From b9c74fd7d231d4086eb6b6af60dccd666cda1288 Mon Sep 17 00:00:00 2001 From: Gaurav Minocha Date: Wed, 3 Sep 2014 00:16:29 -0700 Subject: of: Documentation regarding attaching OF Selftest testdata This patch add a document that explains how the selftest test data is dynamically attached into the live device tree irrespective of the machine's architecture. Signed-off-by: Gaurav Minocha Signed-off-by: Grant Likely --- Documentation/devicetree/of_selftest.txt | 211 +++++++++++++++++++++++++++++++ 1 file changed, 211 insertions(+) create mode 100644 Documentation/devicetree/of_selftest.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/of_selftest.txt b/Documentation/devicetree/of_selftest.txt new file mode 100644 index 00000000000..3a2f54d07fc --- /dev/null +++ b/Documentation/devicetree/of_selftest.txt @@ -0,0 +1,211 @@ +Open Firmware Device Tree Selftest +---------------------------------- + +Author: Gaurav Minocha + +1. Introduction + +This document explains how the test data required for executing OF selftest +is attached to the live tree dynamically, independent of the machine's +architecture. + +It is recommended to read the following documents before moving ahead. + +[1] Documentation/devicetree/usage-model.txt +[2] http://www.devicetree.org/Device_Tree_Usage + +OF Selftest has been designed to test the interface (include/linux/of.h) +provided to device driver developers to fetch the device information..etc. +from the unflattened device tree data structure. This interface is used by +most of the device drivers in various use cases. + + +2. Test-data + +The Device Tree Source file (drivers/of/testcase-data/testcases.dts) contains +the test data required for executing the unit tests automated in +drivers/of/selftests.c. Currently, following Device Tree Source Include files +(.dtsi) are included in testcase.dts: + +drivers/of/testcase-data/tests-interrupts.dtsi +drivers/of/testcase-data/tests-platform.dtsi +drivers/of/testcase-data/tests-phandle.dtsi +drivers/of/testcase-data/tests-match.dtsi + +When the kernel is build with OF_SELFTEST enabled, then the following make rule + +$(obj)/%.dtb: $(src)/%.dts FORCE + $(call if_changed_dep, dtc) + +is used to compile the DT source file (testcase.dts) into a binary blob +(testcase.dtb), also referred as flattened DT. + +After that, using the following rule the binary blob above is wrapped as an +assembly file (testcase.dtb.S). + +$(obj)/%.dtb.S: $(obj)/%.dtb + $(call cmd, dt_S_dtb) + +The assembly file is compiled into an object file (testcase.dtb.o), and is +linked into the kernel image. + + +2.1. Adding the test data + +Un-flattened device tree structure: + +Un-flattened device tree consists of connected device_node(s) in form of a tree +structure described below. + +// following struct members are used to construct the tree +struct device_node { + ... + struct device_node *parent; + struct device_node *child; + struct device_node *sibling; + struct device_node *allnext; /* next in list of all nodes */ + ... + }; + +Figure 1, describes a generic structure of machine’s un-flattened device tree +considering only child and sibling pointers. There exists another pointer, +*parent, that is used to traverse the tree in the reverse direction. So, at +a particular level the child node and all the sibling nodes will have a parent +pointer pointing to a common node (e.g. child1, sibling2, sibling3, sibling4’s +parent points to root node) + +root (‘/’) + | +child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | + | | | null + | | | + | | child31 -> sibling32 -> null + | | | | + | | null null + | | + | child21 -> sibling22 -> sibling23 -> null + | | | | + | null null null + | +child11 -> sibling12 -> sibling13 -> sibling14 -> null + | | | | + | | | null + | | | + null null child131 -> null + | + null + +Figure 1: Generic structure of un-flattened device tree + + +*allnext: it is used to link all the nodes of DT into a list. So, for the + above tree the list would be as follows: + +root->child1->child11->sibling12->sibling13->child131->sibling14->sibling2-> +child21->sibling22->sibling23->sibling3->child31->sibling32->sibling4->null + +Before executing OF selftest, it is required to attach the test data to +machine's device tree (if present). So, when selftest_data_add() is called, +at first it reads the flattened device tree data linked into the kernel image +via the following kernel symbols: + +__dtb_testcases_begin - address marking the start of test data blob +__dtb_testcases_end - address marking the end of test data blob + +Secondly, it calls of_fdt_unflatten_device_tree() to unflatten the flattened +blob. And finally, if the machine’s device tree (i.e live tree) is present, +then it attaches the unflattened test data tree to the live tree, else it +attaches itself as a live device tree. + +attach_node_and_children() uses of_attach_node() to attach the nodes into the +live tree as explained below. To explain the same, the test data tree described + in Figure 2 is attached to the live tree described in Figure 1. + +root (‘/’) + | + testcase-data + | + test-child0 -> test-sibling1 -> test-sibling2 -> test-sibling3 -> null + | | | | + test-child01 null null null + + +allnext list: + +root->testcase-data->test-child0->test-child01->test-sibling1->test-sibling2 +->test-sibling3->null + +Figure 2: Example test data tree to be attached to live tree. + +According to the scenario above, the live tree is already present so it isn’t +required to attach the root(‘/’) node. All other nodes are attached by calling +of_attach_node() on each node. + +In the function of_attach_node(), the new node is attached as the child of the +given parent in live tree. But, if parent already has a child then the new node +replaces the current child and turns it into its sibling. So, when the testcase +data node is attached to the live tree above (Figure 1), the final structure is + as shown in Figure 3. + +root (‘/’) + | +testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | | + (...) | | | null + | | child31 -> sibling32 -> null + | | | | + | | null null + | | + | child21 -> sibling22 -> sibling23 -> null + | | | | + | null null null + | + child11 -> sibling12 -> sibling13 -> sibling14 -> null + | | | | + null null | null + | + child131 -> null + | + null +----------------------------------------------------------------------- + +root (‘/’) + | +testcase-data -> child1 -> sibling2 -> sibling3 -> sibling4 -> null + | | | | | + | (...) (...) (...) null + | +test-sibling3 -> test-sibling2 -> test-sibling1 -> test-child0 -> null + | | | | + null null null test-child01 + + +Figure 3: Live device tree structure after attaching the testcase-data. + + +Astute readers would have noticed that test-child0 node becomes the last +sibling compared to the earlier structure (Figure 2). After attaching first +test-child0 the test-sibling1 is attached that pushes the child node +(i.e. test-child0) to become a sibling and makes itself a child node, + as mentioned above. + +If a duplicate node is found (i.e. if a node with same full_name property is +already present in the live tree), then the node isn’t attached rather its +properties are updated to the live tree’s node by calling the function +update_node_properties(). + + +2.2. Removing the test data + +Once the test case execution is complete, selftest_data_remove is called in +order to remove the device nodes attached initially (first the leaf nodes are +detached and then moving up the parent nodes are removed, and eventually the +whole tree). selftest_data_remove() calls detach_node_and_children() that uses +of_detach_node() to detach the nodes from the live device tree. + +To detach a node, of_detach_node() first updates all_next linked list, by +attaching the previous node’s allnext to current node’s allnext pointer. And +then, it either updates the child pointer of given node’s parent to its +sibling or attaches the previous sibling to the given node’s sibling, as +appropriate. That is it :) -- cgit v1.2.3-70-g09d2 From 1b134c9c4b555342be667f144ee714af1c3f6a9f Mon Sep 17 00:00:00 2001 From: Markus Niebel Date: Thu, 11 Sep 2014 15:56:56 +0800 Subject: ARM: DT: imx53: fix lvds channel 1 port using