFLOW) + cs_dsp_err(dsp, "%s: file content overflows file data\n", file); + return ret; } @@ -2203,6 +2303,11 @@ static int cs_dsp_common_init(struct cs_dsp *dsp) mutex_init(&dsp->pwr_lock); +#ifdef CONFIG_DEBUG_FS + /* Ensure this is invalid if client never provides a debugfs root */ + dsp->debugfs_root = ERR_PTR(-ENODEV); +#endif + return 0; } diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c index 7acbac16eae0..95da291c3083 100644 --- a/drivers/firmware/efi/libstub/tpm.c +++ b/drivers/firmware/efi/libstub/tpm.c @@ -115,7 +115,7 @@ void efi_retrieve_tpm2_eventlog(void) } /* Allocate space for the logs and copy them. */ - status = efi_bs_call(allocate_pool, EFI_LOADER_DATA, + status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY, sizeof(*log_tbl) + log_size, (void **)&log_tbl); if (status != EFI_SUCCESS) { diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c index f7eb389aeec0..b8246fc7f412 100644 --- a/drivers/firmware/efi/libstub/x86-stub.c +++ b/drivers/firmware/efi/libstub/x86-stub.c @@ -435,11 +435,12 @@ void __noreturn efi_stub_entry(efi_handle_t handle, efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_system_table_t *sys_table_arg) { - static struct boot_params boot_params __page_aligned_bss; - struct setup_header *hdr = &boot_params.hdr; efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID; + struct boot_params *boot_params; + struct setup_header *hdr; int options_size = 0; efi_status_t status; + unsigned long alloc; char *cmdline_ptr; if (efi_is_native()) @@ -457,6 +458,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, efi_exit(handle, status); } + status = efi_allocate_pages(PARAM_SIZE, &alloc, ULONG_MAX); + if (status != EFI_SUCCESS) + efi_exit(handle, status); + + boot_params = memset((void *)alloc, 0x0, PARAM_SIZE); + hdr = &boot_params->hdr; + /* Assign the setup_header fields that the kernel actually cares about */ hdr->root_flags = 1; hdr->vid_mode = 0xffff; @@ -466,17 +474,16 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle, /* Convert unicode cmdline to ascii */ cmdline_ptr = efi_convert_cmdline(image, &options_size); - if (!cmdline_ptr) - goto fail; + if (!cmdline_ptr) { + efi_free(PARAM_SIZE, alloc); + efi_exit(handle, EFI_OUT_OF_RESOURCES); + } efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr, - &boot_params.ext_cmd_line_ptr); + &boot_params->ext_cmd_line_ptr); - efi_stub_entry(handle, sys_table_arg, &boot_params); + efi_stub_entry(handle, sys_table_arg, boot_params); /* not reached */ - -fail: - efi_exit(handle, status); } static void add_e820ext(struct boot_params *params, diff --git a/drivers/firmware/efi/libstub/zboot.lds b/drivers/firmware/efi/libstub/zboot.lds index 93d33f68333b..a7fffbad6d46 100644 --- a/drivers/firmware/efi/libstub/zboot.lds +++ b/drivers/firmware/efi/libstub/zboot.lds @@ -34,6 +34,7 @@ SECTIONS } /DISCARD/ : { + *(.discard .discard.*) *(.modinfo .init.modinfo) } } diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c index 037db21de510..f0c3980b2864 100644 --- a/drivers/firmware/tegra/bpmp.c +++ b/drivers/firmware/tegra/bpmp.c @@ -25,12 +25,6 @@ #define MSG_RING BIT(1) #define TAG_SZ 32 -static inline struct tegra_bpmp * -mbox_client_to_bpmp(struct mbox_client *client) -{ - return container_of(client, struct tegra_bpmp, mbox.client); -} - static inline const struct tegra_bpmp_ops * channel_to_ops(struct tegra_bpmp_channel *channel) { diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c index c2d34dc8ba46..c3d49fcc5330 100644 --- a/drivers/firmware/turris-mox-rwtm.c +++ b/drivers/firmware/turris-mox-rwtm.c @@ -2,7 +2,7 @@ /* * Turris Mox rWTM firmware driver * - * Copyright (C) 2019 Marek Behún + * Copyright (C) 2019, 2024 Marek Behún */ #include @@ -174,6 +174,9 @@ static void mox_rwtm_rx_callback(struct mbox_client *cl, void *data) struct mox_rwtm *rwtm = dev_get_drvdata(cl->dev); struct armada_37xx_rwtm_rx_msg *msg = data; + if (completion_done(&rwtm->cmd_done)) + return; + rwtm->reply = *msg; complete(&rwtm->cmd_done); } @@ -199,9 +202,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_BOARD_INFO, reply->retval); if (ret == -ENODATA) { @@ -235,9 +237,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; ret = mox_get_status(MBOX_CMD_ECDSA_PUB_KEY, reply->retval); if (ret == -ENODATA) { @@ -274,9 +275,8 @@ static int check_get_random_support(struct mox_rwtm *rwtm) if (ret < 0) return ret; - ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2); - if (ret < 0) - return ret; + if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2)) + return -ETIMEDOUT; return mox_get_status(MBOX_CMD_GET_RANDOM, rwtm->reply.retval); } @@ -499,6 +499,7 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) platform_set_drvdata(pdev, rwtm); mutex_init(&rwtm->busy); + init_completion(&rwtm->cmd_done); rwtm->mbox_client.dev = dev; rwtm->mbox_client.rx_callback = mox_rwtm_rx_callback; @@ -512,8 +513,6 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev) goto remove_files; } - init_completion(&rwtm->cmd_done); - ret = mox_get_board_info(rwtm); if (ret < 0) dev_warn(dev, "Cannot read board information: %i\n", ret); diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c index 42d3e1cf7352..21deb228c7d7 100644 --- a/drivers/gpio/gpio-aspeed.c +++ b/drivers/gpio/gpio-aspeed.c @@ -404,6 +404,8 @@ static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset, gpio->dcache[GPIO_BANK(offset)] = reg; iowrite32(reg, addr); + /* Flush write */ + ioread32(addr); } static void aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset, @@ -1154,7 +1156,7 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev) if (!gpio_id) return -EINVAL; - gpio->clk = of_clk_get(pdev->dev.of_node, 0); + gpio->clk = devm_clk_get_enabled(&pdev->dev, NULL); if (IS_ERR(gpio->clk)) { dev_warn(&pdev->dev, "Failed to get clock from devicetree, debouncing disabled\n"); diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c index 206829165fc5..cac9737b25a5 100644 --- a/drivers/gpio/gpio-davinci.c +++ b/drivers/gpio/gpio-davinci.c @@ -295,7 +295,7 @@ static int davinci_gpio_probe(struct platform_device *pdev) * serve as EDMA event triggers. */ -static void gpio_irq_disable(struct irq_data *d) +static void gpio_irq_mask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -304,7 +304,7 @@ static void gpio_irq_disable(struct irq_data *d) writel_relaxed(mask, &g->clr_rising); } -static void gpio_irq_enable(struct irq_data *d) +static void gpio_irq_unmask(struct irq_data *d) { struct davinci_gpio_regs __iomem *g = irq2regs(d); uintptr_t mask = (uintptr_t)irq_data_get_irq_handler_data(d); @@ -330,8 +330,8 @@ static int gpio_irq_type(struct irq_data *d, unsigned trigger) static struct irq_chip gpio_irqchip = { .name = "GPIO", - .irq_enable = gpio_irq_enable, - .irq_disable = gpio_irq_disable, + .irq_unmask = gpio_irq_unmask, + .irq_mask = gpio_irq_mask, .irq_set_type = gpio_irq_type, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE, }; diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c index bf21803a0036..9ce54bf2030d 100644 --- a/drivers/gpio/gpio-pca953x.c +++ b/drivers/gpio/gpio-pca953x.c @@ -768,6 +768,8 @@ static void pca953x_irq_bus_sync_unlock(struct irq_data *d) int level; if (chip->driver_data & PCA_PCAL) { + guard(mutex)(&chip->i2c_lock); + /* Enable latch on interrupt-enabled inputs */ pca953x_write_regs(chip, PCAL953X_IN_LATCH, chip->irq_mask); diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c index a0d69387c153..2f3c9ebfa78d 100644 --- a/drivers/gpio/gpio-zynqmp-modepin.c +++ b/drivers/gpio/gpio-zynqmp-modepin.c @@ -146,6 +146,7 @@ static const struct of_device_id modepin_platform_id[] = { { .compatible = "xlnx,zynqmp-gpio-modepin", }, { } }; +MODULE_DEVICE_TABLE(of, modepin_platform_id); static struct platform_driver modepin_platform_driver = { .driver = { diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c index be51bd00d2fd..55f640ef3fee 100644 --- a/drivers/gpio/gpiolib-cdev.c +++ b/drivers/gpio/gpiolib-cdev.c @@ -1523,12 +1523,14 @@ static long linereq_set_config_unlocked(struct linereq *lr, line = &lr->lines[i]; desc = lr->lines[i].desc; flags = gpio_v2_line_config_flags(lc, i); + /* + * Lines not explicitly reconfigured as input or output + * are left unchanged. + */ + if (!(flags & GPIO_V2_LINE_DIRECTION_FLAGS)) + continue; gpio_v2_line_config_flags_to_desc_flags(flags, &desc->flags); edflags = flags & GPIO_V2_LINE_EDGE_DETECTOR_FLAGS; - /* - * Lines have to be requested explicitly for input - * or output, else the line will be treated "as is". - */ if (flags & GPIO_V2_LINE_FLAG_OUTPUT) { int val = gpio_v2_line_config_output_value(lc, i); @@ -1536,7 +1538,7 @@ static long linereq_set_config_unlocked(struct linereq *lr, ret = gpiod_direction_output(desc, val); if (ret) return ret; - } else if (flags & GPIO_V2_LINE_FLAG_INPUT) { + } else { ret = gpiod_direction_input(desc); if (ret) return ret; diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c index 9d8c78312403..a0c1dabd2939 100644 --- a/drivers/gpio/gpiolib.c +++ b/drivers/gpio/gpiolib.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -146,7 +147,7 @@ struct gpio_desc *gpiochip_get_desc(struct gpio_chip *gc, if (hwnum >= gdev->ngpio) return ERR_PTR(-EINVAL); - return &gdev->descs[hwnum]; + return &gdev->descs[array_index_nospec(hwnum, gdev->ngpio)]; } EXPORT_SYMBOL_GPL(gpiochip_get_desc); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c index e32bd990800d..d967fba2e85e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c @@ -107,6 +107,7 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, struct acpi_buffer *params) { acpi_status status; + union acpi_object *obj; union acpi_object atif_arg_elements[2]; struct acpi_object_list atif_arg; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; @@ -129,16 +130,24 @@ static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif, status = acpi_evaluate_object(atif->handle, NULL, &atif_arg, &buffer); + obj = (union acpi_object *)buffer.pointer; - /* Fail only if calling the method fails and ATIF is supported */ + /* Fail if calling the method fails and ATIF is supported */ if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) { DRM_DEBUG_DRIVER("failed to evaluate ATIF got %s\n", acpi_format_exception(status)); - kfree(buffer.pointer); + kfree(obj); return NULL; } - return buffer.pointer; + if (obj->type != ACPI_TYPE_BUFFER) { + DRM_DEBUG_DRIVER("bad object returned from ATIF: %d\n", + obj->type); + kfree(obj); + return NULL; + } + + return obj; } /** diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c index a4d65973bf7c..80771b1480ff 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c @@ -100,6 +100,7 @@ struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock) amdgpu_afmt_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000); amdgpu_afmt_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100); amdgpu_afmt_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000); + res.clock = clock; return res; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h index dbc842590b25..4b694886715c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h @@ -286,6 +286,7 @@ int amdgpu_amdkfd_gpuvm_map_memory_to_gpu(struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv); +int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv); int amdgpu_amdkfd_gpuvm_sync_memory( struct amdgpu_device *adev, struct kgd_mem *mem, bool intr); int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_mem *mem, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index 7d5fbaaba72f..d486f5dc052e 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -719,7 +719,7 @@ kfd_mem_dmaunmap_sg_bo(struct kgd_mem *mem, enum dma_data_direction dir; if (unlikely(!ttm->sg)) { - pr_err("SG Table of BO is UNEXPECTEDLY NULL"); + pr_debug("SG Table of BO is NULL"); return; } @@ -1226,8 +1226,6 @@ static void unmap_bo_from_gpuvm(struct kgd_mem *mem, amdgpu_vm_clear_freed(adev, vm, &bo_va->last_pt_update); amdgpu_sync_fence(sync, bo_va->last_pt_update); - - kfd_mem_dmaunmap_attachment(mem, entry); } static int update_gpuvm_pte(struct kgd_mem *mem, @@ -1282,6 +1280,7 @@ static int map_bo_to_gpuvm(struct kgd_mem *mem, update_gpuvm_pte_failed: unmap_bo_from_gpuvm(mem, entry, sync); + kfd_mem_dmaunmap_attachment(mem, entry); return ret; } @@ -1852,8 +1851,10 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( mem->va + bo_size * (1 + mem->aql_queue)); /* Remove from VM internal data structures */ - list_for_each_entry_safe(entry, tmp, &mem->attachments, list) + list_for_each_entry_safe(entry, tmp, &mem->attachments, list) { + kfd_mem_dmaunmap_attachment(mem, entry); kfd_mem_detach(entry); + } ret = unreserve_bo_and_vms(&ctx, false, false); @@ -2024,6 +2025,37 @@ out: return ret; } +int amdgpu_amdkfd_gpuvm_dmaunmap_mem(struct kgd_mem *mem, void *drm_priv) +{ + struct kfd_mem_attachment *entry; + struct amdgpu_vm *vm; + int ret; + + vm = drm_priv_to_vm(drm_priv); + + mutex_lock(&mem->lock); + + ret = amdgpu_bo_reserve(mem->bo, true); + if (ret) + goto out; + + list_for_each_entry(entry, &mem->attachments, list) { + if (entry->bo_va->base.vm != vm) + continue; + if (entry->bo_va->base.bo->tbo.ttm && + !entry->bo_va->base.bo->tbo.ttm->sg) + continue; + + kfd_mem_dmaunmap_attachment(mem, entry); + } + + amdgpu_bo_unreserve(mem->bo); +out: + mutex_unlock(&mem->lock); + + return ret; +} + int amdgpu_amdkfd_gpuvm_unmap_memory_from_gpu( struct amdgpu_device *adev, struct kgd_mem *mem, void *drm_priv) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c index 9ba4817a9148..816014ea5381 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c @@ -1476,6 +1476,8 @@ int amdgpu_atombios_init_mc_reg_table(struct amdgpu_device *adev, (u32)le32_to_cpu(*((u32 *)reg_data + j)); j++; } else if ((reg_table->mc_reg_address[i].pre_reg_data & LOW_NIBBLE_MASK) == DATA_EQU_PREV) { + if (i == 0) + continue; reg_table->mc_reg_table_entry[num_ranges].mc_data[i] = reg_table->mc_reg_table_entry[num_ranges].mc_data[i - 1]; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index f1a050379190..682de88cf91f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -213,6 +213,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, struct amdgpu_firmware_info *ucode; id = fw_type_convert(cgs_device, type); + if (id >= AMDGPU_UCODE_ID_MAXIMUM) + return -EINVAL; + ucode = &adev->firmware.ucode[id]; if (ucode->fw == NULL) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 133e4e03c143..25cccd080d97 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -257,6 +257,10 @@ static int amdgpu_cs_pass1(struct amdgpu_cs_parser *p, if (size < sizeof(struct drm_amdgpu_bo_list_in)) goto free_partial_kdata; + /* Only a single BO list is allowed to simplify handling. */ + if (p->bo_list) + goto free_partial_kdata; + ret = amdgpu_cs_p1_bo_handles(p, p->chunks[i].kdata); if (ret) goto free_partial_kdata; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c index 1ed2142a6e7b..3898b67c35bc 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c @@ -656,16 +656,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data, switch (args->in.op) { case AMDGPU_CTX_OP_ALLOC_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id); args->out.alloc.ctx_id = id; break; case AMDGPU_CTX_OP_FREE_CTX: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_free(fpriv, id); break; case AMDGPU_CTX_OP_QUERY_STATE: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_QUERY_STATE2: + if (args->in.flags) + return -EINVAL; r = amdgpu_ctx_query2(adev, fpriv, id, &args->out); break; case AMDGPU_CTX_OP_GET_STABLE_PSTATE: diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index 157441dd0704..1d0f6628f1d6 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -3631,6 +3631,7 @@ int amdgpu_device_init(struct amdgpu_device *adev, mutex_init(&adev->grbm_idx_mutex); mutex_init(&adev->mn_lock); mutex_init(&adev->virt.vf_errors.lock); + mutex_init(&adev->virt.rlcg_reg_lock); hash_init(adev->mn_hash); mutex_init(&adev->psp.mutex); mutex_init(&adev->notifier_lock); @@ -4559,7 +4560,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev) shadow = vmbo->shadow; /* No need to recover an evicted BO */ - if (shadow->tbo.resource->mem_type != TTM_PL_TT || + if (!shadow->tbo.resource || + shadow->tbo.resource->mem_type != TTM_PL_TT || shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET || shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM) continue; @@ -5389,7 +5391,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, * to put adev in the 1st position. */ INIT_LIST_HEAD(&device_list); - if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) { + if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1) && hive) { list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) { list_add_tail(&tmp_adev->reset_list, &device_list); if (gpu_reset_for_dev_remove && adev->shutdown) @@ -5815,7 +5817,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev) adev->nbio.funcs->enable_doorbell_interrupt) adev->nbio.funcs->enable_doorbell_interrupt(adev, true); - if (amdgpu_passthrough(adev) && + if (amdgpu_passthrough(adev) && adev->nbio.funcs && adev->nbio.funcs->clear_doorbell_interrupt) adev->nbio.funcs->clear_doorbell_interrupt(adev); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c index aabde6ebb190..cd0bccc95205 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c @@ -873,8 +873,7 @@ static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb) { u64 micro_tile_mode; - /* Zero swizzle mode means linear */ - if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0) + if (AMDGPU_TILING_GET(afb->tiling_flags, ARRAY_MODE) == 1) /* LINEAR_ALIGNED */ return 0; micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE); @@ -998,6 +997,30 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb) block_width = 256 / format_info->cpp[i]; block_height = 1; block_size_log2 = 8; + } else if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) >= AMD_FMT_MOD_TILE_VER_GFX12) { + int swizzle = AMD_FMT_MOD_GET(TILE, modifier); + + switch (swizzle) { + case AMD_FMT_MOD_TILE_GFX12_256B_2D: + block_size_log2 = 8; + break; + case AMD_FMT_MOD_TILE_GFX12_4K_2D: + block_size_log2 = 12; + break; + case AMD_FMT_MOD_TILE_GFX12_64K_2D: + block_size_log2 = 16; + break; + case AMD_FMT_MOD_TILE_GFX12_256K_2D: + block_size_log2 = 18; + break; + default: + drm_dbg_kms(rfb->base.dev, + "Gfx12 swizzle mode with unknown block size: %d\n", swizzle); + return -EINVAL; + } + + get_block_dimensions(block_size_log2, format_info->cpp[i], + &block_width, &block_height); } else { int swizzle = AMD_FMT_MOD_GET(TILE, modifier); @@ -1033,7 +1056,8 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb) return ret; } - if (AMD_FMT_MOD_GET(DCC, modifier)) { + if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) <= AMD_FMT_MOD_TILE_VER_GFX11 && + AMD_FMT_MOD_GET(DCC, modifier)) { if (AMD_FMT_MOD_GET(DCC_RETILE, modifier)) { block_size_log2 = get_dcc_block_size(modifier, false, false); get_block_dimensions(block_size_log2 + 8, format_info->cpp[0], diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c index d6c4293829aa..3e4912f1f92a 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c @@ -179,7 +179,7 @@ static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, * Returns the number of bytes read/written; -errno on error. */ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, - u8 *eeprom_buf, u16 buf_size, bool read) + u8 *eeprom_buf, u32 buf_size, bool read) { const struct i2c_adapter_quirks *quirks = i2c_adap->quirks; u16 limit; @@ -226,7 +226,7 @@ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr, int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes) + u32 bytes) { return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes, true); @@ -234,7 +234,7 @@ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes) + u32 bytes) { return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes, false); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h index 6935adb2be1f..8083b8253ef4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h @@ -28,10 +28,10 @@ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes); + u32 bytes); int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap, u32 eeprom_addr, u8 *eeprom_buf, - u16 bytes); + u32 bytes); #endif diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index e9e0e7328c4e..6b818c6c9a4c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -676,8 +676,11 @@ int amdgpu_gfx_ras_late_init(struct amdgpu_device *adev, struct ras_common_if *r int r; if (amdgpu_ras_is_supported(adev, ras_block->block)) { - if (!amdgpu_persistent_edc_harvesting_supported(adev)) - amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX); + if (!amdgpu_persistent_edc_harvesting_supported(adev)) { + r = amdgpu_ras_reset_error_status(adev, AMDGPU_RAS_BLOCK__GFX); + if (r) + return r; + } r = amdgpu_ras_block_late_init(adev, ras_block); if (r) @@ -758,7 +761,10 @@ uint32_t amdgpu_kiq_rreg(struct amdgpu_device *adev, uint32_t reg) pr_err("critical bug! too many kiq readers\n"); goto failed_unlock; } - amdgpu_ring_alloc(ring, 32); + r = amdgpu_ring_alloc(ring, 32); + if (r) + goto failed_unlock; + amdgpu_ring_emit_rreg(ring, reg, reg_val_offs); r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); if (r) @@ -824,7 +830,10 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) } spin_lock_irqsave(&kiq->ring_lock, flags); - amdgpu_ring_alloc(ring, 32); + r = amdgpu_ring_alloc(ring, 32); + if (r) + goto failed_unlock; + amdgpu_ring_emit_wreg(ring, reg, v); r = amdgpu_fence_emit_polling(ring, &seq, MAX_KIQ_REG_WAIT); if (r) @@ -860,6 +869,7 @@ void amdgpu_kiq_wreg(struct amdgpu_device *adev, uint32_t reg, uint32_t v) failed_undo: amdgpu_ring_undo(ring); +failed_unlock: spin_unlock_irqrestore(&kiq->ring_lock, flags); failed_kiq_write: dev_err(adev->dev, "failed to write reg:%x\n", reg); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c index ea0fb079f942..fd98d2508a22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c @@ -583,7 +583,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev) struct amdgpu_gmc *gmc = &adev->gmc; uint32_t gc_ver = adev->ip_versions[GC_HWIP][0]; bool noretry_default = (gc_ver == IP_VERSION(9, 0, 1) || - gc_ver == IP_VERSION(9, 3, 0) || gc_ver == IP_VERSION(9, 4, 0) || gc_ver == IP_VERSION(9, 4, 1) || gc_ver == IP_VERSION(9, 4, 2) || diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c index 9a4cbfbd5d9e..3feb792c210d 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c @@ -1038,8 +1038,10 @@ int amdgpu_mes_add_ring(struct amdgpu_device *adev, int gang_id, r = amdgpu_ring_init(adev, ring, 1024, NULL, 0, AMDGPU_RING_PRIO_DEFAULT, NULL); - if (r) + if (r) { + amdgpu_mes_unlock(&adev->mes); goto clean_up_memory; + } amdgpu_mes_ring_to_queue_props(adev, ring, &qprops); @@ -1072,7 +1074,6 @@ clean_up_ring: amdgpu_ring_fini(ring); clean_up_memory: kfree(ring); - amdgpu_mes_unlock(&adev->mes); return r; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c index 8764ff7ed97e..f8740ad08af4 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c @@ -1297,6 +1297,9 @@ static void psp_xgmi_reflect_topology_info(struct psp_context *psp, uint8_t dst_num_links = node_info.num_links; hive = amdgpu_get_xgmi_hive(psp->adev); + if (WARN_ON(!hive)) + return; + list_for_each_entry(mirror_adev, &hive->device_list, gmc.xgmi.head) { struct psp_xgmi_topology_info *mirror_top_info; int j; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c index 0988e00612e5..09a995df95e8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c @@ -148,6 +148,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t if (ret) return -EINVAL; + if (ta_bin_len > PSP_1_MEG) + return -EINVAL; + copy_pos += sizeof(uint32_t); ta_bin = kzalloc(ta_bin_len, GFP_KERNEL); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c index ee83d282b49a..4b7b3278a05f 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c @@ -1679,12 +1679,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work) int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev, struct ras_dispatch_if *info) { - struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head); - struct ras_ih_data *data = &obj->ih_data; + struct ras_manager *obj; + struct ras_ih_data *data; + obj = amdgpu_ras_find_obj(adev, &info->head); if (!obj) return -EINVAL; + data = &obj->ih_data; + if (data->inuse == 0) return 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index 296b2d5976af..cb73d06e1d38 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -324,7 +324,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring, ring->max_dw = max_dw; ring->hw_prio = hw_prio; - if (!ring->no_scheduler) { + if (!ring->no_scheduler && ring->funcs->type < AMDGPU_HW_IP_NUM) { hw_ip = ring->funcs->type; num_sched = &adev->gpu_sched[hw_ip][hw_prio].num_scheds; adev->gpu_sched[hw_ip][hw_prio].sched[(*num_sched)++] = @@ -434,8 +434,9 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf, size_t size, loff_t *pos) { struct amdgpu_ring *ring = file_inode(f)->i_private; - int r, i; uint32_t value, result, early[3]; + loff_t i; + int r; if (*pos & 3 || size & 3) return -EINVAL; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c index 02cb3a12dd76..bc030588cd22 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c @@ -743,7 +743,8 @@ int amdgpu_vce_ring_parse_cs(struct amdgpu_cs_parser *p, uint32_t created = 0; uint32_t allocated = 0; uint32_t tmp, handle = 0; - uint32_t *size = &tmp; + uint32_t dummy = 0xffffffff; + uint32_t *size = &dummy; unsigned idx; int i, r = 0; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c index 48e612023d0c..e2475f656ff2 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c @@ -239,6 +239,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev) return r; } + /* from vcn4 and above, only unified queue is used */ + adev->vcn.using_unified_queue = + adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0); + hdr = (const struct common_firmware_header *)adev->vcn.fw->data; adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version); @@ -357,18 +361,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev) return 0; } -/* from vcn4 and above, only unified queue is used */ -static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring) -{ - struct amdgpu_device *adev = ring->adev; - bool ret = false; - - if (adev->ip_versions[UVD_HWIP][0] >= IP_VERSION(4, 0, 0)) - ret = true; - - return ret; -} - bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance) { bool ret = false; @@ -480,7 +472,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work) fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]); } - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state; if (fence[j] || @@ -526,7 +520,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN, AMD_PG_STATE_UNGATE); - if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) { + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ + if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && + !adev->vcn.using_unified_queue) { struct dpg_pause_state new_state; if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) { @@ -552,8 +548,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring) void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring) { + struct amdgpu_device *adev = ring->adev; + + /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG && - ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) + ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC && + !adev->vcn.using_unified_queue) atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt); atomic_dec(&ring->adev->vcn.total_submission_cnt); @@ -806,12 +806,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, struct amdgpu_job *job; struct amdgpu_ib *ib; uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr); - bool sq = amdgpu_vcn_using_unified_queue(ring); uint32_t *ib_checksum; uint32_t ib_pack_in_dw; int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(adev, ib_size_dw * 4, @@ -823,7 +822,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, ib->length_dw = 0; /* single queue headers */ - if (sq) { + if (adev->vcn.using_unified_queue) { ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t) + 4 + 2; /* engine info + decoding ib in dw */ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false); @@ -842,7 +841,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring, for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw); r = amdgpu_job_submit_direct(job, ring, &f); @@ -932,15 +931,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, @@ -953,7 +952,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand ib->length_dw = 0; - if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -975,7 +974,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); @@ -998,15 +997,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han struct dma_fence **fence) { unsigned int ib_size_dw = 16; + struct amdgpu_device *adev = ring->adev; struct amdgpu_job *job; struct amdgpu_ib *ib; struct dma_fence *f = NULL; uint32_t *ib_checksum = NULL; uint64_t addr; - bool sq = amdgpu_vcn_using_unified_queue(ring); int i, r; - if (sq) + if (adev->vcn.using_unified_queue) ib_size_dw += 8; r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, @@ -1019,7 +1018,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han ib->length_dw = 0; - if (sq) + if (adev->vcn.using_unified_queue) ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true); ib->ptr[ib->length_dw++] = 0x00000018; @@ -1041,7 +1040,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han for (i = ib->length_dw; i < ib_size_dw; ++i) ib->ptr[i] = 0x0; - if (sq) + if (adev->vcn.using_unified_queue) amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11); r = amdgpu_job_submit_direct(job, ring, &f); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h index 253ea6b159df..165d841e0aaa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h @@ -271,6 +271,7 @@ struct amdgpu_vcn { struct ras_common_if *ras_if; struct amdgpu_vcn_ras *ras; + bool using_unified_queue; }; struct amdgpu_fw_shared_rb_ptrs_struct { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c index 81549f1edfe0..d7b76a3d2d55 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c @@ -132,8 +132,10 @@ int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init) if (virt->ops && virt->ops->req_full_gpu) { r = virt->ops->req_full_gpu(adev, init); - if (r) + if (r) { + adev->no_hw_access = true; return r; + } adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME; } @@ -604,7 +606,7 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev) vf2pf_info->dummy_page_addr = (uint64_t)adev->dummy_page_addr; vf2pf_info->checksum = amd_sriov_msg_checksum( - vf2pf_info, vf2pf_info->header.size, 0, 0); + vf2pf_info, sizeof(*vf2pf_info), 0, 0); return 0; } @@ -956,6 +958,9 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1; scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2; scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3; + + mutex_lock(&adev->virt.rlcg_reg_lock); + if (reg_access_ctrl->spare_int) spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int; @@ -1009,6 +1014,9 @@ static u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v } ret = readl(scratch_reg0); + + mutex_unlock(&adev->virt.rlcg_reg_lock); + return ret; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h index 2b9d806e23af..dc6aaa4d67be 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h @@ -260,6 +260,8 @@ struct amdgpu_virt { /* the ucode id to signal the autoload */ uint32_t autoload_ucode_id; + + struct mutex rlcg_reg_lock; }; struct amdgpu_video_codec_info; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c index 69b3829bbe53..370d02bdde86 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_pt.c @@ -754,11 +754,15 @@ int amdgpu_vm_pde_update(struct amdgpu_vm_update_params *params, struct amdgpu_vm_bo_base *entry) { struct amdgpu_vm_bo_base *parent = amdgpu_vm_pt_parent(entry); - struct amdgpu_bo *bo = parent->bo, *pbo; + struct amdgpu_bo *bo, *pbo; struct amdgpu_vm *vm = params->vm; uint64_t pde, pt, flags; unsigned int level; + if (WARN_ON(!parent)) + return -EINVAL; + + bo = parent->bo; for (level = 0, pbo = bo->parent; pbo; ++level) pbo = pbo->parent; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h index 6c97148ca0ed..99f459bd2748 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h @@ -209,7 +209,7 @@ struct amd_sriov_msg_pf2vf_info { uint32_t pcie_atomic_ops_support_flags; /* reserved */ uint32_t reserved[256 - AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE]; -}; +} __packed; struct amd_sriov_msg_vf2pf_info_header { /* the total structure size in byte */ @@ -267,7 +267,7 @@ struct amd_sriov_msg_vf2pf_info { /* reserved */ uint32_t reserved[256 - AMD_SRIOV_MSG_VF2PF_INFO_FILLED_SIZE]; -}; +} __packed; /* mailbox message send from guest to host */ enum amd_sriov_mailbox_request_message { diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c index 6be9ac2b9c5b..713b9796f0f9 100644 --- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c +++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c @@ -2066,23 +2066,29 @@ amdgpu_atombios_encoder_get_lcd_info(struct amdgpu_encoder *encoder) fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; if (fake_edid_record->ucFakeEDIDLength) { struct edid *edid; - int edid_size = - max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength); - edid = kmalloc(edid_size, GFP_KERNEL); - if (edid) { - memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0], - fake_edid_record->ucFakeEDIDLength); + int edid_size; + if (fake_edid_record->ucFakeEDIDLength == 128) + edid_size = fake_edid_record->ucFakeEDIDLength; + else + edid_size = fake_edid_record->ucFakeEDIDLength * 128; + edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0], + edid_size, GFP_KERNEL); + if (edid) { if (drm_edid_is_valid(edid)) { adev->mode_info.bios_hardcoded_edid = edid; adev->mode_info.bios_hardcoded_edid_size = edid_size; - } else + } else { kfree(edid); + } } + record += struct_size(fake_edid_record, + ucFakeEDIDString, + edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; } - record += fake_edid_record->ucFakeEDIDLength ? - fake_edid_record->ucFakeEDIDLength + 2 : - sizeof(ATOM_FAKE_EDID_PATCH_RECORD); break; case LCD_PANEL_RESOLUTION_RECORD_TYPE: panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c index b991609f46c1..d4909ee97cd2 100644 --- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c +++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c @@ -70,6 +70,8 @@ static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev) int fb_channel_number; fb_channel_number = adev->df.funcs->get_fb_channel_number(adev); + if (fb_channel_number >= ARRAY_SIZE(df_v1_7_channel_number)) + fb_channel_number = 0; return df_v1_7_channel_number[fb_channel_number]; } diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 1f9f7fdd4b8e..c76895cca4d9 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -4330,11 +4330,11 @@ static int gfx_v11_0_hw_init(void *handle) /* RLC autoload sequence 1: Program rlc ram */ if (adev->gfx.imu.funcs->program_rlc_ram) adev->gfx.imu.funcs->program_rlc_ram(adev); + /* rlc autoload firmware */ + r = gfx_v11_0_rlc_backdoor_autoload_enable(adev); + if (r) + return r; } - /* rlc autoload firmware */ - r = gfx_v11_0_rlc_backdoor_autoload_enable(adev); - if (r) - return r; } else { if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) { if (adev->gfx.imu.funcs && (amdgpu_dpm > 0)) { diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c index 6a1fe2168514..3cec6a145a5c 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c @@ -1173,6 +1173,10 @@ static const struct amdgpu_gfxoff_quirk amdgpu_gfxoff_quirk_list[] = { { 0x1002, 0x15dd, 0x1002, 0x15dd, 0xc6 }, /* Apple MacBook Pro (15-inch, 2019) Radeon Pro Vega 20 4 GB */ { 0x1002, 0x69af, 0x106b, 0x019a, 0xc0 }, + /* https://bbs.openkylin.top/t/topic/171497 */ + { 0x1002, 0x15d8, 0x19e5, 0x3e14, 0xc2 }, + /* HP 705G4 DM with R5 2400G */ + { 0x1002, 0x15dd, 0x103c, 0x8464, 0xd6 }, { 0, 0, 0, 0, 0 }, }; diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c index 657e4ca6f9dd..fccbec438bbe 100644 --- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c +++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c @@ -135,6 +135,34 @@ static int ih_v6_0_toggle_ring_interrupts(struct amdgpu_device *adev, tmp = RREG32(ih_regs->ih_rb_cntl); tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0)); + + if (enable) { + /* Unset the CLEAR_OVERFLOW bit to make sure the next step + * is switching the bit from 0 to 1 + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) { + if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) + return -ETIMEDOUT; + } else { + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + } + + /* Clear RB_OVERFLOW bit */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1); + if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) { + if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp)) + return -ETIMEDOUT; + } else { + WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp); + } + + /* Unset the CLEAR_OVERFLOW bit immediately so new overflows + * can be detected. + */ + tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0); + } + /* enable_intr field is only valid in ring0 */ if (ih == &adev->irq.ih) tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0)); diff --git a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c index 95548c512f4f..3c21128fa1d8 100644 --- a/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/imu_v11_0.c @@ -38,7 +38,7 @@ MODULE_FIRMWARE("amdgpu/gc_11_0_3_imu.bin"); static int imu_v11_0_init_microcode(struct amdgpu_device *adev) { - char fw_name[40]; + char fw_name[45]; char ucode_prefix[30]; int err; const struct imu_firmware_header_v1_0 *imu_hdr; diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c index f3c1af5130ab..3301ad980f28 100644 --- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c +++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c @@ -541,11 +541,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring, amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); - amdgpu_ring_write(ring, (vmid | (vmid << 4))); + amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8))); amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET, 0, 0, PACKETJ_TYPE0)); diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c index 19455a725939..7679a4cd55c0 100644 --- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c +++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c @@ -384,7 +384,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device else WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl); - if (!ras->disable_ras_err_cnt_harvest) { + if (ras && !ras->disable_ras_err_cnt_harvest && obj) { /* * clear error status after ras_controller_intr * according to hw team and count ue number diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c index 68cdb6682776..b19353412d8a 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c @@ -2045,7 +2045,7 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev, struct amdgpu_irq_src *source, struct amdgpu_iv_entry *entry) { - uint32_t instance; + int instance; DRM_DEBUG("IH: SDMA trap\n"); instance = sdma_v4_0_irq_id_to_seq(entry->client_id); diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c index c7af36370b0d..38f57455bc74 100644 --- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c +++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c @@ -241,6 +241,14 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring) DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n", ring->doorbell_index, ring->wptr << 2); WDOORBELL64(ring->doorbell_index, ring->wptr << 2); + /* SDMA seems to miss doorbells sometimes when powergating kicks in. + * Updating the wptr directly will wake it. This is only safe because + * we disallow gfxoff in begin_use() and then allow it again in end_use(). + */ + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), + lower_32_bits(ring->wptr << 2)); + WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), + upper_32_bits(ring->wptr << 2)); } else { DRM_DEBUG("Not using doorbell -- " "mmSDMA%i_GFX_RB_WPTR == 0x%08x " @@ -1705,6 +1713,10 @@ static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring) * but it shouldn't hurt for other parts since * this GFXOFF will be disallowed anyway when SDMA is * active, this just makes it explicit. + * sdma_v5_2_ring_set_wptr() takes advantage of this + * to update the wptr because sometimes SDMA seems to miss + * doorbells when entering PG. If you remove this, update + * sdma_v5_2_ring_set_wptr() as well! */ amdgpu_gfx_off_ctrl(adev, false); } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c index b0f475d51ae7..e3cd66c4d95d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c @@ -1400,17 +1400,23 @@ static int kfd_ioctl_unmap_memory_from_gpu(struct file *filep, goto sync_memory_failed; } } + + /* Flush TLBs after waiting for the page table updates to complete */ + for (i = 0; i < args->n_devices; i++) { + peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); + if (WARN_ON_ONCE(!peer_pdd)) + continue; + if (flush_tlb) + kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); + + /* Remove dma mapping after tlb flush to avoid IO_PAGE_FAULT */ + err = amdgpu_amdkfd_gpuvm_dmaunmap_mem(mem, peer_pdd->drm_priv); + if (err) + goto sync_memory_failed; + } + mutex_unlock(&p->mutex); - if (flush_tlb) { - /* Flush TLBs after waiting for the page table updates to complete */ - for (i = 0; i < args->n_devices; i++) { - peer_pdd = kfd_process_device_data_by_id(p, devices_arr[i]); - if (WARN_ON_ONCE(!peer_pdd)) - continue; - kfd_flush_tlb(peer_pdd, TLB_FLUSH_HEAVYWEIGHT); - } - } kfree(devices_arr); return 0; diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h index a8671061a175..bf90a6479867 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h @@ -43,8 +43,6 @@ #define CRAT_OEMTABLEID_LENGTH 8 #define CRAT_RESERVED_LENGTH 6 -#define CRAT_OEMID_64BIT_MASK ((1ULL << (CRAT_OEMID_LENGTH * 8)) - 1) - /* Compute Unit flags */ #define COMPUTE_UNIT_CPU (1 << 0) /* Create Virtual CRAT for CPU */ #define COMPUTE_UNIT_GPU (1 << 1) /* Create Virtual CRAT for GPU */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c index 4236539d9f93..99aa8a8399d6 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c @@ -890,6 +890,7 @@ exit: pr_debug("Queue id %d was restored successfully\n", queue_id); kfree(q_data); + kfree(q_extra_data); return ret; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c index 029916971bf6..d841200a405b 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c @@ -972,8 +972,7 @@ static void kfd_update_system_properties(void) dev = list_last_entry(&topology_device_list, struct kfd_topology_device, list); if (dev) { - sys_props.platform_id = - (*((uint64_t *)dev->oem_id)) & CRAT_OEMID_64BIT_MASK; + sys_props.platform_id = dev->oem_id64; sys_props.platform_oem = *((uint64_t *)dev->oem_table_id); sys_props.platform_rev = dev->oem_revision; } diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index 19283b8b1688..00a78c2ce686 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -146,7 +146,10 @@ struct kfd_topology_device { struct attribute attr_gpuid; struct attribute attr_name; struct attribute attr_props; - uint8_t oem_id[CRAT_OEMID_LENGTH]; + union { + uint8_t oem_id[CRAT_OEMID_LENGTH]; + uint64_t oem_id64; + }; uint8_t oem_table_id[CRAT_OEMTABLEID_LENGTH]; uint32_t oem_revision; }; diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 31bae620aeff..8f7130f7d8c6 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -712,6 +712,12 @@ static void dmub_hpd_callback(struct amdgpu_device *adev, return; } + /* Skip DMUB HPD IRQ in suspend/resume. We will probe them later. */ + if (notify->type == DMUB_NOTIFICATION_HPD && adev->in_suspend) { + DRM_INFO("Skip DMUB HPD IRQ callback in suspend/resume\n"); + return; + } + link_index = notify->link_index; link = adev->dm.dc->links[link_index]; dev = adev->dm.ddev; @@ -2636,7 +2642,8 @@ static int dm_suspend(void *handle) dm->cached_dc_state = dc_copy_state(dm->dc->current_state); - dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); + if (dm->cached_dc_state) + dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false); amdgpu_dm_commit_zero_streams(dm->dc); @@ -4049,6 +4056,7 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev) #define AMDGPU_DM_DEFAULT_MIN_BACKLIGHT 12 #define AMDGPU_DM_DEFAULT_MAX_BACKLIGHT 255 +#define AMDGPU_DM_MIN_SPREAD ((AMDGPU_DM_DEFAULT_MAX_BACKLIGHT - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT) / 