From b1a37ed00d7908a991c1d0f18a8cba3c2aa99bdc Mon Sep 17 00:00:00 2001 From: Lee Jones Date: Mon, 23 Jan 2023 12:39:11 +0000 Subject: HID: core: Provide new max_buffer_size attribute to over-ride the default Presently, when a report is processed, its proposed size, provided by the user of the API (as Report Size * Report Count) is compared against the subsystem default HID_MAX_BUFFER_SIZE (16k). However, some low-level HID drivers allocate a reduced amount of memory to their buffers (e.g. UHID only allocates UHID_DATA_MAX (4k) buffers), rending this check inadequate in some cases. In these circumstances, if the received report ends up being smaller than the proposed report size, the remainder of the buffer is zeroed. That is, the space between sizeof(csize) (size of the current report) and the rsize (size proposed i.e. Report Size * Report Count), which can be handled up to HID_MAX_BUFFER_SIZE (16k). Meaning that memset() shoots straight past the end of the buffer boundary and starts zeroing out in-use values, often resulting in calamity. This patch introduces a new variable into 'struct hid_ll_driver' where individual low-level drivers can over-ride the default maximum value of HID_MAX_BUFFER_SIZE (16k) with something more sympathetic to the interface. Signed-off-by: Lee Jones Signed-off-by: Jiri Kosina --- include/linux/hid.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid.h b/include/linux/hid.h index eaf8ab177303..1ea8c7a3570b 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -834,6 +834,7 @@ struct hid_driver { * @output_report: send output report to device * @idle: send idle request to device * @may_wakeup: return if device may act as a wakeup source during system-suspend + * @max_buffer_size: over-ride maximum data buffer size (default: HID_MAX_BUFFER_SIZE) */ struct hid_ll_driver { int (*start)(struct hid_device *hdev); @@ -859,6 +860,8 @@ struct hid_ll_driver { int (*idle)(struct hid_device *hdev, int report, int idle, int reqtype); bool (*may_wakeup)(struct hid_device *hdev); + + unsigned int max_buffer_size; }; extern bool hid_is_usb(const struct hid_device *hdev); -- cgit v1.2.3 From 80c16b2b121fbc3380dbffa9bab7559acbaaa2ed Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Mon, 6 Mar 2023 17:22:04 +0200 Subject: cpumask: Fix typo nr_cpumask_size --> nr_cpumask_bits The never used nr_cpumask_size is just a typo, hence use existing redefinition that's called nr_cpumask_bits. Signed-off-by: Andy Shevchenko Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 8fbe76607965..ce8eb7ef2107 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -66,7 +66,7 @@ static inline void set_nr_cpu_ids(unsigned int nr) * * Finally, some operations just want the exact limit, either because * they set bits or just don't have any faster fixed-sized versions. We - * call this just 'nr_cpumask_size'. + * call this just 'nr_cpumask_bits'. * * Note that these optional constants are always guaranteed to be at * least as big as 'nr_cpu_ids' itself is, and all our cpumask -- cgit v1.2.3 From c28cd1f3433c7e339315d1ddacaeacf0fdfbe252 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Mar 2023 17:46:38 -0800 Subject: clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro We already mark fwnodes as initialized when they are registered as clock providers. We do this so that fw_devlink can tell when a clock driver doesn't use the driver core framework to probe/initialize its device. This ensures fw_devlink doesn't block the consumers of such a clock provider indefinitely. However, some users of CLK_OF_DECLARE() macros don't use the same node that matches the macro as the node for the clock provider, but they initialize the entire node. To cover these cases, also mark the nodes that match the macros as initialized when the init callback function is called. An example of this is "stericsson,u8500-clks" that's handled using CLK_OF_DECLARE() and looks something like this: clocks { compatible = "stericsson,u8500-clks"; prcmu_clk: prcmu-clock { #clock-cells = <1>; }; prcc_pclk: prcc-periph-clock { #clock-cells = <2>; }; prcc_kclk: prcc-kernel-clock { #clock-cells = <2>; }; prcc_reset: prcc-reset-controller { #reset-cells = <2>; }; ... }; This patch makes sure that "clocks" is marked as initialized so that fw_devlink knows that all nodes under it have been initialized. If the driver creates struct devices for some of the subnodes, fw_devlink is smart enough to know to wait for those devices to probe, so no special handling is required for those cases. Cc: Greg Kroah-Hartman Reported-by: Linus Walleij Link: https://lore.kernel.org/lkml/CACRpkdamxDX6EBVjKX5=D3rkHp17f5pwGdBVhzFU90-0MHY6dQ@mail.gmail.com/ Fixes: 4a032827daa8 ("of: property: Simplify of_link_to_phandle()") Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20230302014639.297514-1-saravanak@google.com Reviewed-by: Linus Walleij Tested-by: Linus Walleij Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index 842e72a5348f..c9f5276006a0 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1363,7 +1363,13 @@ struct clk_hw_onecell_data { struct clk_hw *hws[]; }; -#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn) +#define CLK_OF_DECLARE(name, compat, fn) \ + static void __init name##_of_clk_init_declare(struct device_node *np) \ + { \ + fn(np); \ + fwnode_dev_initialized(of_fwnode_handle(np), true); \ + } \ + OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From 849ad04cf562ac63b0371a825eed473d84de9c6d Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 7 Mar 2023 01:50:53 -0500 Subject: new helper: put_and_unmap_page() kunmap_local() + put_page(), as done by e.g. ext2 directory handling. Signed-off-by: Al Viro --- include/linux/highmem.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/highmem.h b/include/linux/highmem.h index b06254e76d99..8fc10089e19e 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -481,4 +481,10 @@ static inline void folio_zero_range(struct folio *folio, zero_user_segments(&folio->page, start, start + length, 0, 0); } +static inline void put_and_unmap_page(struct page *page, void *addr) +{ + kunmap_local(addr); + put_page(page); +} + #endif /* _LINUX_HIGHMEM_H */ -- cgit v1.2.3 From 63355b9884b3d1677de6bd1517cd2b8a9bf53978 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 7 Mar 2023 12:16:18 -0800 Subject: cpumask: be more careful with 'cpumask_setall()' Commit 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations") changed cpumask_setall() to use "bitmap_set()" instead of "bitmap_fill()", because bitmap_fill() would explicitly set all the bits of a constant sized small bitmap, and that's exactly what we don't want: we want to only set bits up to 'nr_cpu_ids', which is what "bitmap_set()" does. However, Yury correctly points out that while "bitmap_set()" does indeed only set bits up to the required bitmap size, it doesn't _clear_ bits above that size, so the upper bits would still not have well-defined values. Now, none of this should really matter, since any bits set past 'nr_cpu_ids' should always be ignored in the first place. Yes, the bit scanning functions might return them as a result, but since users should always consider the ">= nr_cpu_ids" condition to mean "no more bits", that shouldn't have any actual effect (see previous commit 8ca09d5fa354 "cpumask: fix incorrect cpumask scanning result checks"). But let's just do it right, the way the code was _intended_ to work. We have had enough lazy code that works but bites us in the *rse later (again, see previous commit) that there's no reason to not just do this properly. It turns out that "bitmap_fill()" gets this all right for the complex case, and really only fails for the inlined optimized case that just fills the whole word. And while we could just fix bitmap_fill() to use the proper last word mask, there's two issues with that: - the cpumask case wants to do the _optimization_ based on "NR_CPUS is a small constant", but then wants to do the actual bit _fill_ based on "nr_cpu_ids" that isn't necessarily that same constant - we have lots of non-cpumask users of bitmap_fill(), and while they hopefully don't care, and probably would want the proper semantics anyway ("only set bits up to the limit"), I do not want the cpumask changes to impact other parts So this ends up just doing the single-word optimization by hand in the cpumask code. If our cpumask is fundamentally limited to a single word, just do the proper "fill in that word" exactly. And if it's the more complex multi-word case, then the generic bitmap_fill() will DTRT. This is all an example of how our bitmap function optimizations really are somewhat broken. They conflate the "this is size of the bitmap" optimizations with the actual bit(s) we want to set. In many cases we really want to have the two be separate things: sometimes we base our optimizations on the size of the whole bitmap ("I know this whole bitmap fits in a single word, so I'll just use single-word accesses"), and sometimes we base them on the bit we are looking at ("this is just acting on bits that are in the first word, so I'll use single-word accesses"). Notice how the end result of the two optimizations are the same, but the way we get to them are quite different. And all our cpumask optimization games are really about that fundamental distinction, and we'd often really want to pass in both the "this is the bit I'm working on" (which _can_ be a small constant but might be variable), and "I know it's in this range even if it's variable" (based on CONFIG_NR_CPUS). So this cpumask_setall() implementation just makes that explicit. It checks the "I statically know the size is small" using the known static size of the cpumask (which is what that 'small_cpumask_bits' is all about), but then sets the actual bits using the exact number of cpus we have (ie 'nr_cpumask_bits') Of course, in a perfect world, the compiler would have done all the range analysis (possibly with help from us just telling it that "this value is always in this range"), and would do all of this for us. But that is not the world we live in. While we dream of that perfect world, this does that manual logic to make it all work out. And this was a very long explanation for a small code change that shouldn't even matter. Reported-by: Yury Norov Link: https://lore.kernel.org/lkml/ZAV9nGG9e1%2FrV+L%2F@yury-laptop/ Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ce8eb7ef2107..63d637d18e79 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -518,14 +518,14 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask * /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer - * - * Note: since we set bits, we should use the tighter 'bitmap_set()' with - * the eact number of bits, not 'bitmap_fill()' that will fill past the - * end. */ static inline void cpumask_setall(struct cpumask *dstp) { - bitmap_set(cpumask_bits(dstp), 0, nr_cpumask_bits); + if (small_const_nbits(small_cpumask_bits)) { + cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits); + return; + } + bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** -- cgit v1.2.3 From eb59eca0d8ac15f8c1b7f1cd35999455a90292c0 Mon Sep 17 00:00:00 2001 From: Johan Hovold Date: Mon, 6 Mar 2023 08:56:31 +0100 Subject: interconnect: fix provider registration API The current interconnect provider interface is inherently racy as providers are expected to be added before being fully initialised. Specifically, nodes are currently not added and the provider data is not initialised until after registering the provider which can cause racing DT lookups to fail. Add a new provider API which will be used to fix up the interconnect drivers. The old API is reimplemented using the new interface and will be removed once all drivers have been fixed. Fixes: 11f1ceca7031 ("interconnect: Add generic on-chip interconnect API") Fixes: 87e3031b6fbd ("interconnect: Allow endpoints translation via DT") Cc: stable@vger.kernel.org # 5.1 Reviewed-by: Konrad Dybcio Signed-off-by: Johan Hovold Tested-by: Luca Ceresoli # i.MX8MP MSC SM2-MB-EP1 Board Link: https://lore.kernel.org/r/20230306075651.2449-4-johan+linaro@kernel.org Signed-off-by: Georgi Djakov --- drivers/interconnect/core.c | 52 +++++++++++++++++++++++++---------- include/linux/interconnect-provider.h | 12 ++++++++ 2 files changed, 50 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c index cabb6f5df83e..7a24c1444ace 100644 --- a/drivers/interconnect/core.c +++ b/drivers/interconnect/core.c @@ -1033,44 +1033,68 @@ int icc_nodes_remove(struct icc_provider *provider) EXPORT_SYMBOL_GPL(icc_nodes_remove); /** - * icc_provider_add() - add a new interconnect provider - * @provider: the interconnect provider that will be added into topology + * icc_provider_init() - initialize a new interconnect provider + * @provider: the interconnect provider to initialize + * + * Must be called before adding nodes to the provider. + */ +void icc_provider_init(struct icc_provider *provider) +{ + WARN_ON(!provider->set); + + INIT_LIST_HEAD(&provider->nodes); +} +EXPORT_SYMBOL_GPL(icc_provider_init); + +/** + * icc_provider_register() - register a new interconnect provider + * @provider: the interconnect provider to register * * Return: 0 on success, or an error code otherwise */ -int icc_provider_add(struct icc_provider *provider) +int icc_provider_register(struct icc_provider *provider) { - if (WARN_ON(!provider->set)) - return -EINVAL; if (WARN_ON(!provider->xlate && !provider->xlate_extended)) return -EINVAL; mutex_lock(&icc_lock); - - INIT_LIST_HEAD(&provider->nodes); list_add_tail(&provider->provider_list, &icc_providers); - mutex_unlock(&icc_lock); - dev_dbg(provider->dev, "interconnect provider added to topology\n"); + dev_dbg(provider->dev, "interconnect provider registered\n"); return 0; } -EXPORT_SYMBOL_GPL(icc_provider_add); +EXPORT_SYMBOL_GPL(icc_provider_register); /** - * icc_provider_del() - delete previously added interconnect provider - * @provider: the interconnect provider that will be removed from topology + * icc_provider_deregister() - deregister an interconnect provider + * @provider: the interconnect provider to deregister */ -void icc_provider_del(struct icc_provider *provider) +void icc_provider_deregister(struct icc_provider *provider) { mutex_lock(&icc_lock); WARN_ON(provider->users); - WARN_ON(!list_empty(&provider->nodes)); list_del(&provider->provider_list); mutex_unlock(&icc_lock); } +EXPORT_SYMBOL_GPL(icc_provider_deregister); + +int icc_provider_add(struct icc_provider *provider) +{ + icc_provider_init(provider); + + return icc_provider_register(provider); +} +EXPORT_SYMBOL_GPL(icc_provider_add); + +void