From 176bb149c6a29b8a219e0ae0972f0ba178843a68 Mon Sep 17 00:00:00 2001 From: Alan Stern Date: Mon, 6 Jul 2020 11:14:36 -0400 Subject: [PATCH 01/24] FROMGIT: scsi: block: pm: Simplify resume handling Commit 05d18ae1cc8a ("scsi: pm: Balance pm_only counter of request queue during system resume") fixed a problem in the block layer's runtime-PM code: blk_set_runtime_active() failed to call blk_clear_pm_only(). However, the commit's implementation was awkward; it forced the SCSI system-resume handler to choose whether to call blk_post_runtime_resume() or blk_set_runtime_active(), depending on whether or not the SCSI device had previously been runtime suspended. This patch simplifies the situation considerably by adding the missing function call directly into blk_set_runtime_active() (under the condition that the queue is not already in the RPM_ACTIVE state). This allows the SCSI routine to revert back to its original form. Furthermore, making this change reveals that blk_post_runtime_resume() (in its success pathway) does exactly the same thing as blk_set_runtime_active(). The duplicate code is easily removed by making one routine call the other. No functional changes are intended. Link: https://lore.kernel.org/r/20200706151436.GA702867@rowland.harvard.edu CC: Can Guo CC: Bart Van Assche Reviewed-by: Bart Van Assche Signed-off-by: Alan Stern Signed-off-by: Martin K. Petersen Bug: 162892567 (cherry picked from commit 8f38f8e0a30e1c33cdfc48eba2bd63ac2eae373a https://git.kernel.org/pub/scm/linux/kernel/git/mkp/scsi.git 5.9/scsi-queue) Change-Id: Ibeca9786fb65ee7d782314f48fb39274b82feb57 Signed-off-by: Can Guo --- block/blk-pm.c | 41 ++++++++++++++++++++++------------------- drivers/scsi/scsi_pm.c | 10 ++-------- 2 files changed, 24 insertions(+), 27 deletions(-) diff --git a/block/blk-pm.c b/block/blk-pm.c index 1adc1cd748b4..b85234d758f7 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -164,9 +164,8 @@ EXPORT_SYMBOL(blk_pre_runtime_resume); * * Description: * Update the queue's runtime status according to the return value of the - * device's runtime_resume function. If it is successfully resumed, process - * the requests that are queued into the device's queue when it is resuming - * and then mark last busy and initiate autosuspend for it. + * device's runtime_resume function. If the resume was successful, call + * blk_set_runtime_active() to do the real work of restarting the queue. * * This function should be called near the end of the device's * runtime_resume callback. @@ -175,19 +174,13 @@ void blk_post_runtime_resume(struct request_queue *q, int err) { if (!q->dev) return; - - spin_lock_irq(&q->queue_lock); if (!err) { - q->rpm_status = RPM_ACTIVE; - pm_runtime_mark_last_busy(q->dev); - pm_request_autosuspend(q->dev); + blk_set_runtime_active(q); } else { + spin_lock_irq(&q->queue_lock); q->rpm_status = RPM_SUSPENDED; + spin_unlock_irq(&q->queue_lock); } - spin_unlock_irq(&q->queue_lock); - - if (!err) - blk_clear_pm_only(q); } EXPORT_SYMBOL(blk_post_runtime_resume); @@ -204,15 +197,25 @@ EXPORT_SYMBOL(blk_post_runtime_resume); * This function can be used in driver's resume hook to correct queue * runtime PM status and re-enable peeking requests from the queue. It * should be called before first request is added to the queue. + * + * This function is also called by blk_post_runtime_resume() for successful + * runtime resumes. It does everything necessary to restart the queue. */ void blk_set_runtime_active(struct request_queue *q) { - if (q->dev) { - spin_lock_irq(&q->queue_lock); - q->rpm_status = RPM_ACTIVE; - pm_runtime_mark_last_busy(q->dev); - pm_request_autosuspend(q->dev); - spin_unlock_irq(&q->queue_lock); - } + int old_status; + + if (!q->dev) + return; + + spin_lock_irq(&q->queue_lock); + old_status = q->rpm_status; + q->rpm_status = RPM_ACTIVE; + pm_runtime_mark_last_busy(q->dev); + pm_request_autosuspend(q->dev); + spin_unlock_irq(&q->queue_lock); + + if (old_status != RPM_ACTIVE) + blk_clear_pm_only(q); } EXPORT_SYMBOL(blk_set_runtime_active); diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c index 5f0ad8b32e3a..3717eea37ecb 100644 --- a/drivers/scsi/scsi_pm.c +++ b/drivers/scsi/scsi_pm.c @@ -80,10 +80,6 @@ static int scsi_dev_type_resume(struct device *dev, dev_dbg(dev, "scsi resume: %d\n", err); if (err == 0) { - bool was_runtime_suspended; - - was_runtime_suspended = pm_runtime_suspended(dev); - pm_runtime_disable(dev); err = pm_runtime_set_active(dev); pm_runtime_enable(dev); @@ -97,10 +93,8 @@ static int scsi_dev_type_resume(struct device *dev, */ if (!err && scsi_is_sdev_device(dev)) { struct scsi_device *sdev = to_scsi_device(dev); - if (was_runtime_suspended) - blk_post_runtime_resume(sdev->request_queue, 0); - else - blk_set_runtime_active(sdev->request_queue); + + blk_set_runtime_active(sdev->request_queue); } } From 31a348791a324966ad050c4207de7f757438052d Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Mon, 22 Jun 2020 18:18:02 -0700 Subject: [PATCH 02/24] UPSTREAM: arm64/module: Optimize module load time by optimizing PLT counting When loading a module, module_frob_arch_sections() tries to figure out the number of PLTs that'll be needed to handle all the RELAs. While doing this, it tries to dedupe PLT allocations for multiple R_AARCH64_CALL26 relocations to the same symbol. It does the same for R_AARCH64_JUMP26 relocations. To make checks for duplicates easier/faster, it sorts the relocation list by type, symbol and addend. That way, to check for a duplicate relocation, it just needs to compare with the previous entry. However, sorting the entire relocation array is unnecessary and expensive (O(n log n)) because there are a lot of other relocation types that don't need deduping or can't be deduped. So this commit partitions the array into entries that need deduping and those that don't. And then sorts just the part that needs deduping. And when CONFIG_RANDOMIZE_BASE is disabled, the sorting is skipped entirely because PLTs are not allocated for R_AARCH64_CALL26 and R_AARCH64_JUMP26 if it's disabled. This gives significant reduction in module load time for modules with large number of relocations with no measurable impact on modules with a small number of relocations. In my test setup with CONFIG_RANDOMIZE_BASE enabled, these were the results for a few downstream modules: Module Size (MB) wlan 14 video codec 3.8 drm 1.8 IPA 2.5 audio 1.2 gpu 1.8 Without this patch: Module Number of entries sorted Module load time (ms) wlan 243739 283 video codec 74029 138 drm 53837 67 IPA 42800 90 audio 21326 27 gpu 20967 32 Total time to load all these module: 637 ms With this patch: Module Number of entries sorted Module load time (ms) wlan 22454 61 video codec 10150 47 drm 13014 40 IPA 8097 63 audio 4606 16 gpu 6527 20 Total time to load all these modules: 247 Time saved during boot for just these 6 modules: 390 ms Signed-off-by: Saravana Kannan Acked-by: Will Deacon Cc: Ard Biesheuvel Link: https://lore.kernel.org/r/20200623011803.91232-1-saravanak@google.com Signed-off-by: Catalin Marinas (cherry picked from commit d4e0340919fb9190a57e879fb3125c4acce0d9b2) Signed-off-by: Saravana Kannan Bug: 159681305 Change-Id: I6660f6e5d5e950340445f388d047c306fb0dfe6d --- arch/arm64/kernel/module-plts.c | 46 ++++++++++++++++++++++++++++++--- 1 file changed, 43 insertions(+), 3 deletions(-) diff --git a/arch/arm64/kernel/module-plts.c b/arch/arm64/kernel/module-plts.c index b182442b87a3..ce2d19f895a1 100644 --- a/arch/arm64/kernel/module-plts.c +++ b/arch/arm64/kernel/module-plts.c @@ -252,6 +252,40 @@ static unsigned int count_plts(Elf64_Sym *syms, Elf64_Rela *rela, int num, return ret; } +static bool branch_rela_needs_plt(Elf64_Sym *syms, Elf64_Rela *rela, + Elf64_Word dstidx) +{ + + Elf64_Sym *s = syms + ELF64_R_SYM(rela->r_info); + + if (s->st_shndx == dstidx) + return false; + + return ELF64_R_TYPE(rela->r_info) == R_AARCH64_JUMP26 || + ELF64_R_TYPE(rela->r_info) == R_AARCH64_CALL26; +} + +/* Group branch PLT relas at the front end of the array. */ +static int partition_branch_plt_relas(Elf64_Sym *syms, Elf64_Rela *rela, + int numrels, Elf64_Word dstidx) +{ + int i = 0, j = numrels - 1; + + if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + return 0; + + while (i < j) { + if (branch_rela_needs_plt(syms, &rela[i], dstidx)) + i++; + else if (branch_rela_needs_plt(syms, &rela[j], dstidx)) + swap(rela[i], rela[j]); + else + j--; + } + + return i; +} + int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings, struct module *mod) { @@ -289,7 +323,7 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, for (i = 0; i < ehdr->e_shnum; i++) { Elf64_Rela *rels = (void *)ehdr + sechdrs[i].sh_offset; - int numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela); + int nents, numrels = sechdrs[i].sh_size / sizeof(Elf64_Rela); Elf64_Shdr *dstsec = sechdrs + sechdrs[i].sh_info; if (sechdrs[i].sh_type != SHT_RELA) @@ -299,8 +333,14 @@ int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, if (!(dstsec->sh_flags & SHF_EXECINSTR)) continue; - /* sort by type, symbol index and addend */ - sort(rels, numrels, sizeof(Elf64_Rela), cmp_rela, NULL); + /* + * sort branch relocations requiring a PLT by type, symbol index + * and addend + */ + nents = partition_branch_plt_relas(syms, rels, numrels, + sechdrs[i].sh_info); + if (nents) + sort(rels, nents, sizeof(Elf64_Rela), cmp_rela, NULL); if (!str_has_prefix(secstrings + dstsec->sh_name, ".init")) core_plts += count_plts(syms, rels, numrels, From 2b2b5b944c36f9ba96a110d6db76ce68ee5b94f4 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Jul 2020 12:42:57 -0700 Subject: [PATCH 03/24] UPSTREAM: driver core: Don't do deferred probe in parallel with kernel_init thread The current deferred probe implementation can mess up suspend/resume ordering if deferred probe thread is kicked off in parallel with the main initcall thread (kernel_init thread) [1]. For example: Say device-B is a consumer of device-A. Initcall thread Deferred probe thread =============== ===================== 1. device-A is added. 2. device-B is added. 3. dpm_list is now [device-A, device-B]. 4. driver-A defers probe of device-A. 5. device-A is moved to end of dpm_list 6. dpm_list is now [device-B, device-A] 7. driver-B is registereed and probes device-B. 8. dpm_list stays as [device-B, device-A]. The reverse order of dpm_list is used for suspend. So in this case device-A would incorrectly get suspended before device-B. Commit 716a7a259690 ("driver core: fw_devlink: Add support for batching fwnode parsing") kicked off the deferred probe thread early during boot to run in parallel with the initcall thread and caused suspend/resume regressions. This patch removes the parallel run of the deferred probe thread to avoid the suspend/resume regressions. [1] - https://lore.kernel.org/lkml/CAGETcx8W96KAw-d_siTX4qHB_-7ddk0miYRDQeHE6E0_8qx-6Q@mail.gmail.com/ Fixes: 716a7a259690 ("driver core: fw_devlink: Add support for batching fwnode parsing") Signed-off-by: Saravana Kannan Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200701194259.3337652-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit cec72f3efc6272420c2c2c699607f03d09b93e41) Signed-off-by: Saravana Kannan Bug: 157691602 Change-Id: I13f61a7cbeb705eb6ca1c67b07df5a9b69045029 --- drivers/base/base.h | 1 - drivers/base/core.c | 1 - drivers/base/dd.c | 5 ----- 3 files changed, 7 deletions(-) diff --git a/drivers/base/base.h b/drivers/base/base.h index 2faf767d18dc..0d32544b6f91 100644 --- a/drivers/base/base.h +++ b/drivers/base/base.h @@ -142,7 +142,6 @@ extern char *make_class_name(const char *name, struct kobject *kobj); extern int devres_release_all(struct device *dev); extern void device_block_probing(void); extern void device_unblock_probing(void); -extern void driver_deferred_probe_force_trigger(void); /* /sys/devices directory */ extern struct kset *devices_kset; diff --git a/drivers/base/core.c b/drivers/base/core.c index 6764f1827523..a32b1c32611c 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1287,7 +1287,6 @@ void fw_devlink_resume(void) goto out; device_link_add_missing_supplier_links(); - driver_deferred_probe_force_trigger(); out: mutex_unlock(&defer_fw_devlink_lock); } diff --git a/drivers/base/dd.c b/drivers/base/dd.c index 802f03eb3c37..b25bcab2a26b 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -164,11 +164,6 @@ static void driver_deferred_probe_trigger(void) if (!driver_deferred_probe_enable) return; - driver_deferred_probe_force_trigger(); -} - -void driver_deferred_probe_force_trigger(void) -{ /* * A successful probe means that all