2) #define AUX_BL_DEFAULT_TRANSITION_TIME_MS 50 static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, @@ -4063,6 +4071,21 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm, return; amdgpu_acpi_get_backlight_caps(&caps); + + /* validate the firmware value is sane */ + if (caps.caps_valid) { + int spread = caps.max_input_signal - caps.min_input_signal; + + if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + caps.min_input_signal < 0 || + spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT || + spread < AMDGPU_DM_MIN_SPREAD) { + DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n", + caps.min_input_signal, caps.max_input_signal); + caps.caps_valid = false; + } + } + if (caps.caps_valid) { dm->backlight_caps[bl_idx].caps_valid = true; if (caps.aux_support) @@ -4358,7 +4381,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev) /* There is one primary plane per CRTC */ primary_planes = dm->dc->caps.max_streams; - ASSERT(primary_planes <= AMDGPU_MAX_PLANES); + if (primary_planes > AMDGPU_MAX_PLANES) { + DRM_ERROR("DM: Plane nums out of 6 planes\n"); + return -EINVAL; + } /* * Initialize primary planes, implicit planes for legacy IOCTLS. @@ -6388,7 +6414,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector) aconnector->dc_sink = aconnector->dc_link->local_sink ? aconnector->dc_link->local_sink : aconnector->dc_em_sink; - dc_sink_retain(aconnector->dc_sink); + if (aconnector->dc_sink) + dc_sink_retain(aconnector->dc_sink); } } @@ -6762,7 +6789,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state, } } - if (j == dc_state->stream_count) + if (j == dc_state->stream_count || pbn_div == 0) continue; slot_num = DIV_ROUND_UP(pbn, pbn_div); @@ -7121,7 +7148,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector) drm_add_modes_noedid(connector, 640, 480); } else { amdgpu_dm_connector_ddc_get_modes(connector, edid); - amdgpu_dm_connector_add_common_modes(encoder, connector); + if (encoder) + amdgpu_dm_connector_add_common_modes(encoder, connector); amdgpu_dm_connector_add_freesync_modes(connector, edid); } amdgpu_dm_fbc_init(connector); @@ -8049,15 +8077,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, bundle->stream_update.vrr_infopacket = &acrtc_state->stream->vrr_infopacket; } - } else if (cursor_update && acrtc_state->active_planes > 0 && - acrtc_attach->base.state->event) { - drm_crtc_vblank_get(pcrtc); - + } else if (cursor_update && acrtc_state->active_planes > 0) { spin_lock_irqsave(&pcrtc->dev->event_lock, flags); - - acrtc_attach->event = acrtc_attach->base.state->event; - acrtc_attach->base.state->event = NULL; - + if (acrtc_attach->base.state->event) { + drm_crtc_vblank_get(pcrtc); + acrtc_attach->event = acrtc_attach->base.state->event; + acrtc_attach->base.state->event = NULL; + } spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags); } diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h index 2c9a33c80c81..df18b4df1f2c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h @@ -49,7 +49,7 @@ #define AMDGPU_DM_MAX_NUM_EDP 2 -#define AMDGPU_DMUB_NOTIFICATION_MAX 5 +#define AMDGPU_DMUB_NOTIFICATION_MAX 6 /* #include "include/amdgpu_dal_power_if.h" diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c index a9ddff774a97..1acef5f3838f 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c @@ -251,7 +251,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto aconnector->dsc_aux = &aconnector->mst_port->dm_dp_aux.aux; /* synaptics cascaded MST hub case */ - if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port)) + if (is_synaptics_cascaded_panamera(aconnector->dc_link, port)) aconnector->dsc_aux = port->mgr->aux; if (!aconnector->dsc_aux) @@ -1255,6 +1255,12 @@ static bool is_dsc_need_re_compute( } } + if (new_stream_on_link_num == 0) + return false; + + if (new_stream_on_link_num == 0) + return false; + /* check current_state if there stream on link but it is not in * new request state */ diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c index cd6e99cf74a0..df4cbf81c6b5 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c @@ -28,6 +28,7 @@ #include #include #include +#include #include #include "amdgpu.h" @@ -848,10 +849,14 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane, } afb = to_amdgpu_framebuffer(new_state->fb); - obj = new_state->fb->obj[0]; + obj = drm_gem_fb_get_obj(new_state->fb, 0); + if (!obj) { + DRM_ERROR("Failed to get obj from framebuffer\n"); + return -EINVAL; + } + rbo = gem_to_amdgpu_bo(obj); adev = amdgpu_ttm_adev(rbo->tbo.bdev); - r = amdgpu_bo_reserve(rbo, true); if (r) { dev_err(adev->dev, "fail to reserve bo (%d)\n", r); @@ -1276,7 +1281,8 @@ void handle_cursor_update(struct drm_plane *plane, adev->dm.dc->caps.color.dpp.gamma_corr) attributes.attribute_flags.bits.ENABLE_CURSOR_DEGAMMA = 1; - attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; + if (afb) + attributes.pitch = afb->base.pitches[0] / afb->base.format->cpp[0]; if (crtc_state->stream) { mutex_lock(&adev->dm.dc_lock); diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c index ca6dfd2d7561..35386011c56c 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c @@ -484,7 +484,8 @@ static void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_sm ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; /* Modify previous watermark range to cover up to max */ - ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; + if (num_valid_sets > 0) + ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX; } num_valid_sets++; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index f415733f1a97..2721842af806 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1265,6 +1265,7 @@ struct dc *dc_create(const struct dc_init_data *init_params) return NULL; if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) { + dc->caps.linear_pitch_alignment = 64; if (!dc_construct_ctx(dc, init_params)) goto destruct_dc; } else { @@ -1658,7 +1659,7 @@ bool dc_validate_boot_timing(const struct dc *dc, if (crtc_timing->pix_clk_100hz != pix_clk_100hz) return false; - if (!se->funcs->dp_get_pixel_format) + if (!se || !se->funcs->dp_get_pixel_format) return false; if (!se->funcs->dp_get_pixel_format( @@ -3726,7 +3727,8 @@ static void commit_planes_for_stream(struct dc *dc, } if ((update_type != UPDATE_TYPE_FAST) && stream->update_flags.bits.dsc_changed) - if (top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { + if (top_pipe_to_program && + top_pipe_to_program->stream_res.tg->funcs->lock_doublebuffer_enable) { top_pipe_to_program->stream_res.tg->funcs->wait_for_state( top_pipe_to_program->stream_res.tg, CRTC_STATE_VACTIVE); @@ -4514,7 +4516,8 @@ void dc_allow_idle_optimizations(struct dc *dc, bool allow) if (allow == dc->idle_optimizations_allowed) return; - if (dc->hwss.apply_idle_power_optimizations && dc->hwss.apply_idle_power_optimizations(dc, allow)) + if (dc->hwss.apply_idle_power_optimizations && dc->clk_mgr != NULL && + dc->hwss.apply_idle_power_optimizations(dc, allow)) dc->idle_optimizations_allowed = allow; } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c index 83898e46bcad..8b27fe2f5ab1 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c @@ -1915,6 +1915,8 @@ static bool are_stream_backends_same( bool dc_is_stream_unchanged( struct dc_stream_state *old_stream, struct dc_stream_state *stream) { + if (!old_stream || !stream) + return false; if (!are_stream_backends_same(old_stream, stream)) return false; @@ -2634,8 +2636,10 @@ static bool planes_changed_for_existing_stream(struct dc_state *context, } } - if (!stream_status) + if (!stream_status) { ASSERT(0); + return false; + } for (i = 0; i < set_count; i++) if (set[i].stream == stream) @@ -3629,6 +3633,9 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream, enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream) { + if (dc == NULL || stream == NULL) + return DC_ERROR_UNEXPECTED; + struct dc_link *link = stream->link; struct timing_generator *tg = dc->res_pool->timing_generators[0]; enum dc_status res = DC_OK; diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c index a80e45300783..f4f3ca7aad60 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c @@ -154,7 +154,8 @@ const struct dc_plane_status *dc_plane_get_status( if (pipe_ctx->plane_state != plane_state) continue; - pipe_ctx->plane_state->status.is_flip_pending = false; + if (pipe_ctx->plane_state) + pipe_ctx->plane_state->status.is_flip_pending = false; break; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c index c0372aa4ec83..684e30f9cf89 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c @@ -571,6 +571,8 @@ bool cm_helper_translate_curve_to_degamma_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c index d6c5d48c878e..416168c7dcc5 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c @@ -3633,7 +3633,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx) (int)hubp->curs_attr.width || pos_cpy.x <= (int)hubp->curs_attr.width + pipe_ctx->plane_state->src_rect.x) { - pos_cpy.x = 2 * viewport_width - temp_x; + pos_cpy.x = temp_x + viewport_width; } } } else { diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c index 994fb732a7cb..a0d437f0ce2b 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c @@ -690,6 +690,9 @@ static void wbscl_set_scaler_filter( int pair; uint16_t odd_coef, even_coef; + if (!filter) + return; + for (phase = 0; phase < (NUM_PHASES / 2 + 1); phase++) { for (pair = 0; pair < tap_pairs; pair++) { even_coef = filter[phase * taps + 2 * pair]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c index e0df9b0065f9..62c02adae7e7 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_cm_common.c @@ -178,6 +178,8 @@ bool cm3_helper_translate_curve_to_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; @@ -355,6 +357,8 @@ bool cm3_helper_translate_curve_to_degamma_hw_format( i += increment) { if (j == hw_points - 1) break; + if (i >= TRANSFER_FUNC_POINTS) + return false; rgb_resulted[j].red = output_tf->tf_pts.red[i]; rgb_resulted[j].green = output_tf->tf_pts.green[i]; rgb_resulted[j].blue = output_tf->tf_pts.blue[i]; diff --git a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c index 0225b2c96041..407f7889e8fd 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/dcn30/dcn30_hwseq.c @@ -215,7 +215,11 @@ bool dcn30_set_output_transfer_func(struct dc *dc, } } - mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + if (mpc->funcs->set_output_gamma) + mpc->funcs->set_output_gamma(mpc, mpcc_id, params); + else + DC_LOG_ERROR("%s: set_output_gamma function pointer is NULL.\n", __func__); + return ret; } diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c index e73f089c84bb..ebd7ed1b9a3c 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c +++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c @@ -1453,10 +1453,9 @@ void dcn_bw_update_from_pplib_fclks( ASSERT(fclks->num_levels); vmin0p65_idx = 0; - vmid0p72_idx = fclks->num_levels - - (fclks->num_levels > 2 ? 3 : (fclks->num_levels > 1 ? 2 : 1)); - vnom0p8_idx = fclks->num_levels - (fclks->num_levels > 1 ? 2 : 1); - vmax0p9_idx = fclks->num_levels - 1; + vmid0p72_idx = fclks->num_levels > 2 ? fclks->num_levels - 3 : 0; + vnom0p8_idx = fclks->num_levels > 1 ? fclks->num_levels - 2 : 0; + vmax0p9_idx = fclks->num_levels > 0 ? fclks->num_levels - 1 : 0; dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 = 32 * (fclks->data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0; diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c index 0fc9f3e3ffae..f603486af6e3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn20/display_rq_dlg_calc_20v2.c @@ -78,7 +78,7 @@ static void calculate_ttu_cursor(struct display_mode_lib *mode_lib, static unsigned int get_bytes_per_element(enum source_format_class source_format, bool is_chroma) { - unsigned int ret_val = 0; + unsigned int ret_val = 1; if (source_format == dm_444_16) { if (!is_chroma) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c index 618f4b682ab1..9f28e4d3c664 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn21/display_rq_dlg_calc_21.c @@ -53,7 +53,7 @@ static void calculate_ttu_cursor( static unsigned int get_bytes_per_element(enum source_format_class source_format, bool is_chroma) { - unsigned int ret_val = 0; + unsigned int ret_val = 1; if (source_format == dm_444_16) { if (!is_chroma) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c index cc8c1a48c5c4..76df036fb2f3 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/display_mode_vba_32.c @@ -3338,6 +3338,9 @@ void dml32_ModeSupportAndSystemConfigurationFull(struct display_mode_lib *mode_l &mode_lib->vba.UrgentBurstFactorLumaPre[k], &mode_lib->vba.UrgentBurstFactorChromaPre[k], &mode_lib->vba.NotUrgentLatencyHidingPre[k]); + + v->cursor_bw_pre[k] = mode_lib->vba.NumberOfCursors[k] * mode_lib->vba.CursorWidth[k][0] * mode_lib->vba.CursorBPP[k][0] / + 8.0 / (mode_lib->vba.HTotal[k] / mode_lib->vba.PixelClock[k]) * v->VRatioPreY[i][j][k]; } { diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c index 1070cf870196..b2ad56c459ba 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c +++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c @@ -1099,8 +1099,13 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib) // Total Available Pipes Support Check for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) { - total_pipes += mode_lib->vba.DPPPerPlane[k]; pipe_idx = get_pipe_idx(mode_lib, k); + if (pipe_idx == -1) { + ASSERT(0); + continue; // skip inactive planes + } + total_pipes += mode_lib->vba.DPPPerPlane[k]; + if (mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz > 0.0) mode_lib->vba.DPPCLK[k] = mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz; else diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c index 3ede6e02c3a7..f2037d78f71a 100644 --- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c +++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c @@ -56,7 +56,7 @@ struct gpio_service *dal_gpio_service_create( struct dc_context *ctx) { struct gpio_service *service; - uint32_t index_of_id; + int32_t index_of_id; service = kzalloc(sizeof(struct gpio_service), GFP_KERNEL); @@ -112,7 +112,7 @@ struct gpio_service *dal_gpio_service_create( return service; failure_2: - while (index_of_id) { + while (index_of_id > 0) { --index_of_id; kfree(service->busyness[index_of_id]); } @@ -239,6 +239,9 @@ static bool is_pin_busy( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return false; + return service->busyness[id][en]; } @@ -247,6 +250,9 @@ static void set_pin_busy( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return; + service->busyness[id][en] = true; } @@ -255,6 +261,9 @@ static void set_pin_free( enum gpio_id id, uint32_t en) { + if (id == GPIO_ID_UNKNOWN) + return; + service->busyness[id][en] = false; } @@ -263,7 +272,7 @@ enum gpio_result dal_gpio_service_lock( enum gpio_id id, uint32_t en) { - if (!service->busyness[id]) { + if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) { ASSERT_CRITICAL(false); return GPIO_RESULT_OPEN_FAILED; } @@ -277,7 +286,7 @@ enum gpio_result dal_gpio_service_unlock( enum gpio_id id, uint32_t en) { - if (!service->busyness[id]) { + if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) { ASSERT_CRITICAL(false); return GPIO_RESULT_OPEN_FAILED; } diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c index 4233955e3c47..c9851492ec84 100644 --- a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c +++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c @@ -131,13 +131,21 @@ static bool hdmi_14_process_transaction( const uint8_t hdcp_i2c_addr_link_primary = 0x3a; /* 0x74 >> 1*/ const uint8_t hdcp_i2c_addr_link_secondary = 0x3b; /* 0x76 >> 1*/ struct i2c_command i2c_command; - uint8_t offset = hdcp_i2c_offsets[message_info->msg_id]; + uint8_t offset; struct i2c_payload i2c_payloads[] = { - { true, 0, 1, &offset }, + { true, 0, 1, 0 }, /* actual hdcp payload, will be filled later, zeroed for now*/ { 0 } }; + if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) { + DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id); + return false; + } + + offset = hdcp_i2c_offsets[message_info->msg_id]; + i2c_payloads[0].data = &offset; + switch (message_info->link) { case HDCP_LINK_SECONDARY: i2c_payloads[0].address = hdcp_i2c_addr_link_secondary; @@ -311,6 +319,11 @@ static bool dp_11_process_transaction( struct dc_link *link, struct hdcp_protection_message *message_info) { + if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) { + DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id); + return false; + } + return dpcd_access_helper( link, message_info->length, diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c index 9e74b6e8b573..e9f64fc72985 100644 --- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c +++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c @@ -133,7 +133,7 @@ unsigned int mod_freesync_calc_v_total_from_refresh( v_total = div64_u64(div64_u64(((unsigned long long)( frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)), - stream->timing.h_total), 1000000); + stream->timing.h_total) + 500000, 1000000); /* v_total cannot be less than nominal */ if (v_total < stream->timing.v_total) { diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c index 1ddb4f5eac8e..93c0455766dd 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c @@ -433,17 +433,20 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp, } if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, + if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus, &input->bstatus_read, &status, - hdcp, "bstatus_read"); + hdcp, "bstatus_read")) + goto out; if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(check_link_integrity_dp, + if (!mod_hdcp_execute_and_set(check_link_integrity_dp, &input->link_integrity_check, &status, - hdcp, "link_integrity_check"); + hdcp, "link_integrity_check")) + goto out; if (status == MOD_HDCP_STATUS_SUCCESS) - mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, + if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp, &input->reauth_request_check, &status, - hdcp, "reauth_request_check"); + hdcp, "reauth_request_check")) + goto out; out: return status; } diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c index 8e9caae7c955..1b2df97226a3 100644 --- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c +++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c @@ -156,11 +156,16 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp, uint32_t cur_size = 0; uint32_t data_offset = 0; - if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID) { + if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID || + msg_id >= MOD_HDCP_MESSAGE_ID_MAX) return MOD_HDCP_STATUS_DDC_FAILURE; - } if (is_dp_hdcp(hdcp)) { + int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) / + sizeof(hdcp_dpcd_addrs[0]); + if (msg_id >= num_dpcd_addrs) + return MOD_HDCP_STATUS_DDC_FAILURE; + while (buf_len > 0) { cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE); success = hdcp->config.ddc.funcs.read_dpcd(hdcp->config.ddc.handle, @@ -175,6 +180,11 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp, data_offset += cur_size; } } else { + int num_i2c_offsets = sizeof(hdcp_i2c_offsets) / + sizeof(hdcp_i2c_offsets[0]); + if (msg_id >= num_i2c_offsets) + return MOD_HDCP_STATUS_DDC_FAILURE; + success = hdcp->config.ddc.funcs.read_i2c( hdcp->config.ddc.handle, HDCP_I2C_ADDR, @@ -219,11 +229,16 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp, uint32_t cur_size = 0; uint32_t data_offset = 0; - if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID) { + if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID || + msg_id >= MOD_HDCP_MESSAGE_ID_MAX) return MOD_HDCP_STATUS_DDC_FAILURE; - } if (is_dp_hdcp(hdcp)) { + int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) / + sizeof(hdcp_dpcd_addrs[0]); + if (msg_id >= num_dpcd_addrs) + return MOD_HDCP_STATUS_DDC_FAILURE; + while (buf_len > 0) { cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE); success = hdcp->config.ddc.funcs.write_dpcd( @@ -239,6 +254,11 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp, data_offset += cur_size; } } else { + int num_i2c_offsets = sizeof(hdcp_i2c_offsets) / + sizeof(hdcp_i2c_offsets[0]); + if (msg_id >= num_i2c_offsets) + return MOD_HDCP_STATUS_DDC_FAILURE; + hdcp->buf[0] = hdcp_i2c_offsets[msg_id]; memmove(&hdcp->buf[1], buf, buf_len); success = hdcp->config.ddc.funcs.write_i2c( diff --git a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c index 67287ad07226..e83ad362e06f 100644 --- a/drivers/gpu/drm/amd/display/modules/power/power_helpers.c +++ b/drivers/gpu/drm/amd/display/modules/power/power_helpers.c @@ -818,6 +818,8 @@ bool is_psr_su_specific_panel(struct dc_link *link) isPSRSUSupported = false; else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x03) isPSRSUSupported = false; + else if (dpcd_caps->sink_dev_id_str[1] == 0x08 && dpcd_caps->sink_dev_id_str[0] == 0x01) + isPSRSUSupported = false; else if (dpcd_caps->psr_info.force_psrsu_cap == 0x1) isPSRSUSupported = true; } diff --git a/drivers/gpu/drm/amd/include/atombios.h b/drivers/gpu/drm/amd/include/atombios.h index 15943bc21bc5..b5b1d073f8e2 100644 --- a/drivers/gpu/drm/amd/include/atombios.h +++ b/drivers/gpu/drm/amd/include/atombios.h @@ -4107,7 +4107,7 @@ typedef struct _ATOM_FAKE_EDID_PATCH_RECORD { UCHAR ucRecordType; UCHAR ucFakeEDIDLength; // = 128 means EDID length is 128 bytes, otherwise the EDID length = ucFakeEDIDLength*128 - UCHAR ucFakeEDIDString[1]; // This actually has ucFakeEdidLength elements. + UCHAR ucFakeEDIDString[]; // This actually has ucFakeEdidLength elements. } ATOM_FAKE_EDID_PATCH_RECORD; typedef struct _ATOM_PANEL_RESOLUTION_PATCH_RECORD diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h index 6ea596a8a03d..dea810c9b8fb 100644 --- a/drivers/gpu/drm/amd/include/atomfirmware.h +++ b/drivers/gpu/drm/amd/include/atomfirmware.h @@ -1005,7 +1005,7 @@ struct display_object_info_table_v1_4 uint16_t supporteddevices; uint8_t number_of_path; uint8_t reserved; - struct atom_display_object_path_v2 display_path[8]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path + struct atom_display_object_path_v2 display_path[]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path }; struct display_object_info_table_v1_5 { @@ -1015,7 +1015,7 @@ struct display_object_info_table_v1_5 { uint8_t reserved; // the real number of this included in the structure is calculated by using the // (whole structure size - the header size- number_of_path)/size of atom_display_object_path - struct atom_display_object_path_v3 display_path[8]; + struct atom_display_object_path_v3 display_path[]; }; /* diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c index 179e1c593a53..eae4b4826f04 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c +++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c @@ -99,7 +99,7 @@ static void pp_swctf_delayed_work_handler(struct work_struct *work) struct amdgpu_device *adev = hwmgr->adev; struct amdgpu_dpm_thermal *range = &adev->pm.dpm.thermal; - uint32_t gpu_temperature, size; + uint32_t gpu_temperature, size = sizeof(gpu_temperature); int ret; /* @@ -928,7 +928,7 @@ static int pp_dpm_switch_power_profile(void *handle, enum PP_SMC_POWER_PROFILE type, bool en) { struct pp_hwmgr *hwmgr = handle; - long workload; + long workload[1]; uint32_t index; if (!hwmgr || !hwmgr->pm_en) @@ -946,12 +946,12 @@ static int pp_dpm_switch_power_profile(void *handle, hwmgr->workload_mask &= ~(1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } else { hwmgr->workload_mask |= (1 << hwmgr->workload_prority[type]); index = fls(hwmgr->workload_mask); index = index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; } if (type == PP_SMC_POWER_PROFILE_COMPUTE && @@ -961,7 +961,7 @@ static int pp_dpm_switch_power_profile(void *handle, } if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); return 0; } diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c index 1d829402cd2e..18f00038d844 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c @@ -30,9 +30,8 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr) { int result; unsigned int i; - unsigned int table_entries; struct pp_power_state *state; - int size; + int size, table_entries; if (hwmgr->hwmgr_func->get_num_of_pp_table_entries == NULL) return 0; @@ -40,15 +39,19 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr) if (hwmgr->hwmgr_func->get_power_state_size == NULL) return 0; - hwmgr->num_ps = table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr); + table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr); - hwmgr->ps_size = size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) + + size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) + sizeof(struct pp_power_state); - if (table_entries == 0 || size == 0) { + if (table_entries <= 0 || size == 0) { pr_warn("Please check whether power state management is supported on this asic\n"); + hwmgr->num_ps = 0; + hwmgr->ps_size = 0; return 0; } + hwmgr->num_ps = table_entries; + hwmgr->ps_size = size; hwmgr->ps = kcalloc(table_entries, size, GFP_KERNEL); if (hwmgr->ps == NULL) @@ -269,7 +272,7 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set struct pp_power_state *new_ps) { uint32_t index; - long workload; + long workload[1]; if (hwmgr->not_vf) { if (!skip_display_settings) @@ -294,10 +297,10 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) { index = fls(hwmgr->workload_mask); index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0; - workload = hwmgr->workload_setting[index]; + workload[0] = hwmgr->workload_setting[index]; - if (hwmgr->power_profile_mode != workload && hwmgr->hwmgr_func->set_power_profile_mode) - hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0); + if (hwmgr->power_profile_mode != workload[0] && hwmgr->hwmgr_func->set_power_profile_mode) + hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0); } return 0; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c index f503e61faa60..cc3b62f73394 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c @@ -73,8 +73,9 @@ static int atomctrl_retrieve_ac_timing( j++; } else if ((table->mc_reg_address[i].uc_pre_reg_data & LOW_NIBBLE_MASK) == DATA_EQU_PREV) { - table->mc_reg_table_entry[num_ranges].mc_data[i] = - table->mc_reg_table_entry[num_ranges].mc_data[i-1]; + if (i) + table->mc_reg_table_entry[num_ranges].mc_data[i] = + table->mc_reg_table_entry[num_ranges].mc_data[i-1]; } } num_ranges++; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c index 182118e3fd5f..2ca93a1f0b8e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/processpptables.c @@ -1185,6 +1185,8 @@ static int init_overdrive_limits(struct pp_hwmgr *hwmgr, fw_info = smu_atom_get_data_table(hwmgr->adev, GetIndexIntoMasterTable(DATA, FirmwareInfo), &size, &frev, &crev); + PP_ASSERT_WITH_CODE(fw_info != NULL, + "Missing firmware info!", return -EINVAL); if ((fw_info->ucTableFormatRevision == 1) && (le16_to_cpu(fw_info->usStructureSize) >= sizeof(ATOM_FIRMWARE_INFO_V1_4))) diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c index 86d6e88c7386..4f3488f4e0d0 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c @@ -1036,7 +1036,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, switch (type) { case PP_SCLK: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now); + if (ret) + return ret; /* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */ if (now == data->gfx_max_freq_limit/100) @@ -1057,7 +1059,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr, i == 2 ? "*" : ""); break; case PP_MCLK: - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now); + if (ret) + return ret; for (i = 0; i < mclk_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -1550,7 +1554,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, } if (input[0] == 0) { - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + if (ret) + return ret; + if (input[1] < min_freq) { pr_err("Fine grain setting minimum sclk (%ld) MHz is less than the minimum allowed (%d) MHz\n", input[1], min_freq); @@ -1558,7 +1565,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, } smu10_data->gfx_actual_soft_min_freq = input[1]; } else if (input[0] == 1) { - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + if (ret) + return ret; + if (input[1] > max_freq) { pr_err("Fine grain setting maximum sclk (%ld) MHz is greater than the maximum allowed (%d) MHz\n", input[1], max_freq); @@ -1573,10 +1583,15 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr, pr_err("Input parameter number not correct\n"); return -EINVAL; } - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); - + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq); + if (ret) + return ret; smu10_data->gfx_actual_soft_min_freq = min_freq; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq); + if (ret) + return ret; + smu10_data->gfx_actual_soft_max_freq = max_freq; } else if (type == PP_OD_COMMIT_DPM_TABLE) { if (size != 0) { diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c index 5e9410117712..530888c475be 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c @@ -2970,6 +2970,7 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr) static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { + struct amdgpu_device *adev = hwmgr->adev; struct smu7_hwmgr *data; int result = 0; @@ -3006,40 +3007,37 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr) /* Initalize Dynamic State Adjustment Rule Settings */ result = phm_initializa_dynamic_state_adjustment_rule_settings(hwmgr); - if (0 == result) { - struct amdgpu_device *adev = hwmgr->adev; + if (result) + goto fail; - data->is_tlu_enabled = false; + data->is_tlu_enabled = false; - hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = + hwmgr->platform_descriptor.hardwareActivityPerformanceLevels = SMU7_MAX_HARDWARE_POWERLEVELS; - hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; - hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; + hwmgr->platform_descriptor.hardwarePerformanceLevels = 2; + hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50; - data->pcie_gen_cap = adev->pm.pcie_gen_mask; - if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) - data->pcie_spc_cap = 20; - else - data->pcie_spc_cap = 16; - data->pcie_lane_cap = adev->pm.pcie_mlw_mask; + data->pcie_gen_cap = adev->pm.pcie_gen_mask; + if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) + data->pcie_spc_cap = 20; + else + data->pcie_spc_cap = 16; + data->pcie_lane_cap = adev->pm.pcie_mlw_mask; - hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ -/* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ - hwmgr->platform_descriptor.clockStep.engineClock = 500; - hwmgr->platform_descriptor.clockStep.memoryClock = 500; - smu7_thermal_parameter_init(hwmgr); - } else { - /* Ignore return value in here, we are cleaning up a mess. */ - smu7_hwmgr_backend_fini(hwmgr); - } + hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */ + /* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */ + hwmgr->platform_descriptor.clockStep.engineClock = 500; + hwmgr->platform_descriptor.clockStep.memoryClock = 500; + smu7_thermal_parameter_init(hwmgr); result = smu7_update_edc_leakage_table(hwmgr); - if (result) { - smu7_hwmgr_backend_fini(hwmgr); - return result; - } + if (result) + goto fail; return 0; +fail: + smu7_hwmgr_backend_fini(hwmgr); + return result; } static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr) @@ -3329,8 +3327,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct smu7_power_state *smu7_ps = - cast_phw_smu7_power_state(&request_ps->hardware); + struct smu7_power_state *smu7_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3347,6 +3344,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t latency; bool latency_allowed = false; + smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware); + if (!smu7_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); data->mclk_ignore_signal = false; @@ -5638,7 +5639,7 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint mode = input[size]; switch (mode) { case PP_SMC_POWER_PROFILE_CUSTOM: - if (size < 8 && size != 0) + if (size != 8 && size != 0) return -EINVAL; /* If only CUSTOM is passed in, use the saved values. Check * that we actually have a CUSTOM profile by ensuring that diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c index b015a601b385..7e1197420873 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c @@ -584,6 +584,7 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.uvd_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -591,7 +592,9 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr) data->uvd_dpm.soft_min_clk = 0; data->uvd_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].vclk; @@ -611,6 +614,7 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.vce_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -618,7 +622,9 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr) data->vce_dpm.soft_min_clk = 0; data->vce_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].ecclk; @@ -638,6 +644,7 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr) hwmgr->dyn_state.acp_clock_voltage_dependency_table; unsigned long clock = 0; uint32_t level; + int ret; if (NULL == table || table->count <= 0) return -EINVAL; @@ -645,7 +652,9 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr) data->acp_dpm.soft_min_clk = 0; data->acp_dpm.hard_min_clk = 0; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level); + if (ret) + return ret; if (level < table->count) clock = table->entries[level].acpclk; @@ -1065,16 +1074,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, struct pp_power_state *prequest_ps, const struct pp_power_state *pcurrent_ps) { - struct smu8_power_state *smu8_ps = - cast_smu8_power_state(&prequest_ps->hardware); - - const struct smu8_power_state *smu8_current_ps = - cast_const_smu8_power_state(&pcurrent_ps->hardware); - + struct smu8_power_state *smu8_ps; + const struct smu8_power_state *smu8_current_ps; struct smu8_hwmgr *data = hwmgr->backend; struct PP_Clocks clocks = {0, 0, 0, 0}; bool force_high; + smu8_ps = cast_smu8_power_state(&prequest_ps->hardware); + smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware); + + if (!smu8_ps || !smu8_current_ps) + return -EINVAL; + smu8_ps->need_dfs_bypass = true; data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c index d8cd23438b76..c4d81c0aa18e 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c @@ -355,13 +355,13 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr) return 0; } -static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega10_hwmgr *data = hwmgr->backend; - int i; uint32_t sub_vendor_id, hw_revision; uint32_t top32, bottom32; struct amdgpu_device *adev = hwmgr->adev; + int ret, i; vega10_initialize_power_tune_defaults(hwmgr); @@ -486,9 +486,12 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) if (data->registry_data.vr0hot_enabled) data->smu_features[GNLD_VR0HOT].supported = true; - smum_send_msg_to_smc(hwmgr, + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetSmuVersion, &hwmgr->smu_version); + if (ret) + return ret; + /* ACG firmware has major version 5 */ if ((hwmgr->smu_version & 0xff000000) == 0x5000000) data->smu_features[GNLD_ACG].supported = true; @@ -506,10 +509,16 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr) data->smu_features[GNLD_PCC_LIMIT].supported = true; /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + return 0; } #ifdef PPLIB_VEGA10_EVV_SUPPORT @@ -883,7 +892,9 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega10_set_features_platform_caps(hwmgr); - vega10_init_dpm_defaults(hwmgr); + result = vega10_init_dpm_defaults(hwmgr); + if (result) + return result; #ifdef PPLIB_VEGA10_EVV_SUPPORT /* Get leakage voltage based on leakage ID. */ @@ -2354,15 +2365,20 @@ static int vega10_acg_enable(struct pp_hwmgr *hwmgr) { struct vega10_hwmgr *data = hwmgr->backend; uint32_t agc_btc_response; + int ret; if (data->smu_features[GNLD_ACG].supported) { if (0 == vega10_enable_smc_features(hwmgr, true, data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_bitmap)) data->smu_features[GNLD_DPM_PREFETCHER].enabled = true; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL); + if (ret) + return ret; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response); + if (ret) + agc_btc_response = 0; if (1 == agc_btc_response) { if (1 == data->acg_loop_state) @@ -2575,8 +2591,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr) } } - pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC, + result = pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC, VOLTAGE_OBJ_SVID2, &voltage_table); + PP_ASSERT_WITH_CODE(!result, + "Failed to get voltage table!", + return result); pp_table->MaxVidStep = voltage_table.max_vid_step; pp_table->GfxDpmVoltageMode = @@ -3263,8 +3282,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, const struct pp_power_state *current_ps) { struct amdgpu_device *adev = hwmgr->adev; - struct vega10_power_state *vega10_ps = - cast_phw_vega10_power_state(&request_ps->hardware); + struct vega10_power_state *vega10_ps; uint32_t sclk; uint32_t mclk; struct PP_Clocks minimum_clocks = {0}; @@ -3282,6 +3300,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr, uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0; uint32_t latency; + vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware); + if (!vega10_ps) + return -EINVAL; + data->battery_state = (PP_StateUILabel_Battery == request_ps->classification.ui_label); @@ -3419,13 +3441,17 @@ static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, co const struct vega10_power_state *vega10_ps = cast_const_phw_vega10_power_state(states->pnew_state); struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table); - uint32_t sclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].gfx_clock; struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table); - uint32_t mclk = vega10_ps->performance_levels - [vega10_ps->performance_level_count - 1].mem_clock; + uint32_t sclk, mclk; uint32_t i; + if (vega10_ps == NULL) + return -EINVAL; + sclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].gfx_clock; + mclk = vega10_ps->performance_levels + [vega10_ps->performance_level_count - 1].mem_clock; + for (i = 0; i < sclk_table->count; i++) { if (sclk == sclk_table->dpm_levels[i].value) break; @@ -3732,6 +3758,9 @@ static int vega10_generate_dpm_level_enable_mask( cast_const_phw_vega10_power_state(states->pnew_state); int i; + if (vega10_ps == NULL) + return -EINVAL; + PP_ASSERT_WITH_CODE(!vega10_trim_dpm_states(hwmgr, vega10_ps), "Attempt to Trim DPM States Failed!", return -1); @@ -3904,11 +3933,14 @@ static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query) { uint32_t value; + int ret; if (!query) return -EINVAL; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value); + if (ret) + return ret; /* SMC returning actual watts, keep consistent with legacy asics, low 8 bit as 8 fractional bits */ *query = value << 8; @@ -4804,14 +4836,16 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width; PPTable_t *pptable = &(data->smc_state_table.pp_table); - int i, now, size = 0, count = 0; + int i, ret, now, size = 0, count = 0; switch (type) { case PP_SCLK: if (data->registry_data.sclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now); + if (ret) + break; if (hwmgr->pp_one_vf && (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)) @@ -4827,7 +4861,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.mclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now); + if (ret) + break; for (i = 0; i < mclk_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4838,7 +4874,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.socclk_dpm_key_disabled) break; - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now); + if (ret) + break; for (i = 0; i < soc_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4849,8 +4887,10 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr, if (data->registry_data.dcefclk_dpm_key_disabled) break; - smum_send_msg_to_smc_with_parameter(hwmgr, + ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now); + if (ret) + break; for (i = 0; i < dcef_table->count; i++) size += sprintf(buf + size, "%d: %uMhz %s\n", @@ -4999,6 +5039,8 @@ static int vega10_check_states_equal(struct pp_hwmgr *hwmgr, vega10_psa = cast_const_phw_vega10_power_state(pstate1); vega10_psb = cast_const_phw_vega10_power_state(pstate2); + if (vega10_psa == NULL || vega10_psb == NULL) + return -EINVAL; /* If the two states don't even have the same number of performance levels * they cannot be the same state. @@ -5132,6 +5174,8 @@ static int vega10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].gfx_clock = @@ -5183,6 +5227,8 @@ static int vega10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value) return -EINVAL; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return -EINVAL; vega10_ps->performance_levels [vega10_ps->performance_level_count - 1].mem_clock = @@ -5424,6 +5470,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) return; vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5446,6 +5495,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr) ps = (struct pp_power_state *)((unsigned long)(hwmgr->ps) + hwmgr->ps_size * (hwmgr->num_ps - 1)); vega10_ps = cast_phw_vega10_power_state(&ps->hardware); + if (vega10_ps == NULL) + return; + max_level = vega10_ps->performance_level_count - 1; if (vega10_ps->performance_levels[max_level].gfx_clock != @@ -5636,6 +5688,8 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_ return -EINVAL; vega10_ps = cast_const_phw_vega10_power_state(state); + if (vega10_ps == NULL) + return -EINVAL; i = index > vega10_ps->performance_level_count - 1 ? vega10_ps->performance_level_count - 1 : index; diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c index 1069eaaae2f8..e4948a118475 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c @@ -294,12 +294,12 @@ static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr) return 0; } -static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend); struct amdgpu_device *adev = hwmgr->adev; uint32_t top32, bottom32; - int i; + int i, ret; data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id = FEATURE_DPM_PREFETCHER_BIT; @@ -365,10 +365,16 @@ static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr) } /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + + return 0; } static int vega12_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) @@ -411,7 +417,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega12_set_features_platform_caps(hwmgr); - vega12_init_dpm_defaults(hwmgr); + result = vega12_init_dpm_defaults(hwmgr); + if (result) { + pr_err("%s failed\n", __func__); + return result; + } /* Parse pptable data read from VBIOS */ vega12_set_private_data_based_on_pptable(hwmgr); diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c index ff77a3683efd..89f1ed7d08c2 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c @@ -329,12 +329,12 @@ static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr) return 0; } -static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) +static int vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); struct amdgpu_device *adev = hwmgr->adev; uint32_t top32, bottom32; - int i; + int i, ret; data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id = FEATURE_DPM_PREFETCHER_BIT; @@ -405,10 +405,17 @@ static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr) } /* Get the SN to turn into a Unique ID */ - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); - smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32); + if (ret) + return ret; + + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32); + if (ret) + return ret; adev->unique_id = ((uint64_t)bottom32 << 32) | top32; + + return 0; } static int vega20_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr) @@ -428,6 +435,7 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr) { struct vega20_hwmgr *data; struct amdgpu_device *adev = hwmgr->adev; + int result; data = kzalloc(sizeof(struct vega20_hwmgr), GFP_KERNEL); if (data == NULL) @@ -453,8 +461,11 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr) vega20_set_features_platform_caps(hwmgr); - vega20_init_dpm_defaults(hwmgr); - + result = vega20_init_dpm_defaults(hwmgr); + if (result) { + pr_err("%s failed\n", __func__); + return result; + } /* Parse pptable data read from VBIOS */ vega20_set_private_data_based_on_pptable(hwmgr); @@ -4084,9 +4095,11 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui if (power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) { struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend); - if (size == 0 && !data->is_custom_profile_set) + + if (size != 10 && size != 0) return -EINVAL; - if (size < 10 && size != 0) + + if (size == 0 && !data->is_custom_profile_set) return -EINVAL; result = vega20_get_activity_monitor_coeff(hwmgr, @@ -4148,6 +4161,8 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui activity_monitor.Fclk_PD_Data_error_coeff = input[8]; activity_monitor.Fclk_PD_Data_error_rate_coeff = input[9]; break; + default: + return -EINVAL; } result = vega20_set_activity_monitor_coeff(hwmgr, diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c index a70d73896649..f9c0f117725d 100644 --- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c +++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c @@ -130,13 +130,17 @@ int vega10_get_enabled_smc_features(struct pp_hwmgr *hwmgr, uint64_t *features_enabled) { uint32_t enabled_features; + int ret; if (features_enabled == NULL) return -EINVAL; - smum_send_msg_to_smc(hwmgr, + ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures, &enabled_features); + if (ret) + return ret; + *features_enabled = enabled_features; return 0; diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c index 1d0693dad818..1a02930d93df 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c @@ -1829,12 +1829,13 @@ static int smu_bump_power_profile_mode(struct smu_context *smu, } static int smu_adjust_power_state_dynamic(struct smu_context *smu, - enum amd_dpm_forced_level level, - bool skip_display_settings) + enum amd_dpm_forced_level level, + bool skip_display_settings, + bool init) { int ret = 0; int index = 0; - long workload; + long workload[1]; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); if (!skip_display_settings) { @@ -1874,10 +1875,10 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu, smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) { index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; - if (smu->power_profile_mode != workload) - smu_bump_power_profile_mode(smu, &workload, 0); + if (init || smu->power_profile_mode != workload[0]) + smu_bump_power_profile_mode(smu, workload, 0); } return ret; @@ -1897,11 +1898,13 @@ static int smu_handle_task(struct smu_context *smu, ret = smu_pre_display_config_changed(smu); if (ret) return ret; - ret = smu_adjust_power_state_dynamic(smu, level, false); + ret = smu_adjust_power_state_dynamic(smu, level, false, false); break; case AMD_PP_TASK_COMPLETE_INIT: + ret = smu_adjust_power_state_dynamic(smu, level, true, true); + break; case AMD_PP_TASK_READJUST_POWER_STATE: - ret = smu_adjust_power_state_dynamic(smu, level, true); + ret = smu_adjust_power_state_dynamic(smu, level, true, false); break; default: break; @@ -1927,7 +1930,7 @@ static int smu_switch_power_profile(void *handle, { struct smu_context *smu = handle; struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm); - long workload; + long workload[1]; uint32_t index; if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled) @@ -1940,17 +1943,17 @@ static int smu_switch_power_profile(void *handle, smu->workload_mask &= ~(1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } else { smu->workload_mask |= (1 << smu->workload_prority[type]); index = fls(smu->workload_mask); index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0; - workload = smu->workload_setting[index]; + workload[0] = smu->workload_setting[index]; } if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL && smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) - smu_bump_power_profile_mode(smu, &workload, 0); + smu_bump_power_profile_mode(smu, workload, 0); return 0; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index ed2112efc6c6..286f4f9bfa35 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -1215,19 +1215,22 @@ static int navi10_get_current_clk_freq_by_table(struct smu_context *smu, value); } -static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) +static int navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type) { PPTable_t *pptable = smu->smu_table.driver_pptable; DpmDescriptor_t *dpm_desc = NULL; - uint32_t clk_index = 0; + int clk_index = 0; clk_index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_CLK, clk_type); + if (clk_index < 0) + return clk_index; + dpm_desc = &pptable->DpmDescriptor[clk_index]; /* 0 - Fine grained DPM, 1 - Discrete DPM */ - return dpm_desc->SnapToDiscrete == 0; + return dpm_desc->SnapToDiscrete == 0 ? 1 : 0; } static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap) @@ -1283,7 +1286,11 @@ static int navi10_emit_clk_levels(struct smu_context *smu, if (ret) return ret; - if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (!ret) { for (i = 0; i < count; i++) { ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value); @@ -1492,7 +1499,11 @@ static int navi10_print_clk_levels(struct smu_context *smu, if (ret) return size; - if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (!ret) { for (i = 0; i < count; i++) { ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value); if (ret) @@ -1661,7 +1672,11 @@ static int navi10_force_clk_levels(struct smu_context *smu, case SMU_UCLK: case SMU_FCLK: /* There is only 2 levels for fine grained DPM */ - if (navi10_is_support_fine_grained_dpm(smu, clk_type)) { + ret = navi10_is_support_fine_grained_dpm(smu, clk_type); + if (ret < 0) + return ret; + + if (ret) { soft_max_level = (soft_max_level >= 1 ? 1 : 0); soft_min_level = (soft_min_level >= 1 ? 1 : 0); } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c index 1b731a9c92d9..c9c0aa6376e3 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c @@ -1003,6 +1003,18 @@ static int vangogh_get_dpm_ultimate_freq(struct smu_context *smu, } } if (min) { + ret = vangogh_get_profiling_clk_mask(smu, + AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK, + NULL, + NULL, + &mclk_mask, + &fclk_mask, + &soc_mask); + if (ret) + goto failed; + + vclk_mask = dclk_mask = 0; + switch (clk_type) { case SMU_UCLK: case SMU_MCLK: @@ -2363,6 +2375,8 @@ static u32 vangogh_set_gfxoff_residency(struct smu_context *smu, bool start) ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_LogGfxOffResidency, start, &residency); + if (ret) + return ret; if (!start) adev->gfx.gfx_off_residency = residency; diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index cd8b0ab0112a..c79bff02a31a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1939,7 +1939,8 @@ static int aldebaran_mode2_reset(struct smu_context *smu) index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG, SMU_MSG_GfxDeviceDriverReset); - + if (index < 0 ) + return -EINVAL; mutex_lock(&smu->message_lock); if (smu_version >= 0x00441400) { ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, SMU_RESET_MODE_2); diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index f3257cf4b06f..3aab1caed2ac 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -79,8 +79,8 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin"); #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4 #define smnPCIE_LC_SPEED_CNTL 0x11140290 -#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xC000 -#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0xE +#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xE0 +#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5 static const int link_width[] = {0, 1, 2, 4, 8, 12, 16}; static const int link_speed[] = {25, 50, 80, 160}; diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c index 451746ebbe71..89f3d6aa72b0 100644 --- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c +++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c @@ -163,6 +163,7 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, struct drm_plane *plane; struct list_head zorder_list; int order = 0, err; + u32 slave_zpos = 0; DRM_DEBUG_ATOMIC("[CRTC:%d:%s] calculating normalized zpos values\n", crtc->base.id, crtc->name); @@ -202,10 +203,13 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc, plane_st->zpos, plane_st->normalized_zpos); /* calculate max slave zorder */ - if (has_bit(drm_plane_index(plane), kcrtc->slave_planes)) + if (has_bit(drm_plane_index(plane), kcrtc->slave_planes)) { + slave_zpos = plane_st->normalized_zpos; + if (to_kplane_st(plane_st)->layer_split) + slave_zpos++; kcrtc_st->max_slave_zorder = - max(plane_st->normalized_zpos, - kcrtc_st->max_slave_zorder); + max(slave_zpos, kcrtc_st->max_slave_zorder); + } } crtc_st->zpos_changed = true; diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c index 8b89e45d2fda..e72524eab4c2 100644 --- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c +++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c @@ -1143,7 +1143,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, u32 reg; u8 *buffer = msg->buffer; unsigned int i; - int num_transferred = 0; int ret; /* Buffer size of AUX CH is 16 bytes */ @@ -1195,7 +1194,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = buffer[i]; analogix_dp_write(dp, ANALOGIX_DP_BUF_DATA_0 + 4 * i, reg); - num_transferred++; } } @@ -1244,7 +1242,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, reg = analogix_dp_read(dp, ANALOGIX_DP_BUF_DATA_0 + 4 * i); buffer[i] = (unsigned char)reg; - num_transferred++; } } @@ -1261,7 +1258,7 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp, (msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_READ) msg->reply = DP_AUX_NATIVE_REPLY_ACK; - return (num_transferred == msg->size) ? num_transferred : -EBUSY; + return msg->size; aux_error: /* if aux err happen, reset aux */ diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c index 55a7fa4670a7..825d0973663a 100644 --- a/drivers/gpu/drm/bridge/lontium-lt8912b.c +++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c @@ -411,22 +411,6 @@ static const struct drm_connector_funcs lt8912_connector_funcs = { .atomic_destroy_state = drm_atomic_helper_connector_destroy_state, }; -static enum drm_mode_status -lt8912_connector_mode_valid(struct drm_connector *connector, - struct drm_display_mode *mode) -{ - if (mode->clock > 150000) - return MODE_CLOCK_HIGH; - - if (mode->hdisplay > 1920) - return MODE_BAD_HVALUE; - - if (mode->vdisplay > 1080) - return MODE_BAD_VVALUE; - - return MODE_OK; -} - static int lt8912_connector_get_modes(struct drm_connector *connector) { struct edid *edid; @@ -454,7 +438,6 @@ static int lt8912_connector_get_modes(struct drm_connector *connector) static const struct drm_connector_helper_funcs lt8912_connector_helper_funcs = { .get_modes = lt8912_connector_get_modes, - .mode_valid = lt8912_connector_mode_valid, }; static void lt8912_bridge_mode_set(struct drm_bridge *bridge, @@ -596,6 +579,23 @@ static void lt8912_bridge_detach(struct drm_bridge *bridge) drm_bridge_hpd_disable(lt->hdmi_port); } +static enum drm_mode_status +lt8912_bridge_mode_valid(struct drm_bridge *bridge, + const struct drm_display_info *info, + const struct drm_display_mode *mode) +{ + if (mode->clock > 150000) + return MODE_CLOCK_HIGH; + + if (mode->hdisplay > 1920) + return MODE_BAD_HVALUE; + + if (mode->vdisplay > 1080) + return MODE_BAD_VVALUE; + + return MODE_OK; +} + static enum drm_connector_status lt8912_bridge_detect(struct drm_bridge *bridge) { @@ -626,6 +626,7 @@ static struct edid *lt8912_bridge_get_edid(struct drm_bridge *bridge, static const struct drm_bridge_funcs lt8912_bridge_funcs = { .attach = lt8912_bridge_attach, .detach = lt8912_bridge_detach, + .mode_valid = lt8912_bridge_mode_valid, .mode_set = lt8912_bridge_mode_set, .enable = lt8912_bridge_enable, .detect = lt8912_bridge_detect, diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c index 926ab5c3c31a..0af2bd8706e4 100644 --- a/drivers/gpu/drm/bridge/tc358767.c +++ b/drivers/gpu/drm/bridge/tc358767.c @@ -1841,7 +1841,7 @@ static irqreturn_t tc_irq_handler(int irq, void *arg) dev_err(tc->dev, "syserr %x\n", stat); } - if (tc->hpd_pin >= 0 && tc->bridge.dev) { + if (tc->hpd_pin >= 0 && tc->bridge.dev && tc->aux.drm_dev) { /* * H is triggered when the GPIO goes high. * diff --git a/drivers/gpu/drm/bridge/tc358768.c b/drivers/gpu/drm/bridge/tc358768.c index 8429b6518b50..aabdb5c74d93 100644 --- a/drivers/gpu/drm/bridge/tc358768.c +++ b/drivers/gpu/drm/bridge/tc358768.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -158,6 +159,7 @@ struct tc358768_priv { u32 frs; /* PLL Freqency range for HSCK (post divider) */ u32 dsiclk; /* pll_clk / 2 */ + u32 pclk; /* incoming pclk rate */ }; static inline struct tc358768_priv *dsi_host_to_tc358768(struct mipi_dsi_host @@ -381,6 +383,7 @@ found: priv->prd = best_prd; priv->frs = frs; priv->dsiclk = best_pll / 2; + priv->pclk = mode->clock * 1000; return 0; } @@ -639,6 +642,28 @@ static u32 tc358768_ps_to_ns(u32 ps) return ps / 1000; } +static u32 tc358768_dpi_to_ns(u32 val, u32 pclk) +{ + return (u32)div_u64((u64)val * NANO, pclk); +} + +/* Convert value in DPI pixel clock units to DSI byte count */ +static u32 tc358768_dpi_to_dsi_bytes(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * priv->dsiclk / 4 * priv->dsi_lanes; + u64 n = priv->pclk; + + return (u32)div_u64(m + n - 1, n); +} + +static u32 tc358768_dsi_bytes_to_ns(struct tc358768_priv *priv, u32 val) +{ + u64 m = (u64)val * NANO; + u64 n = priv->dsiclk / 4 * priv->dsi_lanes; + + return (u32)div_u64(m, n); +} + static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) { struct tc358768_priv *priv = bridge_to_tc358768(bridge); @@ -648,11 +673,19 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) s32 raw_val; const struct drm_display_mode *mode; u32 hsbyteclk_ps, dsiclk_ps, ui_ps; - u32 dsiclk, hsbyteclk, video_start; - const u32 internal_delay = 40; + u32 dsiclk, hsbyteclk; int ret, i; struct videomode vm; struct device *dev = priv->dev; + /* In pixelclock units */ + u32 dpi_htot, dpi_data_start; + /* In byte units */ + u32 dsi_dpi_htot, dsi_dpi_data_start; + u32 dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp; + const u32 dsi_hss = 4; /* HSS is a short packet (4 bytes) */ + /* In hsbyteclk units */ + u32 dsi_vsdly; + const u32 internal_dly = 40; if (mode_flags & MIPI_DSI_CLOCK_NON_CONTINUOUS) { dev_warn_once(dev, "Non-continuous mode unimplemented, falling back to continuous\n"); @@ -687,27 +720,23 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) case MIPI_DSI_FMT_RGB888: val |= (0x3 << 4); hact = vm.hactive * 3; - video_start = (vm.hsync_len + vm.hback_porch) * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_24; break; case MIPI_DSI_FMT_RGB666: val |= (0x4 << 4); hact = vm.hactive * 3; - video_start = (vm.hsync_len + vm.hback_porch) * 3; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_18; break; case MIPI_DSI_FMT_RGB666_PACKED: val |= (0x4 << 4) | BIT(3); hact = vm.hactive * 18 / 8; - video_start = (vm.hsync_len + vm.hback_porch) * 18 / 8; data_type = MIPI_DSI_PIXEL_STREAM_3BYTE_18; break; case MIPI_DSI_FMT_RGB565: val |= (0x5 << 4); hact = vm.hactive * 2; - video_start = (vm.hsync_len + vm.hback_porch) * 2; data_type = MIPI_DSI_PACKED_PIXEL_STREAM_16; break; default: @@ -717,9 +746,152 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) return; } + /* + * There are three important things to make TC358768 work correctly, + * which are not trivial to manage: + * + * 1. Keep the DPI line-time and the DSI line-time as close to each + * other as possible. + * 2. TC358768 goes to LP mode after each line's active area. The DSI + * HFP period has to be long enough for entering and exiting LP mode. + * But it is not clear how to calculate this. + * 3. VSDly (video start delay) has to be long enough to ensure that the + * DSI TX does not start transmitting until we have started receiving + * pixel data from the DPI input. It is not clear how to calculate + * this either. + */ + + dpi_htot = vm.hactive + vm.hfront_porch + vm.hsync_len + vm.hback_porch; + dpi_data_start = vm.hsync_len + vm.hback_porch; + + dev_dbg(dev, "dpi horiz timing (pclk): %u + %u + %u + %u = %u\n", + vm.hsync_len, vm.hback_porch, vm.hactive, vm.hfront_porch, + dpi_htot); + + dev_dbg(dev, "dpi horiz timing (ns): %u + %u + %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(vm.hactive, vm.pixelclock), + tc358768_dpi_to_ns(vm.hfront_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_htot, vm.pixelclock)); + + dev_dbg(dev, "dpi data start (ns): %u + %u = %u\n", + tc358768_dpi_to_ns(vm.hsync_len, vm.pixelclock), + tc358768_dpi_to_ns(vm.hback_porch, vm.pixelclock), + tc358768_dpi_to_ns(dpi_data_start, vm.pixelclock)); + + dsi_dpi_htot = tc358768_dpi_to_dsi_bytes(priv, dpi_htot); + dsi_dpi_data_start = tc358768_dpi_to_dsi_bytes(priv, dpi_data_start); + + if (dsi_dev->mode_flags & MIPI_DSI_MODE_VIDEO_SYNC_PULSE) { + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, vm.hsync_len); + dsi_hbp = tc358768_dpi_to_dsi_bytes(priv, vm.hback_porch); + } else { + /* HBP is included in HSW in event mode */ + dsi_hbp = 0; + dsi_hsw = tc358768_dpi_to_dsi_bytes(priv, + vm.hsync_len + + vm.hback_porch); + + /* + * The pixel packet includes the actual pixel data, and: + * DSI packet header = 4 bytes + * DCS code = 1 byte + * DSI packet footer = 2 bytes + */ + dsi_hact = hact + 4 + 1 + 2; + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + /* + * Here we should check if HFP is long enough for entering LP + * and exiting LP, but it's not clear how to calculate that. + * Instead, this is a naive algorithm that just adjusts the HFP + * and HSW so that HFP is (at least) roughly 2/3 of the total + * blanking time. + */ + if (dsi_hfp < (dsi_hfp + dsi_hsw + dsi_hss) * 2 / 3) { + u32 old_hfp = dsi_hfp; + u32 old_hsw = dsi_hsw; + u32 tot = dsi_hfp + dsi_hsw + dsi_hss; + + dsi_hsw = tot / 3; + + /* + * Seems like sometimes HSW has to be divisible by num-lanes, but + * not always... + */ + dsi_hsw = roundup(dsi_hsw, priv->dsi_lanes); + + dsi_hfp = dsi_dpi_htot - dsi_hact - dsi_hsw - dsi_hss; + + dev_dbg(dev, + "hfp too short, adjusting dsi hfp and dsi hsw from %u, %u to %u, %u\n", + old_hfp, old_hsw, dsi_hfp, dsi_hsw); + } + + dev_dbg(dev, + "dsi horiz timing (bytes): %u, %u + %u + %u + %u = %u\n", + dsi_hss, dsi_hsw, dsi_hbp, dsi_hact, dsi_hfp, + dsi_hss + dsi_hsw + dsi_hbp + dsi_hact + dsi_hfp); + + dev_dbg(dev, "dsi horiz timing (ns): %u + %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_hact), + tc358768_dsi_bytes_to_ns(priv, dsi_hfp), + tc358768_dsi_bytes_to_ns(priv, dsi_hss + dsi_hsw + + dsi_hbp + dsi_hact + dsi_hfp)); + } + + /* VSDly calculation */ + + /* Start with the HW internal delay */ + dsi_vsdly = internal_dly; + + /* Convert to byte units as the other variables are in byte units */ + dsi_vsdly *= priv->dsi_lanes; + + /* Do we need more delay, in addition to the internal? */ + if (dsi_dpi_data_start > dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp) { + dsi_vsdly = dsi_dpi_data_start - dsi_hss - dsi_hsw - dsi_hbp; + dsi_vsdly = roundup(dsi_vsdly, priv->dsi_lanes); + } + + dev_dbg(dev, "dsi data start (bytes) %u + %u + %u + %u = %u\n", + dsi_vsdly, dsi_hss, dsi_hsw, dsi_hbp, + dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp); + + dev_dbg(dev, "dsi data start (ns) %u + %u + %u + %u = %u\n", + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly), + tc358768_dsi_bytes_to_ns(priv, dsi_hss), + tc358768_dsi_bytes_to_ns(priv, dsi_hsw), + tc358768_dsi_bytes_to_ns(priv, dsi_hbp), + tc358768_dsi_bytes_to_ns(priv, dsi_vsdly + dsi_hss + dsi_hsw + dsi_hbp)); + + /* Convert back to hsbyteclk */ + dsi_vsdly /= priv->dsi_lanes; + + /* + * The docs say that there is an internal delay of 40 cycles. + * However, we get underflows if we follow that rule. If we + * instead ignore the internal delay, things work. So either + * the docs are wrong or the calculations are wrong. + * + * As a temporary fix, add the internal delay here, to counter + * the subtraction when writing the register. + */ + dsi_vsdly += internal_dly; + + /* Clamp to the register max */ + if (dsi_vsdly - internal_dly > 0x3ff) { + dev_warn(dev, "VSDly too high, underflows likely\n"); + dsi_vsdly = 0x3ff + internal_dly; + } + /* VSDly[9:0] */ - video_start = max(video_start, internal_delay + 1) - internal_delay; - tc358768_write(priv, TC358768_VSDLY, video_start); + tc358768_write(priv, TC358768_VSDLY, dsi_vsdly - internal_dly); tc358768_write(priv, TC358768_DATAFMT, val); tc358768_write(priv, TC358768_DSITX_DT, data_type); @@ -827,18 +999,6 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) /* vbp */ tc358768_write(priv, TC358768_DSI_VBPR, vm.vback_porch); - - /* hsw * byteclk * ndl / pclk */ - val = (u32)div_u64(vm.hsync_len * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HSW, val); - - /* hbp * byteclk * ndl / pclk */ - val = (u32)div_u64(vm.hback_porch * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HBPR, val); } else { /* Set event mode */ tc358768_write(priv, TC358768_DSI_EVENT, 1); @@ -852,17 +1012,14 @@ static void tc358768_bridge_pre_enable(struct drm_bridge *bridge) /* vbp (not used in event mode) */ tc358768_write(priv, TC358768_DSI_VBPR, 0); - - /* (hsw + hbp) * byteclk * ndl / pclk */ - val = (u32)div_u64((vm.hsync_len + vm.hback_porch) * - (u64)hsbyteclk * priv->dsi_lanes, - vm.pixelclock); - tc358768_write(priv, TC358768_DSI_HSW, val); - - /* hbp (not used in event mode) */ - tc358768_write(priv, TC358768_DSI_HBPR, 0); } + /* hsw (bytes) */ + tc358768_write(priv, TC358768_DSI_HSW, dsi_hsw); + + /* hbp (bytes) */ + tc358768_write(priv, TC358768_DSI_HBPR, dsi_hbp); + /* hact (bytes) */ tc358768_write(priv, TC358768_DSI_HACT, hact); diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c index 72b2b171e533..4204d1f93013 100644 --- a/drivers/gpu/drm/display/drm_dp_mst_topology.c +++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c @@ -2923,7 +2923,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, /* FIXME: Actually do some real error handling here */ ret = drm_dp_mst_wait_tx_reply(mstb, txmsg); - if (ret <= 0) { + if (ret < 0) { drm_err(mgr->dev, "Sending link address failed with %d\n", ret); goto out; } @@ -2975,7 +2975,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr, mutex_unlock(&mgr->lock); out: - if (ret <= 0) + if (ret < 0) mstb->link_address_sent = false; kfree(txmsg); return ret < 0 ? ret : changed; @@ -4024,6 +4024,7 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) { const struct drm_dp_connection_status_notify *conn_stat = &up_req->msg.u.conn_stat; + bool handle_csn; drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n", conn_stat->port_number, @@ -4032,6 +4033,16 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr) conn_stat->message_capability_status, conn_stat->input_port, conn_stat->peer_device_type); + + mutex_lock(&mgr->probe_lock); + handle_csn = mgr->mst_primary->link_address_sent; + mutex_unlock(&mgr->probe_lock); + + if (!handle_csn) { + drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it."); + kfree(up_req); + goto out; + } } else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) { const struct drm_dp_resource_status_notify *res_stat = &up_req->msg.u.resource_stat; diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 79730fa1dd8e..b620a0da2d02 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -567,7 +567,7 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, &state->fb_damage_clips, val, -1, - sizeof(struct drm_rect), + sizeof(struct drm_mode_rect), &replaced); return ret; } else if (property == plane->scaling_filter_property) { diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c index 9a65806047b5..718acff90e2d 100644 --- a/drivers/gpu/drm/drm_client_modeset.c +++ b/drivers/gpu/drm/drm_client_modeset.c @@ -873,6 +873,11 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width, kfree(modeset->mode); modeset->mode = drm_mode_duplicate(dev, mode); + if (!modeset->mode) { + ret = -ENOMEM; + break; + } + drm_connector_get(connector); modeset->connectors[modeset->num_connectors++] = connector; modeset->x = offset->x; diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c index cb90e70d85e8..65f9f66933bb 100644 --- a/drivers/gpu/drm/drm_crtc.c +++ b/drivers/gpu/drm/drm_crtc.c @@ -904,6 +904,7 @@ out: connector_set = NULL; fb = NULL; mode = NULL; + num_connectors = 0; DRM_MODESET_LOCK_ALL_END(dev, ctx, ret); diff --git a/drivers/gpu/drm/drm_gem_shmem_helper.c b/drivers/gpu/drm/drm_gem_shmem_helper.c index e33f06bb66eb..fb8093577245 100644 --- a/drivers/gpu/drm/drm_gem_shmem_helper.c +++ b/drivers/gpu/drm/drm_gem_shmem_helper.c @@ -638,6 +638,9 @@ int drm_gem_shmem_mmap(struct drm_gem_shmem_object *shmem, struct vm_area_struct return ret; } + if (is_cow_mapping(vma->vm_flags)) + return -EINVAL; + ret = drm_gem_shmem_get_pages(shmem); if (ret) return ret; diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c index 426bbee2d9f5..5b2506c65e95 100644 --- a/drivers/gpu/drm/drm_panel_orientation_quirks.c +++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c @@ -202,6 +202,24 @@ static const struct dmi_system_id orientation_data[] = { DMI_MATCH(DMI_BOARD_NAME, "NEXT"), }, .driver_data = (void *)&lcd800x1280_rightside_up, + }, { /* AYA NEO KUN */ + .matches = { + DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AYANEO"), + DMI_MATCH(DMI_BOARD_NAME, "KUN"), + }, + .driver_data = (void *)&lcd1600x2560_rightside_up, + }, { /* AYN Loki Max */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Max"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, + }, { /* AYN Loki Zero */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Zero"), + }, + .driver_data = (void *)&lcd1080x1920_leftside_up, }, { /* Chuwi HiBook (CWI514) */ .