icc_provider_del(struct icc_provider *provider) +{ + WARN_ON(!list_empty(&provider->nodes)); + + icc_provider_deregister(provider); +} EXPORT_SYMBOL_GPL(icc_provider_del); static const struct of_device_id __maybe_unused ignore_list[] = { diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h index cd5c5a27557f..d12cd18aab3f 100644 --- a/include/linux/interconnect-provider.h +++ b/include/linux/interconnect-provider.h @@ -122,6 +122,9 @@ int icc_link_destroy(struct icc_node *src, struct icc_node *dst); void icc_node_add(struct icc_node *node, struct icc_provider *provider); void icc_node_del(struct icc_node *node); int icc_nodes_remove(struct icc_provider *provider); +void icc_provider_init(struct icc_provider *provider); +int icc_provider_register(struct icc_provider *provider); +void icc_provider_deregister(struct icc_provider *provider); int icc_provider_add(struct icc_provider *provider); void icc_provider_del(struct icc_provider *provider); struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec); @@ -167,6 +170,15 @@ static inline int icc_nodes_remove(struct icc_provider *provider) return -ENOTSUPP; } +static inline void icc_provider_init(struct icc_provider *provider) { } + +static inline int icc_provider_register(struct icc_provider *provider) +{ + return -ENOTSUPP; +} + +static inline void icc_provider_deregister(struct icc_provider *provider) { } + static inline int icc_provider_add(struct icc_provider *provider) { return -ENOTSUPP; -- cgit v1.2.3 From 03c835f498b540087244a6757e87dfe7ef10999b Mon Sep 17 00:00:00 2001 From: Uwe Kleine-König Date: Sun, 26 Feb 2023 23:26:52 +0100 Subject: i2c: Switch .probe() to not take an id parameter MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit b8a1a4cd5a98 ("i2c: Provide a temporary .probe_new() call-back type") introduced a new probe callback to convert i2c init routines to not take an i2c_device_id parameter. Now that all in-tree drivers are converted to the temporary .probe_new() callback, .probe() can be modified to match the desired prototype. Now that .probe() and .probe_new() have the same semantic, they can be defined as members of an anonymous union to save some memory and simplify the core code a bit. Signed-off-by: Uwe Kleine-König Signed-off-by: Wolfram Sang --- drivers/i2c/i2c-core-base.c | 11 ++--------- include/linux/i2c.h | 18 +++++++++++------- 2 files changed, 13 insertions(+), 16 deletions(-) (limited to 'include/linux') diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c index cb5fa971d67e..63253e2b2c1f 100644 --- a/drivers/i2c/i2c-core-base.c +++ b/drivers/i2c/i2c-core-base.c @@ -561,15 +561,8 @@ static int i2c_device_probe(struct device *dev) goto err_detach_pm_domain; } - /* - * When there are no more users of probe(), - * rename probe_new to probe. - */ - if (driver->probe_new) - status = driver->probe_new(client); - else if (driver->probe) - status = driver->probe(client, - i2c_match_id(driver->id_table, client)); + if (driver->probe) + status = driver->probe(client); else status = -EINVAL; diff --git a/include/linux/i2c.h b/include/linux/i2c.h index 500404d85141..5ba89663ea86 100644 --- a/include/linux/i2c.h +++ b/include/linux/i2c.h @@ -236,8 +236,8 @@ enum i2c_driver_flags { /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) - * @probe: Callback for device binding - soon to be deprecated - * @probe_new: New callback for device binding + * @probe: Callback for device binding + * @probe_new: Transitional callback for device binding - do not use * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown * @alert: Alert callback, for example for the SMBus alert protocol @@ -272,14 +272,18 @@ enum i2c_driver_flags { struct i2c_driver { unsigned int class; + union { /* Standard driver model interfaces */ - int (*probe)(struct i2c_client *client, const struct i2c_device_id *id); + int (*probe)(struct i2c_client *client); + /* + * Legacy callback that was part of a conversion of .probe(). + * Today it has the same semantic as .probe(). Don't use for new + * code. + */ + int (*probe_new)(struct i2c_client *client); + }; void (*remove)(struct i2c_client *client); - /* New driver model interface to aid the seamless removal of the - * current probe()'s, more commonly unused than used second parameter. - */ - int (*probe_new)(struct i2c_client *client); /* driver model interfaces that don't relate to enumeration */ void (*shutdown)(struct i2c_client *client); -- cgit v1.2.3 From 5cf9d015be160e2d90d29ae74ef1364390e8fce8 Mon Sep 17 00:00:00 2001 From: Nathan Chancellor Date: Wed, 8 Mar 2023 13:47:11 -0700 Subject: clk: Avoid invalid function names in CLK_OF_DECLARE() After commit c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro"), drivers/clk/mvebu/kirkwood.c fails to build: drivers/clk/mvebu/kirkwood.c:358:1: error: expected identifier or '(' CLK_OF_DECLARE(98dx1135_clk, "marvell,mv98dx1135-core-clock", ^ include/linux/clk-provider.h:1367:21: note: expanded from macro 'CLK_OF_DECLARE' static void __init name##_of_clk_init_declare(struct device_node *np) \ ^ :124:1: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ drivers/clk/mvebu/kirkwood.c:358:1: error: invalid digit 'd' in decimal constant include/linux/clk-provider.h:1372:34: note: expanded from macro 'CLK_OF_DECLARE' OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) ^ :125:3: note: expanded from here 98dx1135_clk_of_clk_init_declare ^ C function names must start with either an alphabetic letter or an underscore. To avoid generating invalid function names from clock names, add two underscores to the beginning of the identifier. Fixes: c28cd1f3433c ("clk: Mark a fwnode as initialized when using CLK_OF_DECLARE() macro") Suggested-by: Saravana Kannan Signed-off-by: Nathan Chancellor Link: https://lore.kernel.org/r/20230308-clk_of_declare-fix-v1-1-317b741e2532@kernel.org Reviewed-by: Saravana Kannan Reported-by: Naresh Kamboju Signed-off-by: Stephen Boyd --- include/linux/clk-provider.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h index c9f5276006a0..6f3175f0678a 100644 --- a/include/linux/clk-provider.h +++ b/include/linux/clk-provider.h @@ -1364,12 +1364,12 @@ struct clk_hw_onecell_data { }; #define CLK_OF_DECLARE(name, compat, fn) \ - static void __init name##_of_clk_init_declare(struct device_node *np) \ + static void __init __##name##_of_clk_init_declare(struct device_node *np) \ { \ fn(np); \ fwnode_dev_initialized(of_fwnode_handle(np), true); \ } \ - OF_DECLARE_1(clk, name, compat, name##_of_clk_init_declare) + OF_DECLARE_1(clk, name, compat, __##name##_of_clk_init_declare) /* * Use this macro when you have a driver that requires two initialization -- cgit v1.2.3 From fe9ae05cfbe587dda724fcf537c00bc2f287da62 Mon Sep 17 00:00:00 2001 From: Takashi Iwai Date: Wed, 8 Mar 2023 11:50:12 +0100 Subject: fbdev: Fix incorrect page mapping clearance at fb_deferred_io_release() The recent fix for the deferred I/O by the commit 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") caused a regression when the same fb device is opened/closed while it's being used. It resulted in a frozen screen even if something is redrawn there after the close. The breakage is because the patch was made under a wrong assumption of a single open; in the current code, fb_deferred_io_release() cleans up the page mapping of the pageref list and it calls cancel_delayed_work_sync() unconditionally, where both are no correct behavior for multiple opens. This patch adds a refcount for the opens of the device, and applies the cleanup only when all files get closed. As both fb_deferred_io_open() and _close() are called always in the fb_info lock (mutex), it's safe to use the normal int for the refcounting. Also, a useless BUG_ON() is dropped. Fixes: 3efc61d95259 ("fbdev: Fix invalid page access after closing deferred I/O devices") Cc: Signed-off-by: Takashi Iwai Reviewed-by: Patrik Jakobsson Signed-off-by: Thomas Zimmermann Link: https://patchwork.freedesktop.org/patch/msgid/20230308105012.1845-1-tiwai@suse.de --- drivers/video/fbdev/core/fb_defio.c | 17 +++++++++++++---- include/linux/fb.h | 1 + 2 files changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c index 583cbcf09446..a3cf1f764f29 100644 --- a/drivers/video/fbdev/core/fb_defio.c +++ b/drivers/video/fbdev/core/fb_defio.c @@ -309,17 +309,18 @@ void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file) { + struct fb_deferred_io *fbdefio = info->fbdefio; + file->f_mapping->a_ops = &fb_deferred_io_aops; + fbdefio->open_count++; } EXPORT_SYMBOL_GPL(fb_deferred_io_open); -void fb_deferred_io_release(struct fb_info *info) +static void fb_deferred_io_lastclose(struct fb_info *info) { - struct fb_deferred_io *fbdefio = info->fbdefio; struct page *page; int i; - BUG_ON(!fbdefio); cancel_delayed_work_sync(&info->deferred_work); /* clear out the mapping that we setup */ @@ -328,13 +329,21 @@ void fb_deferred_io_release(struct fb_info *info) page->mapping = NULL; } } + +void fb_deferred_io_release(struct fb_info *info) +{ + struct fb_deferred_io *fbdefio = info->fbdefio; + + if (!--fbdefio->open_count) + fb_deferred_io_lastclose(info); +} EXPORT_SYMBOL_GPL(fb_deferred_io_release); void fb_deferred_io_cleanup(struct fb_info *info) { struct fb_deferred_io *fbdefio = info->fbdefio; - fb_deferred_io_release(info); + fb_deferred_io_lastclose(info); kvfree(info->pagerefs); mutex_destroy(&fbdefio->lock); diff --git a/include/linux/fb.h b/include/linux/fb.h index 73eb1f85ea8e..05e40fcc7696 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -212,6 +212,7 @@ struct fb_deferred_io { /* delay between mkwrite and deferred handler */ unsigned long delay; bool sort_pagereflist; /* sort pagelist by offset */ + int open_count; /* number of opened files; protected by fb_info lock */ struct mutex lock; /* mutex that protects the pageref list */ struct list_head pagereflist; /* list of pagerefs for touched pages */ /* callback */ -- cgit v1.2.3 From 62913ae96de747091c4dacd06d158e7729c1a76d Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 7 Mar 2023 23:15:49 -0500 Subject: ext4, jbd2: add an optimized bmap for the journal inode The generic bmap() function exported by the VFS takes locks and does checks that are not necessary for the journal inode. So allow the file system to set a journal-optimized bmap function in journal->j_bmap. Reported-by: syzbot+9543479984ae9e576000@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=e4aaa78795e490421c79f76ec3679006c8ff4cf0 Signed-off-by: Theodore Ts'o --- fs/ext4/super.c | 23 +++++++++++++++++++++++ fs/jbd2/journal.c | 9 ++++++--- include/linux/jbd2.h | 8 ++++++++ 3 files changed, 37 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 2192b4111442..46b7345d2b6a 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5742,6 +5742,28 @@ static struct inode *ext4_get_journal_inode(struct super_block *sb, return journal_inode; } +static int ext4_journal_bmap(journal_t *journal, sector_t *block) +{ + struct ext4_map_blocks map; + int ret; + + if (journal->j_inode == NULL) + return 0; + + map.m_lblk = *block; + map.m_len = 1; + ret = ext4_map_blocks(NULL, journal->j_inode, &map, 0); + if (ret <= 0) { + ext4_msg(journal->j_inode->i_sb, KERN_CRIT, + "journal bmap failed: block %llu ret %d\n", + *block, ret); + jbd2_journal_abort(journal, ret ? ret : -EIO); + return ret; + } + *block = map.m_pblk; + return 0; +} + static journal_t *ext4_get_journal(struct super_block *sb, unsigned int journal_inum) { @@ -5762,6 +5784,7 @@ static journal_t *ext4_get_journal(struct super_block *sb, return NULL; } journal->j_private = sb; + journal->j_bmap = ext4_journal_bmap; ext4_init_journal_params(sb, journal); return journal; } diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 2696f43e7239..c84f588fdcd0 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -970,10 +970,13 @@ int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr, { int err = 0; unsigned long long ret; - sector_t block = 0; + sector_t block = blocknr; - if (journal->j_inode) { - block = blocknr; + if (journal->j_bmap) { + err = journal->j_bmap(journal, &block); + if (err == 0) + *retp = block; + } else if (journal->j_inode) { ret = bmap(journal->j_inode, &block); if (ret || !block) { diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index 2170e0cc279d..6ffa34c51a11 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1308,6 +1308,14 @@ struct journal_s struct buffer_head *bh, enum passtype pass, int off, tid_t expected_commit_id); + + /** + * @j_bmap: + * + * Bmap function that should be used instead of the generic + * VFS bmap function. + */ + int (*j_bmap)(struct journal_s *journal, sector_t *block); }; #define jbd2_might_wait_for_commit(j) \ -- cgit v1.2.3 From e7304080e0e50d979ce9eaf694ad8283e2e539ea Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 12 Mar 2023 08:52:03 -0700 Subject: cpumask: relax sanity checking constraints The cpumask_check() was unnecessarily tight, and causes problems for the users of cpumask_next(). We have a number of users that take the previous return value of one of the bit scanning functions and subtract one to keep it in "range". But since the scanning functions end up returning up to 'small_cpumask_bits' instead of the tighter 'nr_cpumask_bits', the range really needs to be using that widened form. [ This "previous-1" behavior is also the reason we have all those comments about /* -1 is a legal arg here. */ and separate checks for that being ok. So we could have just made "small_cpumask_bits-1" be a similar special "don't check this" value. Tetsuo Handa even suggested a patch that only does that for cpumask_next(), since that seems to be the only actual case that triggers, but that all makes it even _more_ magical and special. So just relax the check ] One example of this kind of pattern being the 'c_start()' function in arch/x86/kernel/cpu/proc.c, but also duplicated in various forms on other architectures. Reported-by: syzbot+96cae094d90877641f32@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?extid=96cae094d90877641f32 Reported-by: Tetsuo Handa Link: https://lore.kernel.org/lkml/c1f4cc16-feea-b83c-82cf-1a1f007b7eb9@I-love.SAKURA.ne.jp/ Fixes: 596ff4a09b89 ("cpumask: re-introduce constant-sized cpumask optimizations") Signed-off-by: Linus Torvalds --- include/linux/cpumask.