From 82af5b6609673f1cc7d3453d0be3d292dfffc813 Mon Sep 17 00:00:00 2001 From: Nayna Jain Date: Tue, 1 Oct 2019 19:37:18 -0400 Subject: sysfs: Fixes __BIN_ATTR_WO() macro This patch fixes the size and write parameter for the macro __BIN_ATTR_WO(). Fixes: 7f905761e15a8 ("sysfs: add BIN_ATTR_WO() macro") Signed-off-by: Nayna Jain Link: https://lore.kernel.org/r/1569973038-2710-1-git-send-email-nayna@linux.ibm.com Signed-off-by: Greg Kroah-Hartman --- include/linux/sysfs.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h index 5420817ed317..fa7ee503fb76 100644 --- a/include/linux/sysfs.h +++ b/include/linux/sysfs.h @@ -196,9 +196,9 @@ struct bin_attribute { .size = _size, \ } -#define __BIN_ATTR_WO(_name) { \ +#define __BIN_ATTR_WO(_name, _size) { \ .attr = { .name = __stringify(_name), .mode = 0200 }, \ - .store = _name##_store, \ + .write = _name##_write, \ .size = _size, \ } -- cgit v1.2.3 From d983ea6f16b835dcde2ee9a58a1e764ce68bfccc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 10 Oct 2019 20:17:38 -0700 Subject: tcp: add rcu protection around tp->fastopen_rsk Both tcp_v4_err() and tcp_v6_err() do the following operations while they do not own the socket lock : fastopen = tp->fastopen_rsk; snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; The problem is that without appropriate barrier, the compiler might reload tp->fastopen_rsk and trigger a NULL deref. request sockets are protected by RCU, we can simply add the missing annotations and barriers to solve the issue. Fixes: 168a8f58059a ("tcp: TCP Fast Open Server - main code path") Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 99617e528ea2..668e25a76d69 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -393,7 +393,7 @@ struct tcp_sock { /* fastopen_rsk points to request_sock that resulted in this big * socket. Used to retransmit SYNACKs etc. */ - struct request_sock *fastopen_rsk; + struct request_sock __rcu *fastopen_rsk; u32 *saved_syn; }; @@ -447,8 +447,8 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) static inline bool tcp_passive_fastopen(const struct sock *sk) { - return (sk->sk_state == TCP_SYN_RECV && - tcp_sk(sk)->fastopen_rsk != NULL); + return sk->sk_state == TCP_SYN_RECV && + rcu_access_pointer(tcp_sk(sk)->fastopen_rsk) != NULL; } static inline void fastopen_queue_tune(struct sock *sk, int backlog) -- cgit v1.2.3 From 5556cfe8d994d5e7b4d50fd91597b8dc0b3a82fd Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 14 Oct 2019 14:11:40 -0700 Subject: mm, page_owner: fix off-by-one error in __set_page_owner_handle() Patch series "followups to debug_pagealloc improvements through page_owner", v3. These are followups to [1] which made it to Linus meanwhile. Patches 1 and 3 are based on Kirill's review, patch 2 on KASAN request [2]. It would be nice if all of this made it to 5.4 with [1] already there (or at least Patch 1). This patch (of 3): As noted by Kirill, commit 7e2f2a0cd17c ("mm, page_owner: record page owner for each subpage") has introduced an off-by-one error in __set_page_owner_handle() when looking up page_ext for subpages. As a result, the head page page_owner info is set twice, while for the last tail page, it's not set at all. Fix this and also make the code more efficient by advancing the page_ext pointer we already have, instead of calling lookup_page_ext() for each subpage. Since the full size of struct page_ext is not known at compile time, we can't use a simple page_ext++ statement, so introduce a page_ext_next() inline function for that. Link: http://lkml.kernel.org/r/20190930122916.14969-2-vbabka@suse.cz Fixes: 7e2f2a0cd17c ("mm, page_owner: record page owner for each subpage") Signed-off-by: Vlastimil Babka Reported-by: Kirill A. Shutemov Reported-by: Miles Chen Acked-by: Kirill A. Shutemov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 682fd465df06..5e856512bafb 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -36,6 +36,7 @@ struct page_ext { unsigned long flags; }; +extern unsigned long page_ext_size; extern void pgdat_page_ext_init(struct pglist_data *pgdat); #ifdef CONFIG_SPARSEMEM @@ -52,6 +53,13 @@ static inline void page_ext_init(void) struct page_ext *lookup_page_ext(const struct page *page); +static inline struct page_ext *page_ext_next(struct page_ext *curr) +{ + void *next = curr; + next += page_ext_size; + return next; +} + #else /* !CONFIG_PAGE_EXTENSION */ struct page_ext; -- cgit v1.2.3 From fdf3bf809162592b54c278b9b0e84f3e126f8844 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 14 Oct 2019 14:11:47 -0700 Subject: mm, page_owner: rename flag indicating that page is allocated Commit 37389167a281 ("mm, page_owner: keep owner info when freeing the page") has introduced a flag PAGE_EXT_OWNER_ACTIVE to indicate that page is tracked as being allocated. Kirril suggested naming it PAGE_EXT_OWNER_ALLOCATED to make it more clear, as "active is somewhat loaded term for a page". Link: http://lkml.kernel.org/r/20190930122916.14969-4-vbabka@suse.cz Signed-off-by: Vlastimil Babka Suggested-by: Kirill A. Shutemov Cc: Andrey Ryabinin Cc: Dmitry Vyukov Cc: Kirill A. Shutemov Cc: Walter Wu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_ext.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h index 5e856512bafb..cfce186f0c4e 100644 --- a/include/linux/page_ext.h +++ b/include/linux/page_ext.h @@ -18,7 +18,7 @@ struct page_ext_operations { enum page_ext_flags { PAGE_EXT_OWNER, - PAGE_EXT_OWNER_ACTIVE, + PAGE_EXT_OWNER_ALLOCATED, #if defined(CONFIG_IDLE_PAGE_TRACKING) && !defined(CONFIG_64BIT) PAGE_EXT_YOUNG, PAGE_EXT_IDLE, -- cgit v1.2.3 From 2a7e582f429bd983816ad366cf0f1fcf87ec6ba6 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 14 Oct 2019 14:12:20 -0700 Subject: bitmap.h: fix kernel-doc warning and typo Fix kernel-doc warning in : include/linux/bitmap.h:341: warning: Function parameter or member 'nbits' not described in 'bitmap_or_equal' Also fix small typo (bitnaps). Link: http://lkml.kernel.org/r/0729ea7a-2c0d-b2c5-7dd3-3629ee0803e2@infradead.org Fixes: b9fa6442f704 ("cpumask: Implement cpumask_or_equal()") Signed-off-by: Randy Dunlap Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bitmap.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 90528f12bdfa..29fc933df3bf 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -326,10 +326,11 @@ static inline int bitmap_equal(const unsigned long *src1, } /** - * bitmap_or_equal - Check whether the or of two bitnaps is equal to a third + * bitmap_or_equal - Check whether the or of two bitmaps is equal to a third * @src1: Pointer to bitmap 1 * @src2: Pointer to bitmap 2 will be or'ed with bitmap 1 * @src3: Pointer to bitmap 3. Compare to the result of *@src1 | *@src2 + * @nbits: number of bits in each of these bitmaps * * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise */ -- cgit v1.2.3 From 13bea898cd9153be91baa92de68ec32ff0b99362 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 14 Oct 2019 14:12:23 -0700 Subject: xarray.h: fix kernel-doc warning Fix (Sphinx) kernel-doc warning in : include/linux/xarray.h:232: WARNING: Unexpected indentation. Link: http://lkml.kernel.org/r/89ba2134-ce23-7c10-5ee1-ef83b35aa984@infradead.org Fixes: a3e4d3f97ec8 ("XArray: Redesign xa_alloc API") Signed-off-by: Randy Dunlap Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/xarray.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 5921599b6dc4..86eecbd98e84 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -230,8 +230,8 @@ static inline int xa_err(void *entry) * This structure is used either directly or via the XA_LIMIT() macro * to communicate the range of IDs that are valid for allocation. * Two common ranges are predefined for you: - * * xa_limit_32b - [0 - UINT_MAX] - * * xa_limit_31b - [0 - INT_MAX] + * * xa_limit_32b - [0 - UINT_MAX] + * * xa_limit_31b - [0 - INT_MAX] */ struct xa_limit { u32 max; -- cgit v1.2.3 From 9411e3aaa6342eb730daa55cf3377463a37d2aa7 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 9 Oct 2019 17:34:44 +0300 Subject: gpiolib: Initialize the hardware with a callback After changing the drivers to use GPIO core to add an IRQ chip it appears that some of them requires a hardware initialization before adding the IRQ chip. Add an optional callback ->init_hw() to allow that drivers to initialize hardware if needed. This change is a part of the fix NULL pointer dereference brought to the several drivers recently. Cc: Hans de Goede Signed-off-by: Andy Shevchenko Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index