the devices in the pending list * should be triggered to be reprobed. Move all the deferred devices From 7d2718b6ffe2735b89c5ea822f1b78eec5ac28f9 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Jul 2020 12:42:58 -0700 Subject: [PATCH 04/24] UPSTREAM: driver core: Rename dev_links_info.defer_sync to defer_hook The defer_sync field is used as a hook to add the device to the deferred_sync list. Rename it so that it's more meaningful for the next patch that'll also use this field as a hook to a deferred_fw_devlink list. Signed-off-by: Saravana Kannan Reviewed-by: Rafael J. Wysocki Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200701194259.3337652-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit ec7bd78498f29680f536451fbdf9464e851273ed) Signed-off-by: Saravana Kannan Bug: 157691602 Change-Id: Ia213a9b8b6efc33882f5b2cfaad284ee0eca8cd4 --- drivers/base/core.c | 22 +++++++++++----------- include/linux/device.h | 4 ++-- 2 files changed, 13 insertions(+), 13 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index a32b1c32611c..5d7fbe7b9727 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -753,11 +753,11 @@ static void __device_links_queue_sync_state(struct device *dev, */ dev->state_synced = true; - if (WARN_ON(!list_empty(&dev->links.defer_sync))) + if (WARN_ON(!list_empty(&dev->links.defer_hook))) return; get_device(dev); - list_add_tail(&dev->links.defer_sync, list); + list_add_tail(&dev->links.defer_hook, list); } /** @@ -775,8 +775,8 @@ static void device_links_flush_sync_list(struct list_head *list, { struct device *dev, *tmp; - list_for_each_entry_safe(dev, tmp, list, links.defer_sync) { - list_del_init(&dev->links.defer_sync); + list_for_each_entry_safe(dev, tmp, list, links.defer_hook) { + list_del_init(&dev->links.defer_hook); if (dev != dont_lock_dev) device_lock(dev); @@ -814,12 +814,12 @@ void device_links_supplier_sync_state_resume(void) if (defer_sync_state_count) goto out; - list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_sync) { + list_for_each_entry_safe(dev, tmp, &deferred_sync, links.defer_hook) { /* * Delete from deferred_sync list before queuing it to - * sync_list because defer_sync is used for both lists. + * sync_list because defer_hook is used for both lists. */ - list_del_init(&dev->links.defer_sync); + list_del_init(&dev->links.defer_hook); __device_links_queue_sync_state(dev, &sync_list); } out: @@ -837,8 +837,8 @@ late_initcall(sync_state_resume_initcall); static void __device_links_supplier_defer_sync(struct device *sup) { - if (list_empty(&sup->links.defer_sync) && dev_has_sync_state(sup)) - list_add_tail(&sup->links.defer_sync, &deferred_sync); + if (list_empty(&sup->links.defer_hook) && dev_has_sync_state(sup)) + list_add_tail(&sup->links.defer_hook, &deferred_sync); } static void device_link_drop_managed(struct device_link *link) @@ -1051,7 +1051,7 @@ void device_links_driver_cleanup(struct device *dev) WRITE_ONCE(link->status, DL_STATE_DORMANT); } - list_del_init(&dev->links.defer_sync); + list_del_init(&dev->links.defer_hook); __device_links_no_driver(dev); device_links_write_unlock(); @@ -2135,7 +2135,7 @@ void device_initialize(struct device *dev) INIT_LIST_HEAD(&dev->links.consumers); INIT_LIST_HEAD(&dev->links.suppliers); INIT_LIST_HEAD(&dev->links.needs_suppliers); - INIT_LIST_HEAD(&dev->links.defer_sync); + INIT_LIST_HEAD(&dev->links.defer_hook); dev->links.status = DL_DEV_NO_DRIVER; } EXPORT_SYMBOL_GPL(device_initialize); diff --git a/include/linux/device.h b/include/linux/device.h index 807b57889169..7454ba587749 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1170,7 +1170,7 @@ enum dl_dev_state { * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. - * @defer_sync: Hook to global list of devices that have deferred sync_state. + * @defer_hook: Hook to global list of devices that have deferred sync_state. * @need_for_probe: If needs_suppliers is on a list, this indicates if the * suppliers are needed for probe or not. * @status: Driver status information. @@ -1179,7 +1179,7 @@ struct dev_links_info { struct list_head suppliers; struct list_head consumers; struct list_head needs_suppliers; - struct list_head defer_sync; + struct list_head defer_hook; bool need_for_probe; enum dl_dev_state status; }; From c88a69f0e9a39d48d2ed72c2473a3502aded7d25 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Jul 2020 12:42:59 -0700 Subject: [PATCH 05/24] UPSTREAM: driver core: Avoid deferred probe due to fw_devlink_pause/resume() With the earlier patch in this series, all devices that deferred probe due to fw_devlink_pause() will have their probes delayed till the deferred probe thread is kicked off during late_initcall. This will also affect all their consumers. This delayed probing in unnecessary. So this patch just keeps track of the devices that had their probe deferred due to fw_devlink_pause() and attempts to probe them once during fw_devlink_resume(). Fixes: 716a7a259690 ("driver core: fw_devlink: Add support for batching fwnode parsing") Signed-off-by: Saravana Kannan Tested-by: Geert Uytterhoeven Link: https://lore.kernel.org/r/20200701194259.3337652-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 2451e746478a6a6e981cfa66b62b791ca93b90c8) Signed-off-by: Saravana Kannan Bug: 157691602 Change-Id: I76205ec0851fa251da5df485b1503b65b3296c7c --- drivers/base/core.c | 21 +++++++++++++++++++++ include/linux/device.h | 3 ++- 2 files changed, 23 insertions(+), 1 deletion(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 5d7fbe7b9727..c0ed1045a7e1 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -50,6 +50,7 @@ static DEFINE_MUTEX(wfs_lock); static LIST_HEAD(deferred_sync); static unsigned int defer_sync_state_count = 1; static unsigned int defer_fw_devlink_count; +static LIST_HEAD(deferred_fw_devlink); static DEFINE_MUTEX(defer_fw_devlink_lock); #ifdef CONFIG_SRCU @@ -1208,6 +1209,12 @@ static void fw_devlink_link_device(struct device *dev) fw_ret = fwnode_call_int_op(dev->fwnode, add_links, dev); } else { fw_ret = -ENODEV; + /* + * defer_hook is not used to add device to deferred_sync list + * until device is bound. Since deferred fw devlink also blocks + * probing, same list hook can be used for deferred_fw_devlink. + */ + list_add_tail(&dev->links.defer_hook, &deferred_fw_devlink); } if (fw_ret == -ENODEV) @@ -1276,6 +1283,9 @@ void fw_devlink_pause(void) */ void fw_devlink_resume(void) { + struct device *dev, *tmp; + LIST_HEAD(probe_list); + mutex_lock(&defer_fw_devlink_lock); if (!defer_fw_devlink_count) { WARN(true, "Unmatched fw_devlink pause/resume!"); @@ -1287,8 +1297,19 @@ void fw_devlink_resume(void) goto out; device_link_add_missing_supplier_links(); + list_splice_tail_init(&deferred_fw_devlink, &probe_list); out: mutex_unlock(&defer_fw_devlink_lock); + + /* + * bus_probe_device() can cause new devices to get added and they'll + * try to grab defer_fw_devlink_lock. So, this needs to be done outside + * the defer_fw_devlink_lock. + */ + list_for_each_entry_safe(dev, tmp, &probe_list, links.defer_hook) { + list_del_init(&dev->links.defer_hook); + bus_probe_device(dev); + } } /* Device links support end. */ diff --git a/include/linux/device.h b/include/linux/device.h index 7454ba587749..44bc87d85b33 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1170,7 +1170,8 @@ enum dl_dev_state { * @suppliers: List of links to supplier devices. * @consumers: List of links to consumer devices. * @needs_suppliers: Hook to global list of devices waiting for suppliers. - * @defer_hook: Hook to global list of devices that have deferred sync_state. + * @defer_hook: Hook to global list of devices that have deferred sync_state or + * deferred fw_devlink. * @need_for_probe: If needs_suppliers is on a list, this indicates if the * suppliers are needed for probe or not. * @status: Driver status information. From 3b499928c275f4b1ee7fc7fbf80719d0d96cb43b Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 21 May 2020 12:17:58 -0700 Subject: [PATCH 06/24] UPSTREAM: driver core: Expose device link details in sysfs It's helpful to be able to look at device link details from sysfs. So, expose it in sysfs. Say device-A is supplier of device-B. These are the additional files this patch would create: /sys/class/devlink/device-A:device-B/ auto_remove_on consumer/ -> .../device-B/ runtime_pm status supplier/ -> .../device-A/ sync_state_only /sys/devices/.../device-A/ consumer:device-B/ -> /sys/class/devlink/device-A:device-B/ /sys/devices/.../device-B/ supplier:device-A/ -> /sys/class/devlink/device-A:device-B/ That way: To get a list of all the device link in the system: ls /sys/class/devlink/ To get the consumer names and links of a device: ls -d /sys/devices/.../device-X/consumer:* To get the supplier names and links of a device: ls -d /sys/devices/.../device-X/supplier:* Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200521191800.136035-2-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 287905e68dd29873bcb7986a8290cd1e4cfde600) Signed-off-by: Saravana Kannan Bug: 163090256 Change-Id: I41dafdd731b8d429b5a21fd2e8d4d396b2bb571e --- Documentation/ABI/testing/sysfs-class-devlink | 126 +++++++++++ .../ABI/testing/sysfs-devices-consumer | 8 + .../ABI/testing/sysfs-devices-supplier | 8 + drivers/base/core.c | 211 +++++++++++++++++- include/linux/device.h | 58 ++--- 5 files changed, 375 insertions(+), 36 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-class-devlink create mode 100644 Documentation/ABI/testing/sysfs-devices-consumer create mode 100644 Documentation/ABI/testing/sysfs-devices-supplier diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink new file mode 100644 index 000000000000..3a24973abb83 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-class-devlink @@ -0,0 +1,126 @@ +What: /sys/class/devlink/.../ +Date: May 2020 +Contact: Saravana Kannan +Description: + Provide a place in sysfs for the device link objects in the + kernel at any given time. The name of a device link directory, + denoted as ... above, is of the form : + where is the supplier device name and is + the consumer device name. + +What: /sys/class/devlink/.../auto_remove_on +Date: May 2020 +Contact: Saravana Kannan +Description: + This file indicates if the device link will ever be + automatically removed by the driver core when the consumer and + supplier devices themselves are still present. + + This will be one of the following strings: + + 'consumer unbind' + 'supplier unbind' + 'never' + + 'consumer unbind' means the device link will be removed when + the consumer's driver is unbound from the consumer device. + + 'supplier unbind' means the device link will be removed when + the supplier's driver is unbound from the supplier device. + + 'never' means the device link will not be automatically removed + when as long as the supplier and consumer devices themselves + are still present. + +What: /sys/class/devlink/.../consumer +Date: May 2020 +Contact: Saravana Kannan +Description: + This file is a symlink to the consumer device's sysfs directory. + +What: /sys/class/devlink/.../runtime_pm +Date: May 2020 +Contact: Saravana Kannan +Description: + This file indicates if the device link has any impact on the + runtime power management behavior of the consumer and supplier + devices. For example: Making sure the supplier doesn't enter + runtime suspend while the consumer is active. + + This will be one of the following strings: + + '0' - Does not affect runtime power management + '1' - Affects runtime power management + +What: /sys/class/devlink/.../status +Date: May 2020 +Contact: Saravana Kannan +Description: + This file indicates the status of the device link. The status + of a device link is affected by whether the supplier and + consumer devices have been bound to their corresponding + drivers. The status of a device link also affects the binding + and unbinding of the supplier and consumer devices with their + drivers and also affects whether the software state of the + supplier device is synced with the hardware state of the + supplier device after boot up. + See also: sysfs-devices-state_synced. + + This will be one of the following strings: + + 'not tracked' + 'dormant' + 'available' + 'consumer probing' + 'active' + 'supplier unbinding' + 'unknown' + + 'not tracked' means this device link does not track the status + and has no impact on the binding, unbinding and syncing the + hardware and software device state. + + 'dormant' means the supplier and the consumer devices have not + bound to their driver. + + 'available' means the supplier has bound to its driver and is + available