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 63d637d18e79..d4901ca8883c 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -147,7 +147,7 @@ static __always_inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bit /* verify cpu argument to cpumask_* operators */ static __always_inline unsigned int cpumask_check(unsigned int cpu) { - cpu_max_bits_warn(cpu, nr_cpumask_bits); + cpu_max_bits_warn(cpu, small_cpumask_bits); return cpu; } -- cgit v1.2.3 From ab909509850b27fd39b8ba99e44cda39dbc3858c Mon Sep 17 00:00:00 2001 From: Niklas Schnelle Date: Mon, 6 Mar 2023 16:10:11 +0100 Subject: PCI: s390: Fix use-after-free of PCI resources with per-function hotplug On s390 PCI functions may be hotplugged individually even when they belong to a multi-function device. In particular on an SR-IOV device VFs may be removed and later re-added. In commit a50297cf8235 ("s390/pci: separate zbus creation from scanning") it was missed however that struct pci_bus and struct zpci_bus's resource list retained a reference to the PCI functions MMIO resources even though those resources are released and freed on hot-unplug. These stale resources may subsequently be claimed when the PCI function re-appears resulting in use-after-free. One idea of fixing this use-after-free in s390 specific code that was investigated was to simply keep resources around from the moment a PCI function first appeared until the whole virtual PCI bus created for a multi-function device disappears. The problem with this however is that due to the requirement of artificial MMIO addreesses (address cookies) extra logic is then needed to keep the address cookies compatible on re-plug. At the same time the MMIO resources semantically belong to the PCI function so tying their lifecycle to the function seems more logical. Instead a simpler approach is to remove the resources of an individually hot-unplugged PCI function from the PCI bus's resource list while keeping the resources of other PCI functions on the PCI bus untouched. This is done by introducing pci_bus_remove_resource() to remove an individual resource. Similarly the resource also needs to be removed from the struct zpci_bus's resource list. It turns out however, that there is really no need to add the MMIO resources to the struct zpci_bus's resource list at all and instead we can simply use the zpci_bar_struct's resource pointer directly. Fixes: a50297cf8235 ("s390/pci: separate zbus creation from scanning") Signed-off-by: Niklas Schnelle Reviewed-by: Matthew Rosato Acked-by: Bjorn Helgaas Link: https://lore.kernel.org/r/20230306151014.60913-2-schnelle@linux.ibm.com Signed-off-by: Vasily Gorbik --- arch/s390/pci/pci.c | 16 ++++++++++------ arch/s390/pci/pci_bus.c | 12 +++++------- arch/s390/pci/pci_bus.h | 3 +-- drivers/pci/bus.c | 21 +++++++++++++++++++++ include/linux/pci.h | 1 + 5 files changed, 38 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c index ef38b1514c77..e16afacc8fd1 100644 --- a/arch/s390/pci/pci.c +++ b/arch/s390/pci/pci.c @@ -544,8 +544,7 @@ static struct resource *__alloc_res(struct zpci_dev *zdev, unsigned long start, return r; } -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources) +int zpci_setup_bus_resources(struct zpci_dev *zdev) { unsigned long addr, size, flags; struct resource *res; @@ -581,7 +580,6 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, return -ENOMEM; } zdev->bars[i].res = res; - pci_add_resource(resources, res); } zdev->has_resources = 1; @@ -590,17 +588,23 @@ int zpci_setup_bus_resources(struct zpci_dev *zdev, static void zpci_cleanup_bus_resources(struct zpci_dev *zdev) { + struct resource *res; int i; + pci_lock_rescan_remove(); for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!zdev->bars[i].size || !zdev->bars[i].res) + res = zdev->bars[i].res; + if (!res) continue; + release_resource(res); + pci_bus_remove_resource(zdev->zbus->bus, res); zpci_free_iomap(zdev, zdev->bars[i].map_idx); - release_resource(zdev->bars[i].res); - kfree(zdev->bars[i].res); + zdev->bars[i].res = NULL; + kfree(res); } zdev->has_resources = 0; + pci_unlock_rescan_remove(); } int pcibios_device_add(struct pci_dev *pdev) diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c index 6a8da1b742ae..a99926af2b69 100644 --- a/arch/s390/pci/pci_bus.c +++ b/arch/s390/pci/pci_bus.c @@ -41,9 +41,7 @@ static int zpci_nb_devices; */ static int zpci_bus_prepare_device(struct zpci_dev *zdev) { - struct resource_entry *window, *n; - struct resource *res; - int rc; + int rc, i; if (!zdev_enabled(zdev)) { rc = zpci_enable_device(zdev); @@ -57,10 +55,10 @@ static int zpci_bus_prepare_device(struct zpci_dev *zdev) } if (!zdev->has_resources) { - zpci_setup_bus_resources(zdev, &zdev->zbus->resources); - resource_list_for_each_entry_safe(window, n, &zdev->zbus->resources) { - res = window->res; - pci_bus_add_resource(zdev->zbus->bus, res, 0); + zpci_setup_bus_resources(zdev); + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (zdev->bars[i].res) + pci_bus_add_resource(zdev->zbus->bus, zdev->bars[i].res, 0); } } diff --git a/arch/s390/pci/pci_bus.h b/arch/s390/pci/pci_bus.h index e96c9860e064..af9f0ac79a1b 100644 --- a/arch/s390/pci/pci_bus.h +++ b/arch/s390/pci/pci_bus.h @@ -30,8 +30,7 @@ static inline void zpci_zdev_get(struct zpci_dev *zdev) int zpci_alloc_domain(int domain); void zpci_free_domain(int domain); -int zpci_setup_bus_resources(struct zpci_dev *zdev, - struct list_head *resources); +int zpci_setup_bus_resources(struct zpci_dev *zdev); static inline struct zpci_dev *zdev_from_bus(struct pci_bus *bus, unsigned int devfn) diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index 83ae838ceb5f..549c4bd5caec 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -76,6 +76,27 @@ struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n) } EXPORT_SYMBOL_GPL(pci_bus_resource_n); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res) +{ + struct pci_bus_resource *bus_res, *tmp; + int i; + + for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) { + if (bus->resource[i] == res) { + bus->resource[i] = NULL; + return; + } + } + + list_for_each_entry_safe(bus_res, tmp, &bus->resources, list) { + if (bus_res->res == res) { + list_del(&bus_res->list); + kfree(bus_res); + return; + } + } +} + void pci_bus_remove_resources(struct pci_bus *bus) { int i; diff --git a/include/linux/pci.h b/include/linux/pci.h index fafd8020c6d7..b50e5c79f7e3 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1438,6 +1438,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res, unsigned int flags); struct resource *pci_bus_resource_n(const struct pci_bus *bus, int n); void pci_bus_remove_resources(struct pci_bus *bus); +void pci_bus_remove_resource(struct pci_bus *bus, struct resource *res); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); -- cgit v1.2.3 From 8b3a149db461d3286d1e211112de3b44ccaeaf71 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Sun, 12 Mar 2023 23:00:03 +0100 Subject: efi: earlycon: Reprobe after parsing config tables Commit 732ea9db9d8a ("efi: libstub: Move screen_info handling to common code") reorganized the earlycon handling so that all architectures pass the screen_info data via a EFI config table instead of populating struct screen_info directly, as the latter is only possible when the EFI stub is baked into the kernel (and not into the decompressor). However, this means that struct screen_info may not have been populated yet by the time the earlycon probe takes place, and this results in a non-functional early console. So let's probe again right after parsing the config tables and populating struct screen_info. Note that this means that earlycon output starts a bit later than before, and so it may fail to capture issues that occur while doing the early EFI initialization. Fixes: 732ea9db9d8a ("efi: libstub: Move screen_info handling to common code") Reported-by: Shawn Guo Tested-by: Shawn Guo Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/earlycon.c | 16 +++++++++++++--- drivers/firmware/efi/efi-init.c | 3 +++ include/linux/efi.h | 1 + 3 files changed, 17 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/earlycon.c b/drivers/firmware/efi/earlycon.c index f54e6fdf08e2..f80a9af3d16e 100644 --- a/drivers/firmware/efi/earlycon.c +++ b/drivers/firmware/efi/earlycon.c @@ -215,6 +215,14 @@ efi_earlycon_write(struct console *con, const char *str, unsigned int num) } } +static bool __initdata fb_probed; + +void __init efi_earlycon_reprobe(void) +{ + if (fb_probed) + setup_earlycon("efifb"); +} + static int __init efi_earlycon_setup(struct earlycon_device *device, const char *opt) { @@ -222,15 +230,17 @@ static int __init efi_earlycon_setup(struct earlycon_device *device, u16 xres, yres; u32 i; - if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) + fb_wb = opt && !strcmp(opt, "ram"); + + if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI) { + fb_probed = true; return -ENODEV; + } fb_base = screen_info.lfb_base; if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) fb_base |= (u64)screen_info.ext_lfb_base << 32; - fb_wb = opt && !strcmp(opt, "ram"); - si = &screen_info; xres = si->lfb_width; yres = si->lfb_height; diff --git a/drivers/firmware/efi/efi-init.c b/drivers/firmware/efi/efi-init.c index 2c16080e1f71..ef0820f1a924 100644 --- a/drivers/firmware/efi/efi-init.c +++ b/drivers/firmware/efi/efi-init.c @@ -72,6 +72,9 @@ static void __init init_screen_info(void) if (memblock_is_map_memory(screen_info.lfb_base)) memblock_mark_nomap(screen_info.lfb_base, screen_info.lfb_size); + + if (IS_ENABLED(CONFIG_EFI_EARLYCON)) + efi_earlycon_reprobe(); } } diff --git a/include/linux/efi.h b/include/linux/efi.h index 04a733f0ba95..7aa62c92185f 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -693,6 +693,7 @@ efi_guid_to_str(efi_guid_t *guid, char *out) } extern void efi_init (void); +extern void efi_earlycon_reprobe(void); #ifdef CONFIG_EFI extern void efi_enter_virtual_mode (void); /* switch EFI to virtual mode, if possible */ #else -- cgit v1.2.3 From 34e0a279a993debaff03158fc2fbf6a00c093643 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Mon, 13 Mar 2023 10:30:02 +0100 Subject: block: do not reverse request order when flushing plug list Commit 26fed4ac4eab ("block: flush plug based on hardware and software queue order") changed flushing of plug list to submit requests one device at a time. However while doing that it also started using list_add_tail() instead of list_add() used previously thus effectively submitting requests in reverse order. Also when forming a rq_list with remaining requests (in case two or more devices are used), we effectively reverse the ordering of the plug list for each device we process. Submitting requests in reverse order has negative impact on performance for rotational disks (when BFQ is not in use). We observe 10-25% regression in random 4k write throughput, as well as ~20% regression in MariaDB OLTP benchmark on rotational storage on btrfs filesystem. Fix the problem by preserving ordering of the plug list when inserting requests into the queuelist as well as by appending to requeue_list instead of prepending to it. Fixes: 26fed4ac4eab ("block: flush plug based on hardware and software queue order") Signed-off-by: Jan Kara Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230313093002.11756-1-jack@suse.cz Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- include/linux/blk-mq.h | 6 ++++++ 2 files changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-mq.c b/block/blk-mq.c index d0cb2ef18fe2..cf1a39adf9a5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2725,6 +2725,7 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) struct blk_mq_hw_ctx *this_hctx = NULL; struct blk_mq_ctx *this_ctx = NULL; struct request *requeue_list = NULL; + struct request **requeue_lastp = &requeue_list; unsigned int depth = 0; LIST_HEAD(list); @@ -2735,10 +2736,10 @@ static void blk_mq_dispatch_plug_list(struct blk_plug *plug, bool from_sched) this_hctx = rq->mq_hctx; this_ctx = rq->mq_ctx; } else if (this_hctx != rq->mq_hctx || this_ctx != rq->mq_ctx) { - rq_list_add(&requeue_list, rq); + rq_list_add_tail(&requeue_lastp, rq); continue; } - list_add_tail(&rq->queuelist, &list); + list_add(&rq->queuelist, &list); depth++; } while (!rq_list_empty(plug->mq_list)); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index dd5ce1137f04..de0b0c3e7395 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -228,6 +228,12 @@ static inline unsigned short req_get_ioprio(struct request *req) *(listptr) = rq; \ } while (0) +#define rq_list_add_tail(lastpptr, rq) do { \ + (rq)->rq_next = NULL; \ + **(lastpptr) = rq; \ + *(lastpptr) = &rq->rq_next; \ +} while (0) + #define rq_list_pop(listptr) \ ({ \ struct request *__req = NULL; \ -- cgit v1.2.3 From 7ff84910c66c9144cc0de9d9deed9fb84c03aff0 Mon Sep 17 00:00:00 2001 From: Jeff Layton Date: Tue, 14 Mar 2023 06:20:58 -0400 Subject: lockd: set file_lock start and end when decoding nlm4 testargs Commit 6930bcbfb6ce dropped the setting of the file_lock range when decoding a nlm_lock off the wire. This causes the client side grant callback to miss matching blocks and reject the lock, only to rerequest it 30s later. Add a helper function to set the file_lock range from the start and end values that the protocol uses, and have the nlm_lock decoder call that to set up the file_lock args properly. Fixes: 6930bcbfb6ce ("lockd: detect and reject lock arguments that overflow") Reported-by: Amir Goldstein Signed-off-by: Jeff Layton Tested-by: Amir Goldstein Cc: stable@vger.kernel.org #6.0 Signed-off-by: Anna Schumaker --- fs/lockd/clnt4xdr.c | 9 +-------- fs/lockd/xdr4.c | 13 ++++++++++++- include/linux/lockd/xdr4.h | 1 + 3 files changed, 14 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c index 7df6324ccb8a..8161667c976f 100644 --- a/fs/lockd/clnt4xdr.c +++ b/fs/lockd/clnt4xdr.c @@ -261,7 +261,6 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) u32 exclusive; int error; __be32 *p; - s32 end; memset(lock, 0, sizeof(*lock)); locks_init_lock(fl); @@ -285,13 +284,7 @@ static int decode_nlm4_holder(struct xdr_stream *xdr, struct nlm_res *result) fl->fl_type = exclusive != 0 ? F_WRLCK : F_RDLCK; p = xdr_decode_hyper(p, &l_offset); xdr_decode_hyper(p, &l_len); - end = l_offset + l_len - 1; - - fl->fl_start = (loff_t)l_offset; - if (l_len == 0 || end < 0) - fl->fl_end = OFFSET_MAX; - else - fl->fl_end = (loff_t)end; + nlm4svc_set_file_lock_range(fl, l_offset, l_len); error = 0; out: return error; diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c index 712fdfeb8ef0..5fcbf30cd275 100644 --- a/fs/lockd/xdr4.c +++ b/fs/lockd/xdr4.c @@ -33,6 +33,17 @@ loff_t_to_s64(loff_t offset) return res; } +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len) +{ + s64 end = off + len - 1; + + fl->fl_start = off; + if (len == 0 || end < 0) + fl->fl_end = OFFSET_MAX; + else + fl->fl_end = end; +} + /* * NLM file handles are defined by specification to be a variable-length * XDR opaque no longer than 1024 