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"), @@ -408,6 +426,12 @@ static const struct dmi_system_id orientation_data[] = { DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"), }, .driver_data = (void *)&lcd1600x2560_leftside_up, + }, { /* OrangePi Neo */ + .matches = { + DMI_EXACT_MATCH(DMI_SYS_VENDOR, "OrangePi"), + DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "NEO-01"), + }, + .driver_data = (void *)&lcd1200x1920_rightside_up, }, { /* Samsung GalaxyBook 10.6 */ .matches = { DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."), diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c index 5b93c11895bb..aab76334083e 100644 --- a/drivers/gpu/drm/drm_print.c +++ b/drivers/gpu/drm/drm_print.c @@ -100,8 +100,9 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str) copy = iterator->remain; /* Copy out the bit of the string that we need */ - memcpy(iterator->data, - str + (iterator->start - iterator->offset), copy); + if (iterator->data) + memcpy(iterator->data, + str + (iterator->start - iterator->offset), copy); iterator->offset = iterator->start + copy; iterator->remain -= copy; @@ -110,7 +111,8 @@ void __drm_puts_coredump(struct drm_printer *p, const char *str) len = min_t(ssize_t, strlen(str), iterator->remain); - memcpy(iterator->data + pos, str, len); + if (iterator->data) + memcpy(iterator->data + pos, str, len); iterator->offset += len; iterator->remain -= len; @@ -140,8 +142,9 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf) if ((iterator->offset >= iterator->start) && (len < iterator->remain)) { ssize_t pos = iterator->offset - iterator->start; - snprintf(((char *) iterator->data) + pos, - iterator->remain, "%pV", vaf); + if (iterator->data) + snprintf(((char *) iterator->data) + pos, + iterator->remain, "%pV", vaf); iterator->offset += len; iterator->remain -= len; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c index 5cf13e52f7c9..23d5058eca8d 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c @@ -355,9 +355,11 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj) static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op) { - if (op & ETNA_PREP_READ) + op &= ETNA_PREP_READ | ETNA_PREP_WRITE; + + if (op == ETNA_PREP_READ) return DMA_FROM_DEVICE; - else if (op & ETNA_PREP_WRITE) + else if (op == ETNA_PREP_WRITE) return DMA_TO_DEVICE; else return DMA_BIDIRECTIONAL; diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c index 72e2553fbc98..5d506767b8f2 100644 --- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c +++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c @@ -38,9 +38,6 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job u32 dma_addr; int change; - /* block scheduler */ - drm_sched_stop(&gpu->sched, sched_job); - /* * If the GPU managed to complete this jobs fence, the timout is * spurious. Bail out. @@ -62,6 +59,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job goto out_no_timeout; } + /* block scheduler */ + drm_sched_stop(&gpu->sched, sched_job); + if(sched_job) drm_sched_increase_karma(sched_job); @@ -75,8 +75,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job return DRM_GPU_SCHED_STAT_NOMINAL; out_no_timeout: - /* restart scheduler after GPU is usable again */ - drm_sched_start(&gpu->sched, true); + list_add(&sched_job->list, &sched_job->sched->pending_list); return DRM_GPU_SCHED_STAT_NOMINAL; } diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c index 68ea92742b06..f8b45fc5b15a 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c +++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c @@ -1173,7 +1173,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data) struct exynos_drm_ipp *ipp = &ctx->ipp; ctx->drm_dev = drm_dev; - ctx->drm_dev = drm_dev; + ipp->drm_dev = drm_dev; exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv); exynos_drm_ipp_register(dev, ipp, &ipp_funcs, diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c index be6efcaaa3b3..c9ad16960e82 100644 --- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c +++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c @@ -309,6 +309,9 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c index 7ee6c8ce103b..9842de0dad3a 100644 --- a/drivers/gpu/drm/gma500/psb_intel_lvds.c +++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c @@ -502,6 +502,9 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector) if (mode_dev->panel_fixed_mode != NULL) { struct drm_display_mode *mode = drm_mode_duplicate(dev, mode_dev->panel_fixed_mode); + if (!mode) + return 0; + drm_mode_probed_add(connector, mode); return 1; } diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index a27563bfd909..3f65d890b8a9 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -4089,6 +4089,8 @@ int intel_dp_retrain_link(struct intel_encoder *encoder, !intel_dp_mst_is_master_trans(crtc_state)) continue; + intel_dp->link_trained = false; + intel_dp_check_frl_training(intel_dp); intel_dp_pcon_dsc_configure(intel_dp, crtc_state); intel_dp_start_link_train(intel_dp, crtc_state); diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c index 3d3efcf02011..1d9e4534287b 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c +++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c @@ -103,12 +103,26 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable) return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1; } -static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +static bool intel_dp_lttpr_transparent_mode_enabled(struct intel_dp *intel_dp) +{ + return intel_dp->lttpr_common_caps[DP_PHY_REPEATER_MODE - + DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] == + DP_PHY_REPEATER_MODE_TRANSPARENT; +} + +/* + * Read the LTTPR common capabilities and switch the LTTPR PHYs to + * non-transparent mode if this is supported. Preserve the + * transparent/non-transparent mode on an active link. + * + * Return the number of detected LTTPRs in non-transparent mode or 0 if the + * LTTPRs are in transparent mode or the detection failed. + */ +static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) { struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base; struct drm_i915_private *i915 = to_i915(encoder->base.dev); int lttpr_count; - int i; if (!intel_dp_read_lttpr_common_caps(intel_dp, dpcd)) return 0; @@ -122,6 +136,19 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI if (lttpr_count == 0) return 0; + /* + * Don't change the mode on an active link, to prevent a loss of link + * synchronization. See DP Standard v2.0 3.6.7. about the LTTPR + * resetting its internal state when the mode is changed from + * non-transparent to transparent. + */ + if (intel_dp->link_trained) { + if (lttpr_count < 0 || intel_dp_lttpr_transparent_mode_enabled(intel_dp)) + goto out_reset_lttpr_count; + + return lttpr_count; + } + /* * See DP Standard v2.0 3.6.6.1. about the explicit disabling of * non-transparent mode and the disable->enable non-transparent mode @@ -143,11 +170,25 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI encoder->base.base.id, encoder->base.name); intel_dp_set_lttpr_transparent_mode(intel_dp, true); - intel_dp_reset_lttpr_count(intel_dp); - return 0; + goto out_reset_lttpr_count; } + return lttpr_count; + +out_reset_lttpr_count: + intel_dp_reset_lttpr_count(intel_dp); + + return 0; +} + +static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE]) +{ + int lttpr_count; + int i; + + lttpr_count = intel_dp_init_lttpr_phys(intel_dp, dpcd); + for (i = 0; i < lttpr_count; i++) intel_dp_read_lttpr_phy_caps(intel_dp, dpcd, DP_PHY_LTTPR(i)); @@ -1435,8 +1476,9 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp, { bool passed; /* - * TODO: Reiniting LTTPRs here won't be needed once proper connector - * HW state readout is added. + * Reinit the LTTPRs here to ensure that they are switched to + * non-transparent mode. During an earlier LTTPR detection this + * could've been prevented by an active link. */ int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp); diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c index 64dd603dc69a..ec0ef3ff9e6a 100644 --- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c +++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c @@ -1552,7 +1552,7 @@ static void skl_wrpll_params_populate(struct skl_wrpll_params *params, } static int -skl_ddi_calculate_wrpll(int clock /* in Hz */, +skl_ddi_calculate_wrpll(int clock, int ref_clock, struct skl_wrpll_params *wrpll_params) { @@ -1577,7 +1577,7 @@ skl_ddi_calculate_wrpll(int clock /* in Hz */, }; unsigned int dco, d, i; unsigned int p0, p1, p2; - u64 afe_clock = clock * 5; /* AFE Clock is 5x Pixel clock */ + u64 afe_clock = (u64)clock * 1000 * 5; /* AFE Clock is 5x Pixel clock, in Hz */ for (d = 0; d < ARRAY_SIZE(dividers); d++) { for (dco = 0; dco < ARRAY_SIZE(dco_central_freq); dco++) { @@ -1709,7 +1709,7 @@ static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state) ctrl1 |= DPLL_CTRL1_HDMI_MODE(0); - ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000, + ret = skl_ddi_calculate_wrpll(crtc_state->port_clock, i915->display.dpll.ref_clks.nssc, &wrpll_params); if (ret) return ret; diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h index 2a3733e8966c..2702cc8c88d8 100644 --- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h +++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h @@ -249,7 +249,7 @@ #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \ (GRAPHICS_VER(dev_priv) >= 12 ? \ TRANS_HDCP2_STREAM_STATUS(trans) : \ - PIPE_HDCP2_STREAM_STATUS(pipe)) + PIPE_HDCP2_STREAM_STATUS(port)) #define _PORTA_HDCP2_AUTH_STREAM 0x66F00 #define _PORTB_HDCP2_AUTH_STREAM 0x66F04 diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c index d7e30d889a5c..7e9310d01dfd 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c @@ -290,6 +290,41 @@ out: return i915_error_to_vmf_fault(err); } +static void set_address_limits(struct vm_area_struct *area, + struct i915_vma *vma, + unsigned long obj_offset, + unsigned long *start_vaddr, + unsigned long *end_vaddr) +{ + unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */ + long start, end; /* memory boundaries */ + + /* + * Let's move into the ">> PAGE_SHIFT" + * domain to be sure not to lose bits + */ + vm_start = area->vm_start >> PAGE_SHIFT; + vm_end = area->vm_end >> PAGE_SHIFT; + vma_size = vma->size >> PAGE_SHIFT; + + /* + * Calculate the memory boundaries by considering the offset + * provided by the user during memory mapping and the offset + * provided for the partial mapping. + */ + start = vm_start; + start -= obj_offset; + start += vma->gtt_view.partial.offset; + end = start + vma_size; + + start = max_t(long, start, vm_start); + end = min_t(long, end, vm_end); + + /* Let's move back into the "<< PAGE_SHIFT" domain */ + *start_vaddr = (unsigned long)start << PAGE_SHIFT; + *end_vaddr = (unsigned long)end << PAGE_SHIFT; +} + static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) { #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT) @@ -302,14 +337,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf) struct i915_ggtt *ggtt = to_gt(i915)->ggtt; bool write = area->vm_flags & VM_WRITE; struct i915_gem_ww_ctx ww; + unsigned long obj_offset; + unsigned long start, end; /* memory boundaries */ intel_wakeref_t wakeref; struct i915_vma *vma; pgoff_t page_offset; + unsigned long pfn; int srcu; int ret; - /* We don't use vmf->pgoff since that has the fake offset */ + obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node); page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT; + page_offset += obj_offset; trace_i915_gem_object_fault(obj, page_offset, true, write); @@ -393,12 +432,14 @@ retry: if (ret) goto err_unpin; + set_address_limits(area, vma, obj_offset, &start, &end); + + pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT; + pfn += (start - area->vm_start) >> PAGE_SHIFT; + pfn += obj_offset - vma->gtt_view.partial.offset; + /* Finally, remap it using the new GTT offset */ - ret = remap_io_mapping(area, - area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT), - (ggtt->gmadr.start + vma->node.start) >> PAGE_SHIFT, - min_t(u64, vma->size, area->vm_end - area->vm_start), - &ggtt->iomap); + ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap); if (ret) goto err_fence; @@ -928,53 +969,15 @@ static struct file *mmap_singleton(struct drm_i915_private *i915) return file; } -/* - * This overcomes the limitation in drm_gem_mmap's assignment of a - * drm_gem_object as the vma->vm_private_data. Since we need to - * be able to resolve multiple mmap offsets which could be tied - * to a single gem object. - */ -int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) +static int +i915_gem_object_mmap(struct drm_i915_gem_object *obj, + struct i915_mmap_offset *mmo, + struct vm_area_struct *vma) { - struct drm_vma_offset_node *node; - struct drm_file *priv = filp->private_data; - struct drm_device *dev = priv->minor->dev; - struct drm_i915_gem_object *obj = NULL; - struct i915_mmap_offset *mmo = NULL; + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct drm_device *dev = &i915->drm; struct file *anon; - if (drm_dev_is_unplugged(dev)) - return -ENODEV; - - rcu_read_lock(); - drm_vma_offset_lock_lookup(dev->vma_offset_manager); - node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager, - vma->vm_pgoff, - vma_pages(vma)); - if (node && drm_vma_node_is_allowed(node, priv)) { - /* - * Skip 0-refcnted objects as it is in the process of being - * destroyed and will be invalid when the vma manager lock - * is released. - */ - if (!node->driver_private) { - mmo = container_of(node, struct i915_mmap_offset, vma_node); - obj = i915_gem_object_get_rcu(mmo->obj); - - GEM_BUG_ON(obj && obj->ops->mmap_ops); - } else { - obj = i915_gem_object_get_rcu - (container_of(node, struct drm_i915_gem_object, - base.vma_node)); - - GEM_BUG_ON(obj && !obj->ops->mmap_ops); - } - } - drm_vma_offset_unlock_lookup(dev->vma_offset_manager); - rcu_read_unlock(); - if (!obj) - return node ? -EACCES : -EINVAL; - if (i915_gem_object_is_readonly(obj)) { if (vma->vm_flags & VM_WRITE) { i915_gem_object_put(obj); @@ -1006,7 +1009,7 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) if (obj->ops->mmap_ops) { vma->vm_page_prot = pgprot_decrypted(vm_get_page_prot(vma->vm_flags)); vma->vm_ops = obj->ops->mmap_ops; - vma->vm_private_data = node->driver_private; + vma->vm_private_data = obj->base.vma_node.driver_private; return 0; } @@ -1044,6 +1047,93 @@ int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) return 0; } +/* + * This overcomes the limitation in drm_gem_mmap's assignment of a + * drm_gem_object as the vma->vm_private_data. Since we need to + * be able to resolve multiple mmap offsets which could be tied + * to a single gem object. + */ +int i915_gem_mmap(struct file *filp, struct vm_area_struct *vma) +{ + struct drm_vma_offset_node *node; + struct drm_file *priv = filp->private_data; + struct drm_device *dev = priv->minor->dev; + struct drm_i915_gem_object *obj = NULL; + struct i915_mmap_offset *mmo = NULL; + + if (drm_dev_is_unplugged(dev)) + return -ENODEV; + + rcu_read_lock(); + drm_vma_offset_lock_lookup(dev->vma_offset_manager); + node = drm_vma_offset_exact_lookup_locked(dev->vma_offset_manager, + vma->vm_pgoff, + vma_pages(vma)); + if (node && drm_vma_node_is_allowed(node, priv)) { + /* + * Skip 0-refcnted objects as it is in the process of being + * destroyed and will be invalid when the vma manager lock + * is released. + */ + if (!node->driver_private) { + mmo = container_of(node, struct i915_mmap_offset, vma_node); + obj = i915_gem_object_get_rcu(mmo->obj); + + GEM_BUG_ON(obj && obj->ops->mmap_ops); + } else { + obj = i915_gem_object_get_rcu + (container_of(node, struct drm_i915_gem_object, + base.vma_node)); + + GEM_BUG_ON(obj && !obj->ops->mmap_ops); + } + } + drm_vma_offset_unlock_lookup(dev->vma_offset_manager); + rcu_read_unlock(); + if (!obj) + return node ? -EACCES : -EINVAL; + + return i915_gem_object_mmap(obj, mmo, vma); +} + +int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma) +{ + struct drm_i915_private *i915 = to_i915(obj->base.dev); + struct drm_device *dev = &i915->drm; + struct i915_mmap_offset *mmo = NULL; + enum i915_mmap_type mmap_type; + struct i915_ggtt *ggtt = to_gt(i915)->ggtt; + + if (drm_dev_is_unplugged(dev)) + return -ENODEV; + + /* handle ttm object */ + if (obj->ops->mmap_ops) { + /* + * ttm fault handler, ttm_bo_vm_fault_reserved() uses fake offset + * to calculate page offset so set that up. + */ + vma->vm_pgoff += drm_vma_node_start(&obj->base.vma_node); + } else { + /* handle stolen and smem objects */ + mmap_type = i915_ggtt_has_aperture(ggtt) ? I915_MMAP_TYPE_GTT : I915_MMAP_TYPE_WC; + mmo = mmap_offset_attach(obj, mmap_type, NULL); + if (IS_ERR(mmo)) + return PTR_ERR(mmo); + + vma->vm_pgoff += drm_vma_node_start(&mmo->vma_node); + } + + /* + * When we install vm_ops for mmap we are too late for + * the vm_ops->open() which increases the ref_count of + * this obj and then it gets decreased by the vm_ops->close(). + * To balance this increase the obj ref_count here. + */ + obj = i915_gem_object_get(obj); + return i915_gem_object_mmap(obj, mmo, vma); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/i915_gem_mman.c" #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.h b/drivers/gpu/drm/i915/gem/i915_gem_mman.h index 1fa91b3033b3..196417fd0f5c 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_mman.h +++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.h @@ -29,5 +29,5 @@ void i915_gem_object_release_mmap_gtt(struct drm_i915_gem_object *obj); void i915_gem_object_runtime_pm_release_mmap_offset(struct drm_i915_gem_object *obj); void i915_gem_object_release_mmap_offset(struct drm_i915_gem_object *obj); - +int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma); #endif diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c index be4c081e7e13..8aedb423dad3 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c @@ -1058,7 +1058,7 @@ static vm_fault_t vm_fault_ttm(struct vm_fault *vmf) spin_unlock(&to_i915(obj->base.dev)->runtime_pm.lmem_userfault_lock); } - if (wakeref & CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND) + if (wakeref && CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND != 0) intel_wakeref_auto(&to_i915(obj->base.dev)->runtime_pm.userfault_wakeref, msecs_to_jiffies_timeout(CONFIG_DRM_I915_USERFAULT_AUTOSUSPEND)); diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c index eae138b9f2df..321dbecba0f3 100644 --- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c +++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c @@ -3313,11 +3313,7 @@ static void remove_from_engine(struct i915_request *rq) static bool can_preempt(struct intel_engine_cs *engine) { - if (GRAPHICS_VER(engine->i915) > 8) - return true; - - /* GPGPU on bdw requires extra w/a; not implemented */ - return engine->class != RENDER_CLASS; + return GRAPHICS_VER(engine->i915) > 8; } static void kick_execlists(const struct i915_request *rq, int prio) diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c index fecdc7ea78eb..56df4c4a8a1a 100644 --- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c +++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c @@ -2603,9 +2603,9 @@ static void prepare_context_registration_info_v70(struct intel_context *ce, ce->parallel.guc.wqi_tail = 0; ce->parallel.guc.wqi_head = 0; - wq_desc_offset = i915_ggtt_offset(ce->state) + + wq_desc_offset = (u64)i915_ggtt_offset(ce->state) + __get_parent_scratch_offset(ce); - wq_base_offset = i915_ggtt_offset(ce->state) + + wq_base_offset = (u64)i915_ggtt_offset(ce->state) + __get_wq_offset(ce); info->wq_desc_lo = lower_32_bits(wq_desc_offset); info->wq_desc_hi = upper_32_bits(wq_desc_offset); diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c index 6fc0d1b89690..e664f8e461e6 100644 --- a/drivers/gpu/drm/i915/i915_sw_fence.c +++ b/drivers/gpu/drm/i915/i915_sw_fence.c @@ -51,7 +51,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence) debug_object_init(fence, &i915_sw_fence_debug_descr); } -static inline void debug_fence_init_onstack(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence) { debug_object_init_on_stack(fence, &i915_sw_fence_debug_descr); } @@ -77,7 +77,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence) debug_object_destroy(fence, &i915_sw_fence_debug_descr); } -static inline void debug_fence_free(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence) { debug_object_free(fence, &i915_sw_fence_debug_descr); smp_wmb(); /* flush the change in state before reallocation */ @@ -94,7 +94,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence) { } -static inline void debug_fence_init_onstack(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence) { } @@ -115,7 +115,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence) { } -static inline void debug_fence_free(struct i915_sw_fence *fence) +static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence) { } diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c index 39cab4a55f57..53ac94bdf475 100644 --- a/drivers/gpu/drm/lima/lima_drv.c +++ b/drivers/gpu/drm/lima/lima_drv.c @@ -489,3 +489,4 @@ module_platform_driver(lima_platform_driver); MODULE_AUTHOR("Lima Project Developers"); MODULE_DESCRIPTION("Lima DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); diff --git a/drivers/gpu/drm/lima/lima_gp.c b/drivers/gpu/drm/lima/lima_gp.c index ca3842f71984..82071835ec9e 100644 --- a/drivers/gpu/drm/lima/lima_gp.c +++ b/drivers/gpu/drm/lima/lima_gp.c @@ -166,6 +166,11 @@ static void lima_gp_task_run(struct lima_sched_pipe *pipe, gp_write(LIMA_GP_CMD, cmd); } +static int lima_gp_bus_stop_poll(struct lima_ip *ip) +{ + return !!