to supply resources to the consumer device. + + 'consumer probing' means the consumer device is currently + trying to bind to its driver. + + 'active' means the supplier and consumer devices have both + bound successfully to their drivers. + + 'supplier unbinding' means the supplier devices is currently in + the process of unbinding from its driver. + + 'unknown' means the state of the device link is not any of the + above. If this is ever the value, there's a bug in the kernel. + +What: /sys/class/devlink/.../supplier +Date: May 2020 +Contact: Saravana Kannan +Description: + This file is a symlink to the supplier device's sysfs directory. + +What: /sys/class/devlink/.../sync_state_only +Date: May 2020 +Contact: Saravana Kannan +Description: + This file indicates if the device link is limited to only + affecting the syncing of the hardware and software state of the + supplier device. + + This will be one of the following strings: + + '0' + '1' - Affects runtime power management + + '0' means the device link can affect other device behaviors + like binding/unbinding, suspend/resume, runtime power + management, etc. + + '1' means the device link will only affect the syncing of + hardware and software state of the supplier device after boot + up and doesn't not affect other behaviors of the devices. diff --git a/Documentation/ABI/testing/sysfs-devices-consumer b/Documentation/ABI/testing/sysfs-devices-consumer new file mode 100644 index 000000000000..1f06d74d1c3c --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-consumer @@ -0,0 +1,8 @@ +What: /sys/devices/.../consumer: +Date: May 2020 +Contact: Saravana Kannan +Description: + The /sys/devices/.../consumer: are symlinks to device + links where this device is the supplier. denotes the + name of the consumer in that device link. There can be zero or + more of these symlinks for a given device. diff --git a/Documentation/ABI/testing/sysfs-devices-supplier b/Documentation/ABI/testing/sysfs-devices-supplier new file mode 100644 index 000000000000..a919e0db5e90 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-supplier @@ -0,0 +1,8 @@ +What: /sys/devices/.../supplier: +Date: May 2020 +Contact: Saravana Kannan +Description: + The /sys/devices/.../supplier: are symlinks to device + links where this device is the consumer. denotes the + name of the supplier in that device link. There can be zero or + more of these symlinks for a given device. diff --git a/drivers/base/core.c b/drivers/base/core.c index c0ed1045a7e1..cfceaab85028 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -235,6 +235,186 @@ void device_pm_move_to_tail(struct device *dev) device_links_read_unlock(idx); } +#define to_devlink(dev) container_of((dev), struct device_link, link_dev) + +static ssize_t status_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + char *status; + + switch (to_devlink(dev)->status) { + case DL_STATE_NONE: + status = "not tracked"; break; + case DL_STATE_DORMANT: + status = "dormant"; break; + case DL_STATE_AVAILABLE: + status = "available"; break; + case DL_STATE_CONSUMER_PROBE: + status = "consumer probing"; break; + case DL_STATE_ACTIVE: + status = "active"; break; + case DL_STATE_SUPPLIER_UNBIND: + status = "supplier unbinding"; break; + default: + status = "unknown"; break; + } + return sprintf(buf, "%s\n", status); +} +static DEVICE_ATTR_RO(status); + +static ssize_t auto_remove_on_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct device_link *link = to_devlink(dev); + char *str; + + if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER) + str = "supplier unbind"; + else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) + str = "consumer unbind"; + else + str = "never"; + + return sprintf(buf, "%s\n", str); +} +static DEVICE_ATTR_RO(auto_remove_on); + +static ssize_t runtime_pm_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct device_link *link = to_devlink(dev); + + return sprintf(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME)); +} +static DEVICE_ATTR_RO(runtime_pm); + +static ssize_t sync_state_only_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct device_link *link = to_devlink(dev); + + return sprintf(buf, "%d\n", !!(link->flags & DL_FLAG_SYNC_STATE_ONLY)); +} +static DEVICE_ATTR_RO(sync_state_only); + +static struct attribute *devlink_attrs[] = { + &dev_attr_status.attr, + &dev_attr_auto_remove_on.attr, + &dev_attr_runtime_pm.attr, + &dev_attr_sync_state_only.attr, + NULL, +}; +ATTRIBUTE_GROUPS(devlink); + +static void devlink_dev_release(struct device *dev) +{ + kfree(to_devlink(dev)); +} + +static struct class devlink_class = { + .name = "devlink", + .owner = THIS_MODULE, + .dev_groups = devlink_groups, + .dev_release = devlink_dev_release, +}; + +static int devlink_add_symlinks(struct device *dev, + struct class_interface *class_intf) +{ + int ret; + size_t len; + struct device_link *link = to_devlink(dev); + struct device *sup = link->supplier; + struct device *con = link->consumer; + char *buf; + + len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len += strlen("supplier:") + 1; + buf = kzalloc(len, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + ret = sysfs_create_link(&link->link_dev.kobj, &sup->kobj, "supplier"); + if (ret) + goto out; + + ret = sysfs_create_link(&link->link_dev.kobj, &con->kobj, "consumer"); + if (ret) + goto err_con; + + snprintf(buf, len, "consumer:%s", dev_name(con)); + ret = sysfs_create_link(&sup->kobj, &link->link_dev.kobj, buf); + if (ret) + goto err_con_dev; + + snprintf(buf, len, "supplier:%s", dev_name(sup)); + ret = sysfs_create_link(&con->kobj, &link->link_dev.kobj, buf); + if (ret) + goto err_sup_dev; + + goto out; + +err_sup_dev: + snprintf(buf, len, "consumer:%s", dev_name(con)); + sysfs_remove_link(&sup->kobj, buf); +err_con_dev: + sysfs_remove_link(&link->link_dev.kobj, "consumer"); +err_con: + sysfs_remove_link(&link->link_dev.kobj, "supplier"); +out: + kfree(buf); + return ret; +} + +static void devlink_remove_symlinks(struct device *dev, + struct class_interface *class_intf) +{ + struct device_link *link = to_devlink(dev); + size_t len; + struct device *sup = link->supplier; + struct device *con = link->consumer; + char *buf; + + sysfs_remove_link(&link->link_dev.kobj, "consumer"); + sysfs_remove_link(&link->link_dev.kobj, "supplier"); + + len = max(strlen(dev_name(sup)), strlen(dev_name(con))); + len += strlen("supplier:") + 1; + buf = kzalloc(len, GFP_KERNEL); + if (!buf) { + WARN(1, "Unable to properly free device link symlinks!\n"); + return; + } + + snprintf(buf, len, "supplier:%s", dev_name(sup)); + sysfs_remove_link(&con->kobj, buf); + snprintf(buf, len, "consumer:%s", dev_name(con)); + sysfs_remove_link(&sup->kobj, buf); + kfree(buf); +} + +static struct class_interface devlink_class_intf = { + .class = &devlink_class, + .add_dev = devlink_add_symlinks, + .remove_dev = devlink_remove_symlinks, +}; + +static int __init devlink_class_init(void) +{ + int ret; + + ret = class_register(&devlink_class); + if (ret) + return ret; + + ret = class_interface_register(&devlink_class_intf); + if (ret) + class_unregister(&devlink_class); + + return ret; +} +postcore_initcall(devlink_class_init); + #define DL_MANAGED_LINK_FLAGS (DL_FLAG_AUTOREMOVE_CONSUMER | \ DL_FLAG_AUTOREMOVE_SUPPLIER | \ DL_FLAG_AUTOPROBE_CONSUMER | \ @@ -407,13 +587,6 @@ struct device_link *device_link_add(struct device *consumer, refcount_set(&link->rpm_active, 1); - if (flags & DL_FLAG_PM_RUNTIME) { - if (flags & DL_FLAG_RPM_ACTIVE) - refcount_inc(&link->rpm_active); - - pm_runtime_new_link(consumer); - } - get_device(supplier); link->supplier = supplier; INIT_LIST_HEAD(&link->s_node); @@ -423,6 +596,25 @@ struct device_link *device_link_add(struct device *consumer, link->flags = flags; kref_init(&link->kref); + link->link_dev.class = &devlink_class; + device_set_pm_not_required(&link->link_dev); + dev_set_name(&link->link_dev, "%s:%s", + dev_name(supplier), dev_name(consumer)); + if (device_register(&link->link_dev)) { + put_device(consumer); + put_device(supplier); + kfree(link); + link = NULL; + goto out; + } + + if (flags & DL_FLAG_PM_RUNTIME) { + if (flags & DL_FLAG_RPM_ACTIVE) + refcount_inc(&link->rpm_active); + + pm_runtime_new_link(consumer); + } + /* Determine the initial link state. */ if (flags & DL_FLAG_STATELESS) link->status = DL_STATE_NONE; @@ -545,7 +737,7 @@ static void device_link_free(struct device_link *link) put_device(link->consumer); put_device(link->supplier); - kfree(link); + device_unregister(&link->link_dev); } #ifdef CONFIG_SRCU @@ -1159,6 +1351,9 @@ static void device_links_purge(struct device *dev) { struct device_link *link, *ln; + if (dev->class == &devlink_class) + return; + mutex_lock(&wfs_lock); list_del(&dev->links.needs_suppliers); mutex_unlock(&wfs_lock); diff --git a/include/linux/device.h b/include/linux/device.h index 44bc87d85b33..e1628d2101c4 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -1123,34 +1123,6 @@ enum device_link_state { #define DL_FLAG_MANAGED BIT(6) #define DL_FLAG_SYNC_STATE_ONLY BIT(7) -/** - * struct device_link - Device link representation. - * @supplier: The device on the supplier end of the link. - * @s_node: Hook to the supplier device's list of links to consumers. - * @consumer: The device on the consumer end of the link. - * @c_node: Hook to the consumer device's list of links to suppliers. - * @status: The state of the link (with respect to the presence of drivers). - * @flags: Link flags. - * @rpm_active: Whether or not the consumer device is runtime-PM-active. - * @kref: Count repeated addition of the same link. - * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. - * @supplier_preactivated: Supplier has been made active before consumer probe. - */ -struct device_link { - struct device *supplier; - struct list_head s_node; - struct device *consumer; - struct list_head c_node; - enum device_link_state status; - u32 flags; - refcount_t rpm_active; - struct kref kref; -#ifdef CONFIG_SRCU - struct rcu_head rcu_head; -#endif - bool supplier_preactivated; /* Owned by consumer probe. */ -}; - /** * enum dl_dev_state - Device driver presence tracking information. * @DL_DEV_NO_DRIVER: There is no driver attached to the device. @@ -1372,6 +1344,36 @@ struct device { ANDROID_KABI_RESERVE(8); }; +/** + * struct device_link - Device link representation. + * @supplier: The device on the supplier end of the link. + * @s_node: Hook to the supplier device's list of links to consumers. + * @consumer: The device on the consumer end of the link. + * @c_node: Hook to the consumer device's list of links to suppliers. + * @link_dev: device used to expose link details in sysfs + * @status: The state of the link (with respect to the presence of drivers). + * @flags: Link flags. + * @rpm_active: Whether or not the consumer device is runtime-PM-active. + * @kref: Count repeated addition of the same link. + * @rcu_head: An RCU head to use for deferred execution of SRCU callbacks. + * @supplier_preactivated: Supplier has been made active before consumer probe. + */ +struct device_link { + struct device *supplier; + struct list_head s_node; + struct device *consumer; + struct list_head c_node; + struct device link_dev; + enum device_link_state status; + u32 flags; + refcount_t rpm_active; + struct kref kref; +#ifdef CONFIG_SRCU + struct rcu_head rcu_head; +#endif + bool supplier_preactivated; /* Owned by consumer probe. */ +}; + static inline struct device *kobj_to_dev(struct kobject *kobj) { return container_of(kobj, struct device, kobj); From e157d387e1a3f8e8b214921a325a5e2f9f70ee07 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 21 May 2020 12:17:59 -0700 Subject: [PATCH 07/24] UPSTREAM: driver core: Add state_synced sysfs file for devices that support it This can be used to check if a device supports sync_state() callbacks and therefore keeps resources left on by the bootloader enabled till all its consumers have probed. This can also be used to check if sync_state() has been called for a device or whether it is still trying to keep resources enabled because they were left enabled by the bootloader and all its consumers haven't probed yet. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200521191800.136035-3-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 8fd456ec0cf03875908d6b67c1cd20cf0a7b4474) Signed-off-by: Saravana Kannan Bug: 163090256 Change-Id: I15b6db469e545eed9ecc97aca02ea90e7d318f2c --- .../ABI/testing/sysfs-devices-state_synced | 24 +++++++++++++++++++ drivers/base/dd.c | 22 +++++++++++++++++ 2 files changed, 46 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-devices-state_synced diff --git a/Documentation/ABI/testing/sysfs-devices-state_synced b/Documentation/ABI/testing/sysfs-devices-state_synced new file mode 100644 index 000000000000..0c922d7d02fc --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-state_synced @@ -0,0 +1,24 @@ +What: /sys/devices/.../state_synced +Date: May 2020 +Contact: Saravana Kannan +Description: + The /sys/devices/.../state_synced attribute is only present for + devices whose bus types or driver provides the .sync_state() + callback. The number read from it (0 or 1) reflects the value + of the device's 'state_synced' field. A value of 0 means the + .sync_state() callback hasn't been called yet. A value of 1 + means the .sync_state() callback has been called. + + Generally, if a device has sync_state() support and has some of + the resources it provides enabled at the time the kernel starts + (Eg: enabled by hardware reset or bootloader or anything that + run before the kernel starts), then it'll keep those resources + enabled and in a state that's compatible with the state they + were in at the start of the kernel. The device will stop doing + this only when the sync_state() callback has been called -- + which happens only when all its consumer devices are registered + and have probed successfully. Resources that were left disabled + at the time the kernel starts are not affected or limited in + any way by sync_state() callbacks. + + diff --git a/drivers/base/dd.c b/drivers/base/dd.c index b25bcab2a26b..6b69abab08f8 100644 --- a/drivers/base/dd.c +++ b/drivers/base/dd.c @@ -489,6 +489,18 @@ static void driver_deferred_probe_add_trigger(struct device *dev, driver_deferred_probe_trigger(); } +static ssize_t state_synced_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + bool val; + + device_lock(dev); + val = dev->state_synced; + device_unlock(dev); + return sprintf(buf, "%u\n", val); +} +static DEVICE_ATTR_RO(state_synced); + static int really_probe(struct device *dev, struct device_driver *drv) { int ret = -EPROBE_DEFER; @@ -562,9 +574,16 @@ re_probe: goto dev_groups_failed; } + if (dev_has_sync_state(dev) && + device_create_file(dev, &dev_attr_state_synced)) { + dev_err(dev, "state_synced sysfs add failed\n"); + goto dev_sysfs_state_synced_failed; + } + if (test_remove) { test_remove = false; + device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus->remove) @@ -594,6 +613,8 @@ re_probe: drv->bus->name, __func__, dev_name(dev), drv->name); goto done; +dev_sysfs_state_synced_failed: + device_remove_groups(dev, drv->dev_groups); dev_groups_failed: if (dev->bus->remove) dev->bus->remove(dev); @@ -1129,6 +1150,7 @@ static void __device_release_driver(struct device *dev, struct device *parent) pm_runtime_put_sync(dev); + device_remove_file(dev, &dev_attr_state_synced); device_remove_groups(dev, drv->dev_groups); if (dev->bus && dev->bus->remove) From 86cf413468982082737a76f87f964974284bd1fb Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 21 May 2020 12:18:00 -0700 Subject: [PATCH 08/24] BACKPORT: driver core: Add waiting_for_supplier sysfs file for devices This would be useful to check if a device is not probing because it's waiting for a supplier to be added and then linked to before it can probe. To reduce sysfs clutter, this file is added only if it can ever be 1. So, if fw_devlink is disabled or set to permissive, this file is not added. Also, this file is removed once the device probes as it's no longer relevant. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200521191800.136035-4-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit da6d647598a6d182eb6a0344a7b14ae005244399) [Conflicts due to missing fw_devlink_is_permissive() and fw_devlink_flags] Signed-off-by: Saravana Kannan Bug: 163090256 Change-Id: Ief4b9e35aff600f2eb88d15839e98a610f1c252f --- .../sysfs-devices-waiting_for_supplier | 17 +++++++++++++ drivers/base/core.c | 24 +++++++++++++++++++ 2 files changed, 41 insertions(+) create mode 100644 Documentation/ABI/testing/sysfs-devices-waiting_for_supplier diff --git a/Documentation/ABI/testing/sysfs-devices-waiting_for_supplier b/Documentation/ABI/testing/sysfs-devices-waiting_for_supplier new file mode 100644 index 000000000000..59d073d20db6 --- /dev/null +++ b/Documentation/ABI/testing/sysfs-devices-waiting_for_supplier @@ -0,0 +1,17 @@ +What: /sys/devices/.../waiting_for_supplier +Date: May 2020 +Contact: Saravana Kannan +Description: + The /sys/devices/.../waiting_for_supplier attribute is only + present when fw_devlink kernel command line option is enabled + and is set to something stricter than "permissive". It is + removed once a device probes successfully (because the + information is no longer relevant). The number read from it (0 + or 1) reflects whether the device is waiting for one or more + suppliers to be added and then linked to using device links + before the device can probe. + + A value of 0 means the device is not waiting for any suppliers + to be added before it can probe. A value of 1 means the device + is waiting for one or more suppliers to be added before it can + probe. diff --git a/drivers/base/core.c b/drivers/base/core.c index cfceaab85028..1e933dee5aba 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -1041,6 +1041,22 @@ static void device_link_drop_managed(struct device_link *link) kref_put(&link->kref, __device_link_del); } +static ssize_t waiting_for_supplier_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + bool val; + + device_lock(dev); + mutex_lock(&wfs_lock); + val = !list_empty(&dev->links.needs_suppliers) + && dev->links.need_for_probe; + mutex_unlock(&wfs_lock); + device_unlock(dev); + return sprintf(buf, "%u\n", val); +} +static DEVICE_ATTR_RO(waiting_for_supplier); + /** * device_links_driver_bound - Update device links after probing its driver. * @dev: Device to update the links for. @@ -1065,6 +1081,7 @@ void device_links_driver_bound(struct device *dev) mutex_lock(&wfs_lock); list_del_init(&dev->links.needs_suppliers); mutex_unlock(&wfs_lock); + device_remove_file(dev, &dev_attr_waiting_for_supplier); device_links_write_lock(); @@ -2128,8 +2145,14 @@ static int device_add_attrs(struct device *dev) goto err_remove_dev_groups; } + error = device_create_file(dev, &dev_attr_waiting_for_supplier); + if (error) + goto err_remove_dev_online; + return 0; + err_remove_dev_online: + device_remove_file(dev, &dev_attr_online); err_remove_dev_groups: device_remove_groups(dev, dev->groups); err_remove_type_groups: @@ -2147,6 +2170,7 @@ static void device_remove_attrs(struct device *dev) struct class *class = dev->class; const struct device_type *type = dev->type; + device_remove_file(dev, &dev_attr_waiting_for_supplier); device_remove_file(dev, &dev_attr_online); device_remove_groups(dev, dev->groups); From d75aed2721d798d5677c65787a3d9bb81d315060 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 16 Jul 2020 14:45:23 -0700 Subject: [PATCH 09/24] UPSTREAM: driver core: Fix sleeping in invalid context during device link deletion Marek and Guenter reported that commit 287905e68dd2 ("driver core: Expose device link details in sysfs") caused sleeping/scheduling while atomic warnings. BUG: sleeping function called from invalid context at kernel/locking/mutex.c:935 in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 12, name: kworker/0:1 2 locks held by kworker/0:1/12: #0: ee8074a8 ((wq_completion)rcu_gp){+.+.}-{0:0}, at: process_one_work+0x174/0x7dc #1: ee921f20 ((work_completion)(&sdp->work)){+.+.}-{0:0}, at: process_one_work+0x174/0x7dc Preemption disabled at: [] srcu_invoke_callbacks+0xc0/0x154 ----- 8< ----- SNIP [] (device_del) from [] (device_unregister+0x24/0x64) [] (device_unregister) from [] (srcu_invoke_callbacks+0xcc/0x154) [] (srcu_invoke_callbacks) from [] (process_one_work+0x234/0x7dc) [] (process_one_work) from [] (worker_thread+0x44/0x51c) [] (worker_thread) from [] (kthread+0x158/0x1a0) [] (kthread) from [] (ret_from_fork+0x14/0x20) Exception stack(0xee921fb0 to 0xee921ff8) This was caused by the device link device being released in the context of srcu_invoke_callbacks(). There is no need to wait till the RCU callback to release the device link device. So release the device earlier and move the call_srcu() into the device release code. That way, the memory will get freed only after the device is released AND the RCU callback is called. Fixes: 287905e68dd2 ("driver core: Expose device link details in sysfs") Reported-by: Marek Szyprowski Reported-by: Guenter Roeck Reported-by: Naresh Kamboju Signed-off-by: Saravana Kannan Tested-by: Marek Szyprowski Tested-by: Guenter Roeck Link: https://lore.kernel.org/r/20200716214523.2924704-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 843e600b8a2b01463c4d873a90b2c2ea8033f1f6) Signed-off-by: Saravana Kannan Bug: 163090256 Change-Id: I3381dcf475ff55ee5971a57968f847eeef36e05b --- drivers/base/core.c | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/drivers/base/core.c b/drivers/base/core.c index 1e933dee5aba..496aedba15b9 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -306,10 +306,34 @@ static struct attribute *devlink_attrs[] = { }; ATTRIBUTE_GROUPS(devlink); +static void device_link_free(struct device_link *link) +{ + while (refcount_dec_not_one(&link->rpm_active)) + pm_runtime_put(link->supplier); + + put_device(link->consumer); + put_device(link->supplier); + kfree(link); +} + +#ifdef CONFIG_SRCU +static void __device_link_free_srcu(struct rcu_head *rhead) +{ + device_link_free(container_of(rhead, struct device_link, rcu_head)); +} + static void devlink_dev_release(struct device *dev) { - kfree(to_devlink(dev)); + struct device_link *link = to_devlink(dev); + + call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); } +#else +static void devlink_dev_release(struct device *dev) +{ + device_link_free(to_devlink(dev)); +} +#endif static struct class devlink_class = { .name = "devlink", @@ -730,22 +754,7 @@ static void device_link_add_missing_supplier_links(void) mutex_unlock(&wfs_lock); } -static void device_link_free(struct device_link *link) -{ - while (refcount_dec_not_one(&link->rpm_active)) - pm_runtime_put(link->supplier); - - put_device(link->consumer); - put_device(link->supplier); - device_unregister(&link->link_dev); -} - #ifdef CONFIG_SRCU -static void __device_link_free_srcu(struct rcu_head *rhead) -{ - device_link_free(container_of(rhead, struct device_link, rcu_head)); -} - static void __device_link_del(struct kref *kref) { struct device_link *link = container_of(kref, struct device_link, kref); @@ -758,7 +767,7 @@ static void __device_link_del(struct kref *kref) list_del_rcu(&link->s_node); list_del_rcu(&link->c_node); - call_srcu(&device_links_srcu, &link->rcu_head, __device_link_free_srcu); + device_unregister(&link->link_dev); } #else /* !CONFIG_SRCU */ static void __device_link_del(struct kref *kref) @@ -773,7 +782,7 @@ static void __device_link_del(struct kref *kref) list_del(&link->s_node); list_del(&link->c_node); - device_link_free(link); + device_unregister(&link->link_dev); } #endif /* !CONFIG_SRCU */ From 660cd67d1e3efc46505136a0a861102721fee599 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 24 Jul 2020 11:05:22 -0700 Subject: [PATCH 10/24] UPSTREAM: driver core: Change delimiter in devlink device's name to "--" The devlink device name is of the form "supplier:consumer". But ":" is fairly common in device names and makes it visually hard to distinguish supplier and consumer. So, replace it with "--" to make it easier. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200724180523.1393383-1-saravanak@google.com Signed-off-by: Greg Kroah-Hartman (cherry picked from commit 90b109d50da09ddaa179732c01ccba7f759c125d) Signed-off-by: Saravana Kannan Bug: 163090256 Change-Id: Ibda7db293de6c2e0d9f963e61f2cec0321c82e09 --- Documentation/ABI/testing/sysfs-class-devlink | 2 +- drivers/base/core.