bytes. However, this implementation @@ -80,7 +91,7 @@ svcxdr_decode_lock(struct xdr_stream *xdr, struct nlm_lock *lock) locks_init_lock(fl); fl->fl_flags = FL_POSIX; fl->fl_type = F_RDLCK; - + nlm4svc_set_file_lock_range(fl, lock->lock_start, lock->lock_len); return true; } diff --git a/include/linux/lockd/xdr4.h b/include/linux/lockd/xdr4.h index 9a6b55da8fd6..72831e35dca3 100644 --- a/include/linux/lockd/xdr4.h +++ b/include/linux/lockd/xdr4.h @@ -22,6 +22,7 @@ #define nlm4_fbig cpu_to_be32(NLM_FBIG) #define nlm4_failed cpu_to_be32(NLM_FAILED) +void nlm4svc_set_file_lock_range(struct file_lock *fl, u64 off, u64 len); bool nlm4svc_decode_void(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_testargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); bool nlm4svc_decode_lockargs(struct svc_rqst *rqstp, struct xdr_stream *xdr); -- cgit v1.2.3 From c2679254b9c9980d9045f0f722cf093a2b1f7590 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" Date: Fri, 10 Mar 2023 17:28:56 -0500 Subject: tracing: Make tracepoint lockdep check actually test something A while ago where the trace events had the following: rcu_read_lock_sched_notrace(); rcu_dereference_sched(...); rcu_read_unlock_sched_notrace(); If the tracepoint is enabled, it could trigger RCU issues if called in the wrong place. And this warning was only triggered if lockdep was enabled. If the tracepoint was never enabled with lockdep, the bug would not be caught. To handle this, the above sequence was done when lockdep was enabled regardless if the tracepoint was enabled or not (although the always enabled code really didn't do anything, it would still trigger a warning). But a lot has changed since that lockdep code was added. One is, that sequence no longer triggers any warning. Another is, the tracepoint when enabled doesn't even do that sequence anymore. The main check we care about today is whether RCU is "watching" or not. So if lockdep is enabled, always check if rcu_is_watching() which will trigger a warning if it is not (tracepoints require RCU to be watching). Note, that old sequence did add a bit of overhead when lockdep was enabled, and with the latest kernel updates, would cause the system to slow down enough to trigger kernel "stalled" warnings. Link: http://lore.kernel.org/lkml/20140806181801.GA4605@redhat.com Link: http://lore.kernel.org/lkml/20140807175204.C257CAC5@viggo.jf.intel.com Link: https://lore.kernel.org/lkml/20230307184645.521db5c9@gandalf.local.home/ Link: https://lore.kernel.org/linux-trace-kernel/20230310172856.77406446@gandalf.local.home Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Dave Hansen Cc: "Paul E. McKenney" Cc: Mathieu Desnoyers Cc: Joel Fernandes Acked-by: Peter Zijlstra (Intel) Acked-by: Paul E. McKenney Fixes: e6753f23d961 ("tracepoint: Make rcuidle tracepoint callers use SRCU") Signed-off-by: Steven Rostedt (Google) --- include/linux/tracepoint.h | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h index fa1004fcf810..2083f2d2f05b 100644 --- a/include/linux/tracepoint.h +++ b/include/linux/tracepoint.h @@ -231,12 +231,11 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) * not add unwanted padding between the beginning of the section and the * structure. Force alignment to the same alignment as the section start. * - * When lockdep is enabled, we make sure to always do the RCU portions of - * the tracepoint code, regardless of whether tracing is on. However, - * don't check if the condition is false, due to interaction with idle - * instrumentation. This lets us find RCU issues triggered with tracepoints - * even when this tracepoint is off. This code has no purpose other than - * poking RCU a bit. + * When lockdep is enabled, we make sure to always test if RCU is + * "watching" regardless if the tracepoint is enabled or not. Tracepoints + * require RCU to be active, and it should always warn at the tracepoint + * site if it is not watching, as it will need to be active when the + * tracepoint is enabled. */ #define __DECLARE_TRACE(name, proto, args, cond, data_proto) \ extern int __traceiter_##name(data_proto); \ @@ -249,9 +248,7 @@ static inline struct tracepoint *tracepoint_ptr_deref(tracepoint_ptr_t *p) TP_ARGS(args), \ TP_CONDITION(cond), 0); \ if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) { \ - rcu_read_lock_sched_notrace(); \ - rcu_dereference_sched(__tracepoint_##name.funcs);\ - rcu_read_unlock_sched_notrace(); \ + WARN_ON_ONCE(!rcu_is_watching()); \ } \ } \ __DECLARE_TRACE_RCU(name, PARAMS(proto), PARAMS(args), \ -- cgit v1.2.3 From 4b397c06cb987935b1b097336532aa6b4210e091 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 10 Mar 2023 19:11:09 +0000 Subject: net: tunnels: annotate lockless accesses to dev->needed_headroom IP tunnels can apparently update dev->needed_headroom in their xmit path. This patch takes care of three tunnels xmit, and also the core LL_RESERVED_SPACE() and LL_RESERVED_SPACE_EXTRA() helpers. More changes might be needed for completeness. BUG: KCSAN: data-race in ip_tunnel_xmit / ip_tunnel_xmit read to 0xffff88815b9da0ec of 2 bytes by task 888 on cpu 1: ip_tunnel_xmit+0x1270/0x1730 net/ipv4/ip_tunnel.c:803 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip_finish_output2+0x740/0x840 net/ipv4/ip_output.c:228 ip_finish_output+0xf4/0x240 net/ipv4/ip_output.c:316 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip_output+0xe5/0x1b0 net/ipv4/ip_output.c:430 dst_output include/net/dst.h:444 [inline] ip_local_out+0x64/0x80 net/ipv4/ip_output.c:126 iptunnel_xmit+0x34a/0x4b0 net/ipv4/ip_tunnel_core.c:82 ip_tunnel_xmit+0x1451/0x1730 net/ipv4/ip_tunnel.c:813 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 write to 0xffff88815b9da0ec of 2 bytes by task 2379 on cpu 0: ip_tunnel_xmit+0x1294/0x1730 net/ipv4/ip_tunnel.c:804 __gre_xmit net/ipv4/ip_gre.c:469 [inline] ipgre_xmit+0x516/0x570 net/ipv4/ip_gre.c:661 __netdev_start_xmit include/linux/netdevice.h:4881 [inline] netdev_start_xmit include/linux/netdevice.h:4895 [inline] xmit_one net/core/dev.c:3580 [inline] dev_hard_start_xmit+0x127/0x400 net/core/dev.c:3596 __dev_queue_xmit+0x1007/0x1eb0 net/core/dev.c:4246 dev_queue_xmit include/linux/netdevice.h:3051 [inline] neigh_direct_output+0x17/0x20 net/core/neighbour.c:1623 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x9bc/0xc50 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x39a/0x4e0 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0xeb/0x220 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:444 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] mld_sendpack+0x438/0x6a0 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x519/0x7b0 net/ipv6/mcast.c:2653 process_one_work+0x3e6/0x750 kernel/workqueue.c:2390 worker_thread+0x5f2/0xa10 kernel/workqueue.c:2537 kthread+0x1ac/0x1e0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:308 value changed: 0x0dd4 -> 0x0e14 Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 2379 Comm: kworker/0:0 Not tainted 6.3.0-rc1-syzkaller-00002-g8ca09d5fa354-dirty #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 03/02/2023 Workqueue: mld mld_ifc_work Fixes: 8eb30be0352d ("ipv6: Create ip6_tnl_xmit") Reported-by: syzbot Signed-off-by: Eric Dumazet Link: https://lore.kernel.org/r/20230310191109.2384387-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 6 ++++-- net/ipv4/ip_tunnel.c | 12 ++++++------ net/ipv6/ip6_tunnel.c | 4 ++-- 3 files changed, 12 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6a14b7b11766..470085b121d3 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -297,9 +297,11 @@ struct hh_cache { * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ - ((((dev)->hard_header_len+(dev)->needed_headroom)&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ - ((((dev)->hard_header_len+(dev)->needed_headroom+(extra))&~(HH_DATA_MOD - 1)) + HH_DATA_MOD) + ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ + & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index de90b09dfe78..2541083d49ad 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -614,10 +614,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > dev->needed_headroom) - dev->needed_headroom = headroom; + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); goto tx_dropped; } @@ -800,10 +800,10 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, dev->needed_headroom)) { + if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { ip_rt_put(rt); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 47b6607a1370..5e80e517f071 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1240,8 +1240,8 @@ route_lookup: */ max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; - if (max_headroom > dev->needed_headroom) - dev->needed_headroom = max_headroom; + if (max_headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) -- cgit v1.2.3 From 8e19b87cfce2de2125f11363d7dea3d08f16ccae Mon Sep 17 00:00:00 2001 From: Minwoo Im Date: Thu, 9 Mar 2023 23:31:18 +0900 Subject: nvme-trace: show more opcode names We have more commands to show in the trace. Sync up. Signed-off-by: Minwoo Im Reviewed-by: Chaitanya Kulkarni Signed-off-by: Christoph Hellwig --- include/linux/nvme.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 4fad4aa245fb..779507ac750b 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -812,6 +812,7 @@ enum nvme_opcode { nvme_opcode_name(nvme_cmd_compare), \ nvme_opcode_name(nvme_cmd_write_zeroes), \ nvme_opcode_name(nvme_cmd_dsm), \ + nvme_opcode_name(nvme_cmd_verify), \ nvme_opcode_name(nvme_cmd_resv_register), \ nvme_opcode_name(nvme_cmd_resv_report), \ nvme_opcode_name(nvme_cmd_resv_acquire), \ @@ -1144,10 +1145,14 @@ enum nvme_admin_opcode { nvme_admin_opcode_name(nvme_admin_ns_mgmt), \ nvme_admin_opcode_name(nvme_admin_activate_fw), \ nvme_admin_opcode_name(nvme_admin_download_fw), \ + nvme_admin_opcode_name(nvme_admin_dev_self_test), \ nvme_admin_opcode_name(nvme_admin_ns_attach), \ nvme_admin_opcode_name(nvme_admin_keep_alive), \ nvme_admin_opcode_name(nvme_admin_directive_send), \ nvme_admin_opcode_name(nvme_admin_directive_recv), \ + nvme_admin_opcode_name(nvme_admin_virtual_mgmt), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_send), \ + nvme_admin_opcode_name(nvme_admin_nvme_mi_recv), \ nvme_admin_opcode_name(nvme_admin_dbbuf), \ nvme_admin_opcode_name(nvme_admin_format_nvm), \ nvme_admin_opcode_name(nvme_admin_security_send), \ -- cgit v1.2.3 From 5f27571382ca42daa3e3d40d1b252bf18c2b61d2 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Thu, 23 Feb 2023 17:12:26 +0800 Subject: block: count 'ios' and 'sectors' when io is done for bio-based device While using iostat for raid, I observed very strange 'await' occasionally, and turns out it's due to that 'ios' and 'sectors' is counted in bdev_start_io_acct(), while 'nsecs' is counted in bdev_end_io_acct(). I'm not sure why they are ccounted like that but I think this behaviour is obviously wrong because user will get wrong disk stats. Fix the problem by counting 'ios' and 'sectors' when io is done, like what rq-based device does. Fixes: 394ffa503bc4 ("blk: introduce generic io stat accounting help function") Signed-off-by: Yu Kuai Reviewed-by: Christoph Hellwig Link: https://lore.kernel.org/r/20230223091226.1135678-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-core.c | 16 ++++++---------- drivers/md/dm.c | 6 +++--- drivers/nvme/host/multipath.c | 8 ++++---- include/linux/blkdev.h | 5 ++--- 4 files changed, 15 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/block/blk-core.c b/block/blk-core.c index 9e5e0277a4d9..42926e6cb83c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -959,16 +959,11 @@ again: } } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { - const int sgrp = op_stat_group(op); - part_stat_lock(); update_io_ticks(bdev, start_time, false); - part_stat_inc(bdev, ios[sgrp]); - part_stat_add(bdev, sectors[sgrp], sectors); part_stat_local_inc(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -984,13 +979,12 @@ EXPORT_SYMBOL(bdev_start_io_acct); */ unsigned long bio_start_io_acct(struct bio *bio) { - return bdev_start_io_acct(bio->bi_bdev, bio_sectors(bio), - bio_op(bio), jiffies); + return bdev_start_io_acct(bio->bi_bdev, bio_op(bio), jiffies); } EXPORT_SYMBOL_GPL(bio_start_io_acct); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time) + unsigned int sectors, unsigned long start_time) { const int sgrp = op_stat_group(op); unsigned long now = READ_ONCE(jiffies); @@ -998,6 +992,8 @@ void bdev_end_io_acct(struct block_device *bdev, enum req_op op, part_stat_lock(); update_io_ticks(bdev, now, true); + part_stat_inc(bdev, ios[sgrp]); + part_stat_add(bdev, sectors[sgrp], sectors); part_stat_add(bdev, nsecs[sgrp], jiffies_to_nsecs(duration)); part_stat_local_dec(bdev, in_flight[op_is_write(op)]); part_stat_unlock(); @@ -1007,7 +1003,7 @@ EXPORT_SYMBOL(bdev_end_io_acct); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, struct block_device *orig_bdev) { - bdev_end_io_acct(orig_bdev, bio_op(bio), start_time); + bdev_end_io_acct(orig_bdev, bio_op(bio), bio_sectors(bio), start_time); } EXPORT_SYMBOL_GPL(bio_end_io_acct_remapped); diff --git a/drivers/md/dm.c b/drivers/md/dm.c index eace45a18d45..f5cc330bb549 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -512,10 +512,10 @@ static void dm_io_acct(struct dm_io *io, bool end) sectors = io->sectors; if (!end) - bdev_start_io_acct(bio->bi_bdev, sectors, bio_op(bio), - start_time); + bdev_start_io_acct(bio->bi_bdev, bio_op(bio), start_time); else - bdev_end_io_acct(bio->bi_bdev, bio_op(bio), start_time); + bdev_end_io_acct(bio->bi_bdev, bio_op(bio), sectors, + start_time); if (static_branch_unlikely(&stats_enabled) && unlikely(dm_stats_used(&md->stats))) { diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index fc39d01e7b63..9171452e2f6d 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -123,9 +123,8 @@ void nvme_mpath_start_request(struct request *rq) return; nvme_req(rq)->flags |= NVME_MPATH_IO_STATS; - nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, - blk_rq_bytes(rq) >> SECTOR_SHIFT, - req_op(rq), jiffies); + nvme_req(rq)->start_time = bdev_start_io_acct(disk->part0, req_op(rq), + jiffies); } EXPORT_SYMBOL_GPL(nvme_mpath_start_request); @@ -136,7 +135,8 @@ void nvme_mpath_end_request(struct request *rq) if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS)) return; bdev_end_io_acct(ns->head->disk->part0, req_op(rq), - nvme_req(rq)->start_time); + blk_rq_bytes(rq) >> SECTOR_SHIFT, + nvme_req(rq)->start_time); } void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d1aee08f8c18..941304f17492 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1446,11 +1446,10 