(gp_read(LIMA_GP_STATUS) & LIMA_GP_STATUS_BUS_STOPPED); +} + static int lima_gp_hard_reset_poll(struct lima_ip *ip) { gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC01A0000); @@ -179,6 +184,13 @@ static int lima_gp_hard_reset(struct lima_ip *ip) gp_write(LIMA_GP_PERF_CNT_0_LIMIT, 0xC0FFE000); gp_write(LIMA_GP_INT_MASK, 0); + + gp_write(LIMA_GP_CMD, LIMA_GP_CMD_STOP_BUS); + ret = lima_poll_timeout(ip, lima_gp_bus_stop_poll, 10, 100); + if (ret) { + dev_err(dev->dev, "%s bus stop timeout\n", lima_ip_name(ip)); + return ret; + } gp_write(LIMA_GP_CMD, LIMA_GP_CMD_RESET); ret = lima_poll_timeout(ip, lima_gp_hard_reset_poll, 10, 100); if (ret) { diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c index beaaf44004cf..aba26ec9a142 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c @@ -65,6 +65,8 @@ struct mtk_drm_crtc { /* lock for display hardware access */ struct mutex hw_lock; bool config_updating; + /* lock for config_updating to cmd buffer */ + spinlock_t config_lock; }; struct mtk_crtc_state { @@ -102,11 +104,16 @@ static void mtk_drm_crtc_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) static void mtk_drm_finish_page_flip(struct mtk_drm_crtc *mtk_crtc) { + unsigned long flags; + drm_crtc_handle_vblank(&mtk_crtc->base); + + spin_lock_irqsave(&mtk_crtc->config_lock, flags); if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) { mtk_drm_crtc_finish_page_flip(mtk_crtc); mtk_crtc->pending_needs_vblank = false; } + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); } #if IS_REACHABLE(CONFIG_MTK_CMDQ) @@ -289,12 +296,19 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) struct mtk_drm_crtc *mtk_crtc = container_of(cmdq_cl, struct mtk_drm_crtc, cmdq_client); struct mtk_crtc_state *state; unsigned int i; + unsigned long flags; if (data->sta < 0) return; state = to_mtk_crtc_state(mtk_crtc->base.state); + spin_lock_irqsave(&mtk_crtc->config_lock, flags); + if (mtk_crtc->config_updating) { + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + goto ddp_cmdq_cb_out; + } + state->pending_config = false; if (mtk_crtc->pending_planes) { @@ -321,6 +335,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg) mtk_crtc->pending_async_planes = false; } + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + +ddp_cmdq_cb_out: + mtk_crtc->cmdq_vblank_cnt = 0; wake_up(&mtk_crtc->cb_blocking_queue); } @@ -426,6 +444,7 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc) { struct drm_device *drm = mtk_crtc->base.dev; struct drm_crtc *crtc = &mtk_crtc->base; + unsigned long flags; int i; for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) { @@ -452,10 +471,10 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_drm_crtc *mtk_crtc) pm_runtime_put(drm->dev); if (crtc->state->event && !crtc->state->active) { - spin_lock_irq(&crtc->dev->event_lock); + spin_lock_irqsave(&crtc->dev->event_lock, flags); drm_crtc_send_vblank_event(crtc, crtc->state->event); crtc->state->event = NULL; - spin_unlock_irq(&crtc->dev->event_lock); + spin_unlock_irqrestore(&crtc->dev->event_lock, flags); } } @@ -544,9 +563,14 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc, struct mtk_drm_private *priv = crtc->dev->dev_private; unsigned int pending_planes = 0, pending_async_planes = 0; int i; + unsigned long flags; mutex_lock(&mtk_crtc->hw_lock); + + spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = true; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + if (needs_vblank) mtk_crtc->pending_needs_vblank = true; @@ -600,7 +624,10 @@ static void mtk_drm_crtc_update_config(struct mtk_drm_crtc *mtk_crtc, mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0); } #endif + spin_lock_irqsave(&mtk_crtc->config_lock, flags); mtk_crtc->config_updating = false; + spin_unlock_irqrestore(&mtk_crtc->config_lock, flags); + mutex_unlock(&mtk_crtc->hw_lock); } @@ -971,6 +998,7 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev, drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size); priv->num_pipes++; mutex_init(&mtk_crtc->hw_lock); + spin_lock_init(&mtk_crtc->config_lock); #if IS_REACHABLE(CONFIG_MTK_CMDQ) mtk_crtc->cmdq_client.client.dev = mtk_crtc->mmsys_dev; diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index 25639fbfd374..905275df0980 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -598,6 +598,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = { .data = (void *)MTK_DISP_OVL }, { .compatible = "mediatek,mt8192-disp-ovl", .data = (void *)MTK_DISP_OVL }, + { .compatible = "mediatek,mt8195-disp-ovl", + .data = (void *)MTK_DISP_OVL }, { .compatible = "mediatek,mt8183-disp-ovl-2l", .data = (void *)MTK_DISP_OVL_2L }, { .compatible = "mediatek,mt8192-disp-ovl-2l", diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c index c4a0203d17e3..30d361671aa9 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c @@ -157,6 +157,8 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane, plane->state->src_y = new_state->src_y; plane->state->src_h = new_state->src_h; plane->state->src_w = new_state->src_w; + plane->state->dst.x1 = new_state->dst.x1; + plane->state->dst.y1 = new_state->dst.y1; mtk_plane_update_new_state(new_state, new_plane_state); swap(plane->state->fb, new_state->fb); diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c index fbac39aa38cc..f0df41cf39a3 100644 --- a/drivers/gpu/drm/meson/meson_drv.c +++ b/drivers/gpu/drm/meson/meson_drv.c @@ -249,29 +249,20 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (ret) goto free_drm; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_0); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - goto free_drm; - } + if (ret) + goto free_canvas_osd1; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_1); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); - goto free_drm; - } + if (ret) + goto free_canvas_vd1_0; ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_2); - if (ret) { - meson_canvas_free(priv->canvas, priv->canvas_id_osd1); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); - meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1); - goto free_drm; - } + if (ret) + goto free_canvas_vd1_1; priv->vsync_irq = platform_get_irq(pdev, 0); ret = drm_vblank_init(drm, 1); if (ret) - goto free_drm; + goto free_canvas_vd1_2; /* Assign limits per soc revision/package */ for (i = 0 ; i < ARRAY_SIZE(meson_drm_soc_attrs) ; ++i) { @@ -287,11 +278,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) */ ret = drm_aperture_remove_framebuffers(&meson_driver); if (ret) - goto free_drm; + goto free_canvas_vd1_2; ret = drmm_mode_config_init(drm); if (ret) - goto free_drm; + goto free_canvas_vd1_2; drm->mode_config.max_width = 3840; drm->mode_config.max_height = 2160; drm->mode_config.funcs = &meson_mode_config_funcs; @@ -306,7 +297,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components) if (priv->afbcd.ops) { ret = priv->afbcd.ops->init(priv); if (ret) - goto free_drm; + goto free_canvas_vd1_2; } /* Encoder Initialization */ @@ -364,6 +355,14 @@ uninstall_irq: exit_afbcd: if (priv->afbcd.ops) priv->afbcd.ops->exit(priv); +free_canvas_vd1_2: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2); +free_canvas_vd1_1: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1); +free_canvas_vd1_0: + meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0); +free_canvas_osd1: + meson_canvas_free(priv->canvas, priv->canvas_id_osd1); free_drm: drm_dev_put(drm); diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c index 815dfe30492b..b43ac61201f3 100644 --- a/drivers/gpu/drm/meson/meson_plane.c +++ b/drivers/gpu/drm/meson/meson_plane.c @@ -534,6 +534,7 @@ int meson_plane_create(struct meson_drm *priv) struct meson_plane *meson_plane; struct drm_plane *plane; const uint64_t *format_modifiers = format_modifiers_default; + int ret; meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane), GFP_KERNEL); @@ -548,12 +549,16 @@ int meson_plane_create(struct meson_drm *priv) else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A)) format_modifiers = format_modifiers_afbc_g12a; - drm_universal_plane_init(priv->drm, plane, 0xFF, - &meson_plane_funcs, - supported_drm_formats, - ARRAY_SIZE(supported_drm_formats), - format_modifiers, - DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane"); + ret = drm_universal_plane_init(priv->drm, plane, 0xFF, + &meson_plane_funcs, + supported_drm_formats, + ARRAY_SIZE(supported_drm_formats), + format_modifiers, + DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane"); + if (ret) { + devm_kfree(priv->drm->dev, meson_plane); + return ret; + } drm_plane_helper_add(plane, &meson_plane_helper_funcs); diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c index 0c48bdf3e7f8..f5c5d06d0d4b 100644 --- a/drivers/gpu/drm/mgag200/mgag200_i2c.c +++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c @@ -31,6 +31,8 @@ #include #include +#include + #include "mgag200_drv.h" static int mga_i2c_read_gpio(struct mga_device *mdev) @@ -86,7 +88,7 @@ static int mga_gpio_getscl(void *data) return (mga_i2c_read_gpio(mdev) & i2c->clock) ? 1 : 0; } -static void mgag200_i2c_release(void *res) +static void mgag200_i2c_release(struct drm_device *dev, void *res) { struct mga_i2c_chan *i2c = res; @@ -115,7 +117,7 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) i2c->adapter.algo_data = &i2c->bit; i2c->bit.udelay = 10; - i2c->bit.timeout = 2; + i2c->bit.timeout = usecs_to_jiffies(2200); i2c->bit.data = i2c; i2c->bit.setsda = mga_gpio_setsda; i2c->bit.setscl = mga_gpio_setscl; @@ -126,5 +128,5 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c) if (ret) return ret; - return devm_add_action_or_reset(dev->dev, mgag200_i2c_release, i2c); + return drmm_add_action_or_reset(dev, mgag200_i2c_release, i2c); } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 895a0e9db1f0..5a10628934bc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -65,6 +65,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring, static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); struct msm_ringbuffer *ring = submit->ring; struct msm_gem_object *obj; uint32_t *ptr, dwords; @@ -109,6 +111,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit } } + a5xx_gpu->last_seqno[ring->id] = submit->seqno; a5xx_flush(gpu, ring, true); a5xx_preempt_trigger(gpu); @@ -150,9 +153,13 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1); OUT_RING(ring, 1); - /* Enable local preemption for finegrain preemption */ + /* + * Disable local preemption by default because it requires + * user-space to be aware of it and provide additional handling + * to restore rendering state or do various flushes on switch. + */ OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1); - OUT_RING(ring, 0x1); + OUT_RING(ring, 0x0); /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */ OUT_PKT7(ring, CP_YIELD_ENABLE, 1); @@ -206,6 +213,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) /* Write the fence to the scratch register */ OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1); OUT_RING(ring, submit->seqno); + a5xx_gpu->last_seqno[ring->id] = submit->seqno; /* * Execute a CACHE_FLUSH_TS event. This will ensure that the diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h index c7187bcc5e90..9c0d701fe4b8 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h @@ -34,8 +34,10 @@ struct a5xx_gpu { struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS]; struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS]; uint64_t preempt_iova[MSM_GPU_MAX_RINGS]; + uint32_t last_seqno[MSM_GPU_MAX_RINGS]; atomic_t preempt_state; + spinlock_t preempt_start_lock; struct timer_list preempt_timer; struct drm_gem_object *shadow_bo; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index f58dd564d122..0469fea55010 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -55,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) /* Return the highest priority ringbuffer with something in it */ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) { + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu); unsigned long flags; int i; @@ -64,6 +66,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu) spin_lock_irqsave(&ring->preempt_lock, flags); empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring)); + if (!empty && ring == a5xx_gpu->cur_ring) + empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i]; spin_unlock_irqrestore(&ring->preempt_lock, flags); if (!empty) @@ -97,12 +101,19 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) if (gpu->nr_rings == 1) return; + /* + * Serialize preemption start to ensure that we always make + * decision on latest state. Otherwise we can get stuck in + * lower priority or empty ring. + */ + spin_lock_irqsave(&a5xx_gpu->preempt_start_lock, flags); + /* * Try to start preemption by moving from NONE to START. If * unsuccessful, a preemption is already in flight */ if (!try_preempt_state(a5xx_gpu, PREEMPT_NONE, PREEMPT_START)) - return; + goto out; /* Get the next ring to preempt to */ ring = get_next_ring(gpu); @@ -127,9 +138,11 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) set_preempt_state(a5xx_gpu, PREEMPT_ABORT); update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); - return; + goto out; } + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); + /* Make sure the wptr doesn't update while we're in motion */ spin_lock_irqsave(&ring->preempt_lock, flags); a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring); @@ -152,6 +165,10 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* And actually start the preemption */ gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1); + return; + +out: + spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags); } void a5xx_preempt_irq(struct msm_gpu *gpu) @@ -188,6 +205,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu) update_wptr(gpu, a5xx_gpu->cur_ring); set_preempt_state(a5xx_gpu, PREEMPT_NONE); + + /* + * Try to trigger preemption again in case there was a submit or + * retire during ring switch + */ + a5xx_preempt_trigger(gpu); } void a5xx_preempt_hw_init(struct msm_gpu *gpu) @@ -204,6 +227,8 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) return; for (i = 0; i < gpu->nr_rings; i++) { + a5xx_gpu->preempt[i]->data = 0; + a5xx_gpu->preempt[i]->info = 0; a5xx_gpu->preempt[i]->wptr = 0; a5xx_gpu->preempt[i]->rptr = 0; a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova; @@ -298,5 +323,6 @@ void a5xx_preempt_init(struct msm_gpu *gpu) } } + spin_lock_init(&a5xx_gpu->preempt_start_lock); timer_setup(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, 0); } diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index dfd4eec21785..c73eb07afb0a 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname, * was a bad idea, and is only provided for backwards * compatibility for older targets. */ - return -ENODEV; + return -ENOENT; } if (IS_ERR(fw)) { @@ -418,7 +418,7 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname) ret = request_firmware_direct(&fw, fwname, drm->dev); if (!ret) { DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n", - newname); + fwname); adreno_gpu->fwloc = FW_LOCATION_LEGACY; goto out; } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) { diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c index 3632f0768aa9..ba8f2ba04629 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c @@ -1106,21 +1106,20 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc, for (i = 0; i < dpu_enc->num_phys_encs; i++) { struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i]; - if (!dpu_enc->hw_pp[i]) { + phys->hw_pp = dpu_enc->hw_pp[i]; + if (!phys->hw_pp) { DPU_ERROR_ENC(dpu_enc, "no pp block assigned at idx: %d\n", i); return; } - if (!hw_ctl[i]) { + phys->hw_ctl = i < num_ctl ? to_dpu_hw_ctl(hw_ctl[i]) : NULL; + if (!phys->hw_ctl) { DPU_ERROR_ENC(dpu_enc, "no ctl block assigned at idx: %d\n", i); return; } - phys->hw_pp = dpu_enc->hw_pp[i]; - phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]); - phys->cached_mode = crtc_state->adjusted_mode; if (phys->ops.atomic_mode_set) phys->ops.atomic_mode_set(phys, crtc_state, conn_state); @@ -1653,8 +1652,7 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc) phys = dpu_enc->phys_encs[i]; ctl = phys->hw_ctl; - if (ctl->ops.clear_pending_flush) - ctl->ops.clear_pending_flush(ctl); + ctl->ops.clear_pending_flush(ctl); /* update only for command mode primary ctl */ if ((phys == dpu_enc->cur_master) && diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c index ce58d97818bc..e05c3ccf07f8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c @@ -61,6 +61,7 @@ static void _dpu_encoder_phys_cmd_update_intf_cfg( intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD; intf_cfg.stream_sel = cmd_enc->stream_sel; intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); + intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); ctl->ops.setup_intf_cfg(ctl, &intf_cfg); /* setup which pp blk will connect to this intf */ diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c index 2baade1cd487..aba2488c32fa 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c @@ -276,7 +276,8 @@ static void dpu_encoder_phys_vid_setup_timing_engine( intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID; intf_cfg.stream_sel = 0; /* Don't care value for video mode */ intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc); - if (phys_enc->hw_pp->merge_3d) + intf_cfg.dsc = dpu_encoder_helper_get_dsc(phys_enc); + if (intf_cfg.mode_3d && phys_enc->hw_pp->merge_3d) intf_cfg.merge_3d = phys_enc->hw_pp->merge_3d->idx; spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c index 42c7e378d504..05a09d86e183 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c @@ -548,8 +548,7 @@ static void dpu_encoder_phys_wb_disable(struct dpu_encoder_phys *phys_enc) } /* reset h/w before final flush */ - if (phys_enc->hw_ctl->ops.clear_pending_flush) - phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl); + phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl); /* * New CTL reset sequence from 5.0 MDP onwards. diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h index 96c012ec8467..ec5265771cdf 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h @@ -81,7 +81,8 @@ struct dpu_hw_ctl_ops { /** * Clear the value of the cached pending_flush_mask - * No effect on hardware + * No effect on hardware. + * Required to be implemented. * @ctx : ctl path ctx pointer */ void (*clear_pending_flush)(struct dpu_hw_ctl *ctx); diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h index bb35aa5f5709..41e44a77c2be 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h @@ -31,24 +31,14 @@ * @fmt: Pointer to format string */ #define DPU_DEBUG(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_KMS)) \ - DRM_DEBUG(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) /** * DPU_DEBUG_DRIVER - macro for hardware driver logging * @fmt: Pointer to format string */ #define DPU_DEBUG_DRIVER(fmt, ...) \ - do { \ - if (drm_debug_enabled(DRM_UT_DRIVER)) \ - DRM_ERROR(fmt, ##__VA_ARGS__); \ - else \ - pr_debug(fmt, ##__VA_ARGS__); \ - } while (0) + DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__) #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__) #define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__) diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c index 62d48c0f905e..61c456c5015a 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c @@ -889,6 +889,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane, new_state->fb, &layout); if (ret) { DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret); + if (pstate->aspace) + msm_framebuffer_cleanup(new_state->fb, pstate->aspace, + pstate->needs_dirtyfb); return ret; } diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c index 56a3063545ec..12d07e93a4c4 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c @@ -356,7 +356,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p) drm_printf(p, "%s:%d\t%d\t%s\n", pipe2name(pipe), j, inuse, - plane ? plane->name : NULL); + plane ? plane->name : "(null)"); total += inuse; } diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c index add72bbc28b1..4d55e3cf570f 100644 --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot_util.c @@ -26,7 +26,7 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b end_addr = base_addr + aligned_len; if (!