OpenCloudOS-Kernel/drivers/of/of_private.h

176 lines
5.6 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0+ */
#ifndef _LINUX_OF_PRIVATE_H
#define _LINUX_OF_PRIVATE_H
/*
* Private symbols used by OF support code
*
* Paul Mackerras August 1996.
* Copyright (C) 1996-2005 Paul Mackerras.
*/
#define FDT_ALIGN_SIZE 8
/**
* struct alias_prop - Alias property in 'aliases' node
* @link: List node to link the structure in aliases_lookup list
* @alias: Alias property name
* @np: Pointer to device_node that the alias stands for
* @id: Index value from end of alias name
* @stem: Alias string without the index
*
* The structure represents one alias property of 'aliases' node as
* an entry in aliases_lookup list.
*/
struct alias_prop {
struct list_head link;
const char *alias;
struct device_node *np;
int id;
char stem[];
};
#if defined(CONFIG_SPARC)
#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 2
#else
#define OF_ROOT_NODE_ADDR_CELLS_DEFAULT 1
#endif
#define OF_ROOT_NODE_SIZE_CELLS_DEFAULT 1
extern struct mutex of_mutex;
extern struct list_head aliases_lookup;
of: Make devicetree sysfs update functions consistent. All of the DT modification functions are split into two parts, the first part manipulates the DT data structure, and the second part updates sysfs, but the code isn't very consistent about how the second half is called. They don't all enforce the same rules about when it is valid to update sysfs, and there isn't any clarity on locking. The transactional DT modification feature that is coming also needs access to these functions so that it can perform all the structure changes together, and then all the sysfs updates as a second stage instead of doing each one at a time. Fix up the second have by creating a separate __of_*_sysfs() function for each of the helpers. The new functions have consistent naming (ie. of_node_add() becomes __of_attach_node_sysfs()) and all of them now defer if of_init hasn't been called yet. Callers of the new functions must hold the of_mutex to ensure there are no race conditions with of_init(). The mutex ensures that there will only ever be one writer to the tree at any given time. There can still be any number of readers and the raw_spin_lock is still used to make sure access to the data structure is still consistent. Finally, put the function prototypes into of_private.h so they are accessible to the transaction code. Signed-off-by: Pantelis Antoniou <pantelis.antoniou@konsulko.com> [grant.likely: Changed suffix from _post to _sysfs to match existing code] [grant.likely: Reorganized to eliminate trivial wrappers] Signed-off-by: Grant Likely <grant.likely@linaro.org>
2014-07-24 07:05:06 +08:00
extern struct kset *of_kset;
#if defined(CONFIG_OF_DYNAMIC)
extern int of_property_notify(int action, struct device_node *np,
struct property *prop, struct property *old_prop);
extern void of_node_release(struct kobject *kobj);
extern int __of_changeset_apply_entries(struct of_changeset *ocs,
int *ret_revert);
extern int __of_changeset_apply_notify(struct of_changeset *ocs);
extern int __of_changeset_revert_entries(struct of_changeset *ocs,
int *ret_apply);
extern int __of_changeset_revert_notify(struct of_changeset *ocs);
#else /* CONFIG_OF_DYNAMIC */
static inline int of_property_notify(int action, struct device_node *np,
struct property *prop, struct property *old_prop)
{
return 0;
}
#endif /* CONFIG_OF_DYNAMIC */
#if defined(CONFIG_OF_KOBJ)
int of_node_is_attached(const struct device_node *node);
int __of_add_property_sysfs(struct device_node *np, struct property *pp);
void __of_remove_property_sysfs(struct device_node *np, struct property *prop);
void __of_update_property_sysfs(struct device_node *np, struct property *newprop,
struct property *oldprop);
int __of_attach_node_sysfs(struct device_node *np);
void __of_detach_node_sysfs(struct device_node *np);
#else
static inline int __of_add_property_sysfs(struct device_node *np, struct property *pp)