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, enum req_op op, +unsigned long bdev_start_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time); void bdev_end_io_acct(struct block_device *bdev, enum req_op op, - unsigned long start_time); + unsigned int sectors, unsigned long start_time); unsigned long bio_start_io_acct(struct bio *bio); void bio_end_io_acct_remapped(struct bio *bio, unsigned long start_time, -- cgit v1.2.3 From 3615c78673c332b69aaacefbcde5937c5c706686 Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 14 Mar 2023 13:31:02 +0100 Subject: efi: sysfb_efi: Fix DMI quirks not working for simpledrm Commit 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") moved the sysfb_apply_efi_quirks() call in sysfb_init() from before the [sysfb_]parse_mode() call to after it. But sysfb_apply_efi_quirks() modifies the global screen_info struct which [sysfb_]parse_mode() parses, so doing it later is too late. This has broken all DMI based quirks for correcting wrong firmware efifb settings when simpledrm is used. To fix this move the sysfb_apply_efi_quirks() call back to its old place and split the new setup of the efifb_fwnode (which requires the platform_device) into its own function and call that at the place of the moved sysfb_apply_efi_quirks(pd) calls. Fixes: 8633ef82f101 ("drivers/firmware: consolidate EFI framebuffer setup for all arches") Cc: stable@vger.kernel.org Cc: Javier Martinez Canillas Cc: Thomas Zimmermann Signed-off-by: Hans de Goede Reviewed-by: Javier Martinez Canillas Signed-off-by: Ard Biesheuvel --- drivers/firmware/efi/sysfb_efi.c | 5 ++++- drivers/firmware/sysfb.c | 4 +++- drivers/firmware/sysfb_simplefb.c | 2 +- include/linux/sysfb.h | 9 +++++++-- 4 files changed, 15 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/firmware/efi/sysfb_efi.c b/drivers/firmware/efi/sysfb_efi.c index f06fdacc9bc8..e76d6803bdd0 100644 --- a/drivers/firmware/efi/sysfb_efi.c +++ b/drivers/firmware/efi/sysfb_efi.c @@ -341,7 +341,7 @@ static const struct fwnode_operations efifb_fwnode_ops = { #ifdef CONFIG_EFI static struct fwnode_handle efifb_fwnode; -__init void sysfb_apply_efi_quirks(struct platform_device *pd) +__init void sysfb_apply_efi_quirks(void) { if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || !(screen_info.capabilities & VIDEO_CAPABILITY_SKIP_QUIRKS)) @@ -355,7 +355,10 @@ __init void sysfb_apply_efi_quirks(struct platform_device *pd) screen_info.lfb_height = temp; screen_info.lfb_linelength = 4 * screen_info.lfb_width; } +} +__init void sysfb_set_efifb_fwnode(struct platform_device *pd) +{ if (screen_info.orig_video_isVGA == VIDEO_TYPE_EFI && IS_ENABLED(CONFIG_PCI)) { fwnode_init(&efifb_fwnode, &efifb_fwnode_ops); pd->dev.fwnode = &efifb_fwnode; diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c index 3fd3563d962b..3c197db42c9d 100644 --- a/drivers/firmware/sysfb.c +++ b/drivers/firmware/sysfb.c @@ -81,6 +81,8 @@ static __init int sysfb_init(void) if (disabled) goto unlock_mutex; + sysfb_apply_efi_quirks(); + /* try to create a simple-framebuffer device */ compatible = sysfb_parse_mode(si, &mode); if (compatible) { @@ -107,7 +109,7 @@ static __init int sysfb_init(void) goto unlock_mutex; } - sysfb_apply_efi_quirks(pd); + sysfb_set_efifb_fwnode(pd); ret = platform_device_add_data(pd, si, sizeof(*si)); if (ret) diff --git a/drivers/firmware/sysfb_simplefb.c b/drivers/firmware/sysfb_simplefb.c index ce9c007ed66f..82c64cb9f531 100644 --- a/drivers/firmware/sysfb_simplefb.c +++ b/drivers/firmware/sysfb_simplefb.c @@ -141,7 +141,7 @@ __init struct platform_device *sysfb_create_simplefb(const struct screen_info *s if (!pd) return ERR_PTR(-ENOMEM); - sysfb_apply_efi_quirks(pd); + sysfb_set_efifb_fwnode(pd); ret = platform_device_add_resources(pd, &res, 1); if (ret) diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h index 8ba8b5be5567..c1ef5fc60a3c 100644 --- a/include/linux/sysfb.h +++ b/include/linux/sysfb.h @@ -70,11 +70,16 @@ static inline void sysfb_disable(void) #ifdef CONFIG_EFI extern struct efifb_dmi_info efifb_dmi_list[]; -void sysfb_apply_efi_quirks(struct platform_device *pd); +void sysfb_apply_efi_quirks(void); +void sysfb_set_efifb_fwnode(struct platform_device *pd); #else /* CONFIG_EFI */ -static inline void sysfb_apply_efi_quirks(struct platform_device *pd) +static inline void sysfb_apply_efi_quirks(void) +{ +} + +static inline void sysfb_set_efifb_fwnode(struct platform_device *pd) { } -- cgit v1.2.3 From 99669259f3361d759219811e670b7e0742668556 Mon Sep 17 00:00:00 2001 From: Maxime Bizon Date: Thu, 16 Mar 2023 16:33:16 -0700 Subject: net: mdio: fix owner field for mdio buses registered using device-tree Bus ownership is wrong when using of_mdiobus_register() to register an mdio bus. That function is not inline, so when it calls mdiobus_register() the wrong THIS_MODULE value is captured. Signed-off-by: Maxime Bizon Fixes: 90eff9096c01 ("net: phy: Allow splitting MDIO bus/device support from PHYs") [florian: fix kdoc, added Fixes tag] Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/mdio/of_mdio.c | 12 +++++++----- drivers/net/phy/mdio_devres.c | 11 ++++++----- include/linux/of_mdio.h | 22 +++++++++++++++++++--- 3 files changed, 32 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 510822d6d0d9..1e46e39f5f46 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -139,21 +139,23 @@ bool of_mdiobus_child_is_phy(struct device_node *child) EXPORT_SYMBOL(of_mdiobus_child_is_phy); /** - * of_mdiobus_register - Register mii_bus and create PHYs from the device tree + * __of_mdiobus_register - Register mii_bus and create PHYs from the device tree * @mdio: pointer to mii_bus structure * @np: pointer to device_node of MDIO bus. + * @owner: module owning the @mdio object. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @np. */ -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner) { struct device_node *child; bool scanphys = false; int addr, rc; if (!np) - return mdiobus_register(mdio); + return __mdiobus_register(mdio, owner); /* Do not continue if the node is disabled */ if (!of_device_is_available(np)) @@ -172,7 +174,7 @@ int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np) of_property_read_u32(np, "reset-post-delay-us", &mdio->reset_post_delay_us); /* Register the MDIO bus */ - rc = mdiobus_register(mdio); + rc = __mdiobus_register(mdio, owner); if (rc) return rc; @@ -236,7 +238,7 @@ unregister: mdiobus_unregister(mdio); return rc; } -EXPORT_SYMBOL(of_mdiobus_register); +EXPORT_SYMBOL(__of_mdiobus_register); /** * of_mdio_find_device - Given a device tree node, find the mdio_device diff --git a/drivers/net/phy/mdio_devres.c b/drivers/net/phy/mdio_devres.c index b560e99695df..69b829e6ab35 100644 --- a/drivers/net/phy/mdio_devres.c +++ b/drivers/net/phy/mdio_devres.c @@ -98,13 +98,14 @@ EXPORT_SYMBOL(__devm_mdiobus_register); #if IS_ENABLED(CONFIG_OF_MDIO) /** - * devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() + * __devm_of_mdiobus_register - Resource managed variant of of_mdiobus_register() * @dev: Device to register mii_bus for * @mdio: MII bus structure to register * @np: Device node to parse + * @owner: Owning module */ -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np) +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner) { struct mdiobus_devres *dr; int ret; @@ -117,7 +118,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, if (!dr) return -ENOMEM; - ret = of_mdiobus_register(mdio, np); + ret = __of_mdiobus_register(mdio, np, owner); if (ret) { devres_free(dr); return ret; @@ -127,7 +128,7 @@ int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, devres_add(dev, dr); return 0; } -EXPORT_SYMBOL(devm_of_mdiobus_register); +EXPORT_SYMBOL(__devm_of_mdiobus_register); #endif /* CONFIG_OF_MDIO */ MODULE_LICENSE("GPL"); diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h index da633d34ab86..8a52ef2e6fa6 100644 --- a/include/linux/of_mdio.h +++ b/include/linux/of_mdio.h @@ -14,9 +14,25 @@ #if IS_ENABLED(CONFIG_OF_MDIO) bool of_mdiobus_child_is_phy(struct device_node *child); -int of_mdiobus_register(struct mii_bus *mdio, struct device_node *np); -int devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, - struct device_node *np); +int __of_mdiobus_register(struct mii_bus *mdio, struct device_node *np, + struct module *owner); + +static inline int of_mdiobus_register(struct mii_bus *mdio, + struct device_node *np) +{ + return __of_mdiobus_register(mdio, np, THIS_MODULE); +} + +int __devm_of_mdiobus_register(struct device *dev, struct mii_bus *mdio, + struct device_node *np, struct module *owner); + +static inline int devm_of_mdiobus_register(struct device *dev, + struct mii_bus *mdio, + struct device_node *np) +{ + return __devm_of_mdiobus_register(dev, mdio, np, THIS_MODULE); +} + struct mdio_device *of_mdio_find_device(struct device_node *np); struct phy_device *of_phy_find_device(struct device_node *phy_np); struct phy_device * -- cgit v1.2.3 From 30b605b8501e321f79e19c3238aa6ca31da6087c Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Thu, 16 Mar 2023 16:33:17 -0700 Subject: net: mdio: fix owner field for mdio buses registered using ACPI Bus ownership is wrong when using acpi_mdiobus_register() to register an mdio bus. That function is not inline, so when it calls mdiobus_register() the wrong THIS_MODULE value is captured. CC: Maxime Bizon Fixes: 803ca24d2f92 ("net: mdio: Add ACPI support code for mdio") Signed-off-by: Florian Fainelli Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/mdio/acpi_mdio.c | 10 ++++++---- include/linux/acpi_mdio.h | 9 ++++++++- 2 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c index d77c987fda9c..4630dde01974 100644 --- a/drivers/net/mdio/acpi_mdio.c +++ b/drivers/net/mdio/acpi_mdio.c @@ -18,16 +18,18 @@ MODULE_AUTHOR("Calvin Johnson "); MODULE_LICENSE("GPL"); /** - * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. + * __acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. * @mdio: pointer to mii_bus structure * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent + * @owner: module owning this @mdio object. * an ACPI device object corresponding to the MDIO bus and its children are * expected to correspond to the PHY devices on that bus. * * This function registers the mii_bus structure and registers a phy_device * for each child node of @fwnode. */ -int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +int __acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode, + struct module *owner) { struct fwnode_handle *child; u32 addr; @@ -35,7 +37,7 @@ int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) /* Mask out all PHYs from auto probing. */ mdio->phy_mask = GENMASK(31, 0); - ret = mdiobus_register(mdio); + ret = __mdiobus_register(mdio, owner); if (ret) return ret; @@ -55,4 +57,4 @@ int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) } return 0; } -EXPORT_SYMBOL(acpi_mdiobus_register); +EXPORT_SYMBOL(__acpi_mdiobus_register); diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h index 0a24ab7cb66f..8e2eefa9fbc0 100644 --- a/include/linux/acpi_mdio.h +++ b/include/linux/acpi_mdio.h @@ -9,7 +9,14 @@ #include #if IS_ENABLED(CONFIG_ACPI_MDIO) -int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +int __acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode, + struct module *owner); + +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *handle) +{ + return __acpi_mdiobus_register(mdio, handle, THIS_MODULE); +} #else /* CONFIG_ACPI_MDIO */ static inline int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) -- cgit v1.2.3 From 070246e4674b125860d311c18ce2623e73e2bd51 Mon Sep 17 00:00:00 2001 From: Jochen Henneberg Date: Fri, 17 Mar 2023 09:08:17 +0100 Subject: net: stmmac: Fix for mismatched host/device DMA address width Currently DMA address width is either read from a RO device register or force set from the platform data. This breaks DMA when the host DMA address width is <=32it but the device is >32bit. Right now the driver may decide to use a 2nd DMA descriptor for another buffer (happens in case of TSO xmit) assuming that 32bit addressing is used due to platform configuration but the device will still use both descriptor addresses as one address. This can be observed with the Intel EHL platform driver that sets 32bit for addr64 but the MAC reports 40bit. The TX queue gets stuck in case of TCP with iptables NAT configuration on TSO packets. The logic should be like this: Whatever we do on the host side (memory allocation GFP flags) should happen with the host DMA width, whenever we decide how to set addresses on the device registers we must use the device DMA address width. This patch renames the platform address width field from addr64 (term used in device datasheet) to host_addr and uses this value exclusively for host side operations while all chip operations consider the device DMA width as read from the device register. Fixes: 7cfc4486e7ea ("stmmac: intel: Configure EHL PSE0 GbE and PSE1 GbE to 32 bits DMA addressing") Signed-off-by: Jochen Henneberg Signed-off-by: David S. Miller --- drivers/net/ethernet/stmicro/stmmac/common.h | 1 + drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c | 2 +- drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 4 +-- .../net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 2 +- drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 30 ++++++++++++---------- include/linux/stmmac.h | 2 +- 6 files changed, 22 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index 6b5d96bced47..ec9c130276d8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -418,6 +418,7 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int host_dma_width; unsigned int rssen; unsigned int vlhash; unsigned int sphen; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c index ac550d1ac015..2a2be65d65a0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c @@ -288,7 +288,7 @@ static int imx_dwmac_probe(struct platform_device *pdev) goto err_parse_dt; } - plat_dat->addr64 = dwmac->ops->addr_width; + plat_dat->host_dma_width = dwmac->ops->addr_width; plat_dat->init = imx_dwmac_init; plat_dat->exit = imx_dwmac_exit; plat_dat->clks_config = imx_dwmac_clks_config; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c index 7deb1f817dac..13aa919633b4 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c @@ -684,7 +684,7 @@ static int ehl_pse0_common_data(struct pci_dev *pdev, intel_priv->is_pse = true; plat->bus_id = 2; - plat->addr64 = 32; + plat->host_dma_width = 32; plat->clk_ptp_rate = 200000000; @@ -725,7 +725,7 @@ static int ehl_pse1_common_data(struct pci_dev *pdev, intel_priv->is_pse = true; plat->bus_id = 3; - plat->addr64 = 32; + plat->host_dma_width = 32; plat->clk_ptp_rate = 200000000; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c index 2f7d8e4561d9..9ae31e3dc821 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c @@ -591,7 +591,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev, plat->use_phy_wol = priv_plat->mac_wol ? 