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-class-devlink b/Documentation/ABI/testing/sysfs-class-devlink index 3a24973abb83..64791b65c9a3 100644 --- a/Documentation/ABI/testing/sysfs-class-devlink +++ b/Documentation/ABI/testing/sysfs-class-devlink @@ -4,7 +4,7 @@ Contact: Saravana Kannan Description: Provide a place in sysfs for the device link objects in the kernel at any given time. The name of a device link directory, - denoted as ... above, is of the form : + denoted as ... above, is of the form -- where is the supplier device name and is the consumer device name. diff --git a/drivers/base/core.c b/drivers/base/core.c index 496aedba15b9..5b53e35775d2 100644 --- a/drivers/base/core.c +++ b/drivers/base/core.c @@ -622,7 +622,7 @@ struct device_link *device_link_add(struct device *consumer, link->link_dev.class = &devlink_class; device_set_pm_not_required(&link->link_dev); - dev_set_name(&link->link_dev, "%s:%s", + dev_set_name(&link->link_dev, "%s--%s", dev_name(supplier), dev_name(consumer)); if (device_register(&link->link_dev)) { put_device(consumer); From 30e88e79b63c2d78f53ae5c84ea0114677dcbaea Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Wed, 1 Apr 2020 15:52:03 -0700 Subject: [PATCH 11/24] UPSTREAM: of: property: Add device link support for extcon Add support for creating device links out of more DT properties. Cc: MyungJoo Ham Cc: Chanwoo Choi Signed-off-by: Saravana Kannan Signed-off-by: Rob Herring (cherry picked from commit 78056e701c61132d15e0942e415926a6393fcf17) Signed-off-by: Saravana Kannan Bug: 163091301 Change-Id: Ifbf40d33788e59003a80c918098b08e94257d350 --- drivers/of/property.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index 933294195ec3..c96b0be78fc5 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1192,6 +1192,7 @@ DEFINE_SIMPLE_PROP(interrupt_parent, "interrupt-parent", NULL) DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells") +DEFINE_SIMPLE_PROP(extcon, "extcon", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells") @@ -1216,6 +1217,7 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_dmas, }, { .parse_prop = parse_power_domains, }, { .parse_prop = parse_hwlocks, }, + { .parse_prop = parse_extcon, }, { .parse_prop = parse_regulators, }, { .parse_prop = parse_gpio, }, { .parse_prop = parse_gpios, }, From 59356725e028cb9fb87d3d00d0a0191b95a9893f Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 24 Jul 2020 16:44:14 -0700 Subject: [PATCH 12/24] UPSTREAM: of: property: Add device link support for multiple DT bindings Add support for creating device links out of the following DT bindings: - interrupts-extended - nvmem-cells - phys - wakeup-parent Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200724234415.1651639-1-saravanak@google.com Signed-off-by: Rob Herring (cherry picked from commit 53e6a671f70abc2c30fa94ae33c0f1c2fe24985e) Signed-off-by: Saravana Kannan Bug: 163091301 Bug: 160823849 Change-Id: I99c29fd21b7e559db9fb9fa79ea24a7deefd717f --- drivers/of/property.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index c96b0be78fc5..230d90436ff7 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1193,6 +1193,11 @@ DEFINE_SIMPLE_PROP(dmas, "dmas", "#dma-cells") DEFINE_SIMPLE_PROP(power_domains, "power-domains", "#power-domain-cells") DEFINE_SIMPLE_PROP(hwlocks, "hwlocks", "#hwlock-cells") DEFINE_SIMPLE_PROP(extcon, "extcon", NULL) +DEFINE_SIMPLE_PROP(interrupts_extended, "interrupts-extended", + "#interrupt-cells") +DEFINE_SIMPLE_PROP(nvmem_cells, "nvmem-cells", NULL) +DEFINE_SIMPLE_PROP(phys, "phys", "#phy-cells") +DEFINE_SIMPLE_PROP(wakeup_parent, "wakeup-parent", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells") @@ -1218,6 +1223,10 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_power_domains, }, { .parse_prop = parse_hwlocks, }, { .parse_prop = parse_extcon, }, + { .parse_prop = parse_interrupts_extended, }, + { .parse_prop = parse_nvmem_cells, }, + { .parse_prop = parse_phys, }, + { .parse_prop = parse_wakeup_parent, }, { .parse_prop = parse_regulators, }, { .parse_prop = parse_gpio, }, { .parse_prop = parse_gpios, }, From 36f846bb22b7b6b97634790c45706036f4d4f1a7 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Fri, 24 Jul 2020 16:44:15 -0700 Subject: [PATCH 13/24] UPSTREAM: of: property: Add device link support for pinctrl-0 through pinctrl-8 Add support for pinctrl-0 through pinctrl-8 explicitly instead of trying to add support for pinctrl-%d properties. Of all the pinctrl-* properties in dts files (20322), only 47% (9531) are pinctrl-%d properties. Of all the pinctrl-%d properties, 99.5% (9486) are made up of pinctrl-[0-2]. 'pinctrl-8' is the current maximum found in dts files. Trying to parse all pinctrl-* properties and checking for pinctrl-%d is unnecessarily complicated. So, just add support for pinctrl-[0-8] for now. In the unlikely event we ever exceed pinctrl-8, we can come back and improve this. Signed-off-by: Saravana Kannan Link: https://lore.kernel.org/r/20200724234415.1651639-2-saravanak@google.com Signed-off-by: Rob Herring (cherry picked from commit fb820b494acb70e3a20e50935118239c7e5c94dd) Signed-off-by: Saravana Kannan Bug: 163091301 Change-Id: I1ad8ba1b784a59a4230ac04331139c13da5d32ed --- drivers/of/property.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/drivers/of/property.c b/drivers/of/property.c index 230d90436ff7..277d2d854ad5 100644 --- a/drivers/of/property.c +++ b/drivers/of/property.c @@ -1198,6 +1198,15 @@ DEFINE_SIMPLE_PROP(interrupts_extended, "interrupts-extended", DEFINE_SIMPLE_PROP(nvmem_cells, "nvmem-cells", NULL) DEFINE_SIMPLE_PROP(phys, "phys", "#phy-cells") DEFINE_SIMPLE_PROP(wakeup_parent, "wakeup-parent", NULL) +DEFINE_SIMPLE_PROP(pinctrl0, "pinctrl-0", NULL) +DEFINE_SIMPLE_PROP(pinctrl1, "pinctrl-1", NULL) +DEFINE_SIMPLE_PROP(pinctrl2, "pinctrl-2", NULL) +DEFINE_SIMPLE_PROP(pinctrl3, "pinctrl-3", NULL) +DEFINE_SIMPLE_PROP(pinctrl4, "pinctrl-4", NULL) +DEFINE_SIMPLE_PROP(pinctrl5, "pinctrl-5", NULL) +DEFINE_SIMPLE_PROP(pinctrl6, "pinctrl-6", NULL) +DEFINE_SIMPLE_PROP(pinctrl7, "pinctrl-7", NULL) +DEFINE_SIMPLE_PROP(pinctrl8, "pinctrl-8", NULL) DEFINE_SUFFIX_PROP(regulators, "-supply", NULL) DEFINE_SUFFIX_PROP(gpio, "-gpio", "#gpio-cells") DEFINE_SUFFIX_PROP(gpios, "-gpios", "#gpio-cells") @@ -1227,6 +1236,15 @@ static const struct supplier_bindings of_supplier_bindings[] = { { .parse_prop = parse_nvmem_cells, }, { .parse_prop = parse_phys, }, { .parse_prop = parse_wakeup_parent, }, + { .parse_prop = parse_pinctrl0, }, + { .parse_prop = parse_pinctrl1, }, + { .parse_prop = parse_pinctrl2, }, + { .parse_prop = parse_pinctrl3, }, + { .parse_prop = parse_pinctrl4, }, + { .parse_prop = parse_pinctrl5, }, + { .parse_prop = parse_pinctrl6, }, + { .parse_prop = parse_pinctrl7, }, + { .parse_prop = parse_pinctrl8, }, { .parse_prop = parse_regulators, }, { .parse_prop = parse_gpio, }, { .parse_prop = parse_gpios, }, From 221bf83690f075f6aa06e7641e57da7442e17f45 Mon Sep 17 00:00:00 2001 From: Saravana Kannan Date: Thu, 6 Aug 2020 19:46:19 -0700 Subject: [PATCH 14/24] ANDROID: Update ABI xml Leaf changes summary: 642 artifacts changed (2214 filtered out) Changed leaf types summary: 1 leaf type changed Removed/Changed/Added functions summary: 0 Removed, 632 Changed (2201 filtered out), 0 Added function Removed/Changed/Added variables summary: 0 Removed, 9 Changed (13 filtered out), 0 Added variable 632 functions with some sub-type change: ... lots of CRC changes ... 'struct device_link at device.h:1139:1' changed: type size changed from 704 to 7808 (in bits) 1 data member insertion: 'device device_link::link_dev', at offset 384 (in bits) at device.h:1366:1 there are data member changes: 'device_link_state device_link::status' offset changed from 384 to 7488 (in bits) (by +7104 bits) 'u32 device_link::flags' offset changed from 416 to 7520 (in bits) (by +7104 bits) 'refcount_t device_link::rpm_active' offset changed from 448 to 7552 (in bits) (by +7104 bits) 'kref device_link::kref' offset changed from 480 to 7584 (in bits) (by +7104 bits) 'callback_head device_link::callback_head' offset changed from 512 to 7616 (in bits) (by +7104 bits) 'bool device_link::supplier_preactivated' offset changed from 640 to 7744 (in bits) (by +7104 bits) 2 impacted interfaces Bug: 163090256 Bug: 157691602 Change-Id: Ia4d75e7d43fb546a88e682c3c66aac0bd47304fc Signed-off-by: Saravana Kannan --- android/abi_gki_aarch64.xml | 7046 ++++++++++++++++++----------------- 1 file changed, 3539 insertions(+), 3507 deletions(-) diff --git a/android/abi_gki_aarch64.xml b/android/abi_gki_aarch64.xml index d32a00e62cb1..c4fdc931507a 100644 --- a/android/abi_gki_aarch64.xml +++ b/android/abi_gki_aarch64.xml @@ -3,12 +3,12 @@ - + - - + + - + @@ -22,32 +22,32 @@ - - - - - - - - - - - + + + + + + + + + + + - - - - + + + + - - + + - + - + @@ -55,63 +55,63 @@ - - - - - - - - - - - - - + + + + + + + + + + + + + - - - - - - - - - + + + + + + + + + - + - - - + + + - - + + - + - - - - - + + + + + - - + + - + - + @@ -122,130 +122,130 @@ - - - - - - + + + + + + - - - - + + + + - - + + - - - - + + + + - - - - - - - - - - - - - - + + + + + + + + + + + + + + - - + + - - - + + + - - + + - - - - + + + + - + - - - - - + + + + + - + - + - - - - - + + + + + - - - - + + + + - + - + - - + + - + - + - - - + + + - + - + - - - - - - + + + + + + @@ -272,15 +272,15 @@ - - - + + + - + @@ -288,285 +288,285 @@ - + - - - - + + + + - + - - - - + + + + - + - + - - - - - - - - - - + + + + + + + + + + - - - - + + + + - - - - - - - - - - - + + + + + + + + + + + - - - - + + + + - - - + + + - - - - - - - - - - - - - + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - + - - - - - - + + + + + + - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - + - - - - - + + + + + - - - - - - - - - + + + + + + + + + - + - - - - - - - + + + + + + + - - + + - + - - - - - - - + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - + + - + - - - - - - - - - + + + + + + + + + - + - - - + + + @@ -574,73 +574,73 @@ - + - - + + - + - + - + - - - - - - - - + + + + + + + + - + - - + + - + - - - - + + + + - - + + - - + + - - + + - - + + @@ -652,66 +652,66 @@ - - - - + + + + - + - + - - + + - + - - - - - + + + + + - + - + - + - - - + + + - - - - - + + + + + - + - - - + + + - + @@ -723,240 +723,240 @@ - - - - - + + + + + - + - - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + @@ -965,38 +965,38 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -1011,20 +1011,20 @@ - - - - - - - + + + + + + + - + - - - + + + @@ -1033,13 +1033,13 @@ - - - - - - - + + + + + + + @@ -1051,244 +1051,244 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - + + + + + + + - - - - - + + + + + - + - - - - + + + + - - - - + + + + - - - - - - - - - - - - - - + + + + + + + + + + + + + + - - + + - - + + - - - - - - + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - - + + + + + + + - - - - - - - + + + + + + + - - - - + + + + - - - + + + - - + + - - - - + + + + @@ -1297,154 +1297,154 @@ - - + + - - - - - + + + + + - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + - + - - - - - - - - - + + + + + + + + + - - - - - - + + + + + + - - - - + + + + - - + + - - + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - + + + - + - + - + - + - + - + - - + + - - - - - - - - + + + + + + + + @@ -1458,125 +1458,125 @@ - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + - - - - - - - - - - - + + + + + + + + + + + - + - - - - + + + + - - - + + + - - - - - - - - - - - - - + + + + + + + + + + + + + - - - - - + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - + + - - + + - - - - + + + + - + @@ -1592,58 +1592,58 @@ - - + + - - + + - - - - - - - - - - - + + + + + + + + + + + - - - - - - + + + + + + - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + - - - - - - + + + + + + @@ -1656,10 +1656,10 @@ - - - - + + + + @@ -1668,268 +1668,268 @@ - + - - + + - - - + + + - - - - - - - - - + + + + + + + + + - - - + + + - - - - - - + + + + + + - - + + - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + - - - - - - - - - - - - + + + + + + + + + + + + - - - - - - - - - + + + + + + + + + - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + - - - - - + + + + + - - - + + + - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + - - - + + + - + - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - - - - - - - - + + + + + + + + - - + + - - - - - - - - - + + + + + + + + + - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - + + + + + + + + + + + + + + - + - - + + - + - - - + + + - - - - + + + + - - - - + + + + - + @@ -1938,28 +1938,28 @@ - - + + - - - - - - - + + + + + + + - - - - - - - + + + + + + + @@ -1971,8 +1971,8 @@ - - + + @@ -2029,78 +2029,78 @@ - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + - - + + - + - - + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -2122,96 +2122,96 @@ - - - - - - - - - + + + + + + + + + - - - - - - - - - - - - - + + + + + + + + + + + + + - - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - + + + + + + @@ -2220,216 +2220,216 @@ - - - - - - - - - + + + + + + + + + - - + + - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - + + + + + + + + + + + + + - + - + - - + + - - - + + + - - - + + + - - - - + + + + - + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + - + @@ -2437,173 +2437,173 