f8245d67f070..5dd9c982e2cb 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -201,6 +201,14 @@ struct gpio_irq_chip { */ bool threaded; + /** + * @init_hw: optional routine to initialize hardware before + * an IRQ chip will be added. This is quite useful when + * a particular driver wants to clear IRQ related registers + * in order to avoid undesired events. + */ + int (*init_hw)(struct gpio_chip *chip); + /** * @init_valid_mask: optional routine to initialize @valid_mask, to be * used if not all GPIO lines are valid interrupts. Sometimes some -- cgit v1.2.3 From fa4e0f8855fcba600e0be2575ee29c69166f74bd Mon Sep 17 00:00:00 2001 From: Davide Caratti Date: Sat, 12 Oct 2019 13:55:07 +0200 Subject: net/sched: fix corrupted L2 header with MPLS 'push' and 'pop' actions the following script: # tc qdisc add dev eth0 clsact # tc filter add dev eth0 egress protocol ip matchall \ > action mpls push protocol mpls_uc label 0x355aa bos 1 causes corruption of all IP packets transmitted by eth0. On TC egress, we can't rely on the value of skb->mac_len, because it's 0 and a MPLS 'push' operation will result in an overwrite of the first 4 octets in the packet L2 header (e.g. the Destination Address if eth0 is an Ethernet); the same error pattern is present also in the MPLS 'pop' operation. Fix this error in act_mpls data plane, computing 'mac_len' as the difference between the network header and the mac header (when not at TC ingress), and use it in MPLS 'push'/'pop' core functions. v2: unbreak 'make htmldocs' because of missing documentation of 'mac_len' in skb_mpls_pop(), reported by kbuild test robot CC: Lorenzo Bianconi Fixes: 2a2ea50870ba ("net: sched: add mpls manipulation actions to TC") Reviewed-by: Simon Horman Acked-by: John Hurley Signed-off-by: Davide Caratti Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4351577b14d7..7914fdaf4226 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -3510,8 +3510,9 @@ int skb_ensure_writable(struct sk_buff *skb, int write_len); int __skb_vlan_pop(struct sk_buff *skb, u16 *vlan_tci); int skb_vlan_pop(struct sk_buff *skb); int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci); -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto); -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto); +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len); +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len); int skb_mpls_update_lse(struct sk_buff *skb, __be32 mpls_lse); int skb_mpls_dec_ttl(struct sk_buff *skb); struct sk_buff *pskb_extract(struct sk_buff *skb, int off, int to_copy, -- cgit v1.2.3 From 19c95f261c6558d4c2cbbfacd2d8bb6501384601 Mon Sep 17 00:00:00 2001 From: Julien Thierry Date: Tue, 15 Oct 2019 18:25:44 +0100 Subject: arm64: entry.S: Do not preempt from IRQ before all cpufeatures are enabled Preempting from IRQ-return means that the task has its PSTATE saved on the stack, which will get restored when the task is resumed and does the actual IRQ return. However, enabling some CPU features requires modifying the PSTATE. This means that, if a task was scheduled out during an IRQ-return before all CPU features are enabled, the task might restore a PSTATE that does not include the feature enablement changes once scheduled back in. * Task 1: PAN == 0 ---| |--------------- | |<- return from IRQ, PSTATE.PAN = 0 | <- IRQ | +--------+ <- preempt() +-- ^ | reschedule Task 1, PSTATE.PAN == 1 * Init: --------------------+------------------------ ^ | enable_cpu_features set PSTATE.PAN on all CPUs Worse than this, since PSTATE is untouched when task switching is done, a task missing the new bits in PSTATE might affect another task, if both do direct calls to schedule() (outside of IRQ/exception contexts). Fix this by preventing preemption on IRQ-return until features are enabled on all CPUs. This way the only PSTATE values that are saved on the stack are from synchronous exceptions. These are expected to be fatal this early, the exception is BRK for WARN_ON(), but as this uses do_debug_exception() which keeps IRQs masked, it shouldn't call schedule(). Signed-off-by: Julien Thierry [james: Replaced a really cool hack, with an even simpler static key in C. expanded commit message with Julien's cover-letter ascii art] Signed-off-by: James Morse Signed-off-by: Will Deacon --- include/linux/sched.