{
return 0;
}
static inline void __of_remove_property_sysfs(struct device_node *np, struct property *prop) {}
static inline void __of_update_property_sysfs(struct device_node *np,
struct property *newprop, struct property *oldprop) {}
static inline int __of_attach_node_sysfs(struct device_node *np)
{
return 0;
}
static inline void __of_detach_node_sysfs(struct device_node *np) {}
#endif
#if defined(CONFIG_OF_RESOLVE)
int of_resolve_phandles(struct device_node *tree);
#endif
of: Rework and simplify phandle cache to use a fixed size The phandle cache was added to speed up of_find_node_by_phandle() by avoiding walking the whole DT to find a matching phandle. The implementation has several shortcomings: - The cache is designed to work on a linear set of phandle values. This is true for dtc generated DTs, but not for other cases such as Power. - The cache isn't enabled until of_core_init() and a typical system may see hundreds of calls to of_find_node_by_phandle() before that point. - The cache is freed and re-allocated when the number of phandles changes. - It takes a raw spinlock around a memory allocation which breaks on RT. Change the implementation to a fixed size and use hash_32() as the cache index. This greatly simplifies the implementation. It avoids the need for any re-alloc of the cache and taking a reference on nodes in the cache. We only have a single source of removing cache entries which is of_detach_node(). Using hash_32() removes any assumption on phandle values improving the hit rate for non-linear phandle values. The effect on linear values using hash_32() is about a 10% collision. The chances of thrashing on colliding values seems to be low. To compare performance, I used a RK3399 board which is a pretty typical system. I found that just measuring boot time as done previously is noisy and may be impacted by other things. Also bringing up secondary cores causes some issues with measuring, so I booted with 'nr_cpus=1'. With no caching, calls to of_find_node_by_phandle() take about 20124 us for 1248 calls. There's an additional 288 calls before time keeping is up. Using the average time per hit/miss with the cache, we can calculate these calls to take 690 us (277 hit / 11 miss) with a 128 entry cache and 13319 us with no cache or an uninitialized cache. Comparing the 3 implementations the time spent in of_find_node_by_phandle() is: no cache: 20124 us (+ 13319 us) 128 entry cache: 5134 us (+ 690 us) current cache: 819 us (+ 13319 us) We could move the allocation of the cache earlier to improve the current cache, but that just further complicates the situation as it needs to be after slab is up, so we can't do it when unflattening (which uses memblock). Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Segher Boessenkool <segher@kernel.crashing.org> Cc: Frank Rowand <frowand.list@gmail.com> Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reviewed-by: Frank Rowand <frowand.list@gmail.com> Tested-by: Frank Rowand <frowand.list@gmail.com> Signed-off-by: Rob Herring <robh@kernel.org>
2019-12-07 06:27:41 +08:00
void __of_phandle_cache_inv_entry(phandle handle);
#if defined(CONFIG_OF_OVERLAY)
void of_overlay_mutex_lock(void);
void of_overlay_mutex_unlock(void);
#else
static inline void of_overlay_mutex_lock(void) {};
static inline void of_overlay_mutex_unlock(void) {};
#endif
#if defined(CONFIG_OF_UNITTEST) && defined(CONFIG_OF_OVERLAY)
extern void __init unittest_unflatten_overlay_base(void);
#else
static inline void unittest_unflatten_overlay_base(void) {};
#endif
extern void *__unflatten_device_tree(const void *blob,
struct device_node *dad,
struct device_node **mynodes,
void *(*dt_alloc)(u64 size, u64 align),
bool detached);
/**
* General utilities for working with live trees.
*
* All functions with two leading underscores operate
* without taking node references, so you either have to
* own the devtree lock or work on detached trees only.