0 : 1; plat->riwt_off = 1; plat->maxmtu = ETH_DATA_LEN; - plat->addr64 = priv_plat->variant->dma_bit_mask; + plat->host_dma_width = priv_plat->variant->dma_bit_mask; plat->bsp_priv = priv_plat; plat->init = mediatek_dwmac_init; plat->clks_config = mediatek_dwmac_clks_config; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 8f543c3ab5c5..17310ade88dd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -1431,7 +1431,7 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct stmmac_rx_buffer *buf = &rx_q->buf_pool[i]; gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - if (priv->dma_cap.addr64 <= 32) + if (priv->dma_cap.host_dma_width <= 32) gfp |= GFP_DMA32; if (!buf->page) { @@ -4587,7 +4587,7 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) unsigned int entry = rx_q->dirty_rx; gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); - if (priv->dma_cap.addr64 <= 32) + if (priv->dma_cap.host_dma_width <= 32) gfp |= GFP_DMA32; while (dirty-- > 0) { @@ -6205,7 +6205,7 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) seq_printf(seq, "\tFlexible RX Parser: %s\n", priv->dma_cap.frpsel ? "Y" : "N"); seq_printf(seq, "\tEnhanced Addressing: %d\n", - priv->dma_cap.addr64); + priv->dma_cap.host_dma_width); seq_printf(seq, "\tReceive Side Scaling: %s\n", priv->dma_cap.rssen ? "Y" : "N"); seq_printf(seq, "\tVLAN Hash Filtering: %s\n", @@ -7178,20 +7178,22 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "SPH feature enabled\n"); } - /* The current IP register MAC_HW_Feature1[ADDR64] only define - * 32/40/64 bit width, but some SOC support others like i.MX8MP - * support 34 bits but it map to 40 bits width in MAC_HW_Feature1[ADDR64]. - * So overwrite dma_cap.addr64 according to HW real design. + /* Ideally our host DMA address width is the same as for the + * device. However, it may differ and then we have to use our + * host DMA width for allocation and the device DMA width for + * register handling. */ - if (priv->plat->addr64) - priv->dma_cap.addr64 = priv->plat->addr64; + if (priv->plat->host_dma_width) + priv->dma_cap.host_dma_width = priv->plat->host_dma_width; + else + priv->dma_cap.host_dma_width = priv->dma_cap.addr64; - if (priv->dma_cap.addr64) { + if (priv->dma_cap.host_dma_width) { ret = dma_set_mask_and_coherent(device, - DMA_BIT_MASK(priv->dma_cap.addr64)); + DMA_BIT_MASK(priv->dma_cap.host_dma_width)); if (!ret) { - dev_info(priv->device, "Using %d bits DMA width\n", - priv->dma_cap.addr64); + dev_info(priv->device, "Using %d/%d bits DMA host/device width\n", + priv->dma_cap.host_dma_width, priv->dma_cap.addr64); /* * If more than 32 bits can be addressed, make sure to @@ -7206,7 +7208,7 @@ int stmmac_dvr_probe(struct device *device, goto error_hw_init; } - priv->dma_cap.addr64 = 32; + priv->dma_cap.host_dma_width = 32; } } diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a152678b82b7..a2414c187483 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -215,7 +215,7 @@ struct plat_stmmacenet_data { int unicast_filter_entries; int tx_fifo_size; int rx_fifo_size; - u32 addr64; + u32 host_dma_width; u32 rx_queues_to_use; u32 tx_queues_to_use; u8 rx_sched_algorithm; -- cgit v1.2.3 From 1470afefc3c42df5d1662f87d079b46651bdc95b Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 15 Mar 2023 17:31:02 -0700 Subject: cpumask: introduce for_each_cpu_or Equivalent of for_each_cpu_and, except it ORs the two masks together so it iterates all the CPUs present in either mask. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/cpumask.h | 17 +++++++++++++++++ include/linux/find.h | 37 +++++++++++++++++++++++++++++++++++++ lib/find_bit.c | 9 +++++++++ 3 files changed, 63 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 8fbe76607965..220974ef1bf5 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -350,6 +350,23 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta #define for_each_cpu_andnot(cpu, mask1, mask2) \ for_each_andnot_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) +/** + * for_each_cpu_or - iterate over every cpu present in either mask + * @cpu: the (optionally unsigned) integer iterator + * @mask1: the first cpumask pointer + * @mask2: the second cpumask pointer + * + * This saves a temporary CPU mask in many places. It is equivalent to: + * struct cpumask tmp; + * cpumask_or(&tmp, &mask1, &mask2); + * for_each_cpu(cpu, &tmp) + * ... + * + * After the loop, cpu is >= nr_cpu_ids. + */ +#define for_each_cpu_or(cpu, mask1, mask2) \ + for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits) + /** * cpumask_any_but - return a "random" in a cpumask, but not this one. * @mask: the cpumask to search diff --git a/include/linux/find.h b/include/linux/find.h index 4647864a5ffd..5e4f39ef2e72 100644 --- a/include/linux/find.h +++ b/include/linux/find.h @@ -14,6 +14,8 @@ unsigned long _find_next_and_bit(const unsigned long *addr1, const unsigned long unsigned long nbits, unsigned long start); unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned long *addr2, unsigned long nbits, unsigned long start); +unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start); unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start); extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); @@ -127,6 +129,36 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1, } #endif +#ifndef find_next_or_bit +/** + * find_next_or_bit - find the next set bit in either memory regions + * @addr1: The first address to base the search on + * @addr2: The second address to base the search on + * @size: The bitmap size in bits + * @offset: The bitnumber to start searching at + * + * Returns the bit number for the next set bit + * If no bits are set, returns @size. + */ +static inline +unsigned long find_next_or_bit(const unsigned long *addr1, + const unsigned long *addr2, unsigned long size, + unsigned long offset) +{ + if (small_const_nbits(size)) { + unsigned long val; + + if (unlikely(offset >= size)) + return size; + + val = (*addr1 | *addr2) & GENMASK(size - 1, offset); + return val ? __ffs(val) : size; + } + + return _find_next_or_bit(addr1, addr2, size, offset); +} +#endif + #ifndef find_next_zero_bit /** * find_next_zero_bit - find the next cleared bit in a memory region @@ -536,6 +568,11 @@ unsigned long find_next_bit_le(const void *addr, unsigned (bit) = find_next_andnot_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ (bit)++) +#define for_each_or_bit(bit, addr1, addr2, size) \ + for ((bit) = 0; \ + (bit) = find_next_or_bit((addr1), (addr2), (size), (bit)), (bit) < (size);\ + (bit)++) + /* same as for_each_set_bit() but use bit as value to start with */ #define for_each_set_bit_from(bit, addr, size) \ for (; (bit) = find_next_bit((addr), (size), (bit)), (bit) < (size); (bit)++) diff --git a/lib/find_bit.c b/lib/find_bit.c index c10920e66788..32f99e9a670e 100644 --- a/lib/find_bit.c +++ b/lib/find_bit.c @@ -182,6 +182,15 @@ unsigned long _find_next_andnot_bit(const unsigned long *addr1, const unsigned l EXPORT_SYMBOL(_find_next_andnot_bit); #endif +#ifndef find_next_or_bit +unsigned long _find_next_or_bit(const unsigned long *addr1, const unsigned long *addr2, + unsigned long nbits, unsigned long start) +{ + return FIND_NEXT_BIT(addr1[idx] | addr2[idx], /* nop */, nbits, start); +} +EXPORT_SYMBOL(_find_next_or_bit); +#endif + #ifndef find_next_zero_bit unsigned long _find_next_zero_bit(const unsigned long *addr, unsigned long nbits, unsigned long start) -- cgit v1.2.3 From e9b60c7f97130795c7aa81a649ae4b93a172a277 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 15 Mar 2023 17:31:03 -0700 Subject: pcpcntr: remove percpu_counter_sum_all() percpu_counter_sum_all() is now redundant as the race condition it was invented to handle is now dealt with by percpu_counter_sum() directly and all users of percpu_counter_sum_all() have been removed. Remove it. This effectively reverts the changes made in f689054aace2 ("percpu_counter: add percpu_counter_sum_all interface") except for the cpumask iteration that fixes percpu_counter_sum() made earlier in this series. Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- include/linux/percpu_counter.h | 6 ------ lib/percpu_counter.c | 40 +++++++++++----------------------------- 2 files changed, 11 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h index 521a733e21a9..75b73c83bc9d 100644 --- a/include/linux/percpu_counter.h +++ b/include/linux/percpu_counter.h @@ -45,7 +45,6 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount); void percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch); s64 __percpu_counter_sum(struct percpu_counter *fbc); -s64 percpu_counter_sum_all(struct percpu_counter *fbc); int __percpu_counter_compare(struct percpu_counter *fbc, s64 rhs, s32 batch); void percpu_counter_sync(struct percpu_counter *fbc); @@ -196,11 +195,6 @@ static inline s64 percpu_counter_sum(struct percpu_counter *fbc) return percpu_counter_read(fbc); } -static inline s64 percpu_counter_sum_all(struct percpu_counter *fbc) -{ - return percpu_counter_read(fbc); -} - static inline bool percpu_counter_initialized(struct percpu_counter *fbc) { return true; diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c index 0e096311e0c0..5004463c4f9f 100644 --- a/lib/percpu_counter.c +++ b/lib/percpu_counter.c @@ -122,23 +122,6 @@ void percpu_counter_sync(struct percpu_counter *fbc) } EXPORT_SYMBOL(percpu_counter_sync); -static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc, - const struct cpumask *cpu_mask) -{ - s64 ret; - int cpu; - unsigned long flags; - - raw_spin_lock_irqsave(&fbc->lock, flags); - ret = fbc->count; - for_each_cpu_or(cpu, cpu_online_mask, cpu_mask) { - s32 *pcount = per_cpu_ptr(fbc->counters, cpu); - ret += *pcount; - } - raw_spin_unlock_irqrestore(&fbc->lock, flags); - return ret; -} - /* * Add up all the per-cpu counts, return the result. This is a more accurate * but much slower version of percpu_counter_read_positive(). @@ -153,22 +136,21 @@ static s64 __percpu_counter_sum_mask(struct percpu_counter *fbc, */ s64 __percpu_counter_sum(struct percpu_counter *fbc) { + s64 ret; + int cpu; + unsigned long flags; - return __percpu_counter_sum_mask(fbc, cpu_dying_mask); + raw_spin_lock_irqsave(&fbc->lock, flags); + ret = fbc->count; + for_each_cpu_or(cpu, cpu_online_mask, cpu_dying_mask) { + s32 *pcount = per_cpu_ptr(fbc->counters, cpu); + ret += *pcount; + } + raw_spin_unlock_irqrestore(&fbc->lock, flags); + return ret; } EXPORT_SYMBOL(__percpu_counter_sum); -/* - * This is slower version of percpu_counter_sum as it traverses all possible - * cpus. Use this only in the cases where accurate data is needed in the - * presense of CPUs getting offlined. - */ -s64 percpu_counter_sum_all(struct percpu_counter *fbc) -{ - return __percpu_counter_sum_mask(fbc, cpu_possible_mask); -} -EXPORT_SYMBOL(percpu_counter_sum_all); - int __percpu_counter_init(struct percpu_counter *fbc, s64 amount, gfp_t gfp, struct lock_class_key *key) { -- cgit v1.2.3 From 9d2789ac9d60c049d26ef6d3005d9c94c5a559e9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 20 Mar 2023 20:01:25 -0600 Subject: block/io_uring: pass in issue_flags for uring_cmd task_work handling io_uring_cmd_done() currently assumes that the uring_lock is held when invoked, and while it generally is, this is not guaranteed. Pass in the issue_flags associated with it, so that we have IO_URING_F_UNLOCKED available to be able to lock the CQ ring appropriately when completing events. Cc: stable@vger.kernel.org Fixes: ee692a21e9bf ("fs,io_uring: add infrastructure for uring-cmd") Signed-off-by: Jens Axboe --- drivers/block/ublk_drv.c | 31 ++++++++++++++++++------------- drivers/nvme/host/ioctl.c | 14 ++++++++------ include/linux/io_uring.h | 11 ++++++----- io_uring/uring_cmd.c | 10 ++++++---- 4 files changed, 38 insertions(+), 28 deletions(-) (limited to 'include/linux') diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c index fb5a557afde8..c73cc57ec547 100644 --- a/drivers/block/ublk_drv.c +++ b/drivers/block/ublk_drv.c @@ -715,7 +715,8 @@ static void __ublk_fail_req(struct ublk_queue *ubq, struct ublk_io *io, } } -static void ubq_complete_io_cmd(struct ublk_io *io, int res) +static void ubq_complete_io_cmd(struct ublk_io *io, int res, + unsigned issue_flags) { /* mark this cmd owned by ublksrv */ io->flags |= UBLK_IO_FLAG_OWNED_BY_SRV; @@ -727,7 +728,7 @@ static void ubq_complete_io_cmd(struct ublk_io *io, int res) io->flags &= ~UBLK_IO_FLAG_ACTIVE; /* tell ublksrv one io request is coming */ - io_uring_cmd_done(io->cmd, res, 0); + io_uring_cmd_done(io->cmd, res, 0, issue_flags); } #define UBLK_REQUEUE_DELAY_MS 3 @@ -744,7 +745,8 @@ static inline void __ublk_abort_rq(struct ublk_queue *ubq, mod_delayed_work(system_wq, &ubq->dev->monitor_work, 0); } -static inline void __ublk_rq_task_work(struct request *req) +static inline void __ublk_rq_task_work(struct request *req, + unsigned issue_flags) { struct ublk_queue *ubq = req->mq_hctx->driver_data; int tag = req->tag; @@ -782,7 +784,7 @@ static inline void __ublk_rq_task_work(struct request *req) pr_devel("%s: need get data. op %d, qid %d tag %d io_flags %x\n", __func__, io->cmd->cmd_op, ubq->q_id, req->tag, io->flags); - ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA); + ubq_complete_io_cmd(io, UBLK_IO_RES_NEED_GET_DATA, issue_flags); return; } /* @@ -820,17 +822,18 @@ static inline void __ublk_rq_task_work(struct request *req) mapped_bytes >> 9; } - ubq_complete_io_cmd(io, UBLK_IO_RES_OK); + ubq_complete_io_cmd(io, UBLK_IO_RES_OK, issue_flags); } -static inline void ublk_forward_io_cmds(struct ublk_queue *ubq) +static inline void ublk_forward_io_cmds(struct ublk_queue *ubq, + unsigned issue_flags) { struct llist_node *io_cmds = llist_del_all(&ubq->io_cmds); struct ublk_rq_data *data, *tmp; io_cmds = llist_reverse_order(io_cmds); llist_for_each_entry_safe(data, tmp, io_cmds, node) - __ublk_rq_task_work(blk_mq_rq_from_pdu(data)); + __ublk_rq_task_work(blk_mq_rq_from_pdu(data), issue_flags); } static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) @@ -842,12 +845,12 @@ static inline void ublk_abort_io_cmds(struct ublk_queue *ubq) __ublk_abort_rq(ubq, blk_mq_rq_from_pdu(data)); } -static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd) +static void ublk_rq_task_work_cb(struct io_uring_cmd *cmd, unsigned issue_flags) { struct ublk_uring_cmd_pdu *pdu = ublk_get_uring_cmd_pdu(cmd); struct