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 2c2e56bd8913..67a1d86981a9 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -223,6 +223,7 @@ extern long schedule_timeout_uninterruptible(long timeout); extern long schedule_timeout_idle(long timeout); asmlinkage void schedule(void); extern void schedule_preempt_disabled(void); +asmlinkage void preempt_schedule_irq(void); extern int __must_check io_schedule_prepare(void); extern void io_schedule_finish(int token); -- cgit v1.2.3 From 1d951ba3da67bbc7a9b0e05987e09552c2060e18 Mon Sep 17 00:00:00 2001 From: Marek Vasut Date: Wed, 16 Oct 2019 15:35:07 +0200 Subject: net: phy: micrel: Update KSZ87xx PHY name The KSZ8795 PHY ID is in fact used by KSZ8794/KSZ8795/KSZ8765 switches. Update the PHY ID and name to reflect that, as this family of switches is commonly refered to as KSZ87xx Signed-off-by: Marek Vasut Cc: Andrew Lunn Cc: David S. Miller Cc: Florian Fainelli Cc: George McCollister Cc: Heiner Kallweit Cc: Sean Nyekjaer Cc: Tristram Ha Cc: Woojung Huh Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad24554f11f9..75f880c25bb8 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -31,7 +31,7 @@ #define PHY_ID_KSZ886X 0x00221430 #define PHY_ID_KSZ8863 0x00221435 -#define PHY_ID_KSZ8795 0x00221550 +#define PHY_ID_KSZ87XX 0x00221550 #define PHY_ID_KSZ9477 0x00221631 -- cgit v1.2.3 From 69923208431e097ce3830647aee98e5bd3e889c8 Mon Sep 17 00:00:00 2001 From: Matthias Maennich Date: Fri, 18 Oct 2019 10:31:42 +0100 Subject: symbol namespaces: revert to previous __ksymtab name scheme The introduction of Symbol Namespaces changed the naming schema of the __ksymtab entries from __kysmtab__symbol to __ksymtab_NAMESPACE.symbol. That caused some breakages in tools that depend on the name layout in either the binaries(vmlinux,*.ko) or in System.map. E.g. kmod's depmod would not be able to read System.map without a patch to support symbol namespaces. A warning reported by depmod for namespaced symbols would look like depmod: WARNING: [...]/uas.ko needs unknown symbol usb_stor_adjust_quirks In order to address this issue, revert to the original naming scheme and rather read the __kstrtabns_ entries and their corresponding values from __ksymtab_strings to update the namespace values for symbols. After having read all symbols and handled them in handle_modversions(), the symbols are created. In a second pass, read the __kstrtabns_ entries and update the namespaces accordingly. Fixes: 8651ec01daed ("module: add support for symbol namespaces.") Reported-by: Stefan Wahren Suggested-by: Masahiro Yamada Acked-by: Will Deacon Reviewed-by: Greg Kroah-Hartman Reviewed-by: Masahiro Yamada Signed-off-by: Matthias Maennich Signed-off-by: Jessica Yu --- include/linux/export.h | 14 +++++--------- 1 file changed, 5 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/export.h b/include/linux/export.h index 621158ecd2e2..941d075f03d6 100644 --- a/include/linux/export.h +++ b/include/linux/export.h @@ -18,8 +18,6 @@ extern struct module __this_module; #define THIS_MODULE ((struct module *)0) #endif -#define NS_SEPARATOR "." - #ifdef CONFIG_MODVERSIONS /* Mark the CRC weak since genksyms apparently decides not to * generate a checksums for some symbols */ @@ -48,11 +46,11 @@ extern struct module __this_module; * absolute relocations that require runtime processing on relocatable * kernels. */ -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ __ADDRESSABLE(sym) \ asm(" .section \"___ksymtab" sec "+" #sym "\", \"a\" \n" \ " .balign 4 \n" \ - "__ksymtab_" #ns NS_SEPARATOR #sym ": \n" \ + "__ksymtab_" #sym ": \n" \ " .long " #sym "- . \n" \ " .long __kstrtab_" #sym "- . \n" \ " .long __kstrtabns_" #sym "- . \n" \ @@ -74,16 +72,14 @@ struct kernel_symbol { int namespace_offset; }; #else -#define __KSYMTAB_ENTRY_NS(sym, sec, ns) \ - static const struct kernel_symbol __ksymtab_##sym##__##ns \ - asm("__ksymtab_" #ns NS_SEPARATOR #sym) \ +#define __KSYMTAB_ENTRY_NS(sym, sec) \ + static const struct kernel_symbol __ksymtab_##sym \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ = { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym } #define __KSYMTAB_ENTRY(sym, sec) \ static const struct kernel_symbol __ksymtab_##sym \ - asm("__ksymtab_" #sym) \ __attribute__((section("___ksymtab" sec "+" #sym), used)) \ __aligned(sizeof(void *)) \ = { (unsigned long)&sym, __kstrtab_##sym, NULL } @@ -115,7 +111,7 @@ struct kernel_symbol { static const char __kstrtabns_##sym[] \ __attribute__((section("__ksymtab_strings"), used, aligned(1))) \ = #ns; \ - __KSYMTAB_ENTRY_NS(sym, sec, ns) + __KSYMTAB_ENTRY_NS(sym, sec) #define ___EXPORT_SYMBOL(sym, sec) \ ___export_symbol_common(sym, sec); \ -- cgit v1.2.3 From 77751a466ebd1a785456556061a2db6d60ea3898 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Oct 2019 12:41:24 +0200 Subject: PM: QoS: Introduce frequency QoS Introduce frequency QoS, based on the "raw" low-level PM QoS, to represent min and max frequency requests and aggregate constraints. The min and max frequency requests are to be represented by struct freq_qos_request objects and the aggregate constraints are to be represented by struct freq_constraints objects. The latter are expected to be initialized with the help of freq_constraints_init(). The freq_qos_read_value() helper is defined to retrieve the aggregate constraints values from a given struct freq_constraints object and there are the freq_qos_add_request(), freq_qos_update_request() and freq_qos_remove_request() helpers to manipulate the min and max frequency requests. It is assumed that the the helpers will not run concurrently with each other for the same struct freq_qos_request object, so if that may be the case, their uses must ensure proper synchronization between them (e.g. through locking). In addition, freq_qos_add_notifier() and freq_qos_remove_notifier() are provided to add and remove notifiers that will trigger on aggregate constraint changes to and from a given struct freq_constraints object, respectively. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/pm_qos.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 222c3e01397c..57b93e3d8f29 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -267,4 +267,48 @@ static inline s32 dev_pm_qos_raw_resume_latency(struct device *dev) } #endif +#define FREQ_QOS_MIN_DEFAULT_VALUE 0 +#define FREQ_QOS_MAX_DEFAULT_VALUE (-1) + +enum freq_qos_req_type { + FREQ_QOS_MIN = 1, + FREQ_QOS_MAX, +}; + +struct freq_constraints { + struct pm_qos_constraints min_freq; + struct blocking_notifier_head min_freq_notifiers; + struct pm_qos_constraints max_freq; + struct blocking_notifier_head max_freq_notifiers; +}; + +struct freq_qos_request { + enum freq_qos_req_type type; + struct plist_node pnode; + struct freq_constraints *qos; +}; + +static inline int freq_qos_request_active(struct freq_qos_request *req) +{ + return !IS_ERR_OR_NULL(req->qos); +} + +void freq_constraints_init(struct freq_constraints *qos); + +s32 freq_qos_read_value(struct freq_constraints *qos, + enum freq_qos_req_type type); + +int freq_qos_add_request(struct freq_constraints *qos, + struct freq_qos_request *req, + enum freq_qos_req_type type, s32 value); +int freq_qos_update_request(struct freq_qos_request *req, s32 new_value); +int freq_qos_remove_request(struct freq_qos_request *req); + +int freq_qos_add_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); +int freq_qos_remove_notifier(struct freq_constraints *qos, + enum freq_qos_req_type type, + struct notifier_block *notifier); + #endif -- cgit v1.2.3 From 3000ce3c52f8b8db093e4dc649cd172390f71137 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Oct 2019 12:47:06 +0200 Subject: cpufreq: Use per-policy frequency QoS Replace the CPU device PM QoS used for the management of min and max frequency constraints in cpufreq (and its users) with per-policy frequency QoS to avoid problems with cpufreq policies covering more then one CPU. Namely, a cpufreq driver is registered with the subsys interface which calls cpufreq_add_dev() for each CPU, starting from CPU0, so currently the PM QoS notifiers are added to the first CPU in the policy (i.e. CPU0 in the majority of cases). In turn, when the cpufreq driver is unregistered, the subsys interface doing that calls cpufreq_remove_dev() for each CPU, starting from CPU0, and the PM QoS notifiers are only removed when cpufreq_remove_dev() is called