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - + + + + + + + + + - - - - - + + + + + - + - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -2611,56 +2611,56 @@ - - - - - - - - - - - - + + + + + + + + + + + + - - + + - + - - - - + + + + - - - + + + - - + + - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + - + @@ -2678,28 +2678,28 @@ - - - - - - - - + + + + + + + + - - - - - - - - - + + + + + + + + + - + @@ -2721,9 +2721,9 @@ - - - + + + @@ -2731,124 +2731,124 @@ - - - - - + + + + + - + - + - - - + + + - - + + - + - + - - - + + + - - - - + + + + - - - - - - + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - + + + + + - + - - + + @@ -2859,148 +2859,148 @@ - - - - - - - - - - - + + + + + + + + + + + - - - - - - - - - - - + + + + + + + + + + + - - + + - + - + - - + + - + - - - + + + - - - - + + + + - - - + + + - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + - - - - - - - + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + @@ -3014,34 +3014,34 @@ - - - - - - - - - - - - - - + + + + + + + + + + + + + + - - - - - - + + + + + + - - - + + + @@ -3060,79 +3060,79 @@ - + - + - - - + + + - - - - - - - - + + + + + + + + - - - + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -3143,226 +3143,226 @@ - - - - - - - - - - - - + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + - - - - - + + + + + - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + - + - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + @@ -3371,10 +3371,10 @@ - + - + @@ -3382,7 +3382,7 @@ - + @@ -3404,25 +3404,25 @@ - - - - + + + + - - + + - - + + - - - + + + @@ -3441,49 +3441,49 @@ - - - - - + + + + + - - - - - - - - - - + + + + + + + + + + - + - - - - - - + + + + + + - + - - - - + + + + @@ -3500,193 +3500,193 @@ - - + + - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + - - + + - - - - - - - - + + + + + + + + - - + + - + - + - + - - - - - - - - + + + + + + + + - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + - - - - - - + + + + + + - - + + - + - + - - + + - - + + - - - + + + - - - - - - - - + + + + + + + + - + - - - - - - - - - - + + + + + + + + + + - - - + + + - - + + - - - + + + - - - - + + + + - + @@ -3699,122 +3699,122 @@ - - - - - + + + + + - - - - - - - - - - - - - - + + + + + + + + + + + + + + - - - - - - - - + + + + + + + + - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + - - - - - - - - - + + + + + + + + + - - - - - - + + + + + + - - - - - - + + + + + + - - - - - - + + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + - + @@ -3822,57 +3822,57 @@ - - - + + + - - - + + + - - - - + + + + - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + - - - + + + - - - + + + - - + + - - + + @@ -3886,95 +3886,95 @@ - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + - - - - - - - - - - - - + + + + + + + + + + + + - - - - - + + + + + - - - - - - - - - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + + + + + + + + + - - - + + + - + - - - + + + - - + + - - + + @@ -3988,27 +3988,27 @@ - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + - - + + @@ -4017,43 +4017,43 @@ - + - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + - - - - - - - - - - - - - - - - - - - + + + + + + + + + + + + + + + + + + + @@ -4078,9 +4078,9 @@ - + - + @@ -4093,7 +4093,7 @@ - + @@ -4111,31 +4111,31 @@ - - + + - - + + - + - + - + - - + + @@ -4153,9 +4153,9 @@ - + - + @@ -4165,13 +4165,13 @@ - - + + - - - + + + @@ -4186,14 +4186,14 @@ - + - + - + @@ -21678,51 +21678,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -21738,10 +21693,6 @@ - - - - @@ -21886,91 +21837,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -22000,13 +21866,186 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + - - + + + + + + - - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -26032,7 +26071,7 @@ - + @@ -26116,7 +26155,7 @@ - + @@ -35071,45 +35110,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -35212,6 +35212,55 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -35320,43 +35369,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -35426,35 +35438,35 @@ - - + + - - + + - - + + - - + + - - - - + + + + - - - + + + @@ -35483,14 +35495,6 @@ - - - - - - - - @@ -35832,7 +35836,6 @@ - @@ -36852,13 +36855,13 @@ - + - + @@ -38946,7 +38949,7 @@ - + @@ -39038,7 +39041,7 @@ - + @@ -39617,17 +39620,17 @@ - + - + - + @@ -41321,7 +41324,7 @@ - + @@ -41333,7 +41336,7 @@ - + @@ -41453,7 +41456,7 @@ - + @@ -41921,7 +41924,7 @@ - + @@ -41933,7 +41936,7 @@ - + @@ -44308,7 +44311,7 @@ - + @@ -44454,7 +44457,7 @@ - + @@ -46436,13 +46439,13 @@ - + - + @@ -47171,7 +47174,7 @@ - + @@ -47219,7 +47222,7 @@ - + @@ -47228,7 +47231,7 @@ - + @@ -47239,7 +47242,7 @@ - + @@ -49214,7 +49217,7 @@ - + @@ -49878,7 +49881,7 @@ - + @@ -50859,13 +50862,13 @@ - + - + @@ -51376,7 +51379,6 @@ - @@ -51400,7 +51402,7 @@ - + @@ -51408,7 +51410,7 @@ - + @@ -51637,7 +51639,7 @@ - + @@ -51651,17 +51653,6 @@ - - - - - - - - - - - @@ -51858,6 +51849,17 @@ + + + + + + + + + + + @@ -55023,6 +55025,17 @@ + + + + + + + + + + + @@ -57114,17 +57127,6 @@ - - - - - - - - - - - @@ -58569,20 +58571,6 @@ - - - - - - - - - - - - - - @@ -60336,7 +60324,6 @@ - @@ -61411,6 +61398,17 @@ + + + + + + + + + + + @@ -61871,7 +61869,7 @@ - + @@ -63769,36 +63767,39 @@ - + - + - + - + - + - + - - + + - - + + - - + + - - + + - - + + + + + @@ -63853,7 +63854,7 @@ - + @@ -64668,7 +64669,7 @@ - + @@ -65241,7 +65242,7 @@ - + @@ -66941,17 +66942,17 @@ - + - + - + @@ -67890,8 +67891,8 @@ - - + + @@ -72038,7 +72039,7 @@ - + @@ -75626,7 +75627,7 @@ - + @@ -75653,7 +75654,7 @@ - + @@ -75755,7 +75756,7 @@ - + @@ -78466,7 +78467,7 @@ - + @@ -80235,15 +80236,15 @@ - + - + - + @@ -80670,7 +80671,7 @@ - + @@ -83717,7 +83718,7 @@ - + @@ -84353,6 +84354,25 @@ + + + + + + + + + + + + + + + + + + + @@ -84992,7 +85012,7 @@ - + @@ -85010,13 +85030,13 @@ - + - + @@ -85070,7 +85090,7 @@ - + @@ -85468,7 +85488,7 @@ - + @@ -86336,7 +86356,7 @@ - + @@ -88264,7 +88284,7 @@ - + @@ -88280,7 +88300,7 @@ - + @@ -88288,7 +88308,7 @@ - + @@ -88316,6 +88336,25 @@ + + + + + + + + + + + + + + + + + + + @@ -88870,7 +88909,7 @@ - + @@ -88892,8 +88931,8 @@ - - + + @@ -89359,159 +89398,159 @@ - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + @@ -89667,7 +89706,7 @@ - + @@ -89993,7 +90032,7 @@ - + @@ -90011,7 +90050,7 @@ - + @@ -91146,10 +91185,10 @@ - + - + @@ -92498,7 +92537,7 @@ - + @@ -92865,7 +92904,7 @@ - + @@ -94765,7 +94804,7 @@ - + @@ -96856,27 +96895,27 @@ - + - + - + - + - + - + - + - + @@ -97577,7 +97616,7 @@ - + @@ -97858,7 +97897,7 @@ - + @@ -97943,7 +97982,7 @@ - + @@ -98938,7 +98977,7 @@ - + @@ -100475,7 +100514,7 @@ - + @@ -101908,7 +101947,7 @@ - + @@ -101938,7 +101977,7 @@ - + @@ -102023,7 +102062,7 @@ - + @@ -102191,7 +102230,7 @@ - + @@ -102470,17 +102509,6 @@ - - - - - - - - - - - @@ -102829,17 +102857,6 @@ - - - - - - - - - - - @@ -103390,7 +103407,7 @@ - + @@ -103401,7 +103418,7 @@ - + @@ -103488,25 +103505,6 @@ - - - - - - - - - - - - - - - - - - - @@ -104024,7 +104022,7 @@ - + @@ -104104,7 +104102,7 @@ - + @@ -104241,7 +104239,7 @@ - + @@ -104304,7 +104302,7 @@ - + @@ -104865,6 +104863,36 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -104888,7 +104916,7 @@ - + @@ -105091,6 +105119,25 @@ + + + + + + + + + + + + + + + + + + + @@ -105132,7 +105179,7 @@ - + @@ -105654,8 +105701,8 @@ - - + + @@ -105822,7 +105869,7 @@ - + @@ -105830,7 +105877,7 @@ - + @@ -105852,7 +105899,7 @@ - + @@ -105860,7 +105907,7 @@ - + @@ -105885,7 +105932,7 @@ - + @@ -106752,10 +106799,10 @@ - + - + @@ -106924,7 +106971,7 @@ - + @@ -106934,7 +106981,7 @@ - + @@ -107640,7 +107687,7 @@ - + @@ -107648,7 +107695,7 @@ - + @@ -107664,7 +107711,7 @@ - + @@ -107740,7 +107787,7 @@ - + @@ -108023,7 +108070,7 @@ - + @@ -108032,7 +108079,7 @@ - + @@ -108783,62 +108830,6 @@ - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - @@ -108960,10 +108951,10 @@ - + - + @@ -109116,8 +109107,6 @@ - - @@ -109411,14 +109400,6 @@ - - - - - - - - @@ -109440,10 +109421,10 @@ - + - + @@ -109451,14 +109432,6 @@ - - - - - - - - @@ -109476,7 +109449,7 @@ - + @@ -109484,7 +109457,7 @@ - + @@ -109849,17 +109822,6 @@ - - - - - - - - - - - @@ -109969,7 +109931,7 @@ - + @@ -109988,7 +109950,7 @@ - + @@ -110391,7 +110353,7 @@ - + @@ -110403,6 +110365,41 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -110424,21 +110421,45 @@ - + - + - - - - - - - + - + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + @@ -112027,7 +112048,7 @@ - + @@ -112057,7 +112078,7 @@ - + @@ -112076,10 +112097,10 @@ - + - + @@ -115171,7 +115192,7 @@ - + @@ -115179,7 +115200,7 @@ - + @@ -115187,7 +115208,7 @@ - + @@ -115195,7 +115216,7 @@ - + @@ -115217,7 +115238,7 @@ - + @@ -115225,7 +115246,7 @@ - + @@ -115236,7 +115257,7 @@ - + @@ -116068,10 +116089,10 @@ - + - + @@ -116079,7 +116100,7 @@ - + @@ -116125,7 +116146,7 @@ - + @@ -116207,10 +116228,10 @@ - + - + @@ -116786,7 +116807,7 @@ - + @@ -116938,6 +116959,17 @@ + + + + + + + + + + + @@ -117030,7 +117062,7 @@ - + @@ -117082,7 +117114,7 @@ - + @@ -117142,7 +117174,7 @@ - + @@ -117876,17 +117908,17 @@ - + - + - + @@ -117894,7 +117926,7 @@ - + @@ -117922,7 +117954,7 @@ - + @@ -117939,7 +117971,7 @@ - + @@ -117967,22 +117999,22 @@ - + - + - + - + - + @@ -117990,7 +118022,7 @@ - + @@ -117998,7 +118030,7 @@ - + @@ -118006,7 +118038,7 @@ - + @@ -118029,7 +118061,7 @@ - + @@ -118107,13 +118139,13 @@ - + - + @@ -119021,7 +119053,7 @@ - + @@ -119189,7 +119221,7 @@ - + @@ -119873,7 +119905,7 @@ - + @@ -119990,10 +120022,10 @@ - + - + @@ -120078,10 +120110,10 @@ - + - + @@ -120951,7 +120983,7 @@ - + @@ -122160,7 +122192,7 @@ - + @@ -122775,15 +122807,15 @@ - + - - - - + + + + @@ -122791,6 +122823,6 @@ From c15a77bdda2c4f8acaa3e436128630a81f904ae7 Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Fri, 10 Jul 2020 15:23:19 +0200 Subject: [PATCH 15/24] random32: update the net random state on interrupt and activity commit f227e3ec3b5cad859ad15666874405e8c1bbc1d4 upstream. This modifies the first 32 bits out of the 128 bits of a random CPU's net_rand_state on interrupt or CPU activity to complicate remote observations that could lead to guessing the network RNG's internal state. Note that depending on some network devices' interrupt rate moderation or binding, this re-seeding might happen on every packet or even almost never. In addition, with NOHZ some CPUs might not even get timer interrupts, leaving their local state rarely updated, while they are running networked processes making use of the random state. For this reason, we also perform this update in update_process_times() in order to at least update the state when there is user or system activity, since it's the only case we care about. Reported-by: Amit Klein Suggested-by: Linus Torvalds Cc: Eric Dumazet Cc: "Jason A. Donenfeld" Cc: Andy Lutomirski Cc: Kees Cook Cc: Thomas Gleixner Cc: Peter Zijlstra Cc: Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- drivers/char/random.c | 1 + include/linux/random.h | 3 +++ kernel/time/timer.c | 8 ++++++++ lib/random32.c | 2 +- 4 files changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/char/random.c b/drivers/char/random.c index 8ff28c14af7e..e877c20e0ee0 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1330,6 +1330,7 @@ void add_interrupt_randomness(int irq, int irq_flags) fast_mix(fast_pool); add_interrupt_bench(cycles); + this_cpu_add(net_rand_state.s1, fast_pool->pool[cycles & 3]); if (unlikely(crng_init == 0)) { if ((fast_pool->count >= 64) && diff --git a/include/linux/random.h b/include/linux/random.h index f189c927fdea..4d080e5ef6eb 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,6 +9,7 @@ #include #include +#include #include @@ -117,6 +118,8 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; +DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; + u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); diff --git a/kernel/time/timer.c b/kernel/time/timer.c index 1e9b81a930c0..a3ae244b1bcd 100644 --- a/kernel/time/timer.c +++ b/kernel/time/timer.c @@ -43,6 +43,7 @@ #include #include #include +#include #include #include @@ -1742,6 +1743,13 @@ void update_process_times(int user_tick) scheduler_tick(); if (IS_ENABLED(CONFIG_POSIX_TIMERS)) run_posix_cpu_timers(); + + /* The current CPU might make use of net randoms without receiving IRQs + * to renew them often enough. Let's update the net_rand_state from a + * non-constant value that's not affine to the number of calls to make + * sure it's updated when there's some activity (we don't care in idle). + */ + this_cpu_add(net_rand_state.s1, rol32(jiffies, 24) + user_tick); } /** diff --git a/lib/random32.c b/lib/random32.c index 763b920a6206..c4d317be2997 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void) } #endif -static DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; /** * prandom_u32_state - seeded pseudo-random number generator. From 50bf89625bbaf6c29ba66a8b2b6faf80256a2466 Mon Sep 17 00:00:00 2001 From: Grygorii Strashko Date: Thu, 30 Jul 2020 22:05:01 +0300 Subject: [PATCH 16/24] ARM: percpu.h: fix build error MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit aa54ea903abb02303bf55855fb51e3fcee135d70 upstream. Fix build error for the case: defined(CONFIG_SMP) && !defined(CONFIG_CPU_V6) config: keystone_defconfig CC arch/arm/kernel/signal.o In file included from ../include/linux/random.h:14, from ../arch/arm/kernel/signal.c:8: ../arch/arm/include/asm/percpu.h: In function ‘__my_cpu_offset’: ../arch/arm/include/asm/percpu.h:29:34: error: ‘current_stack_pointer’ undeclared (first use in this function); did you mean ‘user_stack_pointer’? : "Q" (*(const unsigned long *)current_stack_pointer)); ^~~~~~~~~~~~~~~~~~~~~ user_stack_pointer Fixes: f227e3ec3b5c ("random32: update the net random state on interrupt and activity") Signed-off-by: Grygorii Strashko Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- arch/arm/include/asm/percpu.