ublk_queue *ubq = pdu->ubq; - ublk_forward_io_cmds(ubq); + ublk_forward_io_cmds(ubq, issue_flags); } static void ublk_rq_task_work_fn(struct callback_head *work) @@ -856,8 +859,9 @@ static void ublk_rq_task_work_fn(struct callback_head *work) struct ublk_rq_data, work); struct request *req = blk_mq_rq_from_pdu(data); struct ublk_queue *ubq = req->mq_hctx->driver_data; + unsigned issue_flags = IO_URING_F_UNLOCKED; - ublk_forward_io_cmds(ubq); + ublk_forward_io_cmds(ubq, issue_flags); } static void ublk_queue_cmd(struct ublk_queue *ubq, struct request *rq) @@ -1111,7 +1115,8 @@ static void ublk_cancel_queue(struct ublk_queue *ubq) struct ublk_io *io = &ubq->ios[i]; if (io->flags & UBLK_IO_FLAG_ACTIVE) - io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0); + io_uring_cmd_done(io->cmd, UBLK_IO_RES_ABORT, 0, + IO_URING_F_UNLOCKED); } /* all io commands are canceled */ @@ -1351,7 +1356,7 @@ static int ublk_ch_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags) return -EIOCBQUEUED; out: - io_uring_cmd_done(cmd, ret, 0); + io_uring_cmd_done(cmd, ret, 0, issue_flags); pr_devel("%s: complete: cmd op %d, tag %d ret %x io_flags %x\n", __func__, cmd_op, tag, ret, io->flags); return -EIOCBQUEUED; @@ -2234,7 +2239,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd, if (ub) ublk_put_device(ub); out: - io_uring_cmd_done(cmd, ret, 0); + io_uring_cmd_done(cmd, ret, 0, issue_flags); pr_devel("%s: cmd done ret %d cmd_op %x, dev id %d qid %d\n", __func__, ret, cmd->cmd_op, header->dev_id, header->queue_id); return -EIOCBQUEUED; diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c index 723e7d5b778f..d24ea2e05156 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -464,7 +464,8 @@ static inline struct nvme_uring_cmd_pdu *nvme_uring_cmd_pdu( return (struct nvme_uring_cmd_pdu *)&ioucmd->pdu; } -static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd, + unsigned issue_flags) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); struct request *req = pdu->req; @@ -485,17 +486,18 @@ static void nvme_uring_task_meta_cb(struct io_uring_cmd *ioucmd) blk_rq_unmap_user(req->bio); blk_mq_free_request(req); - io_uring_cmd_done(ioucmd, status, result); + io_uring_cmd_done(ioucmd, status, result, issue_flags); } -static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd) +static void nvme_uring_task_cb(struct io_uring_cmd *ioucmd, + unsigned issue_flags) { struct nvme_uring_cmd_pdu *pdu = nvme_uring_cmd_pdu(ioucmd); if (pdu->bio) blk_rq_unmap_user(pdu->bio); - io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result); + io_uring_cmd_done(ioucmd, pdu->nvme_status, pdu->u.result, issue_flags); } static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, @@ -517,7 +519,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io(struct request *req, * Otherwise, move the completion to task work. */ if (cookie != NULL && blk_rq_is_poll(req)) - nvme_uring_task_cb(ioucmd); + nvme_uring_task_cb(ioucmd, IO_URING_F_UNLOCKED); else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_cb); @@ -539,7 +541,7 @@ static enum rq_end_io_ret nvme_uring_cmd_end_io_meta(struct request *req, * Otherwise, move the completion to task work. */ if (cookie != NULL && blk_rq_is_poll(req)) - nvme_uring_task_meta_cb(ioucmd); + nvme_uring_task_meta_cb(ioucmd, IO_URING_F_UNLOCKED); else io_uring_cmd_complete_in_task(ioucmd, nvme_uring_task_meta_cb); diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h index 934e5dd4ccc0..35b9328ca335 100644 --- a/include/linux/io_uring.h +++ b/include/linux/io_uring.h @@ -27,7 +27,7 @@ struct io_uring_cmd { const void *cmd; union { /* callback to defer completions to task context */ - void (*task_work_cb)(struct io_uring_cmd *cmd); + void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned); /* used for polled completion */ void *cookie; }; @@ -39,9 +39,10 @@ struct io_uring_cmd { #if defined(CONFIG_IO_URING) int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, struct iov_iter *iter, void *ioucmd); -void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2); +void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2, + unsigned issue_flags); void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)); + void (*task_work_cb)(struct io_uring_cmd *, unsigned)); struct sock *io_uring_get_socket(struct file *file); void __io_uring_cancel(bool cancel_all); void __io_uring_free(struct task_struct *tsk); @@ -72,11 +73,11 @@ static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw, return -EOPNOTSUPP; } static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, - ssize_t ret2) + ssize_t ret2, unsigned issue_flags) { } static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { } static inline struct sock *io_uring_get_socket(struct file *file) diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c index 446a189b78b0..e535e8db01e3 100644 --- a/io_uring/uring_cmd.c +++ b/io_uring/uring_cmd.c @@ -15,12 +15,13 @@ static void io_uring_cmd_work(struct io_kiocb *req, bool *locked) { struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd); + unsigned issue_flags = *locked ? 0 : IO_URING_F_UNLOCKED; - ioucmd->task_work_cb(ioucmd); + ioucmd->task_work_cb(ioucmd, issue_flags); } void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd, - void (*task_work_cb)(struct io_uring_cmd *)) + void (*task_work_cb)(struct io_uring_cmd *, unsigned)) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); @@ -42,7 +43,8 @@ static inline void io_req_set_cqe32_extra(struct io_kiocb *req, * Called by consumers of io_uring_cmd, if they originally returned * -EIOCBQUEUED upon receiving the command. */ -void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) +void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2, + unsigned issue_flags) { struct io_kiocb *req = cmd_to_io_kiocb(ioucmd); @@ -56,7 +58,7 @@ void io_uring_cmd_done(struct io_uring_cmd *ioucmd, ssize_t ret, ssize_t res2) /* order with io_iopoll_req_issued() checking ->iopoll_complete */ smp_store_release(&req->iopoll_completed, 1); else - io_req_complete_post(req, 0); + io_req_complete_post(req, issue_flags); } EXPORT_SYMBOL_GPL(io_uring_cmd_done); -- cgit v1.2.3 From f87d28673b71b35b248231a2086f9404afbb7f28 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Sat, 25 Feb 2023 16:01:36 -0800 Subject: entry: Fix noinstr warning in __enter_from_user_mode() __enter_from_user_mode() is triggering noinstr warnings with CONFIG_DEBUG_PREEMPT due to its call of preempt_count_add() via ct_state(). The preemption disable isn't needed as interrupts are already disabled. And the context_tracking_enabled() check in ct_state() also isn't needed as that's already being done by the CT_WARN_ON(). Just use __ct_state() instead. Fixes the following warnings: vmlinux.o: warning: objtool: enter_from_user_mode+0xba: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode+0xf9: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: syscall_enter_from_user_mode_prepare+0xc7: call to preempt_count_add() leaves .noinstr.text section vmlinux.o: warning: objtool: irqentry_enter_from_user_mode+0xba: call to preempt_count_add() leaves .noinstr.text section Fixes: 171476775d32 ("context_tracking: Convert state to atomic_t") Signed-off-by: Josh Poimboeuf Signed-off-by: Thomas Gleixner Link: https://lore.kernel.org/r/d8955fa6d68dc955dda19baf13ae014ae27926f5.1677369694.git.jpoimboe@kernel.org --- include/linux/context_tracking.h | 1 + include/linux/context_tracking_state.h | 2 ++ kernel/entry/common.c | 2 +- 3 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h index d4afa8508a80..3a7909ed5498 100644 --- a/include/linux/context_tracking.h +++ b/include/linux/context_tracking.h @@ -96,6 +96,7 @@ static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } +static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static inline void context_tracking_guest_exit(void) { } #define CT_WARN_ON(cond) do { } while (0) diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h index 4a4d56f77180..fdd537ea513f 100644 --- a/include/linux/context_tracking_state.h +++ b/include/linux/context_tracking_state.h @@ -46,7 +46,9 @@ struct context_tracking { #ifdef CONFIG_CONTEXT_TRACKING DECLARE_PER_CPU(struct context_tracking, context_tracking); +#endif +#ifdef CONFIG_CONTEXT_TRACKING_USER static __always_inline int __ct_state(void) { return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK; diff --git a/kernel/entry/common.c b/kernel/entry/common.c index 846add8394c4..1314894d2efa 100644 --- a/kernel/entry/common.c +++ b/kernel/entry/common.c @@ -21,7 +21,7 @@ static __always_inline void __enter_from_user_mode(struct pt_regs *regs) arch_enter_from_user_mode(regs); lockdep_hardirqs_off(CALLER_ADDR0); - CT_WARN_ON(ct_state() != CONTEXT_USER); + CT_WARN_ON(__ct_state() != CONTEXT_USER); user_exit_irqoff(); instrumentation_begin(); -- cgit v1.2.3 From aa01c67de5926fdb276793180564f172c55fb0d7 Mon Sep 17 00:00:00 2001 From: Caleb Sander Date: Mon, 20 Mar 2023 09:57:36 -0600 Subject: nvme-tcp: fix nvme_tcp_term_pdu to match spec The FEI field of C2HTermReq/H2CTermReq is 4 bytes but not 4-byte-aligned in the NVMe/TCP specification (it is located at offset 10 in the PDU). Split it into two 16-bit integers in struct nvme_tcp_term_pdu so no padding is inserted. There should also be 10 reserved bytes after. There are currently no users of this type. Fixes: fc221d05447aa6db ("nvme-tcp: Add protocol header") Reported-by: Geert Uytterhoeven Signed-off-by: Caleb Sander Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig --- include/linux/nvme-tcp.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h index 75470159a194..57ebe1267f7f 100644 --- a/include/linux/nvme-tcp.h +++ b/include/linux/nvme-tcp.h @@ -115,8 +115,9 @@ struct nvme_tcp_icresp_pdu { struct nvme_tcp_term_pdu { struct nvme_tcp_hdr hdr; __le16 fes; - __le32 fei; - __u8 rsvd[8]; + __le16 feil; + __le16 feiu; + __u8 rsvd[10]; }; /** -- cgit v1.2.3 From 790930f44289c8209c57461b2db499fcc702e0b3 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Fri, 17 Mar 2023 18:01:26 +0100 Subject: thermal: core: Introduce thermal_cooling_device_update() Introduce a core thermal API function, thermal_cooling_device_update(), for updating the max_state value for a cooling device and rearranging its statistics in sysfs after a possible change of its ->get_max_state() callback return value. That callback is now invoked only once, during cooling device registration, to populate the max_state field in the cooling device object, so if its return value changes, it needs to be invoked again and the new return value needs to be stored as max_state. Moreover, the statistics presented in sysfs need to be rearranged in general, because there may not be enough room in them to store data for all of the possible states (in the case when max_state grows). The new function takes care of that (and some other minor things related to it), but some extra locking and lockdep annotations are added in several places too to protect against crashes in the cases when the statistics are not present or when a stale max_state value might be used by sysfs attributes. Note that the actual user of the new function will be added separately. Link: https://lore.kernel.org/linux-pm/53ec1f06f61c984100868926f282647e57ecfb2d.camel@intel.com/ Signed-off-by: Rafael J. Wysocki Tested-by: Zhang Rui Reviewed-by: Zhang Rui --- drivers/thermal/thermal_core.c | 83 ++++++++++++++++++++++++++++++++++++++++- drivers/thermal/thermal_core.h | 2 + drivers/thermal/thermal_sysfs.c | 74 +++++++++++++++++++++++++++++++----- include/linux/thermal.h | 1 + 4 files changed, 150 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c index 8894342540f1..cfd4c1afeae7 100644 --- a/drivers/thermal/thermal_core.c +++ b/drivers/thermal/thermal_core.c @@ -613,6 +613,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, struct thermal_instance *pos; struct thermal_zone_device *pos1; struct thermal_cooling_device *pos2; + bool upper_no_limit; int result; if (trip >= tz->num_trips || trip < 0) @@ -632,7 +633,13 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, /* lower default 0, upper default max_state */ lower = lower == THERMAL_NO_LIMIT ? 0 : lower; - upper = upper == THERMAL_NO_LIMIT ? cdev->max_state : upper; + + if (upper == THERMAL_NO_LIMIT) { + upper = cdev->max_state; + upper_no_limit = true; + } else { + upper_no_limit = false; + } if (lower > upper || upper > cdev->max_state) return -EINVAL; @@ -644,6 +651,7 @@ int thermal_zone_bind_cooling_device(struct thermal_zone_device *tz, dev->cdev = cdev; dev->trip = trip; dev->upper = upper; + dev->upper_no_limit = upper_no_limit; dev->lower = lower; dev->target = THERMAL_NO_TARGET; dev->weight = weight; @@ -1057,6 +1065,79 @@ static bool thermal_cooling_device_present(struct thermal_cooling_device *cdev) return false; } +/** + * thermal_cooling_device_update - Update a cooling device object + * @cdev: Target cooling device. + * + * Update @cdev to reflect a change of the underlying hardware or platform. + * + * Must be called when the maximum cooling state of @cdev becomes invalid and so + * its .get_max_state() callback needs to be run to produce the new maximum + * cooling state value. + */ +void thermal_cooling_device_update(struct thermal_cooling_device *cdev) +{ + struct thermal_instance *ti; + unsigned long state; + + if (IS_ERR_OR_NULL(cdev)) + return; + + /* + * Hold thermal_list_lock throughout the update to prevent the device + * from going away while being updated. + */ + mutex_lock(&thermal_list_lock); + + if (!thermal_cooling_device_present(cdev)) + goto unlock_list; + + /* + * Update under the cdev lock to prevent the state from being set beyond + * the new limit concurrently. + */ + mutex_lock(&cdev->lock); + + if (cdev->ops->get_max_state(cdev, &cdev->max_state)) + goto unlock; + + thermal_cooling_device_stats_reinit(cdev); + + list_for_each_entry(ti, &cdev->thermal_instances, cdev_node) { + if (ti->upper == cdev->max_state) + continue; + + if (ti->upper < cdev->max_state) { + if (ti->upper_no_limit) + ti->upper = cdev->max_state; + + continue; + } + + ti->upper = cdev->max_state; + if (ti->lower > ti->upper) + ti->lower = ti->upper; + + if (ti->target == THERMAL_NO_TARGET) + continue; + + if (ti->target > ti->upper) + ti->target = ti->upper; + } + + if (cdev->ops->get_cur_state(cdev, &state) || state > cdev->max_state) + goto unlock; + + thermal_cooling_device_stats_update(cdev, state); + +unlock: + mutex_unlock(&cdev->lock); + +unlock_list: + mutex_unlock(&thermal_list_lock); +} +EXPORT_SYMBOL_GPL(thermal_cooling_device_update); + static void __unbind(struct thermal_zone_device *tz, int mask, struct