LVDS channel 1 on an i.MX53 leads to following error: imx-ldb 53fa8008.ldb: unable to set di0 parent clock to ldb_di1 This comes from imx_ldb_set_clock with mux = 0. Mux parameter must be "1" for reparenting di1 clock to ldb_di1. The value of the mux param comes from device tree port settings. On i.MX5, the internal two-input-multiplexer is used. Due to hardware limitations, only one port (port@[0,1]) can be used for each channel (lvds-channel@[0,1], respectively) Documentation update suggested by Philipp Zabel Signed-off-by: Markus Niebel Fixes: e05c8c9a790a ("ARM: dts: imx53: Add IPU DI ports and endpoints, move imx-drm node to dtsi") Cc: Acked-by: Philipp Zabel Signed-off-by: Shawn Guo Signed-off-by: Arnd Bergmann --- Documentation/devicetree/bindings/staging/imx-drm/ldb.txt | 15 +++++++++++++-- arch/arm/boot/dts/imx53.dtsi | 12 ++++++++++-- 2 files changed, 23 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt b/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt index 578a1fca366..443bcb6134d 100644 --- a/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt +++ b/Documentation/devicetree/bindings/staging/imx-drm/ldb.txt @@ -56,6 +56,9 @@ Required properties: - fsl,data-width : should be <18> or <24> - port: A port node with endpoint definitions as defined in Documentation/devicetree/bindings/media/video-interfaces.txt. + On i.MX5, the internal two-input-multiplexer is used. + Due to hardware limitations, only one port (port@[0,1]) + can be used for each channel (lvds-channel@[0,1], respectively) On i.MX6, there should be four ports (port@[0-3]) that correspond to the four LVDS multiplexer inputs. @@ -78,6 +81,8 @@ ldb: ldb@53fa8008 { "di0", "di1"; lvds-channel@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; fsl,data-mapping = "spwg"; fsl,data-width = <24>; @@ -86,7 +91,9 @@ ldb: ldb@53fa8008 { /* ... */ }; - port { + port@0 { + reg = <0>; + lvds0_in: endpoint { remote-endpoint = <&ipu_di0_lvds0>; }; @@ -94,6 +101,8 @@ ldb: ldb@53fa8008 { }; lvds-channel@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; fsl,data-mapping = "spwg"; fsl,data-width = <24>; @@ -102,7 +111,9 @@ ldb: ldb@53fa8008 { /* ... */ }; - port { + port@1 { + reg = <1>; + lvds1_in: endpoint { remote-endpoint = <&ipu_di1_lvds1>; }; diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi index c6c58c1c00e..6b675a02066 100644 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@ -423,10 +423,14 @@ status = "disabled"; lvds-channel@0 { + #address-cells = <1>; + #size-cells = <0>; reg = <0>; status = "disabled"; - port { + port@0 { + reg = <0>; + lvds0_in: endpoint { remote-endpoint = <&ipu_di0_lvds0>; }; @@ -434,10 +438,14 @@ }; lvds-channel@1 { + #address-cells = <1>; + #size-cells = <0>; reg = <1>; status = "disabled"; - port { + port@1 { + reg = <1>; + lvds1_in: endpoint { remote-endpoint = <&ipu_di1_lvds1>; }; -- cgit v1.2.3-70-g09d2 From 2ad654bc5e2b211e92f66da1d819e47d79a866f0 Mon Sep 17 00:00:00 2001 From: Zefan Li Date: Thu, 25 Sep 2014 09:41:02 +0800 Subject: cpuset: PF_SPREAD_PAGE and PF_SPREAD_SLAB should be atomic flags When we change cpuset.memory_spread_{page,slab}, cpuset will flip PF_SPREAD_{PAGE,SLAB} bit of tsk->flags for each task in that cpuset. This should be done using atomic bitops, but currently we don't, which is broken. Tetsuo reported a hard-to-reproduce kernel crash on RHEL6, which happened when one thread tried to clear PF_USED_MATH while at the same time another thread tried to flip PF_SPREAD_PAGE/PF_SPREAD_SLAB. They both operate on the same task. Here's the full report: https://lkml.org/lkml/2014/9/19/230 To fix this, we make PF_SPREAD_PAGE and PF_SPREAD_SLAB atomic flags. v4: - updated mm/slab.c. (Fengguang Wu) - updated Documentation. Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Miao Xie Cc: Kees Cook Fixes: 950592f7b991 ("cpusets: update tasks' page/slab spread flags in time") Cc: # 2.6.31+ Reported-by: Tetsuo Handa Signed-off-by: Zefan Li Signed-off-by: Tejun Heo --- Documentation/cgroups/cpusets.txt | 6 +++--- include/linux/cpuset.h | 4 ++-- include/linux/sched.h | 13 +++++++++++-- kernel/cpuset.c | 9 +++++---- mm/slab.c | 4 ++-- 5 files changed, 23 insertions(+), 13 deletions(-) (limited to 'Documentation') diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 7740038d82b..3c94ff3f969 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -345,14 +345,14 @@ the named feature on. The implementation is simple. Setting the flag 'cpuset.memory_spread_page' turns on a per-process flag -PF_SPREAD_PAGE for each task that is in that cpuset or subsequently +PFA_SPREAD_PAGE for each task that is in that cpuset or subsequently joins that cpuset. The page allocation calls for the page cache -is modified to perform an inline check for this PF_SPREAD_PAGE task +is modified to perform an inline check for this PFA_SPREAD_PAGE task flag, and if set, a call to a new routine cpuset_mem_spread_node() returns the node to prefer for the allocation. Similarly, setting 'cpuset.memory_spread_slab' turns on the flag -PF_SPREAD_SLAB, and appropriately marked slab caches will allocate +PFA_SPREAD_SLAB, and appropriately marked slab caches will allocate pages from the node returned by cpuset_mem_spread_node(). The cpuset_mem_spread_node() routine is also simple. It uses the diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index ade2390ffe9..6e39c9bb0da 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -93,12 +93,12 @@ extern int cpuset_slab_spread_node(void); static inline int cpuset_do_page_mem_spread(void) { - return current->flags & PF_SPREAD_PAGE; + return task_spread_page(current); } static inline int cpuset_do_slab_mem_spread(void) { - return current->flags & PF_SPREAD_SLAB; + return task_spread_slab(current); } extern int current_cpuset_is_being_rebound(void); diff --git a/include/linux/sched.h b/include/linux/sched.h index 5630763956d..7b1cafefb05 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1903,8 +1903,6 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ -#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */ -#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ @@ -1958,6 +1956,9 @@ static inline void memalloc_noio_restore(unsigned int flags) /* Per-process atomic flags. */ #define PFA_NO_NEW_PRIVS 0 /* May not gain new privileges. */ +#define PFA_SPREAD_PAGE 1 /* Spread page cache over cpuset */ +#define PFA_SPREAD_SLAB 2 /* Spread some slab caches over cpuset */ + #define TASK_PFA_TEST(name, func) \ static inline bool task_##func(struct task_struct *p) \ @@ -1972,6 +1973,14 @@ static inline void memalloc_noio_restore(unsigned int flags) TASK_PFA_TEST(NO_NEW_PRIVS, no_new_privs) TASK_PFA_SET(NO_NEW_PRIVS, no_new_privs) +TASK_PFA_TEST(SPREAD_PAGE, spread_page) +TASK_PFA_SET(SPREAD_PAGE, spread_page) +TASK_PFA_CLEAR(SPREAD_PAGE, spread_page) + +TASK_PFA_TEST(SPREAD_SLAB, spread_slab) +TASK_PFA_SET(SPREAD_SLAB, spread_slab) +TASK_PFA_CLEAR(SPREAD_SLAB, spread_slab) + /* * task->jobctl flags */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 22874d7cf2c..52cb04c993b 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -365,13 +365,14 @@ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) - tsk->flags |= PF_SPREAD_PAGE; + task_set_spread_page(tsk); else - tsk->flags &= ~PF_SPREAD_PAGE; + task_clear_spread_page(tsk); + if (is_spread_slab(cs)) - tsk->flags |= PF_SPREAD_SLAB; + task_set_spread_slab(tsk); else - tsk->flags &= ~PF_SPREAD_SLAB; + task_clear_spread_slab(tsk); } /* diff --git a/mm/slab.c b/mm/slab.c index a467b308c68..881951e67f1 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2994,7 +2994,7 @@ out: #ifdef CONFIG_NUMA /* - * Try allocating on another node if PF_SPREAD_SLAB is a mempolicy is set. + * Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set. * * If we are in_interrupt, then process context, including cpusets and * mempolicy, may not apply and should not be used for allocation policy. @@ -3226,7 +3226,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags) { void *objp; - if (current->mempolicy || unlikely(current->flags & PF_SPREAD_SLAB)) { + if (current->mempolicy || cpuset_do_slab_mem_spread()) { objp = alternate_node_alloc(cache, flags); if (objp) goto out; -- cgit v1.2.3-70-g09d2