*/
struct property *__of_prop_dup(const struct property *prop, gfp_t allocflags);
struct device_node *__of_node_dup(const struct device_node *np,
const char *full_name);
struct device_node *__of_find_node_by_path(struct device_node *parent,
const char *path);
struct device_node *__of_find_node_by_full_path(struct device_node *node,
const char *path);
extern const void *__of_get_property(const struct device_node *np,
const char *name, int *lenp);
extern int __of_add_property(struct device_node *np, struct property *prop);
extern int __of_remove_property(struct device_node *np, struct property *prop);
extern int __of_update_property(struct device_node *np,
struct property *newprop, struct property **oldprop);
extern void __of_detach_node(struct device_node *np);
extern void __of_sysfs_remove_bin_file(struct device_node *np,
struct property *prop);
of: cache phandle nodes to reduce cost of of_find_node_by_phandle() Create a cache of the nodes that contain a phandle property. Use this cache to find the node for a given phandle value instead of scanning the devicetree to find the node. If the phandle value is not found in the cache, of_find_node_by_phandle() will fall back to the tree scan algorithm. The cache is initialized in of_core_init(). The cache is freed via a late_initcall_sync() if modules are not enabled. If the devicetree is created by the dtc compiler, with all phandle property values auto generated, then the size required by the cache could be 4 * (1 + number of phandles) bytes. This results in an O(1) node lookup cost for a given phandle value. Due to a concern that the phandle property values might not be consistent with what is generated by the dtc compiler, a mask has been added to the cache lookup algorithm. To maintain the O(1) node lookup cost, the size of the cache has been increased by rounding the number of entries up to the next power of two. The overhead of finding the devicetree node containing a given phandle value has been noted by several people in the recent past, in some cases with a patch to add a hashed index of devicetree nodes, based on the phandle value of the node. One concern with this approach is the extra space added to each node. This patch takes advantage of the phandle property values auto generated by the dtc compiler, which begin with one and monotonically increase by one, resulting in a range of 1..n for n phandle values. This implementation should also provide a good reduction of overhead for any range of phandle values that are mostly in a monotonic range. Performance measurements by Chintan Pandya <cpandya@codeaurora.org> of several implementations of patches that are similar to this one suggest an expected reduction of boot time by ~400ms for his test system. If the cache size was decreased to 64 entries, the boot time was reduced by ~340 ms. The measurements were on a 4.9.73 kernel for arch/arm64/boot/dts/qcom/sda670-mtp.dts, contains 2371 nodes and 814 phandle values. Reported-by: Chintan Pandya <cpandya@codeaurora.org> Signed-off-by: Frank Rowand <frank.rowand@sony.com> Signed-off-by: Rob Herring <robh@kernel.org>
2018-03-05 08:14:47 +08:00
/* illegal phandle value (set when unresolved) */
#define OF_PHANDLE_ILLEGAL 0xdeadbeef
/* iterators for transactions, used for overlays */
/* forward iterator */
#define for_each_transaction_entry(_oft, _te) \
list_for_each_entry(_te, &(_oft)->te_list, node)
/* reverse iterator */
#define for_each_transaction_entry_reverse(_oft, _te) \
list_for_each_entry_reverse(_te, &(_oft)->te_list, node)
extern int of_bus_n_addr_cells(struct device_node *np);
extern int of_bus_n_size_cells(struct device_node *np);
struct bus_dma_region;
#if defined(CONFIG_OF_ADDRESS) && defined(CONFIG_HAS_DMA)
int of_dma_get_range(struct device_node *np,
const struct bus_dma_region **map);
struct device_node *__of_get_dma_parent(const struct device_node *np);
#else
static inline int of_dma_get_range(struct device_node *np,
const struct bus_dma_region **map)
{
return -ENODEV;
}
static inline struct device_node *__of_get_dma_parent(const struct device_node *np)
{
return of_get_parent(np);
}
#endif
void fdt_init_reserved_mem(void);
void fdt_reserved_mem_save_node(unsigned long node, const char *uname,
phys_addr_t base, phys_addr_t size);
#endif /* _LINUX_OF_PRIVATE_H */