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/arm/include/asm/percpu.h b/arch/arm/include/asm/percpu.h index f44f448537f2..1a3eedbac4a2 100644 --- a/arch/arm/include/asm/percpu.h +++ b/arch/arm/include/asm/percpu.h @@ -5,6 +5,8 @@ #ifndef _ASM_ARM_PERCPU_H_ #define _ASM_ARM_PERCPU_H_ +#include + /* * Same as asm-generic/percpu.h, except that we store the per cpu offset * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7 From 7471f3228e7ad9641a8b2330960d27eb00af0d0f Mon Sep 17 00:00:00 2001 From: Willy Tarreau Date: Thu, 30 Jul 2020 07:59:24 +0200 Subject: [PATCH 17/24] random: fix circular include dependency on arm64 after addition of percpu.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit commit 1c9df907da83812e4f33b59d3d142c864d9da57f upstream. Daniel Díaz and Kees Cook independently reported that commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity") broke arm64 due to a circular dependency on include files since the addition of percpu.h in random.h. The correct fix would definitely be to move all the prandom32 stuff out of random.h but for backporting, a smaller solution is preferred. This one replaces linux/percpu.h with asm/percpu.h, and this fixes the problem on x86_64, arm64, arm, and mips. Note that moving percpu.h around didn't change anything and that removing it entirely broke differently. When backporting, such options might still be considered if this patch fails to help. [ It turns out that an alternate fix seems to be to just remove the troublesome remove from the arm64 that causes the circular dependency. But we might as well do the whole belt-and-suspenders thing, and minimize inclusion in too. Either will fix the problem, and both are good changes. - Linus ] Reported-by: Daniel Díaz Reported-by: Kees Cook Tested-by: Marc Zyngier Fixes: f227e3ec3b5c Cc: Stephen Rothwell Signed-off-by: Willy Tarreau Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/random.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/random.h b/include/linux/random.h index 4d080e5ef6eb..e5d63f875c02 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,7 +9,7 @@ #include #include -#include +#include #include From c131009987f2501642e3b3fa328ef6c65cbbc72a Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 29 Jul 2020 19:11:00 -0700 Subject: [PATCH 18/24] random32: remove net_rand_state from the latent entropy gcc plugin commit 83bdc7275e6206f560d247be856bceba3e1ed8f2 upstream. It turns out that the plugin right now ends up being really unhappy about the change from 'static' to 'extern' storage that happened in commit f227e3ec3b5c ("random32: update the net random state on interrupt and activity"). This is probably a trivial fix for the latent_entropy plugin, but for now, just remove net_rand_state from the list of things the plugin worries about. Reported-by: Stephen Rothwell Cc: Emese Revfy Cc: Kees Cook Cc: Willy Tarreau Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/random.h | 2 +- lib/random32.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/linux/random.h b/include/linux/random.h index e5d63f875c02..2625c0deda47 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -118,7 +118,7 @@ struct rnd_state { __u32 s1, s2, s3, s4; }; -DECLARE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DECLARE_PER_CPU(struct rnd_state, net_rand_state); u32 prandom_u32_state(struct rnd_state *state); void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); diff --git a/lib/random32.c b/lib/random32.c index c4d317be2997..3d749abb9e80 100644 --- a/lib/random32.c +++ b/lib/random32.c @@ -48,7 +48,7 @@ static inline void prandom_state_selftest(void) } #endif -DEFINE_PER_CPU(struct rnd_state, net_rand_state) __latent_entropy; +DEFINE_PER_CPU(struct rnd_state, net_rand_state); /** * prandom_u32_state - seeded pseudo-random number generator. From f06d60ff794adeca67795dd12a8085cc921c4279 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 31 Jul 2020 07:51:14 +0200 Subject: [PATCH 19/24] random32: move the pseudo-random 32-bit definitions to prandom.h commit c0842fbc1b18c7a044e6ff3e8fa78bfa822c7d1a upstream. The addition of percpu.h to the list of includes in random.h revealed some circular dependencies on arm64 and possibly other platforms. This include was added solely for the pseudo-random definitions, which have nothing to do with the rest of the definitions in this file but are still there for legacy reasons. This patch moves the pseudo-random parts to linux/prandom.h and the percpu.h include with it, which is now guarded by _LINUX_PRANDOM_H and protected against recursive inclusion. A further cleanup step would be to remove this from entirely, and make people who use the prandom infrastructure include just the new header file. That's a bit of a churn patch, but grepping for "prandom_" and "next_pseudo_random32" "struct rnd_state" should catch most users. But it turns out that that nice cleanup step is fairly painful, because a _lot_ of code currently seems to depend on the implicit include of , which can currently come in a lot of ways, including such fairly core headfers as . So the "nice cleanup" part may or may never happen. Fixes: 1c9df907da83 ("random: fix circular include dependency on arm64 after addition of percpu.h") Tested-by: Guenter Roeck Acked-by: Willy Tarreau Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/prandom.h | 78 +++++++++++++++++++++++++++++++++++++++++ include/linux/random.h | 66 +++------------------------------- 2 files changed, 82 insertions(+), 62 deletions(-) create mode 100644 include/linux/prandom.h diff --git a/include/linux/prandom.h b/include/linux/prandom.h new file mode 100644 index 000000000000..aa16e6468f91 --- /dev/null +++ b/include/linux/prandom.h @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * include/linux/prandom.h + * + * Include file for the fast pseudo-random 32-bit + * generation. + */ +#ifndef _LINUX_PRANDOM_H +#define _LINUX_PRANDOM_H + +#include +#include + +u32 prandom_u32(void); +void prandom_bytes(void *buf, size_t nbytes); +void prandom_seed(u32 seed); +void prandom_reseed_late(void); + +struct rnd_state { + __u32 s1, s2, s3, s4; +}; + +DECLARE_PER_CPU(struct rnd_state, net_rand_state); + +u32 prandom_u32_state(struct rnd_state *state); +void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); +void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); + +#define prandom_init_once(pcpu_state) \ + DO_ONCE(prandom_seed_full_state, (pcpu_state)) + +/** + * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) + * @ep_ro: right open interval endpoint + * + * Returns a pseudo-random number that is in interval [0, ep_ro). Note + * that the result depends on PRNG being well distributed in [0, ~0U] + * u32 space. Here we use maximally equidistributed combined Tausworthe + * generator, that is, prandom_u32(). This is useful when requesting a + * random index of an array containing ep_ro elements, for example. + * + * Returns: pseudo-random number in interval [0, ep_ro) + */ +static inline u32 prandom_u32_max(u32 ep_ro) +{ + return (u32)(((u64) prandom_u32() * ep_ro) >> 32); +} + +/* + * Handle minimum values for seeds + */ +static inline u32 __seed(u32 x, u32 m) +{ + return (x < m) ? x + m : x; +} + +/** + * prandom_seed_state - set seed for prandom_u32_state(). + * @state: pointer to state structure to receive the seed. + * @seed: arbitrary 64-bit value to use as a seed. + */ +static inline void prandom_seed_state(struct rnd_state *state, u64 seed) +{ + u32 i = (seed >> 32) ^ (seed << 10) ^ seed; + + state->s1 = __seed(i, 2U); + state->s2 = __seed(i, 8U); + state->s3 = __seed(i, 16U); + state->s4 = __seed(i, 128U); +} + +/* Pseudo random number generator from numerical recipes. */ +static inline u32 next_pseudo_random32(u32 seed) +{ + return seed * 1664525 + 1013904223; +} + +#endif diff --git a/include/linux/random.h b/include/linux/random.h index 2625c0deda47..5b3ec7d2791f 100644 --- a/include/linux/random.h +++ b/include/linux/random.h @@ -9,7 +9,6 @@ #include #include -#include #include @@ -109,63 +108,12 @@ declare_get_random_var_wait(long) unsigned long randomize_page(unsigned long start, unsigned long range); -u32 prandom_u32(void); -void prandom_bytes(void *buf, size_t nbytes); -void prandom_seed(u32 seed); -void prandom_reseed_late(void); - -struct rnd_state { - __u32 s1, s2, s3, s4; -}; - -DECLARE_PER_CPU(struct rnd_state, net_rand_state); - -u32 prandom_u32_state(struct rnd_state *state); -void prandom_bytes_state(struct rnd_state *state, void *buf, size_t nbytes); -void prandom_seed_full_state(struct rnd_state __percpu *pcpu_state); - -#define prandom_init_once(pcpu_state) \ - DO_ONCE(prandom_seed_full_state, (pcpu_state)) - -/** - * prandom_u32_max - returns a pseudo-random number in interval [0, ep_ro) - * @ep_ro: right open interval endpoint - * - * Returns a pseudo-random number that is in interval [0, ep_ro). Note - * that the result depends on PRNG being well distributed in [0, ~0U] - * u32 space. Here we use maximally equidistributed combined Tausworthe - * generator, that is, prandom_u32(). This is useful when requesting a - * random index of an array containing ep_ro elements, for example. - * - * Returns: pseudo-random number in interval [0, ep_ro) - */ -static inline u32 prandom_u32_max(u32 ep_ro) -{ - return (u32)(((u64) prandom_u32() * ep_ro) >> 32); -} - /* - * Handle minimum values for seeds + * This is designed to be standalone for just prandom + * users, but for now we include it from + * for legacy reasons. */ -static inline u32 __seed(u32 x, u32 m) -{ - return (x < m) ? x + m : x; -} - -/** - * prandom_seed_state - set seed for prandom_u32_state(). - * @state: pointer to state structure to receive the seed. - * @seed: arbitrary 64-bit value to use as a seed. - */ -static inline void prandom_seed_state(struct rnd_state *state, u64 seed) -{ - u32 i = (seed >> 32) ^ (seed << 10) ^ seed; - - state->s1 = __seed(i, 2U); - state->s2 = __seed(i, 8U); - state->s3 = __seed(i, 16U); - state->s4 = __seed(i, 128U); -} +#include #ifdef CONFIG_ARCH_RANDOM # include @@ -196,10 +144,4 @@ static inline bool arch_has_random_seed(void) } #endif -/* Pseudo random number generator from numerical recipes. */ -static inline u32 next_pseudo_random32(u32 seed) -{ - return seed * 1664525 + 1013904223; -} - #endif /* _LINUX_RANDOM_H */ From 6330b0cb2ace1d98ed4751c0cd131eddf1eb25b7 Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Wed, 5 Aug 2020 12:10:44 +0100 Subject: [PATCH 20/24] arm64: Workaround circular dependency in pointer_auth.h MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit With the backport of f227e3ec3b5c ("random32: update the net random state on interrupt and activity") and its associated fixes, the arm64 build explodes early: In file included from ../include/linux/smp.h:67, from ../include/linux/percpu.h:7, from ../include/linux/prandom.h:12, from ../include/linux/random.h:118, from ../arch/arm64/include/asm/pointer_auth.h:6, from ../arch/arm64/include/asm/processor.h:39, from ../include/linux/mutex.h:19, from ../include/linux/kernfs.h:12, from ../include/linux/sysfs.h:16, from ../include/linux/kobject.h:20, from ../include/linux/of.h:17, from ../include/linux/irqdomain.h:35, from ../include/linux/acpi.h:13, from ../include/acpi/apei.h:9, from ../include/acpi/ghes.h:5, from ../include/linux/arm_sdei.h:8, from ../arch/arm64/kernel/asm-offsets.c:10: ../arch/arm64/include/asm/smp.h:100:29: error: field ‘ptrauth_key’ has incomplete type This is due to struct ptrauth_keys_kernel not being defined before we transitively include asm/smp.h from linux/random.h. Paper over it by moving the inclusion of linux/random.h *after* the type has been defined. Signed-off-by: Marc Zyngier Signed-off-by: Greg Kroah-Hartman --- arch/arm64/include/asm/pointer_auth.