thermal_cooling_device *cdev) { diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h index 7af54382e915..3d4a787c6b28 100644 --- a/drivers/thermal/thermal_core.h +++ b/drivers/thermal/thermal_core.h @@ -101,6 +101,7 @@ struct thermal_instance { struct list_head tz_node; /* node in tz->thermal_instances */ struct list_head cdev_node; /* node in cdev->thermal_instances */ unsigned int weight; /* The weight of the cooling device */ + bool upper_no_limit; }; #define to_thermal_zone(_dev) \ @@ -127,6 +128,7 @@ int thermal_zone_create_device_groups(struct thermal_zone_device *, int); void thermal_zone_destroy_device_groups(struct thermal_zone_device *); void thermal_cooling_device_setup_sysfs(struct thermal_cooling_device *); void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev); +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev); /* used only at binding time */ ssize_t trip_point_show(struct device *, struct device_attribute *, char *); ssize_t weight_show(struct device *, struct device_attribute *, char *); diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c index cef860deaf91..a4aba7b8bb8b 100644 --- a/drivers/thermal/thermal_sysfs.c +++ b/drivers/thermal/thermal_sysfs.c @@ -685,6 +685,8 @@ void thermal_cooling_device_stats_update(struct thermal_cooling_device *cdev, { struct cooling_dev_stats *stats = cdev->stats; + lockdep_assert_held(&cdev->lock); + if (!stats) return; @@ -706,13 +708,22 @@ static ssize_t total_trans_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int ret; + struct cooling_dev_stats *stats; + int ret = 0; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; spin_lock(&stats->lock); ret = sprintf(buf, "%u\n", stats->total_trans); spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return ret; } @@ -721,11 +732,18 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + spin_lock(&stats->lock); + update_time_in_state(stats); for (i = 0; i <= cdev->max_state; i++) { @@ -734,6 +752,9 @@ time_in_state_ms_show(struct device *dev, struct device_attribute *attr, } spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -742,8 +763,16 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; - int i, states = cdev->max_state + 1; + struct cooling_dev_stats *stats; + int i, states; + + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) + goto unlock; + + states = cdev->max_state + 1; spin_lock(&stats->lock); @@ -757,6 +786,9 @@ reset_store(struct device *dev, struct device_attribute *attr, const char *buf, spin_unlock(&stats->lock); +unlock: + mutex_unlock(&cdev->lock); + return count; } @@ -764,10 +796,18 @@ static ssize_t trans_table_show(struct device *dev, struct device_attribute *attr, char *buf) { struct thermal_cooling_device *cdev = to_cooling_device(dev); - struct cooling_dev_stats *stats = cdev->stats; + struct cooling_dev_stats *stats; ssize_t len = 0; int i, j; + mutex_lock(&cdev->lock); + + stats = cdev->stats; + if (!stats) { + len = -ENODATA; + goto unlock; + } + len += snprintf(buf + len, PAGE_SIZE - len, " From : To\n"); len += snprintf(buf + len, PAGE_SIZE - len, " : "); for (i = 0; i <= cdev->max_state; i++) { @@ -775,8 +815,10 @@ static ssize_t trans_table_show(struct device *dev, break; len += snprintf(buf + len, PAGE_SIZE - len, "state%2u ", i); } - if (len >= PAGE_SIZE) - return PAGE_SIZE; + if (len >= PAGE_SIZE) { + len = PAGE_SIZE; + goto unlock; + } len += snprintf(buf + len, PAGE_SIZE - len, "\n"); @@ -799,8 +841,12 @@ static ssize_t trans_table_show(struct device *dev, if (len >= PAGE_SIZE) { pr_warn_once("Thermal transition table exceeds PAGE_SIZE. Disabling\n"); - return -EFBIG; + len = -EFBIG; } + +unlock: + mutex_unlock(&cdev->lock); + return len; } @@ -830,6 +876,8 @@ static void cooling_device_stats_setup(struct thermal_cooling_device *cdev) unsigned long states = cdev->max_state + 1; int var; + lockdep_assert_held(&cdev->lock); + var = sizeof(*stats); var += sizeof(*stats->time_in_state) * states; var += sizeof(*stats->trans_table) * states * states; @@ -855,6 +903,8 @@ out: static void cooling_device_stats_destroy(struct thermal_cooling_device *cdev) { + lockdep_assert_held(&cdev->lock); + kfree(cdev->stats); cdev->stats = NULL; } @@ -879,6 +929,12 @@ void thermal_cooling_device_destroy_sysfs(struct thermal_cooling_device *cdev) cooling_device_stats_destroy(cdev); } +void thermal_cooling_device_stats_reinit(struct thermal_cooling_device *cdev) +{ + cooling_device_stats_destroy(cdev); + cooling_device_stats_setup(cdev); +} + /* these helper will be used only at the time of bindig */ ssize_t trip_point_show(struct device *dev, struct device_attribute *attr, char *buf) diff --git a/include/linux/thermal.h b/include/linux/thermal.h index 2bb4bf33f4f3..13c6aaed18df 100644 --- a/include/linux/thermal.h +++ b/include/linux/thermal.h @@ -384,6 +384,7 @@ devm_thermal_of_cooling_device_register(struct device *dev, struct device_node *np, char *type, void *devdata, const struct thermal_cooling_device_ops *ops); +void thermal_cooling_device_update(struct thermal_cooling_device *); void thermal_cooling_device_unregister(struct thermal_cooling_device *); struct thermal_zone_device *thermal_zone_get_zone_by_name(const char *name); int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp); -- cgit v1.2.3 From a90ac762d345890b40d88a1385a34a2449c2d75e Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 24 Mar 2023 09:23:42 +0000 Subject: net: sfp: make sfp_bus_find_fwnode() take a const fwnode sfp_bus_find_fwnode() does not write to the fwnode, so let's make it const. Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/sfp-bus.c | 2 +- include/linux/sfp.h | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index daac293e8ede..8284f29b3644 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -593,7 +593,7 @@ static void sfp_upstream_clear(struct sfp_bus *bus) * - %-ENOMEM if we failed to allocate the bus. * - an error from the upstream's connect_phy() method. */ -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { struct fwnode_reference_args ref; struct sfp_bus *bus; diff --git a/include/linux/sfp.h b/include/linux/sfp.h index 52b98f9666a2..ef06a195b3c2 100644 --- a/include/linux/sfp.h +++ b/include/linux/sfp.h @@ -557,7 +557,7 @@ int sfp_get_module_eeprom_by_page(struct sfp_bus *bus, void sfp_upstream_start(struct sfp_bus *bus); void sfp_upstream_stop(struct sfp_bus *bus); void sfp_bus_put(struct sfp_bus *bus); -struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode); +struct sfp_bus *sfp_bus_find_fwnode(const struct fwnode_handle *fwnode); int sfp_bus_add_upstream(struct sfp_bus *bus, void *upstream, const struct sfp_upstream_ops *ops); void sfp_bus_del_upstream(struct sfp_bus *bus); @@ -619,7 +619,8 @@ static inline void sfp_bus_put(struct sfp_bus *bus) { } -static inline struct sfp_bus *sfp_bus_find_fwnode(struct fwnode_handle *fwnode) +static inline struct sfp_bus * +sfp_bus_find_fwnode(const struct fwnode_handle *fwnode) { return NULL; } -- cgit v1.2.3 From 4a0faa02d419a6728abef0f1d8a32d8c35ef95e6 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Fri, 24 Mar 2023 09:23:53 +0000 Subject: net: phy: constify fwnode_get_phy_node() fwnode argument fwnode_get_phy_node() does not motify the fwnode structure, so make the argument const, Signed-off-by: Russell King (Oracle) Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- drivers/net/phy/phy_device.c | 2 +- include/linux/phy.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 1785f1cead97..1de3e339b31a 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3057,7 +3057,7 @@ EXPORT_SYMBOL_GPL(device_phy_find_device); * and "phy-device" are not supported in ACPI. DT supports all the three * named references to the phy node. */ -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode) { struct fwnode_handle *phy_node; diff --git a/include/linux/phy.h b/include/linux/phy.h index 36bf0bbc8efa..db7c0bd67559 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1547,7 +1547,7 @@ int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); struct phy_device *device_phy_find_device(struct device *dev); -struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); +struct fwnode_handle *fwnode_get_phy_node(const struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); -- cgit v1.2.3 From 16812c96550c30a8d5743167ef4e462d6fbe7472 Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Wed, 29 Mar 2023 21:47:21 +0800 Subject: iommu/vt-d: Fix an IOMMU perfmon warning when CPU hotplug A warning can be triggered when hotplug CPU 0. $ echo 0 > /sys/devices/system/cpu/cpu0/online ------------[ cut here ]------------ Voluntary context switch within RCU read-side critical section! WARNING: CPU: 0 PID: 19 at kernel/rcu/tree_plugin.h:318 rcu_note_context_switch+0x4f4/0x580 RIP: 0010:rcu_note_context_switch+0x4f4/0x580 Call Trace: ? perf_event_update_userpage+0x104/0x150 __schedule+0x8d/0x960 ? perf_event_set_state.part.82+0x11/0x50 schedule+0x44/0xb0 schedule_timeout+0x226/0x310 ? __perf_event_disable+0x64/0x1a0 ? _raw_spin_unlock+0x14/0x30 wait_for_completion+0x94/0x130 __wait_rcu_gp+0x108/0x130 synchronize_rcu+0x67/0x70 ? invoke_rcu_core+0xb0/0xb0 ? __bpf_trace_rcu_stall_warning+0x10/0x10 perf_pmu_migrate_context+0x121/0x370 iommu_pmu_cpu_offline+0x6a/0xa0 ? iommu_pmu_del+0x1e0/0x1e0 cpuhp_invoke_callback+0x129/0x510 cpuhp_thread_fun+0x94/0x150 smpboot_thread_fn+0x183/0x220 ? sort_range+0x20/0x20 kthread+0xe6/0x110 ? kthread_complete_and_exit+0x20/0x20 ret_from_fork+0x1f/0x30 ---[ end trace 0000000000000000 ]--- The synchronize_rcu() will be invoked in the perf_pmu_migrate_context(), when migrating a PMU to a new CPU. However, the current for_each_iommu() is within RCU read-side critical section. Two methods were considered to fix the issue. - Use the dmar_global_lock to replace the RCU read lock when going through the drhd list. But it triggers a lockdep warning. - Use the cpuhp_setup_state_multi() to set up a dedicated state for each IOMMU PMU. The lock can be avoided. The latter method is implemented in this patch. Since each IOMMU PMU has a dedicated state, add cpuhp_node and cpu in struct iommu_pmu to track the state. The state can be dynamically allocated now. Remove the CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE. Fixes: 46284c6ceb5e ("iommu/vt-d: Support cpumask for IOMMU perfmon") Reported-by: Ammy Yi Signed-off-by: Kan Liang Link: https://lore.kernel.org/r/20230328182028.1366416-1-kan.liang@linux.intel.com Signed-off-by: Lu Baolu Link: https://lore.kernel.org/r/20230329134721.469447-4-baolu.lu@linux.intel.com Signed-off-by: Joerg Roedel --- drivers/iommu/intel/iommu.h | 2 ++ drivers/iommu/intel/perfmon.c | 68 ++++++++++++++++++++++++++++--------------- include/linux/cpuhotplug.h | 1 - 3 files changed, 46 insertions(+), 25 deletions(-) (limited to 'include/linux') diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h index d6df3b865812..694ab9b7d3e9 100644 --- a/drivers/iommu/intel/iommu.h +++ b/drivers/iommu/intel/iommu.h @@ -641,6 +641,8 @@ struct iommu_pmu { DECLARE_BITMAP(used_mask, IOMMU_PMU_IDX_MAX); struct perf_event *event_list[IOMMU_PMU_IDX_MAX]; unsigned char irq_name[16]; + struct hlist_node cpuhp_node; + int cpu; }; #define IOMMU_IRQ_ID_OFFSET_PRQ (DMAR_UNITS_SUPPORTED) diff --git a/drivers/iommu/intel/perfmon.c b/drivers/iommu/intel/perfmon.c index e17d9743a0d8..cf43e798eca4 100644 --- a/drivers/iommu/intel/perfmon.c +++ b/drivers/iommu/intel/perfmon.c @@ -773,19 +773,34 @@ static void iommu_pmu_unset_interrupt(struct intel_iommu *iommu) iommu->perf_irq = 0; } -static int iommu_pmu_cpu_online(unsigned int cpu) +static int iommu_pmu_cpu_online(unsigned int cpu, struct hlist_node *node) { + struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node); + if (cpumask_empty(&iommu_pmu_cpu_mask)) cpumask_set_cpu(cpu, &iommu_pmu_cpu_mask); + if (cpumask_test_cpu(cpu, &iommu_pmu_cpu_mask)) + iommu_pmu->cpu = cpu; + return 0; } -static int iommu_pmu_cpu_offline(unsigned int cpu) +static int iommu_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node) { - struct dmar_drhd_unit *drhd; - struct intel_iommu *iommu; - int target; + struct iommu_pmu *iommu_pmu = hlist_entry_safe(node, typeof(*iommu_pmu), cpuhp_node); + int target = cpumask_first(&iommu_pmu_cpu_mask); + + /* + * The iommu_pmu_cpu_mask has been updated when offline the CPU + * for the first iommu_pmu. Migrate the other iommu_pmu to the + * new target. + */ + if (target < nr_cpu_ids && target != iommu_pmu->cpu) { + perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target); + iommu_pmu->cpu = target; + return 0; + } if (!cpumask_test_and_clear_cpu(cpu, &iommu_pmu_cpu_mask)) return 0; @@ -795,45 +810,50 @@ static int iommu_pmu_cpu_offline(unsigned int cpu) if (target < nr_cpu_ids) cpumask_set_cpu(target, &iommu_pmu_cpu_mask); else - target = -1; + return 0; - rcu_read_lock(); - - for_each_iommu(iommu, drhd) { - if (!iommu->pmu) - continue; - perf_pmu_migrate_context(&iommu->pmu->pmu, cpu, target); - } - rcu_read_unlock(); + perf_pmu_migrate_context(&iommu_pmu->pmu, cpu, target); + iommu_pmu->cpu = target; return 0; } static int nr_iommu_pmu; +static enum cpuhp_state iommu_cpuhp_slot; static int iommu_pmu_cpuhp_setup(struct iommu_pmu *iommu_pmu) { int ret; - if (nr_iommu_pmu++) - return 0; + if (!nr_iommu_pmu) { + ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, + "driver/iommu/intel/perfmon:online", + iommu_pmu_cpu_online, + iommu_pmu_cpu_offline); + if (ret < 0) + return ret; + iommu_cpuhp_slot = ret; + } - ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, - "driver/iommu/intel/perfmon:online", - iommu_pmu_cpu_online, - iommu_pmu_cpu_offline); - if (ret) - nr_iommu_pmu = 0; + ret = cpuhp_state_add_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node); + if (ret) { + if (!nr_iommu_pmu) + cpuhp_remove_multi_state(iommu_cpuhp_slot); + return ret; + } + nr_iommu_pmu++; - return ret; + return 0; } static void iommu_pmu_cpuhp_free(struct iommu_pmu *iommu_pmu) { + cpuhp_state_remove_instance(iommu_cpuhp_slot, &iommu_pmu->cpuhp_node); + if (--nr_iommu_pmu) return; - cpuhp_remove_state(CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE); + cpuhp_remove_multi_state(iommu_cpuhp_slot); } void iommu_pmu_register(struct intel_iommu *iommu) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index c6fab004104a..5b2f8147d1ae 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -218,7 +218,6 @@ enum cpuhp_state { CPUHP_AP_PERF_X86_CQM_ONLINE, CPUHP_AP_PERF_X86_CSTATE_ONLINE, CPUHP_AP_PERF_X86_IDXD_ONLINE, - CPUHP_AP_PERF_X86_IOMMU_PERF_ONLINE, CPUHP_AP_PERF_S390_CF_ONLINE, CPUHP_AP_PERF_S390_SF_ONLINE, CPUHP_AP_PERF_ARM_CCI_ONLINE, -- cgit v1.2.3