(*reg)) - *reg = kzalloc(len_padded, GFP_KERNEL); + *reg = kvzalloc(len_padded, GFP_KERNEL); if (*reg) dump_addr = *reg; @@ -48,20 +48,21 @@ static void msm_disp_state_dump_regs(u32 **reg, u32 aligned_len, void __iomem *b } } -static void msm_disp_state_print_regs(u32 **reg, u32 len, void __iomem *base_addr, - struct drm_printer *p) +static void msm_disp_state_print_regs(const u32 *dump_addr, u32 len, + void __iomem *base_addr, struct drm_printer *p) { int i; - u32 *dump_addr = NULL; void __iomem *addr; u32 num_rows; + if (!dump_addr) { + drm_printf(p, "Registers not stored\n"); + return; + } + addr = base_addr; num_rows = len / REG_DUMP_ALIGN; - if (*reg) - dump_addr = *reg; - for (i = 0; i < num_rows; i++) { drm_printf(p, "0x%lx : %08x %08x %08x %08x\n", (unsigned long)(addr - base_addr), @@ -89,7 +90,7 @@ void msm_disp_state_print(struct msm_disp_state *state, struct drm_printer *p) list_for_each_entry_safe(block, tmp, &state->blocks, node) { drm_printf(p, "====================%s================\n", block->name); - msm_disp_state_print_regs(&block->state, block->size, block->base_addr, p); + msm_disp_state_print_regs(block->state, block->size, block->base_addr, p); } drm_printf(p, "===================dpu drm state================\n"); @@ -161,7 +162,7 @@ void msm_disp_state_free(void *data) list_for_each_entry_safe(block, tmp, &disp_state->blocks, node) { list_del(&block->node); - kfree(block->state); + kvfree(block->state); kfree(block); } diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c index bd1343602f55..3c001b792423 100644 --- a/drivers/gpu/drm/msm/dp/dp_ctrl.c +++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c @@ -1248,6 +1248,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl, link_info.rate = ctrl->link->link_params.rate; link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING; + dp_link_reset_phy_params_vx_px(ctrl->link); + dp_aux_link_configure(ctrl->aux, &link_info); if (drm_dp_max_downspread(dpcd)) diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c index d38086650fcf..f2cc0cc0b66b 100644 --- a/drivers/gpu/drm/msm/dp/dp_panel.c +++ b/drivers/gpu/drm/msm/dp/dp_panel.c @@ -113,22 +113,22 @@ end: static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel, u32 mode_edid_bpp, u32 mode_pclk_khz) { - struct dp_link_info *link_info; + const struct dp_link_info *link_info; const u32 max_supported_bpp = 30, min_supported_bpp = 18; - u32 bpp = 0, data_rate_khz = 0; + u32 bpp, data_rate_khz; - bpp = min_t(u32, mode_edid_bpp, max_supported_bpp); + bpp = min(mode_edid_bpp, max_supported_bpp); link_info = &dp_panel->link_info; data_rate_khz = link_info->num_lanes * link_info->rate * 8; - while (bpp > min_supported_bpp) { + do { if (mode_pclk_khz * bpp <= data_rate_khz) - break; + return bpp; bpp -= 6; - } + } while (bpp > min_supported_bpp); - return bpp; + return min_supported_bpp; } static int dp_panel_update_modes(struct drm_connector *connector, @@ -421,8 +421,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel) drm_mode->clock); drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp); - dp_panel->dp_mode.bpp = max_t(u32, 18, - min_t(u32, dp_panel->dp_mode.bpp, 30)); + dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp, + dp_panel->dp_mode.drm_mode.clock); + drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n", dp_panel->dp_mode.bpp); diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c index cd9ca3690161..88843505d89c 100644 --- a/drivers/gpu/drm/msm/dsi/dsi_host.c +++ b/drivers/gpu/drm/msm/dsi/dsi_host.c @@ -576,7 +576,7 @@ static unsigned long dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_bo struct drm_display_mode *mode = msm_host->mode; unsigned long pclk_rate; - pclk_rate = mode->clock * 1000; + pclk_rate = mode->clock * 1000u; /* * For bonded DSI mode, the current DRM mode has the complete width of the @@ -848,6 +848,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod u32 slice_per_intf, total_bytes_per_intf; u32 pkt_per_line; u32 eol_byte_num; + u32 bytes_per_pkt; /* first calculate dsc parameters and then program * compress mode registers @@ -855,6 +856,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod slice_per_intf = DIV_ROUND_UP(hdisplay, dsc->slice_width); total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf; + bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */ eol_byte_num = total_bytes_per_intf % 3; @@ -892,6 +894,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL, reg_ctrl); dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL2, reg_ctrl2); } else { + reg |= DSI_VIDEO_COMPRESSION_MODE_CTRL_WC(bytes_per_pkt); dsi_write(msm_host, REG_DSI_VIDEO_COMPRESSION_MODE_CTRL, reg); } } diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c index 31f054c903a4..a35c98306f1e 100644 --- a/drivers/gpu/drm/msm/msm_gem_shrinker.c +++ b/drivers/gpu/drm/msm/msm_gem_shrinker.c @@ -76,7 +76,7 @@ static bool wait_for_idle(struct drm_gem_object *obj) { enum dma_resv_usage usage = dma_resv_usage_rw(true); - return dma_resv_wait_timeout(obj->resv, usage, false, 1000) > 0; + return dma_resv_wait_timeout(obj->resv, usage, false, 10) > 0; } static bool diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 6ca4a46a82ee..e38d57fc8a79 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -194,7 +194,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) if (!spage || !(src & MIGRATE_PFN_MIGRATE)) goto done; - dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma, vmf->address); if (!dpage) goto done; diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index 9608121e49b7..8340d55aaa98 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -63,7 +63,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, * to the caller, instead of a normal nouveau_bo ttm reference. */ ret = drm_gem_object_init(dev, &nvbo->bo.base, size); if (ret) { - nouveau_bo_ref(NULL, &nvbo); + drm_gem_object_release(&nvbo->bo.base); + kfree(nvbo); obj = ERR_PTR(-ENOMEM); goto unlock; } diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c index 5b6d1668f405..cc3bb0f6435b 100644 --- a/drivers/gpu/drm/omapdrm/omap_drv.c +++ b/drivers/gpu/drm/omapdrm/omap_drv.c @@ -746,6 +746,10 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev) soc = soc_device_match(omapdrm_soc_devices); priv->omaprev = soc ? (uintptr_t)soc->data : 0; priv->wq = alloc_ordered_workqueue("omapdrm", 0); + if (!priv->wq) { + ret = -ENOMEM; + goto err_alloc_workqueue; + } mutex_init(&priv->list_lock); INIT_LIST_HEAD(&priv->obj_list); @@ -808,6 +812,7 @@ err_gem_deinit: drm_mode_config_cleanup(ddev); omap_gem_deinit(ddev); destroy_workqueue(priv->wq); +err_alloc_workqueue: omap_disconnect_pipelines(ddev); drm_dev_put(ddev); return ret; diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c index 1c008bd9102f..820d8d29b62b 100644 --- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c +++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c @@ -1271,7 +1271,11 @@ static int boe_panel_prepare(struct drm_panel *panel) usleep_range(10000, 11000); if (boe->desc->lp11_before_reset) { - mipi_dsi_dcs_nop(boe->dsi); + ret = mipi_dsi_dcs_nop(boe->dsi); + if (ret < 0) { + dev_err(&boe->dsi->dev, "Failed to send NOP: %d\n", ret); + goto poweroff; + } usleep_range(1000, 2000); } gpiod_set_value(boe->enable_gpio, 1); @@ -1292,13 +1296,13 @@ static int boe_panel_prepare(struct drm_panel *panel) return 0; poweroff: + gpiod_set_value(boe->enable_gpio, 0); regulator_disable(boe->avee); poweroffavdd: regulator_disable(boe->avdd); poweroff1v8: usleep_range(5000, 7000); regulator_disable(boe->pp1800); - gpiod_set_value(boe->enable_gpio, 0); return ret; } diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c index 919e6cc04982..3c0aa8b5e1ae 100644 --- a/drivers/gpu/drm/panfrost/panfrost_drv.c +++ b/drivers/gpu/drm/panfrost/panfrost_drv.c @@ -704,3 +704,4 @@ module_platform_driver(panfrost_driver); MODULE_AUTHOR("Panfrost Project Developers"); MODULE_DESCRIPTION("Panfrost DRM Driver"); MODULE_LICENSE("GPL v2"); +MODULE_SOFTDEP("pre: governor_simpleondemand"); diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index f91a86225d5e..462a4d2ac0b9 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -236,6 +236,9 @@ static int qxl_add_mode(struct drm_connector *connector, return 0; mode = drm_cvt_mode(dev, width, height, 60, false, false, false); + if (!mode) + return 0; + if (preferred) mode->type |= DRM_MODE_TYPE_PREFERRED; mode->hdisplay = width; diff --git a/drivers/gpu/drm/radeon/atombios.h b/drivers/gpu/drm/radeon/atombios.h index da35a970fcc0..235e59b547a1 100644 --- a/drivers/gpu/drm/radeon/atombios.h +++ b/drivers/gpu/drm/radeon/atombios.h @@ -3615,7 +3615,7 @@ typedef struct _ATOM_FAKE_EDID_PATCH_RECORD { UCHAR ucRecordType; UCHAR ucFakeEDIDLength; - UCHAR ucFakeEDIDString[1]; // This actually has ucFakeEdidLength elements. + UCHAR ucFakeEDIDString[]; // This actually has ucFakeEdidLength elements. } ATOM_FAKE_EDID_PATCH_RECORD; typedef struct _ATOM_PANEL_RESOLUTION_PATCH_RECORD diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c index 0de79f3a7e3f..820c2c3641d3 100644 --- a/drivers/gpu/drm/radeon/evergreen_cs.c +++ b/drivers/gpu/drm/radeon/evergreen_cs.c @@ -395,7 +395,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028C6C_SLICE_MAX(track->cb_color_view[id]) + 1; @@ -433,14 +433,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i return r; } - offset = track->cb_color_bo_offset[id] << 8; + offset = (u64)track->cb_color_bo_offset[id] << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d cb[%d] bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d cb[%d] bo base %llu not aligned with %ld\n", __func__, __LINE__, id, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->cb_color_bo[id])) { /* old ddx are broken they allocate bo with w*h*bpp but * program slice with ALIGN(h, 8), catch this and patch @@ -448,14 +448,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i */ if (!surf.mode) { uint32_t *ib = p->ib.ptr; - unsigned long tmp, nby, bsize, size, min = 0; + u64 tmp, nby, bsize, size, min = 0; /* find the height the ddx wants */ if (surf.nby > 8) { min = surf.nby - 8; } bsize = radeon_bo_size(track->cb_color_bo[id]); - tmp = track->cb_color_bo_offset[id] << 8; + tmp = (u64)track->cb_color_bo_offset[id] << 8; for (nby = surf.nby; nby > min; nby--) { size = nby * surf.nbx * surf.bpe * surf.nsamples; if ((tmp + size * mslice) <= bsize) { @@ -467,7 +467,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i slice = ((nby * surf.nbx) / 64) - 1; if (!evergreen_surface_check(p, &surf, "cb")) { /* check if this one works */ - tmp += surf.layer_size * mslice; + tmp += (u64)surf.layer_size * mslice; if (tmp <= bsize) { ib[track->cb_color_slice_idx[id]] = slice; goto old_ddx_ok; @@ -476,9 +476,9 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i } } dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, " - "offset %d, max layer %d, bo size %ld, slice %d)\n", + "offset %llu, max layer %d, bo size %ld, slice %d)\n", __func__, __LINE__, id, surf.layer_size, - track->cb_color_bo_offset[id] << 8, mslice, + (u64)track->cb_color_bo_offset[id] << 8, mslice, radeon_bo_size(track->cb_color_bo[id]), slice); dev_warn(p->dev, "%s:%d problematic surf: (%d %d) (%d %d %d %d %d %d %d)\n", __func__, __LINE__, surf.nbx, surf.nby, @@ -562,7 +562,7 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1; @@ -608,18 +608,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) return r; } - offset = track->db_s_read_offset << 8; + offset = (u64)track->db_s_read_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_s_read_bo)) { dev_warn(p->dev, "%s:%d stencil read bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_s_read_offset << 8, mslice, + (u64)track->db_s_read_offset << 8, mslice, radeon_bo_size(track->db_s_read_bo)); dev_warn(p->dev, "%s:%d stencil invalid (0x%08x 0x%08x 0x%08x 0x%08x)\n", __func__, __LINE__, track->db_depth_size, @@ -627,18 +627,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p) return -EINVAL; } - offset = track->db_s_write_offset << 8; + offset = (u64)track->db_s_write_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_s_write_bo)) { dev_warn(p->dev, "%s:%d stencil write bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_s_write_offset << 8, mslice, + (u64)track->db_s_write_offset << 8, mslice, radeon_bo_size(track->db_s_write_bo)); return -EINVAL; } @@ -659,7 +659,7 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p) struct evergreen_cs_track *track = p->track; struct eg_surface surf; unsigned pitch, slice, mslice; - unsigned long offset; + u64 offset; int r; mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1; @@ -706,34 +706,34 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p) return r; } - offset = track->db_z_read_offset << 8; + offset = (u64)track->db_z_read_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_z_read_bo)) { dev_warn(p->dev, "%s:%d depth read bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_z_read_offset << 8, mslice, + (u64)track->db_z_read_offset << 8, mslice, radeon_bo_size(track->db_z_read_bo)); return -EINVAL; } - offset = track->db_z_write_offset << 8; + offset = (u64)track->db_z_write_offset << 8; if (offset & (surf.base_align - 1)) { - dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n", + dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n", __func__, __LINE__, offset, surf.base_align); return -EINVAL; } - offset += surf.layer_size * mslice; + offset += (u64)surf.layer_size * mslice; if (offset > radeon_bo_size(track->db_z_write_bo)) { dev_warn(p->dev, "%s:%d depth write bo too small (layer size %d, " - "offset %ld, max layer %d, bo size %ld)\n", + "offset %llu, max layer %d, bo size %ld)\n", __func__, __LINE__, surf.layer_size, - (unsigned long)track->db_z_write_offset << 8, mslice, + (u64)track->db_z_write_offset << 8, mslice, radeon_bo_size(track->db_z_write_bo)); return -EINVAL; } diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c index f336b5b3b11f..42605e2765f8 100644 --- a/drivers/gpu/drm/radeon/r100.c +++ b/drivers/gpu/drm/radeon/r100.c @@ -1015,45 +1015,65 @@ static int r100_cp_init_microcode(struct radeon_device *rdev) DRM_DEBUG_KMS("\n"); - if ((rdev->family == CHIP_R100) || (rdev->family == CHIP_RV100) || - (rdev->family == CHIP_RV200) || (rdev->family == CHIP_RS100) || - (rdev->family == CHIP_RS200)) { + switch (rdev->family) { + case CHIP_R100: + case CHIP_RV100: + case CHIP_RV200: + case CHIP_RS100: + case CHIP_RS200: DRM_INFO("Loading R100 Microcode\n"); fw_name = FIRMWARE_R100; - } else if ((rdev->family == CHIP_R200) || - (rdev->family == CHIP_RV250) || - (rdev->family == CHIP_RV280) || - (rdev->family == CHIP_RS300)) { + break; + + case CHIP_R200: + case CHIP_RV250: + case CHIP_RV280: + case CHIP_RS300: DRM_INFO("Loading R200 Microcode\n"); fw_name = FIRMWARE_R200; - } else if ((rdev->family == CHIP_R300) || - (rdev->family == CHIP_R350) || - (rdev->family == CHIP_RV350) || - (rdev->family == CHIP_RV380) || - (rdev->family == CHIP_RS400) || - (rdev->family == CHIP_RS480)) { + break; + + case CHIP_R300: + case CHIP_R350: + case CHIP_RV350: + case CHIP_RV380: + case CHIP_RS400: + case CHIP_RS480: DRM_INFO("Loading R300 Microcode\n"); fw_name = FIRMWARE_R300; - } else if ((rdev->family == CHIP_R420) || - (rdev->family == CHIP_R423) || - (rdev->family == CHIP_RV410)) { + break; + + case CHIP_R420: + case CHIP_R423: + case CHIP_RV410: DRM_INFO("Loading R400 Microcode\n"); fw_name = FIRMWARE_R420; - } else if ((rdev->family == CHIP_RS690) || - (rdev->family == CHIP_RS740)) { + break; + + case CHIP_RS690: + case CHIP_RS740: DRM_INFO("Loading RS690/RS740 Microcode\n"); fw_name = FIRMWARE_RS690; - } else if (rdev->family == CHIP_RS600) { + break; + + case CHIP_RS600: DRM_INFO("Loading RS600 Microcode\n"); fw_name = FIRMWARE_RS600; - } else if ((rdev->family == CHIP_RV515) || - (rdev->family == CHIP_R520) || - (rdev->family == CHIP_RV530) || - (rdev->family == CHIP_R580) || - (rdev->family == CHIP_RV560) || - (rdev->family == CHIP_RV570)) { + break; + + case CHIP_RV515: + case CHIP_R520: + case CHIP_RV530: + case CHIP_R580: + case CHIP_RV560: + case CHIP_RV570: DRM_INFO("Loading R500 Microcode\n"); fw_name = FIRMWARE_R520; + break; + + default: + DRM_ERROR("Unsupported Radeon family %u\n", rdev->family); + return -EINVAL; } err = request_firmware(&rdev->me_fw, fw_name, rdev->dev); diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c index 204127bad89c..42ed71b6db8e 100644 --- a/drivers/gpu/drm/radeon/radeon_atombios.c +++ b/drivers/gpu/drm/radeon/radeon_atombios.c @@ -1712,23 +1712,29 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record; if (fake_edid_record->ucFakeEDIDLength) { struct edid *edid; - int edid_size = - max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength); - edid = kmalloc(edid_size, GFP_KERNEL); - if (edid) { - memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0], - fake_edid_record->ucFakeEDIDLength); + int edid_size; + if (fake_edid_record->ucFakeEDIDLength == 128) + edid_size = fake_edid_record->ucFakeEDIDLength; + else + edid_size = fake_edid_record->ucFakeEDIDLength * 128; + edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0], + edid_size, GFP_KERNEL); + if (edid) { if (drm_edid_is_valid(edid)) { rdev->mode_info.bios_hardcoded_edid = edid; rdev->mode_info.bios_hardcoded_edid_size = edid_size; - } else + } else { kfree(edid); + } } + record += struct_size(fake_edid_record, + ucFakeEDIDString, + edid_size); + } else { + /* empty fake edid record must be 3 bytes long */ + record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1; } - record += fake_edid_record->ucFakeEDIDLength ? - fake_edid_record->ucFakeEDIDLength + 2 : - sizeof(ATOM_FAKE_EDID_PATCH_RECORD); break; case LCD_PANEL_RESOLUTION_RECORD_TYPE: panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record; diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c index fbc0a2182318..af53ebd51310 100644 --- a/drivers/gpu/drm/radeon/radeon_encoders.c +++ b/drivers/gpu/drm/radeon/radeon_encoders.c @@ -43,7 +43,7 @@ static uint32_t radeon_encoder_clones(struct drm_encoder *encoder) struct radeon_device *rdev = dev->dev_private; struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder); struct drm_encoder *clone_encoder; - uint32_t index_mask = 0; + uint32_t index_mask = drm_encoder_mask(encoder); int count; /* DIG routing gets problematic */ diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c index 75d79c311038..3388a3d21d2c 100644 --- a/drivers/gpu/drm/radeon/radeon_gem.c +++ b/drivers/gpu/drm/radeon/radeon_gem.c @@ -657,7 +657,7 @@ static void radeon_gem_va_update_vm(struct radeon_device *rdev, if (r) goto error_unlock; - if (bo_va->it.start) + if (bo_va->it.start && bo_va->bo) r = radeon_vm_bo_update(rdev, bo_va, bo_va->bo->tbo.resource); error_unlock: diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c index 410606328d3e..232d6a60e406 100644 --- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c +++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c @@ -3866,6 +3866,8 @@ static void dw_hdmi_rk3328_setup_hpd(struct dw_hdmi *dw_hdmi, void *data) HIWORD_UPDATE(RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK, RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK | RK3328_HDMI_HPD_IOE)); + + dw_hdmi_rk3328_read_hpd(dw_hdmi, data); } static void dw_hdmi_qp_rockchip_phy_disable(struct dw_hdmi_qp *dw_hdmi, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c index bf7fd4e1c542..a4b2d187d508 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c @@ -4414,8 +4414,8 @@ static void vop_crtc_atomic_flush(struct drm_crtc *crtc, } static const struct drm_crtc_helper_funcs vop_crtc_helper_funcs = { - .mode_fixup = vop_crtc_mode_fixup, .mode_valid = vop_crtc_mode_valid, + .mode_fixup = vop_crtc_mode_fixup, .atomic_check = vop_crtc_atomic_check, .atomic_flush = vop_crtc_atomic_flush, .atomic_enable = vop_crtc_atomic_enable, diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h index 3d7790259907..32e6b90c8d1e 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h +++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.h @@ -27,11 +27,6 @@ enum win_dly_mode { VOP2_DLY_MODE_MAX, }; -struct vop_rect { - int width; - int height; -}; - enum vop2_scale_up_mode { VOP2_SCALE_UP_NRST_NBOR, VOP2_SCALE_UP_BIL, diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index 4b913dbb7d7b..763b80633523 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -110,8 +110,10 @@ void drm_sched_entity_modify_sched(struct drm_sched_entity *entity, { WARN_ON(!num_sched_list || !sched_list); + spin_lock(&entity->rq_lock); entity->sched_list = sched_list; entity->num_sched_list = num_sched_list; + spin_unlock(&entity->rq_lock); } EXPORT_SYMBOL(drm_sched_entity_modify_sched); diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c index 0a09a85ac9d6..7a3f1b402029 100644 --- a/drivers/gpu/drm/stm/drv.c +++ b/drivers/gpu/drm/stm/drv.c @@ -24,6 +24,7 @@ #include #include #include +#include #include "ltdc.h" @@ -74,7 +75,7 @@ static int drv_load(struct drm_device *ddev) DRM_DEBUG("%s\n", __func__); - ldev = devm_kzalloc(ddev->dev, sizeof(*ldev), GFP_KERNEL); + ldev = drmm_kzalloc(ddev, sizeof(*ldev), GFP_KERNEL); if (!ldev) return -ENOMEM; @@ -201,12 +202,14 @@ static int stm_drm_platform_probe(struct platform_device *pdev) ret = drm_dev_register(ddev, 0); if (ret) - goto err_put; + goto err_unload; drm_fbdev_generic_setup(ddev, 16); return 0; +err_unload: + drv_unload(ddev); err_put: drm_dev_put(ddev); diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c index b8be4c1db423..a192f7791545 100644 --- a/drivers/gpu/drm/stm/ltdc.c +++ b/drivers/gpu/drm/stm/ltdc.c @@ -37,6 +37,7 @@ #include #include #include +#include #include