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/arch/arm64/include/asm/pointer_auth.h b/arch/arm64/include/asm/pointer_auth.h index 7a24bad1a58b..076a4157a74f 100644 --- a/arch/arm64/include/asm/pointer_auth.h +++ b/arch/arm64/include/asm/pointer_auth.h @@ -3,7 +3,6 @@ #define __ASM_POINTER_AUTH_H #include -#include #include #include @@ -30,6 +29,13 @@ struct ptrauth_keys { struct ptrauth_key apga; }; +/* + * Only include random.h once ptrauth_keys_* structures are defined + * to avoid yet another circular include hell (random.h * ends up + * including asm/smp.h, which requires ptrauth_keys_kernel). + */ +#include + static inline void ptrauth_keys_init(struct ptrauth_keys *keys) { if (system_supports_address_auth()) { From c776104353550d4983ccc437aa40509f53b2227b Mon Sep 17 00:00:00 2001 From: Jiang Ying Date: Wed, 5 Aug 2020 15:57:21 +0800 Subject: [PATCH 21/24] ext4: fix direct I/O read error This patch is used to fix ext4 direct I/O read error when the read size is not aligned with block size. Then, I will use a test to explain the error. (1) Make a file that is not aligned with block size: $dd if=/dev/zero of=./test.jar bs=1000 count=3 (2) I wrote a source file named "direct_io_read_file.c" as following: #include #include #include #include #include #include #include #define BUF_SIZE 1024 int main() { int fd; int ret; unsigned char *buf; ret = posix_memalign((void **)&buf, 512, BUF_SIZE); if (ret) { perror("posix_memalign failed"); exit(1); } fd = open("./test.jar", O_RDONLY | O_DIRECT, 0755); if (fd < 0){ perror("open ./test.jar failed"); exit(1); } do { ret = read(fd, buf, BUF_SIZE); printf("ret=%d\n",ret); if (ret < 0) { perror("write test.jar failed"); } } while (ret > 0); free(buf); close(fd); } (3) Compile the source file: $gcc direct_io_read_file.c -D_GNU_SOURCE (4) Run the test program: $./a.out The result is as following: ret=1024 ret=1024 ret=952 ret=-1 write test.jar failed: Invalid argument. I have tested this program on XFS filesystem, XFS does not have this problem, because XFS use iomap_dio_rw() to do direct I/O read. And the comparing between read offset and file size is done in iomap_dio_rw(), the code is as following: if (pos < size) { retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); } ... } ...only when "pos < size", direct I/O can be done, or 0 will be return. I have tested the fix patch on Ext4, it is up to the mustard of EINVAL in man2(read) as following: #include ssize_t read(int fd, void *buf, size_t count); EINVAL fd is attached to an object which is unsuitable for reading; or the file was opened with the O_DIRECT flag, and either the address specified in buf, the value specified in count, or the current file offset is not suitably aligned. So I think this patch can be applied to fix ext4 direct I/O error. However Ext4 introduces direct I/O read using iomap infrastructure on kernel 5.5, the patch is commit ("ext4: introduce direct I/O read using iomap infrastructure"), then Ext4 will be the same as XFS, they all use iomap_dio_rw() to do direct I/O read. So this problem does not exist on kernel 5.5 for Ext4. >From above description, we can see this problem exists on all the kernel versions between kernel 3.14 and kernel 5.4. It will cause the Applications to fail to read. For example, when the search service downloads a new full index file, the search engine is loading the previous index file and is processing the search request, it can not use buffer io that may squeeze the previous index file in use from pagecache, so the serch service must use direct I/O read. Please apply this patch on these kernel versions, or please use the method on kernel 5.5 to fix this problem. Fixes: 9fe55eea7e4b ("Fix race when checking i_size on direct i/o read") Reviewed-by: Jan Kara Co-developed-by: Wang Long Signed-off-by: Wang Long Signed-off-by: Jiang Ying Signed-off-by: Greg Kroah-Hartman --- fs/ext4/inode.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 7e0c77de551b..a284d99a1ee5 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3836,6 +3836,11 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter) struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); ssize_t ret; + loff_t offset = iocb->ki_pos; + loff_t size = i_size_read(inode); + + if (offset >= size) + return 0; /* * Shared inode_lock is enough for us - it protects against concurrent From 9fe975acb53fa4c35bd8fd9c1ec6a47056659b46 Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Thu, 9 Jul 2020 12:51:51 +0100 Subject: [PATCH 22/24] selftests: bpf: Fix detach from sockmap tests commit f43cb0d672aa8eb09bfdb779de5900c040487d1d upstream. Fix sockmap tests which rely on old bpf_prog_dispatch behaviour. In the first case, the tests check that detaching without giving a program succeeds. Since these are not the desired semantics, invert the condition. In the second case, the clean up code doesn't supply the necessary program fds. Fixes: bb0de3131f4c ("bpf: sockmap: Require attach_bpf_fd when detaching a program") Reported-by: Martin KaFai Lau Signed-off-by: Lorenz Bauer Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Link: https://lore.kernel.org/bpf/20200709115151.75829-1-lmb@cloudflare.com Signed-off-by: Greg Kroah-Hartman --- tools/testing/selftests/bpf/test_maps.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c index e1f1becda529..c812f0178b64 100644 --- a/tools/testing/selftests/bpf/test_maps.c +++ b/tools/testing/selftests/bpf/test_maps.c @@ -793,19 +793,19 @@ static void test_sockmap(unsigned int tasks, void *data) } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_PARSER); - if (err) { + if (!err) { printf("Failed empty parser prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_SKB_STREAM_VERDICT); - if (err) { + if (!err) { printf("Failed empty verdict prog detach\n"); goto out_sockmap; } err = bpf_prog_detach(fd, BPF_SK_MSG_VERDICT); - if (err) { + if (!err) { printf("Failed empty msg verdict prog detach\n"); goto out_sockmap; } @@ -1094,19 +1094,19 @@ static void test_sockmap(unsigned int tasks, void *data) assert(status == 0); } - err = bpf_prog_detach(map_fd_rx, __MAX_BPF_ATTACH_TYPE); + err = bpf_prog_detach2(parse_prog, map_fd_rx, __MAX_BPF_ATTACH_TYPE); if (!err) { printf("Detached an invalid prog type.\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_PARSER); + err = bpf_prog_detach2(parse_prog, map_fd_rx, BPF_SK_SKB_STREAM_PARSER); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; } - err = bpf_prog_detach(map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); + err = bpf_prog_detach2(verdict_prog, map_fd_rx, BPF_SK_SKB_STREAM_VERDICT); if (err) { printf("Failed parser prog detach\n"); goto out_sockmap; From ca7ace8fd26d9ae4be3cf69f474ddcfb0e8506ce Mon Sep 17 00:00:00 2001 From: Lorenz Bauer Date: Mon, 29 Jun 2020 10:56:28 +0100 Subject: [PATCH 23/24] bpf: sockmap: Require attach_bpf_fd when detaching a program commit bb0de3131f4c60a9bf976681e0fe4d1e55c7a821 upstream. The sockmap code currently ignores the value of attach_bpf_fd when detaching a program. This is contrary to the usual behaviour of checking that attach_bpf_fd represents the currently attached program. Ensure that attach_bpf_fd is indeed the currently attached program. It turns out that all sockmap selftests already do this, which indicates that this is unlikely to cause breakage. Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Lorenz Bauer Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200629095630.7933-5-lmb@cloudflare.com Signed-off-by: Greg Kroah-Hartman --- include/linux/bpf.h | 13 +++++++++-- include/linux/skmsg.h | 13 +++++++++++ kernel/bpf/syscall.c | 4 ++-- net/core/sock_map.c | 50 ++++++++++++++++++++++++++++++++++++++----- 4 files changed, 71 insertions(+), 9 deletions(-) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 3bf3835d0e86..7aa0d8b5aaf0 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -956,11 +956,14 @@ static inline void bpf_map_offload_map_free(struct bpf_map *map) #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ #if defined(CONFIG_BPF_STREAM_PARSER) -int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which); +int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, + struct bpf_prog *old, u32 which); int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog); +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype); #else static inline int sock_map_prog_update(struct bpf_map *map, - struct bpf_prog *prog, u32 which) + struct bpf_prog *prog, + struct bpf_prog *old, u32 which) { return -EOPNOTSUPP; } @@ -970,6 +973,12 @@ static inline int sock_map_get_from_fd(const union bpf_attr *attr, { return -EINVAL; } + +static inline int sock_map_prog_detach(const union bpf_attr *attr, + enum bpf_prog_type ptype) +{ + return -EOPNOTSUPP; +} #endif #if defined(CONFIG_XDP_SOCKETS) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 4bdb5e4bbd6a..20f3550b0b11 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -450,6 +450,19 @@ static inline void psock_set_prog(struct bpf_prog **pprog, bpf_prog_put(prog); } +static inline int psock_replace_prog(struct bpf_prog **pprog, + struct bpf_prog *prog, + struct bpf_prog *old) +{ + if (cmpxchg(pprog, old, prog) != old) + return -ENOENT; + + if (old) + bpf_prog_put(old); + + return 0; +} + static inline void psock_progs_drop(struct sk_psock_progs *progs) { psock_set_prog(&progs->msg_parser, NULL); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8bc904f9badb..bf03d04a9e2f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2029,10 +2029,10 @@ static int bpf_prog_detach(const union bpf_attr *attr) ptype = BPF_PROG_TYPE_CGROUP_DEVICE; break; case BPF_SK_MSG_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_MSG); case BPF_SK_SKB_STREAM_PARSER: case BPF_SK_SKB_STREAM_VERDICT: - return sock_map_get_from_fd(attr, NULL); + return sock_map_prog_detach(attr, BPF_PROG_TYPE_SK_SKB); case BPF_LIRC_MODE2: return lirc_prog_detach(attr); case BPF_FLOW_DISSECTOR: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 6bbc118bf00e..df52061f99f7 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -71,7 +71,42 @@ int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) map = __bpf_map_get(f); if (IS_ERR(map)) return PTR_ERR(map); - ret = sock_map_prog_update(map, prog, attr->attach_type); + ret = sock_map_prog_update(map, prog, NULL, attr->attach_type); + fdput(f); + return ret; +} + +int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype) +{ + u32 ufd = attr->target_fd; + struct bpf_prog *prog; + struct bpf_map *map; + struct fd f; + int ret; + + if (attr->attach_flags) + return -EINVAL; + + f = fdget(ufd); + map = __bpf_map_get(f); + if (IS_ERR(map)) + return PTR_ERR(map); + + prog = bpf_prog_get(attr->attach_bpf_fd); + if (IS_ERR(prog)) { + ret = PTR_ERR(prog); + goto put_map; + } + + if (prog->type != ptype) { + ret = -EINVAL; + goto put_prog; + } + + ret = sock_map_prog_update(map, NULL, prog, attr->attach_type); +put_prog: + bpf_prog_put(prog); +put_map: fdput(f); return ret; } @@ -1015,27 +1050,32 @@ static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) } int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, - u32 which) + struct bpf_prog *old, u32 which) { struct sk_psock_progs *progs = sock_map_progs(map); + struct bpf_prog **pprog; if (!progs) return -EOPNOTSUPP; switch (which) { case BPF_SK_MSG_VERDICT: - psock_set_prog(&progs->msg_parser, prog); + pprog = &progs->msg_parser; break; case BPF_SK_SKB_STREAM_PARSER: - psock_set_prog(&progs->skb_parser, prog); + pprog = &progs->skb_parser; break; case BPF_SK_SKB_STREAM_VERDICT: - psock_set_prog(&progs->skb_verdict, prog); + pprog = &progs->skb_verdict; break; default: return -EOPNOTSUPP; } + if (old) + return psock_replace_prog(pprog, prog, old); + + psock_set_prog(pprog, prog); return 0; } From d9939285fc818425ae92bd99f8c97b6b9ef3bb88 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 7 Aug 2020 09:34:02 +0200 Subject: [PATCH 24/24] Linux 5.4.57 Tested-by: Shuah Khan Signed-off-by: Greg Kroah-Hartman --- Makefile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Makefile b/Makefile index c33fb4eebd4d..dd753ef637fd 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 5 PATCHLEVEL = 4 -SUBLEVEL = 56 +SUBLEVEL = 57 EXTRAVERSION = NAME = Kleptomaniac Octopus