for the last CPU in the policy, say CPUx, which as a rule is not CPU0 if the policy covers more than one CPU. Then, the PM QoS notifiers cannot be removed, because CPUx does not have them, and they are still there in the device PM QoS notifiers list of CPU0, which prevents new PM QoS notifiers from being registered for CPU0 on the next attempt to register the cpufreq driver. The same issue occurs when the first CPU in the policy goes offline before unregistering the driver. After this change it does not matter which CPU is the policy CPU at the driver registration time and whether or not it is online all the time, because the frequency QoS is per policy and not per CPU. Fixes: 67d874c3b2c6 ("cpufreq: Register notifiers with the PM QoS framework") Reported-by: Dmitry Osipenko Tested-by: Dmitry Osipenko Reported-by: Sudeep Holla Tested-by: Sudeep Holla Diagnosed-by: Viresh Kumar Link: https://lore.kernel.org/linux-pm/5ad2624194baa2f53acc1f1e627eb7684c577a19.1562210705.git.viresh.kumar@linaro.org/T/#md2d89e95906b8c91c15f582146173dce2e86e99f Link: https://lore.kernel.org/linux-pm/20191017094612.6tbkwoq4harsjcqv@vireshk-i7/T/#m30d48cc23b9a80467fbaa16e30f90b3828a5a29b Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/cpufreq.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index c57e88e85c41..92d5fdc8154e 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -13,6 +13,7 @@ #include #include #include +#include #include #include @@ -76,8 +77,10 @@ struct cpufreq_policy { struct work_struct update; /* if update_policy() needs to be * called, but you're in IRQ context */ - struct dev_pm_qos_request *min_freq_req; - struct dev_pm_qos_request *max_freq_req; + struct freq_constraints constraints; + struct freq_qos_request *min_freq_req; + struct freq_qos_request *max_freq_req; + struct cpufreq_frequency_table *freq_table; enum cpufreq_table_sorting freq_table_sorted; -- cgit v1.2.3 From 2aac8bdf7a0fbd3e2a34141d28b57a7e21482cf7 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Wed, 16 Oct 2019 12:47:53 +0200 Subject: PM: QoS: Drop frequency QoS types from device PM QoS There are no more active users of DEV_PM_QOS_MIN_FREQUENCY and DEV_PM_QOS_MAX_FREQUENCY device PM QoS request types, so drop them along with the code supporting them. Signed-off-by: Rafael J. Wysocki Acked-by: Viresh Kumar --- include/linux/pm_qos.h | 12 ------------ 1 file changed, 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pm_qos.h b/include/linux/pm_qos.h index 57b93e3d8f29..ebf5ef17cc2a 100644 --- a/include/linux/pm_qos.h +++ b/include/linux/pm_qos.h @@ -34,8 +34,6 @@ enum pm_qos_flags_status { #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT PM_QOS_LATENCY_ANY #define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS PM_QOS_LATENCY_ANY_NS #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE 0 -#define PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE 0 -#define PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE (-1) #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT (-1) #define PM_QOS_FLAG_NO_POWER_OFF (1 << 0) @@ -54,8 +52,6 @@ struct pm_qos_flags_request { enum dev_pm_qos_req_type { DEV_PM_QOS_RESUME_LATENCY = 1, DEV_PM_QOS_LATENCY_TOLERANCE, - DEV_PM_QOS_MIN_FREQUENCY, - DEV_PM_QOS_MAX_FREQUENCY, DEV_PM_QOS_FLAGS, }; @@ -97,14 +93,10 @@ struct pm_qos_flags { struct dev_pm_qos { struct pm_qos_constraints resume_latency; struct pm_qos_constraints latency_tolerance; - struct pm_qos_constraints min_frequency; - struct pm_qos_constraints max_frequency; struct pm_qos_flags flags; struct dev_pm_qos_request *resume_latency_req; struct dev_pm_qos_request *latency_tolerance_req; struct dev_pm_qos_request *flags_req; - struct dev_pm_qos_request *min_frequency_req; - struct dev_pm_qos_request *max_frequency_req; }; /* Action requested to pm_qos_update_target */ @@ -199,10 +191,6 @@ static inline s32 dev_pm_qos_read_value(struct device *dev, switch (type) { case DEV_PM_QOS_RESUME_LATENCY: return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; - case DEV_PM_QOS_MIN_FREQUENCY: - return PM_QOS_MIN_FREQUENCY_DEFAULT_VALUE; - case DEV_PM_QOS_MAX_FREQUENCY: - return PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE; default: WARN_ON(1); return 0; -- cgit v1.2.3